| 810 1353 810 282 1353 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IVERSION_H #define _LINUX_IVERSION_H #include <linux/fs.h> /* * The inode->i_version field: * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must * appear larger to observers if there was an explicit change to the inode's * data or metadata since it was last queried. * * An explicit change is one that would ordinarily result in a change to the * inode status change time (aka ctime). i_version must appear to change, even * if the ctime does not (since the whole point is to avoid missing updates due * to timestamp granularity). If POSIX or other relevant spec mandates that the * ctime must change due to an operation, then the i_version counter must be * incremented as well. * * Making the i_version update completely atomic with the operation itself would * be prohibitively expensive. Traditionally the kernel has updated the times on * directories after an operation that changes its contents. For regular files, * the ctime is usually updated before the data is copied into the cache for a * write. This means that there is a window of time when an observer can * associate a new timestamp with old file contents. Since the purpose of the * i_version is to allow for better cache coherency, the i_version must always * be updated after the results of the operation are visible. Updating it before * and after a change is also permitted. (Note that no filesystems currently do * this. Fixing that is a work-in-progress). * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the * inode. If it's different then something has changed. Observers cannot infer * anything about the nature or magnitude of the changes from the value, only * that the inode has changed in some fashion. * * Not all filesystems properly implement the i_version counter. Subsystems that * want to use i_version field on an inode should first check whether the * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro). * * Those that set SB_I_VERSION will automatically have their i_version counter * incremented on writes to normal files. If the SB_I_VERSION is not set, then * the VFS will not touch it on writes, and the filesystem can use it how it * wishes. Note that the filesystem is always responsible for updating the * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.). * We consider these sorts of filesystems to have a kernel-managed i_version. * * It may be impractical for filesystems to keep i_version updates atomic with * respect to the changes that cause them. They should, however, guarantee * that i_version updates are never visible before the changes that caused * them. Also, i_version updates should never be delayed longer than it takes * the original change to reach disk. * * This implementation uses the low bit in the i_version field as a flag to * track when the value has been queried. If it has not been queried since it * was last incremented, we can skip the increment in most cases. * * In the event that we're updating the ctime, we will usually go ahead and * bump the i_version anyway. Since that has to go to stable storage in some * fashion, we might as well increment it as well. * * With this implementation, the value should always appear to observers to * increase over time if the file has changed. It's recommended to use * inode_eq_iversion() helper to compare values. * * Note that some filesystems (e.g. NFS and AFS) just use the field to store * a server-provided value (for the most part). For that reason, those * filesystems do not set SB_I_VERSION. These filesystems are considered to * have a self-managed i_version. * * Persistently storing the i_version * ---------------------------------- * Queries of the i_version field are not gated on them hitting the backing * store. It's always possible that the host could crash after allowing * a query of the value but before it has made it to disk. * * To mitigate this problem, filesystems should always use * inode_set_iversion_queried when loading an existing inode from disk. This * ensures that the next attempted inode increment will result in the value * changing. * * Storing the value to disk therefore does not count as a query, so those * filesystems should use inode_peek_iversion to grab the value to be stored. * There is no need to flag the value as having been queried in that case. */ /* * We borrow the lowest bit in the i_version to use as a flag to tell whether * it has been queried since we last incremented it. If it has, then we must * increment it on the next change. After that, we can clear the flag and * avoid incrementing it again until it has again been queried. */ #define I_VERSION_QUERIED_SHIFT (1) #define I_VERSION_QUERIED (1ULL << (I_VERSION_QUERIED_SHIFT - 1)) #define I_VERSION_INCREMENT (1ULL << I_VERSION_QUERIED_SHIFT) /** * inode_set_iversion_raw - set i_version to the specified raw value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for use by * filesystems that self-manage the i_version. * * For example, the NFS client stores its NFSv4 change attribute in this way, * and the AFS client stores the data_version from the server here. */ static inline void inode_set_iversion_raw(struct inode *inode, u64 val) { atomic64_set(&inode->i_version, val); } /** * inode_peek_iversion_raw - grab a "raw" iversion value * @inode: inode from which i_version should be read * * Grab a "raw" inode->i_version value and return it. The i_version is not * flagged or converted in any way. This is mostly used to access a self-managed * i_version. * * With those filesystems, we want to treat the i_version as an entirely * opaque value. */ static inline u64 inode_peek_iversion_raw(const struct inode *inode) { return atomic64_read(&inode->i_version); } /** * inode_set_max_iversion_raw - update i_version new value is larger * @inode: inode to set * @val: new i_version to set * * Some self-managed filesystems (e.g Ceph) will only update the i_version * value if the new value is larger than the one we already have. */ static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { u64 cur = inode_peek_iversion_raw(inode); do { if (cur > val) break; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** * inode_set_iversion - set i_version to a particular value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for filesystems with * a kernel-managed i_version, for initializing a newly-created inode from * scratch. * * In this case, we do not set the QUERIED flag since we know that this value * has never been queried. */ static inline void inode_set_iversion(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT); } /** * inode_set_iversion_queried - set i_version to a particular value as quereied * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val, and flag it for increment on the next * change. * * Filesystems that persistently store the i_version on disk should use this * when loading an existing inode from disk. * * When loading in an i_version value from a backing store, we can't be certain * that it wasn't previously viewed before being stored. Thus, we must assume * that it was, to ensure that we don't end up handing out the same value for * different versions of the same inode. */ static inline void inode_set_iversion_queried(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) | I_VERSION_QUERIED); } bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version * @inode: inode that needs to be updated * * Forcbily increment the i_version field. This always results in a change to * the observable value. */ static inline void inode_inc_iversion(struct inode *inode) { inode_maybe_inc_iversion(inode, true); } /** * inode_iversion_need_inc - is the i_version in need of being incremented? * @inode: inode to check * * Returns whether the inode->i_version counter needs incrementing on the next * change. Just fetch the value and check the QUERIED flag. */ static inline bool inode_iversion_need_inc(struct inode *inode) { return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED; } /** * inode_inc_iversion_raw - forcibly increment raw i_version * @inode: inode that needs to be updated * * Forcbily increment the raw i_version field. This always results in a change * to the raw value. * * NFS will use the i_version field to store the value from the server. It * mostly treats it as opaque, but in the case where it holds a write * delegation, it must increment the value itself. This function does that. */ static inline void inode_inc_iversion_raw(struct inode *inode) { atomic64_inc(&inode->i_version); } /** * inode_peek_iversion - read i_version without flagging it to be incremented * @inode: inode from which i_version should be read * * Read the inode i_version counter for an inode without registering it as a * query. * * This is typically used by local filesystems that need to store an i_version * on disk. In that situation, it's not necessary to flag it as having been * viewed, as the result won't be used to gauge changes from that point. */ static inline u64 inode_peek_iversion(const struct inode *inode) { return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } /* * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: */ static inline u64 time_to_chattr(const struct timespec64 *t) { u64 chattr = t->tv_sec; chattr <<= 32; chattr += t->tv_nsec; return chattr; } u64 inode_query_iversion(struct inode *inode); /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare the current raw i_version counter with a previous one. Returns true * if they are the same or false if they are different. */ static inline bool inode_eq_iversion_raw(const struct inode *inode, u64 old) { return inode_peek_iversion_raw(inode) == old; } /** * inode_eq_iversion - check whether the i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare an i_version counter with a previous one. Returns true if they are * the same, and false if they are different. * * Note that we don't need to set the QUERIED flag in this case, as the value * in the inode is not being recorded for later use. */ static inline bool inode_eq_iversion(const struct inode *inode, u64 old) { return inode_peek_iversion(inode) == old; } #endif |
| 4 3 4 2 3 3 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | // SPDX-License-Identifier: GPL-2.0 /* * super.c * * Copyright (c) 1999 Al Smith * * Portions derived from work (c) 1995,1996 Christian Vogelgsang. */ #include <linux/init.h> #include <linux/module.h> #include <linux/exportfs.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include "efs.h" #include <linux/efs_vh.h> #include <linux/efs_fs_sb.h> static int efs_statfs(struct dentry *dentry, struct kstatfs *buf); static int efs_init_fs_context(struct fs_context *fc); static void efs_kill_sb(struct super_block *s) { struct efs_sb_info *sbi = SUPER_INFO(s); kill_block_super(s); kfree(sbi); } static struct pt_types sgi_pt_types[] = { {0x00, "SGI vh"}, {0x01, "SGI trkrepl"}, {0x02, "SGI secrepl"}, {0x03, "SGI raw"}, {0x04, "SGI bsd"}, {SGI_SYSV, "SGI sysv"}, {0x06, "SGI vol"}, {SGI_EFS, "SGI efs"}, {0x08, "SGI lv"}, {0x09, "SGI rlv"}, {0x0A, "SGI xfs"}, {0x0B, "SGI xfslog"}, {0x0C, "SGI xlv"}, {0x82, "Linux swap"}, {0x83, "Linux native"}, {0, NULL} }; /* * File system definition and registration. */ static struct file_system_type efs_fs_type = { .owner = THIS_MODULE, .name = "efs", .kill_sb = efs_kill_sb, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = efs_init_fs_context, }; MODULE_ALIAS_FS("efs"); static struct kmem_cache * efs_inode_cachep; static struct inode *efs_alloc_inode(struct super_block *sb) { struct efs_inode_info *ei; ei = alloc_inode_sb(sb, efs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void efs_free_inode(struct inode *inode) { kmem_cache_free(efs_inode_cachep, INODE_INFO(inode)); } static void init_once(void *foo) { struct efs_inode_info *ei = (struct efs_inode_info *) foo; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", sizeof(struct efs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, init_once); if (efs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(efs_inode_cachep); } static const struct super_operations efs_superblock_operations = { .alloc_inode = efs_alloc_inode, .free_inode = efs_free_inode, .statfs = efs_statfs, }; static const struct export_operations efs_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = efs_fh_to_dentry, .fh_to_parent = efs_fh_to_parent, .get_parent = efs_get_parent, }; static int __init init_efs_fs(void) { int err; pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); err = init_inodecache(); if (err) goto out1; err = register_filesystem(&efs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_efs_fs(void) { unregister_filesystem(&efs_fs_type); destroy_inodecache(); } module_init(init_efs_fs) module_exit(exit_efs_fs) static efs_block_t efs_validate_vh(struct volume_header *vh) { int i; __be32 cs, *ui; int csum; efs_block_t sblock = 0; /* shuts up gcc */ struct pt_types *pt_entry; int pt_type, slice = -1; if (be32_to_cpu(vh->vh_magic) != VHMAGIC) { /* * assume that we're dealing with a partition and allow * read_super() to try and detect a valid superblock * on the next block. */ return 0; } ui = ((__be32 *) (vh + 1)) - 1; for(csum = 0; ui >= ((__be32 *) vh);) { cs = *ui--; csum += be32_to_cpu(cs); } if (csum) { pr_warn("SGI disklabel: checksum bad, label corrupted\n"); return 0; } #ifdef DEBUG pr_debug("bf: \"%16s\"\n", vh->vh_bootfile); for(i = 0; i < NVDIR; i++) { int j; char name[VDNAMESIZE+1]; for(j = 0; j < VDNAMESIZE; j++) { name[j] = vh->vh_vd[i].vd_name[j]; } name[j] = (char) 0; if (name[0]) { pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n", name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn), (int) be32_to_cpu(vh->vh_vd[i].vd_nbytes)); } } #endif for(i = 0; i < NPARTAB; i++) { pt_type = (int) be32_to_cpu(vh->vh_pt[i].pt_type); for(pt_entry = sgi_pt_types; pt_entry->pt_name; pt_entry++) { if (pt_type == pt_entry->pt_type) break; } #ifdef DEBUG if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) { pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n", i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn), (int)be32_to_cpu(vh->vh_pt[i].pt_nblks), pt_type, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown"); } #endif if (IS_EFS(pt_type)) { sblock = be32_to_cpu(vh->vh_pt[i].pt_firstlbn); slice = i; } } if (slice == -1) { pr_notice("partition table contained no EFS partitions\n"); #ifdef DEBUG } else { pr_info("using slice %d (type %s, offset 0x%x)\n", slice, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown", sblock); #endif } return sblock; } static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) { if (!IS_EFS_MAGIC(be32_to_cpu(super->fs_magic))) return -1; sb->fs_magic = be32_to_cpu(super->fs_magic); sb->total_blocks = be32_to_cpu(super->fs_size); sb->first_block = be32_to_cpu(super->fs_firstcg); sb->group_size = be32_to_cpu(super->fs_cgfsize); sb->data_free = be32_to_cpu(super->fs_tfree); sb->inode_free = be32_to_cpu(super->fs_tinode); sb->inode_blocks = be16_to_cpu(super->fs_cgisize); sb->total_groups = be16_to_cpu(super->fs_ncg); return 0; } static int efs_fill_super(struct super_block *s, struct fs_context *fc) { struct efs_sb_info *sb; struct buffer_head *bh; struct inode *root; sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL); if (!sb) return -ENOMEM; s->s_fs_info = sb; s->s_time_min = 0; s->s_time_max = U32_MAX; s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { pr_err("device does not support %d byte blocks\n", EFS_BLOCKSIZE); return invalf(fc, "device does not support %d byte blocks\n", EFS_BLOCKSIZE); } /* read the vh (volume header) block */ bh = sb_bread(s, 0); if (!bh) { pr_err("cannot read volume header\n"); return -EIO; } /* * if this returns zero then we didn't find any partition table. * this isn't (yet) an error - just assume for the moment that * the device is valid and go on to search for a superblock. */ sb->fs_start = efs_validate_vh((struct volume_header *) bh->b_data); brelse(bh); if (sb->fs_start == -1) { return -EINVAL; } bh = sb_bread(s, sb->fs_start + EFS_SUPER); if (!bh) { pr_err("cannot read superblock\n"); return -EIO; } if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) { #ifdef DEBUG pr_warn("invalid superblock at block %u\n", sb->fs_start + EFS_SUPER); #endif brelse(bh); return -EINVAL; } brelse(bh); if (!sb_rdonly(s)) { #ifdef DEBUG pr_info("forcing read-only mode\n"); #endif s->s_flags |= SB_RDONLY; } s->s_op = &efs_superblock_operations; s->s_export_op = &efs_export_ops; root = efs_iget(s, EFS_ROOTINODE); if (IS_ERR(root)) { pr_err("get root inode failed\n"); return PTR_ERR(root); } s->s_root = d_make_root(root); if (!(s->s_root)) { pr_err("get root dentry failed\n"); return -ENOMEM; } return 0; } static int efs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, efs_fill_super); } static int efs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; return 0; } static const struct fs_context_operations efs_context_opts = { .get_tree = efs_get_tree, .reconfigure = efs_reconfigure, }; /* * Set up the filesystem mount context. */ static int efs_init_fs_context(struct fs_context *fc) { fc->ops = &efs_context_opts; return 0; } static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct efs_sb_info *sbi = SUPER_INFO(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = EFS_SUPER_MAGIC; /* efs magic number */ buf->f_bsize = EFS_BLOCKSIZE; /* blocksize */ buf->f_blocks = sbi->total_groups * /* total data blocks */ (sbi->group_size - sbi->inode_blocks); buf->f_bfree = sbi->data_free; /* free data blocks */ buf->f_bavail = sbi->data_free; /* free blocks for non-root */ buf->f_files = sbi->total_groups * /* total inodes */ sbi->inode_blocks * (EFS_BLOCKSIZE / sizeof(struct efs_dinode)); buf->f_ffree = sbi->inode_free; /* free inodes */ buf->f_fsid = u64_to_fsid(id); buf->f_namelen = EFS_MAXNAMELEN; /* max filename length */ return 0; } |
| 1 1 1 1 1 1 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 4 4 7 7 4 4 4 4 4 4 4 4 4 4 3 4 4 3 4 3 4 4 4 1 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * The input core * * Copyright (c) 1999-2002 Vojtech Pavlik */ #define pr_fmt(fmt) KBUILD_BASENAME ": " fmt #include <linux/export.h> #include <linux/init.h> #include <linux/types.h> #include <linux/idr.h> #include <linux/input/mt.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/major.h> #include <linux/proc_fs.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/pm.h> #include <linux/poll.h> #include <linux/device.h> #include <linux/kstrtox.h> #include <linux/mutex.h> #include <linux/rcupdate.h> #include "input-compat.h" #include "input-core-private.h" #include "input-poller.h" MODULE_AUTHOR("Vojtech Pavlik <vojtech@suse.cz>"); MODULE_DESCRIPTION("Input core"); MODULE_LICENSE("GPL"); #define INPUT_MAX_CHAR_DEVICES 1024 #define INPUT_FIRST_DYNAMIC_DEV 256 static DEFINE_IDA(input_ida); static LIST_HEAD(input_dev_list); static LIST_HEAD(input_handler_list); /* * input_mutex protects access to both input_dev_list and input_handler_list. * This also causes input_[un]register_device and input_[un]register_handler * be mutually exclusive which simplifies locking in drivers implementing * input handlers. */ static DEFINE_MUTEX(input_mutex); static const struct input_value input_value_sync = { EV_SYN, SYN_REPORT, 1 }; static const unsigned int input_max_code[EV_CNT] = { [EV_KEY] = KEY_MAX, [EV_REL] = REL_MAX, [EV_ABS] = ABS_MAX, [EV_MSC] = MSC_MAX, [EV_SW] = SW_MAX, [EV_LED] = LED_MAX, [EV_SND] = SND_MAX, [EV_FF] = FF_MAX, }; static inline int is_event_supported(unsigned int code, unsigned long *bm, unsigned int max) { return code <= max && test_bit(code, bm); } static int input_defuzz_abs_event(int value, int old_val, int fuzz) { if (fuzz) { if (value > old_val - fuzz / 2 && value < old_val + fuzz / 2) return old_val; if (value > old_val - fuzz && value < old_val + fuzz) return (old_val * 3 + value) / 4; if (value > old_val - fuzz * 2 && value < old_val + fuzz * 2) return (old_val + value) / 2; } return value; } static void input_start_autorepeat(struct input_dev *dev, int code) { if (test_bit(EV_REP, dev->evbit) && dev->rep[REP_PERIOD] && dev->rep[REP_DELAY] && dev->timer.function) { dev->repeat_key = code; mod_timer(&dev->timer, jiffies + msecs_to_jiffies(dev->rep[REP_DELAY])); } } static void input_stop_autorepeat(struct input_dev *dev) { timer_delete(&dev->timer); } /* * Pass values first through all filters and then, if event has not been * filtered out, through all open handles. This order is achieved by placing * filters at the head of the list of handles attached to the device, and * placing regular handles at the tail of the list. * * This function is called with dev->event_lock held and interrupts disabled. */ static void input_pass_values(struct input_dev *dev, struct input_value *vals, unsigned int count) { struct input_handle *handle; struct input_value *v; lockdep_assert_held(&dev->event_lock); scoped_guard(rcu) { handle = rcu_dereference(dev->grab); if (handle) { count = handle->handle_events(handle, vals, count); break; } list_for_each_entry_rcu(handle, &dev->h_list, d_node) { if (handle->open) { count = handle->handle_events(handle, vals, count); if (!count) break; } } } /* trigger auto repeat for key events */ if (test_bit(EV_REP, dev->evbit) && test_bit(EV_KEY, dev->evbit)) { for (v = vals; v != vals + count; v++) { if (v->type == EV_KEY && v->value != 2) { if (v->value) input_start_autorepeat(dev, v->code); else input_stop_autorepeat(dev); } } } } #define INPUT_IGNORE_EVENT 0 #define INPUT_PASS_TO_HANDLERS 1 #define INPUT_PASS_TO_DEVICE 2 #define INPUT_SLOT 4 #define INPUT_FLUSH 8 #define INPUT_PASS_TO_ALL (INPUT_PASS_TO_HANDLERS | INPUT_PASS_TO_DEVICE) static int input_handle_abs_event(struct input_dev *dev, unsigned int code, int *pval) { struct input_mt *mt = dev->mt; bool is_new_slot = false; bool is_mt_event; int *pold; if (code == ABS_MT_SLOT) { /* * "Stage" the event; we'll flush it later, when we * get actual touch data. */ if (mt && *pval >= 0 && *pval < mt->num_slots) mt->slot = *pval; return INPUT_IGNORE_EVENT; } is_mt_event = input_is_mt_value(code); if (!is_mt_event) { pold = &dev->absinfo[code].value; } else if (mt) { pold = &mt->slots[mt->slot].abs[code - ABS_MT_FIRST]; is_new_slot = mt->slot != dev->absinfo[ABS_MT_SLOT].value; } else { /* * Bypass filtering for multi-touch events when * not employing slots. */ pold = NULL; } if (pold) { *pval = input_defuzz_abs_event(*pval, *pold, dev->absinfo[code].fuzz); if (*pold == *pval) return INPUT_IGNORE_EVENT; *pold = *pval; } /* Flush pending "slot" event */ if (is_new_slot) { dev->absinfo[ABS_MT_SLOT].value = mt->slot; return INPUT_PASS_TO_HANDLERS | INPUT_SLOT; } return INPUT_PASS_TO_HANDLERS; } static int input_get_disposition(struct input_dev *dev, unsigned int type, unsigned int code, int *pval) { int disposition = INPUT_IGNORE_EVENT; int value = *pval; /* filter-out events from inhibited devices */ if (dev->inhibited) return INPUT_IGNORE_EVENT; switch (type) { case EV_SYN: switch (code) { case SYN_CONFIG: disposition = INPUT_PASS_TO_ALL; break; case SYN_REPORT: disposition = INPUT_PASS_TO_HANDLERS | INPUT_FLUSH; break; case SYN_MT_REPORT: disposition = INPUT_PASS_TO_HANDLERS; break; } break; case EV_KEY: if (is_event_supported(code, dev->keybit, KEY_MAX)) { /* auto-repeat bypasses state updates */ if (value == 2) { disposition = INPUT_PASS_TO_HANDLERS; break; } if (!!test_bit(code, dev->key) != !!value) { __change_bit(code, dev->key); disposition = INPUT_PASS_TO_HANDLERS; } } break; case EV_SW: if (is_event_supported(code, dev->swbit, SW_MAX) && !!test_bit(code, dev->sw) != !!value) { __change_bit(code, dev->sw); disposition = INPUT_PASS_TO_HANDLERS; } break; case EV_ABS: if (is_event_supported(code, dev->absbit, ABS_MAX)) disposition = input_handle_abs_event(dev, code, &value); break; case EV_REL: if (is_event_supported(code, dev->relbit, REL_MAX) && value) disposition = INPUT_PASS_TO_HANDLERS; break; case EV_MSC: if (is_event_supported(code, dev->mscbit, MSC_MAX)) disposition = INPUT_PASS_TO_ALL; break; case EV_LED: if (is_event_supported(code, dev->ledbit, LED_MAX) && !!test_bit(code, dev->led) != !!value) { __change_bit(code, dev->led); disposition = INPUT_PASS_TO_ALL; } break; case EV_SND: if (is_event_supported(code, dev->sndbit, SND_MAX)) { if (!!test_bit(code, dev->snd) != !!value) __change_bit(code, dev->snd); disposition = INPUT_PASS_TO_ALL; } break; case EV_REP: if (code <= REP_MAX && value >= 0 && dev->rep[code] != value) { dev->rep[code] = value; disposition = INPUT_PASS_TO_ALL; } break; case EV_FF: if (value >= 0) disposition = INPUT_PASS_TO_ALL; break; case EV_PWR: disposition = INPUT_PASS_TO_ALL; break; } *pval = value; return disposition; } static void input_event_dispose(struct input_dev *dev, int disposition, unsigned int type, unsigned int code, int value) { if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event) dev->event(dev, type, code, value); if (disposition & INPUT_PASS_TO_HANDLERS) { struct input_value *v; if (disposition & INPUT_SLOT) { v = &dev->vals[dev->num_vals++]; v->type = EV_ABS; v->code = ABS_MT_SLOT; v->value = dev->mt->slot; } v = &dev->vals[dev->num_vals++]; v->type = type; v->code = code; v->value = value; } if (disposition & INPUT_FLUSH) { if (dev->num_vals >= 2) input_pass_values(dev, dev->vals, dev->num_vals); dev->num_vals = 0; /* * Reset the timestamp on flush so we won't end up * with a stale one. Note we only need to reset the * monolithic one as we use its presence when deciding * whether to generate a synthetic timestamp. */ dev->timestamp[INPUT_CLK_MONO] = ktime_set(0, 0); } else if (dev->num_vals >= dev->max_vals - 2) { dev->vals[dev->num_vals++] = input_value_sync; input_pass_values(dev, dev->vals, dev->num_vals); dev->num_vals = 0; } } void input_handle_event(struct input_dev *dev, unsigned int type, unsigned int code, int value) { int disposition; lockdep_assert_held(&dev->event_lock); disposition = input_get_disposition(dev, type, code, &value); if (disposition != INPUT_IGNORE_EVENT) { if (type != EV_SYN) add_input_randomness(type, code, value); input_event_dispose(dev, disposition, type, code, value); } } /** * input_event() - report new input event * @dev: device that generated the event * @type: type of the event * @code: event code * @value: value of the event * * This function should be used by drivers implementing various input * devices to report input events. See also input_inject_event(). * * NOTE: input_event() may be safely used right after input device was * allocated with input_allocate_device(), even before it is registered * with input_register_device(), but the event will not reach any of the * input handlers. Such early invocation of input_event() may be used * to 'seed' initial state of a switch or initial position of absolute * axis, etc. */ void input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value) { if (is_event_supported(type, dev->evbit, EV_MAX)) { guard(spinlock_irqsave)(&dev->event_lock); input_handle_event(dev, type, code, value); } } EXPORT_SYMBOL(input_event); /** * input_inject_event() - send input event from input handler * @handle: input handle to send event through * @type: type of the event * @code: event code * @value: value of the event * * Similar to input_event() but will ignore event if device is * "grabbed" and handle injecting event is not the one that owns * the device. */ void input_inject_event(struct input_handle *handle, unsigned int type, unsigned int code, int value) { struct input_dev *dev = handle->dev; struct input_handle *grab; if (is_event_supported(type, dev->evbit, EV_MAX)) { guard(spinlock_irqsave)(&dev->event_lock); guard(rcu)(); grab = rcu_dereference(dev->grab); if (!grab || grab == handle) input_handle_event(dev, type, code, value); } } EXPORT_SYMBOL(input_inject_event); /** * input_alloc_absinfo - allocates array of input_absinfo structs * @dev: the input device emitting absolute events * * If the absinfo struct the caller asked for is already allocated, this * functions will not do anything. */ void input_alloc_absinfo(struct input_dev *dev) { if (dev->absinfo) return; dev->absinfo = kcalloc(ABS_CNT, sizeof(*dev->absinfo), GFP_KERNEL); if (!dev->absinfo) { dev_err(dev->dev.parent ?: &dev->dev, "%s: unable to allocate memory\n", __func__); /* * We will handle this allocation failure in * input_register_device() when we refuse to register input * device with ABS bits but without absinfo. */ } } EXPORT_SYMBOL(input_alloc_absinfo); void input_set_abs_params(struct input_dev *dev, unsigned int axis, int min, int max, int fuzz, int flat) { struct input_absinfo *absinfo; __set_bit(EV_ABS, dev->evbit); __set_bit(axis, dev->absbit); input_alloc_absinfo(dev); if (!dev->absinfo) return; absinfo = &dev->absinfo[axis]; absinfo->minimum = min; absinfo->maximum = max; absinfo->fuzz = fuzz; absinfo->flat = flat; } EXPORT_SYMBOL(input_set_abs_params); /** * input_copy_abs - Copy absinfo from one input_dev to another * @dst: Destination input device to copy the abs settings to * @dst_axis: ABS_* value selecting the destination axis * @src: Source input device to copy the abs settings from * @src_axis: ABS_* value selecting the source axis * * Set absinfo for the selected destination axis by copying it from * the specified source input device's source axis. * This is useful to e.g. setup a pen/stylus input-device for combined * touchscreen/pen hardware where the pen uses the same coordinates as * the touchscreen. */ void input_copy_abs(struct input_dev *dst, unsigned int dst_axis, const struct input_dev *src, unsigned int src_axis) { /* src must have EV_ABS and src_axis set */ if (WARN_ON(!(test_bit(EV_ABS, src->evbit) && test_bit(src_axis, src->absbit)))) return; /* * input_alloc_absinfo() may have failed for the source. Our caller is * expected to catch this when registering the input devices, which may * happen after the input_copy_abs() call. */ if (!src->absinfo) return; input_set_capability(dst, EV_ABS, dst_axis); if (!dst->absinfo) return; dst->absinfo[dst_axis] = src->absinfo[src_axis]; } EXPORT_SYMBOL(input_copy_abs); /** * input_grab_device - grabs device for exclusive use * @handle: input handle that wants to own the device * * When a device is grabbed by an input handle all events generated by * the device are delivered only to this handle. Also events injected * by other input handles are ignored while device is grabbed. */ int input_grab_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { if (dev->grab) return -EBUSY; rcu_assign_pointer(dev->grab, handle); } return 0; } EXPORT_SYMBOL(input_grab_device); static void __input_release_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; struct input_handle *grabber; grabber = rcu_dereference_protected(dev->grab, lockdep_is_held(&dev->mutex)); if (grabber == handle) { rcu_assign_pointer(dev->grab, NULL); /* Make sure input_pass_values() notices that grab is gone */ synchronize_rcu(); list_for_each_entry(handle, &dev->h_list, d_node) if (handle->open && handle->handler->start) handle->handler->start(handle); } } /** * input_release_device - release previously grabbed device * @handle: input handle that owns the device * * Releases previously grabbed device so that other input handles can * start receiving input events. Upon release all handlers attached * to the device have their start() method called so they have a change * to synchronize device state with the rest of the system. */ void input_release_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; guard(mutex)(&dev->mutex); __input_release_device(handle); } EXPORT_SYMBOL(input_release_device); /** * input_open_device - open input device * @handle: handle through which device is being accessed * * This function should be called by input handlers when they * want to start receive events from given input device. */ int input_open_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; int error; scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { if (dev->going_away) return -ENODEV; handle->open++; if (handle->handler->passive_observer) return 0; if (dev->users++ || dev->inhibited) { /* * Device is already opened and/or inhibited, * so we can exit immediately and report success. */ return 0; } if (dev->open) { error = dev->open(dev); if (error) { dev->users--; handle->open--; /* * Make sure we are not delivering any more * events through this handle. */ synchronize_rcu(); return error; } } if (dev->poller) input_dev_poller_start(dev->poller); } return 0; } EXPORT_SYMBOL(input_open_device); int input_flush_device(struct input_handle *handle, struct file *file) { struct input_dev *dev = handle->dev; scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { if (dev->flush) return dev->flush(dev, file); } return 0; } EXPORT_SYMBOL(input_flush_device); /** * input_close_device - close input device * @handle: handle through which device is being accessed * * This function should be called by input handlers when they * want to stop receive events from given input device. */ void input_close_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; guard(mutex)(&dev->mutex); __input_release_device(handle); if (!handle->handler->passive_observer) { if (!--dev->users && !dev->inhibited) { if (dev->poller) input_dev_poller_stop(dev->poller); if (dev->close) dev->close(dev); } } if (!--handle->open) { /* * synchronize_rcu() makes sure that input_pass_values() * completed and that no more input events are delivered * through this handle */ synchronize_rcu(); } } EXPORT_SYMBOL(input_close_device); /* * Simulate keyup events for all keys that are marked as pressed. * The function must be called with dev->event_lock held. */ static bool input_dev_release_keys(struct input_dev *dev) { bool need_sync = false; int code; lockdep_assert_held(&dev->event_lock); if (is_event_supported(EV_KEY, dev->evbit, EV_MAX)) { for_each_set_bit(code, dev->key, KEY_CNT) { input_handle_event(dev, EV_KEY, code, 0); need_sync = true; } } return need_sync; } /* * Prepare device for unregistering */ static void input_disconnect_device(struct input_dev *dev) { struct input_handle *handle; /* * Mark device as going away. Note that we take dev->mutex here * not to protect access to dev->going_away but rather to ensure * that there are no threads in the middle of input_open_device() */ scoped_guard(mutex, &dev->mutex) dev->going_away = true; guard(spinlock_irq)(&dev->event_lock); /* * Simulate keyup events for all pressed keys so that handlers * are not left with "stuck" keys. The driver may continue * generate events even after we done here but they will not * reach any handlers. */ if (input_dev_release_keys(dev)) input_handle_event(dev, EV_SYN, SYN_REPORT, 1); list_for_each_entry(handle, &dev->h_list, d_node) handle->open = 0; } /** * input_scancode_to_scalar() - converts scancode in &struct input_keymap_entry * @ke: keymap entry containing scancode to be converted. * @scancode: pointer to the location where converted scancode should * be stored. * * This function is used to convert scancode stored in &struct keymap_entry * into scalar form understood by legacy keymap handling methods. These * methods expect scancodes to be represented as 'unsigned int'. */ int input_scancode_to_scalar(const struct input_keymap_entry *ke, unsigned int *scancode) { switch (ke->len) { case 1: *scancode = *((u8 *)ke->scancode); break; case 2: *scancode = *((u16 *)ke->scancode); break; case 4: *scancode = *((u32 *)ke->scancode); break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL(input_scancode_to_scalar); /* * Those routines handle the default case where no [gs]etkeycode() is * defined. In this case, an array indexed by the scancode is used. */ static unsigned int input_fetch_keycode(struct input_dev *dev, unsigned int index) { switch (dev->keycodesize) { case 1: return ((u8 *)dev->keycode)[index]; case 2: return ((u16 *)dev->keycode)[index]; default: return ((u32 *)dev->keycode)[index]; } } static int input_default_getkeycode(struct input_dev *dev, struct input_keymap_entry *ke) { unsigned int index; int error; if (!dev->keycodesize) return -EINVAL; if (ke->flags & INPUT_KEYMAP_BY_INDEX) index = ke->index; else { error = input_scancode_to_scalar(ke, &index); if (error) return error; } if (index >= dev->keycodemax) return -EINVAL; ke->keycode = input_fetch_keycode(dev, index); ke->index = index; ke->len = sizeof(index); memcpy(ke->scancode, &index, sizeof(index)); return 0; } static int input_default_setkeycode(struct input_dev *dev, const struct input_keymap_entry *ke, unsigned int *old_keycode) { unsigned int index; int error; int i; if (!dev->keycodesize) return -EINVAL; if (ke->flags & INPUT_KEYMAP_BY_INDEX) { index = ke->index; } else { error = input_scancode_to_scalar(ke, &index); if (error) return error; } if (index >= dev->keycodemax) return -EINVAL; if (dev->keycodesize < sizeof(ke->keycode) && (ke->keycode >> (dev->keycodesize * 8))) return -EINVAL; switch (dev->keycodesize) { case 1: { u8 *k = (u8 *)dev->keycode; *old_keycode = k[index]; k[index] = ke->keycode; break; } case 2: { u16 *k = (u16 *)dev->keycode; *old_keycode = k[index]; k[index] = ke->keycode; break; } default: { u32 *k = (u32 *)dev->keycode; *old_keycode = k[index]; k[index] = ke->keycode; break; } } if (*old_keycode <= KEY_MAX) { __clear_bit(*old_keycode, dev->keybit); for (i = 0; i < dev->keycodemax; i++) { if (input_fetch_keycode(dev, i) == *old_keycode) { __set_bit(*old_keycode, dev->keybit); /* Setting the bit twice is useless, so break */ break; } } } __set_bit(ke->keycode, dev->keybit); return 0; } /** * input_get_keycode - retrieve keycode currently mapped to a given scancode * @dev: input device which keymap is being queried * @ke: keymap entry * * This function should be called by anyone interested in retrieving current * keymap. Presently evdev handlers use it. */ int input_get_keycode(struct input_dev *dev, struct input_keymap_entry *ke) { guard(spinlock_irqsave)(&dev->event_lock); return dev->getkeycode(dev, ke); } EXPORT_SYMBOL(input_get_keycode); /** * input_set_keycode - attribute a keycode to a given scancode * @dev: input device which keymap is being updated * @ke: new keymap entry * * This function should be called by anyone needing to update current * keymap. Presently keyboard and evdev handlers use it. */ int input_set_keycode(struct input_dev *dev, const struct input_keymap_entry *ke) { unsigned int old_keycode; int error; if (ke->keycode > KEY_MAX) return -EINVAL; guard(spinlock_irqsave)(&dev->event_lock); error = dev->setkeycode(dev, ke, &old_keycode); if (error) return error; /* Make sure KEY_RESERVED did not get enabled. */ __clear_bit(KEY_RESERVED, dev->keybit); /* * Simulate keyup event if keycode is not present * in the keymap anymore */ if (old_keycode > KEY_MAX) { dev_warn(dev->dev.parent ?: &dev->dev, "%s: got too big old keycode %#x\n", __func__, old_keycode); } else if (test_bit(EV_KEY, dev->evbit) && !is_event_supported(old_keycode, dev->keybit, KEY_MAX) && __test_and_clear_bit(old_keycode, dev->key)) { /* * We have to use input_event_dispose() here directly instead * of input_handle_event() because the key we want to release * here is considered no longer supported by the device and * input_handle_event() will ignore it. */ input_event_dispose(dev, INPUT_PASS_TO_HANDLERS, EV_KEY, old_keycode, 0); input_event_dispose(dev, INPUT_PASS_TO_HANDLERS | INPUT_FLUSH, EV_SYN, SYN_REPORT, 1); } return 0; } EXPORT_SYMBOL(input_set_keycode); bool input_match_device_id(const struct input_dev *dev, const struct input_device_id *id) { if (id->flags & INPUT_DEVICE_ID_MATCH_BUS) if (id->bustype != dev->id.bustype) return false; if (id->flags & INPUT_DEVICE_ID_MATCH_VENDOR) if (id->vendor != dev->id.vendor) return false; if (id->flags & INPUT_DEVICE_ID_MATCH_PRODUCT) if (id->product != dev->id.product) return false; if (id->flags & INPUT_DEVICE_ID_MATCH_VERSION) if (id->version != dev->id.version) return false; if (!bitmap_subset(id->evbit, dev->evbit, EV_MAX) || !bitmap_subset(id->keybit, dev->keybit, KEY_MAX) || !bitmap_subset(id->relbit, dev->relbit, REL_MAX) || !bitmap_subset(id->absbit, dev->absbit, ABS_MAX) || !bitmap_subset(id->mscbit, dev->mscbit, MSC_MAX) || !bitmap_subset(id->ledbit, dev->ledbit, LED_MAX) || !bitmap_subset(id->sndbit, dev->sndbit, SND_MAX) || !bitmap_subset(id->ffbit, dev->ffbit, FF_MAX) || !bitmap_subset(id->swbit, dev->swbit, SW_MAX) || !bitmap_subset(id->propbit, dev->propbit, INPUT_PROP_MAX)) { return false; } return true; } EXPORT_SYMBOL(input_match_device_id); static const struct input_device_id *input_match_device(struct input_handler *handler, struct input_dev *dev) { const struct input_device_id *id; for (id = handler->id_table; id->flags; id++) { if (input_match_device_id(dev, id) && (!handler->match || handler->match(handler, dev))) { return id; } } return NULL; } static int input_attach_handler(struct input_dev *dev, struct input_handler *handler) { const struct input_device_id *id; int error; id = input_match_device(handler, dev); if (!id) return -ENODEV; error = handler->connect(handler, dev, id); if (error && error != -ENODEV) pr_err("failed to attach handler %s to device %s, error: %d\n", handler->name, kobject_name(&dev->dev.kobj), error); return error; } #ifdef CONFIG_PROC_FS static struct proc_dir_entry *proc_bus_input_dir; static DECLARE_WAIT_QUEUE_HEAD(input_devices_poll_wait); static int input_devices_state; static inline void input_wakeup_procfs_readers(void) { input_devices_state++; wake_up(&input_devices_poll_wait); } struct input_seq_state { unsigned short pos; bool mutex_acquired; int input_devices_state; }; static __poll_t input_proc_devices_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; struct input_seq_state *state = seq->private; poll_wait(file, &input_devices_poll_wait, wait); if (state->input_devices_state != input_devices_state) { state->input_devices_state = input_devices_state; return EPOLLIN | EPOLLRDNORM; } return 0; } static void *input_devices_seq_start(struct seq_file *seq, loff_t *pos) { struct input_seq_state *state = seq->private; int error; error = mutex_lock_interruptible(&input_mutex); if (error) { state->mutex_acquired = false; return ERR_PTR(error); } state->mutex_acquired = true; return seq_list_start(&input_dev_list, *pos); } static void *input_devices_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &input_dev_list, pos); } static void input_seq_stop(struct seq_file *seq, void *v) { struct input_seq_state *state = seq->private; if (state->mutex_acquired) mutex_unlock(&input_mutex); } static void input_seq_print_bitmap(struct seq_file *seq, const char *name, unsigned long *bitmap, int max) { int i; bool skip_empty = true; char buf[18]; seq_printf(seq, "B: %s=", name); for (i = BITS_TO_LONGS(max) - 1; i >= 0; i--) { if (input_bits_to_string(buf, sizeof(buf), bitmap[i], skip_empty)) { skip_empty = false; seq_printf(seq, "%s%s", buf, i > 0 ? " " : ""); } } /* * If no output was produced print a single 0. */ if (skip_empty) seq_putc(seq, '0'); seq_putc(seq, '\n'); } static int input_devices_seq_show(struct seq_file *seq, void *v) { struct input_dev *dev = container_of(v, struct input_dev, node); const char *path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); struct input_handle *handle; seq_printf(seq, "I: Bus=%04x Vendor=%04x Product=%04x Version=%04x\n", dev->id.bustype, dev->id.vendor, dev->id.product, dev->id.version); seq_printf(seq, "N: Name=\"%s\"\n", dev->name ? dev->name : ""); seq_printf(seq, "P: Phys=%s\n", dev->phys ? dev->phys : ""); seq_printf(seq, "S: Sysfs=%s\n", path ? path : ""); seq_printf(seq, "U: Uniq=%s\n", dev->uniq ? dev->uniq : ""); seq_puts(seq, "H: Handlers="); list_for_each_entry(handle, &dev->h_list, d_node) seq_printf(seq, "%s ", handle->name); seq_putc(seq, '\n'); input_seq_print_bitmap(seq, "PROP", dev->propbit, INPUT_PROP_MAX); input_seq_print_bitmap(seq, "EV", dev->evbit, EV_MAX); if (test_bit(EV_KEY, dev->evbit)) input_seq_print_bitmap(seq, "KEY", dev->keybit, KEY_MAX); if (test_bit(EV_REL, dev->evbit)) input_seq_print_bitmap(seq, "REL", dev->relbit, REL_MAX); if (test_bit(EV_ABS, dev->evbit)) input_seq_print_bitmap(seq, "ABS", dev->absbit, ABS_MAX); if (test_bit(EV_MSC, dev->evbit)) input_seq_print_bitmap(seq, "MSC", dev->mscbit, MSC_MAX); if (test_bit(EV_LED, dev->evbit)) input_seq_print_bitmap(seq, "LED", dev->ledbit, LED_MAX); if (test_bit(EV_SND, dev->evbit)) input_seq_print_bitmap(seq, "SND", dev->sndbit, SND_MAX); if (test_bit(EV_FF, dev->evbit)) input_seq_print_bitmap(seq, "FF", dev->ffbit, FF_MAX); if (test_bit(EV_SW, dev->evbit)) input_seq_print_bitmap(seq, "SW", dev->swbit, SW_MAX); seq_putc(seq, '\n'); kfree(path); return 0; } static const struct seq_operations input_devices_seq_ops = { .start = input_devices_seq_start, .next = input_devices_seq_next, .stop = input_seq_stop, .show = input_devices_seq_show, }; static int input_proc_devices_open(struct inode *inode, struct file *file) { return seq_open_private(file, &input_devices_seq_ops, sizeof(struct input_seq_state)); } static const struct proc_ops input_devices_proc_ops = { .proc_open = input_proc_devices_open, .proc_poll = input_proc_devices_poll, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release_private, }; static void *input_handlers_seq_start(struct seq_file *seq, loff_t *pos) { struct input_seq_state *state = seq->private; int error; error = mutex_lock_interruptible(&input_mutex); if (error) { state->mutex_acquired = false; return ERR_PTR(error); } state->mutex_acquired = true; state->pos = *pos; return seq_list_start(&input_handler_list, *pos); } static void *input_handlers_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct input_seq_state *state = seq->private; state->pos = *pos + 1; return seq_list_next(v, &input_handler_list, pos); } static int input_handlers_seq_show(struct seq_file *seq, void *v) { struct input_handler *handler = container_of(v, struct input_handler, node); struct input_seq_state *state = seq->private; seq_printf(seq, "N: Number=%u Name=%s", state->pos, handler->name); if (handler->filter) seq_puts(seq, " (filter)"); if (handler->legacy_minors) seq_printf(seq, " Minor=%d", handler->minor); seq_putc(seq, '\n'); return 0; } static const struct seq_operations input_handlers_seq_ops = { .start = input_handlers_seq_start, .next = input_handlers_seq_next, .stop = input_seq_stop, .show = input_handlers_seq_show, }; static int input_proc_handlers_open(struct inode *inode, struct file *file) { return seq_open_private(file, &input_handlers_seq_ops, sizeof(struct input_seq_state)); } static const struct proc_ops input_handlers_proc_ops = { .proc_open = input_proc_handlers_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release_private, }; static int __init input_proc_init(void) { struct proc_dir_entry *entry; proc_bus_input_dir = proc_mkdir("bus/input", NULL); if (!proc_bus_input_dir) return -ENOMEM; entry = proc_create("devices", 0, proc_bus_input_dir, &input_devices_proc_ops); if (!entry) goto fail1; entry = proc_create("handlers", 0, proc_bus_input_dir, &input_handlers_proc_ops); if (!entry) goto fail2; return 0; fail2: remove_proc_entry("devices", proc_bus_input_dir); fail1: remove_proc_entry("bus/input", NULL); return -ENOMEM; } static void input_proc_exit(void) { remove_proc_entry("devices", proc_bus_input_dir); remove_proc_entry("handlers", proc_bus_input_dir); remove_proc_entry("bus/input", NULL); } #else /* !CONFIG_PROC_FS */ static inline void input_wakeup_procfs_readers(void) { } static inline int input_proc_init(void) { return 0; } static inline void input_proc_exit(void) { } #endif #define INPUT_DEV_STRING_ATTR_SHOW(name) \ static ssize_t input_dev_show_##name(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ struct input_dev *input_dev = to_input_dev(dev); \ \ return sysfs_emit(buf, "%s\n", \ input_dev->name ? input_dev->name : ""); \ } \ static DEVICE_ATTR(name, S_IRUGO, input_dev_show_##name, NULL) INPUT_DEV_STRING_ATTR_SHOW(name); INPUT_DEV_STRING_ATTR_SHOW(phys); INPUT_DEV_STRING_ATTR_SHOW(uniq); static int input_print_modalias_bits(char *buf, int size, char name, const unsigned long *bm, unsigned int min_bit, unsigned int max_bit) { int bit = min_bit; int len = 0; len += snprintf(buf, max(size, 0), "%c", name); for_each_set_bit_from(bit, bm, max_bit) len += snprintf(buf + len, max(size - len, 0), "%X,", bit); return len; } static int input_print_modalias_parts(char *buf, int size, int full_len, const struct input_dev *id) { int len, klen, remainder, space; len = snprintf(buf, max(size, 0), "input:b%04Xv%04Xp%04Xe%04X-", id->id.bustype, id->id.vendor, id->id.product, id->id.version); len += input_print_modalias_bits(buf + len, size - len, 'e', id->evbit, 0, EV_MAX); /* * Calculate the remaining space in the buffer making sure we * have place for the terminating 0. */ space = max(size - (len + 1), 0); klen = input_print_modalias_bits(buf + len, size - len, 'k', id->keybit, KEY_MIN_INTERESTING, KEY_MAX); len += klen; /* * If we have more data than we can fit in the buffer, check * if we can trim key data to fit in the rest. We will indicate * that key data is incomplete by adding "+" sign at the end, like * this: * "k1,2,3,45,+,". * * Note that we shortest key info (if present) is "k+," so we * can only try to trim if key data is longer than that. */ if (full_len && size < full_len + 1 && klen > 3) { remainder = full_len - len; /* * We can only trim if we have space for the remainder * and also for at least "k+," which is 3 more characters. */ if (remainder <= space - 3) { /* * We are guaranteed to have 'k' in the buffer, so * we need at least 3 additional bytes for storing * "+," in addition to the remainder. */ for (int i = size - 1 - remainder - 3; i >= 0; i--) { if (buf[i] == 'k' || buf[i] == ',') { strcpy(buf + i + 1, "+,"); len = i + 3; /* Not counting '\0' */ break; } } } } len += input_print_modalias_bits(buf + len, size - len, 'r', id->relbit, 0, REL_MAX); len += input_print_modalias_bits(buf + len, size - len, 'a', id->absbit, 0, ABS_MAX); len += input_print_modalias_bits(buf + len, size - len, 'm', id->mscbit, 0, MSC_MAX); len += input_print_modalias_bits(buf + len, size - len, 'l', id->ledbit, 0, LED_MAX); len += input_print_modalias_bits(buf + len, size - len, 's', id->sndbit, 0, SND_MAX); len += input_print_modalias_bits(buf + len, size - len, 'f', id->ffbit, 0, FF_MAX); len += input_print_modalias_bits(buf + len, size - len, 'w', id->swbit, 0, SW_MAX); return len; } static int input_print_modalias(char *buf, int size, const struct input_dev *id) { int full_len; /* * Printing is done in 2 passes: first one figures out total length * needed for the modalias string, second one will try to trim key * data in case when buffer is too small for the entire modalias. * If the buffer is too small regardless, it will fill as much as it * can (without trimming key data) into the buffer and leave it to * the caller to figure out what to do with the result. */ full_len = input_print_modalias_parts(NULL, 0, 0, id); return input_print_modalias_parts(buf, size, full_len, id); } static ssize_t input_dev_show_modalias(struct device *dev, struct device_attribute *attr, char *buf) { struct input_dev *id = to_input_dev(dev); ssize_t len; len = input_print_modalias(buf, PAGE_SIZE, id); if (len < PAGE_SIZE - 2) len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return min_t(int, len, PAGE_SIZE); } static DEVICE_ATTR(modalias, S_IRUGO, input_dev_show_modalias, NULL); static int input_print_bitmap(char *buf, int buf_size, const unsigned long *bitmap, int max, int add_cr); static ssize_t input_dev_show_properties(struct device *dev, struct device_attribute *attr, char *buf) { struct input_dev *input_dev = to_input_dev(dev); int len = input_print_bitmap(buf, PAGE_SIZE, input_dev->propbit, INPUT_PROP_MAX, true); return min_t(int, len, PAGE_SIZE); } static DEVICE_ATTR(properties, S_IRUGO, input_dev_show_properties, NULL); static int input_inhibit_device(struct input_dev *dev); static int input_uninhibit_device(struct input_dev *dev); static ssize_t inhibited_show(struct device *dev, struct device_attribute *attr, char *buf) { struct input_dev *input_dev = to_input_dev(dev); return sysfs_emit(buf, "%d\n", input_dev->inhibited); } static ssize_t inhibited_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct input_dev *input_dev = to_input_dev(dev); ssize_t rv; bool inhibited; if (kstrtobool(buf, &inhibited)) return -EINVAL; if (inhibited) rv = input_inhibit_device(input_dev); else rv = input_uninhibit_device(input_dev); if (rv != 0) return rv; return len; } static DEVICE_ATTR_RW(inhibited); static struct attribute *input_dev_attrs[] = { &dev_attr_name.attr, &dev_attr_phys.attr, &dev_attr_uniq.attr, &dev_attr_modalias.attr, &dev_attr_properties.attr, &dev_attr_inhibited.attr, NULL }; static const struct attribute_group input_dev_attr_group = { .attrs = input_dev_attrs, }; #define INPUT_DEV_ID_ATTR(name) \ static ssize_t input_dev_show_id_##name(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ struct input_dev *input_dev = to_input_dev(dev); \ return sysfs_emit(buf, "%04x\n", input_dev->id.name); \ } \ static DEVICE_ATTR(name, S_IRUGO, input_dev_show_id_##name, NULL) INPUT_DEV_ID_ATTR(bustype); INPUT_DEV_ID_ATTR(vendor); INPUT_DEV_ID_ATTR(product); INPUT_DEV_ID_ATTR(version); static struct attribute *input_dev_id_attrs[] = { &dev_attr_bustype.attr, &dev_attr_vendor.attr, &dev_attr_product.attr, &dev_attr_version.attr, NULL }; static const struct attribute_group input_dev_id_attr_group = { .name = "id", .attrs = input_dev_id_attrs, }; static int input_print_bitmap(char *buf, int buf_size, const unsigned long *bitmap, int max, int add_cr) { int i; int len = 0; bool skip_empty = true; for (i = BITS_TO_LONGS(max) - 1; i >= 0; i--) { len += input_bits_to_string(buf + len, max(buf_size - len, 0), bitmap[i], skip_empty); if (len) { skip_empty = false; if (i > 0) len += snprintf(buf + len, max(buf_size - len, 0), " "); } } /* * If no output was produced print a single 0. */ if (len == 0) len = snprintf(buf, buf_size, "%d", 0); if (add_cr) len += snprintf(buf + len, max(buf_size - len, 0), "\n"); return len; } #define INPUT_DEV_CAP_ATTR(ev, bm) \ static ssize_t input_dev_show_cap_##bm(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ struct input_dev *input_dev = to_input_dev(dev); \ int len = input_print_bitmap(buf, PAGE_SIZE, \ input_dev->bm##bit, ev##_MAX, \ true); \ return min_t(int, len, PAGE_SIZE); \ } \ static DEVICE_ATTR(bm, S_IRUGO, input_dev_show_cap_##bm, NULL) INPUT_DEV_CAP_ATTR(EV, ev); INPUT_DEV_CAP_ATTR(KEY, key); INPUT_DEV_CAP_ATTR(REL, rel); INPUT_DEV_CAP_ATTR(ABS, abs); INPUT_DEV_CAP_ATTR(MSC, msc); INPUT_DEV_CAP_ATTR(LED, led); INPUT_DEV_CAP_ATTR(SND, snd); INPUT_DEV_CAP_ATTR(FF, ff); INPUT_DEV_CAP_ATTR(SW, sw); static struct attribute *input_dev_caps_attrs[] = { &dev_attr_ev.attr, &dev_attr_key.attr, &dev_attr_rel.attr, &dev_attr_abs.attr, &dev_attr_msc.attr, &dev_attr_led.attr, &dev_attr_snd.attr, &dev_attr_ff.attr, &dev_attr_sw.attr, NULL }; static const struct attribute_group input_dev_caps_attr_group = { .name = "capabilities", .attrs = input_dev_caps_attrs, }; static const struct attribute_group *input_dev_attr_groups[] = { &input_dev_attr_group, &input_dev_id_attr_group, &input_dev_caps_attr_group, &input_poller_attribute_group, NULL }; static void input_dev_release(struct device *device) { struct input_dev *dev = to_input_dev(device); input_ff_destroy(dev); input_mt_destroy_slots(dev); kfree(dev->poller); kfree(dev->absinfo); kfree(dev->vals); kfree(dev); module_put(THIS_MODULE); } /* * Input uevent interface - loading event handlers based on * device bitfields. */ static int input_add_uevent_bm_var(struct kobj_uevent_env *env, const char *name, const unsigned long *bitmap, int max) { int len; if (add_uevent_var(env, "%s", name)) return -ENOMEM; len = input_print_bitmap(&env->buf[env->buflen - 1], sizeof(env->buf) - env->buflen, bitmap, max, false); if (len >= (sizeof(env->buf) - env->buflen)) return -ENOMEM; env->buflen += len; return 0; } /* * This is a pretty gross hack. When building uevent data the driver core * may try adding more environment variables to kobj_uevent_env without * telling us, so we have no idea how much of the buffer we can use to * avoid overflows/-ENOMEM elsewhere. To work around this let's artificially * reduce amount of memory we will use for the modalias environment variable. * * The potential additions are: * * SEQNUM=18446744073709551615 - (%llu - 28 bytes) * HOME=/ (6 bytes) * PATH=/sbin:/bin:/usr/sbin:/usr/bin (34 bytes) * * 68 bytes total. Allow extra buffer - 96 bytes */ #define UEVENT_ENV_EXTRA_LEN 96 static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, const struct input_dev *dev) { int len; if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; len = input_print_modalias(&env->buf[env->buflen - 1], (int)sizeof(env->buf) - env->buflen - UEVENT_ENV_EXTRA_LEN, dev); if (len >= ((int)sizeof(env->buf) - env->buflen - UEVENT_ENV_EXTRA_LEN)) return -ENOMEM; env->buflen += len; return 0; } #define INPUT_ADD_HOTPLUG_VAR(fmt, val...) \ do { \ int err = add_uevent_var(env, fmt, val); \ if (err) \ return err; \ } while (0) #define INPUT_ADD_HOTPLUG_BM_VAR(name, bm, max) \ do { \ int err = input_add_uevent_bm_var(env, name, bm, max); \ if (err) \ return err; \ } while (0) #define INPUT_ADD_HOTPLUG_MODALIAS_VAR(dev) \ do { \ int err = input_add_uevent_modalias_var(env, dev); \ if (err) \ return err; \ } while (0) static int input_dev_uevent(const struct device *device, struct kobj_uevent_env *env) { const struct input_dev *dev = to_input_dev(device); INPUT_ADD_HOTPLUG_VAR("PRODUCT=%x/%x/%x/%x", dev->id.bustype, dev->id.vendor, dev->id.product, dev->id.version); if (dev->name) INPUT_ADD_HOTPLUG_VAR("NAME=\"%s\"", dev->name); if (dev->phys) INPUT_ADD_HOTPLUG_VAR("PHYS=\"%s\"", dev->phys); if (dev->uniq) INPUT_ADD_HOTPLUG_VAR("UNIQ=\"%s\"", dev->uniq); INPUT_ADD_HOTPLUG_BM_VAR("PROP=", dev->propbit, INPUT_PROP_MAX); INPUT_ADD_HOTPLUG_BM_VAR("EV=", dev->evbit, EV_MAX); if (test_bit(EV_KEY, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("KEY=", dev->keybit, KEY_MAX); if (test_bit(EV_REL, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("REL=", dev->relbit, REL_MAX); if (test_bit(EV_ABS, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("ABS=", dev->absbit, ABS_MAX); if (test_bit(EV_MSC, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("MSC=", dev->mscbit, MSC_MAX); if (test_bit(EV_LED, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("LED=", dev->ledbit, LED_MAX); if (test_bit(EV_SND, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("SND=", dev->sndbit, SND_MAX); if (test_bit(EV_FF, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("FF=", dev->ffbit, FF_MAX); if (test_bit(EV_SW, dev->evbit)) INPUT_ADD_HOTPLUG_BM_VAR("SW=", dev->swbit, SW_MAX); INPUT_ADD_HOTPLUG_MODALIAS_VAR(dev); return 0; } #define INPUT_DO_TOGGLE(dev, type, bits, on) \ do { \ int i; \ bool active; \ \ if (!test_bit(EV_##type, dev->evbit)) \ break; \ \ for_each_set_bit(i, dev->bits##bit, type##_CNT) { \ active = test_bit(i, dev->bits); \ if (!active && !on) \ continue; \ \ dev->event(dev, EV_##type, i, on ? active : 0); \ } \ } while (0) static void input_dev_toggle(struct input_dev *dev, bool activate) { if (!dev->event) return; INPUT_DO_TOGGLE(dev, LED, led, activate); INPUT_DO_TOGGLE(dev, SND, snd, activate); if (activate && test_bit(EV_REP, dev->evbit)) { dev->event(dev, EV_REP, REP_PERIOD, dev->rep[REP_PERIOD]); dev->event(dev, EV_REP, REP_DELAY, dev->rep[REP_DELAY]); } } /** * input_reset_device() - reset/restore the state of input device * @dev: input device whose state needs to be reset * * This function tries to reset the state of an opened input device and * bring internal state and state if the hardware in sync with each other. * We mark all keys as released, restore LED state, repeat rate, etc. */ void input_reset_device(struct input_dev *dev) { guard(mutex)(&dev->mutex); guard(spinlock_irqsave)(&dev->event_lock); input_dev_toggle(dev, true); if (input_dev_release_keys(dev)) input_handle_event(dev, EV_SYN, SYN_REPORT, 1); } EXPORT_SYMBOL(input_reset_device); static int input_inhibit_device(struct input_dev *dev) { guard(mutex)(&dev->mutex); if (dev->inhibited) return 0; if (dev->users) { if (dev->close) dev->close(dev); if (dev->poller) input_dev_poller_stop(dev->poller); } scoped_guard(spinlock_irq, &dev->event_lock) { input_mt_release_slots(dev); input_dev_release_keys(dev); input_handle_event(dev, EV_SYN, SYN_REPORT, 1); input_dev_toggle(dev, false); } dev->inhibited = true; return 0; } static int input_uninhibit_device(struct input_dev *dev) { int error; guard(mutex)(&dev->mutex); if (!dev->inhibited) return 0; if (dev->users) { if (dev->open) { error = dev->open(dev); if (error) return error; } if (dev->poller) input_dev_poller_start(dev->poller); } dev->inhibited = false; scoped_guard(spinlock_irq, &dev->event_lock) input_dev_toggle(dev, true); return 0; } static int input_dev_suspend(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); guard(spinlock_irq)(&input_dev->event_lock); /* * Keys that are pressed now are unlikely to be * still pressed when we resume. */ if (input_dev_release_keys(input_dev)) input_handle_event(input_dev, EV_SYN, SYN_REPORT, 1); /* Turn off LEDs and sounds, if any are active. */ input_dev_toggle(input_dev, false); return 0; } static int input_dev_resume(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); guard(spinlock_irq)(&input_dev->event_lock); /* Restore state of LEDs and sounds, if any were active. */ input_dev_toggle(input_dev, true); return 0; } static int input_dev_freeze(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); guard(spinlock_irq)(&input_dev->event_lock); /* * Keys that are pressed now are unlikely to be * still pressed when we resume. */ if (input_dev_release_keys(input_dev)) input_handle_event(input_dev, EV_SYN, SYN_REPORT, 1); return 0; } static int input_dev_poweroff(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); guard(spinlock_irq)(&input_dev->event_lock); /* Turn off LEDs and sounds, if any are active. */ input_dev_toggle(input_dev, false); return 0; } static const struct dev_pm_ops input_dev_pm_ops = { .suspend = input_dev_suspend, .resume = input_dev_resume, .freeze = input_dev_freeze, .poweroff = input_dev_poweroff, .restore = input_dev_resume, }; static const struct device_type input_dev_type = { .groups = input_dev_attr_groups, .release = input_dev_release, .uevent = input_dev_uevent, .pm = pm_sleep_ptr(&input_dev_pm_ops), }; static char *input_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "input/%s", dev_name(dev)); } const struct class input_class = { .name = "input", .devnode = input_devnode, }; EXPORT_SYMBOL_GPL(input_class); /** * input_allocate_device - allocate memory for new input device * * Returns prepared struct input_dev or %NULL. * * NOTE: Use input_free_device() to free devices that have not been * registered; input_unregister_device() should be used for already * registered devices. */ struct input_dev *input_allocate_device(void) { static atomic_t input_no = ATOMIC_INIT(-1); struct input_dev *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; /* * Start with space for SYN_REPORT + 7 EV_KEY/EV_MSC events + 2 spare, * see input_estimate_events_per_packet(). We will tune the number * when we register the device. */ dev->max_vals = 10; dev->vals = kcalloc(dev->max_vals, sizeof(*dev->vals), GFP_KERNEL); if (!dev->vals) { kfree(dev); return NULL; } mutex_init(&dev->mutex); spin_lock_init(&dev->event_lock); timer_setup(&dev->timer, NULL, 0); INIT_LIST_HEAD(&dev->h_list); INIT_LIST_HEAD(&dev->node); dev->dev.type = &input_dev_type; dev->dev.class = &input_class; device_initialize(&dev->dev); /* * From this point on we can no longer simply "kfree(dev)", we need * to use input_free_device() so that device core properly frees its * resources associated with the input device. */ dev_set_name(&dev->dev, "input%lu", (unsigned long)atomic_inc_return(&input_no)); __module_get(THIS_MODULE); return dev; } EXPORT_SYMBOL(input_allocate_device); struct input_devres { struct input_dev *input; }; static int devm_input_device_match(struct device *dev, void *res, void *data) { struct input_devres *devres = res; return devres->input == data; } static void devm_input_device_release(struct device *dev, void *res) { struct input_devres *devres = res; struct input_dev *input = devres->input; dev_dbg(dev, "%s: dropping reference to %s\n", __func__, dev_name(&input->dev)); input_put_device(input); } /** * devm_input_allocate_device - allocate managed input device * @dev: device owning the input device being created * * Returns prepared struct input_dev or %NULL. * * Managed input devices do not need to be explicitly unregistered or * freed as it will be done automatically when owner device unbinds from * its driver (or binding fails). Once managed input device is allocated, * it is ready to be set up and registered in the same fashion as regular * input device. There are no special devm_input_device_[un]register() * variants, regular ones work with both managed and unmanaged devices, * should you need them. In most cases however, managed input device need * not be explicitly unregistered or freed. * * NOTE: the owner device is set up as parent of input device and users * should not override it. */ struct input_dev *devm_input_allocate_device(struct device *dev) { struct input_dev *input; struct input_devres *devres; devres = devres_alloc(devm_input_device_release, sizeof(*devres), GFP_KERNEL); if (!devres) return NULL; input = input_allocate_device(); if (!input) { devres_free(devres); return NULL; } input->dev.parent = dev; input->devres_managed = true; devres->input = input; devres_add(dev, devres); return input; } EXPORT_SYMBOL(devm_input_allocate_device); /** * input_free_device - free memory occupied by input_dev structure * @dev: input device to free * * This function should only be used if input_register_device() * was not called yet or if it failed. Once device was registered * use input_unregister_device() and memory will be freed once last * reference to the device is dropped. * * Device should be allocated by input_allocate_device(). * * NOTE: If there are references to the input device then memory * will not be freed until last reference is dropped. */ void input_free_device(struct input_dev *dev) { if (dev) { if (dev->devres_managed) WARN_ON(devres_destroy(dev->dev.parent, devm_input_device_release, devm_input_device_match, dev)); input_put_device(dev); } } EXPORT_SYMBOL(input_free_device); /** * input_set_timestamp - set timestamp for input events * @dev: input device to set timestamp for * @timestamp: the time at which the event has occurred * in CLOCK_MONOTONIC * * This function is intended to provide to the input system a more * accurate time of when an event actually occurred. The driver should * call this function as soon as a timestamp is acquired ensuring * clock conversions in input_set_timestamp are done correctly. * * The system entering suspend state between timestamp acquisition and * calling input_set_timestamp can result in inaccurate conversions. */ void input_set_timestamp(struct input_dev *dev, ktime_t timestamp) { dev->timestamp[INPUT_CLK_MONO] = timestamp; dev->timestamp[INPUT_CLK_REAL] = ktime_mono_to_real(timestamp); dev->timestamp[INPUT_CLK_BOOT] = ktime_mono_to_any(timestamp, TK_OFFS_BOOT); } EXPORT_SYMBOL(input_set_timestamp); /** * input_get_timestamp - get timestamp for input events * @dev: input device to get timestamp from * * A valid timestamp is a timestamp of non-zero value. */ ktime_t *input_get_timestamp(struct input_dev *dev) { const ktime_t invalid_timestamp = ktime_set(0, 0); if (!ktime_compare(dev->timestamp[INPUT_CLK_MONO], invalid_timestamp)) input_set_timestamp(dev, ktime_get()); return dev->timestamp; } EXPORT_SYMBOL(input_get_timestamp); /** * input_set_capability - mark device as capable of a certain event * @dev: device that is capable of emitting or accepting event * @type: type of the event (EV_KEY, EV_REL, etc...) * @code: event code * * In addition to setting up corresponding bit in appropriate capability * bitmap the function also adjusts dev->evbit. */ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code) { if (type < EV_CNT && input_max_code[type] && code > input_max_code[type]) { pr_err("%s: invalid code %u for type %u\n", __func__, code, type); dump_stack(); return; } switch (type) { case EV_KEY: __set_bit(code, dev->keybit); break; case EV_REL: __set_bit(code, dev->relbit); break; case EV_ABS: input_alloc_absinfo(dev); __set_bit(code, dev->absbit); break; case EV_MSC: __set_bit(code, dev->mscbit); break; case EV_SW: __set_bit(code, dev->swbit); break; case EV_LED: __set_bit(code, dev->ledbit); break; case EV_SND: __set_bit(code, dev->sndbit); break; case EV_FF: __set_bit(code, dev->ffbit); break; case EV_PWR: /* do nothing */ break; default: pr_err("%s: unknown type %u (code %u)\n", __func__, type, code); dump_stack(); return; } __set_bit(type, dev->evbit); } EXPORT_SYMBOL(input_set_capability); static unsigned int input_estimate_events_per_packet(struct input_dev *dev) { int mt_slots; int i; unsigned int events; if (dev->mt) { mt_slots = dev->mt->num_slots; } else if (test_bit(ABS_MT_TRACKING_ID, dev->absbit)) { mt_slots = dev->absinfo[ABS_MT_TRACKING_ID].maximum - dev->absinfo[ABS_MT_TRACKING_ID].minimum + 1; mt_slots = clamp(mt_slots, 2, 32); } else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) { mt_slots = 2; } else { mt_slots = 0; } events = mt_slots + 1; /* count SYN_MT_REPORT and SYN_REPORT */ if (test_bit(EV_ABS, dev->evbit)) for_each_set_bit(i, dev->absbit, ABS_CNT) events += input_is_mt_axis(i) ? mt_slots : 1; if (test_bit(EV_REL, dev->evbit)) events += bitmap_weight(dev->relbit, REL_CNT); /* Make room for KEY and MSC events */ events += 7; return events; } #define INPUT_CLEANSE_BITMASK(dev, type, bits) \ do { \ if (!test_bit(EV_##type, dev->evbit)) \ memset(dev->bits##bit, 0, \ sizeof(dev->bits##bit)); \ } while (0) static void input_cleanse_bitmasks(struct input_dev *dev) { INPUT_CLEANSE_BITMASK(dev, KEY, key); INPUT_CLEANSE_BITMASK(dev, REL, rel); INPUT_CLEANSE_BITMASK(dev, ABS, abs); INPUT_CLEANSE_BITMASK(dev, MSC, msc); INPUT_CLEANSE_BITMASK(dev, LED, led); INPUT_CLEANSE_BITMASK(dev, SND, snd); INPUT_CLEANSE_BITMASK(dev, FF, ff); INPUT_CLEANSE_BITMASK(dev, SW, sw); } static void __input_unregister_device(struct input_dev *dev) { struct input_handle *handle, *next; input_disconnect_device(dev); scoped_guard(mutex, &input_mutex) { list_for_each_entry_safe(handle, next, &dev->h_list, d_node) handle->handler->disconnect(handle); WARN_ON(!list_empty(&dev->h_list)); timer_delete_sync(&dev->timer); list_del_init(&dev->node); input_wakeup_procfs_readers(); } device_del(&dev->dev); } static void devm_input_device_unregister(struct device *dev, void *res) { struct input_devres *devres = res; struct input_dev *input = devres->input; dev_dbg(dev, "%s: unregistering device %s\n", __func__, dev_name(&input->dev)); __input_unregister_device(input); } /* * Generate software autorepeat event. Note that we take * dev->event_lock here to avoid racing with input_event * which may cause keys get "stuck". */ static void input_repeat_key(struct timer_list *t) { struct input_dev *dev = timer_container_of(dev, t, timer); guard(spinlock_irqsave)(&dev->event_lock); if (!dev->inhibited && test_bit(dev->repeat_key, dev->key) && is_event_supported(dev->repeat_key, dev->keybit, KEY_MAX)) { input_set_timestamp(dev, ktime_get()); input_handle_event(dev, EV_KEY, dev->repeat_key, 2); input_handle_event(dev, EV_SYN, SYN_REPORT, 1); if (dev->rep[REP_PERIOD]) mod_timer(&dev->timer, jiffies + msecs_to_jiffies(dev->rep[REP_PERIOD])); } } /** * input_enable_softrepeat - enable software autorepeat * @dev: input device * @delay: repeat delay * @period: repeat period * * Enable software autorepeat on the input device. */ void input_enable_softrepeat(struct input_dev *dev, int delay, int period) { dev->timer.function = input_repeat_key; dev->rep[REP_DELAY] = delay; dev->rep[REP_PERIOD] = period; } EXPORT_SYMBOL(input_enable_softrepeat); bool input_device_enabled(struct input_dev *dev) { lockdep_assert_held(&dev->mutex); return !dev->inhibited && dev->users > 0; } EXPORT_SYMBOL_GPL(input_device_enabled); static int input_device_tune_vals(struct input_dev *dev) { struct input_value *vals; unsigned int packet_size; unsigned int max_vals; packet_size = input_estimate_events_per_packet(dev); if (dev->hint_events_per_packet < packet_size) dev->hint_events_per_packet = packet_size; max_vals = dev->hint_events_per_packet + 2; if (dev->max_vals >= max_vals) return 0; vals = kcalloc(max_vals, sizeof(*vals), GFP_KERNEL); if (!vals) return -ENOMEM; scoped_guard(spinlock_irq, &dev->event_lock) { dev->max_vals = max_vals; swap(dev->vals, vals); } /* Because of swap() above, this frees the old vals memory */ kfree(vals); return 0; } /** * input_register_device - register device with input core * @dev: device to be registered * * This function registers device with input core. The device must be * allocated with input_allocate_device() and all it's capabilities * set up before registering. * If function fails the device must be freed with input_free_device(). * Once device has been successfully registered it can be unregistered * with input_unregister_device(); input_free_device() should not be * called in this case. * * Note that this function is also used to register managed input devices * (ones allocated with devm_input_allocate_device()). Such managed input * devices need not be explicitly unregistered or freed, their tear down * is controlled by the devres infrastructure. It is also worth noting * that tear down of managed input devices is internally a 2-step process: * registered managed input device is first unregistered, but stays in * memory and can still handle input_event() calls (although events will * not be delivered anywhere). The freeing of managed input device will * happen later, when devres stack is unwound to the point where device * allocation was made. */ int input_register_device(struct input_dev *dev) { struct input_devres *devres = NULL; struct input_handler *handler; const char *path; int error; if (test_bit(EV_ABS, dev->evbit) && !dev->absinfo) { dev_err(&dev->dev, "Absolute device without dev->absinfo, refusing to register\n"); return -EINVAL; } if (dev->devres_managed) { devres = devres_alloc(devm_input_device_unregister, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; devres->input = dev; } /* Every input device generates EV_SYN/SYN_REPORT events. */ __set_bit(EV_SYN, dev->evbit); /* KEY_RESERVED is not supposed to be transmitted to userspace. */ __clear_bit(KEY_RESERVED, dev->keybit); /* Make sure that bitmasks not mentioned in dev->evbit are clean. */ input_cleanse_bitmasks(dev); error = input_device_tune_vals(dev); if (error) goto err_devres_free; /* * If delay and period are pre-set by the driver, then autorepeating * is handled by the driver itself and we don't do it in input.c. */ if (!dev->rep[REP_DELAY] && !dev->rep[REP_PERIOD]) input_enable_softrepeat(dev, 250, 33); if (!dev->getkeycode) dev->getkeycode = input_default_getkeycode; if (!dev->setkeycode) dev->setkeycode = input_default_setkeycode; if (dev->poller) input_dev_poller_finalize(dev->poller); error = device_add(&dev->dev); if (error) goto err_devres_free; path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); pr_info("%s as %s\n", dev->name ? dev->name : "Unspecified device", path ? path : "N/A"); kfree(path); error = -EINTR; scoped_cond_guard(mutex_intr, goto err_device_del, &input_mutex) { list_add_tail(&dev->node, &input_dev_list); list_for_each_entry(handler, &input_handler_list, node) input_attach_handler(dev, handler); input_wakeup_procfs_readers(); } if (dev->devres_managed) { dev_dbg(dev->dev.parent, "%s: registering %s with devres.\n", __func__, dev_name(&dev->dev)); devres_add(dev->dev.parent, devres); } return 0; err_device_del: device_del(&dev->dev); err_devres_free: devres_free(devres); return error; } EXPORT_SYMBOL(input_register_device); /** * input_unregister_device - unregister previously registered device * @dev: device to be unregistered * * This function unregisters an input device. Once device is unregistered * the caller should not try to access it as it may get freed at any moment. */ void input_unregister_device(struct input_dev *dev) { if (dev->devres_managed) { WARN_ON(devres_destroy(dev->dev.parent, devm_input_device_unregister, devm_input_device_match, dev)); __input_unregister_device(dev); /* * We do not do input_put_device() here because it will be done * when 2nd devres fires up. */ } else { __input_unregister_device(dev); input_put_device(dev); } } EXPORT_SYMBOL(input_unregister_device); static int input_handler_check_methods(const struct input_handler *handler) { int count = 0; if (handler->filter) count++; if (handler->events) count++; if (handler->event) count++; if (count > 1) { pr_err("%s: only one event processing method can be defined (%s)\n", __func__, handler->name); return -EINVAL; } return 0; } /** * input_register_handler - register a new input handler * @handler: handler to be registered * * This function registers a new input handler (interface) for input * devices in the system and attaches it to all input devices that * are compatible with the handler. */ int input_register_handler(struct input_handler *handler) { struct input_dev *dev; int error; error = input_handler_check_methods(handler); if (error) return error; scoped_cond_guard(mutex_intr, return -EINTR, &input_mutex) { INIT_LIST_HEAD(&handler->h_list); list_add_tail(&handler->node, &input_handler_list); list_for_each_entry(dev, &input_dev_list, node) input_attach_handler(dev, handler); input_wakeup_procfs_readers(); } return 0; } EXPORT_SYMBOL(input_register_handler); /** * input_unregister_handler - unregisters an input handler * @handler: handler to be unregistered * * This function disconnects a handler from its input devices and * removes it from lists of known handlers. */ void input_unregister_handler(struct input_handler *handler) { struct input_handle *handle, *next; guard(mutex)(&input_mutex); list_for_each_entry_safe(handle, next, &handler->h_list, h_node) handler->disconnect(handle); WARN_ON(!list_empty(&handler->h_list)); list_del_init(&handler->node); input_wakeup_procfs_readers(); } EXPORT_SYMBOL(input_unregister_handler); /** * input_handler_for_each_handle - handle iterator * @handler: input handler to iterate * @data: data for the callback * @fn: function to be called for each handle * * Iterate over @bus's list of devices, and call @fn for each, passing * it @data and stop when @fn returns a non-zero value. The function is * using RCU to traverse the list and therefore may be using in atomic * contexts. The @fn callback is invoked from RCU critical section and * thus must not sleep. */ int input_handler_for_each_handle(struct input_handler *handler, void *data, int (*fn)(struct input_handle *, void *)) { struct input_handle *handle; int retval; guard(rcu)(); list_for_each_entry_rcu(handle, &handler->h_list, h_node) { retval = fn(handle, data); if (retval) return retval; } return 0; } EXPORT_SYMBOL(input_handler_for_each_handle); /* * An implementation of input_handle's handle_events() method that simply * invokes handler->event() method for each event one by one. */ static unsigned int input_handle_events_default(struct input_handle *handle, struct input_value *vals, unsigned int count) { struct input_handler *handler = handle->handler; struct input_value *v; for (v = vals; v != vals + count; v++) handler->event(handle, v->type, v->code, v->value); return count; } /* * An implementation of input_handle's handle_events() method that invokes * handler->filter() method for each event one by one and removes events * that were filtered out from the "vals" array. */ static unsigned int input_handle_events_filter(struct input_handle *handle, struct input_value *vals, unsigned int count) { struct input_handler *handler = handle->handler; struct input_value *end = vals; struct input_value *v; for (v = vals; v != vals + count; v++) { if (handler->filter(handle, v->type, v->code, v->value)) continue; if (end != v) *end = *v; end++; } return end - vals; } /* * An implementation of input_handle's handle_events() method that does nothing. */ static unsigned int input_handle_events_null(struct input_handle *handle, struct input_value *vals, unsigned int count) { return count; } /* * Sets up appropriate handle->event_handler based on the input_handler * associated with the handle. */ static void input_handle_setup_event_handler(struct input_handle *handle) { struct input_handler *handler = handle->handler; if (handler->filter) handle->handle_events = input_handle_events_filter; else if (handler->event) handle->handle_events = input_handle_events_default; else if (handler->events) handle->handle_events = handler->events; else handle->handle_events = input_handle_events_null; } /** * input_register_handle - register a new input handle * @handle: handle to register * * This function puts a new input handle onto device's * and handler's lists so that events can flow through * it once it is opened using input_open_device(). * * This function is supposed to be called from handler's * connect() method. */ int input_register_handle(struct input_handle *handle) { struct input_handler *handler = handle->handler; struct input_dev *dev = handle->dev; input_handle_setup_event_handler(handle); /* * We take dev->mutex here to prevent race with * input_release_device(). */ scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { /* * Filters go to the head of the list, normal handlers * to the tail. */ if (handler->filter) list_add_rcu(&handle->d_node, &dev->h_list); else list_add_tail_rcu(&handle->d_node, &dev->h_list); } /* * Since we are supposed to be called from ->connect() * which is mutually exclusive with ->disconnect() * we can't be racing with input_unregister_handle() * and so separate lock is not needed here. */ list_add_tail_rcu(&handle->h_node, &handler->h_list); if (handler->start) handler->start(handle); return 0; } EXPORT_SYMBOL(input_register_handle); /** * input_unregister_handle - unregister an input handle * @handle: handle to unregister * * This function removes input handle from device's * and handler's lists. * * This function is supposed to be called from handler's * disconnect() method. */ void input_unregister_handle(struct input_handle *handle) { struct input_dev *dev = handle->dev; list_del_rcu(&handle->h_node); /* * Take dev->mutex to prevent race with input_release_device(). */ scoped_guard(mutex, &dev->mutex) list_del_rcu(&handle->d_node); synchronize_rcu(); } EXPORT_SYMBOL(input_unregister_handle); /** * input_get_new_minor - allocates a new input minor number * @legacy_base: beginning or the legacy range to be searched * @legacy_num: size of legacy range * @allow_dynamic: whether we can also take ID from the dynamic range * * This function allocates a new device minor for from input major namespace. * Caller can request legacy minor by specifying @legacy_base and @legacy_num * parameters and whether ID can be allocated from dynamic range if there are * no free IDs in legacy range. */ int input_get_new_minor(int legacy_base, unsigned int legacy_num, bool allow_dynamic) { /* * This function should be called from input handler's ->connect() * methods, which are serialized with input_mutex, so no additional * locking is needed here. */ if (legacy_base >= 0) { int minor = ida_alloc_range(&input_ida, legacy_base, legacy_base + legacy_num - 1, GFP_KERNEL); if (minor >= 0 || !allow_dynamic) return minor; } return ida_alloc_range(&input_ida, INPUT_FIRST_DYNAMIC_DEV, INPUT_MAX_CHAR_DEVICES - 1, GFP_KERNEL); } EXPORT_SYMBOL(input_get_new_minor); /** * input_free_minor - release previously allocated minor * @minor: minor to be released * * This function releases previously allocated input minor so that it can be * reused later. */ void input_free_minor(unsigned int minor) { ida_free(&input_ida, minor); } EXPORT_SYMBOL(input_free_minor); static int __init input_init(void) { int err; err = class_register(&input_class); if (err) { pr_err("unable to register input_dev class\n"); return err; } err = input_proc_init(); if (err) goto fail1; err = register_chrdev_region(MKDEV(INPUT_MAJOR, 0), INPUT_MAX_CHAR_DEVICES, "input"); if (err) { pr_err("unable to register char major %d", INPUT_MAJOR); goto fail2; } return 0; fail2: input_proc_exit(); fail1: class_unregister(&input_class); return err; } static void __exit input_exit(void) { input_proc_exit(); unregister_chrdev_region(MKDEV(INPUT_MAJOR, 0), INPUT_MAX_CHAR_DEVICES); class_unregister(&input_class); } subsys_initcall(input_init); module_exit(input_exit); |
| 856 3405 6203 180 3387 3579 112 241 60 312 3377 61 61 3209 6210 6203 3169 1999 770 1604 1996 1658 1662 1658 1655 823 825 1949 6194 1433 1435 1437 1 535 320 830 24 832 1866 39 258 252 21 241 255 255 3512 3511 1885 3368 535 60 565 60 1184 948 1006 1185 895 813 1026 1167 1 1 1 1 1 1169 1184 1185 1169 1167 67 12 5989 348 5958 12 13 5759 5776 3515 31 3293 3295 3293 3296 12 3291 1372 1331 493 112 181 181 181 179 181 180 181 3506 1877 3500 3384 3387 424 172 172 172 172 172 3293 12 12 13 13 13 3327 1395 1399 1384 1384 1339 181 288 279 61 61 227 285 260 274 281 281 287 287 241 61 287 419 420 413 154 154 61 60 1550 212 1373 1548 1564 1572 1540 1548 1551 240 154 155 1514 1515 3291 3288 3268 550 3299 20 1668 3281 3290 2888 3172 3169 3165 3171 3292 3293 33 32 1 492 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #include <linux/init.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/dma-mapping.h> #include <net/addrconf.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/rdma_netlink.h> #include <linux/kthread.h> #include "siw.h" #include "siw_verbs.h" MODULE_AUTHOR("Bernard Metzler"); MODULE_DESCRIPTION("Software iWARP Driver"); MODULE_LICENSE("Dual BSD/GPL"); /* transmit from user buffer, if possible */ const bool zcopy_tx = true; /* Restrict usage of GSO, if hardware peer iwarp is unable to process * large packets. try_gso = true lets siw try to use local GSO, * if peer agrees. Not using GSO severly limits siw maximum tx bandwidth. */ const bool try_gso; /* Attach siw also with loopback devices */ const bool loopback_enabled = true; /* We try to negotiate CRC on, if true */ const bool mpa_crc_required; /* MPA CRC on/off enforced */ const bool mpa_crc_strict; /* Control TCP_NODELAY socket option */ const bool siw_tcp_nagle; /* Select MPA version to be used during connection setup */ u_char mpa_version = MPA_REVISION_2; /* Selects MPA P2P mode (additional handshake during connection * setup, if true. */ const bool peer_to_peer; struct task_struct *siw_tx_thread[NR_CPUS]; static int siw_device_register(struct siw_device *sdev, const char *name) { struct ib_device *base_dev = &sdev->base_dev; static int dev_id = 1; int rv; sdev->vendor_part_id = dev_id++; rv = ib_register_device(base_dev, name, NULL); if (rv) { pr_warn("siw: device registration error %d\n", rv); return rv; } siw_dbg(base_dev, "HWaddr=%pM\n", sdev->raw_gid); return 0; } static void siw_device_cleanup(struct ib_device *base_dev) { struct siw_device *sdev = to_siw_dev(base_dev); xa_destroy(&sdev->qp_xa); xa_destroy(&sdev->mem_xa); } static int siw_dev_qualified(struct net_device *netdev) { /* * Additional hardware support can be added here * (e.g. ARPHRD_FDDI, ARPHRD_ATM, ...) - see * <linux/if_arp.h> for type identifiers. */ if (netdev->type == ARPHRD_ETHER || netdev->type == ARPHRD_IEEE802 || netdev->type == ARPHRD_NONE || (netdev->type == ARPHRD_LOOPBACK && loopback_enabled)) return 1; return 0; } static DEFINE_PER_CPU(atomic_t, siw_use_cnt); static struct { struct cpumask **tx_valid_cpus; int num_nodes; } siw_cpu_info; static void siw_destroy_cpulist(int number) { int i = 0; while (i < number) kfree(siw_cpu_info.tx_valid_cpus[i++]); kfree(siw_cpu_info.tx_valid_cpus); siw_cpu_info.tx_valid_cpus = NULL; } static int siw_init_cpulist(void) { int i, num_nodes = nr_node_ids; memset(siw_tx_thread, 0, sizeof(siw_tx_thread)); siw_cpu_info.num_nodes = num_nodes; siw_cpu_info.tx_valid_cpus = kcalloc(num_nodes, sizeof(struct cpumask *), GFP_KERNEL); if (!siw_cpu_info.tx_valid_cpus) { siw_cpu_info.num_nodes = 0; return -ENOMEM; } for (i = 0; i < siw_cpu_info.num_nodes; i++) { siw_cpu_info.tx_valid_cpus[i] = kzalloc(sizeof(struct cpumask), GFP_KERNEL); if (!siw_cpu_info.tx_valid_cpus[i]) goto out_err; cpumask_clear(siw_cpu_info.tx_valid_cpus[i]); } for_each_possible_cpu(i) cpumask_set_cpu(i, siw_cpu_info.tx_valid_cpus[cpu_to_node(i)]); return 0; out_err: siw_cpu_info.num_nodes = 0; siw_destroy_cpulist(i); return -ENOMEM; } /* * Choose CPU with least number of active QP's from NUMA node of * TX interface. */ int siw_get_tx_cpu(struct siw_device *sdev) { const struct cpumask *tx_cpumask; int i, num_cpus, cpu, min_use, node = sdev->numa_node, tx_cpu = -1; if (node < 0) tx_cpumask = cpu_online_mask; else tx_cpumask = siw_cpu_info.tx_valid_cpus[node]; num_cpus = cpumask_weight(tx_cpumask); if (!num_cpus) { /* no CPU on this NUMA node */ tx_cpumask = cpu_online_mask; num_cpus = cpumask_weight(tx_cpumask); } if (!num_cpus) goto out; cpu = cpumask_first(tx_cpumask); for (i = 0, min_use = SIW_MAX_QP; i < num_cpus; i++, cpu = cpumask_next(cpu, tx_cpumask)) { int usage; /* Skip any cores which have no TX thread */ if (!siw_tx_thread[cpu]) continue; usage = atomic_read(&per_cpu(siw_use_cnt, cpu)); if (usage <= min_use) { tx_cpu = cpu; min_use = usage; } } siw_dbg(&sdev->base_dev, "tx cpu %d, node %d, %d qp's\n", tx_cpu, node, min_use); out: if (tx_cpu >= 0) atomic_inc(&per_cpu(siw_use_cnt, tx_cpu)); else pr_warn("siw: no tx cpu found\n"); return tx_cpu; } void siw_put_tx_cpu(int cpu) { atomic_dec(&per_cpu(siw_use_cnt, cpu)); } static struct ib_qp *siw_get_base_qp(struct ib_device *base_dev, int id) { struct siw_qp *qp = siw_qp_id2obj(to_siw_dev(base_dev), id); if (qp) { /* * siw_qp_id2obj() increments object reference count */ siw_qp_put(qp); return &qp->base_qp; } return NULL; } static const struct ib_device_ops siw_device_ops = { .owner = THIS_MODULE, .uverbs_abi_ver = SIW_ABI_VERSION, .driver_id = RDMA_DRIVER_SIW, .alloc_mr = siw_alloc_mr, .alloc_pd = siw_alloc_pd, .alloc_ucontext = siw_alloc_ucontext, .create_cq = siw_create_cq, .create_qp = siw_create_qp, .create_srq = siw_create_srq, .dealloc_driver = siw_device_cleanup, .dealloc_pd = siw_dealloc_pd, .dealloc_ucontext = siw_dealloc_ucontext, .dereg_mr = siw_dereg_mr, .destroy_cq = siw_destroy_cq, .destroy_qp = siw_destroy_qp, .destroy_srq = siw_destroy_srq, .get_dma_mr = siw_get_dma_mr, .get_port_immutable = siw_get_port_immutable, .iw_accept = siw_accept, .iw_add_ref = siw_qp_get_ref, .iw_connect = siw_connect, .iw_create_listen = siw_create_listen, .iw_destroy_listen = siw_destroy_listen, .iw_get_qp = siw_get_base_qp, .iw_reject = siw_reject, .iw_rem_ref = siw_qp_put_ref, .map_mr_sg = siw_map_mr_sg, .mmap = siw_mmap, .mmap_free = siw_mmap_free, .modify_qp = siw_verbs_modify_qp, .modify_srq = siw_modify_srq, .poll_cq = siw_poll_cq, .post_recv = siw_post_receive, .post_send = siw_post_send, .post_srq_recv = siw_post_srq_recv, .query_device = siw_query_device, .query_gid = siw_query_gid, .query_port = siw_query_port, .query_qp = siw_query_qp, .query_srq = siw_query_srq, .req_notify_cq = siw_req_notify_cq, .reg_user_mr = siw_reg_user_mr, INIT_RDMA_OBJ_SIZE(ib_cq, siw_cq, base_cq), INIT_RDMA_OBJ_SIZE(ib_pd, siw_pd, base_pd), INIT_RDMA_OBJ_SIZE(ib_qp, siw_qp, base_qp), INIT_RDMA_OBJ_SIZE(ib_srq, siw_srq, base_srq), INIT_RDMA_OBJ_SIZE(ib_ucontext, siw_ucontext, base_ucontext), }; static struct siw_device *siw_device_create(struct net_device *netdev) { struct siw_device *sdev = NULL; struct ib_device *base_dev; int rv; sdev = ib_alloc_device(siw_device, base_dev); if (!sdev) return NULL; base_dev = &sdev->base_dev; if (netdev->addr_len) { memcpy(sdev->raw_gid, netdev->dev_addr, min_t(unsigned int, netdev->addr_len, ETH_ALEN)); } else { /* * This device does not have a HW address, but * connection mangagement requires a unique gid. */ eth_random_addr(sdev->raw_gid); } addrconf_addr_eui48((u8 *)&base_dev->node_guid, sdev->raw_gid); base_dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND); base_dev->node_type = RDMA_NODE_RNIC; memcpy(base_dev->node_desc, SIW_NODE_DESC_COMMON, sizeof(SIW_NODE_DESC_COMMON)); /* * Current model (one-to-one device association): * One Softiwarp device per net_device or, equivalently, * per physical port. */ base_dev->phys_port_cnt = 1; base_dev->num_comp_vectors = num_possible_cpus(); xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1); ib_set_device_ops(base_dev, &siw_device_ops); rv = ib_device_set_netdev(base_dev, netdev, 1); if (rv) goto error; memcpy(base_dev->iw_ifname, netdev->name, sizeof(base_dev->iw_ifname)); /* Disable TCP port mapping */ base_dev->iw_driver_flags = IW_F_NO_PORT_MAP; sdev->attrs.max_qp = SIW_MAX_QP; sdev->attrs.max_qp_wr = SIW_MAX_QP_WR; sdev->attrs.max_ord = SIW_MAX_ORD_QP; sdev->attrs.max_ird = SIW_MAX_IRD_QP; sdev->attrs.max_sge = SIW_MAX_SGE; sdev->attrs.max_sge_rd = SIW_MAX_SGE_RD; sdev->attrs.max_cq = SIW_MAX_CQ; sdev->attrs.max_cqe = SIW_MAX_CQE; sdev->attrs.max_mr = SIW_MAX_MR; sdev->attrs.max_pd = SIW_MAX_PD; sdev->attrs.max_mw = SIW_MAX_MW; sdev->attrs.max_srq = SIW_MAX_SRQ; sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR; sdev->attrs.max_srq_sge = SIW_MAX_SGE; INIT_LIST_HEAD(&sdev->cep_list); INIT_LIST_HEAD(&sdev->qp_list); atomic_set(&sdev->num_ctx, 0); atomic_set(&sdev->num_srq, 0); atomic_set(&sdev->num_qp, 0); atomic_set(&sdev->num_cq, 0); atomic_set(&sdev->num_mr, 0); atomic_set(&sdev->num_pd, 0); sdev->numa_node = dev_to_node(&netdev->dev); spin_lock_init(&sdev->lock); return sdev; error: ib_dealloc_device(base_dev); return NULL; } static int siw_netdev_event(struct notifier_block *nb, unsigned long event, void *arg) { struct net_device *netdev = netdev_notifier_info_to_dev(arg); struct ib_device *base_dev; struct siw_device *sdev; dev_dbg(&netdev->dev, "siw: event %lu\n", event); base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (!base_dev) return NOTIFY_OK; sdev = to_siw_dev(base_dev); switch (event) { case NETDEV_REGISTER: /* * Device registration now handled only by * rdma netlink commands. So it shall be impossible * to end up here with a valid siw device. */ siw_dbg(base_dev, "unexpected NETDEV_REGISTER event\n"); break; case NETDEV_UNREGISTER: ib_unregister_device_queued(&sdev->base_dev); break; case NETDEV_CHANGEADDR: siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* * All other events are not handled */ default: break; } ib_device_put(&sdev->base_dev); return NOTIFY_OK; } static struct notifier_block siw_netdev_nb = { .notifier_call = siw_netdev_event, }; static int siw_newlink(const char *basedev_name, struct net_device *netdev) { struct ib_device *base_dev; struct siw_device *sdev = NULL; int rv = -ENOMEM; if (!siw_dev_qualified(netdev)) return -EINVAL; base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (base_dev) { ib_device_put(base_dev); return -EEXIST; } sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); ib_mark_name_assigned_by_user(&sdev->base_dev); rv = siw_device_register(sdev, basedev_name); if (rv) ib_dealloc_device(&sdev->base_dev); } return rv; } static struct rdma_link_ops siw_link_ops = { .type = "siw", .newlink = siw_newlink, }; /* * siw_init_module - Initialize Softiwarp module and register with netdev * subsystem. */ static __init int siw_init_module(void) { int rv; if (SENDPAGE_THRESH < SIW_MAX_INLINE) { pr_info("siw: sendpage threshold too small: %u\n", (int)SENDPAGE_THRESH); rv = -EINVAL; goto out_error; } rv = siw_init_cpulist(); if (rv) goto out_error; rv = siw_cm_init(); if (rv) goto out_error; if (!siw_create_tx_threads()) { pr_info("siw: Could not start any TX thread\n"); rv = -ENOMEM; goto out_error; } rv = register_netdevice_notifier(&siw_netdev_nb); if (rv) goto out_error; rdma_link_register(&siw_link_ops); pr_info("SoftiWARP attached\n"); return 0; out_error: siw_stop_tx_threads(); pr_info("SoftIWARP attach failed. Error: %d\n", rv); siw_cm_exit(); siw_destroy_cpulist(siw_cpu_info.num_nodes); return rv; } static void __exit siw_exit_module(void) { siw_stop_tx_threads(); unregister_netdevice_notifier(&siw_netdev_nb); rdma_link_unregister(&siw_link_ops); ib_unregister_driver(RDMA_DRIVER_SIW); siw_cm_exit(); siw_destroy_cpulist(siw_cpu_info.num_nodes); pr_info("SoftiWARP detached\n"); } module_init(siw_init_module); module_exit(siw_exit_module); MODULE_ALIAS_RDMA_LINK("siw"); |
| 11 12 12 511 509 13 501 502 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which manage clock event devices. * * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/clockchips.h> #include <linux/hrtimer.h> #include <linux/init.h> #include <linux/module.h> #include <linux/smp.h> #include <linux/device.h> #include "tick-internal.h" /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); /* Protection for unbind operations */ static DEFINE_MUTEX(clockevents_mutex); struct ce_unbind { struct clock_event_device *ce; int res; }; static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt, bool ismax) { u64 clc = (u64) latch << evt->shift; u64 rnd; if (WARN_ON(!evt->mult)) evt->mult = 1; rnd = (u64) evt->mult - 1; /* * Upper bound sanity check. If the backwards conversion is * not equal latch, we know that the above shift overflowed. */ if ((clc >> evt->shift) != (u64)latch) clc = ~0ULL; /* * Scaled math oddities: * * For mult <= (1 << shift) we can safely add mult - 1 to * prevent integer rounding loss. So the backwards conversion * from nsec to device ticks will be correct. * * For mult > (1 << shift), i.e. device frequency is > 1GHz we * need to be careful. Adding mult - 1 will result in a value * which when converted back to device ticks can be larger * than latch by up to (mult - 1) >> shift. For the min_delta * calculation we still want to apply this in order to stay * above the minimum device ticks limit. For the upper limit * we would end up with a latch value larger than the upper * limit of the device, so we omit the add to stay below the * device upper boundary. * * Also omit the add if it would overflow the u64 boundary. */ if ((~0ULL - clc > rnd) && (!ismax || evt->mult <= (1ULL << evt->shift))) clc += rnd; do_div(clc, evt->mult); /* Deltas less than 1usec are pointless noise */ return clc > 1000 ? clc : 1000; } /** * clockevent_delta2ns - Convert a latch value (device ticks) to nanoseconds * @latch: value to convert * @evt: pointer to clock event device descriptor * * Math helper, returns latch value converted to nanoseconds (bound checked) */ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) { return cev_delta2ns(latch, evt, false); } EXPORT_SYMBOL_GPL(clockevent_delta2ns); static int __clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; /* Transition with new state-specific callbacks */ switch (state) { case CLOCK_EVT_STATE_DETACHED: /* The clockevent device is getting replaced. Shut it down. */ case CLOCK_EVT_STATE_SHUTDOWN: if (dev->set_state_shutdown) return dev->set_state_shutdown(dev); return 0; case CLOCK_EVT_STATE_PERIODIC: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) return -ENOSYS; if (dev->set_state_periodic) return dev->set_state_periodic(dev); return 0; case CLOCK_EVT_STATE_ONESHOT: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return -ENOSYS; if (dev->set_state_oneshot) return dev->set_state_oneshot(dev); return 0; case CLOCK_EVT_STATE_ONESHOT_STOPPED: /* Core internal bug */ if (WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", clockevent_get_state(dev))) return -EINVAL; if (dev->set_state_oneshot_stopped) return dev->set_state_oneshot_stopped(dev); else return -ENOSYS; default: return -ENOSYS; } } /** * clockevents_switch_state - set the operating state of a clock event device * @dev: device to modify * @state: new state * * Must be called with interrupts disabled ! */ void clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { if (clockevent_get_state(dev) != state) { if (__clockevents_switch_state(dev, state)) return; clockevent_set_state(dev, state); /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ if (clockevent_state_oneshot(dev)) { if (WARN_ON(!dev->mult)) dev->mult = 1; } } } /** * clockevents_shutdown - shutdown the device and clear next_event * @dev: device to shutdown */ void clockevents_shutdown(struct clock_event_device *dev) { clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event = KTIME_MAX; } /** * clockevents_tick_resume - Resume the tick device before using it again * @dev: device to resume */ int clockevents_tick_resume(struct clock_event_device *dev) { int ret = 0; if (dev->tick_resume) ret = dev->tick_resume(dev); return ret; } #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST /* Limit min_delta to a jiffy */ #define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) /** * clockevents_increase_min_delta - raise minimum delta of a clock event device * @dev: device to increase the minimum delta * * Returns 0 on success, -ETIME when the minimum delta reached the limit. */ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { printk_deferred(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); dev->next_event = KTIME_MAX; return -ETIME; } if (dev->min_delta_ns < 5000) dev->min_delta_ns = 5000; else dev->min_delta_ns += dev->min_delta_ns >> 1; if (dev->min_delta_ns > MIN_DELTA_LIMIT) dev->min_delta_ns = MIN_DELTA_LIMIT; printk_deferred(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", dev->name ? dev->name : "?", (unsigned long long) dev->min_delta_ns); return 0; } /** * clockevents_program_min_delta - Set clock event device to the minimum delay. * @dev: device to program * * Returns 0 on success, -ETIME when the retry loop failed. */ static int clockevents_program_min_delta(struct clock_event_device *dev) { unsigned long long clc; int64_t delta; int i; for (i = 0;;) { delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); if (clockevent_state_shutdown(dev)) return 0; dev->retries++; clc = ((unsigned long long) delta * dev->mult) >> dev->shift; if (dev->set_next_event((unsigned long) clc, dev) == 0) return 0; if (++i > 2) { /* * We tried 3 times to program the device with the * given min_delta_ns. Try to increase the minimum * delta, if that fails as well get out of here. */ if (clockevents_increase_min_delta(dev)) return -ETIME; i = 0; } } } #else /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ /** * clockevents_program_min_delta - Set clock event device to the minimum delay. * @dev: device to program * * Returns 0 on success, -ETIME when the retry loop failed. */ static int clockevents_program_min_delta(struct clock_event_device *dev) { unsigned long long clc; int64_t delta = 0; int i; for (i = 0; i < 10; i++) { delta += dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); if (clockevent_state_shutdown(dev)) return 0; dev->retries++; clc = ((unsigned long long) delta * dev->mult) >> dev->shift; if (dev->set_next_event((unsigned long) clc, dev) == 0) return 0; } return -ETIME; } #endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ /** * clockevents_program_event - Reprogram the clock event device. * @dev: device to program * @expires: absolute expiry time (monotonic clock) * @force: program minimum delay if expires can not be set * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force) { unsigned long long clc; int64_t delta; int rc; if (WARN_ON_ONCE(expires < 0)) return -ETIME; dev->next_event = expires; if (clockevent_state_shutdown(dev)) return 0; /* We must be in ONESHOT state here */ WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", clockevent_get_state(dev)); /* Shortcut for clockevent devices that can deal with ktime. */ if (dev->features & CLOCK_EVT_FEAT_KTIME) return dev->set_next_ktime(expires, dev); delta = ktime_to_ns(ktime_sub(expires, ktime_get())); if (delta <= 0) return force ? clockevents_program_min_delta(dev) : -ETIME; delta = min(delta, (int64_t) dev->max_delta_ns); delta = max(delta, (int64_t) dev->min_delta_ns); clc = ((unsigned long long) delta * dev->mult) >> dev->shift; rc = dev->set_next_event((unsigned long) clc, dev); return (rc && force) ? clockevents_program_min_delta(dev) : rc; } /* * Called after a clockevent has been added which might * have replaced a current regular or broadcast device. A * released normal device might be a suitable replacement * for the current broadcast device. Similarly a released * broadcast device might be a suitable replacement for a * normal device. */ static void clockevents_notify_released(void) { struct clock_event_device *dev; /* * Keep iterating as long as tick_check_new_device() * replaces a device. */ while (!list_empty(&clockevents_released)) { dev = list_entry(clockevents_released.next, struct clock_event_device, list); list_move(&dev->list, &clockevent_devices); tick_check_new_device(dev); } } /* * Try to install a replacement clock event device */ static int clockevents_replace(struct clock_event_device *ced) { struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { if (dev == ced || !clockevent_state_detached(dev)) continue; if (!tick_check_replacement(newdev, dev)) continue; if (!try_module_get(dev->owner)) continue; if (newdev) module_put(newdev->owner); newdev = dev; } if (newdev) { tick_install_replacement(newdev); list_del_init(&ced->list); } return newdev ? 0 : -EBUSY; } /* * Called with clockevents_mutex and clockevents_lock held */ static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ if (clockevent_state_detached(ced)) { list_del_init(&ced->list); return 0; } return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; } /* * SMP function call to unbind a device */ static void __clockevents_unbind(void *arg) { struct ce_unbind *cu = arg; int res; raw_spin_lock(&clockevents_lock); res = __clockevents_try_unbind(cu->ce, smp_processor_id()); if (res == -EAGAIN) res = clockevents_replace(cu->ce); cu->res = res; raw_spin_unlock(&clockevents_lock); } /* * Issues smp function call to unbind a per cpu device. Called with * clockevents_mutex held. */ static int clockevents_unbind(struct clock_event_device *ced, int cpu) { struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); return cu.res; } /* * Unbind a clockevents device. */ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) { int ret; mutex_lock(&clockevents_mutex); ret = clockevents_unbind(ced, cpu); mutex_unlock(&clockevents_mutex); return ret; } EXPORT_SYMBOL_GPL(clockevents_unbind_device); /** * clockevents_register_device - register a clock event device * @dev: device to register */ void clockevents_register_device(struct clock_event_device *dev) { unsigned long flags; /* Initialize state to DETACHED */ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); dev->cpumask = cpumask_of(smp_processor_id()); } if (dev->cpumask == cpu_all_mask) { WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n", dev->name); dev->cpumask = cpu_possible_mask; } raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_register_device); static void clockevents_config(struct clock_event_device *dev, u32 freq) { u64 sec; if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; /* * Calculate the maximum number of seconds we can sleep. Limit * to 10 minutes for hardware which can program more than * 32bit ticks so we still get reasonable conversion values. */ sec = dev->max_delta_ticks; do_div(sec, freq); if (!sec) sec = 1; else if (sec > 600 && dev->max_delta_ticks > UINT_MAX) sec = 600; clockevents_calc_mult_shift(dev, freq, sec); dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false); dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true); } /** * clockevents_config_and_register - Configure and register a clock event device * @dev: device to register * @freq: The clock frequency * @min_delta: The minimum clock ticks to program in oneshot mode * @max_delta: The maximum clock ticks to program in oneshot mode * * min/max_delta can be 0 for devices which do not support oneshot mode. */ void clockevents_config_and_register(struct clock_event_device *dev, u32 freq, unsigned long min_delta, unsigned long max_delta) { dev->min_delta_ticks = min_delta; dev->max_delta_ticks = max_delta; clockevents_config(dev, freq); clockevents_register_device(dev); } EXPORT_SYMBOL_GPL(clockevents_config_and_register); int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); if (clockevent_state_oneshot(dev)) return clockevents_program_event(dev, dev->next_event, false); if (clockevent_state_periodic(dev)) return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } /** * clockevents_update_freq - Update frequency and reprogram a clock event device. * @dev: device to modify * @freq: new device frequency * * Reconfigure and reprogram a clock event device in oneshot * mode. Must be called on the cpu for which the device delivers per * cpu timer events. If called for the broadcast device the core takes * care of serialization. * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_update_freq(struct clock_event_device *dev, u32 freq) { unsigned long flags; int ret; local_irq_save(flags); ret = tick_broadcast_update_freq(dev, freq); if (ret == -ENODEV) ret = __clockevents_update_freq(dev, freq); local_irq_restore(flags); return ret; } /* * Noop handler when we shut down an event device */ void clockevents_handle_noop(struct clock_event_device *dev) { } /** * clockevents_exchange_device - release and request clock devices * @old: device to release (can be NULL) * @new: device to request (can be NULL) * * Called from various tick functions with clockevents_lock held and * interrupts disabled. */ void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new) { /* * Caller releases a clock event device. We queue it into the * released list and do a notify add later. */ if (old) { module_put(old->owner); clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); list_move(&old->list, &clockevents_released); } if (new) { BUG_ON(!clockevent_state_detached(new)); clockevents_shutdown(new); } } /** * clockevents_suspend - suspend clock devices */ void clockevents_suspend(void) { struct clock_event_device *dev; list_for_each_entry_reverse(dev, &clockevent_devices, list) if (dev->suspend && !clockevent_state_detached(dev)) dev->suspend(dev); } /** * clockevents_resume - resume clock devices */ void clockevents_resume(void) { struct clock_event_device *dev; list_for_each_entry(dev, &clockevent_devices, list) if (dev->resume && !clockevent_state_detached(dev)) dev->resume(dev); } #ifdef CONFIG_HOTPLUG_CPU /** * tick_offline_cpu - Shutdown all clock events related * to this CPU and take it out of the * broadcast mechanism. * @cpu: The outgoing CPU * * Called by the dying CPU during teardown. */ void tick_offline_cpu(unsigned int cpu) { struct clock_event_device *dev, *tmp; raw_spin_lock(&clockevents_lock); tick_broadcast_offline(cpu); tick_shutdown(); /* * Unregister the clock event devices which were * released above. */ list_for_each_entry_safe(dev, tmp, &clockevents_released, list) list_del(&dev->list); /* * Now check whether the CPU has left unused per cpu devices */ list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { BUG_ON(!clockevent_state_detached(dev)); list_del(&dev->list); } } raw_spin_unlock(&clockevents_lock); } #endif #ifdef CONFIG_SYSFS static const struct bus_type clockevents_subsys = { .name = "clockevents", .dev_name = "clockevent", }; static DEFINE_PER_CPU(struct device, tick_percpu_dev); static struct tick_device *tick_get_tick_dev(struct device *dev); static ssize_t current_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tick_device *td; ssize_t count = 0; raw_spin_lock_irq(&clockevents_lock); td = tick_get_tick_dev(dev); if (td && td->evtdev) count = sysfs_emit(buf, "%s\n", td->evtdev->name); raw_spin_unlock_irq(&clockevents_lock); return count; } static DEVICE_ATTR_RO(current_device); /* We don't support the abomination of removable broadcast devices */ static ssize_t unbind_device_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { char name[CS_NAME_LEN]; ssize_t ret = sysfs_get_uname(buf, name, count); struct clock_event_device *ce = NULL, *iter; if (ret < 0) return ret; ret = -ENODEV; mutex_lock(&clockevents_mutex); raw_spin_lock_irq(&clockevents_lock); list_for_each_entry(iter, &clockevent_devices, list) { if (!strcmp(iter->name, name)) { ret = __clockevents_try_unbind(iter, dev->id); ce = iter; break; } } raw_spin_unlock_irq(&clockevents_lock); /* * We hold clockevents_mutex, so ce can't go away */ if (ret == -EAGAIN) ret = clockevents_unbind(ce, dev->id); mutex_unlock(&clockevents_mutex); return ret ? ret : count; } static DEVICE_ATTR_WO(unbind_device); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static struct device tick_bc_dev = { .init_name = "broadcast", .id = 0, .bus = &clockevents_subsys, }; static struct tick_device *tick_get_tick_dev(struct device *dev) { return dev == &tick_bc_dev ? tick_get_broadcast_device() : &per_cpu(tick_cpu_device, dev->id); } static __init int tick_broadcast_init_sysfs(void) { int err = device_register(&tick_bc_dev); if (!err) err = device_create_file(&tick_bc_dev, &dev_attr_current_device); return err; } #else static struct tick_device *tick_get_tick_dev(struct device *dev) { return &per_cpu(tick_cpu_device, dev->id); } static inline int tick_broadcast_init_sysfs(void) { return 0; } #endif static int __init tick_init_sysfs(void) { int cpu; for_each_possible_cpu(cpu) { struct device *dev = &per_cpu(tick_percpu_dev, cpu); int err; dev->id = cpu; dev->bus = &clockevents_subsys; err = device_register(dev); if (!err) err = device_create_file(dev, &dev_attr_current_device); if (!err) err = device_create_file(dev, &dev_attr_unbind_device); if (err) return err; } return tick_broadcast_init_sysfs(); } static int __init clockevents_init_sysfs(void) { int err = subsys_system_register(&clockevents_subsys, NULL); if (!err) err = tick_init_sysfs(); return err; } device_initcall(clockevents_init_sysfs); #endif /* SYSFS */ |
| 1 4214 4213 4215 42 42 42 42 41 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/panic.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ #include <linux/debug_locks.h> #include <linux/sched/debug.h> #include <linux/interrupt.h> #include <linux/kgdb.h> #include <linux/kmsg_dump.h> #include <linux/kallsyms.h> #include <linux/notifier.h> #include <linux/vt_kern.h> #include <linux/module.h> #include <linux/random.h> #include <linux/ftrace.h> #include <linux/reboot.h> #include <linux/delay.h> #include <linux/kexec.h> #include <linux/panic_notifier.h> #include <linux/sched.h> #include <linux/string_helpers.h> #include <linux/sysrq.h> #include <linux/init.h> #include <linux/nmi.h> #include <linux/console.h> #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> #include <linux/sysfs.h> #include <linux/context_tracking.h> #include <linux/seq_buf.h> #include <linux/sys_info.h> #include <trace/events/error_report.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 #ifdef CONFIG_SMP /* * Should we dump all CPUs backtraces in an oops event? * Defaults to 0, can be changed via sysctl. */ static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; #else #define sysctl_oops_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ int panic_on_oops = IS_ENABLED(CONFIG_PANIC_ON_OOPS); static unsigned long tainted_mask = IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly; static bool panic_console_replay; bool panic_triggering_all_cpu_backtrace; static bool panic_this_cpu_backtrace_printed; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); unsigned long panic_print; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); static void panic_print_deprecated(void) { pr_info_once("Kernel: The 'panic_print' parameter is now deprecated. Please use 'panic_sys_info' and 'panic_console_replay' instead.\n"); } #ifdef CONFIG_SYSCTL /* * Taint values can only be increased * This means we can safely use a temporary. */ static int proc_taint(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; unsigned long tmptaint = get_taint(); int err; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; t = *table; t.data = &tmptaint; err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; if (write) { int i; /* * If we are relying on panic_on_taint not producing * false positives due to userspace input, bail out * before setting the requested taint flags. */ if (panic_on_taint_nousertaint && (tmptaint & panic_on_taint)) return -EINVAL; /* * Poor man's atomic or. Not worth adding a primitive * to everyone's atomic.h for this */ for (i = 0; i < TAINT_FLAGS_COUNT; i++) if ((1UL << i) & tmptaint) add_taint(i, LOCKDEP_STILL_OK); } return err; } static int sysctl_panic_print_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { panic_print_deprecated(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table kern_panic_table[] = { #ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", .data = &sysctl_oops_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tainted", .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_taint, }, { .procname = "panic", .data = &panic_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "panic_on_oops", .data = &panic_on_oops, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "panic_print", .data = &panic_print, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = sysctl_panic_print_handler, }, { .procname = "panic_on_warn", .data = &panic_on_warn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "warn_limit", .data = &warn_limit, .maxlen = sizeof(warn_limit), .mode = 0644, .proc_handler = proc_douintvec, }, #if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \ defined(CONFIG_DEBUG_STACKOVERFLOW) { .procname = "panic_on_stackoverflow", .data = &sysctl_panic_on_stackoverflow, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif { .procname = "panic_sys_info", .data = &panic_print, .maxlen = sizeof(panic_print), .mode = 0644, .proc_handler = sysctl_sys_info_handler, }, }; static __init int kernel_panic_sysctls_init(void) { register_sysctl_init("kernel", kern_panic_table); return 0; } late_initcall(kernel_panic_sysctls_init); #endif /* The format is "panic_sys_info=tasks,mem,locks,ftrace,..." */ static int __init setup_panic_sys_info(char *buf) { /* There is no risk of race in kernel boot phase */ panic_print = sys_info_parse_param(buf); return 1; } __setup("panic_sys_info=", setup_panic_sys_info); static atomic_t warn_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); } static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); static __init int kernel_panic_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); return 0; } late_initcall(kernel_panic_sysfs_init); #endif static long no_blink(int state) { return 0; } /* Returns how long it waited in ms */ long (*panic_blink)(int state); EXPORT_SYMBOL(panic_blink); /* * Stop ourself in panic -- architecture code may override this */ void __weak __noreturn panic_smp_self_stop(void) { while (1) cpu_relax(); } /* * Stop ourselves in NMI context if another CPU has already panicked. Arch code * may override this to prepare for crash dumping, e.g. save regs info. */ void __weak __noreturn nmi_panic_self_stop(struct pt_regs *regs) { panic_smp_self_stop(); } /* * Stop other CPUs in panic. Architecture dependent code may override this * with more suitable version. For example, if the architecture supports * crash dump, it should save registers of each stopped CPU and disable * per-CPU features such as virtualization extensions. */ void __weak crash_smp_send_stop(void) { static int cpus_stopped; /* * This function can be called twice in panic path, but obviously * we execute this only once. */ if (cpus_stopped) return; /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic * situation. */ smp_send_stop(); cpus_stopped = 1; } atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); bool panic_try_start(void) { int old_cpu, this_cpu; /* * Only one CPU is allowed to execute the crash_kexec() code as with * panic(). Otherwise parallel calls of panic() and crash_kexec() * may stop each other. To exclude them, we use panic_cpu here too. */ old_cpu = PANIC_CPU_INVALID; this_cpu = raw_smp_processor_id(); return atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu); } EXPORT_SYMBOL(panic_try_start); void panic_reset(void) { atomic_set(&panic_cpu, PANIC_CPU_INVALID); } EXPORT_SYMBOL(panic_reset); bool panic_in_progress(void) { return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } EXPORT_SYMBOL(panic_in_progress); /* Return true if a panic is in progress on the current CPU. */ bool panic_on_this_cpu(void) { /* * We can use raw_smp_processor_id() here because it is impossible for * the task to be migrated to the panic_cpu, or away from it. If * panic_cpu has already been set, and we're not currently executing on * that CPU, then we never will be. */ return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); } EXPORT_SYMBOL(panic_on_this_cpu); /* * Return true if a panic is in progress on a remote CPU. * * On true, the local CPU should immediately release any printing resources * that may be needed by the panic CPU. */ bool panic_on_other_cpu(void) { return (panic_in_progress() && !panic_on_this_cpu()); } EXPORT_SYMBOL(panic_on_other_cpu); /* * A variant of panic() called from NMI context. We return if we've already * panicked on this CPU. If another CPU already panicked, loop in * nmi_panic_self_stop() which can provide architecture dependent code such * as saving register state for crash dump. */ void nmi_panic(struct pt_regs *regs, const char *msg) { if (panic_try_start()) panic("%s", msg); else if (panic_on_other_cpu()) nmi_panic_self_stop(regs); } EXPORT_SYMBOL(nmi_panic); void check_panic_on_warn(const char *origin) { unsigned int limit; if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin); limit = READ_ONCE(warn_limit); if (atomic_inc_return(&warn_count) >= limit && limit) panic("%s: system warned too often (kernel.warn_limit is %d)", origin, limit); } static void panic_trigger_all_cpu_backtrace(void) { /* Temporary allow non-panic CPUs to write their backtraces. */ panic_triggering_all_cpu_backtrace = true; if (panic_this_cpu_backtrace_printed) trigger_allbutcpu_cpu_backtrace(raw_smp_processor_id()); else trigger_all_cpu_backtrace(); panic_triggering_all_cpu_backtrace = false; } /* * Helper that triggers the NMI backtrace (if set in panic_print) * and then performs the secondary CPUs shutdown - we cannot have * the NMI backtrace after the CPUs are off! */ static void panic_other_cpus_shutdown(bool crash_kexec) { if (panic_print & SYS_INFO_ALL_CPU_BT) panic_trigger_all_cpu_backtrace(); /* * Note that smp_send_stop() is the usual SMP shutdown function, * which unfortunately may not be hardened to work in a panic * situation. If we want to do crash dump after notifier calls * and kmsg_dump, we will need architecture dependent extra * bits in addition to stopping other CPUs, hence we rely on * crash_smp_send_stop() for that. */ if (!crash_kexec) smp_send_stop(); else crash_smp_send_stop(); } /** * vpanic - halt the system * @fmt: The text string to print * @args: Arguments for the format string * * Display a message, then perform cleanups. This function never returns. */ void vpanic(const char *fmt, va_list args) { static char buf[1024]; long i, i_next = 0, len; int state = 0; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; if (panic_on_warn) { /* * This thread may hit another WARN() in the panic path. * Resetting this prevents additional WARN() from panicking the * system on this thread. Other threads are blocked by the * panic_mutex in panic(). */ panic_on_warn = 0; } /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since * there is nothing to prevent an interrupt handler (that runs * after setting panic_cpu) from invoking panic() again. */ local_irq_disable(); preempt_disable_notrace(); /* * It's possible to come here directly from a panic-assertion and * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... * * Only one CPU is allowed to execute the panic code from here. For * multiple parallel invocations of panic, all other CPUs either * stop themself or will wait until they are stopped by the 1st CPU * with smp_send_stop(). * * cmpxchg success means this is the 1st CPU which comes here, * so go ahead. * `old_cpu == this_cpu' means we came from nmi_panic() which sets * panic_cpu to this CPU. In this case, this is also the 1st CPU. */ /* atomic_try_cmpxchg updates old_cpu on failure */ if (panic_try_start()) { /* go ahead */ } else if (panic_on_other_cpu()) panic_smp_self_stop(); console_verbose(); bust_spinlocks(1); len = vscnprintf(buf, sizeof(buf), fmt, args); if (len && buf[len - 1] == '\n') buf[len - 1] = '\0'; pr_emerg("Kernel panic - not syncing: %s\n", buf); /* * Avoid nested stack-dumping if a panic occurs during oops processing */ if (test_taint(TAINT_DIE) || oops_in_progress > 1) { panic_this_cpu_backtrace_printed = true; } else if (IS_ENABLED(CONFIG_DEBUG_BUGVERBOSE)) { dump_stack(); panic_this_cpu_backtrace_printed = true; } /* * If kgdb is enabled, give it a chance to run before we stop all * the other CPUs or else we won't be able to debug processes left * running on them. */ kgdb_panic(buf); /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. * If we want to run this after calling panic_notifiers, pass * the "crash_kexec_post_notifiers" option to the kernel. * * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!_crash_kexec_post_notifiers) __crash_kexec(NULL); panic_other_cpus_shutdown(_crash_kexec_post_notifiers); printk_legacy_allow_panic_sync(); /* * Run any panic handlers, including those that might need to * add information to the kmsg dump output. */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); sys_info(panic_print); kmsg_dump_desc(KMSG_DUMP_PANIC, buf); /* * If you doubt kdump always works fine in any situation, * "crash_kexec_post_notifiers" offers you a chance to run * panic_notifiers and dumping kmsg before kdump. * Note: since some panic_notifiers can make crashed kernel * more unstable, it can increase risks of the kdump failure too. * * Bypass the panic_cpu check and call __crash_kexec directly. */ if (_crash_kexec_post_notifiers) __crash_kexec(NULL); console_unblank(); /* * We may have ended up stopping the CPU holding the lock (in * smp_send_stop()) while still having some valuable data in the console * buffer. Try to acquire the lock then release it regardless of the * result. The release will also print the buffers out. Locks debug * should be disabled to avoid reporting bad unlock balance when * panic() is not being callled from OOPS. */ debug_locks_off(); console_flush_on_panic(CONSOLE_FLUSH_PENDING); if ((panic_print & SYS_INFO_PANIC_CONSOLE_REPLAY) || panic_console_replay) console_flush_on_panic(CONSOLE_REPLAY_ALL); if (!panic_blink) panic_blink = no_blink; if (panic_timeout > 0) { /* * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); if (i >= i_next) { i += panic_blink(state ^= 1); i_next = i + 3600 / PANIC_BLINK_SPD; } mdelay(PANIC_TIMER_STEP); } } if (panic_timeout != 0) { /* * This will not be a clean reboot, with everything * shutting down. But if there is a chance of * rebooting the system it will be rebooted. */ if (panic_reboot_mode != REBOOT_UNDEFINED) reboot_mode = panic_reboot_mode; emergency_restart(); } #ifdef __sparc__ { extern int stop_a_enabled; /* Make sure the user can actually press Stop-A (L1-A) */ stop_a_enabled = 1; pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n" "twice on console to return to the boot prom\n"); } #endif #if defined(CONFIG_S390) disabled_wait(); #endif pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf); /* Do not scroll important messages printed above */ suppress_printk = 1; /* * The final messages may not have been printed if in a context that * defers printing (such as NMI) and irq_work is not available. * Explicitly flush the kernel log buffer one last time. */ console_flush_on_panic(CONSOLE_FLUSH_PENDING); nbcon_atomic_flush_unsafe(); local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); if (i >= i_next) { i += panic_blink(state ^= 1); i_next = i + 3600 / PANIC_BLINK_SPD; } mdelay(PANIC_TIMER_STEP); } } EXPORT_SYMBOL(vpanic); /* Identical to vpanic(), except it takes variadic arguments instead of va_list */ void panic(const char *fmt, ...) { va_list args; va_start(args, fmt); vpanic(fmt, args); va_end(args); } EXPORT_SYMBOL(panic); #define TAINT_FLAG(taint, _c_true, _c_false, _module) \ [ TAINT_##taint ] = { \ .c_true = _c_true, .c_false = _c_false, \ .module = _module, \ .desc = #taint, \ } /* * TAINT_FORCED_RMMOD could be a per-module flag but the module * is being removed anyway. */ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { TAINT_FLAG(PROPRIETARY_MODULE, 'P', 'G', true), TAINT_FLAG(FORCED_MODULE, 'F', ' ', true), TAINT_FLAG(CPU_OUT_OF_SPEC, 'S', ' ', false), TAINT_FLAG(FORCED_RMMOD, 'R', ' ', false), TAINT_FLAG(MACHINE_CHECK, 'M', ' ', false), TAINT_FLAG(BAD_PAGE, 'B', ' ', false), TAINT_FLAG(USER, 'U', ' ', false), TAINT_FLAG(DIE, 'D', ' ', false), TAINT_FLAG(OVERRIDDEN_ACPI_TABLE, 'A', ' ', false), TAINT_FLAG(WARN, 'W', ' ', false), TAINT_FLAG(CRAP, 'C', ' ', true), TAINT_FLAG(FIRMWARE_WORKAROUND, 'I', ' ', false), TAINT_FLAG(OOT_MODULE, 'O', ' ', true), TAINT_FLAG(UNSIGNED_MODULE, 'E', ' ', true), TAINT_FLAG(SOFTLOCKUP, 'L', ' ', false), TAINT_FLAG(LIVEPATCH, 'K', ' ', true), TAINT_FLAG(AUX, 'X', ' ', true), TAINT_FLAG(RANDSTRUCT, 'T', ' ', true), TAINT_FLAG(TEST, 'N', ' ', true), TAINT_FLAG(FWCTL, 'J', ' ', true), }; #undef TAINT_FLAG static void print_tainted_seq(struct seq_buf *s, bool verbose) { const char *sep = ""; int i; if (!tainted_mask) { seq_buf_puts(s, "Not tainted"); return; } seq_buf_printf(s, "Tainted: "); for (i = 0; i < TAINT_FLAGS_COUNT; i++) { const struct taint_flag *t = &taint_flags[i]; bool is_set = test_bit(i, &tainted_mask); char c = is_set ? t->c_true : t->c_false; if (verbose) { if (is_set) { seq_buf_printf(s, "%s[%c]=%s", sep, c, t->desc); sep = ", "; } } else { seq_buf_putc(s, c); } } } static const char *_print_tainted(bool verbose) { /* FIXME: what should the size be? */ static char buf[sizeof(taint_flags)]; struct seq_buf s; BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); seq_buf_init(&s, buf, sizeof(buf)); print_tainted_seq(&s, verbose); return seq_buf_str(&s); } /** * print_tainted - return a string to represent the kernel taint state. * * For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst * * The string is overwritten by the next call to print_tainted(), * but is always NULL terminated. */ const char *print_tainted(void) { return _print_tainted(false); } /** * print_tainted_verbose - A more verbose version of print_tainted() */ const char *print_tainted_verbose(void) { return _print_tainted(true); } int test_taint(unsigned flag) { return test_bit(flag, &tainted_mask); } EXPORT_SYMBOL(test_taint); unsigned long get_taint(void) { return tainted_mask; } /** * add_taint: add a taint flag if not already set. * @flag: one of the TAINT_* constants. * @lockdep_ok: whether lock debugging is still OK. * * If something bad has gone wrong, you'll want @lockdebug_ok = false, but for * some notewortht-but-not-corrupting cases, it can be set to true. */ void add_taint(unsigned flag, enum lockdep_ok lockdep_ok) { if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off()) pr_warn("Disabling lock debugging due to kernel taint\n"); set_bit(flag, &tainted_mask); if (tainted_mask & panic_on_taint) { panic_on_taint = 0; panic("panic_on_taint set ..."); } } EXPORT_SYMBOL(add_taint); static void spin_msec(int msecs) { int i; for (i = 0; i < msecs; i++) { touch_nmi_watchdog(); mdelay(1); } } /* * It just happens that oops_enter() and oops_exit() are identically * implemented... */ static void do_oops_enter_exit(void) { unsigned long flags; static int spin_counter; if (!pause_on_oops) return; spin_lock_irqsave(&pause_on_oops_lock, flags); if (pause_on_oops_flag == 0) { /* This CPU may now print the oops message */ pause_on_oops_flag = 1; } else { /* We need to stall this CPU */ if (!spin_counter) { /* This CPU gets to do the counting */ spin_counter = pause_on_oops; do { spin_unlock(&pause_on_oops_lock); spin_msec(MSEC_PER_SEC); spin_lock(&pause_on_oops_lock); } while (--spin_counter); pause_on_oops_flag = 0; } else { /* This CPU waits for a different one */ while (spin_counter) { spin_unlock(&pause_on_oops_lock); spin_msec(1); spin_lock(&pause_on_oops_lock); } } } spin_unlock_irqrestore(&pause_on_oops_lock, flags); } /* * Return true if the calling CPU is allowed to print oops-related info. * This is a bit racy.. */ bool oops_may_print(void) { return pause_on_oops_flag == 0; } /* * Called when the architecture enters its oops handler, before it prints * anything. If this is the first CPU to oops, and it's oopsing the first * time then let it proceed. * * This is all enabled by the pause_on_oops kernel boot option. We do all * this to ensure that oopses don't scroll off the screen. It has the * side-effect of preventing later-oopsing CPUs from mucking up the display, * too. * * It turns out that the CPU which is allowed to print ends up pausing for * the right duration, whereas all the other CPUs pause for twice as long: * once in oops_enter(), once in oops_exit(). */ void oops_enter(void) { nbcon_cpu_emergency_enter(); tracing_off(); /* can't trust the integrity of the kernel anymore: */ debug_locks_off(); do_oops_enter_exit(); if (sysctl_oops_all_cpu_backtrace) trigger_all_cpu_backtrace(); } static void print_oops_end_marker(void) { pr_warn("---[ end trace %016llx ]---\n", 0ULL); } /* * Called when the architecture exits its oops handler, after printing * everything. */ void oops_exit(void) { do_oops_enter_exit(); print_oops_end_marker(); nbcon_cpu_emergency_exit(); kmsg_dump(KMSG_DUMP_OOPS); } struct warn_args { const char *fmt; va_list args; }; void __warn(const char *file, int line, void *caller, unsigned taint, struct pt_regs *regs, struct warn_args *args) { nbcon_cpu_emergency_enter(); disable_trace_on_warning(); if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, caller); else pr_warn("WARNING: CPU: %d PID: %d at %pS\n", raw_smp_processor_id(), current->pid, caller); #pragma GCC diagnostic push #ifndef __clang__ #pragma GCC diagnostic ignored "-Wsuggest-attribute=format" #endif if (args) vprintk(args->fmt, args->args); #pragma GCC diagnostic pop print_modules(); if (regs) show_regs(regs); check_panic_on_warn("kernel"); if (!regs) dump_stack(); print_irqtrace_events(current); print_oops_end_marker(); trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller); /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); nbcon_cpu_emergency_exit(); } #ifdef CONFIG_BUG #ifndef __WARN_FLAGS void warn_slowpath_fmt(const char *file, int line, unsigned taint, const char *fmt, ...) { bool rcu = warn_rcu_enter(); struct warn_args args; pr_warn(CUT_HERE); if (!fmt) { __warn(file, line, __builtin_return_address(0), taint, NULL, NULL); warn_rcu_exit(rcu); return; } args.fmt = fmt; va_start(args.args, fmt); __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); warn_rcu_exit(rcu); } EXPORT_SYMBOL(warn_slowpath_fmt); #else void __warn_printk(const char *fmt, ...) { bool rcu = warn_rcu_enter(); va_list args; pr_warn(CUT_HERE); va_start(args, fmt); vprintk(fmt, args); va_end(args); warn_rcu_exit(rcu); } EXPORT_SYMBOL(__warn_printk); #endif /* Support resetting WARN*_ONCE state */ static int clear_warn_once_set(void *data, u64 val) { generic_bug_clear_once(); memset(__start_once, 0, __end_once - __start_once); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(clear_warn_once_fops, NULL, clear_warn_once_set, "%lld\n"); static __init int register_warn_debugfs(void) { /* Don't care about failure */ debugfs_create_file_unsafe("clear_warn_once", 0200, NULL, NULL, &clear_warn_once_fops); return 0; } device_initcall(register_warn_debugfs); #endif #ifdef CONFIG_STACKPROTECTOR /* * Called when gcc's -fstack-protector feature is used, and * gcc detects corruption of the on-stack canary value */ __visible noinstr void __stack_chk_fail(void) { unsigned long flags; instrumentation_begin(); flags = user_access_save(); panic("stack-protector: Kernel stack is corrupted in: %pB", __builtin_return_address(0)); user_access_restore(flags); instrumentation_end(); } EXPORT_SYMBOL(__stack_chk_fail); #endif core_param(panic, panic_timeout, int, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); core_param(panic_on_warn, panic_on_warn, int, 0644); core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644); core_param(panic_console_replay, panic_console_replay, bool, 0644); static int panic_print_set(const char *val, const struct kernel_param *kp) { panic_print_deprecated(); return param_set_ulong(val, kp); } static int panic_print_get(char *val, const struct kernel_param *kp) { panic_print_deprecated(); return param_get_ulong(val, kp); } static const struct kernel_param_ops panic_print_ops = { .set = panic_print_set, .get = panic_print_get, }; __core_param_cb(panic_print, &panic_print_ops, &panic_print, 0644); static int __init oops_setup(char *s) { if (!s) return -EINVAL; if (!strcmp(s, "panic")) panic_on_oops = 1; return 0; } early_param("oops", oops_setup); static int __init panic_on_taint_setup(char *s) { char *taint_str; if (!s) return -EINVAL; taint_str = strsep(&s, ","); if (kstrtoul(taint_str, 16, &panic_on_taint)) return -EINVAL; /* make sure panic_on_taint doesn't hold out-of-range TAINT flags */ panic_on_taint &= TAINT_FLAGS_MAX; if (!panic_on_taint) return -EINVAL; if (s && !strcmp(s, "nousertaint")) panic_on_taint_nousertaint = true; pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%s\n", panic_on_taint, str_enabled_disabled(panic_on_taint_nousertaint)); return 0; } early_param("panic_on_taint", panic_on_taint_setup); |
| 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 | /* 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 #define DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE 29 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_LEGACY_FCS = DSA_TAG_PROTO_BRCM_LEGACY_FCS_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 kernel_hwtstamp_config *config); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); 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 |
| 1156 2411 2368 55 | 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 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += get_unaligned((u32 *)k); b += get_unaligned((u32 *)(k + 4)); c += get_unaligned((u32 *)(k + 8)); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 3 3 2 3 3 14 14 14 14 13 1 1 1 1 1 2 16 16 2 15 14 1 1 1 2 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc. * Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com> */ #define pr_fmt(fmt) "PM: hibernation: " fmt #include <crypto/acompress.h> #include <linux/blkdev.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/reboot.h> #include <linux/string.h> #include <linux/device.h> #include <linux/async.h> #include <linux/delay.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/pm.h> #include <linux/nmi.h> #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/ctype.h> #include <linux/ktime.h> #include <linux/security.h> #include <linux/secretmem.h> #include <trace/events/power.h> #include "power.h" static int nocompress; static int noresume; static int nohibernate; static int resume_wait; static unsigned int resume_delay; static char resume_file[256] = CONFIG_PM_STD_PARTITION; dev_t swsusp_resume_device; sector_t swsusp_resume_block; __visible int in_suspend __nosavedata; static char hibernate_compressor[CRYPTO_MAX_ALG_NAME] = CONFIG_HIBERNATION_DEF_COMP; /* * Compression/decompression algorithm to be used while saving/loading * image to/from disk. This would later be used in 'kernel/power/swap.c' * to allocate comp streams. */ char hib_comp_algo[CRYPTO_MAX_ALG_NAME]; enum { HIBERNATION_INVALID, HIBERNATION_PLATFORM, HIBERNATION_SHUTDOWN, HIBERNATION_REBOOT, #ifdef CONFIG_SUSPEND HIBERNATION_SUSPEND, #endif HIBERNATION_TEST_RESUME, /* keep last */ __HIBERNATION_AFTER_LAST }; #define HIBERNATION_MAX (__HIBERNATION_AFTER_LAST-1) #define HIBERNATION_FIRST (HIBERNATION_INVALID + 1) static int hibernation_mode = HIBERNATION_SHUTDOWN; bool freezer_test_done; static const struct platform_hibernation_ops *hibernation_ops; static atomic_t hibernate_atomic = ATOMIC_INIT(1); #ifdef CONFIG_SUSPEND /** * pm_hibernation_mode_is_suspend - Check if hibernation has been set to suspend */ bool pm_hibernation_mode_is_suspend(void) { return hibernation_mode == HIBERNATION_SUSPEND; } EXPORT_SYMBOL_GPL(pm_hibernation_mode_is_suspend); #endif bool hibernate_acquire(void) { return atomic_add_unless(&hibernate_atomic, -1, 0); } void hibernate_release(void) { atomic_inc(&hibernate_atomic); } bool hibernation_in_progress(void) { return !atomic_read(&hibernate_atomic); } bool hibernation_available(void) { return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION) && !secretmem_active() && !cxl_mem_active(); } /** * hibernation_set_ops - Set the global hibernate operations. * @ops: Hibernation operations to use in subsequent hibernation transitions. */ void hibernation_set_ops(const struct platform_hibernation_ops *ops) { unsigned int sleep_flags; if (ops && !(ops->begin && ops->end && ops->pre_snapshot && ops->prepare && ops->finish && ops->enter && ops->pre_restore && ops->restore_cleanup && ops->leave)) { WARN_ON(1); return; } sleep_flags = lock_system_sleep(); hibernation_ops = ops; if (ops) hibernation_mode = HIBERNATION_PLATFORM; else if (hibernation_mode == HIBERNATION_PLATFORM) hibernation_mode = HIBERNATION_SHUTDOWN; unlock_system_sleep(sleep_flags); } EXPORT_SYMBOL_GPL(hibernation_set_ops); static bool entering_platform_hibernation; bool system_entering_hibernation(void) { return entering_platform_hibernation; } EXPORT_SYMBOL(system_entering_hibernation); #ifdef CONFIG_PM_DEBUG static unsigned int pm_test_delay = 5; module_param(pm_test_delay, uint, 0644); MODULE_PARM_DESC(pm_test_delay, "Number of seconds to wait before resuming from hibernation test"); static void hibernation_debug_sleep(void) { pr_info("hibernation debug: Waiting for %d second(s).\n", pm_test_delay); mdelay(pm_test_delay * 1000); } static int hibernation_test(int level) { if (pm_test_level == level) { hibernation_debug_sleep(); return 1; } return 0; } #else /* !CONFIG_PM_DEBUG */ static int hibernation_test(int level) { return 0; } #endif /* !CONFIG_PM_DEBUG */ /** * platform_begin - Call platform to start hibernation. * @platform_mode: Whether or not to use the platform driver. */ static int platform_begin(int platform_mode) { return (platform_mode && hibernation_ops) ? hibernation_ops->begin(PMSG_FREEZE) : 0; } /** * platform_end - Call platform to finish transition to the working state. * @platform_mode: Whether or not to use the platform driver. */ static void platform_end(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->end(); } /** * platform_pre_snapshot - Call platform to prepare the machine for hibernation. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to prepare the system for creating a hibernate image, * if so configured, and return an error code if that fails. */ static int platform_pre_snapshot(int platform_mode) { return (platform_mode && hibernation_ops) ? hibernation_ops->pre_snapshot() : 0; } /** * platform_leave - Call platform to prepare a transition to the working state. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver prepare to prepare the machine for switching to the * normal mode of operation. * * This routine is called on one CPU with interrupts disabled. */ static void platform_leave(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->leave(); } /** * platform_finish - Call platform to switch the system to the working state. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to switch the machine to the normal mode of * operation. * * This routine must be called after platform_prepare(). */ static void platform_finish(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->finish(); } /** * platform_pre_restore - Prepare for hibernate image restoration. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to prepare the system for resume from a hibernation * image. * * If the restore fails after this function has been called, * platform_restore_cleanup() must be called. */ static int platform_pre_restore(int platform_mode) { return (platform_mode && hibernation_ops) ? hibernation_ops->pre_restore() : 0; } /** * platform_restore_cleanup - Switch to the working state after failing restore. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to switch the system to the normal mode of operation * after a failing restore. * * If platform_pre_restore() has been called before the failing restore, this * function must be called too, regardless of the result of * platform_pre_restore(). */ static void platform_restore_cleanup(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->restore_cleanup(); } /** * platform_recover - Recover from a failure to suspend devices. * @platform_mode: Whether or not to use the platform driver. */ static void platform_recover(int platform_mode) { if (platform_mode && hibernation_ops && hibernation_ops->recover) hibernation_ops->recover(); } /** * swsusp_show_speed - Print time elapsed between two events during hibernation. * @start: Starting event. * @stop: Final event. * @nr_pages: Number of memory pages processed between @start and @stop. * @msg: Additional diagnostic message to print. */ void swsusp_show_speed(ktime_t start, ktime_t stop, unsigned nr_pages, char *msg) { ktime_t diff; u64 elapsed_centisecs64; unsigned int centisecs; unsigned int k; unsigned int kps; diff = ktime_sub(stop, start); elapsed_centisecs64 = ktime_divns(diff, 10*NSEC_PER_MSEC); centisecs = elapsed_centisecs64; if (centisecs == 0) centisecs = 1; /* avoid div-by-zero */ k = nr_pages * (PAGE_SIZE / 1024); kps = (k * 100) / centisecs; pr_info("%s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n", msg, k, centisecs / 100, centisecs % 100, kps / 1000, (kps % 1000) / 10); } __weak int arch_resume_nosmt(void) { return 0; } /** * create_image - Create a hibernation image. * @platform_mode: Whether or not to use the platform driver. * * Execute device drivers' "late" and "noirq" freeze callbacks, create a * hibernation image and run the drivers' "noirq" and "early" thaw callbacks. * * Control reappears in this routine after the subsequent restore. */ static int create_image(int platform_mode) { int error; error = dpm_suspend_end(PMSG_FREEZE); if (error) { pr_err("Some devices failed to power down, aborting\n"); return error; } error = platform_pre_snapshot(platform_mode); if (error || hibernation_test(TEST_PLATFORM)) goto Platform_finish; error = pm_sleep_disable_secondary_cpus(); if (error || hibernation_test(TEST_CPUS)) goto Enable_cpus; local_irq_disable(); system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) { pr_err("Some system devices failed to power down, aborting\n"); goto Enable_irqs; } if (hibernation_test(TEST_CORE) || pm_wakeup_pending()) goto Power_up; in_suspend = 1; save_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); /* Restore control flow magically appears here */ restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) pr_err("Error %d creating image\n", error); if (!in_suspend) { events_check_enabled = false; clear_or_poison_free_pages(); } platform_leave(platform_mode); Power_up: syscore_resume(); Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: pm_sleep_enable_secondary_cpus(); /* Allow architectures to do nosmt-specific post-resume dances */ if (!in_suspend) error = arch_resume_nosmt(); Platform_finish: platform_finish(platform_mode); dpm_resume_start(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); return error; } static void shrink_shmem_memory(void) { struct sysinfo info; unsigned long nr_shmem_pages, nr_freed_pages; si_meminfo(&info); nr_shmem_pages = info.sharedram; /* current page count used for shmem */ /* * The intent is to reclaim all shmem pages. Though shrink_all_memory() can * only reclaim about half of them, it's enough for creating the hibernation * image. */ nr_freed_pages = shrink_all_memory(nr_shmem_pages); pr_debug("requested to reclaim %lu shmem pages, actually freed %lu pages\n", nr_shmem_pages, nr_freed_pages); } /** * hibernation_snapshot - Quiesce devices and create a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * * This routine must be called with system_transition_mutex held. */ int hibernation_snapshot(int platform_mode) { pm_message_t msg; int error; pm_suspend_clear_flags(); error = platform_begin(platform_mode); if (error) goto Close; /* Preallocate image memory before shutting down devices. */ error = hibernate_preallocate_memory(); if (error) goto Close; error = freeze_kernel_threads(); if (error) goto Cleanup; if (hibernation_test(TEST_FREEZER)) { /* * Indicate to the caller that we are returning due to a * successful freezer test. */ freezer_test_done = true; goto Thaw; } error = dpm_prepare(PMSG_FREEZE); if (error) { dpm_complete(PMSG_RECOVER); goto Thaw; } /* * Device drivers may move lots of data to shmem in dpm_prepare(). The shmem * pages will use lots of system memory, causing hibernation image creation * fail due to insufficient free memory. * This call is to force flush the shmem pages to swap disk and reclaim * the system memory so that image creation can succeed. */ shrink_shmem_memory(); console_suspend_all(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); if (error || hibernation_test(TEST_DEVICES)) platform_recover(platform_mode); else error = create_image(platform_mode); /* * In the case that we call create_image() above, the control * returns here (1) after the image has been created or the * image creation has failed and (2) after a successful restore. */ /* We may need to release the preallocated image pages here. */ if (error || !in_suspend) swsusp_free(); msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE; dpm_resume(msg); if (error || !in_suspend) pm_restore_gfp_mask(); console_resume_all(); dpm_complete(msg); Close: platform_end(platform_mode); return error; Thaw: thaw_kernel_threads(); Cleanup: swsusp_free(); goto Close; } int __weak hibernate_resume_nonboot_cpu_disable(void) { return suspend_disable_secondary_cpus(); } /** * resume_target_kernel - Restore system state from a hibernation image. * @platform_mode: Whether or not to use the platform driver. * * Execute device drivers' "noirq" and "late" freeze callbacks, restore the * contents of highmem that have not been restored yet from the image and run * the low-level code that will restore the remaining contents of memory and * switch to the just restored target kernel. */ static int resume_target_kernel(bool platform_mode) { int error; error = dpm_suspend_end(PMSG_QUIESCE); if (error) { pr_err("Some devices failed to power down, aborting resume\n"); return error; } error = platform_pre_restore(platform_mode); if (error) goto Cleanup; cpuidle_pause(); error = hibernate_resume_nonboot_cpu_disable(); if (error) goto Enable_cpus; local_irq_disable(); system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) goto Enable_irqs; save_processor_state(); error = restore_highmem(); if (!error) { error = swsusp_arch_resume(); /* * The code below is only ever reached in case of a failure. * Otherwise, execution continues at the place where * swsusp_arch_suspend() was called. */ BUG_ON(!error); /* * This call to restore_highmem() reverts the changes made by * the previous one. */ restore_highmem(); } /* * The only reason why swsusp_arch_resume() can fail is memory being * very tight, so we have to free it as soon as we can to avoid * subsequent failures. */ swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); syscore_resume(); Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: pm_sleep_enable_secondary_cpus(); Cleanup: platform_restore_cleanup(platform_mode); dpm_resume_start(PMSG_RECOVER); return error; } /** * hibernation_restore - Quiesce devices and restore from a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * * This routine must be called with system_transition_mutex held. If it is * successful, control reappears in the restored target kernel in * hibernation_snapshot(). */ int hibernation_restore(int platform_mode) { int error; pm_prepare_console(); console_suspend_all(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); /* * The above should either succeed and jump to the new kernel, * or return with an error. Otherwise things are just * undefined, so let's be paranoid. */ BUG_ON(!error); } dpm_resume_end(PMSG_RECOVER); console_resume_all(); pm_restore_console(); return error; } /** * hibernation_platform_enter - Power off the system using the platform driver. */ int hibernation_platform_enter(void) { int error; if (!hibernation_ops) return -ENOSYS; /* * We have cancelled the power transition by running * hibernation_ops->finish() before saving the image, so we should let * the firmware know that we're going to enter the sleep state after all */ error = hibernation_ops->begin(PMSG_HIBERNATE); if (error) goto Close; entering_platform_hibernation = true; console_suspend_all(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) hibernation_ops->recover(); goto Resume_devices; } error = dpm_suspend_end(PMSG_HIBERNATE); if (error) goto Resume_devices; error = hibernation_ops->prepare(); if (error) goto Platform_finish; error = pm_sleep_disable_secondary_cpus(); if (error) goto Enable_cpus; local_irq_disable(); system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) goto Enable_irqs; if (pm_wakeup_pending()) { error = -EAGAIN; goto Power_up; } hibernation_ops->enter(); /* We should never get here */ while (1); Power_up: syscore_resume(); Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: pm_sleep_enable_secondary_cpus(); Platform_finish: hibernation_ops->finish(); dpm_resume_start(PMSG_RESTORE); Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); console_resume_all(); Close: hibernation_ops->end(); return error; } /** * power_down - Shut the machine down for hibernation. * * Use the platform driver, if configured, to put the system into the sleep * state corresponding to hibernation, or try to power it off or reboot, * depending on the value of hibernation_mode. */ static void power_down(void) { int error; #ifdef CONFIG_SUSPEND if (hibernation_mode == HIBERNATION_SUSPEND) { pm_restore_gfp_mask(); error = suspend_devices_and_enter(mem_sleep_current); if (!error) goto exit; hibernation_mode = hibernation_ops ? HIBERNATION_PLATFORM : HIBERNATION_SHUTDOWN; } #endif switch (hibernation_mode) { case HIBERNATION_REBOOT: kernel_restart(NULL); break; case HIBERNATION_PLATFORM: error = hibernation_platform_enter(); if (error == -EAGAIN || error == -EBUSY) { events_check_enabled = false; pr_info("Wakeup event detected during hibernation, rolling back.\n"); goto exit; } fallthrough; case HIBERNATION_SHUTDOWN: if (kernel_can_power_off()) { entering_platform_hibernation = true; kernel_power_off(); entering_platform_hibernation = false; } break; } kernel_halt(); /* * Valid image is on the disk, if we continue we risk serious data * corruption after resume. */ pr_crit("Power down manually\n"); while (1) cpu_relax(); exit: /* Match the pm_restore_gfp_mask() call in hibernate(). */ pm_restrict_gfp_mask(); /* Restore swap signature. */ error = swsusp_unmark(); if (error) pr_err("Swap will be unusable! Try swapon -a.\n"); } static int load_image_and_restore(void) { int error; unsigned int flags; pm_pr_dbg("Loading hibernation image.\n"); lock_device_hotplug(); error = create_basic_memory_bitmaps(); if (error) { swsusp_close(); goto Unlock; } error = swsusp_read(&flags); swsusp_close(); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); pr_err("Failed to load image, recovering.\n"); swsusp_free(); free_basic_memory_bitmaps(); Unlock: unlock_device_hotplug(); return error; } #define COMPRESSION_ALGO_LZO "lzo" #define COMPRESSION_ALGO_LZ4 "lz4" /** * hibernate - Carry out system hibernation, including saving the image. */ int hibernate(void) { bool snapshot_test = false; unsigned int sleep_flags; int error; if (!hibernation_available()) { pm_pr_dbg("Hibernation not available.\n"); return -EPERM; } /* * Query for the compression algorithm support if compression is enabled. */ if (!nocompress) { strscpy(hib_comp_algo, hibernate_compressor); if (!crypto_has_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC)) { pr_err("%s compression is not available\n", hib_comp_algo); return -EOPNOTSUPP; } } sleep_flags = lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; goto Unlock; } pr_info("hibernation entry\n"); pm_prepare_console(); error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION); if (error) goto Restore; ksys_sync_helper(); if (filesystem_freeze_enabled) filesystems_freeze(); error = freeze_processes(); if (error) goto Exit; lock_device_hotplug(); /* Allocate memory management structures */ error = create_basic_memory_bitmaps(); if (error) goto Thaw; error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM); if (error || freezer_test_done) goto Free_bitmaps; if (in_suspend) { unsigned int flags = 0; if (hibernation_mode == HIBERNATION_PLATFORM) flags |= SF_PLATFORM_MODE; if (nocompress) { flags |= SF_NOCOMPRESS_MODE; } else { flags |= SF_CRC32_MODE; /* * By default, LZO compression is enabled. Use SF_COMPRESSION_ALG_LZ4 * to override this behaviour and use LZ4. * * Refer kernel/power/power.h for more details */ if (!strcmp(hib_comp_algo, COMPRESSION_ALGO_LZ4)) flags |= SF_COMPRESSION_ALG_LZ4; else flags |= SF_COMPRESSION_ALG_LZO; } pm_pr_dbg("Writing hibernation image.\n"); error = swsusp_write(flags); swsusp_free(); if (!error) { if (hibernation_mode == HIBERNATION_TEST_RESUME) snapshot_test = true; else power_down(); } in_suspend = 0; pm_restore_gfp_mask(); } else { pm_pr_dbg("Hibernation image restored successfully.\n"); } Free_bitmaps: free_basic_memory_bitmaps(); Thaw: unlock_device_hotplug(); if (snapshot_test) { pm_pr_dbg("Checking hibernation image\n"); error = swsusp_check(false); if (!error) error = load_image_and_restore(); } thaw_processes(); /* Don't bother checking whether freezer_test_done is true */ freezer_test_done = false; Exit: filesystems_thaw(); pm_notifier_call_chain(PM_POST_HIBERNATION); Restore: pm_restore_console(); hibernate_release(); Unlock: unlock_system_sleep(sleep_flags); pr_info("hibernation exit\n"); return error; } /** * hibernate_quiet_exec - Execute a function with all devices frozen. * @func: Function to execute. * @data: Data pointer to pass to @func. * * Return the @func return value or an error code if it cannot be executed. */ int hibernate_quiet_exec(int (*func)(void *data), void *data) { unsigned int sleep_flags; int error; sleep_flags = lock_system_sleep(); if (!hibernate_acquire()) { error = -EBUSY; goto unlock; } pm_prepare_console(); error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION); if (error) goto restore; if (filesystem_freeze_enabled) filesystems_freeze(); error = freeze_processes(); if (error) goto exit; lock_device_hotplug(); pm_suspend_clear_flags(); error = platform_begin(true); if (error) goto thaw; error = freeze_kernel_threads(); if (error) goto thaw; error = dpm_prepare(PMSG_FREEZE); if (error) goto dpm_complete; console_suspend_all(); error = dpm_suspend(PMSG_FREEZE); if (error) goto dpm_resume; error = dpm_suspend_end(PMSG_FREEZE); if (error) goto dpm_resume; error = platform_pre_snapshot(true); if (error) goto skip; error = func(data); skip: platform_finish(true); dpm_resume_start(PMSG_THAW); dpm_resume: dpm_resume(PMSG_THAW); console_resume_all(); dpm_complete: dpm_complete(PMSG_THAW); thaw_kernel_threads(); thaw: platform_end(true); unlock_device_hotplug(); thaw_processes(); exit: filesystems_thaw(); pm_notifier_call_chain(PM_POST_HIBERNATION); restore: pm_restore_console(); hibernate_release(); unlock: unlock_system_sleep(sleep_flags); return error; } EXPORT_SYMBOL_GPL(hibernate_quiet_exec); static int __init find_resume_device(void) { if (!strlen(resume_file)) return -ENOENT; pm_pr_dbg("Checking hibernation image partition %s\n", resume_file); if (resume_delay) { pr_info("Waiting %dsec before reading resume device ...\n", resume_delay); ssleep(resume_delay); } /* Check if the device is there */ if (!early_lookup_bdev(resume_file, &swsusp_resume_device)) return 0; /* * Some device discovery might still be in progress; we need to wait for * this to finish. */ wait_for_device_probe(); if (resume_wait) { while (early_lookup_bdev(resume_file, &swsusp_resume_device)) msleep(10); async_synchronize_full(); } return early_lookup_bdev(resume_file, &swsusp_resume_device); } static int software_resume(void) { int error; pm_pr_dbg("Hibernation image partition %d:%d present\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); pm_pr_dbg("Looking for hibernation image.\n"); mutex_lock(&system_transition_mutex); error = swsusp_check(true); if (error) goto Unlock; /* * Check if the hibernation image is compressed. If so, query for * the algorithm support. */ if (!(swsusp_header_flags & SF_NOCOMPRESS_MODE)) { if (swsusp_header_flags & SF_COMPRESSION_ALG_LZ4) strscpy(hib_comp_algo, COMPRESSION_ALGO_LZ4); else strscpy(hib_comp_algo, COMPRESSION_ALGO_LZO); if (!crypto_has_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC)) { pr_err("%s compression is not available\n", hib_comp_algo); error = -EOPNOTSUPP; goto Unlock; } } /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; swsusp_close(); goto Unlock; } pr_info("resume from hibernation\n"); pm_prepare_console(); error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE); if (error) goto Restore; if (filesystem_freeze_enabled) filesystems_freeze(); pm_pr_dbg("Preparing processes for hibernation restore.\n"); error = freeze_processes(); if (error) { filesystems_thaw(); goto Close_Finish; } error = freeze_kernel_threads(); if (error) { thaw_processes(); filesystems_thaw(); goto Close_Finish; } error = load_image_and_restore(); thaw_processes(); filesystems_thaw(); Finish: pm_notifier_call_chain(PM_POST_RESTORE); Restore: pm_restore_console(); pr_info("resume failed (%d)\n", error); hibernate_release(); /* For success case, the suspend path will release the lock */ Unlock: mutex_unlock(&system_transition_mutex); pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: swsusp_close(); goto Finish; } /** * software_resume_initcall - Resume from a saved hibernation image. * * This routine is called as a late initcall, when all devices have been * discovered and initialized already. * * The image reading code is called to see if there is a hibernation image * available for reading. If that is the case, devices are quiesced and the * contents of memory is restored from the saved image. * * If this is successful, control reappears in the restored target kernel in * hibernation_snapshot() which returns to hibernate(). Otherwise, the routine * attempts to recover gracefully and make the kernel return to the normal mode * of operation. */ static int __init software_resume_initcall(void) { /* * If the user said "noresume".. bail out early. */ if (noresume || !hibernation_available()) return 0; if (!swsusp_resume_device) { int error = find_resume_device(); if (error) return error; } return software_resume(); } late_initcall_sync(software_resume_initcall); static const char * const hibernation_modes[] = { [HIBERNATION_PLATFORM] = "platform", [HIBERNATION_SHUTDOWN] = "shutdown", [HIBERNATION_REBOOT] = "reboot", #ifdef CONFIG_SUSPEND [HIBERNATION_SUSPEND] = "suspend", #endif [HIBERNATION_TEST_RESUME] = "test_resume", }; /* * /sys/power/disk - Control hibernation mode. * * Hibernation can be handled in several ways. There are a few different ways * to put the system into the sleep state: using the platform driver (e.g. ACPI * or other hibernation_ops), powering it off or rebooting it (for testing * mostly). * * The sysfs file /sys/power/disk provides an interface for selecting the * hibernation mode to use. Reading from this file causes the available modes * to be printed. There are 3 modes that can be supported: * * 'platform' * 'shutdown' * 'reboot' * * If a platform hibernation driver is in use, 'platform' will be supported * and will be used by default. Otherwise, 'shutdown' will be used by default. * The selected option (i.e. the one corresponding to the current value of * hibernation_mode) is enclosed by a square bracket. * * To select a given hibernation mode it is necessary to write the mode's * string representation (as returned by reading from /sys/power/disk) back * into /sys/power/disk. */ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t count = 0; int i; if (!hibernation_available()) return sysfs_emit(buf, "[disabled]\n"); for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (!hibernation_modes[i]) continue; switch (i) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif case HIBERNATION_TEST_RESUME: break; case HIBERNATION_PLATFORM: if (hibernation_ops) break; /* not a valid mode, continue with loop */ continue; } if (i == hibernation_mode) count += sysfs_emit_at(buf, count, "[%s] ", hibernation_modes[i]); else count += sysfs_emit_at(buf, count, "%s ", hibernation_modes[i]); } /* Convert the last space to a newline if needed. */ if (count > 0) buf[count - 1] = '\n'; return count; } static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { int mode = HIBERNATION_INVALID; unsigned int sleep_flags; int error = 0; int len; char *p; int i; if (!hibernation_available()) return -EPERM; p = memchr(buf, '\n', n); len = p ? p - buf : n; sleep_flags = lock_system_sleep(); for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (len == strlen(hibernation_modes[i]) && !strncmp(buf, hibernation_modes[i], len)) { mode = i; break; } } if (mode != HIBERNATION_INVALID) { switch (mode) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif case HIBERNATION_TEST_RESUME: hibernation_mode = mode; break; case HIBERNATION_PLATFORM: if (hibernation_ops) hibernation_mode = mode; else error = -EINVAL; } } else error = -EINVAL; if (!error) pm_pr_dbg("Hibernation mode set to '%s'\n", hibernation_modes[mode]); unlock_system_sleep(sleep_flags); return error ? error : n; } power_attr(disk); static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%d:%d\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); } static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned int sleep_flags; int len = n; char *name; dev_t dev; int error; if (!hibernation_available()) return n; if (len && buf[len-1] == '\n') len--; name = kstrndup(buf, len, GFP_KERNEL); if (!name) return -ENOMEM; error = lookup_bdev(name, &dev); if (error) { unsigned maj, min, offset; char *p, dummy; error = 0; if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { dev = MKDEV(maj, min); if (maj != MAJOR(dev) || min != MINOR(dev)) error = -EINVAL; } else { dev = new_decode_dev(simple_strtoul(name, &p, 16)); if (*p) error = -EINVAL; } } kfree(name); if (error) return error; sleep_flags = lock_system_sleep(); swsusp_resume_device = dev; unlock_system_sleep(sleep_flags); pm_pr_dbg("Configured hibernation resume from disk to %u\n", swsusp_resume_device); noresume = 0; software_resume(); return n; } power_attr(resume); static ssize_t resume_offset_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)swsusp_resume_block); } static ssize_t resume_offset_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long long offset; int rc; rc = kstrtoull(buf, 0, &offset); if (rc) return rc; swsusp_resume_block = offset; return n; } power_attr(resume_offset); static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", image_size); } static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long size; if (sscanf(buf, "%lu", &size) == 1) { image_size = size; return n; } return -EINVAL; } power_attr(image_size); static ssize_t reserved_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", reserved_size); } static ssize_t reserved_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long size; if (sscanf(buf, "%lu", &size) == 1) { reserved_size = size; return n; } return -EINVAL; } power_attr(reserved_size); static struct attribute *g[] = { &disk_attr.attr, &resume_offset_attr.attr, &resume_attr.attr, &image_size_attr.attr, &reserved_size_attr.attr, NULL, }; static const struct attribute_group attr_group = { .attrs = g, }; static int __init pm_disk_init(void) { return sysfs_create_group(power_kobj, &attr_group); } core_initcall(pm_disk_init); static int __init resume_setup(char *str) { if (noresume) return 1; strscpy(resume_file, str); return 1; } static int __init resume_offset_setup(char *str) { unsigned long long offset; if (noresume) return 1; if (sscanf(str, "%llu", &offset) == 1) swsusp_resume_block = offset; return 1; } static int __init hibernate_setup(char *str) { if (!strncmp(str, "noresume", 8)) { noresume = 1; } else if (!strncmp(str, "nocompress", 10)) { nocompress = 1; } else if (!strncmp(str, "no", 2)) { noresume = 1; nohibernate = 1; } else if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && !strncmp(str, "protect_image", 13)) { enable_restore_image_protection(); } return 1; } static int __init noresume_setup(char *str) { noresume = 1; return 1; } static int __init resumewait_setup(char *str) { resume_wait = 1; return 1; } static int __init resumedelay_setup(char *str) { int rc = kstrtouint(str, 0, &resume_delay); if (rc) pr_warn("resumedelay: bad option string '%s'\n", str); return 1; } static int __init nohibernate_setup(char *str) { noresume = 1; nohibernate = 1; return 1; } static const char * const comp_alg_enabled[] = { #if IS_ENABLED(CONFIG_CRYPTO_LZO) COMPRESSION_ALGO_LZO, #endif #if IS_ENABLED(CONFIG_CRYPTO_LZ4) COMPRESSION_ALGO_LZ4, #endif }; static int hibernate_compressor_param_set(const char *compressor, const struct kernel_param *kp) { int index, ret; if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; index = sysfs_match_string(comp_alg_enabled, compressor); if (index >= 0) { ret = param_set_copystring(comp_alg_enabled[index], kp); if (!ret) strscpy(hib_comp_algo, comp_alg_enabled[index]); } else { ret = index; } mutex_unlock(&system_transition_mutex); if (ret) pr_debug("Cannot set specified compressor %s\n", compressor); return ret; } static const struct kernel_param_ops hibernate_compressor_param_ops = { .set = hibernate_compressor_param_set, .get = param_get_string, }; static struct kparam_string hibernate_compressor_param_string = { .maxlen = sizeof(hibernate_compressor), .string = hibernate_compressor, }; module_param_cb(compressor, &hibernate_compressor_param_ops, &hibernate_compressor_param_string, 0644); MODULE_PARM_DESC(compressor, "Compression algorithm to be used with hibernation"); __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); __setup("hibernate=", hibernate_setup); __setup("resumewait", resumewait_setup); __setup("resumedelay=", resumedelay_setup); __setup("nohibernate", nohibernate_setup); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.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/signal.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> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const void *macvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class macvtap_class = { .name = "macvtap", .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct macvtap_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; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; 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 = macvlan_common_newlink(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_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(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_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(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_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 macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int __init macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void __exit macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_DESCRIPTION("MAC-VLAN based tap driver"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IRQDESC_H #define _LINUX_IRQDESC_H #include <linux/rcupdate.h> #include <linux/kobject.h> #include <linux/mutex.h> /* * Core internal functions to deal with irq descriptors */ struct irq_affinity_notify; struct proc_dir_entry; struct module; struct irq_desc; struct irq_domain; struct pt_regs; /** * struct irqstat - interrupt statistics * @cnt: real-time interrupt count * @ref: snapshot of interrupt count */ struct irqstat { unsigned int cnt; #ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT unsigned int ref; #endif }; /** * struct irq_desc - interrupt descriptor * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu * @handle_irq: highlevel irq-events handler * @action: the irq action chain * @status_use_accessors: status information * @core_internal_state__do_not_mess_with_it: core internal status information * @depth: disable-depth, for nested irq_disable() calls * @wake_depth: enable depth, for multiple irq_set_irq_wake() callers * @tot_count: stats field for non-percpu irqs * @irq_count: stats field to detect stalled irqs * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @threads_handled: stats field for deferred spurious detection of threaded handlers * @threads_handled_last: comparator field for deferred spurious detection of threaded handlers * @lock: locking for SMP * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes * @pending_mask: pending rebalanced interrupts * @threads_oneshot: bitfield to handle shared oneshot threads * @threads_active: number of irqaction threads currently running * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers * @nr_actions: number of installed actions on this descriptor * @no_suspend_depth: number of irqactions on a irq descriptor with * IRQF_NO_SUSPEND set * @force_resume_depth: number of irqactions on a irq descriptor with * IRQF_FORCE_RESUME set * @rcu: rcu head for delayed free * @kobj: kobject used to represent this struct in sysfs * @request_mutex: mutex to protect request/free before locking desc->lock * @dir: /proc/irq/ procfs entry * @debugfs_file: dentry for the debugfs file * @name: flow handler name for /proc/interrupts output */ struct irq_desc { struct irq_common_data irq_common_data; struct irq_data irq_data; struct irqstat __percpu *kstat_irqs; irq_flow_handler_t handle_irq; struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; unsigned int core_internal_state__do_not_mess_with_it; unsigned int depth; /* nested irq disables */ unsigned int wake_depth; /* nested wake enables */ unsigned int tot_count; unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; atomic_t threads_handled; int threads_handled_last; raw_spinlock_t lock; struct cpumask *percpu_enabled; const struct cpumask *percpu_affinity; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; struct irq_affinity_notify *affinity_notify; #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_var_t pending_mask; #endif #endif unsigned long threads_oneshot; atomic_t threads_active; wait_queue_head_t wait_for_threads; #ifdef CONFIG_PM_SLEEP unsigned int nr_actions; unsigned int no_suspend_depth; unsigned int cond_suspend_depth; unsigned int force_resume_depth; #endif #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif #ifdef CONFIG_GENERIC_IRQ_DEBUGFS struct dentry *debugfs_file; const char *dev_name; #endif #ifdef CONFIG_SPARSE_IRQ struct rcu_head rcu; struct kobject kobj; #endif struct mutex request_mutex; int parent_irq; struct module *owner; const char *name; #ifdef CONFIG_HARDIRQS_SW_RESEND struct hlist_node resend_node; #endif } ____cacheline_internodealigned_in_smp; #ifdef CONFIG_SPARSE_IRQ extern void irq_lock_sparse(void); extern void irq_unlock_sparse(void); #else static inline void irq_lock_sparse(void) { } static inline void irq_unlock_sparse(void) { } extern struct irq_desc irq_desc[NR_IRQS]; #endif static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc, unsigned int cpu) { return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) { return container_of(data->common, struct irq_desc, irq_common_data); } static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) { return desc->irq_data.irq; } static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc) { return &desc->irq_data; } static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc) { return desc->irq_data.chip; } static inline void *irq_desc_get_chip_data(struct irq_desc *desc) { return desc->irq_data.chip_data; } static inline void *irq_desc_get_handler_data(struct irq_desc *desc) { return desc->irq_common_data.handler_data; } /* * Architectures call this to let the generic IRQ layer * handle an interrupt. */ static inline void generic_handle_irq_desc(struct irq_desc *desc) { desc->handle_irq(desc); } int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); int generic_handle_irq_safe(unsigned int irq); #ifdef CONFIG_IRQ_DOMAIN /* * Convert a HW interrupt number to a logical one using a IRQ domain, * and handle the result interrupt number. Return -EINVAL if * conversion failed. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq); int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq); #endif /* Test to see if a driver has successfully requested an irq */ static inline int irq_desc_has_action(struct irq_desc *desc) { return desc && desc->action != NULL; } /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq * @handler: Flow control handler function for this interrupt * * Sets the handler in the irq descriptor associated to @data. * * Must be called with irq_desc locked and valid parameters. Typical * call site is the irq_set_type() callback. */ static inline void irq_set_handler_locked(struct irq_data *data, irq_flow_handler_t handler) { struct irq_desc *desc = irq_data_to_desc(data); desc->handle_irq = handler; } /** * irq_set_chip_handler_name_locked - Set chip, handler and name from a locked region * @data: Pointer to the irq_data structure for which the chip is set * @chip: Pointer to the new irq chip * @handler: Flow control handler function for this interrupt * @name: Name of the interrupt * * Replace the irq chip at the proper hierarchy level in @data and * sets the handler and name in the associated irq descriptor. * * Must be called with irq_desc locked and valid parameters. */ static inline void irq_set_chip_handler_name_locked(struct irq_data *data, const struct irq_chip *chip, irq_flow_handler_t handler, const char *name) { struct irq_desc *desc = irq_data_to_desc(data); desc->handle_irq = handler; desc->name = name; data->chip = (struct irq_chip *)chip; } bool irq_check_status_bit(unsigned int irq, unsigned int bitmask); static inline bool irq_balancing_disabled(unsigned int irq) { return irq_check_status_bit(irq, IRQ_NO_BALANCING_MASK); } static inline bool irq_is_percpu(unsigned int irq) { return irq_check_status_bit(irq, IRQ_PER_CPU); } static inline bool irq_is_percpu_devid(unsigned int irq) { return irq_check_status_bit(irq, IRQ_PER_CPU_DEVID); } void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, struct lock_class_key *request_class); static inline void irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, struct lock_class_key *request_class) { if (IS_ENABLED(CONFIG_LOCKDEP)) __irq_set_lockdep_class(irq, lock_class, request_class); } #endif |
| 6 6 12 12 12 10 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 | /* * PCM I/O Plug-In Interface * Copyright (c) 1999 by Jaroslav Kysela <perex@perex.cz> * * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Library General Public License as * published by the Free Software Foundation; either version 2 of * the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU Library General Public License for more details. * * You should have received a copy of the GNU Library General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ #include <linux/time.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include "pcm_plugin.h" #define pcm_write(plug,buf,count) snd_pcm_oss_write3(plug,buf,count,1) #define pcm_writev(plug,vec,count) snd_pcm_oss_writev3(plug,vec,count) #define pcm_read(plug,buf,count) snd_pcm_oss_read3(plug,buf,count,1) #define pcm_readv(plug,vec,count) snd_pcm_oss_readv3(plug,vec,count) /* * Basic io plugin */ static snd_pcm_sframes_t io_playback_transfer(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames) { if (snd_BUG_ON(!plugin)) return -ENXIO; if (snd_BUG_ON(!src_channels)) return -ENXIO; if (plugin->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED) { return pcm_write(plugin->plug, src_channels->area.addr, frames); } else { int channel, channels = plugin->dst_format.channels; void **bufs = (void**)plugin->extra_data; if (snd_BUG_ON(!bufs)) return -ENXIO; for (channel = 0; channel < channels; channel++) { if (src_channels[channel].enabled) bufs[channel] = src_channels[channel].area.addr; else bufs[channel] = NULL; } return pcm_writev(plugin->plug, bufs, frames); } } static snd_pcm_sframes_t io_capture_transfer(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames) { if (snd_BUG_ON(!plugin)) return -ENXIO; if (snd_BUG_ON(!dst_channels)) return -ENXIO; if (plugin->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED) { return pcm_read(plugin->plug, dst_channels->area.addr, frames); } else { int channel, channels = plugin->dst_format.channels; void **bufs = (void**)plugin->extra_data; if (snd_BUG_ON(!bufs)) return -ENXIO; for (channel = 0; channel < channels; channel++) { if (dst_channels[channel].enabled) bufs[channel] = dst_channels[channel].area.addr; else bufs[channel] = NULL; } return pcm_readv(plugin->plug, bufs, frames); } return 0; } static snd_pcm_sframes_t io_src_channels(struct snd_pcm_plugin *plugin, snd_pcm_uframes_t frames, struct snd_pcm_plugin_channel **channels) { int err; unsigned int channel; struct snd_pcm_plugin_channel *v; err = snd_pcm_plugin_client_channels(plugin, frames, &v); if (err < 0) return err; *channels = v; if (plugin->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED) { for (channel = 0; channel < plugin->src_format.channels; ++channel, ++v) v->wanted = 1; } return frames; } int snd_pcm_plugin_build_io(struct snd_pcm_substream *plug, struct snd_pcm_hw_params *params, struct snd_pcm_plugin **r_plugin) { int err; struct snd_pcm_plugin_format format; struct snd_pcm_plugin *plugin; if (snd_BUG_ON(!r_plugin)) return -ENXIO; *r_plugin = NULL; if (snd_BUG_ON(!plug || !params)) return -ENXIO; format.format = params_format(params); format.rate = params_rate(params); format.channels = params_channels(params); err = snd_pcm_plugin_build(plug, "I/O io", &format, &format, sizeof(void *) * format.channels, &plugin); if (err < 0) return err; plugin->access = params_access(params); if (snd_pcm_plug_stream(plug) == SNDRV_PCM_STREAM_PLAYBACK) { plugin->transfer = io_playback_transfer; if (plugin->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED) plugin->client_channels = io_src_channels; } else { plugin->transfer = io_capture_transfer; } *r_plugin = plugin; return 0; } |
| 110 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash algorithms. * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_HASH_H #define _CRYPTO_INTERNAL_HASH_H #include <crypto/algapi.h> #include <crypto/hash.h> /* Set this bit to handle partial blocks in the API. */ #define CRYPTO_AHASH_ALG_BLOCK_ONLY 0x01000000 /* Set this bit if final requires at least one byte. */ #define CRYPTO_AHASH_ALG_FINAL_NONZERO 0x02000000 /* Set this bit if finup can deal with multiple blocks. */ #define CRYPTO_AHASH_ALG_FINUP_MAX 0x04000000 /* This bit is set by the Crypto API if export_core is not supported. */ #define CRYPTO_AHASH_ALG_NO_EXPORT_CORE 0x08000000 #define HASH_FBREQ_ON_STACK(name, req) \ char __##name##_req[sizeof(struct ahash_request) + \ MAX_SYNC_HASH_REQSIZE] CRYPTO_MINALIGN_ATTR; \ struct ahash_request *name = ahash_fbreq_on_stack_init( \ __##name##_req, (req)) struct ahash_request; struct scatterlist; struct crypto_hash_walk { const char *data; unsigned int offset; unsigned int flags; struct page *pg; unsigned int entrylen; unsigned int total; struct scatterlist *sg; }; struct ahash_instance { void (*free)(struct ahash_instance *inst); union { struct { char head[offsetof(struct ahash_alg, halg.base)]; struct crypto_instance base; } s; struct ahash_alg alg; }; }; struct shash_instance { void (*free)(struct shash_instance *inst); union { struct { char head[offsetof(struct shash_alg, base)]; struct crypto_instance base; } s; struct shash_alg alg; }; }; struct crypto_ahash_spawn { struct crypto_spawn base; }; struct crypto_shash_spawn { struct crypto_spawn base; }; int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err); int crypto_hash_walk_first(struct ahash_request *req, struct crypto_hash_walk *walk); static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) { return !(walk->entrylen | walk->total); } int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); void crypto_unregister_ahashes(struct ahash_alg *algs, int count); int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst); void ahash_free_singlespawn_instance(struct ahash_instance *inst); int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); static inline bool crypto_shash_alg_has_setkey(struct shash_alg *alg) { return alg->setkey != shash_no_setkey; } bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg); static inline bool crypto_shash_alg_needs_key(struct shash_alg *alg) { return crypto_shash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } static inline bool crypto_hash_alg_needs_key(struct hash_alg_common *alg) { return crypto_hash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } static inline bool crypto_hash_no_export_core(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->base.cra_flags & CRYPTO_AHASH_ALG_NO_EXPORT_CORE; } int crypto_grab_ahash(struct crypto_ahash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_ahash(struct crypto_ahash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct hash_alg_common *crypto_spawn_ahash_alg( struct crypto_ahash_spawn *spawn) { return __crypto_hash_alg_common(spawn->base.alg); } int crypto_register_shash(struct shash_alg *alg); void crypto_unregister_shash(struct shash_alg *alg); int crypto_register_shashes(struct shash_alg *algs, int count); void crypto_unregister_shashes(struct shash_alg *algs, int count); int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst); void shash_free_singlespawn_instance(struct shash_instance *inst); int crypto_grab_shash(struct crypto_shash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_shash(struct crypto_shash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct shash_alg *crypto_spawn_shash_alg( struct crypto_shash_spawn *spawn) { return __crypto_shash_alg(spawn->base.alg); } int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc); static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm) { return crypto_tfm_ctx(crypto_ahash_tfm(tfm)); } static inline void *crypto_ahash_ctx_dma(struct crypto_ahash *tfm) { return crypto_tfm_ctx_dma(crypto_ahash_tfm(tfm)); } static inline struct ahash_alg *__crypto_ahash_alg(struct crypto_alg *alg) { return container_of(__crypto_hash_alg_common(alg), struct ahash_alg, halg); } static inline struct ahash_alg *crypto_ahash_alg(struct crypto_ahash *hash) { return container_of(crypto_hash_alg_common(hash), struct ahash_alg, halg); } static inline void crypto_ahash_set_statesize(struct crypto_ahash *tfm, unsigned int size) { tfm->statesize = size; } static inline void crypto_ahash_set_reqsize(struct crypto_ahash *tfm, unsigned int reqsize) { tfm->reqsize = reqsize; } static inline bool crypto_ahash_tested(struct crypto_ahash *tfm) { struct crypto_tfm *tfm_base = crypto_ahash_tfm(tfm); return tfm_base->__crt_alg->cra_flags & CRYPTO_ALG_TESTED; } static inline void crypto_ahash_set_reqsize_dma(struct crypto_ahash *ahash, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); ahash->reqsize = reqsize; } static inline struct crypto_instance *ahash_crypto_instance( struct ahash_instance *inst) { return &inst->s.base; } static inline struct ahash_instance *ahash_instance( struct crypto_instance *inst) { return container_of(inst, struct ahash_instance, s.base); } static inline struct ahash_instance *ahash_alg_instance( struct crypto_ahash *ahash) { return ahash_instance(crypto_tfm_alg_instance(&ahash->base)); } static inline void *ahash_instance_ctx(struct ahash_instance *inst) { return crypto_instance_ctx(ahash_crypto_instance(inst)); } static inline void *ahash_request_ctx_dma(struct ahash_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(ahash_request_ctx(req), align); } static inline void ahash_request_complete(struct ahash_request *req, int err) { crypto_request_complete(&req->base, err); } static inline u32 ahash_request_flags(struct ahash_request *req) { return crypto_request_flags(&req->base) & ~CRYPTO_AHASH_REQ_PRIVATE; } static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline int ahash_enqueue_request(struct crypto_queue *queue, struct ahash_request *request) { return crypto_enqueue_request(queue, &request->base); } static inline struct ahash_request *ahash_dequeue_request( struct crypto_queue *queue) { return ahash_request_cast(crypto_dequeue_request(queue)); } static inline void *crypto_shash_ctx(struct crypto_shash *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline struct crypto_instance *shash_crypto_instance( struct shash_instance *inst) { return &inst->s.base; } static inline struct shash_instance *shash_instance( struct crypto_instance *inst) { return container_of(inst, struct shash_instance, s.base); } static inline struct shash_instance *shash_alg_instance( struct crypto_shash *shash) { return shash_instance(crypto_tfm_alg_instance(&shash->base)); } static inline void *shash_instance_ctx(struct shash_instance *inst) { return crypto_instance_ctx(shash_crypto_instance(inst)); } static inline struct crypto_shash *crypto_spawn_shash( struct crypto_shash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_shash, base); } static inline bool ahash_request_isvirt(struct ahash_request *req) { return req->base.flags & CRYPTO_AHASH_REQ_VIRT; } static inline bool crypto_ahash_req_virt(struct crypto_ahash *tfm) { return crypto_tfm_req_virt(&tfm->base); } static inline struct crypto_ahash *crypto_ahash_fb(struct crypto_ahash *tfm) { return __crypto_ahash_cast(crypto_ahash_tfm(tfm)->fb); } static inline struct ahash_request *ahash_fbreq_on_stack_init( char *buf, struct ahash_request *old) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(old); struct ahash_request *req = (void *)buf; crypto_stack_request_init(&req->base, crypto_ahash_tfm(crypto_ahash_fb(tfm))); ahash_request_set_callback(req, ahash_request_flags(old), NULL, NULL); req->base.flags &= ~CRYPTO_AHASH_REQ_PRIVATE; req->base.flags |= old->base.flags & CRYPTO_AHASH_REQ_PRIVATE; req->src = old->src; req->result = old->result; req->nbytes = old->nbytes; return req; } /* Return the state size without partial block for block-only algorithms. */ static inline unsigned int crypto_shash_coresize(struct crypto_shash *tfm) { return crypto_shash_statesize(tfm) - crypto_shash_blocksize(tfm) - 1; } /* This can only be used if the request was never cloned. */ #define HASH_REQUEST_ZERO(name) \ memzero_explicit(__##name##_req, sizeof(__##name##_req)) /** * crypto_ahash_export_core() - extract core state for message digest * @req: reference to the ahash_request handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * Export the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_ahash_export_core(struct ahash_request *req, void *out); /** * crypto_ahash_import_core() - import core state * @req: reference to ahash_request handle the state is imported into * @in: buffer holding the state * * Import the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_ahash_import_core(struct ahash_request *req, const void *in); /** * crypto_shash_export_core() - extract core state for message digest * @desc: reference to the operational state handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * Export the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_shash_export_core(struct shash_desc *desc, void *out); /** * crypto_shash_import_core() - import core state * @desc: reference to the operational state handle the state imported into * @in: buffer holding the state * * Import the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_shash_import_core(struct shash_desc *desc, const void *in); #endif /* _CRYPTO_INTERNAL_HASH_H */ |
| 3 3 3 3 3 1 1 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> * * Vendor commands implementation based on net/wireless/nl80211.c * which is: * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ #include <net/genetlink.h> #include <linux/nfc.h> #include <linux/slab.h> #include "nfc.h" #include "llcp.h" static const struct genl_multicast_group nfc_genl_mcgrps[] = { { .name = NFC_GENL_MCAST_EVENT_NAME, }, }; static struct genl_family nfc_genl_family; static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_DEVICE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING, .len = NFC_DEVICE_NAME_MAXSIZE }, [NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 }, [NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, [NFC_ATTR_IM_PROTOCOLS] = { .type = NLA_U32 }, [NFC_ATTR_TM_PROTOCOLS] = { .type = NLA_U32 }, [NFC_ATTR_LLC_PARAM_LTO] = { .type = NLA_U8 }, [NFC_ATTR_LLC_PARAM_RW] = { .type = NLA_U8 }, [NFC_ATTR_LLC_PARAM_MIUX] = { .type = NLA_U16 }, [NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED }, [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, }; static const struct nla_policy nfc_sdp_genl_policy[NFC_SDP_ATTR_MAX + 1] = { [NFC_SDP_ATTR_URI] = { .type = NLA_STRING, .len = U8_MAX - 4 }, [NFC_SDP_ATTR_SAP] = { .type = NLA_U8 }, }; static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, struct netlink_callback *cb, int flags) { void *hdr; hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &nfc_genl_family, flags, NFC_CMD_GET_TARGET); if (!hdr) return -EMSGSIZE; genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, target->supported_protocols) || nla_put_u16(msg, NFC_ATTR_TARGET_SENS_RES, target->sens_res) || nla_put_u8(msg, NFC_ATTR_TARGET_SEL_RES, target->sel_res)) goto nla_put_failure; if (target->nfcid1_len > 0 && nla_put(msg, NFC_ATTR_TARGET_NFCID1, target->nfcid1_len, target->nfcid1)) goto nla_put_failure; if (target->sensb_res_len > 0 && nla_put(msg, NFC_ATTR_TARGET_SENSB_RES, target->sensb_res_len, target->sensb_res)) goto nla_put_failure; if (target->sensf_res_len > 0 && nla_put(msg, NFC_ATTR_TARGET_SENSF_RES, target->sensf_res_len, target->sensf_res)) goto nla_put_failure; if (target->is_iso15693) { if (nla_put_u8(msg, NFC_ATTR_TARGET_ISO15693_DSFID, target->iso15693_dsfid) || nla_put(msg, NFC_ATTR_TARGET_ISO15693_UID, sizeof(target->iso15693_uid), target->iso15693_uid)) goto nla_put_failure; } if (target->ats_len > 0 && nla_put(msg, NFC_ATTR_TARGET_ATS, target->ats_len, target->ats)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct nfc_dev *dev; u32 idx; if (!info->info.attrs[NFC_ATTR_DEVICE_INDEX]) return ERR_PTR(-EINVAL); idx = nla_get_u32(info->info.attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return ERR_PTR(-ENODEV); return dev; } static int nfc_genl_dump_targets(struct sk_buff *skb, struct netlink_callback *cb) { int i = cb->args[0]; struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; int rc; if (!dev) { dev = __get_device_from_cb(cb); if (IS_ERR(dev)) return PTR_ERR(dev); cb->args[1] = (long) dev; } device_lock(&dev->dev); cb->seq = dev->targets_generation; while (i < dev->n_targets) { rc = nfc_genl_send_target(skb, &dev->targets[i], cb, NLM_F_MULTI); if (rc < 0) break; i++; } device_unlock(&dev->dev); cb->args[0] = i; return skb->len; } static int nfc_genl_dump_targets_done(struct netlink_callback *cb) { struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; if (dev) nfc_put_device(dev); return 0; } int nfc_genl_targets_found(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; dev->genl_data.poll_req_portid = 0; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TARGETS_FOUND); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TARGET_LOST); if (!hdr) goto free_msg; if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target_idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TM_ACTIVATED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; if (nla_put_u32(msg, NFC_ATTR_TM_PROTOCOLS, protocol)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_tm_deactivated(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TM_DEACTIVATED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_setup_device_added(struct nfc_dev *dev, struct sk_buff *msg) { if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) || nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up) || nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode)) return -1; return 0; } int nfc_genl_device_added(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_DEVICE_ADDED); if (!hdr) goto free_msg; if (nfc_genl_setup_device_added(dev, msg)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_device_removed(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_DEVICE_REMOVED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list) { struct sk_buff *msg; struct nlattr *sdp_attr, *uri_attr; struct nfc_llcp_sdp_tlv *sdres; struct hlist_node *n; void *hdr; int rc = -EMSGSIZE; int i; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_LLC_SDRES); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; sdp_attr = nla_nest_start_noflag(msg, NFC_ATTR_LLC_SDP); if (sdp_attr == NULL) { rc = -ENOMEM; goto nla_put_failure; } i = 1; hlist_for_each_entry_safe(sdres, n, sdres_list, node) { pr_debug("uri: %s, sap: %d\n", sdres->uri, sdres->sap); uri_attr = nla_nest_start_noflag(msg, i++); if (uri_attr == NULL) { rc = -ENOMEM; goto nla_put_failure; } if (nla_put_u8(msg, NFC_SDP_ATTR_SAP, sdres->sap)) goto nla_put_failure; if (nla_put_string(msg, NFC_SDP_ATTR_URI, sdres->uri)) goto nla_put_failure; nla_nest_end(msg, uri_attr); hlist_del(&sdres->node); nfc_llcp_free_sdp_tlv(sdres); } nla_nest_end(msg, sdp_attr); genlmsg_end(msg, hdr); return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); nla_put_failure: free_msg: nlmsg_free(msg); nfc_llcp_free_sdp_tlv_list(sdres_list); return rc; } int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_ADDED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, type)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_REMOVED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction) { struct nfc_se *se; struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_TRANSACTION); if (!hdr) goto free_msg; se = nfc_find_se(dev, se_idx); if (!se) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type) || nla_put(msg, NFC_ATTR_SE_AID, evt_transaction->aid_len, evt_transaction->aid) || nla_put(msg, NFC_ATTR_SE_PARAMS, evt_transaction->params_len, evt_transaction->params)) goto nla_put_failure; /* evt_transaction is no more used */ devm_kfree(&dev->dev, evt_transaction); genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: /* evt_transaction is no more used */ devm_kfree(&dev->dev, evt_transaction); nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_se_connectivity(struct nfc_dev *dev, u8 se_idx) { const struct nfc_se *se; struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_CONNECTIVITY); if (!hdr) goto free_msg; se = nfc_find_se(dev, se_idx); if (!se) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, flags, NFC_CMD_GET_DEVICE); if (!hdr) return -EMSGSIZE; if (cb) genl_dump_check_consistent(cb, hdr); if (nfc_genl_setup_device_added(dev, msg)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nfc_genl_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; bool first_call = false; if (!iter) { first_call = true; iter = kmalloc(sizeof(struct class_dev_iter), GFP_KERNEL); if (!iter) return -ENOMEM; cb->args[0] = (long) iter; } mutex_lock(&nfc_devlist_mutex); cb->seq = nfc_devlist_generation; if (first_call) { nfc_device_iter_init(iter); dev = nfc_device_iter_next(iter); } while (dev) { int rc; rc = nfc_genl_send_device(skb, dev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (rc < 0) break; dev = nfc_device_iter_next(iter); } mutex_unlock(&nfc_devlist_mutex); cb->args[1] = (long) dev; return skb->len; } static int nfc_genl_dump_devices_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; if (iter) { nfc_device_iter_exit(iter); kfree(iter); } return 0; } int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode) { struct sk_buff *msg; void *hdr; pr_debug("DEP link is up\n"); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_DEP_LINK_UP); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; if (rf_mode == NFC_RF_INITIATOR && nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target_idx)) goto nla_put_failure; if (nla_put_u8(msg, NFC_ATTR_COMM_MODE, comm_mode) || nla_put_u8(msg, NFC_ATTR_RF_MODE, rf_mode)) goto nla_put_failure; genlmsg_end(msg, hdr); dev->dep_link_up = true; genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_dep_link_down_event(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; pr_debug("DEP link is down\n"); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_DEP_LINK_DOWN); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_get_device(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct nfc_dev *dev; u32 idx; int rc = -ENOBUFS; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; goto out_putdev; } rc = nfc_genl_send_device(msg, dev, info->snd_portid, info->snd_seq, NULL, 0); if (rc < 0) goto out_free; nfc_put_device(dev); return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); out_putdev: nfc_put_device(dev); return rc; } static int nfc_genl_dev_up(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dev_up(dev); nfc_put_device(dev); return rc; } static int nfc_genl_dev_down(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dev_down(dev); nfc_put_device(dev); return rc; } static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; u32 im_protocols = 0, tm_protocols = 0; pr_debug("Poll start\n"); if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || ((!info->attrs[NFC_ATTR_IM_PROTOCOLS] && !info->attrs[NFC_ATTR_PROTOCOLS]) && !info->attrs[NFC_ATTR_TM_PROTOCOLS])) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); if (info->attrs[NFC_ATTR_TM_PROTOCOLS]) tm_protocols = nla_get_u32(info->attrs[NFC_ATTR_TM_PROTOCOLS]); if (info->attrs[NFC_ATTR_IM_PROTOCOLS]) im_protocols = nla_get_u32(info->attrs[NFC_ATTR_IM_PROTOCOLS]); else if (info->attrs[NFC_ATTR_PROTOCOLS]) im_protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; mutex_lock(&dev->genl_data.genl_data_mutex); rc = nfc_start_poll(dev, im_protocols, tm_protocols); if (!rc) dev->genl_data.poll_req_portid = info->snd_portid; mutex_unlock(&dev->genl_data.genl_data_mutex); nfc_put_device(dev); return rc; } static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); if (!dev->polling) { device_unlock(&dev->dev); nfc_put_device(dev); return -EINVAL; } device_unlock(&dev->dev); mutex_lock(&dev->genl_data.genl_data_mutex); if (dev->genl_data.poll_req_portid != info->snd_portid) { rc = -EBUSY; goto out; } rc = nfc_stop_poll(dev); dev->genl_data.poll_req_portid = 0; out: mutex_unlock(&dev->genl_data.genl_data_mutex); nfc_put_device(dev); return rc; } static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; u32 device_idx, target_idx, protocol; int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_TARGET_INDEX] || !info->attrs[NFC_ATTR_PROTOCOLS]) return -EINVAL; device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(device_idx); if (!dev) return -ENODEV; target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); protocol = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); nfc_deactivate_target(dev, target_idx, NFC_TARGET_MODE_SLEEP); rc = nfc_activate_target(dev, target_idx, protocol); nfc_put_device(dev); return rc; } static int nfc_genl_deactivate_target(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; u32 device_idx, target_idx; int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_TARGET_INDEX]) return -EINVAL; device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(device_idx); if (!dev) return -ENODEV; target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); rc = nfc_deactivate_target(dev, target_idx, NFC_TARGET_MODE_SLEEP); nfc_put_device(dev); return rc; } static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc, tgt_idx; u32 idx; u8 comm; pr_debug("DEP link up\n"); if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_COMM_MODE]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); if (!info->attrs[NFC_ATTR_TARGET_INDEX]) tgt_idx = NFC_TARGET_IDX_ANY; else tgt_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); comm = nla_get_u8(info->attrs[NFC_ATTR_COMM_MODE]); if (comm != NFC_COMM_ACTIVE && comm != NFC_COMM_PASSIVE) return -EINVAL; dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dep_link_up(dev, tgt_idx, comm); nfc_put_device(dev); return rc; } static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dep_link_down(dev); nfc_put_device(dev); return rc; } static int nfc_genl_send_params(struct sk_buff *msg, struct nfc_llcp_local *local, u32 portid, u32 seq) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, 0, NFC_CMD_LLC_GET_PARAMS); if (!hdr) return -EMSGSIZE; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, local->dev->idx) || nla_put_u8(msg, NFC_ATTR_LLC_PARAM_LTO, local->lto) || nla_put_u8(msg, NFC_ATTR_LLC_PARAM_RW, local->rw) || nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct nfc_llcp_local *local; int rc = 0; struct sk_buff *msg = NULL; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); local = nfc_llcp_find_local(dev); if (!local) { rc = -ENODEV; goto exit; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; goto put_local; } rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); put_local: nfc_llcp_local_put(local); exit: device_unlock(&dev->dev); nfc_put_device(dev); if (rc < 0) { if (msg) nlmsg_free(msg); return rc; } return genlmsg_reply(msg, info); } static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct nfc_llcp_local *local; u8 rw = 0; u16 miux = 0; u32 idx; int rc = 0; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || (!info->attrs[NFC_ATTR_LLC_PARAM_LTO] && !info->attrs[NFC_ATTR_LLC_PARAM_RW] && !info->attrs[NFC_ATTR_LLC_PARAM_MIUX])) return -EINVAL; if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) { rw = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_RW]); if (rw > LLCP_MAX_RW) return -EINVAL; } if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) { miux = nla_get_u16(info->attrs[NFC_ATTR_LLC_PARAM_MIUX]); if (miux > LLCP_MAX_MIUX) return -EINVAL; } idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); local = nfc_llcp_find_local(dev); if (!local) { rc = -ENODEV; goto exit; } if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { if (dev->dep_link_up) { rc = -EINPROGRESS; goto put_local; } local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); } if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) local->rw = rw; if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) local->miux = cpu_to_be16(miux); put_local: nfc_llcp_local_put(local); exit: device_unlock(&dev->dev); nfc_put_device(dev); return rc; } static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct nfc_llcp_local *local; struct nlattr *attr, *sdp_attrs[NFC_SDP_ATTR_MAX+1]; u32 idx; u8 tid; char *uri; int rc = 0, rem; size_t uri_len, tlvs_len; struct hlist_head sdreq_list; struct nfc_llcp_sdp_tlv *sdreq; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_LLC_SDP]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); if (dev->dep_link_up == false) { rc = -ENOLINK; goto exit; } local = nfc_llcp_find_local(dev); if (!local) { rc = -ENODEV; goto exit; } INIT_HLIST_HEAD(&sdreq_list); tlvs_len = 0; nla_for_each_nested(attr, info->attrs[NFC_ATTR_LLC_SDP], rem) { rc = nla_parse_nested_deprecated(sdp_attrs, NFC_SDP_ATTR_MAX, attr, nfc_sdp_genl_policy, info->extack); if (rc != 0) { rc = -EINVAL; goto put_local; } if (!sdp_attrs[NFC_SDP_ATTR_URI]) continue; uri_len = nla_len(sdp_attrs[NFC_SDP_ATTR_URI]); if (uri_len == 0) continue; uri = nla_data(sdp_attrs[NFC_SDP_ATTR_URI]); if (*uri == 0) continue; tid = local->sdreq_next_tid++; sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len); if (sdreq == NULL) { rc = -ENOMEM; goto put_local; } tlvs_len += sdreq->tlv_len; hlist_add_head(&sdreq->node, &sdreq_list); } if (hlist_empty(&sdreq_list)) { rc = -EINVAL; goto put_local; } rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len); put_local: nfc_llcp_local_put(local); exit: device_unlock(&dev->dev); nfc_put_device(dev); return rc; } static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1]; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; nla_strscpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME], sizeof(firmware_name)); rc = nfc_fw_download(dev, firmware_name); nfc_put_device(dev); return rc; } int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_FW_DOWNLOAD); if (!hdr) goto free_msg; if (nla_put_string(msg, NFC_ATTR_FIRMWARE_NAME, firmware_name) || nla_put_u32(msg, NFC_ATTR_FIRMWARE_DOWNLOAD_STATUS, result) || nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_enable_se(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx, se_idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); se_idx = nla_get_u32(info->attrs[NFC_ATTR_SE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_enable_se(dev, se_idx); nfc_put_device(dev); return rc; } static int nfc_genl_disable_se(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx, se_idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); se_idx = nla_get_u32(info->attrs[NFC_ATTR_SE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_disable_se(dev, se_idx); nfc_put_device(dev); return rc; } static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev, u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; struct nfc_se *se, *n; list_for_each_entry_safe(se, n, &dev->secure_elements, list) { hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, flags, NFC_CMD_GET_SE); if (!hdr) goto nla_put_failure; if (cb) genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se->idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) goto nla_put_failure; genlmsg_end(msg, hdr); } return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nfc_genl_dump_ses(struct sk_buff *skb, struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; bool first_call = false; if (!iter) { first_call = true; iter = kmalloc(sizeof(struct class_dev_iter), GFP_KERNEL); if (!iter) return -ENOMEM; cb->args[0] = (long) iter; } mutex_lock(&nfc_devlist_mutex); cb->seq = nfc_devlist_generation; if (first_call) { nfc_device_iter_init(iter); dev = nfc_device_iter_next(iter); } while (dev) { int rc; rc = nfc_genl_send_se(skb, dev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (rc < 0) break; dev = nfc_device_iter_next(iter); } mutex_unlock(&nfc_devlist_mutex); cb->args[1] = (long) dev; return skb->len; } static int nfc_genl_dump_ses_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; if (iter) { nfc_device_iter_exit(iter); kfree(iter); } return 0; } static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context) { struct nfc_se *se; int rc; pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx); device_lock(&dev->dev); if (!device_is_registered(&dev->dev)) { rc = -ENODEV; goto error; } if (!dev->dev_up) { rc = -ENODEV; goto error; } if (!dev->ops->se_io) { rc = -EOPNOTSUPP; goto error; } se = nfc_find_se(dev, se_idx); if (!se) { rc = -EINVAL; goto error; } if (se->state != NFC_SE_ENABLED) { rc = -ENODEV; goto error; } rc = dev->ops->se_io(dev, se_idx, apdu, apdu_length, cb, cb_context); device_unlock(&dev->dev); return rc; error: device_unlock(&dev->dev); kfree(cb_context); return rc; } struct se_io_ctx { u32 dev_idx; u32 se_idx; }; static void se_io_cb(void *context, u8 *apdu, size_t apdu_len, int err) { struct se_io_ctx *ctx = context; struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { kfree(ctx); return; } hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_SE_IO); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, ctx->dev_idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, ctx->se_idx) || nla_put(msg, NFC_ATTR_SE_APDU, apdu_len, apdu)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); kfree(ctx); return; nla_put_failure: free_msg: nlmsg_free(msg); kfree(ctx); return; } static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct se_io_ctx *ctx; u32 dev_idx, se_idx; u8 *apdu; size_t apdu_len; int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX] || !info->attrs[NFC_ATTR_SE_APDU]) return -EINVAL; dev_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); se_idx = nla_get_u32(info->attrs[NFC_ATTR_SE_INDEX]); dev = nfc_get_device(dev_idx); if (!dev) return -ENODEV; if (!dev->ops || !dev->ops->se_io) { rc = -EOPNOTSUPP; goto put_dev; } apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]); if (apdu_len == 0) { rc = -EINVAL; goto put_dev; } apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]); ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL); if (!ctx) { rc = -ENOMEM; goto put_dev; } ctx->dev_idx = dev_idx; ctx->se_idx = se_idx; rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx); put_dev: nfc_put_device(dev); return rc; } static int nfc_genl_vendor_cmd(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; const struct nfc_vendor_cmd *cmd; u32 dev_idx, vid, subcmd; u8 *data; size_t data_len; int i, err; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_VENDOR_ID] || !info->attrs[NFC_ATTR_VENDOR_SUBCMD]) return -EINVAL; dev_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); vid = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_ID]); subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]); dev = nfc_get_device(dev_idx); if (!dev) return -ENODEV; if (!dev->vendor_cmds || !dev->n_vendor_cmds) { err = -ENODEV; goto put_dev; } if (info->attrs[NFC_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]); data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]); if (data_len == 0) { err = -EINVAL; goto put_dev; } } else { data = NULL; data_len = 0; } for (i = 0; i < dev->n_vendor_cmds; i++) { cmd = &dev->vendor_cmds[i]; if (cmd->vendor_id != vid || cmd->subcmd != subcmd) continue; dev->cur_cmd_info = info; err = cmd->doit(dev, data, data_len); dev->cur_cmd_info = NULL; goto put_dev; } err = -EOPNOTSUPP; put_dev: nfc_put_device(dev); return err; } /* message building helper */ static inline void *nfc_hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd) { /* since there is no private header just add the generic one */ return genlmsg_put(skb, portid, seq, &nfc_genl_family, flags, cmd); } static struct sk_buff * __nfc_alloc_vendor_cmd_skb(struct nfc_dev *dev, int approxlen, u32 portid, u32 seq, enum nfc_attrs attr, u32 oui, u32 subcmd, gfp_t gfp) { struct sk_buff *skb; void *hdr; skb = nlmsg_new(approxlen + 100, gfp); if (!skb) return NULL; hdr = nfc_hdr_put(skb, portid, seq, 0, NFC_CMD_VENDOR); if (!hdr) { kfree_skb(skb); return NULL; } if (nla_put_u32(skb, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; if (nla_put_u32(skb, NFC_ATTR_VENDOR_ID, oui)) goto nla_put_failure; if (nla_put_u32(skb, NFC_ATTR_VENDOR_SUBCMD, subcmd)) goto nla_put_failure; ((void **)skb->cb)[0] = dev; ((void **)skb->cb)[1] = hdr; return skb; nla_put_failure: kfree_skb(skb); return NULL; } struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, enum nfc_attrs attr, u32 oui, u32 subcmd, int approxlen) { if (WARN_ON(!dev->cur_cmd_info)) return NULL; return __nfc_alloc_vendor_cmd_skb(dev, approxlen, dev->cur_cmd_info->snd_portid, dev->cur_cmd_info->snd_seq, attr, oui, subcmd, GFP_KERNEL); } EXPORT_SYMBOL(__nfc_alloc_vendor_cmd_reply_skb); int nfc_vendor_cmd_reply(struct sk_buff *skb) { struct nfc_dev *dev = ((void **)skb->cb)[0]; void *hdr = ((void **)skb->cb)[1]; /* clear CB data for netlink core to own from now on */ memset(skb->cb, 0, sizeof(skb->cb)); if (WARN_ON(!dev->cur_cmd_info)) { kfree_skb(skb); return -EINVAL; } genlmsg_end(skb, hdr); return genlmsg_reply(skb, dev->cur_cmd_info); } EXPORT_SYMBOL(nfc_vendor_cmd_reply); static const struct genl_ops nfc_genl_ops[] = { { .cmd = NFC_CMD_GET_DEVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_get_device, .dumpit = nfc_genl_dump_devices, .done = nfc_genl_dump_devices_done, }, { .cmd = NFC_CMD_DEV_UP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dev_up, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEV_DOWN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dev_down, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_START_POLL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_start_poll, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_STOP_POLL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_stop_poll, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEP_LINK_UP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dep_link_up, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEP_LINK_DOWN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dep_link_down, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_GET_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = nfc_genl_dump_targets, .done = nfc_genl_dump_targets_done, }, { .cmd = NFC_CMD_LLC_GET_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_get_params, }, { .cmd = NFC_CMD_LLC_SET_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_set_params, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_LLC_SDREQ, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_sdreq, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_FW_DOWNLOAD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_fw_download, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_ENABLE_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_enable_se, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DISABLE_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_disable_se, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_GET_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = nfc_genl_dump_ses, .done = nfc_genl_dump_ses_done, }, { .cmd = NFC_CMD_SE_IO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_se_io, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_ACTIVATE_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_activate_target, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_VENDOR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_vendor_cmd, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEACTIVATE_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_deactivate_target, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family nfc_genl_family __ro_after_init = { .hdrsize = 0, .name = NFC_GENL_NAME, .version = NFC_GENL_VERSION, .maxattr = NFC_ATTR_MAX, .policy = nfc_genl_policy, .module = THIS_MODULE, .ops = nfc_genl_ops, .n_ops = ARRAY_SIZE(nfc_genl_ops), .resv_start_op = NFC_CMD_DEACTIVATE_TARGET + 1, .mcgrps = nfc_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(nfc_genl_mcgrps), }; struct urelease_work { struct work_struct w; u32 portid; }; static void nfc_urelease_event_work(struct work_struct *work) { struct urelease_work *w = container_of(work, struct urelease_work, w); struct class_dev_iter iter; struct nfc_dev *dev; pr_debug("portid %d\n", w->portid); mutex_lock(&nfc_devlist_mutex); nfc_device_iter_init(&iter); dev = nfc_device_iter_next(&iter); while (dev) { mutex_lock(&dev->genl_data.genl_data_mutex); if (dev->genl_data.poll_req_portid == w->portid) { nfc_stop_poll(dev); dev->genl_data.poll_req_portid = 0; } mutex_unlock(&dev->genl_data.genl_data_mutex); dev = nfc_device_iter_next(&iter); } nfc_device_iter_exit(&iter); mutex_unlock(&nfc_devlist_mutex); kfree(w); } static int nfc_genl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct urelease_work *w; if (event != NETLINK_URELEASE || n->protocol != NETLINK_GENERIC) goto out; pr_debug("NETLINK_URELEASE event from id %d\n", n->portid); w = kmalloc(sizeof(*w), GFP_ATOMIC); if (w) { INIT_WORK(&w->w, nfc_urelease_event_work); w->portid = n->portid; schedule_work(&w->w); } out: return NOTIFY_DONE; } void nfc_genl_data_init(struct nfc_genl_data *genl_data) { genl_data->poll_req_portid = 0; mutex_init(&genl_data->genl_data_mutex); } void nfc_genl_data_exit(struct nfc_genl_data *genl_data) { mutex_destroy(&genl_data->genl_data_mutex); } static struct notifier_block nl_notifier = { .notifier_call = nfc_genl_rcv_nl_event, }; /** * nfc_genl_init() - Initialize netlink interface * * This initialization function registers the nfc netlink family. */ int __init nfc_genl_init(void) { int rc; rc = genl_register_family(&nfc_genl_family); if (rc) return rc; netlink_register_notifier(&nl_notifier); return 0; } /** * nfc_genl_exit() - Deinitialize netlink interface * * This exit function unregisters the nfc netlink family. */ void nfc_genl_exit(void) { netlink_unregister_notifier(&nl_notifier); genl_unregister_family(&nfc_genl_family); } |
| 16 10 15 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 | /* * linux/fs/nls/nls_cp852.c * * Charset cp852 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x016f, 0x0107, 0x00e7, 0x0142, 0x00eb, 0x0150, 0x0151, 0x00ee, 0x0179, 0x00c4, 0x0106, /* 0x90*/ 0x00c9, 0x0139, 0x013a, 0x00f4, 0x00f6, 0x013d, 0x013e, 0x015a, 0x015b, 0x00d6, 0x00dc, 0x0164, 0x0165, 0x0141, 0x00d7, 0x010d, /* 0xa0*/ 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x0104, 0x0105, 0x017d, 0x017e, 0x0118, 0x0119, 0x00ac, 0x017a, 0x010c, 0x015f, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x00c1, 0x00c2, 0x011a, 0x015e, 0x2563, 0x2551, 0x2557, 0x255d, 0x017b, 0x017c, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x0102, 0x0103, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4, /* 0xd0*/ 0x0111, 0x0110, 0x010e, 0x00cb, 0x010f, 0x0147, 0x00cd, 0x00ce, 0x011b, 0x2518, 0x250c, 0x2588, 0x2584, 0x0162, 0x016e, 0x2580, /* 0xe0*/ 0x00d3, 0x00df, 0x00d4, 0x0143, 0x0144, 0x0148, 0x0160, 0x0161, 0x0154, 0x00da, 0x0155, 0x0170, 0x00fd, 0x00dd, 0x0163, 0x00b4, /* 0xf0*/ 0x00ad, 0x02dd, 0x02db, 0x02c7, 0x02d8, 0x00a7, 0x00f7, 0x00b8, 0x00b0, 0x00a8, 0x02d9, 0x0171, 0x0158, 0x0159, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x00, 0x00, 0xcf, 0x00, 0x00, 0xf5, /* 0xa0-0xa7 */ 0xf9, 0x00, 0x00, 0xae, 0xaa, 0xf0, 0x00, 0x00, /* 0xa8-0xaf */ 0xf8, 0x00, 0x00, 0x00, 0xef, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0xf7, 0x00, 0x00, 0xaf, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0xb5, 0xb6, 0x00, 0x8e, 0x00, 0x00, 0x80, /* 0xc0-0xc7 */ 0x00, 0x90, 0x00, 0xd3, 0x00, 0xd6, 0xd7, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0xe0, 0xe2, 0x00, 0x99, 0x9e, /* 0xd0-0xd7 */ 0x00, 0x00, 0xe9, 0x00, 0x9a, 0xed, 0x00, 0xe1, /* 0xd8-0xdf */ 0x00, 0xa0, 0x83, 0x00, 0x84, 0x00, 0x00, 0x87, /* 0xe0-0xe7 */ 0x00, 0x82, 0x00, 0x89, 0x00, 0xa1, 0x8c, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xa2, 0x93, 0x00, 0x94, 0xf6, /* 0xf0-0xf7 */ 0x00, 0x00, 0xa3, 0x00, 0x81, 0xec, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0xc6, 0xc7, 0xa4, 0xa5, 0x8f, 0x86, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0x9f, 0xd2, 0xd4, /* 0x08-0x0f */ 0xd1, 0xd0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xa8, 0xa9, 0xb7, 0xd8, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x91, 0x92, 0x00, 0x00, 0x95, 0x96, 0x00, /* 0x38-0x3f */ 0x00, 0x9d, 0x88, 0xe3, 0xe4, 0x00, 0x00, 0xd5, /* 0x40-0x47 */ 0xe5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x8a, 0x8b, 0x00, 0x00, 0xe8, 0xea, 0x00, 0x00, /* 0x50-0x57 */ 0xfc, 0xfd, 0x97, 0x98, 0x00, 0x00, 0xb8, 0xad, /* 0x58-0x5f */ 0xe6, 0xe7, 0xdd, 0xee, 0x9b, 0x9c, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xde, 0x85, /* 0x68-0x6f */ 0xeb, 0xfb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x8d, 0xab, 0xbd, 0xbe, 0xa6, 0xa7, 0x00, /* 0x78-0x7f */ }; static const unsigned char page02[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf3, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0xf4, 0xfa, 0x00, 0xf2, 0x00, 0xf1, 0x00, 0x00, /* 0xd8-0xdf */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0x00, 0x00, 0xc9, 0x00, 0x00, 0xbb, /* 0x50-0x57 */ 0x00, 0x00, 0xc8, 0x00, 0x00, 0xbc, 0x00, 0x00, /* 0x58-0x5f */ 0xcc, 0x00, 0x00, 0xb9, 0x00, 0x00, 0xcb, 0x00, /* 0x60-0x67 */ 0x00, 0xca, 0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, page02, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8b, 0x8b, 0x8c, 0xab, 0x84, 0x86, /* 0x88-0x8f */ 0x82, 0x92, 0x92, 0x93, 0x94, 0x96, 0x96, 0x98, /* 0x90-0x97 */ 0x98, 0x94, 0x81, 0x9c, 0x9c, 0x88, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa5, 0xa5, 0xa7, 0xa7, /* 0xa0-0xa7 */ 0xa9, 0xa9, 0xaa, 0xab, 0x9f, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xa0, 0x83, 0xd8, /* 0xb0-0xb7 */ 0xad, 0xb9, 0xba, 0xbb, 0xbc, 0xbe, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc7, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd0, 0xd4, 0x89, 0xd4, 0xe5, 0xa1, 0x8c, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xee, 0x85, 0xdf, /* 0xd8-0xdf */ 0xa2, 0xe1, 0x93, 0xe4, 0xe4, 0xe5, 0xe7, 0xe7, /* 0xe0-0xe7 */ 0xea, 0xa3, 0xea, 0xfb, 0xec, 0xec, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfd, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0xb6, 0x8e, 0xde, 0x8f, 0x80, /* 0x80-0x87 */ 0x9d, 0xd3, 0x8a, 0x8a, 0xd7, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x91, 0xe2, 0x99, 0x95, 0x95, 0x97, /* 0x90-0x97 */ 0x97, 0x99, 0x9a, 0x9b, 0x9b, 0x9d, 0x9e, 0xac, /* 0x98-0x9f */ 0xb5, 0xd6, 0xe0, 0xe9, 0xa4, 0xa4, 0xa6, 0xa6, /* 0xa0-0xa7 */ 0xa8, 0xa8, 0xaa, 0x8d, 0xac, 0xb8, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbd, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc6, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd1, 0xd1, 0xd2, 0xd3, 0xd2, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xb7, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe3, 0xd5, 0xe6, 0xe6, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xe8, 0xeb, 0xed, 0xed, 0xdd, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xeb, 0xfc, 0xfc, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp852", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp852(void) { return register_nls(&table); } static void __exit exit_nls_cp852(void) { unregister_nls(&table); } module_init(init_nls_cp852) module_exit(exit_nls_cp852) MODULE_DESCRIPTION("NLS Codepage 852 (Central/Eastern Europe)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0 /* * proc_tty.c -- handles /proc/tty * * Copyright 1997, Theodore Ts'o */ #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/tty.h> #include <linux/seq_file.h> #include <linux/bitops.h> #include "internal.h" /* * The /proc/tty directory inodes... */ static struct proc_dir_entry *proc_tty_driver; /* * This is the handler for /proc/tty/drivers */ static void show_tty_range(struct seq_file *m, struct tty_driver *p, dev_t from, int num) { seq_printf(m, "%-20s ", p->driver_name ? p->driver_name : "unknown"); seq_printf(m, "/dev/%-8s ", p->name); if (p->num > 1) { seq_printf(m, "%3d %d-%d ", MAJOR(from), MINOR(from), MINOR(from) + num - 1); } else { seq_printf(m, "%3d %7d ", MAJOR(from), MINOR(from)); } switch (p->type) { case TTY_DRIVER_TYPE_SYSTEM: seq_puts(m, "system"); if (p->subtype == SYSTEM_TYPE_TTY) seq_puts(m, ":/dev/tty"); else if (p->subtype == SYSTEM_TYPE_SYSCONS) seq_puts(m, ":console"); else if (p->subtype == SYSTEM_TYPE_CONSOLE) seq_puts(m, ":vtmaster"); break; case TTY_DRIVER_TYPE_CONSOLE: seq_puts(m, "console"); break; case TTY_DRIVER_TYPE_SERIAL: seq_puts(m, "serial"); break; case TTY_DRIVER_TYPE_PTY: if (p->subtype == PTY_TYPE_MASTER) seq_puts(m, "pty:master"); else if (p->subtype == PTY_TYPE_SLAVE) seq_puts(m, "pty:slave"); else seq_puts(m, "pty"); break; default: seq_printf(m, "type:%d.%d", p->type, p->subtype); } seq_putc(m, '\n'); } static int show_tty_driver(struct seq_file *m, void *v) { struct tty_driver *p = list_entry(v, struct tty_driver, tty_drivers); dev_t from = MKDEV(p->major, p->minor_start); dev_t to = from + p->num; if (&p->tty_drivers == tty_drivers.next) { /* pseudo-drivers first */ seq_printf(m, "%-20s /dev/%-8s ", "/dev/tty", "tty"); seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 0); seq_puts(m, "system:/dev/tty\n"); seq_printf(m, "%-20s /dev/%-8s ", "/dev/console", "console"); seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 1); seq_puts(m, "system:console\n"); #ifdef CONFIG_UNIX98_PTYS seq_printf(m, "%-20s /dev/%-8s ", "/dev/ptmx", "ptmx"); seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 2); seq_puts(m, "system\n"); #endif #ifdef CONFIG_VT seq_printf(m, "%-20s /dev/%-8s ", "/dev/vc/0", "vc/0"); seq_printf(m, "%3d %7d ", TTY_MAJOR, 0); seq_puts(m, "system:vtmaster\n"); #endif } while (MAJOR(from) < MAJOR(to)) { dev_t next = MKDEV(MAJOR(from)+1, 0); show_tty_range(m, p, from, next - from); from = next; } if (from != to) show_tty_range(m, p, from, to - from); return 0; } /* iterator */ static void *t_start(struct seq_file *m, loff_t *pos) { mutex_lock(&tty_mutex); return seq_list_start(&tty_drivers, *pos); } static void *t_next(struct seq_file *m, void *v, loff_t *pos) { return seq_list_next(v, &tty_drivers, pos); } static void t_stop(struct seq_file *m, void *v) { mutex_unlock(&tty_mutex); } static const struct seq_operations tty_drivers_op = { .start = t_start, .next = t_next, .stop = t_stop, .show = show_tty_driver }; /* * This function is called by tty_register_driver() to handle * registering the driver's /proc handler into /proc/tty/driver/<foo> */ void proc_tty_register_driver(struct tty_driver *driver) { struct proc_dir_entry *ent; if (!driver->driver_name || driver->proc_entry || !driver->ops->proc_show) return; ent = proc_create_single_data(driver->driver_name, 0, proc_tty_driver, driver->ops->proc_show, driver); driver->proc_entry = ent; } /* * This function is called by tty_unregister_driver() */ void proc_tty_unregister_driver(struct tty_driver *driver) { struct proc_dir_entry *ent; ent = driver->proc_entry; if (!ent) return; remove_proc_entry(ent->name, proc_tty_driver); driver->proc_entry = NULL; } /* * Called by proc_root_init() to initialize the /proc/tty subtree */ void __init proc_tty_init(void) { if (!proc_mkdir("tty", NULL)) return; proc_mkdir("tty/ldisc", NULL); /* Preserved: it's userspace visible */ /* * /proc/tty/driver/serial reveals the exact character counts for * serial links which is just too easy to abuse for inferring * password lengths and inter-keystroke timings during password * entry. */ proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL); proc_create_seq("tty/ldiscs", 0, NULL, &tty_ldiscs_seq_ops); proc_create_seq("tty/drivers", 0, NULL, &tty_drivers_op); } |
| 22 18 21 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | /* * linux/fs/nls/nls_cp874.c * * Charset cp874 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2026, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, /* 0x90*/ 0x0000, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, /* 0xa0*/ 0x00a0, 0x0e01, 0x0e02, 0x0e03, 0x0e04, 0x0e05, 0x0e06, 0x0e07, 0x0e08, 0x0e09, 0x0e0a, 0x0e0b, 0x0e0c, 0x0e0d, 0x0e0e, 0x0e0f, /* 0xb0*/ 0x0e10, 0x0e11, 0x0e12, 0x0e13, 0x0e14, 0x0e15, 0x0e16, 0x0e17, 0x0e18, 0x0e19, 0x0e1a, 0x0e1b, 0x0e1c, 0x0e1d, 0x0e1e, 0x0e1f, /* 0xc0*/ 0x0e20, 0x0e21, 0x0e22, 0x0e23, 0x0e24, 0x0e25, 0x0e26, 0x0e27, 0x0e28, 0x0e29, 0x0e2a, 0x0e2b, 0x0e2c, 0x0e2d, 0x0e2e, 0x0e2f, /* 0xd0*/ 0x0e30, 0x0e31, 0x0e32, 0x0e33, 0x0e34, 0x0e35, 0x0e36, 0x0e37, 0x0e38, 0x0e39, 0x0e3a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0e3f, /* 0xe0*/ 0x0e40, 0x0e41, 0x0e42, 0x0e43, 0x0e44, 0x0e45, 0x0e46, 0x0e47, 0x0e48, 0x0e49, 0x0e4a, 0x0e4b, 0x0e4c, 0x0e4d, 0x0e4e, 0x0e4f, /* 0xf0*/ 0x0e50, 0x0e51, 0x0e52, 0x0e53, 0x0e54, 0x0e55, 0x0e56, 0x0e57, 0x0e58, 0x0e59, 0x0e5a, 0x0e5b, 0x0000, 0x0000, 0x0000, 0x0000, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char page0e[256] = { 0x00, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0x00-0x07 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0x08-0x0f */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0x10-0x17 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0x18-0x1f */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0x20-0x27 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0x28-0x2f */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0x30-0x37 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0xdf, /* 0x38-0x3f */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x40-0x47 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x48-0x4f */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0x50-0x57 */ 0xf8, 0xf9, 0xfa, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x96, 0x97, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x91, 0x92, 0x00, 0x00, 0x93, 0x94, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x95, 0x00, 0x00, 0x00, 0x85, 0x00, /* 0x20-0x27 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page0e, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp874", .alias = "tis-620", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp874(void) { return register_nls(&table); } static void __exit exit_nls_cp874(void) { unregister_nls(&table); } module_init(init_nls_cp874) module_exit(exit_nls_cp874) MODULE_DESCRIPTION("NLS Thai charset (CP874, TIS-620)"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS_NLS(tis-620); |
| 114 115 115 115 114 114 1 115 179 178 7 7 7 7 7 191 11 191 190 190 190 11 190 23 23 23 23 21 9 9 9 9 1 27 187 187 184 187 98 156 29 174 2 119 42 65 26 20 2 184 185 183 6 175 175 137 1 136 123 13 14 14 121 121 121 30 14 16 16 3 13 2 14 16 119 1 121 1 120 120 120 121 121 114 114 114 114 114 114 111 110 1 115 115 115 115 115 115 115 7 3 4 179 111 111 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * journal.c * * Defines functions of journalling api * * Copyright (C) 2003, 2004 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/kthread.h> #include <linux/time.h> #include <linux/random.h> #include <linux/delay.h> #include <linux/writeback.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "blockcheck.h" #include "dir.h" #include "dlmglue.h" #include "extent_map.h" #include "heartbeat.h" #include "inode.h" #include "journal.h" #include "localalloc.h" #include "slot_map.h" #include "super.h" #include "sysfile.h" #include "uptodate.h" #include "quota.h" #include "file.h" #include "namei.h" #include "buffer_head_io.h" #include "ocfs2_trace.h" DEFINE_SPINLOCK(trans_inc_lock); #define ORPHAN_SCAN_SCHEDULE_TIMEOUT 300000 static int ocfs2_force_read_journal(struct inode *inode); static int ocfs2_recover_node(struct ocfs2_super *osb, int node_num, int slot_num); static int __ocfs2_recovery_thread(void *arg); static int ocfs2_commit_cache(struct ocfs2_super *osb); static int __ocfs2_wait_on_mount(struct ocfs2_super *osb, int quota); static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb, int dirty, int replayed); static int ocfs2_trylock_journal(struct ocfs2_super *osb, int slot_num); static int ocfs2_recover_orphans(struct ocfs2_super *osb, int slot, enum ocfs2_orphan_reco_type orphan_reco_type); static int ocfs2_commit_thread(void *arg); static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal, int slot_num, struct ocfs2_dinode *la_dinode, struct ocfs2_dinode *tl_dinode, struct ocfs2_quota_recovery *qrec, enum ocfs2_orphan_reco_type orphan_reco_type); static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb) { return __ocfs2_wait_on_mount(osb, 0); } static inline int ocfs2_wait_on_quotas(struct ocfs2_super *osb) { return __ocfs2_wait_on_mount(osb, 1); } /* * This replay_map is to track online/offline slots, so we could recover * offline slots during recovery and mount */ enum ocfs2_replay_state { REPLAY_UNNEEDED = 0, /* Replay is not needed, so ignore this map */ REPLAY_NEEDED, /* Replay slots marked in rm_replay_slots */ REPLAY_DONE /* Replay was already queued */ }; struct ocfs2_replay_map { unsigned int rm_slots; enum ocfs2_replay_state rm_state; unsigned char rm_replay_slots[] __counted_by(rm_slots); }; static void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state) { if (!osb->replay_map) return; /* If we've already queued the replay, we don't have any more to do */ if (osb->replay_map->rm_state == REPLAY_DONE) return; osb->replay_map->rm_state = state; } int ocfs2_compute_replay_slots(struct ocfs2_super *osb) { struct ocfs2_replay_map *replay_map; int i, node_num; /* If replay map is already set, we don't do it again */ if (osb->replay_map) return 0; replay_map = kzalloc(struct_size(replay_map, rm_replay_slots, osb->max_slots), GFP_KERNEL); if (!replay_map) { mlog_errno(-ENOMEM); return -ENOMEM; } spin_lock(&osb->osb_lock); replay_map->rm_slots = osb->max_slots; replay_map->rm_state = REPLAY_UNNEEDED; /* set rm_replay_slots for offline slot(s) */ for (i = 0; i < replay_map->rm_slots; i++) { if (ocfs2_slot_to_node_num_locked(osb, i, &node_num) == -ENOENT) replay_map->rm_replay_slots[i] = 1; } osb->replay_map = replay_map; spin_unlock(&osb->osb_lock); return 0; } static void ocfs2_queue_replay_slots(struct ocfs2_super *osb, enum ocfs2_orphan_reco_type orphan_reco_type) { struct ocfs2_replay_map *replay_map = osb->replay_map; int i; if (!replay_map) return; if (replay_map->rm_state != REPLAY_NEEDED) return; for (i = 0; i < replay_map->rm_slots; i++) if (replay_map->rm_replay_slots[i]) ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL, NULL, orphan_reco_type); replay_map->rm_state = REPLAY_DONE; } void ocfs2_free_replay_slots(struct ocfs2_super *osb) { struct ocfs2_replay_map *replay_map = osb->replay_map; if (!osb->replay_map) return; kfree(replay_map); osb->replay_map = NULL; } int ocfs2_recovery_init(struct ocfs2_super *osb) { struct ocfs2_recovery_map *rm; mutex_init(&osb->recovery_lock); osb->recovery_state = OCFS2_REC_ENABLED; osb->recovery_thread_task = NULL; init_waitqueue_head(&osb->recovery_event); rm = kzalloc(struct_size(rm, rm_entries, osb->max_slots), GFP_KERNEL); if (!rm) { mlog_errno(-ENOMEM); return -ENOMEM; } osb->recovery_map = rm; return 0; } static int ocfs2_recovery_thread_running(struct ocfs2_super *osb) { return osb->recovery_thread_task != NULL; } static void ocfs2_recovery_disable(struct ocfs2_super *osb, enum ocfs2_recovery_state state) { mutex_lock(&osb->recovery_lock); /* * If recovery thread is not running, we can directly transition to * final state. */ if (!ocfs2_recovery_thread_running(osb)) { osb->recovery_state = state + 1; goto out_lock; } osb->recovery_state = state; /* Wait for recovery thread to acknowledge state transition */ wait_event_cmd(osb->recovery_event, !ocfs2_recovery_thread_running(osb) || osb->recovery_state >= state + 1, mutex_unlock(&osb->recovery_lock), mutex_lock(&osb->recovery_lock)); out_lock: mutex_unlock(&osb->recovery_lock); /* * At this point we know that no more recovery work can be queued so * wait for any recovery completion work to complete. */ if (osb->ocfs2_wq) flush_workqueue(osb->ocfs2_wq); } void ocfs2_recovery_disable_quota(struct ocfs2_super *osb) { ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE); } void ocfs2_recovery_exit(struct ocfs2_super *osb) { struct ocfs2_recovery_map *rm; /* disable any new recovery threads and wait for any currently * running ones to exit. Do this before setting the vol_state. */ ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE); /* * Now that recovery is shut down, and the osb is about to be * freed, the osb_lock is not taken here. */ rm = osb->recovery_map; /* XXX: Should we bug if there are dirty entries? */ kfree(rm); } static int __ocfs2_recovery_map_test(struct ocfs2_super *osb, unsigned int node_num) { int i; struct ocfs2_recovery_map *rm = osb->recovery_map; assert_spin_locked(&osb->osb_lock); for (i = 0; i < rm->rm_used; i++) { if (rm->rm_entries[i] == node_num) return 1; } return 0; } /* Behaves like test-and-set. Returns the previous value */ static int ocfs2_recovery_map_set(struct ocfs2_super *osb, unsigned int node_num) { struct ocfs2_recovery_map *rm = osb->recovery_map; spin_lock(&osb->osb_lock); if (__ocfs2_recovery_map_test(osb, node_num)) { spin_unlock(&osb->osb_lock); return 1; } /* XXX: Can this be exploited? Not from o2dlm... */ BUG_ON(rm->rm_used >= osb->max_slots); rm->rm_entries[rm->rm_used] = node_num; rm->rm_used++; spin_unlock(&osb->osb_lock); return 0; } static void ocfs2_recovery_map_clear(struct ocfs2_super *osb, unsigned int node_num) { int i; struct ocfs2_recovery_map *rm = osb->recovery_map; spin_lock(&osb->osb_lock); for (i = 0; i < rm->rm_used; i++) { if (rm->rm_entries[i] == node_num) break; } if (i < rm->rm_used) { /* XXX: be careful with the pointer math */ memmove(&(rm->rm_entries[i]), &(rm->rm_entries[i + 1]), (rm->rm_used - i - 1) * sizeof(unsigned int)); rm->rm_used--; } spin_unlock(&osb->osb_lock); } static int ocfs2_commit_cache(struct ocfs2_super *osb) { int status = 0; unsigned int flushed; struct ocfs2_journal *journal = NULL; journal = osb->journal; /* Flush all pending commits and checkpoint the journal. */ down_write(&journal->j_trans_barrier); flushed = atomic_read(&journal->j_num_trans); trace_ocfs2_commit_cache_begin(flushed); if (flushed == 0) { up_write(&journal->j_trans_barrier); goto finally; } jbd2_journal_lock_updates(journal->j_journal); status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) { up_write(&journal->j_trans_barrier); mlog_errno(status); goto finally; } ocfs2_inc_trans_id(journal); flushed = atomic_read(&journal->j_num_trans); atomic_set(&journal->j_num_trans, 0); up_write(&journal->j_trans_barrier); trace_ocfs2_commit_cache_end(journal->j_trans_id, flushed); ocfs2_wake_downconvert_thread(osb); wake_up(&journal->j_checkpointed); finally: return status; } handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs) { journal_t *journal = osb->journal->j_journal; handle_t *handle; BUG_ON(!osb || !osb->journal->j_journal); if (ocfs2_is_hard_readonly(osb)) return ERR_PTR(-EROFS); BUG_ON(osb->journal->j_state == OCFS2_JOURNAL_FREE); BUG_ON(max_buffs <= 0); /* Nested transaction? Just return the handle... */ if (journal_current_handle()) return jbd2_journal_start(journal, max_buffs); sb_start_intwrite(osb->sb); down_read(&osb->journal->j_trans_barrier); handle = jbd2_journal_start(journal, max_buffs); if (IS_ERR(handle)) { up_read(&osb->journal->j_trans_barrier); sb_end_intwrite(osb->sb); mlog_errno(PTR_ERR(handle)); if (is_journal_aborted(journal)) { ocfs2_abort(osb->sb, "Detected aborted journal\n"); handle = ERR_PTR(-EROFS); } } else { if (!ocfs2_mount_local(osb)) atomic_inc(&(osb->journal->j_num_trans)); } return handle; } int ocfs2_commit_trans(struct ocfs2_super *osb, handle_t *handle) { int ret, nested; struct ocfs2_journal *journal = osb->journal; BUG_ON(!handle); nested = handle->h_ref > 1; ret = jbd2_journal_stop(handle); if (ret < 0) mlog_errno(ret); if (!nested) { up_read(&journal->j_trans_barrier); sb_end_intwrite(osb->sb); } return ret; } /* * 'nblocks' is what you want to add to the current transaction. * * This might call jbd2_journal_restart() which will commit dirty buffers * and then restart the transaction. Before calling * ocfs2_extend_trans(), any changed blocks should have been * dirtied. After calling it, all blocks which need to be changed must * go through another set of journal_access/journal_dirty calls. * * WARNING: This will not release any semaphores or disk locks taken * during the transaction, so make sure they were taken *before* * start_trans or we'll have ordering deadlocks. * * WARNING2: Note that we do *not* drop j_trans_barrier here. This is * good because transaction ids haven't yet been recorded on the * cluster locks associated with this handle. */ int ocfs2_extend_trans(handle_t *handle, int nblocks) { int status, old_nblocks; BUG_ON(!handle); BUG_ON(nblocks < 0); if (!nblocks) return 0; old_nblocks = jbd2_handle_buffer_credits(handle); trace_ocfs2_extend_trans(old_nblocks, nblocks); #ifdef CONFIG_OCFS2_DEBUG_FS status = 1; #else status = jbd2_journal_extend(handle, nblocks, 0); if (status < 0) { mlog_errno(status); goto bail; } #endif if (status > 0) { trace_ocfs2_extend_trans_restart(old_nblocks + nblocks); status = jbd2_journal_restart(handle, old_nblocks + nblocks); if (status < 0) { mlog_errno(status); goto bail; } } status = 0; bail: return status; } /* * Make sure handle has at least 'nblocks' credits available. If it does not * have that many credits available, we will try to extend the handle to have * enough credits. If that fails, we will restart transaction to have enough * credits. Similar notes regarding data consistency and locking implications * as for ocfs2_extend_trans() apply here. */ int ocfs2_assure_trans_credits(handle_t *handle, int nblocks) { int old_nblks = jbd2_handle_buffer_credits(handle); trace_ocfs2_assure_trans_credits(old_nblks); if (old_nblks >= nblocks) return 0; return ocfs2_extend_trans(handle, nblocks - old_nblks); } /* * If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA. * If that fails, restart the transaction & regain write access for the * buffer head which is used for metadata modifications. * Taken from Ext4: extend_or_restart_transaction() */ int ocfs2_allocate_extend_trans(handle_t *handle, int thresh) { int status, old_nblks; BUG_ON(!handle); old_nblks = jbd2_handle_buffer_credits(handle); trace_ocfs2_allocate_extend_trans(old_nblks, thresh); if (old_nblks < thresh) return 0; status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA, 0); if (status < 0) { mlog_errno(status); goto bail; } if (status > 0) { status = jbd2_journal_restart(handle, OCFS2_MAX_TRANS_DATA); if (status < 0) mlog_errno(status); } bail: return status; } static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger_type *triggers) { return container_of(triggers, struct ocfs2_triggers, ot_triggers); } static void ocfs2_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers); /* * We aren't guaranteed to have the superblock here, so we * must unconditionally compute the ecc data. * __ocfs2_journal_access() will only set the triggers if * metaecc is enabled. */ ocfs2_block_check_compute(data, size, data + ot->ot_offset); } /* * Quota blocks have their own trigger because the struct ocfs2_block_check * offset depends on the blocksize. */ static void ocfs2_dq_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { struct ocfs2_disk_dqtrailer *dqt = ocfs2_block_dqtrailer(size, data); /* * We aren't guaranteed to have the superblock here, so we * must unconditionally compute the ecc data. * __ocfs2_journal_access() will only set the triggers if * metaecc is enabled. */ ocfs2_block_check_compute(data, size, &dqt->dq_check); } /* * Directory blocks also have their own trigger because the * struct ocfs2_block_check offset depends on the blocksize. */ static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { struct ocfs2_dir_block_trailer *trailer = ocfs2_dir_trailer_from_size(size, data); /* * We aren't guaranteed to have the superblock here, so we * must unconditionally compute the ecc data. * __ocfs2_journal_access() will only set the triggers if * metaecc is enabled. */ ocfs2_block_check_compute(data, size, &trailer->db_check); } static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh) { struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers); mlog(ML_ERROR, "ocfs2_abort_trigger called by JBD2. bh = 0x%lx, " "bh->b_blocknr = %llu\n", (unsigned long)bh, (unsigned long long)bh->b_blocknr); ocfs2_error(ot->sb, "JBD2 has aborted our journal, ocfs2 cannot continue\n"); } static void ocfs2_setup_csum_triggers(struct super_block *sb, enum ocfs2_journal_trigger_type type, struct ocfs2_triggers *ot) { BUG_ON(type >= OCFS2_JOURNAL_TRIGGER_COUNT); switch (type) { case OCFS2_JTR_DI: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_dinode, i_check); break; case OCFS2_JTR_EB: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_extent_block, h_check); break; case OCFS2_JTR_RB: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_refcount_block, rf_check); break; case OCFS2_JTR_GD: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_group_desc, bg_check); break; case OCFS2_JTR_DB: ot->ot_triggers.t_frozen = ocfs2_db_frozen_trigger; break; case OCFS2_JTR_XB: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_xattr_block, xb_check); break; case OCFS2_JTR_DQ: ot->ot_triggers.t_frozen = ocfs2_dq_frozen_trigger; break; case OCFS2_JTR_DR: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check); break; case OCFS2_JTR_DL: ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; ot->ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check); break; case OCFS2_JTR_NONE: /* To make compiler happy... */ return; } ot->ot_triggers.t_abort = ocfs2_abort_trigger; ot->sb = sb; } void ocfs2_initialize_journal_triggers(struct super_block *sb, struct ocfs2_triggers triggers[]) { enum ocfs2_journal_trigger_type type; for (type = OCFS2_JTR_DI; type < OCFS2_JOURNAL_TRIGGER_COUNT; type++) ocfs2_setup_csum_triggers(sb, type, &triggers[type]); } static int __ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, struct ocfs2_triggers *triggers, int type) { int status; struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); BUG_ON(!ci || !ci->ci_ops); BUG_ON(!handle); BUG_ON(!bh); trace_ocfs2_journal_access( (unsigned long long)ocfs2_metadata_cache_owner(ci), (unsigned long long)bh->b_blocknr, type, bh->b_size); /* we can safely remove this assertion after testing. */ if (!buffer_uptodate(bh)) { mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n"); mlog(ML_ERROR, "b_blocknr=%llu, b_state=0x%lx\n", (unsigned long long)bh->b_blocknr, bh->b_state); lock_buffer(bh); /* * A previous transaction with a couple of buffer heads fail * to checkpoint, so all the bhs are marked as BH_Write_EIO. * For current transaction, the bh is just among those error * bhs which previous transaction handle. We can't just clear * its BH_Write_EIO and reuse directly, since other bhs are * not written to disk yet and that will cause metadata * inconsistency. So we should set fs read-only to avoid * further damage. */ if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) { unlock_buffer(bh); return ocfs2_error(osb->sb, "A previous attempt to " "write this buffer head failed\n"); } unlock_buffer(bh); } /* Set the current transaction information on the ci so * that the locking code knows whether it can drop it's locks * on this ci or not. We're protected from the commit * thread updating the current transaction id until * ocfs2_commit_trans() because ocfs2_start_trans() took * j_trans_barrier for us. */ ocfs2_set_ci_lock_trans(osb->journal, ci); ocfs2_metadata_cache_io_lock(ci); switch (type) { case OCFS2_JOURNAL_ACCESS_CREATE: case OCFS2_JOURNAL_ACCESS_WRITE: status = jbd2_journal_get_write_access(handle, bh); break; case OCFS2_JOURNAL_ACCESS_UNDO: status = jbd2_journal_get_undo_access(handle, bh); break; default: status = -EINVAL; mlog(ML_ERROR, "Unknown access type!\n"); } if (!status && ocfs2_meta_ecc(osb) && triggers) jbd2_journal_set_triggers(bh, &triggers->ot_triggers); ocfs2_metadata_cache_io_unlock(ci); if (status < 0) mlog(ML_ERROR, "Error %d getting %d access to buffer!\n", status, type); return status; } int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_DI], type); } int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_EB], type); } int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_RB], type); } int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_GD], type); } int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_DB], type); } int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_XB], type); } int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_DQ], type); } int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_DR], type); } int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); return __ocfs2_journal_access(handle, ci, bh, &osb->s_journal_triggers[OCFS2_JTR_DL], type); } int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { return __ocfs2_journal_access(handle, ci, bh, NULL, type); } void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh) { int status; trace_ocfs2_journal_dirty((unsigned long long)bh->b_blocknr); status = jbd2_journal_dirty_metadata(handle, bh); if (status) { mlog_errno(status); if (!is_handle_aborted(handle)) { journal_t *journal = handle->h_transaction->t_journal; mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed: " "handle type %u started at line %u, credits %u/%u " "errcode %d. Aborting transaction and journal.\n", handle->h_type, handle->h_line_no, handle->h_requested_credits, jbd2_handle_buffer_credits(handle), status); handle->h_err = status; jbd2_journal_abort_handle(handle); jbd2_journal_abort(journal, status); } } } #define OCFS2_DEFAULT_COMMIT_INTERVAL (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE) void ocfs2_set_journal_params(struct ocfs2_super *osb) { journal_t *journal = osb->journal->j_journal; unsigned long commit_interval = OCFS2_DEFAULT_COMMIT_INTERVAL; if (osb->osb_commit_interval) commit_interval = osb->osb_commit_interval; write_lock(&journal->j_state_lock); journal->j_commit_interval = commit_interval; if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; write_unlock(&journal->j_state_lock); } /* * alloc & initialize skeleton for journal structure. * ocfs2_journal_init() will make fs have journal ability. */ int ocfs2_journal_alloc(struct ocfs2_super *osb) { int status = 0; struct ocfs2_journal *journal; journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL); if (!journal) { mlog(ML_ERROR, "unable to alloc journal\n"); status = -ENOMEM; goto bail; } osb->journal = journal; journal->j_osb = osb; atomic_set(&journal->j_num_trans, 0); init_rwsem(&journal->j_trans_barrier); init_waitqueue_head(&journal->j_checkpointed); spin_lock_init(&journal->j_lock); journal->j_trans_id = 1UL; INIT_LIST_HEAD(&journal->j_la_cleanups); INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery); journal->j_state = OCFS2_JOURNAL_FREE; bail: return status; } static int ocfs2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) { struct address_space *mapping = jinode->i_vfs_inode->i_mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = mapping->nrpages * 2, .range_start = jinode->i_dirty_start, .range_end = jinode->i_dirty_end, }; return filemap_fdatawrite_wbc(mapping, &wbc); } int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) { int status = -1; struct inode *inode = NULL; /* the journal inode */ journal_t *j_journal = NULL; struct ocfs2_journal *journal = osb->journal; struct ocfs2_dinode *di = NULL; struct buffer_head *bh = NULL; int inode_lock = 0; BUG_ON(!journal); /* already have the inode for our journal */ inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE, osb->slot_num); if (inode == NULL) { status = -EACCES; mlog_errno(status); goto done; } if (is_bad_inode(inode)) { mlog(ML_ERROR, "access error (bad inode)\n"); iput(inode); inode = NULL; status = -EACCES; goto done; } SET_INODE_JOURNAL(inode); OCFS2_I(inode)->ip_open_count++; /* Skip recovery waits here - journal inode metadata never * changes in a live cluster so it can be considered an * exception to the rule. */ status = ocfs2_inode_lock_full(inode, &bh, 1, OCFS2_META_LOCK_RECOVERY); if (status < 0) { if (status != -ERESTARTSYS) mlog(ML_ERROR, "Could not get lock on journal!\n"); goto done; } inode_lock = 1; di = (struct ocfs2_dinode *)bh->b_data; if (i_size_read(inode) < OCFS2_MIN_JOURNAL_SIZE) { mlog(ML_ERROR, "Journal file size (%lld) is too small!\n", i_size_read(inode)); status = -EINVAL; goto done; } trace_ocfs2_journal_init(i_size_read(inode), (unsigned long long)inode->i_blocks, OCFS2_I(inode)->ip_clusters); /* call the kernels journal init function now */ j_journal = jbd2_journal_init_inode(inode); if (IS_ERR(j_journal)) { mlog(ML_ERROR, "Linux journal layer error\n"); status = PTR_ERR(j_journal); goto done; } trace_ocfs2_journal_init_maxlen(j_journal->j_total_len); *dirty = (le32_to_cpu(di->id1.journal1.ij_flags) & OCFS2_JOURNAL_DIRTY_FL); journal->j_journal = j_journal; journal->j_journal->j_submit_inode_data_buffers = ocfs2_journal_submit_inode_data_buffers; journal->j_journal->j_finish_inode_data_buffers = jbd2_journal_finish_inode_data_buffers; journal->j_inode = inode; journal->j_bh = bh; ocfs2_set_journal_params(osb); journal->j_state = OCFS2_JOURNAL_LOADED; status = 0; done: if (status < 0) { if (inode_lock) ocfs2_inode_unlock(inode, 1); brelse(bh); if (inode) { OCFS2_I(inode)->ip_open_count--; iput(inode); } } return status; } static void ocfs2_bump_recovery_generation(struct ocfs2_dinode *di) { le32_add_cpu(&(di->id1.journal1.ij_recovery_generation), 1); } static u32 ocfs2_get_recovery_generation(struct ocfs2_dinode *di) { return le32_to_cpu(di->id1.journal1.ij_recovery_generation); } static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb, int dirty, int replayed) { int status; unsigned int flags; struct ocfs2_journal *journal = osb->journal; struct buffer_head *bh = journal->j_bh; struct ocfs2_dinode *fe; fe = (struct ocfs2_dinode *)bh->b_data; /* The journal bh on the osb always comes from ocfs2_journal_init() * and was validated there inside ocfs2_inode_lock_full(). It's a * code bug if we mess it up. */ BUG_ON(!OCFS2_IS_VALID_DINODE(fe)); flags = le32_to_cpu(fe->id1.journal1.ij_flags); if (dirty) flags |= OCFS2_JOURNAL_DIRTY_FL; else flags &= ~OCFS2_JOURNAL_DIRTY_FL; fe->id1.journal1.ij_flags = cpu_to_le32(flags); if (replayed) ocfs2_bump_recovery_generation(fe); ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &fe->i_check); status = ocfs2_write_block(osb, bh, INODE_CACHE(journal->j_inode)); if (status < 0) mlog_errno(status); return status; } /* * If the journal has been kmalloc'd it needs to be freed after this * call. */ void ocfs2_journal_shutdown(struct ocfs2_super *osb) { struct ocfs2_journal *journal = NULL; int status = 0; struct inode *inode = NULL; int num_running_trans = 0; BUG_ON(!osb); journal = osb->journal; if (!journal) goto done; inode = journal->j_inode; if (journal->j_state != OCFS2_JOURNAL_LOADED) goto done; /* need to inc inode use count - jbd2_journal_destroy will iput. */ if (!igrab(inode)) BUG(); num_running_trans = atomic_read(&(journal->j_num_trans)); trace_ocfs2_journal_shutdown(num_running_trans); /* Do a commit_cache here. It will flush our journal, *and* * release any locks that are still held. * set the SHUTDOWN flag and release the trans lock. * the commit thread will take the trans lock for us below. */ journal->j_state = OCFS2_JOURNAL_IN_SHUTDOWN; /* The OCFS2_JOURNAL_IN_SHUTDOWN will signal to commit_cache to not * drop the trans_lock (which we want to hold until we * completely destroy the journal. */ if (osb->commit_task) { /* Wait for the commit thread */ trace_ocfs2_journal_shutdown_wait(osb->commit_task); kthread_stop(osb->commit_task); osb->commit_task = NULL; } BUG_ON(atomic_read(&(journal->j_num_trans)) != 0); if (ocfs2_mount_local(osb) && (journal->j_journal->j_flags & JBD2_LOADED)) { jbd2_journal_lock_updates(journal->j_journal); status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) mlog_errno(status); } /* Shutdown the kernel journal system */ if (!jbd2_journal_destroy(journal->j_journal) && !status) { /* * Do not toggle if flush was unsuccessful otherwise * will leave dirty metadata in a "clean" journal */ status = ocfs2_journal_toggle_dirty(osb, 0, 0); if (status < 0) mlog_errno(status); } journal->j_journal = NULL; OCFS2_I(inode)->ip_open_count--; /* unlock our journal */ ocfs2_inode_unlock(inode, 1); brelse(journal->j_bh); journal->j_bh = NULL; journal->j_state = OCFS2_JOURNAL_FREE; done: iput(inode); kfree(journal); osb->journal = NULL; } static void ocfs2_clear_journal_error(struct super_block *sb, journal_t *journal, int slot) { int olderr; olderr = jbd2_journal_errno(journal); if (olderr) { mlog(ML_ERROR, "File system error %d recorded in " "journal %u.\n", olderr, slot); mlog(ML_ERROR, "File system on device %s needs checking.\n", sb->s_id); jbd2_journal_ack_err(journal); jbd2_journal_clear_err(journal); } } int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed) { int status = 0; struct ocfs2_super *osb; BUG_ON(!journal); osb = journal->j_osb; status = jbd2_journal_load(journal->j_journal); if (status < 0) { mlog(ML_ERROR, "Failed to load journal!\n"); goto done; } ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num); if (replayed) { jbd2_journal_lock_updates(journal->j_journal); status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) mlog_errno(status); } status = ocfs2_journal_toggle_dirty(osb, 1, replayed); if (status < 0) { mlog_errno(status); goto done; } /* Launch the commit thread */ if (!local) { osb->commit_task = kthread_run(ocfs2_commit_thread, osb, "ocfs2cmt-%s", osb->uuid_str); if (IS_ERR(osb->commit_task)) { status = PTR_ERR(osb->commit_task); osb->commit_task = NULL; mlog(ML_ERROR, "unable to launch ocfs2commit thread, " "error=%d", status); goto done; } } else osb->commit_task = NULL; done: return status; } /* 'full' flag tells us whether we clear out all blocks or if we just * mark the journal clean */ int ocfs2_journal_wipe(struct ocfs2_journal *journal, int full) { int status; BUG_ON(!journal); status = jbd2_journal_wipe(journal->j_journal, full); if (status < 0) { mlog_errno(status); goto bail; } status = ocfs2_journal_toggle_dirty(journal->j_osb, 0, 0); if (status < 0) mlog_errno(status); bail: return status; } static int ocfs2_recovery_completed(struct ocfs2_super *osb) { int empty; struct ocfs2_recovery_map *rm = osb->recovery_map; spin_lock(&osb->osb_lock); empty = (rm->rm_used == 0); spin_unlock(&osb->osb_lock); return empty; } void ocfs2_wait_for_recovery(struct ocfs2_super *osb) { wait_event(osb->recovery_event, ocfs2_recovery_completed(osb)); } /* * JBD Might read a cached version of another nodes journal file. We * don't want this as this file changes often and we get no * notification on those changes. The only way to be sure that we've * got the most up to date version of those blocks then is to force * read them off disk. Just searching through the buffer cache won't * work as there may be pages backing this file which are still marked * up to date. We know things can't change on this file underneath us * as we have the lock by now :) */ static int ocfs2_force_read_journal(struct inode *inode) { int status = 0; int i; u64 v_blkno, p_blkno, p_blocks, num_blocks; struct buffer_head *bh = NULL; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); v_blkno = 0; while (v_blkno < num_blocks) { status = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, &p_blocks, NULL); if (status < 0) { mlog_errno(status); goto bail; } for (i = 0; i < p_blocks; i++, p_blkno++) { bh = __find_get_block_nonatomic(osb->sb->s_bdev, p_blkno, osb->sb->s_blocksize); /* block not cached. */ if (!bh) continue; brelse(bh); bh = NULL; /* We are reading journal data which should not * be put in the uptodate cache. */ status = ocfs2_read_blocks_sync(osb, p_blkno, 1, &bh); if (status < 0) { mlog_errno(status); goto bail; } brelse(bh); bh = NULL; } v_blkno += p_blocks; } bail: return status; } struct ocfs2_la_recovery_item { struct list_head lri_list; int lri_slot; struct ocfs2_dinode *lri_la_dinode; struct ocfs2_dinode *lri_tl_dinode; struct ocfs2_quota_recovery *lri_qrec; enum ocfs2_orphan_reco_type lri_orphan_reco_type; }; /* Does the second half of the recovery process. By this point, the * node is marked clean and can actually be considered recovered, * hence it's no longer in the recovery map, but there's still some * cleanup we can do which shouldn't happen within the recovery thread * as locking in that context becomes very difficult if we are to take * recovering nodes into account. * * NOTE: This function can and will sleep on recovery of other nodes * during cluster locking, just like any other ocfs2 process. */ void ocfs2_complete_recovery(struct work_struct *work) { int ret = 0; struct ocfs2_journal *journal = container_of(work, struct ocfs2_journal, j_recovery_work); struct ocfs2_super *osb = journal->j_osb; struct ocfs2_dinode *la_dinode, *tl_dinode; struct ocfs2_la_recovery_item *item, *n; struct ocfs2_quota_recovery *qrec; enum ocfs2_orphan_reco_type orphan_reco_type; LIST_HEAD(tmp_la_list); trace_ocfs2_complete_recovery( (unsigned long long)OCFS2_I(journal->j_inode)->ip_blkno); spin_lock(&journal->j_lock); list_splice_init(&journal->j_la_cleanups, &tmp_la_list); spin_unlock(&journal->j_lock); list_for_each_entry_safe(item, n, &tmp_la_list, lri_list) { list_del_init(&item->lri_list); ocfs2_wait_on_quotas(osb); la_dinode = item->lri_la_dinode; tl_dinode = item->lri_tl_dinode; qrec = item->lri_qrec; orphan_reco_type = item->lri_orphan_reco_type; trace_ocfs2_complete_recovery_slot(item->lri_slot, la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0, tl_dinode ? le64_to_cpu(tl_dinode->i_blkno) : 0, qrec); if (la_dinode) { ret = ocfs2_complete_local_alloc_recovery(osb, la_dinode); if (ret < 0) mlog_errno(ret); kfree(la_dinode); } if (tl_dinode) { ret = ocfs2_complete_truncate_log_recovery(osb, tl_dinode); if (ret < 0) mlog_errno(ret); kfree(tl_dinode); } ret = ocfs2_recover_orphans(osb, item->lri_slot, orphan_reco_type); if (ret < 0) mlog_errno(ret); if (qrec) { ret = ocfs2_finish_quota_recovery(osb, qrec, item->lri_slot); if (ret < 0) mlog_errno(ret); /* Recovery info is already freed now */ } kfree(item); } trace_ocfs2_complete_recovery_end(ret); } /* NOTE: This function always eats your references to la_dinode and * tl_dinode, either manually on error, or by passing them to * ocfs2_complete_recovery */ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal, int slot_num, struct ocfs2_dinode *la_dinode, struct ocfs2_dinode *tl_dinode, struct ocfs2_quota_recovery *qrec, enum ocfs2_orphan_reco_type orphan_reco_type) { struct ocfs2_la_recovery_item *item; item = kmalloc(sizeof(struct ocfs2_la_recovery_item), GFP_NOFS); if (!item) { /* Though we wish to avoid it, we are in fact safe in * skipping local alloc cleanup as fsck.ocfs2 is more * than capable of reclaiming unused space. */ kfree(la_dinode); kfree(tl_dinode); if (qrec) ocfs2_free_quota_recovery(qrec); mlog_errno(-ENOMEM); return; } INIT_LIST_HEAD(&item->lri_list); item->lri_la_dinode = la_dinode; item->lri_slot = slot_num; item->lri_tl_dinode = tl_dinode; item->lri_qrec = qrec; item->lri_orphan_reco_type = orphan_reco_type; spin_lock(&journal->j_lock); list_add_tail(&item->lri_list, &journal->j_la_cleanups); queue_work(journal->j_osb->ocfs2_wq, &journal->j_recovery_work); spin_unlock(&journal->j_lock); } /* Called by the mount code to queue recovery the last part of * recovery for it's own and offline slot(s). */ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb) { struct ocfs2_journal *journal = osb->journal; if (ocfs2_is_hard_readonly(osb)) return; /* No need to queue up our truncate_log as regular cleanup will catch * that */ ocfs2_queue_recovery_completion(journal, osb->slot_num, osb->local_alloc_copy, NULL, NULL, ORPHAN_NEED_TRUNCATE); ocfs2_schedule_truncate_log_flush(osb, 0); osb->local_alloc_copy = NULL; /* queue to recover orphan slots for all offline slots */ ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE); ocfs2_free_replay_slots(osb); } void ocfs2_complete_quota_recovery(struct ocfs2_super *osb) { if (osb->quota_rec) { ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL, NULL, osb->quota_rec, ORPHAN_NEED_TRUNCATE); osb->quota_rec = NULL; } } static int __ocfs2_recovery_thread(void *arg) { int status, node_num, slot_num; struct ocfs2_super *osb = arg; struct ocfs2_recovery_map *rm = osb->recovery_map; int *rm_quota = NULL; int rm_quota_used = 0, i; struct ocfs2_quota_recovery *qrec; /* Whether the quota supported. */ int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA) || OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, OCFS2_FEATURE_RO_COMPAT_GRPQUOTA); status = ocfs2_wait_on_mount(osb); if (status < 0) { goto bail; } if (quota_enabled) { rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS); if (!rm_quota) { status = -ENOMEM; goto bail; } } restart: if (quota_enabled) { mutex_lock(&osb->recovery_lock); /* Confirm that recovery thread will no longer recover quotas */ if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) { osb->recovery_state = OCFS2_REC_QUOTA_DISABLED; wake_up(&osb->recovery_event); } if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED) quota_enabled = 0; mutex_unlock(&osb->recovery_lock); } status = ocfs2_super_lock(osb, 1); if (status < 0) { mlog_errno(status); goto bail; } status = ocfs2_compute_replay_slots(osb); if (status < 0) mlog_errno(status); /* queue recovery for our own slot */ ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL, NULL, NULL, ORPHAN_NO_NEED_TRUNCATE); spin_lock(&osb->osb_lock); while (rm->rm_used) { /* It's always safe to remove entry zero, as we won't * clear it until ocfs2_recover_node() has succeeded. */ node_num = rm->rm_entries[0]; spin_unlock(&osb->osb_lock); slot_num = ocfs2_node_num_to_slot(osb, node_num); trace_ocfs2_recovery_thread_node(node_num, slot_num); if (slot_num == -ENOENT) { status = 0; goto skip_recovery; } /* It is a bit subtle with quota recovery. We cannot do it * immediately because we have to obtain cluster locks from * quota files and we also don't want to just skip it because * then quota usage would be out of sync until some node takes * the slot. So we remember which nodes need quota recovery * and when everything else is done, we recover quotas. */ if (quota_enabled) { for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++) ; if (i == rm_quota_used) rm_quota[rm_quota_used++] = slot_num; } status = ocfs2_recover_node(osb, node_num, slot_num); skip_recovery: if (!status) { ocfs2_recovery_map_clear(osb, node_num); } else { mlog(ML_ERROR, "Error %d recovering node %d on device (%u,%u)!\n", status, node_num, MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); mlog(ML_ERROR, "Volume requires unmount.\n"); } spin_lock(&osb->osb_lock); } spin_unlock(&osb->osb_lock); trace_ocfs2_recovery_thread_end(status); /* Refresh all journal recovery generations from disk */ status = ocfs2_check_journals_nolocks(osb); status = (status == -EROFS) ? 0 : status; if (status < 0) mlog_errno(status); /* Now it is right time to recover quotas... We have to do this under * superblock lock so that no one can start using the slot (and crash) * before we recover it */ if (quota_enabled) { for (i = 0; i < rm_quota_used; i++) { qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); if (IS_ERR(qrec)) { status = PTR_ERR(qrec); mlog_errno(status); continue; } ocfs2_queue_recovery_completion(osb->journal, rm_quota[i], NULL, NULL, qrec, ORPHAN_NEED_TRUNCATE); } } ocfs2_super_unlock(osb, 1); /* queue recovery for offline slots */ ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE); bail: mutex_lock(&osb->recovery_lock); if (!status && !ocfs2_recovery_completed(osb)) { mutex_unlock(&osb->recovery_lock); goto restart; } ocfs2_free_replay_slots(osb); osb->recovery_thread_task = NULL; if (osb->recovery_state == OCFS2_REC_WANT_DISABLE) osb->recovery_state = OCFS2_REC_DISABLED; wake_up(&osb->recovery_event); mutex_unlock(&osb->recovery_lock); kfree(rm_quota); return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) { int was_set = -1; mutex_lock(&osb->recovery_lock); if (osb->recovery_state < OCFS2_REC_WANT_DISABLE) was_set = ocfs2_recovery_map_set(osb, node_num); trace_ocfs2_recovery_thread(node_num, osb->node_num, osb->recovery_state, osb->recovery_thread_task, was_set); if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE) goto out; if (osb->recovery_thread_task) goto out; osb->recovery_thread_task = kthread_run(__ocfs2_recovery_thread, osb, "ocfs2rec-%s", osb->uuid_str); if (IS_ERR(osb->recovery_thread_task)) { mlog_errno((int)PTR_ERR(osb->recovery_thread_task)); osb->recovery_thread_task = NULL; } out: mutex_unlock(&osb->recovery_lock); wake_up(&osb->recovery_event); } static int ocfs2_read_journal_inode(struct ocfs2_super *osb, int slot_num, struct buffer_head **bh, struct inode **ret_inode) { int status = -EACCES; struct inode *inode = NULL; BUG_ON(slot_num >= osb->max_slots); inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE, slot_num); if (!inode || is_bad_inode(inode)) { mlog_errno(status); goto bail; } SET_INODE_JOURNAL(inode); status = ocfs2_read_inode_block_full(inode, bh, OCFS2_BH_IGNORE_CACHE); if (status < 0) { mlog_errno(status); goto bail; } status = 0; bail: if (inode) { if (status || !ret_inode) iput(inode); else *ret_inode = inode; } return status; } /* Does the actual journal replay and marks the journal inode as * clean. Will only replay if the journal inode is marked dirty. */ static int ocfs2_replay_journal(struct ocfs2_super *osb, int node_num, int slot_num) { int status; int got_lock = 0; unsigned int flags; struct inode *inode = NULL; struct ocfs2_dinode *fe; journal_t *journal = NULL; struct buffer_head *bh = NULL; u32 slot_reco_gen; status = ocfs2_read_journal_inode(osb, slot_num, &bh, &inode); if (status) { mlog_errno(status); goto done; } fe = (struct ocfs2_dinode *)bh->b_data; slot_reco_gen = ocfs2_get_recovery_generation(fe); brelse(bh); bh = NULL; /* * As the fs recovery is asynchronous, there is a small chance that * another node mounted (and recovered) the slot before the recovery * thread could get the lock. To handle that, we dirty read the journal * inode for that slot to get the recovery generation. If it is * different than what we expected, the slot has been recovered. * If not, it needs recovery. */ if (osb->slot_recovery_generations[slot_num] != slot_reco_gen) { trace_ocfs2_replay_journal_recovered(slot_num, osb->slot_recovery_generations[slot_num], slot_reco_gen); osb->slot_recovery_generations[slot_num] = slot_reco_gen; status = -EBUSY; goto done; } /* Continue with recovery as the journal has not yet been recovered */ status = ocfs2_inode_lock_full(inode, &bh, 1, OCFS2_META_LOCK_RECOVERY); if (status < 0) { trace_ocfs2_replay_journal_lock_err(status); if (status != -ERESTARTSYS) mlog(ML_ERROR, "Could not lock journal!\n"); goto done; } got_lock = 1; fe = (struct ocfs2_dinode *) bh->b_data; flags = le32_to_cpu(fe->id1.journal1.ij_flags); slot_reco_gen = ocfs2_get_recovery_generation(fe); if (!(flags & OCFS2_JOURNAL_DIRTY_FL)) { trace_ocfs2_replay_journal_skip(node_num); /* Refresh recovery generation for the slot */ osb->slot_recovery_generations[slot_num] = slot_reco_gen; goto done; } /* we need to run complete recovery for offline orphan slots */ ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); printk(KERN_NOTICE "ocfs2: Begin replay journal (node %d, slot %d) on "\ "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters); status = ocfs2_force_read_journal(inode); if (status < 0) { mlog_errno(status); goto done; } journal = jbd2_journal_init_inode(inode); if (IS_ERR(journal)) { mlog(ML_ERROR, "Linux journal layer error\n"); status = PTR_ERR(journal); goto done; } status = jbd2_journal_load(journal); if (status < 0) { mlog_errno(status); BUG_ON(!igrab(inode)); jbd2_journal_destroy(journal); goto done; } ocfs2_clear_journal_error(osb->sb, journal, slot_num); /* wipe the journal */ jbd2_journal_lock_updates(journal); status = jbd2_journal_flush(journal, 0); jbd2_journal_unlock_updates(journal); if (status < 0) mlog_errno(status); /* This will mark the node clean */ flags = le32_to_cpu(fe->id1.journal1.ij_flags); flags &= ~OCFS2_JOURNAL_DIRTY_FL; fe->id1.journal1.ij_flags = cpu_to_le32(flags); /* Increment recovery generation to indicate successful recovery */ ocfs2_bump_recovery_generation(fe); osb->slot_recovery_generations[slot_num] = ocfs2_get_recovery_generation(fe); ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &fe->i_check); status = ocfs2_write_block(osb, bh, INODE_CACHE(inode)); if (status < 0) mlog_errno(status); BUG_ON(!igrab(inode)); jbd2_journal_destroy(journal); printk(KERN_NOTICE "ocfs2: End replay journal (node %d, slot %d) on "\ "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); done: /* drop the lock on this nodes journal */ if (got_lock) ocfs2_inode_unlock(inode, 1); iput(inode); brelse(bh); return status; } /* * Do the most important parts of node recovery: * - Replay it's journal * - Stamp a clean local allocator file * - Stamp a clean truncate log * - Mark the node clean * * If this function completes without error, a node in OCFS2 can be * said to have been safely recovered. As a result, failure during the * second part of a nodes recovery process (local alloc recovery) is * far less concerning. */ static int ocfs2_recover_node(struct ocfs2_super *osb, int node_num, int slot_num) { int status = 0; struct ocfs2_dinode *la_copy = NULL; struct ocfs2_dinode *tl_copy = NULL; trace_ocfs2_recover_node(node_num, slot_num, osb->node_num); /* Should not ever be called to recover ourselves -- in that * case we should've called ocfs2_journal_load instead. */ BUG_ON(osb->node_num == node_num); status = ocfs2_replay_journal(osb, node_num, slot_num); if (status < 0) { if (status == -EBUSY) { trace_ocfs2_recover_node_skip(slot_num, node_num); status = 0; goto done; } mlog_errno(status); goto done; } /* Stamp a clean local alloc file AFTER recovering the journal... */ status = ocfs2_begin_local_alloc_recovery(osb, slot_num, &la_copy); if (status < 0) { mlog_errno(status); goto done; } /* An error from begin_truncate_log_recovery is not * serious enough to warrant halting the rest of * recovery. */ status = ocfs2_begin_truncate_log_recovery(osb, slot_num, &tl_copy); if (status < 0) mlog_errno(status); /* Likewise, this would be a strange but ultimately not so * harmful place to get an error... */ status = ocfs2_clear_slot(osb, slot_num); if (status < 0) mlog_errno(status); /* This will kfree the memory pointed to by la_copy and tl_copy */ ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy, tl_copy, NULL, ORPHAN_NEED_TRUNCATE); status = 0; done: return status; } /* Test node liveness by trylocking his journal. If we get the lock, * we drop it here. Return 0 if we got the lock, -EAGAIN if node is * still alive (we couldn't get the lock) and < 0 on error. */ static int ocfs2_trylock_journal(struct ocfs2_super *osb, int slot_num) { int status, flags; struct inode *inode = NULL; inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE, slot_num); if (inode == NULL) { mlog(ML_ERROR, "access error\n"); status = -EACCES; goto bail; } if (is_bad_inode(inode)) { mlog(ML_ERROR, "access error (bad inode)\n"); iput(inode); inode = NULL; status = -EACCES; goto bail; } SET_INODE_JOURNAL(inode); flags = OCFS2_META_LOCK_RECOVERY | OCFS2_META_LOCK_NOQUEUE; status = ocfs2_inode_lock_full(inode, NULL, 1, flags); if (status < 0) { if (status != -EAGAIN) mlog_errno(status); goto bail; } ocfs2_inode_unlock(inode, 1); bail: iput(inode); return status; } /* Call this underneath ocfs2_super_lock. It also assumes that the * slot info struct has been updated from disk. */ int ocfs2_mark_dead_nodes(struct ocfs2_super *osb) { unsigned int node_num; int status, i; u32 gen; struct buffer_head *bh = NULL; struct ocfs2_dinode *di; /* This is called with the super block cluster lock, so we * know that the slot map can't change underneath us. */ for (i = 0; i < osb->max_slots; i++) { /* Read journal inode to get the recovery generation */ status = ocfs2_read_journal_inode(osb, i, &bh, NULL); if (status) { mlog_errno(status); goto bail; } di = (struct ocfs2_dinode *)bh->b_data; gen = ocfs2_get_recovery_generation(di); brelse(bh); bh = NULL; spin_lock(&osb->osb_lock); osb->slot_recovery_generations[i] = gen; trace_ocfs2_mark_dead_nodes(i, osb->slot_recovery_generations[i]); if (i == osb->slot_num) { spin_unlock(&osb->osb_lock); continue; } status = ocfs2_slot_to_node_num_locked(osb, i, &node_num); if (status == -ENOENT) { spin_unlock(&osb->osb_lock); continue; } if (__ocfs2_recovery_map_test(osb, node_num)) { spin_unlock(&osb->osb_lock); continue; } spin_unlock(&osb->osb_lock); /* Ok, we have a slot occupied by another node which * is not in the recovery map. We trylock his journal * file here to test if he's alive. */ status = ocfs2_trylock_journal(osb, i); if (!status) { /* Since we're called from mount, we know that * the recovery thread can't race us on * setting / checking the recovery bits. */ ocfs2_recovery_thread(osb, node_num); } else if ((status < 0) && (status != -EAGAIN)) { mlog_errno(status); goto bail; } } status = 0; bail: return status; } /* * Scan timer should get fired every ORPHAN_SCAN_SCHEDULE_TIMEOUT. Add some * randomness to the timeout to minimize multiple nodes firing the timer at the * same time. */ static inline unsigned long ocfs2_orphan_scan_timeout(void) { unsigned long time; get_random_bytes(&time, sizeof(time)); time = ORPHAN_SCAN_SCHEDULE_TIMEOUT + (time % 5000); return msecs_to_jiffies(time); } /* * ocfs2_queue_orphan_scan calls ocfs2_queue_recovery_completion for * every slot, queuing a recovery of the slot on the ocfs2_wq thread. This * is done to catch any orphans that are left over in orphan directories. * * It scans all slots, even ones that are in use. It does so to handle the * case described below: * * Node 1 has an inode it was using. The dentry went away due to memory * pressure. Node 1 closes the inode, but it's on the free list. The node * has the open lock. * Node 2 unlinks the inode. It grabs the dentry lock to notify others, * but node 1 has no dentry and doesn't get the message. It trylocks the * open lock, sees that another node has a PR, and does nothing. * Later node 2 runs its orphan dir. It igets the inode, trylocks the * open lock, sees the PR still, and does nothing. * Basically, we have to trigger an orphan iput on node 1. The only way * for this to happen is if node 1 runs node 2's orphan dir. * * ocfs2_queue_orphan_scan gets called every ORPHAN_SCAN_SCHEDULE_TIMEOUT * seconds. It gets an EX lock on os_lockres and checks sequence number * stored in LVB. If the sequence number has changed, it means some other * node has done the scan. This node skips the scan and tracks the * sequence number. If the sequence number didn't change, it means a scan * hasn't happened. The node queues a scan and increments the * sequence number in the LVB. */ static void ocfs2_queue_orphan_scan(struct ocfs2_super *osb) { struct ocfs2_orphan_scan *os; int status, i; u32 seqno = 0; os = &osb->osb_orphan_scan; if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE) goto out; trace_ocfs2_queue_orphan_scan_begin(os->os_count, os->os_seqno, atomic_read(&os->os_state)); status = ocfs2_orphan_scan_lock(osb, &seqno); if (status < 0) { if (status != -EAGAIN) mlog_errno(status); goto out; } /* Do no queue the tasks if the volume is being umounted */ if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE) goto unlock; if (os->os_seqno != seqno) { os->os_seqno = seqno; goto unlock; } for (i = 0; i < osb->max_slots; i++) ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL, NULL, ORPHAN_NO_NEED_TRUNCATE); /* * We queued a recovery on orphan slots, increment the sequence * number and update LVB so other node will skip the scan for a while */ seqno++; os->os_count++; os->os_scantime = ktime_get_seconds(); unlock: ocfs2_orphan_scan_unlock(osb, seqno); out: trace_ocfs2_queue_orphan_scan_end(os->os_count, os->os_seqno, atomic_read(&os->os_state)); return; } /* Worker task that gets fired every ORPHAN_SCAN_SCHEDULE_TIMEOUT millsec */ static void ocfs2_orphan_scan_work(struct work_struct *work) { struct ocfs2_orphan_scan *os; struct ocfs2_super *osb; os = container_of(work, struct ocfs2_orphan_scan, os_orphan_scan_work.work); osb = os->os_osb; mutex_lock(&os->os_lock); ocfs2_queue_orphan_scan(osb); if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work, ocfs2_orphan_scan_timeout()); mutex_unlock(&os->os_lock); } void ocfs2_orphan_scan_stop(struct ocfs2_super *osb) { struct ocfs2_orphan_scan *os; os = &osb->osb_orphan_scan; if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) { atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); mutex_lock(&os->os_lock); cancel_delayed_work(&os->os_orphan_scan_work); mutex_unlock(&os->os_lock); } } void ocfs2_orphan_scan_init(struct ocfs2_super *osb) { struct ocfs2_orphan_scan *os; os = &osb->osb_orphan_scan; os->os_osb = osb; os->os_count = 0; os->os_seqno = 0; mutex_init(&os->os_lock); INIT_DELAYED_WORK(&os->os_orphan_scan_work, ocfs2_orphan_scan_work); } void ocfs2_orphan_scan_start(struct ocfs2_super *osb) { struct ocfs2_orphan_scan *os; os = &osb->osb_orphan_scan; os->os_scantime = ktime_get_seconds(); if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb)) atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); else { atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE); queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work, ocfs2_orphan_scan_timeout()); } } struct ocfs2_orphan_filldir_priv { struct dir_context ctx; struct inode *head; struct ocfs2_super *osb; enum ocfs2_orphan_reco_type orphan_reco_type; }; static bool ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, int name_len, loff_t pos, u64 ino, unsigned type) { struct ocfs2_orphan_filldir_priv *p = container_of(ctx, struct ocfs2_orphan_filldir_priv, ctx); struct inode *iter; if (name_len == 1 && !strncmp(".", name, 1)) return true; if (name_len == 2 && !strncmp("..", name, 2)) return true; /* do not include dio entry in case of orphan scan */ if ((p->orphan_reco_type == ORPHAN_NO_NEED_TRUNCATE) && (!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX, OCFS2_DIO_ORPHAN_PREFIX_LEN))) return true; /* Skip bad inodes so that recovery can continue */ iter = ocfs2_iget(p->osb, ino, OCFS2_FI_FLAG_ORPHAN_RECOVERY, 0); if (IS_ERR(iter)) return true; if (!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX, OCFS2_DIO_ORPHAN_PREFIX_LEN)) OCFS2_I(iter)->ip_flags |= OCFS2_INODE_DIO_ORPHAN_ENTRY; /* Skip inodes which are already added to recover list, since dio may * happen concurrently with unlink/rename */ if (OCFS2_I(iter)->ip_next_orphan) { iput(iter); return true; } trace_ocfs2_orphan_filldir((unsigned long long)OCFS2_I(iter)->ip_blkno); /* No locking is required for the next_orphan queue as there * is only ever a single process doing orphan recovery. */ OCFS2_I(iter)->ip_next_orphan = p->head; p->head = iter; return true; } static int ocfs2_queue_orphans(struct ocfs2_super *osb, int slot, struct inode **head, enum ocfs2_orphan_reco_type orphan_reco_type) { int status; struct inode *orphan_dir_inode = NULL; struct ocfs2_orphan_filldir_priv priv = { .ctx.actor = ocfs2_orphan_filldir, .osb = osb, .head = *head, .orphan_reco_type = orphan_reco_type }; orphan_dir_inode = ocfs2_get_system_file_inode(osb, ORPHAN_DIR_SYSTEM_INODE, slot); if (!orphan_dir_inode) { status = -ENOENT; mlog_errno(status); return status; } inode_lock(orphan_dir_inode); status = ocfs2_inode_lock(orphan_dir_inode, NULL, 0); if (status < 0) { mlog_errno(status); goto out; } status = ocfs2_dir_foreach(orphan_dir_inode, &priv.ctx); if (status) { mlog_errno(status); goto out_cluster; } *head = priv.head; out_cluster: ocfs2_inode_unlock(orphan_dir_inode, 0); out: inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); return status; } static int ocfs2_orphan_recovery_can_continue(struct ocfs2_super *osb, int slot) { int ret; spin_lock(&osb->osb_lock); ret = !osb->osb_orphan_wipes[slot]; spin_unlock(&osb->osb_lock); return ret; } static void ocfs2_mark_recovering_orphan_dir(struct ocfs2_super *osb, int slot) { spin_lock(&osb->osb_lock); /* Mark ourselves such that new processes in delete_inode() * know to quit early. */ ocfs2_node_map_set_bit(osb, &osb->osb_recovering_orphan_dirs, slot); while (osb->osb_orphan_wipes[slot]) { /* If any processes are already in the middle of an * orphan wipe on this dir, then we need to wait for * them. */ spin_unlock(&osb->osb_lock); wait_event_interruptible(osb->osb_wipe_event, ocfs2_orphan_recovery_can_continue(osb, slot)); spin_lock(&osb->osb_lock); } spin_unlock(&osb->osb_lock); } static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb, int slot) { ocfs2_node_map_clear_bit(osb, &osb->osb_recovering_orphan_dirs, slot); } /* * Orphan recovery. Each mounted node has it's own orphan dir which we * must run during recovery. Our strategy here is to build a list of * the inodes in the orphan dir and iget/iput them. The VFS does * (most) of the rest of the work. * * Orphan recovery can happen at any time, not just mount so we have a * couple of extra considerations. * * - We grab as many inodes as we can under the orphan dir lock - * doing iget() outside the orphan dir risks getting a reference on * an invalid inode. * - We must be sure not to deadlock with other processes on the * system wanting to run delete_inode(). This can happen when they go * to lock the orphan dir and the orphan recovery process attempts to * iget() inside the orphan dir lock. This can be avoided by * advertising our state to ocfs2_delete_inode(). */ static int ocfs2_recover_orphans(struct ocfs2_super *osb, int slot, enum ocfs2_orphan_reco_type orphan_reco_type) { int ret = 0; struct inode *inode = NULL; struct inode *iter; struct ocfs2_inode_info *oi; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di = NULL; trace_ocfs2_recover_orphans(slot); ocfs2_mark_recovering_orphan_dir(osb, slot); ret = ocfs2_queue_orphans(osb, slot, &inode, orphan_reco_type); ocfs2_clear_recovering_orphan_dir(osb, slot); /* Error here should be noted, but we want to continue with as * many queued inodes as we've got. */ if (ret) mlog_errno(ret); while (inode) { oi = OCFS2_I(inode); trace_ocfs2_recover_orphans_iput( (unsigned long long)oi->ip_blkno); iter = oi->ip_next_orphan; oi->ip_next_orphan = NULL; if (oi->ip_flags & OCFS2_INODE_DIO_ORPHAN_ENTRY) { inode_lock(inode); ret = ocfs2_rw_lock(inode, 1); if (ret < 0) { mlog_errno(ret); goto unlock_mutex; } /* * We need to take and drop the inode lock to * force read inode from disk. */ ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret) { mlog_errno(ret); goto unlock_rw; } di = (struct ocfs2_dinode *)di_bh->b_data; if (di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)) { ret = ocfs2_truncate_file(inode, di_bh, i_size_read(inode)); if (ret < 0) { if (ret != -ENOSPC) mlog_errno(ret); goto unlock_inode; } ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0); if (ret) mlog_errno(ret); } unlock_inode: ocfs2_inode_unlock(inode, 1); brelse(di_bh); di_bh = NULL; unlock_rw: ocfs2_rw_unlock(inode, 1); unlock_mutex: inode_unlock(inode); /* clear dio flag in ocfs2_inode_info */ oi->ip_flags &= ~OCFS2_INODE_DIO_ORPHAN_ENTRY; } else { spin_lock(&oi->ip_lock); /* Set the proper information to get us going into * ocfs2_delete_inode. */ oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED; spin_unlock(&oi->ip_lock); } iput(inode); inode = iter; } return ret; } static int __ocfs2_wait_on_mount(struct ocfs2_super *osb, int quota) { /* This check is good because ocfs2 will wait on our recovery * thread before changing it to something other than MOUNTED * or DISABLED. */ wait_event(osb->osb_mount_event, (!quota && atomic_read(&osb->vol_state) == VOLUME_MOUNTED) || atomic_read(&osb->vol_state) == VOLUME_MOUNTED_QUOTAS || atomic_read(&osb->vol_state) == VOLUME_DISABLED); /* If there's an error on mount, then we may never get to the * MOUNTED flag, but this is set right before * dismount_volume() so we can trust it. */ if (atomic_read(&osb->vol_state) == VOLUME_DISABLED) { trace_ocfs2_wait_on_mount(VOLUME_DISABLED); mlog(0, "mount error, exiting!\n"); return -EBUSY; } return 0; } static int ocfs2_commit_thread(void *arg) { int status; struct ocfs2_super *osb = arg; struct ocfs2_journal *journal = osb->journal; /* we can trust j_num_trans here because _should_stop() is only set in * shutdown and nobody other than ourselves should be able to start * transactions. committing on shutdown might take a few iterations * as final transactions put deleted inodes on the list */ while (!(kthread_should_stop() && atomic_read(&journal->j_num_trans) == 0)) { wait_event_interruptible(osb->checkpoint_event, atomic_read(&journal->j_num_trans) || kthread_should_stop()); status = ocfs2_commit_cache(osb); if (status < 0) { static unsigned long abort_warn_time; /* Warn about this once per minute */ if (printk_timed_ratelimit(&abort_warn_time, 60*HZ)) mlog(ML_ERROR, "status = %d, journal is " "already aborted.\n", status); /* * After ocfs2_commit_cache() fails, j_num_trans has a * non-zero value. Sleep here to avoid a busy-wait * loop. */ msleep_interruptible(1000); } if (kthread_should_stop() && atomic_read(&journal->j_num_trans)){ mlog(ML_KTHREAD, "commit_thread: %u transactions pending on " "shutdown\n", atomic_read(&journal->j_num_trans)); } } return 0; } /* Reads all the journal inodes without taking any cluster locks. Used * for hard readonly access to determine whether any journal requires * recovery. Also used to refresh the recovery generation numbers after * a journal has been recovered by another node. */ int ocfs2_check_journals_nolocks(struct ocfs2_super *osb) { int ret = 0; unsigned int slot; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; int journal_dirty = 0; for(slot = 0; slot < osb->max_slots; slot++) { ret = ocfs2_read_journal_inode(osb, slot, &di_bh, NULL); if (ret) { mlog_errno(ret); goto out; } di = (struct ocfs2_dinode *) di_bh->b_data; osb->slot_recovery_generations[slot] = ocfs2_get_recovery_generation(di); if (le32_to_cpu(di->id1.journal1.ij_flags) & OCFS2_JOURNAL_DIRTY_FL) journal_dirty = 1; brelse(di_bh); di_bh = NULL; } out: if (journal_dirty) ret = -EROFS; return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NFS internal definitions */ #include "nfs4_fs.h" #include <linux/fs_context.h> #include <linux/security.h> #include <linux/compiler_attributes.h> #include <linux/crc32.h> #include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> #include <linux/nfslocalio.h> #include <linux/wait_bit.h> #define NFS_SB_MASK (SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; struct nfs_string; struct nfs_pageio_descriptor; static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) { if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; return 1; } static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) { if (!(NFS_SB(dentry->d_sb)->flags & NFS_MOUNT_SOFTREVAL)) return false; if (!d_is_positive(dentry) || !NFS_FH(d_inode(dentry))->size) return false; return true; } static inline fmode_t flags_to_mode(int flags) { fmode_t res = (__force fmode_t)flags & FMODE_EXEC; if ((flags & O_ACCMODE) != O_WRONLY) res |= FMODE_READ; if ((flags & O_ACCMODE) != O_RDONLY) res |= FMODE_WRITE; return res; } /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. */ #define NFS_MAX_SECFLAVORS (12) /* * Value used if the user did not specify a port value. */ #define NFS_UNSPEC_PORT (-1) #define NFS_UNSPEC_RETRANS (UINT_MAX) #define NFS_UNSPEC_TIMEO (UINT_MAX) struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ const struct sockaddr_storage *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; struct nfs_subversion *nfs_mod; int proto; u32 minorversion; unsigned int nconnect; unsigned int max_connect; struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; struct xprtsec_parms xprtsec; unsigned long connect_timeout; unsigned long reconnect_timeout; }; /* * In-kernel mount arguments */ struct nfs_fs_context { bool internal; bool skip_reconfig_option_check; bool need_mount; bool sloppy; unsigned int flags; /* NFS{,4}_MOUNT_* flags */ unsigned int rsize, wsize; unsigned int timeo, retrans; unsigned int acregmin, acregmax; unsigned int acdirmin, acdirmax; unsigned int namlen; unsigned int options; unsigned int bsize; struct nfs_auth_info auth_info; rpc_authflavor_t selected_flavor; struct xprtsec_parms xprtsec; char *client_address; unsigned int version; unsigned int minorversion; char *fscache_uniq; unsigned short protofamily; unsigned short mountfamily; bool has_sec_mnt_opts; int lock_status; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; u32 version; int port; unsigned short protocol; } mount_server; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; char *export_path; int port; unsigned short protocol; unsigned short nconnect; unsigned short max_connect; unsigned short export_path_len; } nfs_server; struct nfs_fh *mntfh; struct nfs_server *server; struct nfs_subversion *nfs_mod; /* Information for a cloned mount. */ struct nfs_clone_mount { struct super_block *sb; struct dentry *dentry; struct nfs_fattr *fattr; unsigned int inherited_bsize; } clone_data; }; enum nfs_lock_status { NFS_LOCK_NOT_SET = 0, NFS_LOCK_LOCK = 1, NFS_LOCK_NOLOCK = 2, }; #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) #define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { return fc->fs_private; } /* mount_clnt.c */ struct nfs_mount_request { struct sockaddr_storage *sap; size_t salen; char *hostname; char *dirpath; u32 version; unsigned short protocol; struct nfs_fh *fh; int noresvport; unsigned int *auth_flav_len; rpc_authflavor_t *auth_flavs; struct net *net; }; extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans); /* client.c */ extern const struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); extern void nfs_clients_exit(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); struct nfs_client *nfs_get_client(const struct nfs_client_initdata *); int nfs_probe_server(struct nfs_server *, struct nfs_fh *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); struct nfs_server *nfs_alloc_server(void); void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); extern void nfs_put_client(struct nfs_client *); extern void nfs_free_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); extern struct nfs_server *nfs_create_server(struct fs_context *); extern void nfs_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, struct sockaddr_storage *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); extern bool nfs_client_init_is_complete(const struct nfs_client *clp); extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); extern int nfs_fs_proc_net_init(struct net *net); extern void nfs_fs_proc_net_exit(struct net *net); #else static inline int nfs_fs_proc_net_init(struct net *net) { return 0; } static inline void nfs_fs_proc_net_exit(struct net *net) { } static inline int nfs_fs_proc_init(void) { return 0; } static inline void nfs_fs_proc_exit(void) { } #endif /* callback_xdr.c */ extern const struct svc_version nfs4_callback_version1; extern const struct svc_version nfs4_callback_version4; /* fs_context.c */ extern struct file_system_type nfs_fs_type; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); extern int __init nfs_init_readpagecache(void); extern void nfs_destroy_readpagecache(void); extern int __init nfs_init_writepagecache(void); extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags, struct nfsd_file *localio); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state; } /* nfs2xdr.c */ extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs3xdr.c */ extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; extern const u32 nfs41_maxwrite_overhead; extern const u32 nfs41_maxgetdevinfo_overhead; #endif /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { if (!dst || !src) return NULL; if (src->len > NFS4_MAXLABELLEN) return NULL; dst->lfs = src->lfs; dst->pi = src->pi; dst->len = src->len; memcpy(dst->label, src->label, src->len); return dst; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) nfsi->cache_validity |= NFS_INO_INVALID_LABEL; } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { return NULL; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ extern void nfs_readdir_record_entry_cache_hit(struct inode *dir); extern void nfs_readdir_record_entry_cache_miss(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); struct dentry *nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); int nfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); int nfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int nfs_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); #ifdef CONFIG_NFS_V4_2 static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { if (!(server->caps & NFS_CAP_XATTR)) return 0; return NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | NFS4_ACCESS_XALIST; } #else static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { return 0; } #endif /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); ssize_t nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int nfs_file_mmap_prepare(struct vm_area_desc *); ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, loff_t to); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct workqueue_struct *nfslocaliod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); extern void nfs_zap_acl_cache(struct inode *inode); extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* localio.c */ struct nfs_local_dio { u32 mem_align; u32 offset_align; loff_t middle_offset; loff_t end_offset; ssize_t start_len; /* Length for misaligned first extent */ ssize_t middle_len; /* Length for DIO-aligned middle extent */ ssize_t end_len; /* Length for misaligned last extent */ }; extern void nfs_local_probe_async(struct nfs_client *); extern void nfs_local_probe_async_work(struct work_struct *); extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, const struct cred *, struct nfs_fh *, struct nfs_file_localio *, const fmode_t); extern int nfs_local_doio(struct nfs_client *, struct nfsd_file *, struct nfs_pgio_header *, const struct rpc_call_ops *); extern int nfs_local_commit(struct nfsd_file *, struct nfs_commit_data *, const struct rpc_call_ops *, int); extern bool nfs_server_is_local(const struct nfs_client *clp); #else /* CONFIG_NFS_LOCALIO */ static inline void nfs_local_probe(struct nfs_client *clp) {} static inline void nfs_local_probe_async(struct nfs_client *clp) {} static inline struct nfsd_file * nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, struct nfs_fh *fh, struct nfs_file_localio *nfl, const fmode_t mode) { return NULL; } static inline int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, struct nfs_pgio_header *hdr, const struct rpc_call_ops *call_ops) { return -EINVAL; } static inline int nfs_local_commit(struct nfsd_file *localio, struct nfs_commit_data *data, const struct rpc_call_ops *call_ops, int how) { return -EINVAL; } static inline bool nfs_server_is_local(const struct nfs_client *clp) { return false; } #endif /* CONFIG_NFS_LOCALIO */ /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); extern int nfs_client_for_each_server(struct nfs_client *clp, int (*fn)(struct nfs_server *, void *), void *data); #ifdef CONFIG_NFS_FSCACHE extern const struct netfs_request_ops nfs_netfs_ops; #endif /* io.c */ extern __must_check int nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); extern __must_check int nfs_start_io_write(struct inode *inode); extern void nfs_end_io_write(struct inode *inode); extern __must_check int nfs_start_io_direct(struct inode *inode); extern void nfs_end_io_direct(struct inode *inode); static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) { return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } /* Must be called with exclusively locked inode->i_rwsem */ static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi) { if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { clear_bit(NFS_INO_ODIRECT, &nfsi->flags); inode_dio_wait(&nfsi->vfs_inode); } } /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); int nfs_submount(struct fs_context *, struct nfs_server *); int nfs_do_submount(struct fs_context *); /* getroot.c */ extern int nfs_get_root(struct super_block *s, struct fs_context *fc); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif struct nfs_pgio_completion_ops; /* read.c */ extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size); extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); int nfs_reconfigure(struct fs_context *); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_commit_free(struct nfs_commit_data *p); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags, struct nfsd_file *localio); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max); unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); int nfs_write_need_commit(struct nfs_pgio_header *); void nfs_writeback_update_inode(struct nfs_pgio_header *hdr); int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct inode *inode, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode); void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); int nfs_filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); #ifdef CONFIG_NFS_V4_1 static inline void pnfs_bucket_clear_pnfs_ds_commit_verifiers(struct pnfs_commit_bucket *buckets, unsigned int nbuckets) { unsigned int i; for (i = 0; i < nbuckets; i++) buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; } static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { struct pnfs_commit_array *array; rcu_read_lock(); list_for_each_entry_rcu(array, &cinfo->commits, cinfo_list) pnfs_bucket_clear_pnfs_ds_commit_verifiers(array->buckets, array->nbuckets); rcu_read_unlock(); } #else static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { } #endif #ifdef CONFIG_MIGRATION int nfs_migrate_folio(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); #else #define nfs_migrate_folio NULL #endif static inline int nfs_write_verifier_cmp(const struct nfs_write_verifier *v1, const struct nfs_write_verifier *v2) { return memcmp(v1->data, v2->data, sizeof(v1->data)); } static inline bool nfs_write_match_verf(const struct nfs_writeverf *verf, struct nfs_page *req) { return verf->committed > NFS_UNSTABLE && !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } static inline gfp_t nfs_io_gfp_mask(void) { gfp_t ret = current_gfp_context(GFP_KERNEL); /* For workers __GFP_NORETRY only with __GFP_IO or __GFP_FS */ if ((current->flags & PF_WQ_WORKER) && ret == GFP_KERNEL) ret |= __GFP_NORETRY | __GFP_NOWARN; return ret; } /* * Special version of should_remove_suid() that ignores capabilities. */ static inline int nfs_should_remove_suid(const struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; /* * sgid without any exec bits is just a mandatory locking mark; leave * it alone. If some exec bits are set, it's a real sgid; kill it. */ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; if (unlikely(kill && S_ISREG(mode))) return kill; return 0; } /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *old_dentry, struct dentry *new_dentry, void (*complete)(struct rpc_task *, struct nfs_renamedata *)); extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); /* direct.c */ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset); /* nfs4proc.c */ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); extern int nfs40_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data); static inline struct inode *nfs_igrab_and_active(struct inode *inode) { struct super_block *sb = inode->i_sb; if (sb && nfs_sb_active(sb)) { if (igrab(inode)) return inode; nfs_sb_deactive(sb); } return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) { if (inode != NULL) { struct super_block *sb = inode->i_sb; iput(inode); nfs_sb_deactive(sb); } } /* * Determine the device name as a string */ static inline char *nfs_devname(struct dentry *dentry, char *buffer, ssize_t buflen) { char *dummy; return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); } /* * Determine the actual block size (and log2 thereof) */ static inline unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) { /* make sure blocksize is a power of two */ if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--) ; bsize = 1UL << nrbits; if (nrbitsp) *nrbitsp = nrbits; } return bsize; } /* * Calculate the number of 512byte blocks used. */ static inline blkcnt_t nfs_calc_block_size(u64 tsize) { blkcnt_t used = (tsize + 511) >> 9; return (used > ULONG_MAX) ? ULONG_MAX : used; } /* * Compute and set NFS server blocksize */ static inline unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) { if (bsize < NFS_MIN_FILE_IO_SIZE) bsize = NFS_DEF_FILE_IO_SIZE; else if (bsize >= NFS_MAX_FILE_IO_SIZE) bsize = NFS_MAX_FILE_IO_SIZE; return nfs_block_bits(bsize, nrbitsp); } /* * Compute and set NFS server rsize / wsize */ static inline unsigned long nfs_io_size(unsigned long iosize, enum xprt_transports proto) { if (iosize < NFS_MIN_FILE_IO_SIZE) iosize = NFS_DEF_FILE_IO_SIZE; else if (iosize >= NFS_MAX_FILE_IO_SIZE) iosize = NFS_MAX_FILE_IO_SIZE; if (proto == XPRT_TRANSPORT_UDP || iosize < PAGE_SIZE) return nfs_block_bits(iosize, NULL); return iosize & PAGE_MASK; } /* * Determine the maximum file size for a superblock */ static inline void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) { sb->s_maxbytes = (loff_t)maxfilesize; if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) sb->s_maxbytes = MAX_LFS_FILESIZE; } /* * Record the page as unstable (an extra writeback period) and mark its * inode as dirty. */ static inline void nfs_folio_mark_unstable(struct folio *folio, struct nfs_commit_info *cinfo) { if (folio && !cinfo->dreq) { struct inode *inode = folio->mapping->host; long nr = folio_nr_pages(folio); /* This page is really still in write-back - just that the * writeback is happening on the server now. */ node_stat_mod_folio(folio, NR_WRITEBACK, nr); wb_stat_mod(&inode_to_bdi(inode)->wb, WB_WRITEBACK, nr); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } /* * Determine the number of bytes of data the page contains */ static inline size_t nfs_folio_length(struct folio *folio) { loff_t i_size = i_size_read(folio->mapping->host); if (i_size > 0) { pgoff_t index = folio->index >> folio_order(folio); pgoff_t end_index = (i_size - 1) >> folio_shift(folio); if (index < end_index) return folio_size(folio); if (index == end_index) return offset_in_folio(folio, i_size - 1) + 1; } return 0; } /* * Convert a umode to a dirent->d_type */ static inline unsigned char nfs_umode_to_dtype(umode_t mode) { return (mode >> 12) & 15; } /* * Determine the number of pages in an array of length 'len' and * with a base offset of 'base' */ static inline unsigned int nfs_page_array_len(unsigned int base, size_t len) { return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } /* * Convert a struct timespec64 into a 64-bit change attribute * * This does approximately the same thing as timespec64_to_ns(), * but for calculation efficiency, we multiply the seconds by * 1024*1024*1024. */ static inline u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } static inline bool nfs_current_task_exiting(void) { return (current->flags & PF_EXITING) != 0; } static inline bool nfs_error_is_fatal(int err) { switch (err) { case -ERESTARTSYS: case -EINTR: case -EACCES: case -EDQUOT: case -EFBIG: case -EIO: case -ENOSPC: case -EROFS: case -ESTALE: case -E2BIG: case -ENOMEM: case -ETIMEDOUT: return true; default: return false; } } static inline bool nfs_error_is_fatal_on_server(int err) { switch (err) { case 0: case -ERESTARTSYS: case -EINTR: case -ENOMEM: return false; } return nfs_error_is_fatal(err); } /* * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ static inline void nfs_set_port(struct sockaddr_storage *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; rpc_set_port((struct sockaddr *)sap, *port); } struct nfs_direct_req { struct kref kref; /* release manager */ /* I/O parameters */ struct nfs_open_context *ctx; /* file open context info */ struct nfs_lock_context *l_ctx; /* Lock context info */ struct kiocb * iocb; /* controlling i/o request */ struct inode * inode; /* target file of i/o */ /* completion state */ atomic_t io_count; /* i/os we're waiting for */ spinlock_t lock; /* protect completion state */ loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ /* commit state */ struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ struct work_struct work; int flags; /* for write */ #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ /* for read */ #define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ #define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ }; |
| 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * CPU <-> hardware queue mapping helpers * * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/group_cpus.h> #include <linux/device/bus.h> #include <linux/sched/isolation.h> #include "blk.h" #include "blk-mq.h" static unsigned int blk_mq_num_queues(const struct cpumask *mask, unsigned int max_queues) { unsigned int num; num = cpumask_weight(mask); return min_not_zero(num, max_queues); } /** * blk_mq_num_possible_queues - Calc nr of queues for multiqueue devices * @max_queues: The maximum number of queues the hardware/driver * supports. If max_queues is 0, the argument is * ignored. * * Calculates the number of queues to be used for a multiqueue * device based on the number of possible CPUs. */ unsigned int blk_mq_num_possible_queues(unsigned int max_queues) { return blk_mq_num_queues(cpu_possible_mask, max_queues); } EXPORT_SYMBOL_GPL(blk_mq_num_possible_queues); /** * blk_mq_num_online_queues - Calc nr of queues for multiqueue devices * @max_queues: The maximum number of queues the hardware/driver * supports. If max_queues is 0, the argument is * ignored. * * Calculates the number of queues to be used for a multiqueue * device based on the number of online CPUs. */ unsigned int blk_mq_num_online_queues(unsigned int max_queues) { return blk_mq_num_queues(cpu_online_mask, max_queues); } EXPORT_SYMBOL_GPL(blk_mq_num_online_queues); void blk_mq_map_queues(struct blk_mq_queue_map *qmap) { const struct cpumask *masks; unsigned int queue, cpu, nr_masks; masks = group_cpus_evenly(qmap->nr_queues, &nr_masks); if (!masks) { for_each_possible_cpu(cpu) qmap->mq_map[cpu] = qmap->queue_offset; return; } for (queue = 0; queue < qmap->nr_queues; queue++) { for_each_cpu(cpu, &masks[queue % nr_masks]) qmap->mq_map[cpu] = qmap->queue_offset + queue; } kfree(masks); } EXPORT_SYMBOL_GPL(blk_mq_map_queues); /** * blk_mq_hw_queue_to_node - Look up the memory node for a hardware queue index * @qmap: CPU to hardware queue map. * @index: hardware queue index. * * We have no quick way of doing reverse lookups. This is only used at * queue init time, so runtime isn't important. */ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index) { int i; for_each_possible_cpu(i) { if (index == qmap->mq_map[i]) return cpu_to_node(i); } return NUMA_NO_NODE; } /** * blk_mq_map_hw_queues - Create CPU to hardware queue mapping * @qmap: CPU to hardware queue map * @dev: The device to map queues * @offset: Queue offset to use for the device * * Create a CPU to hardware queue mapping in @qmap. The struct bus_type * irq_get_affinity callback will be used to retrieve the affinity. */ void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, struct device *dev, unsigned int offset) { const struct cpumask *mask; unsigned int queue, cpu; if (!dev->bus->irq_get_affinity) goto fallback; for (queue = 0; queue < qmap->nr_queues; queue++) { mask = dev->bus->irq_get_affinity(dev, queue + offset); if (!mask) goto fallback; for_each_cpu(cpu, mask) qmap->mq_map[cpu] = qmap->queue_offset + queue; } return; fallback: blk_mq_map_queues(qmap); } EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues); |
| 1 1 1 1 1 1 1659 1659 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "swap_table.h" #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entries_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static struct kmem_cache *swap_table_cachep; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); struct percpu_swap_cluster { struct swap_info_struct *si[SWAP_NR_ORDERS]; unsigned long offset[SWAP_NR_ORDERS]; local_lock_t lock; }; static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = { .si = { NULL }, .offset = { SWAP_ENTRY_INVALID }, .lock = INIT_LOCAL_LOCK(), }; /* May return NULL on invalid type, caller must check for NULL return */ static struct swap_info_struct *swap_type_to_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } /* May return NULL on invalid entry, caller must check for NULL return */ static struct swap_info_struct *swap_entry_to_info(swp_entry_t entry) { return swap_type_to_info(swp_type(entry)); } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* * Use the second highest bit of inuse_pages counter as the indicator * if one swap device is on the available plist, so the atomic can * still be updated arithmetically while having special data embedded. * * inuse_pages counter is the only thing indicating if a device should * be on avail_lists or not (except swapon / swapoff). By embedding the * off-list bit in the atomic counter, updates no longer need any lock * to check the list status. * * This bit will be set if the device is not on the plist and not * usable, will be cleared if the device is on the plist. */ #define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) #define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) static long swap_usage_in_pages(struct swap_info_struct *si) { return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 static bool swap_only_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1 && swap_count(count) != SWAP_MAP_SHMEM) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { const swp_entry_t entry = swp_entry(si->type, offset); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; again: folio = swap_cache_get_folio(entry); if (!folio) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; /* * Offset could point to the middle of a large folio, or folio * may no longer point to the expected offset before it's locked. */ if (!folio_matches_swap_entry(folio, entry)) { folio_unlock(folio); folio_put(folio); goto again; } offset = swp_offset(folio->swap); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = swap_cluster_lock(si, offset); need_reclaim = swap_only_has_cache(si, offset, nr_pages); swap_cluster_unlock(ci); if (!need_reclaim) goto out_unlock; swap_cache_del_folio(folio); folio_set_dirty(folio); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #define LATENCY_LIMIT 256 static inline bool cluster_is_empty(struct swap_cluster_info *info) { return info->count == 0; } static inline bool cluster_is_discard(struct swap_cluster_info *info) { return info->flags == CLUSTER_FLAG_DISCARD; } static inline bool cluster_table_is_alloced(struct swap_cluster_info *ci) { return rcu_dereference_protected(ci->table, lockdep_is_held(&ci->lock)); } static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) { if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) return false; if (!cluster_table_is_alloced(ci)) return false; if (!order) return true; return cluster_is_empty(ci) || order == ci->order; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static struct swap_table *swap_table_alloc(gfp_t gfp) { struct folio *folio; if (!SWP_TABLE_USE_PAGE) return kmem_cache_zalloc(swap_table_cachep, gfp); folio = folio_alloc(gfp | __GFP_ZERO, 0); if (folio) return folio_address(folio); return NULL; } static void swap_table_free_folio_rcu_cb(struct rcu_head *head) { struct folio *folio; folio = page_folio(container_of(head, struct page, rcu_head)); folio_put(folio); } static void swap_table_free(struct swap_table *table) { if (!SWP_TABLE_USE_PAGE) { kmem_cache_free(swap_table_cachep, table); return; } call_rcu(&(folio_page(virt_to_folio(table), 0)->rcu_head), swap_table_free_folio_rcu_cb); } static void swap_cluster_free_table(struct swap_cluster_info *ci) { unsigned int ci_off; struct swap_table *table; /* Only empty cluster's table is allow to be freed */ lockdep_assert_held(&ci->lock); VM_WARN_ON_ONCE(!cluster_is_empty(ci)); for (ci_off = 0; ci_off < SWAPFILE_CLUSTER; ci_off++) VM_WARN_ON_ONCE(!swp_tb_is_null(__swap_table_get(ci, ci_off))); table = (void *)rcu_dereference_protected(ci->table, true); rcu_assign_pointer(ci->table, NULL); swap_table_free(table); } /* * Allocate swap table for one cluster. Attempt an atomic allocation first, * then fallback to sleeping allocation. */ static struct swap_cluster_info * swap_cluster_alloc_table(struct swap_info_struct *si, struct swap_cluster_info *ci) { struct swap_table *table; /* * Only cluster isolation from the allocator does table allocation. * Swap allocator uses percpu clusters and holds the local lock. */ lockdep_assert_held(&ci->lock); lockdep_assert_held(&this_cpu_ptr(&percpu_swap_cluster)->lock); /* The cluster must be free and was just isolated from the free list. */ VM_WARN_ON_ONCE(ci->flags || !cluster_is_empty(ci)); table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); if (table) { rcu_assign_pointer(ci->table, table); return ci; } /* * Try a sleep allocation. Each isolated free cluster may cause * a sleep allocation, but there is a limited number of them, so * the potential recursive allocation is limited. */ spin_unlock(&ci->lock); if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); local_unlock(&percpu_swap_cluster.lock); table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | GFP_KERNEL); /* * Back to atomic context. We might have migrated to a new CPU with a * usable percpu cluster. But just keep using the isolated cluster to * make things easier. Migration indicates a slight change of workload * so using a new free cluster might not be a bad idea, and the worst * could happen with ignoring the percpu cluster is fragmentation, * which is acceptable since this fallback and race is rare. */ local_lock(&percpu_swap_cluster.lock); if (!(si->flags & SWP_SOLIDSTATE)) spin_lock(&si->global_cluster_lock); spin_lock(&ci->lock); /* Nothing except this helper should touch a dangling empty cluster. */ if (WARN_ON_ONCE(cluster_table_is_alloced(ci))) { if (table) swap_table_free(table); return ci; } if (!table) { move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); spin_unlock(&ci->lock); return NULL; } rcu_assign_pointer(ci->table, table); return ci; } static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags) { VM_WARN_ON(ci->flags == new_flags); BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); lockdep_assert_held(&ci->lock); spin_lock(&si->lock); if (ci->flags == CLUSTER_FLAG_NONE) list_add_tail(&ci->list, list); else list_move_tail(&ci->list, list); spin_unlock(&si->lock); ci->flags = new_flags; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { swap_cluster_free_table(ci); move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); ci->order = 0; } /* * Isolate and lock the first cluster that is not contented on a list, * clean its flag before taken off-list. Cluster flag must be in sync * with list status, so cluster updaters can always know the cluster * list status without touching si lock. * * Note it's possible that all clusters on a list are contented so * this returns NULL for an non-empty list. */ static struct swap_cluster_info *isolate_lock_cluster( struct swap_info_struct *si, struct list_head *list, int order) { struct swap_cluster_info *ci, *found = NULL; spin_lock(&si->lock); list_for_each_entry(ci, list, list) { if (!spin_trylock(&ci->lock)) continue; /* We may only isolate and clear flags of following lists */ VM_BUG_ON(!ci->flags); VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && ci->flags != CLUSTER_FLAG_FULL); list_del(&ci->list); ci->flags = CLUSTER_FLAG_NONE; found = ci; break; } spin_unlock(&si->lock); if (found && !cluster_table_is_alloced(found)) { /* Only an empty free cluster's swap table can be freed. */ VM_WARN_ON_ONCE(list != &si->free_clusters); VM_WARN_ON_ONCE(!cluster_is_empty(found)); return swap_cluster_alloc_table(si, found); } return found; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. Discard cluster is a bit special as * they don't participate in allocation or reclaim, so clusters marked as * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. */ static bool swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; bool ret = false; unsigned int idx; spin_lock(&si->lock); while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); /* * Delete the cluster from list to prepare for discard, but keep * the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be * pointing to it, or ran into by relocate_cluster. */ list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&ci->lock); /* * Discard is done, clear its flags as it's off-list, then * return the cluster to allocation list. */ ci->flags = CLUSTER_FLAG_NONE; __free_cluster(si, ci); spin_unlock(&ci->lock); ret = true; spin_lock(&si->lock); } spin_unlock(&si->lock); return ret; } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); swap_do_scheduled_discard(si); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } /* * Must be called after freeing if ci->count == 0, moves the cluster to free * or discard list. */ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); lockdep_assert_held(&ci->lock); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * Must be called after freeing if ci->count != 0, moves the cluster to * nonfull list. */ static void partial_free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); lockdep_assert_held(&ci->lock); if (ci->flags != CLUSTER_FLAG_NONFULL) move_cluster(si, ci, &si->nonfull_clusters[ci->order], CLUSTER_FLAG_NONFULL); } /* * Must be called after allocation, moves the cluster to full or frag list. * Note: allocation doesn't acquire si lock, and may drop the ci lock for * reclaim, so the cluster could be any where when called. */ static void relocate_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); /* Discard cluster must remain off-list or on discard list */ if (cluster_is_discard(ci)) return; if (!ci->count) { if (ci->flags != CLUSTER_FLAG_FREE) free_cluster(si, ci); } else if (ci->count != SWAPFILE_CLUSTER) { if (ci->flags != CLUSTER_FLAG_FRAG) move_cluster(si, ci, &si->frag_clusters[ci->order], CLUSTER_FLAG_FRAG); } else { if (ci->flags != CLUSTER_FLAG_FULL) move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL); } } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static int inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_table *table; struct swap_cluster_info *ci; ci = cluster_info + idx; if (!ci->table) { table = swap_table_alloc(GFP_KERNEL); if (!table) return -ENOMEM; rcu_assign_pointer(ci->table, table); } ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); return 0; } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset = start; int nr_reclaim; spin_unlock(&ci->lock); do { switch (READ_ONCE(map[offset])) { case 0: offset++; break; case SWAP_HAS_CACHE: nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); if (nr_reclaim > 0) offset += nr_reclaim; else goto out; break; default: goto out; } } while (offset < end); out: spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages, bool *need_reclaim) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; if (cluster_is_empty(ci)) return true; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; *need_reclaim = true; continue; default: return false; } } return true; } /* * Currently, the swap table is not used for count tracking, just * do a sanity check here to ensure nothing leaked, so the swap * table should be empty upon freeing. */ static void swap_cluster_assert_table_empty(struct swap_cluster_info *ci, unsigned int start, unsigned int nr) { unsigned int ci_off = start % SWAPFILE_CLUSTER; unsigned int ci_end = ci_off + nr; unsigned long swp_tb; if (IS_ENABLED(CONFIG_DEBUG_VM)) { do { swp_tb = __swap_table_get(ci, ci_off); VM_WARN_ON_ONCE(!swp_tb_is_null(swp_tb)); } while (++ci_off < ci_end); } } static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; lockdep_assert_held(&ci->lock); if (!(si->flags & SWP_WRITEOK)) return false; /* * The first allocation in a cluster makes the * cluster exclusive to this order */ if (cluster_is_empty(ci)) ci->order = order; memset(si->swap_map + start, usage, nr_pages); swap_cluster_assert_table_empty(ci, start, nr_pages); swap_range_alloc(si, nr_pages); ci->count += nr_pages; return true; } /* Try use a new cluster for current CPU and allocate from it. */ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long offset, unsigned int order, unsigned char usage) { unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; bool need_reclaim, ret; lockdep_assert_held(&ci->lock); if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) goto out; for (end -= nr_pages; offset <= end; offset += nr_pages) { need_reclaim = false; if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) continue; if (need_reclaim) { ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); /* * Reclaim drops ci->lock and cluster could be used * by another order. Not checking flag as off-list * cluster has no flag set, and change of list * won't cause fragmentation. */ if (!cluster_is_usable(ci, order)) goto out; if (cluster_is_empty(ci)) offset = start; /* Reclaim failed but cluster is usable, try next */ if (!ret) continue; } if (!cluster_alloc_range(si, ci, offset, usage, order)) break; found = offset; offset += nr_pages; if (ci->count < SWAPFILE_CLUSTER && offset <= end) next = offset; break; } out: relocate_cluster(si, ci); swap_cluster_unlock(ci); if (si->flags & SWP_SOLIDSTATE) { this_cpu_write(percpu_swap_cluster.offset[order], next); this_cpu_write(percpu_swap_cluster.si[order], si); } else { si->global_cluster->next[order] = next; } return found; } static unsigned int alloc_swap_scan_list(struct swap_info_struct *si, struct list_head *list, unsigned int order, unsigned char usage, bool scan_all) { unsigned int found = SWAP_ENTRY_INVALID; do { struct swap_cluster_info *ci = isolate_lock_cluster(si, list, order); unsigned long offset; if (!ci) break; offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, usage); if (found) break; } while (scan_all); return found; } static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim; if (force) to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; while ((ci = isolate_lock_cluster(si, &si->full_clusters, 0))) { offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { spin_unlock(&ci->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&ci->lock); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } /* in case no swap cache is reclaimed */ if (ci->flags == CLUSTER_FLAG_NONE) relocate_cluster(si, ci); swap_cluster_unlock(ci); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); swap_reclaim_full_clusters(si, true); } /* * Try to allocate swap entries with specified order and try set a new * cluster for current CPU too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct swap_cluster_info *ci; unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; /* * Swapfile is not block device so unable * to allocate large entries. */ if (order && !(si->flags & SWP_BLKDEV)) return 0; if (!(si->flags & SWP_SOLIDSTATE)) { /* Serialize HDD SWAP allocation for each device. */ spin_lock(&si->global_cluster_lock); offset = si->global_cluster->next[order]; if (offset == SWAP_ENTRY_INVALID) goto new_cluster; ci = swap_cluster_lock(si, offset); /* Cluster could have been used by another order */ if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, usage); } else { swap_cluster_unlock(ci); } if (found) goto done; } new_cluster: /* * If the device need discard, prefer new cluster over nonfull * to spread out the writes. */ if (si->flags & SWP_PAGE_DISCARD) { found = alloc_swap_scan_list(si, &si->free_clusters, order, usage, false); if (found) goto done; } if (order < PMD_ORDER) { found = alloc_swap_scan_list(si, &si->nonfull_clusters[order], order, usage, true); if (found) goto done; } if (!(si->flags & SWP_PAGE_DISCARD)) { found = alloc_swap_scan_list(si, &si->free_clusters, order, usage, false); if (found) goto done; } /* Try reclaim full clusters if free and nonfull lists are drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { /* * Scan only one fragment cluster is good enough. Order 0 * allocation will surely success, and large allocation * failure is not critical. Scanning one cluster still * keeps the list rotated and reclaimed (for HAS_CACHE). */ found = alloc_swap_scan_list(si, &si->frag_clusters[order], order, usage, false); if (found) goto done; } /* * We don't have free cluster but have some clusters in discarding, * do discard now and reclaim them. */ if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) goto new_cluster; if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ found = alloc_swap_scan_list(si, &si->frag_clusters[o], 0, usage, true); if (found) goto done; found = alloc_swap_scan_list(si, &si->nonfull_clusters[o], 0, usage, true); if (found) goto done; } done: if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); return found; } /* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { int nid; unsigned long pages; spin_lock(&swap_avail_lock); if (swapoff) { /* * Forcefully remove it. Clear the SWP_WRITEOK flags for * swapoff here so it's synchronized by both si->lock and * swap_avail_lock, to ensure the result can be seen by * add_to_avail_list. */ lockdep_assert_held(&si->lock); si->flags &= ~SWP_WRITEOK; atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); } else { /* * If not called by swapoff, take it off-list only if it's * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly * si->inuse_pages == pages), any concurrent slot freeing, * or device already removed from plist by someone else * will make this return false. */ pages = si->pages; if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ static void add_to_avail_list(struct swap_info_struct *si, bool swapon) { int nid; long val; unsigned long pages; spin_lock(&swap_avail_lock); /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ if (swapon) { lockdep_assert_held(&si->lock); si->flags |= SWP_WRITEOK; } else { if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) goto skip; } if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) goto skip; val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); /* * When device is full and device is on the plist, only one updater will * see (inuse_pages == si->pages) and will call del_from_avail_list. If * that updater happen to be here, just skip adding. */ pages = si->pages; if (val == pages) { /* Just like the cmpxchg in del_from_avail_list */ if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock * within each cluster, so the total contribution to the global counter should * always be positive and cannot exceed the total number of usable slots. */ static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, * remove it from the plist. */ if (unlikely(val == si->pages)) { del_from_avail_list(si, false); return true; } return false; } static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, * add it to the plist. */ if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) add_to_avail_list(si, false); } static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries) { if (swap_usage_add(si, nr_entries)) { if (vm_swap_full()) schedule_work(&si->reclaim_work); } atomic_long_sub(nr_entries, &nr_swap_pages); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) { clear_bit(offset + i, si->zeromap); zswap_invalidate(swp_entry(si->type, offset + i)); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } __swap_cache_clear_shadow(swp_entry(si->type, begin), nr_entries); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); swap_usage_sub(si, nr_entries); } static bool get_swap_device_info(struct swap_info_struct *si) { if (!percpu_ref_tryget_live(&si->users)) return false; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is * up to dated. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(), and smp_wmb() in swapoff. */ smp_rmb(); return true; } /* * Fast path try to get swap entries with specified order from current * CPU's swap entry pool (a cluster). */ static bool swap_alloc_fast(swp_entry_t *entry, int order) { struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned int offset, found = SWAP_ENTRY_INVALID; /* * Once allocated, swap_info_struct will never be completely freed, * so checking it's liveness by get_swap_device_info is enough. */ si = this_cpu_read(percpu_swap_cluster.si[order]); offset = this_cpu_read(percpu_swap_cluster.offset[order]); if (!si || !offset || !get_swap_device_info(si)) return false; ci = swap_cluster_lock(si, offset); if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, SWAP_HAS_CACHE); if (found) *entry = swp_entry(si->type, found); } else { swap_cluster_unlock(ci); } put_swap_device(si); return !!found; } /* Rotate the device and switch to a new cluster */ static bool swap_alloc_slow(swp_entry_t *entry, int order) { int node; unsigned long offset; struct swap_info_struct *si, *next; node = numa_node_id(); spin_lock(&swap_avail_lock); start_over: plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* Rotate the device and switch to a new cluster */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); if (get_swap_device_info(si)) { offset = cluster_alloc_swap_entry(si, order, SWAP_HAS_CACHE); put_swap_device(si); if (offset) { *entry = swp_entry(si->type, offset); return true; } if (order) return false; } spin_lock(&swap_avail_lock); /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); return false; } /** * folio_alloc_swap - allocate swap space for a folio * @folio: folio we want to move to swap * @gfp: gfp mask for shadow nodes * * Allocate swap space for the folio and add the folio to the * swap cache. * * Context: Caller needs to hold the folio lock. * Return: Whether the folio was added to the swap cache. */ int folio_alloc_swap(struct folio *folio, gfp_t gfp) { unsigned int order = folio_order(folio); unsigned int size = 1 << order; swp_entry_t entry = {}; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); if (order) { /* * Reject large allocation when THP_SWAP is disabled, * the caller should split the folio and try again. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) return -EAGAIN; /* * Allocation size should never exceed cluster size * (HPAGE_PMD_SIZE). */ if (size > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return -EINVAL; } } local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(&entry, order)) swap_alloc_slow(&entry, order); local_unlock(&percpu_swap_cluster.lock); /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ if (mem_cgroup_try_charge_swap(folio, entry)) goto out_free; if (!entry.val) return -ENOMEM; swap_cache_add_folio(folio, entry, NULL); return 0; out_free: put_swap_folio(folio, entry); return -ENOMEM; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swap_entry_to_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static unsigned char swap_entry_put_locked(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned char usage) { unsigned long offset = swp_offset(entry); unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else swap_entries_free(si, ci, entry, 1); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swap_entry_to_info(entry); if (!si) goto bad_nofile; if (!get_swap_device_info(si)) goto out; offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static void swap_entries_put_cache(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; ci = swap_cluster_lock(si, offset); if (swap_only_has_cache(si, offset, nr)) { swap_entries_free(si, ci, entry, nr); } else { for (int i = 0; i < nr; i++, entry.val++) swap_entry_put_locked(si, ci, entry, SWAP_HAS_CACHE); } swap_cluster_unlock(ci); } static bool swap_entries_put_map(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1) goto fallback; count = swap_count(data_race(si->swap_map[offset])); if (count != 1 && count != SWAP_MAP_SHMEM) goto fallback; ci = swap_cluster_lock(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { goto locked_fallback; } if (!has_cache) swap_entries_free(si, ci, entry, nr); else for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); swap_cluster_unlock(ci); return has_cache; fallback: ci = swap_cluster_lock(si, offset); locked_fallback: for (i = 0; i < nr; i++, entry.val++) { count = swap_entry_put_locked(si, ci, entry, 1); if (count == SWAP_HAS_CACHE) has_cache = true; } swap_cluster_unlock(ci); return has_cache; } /* * Only functions with "_nr" suffix are able to free entries spanning * cross multi clusters, so ensure the range is within a single cluster * when freeing entries with functions without "_nr" suffix. */ static bool swap_entries_put_map_nr(struct swap_info_struct *si, swp_entry_t entry, int nr) { int cluster_nr, cluster_rest; unsigned long offset = swp_offset(entry); bool has_cache = false; cluster_rest = SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER; while (nr) { cluster_nr = min(nr, cluster_rest); has_cache |= swap_entries_put_map(si, entry, cluster_nr); cluster_rest = SWAPFILE_CLUSTER; nr -= cluster_nr; entry.val += cluster_nr; } return has_cache; } /* * Check if it's the last ref of swap entry in the freeing path. * Qualified vlaue includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM. */ static inline bool __maybe_unused swap_is_last_ref(unsigned char count) { return (count == SWAP_HAS_CACHE) || (count == 1) || (count == SWAP_MAP_SHMEM); } /* * Drop the last ref of swap entries, caller have to ensure all entries * belong to the same cgroup and cluster. */ static void swap_entries_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; /* It should never free entries across different clusters */ VM_BUG_ON(ci != __swap_offset_to_cluster(si, offset + nr_pages - 1)); VM_BUG_ON(cluster_is_empty(ci)); VM_BUG_ON(ci->count < nr_pages); ci->count -= nr_pages; do { VM_BUG_ON(!swap_is_last_ref(*map)); *map = 0; } while (++map < map_end); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); swap_cluster_assert_table_empty(ci, offset, nr_pages); if (!ci->count) free_cluster(si, ci); else partial_free_cluster(si, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); swap_entries_put_map(sis, swp_entry(sis->type, offset), nr); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; swap_entries_put_cache(si, entry, size); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = __swap_entry_to_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = swap_cluster_lock(si, offset); count = swap_count(si->swap_map[offset]); swap_cluster_unlock(ci); return !!count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = swap_cluster_lock(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: swap_cluster_unlock(ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = swap_cluster_lock(si, offset); if (nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: swap_cluster_unlock(ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_entry_swapped(si, entry); return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; swap_cache_del_folio(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = swap_entries_put_map_nr(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_info(type); unsigned long offset; swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ if (get_swap_device_info(si)) { if (si->flags & SWP_WRITEOK) { /* * Grab the local lock to be complaint * with swap table allocation. */ local_lock(&percpu_swap_cluster.lock); offset = cluster_alloc_swap_entry(si, 0, 1); local_unlock(&percpu_swap_cluster.lock); if (offset) { entry = swp_entry(si->type, offset); atomic_long_dec(&nr_swap_pages); } } put_swap_device(si); } fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; /* * If the folio is removed from swap cache by others, continue to * unuse other PTEs. try_to_unuse may try again if we missed this one. */ if (!folio_matches_swap_entry(folio, entry)) return 0; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); if (check_stable_address_space(mm)) goto unlock; for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } unlock: mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!swap_usage_in_pages(si)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (swap_usage_in_pages(si) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (swap_usage_in_pages(si) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = swap_cache_get_folio(entry); if (!folio) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writeout() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (swap_usage_in_pages(si)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* Add back to available list */ add_to_avail_list(si, true); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } /* * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range * see the updated flags, so there will be no more allocations. */ static void wait_for_allocation(struct swap_info_struct *si) { unsigned long offset; unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); struct swap_cluster_info *ci; BUG_ON(si->flags & SWP_WRITEOK); for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { ci = swap_cluster_lock(si, offset); swap_cluster_unlock(ci); } } static void free_cluster_info(struct swap_cluster_info *cluster_info, unsigned long maxpages) { struct swap_cluster_info *ci; int i, nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); if (!cluster_info) return; for (i = 0; i < nr_clusters; i++) { ci = cluster_info + i; /* Cluster with bad marks count will have a remaining table */ spin_lock(&ci->lock); if (rcu_dereference_protected(ci->table, true)) { ci->count = 0; swap_cluster_free_table(ci); } spin_unlock(&ci->lock); } kvfree(cluster_info); } /* * Called after swap device's reference count is dead, so * neither scan nor allocation will use it. */ static void flush_percpu_swap_cluster(struct swap_info_struct *si) { int cpu, i; struct swap_info_struct **pcp_si; for_each_possible_cpu(cpu) { pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu); /* * Invalidate the percpu swap cluster cache, si->users * is dead, so no new user will point to it, just flush * any existing user. */ for (i = 0; i < SWAP_NR_ORDERS; i++) cmpxchg(&pcp_si[i], si, NULL); } } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; unsigned int maxpages; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p, true); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; spin_unlock(&p->lock); spin_unlock(&swap_lock); wait_for_allocation(p); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); goto out_dput; } /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); flush_percpu_swap_cluster(p); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); swap_file = p->swap_file; p->swap_file = NULL; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; maxpages = p->max; cluster_info = p->cluster_info; p->max = 0; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); kfree(p->global_cluster); p->global_cluster = NULL; vfree(swap_map); kvfree(zeromap); free_cluster_info(cluster_info, maxpages); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(swap_usage_in_pages(si)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } static int setup_swap_map(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages) { unsigned long i; swap_map[0] = SWAP_MAP_BAD; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; si->pages--; } } if (!si->pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return 0; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); struct swap_cluster_info *cluster_info; int err = -ENOMEM; unsigned long i; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); if (!(si->flags & SWP_SOLIDSTATE)) { si->global_cluster = kmalloc(sizeof(*si->global_cluster), GFP_KERNEL); if (!si->global_cluster) goto err_free; for (i = 0; i < SWAP_NR_ORDERS; i++) si->global_cluster->next[i] = SWAP_ENTRY_INVALID; spin_lock_init(&si->global_cluster_lock); } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map(): header page, bad pages, * and the EOF part of the last cluster. */ err = inc_cluster_info_page(si, cluster_info, 0); if (err) goto err; for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr >= maxpages) continue; err = inc_cluster_info_page(si, cluster_info, page_nr); if (err) goto err; } for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) { err = inc_cluster_info_page(si, cluster_info, i); if (err) goto err; } INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); } for (i = 0; i < nr_clusters; i++) { struct swap_cluster_info *ci = &cluster_info[i]; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); } else { ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: free_cluster_info(cluster_info, maxpages); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * The swap subsystem needs a major overhaul to support this. * It doesn't work yet so just disable it for now. */ if (mapping_min_folio_order(mapping) > 0) { error = -EINVAL; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } si->max = maxpages; si->pages = maxpages - 1; nr_extents = setup_swap_extents(si, &span); if (nr_extents < 0) { error = nr_extents; goto bad_swap_unlock_inode; } if (si->pages != si->max - 1) { pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max); error = -EINVAL; goto bad_swap_unlock_inode; } maxpages = si->max; /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = setup_swap_map(si, swap_header, swap_map, maxpages); if (error) goto bad_swap_unlock_inode; /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = zswap_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = swap_flags & SWAP_FLAG_PRIO_MASK; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: kfree(si->global_cluster); si->global_cluster = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); if (cluster_info) free_cluster_info(cluster_info, maxpages); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swap_entry_to_info(entry); if (WARN_ON_ONCE(!si)) { pr_err("%s%08lx\n", Bad_file, entry.val); return -EINVAL; } offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = swap_cluster_lock(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: swap_cluster_unlock(ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } /* * Caller should ensure entries belong to the same folio so * the entries won't span cross cluster boundary. */ void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { swap_entries_put_cache(si, entry, nr); } /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } offset = swp_offset(entry); ci = swap_cluster_lock(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: swap_cluster_unlock(ci); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or caller of swap_entry_put_locked() * holds cluster lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); /* * Once a cluster is freed, it's swap table content is read * only, and all swap cache readers (swap_cache_*) verifies * the content before use. So it's safe to use RCU slab here. */ if (!SWP_TABLE_USE_PAGE) swap_table_cachep = kmem_cache_create("swap_table", sizeof(struct swap_table), 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 1 136 3658 3669 2101 1657 1604 1211 405 147 1 99 3670 3673 3678 3654 99 10 10 1189 1186 1178 1696 1505 2285 1688 1696 1688 1503 1505 1503 268 1281 378 1505 1369 3787 3649 3787 3642 615 424 3674 3787 1 3653 3649 1 266 267 267 267 1 3647 3642 268 3645 3649 3139 2639 3643 255 2627 13 1348 1341 1985 1989 27 27 27 24 20 27 1603 1474 275 276 275 1604 1381 1382 1382 1377 13 1377 1299 179 1383 1381 180 1298 1377 1377 13 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #include "timer_migration.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT 3 #define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) #define LVL_CLK_MASK (LVL_CLK_DIV - 1) #define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) #define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) /* * The time start value for each level to select the bucket at enqueue * time. We start from the last possible delta of the previous level * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()). */ #define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) /* Size of each clock level */ #define LVL_BITS 6 #define LVL_SIZE (1UL << LVL_BITS) #define LVL_MASK (LVL_SIZE - 1) #define LVL_OFFS(n) ((n) * LVL_SIZE) /* Level depth */ #if HZ > 100 # define LVL_DEPTH 9 # else # define LVL_DEPTH 8 #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) #define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON /* * If multiple bases need to be locked, use the base ordering for lock * nesting, i.e. lowest number first. */ # define NR_BASES 3 # define BASE_LOCAL 0 # define BASE_GLOBAL 1 # define BASE_DEF 2 #else # define NR_BASES 1 # define BASE_LOCAL 0 # define BASE_GLOBAL 0 # define BASE_DEF 0 #endif /** * struct timer_base - Per CPU timer base (number of base depends on config) * @lock: Lock protecting the timer_base * @running_timer: When expiring timers, the lock is dropped. To make * sure not to race against deleting/modifying a * currently running timer, the pointer is set to the * timer, which expires at the moment. If no timer is * running, the pointer is NULL. * @expiry_lock: PREEMPT_RT only: Lock is taken in softirq around * timer expiry callback execution and when trying to * delete a running timer and it wasn't successful in * the first glance. It prevents priority inversion * when callback was preempted on a remote CPU and a * caller tries to delete the running timer. It also * prevents a life lock, when the task which tries to * delete a timer preempted the softirq thread which * is running the timer callback function. * @timer_waiters: PREEMPT_RT only: Tells, if there is a waiter * waiting for the end of the timer callback function * execution. * @clk: clock of the timer base; is updated before enqueue * of a timer; during expiry, it is 1 offset ahead of * jiffies to avoid endless requeuing to current * jiffies * @next_expiry: expiry value of the first timer; it is updated when * finding the next timer and during enqueue; the * value is not valid, when next_expiry_recalc is set * @cpu: Number of CPU the timer base belongs to * @next_expiry_recalc: States, whether a recalculation of next_expiry is * required. Value is set true, when a timer was * deleted. * @is_idle: Is set, when timer_base is idle. It is triggered by NOHZ * code. This state is only used in standard * base. Deferrable timers, which are enqueued remotely * never wake up an idle CPU. So no matter of supporting it * for this base. * @timers_pending: Is set, when a timer is pending in the base. It is only * reliable when next_expiry_recalc is not set. * @pending_map: bitmap of the timer wheel; each bit reflects a * bucket of the wheel. When a bit is set, at least a * single timer is enqueued in the related bucket. * @vectors: Array of lists; Each array member reflects a bucket * of the timer wheel. The list contains all timers * which are enqueued into a specific bucket. */ struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; #ifdef CONFIG_PREEMPT_RT spinlock_t expiry_lock; atomic_t timer_waiters; #endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; bool next_expiry_recalc; bool is_idle; bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP static unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { if (sysctl_timer_migration && tick_nohz_active) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); } #ifdef CONFIG_SYSCTL static int timer_migration_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&timer_keys_mutex); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(); mutex_unlock(&timer_keys_mutex); return ret; } static const struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = timer_migration_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static int __init timer_sysctl_init(void) { register_sysctl("kernel", timer_sysctl); return 0; } device_initcall(timer_sysctl_init); #endif /* CONFIG_SYSCTL */ #else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { mutex_lock(&timer_keys_mutex); timers_update_migration(); static_branch_enable(&timers_nohz_active); mutex_unlock(&timer_keys_mutex); } void timers_update_nohz(void) { schedule_work(&timer_update_work); } static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffy is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); static inline unsigned int timer_get_idx(struct timer_list *timer) { return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | idx << TIMER_ARRAYSHIFT; } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned long expires, unsigned lvl, unsigned long *bucket_expiry) { /* * The timer wheel has to guarantee that a timer does not fire * early. Early expiry can happen due to: * - Timer is armed at the edge of a tick * - Truncation of the expiry time in the outer wheel levels * * Round up with level granularity to prevent this. */ expires = (expires >> LVL_SHIFT(lvl)) + 1; *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } static int calc_wheel_index(unsigned long expires, unsigned long clk, unsigned long *bucket_expiry) { unsigned long delta = expires - clk; unsigned int idx; if (delta < LVL_START(1)) { idx = calc_index(expires, 0, bucket_expiry); } else if (delta < LVL_START(2)) { idx = calc_index(expires, 1, bucket_expiry); } else if (delta < LVL_START(3)) { idx = calc_index(expires, 2, bucket_expiry); } else if (delta < LVL_START(4)) { idx = calc_index(expires, 3, bucket_expiry); } else if (delta < LVL_START(5)) { idx = calc_index(expires, 4, bucket_expiry); } else if (delta < LVL_START(6)) { idx = calc_index(expires, 5, bucket_expiry); } else if (delta < LVL_START(7)) { idx = calc_index(expires, 6, bucket_expiry); } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { idx = calc_index(expires, 7, bucket_expiry); } else if ((long) delta < 0) { idx = clk & LVL_MASK; *bucket_expiry = clk; } else { /* * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ if (delta >= WHEEL_TIMEOUT_CUTOFF) expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry); } return idx; } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { /* * Deferrable timers do not prevent the CPU from entering dynticks and * are not taken into account on the idle/nohz_full path. An IPI when a * new deferrable timer is enqueued will wake up the remote CPU but * nothing will be done with the deferrable timer base. Therefore skip * the remote IPI for deferrable timers completely. */ if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE) return; /* * We might have to IPI the remote CPU if the base is idle and the * timer is pinned. If it is a non pinned timer, it is only queued * on the remote CPU, when timer was running during queueing. Then * everything is handled by remote CPU anyway. If the other CPU is * on the way to idle then it can't set base->is_idle as we hold * the base lock: */ if (base->is_idle) { WARN_ON_ONCE(!(timer->flags & TIMER_PINNED || tick_nohz_full_cpu(base->cpu))); wake_up_nohz_cpu(base->cpu); } } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap, store the index in the timer flags then wake up * the target CPU if needed. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx, unsigned long bucket_expiry) { hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); trace_timer_start(timer, bucket_expiry); /* * Check whether this is the new first expiring timer. The * effective expiry time of the timer is required here * (bucket_expiry) instead of timer->expires. */ if (time_before(bucket_expiry, base->next_expiry)) { /* * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ WRITE_ONCE(base->next_expiry, bucket_expiry); base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned long bucket_expiry; unsigned int idx; idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry); enqueue_timer(base, timer, idx, bucket_expiry); } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr timer_debug_descr; struct timer_hint { void (*function)(struct timer_list *t); long offset; }; #define TIMER_HINT(fn, container, timr, hintfn) \ { \ .function = fn, \ .offset = offsetof(container, hintfn) - \ offsetof(container, timr) \ } static const struct timer_hint timer_hints[] = { TIMER_HINT(delayed_work_timer_fn, struct delayed_work, timer, work.func), TIMER_HINT(kthread_delayed_work_timer_fn, struct kthread_delayed_work, timer, work.func), }; static void *timer_debug_hint(void *addr) { struct timer_list *timer = addr; int i; for (i = 0; i < ARRAY_SIZE(timer_hints); i++) { if (timer_hints[i].function == timer->function) { void (**fn)(void) = addr + timer_hints[i].offset; return *fn; } } return timer->function; } static bool timer_is_static_object(void *addr) { struct timer_list *timer = addr; return (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC); } /* * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: timer_delete_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { WARN_ON(1); } /* * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: timer_delete_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; default: return false; } } static const struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .is_static_object = timer_is_static_object, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void timer_init_key_on_stack(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL_GPL(timer_init_key_on_stack); void timer_destroy_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(timer_destroy_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->function = func; if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS)) flags &= TIMER_INIT_FLAGS; timer->flags = flags | raw_smp_processor_id(); lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * timer_init_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * timer_init_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void timer_init_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL(timer_init_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { unsigned idx = timer_get_idx(timer); if (!timer_pending(timer)) return 0; if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) { __clear_bit(idx, base->pending_map); base->next_expiry_recalc = true; } detach_timer(timer, clear_pending); return 1; } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) index = BASE_DEF; return per_cpu_ptr(&timer_bases[index], cpu); } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) index = BASE_DEF; return this_cpu_ptr(&timer_bases[index]); } static inline struct timer_base *get_timer_base(u32 tflags) { return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } static inline void __forward_timer_base(struct timer_base *base, unsigned long basej) { /* * Check whether we can forward the base. We can only do that when * @basej is past base->clk otherwise we might rewind base->clk. */ if (time_before_eq(basej, base->clk)) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ if (time_after(base->next_expiry, basej)) { base->clk = basej; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } } static inline void forward_timer_base(struct timer_base *base) { __forward_timer_base(base, READ_ONCE(jiffies)); } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { struct timer_base *base; u32 tf; /* * We need to use READ_ONCE() here, otherwise the compiler * might re-read @tf between the check for TIMER_MIGRATING * and spin_lock(). */ tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 #define MOD_TIMER_NOTPENDING 0x04 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { unsigned long clk = 0, flags, bucket_expiry; struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; int ret = 0; debug_assert_init(timer); /* * This is a common optimization triggered by the networking code - if * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new * timer with this expiry. */ long diff = timer->expires - expires; if (!diff) return 1; if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* * We lock timer base and calculate the bucket index right * here. If the timer ends up in the same bucket, then we * just update the expiry time and avoid the whole * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated * while holding base lock to prevent a race against the * shutdown code. */ if (!timer->function) goto out_unlock; forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && time_before_eq(timer->expires, expires)) { ret = 1; goto out_unlock; } clk = base->clk; idx = calc_wheel_index(expires, clk, &bucket_expiry); /* * Retrieve and compare the array index of the pending * timer. If it matches set the expiry to the new value so a * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { if (!(options & MOD_TIMER_REDUCE)) timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires; ret = 1; goto out_unlock; } } else { base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated * while holding base lock to prevent a race against the * shutdown code. */ if (!timer->function) goto out_unlock; forward_timer_base(base); } ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; new_base = get_timer_this_cpu_base(timer->flags); if (base != new_base) { /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); forward_timer_base(base); } } debug_timer_activate(timer); timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance * between calculating 'idx' and possibly switching the base, only * enqueue_timer() is required. Otherwise we need to (re)calculate * the wheel index via internal_add_timer(). */ if (idx != UINT_MAX && clk == base->clk) enqueue_timer(base, timer, idx, bucket_expiry); else internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - Modify a pending timer's timeout * @timer: The pending timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), but * will not activate inactive timers. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and not modified or was in * shutdown state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - Modify a timer's timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * timer_delete(timer); timer->expires = expires; add_timer(timer); * * mod_timer() is more efficient than the above open coded sequence. In * case that the timer is inactive, the timer_delete() part is a NOP. The * timer is in any case activated with the new expiry time @expires. * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * If @timer->function == NULL then the start operation is silently * discarded. In this case the return value is 0 and meaningless. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires did * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, 0); } EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only * modify an enqueued timer if that would reduce the expiration time. If * @timer is not enqueued it starts the timer. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires * did not change the effective expiry time such that the * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_REDUCE); } EXPORT_SYMBOL(timer_reduce); /** * add_timer - Start a timer * @timer: The timer to be started * * Start @timer to expire at @timer->expires in the future. @timer->expires * is the absolute expiry time measured in 'jiffies'. When the timer expires * timer->function(timer) will be invoked from soft interrupt context. * * The @timer->expires and @timer->function fields must be set prior * to calling this function. * * If @timer->function == NULL then the start operation is silently * discarded. * * If @timer->expires is already in the past @timer will be queued to * expire at the next timer tick. * * This can only operate on an inactive timer. Attempts to invoke this on * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); /** * add_timer_local() - Start a timer on the local CPU * @timer: The timer to be started * * Same as add_timer() except that the timer flag TIMER_PINNED is set. * * See add_timer() for further details. */ void add_timer_local(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; timer->flags |= TIMER_PINNED; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer_local); /** * add_timer_global() - Start a timer without TIMER_PINNED flag set * @timer: The timer to be started * * Same as add_timer() except that the timer flag TIMER_PINNED is unset. * * See add_timer() for further details. */ void add_timer_global(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; timer->flags &= ~TIMER_PINNED; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer_global); /** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * * Same as add_timer() except that it starts the timer on the given CPU and * the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in * the next round, add_timer_global() should be used instead as it unsets * the TIMER_PINNED flag. * * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { struct timer_base *new_base, *base; unsigned long flags; debug_assert_init(timer); if (WARN_ON_ONCE(timer_pending(timer))) return; /* Make sure timer flags have TIMER_PINNED flag set */ timer->flags |= TIMER_PINNED; new_base = get_timer_cpu_base(timer->flags, cpu); /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated while * holding base lock to prevent a race against the shutdown code. */ if (!timer->function) goto out_unlock; if (base != new_base) { timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } forward_timer_base(base); debug_timer_activate(timer); internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** * __timer_delete - Internal function: Deactivate a timer * @timer: The timer to be deactivated * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the time. In that * case any attempt to rearm @timer after this function returns will be * silently ignored. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; int ret = 0; debug_assert_init(timer); /* * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock * acquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * * If timer->function is currently executed, then this makes sure * that the callback cannot requeue the timer. */ if (timer_pending(timer) || shutdown) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; } /** * timer_delete - Deactivate a timer * @timer: The timer to be deactivated * * The function only deactivates a pending timer, but contrary to * timer_delete_sync() it does not take into account whether the timer's * callback function is concurrently executed on a different CPU or not. * It neither prevents rearming of the timer. If @timer can be rearmed * concurrently then the return value of this function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete(struct timer_list *timer) { return __timer_delete(timer, false); } EXPORT_SYMBOL(timer_delete); /** * timer_shutdown - Deactivate a timer and prevent rearming * @timer: The timer to be deactivated * * The function does not wait for an eventually running timer callback on a * different CPU but it prevents rearming of the timer. Any attempt to arm * @timer after this function returns will be silently ignored. * * This function is useful for teardown code and should only be used when * timer_shutdown_sync() cannot be invoked due to locking or context constraints. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown(struct timer_list *timer) { return __timer_delete(timer, true); } EXPORT_SYMBOL_GPL(timer_shutdown); /** * __try_to_del_timer_sync - Internal function: Try to deactivate a timer * @timer: Timer to deactivate * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the timer. Any * attempt to rearm @timer after this function returns will be silently * ignored. * * This function cannot guarantee that the timer cannot be rearmed * right after dropping the base lock if @shutdown is false. That * needs to be prevented by the calling code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; int ret = -1; debug_assert_init(timer); base = lock_timer_base(timer, &flags); if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * timer_delete_sync_try - Try to deactivate a timer * @timer: Timer to deactivate * * This function tries to deactivate a timer. On success the timer is not * queued and the timer callback function is not running on any CPU. * * This function does not guarantee that the timer cannot be rearmed right * after dropping the base lock. That needs to be prevented by the calling * code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ int timer_delete_sync_try(struct timer_list *timer) { return __try_to_del_timer_sync(timer, false); } EXPORT_SYMBOL(timer_delete_sync_try); #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { spin_lock_init(&base->expiry_lock); } static inline void timer_base_lock_expiry(struct timer_base *base) { spin_lock(&base->expiry_lock); } static inline void timer_base_unlock_expiry(struct timer_base *base) { spin_unlock(&base->expiry_lock); } /* * The counterpart to del_timer_wait_running(). * * If there is a waiter for base->expiry_lock, then it was waiting for the * timer callback to finish. Drop expiry_lock and reacquire it. That allows * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) __releases(&base->lock) __releases(&base->expiry_lock) __acquires(&base->expiry_lock) __acquires(&base->lock) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); raw_spin_lock_irq(&base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion, if the softirq thread on a remote CPU * got preempted, and it prevents a life lock when the task which tries to * delete a timer preempted the softirq thread running the timer callback * function. */ static void del_timer_wait_running(struct timer_list *timer) { u32 tf; tf = READ_ONCE(timer->flags); if (!(tf & (TIMER_MIGRATING | TIMER_IRQSAFE))) { struct timer_base *base = get_timer_base(tf); /* * Mark the base as contended and grab the expiry lock, * which is held by the softirq across the timer * callback. Drop the lock immediately so the softirq can * expire the next timer. In theory the timer could already * be running again, but that's more than unlikely and just * causes another wait loop. */ atomic_inc(&base->timer_waiters); spin_lock_bh(&base->expiry_lock); atomic_dec(&base->timer_waiters); spin_unlock_bh(&base->expiry_lock); } } #else static inline void timer_base_init_expiry_lock(struct timer_base *base) { } static inline void timer_base_lock_expiry(struct timer_base *base) { } static inline void timer_base_unlock_expiry(struct timer_base *base) { } static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif /** * __timer_delete_sync - Internal function: Deactivate a timer and wait * for the handler to finish. * @timer: The timer to be deactivated * @shutdown: If true, @timer->function will be set to NULL under the * timer base lock which prevents rearming of @timer * * If @shutdown is not set the timer can be rearmed later. If the timer can * be rearmed concurrently, i.e. after dropping the base lock then the * return value is meaningless. * * If @shutdown is set then @timer->function is set to NULL under timer * base lock which prevents rearming of the timer. Any attempt to rearm * a shutdown timer is silently ignored. * * If the timer should be reused after shutdown it has to be initialized * again. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete_sync(struct timer_list *timer, bool shutdown) { int ret; #ifdef CONFIG_LOCKDEP unsigned long flags; /* * If lockdep gives a backtrace here, please reference * the synchronization rules above. */ local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it * could lead to deadlock. */ WARN_ON(in_hardirq() && !(timer->flags & TIMER_IRQSAFE)); /* * Must be able to sleep on PREEMPT_RT because of the slowpath in * del_timer_wait_running(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(timer->flags & TIMER_IRQSAFE)) lockdep_assert_preemption_enabled(); do { ret = __try_to_del_timer_sync(timer, shutdown); if (unlikely(ret < 0)) { del_timer_wait_running(timer); cpu_relax(); } } while (ret < 0); return ret; } /** * timer_delete_sync - Deactivate a timer and wait for the handler to finish. * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's callback * function. The timer's handler must not call add_timer_on(). Upon exit * the timer is not queued and the handler is not running on any CPU. * * For !irqsafe timers, the caller must not hold locks that are held in * interrupt context. Even if the lock has nothing to do with the timer in * question. Here's why:: * * CPU0 CPU1 * ---- ---- * <SOFTIRQ> * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * * Now timer_delete_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but it has * interrupted the softirq that CPU0 is waiting to finish. * * This function cannot guarantee that the timer is not rearmed again by * some concurrent or preempting code, right after it dropped the base * lock. If there is the possibility of a concurrent rearm then the return * value of the function is meaningless. * * If such a guarantee is needed, e.g. for teardown situations then use * timer_shutdown_sync() instead. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete_sync(struct timer_list *timer) { return __timer_delete_sync(timer, false); } EXPORT_SYMBOL(timer_delete_sync); /** * timer_shutdown_sync - Shutdown a timer and prevent rearming * @timer: The timer to be shutdown * * When the function returns it is guaranteed that: * - @timer is not queued * - The callback function of @timer is not running * - @timer cannot be enqueued again. Any attempt to rearm * @timer is silently ignored. * * See timer_delete_sync() for synchronization rules. * * This function is useful for final teardown of an infrastructure where * the timer is subject to a circular dependency problem. * * A common pattern for this is a timer and a workqueue where the timer can * schedule work and work can arm the timer. On shutdown the workqueue must * be destroyed and the timer must be prevented from rearming. Unless the * code has conditionals like 'if (mything->in_shutdown)' to prevent that * there is no way to get this correct with timer_delete_sync(). * * timer_shutdown_sync() is solving the problem. The correct ordering of * calls in this case is: * * timer_shutdown_sync(&mything->timer); * workqueue_destroy(&mything->workqueue); * * After this 'mything' can be safely freed. * * This obviously implies that the timer is not required to be functional * for the rest of the shutdown operation. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown_sync(struct timer_list *timer) { return __timer_delete_sync(timer, true); } EXPORT_SYMBOL_GPL(timer_shutdown_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), unsigned long baseclk) { int count = preempt_count(); #ifdef CONFIG_LOCKDEP /* * It is permissible to free the timer from inside the * function that is called from it, this we need to take into * account for lockdep too. To avoid bogus "held lock freed" * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at * timer_delete_sync() by acquiring the lock_map around the fn() * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent * chance to survive and extract information. If the * callback kept a lock held, bad luck, but not worse * than the BUG() we had. */ preempt_count_set(count); } } static void expire_timers(struct timer_base *base, struct hlist_head *head) { /* * This value is required only for tracing. base->clk was * incremented directly before expire_timers was called. But expiry * is related to the old base->clk value. */ unsigned long baseclk = base->clk - 1; while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); timer = hlist_entry(head->first, struct timer_list, entry); base->running_timer = timer; detach_timer(timer, true); fn = timer->function; if (WARN_ON_ONCE(!fn)) { /* Should never happen. Emphasis on should! */ base->running_timer = NULL; continue; } if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); } } } static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { unsigned long clk = base->clk = base->next_expiry; struct hlist_head *vec; int i, levels = 0; unsigned int idx; for (i = 0; i < LVL_DEPTH; i++) { idx = (clk & LVL_MASK) + i * LVL_SIZE; if (__test_and_clear_bit(idx, base->pending_map)) { vec = base->vectors + idx; hlist_move_list(vec, heads++); levels++; } /* Is it time to look at the next level? */ if (clk & LVL_CLK_MASK) break; /* Shift clock for the next level granularity */ clk >>= LVL_CLK_SHIFT; } return levels; } /* * Find the next pending bucket of a level. Search from level start (@offset) * + @clk upwards and if nothing there, search from start of the level * (@offset) up to @offset + clk. */ static int next_pending_bucket(struct timer_base *base, unsigned offset, unsigned clk) { unsigned pos, start = offset + clk; unsigned end = offset + LVL_SIZE; pos = find_next_bit(base->pending_map, end, start); if (pos < end) return pos - start; pos = find_next_bit(base->pending_map, start, offset); return pos < start ? pos + LVL_SIZE - start : -1; } /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. * * Store next expiry time in base->next_expiry. */ static void timer_recalc_next_expiry(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; next = base->clk + TIMER_NEXT_MAX_DELTA; clk = base->clk; for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { int pos = next_pending_bucket(base, offset, clk & LVL_MASK); unsigned long lvl_clk = clk & LVL_CLK_MASK; if (pos >= 0) { unsigned long tmp = clk + (unsigned long) pos; tmp <<= LVL_SHIFT(lvl); if (time_before(tmp, next)) next = tmp; /* * If the next expiration happens before we reach * the next level, no need to check further. */ if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK)) break; } /* * Clock for the next level. If the current level clock lower * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next * expiring jiffy. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 * * we have to look at all levels @index 0. With * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 2 * * LVL0 has the next expiring bucket @index 2. The upper * levels have the next expiring bucket @index 1. * * In case that the propagation wraps the next level the same * rules apply: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 F 2 * * So after looking at LVL0 we get: * * LVL5 LVL4 LVL3 LVL2 LVL1 * 0 0 0 1 0 * * So no propagation from LVL1 to LVL2 because that happened * with the add already, but then we need to propagate further * from LVL2 to LVL3. * * So the simple check whether the lower bits of the current * level are 0 or not is sufficient for all cases. */ adj = lvl_clk ? 1 : 0; clk >>= LVL_CLK_SHIFT; clk += adj; } WRITE_ONCE(base->next_expiry, next); base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + TIMER_NEXT_MAX_DELTA); } #ifdef CONFIG_NO_HZ_COMMON /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); /* * If high resolution timers are enabled * hrtimer_get_next_event() returns KTIME_MAX. */ if (expires <= nextevt) return expires; /* * If the next timer is already expired, return the tick base * time so the tick is fired immediately. */ if (nextevt <= basem) return basem; /* * Round up to the next jiffy. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. * * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } static unsigned long next_timer_interrupt(struct timer_base *base, unsigned long basej) { if (base->next_expiry_recalc) timer_recalc_next_expiry(base); /* * Move next_expiry for the empty base into the future to prevent an * unnecessary raise of the timer softirq when the next_expiry value * will be reached even if there is no timer pending. * * This update is also required to make timer_base::next_expiry values * easy comparable to find out which base holds the first pending timer. */ if (!base->timers_pending) WRITE_ONCE(base->next_expiry, basej + TIMER_NEXT_MAX_DELTA); return base->next_expiry; } static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem, struct timer_base *base_local, struct timer_base *base_global, struct timer_events *tevt) { unsigned long nextevt, nextevt_local, nextevt_global; bool local_first; nextevt_local = next_timer_interrupt(base_local, basej); nextevt_global = next_timer_interrupt(base_global, basej); local_first = time_before_eq(nextevt_local, nextevt_global); nextevt = local_first ? nextevt_local : nextevt_global; /* * If the @nextevt is at max. one tick away, use @nextevt and store * it in the local expiry value. The next global event is irrelevant in * this case and can be left as KTIME_MAX. */ if (time_before_eq(nextevt, basej + 1)) { /* If we missed a tick already, force 0 delta */ if (time_before(nextevt, basej)) nextevt = basej; tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * This is required for the remote check only but it doesn't * hurt, when it is done for both call sites: * * * The remote callers will only take care of the global timers * as local timers will be handled by CPU itself. When not * updating tevt->global with the already missed first global * timer, it is possible that it will be missed completely. * * * The local callers will ignore the tevt->global anyway, when * nextevt is max. one tick away. */ if (!local_first) tevt->global = tevt->local; return nextevt; } /* * Update tevt.* values: * * If the local queue expires first, then the global event can be * ignored. If the global queue is empty, nothing to do either. */ if (!local_first && base_global->timers_pending) tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC; if (base_local->timers_pending) tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC; return nextevt; } # ifdef CONFIG_SMP /** * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic * @tevt: Pointer to the storage for the expiry values * @cpu: Remote CPU * * Stores the next pending local and global timer expiry values in the * struct pointed to by @tevt. If a queue is empty the corresponding * field is set to KTIME_MAX. If local event expires before global * event, global event is set to KTIME_MAX as well. * * Caller needs to make sure timer base locks are held (use * timer_lock_remote_bases() for this purpose). */ void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, struct timer_events *tevt, unsigned int cpu) { struct timer_base *base_local, *base_global; /* Preset local / global events */ tevt->local = tevt->global = KTIME_MAX; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_held(&base_local->lock); lockdep_assert_held(&base_global->lock); fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt); } /** * timer_unlock_remote_bases - unlock timer bases of cpu * @cpu: Remote CPU * * Unlocks the remote timer bases. */ void timer_unlock_remote_bases(unsigned int cpu) __releases(timer_bases[BASE_LOCAL]->lock) __releases(timer_bases[BASE_GLOBAL]->lock) { struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); } /** * timer_lock_remote_bases - lock timer bases of cpu * @cpu: Remote CPU * * Locks the remote timer bases. */ void timer_lock_remote_bases(unsigned int cpu) __acquires(timer_bases[BASE_LOCAL]->lock) __acquires(timer_bases[BASE_GLOBAL]->lock) { struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_irqs_disabled(); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); } /** * timer_base_is_idle() - Return whether timer base is set idle * * Returns value of local timer base is_idle value. */ bool timer_base_is_idle(void) { return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle); } static void __run_timer_base(struct timer_base *base); /** * timer_expire_remote() - expire global timers of cpu * @cpu: Remote CPU * * Expire timers of global base of remote CPU. */ void timer_expire_remote(unsigned int cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); __run_timer_base(base); } static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { u64 next_tmigr; if (timer_base_idle) next_tmigr = tmigr_cpu_new_timer(tevt->global); else if (tick_stop_path) next_tmigr = tmigr_cpu_deactivate(tevt->global); else next_tmigr = tmigr_quick_check(tevt->global); /* * If the CPU is the last going idle in timer migration hierarchy, make * sure the CPU will wake up in time to handle remote timers. * next_tmigr == KTIME_MAX if other CPUs are still active. */ if (next_tmigr < tevt->local) { u64 tmp; /* If we missed a tick already, force 0 delta */ if (next_tmigr < basem) next_tmigr = basem; tmp = div_u64(next_tmigr - basem, TICK_NSEC); *nextevt = basej + (unsigned long)tmp; tevt->local = next_tmigr; } } # else static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { /* * Make sure first event is written into tevt->local to not miss a * timer on !SMP systems. */ tevt->local = min_t(u64, tevt->local, tevt->global); } # endif /* CONFIG_SMP */ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, bool *idle) { struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX }; struct timer_base *base_local, *base_global; unsigned long nextevt; bool idle_is_possible; /* * When the CPU is offline, the tick is cancelled and nothing is supposed * to try to stop it. */ if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) { if (idle) *idle = true; return tevt.local; } base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); nextevt = fetch_next_timer_interrupt(basej, basem, base_local, base_global, &tevt); /* * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. * * The proper timer migration hierarchy function depends on the callsite * and whether timer base is idle or not. @nextevt will be updated when * this CPU needs to handle the first timer migration hierarchy * event. See timer_use_tmigr() for detailed information. */ idle_is_possible = time_after(nextevt, basej + 1); if (idle_is_possible) timer_use_tmigr(basej, basem, &nextevt, idle, base_local->is_idle, &tevt); /* * We have a fresh next event. Check whether we can forward the * base. */ __forward_timer_base(base_local, basej); __forward_timer_base(base_global, basej); /* * Set base->is_idle only when caller is timer_base_try_to_set_idle() */ if (idle) { /* * Bases are idle if the next event is more than a tick * away. Caution: @nextevt could have changed by enqueueing a * global timer into timer migration hierarchy. Therefore a new * check is required here. * * If the base is marked idle then any timer add operation must * forward the base clk itself to keep granularity small. This * idle logic is only maintained for the BASE_LOCAL and * BASE_GLOBAL base, deferrable timers may still see large * granularity skew (by design). */ if (!base_local->is_idle && time_after(nextevt, basej + 1)) { base_local->is_idle = true; /* * Global timers queued locally while running in a task * in nohz_full mode need a self-IPI to kick reprogramming * in IRQ tail. */ if (tick_nohz_full_cpu(base_local->cpu)) base_global->is_idle = true; trace_timer_base_idle(true, base_local->cpu); } *idle = base_local->is_idle; /* * When timer base is not set idle, undo the effect of * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be * changed here. */ if (!base_local->is_idle && idle_is_possible) tmigr_cpu_activate(); } raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); return cmp_next_hrtimer_event(basem, tevt.local); } /** * get_next_timer_interrupt() - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. If timer of global base was queued into * timer migration hierarchy, first global timer is not taken into account. If * it was the last CPU of timer migration hierarchy going idle, first global * event is taken into account. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { return __get_next_timer_interrupt(basej, basem, NULL); } /** * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases * @basej: base time jiffies * @basem: base time clock monotonic * @idle: pointer to store the value of timer_base->is_idle on return; * *idle contains the information whether tick was already stopped * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is * returned as well. */ u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) { if (*idle) return KTIME_MAX; return __get_next_timer_interrupt(basej, basem, idle); } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { /* * We do this unlocked. The worst outcome is a remote pinned timer * enqueue sending a pointless IPI, but taking the lock would just * make the window for sending the IPI a few instructions smaller * for the cost of taking the lock in the exit from idle * path. Required for BASE_LOCAL only. */ __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); if (tick_nohz_full_cpu(smp_processor_id())) __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false); trace_timer_base_idle(false, smp_processor_id()); /* Activate without holding the timer_base->lock */ tmigr_cpu_activate(); } #endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { struct hlist_head heads[LVL_DEPTH]; int levels; lockdep_assert_held(&base->lock); if (base->running_timer) return; while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * TIMER_NEXT_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); /* * While executing timers, base->clk is set 1 offset ahead of * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; timer_recalc_next_expiry(base); while (levels--) expire_timers(base, heads + levels); } } static void __run_timer_base(struct timer_base *base) { /* Can race against a remote CPU updating next_expiry under the lock */ if (time_before(jiffies, READ_ONCE(base->next_expiry))) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); __run_timers(base); raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } static void run_timer_base(int index) { struct timer_base *base = this_cpu_ptr(&timer_bases[index]); __run_timer_base(base); } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(void) { run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { run_timer_base(BASE_GLOBAL); run_timer_base(BASE_DEF); if (is_timers_nohz_active()) tmigr_handle_remote(); } } /* * Called by the local, per-CPU timer interrupt on SMP. */ static void run_local_timers(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); for (int i = 0; i < NR_BASES; i++, base++) { /* * Raise the softirq only if required. * * timer_base::next_expiry can be written by a remote CPU while * holding the lock. If this write happens at the same time than * the lockless local read, sanity checker could complain about * data corruption. * * There are two possible situations where * timer_base::next_expiry is written by a remote CPU: * * 1. Remote CPU expires global timers of this CPU and updates * timer_base::next_expiry of BASE_GLOBAL afterwards in * next_timer_interrupt() or timer_recalc_next_expiry(). The * worst outcome is a superfluous raise of the timer softirq * when the not yet updated value is read. * * 2. A new first pinned timer is enqueued by a remote CPU * and therefore timer_base::next_expiry of BASE_LOCAL is * updated. When this update is missed, this isn't a * problem, as an IPI is executed nevertheless when the CPU * was idle before. When the CPU wasn't idle but the update * is missed, then the timer would expire one jiffy late - * bad luck. * * Those unlikely corner cases where the worst outcome is only a * one jiffy delay or a superfluous raise of the softirq are * not that expensive as doing the check always while holding * the lock. * * Possible remote writers are using WRITE_ONCE(). Local reader * uses therefore READ_ONCE(). */ if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { raise_timer_softirq(TIMER_SOFTIRQ); return; } } } /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { struct task_struct *p = current; /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif sched_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } int timers_prepare_cpu(unsigned int cpu) { struct timer_base *base; int b; for (b = 0; b < NR_BASES; b++) { base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + TIMER_NEXT_MAX_DELTA; base->next_expiry_recalc = false; base->timers_pending = false; base->is_idle = false; } return 0; } int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; int b, i; for (b = 0; b < NR_BASES; b++) { old_base = per_cpu_ptr(&timer_bases[b], cpu); new_base = get_cpu_ptr(&timer_bases[b]); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock_irq(&new_base->lock); raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); /* * The current CPUs base clock might be stale. Update it * before moving the timers over. */ forward_timer_base(new_base); WARN_ON_ONCE(old_base->running_timer); old_base->running_timer = NULL; for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); raw_spin_unlock(&old_base->lock); raw_spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } return 0; } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { struct timer_base *base; int i; for (i = 0; i < NR_BASES; i++) { base = per_cpu_ptr(&timer_bases[i], cpu); base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; base->next_expiry = base->clk + TIMER_NEXT_MAX_DELTA; timer_base_init_expiry_lock(base); } } static void __init init_timer_cpus(void) { int cpu; for_each_possible_cpu(cpu) init_timer_cpu(cpu); } void __init timers_init(void) { init_timer_cpus(); posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } |
| 296 296 277 40 18 21 21 1 110 277 280 280 129 182 50 3 45 3 7 45 86 19 16 37 2 77 87 25 84 73 86 25 25 73 24 24 24 6 24 24 24 24 24 25 73 72 19 73 19 72 1 277 277 1 166 142 60 60 38 49 86 1 85 2 87 87 87 87 25 1 73 234 17 275 41 277 162 58 58 18 47 47 47 36 13 21 47 15 55 17 38 13 49 49 39 39 80 86 55 33 31 53 50 39 69 69 40 25 38 29 29 26 13 39 96 96 96 96 67 18 12 10 34 24 34 54 13 64 12 65 16 20 20 3 6 4 4 4 8 2 6 6 2 7 8 6 1 5 1 1 5 17 2 17 11 4 5 1 3 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/indirect.c * * from * * linux/fs/ext4/inode.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Goal-directed block allocation by Stephen Tweedie * (sct@redhat.com), 1993, 1998 */ #include "ext4_jbd2.h" #include "truncate.h" #include <linux/dax.h> #include <linux/uio.h> #include <trace/events/ext4.h> typedef struct { __le32 *p; __le32 key; struct buffer_head *bh; } Indirect; static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) { p->key = *(p->p = v); p->bh = bh; } /** * ext4_block_to_path - parse the block number into array of offsets * @inode: inode in question (we are only interested in its superblock) * @i_block: block number to be parsed * @offsets: array to store the offsets in * @boundary: set this non-zero if the referred-to block is likely to be * followed (on disk) by an indirect block. * * To store the locations of file's data ext4 uses a data structure common * for UNIX filesystems - tree of pointers anchored in the inode, with * data blocks at leaves and indirect blocks in intermediate nodes. * This function translates the block number into path in that tree - * return value is the path length and @offsets[n] is the offset of * pointer to (n+1)th node in the nth one. If @block is out of range * (negative or too large) warning is printed and zero returned. * * Note: function doesn't find node addresses, so no IO is needed. All * we need to know is the capacity of indirect blocks (taken from the * inode->i_sb). */ /* * Portability note: the last comparison (check that we fit into triple * indirect block) is spelled differently, because otherwise on an * architecture with 32-bit longs and 8Kb pages we might get into trouble * if our filesystem had 8Kb blocks. We might use long long, but that would * kill us on x86. Oh, well, at least the sign propagation does not matter - * i_block would have to be negative in the very beginning, so we would not * get there at all. */ static int ext4_block_to_path(struct inode *inode, ext4_lblk_t i_block, ext4_lblk_t offsets[4], int *boundary) { int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb); int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb); const long direct_blocks = EXT4_NDIR_BLOCKS, indirect_blocks = ptrs, double_blocks = (1 << (ptrs_bits * 2)); int n = 0; int final = 0; if (i_block < direct_blocks) { offsets[n++] = i_block; final = direct_blocks; } else if ((i_block -= direct_blocks) < indirect_blocks) { offsets[n++] = EXT4_IND_BLOCK; offsets[n++] = i_block; final = ptrs; } else if ((i_block -= indirect_blocks) < double_blocks) { offsets[n++] = EXT4_DIND_BLOCK; offsets[n++] = i_block >> ptrs_bits; offsets[n++] = i_block & (ptrs - 1); final = ptrs; } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) { offsets[n++] = EXT4_TIND_BLOCK; offsets[n++] = i_block >> (ptrs_bits * 2); offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1); offsets[n++] = i_block & (ptrs - 1); final = ptrs; } else { ext4_warning(inode->i_sb, "block %lu > max in inode %lu", i_block + direct_blocks + indirect_blocks + double_blocks, inode->i_ino); } if (boundary) *boundary = final - 1 - (i_block & (ptrs - 1)); return n; } /** * ext4_get_branch - read the chain of indirect blocks leading to data * @inode: inode in question * @depth: depth of the chain (1 - direct pointer, etc.) * @offsets: offsets of pointers in inode/indirect blocks * @chain: place to store the result * @err: here we store the error value * * Function fills the array of triples <key, p, bh> and returns %NULL * if everything went OK or the pointer to the last filled triple * (incomplete one) otherwise. Upon the return chain[i].key contains * the number of (i+1)-th block in the chain (as it is stored in memory, * i.e. little-endian 32-bit), chain[i].p contains the address of that * number (it points into struct inode for i==0 and into the bh->b_data * for i>0) and chain[i].bh points to the buffer_head of i-th indirect * block for i>0 and NULL for i==0. In other words, it holds the block * numbers of the chain, addresses they were taken from (and where we can * verify that chain did not change) and buffer_heads hosting these * numbers. * * Function stops when it stumbles upon zero pointer (absent block) * (pointer to last triple returned, *@err == 0) * or when it gets an IO error reading an indirect block * (ditto, *@err == -EIO) * or when it reads all @depth-1 indirect blocks successfully and finds * the whole chain, all way to the data (returns %NULL, *err == 0). * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) */ static Indirect *ext4_get_branch(struct inode *inode, int depth, ext4_lblk_t *offsets, Indirect chain[4], int *err) { struct super_block *sb = inode->i_sb; Indirect *p = chain; struct buffer_head *bh; unsigned int key; int ret = -EIO; *err = 0; /* i_data is not going away, no lock needed */ add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets); if (!p->key) goto no_block; while (--depth) { key = le32_to_cpu(p->key); if (key > ext4_blocks_count(EXT4_SB(sb)->s_es)) { /* the block was out of range */ ret = -EFSCORRUPTED; goto failure; } bh = sb_getblk(sb, key); if (unlikely(!bh)) { ret = -ENOMEM; goto failure; } if (!bh_uptodate_or_lock(bh)) { if (ext4_read_bh(bh, 0, NULL, false) < 0) { put_bh(bh); goto failure; } /* validate block references */ if (ext4_check_indirect_blockref(inode, bh)) { put_bh(bh); goto failure; } } add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets); /* Reader: end */ if (!p->key) goto no_block; } return NULL; failure: *err = ret; no_block: return p; } /** * ext4_find_near - find a place for allocation with sufficient locality * @inode: owner * @ind: descriptor of indirect block. * * This function returns the preferred place for block allocation. * It is used when heuristic for sequential allocation fails. * Rules are: * + if there is a block to the left of our position - allocate near it. * + if pointer will live in indirect block - allocate near that block. * + if pointer will live in inode - allocate in the same * cylinder group. * * In the latter case we colour the starting block by the callers PID to * prevent it from clashing with concurrent allocations for a different inode * in the same block group. The PID is used here so that functionally related * files will be close-by on-disk. * * Caller must make sure that @ind is valid and will stay that way. */ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) { struct ext4_inode_info *ei = EXT4_I(inode); __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data; __le32 *p; /* Try to find previous block */ for (p = ind->p - 1; p >= start; p--) { if (*p) return le32_to_cpu(*p); } /* No such thing, so let's try location of indirect block */ if (ind->bh) return ind->bh->b_blocknr; /* * It is going to be referred to from the inode itself? OK, just put it * into the same cylinder group then. */ return ext4_inode_to_goal_block(inode); } /** * ext4_find_goal - find a preferred place for allocation. * @inode: owner * @block: block we want * @partial: pointer to the last triple within a chain * * Normally this function find the preferred place for block allocation, * returns it. * Because this is only used for non-extent files, we limit the block nr * to 32 bits. */ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, Indirect *partial) { ext4_fsblk_t goal; /* * XXX need to get goal block from mballoc's data structures */ goal = ext4_find_near(inode, partial); goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; return goal; } /** * ext4_blks_to_allocate - Look up the block map and count the number * of direct blocks need to be allocated for the given branch. * * @branch: chain of indirect blocks * @k: number of blocks need for indirect blocks * @blks: number of data blocks to be mapped. * @blocks_to_boundary: the offset in the indirect block * * return the total number of blocks to be allocate, including the * direct and indirect blocks. */ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, int blocks_to_boundary) { unsigned int count = 0; /* * Simple case, [t,d]Indirect block(s) has not allocated yet * then it's clear blocks on that path have not allocated */ if (k > 0) { /* right now we don't handle cross boundary allocation */ if (blks < blocks_to_boundary + 1) count += blks; else count += blocks_to_boundary + 1; return count; } count++; while (count < blks && count <= blocks_to_boundary && le32_to_cpu(*(branch[0].p + count)) == 0) { count++; } return count; } /** * ext4_alloc_branch() - allocate and set up a chain of blocks * @handle: handle for this transaction * @ar: structure describing the allocation request * @indirect_blks: number of allocated indirect blocks * @offsets: offsets (in the blocks) to store the pointers to next. * @branch: place to store the chain in. * * This function allocates blocks, zeroes out all but the last one, * links them into chain and (if we are synchronous) writes them to disk. * In other words, it prepares a branch that can be spliced onto the * inode. It stores the information about that chain in the branch[], in * the same format as ext4_get_branch() would do. We are calling it after * we had read the existing part of chain and partial points to the last * triple of that (one with zero ->key). Upon the exit we have the same * picture as after the successful ext4_get_block(), except that in one * place chain is disconnected - *branch->p is still zero (we did not * set the last link), but branch->key contains the number that should * be placed into *branch->p to fill that gap. * * If allocation fails we free all blocks we've allocated (and forget * their buffer_heads) and return the error value the from failed * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain * as described above and return 0. */ static int ext4_alloc_branch(handle_t *handle, struct ext4_allocation_request *ar, int indirect_blks, ext4_lblk_t *offsets, Indirect *branch) { struct buffer_head * bh; ext4_fsblk_t b, new_blocks[4]; __le32 *p; int i, j, err, len = 1; for (i = 0; i <= indirect_blks; i++) { if (i == indirect_blks) { new_blocks[i] = ext4_mb_new_blocks(handle, ar, &err); } else { ar->goal = new_blocks[i] = ext4_new_meta_blocks(handle, ar->inode, ar->goal, ar->flags & EXT4_MB_DELALLOC_RESERVED, NULL, &err); /* Simplify error cleanup... */ branch[i+1].bh = NULL; } if (err) { i--; goto failed; } branch[i].key = cpu_to_le32(new_blocks[i]); if (i == 0) continue; bh = branch[i].bh = sb_getblk(ar->inode->i_sb, new_blocks[i-1]); if (unlikely(!bh)) { err = -ENOMEM; goto failed; } lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, ar->inode->i_sb, bh, EXT4_JTR_NONE); if (err) { unlock_buffer(bh); goto failed; } memset(bh->b_data, 0, bh->b_size); p = branch[i].p = (__le32 *) bh->b_data + offsets[i]; b = new_blocks[i]; if (i == indirect_blks) len = ar->len; for (j = 0; j < len; j++) *p++ = cpu_to_le32(b++); BUFFER_TRACE(bh, "marking uptodate"); set_buffer_uptodate(bh); unlock_buffer(bh); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, ar->inode, bh); if (err) goto failed; } return 0; failed: if (i == indirect_blks) { /* Free data blocks */ ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i], ar->len, 0); i--; } for (; i >= 0; i--) { /* * We want to ext4_forget() only freshly allocated indirect * blocks. Buffer for new_blocks[i] is at branch[i+1].bh * (buffer at branch[0].bh is indirect block / inode already * existing before ext4_alloc_branch() was called). Also * because blocks are freshly allocated, we don't need to * revoke them which is why we don't set * EXT4_FREE_BLOCKS_METADATA. */ ext4_free_blocks(handle, ar->inode, branch[i+1].bh, new_blocks[i], 1, branch[i+1].bh ? EXT4_FREE_BLOCKS_FORGET : 0); } return err; } /** * ext4_splice_branch() - splice the allocated branch onto inode. * @handle: handle for this transaction * @ar: structure describing the allocation request * @where: location of missing link * @num: number of indirect blocks we are adding * * This function fills the missing link and does all housekeeping needed in * inode (->i_blocks, etc.). In case of success we end up with the full * chain to new block and return 0. */ static int ext4_splice_branch(handle_t *handle, struct ext4_allocation_request *ar, Indirect *where, int num) { int i; int err = 0; ext4_fsblk_t current_block; /* * If we're splicing into a [td]indirect block (as opposed to the * inode) then we need to get write access to the [td]indirect block * before the splice. */ if (where->bh) { BUFFER_TRACE(where->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, ar->inode->i_sb, where->bh, EXT4_JTR_NONE); if (err) goto err_out; } /* That's it */ *where->p = where->key; /* * Update the host buffer_head or inode to point to more just allocated * direct blocks blocks */ if (num == 0 && ar->len > 1) { current_block = le32_to_cpu(where->key) + 1; for (i = 1; i < ar->len; i++) *(where->p + i) = cpu_to_le32(current_block++); } /* We are done with atomic stuff, now do the rest of housekeeping */ /* had we spliced it onto indirect block? */ if (where->bh) { /* * If we spliced it onto an indirect block, we haven't * altered the inode. Note however that if it is being spliced * onto an indirect block at the very end of the file (the * file is growing) then we *will* alter the inode to reflect * the new i_size. But that is not done here - it is done in * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode. */ ext4_debug("splicing indirect only\n"); BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh); if (err) goto err_out; } else { /* * OK, we spliced it into the inode itself on a direct block. */ err = ext4_mark_inode_dirty(handle, ar->inode); if (unlikely(err)) goto err_out; ext4_debug("splicing direct\n"); } return err; err_out: for (i = 1; i <= num; i++) { /* * branch[i].bh is newly allocated, so there is no * need to revoke the block, which is why we don't * need to set EXT4_FREE_BLOCKS_METADATA. */ ext4_free_blocks(handle, ar->inode, where[i].bh, 0, 1, EXT4_FREE_BLOCKS_FORGET); } ext4_free_blocks(handle, ar->inode, NULL, le32_to_cpu(where[num].key), ar->len, 0); return err; } /* * The ext4_ind_map_blocks() function handles non-extents inodes * (i.e., using the traditional indirect/double-indirect i_blocks * scheme) for ext4_map_blocks(). * * Allocation strategy is simple: if we have to allocate something, we will * have to go the whole way to leaf. So let's do it before attaching anything * to tree, set linkage between the newborn blocks, write them if sync is * required, recheck the path, free and repeat if check fails, otherwise * set the last missing link (that will protect us from any truncate-generated * removals - all blocks on the path are immune now) and possibly force the * write on the parent block. * That has a nice additional property: no special recovery from the failed * allocations is needed - we simply release blocks and do not touch anything * reachable from inode. * * `handle' can be NULL if create == 0. * * return > 0, # of blocks mapped or allocated. * return = 0, if plain lookup failed. * return < 0, error case. * * The ext4_ind_get_blocks() function should be called with * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system * blocks. */ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_allocation_request ar; int err = -EIO; ext4_lblk_t offsets[4]; Indirect chain[4]; Indirect *partial; int indirect_blks; int blocks_to_boundary = 0; int depth; u64 count = 0; ext4_fsblk_t first_block = 0; trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))); ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, map->m_lblk, offsets, &blocks_to_boundary); if (depth == 0) goto out; partial = ext4_get_branch(inode, depth, offsets, chain, &err); /* Simplest case - block found, no allocation needed */ if (!partial) { first_block = le32_to_cpu(chain[depth - 1].key); count++; /*map more blocks*/ while (count < map->m_len && count <= blocks_to_boundary) { ext4_fsblk_t blk; blk = le32_to_cpu(*(chain[depth-1].p + count)); if (blk == first_block + count) count++; else break; } goto got_it; } /* Next simple case - plain lookup failed */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { unsigned epb = inode->i_sb->s_blocksize / sizeof(u32); int i; /* * Count number blocks in a subtree under 'partial'. At each * level we count number of complete empty subtrees beyond * current offset and then descend into the subtree only * partially beyond current offset. */ count = 0; for (i = partial - chain + 1; i < depth; i++) count = count * epb + (epb - offsets[i] - 1); count++; /* Fill in size of a hole we found */ map->m_pblk = 0; map->m_len = umin(map->m_len, count); goto cleanup; } /* Failed read of indirect block */ if (err == -EIO) goto cleanup; /* * Okay, we need to do block allocation. */ if (ext4_has_feature_bigalloc(inode->i_sb)) { EXT4_ERROR_INODE(inode, "Can't allocate blocks for " "non-extent mapped inodes with bigalloc"); err = -EFSCORRUPTED; goto out; } /* Set up for the direct block allocation */ memset(&ar, 0, sizeof(ar)); ar.inode = inode; ar.logical = map->m_lblk; if (S_ISREG(inode->i_mode)) ar.flags = EXT4_MB_HINT_DATA; if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ar.flags |= EXT4_MB_DELALLOC_RESERVED; if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) ar.flags |= EXT4_MB_USE_RESERVED; ar.goal = ext4_find_goal(inode, map->m_lblk, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; /* * Next look up the indirect map to count the totoal number of * direct blocks to allocate for this branch. */ ar.len = ext4_blks_to_allocate(partial, indirect_blks, map->m_len, blocks_to_boundary); /* * Block out ext4_truncate while we alter the tree */ err = ext4_alloc_branch(handle, &ar, indirect_blks, offsets + (partial - chain), partial); /* * The ext4_splice_branch call will free and forget any buffers * on the new chain if there is a failure, but that risks using * up transaction credits, especially for bitmaps where the * credits cannot be returned. Can we handle this somehow? We * may need to return -EAGAIN upwards in the worst case. --sct */ if (!err) err = ext4_splice_branch(handle, &ar, partial, indirect_blks); if (err) goto cleanup; map->m_flags |= EXT4_MAP_NEW; ext4_update_inode_fsync_trans(handle, inode, 1); count = ar.len; got_it: map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = le32_to_cpu(chain[depth-1].key); map->m_len = count; if (count > blocks_to_boundary) map->m_flags |= EXT4_MAP_BOUNDARY; err = count; /* Clean up and exit */ partial = chain + depth - 1; /* the whole chain */ cleanup: while (partial > chain) { BUFFER_TRACE(partial->bh, "call brelse"); brelse(partial->bh); partial--; } out: trace_ext4_ind_map_blocks_exit(inode, flags, map, err); return err; } /* * Calculate number of indirect blocks touched by mapping @nrblocks logically * contiguous blocks */ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks) { /* * With N contiguous data blocks, we need at most * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks, * 2 dindirect blocks, and 1 tindirect block */ return DIV_ROUND_UP(nrblocks, EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4; } static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh, int *dropped) { int err; if (bh) { BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); if (unlikely(err)) return err; } err = ext4_mark_inode_dirty(handle, inode); if (unlikely(err)) return err; /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; } /* * Truncate transactions can be complex and absolutely huge. So we need to * be able to restart the transaction at a convenient checkpoint to make * sure we don't overflow the journal. * * Try to extend this transaction for the purposes of truncation. If * extend fails, we restart transaction. */ static int ext4_ind_truncate_ensure_credits(handle_t *handle, struct inode *inode, struct buffer_head *bh, int revoke_creds) { int ret; int dropped = 0; ret = ext4_journal_ensure_credits_fn(handle, EXT4_RESERVE_TRANS_BLOCKS, ext4_blocks_for_truncate(inode), revoke_creds, ext4_ind_trunc_restart_fn(handle, inode, bh, &dropped)); if (dropped) down_write(&EXT4_I(inode)->i_data_sem); if (ret <= 0) return ret; if (bh) { BUFFER_TRACE(bh, "retaking write access"); ret = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (unlikely(ret)) return ret; } return 0; } /* * Probably it should be a library function... search for first non-zero word * or memcmp with zero_page, whatever is better for particular architecture. * Linus? */ static inline int all_zeroes(__le32 *p, __le32 *q) { while (p < q) if (*p++) return 0; return 1; } /** * ext4_find_shared - find the indirect blocks for partial truncation. * @inode: inode in question * @depth: depth of the affected branch * @offsets: offsets of pointers in that branch (see ext4_block_to_path) * @chain: place to store the pointers to partial indirect blocks * @top: place to the (detached) top of branch * * This is a helper function used by ext4_truncate(). * * When we do truncate() we may have to clean the ends of several * indirect blocks but leave the blocks themselves alive. Block is * partially truncated if some data below the new i_size is referred * from it (and it is on the path to the first completely truncated * data block, indeed). We have to free the top of that path along * with everything to the right of the path. Since no allocation * past the truncation point is possible until ext4_truncate() * finishes, we may safely do the latter, but top of branch may * require special attention - pageout below the truncation point * might try to populate it. * * We atomically detach the top of branch from the tree, store the * block number of its root in *@top, pointers to buffer_heads of * partially truncated blocks - in @chain[].bh and pointers to * their last elements that should not be removed - in * @chain[].p. Return value is the pointer to last filled element * of @chain. * * The work left to caller to do the actual freeing of subtrees: * a) free the subtree starting from *@top * b) free the subtrees whose roots are stored in * (@chain[i].p+1 .. end of @chain[i].bh->b_data) * c) free the subtrees growing from the inode past the @chain[0]. * (no partially truncated stuff there). */ static Indirect *ext4_find_shared(struct inode *inode, int depth, ext4_lblk_t offsets[4], Indirect chain[4], __le32 *top) { Indirect *partial, *p; int k, err; *top = 0; /* Make k index the deepest non-null offset + 1 */ for (k = depth; k > 1 && !offsets[k-1]; k--) ; partial = ext4_get_branch(inode, k, offsets, chain, &err); /* Writer: pointers */ if (!partial) partial = chain + k-1; /* * If the branch acquired continuation since we've looked at it - * fine, it should all survive and (new) top doesn't belong to us. */ if (!partial->key && *partial->p) /* Writer: end */ goto no_top; for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--) ; /* * OK, we've found the last block that must survive. The rest of our * branch should be detached before unlocking. However, if that rest * of branch is all ours and does not grow immediately from the inode * it's easier to cheat and just decrement partial->p. */ if (p == chain + k - 1 && p > chain) { p->p--; } else { *top = *p->p; /* Nope, don't do this in ext4. Must leave the tree intact */ #if 0 *p->p = 0; #endif } /* Writer: end */ while (partial > p) { brelse(partial->bh); partial--; } no_top: return partial; } /* * Zero a number of block pointers in either an inode or an indirect block. * If we restart the transaction we must again get write access to the * indirect block for further modification. * * We release `count' blocks on disk, but (last - first) may be greater * than `count' because there can be holes in there. * * Return 0 on success, 1 on invalid block range * and < 0 on fatal error. */ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block_to_free, unsigned long count, __le32 *first, __le32 *last) { __le32 *p; int flags = EXT4_FREE_BLOCKS_VALIDATED; int err; if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA; else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; if (!ext4_inode_block_valid(inode, block_to_free, count)) { EXT4_ERROR_INODE(inode, "attempt to clear invalid " "blocks %llu len %lu", (unsigned long long) block_to_free, count); return 1; } err = ext4_ind_truncate_ensure_credits(handle, inode, bh, ext4_free_data_revoke_credits(inode, count)); if (err < 0) goto out_err; for (p = first; p < last; p++) *p = 0; ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags); return 0; out_err: ext4_std_error(inode->i_sb, err); return err; } /** * ext4_free_data - free a list of data blocks * @handle: handle for this transaction * @inode: inode we are dealing with * @this_bh: indirect buffer_head which contains *@first and *@last * @first: array of block numbers * @last: points immediately past the end of array * * We are freeing all blocks referred from that array (numbers are stored as * little-endian 32-bit) and updating @inode->i_blocks appropriately. * * We accumulate contiguous runs of blocks to free. Conveniently, if these * blocks are contiguous then releasing them at one time will only affect one * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't * actually use a lot of journal space. * * @this_bh will be %NULL if @first and @last point into the inode's direct * block pointers. */ static void ext4_free_data(handle_t *handle, struct inode *inode, struct buffer_head *this_bh, __le32 *first, __le32 *last) { ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */ unsigned long count = 0; /* Number of blocks in the run */ __le32 *block_to_free_p = NULL; /* Pointer into inode/ind corresponding to block_to_free */ ext4_fsblk_t nr; /* Current block # */ __le32 *p; /* Pointer into inode/ind for current block */ int err = 0; if (this_bh) { /* For indirect block */ BUFFER_TRACE(this_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, this_bh, EXT4_JTR_NONE); /* Important: if we can't update the indirect pointers * to the blocks, we can't free them. */ if (err) return; } for (p = first; p < last; p++) { nr = le32_to_cpu(*p); if (nr) { /* accumulate blocks to free if they're contiguous */ if (count == 0) { block_to_free = nr; block_to_free_p = p; count = 1; } else if (nr == block_to_free + count) { count++; } else { err = ext4_clear_blocks(handle, inode, this_bh, block_to_free, count, block_to_free_p, p); if (err) break; block_to_free = nr; block_to_free_p = p; count = 1; } } } if (!err && count > 0) err = ext4_clear_blocks(handle, inode, this_bh, block_to_free, count, block_to_free_p, p); if (err < 0) /* fatal error */ return; if (this_bh) { BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata"); /* * The buffer head should have an attached journal head at this * point. However, if the data is corrupted and an indirect * block pointed to itself, it would have been detached when * the block was cleared. Check for this instead of OOPSing. */ if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh)) ext4_handle_dirty_metadata(handle, inode, this_bh); else EXT4_ERROR_INODE(inode, "circular indirect block detected at " "block %llu", (unsigned long long) this_bh->b_blocknr); } } /** * ext4_free_branches - free an array of branches * @handle: JBD handle for this transaction * @inode: inode we are dealing with * @parent_bh: the buffer_head which contains *@first and *@last * @first: array of block numbers * @last: pointer immediately past the end of array * @depth: depth of the branches to free * * We are freeing all blocks referred from these branches (numbers are * stored as little-endian 32-bit) and updating @inode->i_blocks * appropriately. */ static void ext4_free_branches(handle_t *handle, struct inode *inode, struct buffer_head *parent_bh, __le32 *first, __le32 *last, int depth) { ext4_fsblk_t nr; __le32 *p; if (ext4_handle_is_aborted(handle)) return; if (depth--) { struct buffer_head *bh; int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); p = last; while (--p >= first) { nr = le32_to_cpu(*p); if (!nr) continue; /* A hole */ if (!ext4_inode_block_valid(inode, nr, 1)) { EXT4_ERROR_INODE(inode, "invalid indirect mapped " "block %lu (level %d)", (unsigned long) nr, depth); break; } /* Go read the buffer for the next level down */ bh = ext4_sb_bread_nofail(inode->i_sb, nr); /* * A read failure? Report error and clear slot * (should be rare). */ if (IS_ERR(bh)) { ext4_error_inode_block(inode, nr, -PTR_ERR(bh), "Read failure"); continue; } /* This zaps the entire block. Bottom up. */ BUFFER_TRACE(bh, "free child branches"); ext4_free_branches(handle, inode, bh, (__le32 *) bh->b_data, (__le32 *) bh->b_data + addr_per_block, depth); brelse(bh); /* * Everything below this pointer has been * released. Now let this top-of-subtree go. * * We want the freeing of this indirect block to be * atomic in the journal with the updating of the * bitmap block which owns it. So make some room in * the journal. * * We zero the parent pointer *after* freeing its * pointee in the bitmaps, so if extend_transaction() * for some reason fails to put the bitmap changes and * the release into the same transaction, recovery * will merely complain about releasing a free block, * rather than leaking blocks. */ if (ext4_handle_is_aborted(handle)) return; if (ext4_ind_truncate_ensure_credits(handle, inode, NULL, ext4_free_metadata_revoke_credits( inode->i_sb, 1)) < 0) return; /* * The forget flag here is critical because if * we are journaling (and not doing data * journaling), we have to make sure a revoke * record is written to prevent the journal * replay from overwriting the (former) * indirect block if it gets reallocated as a * data block. This must happen in the same * transaction where the data blocks are * actually freed. */ ext4_free_blocks(handle, inode, NULL, nr, 1, EXT4_FREE_BLOCKS_METADATA| EXT4_FREE_BLOCKS_FORGET); if (parent_bh) { /* * The block which we have just freed is * pointed to by an indirect block: journal it */ BUFFER_TRACE(parent_bh, "get_write_access"); if (!ext4_journal_get_write_access(handle, inode->i_sb, parent_bh, EXT4_JTR_NONE)) { *p = 0; BUFFER_TRACE(parent_bh, "call ext4_handle_dirty_metadata"); ext4_handle_dirty_metadata(handle, inode, parent_bh); } } } } else { /* We have reached the bottom of the tree. */ BUFFER_TRACE(parent_bh, "free data blocks"); ext4_free_data(handle, inode, parent_bh, first, last); } } void ext4_ind_truncate(handle_t *handle, struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); __le32 *i_data = ei->i_data; int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); ext4_lblk_t offsets[4]; Indirect chain[4]; Indirect *partial; __le32 nr = 0; int n = 0; ext4_lblk_t last_block, max_block; unsigned blocksize = inode->i_sb->s_blocksize; last_block = (inode->i_size + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); if (last_block != max_block) { n = ext4_block_to_path(inode, last_block, offsets, NULL); if (n == 0) return; } ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); /* * The orphan list entry will now protect us from any crash which * occurs before the truncate completes, so it is now safe to propagate * the new, shorter inode size (held for now in i_size) into the * on-disk inode. We do this via i_disksize, which is the value which * ext4 *really* writes onto the disk inode. */ ei->i_disksize = inode->i_size; if (last_block == max_block) { /* * It is unnecessary to free any data blocks if last_block is * equal to the indirect block limit. */ return; } else if (n == 1) { /* direct blocks */ ext4_free_data(handle, inode, NULL, i_data+offsets[0], i_data + EXT4_NDIR_BLOCKS); goto do_indirects; } partial = ext4_find_shared(inode, n, offsets, chain, &nr); /* Kill the top of shared branch (not detached) */ if (nr) { if (partial == chain) { /* Shared branch grows from the inode */ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, (chain+n-1) - partial); *partial->p = 0; /* * We mark the inode dirty prior to restart, * and prior to stop. No need for it here. */ } else { /* Shared branch grows from an indirect block */ BUFFER_TRACE(partial->bh, "get_write_access"); ext4_free_branches(handle, inode, partial->bh, partial->p, partial->p+1, (chain+n-1) - partial); } } /* Clear the ends of indirect blocks on the shared branch */ while (partial > chain) { ext4_free_branches(handle, inode, partial->bh, partial->p + 1, (__le32*)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); BUFFER_TRACE(partial->bh, "call brelse"); brelse(partial->bh); partial--; } do_indirects: /* Kill the remaining (whole) subtrees */ switch (offsets[0]) { default: nr = i_data[EXT4_IND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } fallthrough; case EXT4_IND_BLOCK: nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } fallthrough; case EXT4_DIND_BLOCK: nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } fallthrough; case EXT4_TIND_BLOCK: ; } } /** * ext4_ind_remove_space - remove space from the range * @handle: JBD handle for this transaction * @inode: inode we are dealing with * @start: First block to remove * @end: One block after the last block to remove (exclusive) * * Free the blocks in the defined range (end is exclusive endpoint of * range). This is used by ext4_punch_hole(). */ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_inode_info *ei = EXT4_I(inode); __le32 *i_data = ei->i_data; int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); ext4_lblk_t offsets[4], offsets2[4]; Indirect chain[4], chain2[4]; Indirect *partial, *partial2; Indirect *p = NULL, *p2 = NULL; ext4_lblk_t max_block; __le32 nr = 0, nr2 = 0; int n = 0, n2 = 0; unsigned blocksize = inode->i_sb->s_blocksize; max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); if (end >= max_block) end = max_block; if ((start >= end) || (start > max_block)) return 0; n = ext4_block_to_path(inode, start, offsets, NULL); n2 = ext4_block_to_path(inode, end, offsets2, NULL); BUG_ON(n > n2); if ((n == 1) && (n == n2)) { /* We're punching only within direct block range */ ext4_free_data(handle, inode, NULL, i_data + offsets[0], i_data + offsets2[0]); return 0; } else if (n2 > n) { /* * Start and end are on a different levels so we're going to * free partial block at start, and partial block at end of * the range. If there are some levels in between then * do_indirects label will take care of that. */ if (n == 1) { /* * Start is at the direct block level, free * everything to the end of the level. */ ext4_free_data(handle, inode, NULL, i_data + offsets[0], i_data + EXT4_NDIR_BLOCKS); goto end_range; } partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); if (nr) { if (partial == chain) { /* Shared branch grows from the inode */ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, (chain+n-1) - partial); *partial->p = 0; } else { /* Shared branch grows from an indirect block */ BUFFER_TRACE(partial->bh, "get_write_access"); ext4_free_branches(handle, inode, partial->bh, partial->p, partial->p+1, (chain+n-1) - partial); } } /* * Clear the ends of indirect blocks on the shared branch * at the start of the range */ while (partial > chain) { ext4_free_branches(handle, inode, partial->bh, partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); partial--; } end_range: partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); if (nr2) { if (partial2 == chain2) { /* * Remember, end is exclusive so here we're at * the start of the next level we're not going * to free. Everything was covered by the start * of the range. */ goto do_indirects; } } else { /* * ext4_find_shared returns Indirect structure which * points to the last element which should not be * removed by truncate. But this is end of the range * in punch_hole so we need to point to the next element */ partial2->p++; } /* * Clear the ends of indirect blocks on the shared branch * at the end of the range */ while (partial2 > chain2) { ext4_free_branches(handle, inode, partial2->bh, (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); partial2--; } goto do_indirects; } /* Punch happened within the same level (n == n2) */ partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); /* Free top, but only if partial2 isn't its subtree. */ if (nr) { int level = min(partial - chain, partial2 - chain2); int i; int subtree = 1; for (i = 0; i <= level; i++) { if (offsets[i] != offsets2[i]) { subtree = 0; break; } } if (!subtree) { if (partial == chain) { /* Shared branch grows from the inode */ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, (chain+n-1) - partial); *partial->p = 0; } else { /* Shared branch grows from an indirect block */ BUFFER_TRACE(partial->bh, "get_write_access"); ext4_free_branches(handle, inode, partial->bh, partial->p, partial->p+1, (chain+n-1) - partial); } } } if (!nr2) { /* * ext4_find_shared returns Indirect structure which * points to the last element which should not be * removed by truncate. But this is end of the range * in punch_hole so we need to point to the next element */ partial2->p++; } while (partial > chain || partial2 > chain2) { int depth = (chain+n-1) - partial; int depth2 = (chain2+n2-1) - partial2; if (partial > chain && partial2 > chain2 && partial->bh->b_blocknr == partial2->bh->b_blocknr) { /* * We've converged on the same block. Clear the range, * then we're done. */ ext4_free_branches(handle, inode, partial->bh, partial->p + 1, partial2->p, (chain+n-1) - partial); goto cleanup; } /* * The start and end partial branches may not be at the same * level even though the punch happened within one level. So, we * give them a chance to arrive at the same level, then walk * them in step with each other until we converge on the same * block. */ if (partial > chain && depth <= depth2) { ext4_free_branches(handle, inode, partial->bh, partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); partial--; } if (partial2 > chain2 && depth2 <= depth) { ext4_free_branches(handle, inode, partial2->bh, (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); partial2--; } } cleanup: while (p && p > chain) { BUFFER_TRACE(p->bh, "call brelse"); brelse(p->bh); p--; } while (p2 && p2 > chain2) { BUFFER_TRACE(p2->bh, "call brelse"); brelse(p2->bh); p2--; } return 0; do_indirects: /* Kill the remaining (whole) subtrees */ switch (offsets[0]) { default: if (++n >= n2) break; nr = i_data[EXT4_IND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } fallthrough; case EXT4_IND_BLOCK: if (++n >= n2) break; nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } fallthrough; case EXT4_DIND_BLOCK: if (++n >= n2) break; nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } fallthrough; case EXT4_TIND_BLOCK: ; } goto cleanup; } |
| 1 1 1 1 1 68 6 6 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 2 2 2 2 2 2 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * drivers/net/veth.c * * Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc * * Author: Pavel Emelianov <xemul@openvz.org> * Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com> * */ #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/u64_stats_sync.h> #include <net/rtnetlink.h> #include <net/dst.h> #include <net/netdev_lock.h> #include <net/xfrm.h> #include <net/xdp.h> #include <linux/veth.h> #include <linux/module.h> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ptr_ring.h> #include <linux/bpf_trace.h> #include <linux/net_tstamp.h> #include <linux/skbuff_ref.h> #include <net/page_pool/helpers.h> #define DRV_NAME "veth" #define DRV_VERSION "1.0" #define VETH_XDP_FLAG BIT(0) #define VETH_RING_SIZE 256 #define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) #define VETH_XDP_TX_BULK_SIZE 16 #define VETH_XDP_BATCH 16 struct veth_stats { u64 rx_drops; /* xdp */ u64 xdp_packets; u64 xdp_bytes; u64 xdp_redirect; u64 xdp_drops; u64 xdp_tx; u64 xdp_tx_err; u64 peer_tq_xdp_xmit; u64 peer_tq_xdp_xmit_err; }; struct veth_rq_stats { struct veth_stats vs; struct u64_stats_sync syncp; }; struct veth_rq { struct napi_struct xdp_napi; struct napi_struct __rcu *napi; /* points to xdp_napi when the latter is initialized */ struct net_device *dev; struct bpf_prog __rcu *xdp_prog; struct xdp_mem_info xdp_mem; struct veth_rq_stats stats; bool rx_notify_masked; struct ptr_ring xdp_ring; struct xdp_rxq_info xdp_rxq; struct page_pool *page_pool; }; struct veth_priv { struct net_device __rcu *peer; atomic64_t dropped; struct bpf_prog *_xdp_prog; struct veth_rq *rq; unsigned int requested_headroom; }; struct veth_xdp_tx_bq { struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE]; unsigned int count; }; /* * ethtool interface */ struct veth_q_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; }; #define VETH_RQ_STAT(m) offsetof(struct veth_stats, m) static const struct veth_q_stat_desc veth_rq_stats_desc[] = { { "xdp_packets", VETH_RQ_STAT(xdp_packets) }, { "xdp_bytes", VETH_RQ_STAT(xdp_bytes) }, { "drops", VETH_RQ_STAT(rx_drops) }, { "xdp_redirect", VETH_RQ_STAT(xdp_redirect) }, { "xdp_drops", VETH_RQ_STAT(xdp_drops) }, { "xdp_tx", VETH_RQ_STAT(xdp_tx) }, { "xdp_tx_errors", VETH_RQ_STAT(xdp_tx_err) }, }; #define VETH_RQ_STATS_LEN ARRAY_SIZE(veth_rq_stats_desc) static const struct veth_q_stat_desc veth_tq_stats_desc[] = { { "xdp_xmit", VETH_RQ_STAT(peer_tq_xdp_xmit) }, { "xdp_xmit_errors", VETH_RQ_STAT(peer_tq_xdp_xmit_err) }, }; #define VETH_TQ_STATS_LEN ARRAY_SIZE(veth_tq_stats_desc) static struct { const char string[ETH_GSTRING_LEN]; } ethtool_stats_keys[] = { { "peer_ifindex" }, }; struct veth_xdp_buff { struct xdp_buff xdp; struct sk_buff *skb; }; static int veth_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.autoneg = AUTONEG_DISABLE; return 0; } static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { u8 *p = buf; int i, j; switch(stringset) { case ETH_SS_STATS: memcpy(p, ðtool_stats_keys, sizeof(ethtool_stats_keys)); p += sizeof(ethtool_stats_keys); for (i = 0; i < dev->real_num_rx_queues; i++) for (j = 0; j < VETH_RQ_STATS_LEN; j++) ethtool_sprintf(&p, "rx_queue_%u_%.18s", i, veth_rq_stats_desc[j].desc); for (i = 0; i < dev->real_num_tx_queues; i++) for (j = 0; j < VETH_TQ_STATS_LEN; j++) ethtool_sprintf(&p, "tx_queue_%u_%.18s", i, veth_tq_stats_desc[j].desc); page_pool_ethtool_stats_get_strings(p); break; } } static int veth_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: return ARRAY_SIZE(ethtool_stats_keys) + VETH_RQ_STATS_LEN * dev->real_num_rx_queues + VETH_TQ_STATS_LEN * dev->real_num_tx_queues + page_pool_ethtool_stats_get_count(); default: return -EOPNOTSUPP; } } static void veth_get_page_pool_stats(struct net_device *dev, u64 *data) { #ifdef CONFIG_PAGE_POOL_STATS struct veth_priv *priv = netdev_priv(dev); struct page_pool_stats pp_stats = {}; int i; for (i = 0; i < dev->real_num_rx_queues; i++) { if (!priv->rq[i].page_pool) continue; page_pool_get_stats(priv->rq[i].page_pool, &pp_stats); } page_pool_ethtool_stats_get(data, &pp_stats); #endif /* CONFIG_PAGE_POOL_STATS */ } static void veth_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); int i, j, idx, pp_idx; data[0] = peer ? peer->ifindex : 0; idx = 1; for (i = 0; i < dev->real_num_rx_queues; i++) { const struct veth_rq_stats *rq_stats = &priv->rq[i].stats; const void *stats_base = (void *)&rq_stats->vs; unsigned int start; size_t offset; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_RQ_STATS_LEN; j++) { offset = veth_rq_stats_desc[j].offset; data[idx + j] = *(u64 *)(stats_base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); idx += VETH_RQ_STATS_LEN; } pp_idx = idx; if (!peer) goto page_pool_stats; rcv_priv = netdev_priv(peer); for (i = 0; i < peer->real_num_rx_queues; i++) { const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats; const void *base = (void *)&rq_stats->vs; unsigned int start, tx_idx = idx; size_t offset; tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_TQ_STATS_LEN; j++) { offset = veth_tq_stats_desc[j].offset; data[tx_idx + j] += *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); } pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; page_pool_stats: veth_get_page_pool_stats(dev, &data[pp_idx]); } static void veth_get_channels(struct net_device *dev, struct ethtool_channels *channels) { channels->tx_count = dev->real_num_tx_queues; channels->rx_count = dev->real_num_rx_queues; channels->max_tx = dev->num_tx_queues; channels->max_rx = dev->num_rx_queues; } static int veth_set_channels(struct net_device *dev, struct ethtool_channels *ch); static const struct ethtool_ops veth_ethtool_ops = { .get_drvinfo = veth_get_drvinfo, .get_link = ethtool_op_get_link, .get_strings = veth_get_strings, .get_sset_count = veth_get_sset_count, .get_ethtool_stats = veth_get_ethtool_stats, .get_link_ksettings = veth_get_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, .get_channels = veth_get_channels, .set_channels = veth_set_channels, }; /* general routines */ static bool veth_is_xdp_frame(void *ptr) { return (unsigned long)ptr & VETH_XDP_FLAG; } static struct xdp_frame *veth_ptr_to_xdp(void *ptr) { return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG); } static void *veth_xdp_to_ptr(struct xdp_frame *xdp) { return (void *)((unsigned long)xdp | VETH_XDP_FLAG); } static void veth_ptr_free(void *ptr) { if (veth_is_xdp_frame(ptr)) xdp_return_frame(veth_ptr_to_xdp(ptr)); else kfree_skb(ptr); } static void __veth_xdp_flush(struct veth_rq *rq) { /* Write ptr_ring before reading rx_notify_masked */ smp_mb(); if (!READ_ONCE(rq->rx_notify_masked) && napi_schedule_prep(&rq->xdp_napi)) { WRITE_ONCE(rq->rx_notify_masked, true); __napi_schedule(&rq->xdp_napi); } } static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb) { if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) return NETDEV_TX_BUSY; /* signal qdisc layer */ return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */ } static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, struct veth_rq *rq, bool xdp) { return __dev_forward_skb(dev, skb) ?: xdp ? veth_xdp_rx(rq, skb) : __netif_rx(skb); } /* return true if the specified skb has chances of GRO aggregation * Don't strive for accuracy, but try to avoid GRO overhead in the most * common scenarios. * When XDP is enabled, all traffic is considered eligible, as the xmit * device has TSO off. * When TSO is enabled on the xmit device, we are likely interested only * in UDP aggregation, explicitly check for that if the skb is suspected * - the sock_wfree destructor is used by UDP, ICMP and XDP sockets - * to belong to locally generated UDP traffic. */ static bool veth_skb_is_eligible_for_gro(const struct net_device *dev, const struct net_device *rcv, const struct sk_buff *skb) { return !(dev->features & NETIF_F_ALL_TSO) || (skb->destructor == sock_wfree && rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD)); } static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct veth_rq *rq = NULL; struct netdev_queue *txq; struct net_device *rcv; int length = skb->len; bool use_napi = false; int ret, rxq; rcu_read_lock(); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) { kfree_skb(skb); goto drop; } rcv_priv = netdev_priv(rcv); rxq = skb_get_queue_mapping(skb); if (rxq < rcv->real_num_rx_queues) { rq = &rcv_priv->rq[rxq]; /* The napi pointer is available when an XDP program is * attached or when GRO is enabled * Don't bother with napi/GRO if the skb can't be aggregated */ use_napi = rcu_access_pointer(rq->napi) && veth_skb_is_eligible_for_gro(dev, rcv, skb); } skb_tx_timestamp(skb); ret = veth_forward_skb(rcv, skb, rq, use_napi); switch (ret) { case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */ if (!use_napi) dev_sw_netstats_tx_add(dev, 1, length); else __veth_xdp_flush(rq); break; case NETDEV_TX_BUSY: /* If a qdisc is attached to our virtual device, returning * NETDEV_TX_BUSY is allowed. */ txq = netdev_get_tx_queue(dev, rxq); if (qdisc_txq_has_no_queue(txq)) { dev_kfree_skb_any(skb); goto drop; } /* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */ __skb_push(skb, ETH_HLEN); /* Depend on prior success packets started NAPI consumer via * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped, * paired with empty check in veth_poll(). */ netif_tx_stop_queue(txq); smp_mb__after_atomic(); if (unlikely(__ptr_ring_empty(&rq->xdp_ring))) netif_tx_wake_queue(txq); break; case NET_RX_DROP: /* same as NET_XMIT_DROP */ drop: atomic64_inc(&priv->dropped); ret = NET_XMIT_DROP; break; default: net_crit_ratelimited("%s(%s): Invalid return code(%d)", __func__, dev->name, ret); } rcu_read_unlock(); return ret; } static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; result->peer_tq_xdp_xmit_err = 0; result->xdp_packets = 0; result->xdp_tx_err = 0; result->xdp_bytes = 0; result->rx_drops = 0; for (i = 0; i < dev->num_rx_queues; i++) { u64 packets, bytes, drops, xdp_tx_err, peer_tq_xdp_xmit_err; struct veth_rq_stats *stats = &priv->rq[i].stats; unsigned int start; do { start = u64_stats_fetch_begin(&stats->syncp); peer_tq_xdp_xmit_err = stats->vs.peer_tq_xdp_xmit_err; xdp_tx_err = stats->vs.xdp_tx_err; packets = stats->vs.xdp_packets; bytes = stats->vs.xdp_bytes; drops = stats->vs.rx_drops; } while (u64_stats_fetch_retry(&stats->syncp, start)); result->peer_tq_xdp_xmit_err += peer_tq_xdp_xmit_err; result->xdp_tx_err += xdp_tx_err; result->xdp_packets += packets; result->xdp_bytes += bytes; result->rx_drops += drops; } } static void veth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; struct veth_stats rx; tot->tx_dropped = atomic64_read(&priv->dropped); dev_fetch_sw_netstats(tot, dev->tstats); veth_stats_rx(&rx, dev); tot->tx_dropped += rx.xdp_tx_err; tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err; tot->rx_bytes += rx.xdp_bytes; tot->rx_packets += rx.xdp_packets; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { struct rtnl_link_stats64 tot_peer = {}; dev_fetch_sw_netstats(&tot_peer, peer->tstats); tot->rx_bytes += tot_peer.tx_bytes; tot->rx_packets += tot_peer.tx_packets; veth_stats_rx(&rx, peer); tot->tx_dropped += rx.peer_tq_xdp_xmit_err; tot->rx_dropped += rx.xdp_tx_err; tot->tx_bytes += rx.xdp_bytes; tot->tx_packets += rx.xdp_packets; } rcu_read_unlock(); } /* fake multicast ability */ static void veth_set_multicast_list(struct net_device *dev) { } static int veth_select_rxq(struct net_device *dev) { return smp_processor_id() % dev->real_num_rx_queues; } static struct net_device *veth_peer_dev(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); /* Callers must be under RCU read side. */ return rcu_dereference(priv->peer); } static int veth_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags, bool ndo_xmit) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); int i, ret = -ENXIO, nxmit = 0; struct net_device *rcv; unsigned int max_len; struct veth_rq *rq; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; rcv_priv = netdev_priv(rcv); rq = &rcv_priv->rq[veth_select_rxq(rcv)]; /* The napi pointer is set if NAPI is enabled, which ensures that * xdp_ring is initialized on receive side and the peer device is up. */ if (!rcu_access_pointer(rq->napi)) goto out; max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN; spin_lock(&rq->xdp_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *frame = frames[i]; void *ptr = veth_xdp_to_ptr(frame); if (unlikely(xdp_get_frame_len(frame) > max_len || __ptr_ring_produce(&rq->xdp_ring, ptr))) break; nxmit++; } spin_unlock(&rq->xdp_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __veth_xdp_flush(rq); ret = nxmit; if (ndo_xmit) { u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.peer_tq_xdp_xmit += nxmit; rq->stats.vs.peer_tq_xdp_xmit_err += n - nxmit; u64_stats_update_end(&rq->stats.syncp); } out: rcu_read_unlock(); return ret; } static int veth_ndo_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { int err; err = veth_xdp_xmit(dev, n, frames, flags, true); if (err < 0) { struct veth_priv *priv = netdev_priv(dev); atomic64_add(n, &priv->dropped); } return err; } static void veth_xdp_flush_bq(struct veth_rq *rq, struct veth_xdp_tx_bq *bq) { int sent, i, err = 0, drops; sent = veth_xdp_xmit(rq->dev, bq->count, bq->q, 0, false); if (sent < 0) { err = sent; sent = 0; } for (i = sent; unlikely(i < bq->count); i++) xdp_return_frame(bq->q[i]); drops = bq->count - sent; trace_xdp_bulk_tx(rq->dev, sent, drops, err); u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_tx += sent; rq->stats.vs.xdp_tx_err += drops; u64_stats_update_end(&rq->stats.syncp); bq->count = 0; } static void veth_xdp_flush(struct veth_rq *rq, struct veth_xdp_tx_bq *bq) { struct veth_priv *rcv_priv, *priv = netdev_priv(rq->dev); struct net_device *rcv; struct veth_rq *rcv_rq; rcu_read_lock(); veth_xdp_flush_bq(rq, bq); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; rcv_priv = netdev_priv(rcv); rcv_rq = &rcv_priv->rq[veth_select_rxq(rcv)]; /* xdp_ring is initialized on receive side? */ if (unlikely(!rcu_access_pointer(rcv_rq->xdp_prog))) goto out; __veth_xdp_flush(rcv_rq); out: rcu_read_unlock(); } static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp, struct veth_xdp_tx_bq *bq) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); if (unlikely(!frame)) return -EOVERFLOW; if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE)) veth_xdp_flush_bq(rq, bq); bq->q[bq->count++] = frame; return 0; } static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, struct xdp_frame *frame, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { struct xdp_frame orig_frame; struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (likely(xdp_prog)) { struct veth_xdp_buff vxbuf; struct xdp_buff *xdp = &vxbuf.xdp; u32 act; xdp_convert_frame_to_buff(frame, xdp); xdp->rxq = &rq->xdp_rxq; vxbuf.skb = NULL; act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: if (xdp_update_frame_from_buff(xdp, frame)) goto err_xdp; break; case XDP_TX: orig_frame = *frame; xdp->rxq->mem.type = frame->mem_type; if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); frame = &orig_frame; stats->rx_drops++; goto err_xdp; } stats->xdp_tx++; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: orig_frame = *frame; xdp->rxq->mem.type = frame->mem_type; if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) { frame = &orig_frame; stats->rx_drops++; goto err_xdp; } stats->xdp_redirect++; rcu_read_unlock(); goto xdp_xmit; default: bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); fallthrough; case XDP_DROP: stats->xdp_drops++; goto err_xdp; } } rcu_read_unlock(); return frame; err_xdp: rcu_read_unlock(); xdp_return_frame(frame); xdp_xmit: return NULL; } /* frames array contains VETH_XDP_BATCH at most */ static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames, int n_xdpf, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { void *skbs[VETH_XDP_BATCH]; int i; if (unlikely(!napi_skb_cache_get_bulk(skbs, n_xdpf))) { for (i = 0; i < n_xdpf; i++) xdp_return_frame(frames[i]); stats->rx_drops += n_xdpf; return; } for (i = 0; i < n_xdpf; i++) { struct sk_buff *skb = skbs[i]; skb = __xdp_build_skb_from_frame(frames[i], skb, rq->dev); if (!skb) { xdp_return_frame(frames[i]); stats->rx_drops++; continue; } napi_gro_receive(&rq->xdp_napi, skb); } } static void veth_xdp_get(struct xdp_buff *xdp) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i; get_page(virt_to_page(xdp->data)); if (likely(!xdp_buff_has_frags(xdp))) return; for (i = 0; i < sinfo->nr_frags; i++) __skb_frag_ref(&sinfo->frags[i]); } static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, struct xdp_buff *xdp, struct sk_buff **pskb) { struct sk_buff *skb = *pskb; u32 frame_sz; if (skb_shared(skb) || skb_head_is_locked(skb) || skb_shinfo(skb)->nr_frags || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM)) goto drop; skb = *pskb; } /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = skb_end_pointer(skb) - skb->head; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq); xdp_prepare_buff(xdp, skb->head, skb_headroom(skb), skb_headlen(skb), true); if (skb_is_nonlinear(skb)) { skb_shinfo(skb)->xdp_frags_size = skb->data_len; xdp_buff_set_frags_flag(xdp); } else { xdp_buff_clear_frags_flag(xdp); } *pskb = skb; return 0; drop: consume_skb(skb); *pskb = NULL; return -ENOMEM; } static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { void *orig_data, *orig_data_end; struct bpf_prog *xdp_prog; struct veth_xdp_buff vxbuf; struct xdp_buff *xdp = &vxbuf.xdp; u32 act, metalen; int off; skb_prepare_for_gro(skb); rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { rcu_read_unlock(); goto out; } __skb_push(skb, skb->data - skb_mac_header(skb)); if (veth_convert_skb_to_xdp_buff(rq, xdp, &skb)) goto drop; vxbuf.skb = skb; orig_data = xdp->data; orig_data_end = xdp->data_end; act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: break; case XDP_TX: veth_xdp_get(xdp); consume_skb(skb); xdp->rxq->mem = rq->xdp_mem; if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); stats->rx_drops++; goto err_xdp; } stats->xdp_tx++; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: veth_xdp_get(xdp); consume_skb(skb); xdp->rxq->mem = rq->xdp_mem; if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) { stats->rx_drops++; goto err_xdp; } stats->xdp_redirect++; rcu_read_unlock(); goto xdp_xmit; default: bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); fallthrough; case XDP_DROP: stats->xdp_drops++; goto xdp_drop; } rcu_read_unlock(); /* check if bpf_xdp_adjust_head was used */ off = orig_data - xdp->data; if (off > 0) __skb_push(skb, off); else if (off < 0) __skb_pull(skb, -off); skb_reset_mac_header(skb); /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) __skb_put(skb, off); /* positive on grow, negative on shrink */ /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. */ if (xdp_buff_has_frags(xdp)) skb->data_len = skb_shinfo(skb)->xdp_frags_size; else skb->data_len = 0; skb->protocol = eth_type_trans(skb, rq->dev); metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); out: return skb; drop: stats->rx_drops++; xdp_drop: rcu_read_unlock(); kfree_skb(skb); return NULL; err_xdp: rcu_read_unlock(); xdp_return_buff(xdp); xdp_xmit: return NULL; } static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { struct veth_priv *priv = netdev_priv(rq->dev); int queue_idx = rq->xdp_rxq.queue_index; struct netdev_queue *peer_txq; struct net_device *peer_dev; int i, done = 0, n_xdpf = 0; void *xdpf[VETH_XDP_BATCH]; /* NAPI functions as RCU section */ peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); if (!ptr) break; if (veth_is_xdp_frame(ptr)) { /* ndo_xdp_xmit */ struct xdp_frame *frame = veth_ptr_to_xdp(ptr); stats->xdp_bytes += xdp_get_frame_len(frame); frame = veth_xdp_rcv_one(rq, frame, bq, stats); if (frame) { /* XDP_PASS */ xdpf[n_xdpf++] = frame; if (n_xdpf == VETH_XDP_BATCH) { veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); n_xdpf = 0; } } } else { /* ndo_start_xmit */ struct sk_buff *skb = ptr; stats->xdp_bytes += skb->len; skb = veth_xdp_rcv_skb(rq, skb, bq, stats); if (skb) { if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC)) netif_receive_skb(skb); else napi_gro_receive(&rq->xdp_napi, skb); } } done++; } if (n_xdpf) veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_redirect += stats->xdp_redirect; rq->stats.vs.xdp_bytes += stats->xdp_bytes; rq->stats.vs.xdp_drops += stats->xdp_drops; rq->stats.vs.rx_drops += stats->rx_drops; rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq))) netif_tx_wake_queue(peer_txq); return done; } static int veth_poll(struct napi_struct *napi, int budget) { struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); struct veth_stats stats = {}; struct veth_xdp_tx_bq bq; int done; bq.count = 0; xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); if (stats.xdp_redirect > 0) xdp_do_flush(); if (done < budget && napi_complete_done(napi, done)) { /* Write rx_notify_masked before reading ptr_ring */ smp_store_mb(rq->rx_notify_masked, false); if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) { if (napi_schedule_prep(&rq->xdp_napi)) { WRITE_ONCE(rq->rx_notify_masked, true); __napi_schedule(&rq->xdp_napi); } } } if (stats.xdp_tx > 0) veth_xdp_flush(rq, &bq); xdp_clear_return_frame_no_direct(); return done; } static int veth_create_page_pool(struct veth_rq *rq) { struct page_pool_params pp_params = { .order = 0, .pool_size = VETH_RING_SIZE, .nid = NUMA_NO_NODE, .dev = &rq->dev->dev, }; rq->page_pool = page_pool_create(&pp_params); if (IS_ERR(rq->page_pool)) { int err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; return err; } return 0; } static int __veth_napi_enable_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { err = veth_create_page_pool(&priv->rq[i]); if (err) goto err_page_pool; } for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL); if (err) goto err_xdp_ring; } for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; napi_enable(&rq->xdp_napi); rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi); } return 0; err_xdp_ring: for (i--; i >= start; i--) ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free); i = end; err_page_pool: for (i--; i >= start; i--) { page_pool_destroy(priv->rq[i].page_pool); priv->rq[i].page_pool = NULL; } return err; } static int __veth_napi_enable(struct net_device *dev) { return __veth_napi_enable_range(dev, 0, dev->real_num_rx_queues); } static void veth_napi_del_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rcu_assign_pointer(priv->rq[i].napi, NULL); napi_disable(&rq->xdp_napi); __netif_napi_del(&rq->xdp_napi); } synchronize_net(); for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rq->rx_notify_masked = false; ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free); } for (i = start; i < end; i++) { page_pool_destroy(priv->rq[i].page_pool); priv->rq[i].page_pool = NULL; } } static void veth_napi_del(struct net_device *dev) { veth_napi_del_range(dev, 0, dev->real_num_rx_queues); } static bool veth_gro_requested(const struct net_device *dev) { return !!(dev->wanted_features & NETIF_F_GRO); } static int veth_enable_xdp_range(struct net_device *dev, int start, int end, bool napi_already_on) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; if (!napi_already_on) netif_napi_add(dev, &rq->xdp_napi, veth_poll); err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id); if (err < 0) goto err_rxq_reg; err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) goto err_reg_mem; /* Save original mem info as it can be overwritten */ rq->xdp_mem = rq->xdp_rxq.mem; } return 0; err_reg_mem: xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq); err_rxq_reg: for (i--; i >= start; i--) { struct veth_rq *rq = &priv->rq[i]; xdp_rxq_info_unreg(&rq->xdp_rxq); if (!napi_already_on) netif_napi_del(&rq->xdp_napi); } return err; } static void veth_disable_xdp_range(struct net_device *dev, int start, int end, bool delete_napi) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rq->xdp_rxq.mem = rq->xdp_mem; xdp_rxq_info_unreg(&rq->xdp_rxq); if (delete_napi) netif_napi_del(&rq->xdp_napi); } } static int veth_enable_xdp(struct net_device *dev) { bool napi_already_on = veth_gro_requested(dev) && (dev->flags & IFF_UP); struct veth_priv *priv = netdev_priv(dev); int err, i; if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) { err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues, napi_already_on); if (err) return err; if (!napi_already_on) { err = __veth_napi_enable(dev); if (err) { veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true); return err; } } } for (i = 0; i < dev->real_num_rx_queues; i++) { rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog); rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi); } return 0; } static void veth_disable_xdp(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = 0; i < dev->real_num_rx_queues; i++) rcu_assign_pointer(priv->rq[i].xdp_prog, NULL); if (!netif_running(dev) || !veth_gro_requested(dev)) veth_napi_del(dev); veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false); } static int veth_napi_enable_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; netif_napi_add(dev, &rq->xdp_napi, veth_poll); } err = __veth_napi_enable_range(dev, start, end); if (err) { for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; netif_napi_del(&rq->xdp_napi); } return err; } return err; } static int veth_napi_enable(struct net_device *dev) { return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues); } static void veth_disable_range_safe(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); if (start >= end) return; if (priv->_xdp_prog) { veth_napi_del_range(dev, start, end); veth_disable_xdp_range(dev, start, end, false); } else if (veth_gro_requested(dev)) { veth_napi_del_range(dev, start, end); } } static int veth_enable_range_safe(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err; if (start >= end) return 0; if (priv->_xdp_prog) { /* these channels are freshly initialized, napi is not on there even * when GRO is requeste */ err = veth_enable_xdp_range(dev, start, end, false); if (err) return err; err = __veth_napi_enable_range(dev, start, end); if (err) { /* on error always delete the newly added napis */ veth_disable_xdp_range(dev, start, end, true); return err; } } else if (veth_gro_requested(dev)) { return veth_napi_enable_range(dev, start, end); } return 0; } static void veth_set_xdp_features(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; peer = rtnl_dereference(priv->peer); if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) { struct veth_priv *priv_peer = netdev_priv(peer); xdp_features_t val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_RX_SG; if (priv_peer->_xdp_prog || veth_gro_requested(peer)) val |= NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); } else { xdp_clear_features_flag(dev); } } static int veth_set_channels(struct net_device *dev, struct ethtool_channels *ch) { struct veth_priv *priv = netdev_priv(dev); unsigned int old_rx_count, new_rx_count; struct veth_priv *peer_priv; struct net_device *peer; int err; /* sanity check. Upper bounds are already enforced by the caller */ if (!ch->rx_count || !ch->tx_count) return -EINVAL; /* avoid braking XDP, if that is enabled */ peer = rtnl_dereference(priv->peer); peer_priv = peer ? netdev_priv(peer) : NULL; if (priv->_xdp_prog && peer && ch->rx_count < peer->real_num_tx_queues) return -EINVAL; if (peer && peer_priv && peer_priv->_xdp_prog && ch->tx_count > peer->real_num_rx_queues) return -EINVAL; old_rx_count = dev->real_num_rx_queues; new_rx_count = ch->rx_count; if (netif_running(dev)) { /* turn device off */ netif_carrier_off(dev); if (peer) netif_carrier_off(peer); /* try to allocate new resurces, as needed*/ err = veth_enable_range_safe(dev, old_rx_count, new_rx_count); if (err) goto out; } err = netif_set_real_num_rx_queues(dev, ch->rx_count); if (err) goto revert; err = netif_set_real_num_tx_queues(dev, ch->tx_count); if (err) { int err2 = netif_set_real_num_rx_queues(dev, old_rx_count); /* this error condition could happen only if rx and tx change * in opposite directions (e.g. tx nr raises, rx nr decreases) * and we can't do anything to fully restore the original * status */ if (err2) pr_warn("Can't restore rx queues config %d -> %d %d", new_rx_count, old_rx_count, err2); else goto revert; } out: if (netif_running(dev)) { /* note that we need to swap the arguments WRT the enable part * to identify the range we have to disable */ veth_disable_range_safe(dev, new_rx_count, old_rx_count); netif_carrier_on(dev); if (peer) netif_carrier_on(peer); } /* update XDP supported features */ veth_set_xdp_features(dev); if (peer) veth_set_xdp_features(peer); return err; revert: new_rx_count = old_rx_count; old_rx_count = ch->rx_count; goto out; } static int veth_open(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); int err; if (!peer) return -ENOTCONN; if (priv->_xdp_prog) { err = veth_enable_xdp(dev); if (err) return err; } else if (veth_gro_requested(dev)) { err = veth_napi_enable(dev); if (err) return err; } if (peer->flags & IFF_UP) { netif_carrier_on(dev); netif_carrier_on(peer); } veth_set_xdp_features(dev); return 0; } static int veth_close(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); netif_carrier_off(dev); if (peer) netif_carrier_off(peer); if (priv->_xdp_prog) veth_disable_xdp(dev); else if (veth_gro_requested(dev)) veth_napi_del(dev); return 0; } static int is_valid_veth_mtu(int mtu) { return mtu >= ETH_MIN_MTU && mtu <= ETH_MAX_MTU; } static int veth_alloc_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!priv->rq) return -ENOMEM; for (i = 0; i < dev->num_rx_queues; i++) { priv->rq[i].dev = dev; u64_stats_init(&priv->rq[i].stats.syncp); } return 0; } static void veth_free_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); kvfree(priv->rq); } static int veth_dev_init(struct net_device *dev) { netdev_lockdep_set_classes(dev); return veth_alloc_queues(dev); } static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); } #ifdef CONFIG_NET_POLL_CONTROLLER static void veth_poll_controller(struct net_device *dev) { /* veth only receives frames when its peer sends one * Since it has nothing to do with disabling irqs, we are guaranteed * never to have pending data when we poll for it so * there is nothing to do here. * * We need this though so netpoll recognizes us as an interface that * supports polling, which enables bridge devices in virt setups to * still use netconsole */ } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int veth_get_iflink(const struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; int iflink; rcu_read_lock(); peer = rcu_dereference(priv->peer); iflink = peer ? READ_ONCE(peer->ifindex) : 0; rcu_read_unlock(); return iflink; } static netdev_features_t veth_fix_features(struct net_device *dev, netdev_features_t features) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; peer = rtnl_dereference(priv->peer); if (peer) { struct veth_priv *peer_priv = netdev_priv(peer); if (peer_priv->_xdp_prog) features &= ~NETIF_F_GSO_SOFTWARE; } return features; } static int veth_set_features(struct net_device *dev, netdev_features_t features) { netdev_features_t changed = features ^ dev->features; struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; int err; if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog) return 0; peer = rtnl_dereference(priv->peer); if (features & NETIF_F_GRO) { err = veth_napi_enable(dev); if (err) return err; if (peer) xdp_features_set_redirect_target(peer, true); } else { if (peer) xdp_features_clear_redirect_target(peer); veth_napi_del(dev); } return 0; } static void veth_set_rx_headroom(struct net_device *dev, int new_hr) { struct veth_priv *peer_priv, *priv = netdev_priv(dev); struct net_device *peer; if (new_hr < 0) new_hr = 0; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (unlikely(!peer)) goto out; peer_priv = netdev_priv(peer); priv->requested_headroom = new_hr; new_hr = max(priv->requested_headroom, peer_priv->requested_headroom); dev->needed_headroom = new_hr; peer->needed_headroom = new_hr; out: rcu_read_unlock(); } static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct veth_priv *priv = netdev_priv(dev); struct bpf_prog *old_prog; struct net_device *peer; unsigned int max_mtu; int err; old_prog = priv->_xdp_prog; priv->_xdp_prog = prog; peer = rtnl_dereference(priv->peer); if (prog) { if (!peer) { NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached"); err = -ENOTCONN; goto err; } max_mtu = SKB_WITH_OVERHEAD(PAGE_SIZE - VETH_XDP_HEADROOM) - peer->hard_header_len; /* Allow increasing the max_mtu if the program supports * XDP fragments. */ if (prog->aux->xdp_has_frags) max_mtu += PAGE_SIZE * MAX_SKB_FRAGS; if (peer->mtu > max_mtu) { NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP"); err = -ERANGE; goto err; } if (dev->real_num_rx_queues < peer->real_num_tx_queues) { NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues"); err = -ENOSPC; goto err; } if (dev->flags & IFF_UP) { err = veth_enable_xdp(dev); if (err) { NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed"); goto err; } } if (!old_prog) { peer->hw_features &= ~NETIF_F_GSO_SOFTWARE; peer->max_mtu = max_mtu; } xdp_features_set_redirect_target(peer, true); } if (old_prog) { if (!prog) { if (peer && !veth_gro_requested(dev)) xdp_features_clear_redirect_target(peer); if (dev->flags & IFF_UP) veth_disable_xdp(dev); if (peer) { peer->hw_features |= NETIF_F_GSO_SOFTWARE; peer->max_mtu = ETH_MAX_MTU; } } bpf_prog_put(old_prog); } if ((!!old_prog ^ !!prog) && peer) netdev_update_features(peer); return 0; err: priv->_xdp_prog = old_prog; return err; } static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return veth_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { struct veth_xdp_buff *_ctx = (void *)ctx; if (!_ctx->skb) return -ENODATA; *timestamp = skb_hwtstamps(_ctx->skb)->hwtstamp; return 0; } static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { struct veth_xdp_buff *_ctx = (void *)ctx; struct sk_buff *skb = _ctx->skb; if (!skb) return -ENODATA; *hash = skb_get_hash(skb); *rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE; return 0; } static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { const struct veth_xdp_buff *_ctx = (void *)ctx; const struct sk_buff *skb = _ctx->skb; int err; if (!skb) return -ENODATA; err = __vlan_hwaccel_get_tag(skb, vlan_tci); if (err) return err; *vlan_proto = skb->vlan_proto; return err; } static const struct net_device_ops veth_netdev_ops = { .ndo_init = veth_dev_init, .ndo_open = veth_open, .ndo_stop = veth_close, .ndo_start_xmit = veth_xmit, .ndo_get_stats64 = veth_get_stats64, .ndo_set_rx_mode = veth_set_multicast_list, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = veth_poll_controller, #endif .ndo_get_iflink = veth_get_iflink, .ndo_fix_features = veth_fix_features, .ndo_set_features = veth_set_features, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = veth_set_rx_headroom, .ndo_bpf = veth_xdp, .ndo_xdp_xmit = veth_ndo_xdp_xmit, .ndo_get_peer_dev = veth_peer_dev, }; static const struct xdp_metadata_ops veth_xdp_metadata_ops = { .xmo_rx_timestamp = veth_xdp_rx_timestamp, .xmo_rx_hash = veth_xdp_rx_hash, .xmo_rx_vlan_tag = veth_xdp_rx_vlan_tag, }; #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \ NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_STAG_RX ) static void veth_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_PHONY_HEADROOM; dev->priv_flags |= IFF_DISABLE_NETPOLL; dev->lltx = true; dev->netdev_ops = &veth_netdev_ops; dev->xdp_metadata_ops = &veth_xdp_metadata_ops; dev->ethtool_ops = &veth_ethtool_ops; dev->features |= VETH_FEATURES; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); dev->needs_free_netdev = true; dev->priv_destructor = veth_dev_free; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->max_mtu = ETH_MAX_MTU; dev->hw_features = VETH_FEATURES; dev->hw_enc_features = VETH_FEATURES; dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; netif_set_tso_max_size(dev, GSO_MAX_SIZE); } /* * netlink interface */ static int veth_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (tb[IFLA_MTU]) { if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU]))) return -EINVAL; } return 0; } static struct rtnl_link_ops veth_link_ops; static void veth_disable_gro(struct net_device *dev) { dev->features &= ~NETIF_F_GRO; dev->wanted_features &= ~NETIF_F_GRO; netdev_update_features(dev); } static int veth_init_queues(struct net_device *dev, struct nlattr *tb[]) { int err; if (!tb[IFLA_NUM_TX_QUEUES] && dev->num_tx_queues > 1) { err = netif_set_real_num_tx_queues(dev, 1); if (err) return err; } if (!tb[IFLA_NUM_RX_QUEUES] && dev->num_rx_queues > 1) { err = netif_set_real_num_rx_queues(dev, 1); if (err) return err; } return 0; } static int veth_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *peer_net = rtnl_newlink_peer_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; struct net_device *peer; struct veth_priv *priv; char ifname[IFNAMSIZ]; struct nlattr *peer_tb[IFLA_MAX + 1], **tbp; unsigned char name_assign_type; struct ifinfomsg *ifmp; /* * create and register peer first */ if (data && data[VETH_INFO_PEER]) { struct nlattr *nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); tbp = peer_tb; } else { ifmp = NULL; tbp = tb; } if (ifmp && tbp[IFLA_IFNAME]) { nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); name_assign_type = NET_NAME_USER; } else { snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d"); name_assign_type = NET_NAME_ENUM; } peer = rtnl_create_link(peer_net, ifname, name_assign_type, &veth_link_ops, tbp, extack); if (IS_ERR(peer)) return PTR_ERR(peer); if (!ifmp || !tbp[IFLA_ADDRESS]) eth_hw_addr_random(peer); if (ifmp && (dev->ifindex != 0)) peer->ifindex = ifmp->ifi_index; netif_inherit_tso_max(peer, dev); err = register_netdevice(peer); if (err < 0) goto err_register_peer; /* keep GRO disabled by default to be consistent with the established * veth behavior */ veth_disable_gro(peer); netif_carrier_off(peer); err = rtnl_configure_link(peer, ifmp, 0, NULL); if (err < 0) goto err_configure_peer; /* * register dev last * * note, that since we've registered new device the dev's name * should be re-allocated */ if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); else snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d"); err = register_netdevice(dev); if (err < 0) goto err_register_dev; netif_carrier_off(dev); /* * tie the deviced together */ priv = netdev_priv(dev); rcu_assign_pointer(priv->peer, peer); err = veth_init_queues(dev, tb); if (err) goto err_queues; priv = netdev_priv(peer); rcu_assign_pointer(priv->peer, dev); err = veth_init_queues(peer, tb); if (err) goto err_queues; veth_disable_gro(dev); /* update XDP supported features */ veth_set_xdp_features(dev); veth_set_xdp_features(peer); return 0; err_queues: unregister_netdevice(dev); err_register_dev: /* nothing to do */ err_configure_peer: unregister_netdevice(peer); return err; err_register_peer: free_netdev(peer); return err; } static void veth_dellink(struct net_device *dev, struct list_head *head) { struct veth_priv *priv; struct net_device *peer; priv = netdev_priv(dev); peer = rtnl_dereference(priv->peer); /* Note : dellink() is called from default_device_exit_batch(), * before a rcu_synchronize() point. The devices are guaranteed * not being freed before one RCU grace period. */ RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(dev, head); if (peer) { priv = netdev_priv(peer); RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(peer, head); } } static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = { [VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) }, }; static struct net *veth_get_link_net(const struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); return peer ? dev_net(peer) : dev_net(dev); } static unsigned int veth_get_num_queues(void) { /* enforce the same queue limit as rtnl_create_link */ int queues = num_possible_cpus(); if (queues > 4096) queues = 4096; return queues; } static struct rtnl_link_ops veth_link_ops = { .kind = DRV_NAME, .priv_size = sizeof(struct veth_priv), .setup = veth_setup, .validate = veth_validate, .newlink = veth_newlink, .dellink = veth_dellink, .policy = veth_policy, .peer_type = VETH_INFO_PEER, .maxtype = VETH_INFO_MAX, .get_link_net = veth_get_link_net, .get_num_tx_queues = veth_get_num_queues, .get_num_rx_queues = veth_get_num_queues, }; /* * init/fini */ static __init int veth_init(void) { return rtnl_link_register(&veth_link_ops); } static __exit void veth_exit(void) { rtnl_link_unregister(&veth_link_ops); } module_init(veth_init); module_exit(veth_exit); MODULE_DESCRIPTION("Virtual Ethernet Tunnel"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 36 36 15 14 6 26 29 29 29 26 167 203 202 179 28 22 29 112 10 119 118 117 23 24 1 23 7 28 28 24 6 6 28 2 6 28 28 26 5 26 28 28 24 6 6 6 6 6 1 3 1 1 3 6 1 1 2 2 2 28 2 28 26 2 29 1 8 28 28 28 28 28 2 22 30 9 22 22 2 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 | // SPDX-License-Identifier: GPL-2.0-only /* * reservations.c * * Allocation reservations implementation * * Some code borrowed from fs/ext3/balloc.c and is: * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * The rest is copyright (C) 2010 Novell. All rights reserved. */ #include <linux/fs.h> #include <linux/types.h> #include <linux/highmem.h> #include <linux/bitops.h> #include <linux/list.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "ocfs2_trace.h" #ifdef CONFIG_OCFS2_DEBUG_FS #define OCFS2_CHECK_RESERVATIONS #endif static DEFINE_SPINLOCK(resv_lock); int ocfs2_dir_resv_allowed(struct ocfs2_super *osb) { return (osb->osb_resv_level && osb->osb_dir_resv_level); } static unsigned int ocfs2_resv_window_bits(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv) { struct ocfs2_super *osb = resmap->m_osb; unsigned int bits; if (!(resv->r_flags & OCFS2_RESV_FLAG_DIR)) { /* 8, 16, 32, 64, 128, 256, 512, 1024 */ bits = 4 << osb->osb_resv_level; } else { bits = 4 << osb->osb_dir_resv_level; } return bits; } static inline unsigned int ocfs2_resv_end(struct ocfs2_alloc_reservation *resv) { if (resv->r_len) return resv->r_start + resv->r_len - 1; return resv->r_start; } static inline int ocfs2_resv_empty(struct ocfs2_alloc_reservation *resv) { return !!(resv->r_len == 0); } static inline int ocfs2_resmap_disabled(struct ocfs2_reservation_map *resmap) { if (resmap->m_osb->osb_resv_level == 0) return 1; return 0; } static void ocfs2_dump_resv(struct ocfs2_reservation_map *resmap) { struct ocfs2_super *osb = resmap->m_osb; struct rb_node *node; struct ocfs2_alloc_reservation *resv; int i = 0; mlog(ML_NOTICE, "Dumping resmap for device %s. Bitmap length: %u\n", osb->dev_str, resmap->m_bitmap_len); node = rb_first(&resmap->m_reservations); while (node) { resv = rb_entry(node, struct ocfs2_alloc_reservation, r_node); mlog(ML_NOTICE, "start: %u\tend: %u\tlen: %u\tlast_start: %u" "\tlast_len: %u\n", resv->r_start, ocfs2_resv_end(resv), resv->r_len, resv->r_last_start, resv->r_last_len); node = rb_next(node); i++; } mlog(ML_NOTICE, "%d reservations found. LRU follows\n", i); i = 0; list_for_each_entry(resv, &resmap->m_lru, r_lru) { mlog(ML_NOTICE, "LRU(%d) start: %u\tend: %u\tlen: %u\t" "last_start: %u\tlast_len: %u\n", i, resv->r_start, ocfs2_resv_end(resv), resv->r_len, resv->r_last_start, resv->r_last_len); i++; } } #ifdef OCFS2_CHECK_RESERVATIONS static int ocfs2_validate_resmap_bits(struct ocfs2_reservation_map *resmap, int i, struct ocfs2_alloc_reservation *resv) { char *disk_bitmap = resmap->m_disk_bitmap; unsigned int start = resv->r_start; unsigned int end = ocfs2_resv_end(resv); while (start <= end) { if (ocfs2_test_bit(start, disk_bitmap)) { mlog(ML_ERROR, "reservation %d covers an allocated area " "starting at bit %u!\n", i, start); return 1; } start++; } return 0; } static void ocfs2_check_resmap(struct ocfs2_reservation_map *resmap) { unsigned int off = 0; int i = 0; struct rb_node *node; struct ocfs2_alloc_reservation *resv; node = rb_first(&resmap->m_reservations); while (node) { resv = rb_entry(node, struct ocfs2_alloc_reservation, r_node); if (i > 0 && resv->r_start <= off) { mlog(ML_ERROR, "reservation %d has bad start off!\n", i); goto bad; } if (resv->r_len == 0) { mlog(ML_ERROR, "reservation %d has no length!\n", i); goto bad; } if (resv->r_start > ocfs2_resv_end(resv)) { mlog(ML_ERROR, "reservation %d has invalid range!\n", i); goto bad; } if (ocfs2_resv_end(resv) >= resmap->m_bitmap_len) { mlog(ML_ERROR, "reservation %d extends past bitmap!\n", i); goto bad; } if (ocfs2_validate_resmap_bits(resmap, i, resv)) goto bad; off = ocfs2_resv_end(resv); node = rb_next(node); i++; } return; bad: ocfs2_dump_resv(resmap); BUG(); } #else static inline void ocfs2_check_resmap(struct ocfs2_reservation_map *resmap) { } #endif void ocfs2_resv_init_once(struct ocfs2_alloc_reservation *resv) { memset(resv, 0, sizeof(*resv)); INIT_LIST_HEAD(&resv->r_lru); } void ocfs2_resv_set_type(struct ocfs2_alloc_reservation *resv, unsigned int flags) { BUG_ON(flags & ~OCFS2_RESV_TYPES); resv->r_flags |= flags; } void ocfs2_resmap_init(struct ocfs2_super *osb, struct ocfs2_reservation_map *resmap) { memset(resmap, 0, sizeof(*resmap)); resmap->m_osb = osb; resmap->m_reservations = RB_ROOT; /* m_bitmap_len is initialized to zero by the above memset. */ INIT_LIST_HEAD(&resmap->m_lru); } static void ocfs2_resv_mark_lru(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv) { assert_spin_locked(&resv_lock); if (!list_empty(&resv->r_lru)) list_del_init(&resv->r_lru); list_add_tail(&resv->r_lru, &resmap->m_lru); } static void __ocfs2_resv_trunc(struct ocfs2_alloc_reservation *resv) { resv->r_len = 0; resv->r_start = 0; } static void ocfs2_resv_remove(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv) { if (resv->r_flags & OCFS2_RESV_FLAG_INUSE) { list_del_init(&resv->r_lru); rb_erase(&resv->r_node, &resmap->m_reservations); resv->r_flags &= ~OCFS2_RESV_FLAG_INUSE; } } static void __ocfs2_resv_discard(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv) { assert_spin_locked(&resv_lock); __ocfs2_resv_trunc(resv); /* * last_len and last_start no longer make sense if * we're changing the range of our allocations. */ resv->r_last_len = resv->r_last_start = 0; ocfs2_resv_remove(resmap, resv); } /* does nothing if 'resv' is null */ void ocfs2_resv_discard(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv) { if (resv) { spin_lock(&resv_lock); __ocfs2_resv_discard(resmap, resv); spin_unlock(&resv_lock); } } static void ocfs2_resmap_clear_all_resv(struct ocfs2_reservation_map *resmap) { struct rb_node *node; struct ocfs2_alloc_reservation *resv; assert_spin_locked(&resv_lock); while ((node = rb_last(&resmap->m_reservations)) != NULL) { resv = rb_entry(node, struct ocfs2_alloc_reservation, r_node); __ocfs2_resv_discard(resmap, resv); } } void ocfs2_resmap_restart(struct ocfs2_reservation_map *resmap, unsigned int clen, char *disk_bitmap) { if (ocfs2_resmap_disabled(resmap)) return; spin_lock(&resv_lock); ocfs2_resmap_clear_all_resv(resmap); resmap->m_bitmap_len = clen; resmap->m_disk_bitmap = disk_bitmap; spin_unlock(&resv_lock); } void ocfs2_resmap_uninit(struct ocfs2_reservation_map *resmap) { /* Does nothing for now. Keep this around for API symmetry */ } static void ocfs2_resv_insert(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *new) { struct rb_root *root = &resmap->m_reservations; struct rb_node *parent = NULL; struct rb_node **p = &root->rb_node; struct ocfs2_alloc_reservation *tmp; assert_spin_locked(&resv_lock); trace_ocfs2_resv_insert(new->r_start, new->r_len); while (*p) { parent = *p; tmp = rb_entry(parent, struct ocfs2_alloc_reservation, r_node); if (new->r_start < tmp->r_start) { p = &(*p)->rb_left; /* * This is a good place to check for * overlapping reservations. */ BUG_ON(ocfs2_resv_end(new) >= tmp->r_start); } else if (new->r_start > ocfs2_resv_end(tmp)) { p = &(*p)->rb_right; } else { /* This should never happen! */ mlog(ML_ERROR, "Duplicate reservation window!\n"); BUG(); } } rb_link_node(&new->r_node, parent, p); rb_insert_color(&new->r_node, root); new->r_flags |= OCFS2_RESV_FLAG_INUSE; ocfs2_resv_mark_lru(resmap, new); ocfs2_check_resmap(resmap); } /** * ocfs2_find_resv_lhs() - find the window which contains goal * @resmap: reservation map to search * @goal: which bit to search for * * If a window containing that goal is not found, we return the window * which comes before goal. Returns NULL on empty rbtree or no window * before goal. */ static struct ocfs2_alloc_reservation * ocfs2_find_resv_lhs(struct ocfs2_reservation_map *resmap, unsigned int goal) { struct ocfs2_alloc_reservation *resv = NULL; struct ocfs2_alloc_reservation *prev_resv = NULL; struct rb_node *node = resmap->m_reservations.rb_node; assert_spin_locked(&resv_lock); if (!node) return NULL; node = rb_first(&resmap->m_reservations); while (node) { resv = rb_entry(node, struct ocfs2_alloc_reservation, r_node); if (resv->r_start <= goal && ocfs2_resv_end(resv) >= goal) break; /* Check if we overshot the reservation just before goal? */ if (resv->r_start > goal) { resv = prev_resv; break; } prev_resv = resv; node = rb_next(node); } return resv; } /* * We are given a range within the bitmap, which corresponds to a gap * inside the reservations tree (search_start, search_len). The range * can be anything from the whole bitmap, to a gap between * reservations. * * The start value of *rstart is insignificant. * * This function searches the bitmap range starting at search_start * with length search_len for a set of contiguous free bits. We try * to find up to 'wanted' bits, but can sometimes return less. * * Returns the length of allocation, 0 if no free bits are found. * * *cstart and *clen will also be populated with the result. */ static int ocfs2_resmap_find_free_bits(struct ocfs2_reservation_map *resmap, unsigned int wanted, unsigned int search_start, unsigned int search_len, unsigned int *rstart, unsigned int *rlen) { void *bitmap = resmap->m_disk_bitmap; unsigned int best_start, best_len = 0; int offset, start, found; trace_ocfs2_resmap_find_free_bits_begin(search_start, search_len, wanted, resmap->m_bitmap_len); found = best_start = best_len = 0; start = search_start; while ((offset = ocfs2_find_next_zero_bit(bitmap, resmap->m_bitmap_len, start)) < resmap->m_bitmap_len) { /* Search reached end of the region */ if (offset >= (search_start + search_len)) break; if (offset == start) { /* we found a zero */ found++; /* move start to the next bit to test */ start++; } else { /* got a zero after some ones */ found = 1; start = offset + 1; } if (found > best_len) { best_len = found; best_start = start - found; } if (found >= wanted) break; } if (best_len == 0) return 0; if (best_len >= wanted) best_len = wanted; *rlen = best_len; *rstart = best_start; trace_ocfs2_resmap_find_free_bits_end(best_start, best_len); return *rlen; } static void __ocfs2_resv_find_window(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv, unsigned int goal, unsigned int wanted) { struct rb_root *root = &resmap->m_reservations; unsigned int gap_start, gap_end, gap_len; struct ocfs2_alloc_reservation *prev_resv, *next_resv; struct rb_node *prev, *next; unsigned int cstart, clen; unsigned int best_start = 0, best_len = 0; /* * Nasty cases to consider: * * - rbtree is empty * - our window should be first in all reservations * - our window should be last in all reservations * - need to make sure we don't go past end of bitmap */ trace_ocfs2_resv_find_window_begin(resv->r_start, ocfs2_resv_end(resv), goal, wanted, RB_EMPTY_ROOT(root)); assert_spin_locked(&resv_lock); if (RB_EMPTY_ROOT(root)) { /* * Easiest case - empty tree. We can just take * whatever window of free bits we want. */ clen = ocfs2_resmap_find_free_bits(resmap, wanted, goal, resmap->m_bitmap_len - goal, &cstart, &clen); /* * This should never happen - the local alloc window * will always have free bits when we're called. */ BUG_ON(goal == 0 && clen == 0); if (clen == 0) return; resv->r_start = cstart; resv->r_len = clen; ocfs2_resv_insert(resmap, resv); return; } prev_resv = ocfs2_find_resv_lhs(resmap, goal); if (prev_resv == NULL) { /* * A NULL here means that the search code couldn't * find a window that starts before goal. * * However, we can take the first window after goal, * which is also by definition, the leftmost window in * the entire tree. If we can find free bits in the * gap between goal and the LHS window, then the * reservation can safely be placed there. * * Otherwise we fall back to a linear search, checking * the gaps in between windows for a place to * allocate. */ next = rb_first(root); next_resv = rb_entry(next, struct ocfs2_alloc_reservation, r_node); /* * The search should never return such a window. (see * comment above */ if (next_resv->r_start <= goal) { mlog(ML_ERROR, "goal: %u next_resv: start %u len %u\n", goal, next_resv->r_start, next_resv->r_len); ocfs2_dump_resv(resmap); BUG(); } clen = ocfs2_resmap_find_free_bits(resmap, wanted, goal, next_resv->r_start - goal, &cstart, &clen); if (clen) { best_len = clen; best_start = cstart; if (best_len == wanted) goto out_insert; } prev_resv = next_resv; next_resv = NULL; } trace_ocfs2_resv_find_window_prev(prev_resv->r_start, ocfs2_resv_end(prev_resv)); prev = &prev_resv->r_node; /* Now we do a linear search for a window, starting at 'prev_rsv' */ while (1) { next = rb_next(prev); if (next) { next_resv = rb_entry(next, struct ocfs2_alloc_reservation, r_node); gap_start = ocfs2_resv_end(prev_resv) + 1; gap_end = next_resv->r_start - 1; gap_len = gap_end - gap_start + 1; } else { /* * We're at the rightmost edge of the * tree. See if a reservation between this * window and the end of the bitmap will work. */ gap_start = ocfs2_resv_end(prev_resv) + 1; gap_len = resmap->m_bitmap_len - gap_start; gap_end = resmap->m_bitmap_len - 1; } trace_ocfs2_resv_find_window_next(next ? next_resv->r_start: -1, next ? ocfs2_resv_end(next_resv) : -1); /* * No need to check this gap if we have already found * a larger region of free bits. */ if (gap_len <= best_len) goto next_resv; clen = ocfs2_resmap_find_free_bits(resmap, wanted, gap_start, gap_len, &cstart, &clen); if (clen == wanted) { best_len = clen; best_start = cstart; goto out_insert; } else if (clen > best_len) { best_len = clen; best_start = cstart; } next_resv: if (!next) break; prev = next; prev_resv = rb_entry(prev, struct ocfs2_alloc_reservation, r_node); } out_insert: if (best_len) { resv->r_start = best_start; resv->r_len = best_len; ocfs2_resv_insert(resmap, resv); } } static void ocfs2_cannibalize_resv(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv, unsigned int wanted) { struct ocfs2_alloc_reservation *lru_resv; int tmpwindow = !!(resv->r_flags & OCFS2_RESV_FLAG_TMP); unsigned int min_bits; if (!tmpwindow) min_bits = ocfs2_resv_window_bits(resmap, resv) >> 1; else min_bits = wanted; /* We at know the temp window will use all * of these bits */ /* * Take the first reservation off the LRU as our 'target'. We * don't try to be smart about it. There might be a case for * searching based on size but I don't have enough data to be * sure. --Mark (3/16/2010) */ lru_resv = list_first_entry(&resmap->m_lru, struct ocfs2_alloc_reservation, r_lru); trace_ocfs2_cannibalize_resv_begin(lru_resv->r_start, lru_resv->r_len, ocfs2_resv_end(lru_resv)); /* * Cannibalize (some or all) of the target reservation and * feed it to the current window. */ if (lru_resv->r_len <= min_bits) { /* * Discard completely if size is less than or equal to a * reasonable threshold - 50% of window bits for non temporary * windows. */ resv->r_start = lru_resv->r_start; resv->r_len = lru_resv->r_len; __ocfs2_resv_discard(resmap, lru_resv); } else { unsigned int shrink; if (tmpwindow) shrink = min_bits; else shrink = lru_resv->r_len / 2; lru_resv->r_len -= shrink; resv->r_start = ocfs2_resv_end(lru_resv) + 1; resv->r_len = shrink; } trace_ocfs2_cannibalize_resv_end(resv->r_start, ocfs2_resv_end(resv), resv->r_len, resv->r_last_start, resv->r_last_len); ocfs2_resv_insert(resmap, resv); } static void ocfs2_resv_find_window(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv, unsigned int wanted) { unsigned int goal = 0; BUG_ON(!ocfs2_resv_empty(resv)); /* * Begin by trying to get a window as close to the previous * one as possible. Using the most recent allocation as a * start goal makes sense. */ if (resv->r_last_len) { goal = resv->r_last_start + resv->r_last_len; if (goal >= resmap->m_bitmap_len) goal = 0; } __ocfs2_resv_find_window(resmap, resv, goal, wanted); /* Search from last alloc didn't work, try once more from beginning. */ if (ocfs2_resv_empty(resv) && goal != 0) __ocfs2_resv_find_window(resmap, resv, 0, wanted); if (ocfs2_resv_empty(resv)) { /* * Still empty? Pull oldest one off the LRU, remove it from * tree, put this one in it's place. */ ocfs2_cannibalize_resv(resmap, resv, wanted); } BUG_ON(ocfs2_resv_empty(resv)); } int ocfs2_resmap_resv_bits(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv, int *cstart, int *clen) { if (resv == NULL || ocfs2_resmap_disabled(resmap)) return -ENOSPC; spin_lock(&resv_lock); if (ocfs2_resv_empty(resv)) { /* * We don't want to over-allocate for temporary * windows. Otherwise, we run the risk of fragmenting the * allocation space. */ unsigned int wanted = ocfs2_resv_window_bits(resmap, resv); if ((resv->r_flags & OCFS2_RESV_FLAG_TMP) || wanted < *clen) wanted = *clen; /* * Try to get a window here. If it works, we must fall * through and test the bitmap . This avoids some * ping-ponging of windows due to non-reserved space * being allocation before we initialize a window for * that inode. */ ocfs2_resv_find_window(resmap, resv, wanted); trace_ocfs2_resmap_resv_bits(resv->r_start, resv->r_len); } BUG_ON(ocfs2_resv_empty(resv)); *cstart = resv->r_start; *clen = resv->r_len; spin_unlock(&resv_lock); return 0; } static void ocfs2_adjust_resv_from_alloc(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv, unsigned int start, unsigned int end) { unsigned int rhs = 0; unsigned int old_end = ocfs2_resv_end(resv); BUG_ON(start != resv->r_start || old_end < end); /* * Completely used? We can remove it then. */ if (old_end == end) { __ocfs2_resv_discard(resmap, resv); return; } rhs = old_end - end; /* * This should have been trapped above. */ BUG_ON(rhs == 0); resv->r_start = end + 1; resv->r_len = old_end - resv->r_start + 1; } void ocfs2_resmap_claimed_bits(struct ocfs2_reservation_map *resmap, struct ocfs2_alloc_reservation *resv, u32 cstart, u32 clen) { unsigned int cend = cstart + clen - 1; if (resmap == NULL || ocfs2_resmap_disabled(resmap)) return; if (resv == NULL) return; BUG_ON(cstart != resv->r_start); spin_lock(&resv_lock); trace_ocfs2_resmap_claimed_bits_begin(cstart, cend, clen, resv->r_start, ocfs2_resv_end(resv), resv->r_len, resv->r_last_start, resv->r_last_len); BUG_ON(cstart < resv->r_start); BUG_ON(cstart > ocfs2_resv_end(resv)); BUG_ON(cend > ocfs2_resv_end(resv)); ocfs2_adjust_resv_from_alloc(resmap, resv, cstart, cend); resv->r_last_start = cstart; resv->r_last_len = clen; /* * May have been discarded above from * ocfs2_adjust_resv_from_alloc(). */ if (!ocfs2_resv_empty(resv)) ocfs2_resv_mark_lru(resmap, resv); trace_ocfs2_resmap_claimed_bits_end(resv->r_start, ocfs2_resv_end(resv), resv->r_len, resv->r_last_start, resv->r_last_len); ocfs2_check_resmap(resmap); spin_unlock(&resv_lock); } |
| 2 938 2 937 936 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/srcu.h> #include <linux/interval_tree.h> struct mmu_notifier_subscriptions; struct mmu_notifier; struct mmu_notifier_range; struct mmu_interval_notifier; /** * enum mmu_notifier_event - reason for the mmu notifier callback * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that * move the range * * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like * madvise() or replacing a page by another one, ...). * * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range * ie using the vma access permission (vm_page_prot) to update the whole range * is enough no need to inspect changes to the CPU page table (mprotect() * syscall) * * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for * pages in the range so to mirror those changes the user must inspect the CPU * page table (from the end callback). * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtiness catch pages that might be written * through non CPU mappings. * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal * that the mm refcount is zero and the range is no longer accessible. * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. * * @MMU_NOTIFY_EXCLUSIVE: conversion of a page table entry to device-exclusive. * The owner is initialized to the value provided by the caller of * make_device_exclusive(), such that this caller can filter out these * events. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, MMU_NOTIFY_CLEAR, MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier * methods (the ones invoked outside the mm context) and it * should tear down all secondary mmu mappings and freeze the * secondary mmu. If this method isn't implemented you've to * be sure that nothing could possibly write to the pages * through the secondary mmu by the time the last thread with * tsk->mm == mm exits. * * As side note: the pages freed after ->release returns could * be immediately reallocated by the gart at an alias physical * address with a different cache model, so if ->release isn't * implemented because all _software_ driven memory accesses * through the secondary mmu are terminated by the time the * last thread of this mm quits, you've also to be sure that * speculative _hardware_ operations can't allocate dirty * cachelines in the cpu that could not be snooped and made * coherent with the other read and write operations happening * through the gart alias address, so leading to memory * corruption. */ void (*release)(struct mmu_notifier *subscription, struct mm_struct *mm); /* * clear_flush_young is called after the VM is * test-and-clearing the young/accessed bitflag in the * pte. This way the VM will provide proper aging to the * accesses to the page through the secondary MMUs and not * only to the ones through the Linux pte. * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ int (*clear_flush_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * clear_young is a lightweight version of clear_flush_young. Like the * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ int (*clear_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ int (*test_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address); /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the * establishment of sptes is forbidden in the range passed to * invalidate_range_begin/end for the whole duration of the * invalidate_range_begin/end critical section. * * invalidate_range_start() is called when all pages in the * range are still mapped and have at least a refcount of one. * * invalidate_range_end() is called when all pages in the * range have been unmapped and the pages have been freed by * the VM. * * The VM will remove the page table entries and potentially * the page between invalidate_range_start() and * invalidate_range_end(). If the page must not be freed * because of pending I/O or other circumstances then the * invalidate_range_start() callback (or the initial mapping * by the driver) must make sure that the refcount is kept * elevated. * * If the driver increases the refcount when the pages are * initially mapped into an address space then either * invalidate_range_start() or invalidate_range_end() may * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only * dropped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux * address space but may still be referenced by sptes until * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN if sleeping would be required. * 0 should be returned otherwise. Please note that notifiers that can * fail invalidate_range_start are not allowed to implement * invalidate_range_end, as there is no mechanism for informing the * notifier that its start failed. */ int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); void (*invalidate_range_end)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); /* * arch_invalidate_secondary_tlbs() is used to manage a non-CPU TLB * which shares page-tables with the CPU. The * invalidate_range_start()/end() callbacks should not be implemented as * invalidate_secondary_tlbs() already catches the points in time when * an external TLB needs to be flushed. * * This requires arch_invalidate_secondary_tlbs() to be called while * holding the ptl spin-lock and therefore this callback is not allowed * to sleep. * * This is called by architecture code whenever invalidating a TLB * entry. It is assumed that any secondary TLB has the same rules for * when invalidations are required. If this is not the case architecture * code will need to call this explicitly when required for secondary * TLB invalidation. */ void (*arch_invalidate_secondary_tlbs)( struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * These callbacks are used with the get/put interface to manage the * lifetime of the mmu_notifier memory. alloc_notifier() returns a new * notifier for use with the mm. * * free_notifier() is only called after the mmu_notifier has been * fully put, calls to any ops callback are prevented and no ops * callbacks are currently running. It is called from a SRCU callback * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); void (*free_notifier)(struct mmu_notifier *subscription); }; /* * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { struct hlist_node hlist; const struct mmu_notifier_ops *ops; struct mm_struct *mm; struct rcu_head rcu; unsigned int users; }; /** * struct mmu_interval_notifier_ops * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); }; struct mmu_interval_notifier { struct interval_tree_node interval_tree; const struct mmu_interval_notifier_ops *ops; struct mm_struct *mm; struct hlist_node deferred_item; unsigned long invalidate_seq; }; #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif struct mmu_notifier_range { struct mm_struct *mm; unsigned long start; unsigned long end; unsigned flags; enum mmu_notifier_event event; void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->notifier_subscriptions); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm); static inline struct mmu_notifier * mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); void mmu_notifier_synchronize(void); extern int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub); int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence * @interval_sub - The subscription passed to invalidate * @cur_seq - The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call * mmu_interval_read_retry(). It updates the sequence number for later use by * mmu_interval_read_retry(). The provided cur_seq will always be odd. * * If the caller does not call mmu_interval_read_begin() or * mmu_interval_read_retry() then this call is not required. */ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, unsigned long cur_seq) { WRITE_ONCE(interval_sub->invalidate_seq, cur_seq); } /** * mmu_interval_read_retry - End a read side critical section against a VA range * interval_sub: The subscription * seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). * * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * * Returns true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { return interval_sub->invalidate_seq != seq; } /** * mmu_interval_check_retry - Test if a collision has occurred * interval_sub: The subscription * seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() * and mmu_interval_read_retry(). A return of true indicates an invalidation * has collided with this critical region and a future * mmu_interval_read_retry() will return true. * * False is not reliable and only suggests a collision may not have * occurred. It can be called many times and does not have to hold the user * provided lock. * * This call can be used as part of loops and other expensive operations to * expedite a retry. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ return READ_ONCE(interval_sub->invalidate_seq) != seq; } extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r); extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); } static inline void mmu_notifier_release(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_release(mm); } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_flush_young(mm, start, end); return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_young(mm, start, end); return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { if (mm_has_notifiers(mm)) return __mmu_notifier_test_young(mm, address); return 0; } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { might_sleep(); lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); } /* * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it * can return an error if a notifier can't proceed without blocking, in which * case you're not allowed to modify PTEs in the specified range. * * This is mainly intended for OOM handling. */ static inline int __must_check mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; ret = __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); return ret; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range); } static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) __mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { mm->notifier_subscriptions = NULL; } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_subscriptions_destroy(mm); } static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, struct mm_struct *mm, unsigned long start, unsigned long end) { range->event = event; range->mm = mm; range->start = start; range->end = end; range->flags = flags; } static inline void mmu_notifier_range_init_owner( struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned int flags, struct mm_struct *mm, unsigned long start, unsigned long end, void *owner) { mmu_notifier_range_init(range, event, flags, mm, start, end); range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PAGE_SIZE); \ __young; \ }) #define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PMD_SIZE); \ __young; \ }) #define ptep_clear_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PAGE_SIZE); \ __young; \ }) #define pmdp_clear_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PMD_SIZE); \ __young; \ }) #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { unsigned long start; unsigned long end; }; static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, unsigned long start, unsigned long end) { range->start = start; range->end = end; } #define mmu_notifier_range_init(range,event,flags,mm,start,end) \ _mmu_notifier_range_init(range, start, end) #define mmu_notifier_range_init_owner(range, event, flags, mm, start, \ end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return true; } static inline int mm_has_notifiers(struct mm_struct *mm) { return 0; } static inline void mmu_notifier_release(struct mm_struct *mm) { } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { return 0; } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { return 0; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { } #define mmu_notifier_range_update_to_read_only(r) false #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young #define pmdp_clear_young_notify pmdp_test_and_clear_young static inline void mmu_notifier_synchronize(void) { } #endif /* CONFIG_MMU_NOTIFIER */ #endif /* _LINUX_MMU_NOTIFIER_H */ |
| 2510 386 105 106 3 16 16 16 3 13 4 4 925 6 916 1741 1745 1735 1710 33 890 33 4 27 13 919 4 916 914 917 919 919 918 918 917 4 905 13 13 905 920 918 1 1 921 919 917 921 919 919 918 920 919 921 918 921 921 13 907 919 918 919 1352 1351 1352 471 933 466 6 946 1351 1349 1352 491 484 929 23 906 929 918 18 928 14 920 16 904 921 905 17 918 921 921 903 921 919 4510 4511 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/dcache.h> #include <linux/fs.h> #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/srcu.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" /* * Clear all of the marks on an inode when it is being evicted from core */ void __fsnotify_inode_delete(struct inode *inode) { fsnotify_clear_marks_by_inode(inode); } EXPORT_SYMBOL_GPL(__fsnotify_inode_delete); void __fsnotify_vfsmount_delete(struct vfsmount *mnt) { fsnotify_clear_marks_by_mount(mnt); } void __fsnotify_mntns_delete(struct mnt_namespace *mntns) { fsnotify_clear_marks_by_mntns(mntns); } /** * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @sb: superblock being unmounted. * * Called during unmount with no locks held, so needs to be safe against * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block. */ static void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We cannot __iget() an inode in state I_FREEING, * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); continue; } /* * If i_count is zero, the inode cannot have any watches and * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. * However, we should have been called /after/ evict_inodes * removed all zero refcount inodes, in any case. Test to * be sure. */ if (!icount_read(inode)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); /* for each watch, send FS_UNMOUNT and then remove it */ fsnotify_inode(inode, FS_UNMOUNT); fsnotify_inode_delete(inode); iput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); } void fsnotify_sb_delete(struct super_block *sb) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return; fsnotify_unmount_inodes(sb); fsnotify_clear_marks_by_sb(sb); /* Wait for outstanding object references from connectors */ wait_var_event(fsnotify_sb_watched_objects(sb), !atomic_long_read(fsnotify_sb_watched_objects(sb))); WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT)); WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_PRE_CONTENT)); } void fsnotify_sb_free(struct super_block *sb) { kfree(sb->s_fsnotify_info); } /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void fsnotify_set_children_dentry_flags(struct inode *inode) { struct dentry *alias; if (!S_ISDIR(inode->i_mode)) return; spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); hlist_for_each_entry(child, &alias->d_children, d_sib) { if (!child->d_inode) continue; spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } /* * Lazily clear false positive PARENT_WATCHED flag for child whose parent had * stopped watching children. */ static void fsnotify_clear_child_dentry_flag(struct inode *pinode, struct dentry *dentry) { spin_lock(&dentry->d_lock); /* * d_lock is a sufficient barrier to prevent observing a non-watched * parent state from before the fsnotify_set_children_dentry_flags() * or fsnotify_update_flags() call that had set PARENT_WATCHED. */ if (!fsnotify_inode_watches_children(pinode)) dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&dentry->d_lock); } /* Are inode/sb/mount interested in parent and name info with this event? */ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, __u32 mask) { __u32 marks_mask = 0; /* We only send parent/name to inode/sb/mount for events on non-dir */ if (mask & FS_ISDIR) return false; /* * All events that are possible on child can also may be reported with * parent/name info to inode/sb/mount. Otherwise, a watching parent * could result in events reported with unexpected name info to sb/mount. */ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ marks_mask |= fsnotify_parent_needed_mask( READ_ONCE(inode->i_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask( READ_ONCE(inode->i_sb->s_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask(mnt_mask); /* Did they subscribe for this event with parent/name info? */ return mask & marks_mask; } /* Are there any inode/mount/sb objects that watch for these events? */ static inline __u32 fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask | READ_ONCE(inode->i_sb->s_fsnotify_mask); return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } /* Report pre-content event with optional range info */ int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count) { struct file_range range; /* Report page aligned range only when pos is known */ if (!ppos) return fsnotify_path(path, FS_PRE_ACCESS); range.path = path; range.pos = PAGE_ALIGN_DOWN(*ppos); range.count = PAGE_ALIGN(*ppos + count) - range.pos; return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range, FSNOTIFY_EVENT_FILE_RANGE); } /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with * parent and name info. * * Notify only the child without name info if parent is not watching and * inode/sb/mount are not interested in events with parent and name info. */ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); __u32 mnt_mask = path ? READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; struct qstr *file_name = NULL; int ret = 0; /* Optimize the likely case of nobody watching this path */ if (likely(!parent_watched && !fsnotify_object_watched(inode, mnt_mask, mask))) return 0; parent = NULL; parent_needed = fsnotify_event_needs_parent(inode, mnt_mask, mask); if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ parent = dget_parent(dentry); p_inode = parent->d_inode; p_mask = fsnotify_inode_watches_children(p_inode); if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry); /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. */ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; if (parent_interested) mask |= FS_EVENT_ON_CHILD; } notify: ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0); if (file_name) release_dentry_name_snapshot(&name); dput(parent); return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); static int fsnotify_handle_inode_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct inode *inode = fsnotify_data_inode(data, data_type); const struct fsnotify_ops *ops = group->ops; if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; if (WARN_ON_ONCE(!inode && !dir)) return 0; if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; /* Check interest of this mark in case event was sent with two marks */ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS)) return 0; return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie); } static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info); int ret; if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) || WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; /* * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. * The only ->handle_inode_event() backend that supports FS_RENAME is * dnotify, where it means file was renamed within same parent. */ if (mask & FS_RENAME) { struct dentry *moved = fsnotify_data_dentry(data, data_type); if (dir != moved->d_parent->d_inode) return 0; } if (parent_mark) { ret = fsnotify_handle_inode_event(group, parent_mark, mask, data, data_type, dir, name, 0); if (ret) return ret; } if (!inode_mark) return 0; /* * Some events can be sent on both parent dir and child marks (e.g. * FS_ATTRIB). If both parent dir and child are watching, report the * event once to parent dir with name (if interested) and once to child * without name (if interested). * * In any case regardless whether the parent is watching or not, the * child watcher is expecting an event without the FS_EVENT_ON_CHILD * flag. The file name is expected if and only if this is a directory * event. */ mask &= ~FS_EVENT_ON_CHILD; if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) { dir = NULL; name = NULL; } return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type, dir, name, cookie); } static int send_to_group(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignore_mask = 0; bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { fsnotify_foreach_iter_mark_type(iter_info, mark, type) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mark->ignore_mask = 0; } } /* Are any of the group marks interested in this event? */ fsnotify_foreach_iter_mark_type(iter_info, mark, type) { group = mark->group; marks_mask |= mark->mask; marks_ignore_mask |= fsnotify_effective_ignore_mask(mark, is_dir, type); } pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { return group->ops->handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } return fsnotify_handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (conn) node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; if (mark) node = srcu_dereference(mark->obj_list.next, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } /* * iter_info is a multi head priority queue of marks. * Pick a subset of marks from queue heads, all with the same group * and set the report_mask to a subset of the selected marks. * Returns false if there are no more groups to iterate. */ static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; struct fsnotify_mark *mark; int type; /* Choose max prio group among groups of all queue heads */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) max_prio_group = mark->group; } if (!max_prio_group) return false; /* Set the report mask for marks from same group as max prio group */ iter_info->current_group = max_prio_group; iter_info->report_mask = 0; fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) { /* * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode * is watching children and interested in this event, * which is an event possible on child. * But is *this mark* watching children? */ if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD) && !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) continue; fsnotify_iter_set_report_type(iter_info, type); } } return true; } /* * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *mark; int type; /* * We cannot use fsnotify_foreach_iter_mark_type() here because we * may need to advance a mark of type X that belongs to current_group * but was not selected for reporting. */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } } /* * fsnotify - This is the main call to fsnotify. * * The VFS calls into hook specific functions in linux/fsnotify.h. * Those functions then in turn call here. Here will call out to all of the * registered fsnotify_group. Those groups can then use the notification event * in whatever means they feel necessary. * * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - * If @dir and @inode are both non-NULL, event may be * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL; struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; __u32 test_mask, marks_mask = 0; if (path) mnt = real_mount(path->mnt); if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ if (mask & FS_RENAME) { moved = fsnotify_data_dentry(data, data_type); inode2 = moved->d_parent->d_inode; inode2_type = FSNOTIFY_ITER_TYPE_INODE2; } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ inode2 = dir; inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. * However, if we do not walk the lists, we do not have to do * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ if ((!sbinfo || !sbinfo->sb_marks) && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && (!inode2 || !inode2->i_fsnotify_marks) && (!mnt_data || !mnt_data->ns->n_fsnotify_marks)) return 0; if (sb) marks_mask |= READ_ONCE(sb->s_fsnotify_mask); if (mnt) marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask); if (inode) marks_mask |= READ_ONCE(inode->i_fsnotify_mask); if (inode2) marks_mask |= READ_ONCE(inode2->i_fsnotify_mask); if (mnt_data) marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask); /* * If this is a modify event we may need to clear some ignore masks. * In that case, the object with ignore masks will have the FS_MODIFY * event in its mask. * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); if (sbinfo) { iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sbinfo->sb_marks); } if (mnt) { iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (inode2) { iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } if (mnt_data) { iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] = fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks); } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark * ignore masks are properly reflected for mount/sb mark notifications. * That's why this traversal is so complicated... */ while (fsnotify_iter_select_report_types(&iter_info)) { ret = send_to_group(mask, data, data_type, dir, file_name, cookie, &iter_info); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; fsnotify_iter_next(&iter_info); } ret = 0; out: srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx); return ret; } EXPORT_SYMBOL_GPL(fsnotify); #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * At open time we check fsnotify_sb_has_priority_watchers(), call the open perm * hook and set the FMODE_NONOTIFY_ mode bits accordignly. * Later, fsnotify permission hooks do not check if there are permission event * watches, but that there were permission event watches at open time. */ int fsnotify_open_perm_and_set_mode(struct file *file) { struct dentry *dentry = file->f_path.dentry, *parent; struct super_block *sb = dentry->d_sb; __u32 mnt_mask, p_mask = 0; /* Is it a file opened by fanotify? */ if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; /* * Permission events is a super set of pre-content events, so if there * are no permission event watchers, there are also no pre-content event * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit. */ if (likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT))) { file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return 0; } /* * OK, there are some permission event watchers. Check if anybody is * watching for permission events on *this* file. */ mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); p_mask = fsnotify_object_watched(d_inode(dentry), mnt_mask, ALL_FSNOTIFY_PERM_EVENTS); if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { parent = dget_parent(dentry); p_mask |= fsnotify_inode_watches_children(d_inode(parent)); dput(parent); } /* * Legacy FAN_ACCESS_PERM events have very high performance overhead, * so unlikely to be used in the wild. If they are used there will be * no optimizations at all. */ if (unlikely(p_mask & FS_ACCESS_PERM)) { /* Enable all permission and pre-content events */ file_set_fsnotify_mode(file, 0); goto open_perm; } /* * Pre-content events are only supported on regular files. * If there are pre-content event watchers and no permission access * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. * That is the common case with HSM service. */ if (d_is_reg(dentry) && (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)) { file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM); goto open_perm; } /* Nobody watching permission and pre-content events on this file */ file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); open_perm: /* * Send open perm events depending on object masks and regardless of * FMODE_NONOTIFY_PERM. */ if (file->f_flags & __FMODE_EXEC && p_mask & FS_OPEN_EXEC_PERM) { int ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM); if (ret) return ret; } if (p_mask & FS_OPEN_PERM) return fsnotify_path(&file->f_path, FS_OPEN_PERM); return 0; } #endif void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) { struct fsnotify_mnt data = { .ns = ns, .mnt_id = real_mount(mnt)->mnt_id_unique, }; if (WARN_ON_ONCE(!ns)) return; /* * This is an optimization as well as making sure fsnotify_init() has * been called. */ if (!ns->n_fsnotify_marks) return; fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0); } static __init int fsnotify_init(void) { int ret; BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) panic("initializing fsnotify_mark_srcu"); fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector, SLAB_PANIC); return 0; } core_initcall(fsnotify_init); |
| 573 577 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * property.c - Unified device property interface. * * Copyright (C) 2014, Intel Corporation * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com> * Mika Westerberg <mika.westerberg@linux.intel.com> */ #include <linux/device.h> #include <linux/err.h> #include <linux/export.h> #include <linux/kconfig.h> #include <linux/of.h> #include <linux/property.h> #include <linux/phy.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> struct fwnode_handle *__dev_fwnode(struct device *dev) { return IS_ENABLED(CONFIG_OF) && dev->of_node ? of_fwnode_handle(dev->of_node) : dev->fwnode; } EXPORT_SYMBOL_GPL(__dev_fwnode); const struct fwnode_handle *__dev_fwnode_const(const struct device *dev) { return IS_ENABLED(CONFIG_OF) && dev->of_node ? of_fwnode_handle(dev->of_node) : dev->fwnode; } EXPORT_SYMBOL_GPL(__dev_fwnode_const); /** * device_property_present - check if a property of a device is present * @dev: Device whose property is being checked * @propname: Name of the property * * Check if property @propname is present in the device firmware description. * * Return: true if property @propname is present. Otherwise, returns false. */ bool device_property_present(const struct device *dev, const char *propname) { return fwnode_property_present(dev_fwnode(dev), propname); } EXPORT_SYMBOL_GPL(device_property_present); /** * fwnode_property_present - check if a property of a firmware node is present * @fwnode: Firmware node whose property to check * @propname: Name of the property * * Return: true if property @propname is present. Otherwise, returns false. */ bool fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { bool ret; if (IS_ERR_OR_NULL(fwnode)) return false; ret = fwnode_call_bool_op(fwnode, property_present, propname); if (ret) return ret; return fwnode_call_bool_op(fwnode->secondary, property_present, propname); } EXPORT_SYMBOL_GPL(fwnode_property_present); /** * device_property_read_bool - Return the value for a boolean property of a device * @dev: Device whose property is being checked * @propname: Name of the property * * Return if property @propname is true or false in the device firmware description. * * Return: true if property @propname is present. Otherwise, returns false. */ bool device_property_read_bool(const struct device *dev, const char *propname) { return fwnode_property_read_bool(dev_fwnode(dev), propname); } EXPORT_SYMBOL_GPL(device_property_read_bool); /** * fwnode_property_read_bool - Return the value for a boolean property of a firmware node * @fwnode: Firmware node whose property to check * @propname: Name of the property * * Return if property @propname is true or false in the firmware description. */ bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, const char *propname) { bool ret; if (IS_ERR_OR_NULL(fwnode)) return false; ret = fwnode_call_bool_op(fwnode, property_read_bool, propname); if (ret) return ret; return fwnode_call_bool_op(fwnode->secondary, property_read_bool, propname); } EXPORT_SYMBOL_GPL(fwnode_property_read_bool); /** * device_property_read_u8_array - return a u8 array property of a device * @dev: Device to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Function reads an array of u8 properties with @propname from the device * firmware description and stores them to @val if found. * * It's recommended to call device_property_count_u8() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval) { return fwnode_property_read_u8_array(dev_fwnode(dev), propname, val, nval); } EXPORT_SYMBOL_GPL(device_property_read_u8_array); /** * device_property_read_u16_array - return a u16 array property of a device * @dev: Device to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Function reads an array of u16 properties with @propname from the device * firmware description and stores them to @val if found. * * It's recommended to call device_property_count_u16() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval) { return fwnode_property_read_u16_array(dev_fwnode(dev), propname, val, nval); } EXPORT_SYMBOL_GPL(device_property_read_u16_array); /** * device_property_read_u32_array - return a u32 array property of a device * @dev: Device to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Function reads an array of u32 properties with @propname from the device * firmware description and stores them to @val if found. * * It's recommended to call device_property_count_u32() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval) { return fwnode_property_read_u32_array(dev_fwnode(dev), propname, val, nval); } EXPORT_SYMBOL_GPL(device_property_read_u32_array); /** * device_property_read_u64_array - return a u64 array property of a device * @dev: Device to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Function reads an array of u64 properties with @propname from the device * firmware description and stores them to @val if found. * * It's recommended to call device_property_count_u64() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval) { return fwnode_property_read_u64_array(dev_fwnode(dev), propname, val, nval); } EXPORT_SYMBOL_GPL(device_property_read_u64_array); /** * device_property_read_string_array - return a string array property of device * @dev: Device to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Function reads an array of string properties with @propname from the device * firmware description and stores them to @val if found. * * It's recommended to call device_property_string_array_count() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values read on success if @val is non-NULL, * number of values available on success if @val is NULL, * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO or %-EILSEQ if the property is not an array of strings, * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval) { return fwnode_property_read_string_array(dev_fwnode(dev), propname, val, nval); } EXPORT_SYMBOL_GPL(device_property_read_string_array); /** * device_property_read_string - return a string property of a device * @dev: Device to get the property of * @propname: Name of the property * @val: The value is stored here * * Function reads property @propname from the device firmware description and * stores the value into @val if found. The value is checked to be a string. * * Return: %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO or %-EILSEQ if the property type is not a string. * %-ENXIO if no suitable firmware interface is present. */ int device_property_read_string(const struct device *dev, const char *propname, const char **val) { return fwnode_property_read_string(dev_fwnode(dev), propname, val); } EXPORT_SYMBOL_GPL(device_property_read_string); /** * device_property_match_string - find a string in an array and return index * @dev: Device to get the property of * @propname: Name of the property holding the array * @string: String to look for * * Find a given string in a string array and if it is found return the * index back. * * Return: index, starting from %0, if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of strings, * %-ENXIO if no suitable firmware interface is present. */ int device_property_match_string(const struct device *dev, const char *propname, const char *string) { return fwnode_property_match_string(dev_fwnode(dev), propname, string); } EXPORT_SYMBOL_GPL(device_property_match_string); static int fwnode_property_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { int ret; if (IS_ERR_OR_NULL(fwnode)) return -EINVAL; ret = fwnode_call_int_op(fwnode, property_read_int_array, propname, elem_size, val, nval); if (ret != -EINVAL) return ret; return fwnode_call_int_op(fwnode->secondary, property_read_int_array, propname, elem_size, val, nval); } /** * fwnode_property_read_u8_array - return a u8 array property of firmware node * @fwnode: Firmware node to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Read an array of u8 properties with @propname from @fwnode and stores them to * @val if found. * * It's recommended to call fwnode_property_count_u8() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_read_u8_array(const struct fwnode_handle *fwnode, const char *propname, u8 *val, size_t nval) { return fwnode_property_read_int_array(fwnode, propname, sizeof(u8), val, nval); } EXPORT_SYMBOL_GPL(fwnode_property_read_u8_array); /** * fwnode_property_read_u16_array - return a u16 array property of firmware node * @fwnode: Firmware node to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Read an array of u16 properties with @propname from @fwnode and store them to * @val if found. * * It's recommended to call fwnode_property_count_u16() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_read_u16_array(const struct fwnode_handle *fwnode, const char *propname, u16 *val, size_t nval) { return fwnode_property_read_int_array(fwnode, propname, sizeof(u16), val, nval); } EXPORT_SYMBOL_GPL(fwnode_property_read_u16_array); /** * fwnode_property_read_u32_array - return a u32 array property of firmware node * @fwnode: Firmware node to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Read an array of u32 properties with @propname from @fwnode store them to * @val if found. * * It's recommended to call fwnode_property_count_u32() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_read_u32_array(const struct fwnode_handle *fwnode, const char *propname, u32 *val, size_t nval) { return fwnode_property_read_int_array(fwnode, propname, sizeof(u32), val, nval); } EXPORT_SYMBOL_GPL(fwnode_property_read_u32_array); /** * fwnode_property_read_u64_array - return a u64 array property firmware node * @fwnode: Firmware node to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Read an array of u64 properties with @propname from @fwnode and store them to * @val if found. * * It's recommended to call fwnode_property_count_u64() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of numbers, * %-EOVERFLOW if the size of the property is not as expected, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_read_u64_array(const struct fwnode_handle *fwnode, const char *propname, u64 *val, size_t nval) { return fwnode_property_read_int_array(fwnode, propname, sizeof(u64), val, nval); } EXPORT_SYMBOL_GPL(fwnode_property_read_u64_array); /** * fwnode_property_read_string_array - return string array property of a node * @fwnode: Firmware node to get the property of * @propname: Name of the property * @val: The values are stored here or %NULL to return the number of values * @nval: Size of the @val array * * Read an string list property @propname from the given firmware node and store * them to @val if found. * * It's recommended to call fwnode_property_string_array_count() instead of calling * this function with @val equals %NULL and @nval equals 0. * * Return: number of values read on success if @val is non-NULL, * number of values available on success if @val is NULL, * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO or %-EILSEQ if the property is not an array of strings, * %-EOVERFLOW if the size of the property is not as expected, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { int ret; if (IS_ERR_OR_NULL(fwnode)) return -EINVAL; ret = fwnode_call_int_op(fwnode, property_read_string_array, propname, val, nval); if (ret != -EINVAL) return ret; return fwnode_call_int_op(fwnode->secondary, property_read_string_array, propname, val, nval); } EXPORT_SYMBOL_GPL(fwnode_property_read_string_array); /** * fwnode_property_read_string - return a string property of a firmware node * @fwnode: Firmware node to get the property of * @propname: Name of the property * @val: The value is stored here * * Read property @propname from the given firmware node and store the value into * @val if found. The value is checked to be a string. * * Return: %0 if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO or %-EILSEQ if the property is not a string, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_read_string(const struct fwnode_handle *fwnode, const char *propname, const char **val) { int ret = fwnode_property_read_string_array(fwnode, propname, val, 1); return ret < 0 ? ret : 0; } EXPORT_SYMBOL_GPL(fwnode_property_read_string); /** * fwnode_property_match_string - find a string in an array and return index * @fwnode: Firmware node to get the property of * @propname: Name of the property holding the array * @string: String to look for * * Find a given string in a string array and if it is found return the * index back. * * Return: index, starting from %0, if the property was found (success), * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO if the property is not an array of strings, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_match_string(const struct fwnode_handle *fwnode, const char *propname, const char *string) { const char **values; int nval, ret; nval = fwnode_property_string_array_count(fwnode, propname); if (nval < 0) return nval; if (nval == 0) return -ENODATA; values = kcalloc(nval, sizeof(*values), GFP_KERNEL); if (!values) return -ENOMEM; ret = fwnode_property_read_string_array(fwnode, propname, values, nval); if (ret < 0) goto out_free; ret = match_string(values, nval, string); if (ret < 0) ret = -ENODATA; out_free: kfree(values); return ret; } EXPORT_SYMBOL_GPL(fwnode_property_match_string); /** * fwnode_property_match_property_string - find a property string value in an array and return index * @fwnode: Firmware node to get the property of * @propname: Name of the property holding the string value * @array: String array to search in * @n: Size of the @array * * Find a property string value in a given @array and if it is found return * the index back. * * Return: index, starting from %0, if the string value was found in the @array (success), * %-ENOENT when the string value was not found in the @array, * %-EINVAL if given arguments are not valid, * %-ENODATA if the property does not have a value, * %-EPROTO or %-EILSEQ if the property is not a string, * %-ENXIO if no suitable firmware interface is present. */ int fwnode_property_match_property_string(const struct fwnode_handle *fwnode, const char *propname, const char * const *array, size_t n) { const char *string; int ret; ret = fwnode_property_read_string(fwnode, propname, &string); if (ret) return ret; ret = match_string(array, n, string); if (ret < 0) ret = -ENOENT; return ret; } EXPORT_SYMBOL_GPL(fwnode_property_match_property_string); /** * fwnode_property_get_reference_args() - Find a reference with arguments * @fwnode: Firmware node where to look for the reference * @prop: The name of the property * @nargs_prop: The name of the property telling the number of * arguments in the referred node. NULL if @nargs is known, * otherwise @nargs is ignored. * @nargs: Number of arguments. Ignored if @nargs_prop is non-NULL. * @index: Index of the reference, from zero onwards. * @args: Result structure with reference and integer arguments. * May be NULL. * * Obtain a reference based on a named property in an fwnode, with * integer arguments. * * The caller is responsible for calling fwnode_handle_put() on the returned * @args->fwnode pointer. * * Return: %0 on success * %-ENOENT when the index is out of bounds, the index has an empty * reference or the property was not found * %-EINVAL on parse error */ int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args) { int ret; if (IS_ERR_OR_NULL(fwnode)) return -ENOENT; ret = fwnode_call_int_op(fwnode, get_reference_args, prop, nargs_prop, nargs, index, args); if (ret == 0) return ret; if (IS_ERR_OR_NULL(fwnode->secondary)) return ret; return fwnode_call_int_op(fwnode->secondary, get_reference_args, prop, nargs_prop, nargs, index, args); } EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args); /** * fwnode_find_reference - Find named reference to a fwnode_handle * @fwnode: Firmware node where to look for the reference * @name: The name of the reference * @index: Index of the reference * * @index can be used when the named reference holds a table of references. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. * * Return: a pointer to the reference fwnode, when found. Otherwise, * returns an error pointer. */ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *name, unsigned int index) { struct fwnode_reference_args args; int ret; ret = fwnode_property_get_reference_args(fwnode, name, NULL, 0, index, &args); return ret ? ERR_PTR(ret) : args.fwnode; } EXPORT_SYMBOL_GPL(fwnode_find_reference); /** * fwnode_get_name - Return the name of a node * @fwnode: The firmware node * * Return: a pointer to the node name, or %NULL. */ const char *fwnode_get_name(const struct fwnode_handle *fwnode) { return fwnode_call_ptr_op(fwnode, get_name); } EXPORT_SYMBOL_GPL(fwnode_get_name); /** * fwnode_get_name_prefix - Return the prefix of node for printing purposes * @fwnode: The firmware node * * Return: the prefix of a node, intended to be printed right before the node. * The prefix works also as a separator between the nodes. */ const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode) { return fwnode_call_ptr_op(fwnode, get_name_prefix); } /** * fwnode_name_eq - Return true if node name is equal * @fwnode: The firmware node * @name: The name to which to compare the node name * * Compare the name provided as an argument to the name of the node, stopping * the comparison at either NUL or '@' character, whichever comes first. This * function is generally used for comparing node names while ignoring the * possible unit address of the node. * * Return: true if the node name matches with the name provided in the @name * argument, false otherwise. */ bool fwnode_name_eq(const struct fwnode_handle *fwnode, const char *name) { const char *node_name; ptrdiff_t len; node_name = fwnode_get_name(fwnode); if (!node_name) return false; len = strchrnul(node_name, '@') - node_name; return str_has_prefix(node_name, name) == len; } EXPORT_SYMBOL_GPL(fwnode_name_eq); /** * fwnode_get_parent - Return parent firwmare node * @fwnode: Firmware whose parent is retrieved * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. * * Return: parent firmware node of the given node if possible or %NULL if no * parent was available. */ struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode) { return fwnode_call_ptr_op(fwnode, get_parent); } EXPORT_SYMBOL_GPL(fwnode_get_parent); /** * fwnode_get_next_parent - Iterate to the node's parent * @fwnode: Firmware whose parent is retrieved * * This is like fwnode_get_parent() except that it drops the refcount * on the passed node, making it suitable for iterating through a * node's parents. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. Note that this function also puts a reference to @fwnode * unconditionally. * * Return: parent firmware node of the given node if possible or %NULL if no * parent was available. */ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode) { struct fwnode_handle *parent = fwnode_get_parent(fwnode); fwnode_handle_put(fwnode); return parent; } EXPORT_SYMBOL_GPL(fwnode_get_next_parent); /** * fwnode_count_parents - Return the number of parents a node has * @fwnode: The node the parents of which are to be counted * * Return: the number of parents a node has. */ unsigned int fwnode_count_parents(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; unsigned int count = 0; fwnode_for_each_parent_node(fwnode, parent) count++; return count; } EXPORT_SYMBOL_GPL(fwnode_count_parents); /** * fwnode_get_nth_parent - Return an nth parent of a node * @fwnode: The node the parent of which is requested * @depth: Distance of the parent from the node * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. * * Return: the nth parent of a node. If there is no parent at the requested * @depth, %NULL is returned. If @depth is 0, the functionality is equivalent to * fwnode_handle_get(). For @depth == 1, it is fwnode_get_parent() and so on. */ struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode, unsigned int depth) { struct fwnode_handle *parent; if (depth == 0) return fwnode_handle_get(fwnode); fwnode_for_each_parent_node(fwnode, parent) { if (--depth == 0) return parent; } return NULL; } EXPORT_SYMBOL_GPL(fwnode_get_nth_parent); /** * fwnode_get_next_child_node - Return the next child node handle for a node * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the node's child nodes or a %NULL handle. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. Note that this function also puts a reference to @child * unconditionally. */ struct fwnode_handle * fwnode_get_next_child_node(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { return fwnode_call_ptr_op(fwnode, get_next_child_node, child); } EXPORT_SYMBOL_GPL(fwnode_get_next_child_node); /** * fwnode_get_next_available_child_node - Return the next available child node handle for a node * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the node's child nodes or a %NULL handle. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. Note that this function also puts a reference to @child * unconditionally. */ struct fwnode_handle * fwnode_get_next_available_child_node(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct fwnode_handle *next_child = child; if (IS_ERR_OR_NULL(fwnode)) return NULL; do { next_child = fwnode_get_next_child_node(fwnode, next_child); if (!next_child) return NULL; } while (!fwnode_device_is_available(next_child)); return next_child; } EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node); /** * device_get_next_child_node - Return the next child node handle for a device * @dev: Device to find the next child node for. * @child: Handle to one of the device's child nodes or a %NULL handle. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. Note that this function also puts a reference to @child * unconditionally. */ struct fwnode_handle *device_get_next_child_node(const struct device *dev, struct fwnode_handle *child) { const struct fwnode_handle *fwnode = dev_fwnode(dev); struct fwnode_handle *next; if (IS_ERR_OR_NULL(fwnode)) return NULL; /* Try to find a child in primary fwnode */ next = fwnode_get_next_child_node(fwnode, child); if (next) return next; /* When no more children in primary, continue with secondary */ return fwnode_get_next_child_node(fwnode->secondary, child); } EXPORT_SYMBOL_GPL(device_get_next_child_node); /** * fwnode_get_named_child_node - Return first matching named child node handle * @fwnode: Firmware node to find the named child node for. * @childname: String to match child node name against. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. */ struct fwnode_handle * fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { return fwnode_call_ptr_op(fwnode, get_named_child_node, childname); } EXPORT_SYMBOL_GPL(fwnode_get_named_child_node); /** * device_get_named_child_node - Return first matching named child node handle * @dev: Device to find the named child node for. * @childname: String to match child node name against. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. */ struct fwnode_handle *device_get_named_child_node(const struct device *dev, const char *childname) { return fwnode_get_named_child_node(dev_fwnode(dev), childname); } EXPORT_SYMBOL_GPL(device_get_named_child_node); /** * fwnode_handle_get - Obtain a reference to a device node * @fwnode: Pointer to the device node to obtain the reference to. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. * * Return: the fwnode handle. */ struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode) { if (!fwnode_has_op(fwnode, get)) return fwnode; return fwnode_call_ptr_op(fwnode, get); } EXPORT_SYMBOL_GPL(fwnode_handle_get); /** * fwnode_device_is_available - check if a device is available for use * @fwnode: Pointer to the fwnode of the device. * * Return: true if device is available for use. Otherwise, returns false. * * For fwnode node types that don't implement the .device_is_available() * operation, this function returns true. */ bool fwnode_device_is_available(const struct fwnode_handle *fwnode) { if (IS_ERR_OR_NULL(fwnode)) return false; if (!fwnode_has_op(fwnode, device_is_available)) return true; return fwnode_call_bool_op(fwnode, device_is_available); } EXPORT_SYMBOL_GPL(fwnode_device_is_available); /** * fwnode_get_child_node_count - return the number of child nodes for a given firmware node * @fwnode: Pointer to the parent firmware node * * Return: the number of child nodes for a given firmware node. */ unsigned int fwnode_get_child_node_count(const struct fwnode_handle *fwnode) { struct fwnode_handle *child; unsigned int count = 0; fwnode_for_each_child_node(fwnode, child) count++; return count; } EXPORT_SYMBOL_GPL(fwnode_get_child_node_count); /** * fwnode_get_named_child_node_count - number of child nodes with given name * @fwnode: Node which child nodes are counted. * @name: String to match child node name against. * * Scan child nodes and count all the nodes with a specific name. Potential * 'number' -ending after the 'at sign' for scanned names is ignored. * E.g.:: * fwnode_get_named_child_node_count(fwnode, "channel"); * would match all the nodes:: * channel { }, channel@0 {}, channel@0xabba {}... * * Return: the number of child nodes with a matching name for a given device. */ unsigned int fwnode_get_named_child_node_count(const struct fwnode_handle *fwnode, const char *name) { struct fwnode_handle *child; unsigned int count = 0; fwnode_for_each_named_child_node(fwnode, child, name) count++; return count; } EXPORT_SYMBOL_GPL(fwnode_get_named_child_node_count); bool device_dma_supported(const struct device *dev) { return fwnode_call_bool_op(dev_fwnode(dev), device_dma_supported); } EXPORT_SYMBOL_GPL(device_dma_supported); enum dev_dma_attr device_get_dma_attr(const struct device *dev) { if (!fwnode_has_op(dev_fwnode(dev), device_get_dma_attr)) return DEV_DMA_NOT_SUPPORTED; return fwnode_call_int_op(dev_fwnode(dev), device_get_dma_attr); } EXPORT_SYMBOL_GPL(device_get_dma_attr); /** * fwnode_get_phy_mode - Get phy mode for given firmware node * @fwnode: Pointer to the given node * * The function gets phy interface string from property 'phy-mode' or * 'phy-connection-type', and return its index in phy_modes table, or errno in * error case. */ int fwnode_get_phy_mode(const struct fwnode_handle *fwnode) { const char *pm; int err, i; err = fwnode_property_read_string(fwnode, "phy-mode", &pm); if (err < 0) err = fwnode_property_read_string(fwnode, "phy-connection-type", &pm); if (err < 0) return err; for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) if (!strcasecmp(pm, phy_modes(i))) return i; return -ENODEV; } EXPORT_SYMBOL_GPL(fwnode_get_phy_mode); /** * device_get_phy_mode - Get phy mode for given device * @dev: Pointer to the given device * * The function gets phy interface string from property 'phy-mode' or * 'phy-connection-type', and return its index in phy_modes table, or errno in * error case. */ int device_get_phy_mode(struct device *dev) { return fwnode_get_phy_mode(dev_fwnode(dev)); } EXPORT_SYMBOL_GPL(device_get_phy_mode); /** * fwnode_iomap - Maps the memory mapped IO for a given fwnode * @fwnode: Pointer to the firmware node * @index: Index of the IO range * * Return: a pointer to the mapped memory. */ void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index) { return fwnode_call_ptr_op(fwnode, iomap, index); } EXPORT_SYMBOL(fwnode_iomap); /** * fwnode_irq_get - Get IRQ directly from a fwnode * @fwnode: Pointer to the firmware node * @index: Zero-based index of the IRQ * * Return: Linux IRQ number on success. Negative errno on failure. */ int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { int ret; ret = fwnode_call_int_op(fwnode, irq_get, index); /* We treat mapping errors as invalid case */ if (ret == 0) return -EINVAL; return ret; } EXPORT_SYMBOL(fwnode_irq_get); /** * fwnode_irq_get_byname - Get IRQ from a fwnode using its name * @fwnode: Pointer to the firmware node * @name: IRQ name * * Description: * Find a match to the string @name in the 'interrupt-names' string array * in _DSD for ACPI, or of_node for Device Tree. Then get the Linux IRQ * number of the IRQ resource corresponding to the index of the matched * string. * * Return: Linux IRQ number on success, or negative errno otherwise. */ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name) { int index; if (!name) return -EINVAL; index = fwnode_property_match_string(fwnode, "interrupt-names", name); if (index < 0) return index; return fwnode_irq_get(fwnode, index); } EXPORT_SYMBOL(fwnode_irq_get_byname); /** * fwnode_graph_get_next_endpoint - Get next endpoint firmware node * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. Note that this function also puts a reference to @prev * unconditionally. * * Return: an endpoint firmware node pointer or %NULL if no more endpoints * are available. */ struct fwnode_handle * fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *ep, *port_parent = NULL; const struct fwnode_handle *parent; /* * If this function is in a loop and the previous iteration returned * an endpoint from fwnode->secondary, then we need to use the secondary * as parent rather than @fwnode. */ if (prev) { port_parent = fwnode_graph_get_port_parent(prev); parent = port_parent; } else { parent = fwnode; } if (IS_ERR_OR_NULL(parent)) return NULL; ep = fwnode_call_ptr_op(parent, graph_get_next_endpoint, prev); if (ep) goto out_put_port_parent; ep = fwnode_graph_get_next_endpoint(parent->secondary, NULL); out_put_port_parent: fwnode_handle_put(port_parent); return ep; } EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint); /** * fwnode_graph_get_port_parent - Return the device fwnode of a port endpoint * @endpoint: Endpoint firmware node of the port * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. * * Return: the firmware node of the device the @endpoint belongs to. */ struct fwnode_handle * fwnode_graph_get_port_parent(const struct fwnode_handle *endpoint) { struct fwnode_handle *port, *parent; port = fwnode_get_parent(endpoint); parent = fwnode_call_ptr_op(port, graph_get_port_parent); fwnode_handle_put(port); return parent; } EXPORT_SYMBOL_GPL(fwnode_graph_get_port_parent); /** * fwnode_graph_get_remote_port_parent - Return fwnode of a remote device * @fwnode: Endpoint firmware node pointing to the remote endpoint * * Extracts firmware node of a remote device the @fwnode points to. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. */ struct fwnode_handle * fwnode_graph_get_remote_port_parent(const struct fwnode_handle *fwnode) { struct fwnode_handle *endpoint, *parent; endpoint = fwnode_graph_get_remote_endpoint(fwnode); parent = fwnode_graph_get_port_parent(endpoint); fwnode_handle_put(endpoint); return parent; } EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port_parent); /** * fwnode_graph_get_remote_port - Return fwnode of a remote port * @fwnode: Endpoint firmware node pointing to the remote endpoint * * Extracts firmware node of a remote port the @fwnode points to. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. */ struct fwnode_handle * fwnode_graph_get_remote_port(const struct fwnode_handle *fwnode) { return fwnode_get_next_parent(fwnode_graph_get_remote_endpoint(fwnode)); } EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port); /** * fwnode_graph_get_remote_endpoint - Return fwnode of a remote endpoint * @fwnode: Endpoint firmware node pointing to the remote endpoint * * Extracts firmware node of a remote endpoint the @fwnode points to. * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. */ struct fwnode_handle * fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) { return fwnode_call_ptr_op(fwnode, graph_get_remote_endpoint); } EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint); static bool fwnode_graph_remote_available(struct fwnode_handle *ep) { struct fwnode_handle *dev_node; bool available; dev_node = fwnode_graph_get_remote_port_parent(ep); available = fwnode_device_is_available(dev_node); fwnode_handle_put(dev_node); return available; } /** * fwnode_graph_get_endpoint_by_id - get endpoint by port and endpoint numbers * @fwnode: parent fwnode_handle containing the graph * @port: identifier of the port node * @endpoint: identifier of the endpoint node under the port node * @flags: fwnode lookup flags * * The caller is responsible for calling fwnode_handle_put() on the returned * fwnode pointer. * * Return: the fwnode handle of the local endpoint corresponding the port and * endpoint IDs or %NULL if not found. * * If FWNODE_GRAPH_ENDPOINT_NEXT is passed in @flags and the specified endpoint * has not been found, look for the closest endpoint ID greater than the * specified one and return the endpoint that corresponds to it, if present. * * Does not return endpoints that belong to disabled devices or endpoints that * are unconnected, unless FWNODE_GRAPH_DEVICE_DISABLED is passed in @flags. */ struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags) { struct fwnode_handle *ep, *best_ep = NULL; unsigned int best_ep_id = 0; bool endpoint_next = flags & FWNODE_GRAPH_ENDPOINT_NEXT; bool enabled_only = !(flags & FWNODE_GRAPH_DEVICE_DISABLED); fwnode_graph_for_each_endpoint(fwnode, ep) { struct fwnode_endpoint fwnode_ep = { 0 }; int ret; if (enabled_only && !fwnode_graph_remote_available(ep)) continue; ret = fwnode_graph_parse_endpoint(ep, &fwnode_ep); if (ret < 0) continue; if (fwnode_ep.port != port) continue; if (fwnode_ep.id == endpoint) return ep; if (!endpoint_next) continue; /* * If the endpoint that has just been found is not the first * matching one and the ID of the one found previously is closer * to the requested endpoint ID, skip it. */ if (fwnode_ep.id < endpoint || (best_ep && best_ep_id < fwnode_ep.id)) continue; fwnode_handle_put(best_ep); best_ep = fwnode_handle_get(ep); best_ep_id = fwnode_ep.id; } return best_ep; } EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_by_id); /** * fwnode_graph_get_endpoint_count - Count endpoints on a device node * @fwnode: The node related to a device * @flags: fwnode lookup flags * Count endpoints in a device node. * * If FWNODE_GRAPH_DEVICE_DISABLED flag is specified, also unconnected endpoints * and endpoints connected to disabled devices are counted. */ unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags) { struct fwnode_handle *ep; unsigned int count = 0; fwnode_graph_for_each_endpoint(fwnode, ep) { if (flags & FWNODE_GRAPH_DEVICE_DISABLED || fwnode_graph_remote_available(ep)) count++; } return count; } EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_count); /** * fwnode_graph_parse_endpoint - parse common endpoint node properties * @fwnode: pointer to endpoint fwnode_handle * @endpoint: pointer to the fwnode endpoint data structure * * Parse @fwnode representing a graph endpoint node and store the * information in @endpoint. The caller must hold a reference to * @fwnode. */ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { memset(endpoint, 0, sizeof(*endpoint)); return fwnode_call_int_op(fwnode, graph_parse_endpoint, endpoint); } EXPORT_SYMBOL(fwnode_graph_parse_endpoint); const void *device_get_match_data(const struct device *dev) { return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev); } EXPORT_SYMBOL_GPL(device_get_match_data); static unsigned int fwnode_graph_devcon_matches(const struct fwnode_handle *fwnode, const char *con_id, void *data, devcon_match_fn_t match, void **matches, unsigned int matches_len) { struct fwnode_handle *node; struct fwnode_handle *ep; unsigned int count = 0; void *ret; fwnode_graph_for_each_endpoint(fwnode, ep) { if (matches && count >= matches_len) { fwnode_handle_put(ep); break; } node = fwnode_graph_get_remote_port_parent(ep); if (!fwnode_device_is_available(node)) { fwnode_handle_put(node); continue; } ret = match(node, con_id, data); fwnode_handle_put(node); if (ret) { if (matches) matches[count] = ret; count++; } } return count; } static unsigned int fwnode_devcon_matches(const struct fwnode_handle *fwnode, const char *con_id, void *data, devcon_match_fn_t match, void **matches, unsigned int matches_len) { struct fwnode_handle *node; unsigned int count = 0; unsigned int i; void *ret; for (i = 0; ; i++) { if (matches && count >= matches_len) break; node = fwnode_find_reference(fwnode, con_id, i); if (IS_ERR(node)) break; ret = match(node, NULL, data); fwnode_handle_put(node); if (ret) { if (matches) matches[count] = ret; count++; } } return count; } /** * fwnode_connection_find_match - Find connection from a device node * @fwnode: Device node with the connection * @con_id: Identifier for the connection * @data: Data for the match function * @match: Function to check and convert the connection description * * Find a connection with unique identifier @con_id between @fwnode and another * device node. @match will be used to convert the connection description to * data the caller is expecting to be returned. */ void *fwnode_connection_find_match(const struct fwnode_handle *fwnode, const char *con_id, void *data, devcon_match_fn_t match) { unsigned int count; void *ret; if (!fwnode || !match) return NULL; count = fwnode_graph_devcon_matches(fwnode, con_id, data, match, &ret, 1); if (count) return ret; count = fwnode_devcon_matches(fwnode, con_id, data, match, &ret, 1); return count ? ret : NULL; } EXPORT_SYMBOL_GPL(fwnode_connection_find_match); /** * fwnode_connection_find_matches - Find connections from a device node * @fwnode: Device node with the connection * @con_id: Identifier for the connection * @data: Data for the match function * @match: Function to check and convert the connection description * @matches: (Optional) array of pointers to fill with matches * @matches_len: Length of @matches * * Find up to @matches_len connections with unique identifier @con_id between * @fwnode and other device nodes. @match will be used to convert the * connection description to data the caller is expecting to be returned * through the @matches array. * * If @matches is %NULL @matches_len is ignored and the total number of resolved * matches is returned. * * Return: Number of matches resolved, or negative errno. */ int fwnode_connection_find_matches(const struct fwnode_handle *fwnode, const char *con_id, void *data, devcon_match_fn_t match, void **matches, unsigned int matches_len) { unsigned int count_graph; unsigned int count_ref; if (!fwnode || !match) return -EINVAL; count_graph = fwnode_graph_devcon_matches(fwnode, con_id, data, match, matches, matches_len); if (matches) { matches += count_graph; matches_len -= count_graph; } count_ref = fwnode_devcon_matches(fwnode, con_id, data, match, matches, matches_len); return count_graph + count_ref; } EXPORT_SYMBOL_GPL(fwnode_connection_find_matches); |
| 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 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 | // 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_lock.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; } /* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active, * when unregistering a net device and accessing associated sysfs files. The * potential deadlock is as follow: * * CPU 0 CPU 1 * * rtnl_lock vfs_read * unregister_netdevice_many kernfs_seq_start * device_del / kobject_put kernfs_get_active (kn->active++) * kernfs_drain sysfs_kf_seq_show * wait_event( rtnl_lock * kn->active == KN_DEACTIVATED_BIAS) -> waits on CPU 0 to release * -> waits on CPU 1 to decrease kn->active the rtnl lock. * * The historical fix was to use rtnl_trylock with restart_syscall to bail out * of sysfs operations when the lock couldn't be taken. This fixed the above * issue as it allowed CPU 1 to bail out of the ABBA situation. * * But it came with performances issues, as syscalls are being restarted in * loops when there was contention on the rtnl lock, with huge slow downs in * specific scenarios (e.g. lots of virtual interfaces created and userspace * daemons querying their attributes). * * The idea below is to bail out of the active kernfs_node protection * (kn->active) while trying to take the rtnl lock. * * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The * net device is guaranteed to be alive if this returns successfully. */ static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr, struct net_device *ndev) { struct kernfs_node *kn; int ret = 0; /* First, we hold a reference to the net device as the unregistration * path might run in parallel. This will ensure the net device and the * associated sysfs objects won't be freed while we try to take the rtnl * lock. */ dev_hold(ndev); /* sysfs_break_active_protection was introduced to allow self-removal of * devices and their associated sysfs files by bailing out of the * sysfs/kernfs protection. We do this here to allow the unregistration * path to complete in parallel. The following takes a reference on the * kobject and the kernfs_node being accessed. * * This works because we hold a reference onto the net device and the * unregistration path will wait for us eventually in netdev_run_todo * (outside an rtnl lock section). */ kn = sysfs_break_active_protection(kobj, attr); /* We can now try to take the rtnl lock. This can't deadlock us as the * unregistration path is able to drain sysfs files (kernfs_node) thanks * to the above dance. */ if (rtnl_lock_interruptible()) { ret = -ERESTARTSYS; goto unbreak; } /* Check dismantle on the device hasn't started, otherwise deny the * operation. */ if (!dev_isalive(ndev)) { rtnl_unlock(); ret = -ENODEV; goto unbreak; } /* We are now sure the device dismantle hasn't started nor that it can * start before we exit the locking section as we hold the rtnl lock. * There's no need to keep unbreaking the sysfs protection nor to hold * a net device reference from that point; that was only needed to take * the rtnl lock. */ unbreak: sysfs_unbreak_active_protection(kn); dev_put(ndev); return ret; } /* 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; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) goto err; 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 (netif_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 locking section 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; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; 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 locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; 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 locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; 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; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; 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; 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); struct netdev_phys_item_id ppid; ssize_t ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; 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); char name[IFNAMSIZ]; ssize_t ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; 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); struct netdev_phys_item_id ppid = { }; ssize_t ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = netif_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 struct attribute *netdev_phys_attrs[] __ro_after_init = { &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, NULL, }; static umode_t netdev_phys_is_visible(struct kobject *kobj, struct attribute *attr, int index) { struct device *dev = kobj_to_dev(kobj); struct net_device *netdev = to_net_dev(dev); if (attr == &dev_attr_phys_port_id.attr) { if (!netdev->netdev_ops->ndo_get_phys_port_id) return 0; } else if (attr == &dev_attr_phys_port_name.attr) { if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->devlink_port) return 0; } else if (attr == &dev_attr_phys_switch_id.attr) { if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->devlink_port) return 0; } return attr->mode; } static const struct attribute_group netdev_phys_group = { .attrs = netdev_phys_attrs, .is_visible = netdev_phys_is_visible, }; 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 = netif_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_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 = 1UL << flow_table->log; 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->log = ilog2(mask) + 1; for (count = 0; count <= mask; count++) { table->flows[count].cpu = RPS_NO_CPU; table->flows[count].filter = RPS_NO_FILTER; } } 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, .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; int res = 0; mutex_lock(&rps_default_mask_mutex); rps_default_mask = dev_net(dev)->core.rps_default_mask; if (rps_default_mask && !cpumask_empty(rps_default_mask)) res = netdev_rx_queue_set_rps_mask(queue, rps_default_mask); mutex_unlock(&rps_default_mask_mutex); return res; #else return 0; #endif } 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; /* Rx queues are cleared in rx_queue_release to allow later * re-registration. This is triggered when their kobj refcount is * dropped. * * If a queue is removed while both a read (or write) operation and a * the re-addition of the same queue are pending (waiting on rntl_lock) * it might happen that the re-addition will execute before the read, * making the initial removal to never happen (queue's kobj refcount * won't drop enough because of the pending read). In such rare case, * return to allow the removal operation to complete. */ if (unlikely(kobj->state_initialized)) { netdev_warn_once(dev, "Cannot re-add rx queues before their removal completed"); return -EAGAIN; } /* 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; queue->groups = rx_queue_default_groups; error = sysfs_create_groups(kobj, queue->groups); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err_default_groups; } error = rx_queue_default_mask(dev, queue); if (error) goto err_default_groups; kobject_uevent(kobj, KOBJ_ADD); return error; err_default_groups: sysfs_remove_groups(kobj, queue->groups); 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 netdev_rx_queue *queue = &dev->_rx[i]; struct kobject *kobj = &queue->kobj; if (!check_net(dev_net(dev))) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); sysfs_remove_groups(kobj, queue->groups); 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf); ssize_t (*store)(struct kobject *kobj, struct attribute *attr, 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(kobj, attr, 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(kobj, attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int num_tc, tc, index, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; ret = sysfs_rtnl_lock(kobj, attr, queue->dev); if (ret) return ret; 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { int err, index = get_netdev_queue_index(queue); struct net_device *dev = queue->dev; u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the locking section below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; err = sysfs_rtnl_lock(kobj, attr, dev); if (err) return err; err = -EOPNOTSUPP; netdev_lock_ops(dev); if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); netdev_unlock_ops(dev); if (!err) { queue->tx_maxrate = rate; rtnl_unlock(); return len; } rtnl_unlock(); 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, struct attribute *attr, 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 kobject *kobj, \ struct attribute *attr, \ struct netdev_queue *queue, char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct kobject *kobj, \ struct attribute *attr, \ 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int len, tc, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); ret = sysfs_rtnl_lock(kobj, attr, queue->dev); if (ret) return ret; /* 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; } /* Increase the net device refcnt to make sure it won't be freed while * xps_queue_show is running. */ dev_hold(dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); dev_put(dev); return len; } static ssize_t xps_cpus_store(struct kobject *kobj, struct attribute *attr, 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; } err = sysfs_rtnl_lock(kobj, attr, dev); if (err) { free_cpumask_var(mask); return err; } 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int tc, ret; index = get_netdev_queue_index(queue); ret = sysfs_rtnl_lock(kobj, attr, dev); if (ret) return ret; tc = netdev_txq_to_tc(dev, index); /* Increase the net device refcnt to make sure it won't be freed while * xps_queue_show is running. */ dev_hold(dev); rtnl_unlock(); ret = tc >= 0 ? xps_queue_show(dev, index, tc, buf, XPS_RXQS) : -EINVAL; dev_put(dev); return ret; } static ssize_t xps_rxqs_store(struct kobject *kobj, struct attribute *attr, 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; } err = sysfs_rtnl_lock(kobj, attr, dev); if (err) { bitmap_free(mask); return err; } 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, .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; /* Tx queues are cleared in netdev_queue_release to allow later * re-registration. This is triggered when their kobj refcount is * dropped. * * If a queue is removed while both a read (or write) operation and a * the re-addition of the same queue are pending (waiting on rntl_lock) * it might happen that the re-addition will execute before the read, * making the initial removal to never happen (queue's kobj refcount * won't drop enough because of the pending read). In such rare case, * return to allow the removal operation to complete. */ if (unlikely(kobj->state_initialized)) { netdev_warn_once(dev, "Cannot re-add tx queues before their removal completed"); return -EAGAIN; } /* 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; queue->groups = netdev_queue_default_groups; error = sysfs_create_groups(kobj, queue->groups); if (error) goto err; if (netdev_uses_bql(dev)) { error = sysfs_create_group(kobj, &dql_group); if (error) goto err_default_groups; } kobject_uevent(kobj, KOBJ_ADD); return 0; err_default_groups: sysfs_remove_groups(kobj, queue->groups); 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 (!check_net(dev_net(dev))) queue->kobj.uevent_suppress = 1; if (netdev_uses_bql(dev)) sysfs_remove_group(&queue->kobj, &dql_group); sysfs_remove_groups(&queue->kobj, queue->groups); 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); netdev_lock_ops(dev); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; netdev_unlock_ops(dev); #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 (!check_net(dev_net(ndev))) 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; *groups++ = &netdev_phys_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); } |
| 3 3 64 64 63 62 57 61 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/atari.c * * Code extracted from drivers/block/genhd.c * * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King */ #include <linux/ctype.h> #include "check.h" #include "atari.h" /* ++guenther: this should be settable by the user ("make config")?. */ #define ICD_PARTS /* check if a partition entry looks valid -- Atari format is assumed if at least one of the primary entries is ok this way */ #define VALID_PARTITION(pi,hdsiz) \ (((pi)->flg & 1) && \ isalnum((pi)->id[0]) && isalnum((pi)->id[1]) && isalnum((pi)->id[2]) && \ be32_to_cpu((pi)->st) <= (hdsiz) && \ be32_to_cpu((pi)->st) + be32_to_cpu((pi)->siz) <= (hdsiz)) static inline int OK_id(char *s) { return memcmp (s, "GEM", 3) == 0 || memcmp (s, "BGM", 3) == 0 || memcmp (s, "LNX", 3) == 0 || memcmp (s, "SWP", 3) == 0 || memcmp (s, "RAW", 3) == 0 ; } int atari_partition(struct parsed_partitions *state) { Sector sect; struct rootsector *rs; struct partition_info *pi; u32 extensect; u32 hd_size; int slot; #ifdef ICD_PARTS int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */ #endif /* * ATARI partition scheme supports 512 lba only. If this is not * the case, bail early to avoid miscalculating hd_size. */ if (queue_logical_block_size(state->disk->queue) != 512) return 0; rs = read_part_sector(state, 0, §); if (!rs) return -1; /* Verify this is an Atari rootsector: */ hd_size = get_capacity(state->disk); if (!VALID_PARTITION(&rs->part[0], hd_size) && !VALID_PARTITION(&rs->part[1], hd_size) && !VALID_PARTITION(&rs->part[2], hd_size) && !VALID_PARTITION(&rs->part[3], hd_size)) { /* * if there's no valid primary partition, assume that no Atari * format partition table (there's no reliable magic or the like * :-() */ put_dev_sector(sect); return 0; } pi = &rs->part[0]; strlcat(state->pp_buf, " AHDI", PAGE_SIZE); for (slot = 1; pi < &rs->part[4] && slot < state->limit; slot++, pi++) { struct rootsector *xrs; Sector sect2; ulong partsect; if ( !(pi->flg & 1) ) continue; /* active partition */ if (memcmp (pi->id, "XGM", 3) != 0) { /* we don't care about other id's */ put_partition (state, slot, be32_to_cpu(pi->st), be32_to_cpu(pi->siz)); continue; } /* extension partition */ #ifdef ICD_PARTS part_fmt = 1; #endif strlcat(state->pp_buf, " XGM<", PAGE_SIZE); partsect = extensect = be32_to_cpu(pi->st); while (1) { xrs = read_part_sector(state, partsect, §2); if (!xrs) { printk (" block %ld read failed\n", partsect); put_dev_sector(sect); return -1; } /* ++roman: sanity check: bit 0 of flg field must be set */ if (!(xrs->part[0].flg & 1)) { printk( "\nFirst sub-partition in extended partition is not valid!\n" ); put_dev_sector(sect2); break; } put_partition(state, slot, partsect + be32_to_cpu(xrs->part[0].st), be32_to_cpu(xrs->part[0].siz)); if (!(xrs->part[1].flg & 1)) { /* end of linked partition list */ put_dev_sector(sect2); break; } if (memcmp( xrs->part[1].id, "XGM", 3 ) != 0) { printk("\nID of extended partition is not XGM!\n"); put_dev_sector(sect2); break; } partsect = be32_to_cpu(xrs->part[1].st) + extensect; put_dev_sector(sect2); if (++slot == state->limit) { printk( "\nMaximum number of partitions reached!\n" ); break; } } strlcat(state->pp_buf, " >", PAGE_SIZE); } #ifdef ICD_PARTS if ( part_fmt!=1 ) { /* no extended partitions -> test ICD-format */ pi = &rs->icdpart[0]; /* sanity check: no ICD format if first partition invalid */ if (OK_id(pi->id)) { strlcat(state->pp_buf, " ICD<", PAGE_SIZE); for (; pi < &rs->icdpart[8] && slot < state->limit; slot++, pi++) { /* accept only GEM,BGM,RAW,LNX,SWP partitions */ if (!((pi->flg & 1) && OK_id(pi->id))) continue; put_partition (state, slot, be32_to_cpu(pi->st), be32_to_cpu(pi->siz)); } strlcat(state->pp_buf, " >", PAGE_SIZE); } } #endif put_dev_sector(sect); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2008-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2021-2025 Intel Corporation */ #include <linux/export.h> #include <linux/etherdevice.h> #include <net/mac80211.h> #include <linux/unaligned.h> #include "ieee80211_i.h" #include "rate.h" #include "mesh.h" #include "led.h" #include "wme.h" void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int tmp; skb->pkt_type = IEEE80211_TX_STATUS_MSG; skb_queue_tail(info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS ? &local->skb_queue : &local->skb_queue_unreliable, skb); tmp = skb_queue_len(&local->skb_queue) + skb_queue_len(&local->skb_queue_unreliable); while (tmp > IEEE80211_IRQSAFE_QUEUE_LIMIT && (skb = skb_dequeue(&local->skb_queue_unreliable))) { ieee80211_free_txskb(hw, skb); tmp--; I802_DEBUG_INC(local->tx_status_drop); } tasklet_schedule(&local->tasklet); } EXPORT_SYMBOL(ieee80211_tx_status_irqsafe); static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; int ac; if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER | IEEE80211_TX_CTL_AMPDU | IEEE80211_TX_CTL_HW_80211_ENCAP)) { ieee80211_free_txskb(&local->hw, skb); return; } /* * This skb 'survived' a round-trip through the driver, and * hopefully the driver didn't mangle it too badly. However, * we can definitely not rely on the control information * being correct. Clear it so we don't get junk there, and * indicate that it needs new processing, but must not be * modified/encrypted again. */ memset(&info->control, 0, sizeof(info->control)); info->control.jiffies = jiffies; info->control.vif = &sta->sdata->vif; info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; info->flags |= IEEE80211_TX_INTFL_RETRANSMISSION; info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; sta->deflink.status_stats.filtered++; /* * Clear more-data bit on filtered frames, it might be set * but later frames might time out so it might have to be * clear again ... It's all rather unlikely (this frame * should time out first, right?) but let's not confuse * peers unnecessarily. */ if (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_MOREDATA); if (ieee80211_is_data_qos(hdr->frame_control)) { u8 *p = ieee80211_get_qos_ctl(hdr); int tid = *p & IEEE80211_QOS_CTL_TID_MASK; /* * Clear EOSP if set, this could happen e.g. * if an absence period (us being a P2P GO) * shortens the SP. */ if (*p & IEEE80211_QOS_CTL_EOSP) *p &= ~IEEE80211_QOS_CTL_EOSP; ac = ieee80211_ac_from_tid(tid); } else { ac = IEEE80211_AC_BE; } /* * Clear the TX filter mask for this STA when sending the next * packet. If the STA went to power save mode, this will happen * when it wakes up for the next time. */ set_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT); ieee80211_clear_fast_xmit(sta); /* * This code races in the following way: * * (1) STA sends frame indicating it will go to sleep and does so * (2) hardware/firmware adds STA to filter list, passes frame up * (3) hardware/firmware processes TX fifo and suppresses a frame * (4) we get TX status before having processed the frame and * knowing that the STA has gone to sleep. * * This is actually quite unlikely even when both those events are * processed from interrupts coming in quickly after one another or * even at the same time because we queue both TX status events and * RX frames to be processed by a tasklet and process them in the * same order that they were received or TX status last. Hence, there * is no race as long as the frame RX is processed before the next TX * status, which drivers can ensure, see below. * * Note that this can only happen if the hardware or firmware can * actually add STAs to the filter list, if this is done by the * driver in response to set_tim() (which will only reduce the race * this whole filtering tries to solve, not completely solve it) * this situation cannot happen. * * To completely solve this race drivers need to make sure that they * (a) don't mix the irq-safe/not irq-safe TX status/RX processing * functions and * (b) always process RX events before TX status events if ordering * can be unknown, for example with different interrupt status * bits. * (c) if PS mode transitions are manual (i.e. the flag * %IEEE80211_HW_AP_LINK_PS is set), always process PS state * changes before calling TX status events if ordering can be * unknown. */ if (test_sta_flag(sta, WLAN_STA_PS_STA) && skb_queue_len(&sta->tx_filtered[ac]) < STA_MAX_TX_BUFFER) { skb_queue_tail(&sta->tx_filtered[ac], skb); sta_info_recalc_tim(sta); if (!timer_pending(&local->sta_cleanup)) mod_timer(&local->sta_cleanup, round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL)); return; } if (!test_sta_flag(sta, WLAN_STA_PS_STA) && !(info->flags & IEEE80211_TX_INTFL_RETRIED)) { /* Software retry the packet once */ info->flags |= IEEE80211_TX_INTFL_RETRIED; ieee80211_add_pending_skb(local, skb); return; } ps_dbg_ratelimited(sta->sdata, "dropped TX filtered frame, queue_len=%d PS=%d @%lu\n", skb_queue_len(&sta->tx_filtered[ac]), !!test_sta_flag(sta, WLAN_STA_PS_STA), jiffies); ieee80211_free_txskb(&local->hw, skb); } static void ieee80211_check_pending_bar(struct sta_info *sta, u8 *addr, u8 tid) { struct tid_ampdu_tx *tid_tx; tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); if (!tid_tx || !tid_tx->bar_pending) return; tid_tx->bar_pending = false; ieee80211_send_bar(&sta->sdata->vif, addr, tid, tid_tx->failed_bar_ssn); } static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *) skb->data; if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; u8 *qc = ieee80211_get_qos_ctl(hdr); u16 tid = qc[0] & 0xf; ieee80211_check_pending_bar(sta, hdr->addr1, tid); } } static void ieee80211_set_bar_pending(struct sta_info *sta, u8 tid, u16 ssn) { struct tid_ampdu_tx *tid_tx; tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); if (!tid_tx) return; tid_tx->failed_bar_ssn = ssn; tid_tx->bar_pending = true; } static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info, struct ieee80211_tx_status *status) { struct ieee80211_rate_status *status_rate = NULL; int len = sizeof(struct ieee80211_radiotap_header); if (status && status->n_rates) status_rate = &status->rates[status->n_rates - 1]; /* IEEE80211_RADIOTAP_RATE rate */ if (status_rate && !(status_rate->rate_idx.flags & (RATE_INFO_FLAGS_MCS | RATE_INFO_FLAGS_DMG | RATE_INFO_FLAGS_EDMG | RATE_INFO_FLAGS_VHT_MCS | RATE_INFO_FLAGS_HE_MCS))) len += 2; else if (info->status.rates[0].idx >= 0 && !(info->status.rates[0].flags & (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))) len += 2; /* IEEE80211_RADIOTAP_TX_FLAGS */ len += 2; /* IEEE80211_RADIOTAP_DATA_RETRIES */ len += 1; /* IEEE80211_RADIOTAP_MCS * IEEE80211_RADIOTAP_VHT */ if (status_rate) { if (status_rate->rate_idx.flags & RATE_INFO_FLAGS_MCS) len += 3; else if (status_rate->rate_idx.flags & RATE_INFO_FLAGS_VHT_MCS) len = ALIGN(len, 2) + 12; else if (status_rate->rate_idx.flags & RATE_INFO_FLAGS_HE_MCS) len = ALIGN(len, 2) + 12; } else if (info->status.rates[0].idx >= 0) { if (info->status.rates[0].flags & IEEE80211_TX_RC_MCS) len += 3; else if (info->status.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) len = ALIGN(len, 2) + 12; } return len; } static void ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, struct sk_buff *skb, int retry_count, int rtap_len, struct ieee80211_tx_status *status) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; struct ieee80211_rate_status *status_rate = NULL; unsigned char *pos; u16 legacy_rate = 0; u16 txflags; if (status && status->n_rates) status_rate = &status->rates[status->n_rates - 1]; rthdr = skb_push(skb, rtap_len); memset(rthdr, 0, rtap_len); rthdr->it_len = cpu_to_le16(rtap_len); rthdr->it_present = cpu_to_le32(BIT(IEEE80211_RADIOTAP_TX_FLAGS) | BIT(IEEE80211_RADIOTAP_DATA_RETRIES)); pos = (unsigned char *)(rthdr + 1); /* * XXX: Once radiotap gets the bitmap reset thing the vendor * extensions proposal contains, we can actually report * the whole set of tries we did. */ /* IEEE80211_RADIOTAP_RATE */ if (status_rate) { if (!(status_rate->rate_idx.flags & (RATE_INFO_FLAGS_MCS | RATE_INFO_FLAGS_DMG | RATE_INFO_FLAGS_EDMG | RATE_INFO_FLAGS_VHT_MCS | RATE_INFO_FLAGS_HE_MCS))) legacy_rate = status_rate->rate_idx.legacy; } else if (info->status.rates[0].idx >= 0 && !(info->status.rates[0].flags & (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))) { struct ieee80211_supported_band *sband; sband = local->hw.wiphy->bands[info->band]; legacy_rate = sband->bitrates[info->status.rates[0].idx].bitrate; } if (legacy_rate) { rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_RATE)); *pos = DIV_ROUND_UP(legacy_rate, 5); /* padding for tx flags */ pos += 2; } /* IEEE80211_RADIOTAP_TX_FLAGS */ txflags = 0; if (!(info->flags & IEEE80211_TX_STAT_ACK) && !is_multicast_ether_addr(hdr->addr1)) txflags |= IEEE80211_RADIOTAP_F_TX_FAIL; if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT) txflags |= IEEE80211_RADIOTAP_F_TX_CTS; if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) txflags |= IEEE80211_RADIOTAP_F_TX_RTS; put_unaligned_le16(txflags, pos); pos += 2; /* IEEE80211_RADIOTAP_DATA_RETRIES */ /* for now report the total retry_count */ *pos = retry_count; pos++; if (status_rate && (status_rate->rate_idx.flags & RATE_INFO_FLAGS_MCS)) { rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_MCS)); pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | IEEE80211_RADIOTAP_MCS_HAVE_GI | IEEE80211_RADIOTAP_MCS_HAVE_BW; if (status_rate->rate_idx.flags & RATE_INFO_FLAGS_SHORT_GI) pos[1] |= IEEE80211_RADIOTAP_MCS_SGI; if (status_rate->rate_idx.bw == RATE_INFO_BW_40) pos[1] |= IEEE80211_RADIOTAP_MCS_BW_40; pos[2] = status_rate->rate_idx.mcs; pos += 3; } else if (status_rate && (status_rate->rate_idx.flags & RATE_INFO_FLAGS_VHT_MCS)) { u16 known = local->hw.radiotap_vht_details & (IEEE80211_RADIOTAP_VHT_KNOWN_GI | IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH); rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); /* required alignment from rthdr */ pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); /* u16 known - IEEE80211_RADIOTAP_VHT_KNOWN_* */ put_unaligned_le16(known, pos); pos += 2; /* u8 flags - IEEE80211_RADIOTAP_VHT_FLAG_* */ if (status_rate->rate_idx.flags & RATE_INFO_FLAGS_SHORT_GI) *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; pos++; /* u8 bandwidth */ switch (status_rate->rate_idx.bw) { case RATE_INFO_BW_160: *pos = 11; break; case RATE_INFO_BW_80: *pos = 4; break; case RATE_INFO_BW_40: *pos = 1; break; default: *pos = 0; break; } pos++; /* u8 mcs_nss[4] */ *pos = (status_rate->rate_idx.mcs << 4) | status_rate->rate_idx.nss; pos += 4; /* u8 coding */ pos++; /* u8 group_id */ pos++; /* u16 partial_aid */ pos += 2; } else if (status_rate && (status_rate->rate_idx.flags & RATE_INFO_FLAGS_HE_MCS)) { struct ieee80211_radiotap_he *he; rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_HE)); /* required alignment from rthdr */ pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); he = (struct ieee80211_radiotap_he *)pos; he->data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU | IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN | IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN | IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN); he->data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN); #define HE_PREP(f, val) le16_encode_bits(val, IEEE80211_RADIOTAP_HE_##f) he->data6 |= HE_PREP(DATA6_NSTS, status_rate->rate_idx.nss); #define CHECK_GI(s) \ BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \ (int)NL80211_RATE_INFO_HE_GI_##s) CHECK_GI(0_8); CHECK_GI(1_6); CHECK_GI(3_2); he->data3 |= HE_PREP(DATA3_DATA_MCS, status_rate->rate_idx.mcs); he->data3 |= HE_PREP(DATA3_DATA_DCM, status_rate->rate_idx.he_dcm); he->data5 |= HE_PREP(DATA5_GI, status_rate->rate_idx.he_gi); switch (status_rate->rate_idx.bw) { case RATE_INFO_BW_20: he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ); break; case RATE_INFO_BW_40: he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ); break; case RATE_INFO_BW_80: he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ); break; case RATE_INFO_BW_160: he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ); break; case RATE_INFO_BW_HE_RU: #define CHECK_RU_ALLOC(s) \ BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \ NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4) CHECK_RU_ALLOC(26); CHECK_RU_ALLOC(52); CHECK_RU_ALLOC(106); CHECK_RU_ALLOC(242); CHECK_RU_ALLOC(484); CHECK_RU_ALLOC(996); CHECK_RU_ALLOC(2x996); he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, status_rate->rate_idx.he_ru_alloc + 4); break; default: WARN_ONCE(1, "Invalid SU BW %d\n", status_rate->rate_idx.bw); } pos += sizeof(struct ieee80211_radiotap_he); } if (status_rate || info->status.rates[0].idx < 0) return; /* IEEE80211_RADIOTAP_MCS * IEEE80211_RADIOTAP_VHT */ if (info->status.rates[0].flags & IEEE80211_TX_RC_MCS) { rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_MCS)); pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | IEEE80211_RADIOTAP_MCS_HAVE_GI | IEEE80211_RADIOTAP_MCS_HAVE_BW; if (info->status.rates[0].flags & IEEE80211_TX_RC_SHORT_GI) pos[1] |= IEEE80211_RADIOTAP_MCS_SGI; if (info->status.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH) pos[1] |= IEEE80211_RADIOTAP_MCS_BW_40; if (info->status.rates[0].flags & IEEE80211_TX_RC_GREEN_FIELD) pos[1] |= IEEE80211_RADIOTAP_MCS_FMT_GF; pos[2] = info->status.rates[0].idx; pos += 3; } else if (info->status.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) { u16 known = local->hw.radiotap_vht_details & (IEEE80211_RADIOTAP_VHT_KNOWN_GI | IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH); rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); /* required alignment from rthdr */ pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); /* u16 known - IEEE80211_RADIOTAP_VHT_KNOWN_* */ put_unaligned_le16(known, pos); pos += 2; /* u8 flags - IEEE80211_RADIOTAP_VHT_FLAG_* */ if (info->status.rates[0].flags & IEEE80211_TX_RC_SHORT_GI) *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; pos++; /* u8 bandwidth */ if (info->status.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH) *pos = 1; else if (info->status.rates[0].flags & IEEE80211_TX_RC_80_MHZ_WIDTH) *pos = 4; else if (info->status.rates[0].flags & IEEE80211_TX_RC_160_MHZ_WIDTH) *pos = 11; else /* IEEE80211_TX_RC_{20_MHZ_WIDTH,FIXME:DUP_DATA} */ *pos = 0; pos++; /* u8 mcs_nss[4] */ *pos = (ieee80211_rate_get_vht_mcs(&info->status.rates[0]) << 4) | ieee80211_rate_get_vht_nss(&info->status.rates[0]); pos += 4; /* u8 coding */ pos++; /* u8 group_id */ pos++; /* u16 partial_aid */ pos += 2; } } /* * Handles the tx for TDLS teardown frames. * If the frame wasn't ACKed by the peer - it will be re-sent through the AP */ static void ieee80211_tdls_td_tx_handle(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 flags) { struct sk_buff *teardown_skb; struct sk_buff *orig_teardown_skb; bool is_teardown = false; /* Get the teardown data we need and free the lock */ spin_lock(&sdata->u.mgd.teardown_lock); teardown_skb = sdata->u.mgd.teardown_skb; orig_teardown_skb = sdata->u.mgd.orig_teardown_skb; if ((skb == orig_teardown_skb) && teardown_skb) { sdata->u.mgd.teardown_skb = NULL; sdata->u.mgd.orig_teardown_skb = NULL; is_teardown = true; } spin_unlock(&sdata->u.mgd.teardown_lock); if (is_teardown) { /* This mechanism relies on being able to get ACKs */ WARN_ON(!ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)); /* Check if peer has ACKed */ if (flags & IEEE80211_TX_STAT_ACK) { dev_kfree_skb_any(teardown_skb); } else { tdls_dbg(sdata, "TDLS Resending teardown through AP\n"); ieee80211_subif_start_xmit(teardown_skb, skb->dev); } } } static struct ieee80211_sub_if_data * ieee80211_sdata_from_skb(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr = (void *)skb->data; if (skb->dev) { list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!sdata->dev) continue; if (skb->dev == sdata->dev) return sdata; } return NULL; } list_for_each_entry_rcu(sdata, &local->interfaces, list) { switch (sdata->vif.type) { case NL80211_IFTYPE_P2P_DEVICE: break; case NL80211_IFTYPE_NAN: if (sdata->u.nan.started) break; fallthrough; default: continue; } if (ether_addr_equal(sdata->vif.addr, hdr->addr2)) return sdata; } return NULL; } static void ieee80211_report_ack_skb(struct ieee80211_local *local, struct sk_buff *orig_skb, bool acked, bool dropped, ktime_t ack_hwtstamp) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(orig_skb); struct sk_buff *skb; unsigned long flags; spin_lock_irqsave(&local->ack_status_lock, flags); skb = idr_remove(&local->ack_status_frames, info->status_data); spin_unlock_irqrestore(&local->ack_status_lock, flags); if (!skb) return; if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr = (void *)skb->data; bool is_valid_ack_signal = !!(info->status.flags & IEEE80211_TX_STATUS_ACK_SIGNAL_VALID); struct cfg80211_tx_status status = { .cookie = cookie, .buf = skb->data, .len = skb->len, .ack = acked, }; if (ieee80211_is_timing_measurement(orig_skb) || ieee80211_is_ftm(orig_skb)) { status.tx_tstamp = ktime_to_ns(skb_hwtstamps(orig_skb)->hwtstamp); status.ack_tstamp = ktime_to_ns(ack_hwtstamp); } rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { if (skb->protocol == sdata->control_port_protocol || skb->protocol == cpu_to_be16(ETH_P_PREAUTH)) cfg80211_control_port_tx_status(&sdata->wdev, cookie, skb->data, skb->len, acked, GFP_ATOMIC); else if (ieee80211_is_any_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, is_valid_ack_signal, GFP_ATOMIC); else if (ieee80211_is_mgmt(hdr->frame_control)) cfg80211_mgmt_tx_status_ext(&sdata->wdev, &status, GFP_ATOMIC); else pr_warn("Unknown status report in ack skb\n"); } rcu_read_unlock(); dev_kfree_skb_any(skb); } else if (dropped) { dev_kfree_skb_any(skb); } else { /* consumes skb */ skb_complete_wifi_ack(skb, acked); } } static void ieee80211_handle_smps_status(struct ieee80211_sub_if_data *sdata, bool acked, u16 status_data) { u16 sub_data = u16_get_bits(status_data, IEEE80211_STATUS_SUBDATA_MASK); enum ieee80211_smps_mode smps_mode = sub_data & 3; int link_id = (sub_data >> 2); struct ieee80211_link_data *link; if (!sdata || !ieee80211_sdata_running(sdata)) return; if (!acked) return; if (sdata->vif.type != NL80211_IFTYPE_STATION) return; if (WARN(link_id >= ARRAY_SIZE(sdata->link), "bad SMPS status link: %d\n", link_id)) return; link = rcu_dereference(sdata->link[link_id]); if (!link) return; /* * This update looks racy, but isn't, the only other place * updating this variable is in managed mode before assoc, * and we have to be associated to have a status from the * action frame TX, since we cannot send it while we're not * associated yet. */ link->smps_mode = smps_mode; wiphy_work_queue(sdata->local->hw.wiphy, &link->u.mgd.recalc_smps); } static void ieee80211_handle_teardown_ttlm_status(struct ieee80211_sub_if_data *sdata, bool acked) { if (!sdata || !ieee80211_sdata_running(sdata)) return; if (!acked) return; if (sdata->vif.type != NL80211_IFTYPE_STATION) return; wiphy_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.teardown_ttlm_work); } static void ieee80211_report_used_skb(struct ieee80211_local *local, struct sk_buff *skb, bool dropped, ktime_t ack_hwtstamp) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u16 tx_time_est = ieee80211_info_get_tx_time_est(info); struct ieee80211_hdr *hdr = (void *)skb->data; bool acked = info->flags & IEEE80211_TX_STAT_ACK; if (dropped) acked = false; if (tx_time_est) { struct sta_info *sta; rcu_read_lock(); sta = sta_info_get_by_addrs(local, hdr->addr1, hdr->addr2); ieee80211_sta_update_pending_airtime(local, sta, skb_get_queue_mapping(skb), tx_time_est, true); rcu_read_unlock(); } if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) { struct ieee80211_sub_if_data *sdata; rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (!sdata) { skb->dev = NULL; } else if (!dropped) { /* Check to see if packet is a TDLS teardown packet */ if (ieee80211_is_data(hdr->frame_control) && (ieee80211_get_tdls_action(skb) == WLAN_TDLS_TEARDOWN)) { ieee80211_tdls_td_tx_handle(local, sdata, skb, info->flags); } else if (ieee80211_s1g_is_twt_setup(skb)) { if (!acked) { struct sk_buff *qskb; qskb = skb_clone(skb, GFP_ATOMIC); if (qskb) { skb_queue_tail(&sdata->status_queue, qskb); wiphy_work_queue(local->hw.wiphy, &sdata->work); } } } else { ieee80211_mgd_conn_tx_status(sdata, hdr->frame_control, acked); } } rcu_read_unlock(); } else if (info->status_data_idr) { ieee80211_report_ack_skb(local, skb, acked, dropped, ack_hwtstamp); } else if (info->status_data) { struct ieee80211_sub_if_data *sdata; rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); switch (u16_get_bits(info->status_data, IEEE80211_STATUS_TYPE_MASK)) { case IEEE80211_STATUS_TYPE_SMPS: ieee80211_handle_smps_status(sdata, acked, info->status_data); break; case IEEE80211_STATUS_TYPE_NEG_TTLM: ieee80211_handle_teardown_ttlm_status(sdata, acked); break; } rcu_read_unlock(); } if (!dropped && skb->destructor) { skb->wifi_acked_valid = 1; skb->wifi_acked = acked; } ieee80211_led_tx(local); if (skb_has_frag_list(skb)) { kfree_skb_list(skb_shinfo(skb)->frag_list); skb_shinfo(skb)->frag_list = NULL; } } /* * Use a static threshold for now, best value to be determined * by testing ... * Should it depend on: * - on # of retransmissions * - current throughput (higher value for higher tpt)? */ #define STA_LOST_PKT_THRESHOLD 50 #define STA_LOST_PKT_TIME HZ /* 1 sec since last ACK */ #define STA_LOST_TDLS_PKT_TIME (10*HZ) /* 10secs since last ACK */ static void ieee80211_lost_packet(struct sta_info *sta, struct ieee80211_tx_info *info) { unsigned long pkt_time = STA_LOST_PKT_TIME; unsigned int pkt_thr = STA_LOST_PKT_THRESHOLD; /* If driver relies on its own algorithm for station kickout, skip * mac80211 packet loss mechanism. */ if (ieee80211_hw_check(&sta->local->hw, REPORTS_LOW_ACK)) return; /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) return; sta->deflink.status_stats.lost_packets++; if (sta->sta.tdls) { pkt_time = STA_LOST_TDLS_PKT_TIME; pkt_thr = STA_LOST_PKT_THRESHOLD; } /* * If we're in TDLS mode, make sure that all STA_LOST_PKT_THRESHOLD * of the last packets were lost, and that no ACK was received in the * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss * mechanism. * For non-TDLS, use STA_LOST_PKT_THRESHOLD and STA_LOST_PKT_TIME */ if (sta->deflink.status_stats.lost_packets < pkt_thr || !time_after(jiffies, sta->deflink.status_stats.last_pkt_time + pkt_time)) return; cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, sta->deflink.status_stats.lost_packets, GFP_ATOMIC); sta->deflink.status_stats.lost_packets = 0; } static int ieee80211_tx_get_rates(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, int *retry_count) { int count = -1; int i; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) { /* just the first aggr frame carry status info */ info->status.rates[i].idx = -1; info->status.rates[i].count = 0; break; } else if (info->status.rates[i].idx < 0) { break; } else if (i >= hw->max_report_rates) { /* the HW cannot have attempted that rate */ info->status.rates[i].idx = -1; info->status.rates[i].count = 0; break; } count += info->status.rates[i].count; } if (count < 0) count = 0; *retry_count = count; return i - 1; } void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, int retry_count, struct ieee80211_tx_status *status) { struct sk_buff *skb2; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_sub_if_data *sdata; struct net_device *prev_dev = NULL; int rtap_len; /* send frame to monitor interfaces now */ rtap_len = ieee80211_tx_radiotap_len(info, status); if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) { pr_err("ieee80211_tx_status: headroom too small\n"); dev_kfree_skb(skb); return; } ieee80211_add_tx_radiotap_header(local, skb, retry_count, rtap_len, status); /* XXX: is this sufficient for BPF? */ skb_reset_mac_header(skb); skb->ip_summed = CHECKSUM_UNNECESSARY; skb->pkt_type = PACKET_OTHERHOST; skb->protocol = htons(ETH_P_802_2); memset(skb->cb, 0, sizeof(skb->cb)); rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { if (!ieee80211_sdata_running(sdata)) continue; if (sdata->u.mntr.flags & MONITOR_FLAG_SKIP_TX) continue; if (prev_dev) { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) { skb2->dev = prev_dev; netif_rx(skb2); } } prev_dev = sdata->dev; } } if (prev_dev) { skb->dev = prev_dev; netif_rx(skb); skb = NULL; } rcu_read_unlock(); dev_kfree_skb(skb); } static void __ieee80211_tx_status(struct ieee80211_hw *hw, struct ieee80211_tx_status *status, int rates_idx, int retry_count) { struct sk_buff *skb = status->skb; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_tx_info *info = status->info; struct sta_info *sta; __le16 fc; bool acked; bool noack_success; struct ieee80211_bar *bar; int tid = IEEE80211_NUM_TIDS; fc = hdr->frame_control; if (status->sta) { sta = container_of(status->sta, struct sta_info, sta); if (info->flags & IEEE80211_TX_STATUS_EOSP) clear_sta_flag(sta, WLAN_STA_SP); acked = !!(info->flags & IEEE80211_TX_STAT_ACK); noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); /* mesh Peer Service Period support */ if (ieee80211_vif_is_mesh(&sta->sdata->vif) && ieee80211_is_data_qos(fc)) ieee80211_mpsp_trigger_process( ieee80211_get_qos_ctl(hdr), sta, true, acked); if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) && (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) sta->deflink.tx_stats.last_rate = info->status.rates[rates_idx]; if ((info->flags & IEEE80211_TX_STAT_AMPDU_NO_BACK) && (ieee80211_is_data_qos(fc))) { u16 ssn; u8 *qc; qc = ieee80211_get_qos_ctl(hdr); tid = qc[0] & 0xf; ssn = ((le16_to_cpu(hdr->seq_ctrl) + 0x10) & IEEE80211_SCTL_SEQ); ieee80211_send_bar(&sta->sdata->vif, hdr->addr1, tid, ssn); } else if (ieee80211_is_data_qos(fc)) { u8 *qc = ieee80211_get_qos_ctl(hdr); tid = qc[0] & 0xf; } if (!acked && ieee80211_is_back_req(fc)) { u16 control; /* * BAR failed, store the last SSN and retry sending * the BAR when the next unicast transmission on the * same TID succeeds. */ bar = (struct ieee80211_bar *) skb->data; control = le16_to_cpu(bar->control); if (!(control & IEEE80211_BAR_CTRL_MULTI_TID)) { u16 ssn = le16_to_cpu(bar->start_seq_num); tid = (control & IEEE80211_BAR_CTRL_TID_INFO_MASK) >> IEEE80211_BAR_CTRL_TID_INFO_SHIFT; ieee80211_set_bar_pending(sta, tid, ssn); } } if (info->flags & IEEE80211_TX_STAT_TX_FILTERED) { ieee80211_handle_filtered_frame(local, sta, skb); return; } else if (ieee80211_is_data_present(fc)) { if (!acked && !noack_success) sta->deflink.status_stats.msdu_failed[tid]++; sta->deflink.status_stats.msdu_retries[tid] += retry_count; } if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); } /* SNMP counters * Fragments are passed to low-level drivers as separate skbs, so these * are actually fragments, not frames. Update frame counters only for * the first fragment of the frame. */ if ((info->flags & IEEE80211_TX_STAT_ACK) || (info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) { if (ieee80211_is_first_frag(hdr->seq_ctrl)) { I802_DEBUG_INC(local->dot11TransmittedFrameCount); if (is_multicast_ether_addr(ieee80211_get_DA(hdr))) I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); if (retry_count > 0) I802_DEBUG_INC(local->dot11RetryCount); if (retry_count > 1) I802_DEBUG_INC(local->dot11MultipleRetryCount); } /* This counter shall be incremented for an acknowledged MPDU * with an individual address in the address 1 field or an MPDU * with a multicast address in the address 1 field of type Data * or Management. */ if (!is_multicast_ether_addr(hdr->addr1) || ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) I802_DEBUG_INC(local->dot11TransmittedFragmentCount); } else { if (ieee80211_is_first_frag(hdr->seq_ctrl)) I802_DEBUG_INC(local->dot11FailedCount); } if (ieee80211_is_any_nullfunc(fc) && ieee80211_has_pm(fc) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && local->ps_sdata && !(local->scanning)) { if (info->flags & IEEE80211_TX_STAT_ACK) local->ps_sdata->u.mgd.flags |= IEEE80211_STA_NULLFUNC_ACKED; mod_timer(&local->dynamic_ps_timer, jiffies + msecs_to_jiffies(10)); } ieee80211_report_used_skb(local, skb, false, status->ack_hwtstamp); /* * This is a bit racy but we can avoid a lot of work * with this test... */ if (local->tx_mntrs) ieee80211_tx_monitor(local, skb, retry_count, status); else if (status->free_list) list_add_tail(&skb->list, status->free_list); else dev_kfree_skb(skb); } void ieee80211_tx_status_skb(struct ieee80211_hw *hw, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_tx_status status = { .skb = skb, .info = IEEE80211_SKB_CB(skb), }; struct sta_info *sta; rcu_read_lock(); sta = sta_info_get_by_addrs(local, hdr->addr1, hdr->addr2); if (sta) status.sta = &sta->sta; ieee80211_tx_status_ext(hw, &status); rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_tx_status_skb); void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_tx_status *status) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_tx_info *info = status->info; struct ieee80211_sta *pubsta = status->sta; struct sk_buff *skb = status->skb; struct sta_info *sta = NULL; int rates_idx, retry_count; bool acked, noack_success, ack_signal_valid; u16 tx_time_est; if (pubsta) { sta = container_of(pubsta, struct sta_info, sta); if (status->n_rates) sta->deflink.tx_stats.last_rate_info = status->rates[status->n_rates - 1].rate_idx; } if (skb && (tx_time_est = ieee80211_info_get_tx_time_est(IEEE80211_SKB_CB(skb))) > 0) { /* Do this here to avoid the expensive lookup of the sta * in ieee80211_report_used_skb(). */ ieee80211_sta_update_pending_airtime(local, sta, skb_get_queue_mapping(skb), tx_time_est, true); ieee80211_info_set_tx_time_est(IEEE80211_SKB_CB(skb), 0); } if (!status->info) goto free; rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); acked = !!(info->flags & IEEE80211_TX_STAT_ACK); noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); ack_signal_valid = !!(info->status.flags & IEEE80211_TX_STATUS_ACK_SIGNAL_VALID); if (pubsta) { struct ieee80211_sub_if_data *sdata = sta->sdata; if (!acked && !noack_success) sta->deflink.status_stats.retry_failed++; sta->deflink.status_stats.retry_count += retry_count; if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { if (sdata->vif.type == NL80211_IFTYPE_STATION && skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) ieee80211_sta_tx_notify(sdata, (void *) skb->data, acked, info->status.tx_time); if (acked) { sta->deflink.status_stats.last_ack = jiffies; if (sta->deflink.status_stats.lost_packets) sta->deflink.status_stats.lost_packets = 0; /* Track when last packet was ACKed */ sta->deflink.status_stats.last_pkt_time = jiffies; /* Reset connection monitor */ if (sdata->vif.type == NL80211_IFTYPE_STATION && unlikely(sdata->u.mgd.probe_send_count > 0)) sdata->u.mgd.probe_send_count = 0; if (ack_signal_valid) { sta->deflink.status_stats.last_ack_signal = (s8)info->status.ack_signal; sta->deflink.status_stats.ack_signal_filled = true; ewma_avg_signal_add(&sta->deflink.status_stats.avg_ack_signal, -info->status.ack_signal); } } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { /* * The STA is in power save mode, so assume * that this TX packet failed because of that. */ if (skb) ieee80211_handle_filtered_frame(local, sta, skb); return; } else if (noack_success) { /* nothing to do here, do not account as lost */ } else { ieee80211_lost_packet(sta, info); } } rate_control_tx_status(local, status); if (ieee80211_vif_is_mesh(&sta->sdata->vif)) ieee80211s_update_metric(local, sta, status); } if (skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) return __ieee80211_tx_status(hw, status, rates_idx, retry_count); if (acked || noack_success) { I802_DEBUG_INC(local->dot11TransmittedFrameCount); if (!pubsta) I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); if (retry_count > 0) I802_DEBUG_INC(local->dot11RetryCount); if (retry_count > 1) I802_DEBUG_INC(local->dot11MultipleRetryCount); } else { I802_DEBUG_INC(local->dot11FailedCount); } free: if (!skb) return; ieee80211_report_used_skb(local, skb, false, status->ack_hwtstamp); if (status->free_list) list_add_tail(&skb->list, status->free_list); else dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_tx_status_ext); void ieee80211_tx_rate_update(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct ieee80211_tx_info *info) { struct ieee80211_local *local = hw_to_local(hw); struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_tx_status status = { .info = info, .sta = pubsta, }; rate_control_tx_status(local, &status); if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) sta->deflink.tx_stats.last_rate = info->status.rates[0]; } EXPORT_SYMBOL(ieee80211_tx_rate_update); void ieee80211_report_low_ack(struct ieee80211_sta *pubsta, u32 num_packets) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, num_packets, GFP_ATOMIC); } EXPORT_SYMBOL(ieee80211_report_low_ack); void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb) { struct ieee80211_local *local = hw_to_local(hw); ktime_t kt = ktime_set(0, 0); ieee80211_report_used_skb(local, skb, true, kt); dev_kfree_skb_any(skb); } EXPORT_SYMBOL(ieee80211_free_txskb); void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, struct sk_buff_head *skbs) { struct sk_buff *skb; while ((skb = __skb_dequeue(skbs))) ieee80211_free_txskb(hw, skb); } EXPORT_SYMBOL(ieee80211_purge_tx_queue); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic API for algorithms (i.e., low-level API). * * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_ALGAPI_H #define _CRYPTO_ALGAPI_H #include <crypto/utils.h> #include <linux/align.h> #include <linux/cache.h> #include <linux/crypto.h> #include <linux/list.h> #include <linux/types.h> #include <linux/workqueue.h> /* * Maximum values for blocksize and alignmask, used to allocate * static buffers that are big enough for any combination of * algs and architectures. Ciphers have a lower maximum size. */ #define MAX_ALGAPI_BLOCKSIZE 160 #define MAX_ALGAPI_ALIGNMASK 127 #define MAX_CIPHER_BLOCKSIZE 16 #define MAX_CIPHER_ALIGNMASK 15 #ifdef ARCH_DMA_MINALIGN #define CRYPTO_DMA_ALIGN ARCH_DMA_MINALIGN #else #define CRYPTO_DMA_ALIGN CRYPTO_MINALIGN #endif #define CRYPTO_DMA_PADDING ((CRYPTO_DMA_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1)) /* * Autoloaded crypto modules should only use a prefixed name to avoid allowing * arbitrary modules to be loaded. Loading from userspace may still need the * unprefixed names, so retains those aliases as well. * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro * expands twice on the same line. Instead, use a separate base name for the * alias. */ #define MODULE_ALIAS_CRYPTO(name) \ MODULE_INFO(alias, name); \ MODULE_INFO(alias, "crypto-" name) struct crypto_aead; struct crypto_instance; struct module; struct notifier_block; struct rtattr; struct scatterlist; struct seq_file; struct sk_buff; union crypto_no_such_thing; struct crypto_instance { struct crypto_alg alg; struct crypto_template *tmpl; union { /* Node in list of instances after registration. */ struct hlist_node list; /* List of attached spawns before registration. */ struct crypto_spawn *spawns; }; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; struct crypto_template { struct list_head list; struct hlist_head instances; struct hlist_head dead; struct module *module; struct work_struct free_work; int (*create)(struct crypto_template *tmpl, struct rtattr **tb); char name[CRYPTO_MAX_ALG_NAME]; }; struct crypto_spawn { struct list_head list; struct crypto_alg *alg; union { /* Back pointer to instance after registration.*/ struct crypto_instance *inst; /* Spawn list pointer prior to registration. */ struct crypto_spawn *next; }; const struct crypto_type *frontend; u32 mask; bool dead; bool registered; }; struct crypto_queue { struct list_head list; struct list_head *backlog; unsigned int qlen; unsigned int max_qlen; }; struct crypto_attr_alg { char name[CRYPTO_MAX_ALG_NAME]; }; struct crypto_attr_type { u32 type; u32 mask; }; /* * Algorithm registration interface. */ int crypto_register_alg(struct crypto_alg *alg); void crypto_unregister_alg(struct crypto_alg *alg); int crypto_register_algs(struct crypto_alg *algs, int count); void crypto_unregister_algs(struct crypto_alg *algs, int count); void crypto_mod_put(struct crypto_alg *alg); int crypto_register_template(struct crypto_template *tmpl); int crypto_register_templates(struct crypto_template *tmpls, int count); void crypto_unregister_template(struct crypto_template *tmpl); void crypto_unregister_templates(struct crypto_template *tmpls, int count); struct crypto_template *crypto_lookup_template(const char *name); int crypto_register_instance(struct crypto_template *tmpl, struct crypto_instance *inst); void crypto_unregister_instance(struct crypto_instance *inst); int crypto_grab_spawn(struct crypto_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); void crypto_drop_spawn(struct crypto_spawn *spawn); struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type, u32 mask); void *crypto_spawn_tfm2(struct crypto_spawn *spawn); struct crypto_attr_type *crypto_get_attr_type(struct rtattr **tb); int crypto_check_attr_type(struct rtattr **tb, u32 type, u32 *mask_ret); const char *crypto_attr_alg_name(struct rtattr *rta); int __crypto_inst_setname(struct crypto_instance *inst, const char *name, const char *driver, struct crypto_alg *alg); #define crypto_inst_setname(inst, name, ...) \ CONCATENATE(crypto_inst_setname_, COUNT_ARGS(__VA_ARGS__))( \ inst, name, ##__VA_ARGS__) #define crypto_inst_setname_1(inst, name, alg) \ __crypto_inst_setname(inst, name, name, alg) #define crypto_inst_setname_2(inst, name, driver, alg) \ __crypto_inst_setname(inst, name, driver, alg) void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen); int crypto_enqueue_request(struct crypto_queue *queue, struct crypto_async_request *request); void crypto_enqueue_request_head(struct crypto_queue *queue, struct crypto_async_request *request); struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue); static inline unsigned int crypto_queue_len(struct crypto_queue *queue) { return queue->qlen; } void crypto_inc(u8 *a, unsigned int size); static inline void *crypto_tfm_ctx(struct crypto_tfm *tfm) { return tfm->__crt_ctx; } static inline void *crypto_tfm_ctx_align(struct crypto_tfm *tfm, unsigned int align) { if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(crypto_tfm_ctx(tfm), align); } static inline unsigned int crypto_dma_align(void) { return CRYPTO_DMA_ALIGN; } static inline unsigned int crypto_dma_padding(void) { return (crypto_dma_align() - 1) & ~(crypto_tfm_ctx_alignment() - 1); } static inline void *crypto_tfm_ctx_dma(struct crypto_tfm *tfm) { return crypto_tfm_ctx_align(tfm, crypto_dma_align()); } static inline struct crypto_instance *crypto_tfm_alg_instance( struct crypto_tfm *tfm) { return container_of(tfm->__crt_alg, struct crypto_instance, alg); } static inline void *crypto_instance_ctx(struct crypto_instance *inst) { return inst->__ctx; } static inline struct crypto_async_request *crypto_get_backlog( struct crypto_queue *queue) { return queue->backlog == &queue->list ? NULL : container_of(queue->backlog, struct crypto_async_request, list); } static inline u32 crypto_requires_off(struct crypto_attr_type *algt, u32 off) { return (algt->type ^ off) & algt->mask & off; } /* * When an algorithm uses another algorithm (e.g., if it's an instance of a * template), these are the flags that should always be set on the "outer" * algorithm if any "inner" algorithm has them set. */ #define CRYPTO_ALG_INHERITED_FLAGS \ (CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK | \ CRYPTO_ALG_ALLOCATES_MEMORY) /* * Given the type and mask that specify the flags restrictions on a template * instance being created, return the mask that should be passed to * crypto_grab_*() (along with type=0) to honor any request the user made to * have any of the CRYPTO_ALG_INHERITED_FLAGS clear. */ static inline u32 crypto_algt_inherited_mask(struct crypto_attr_type *algt) { return crypto_requires_off(algt, CRYPTO_ALG_INHERITED_FLAGS); } int crypto_register_notifier(struct notifier_block *nb); int crypto_unregister_notifier(struct notifier_block *nb); /* Crypto notification events. */ enum { CRYPTO_MSG_ALG_REQUEST, CRYPTO_MSG_ALG_REGISTER, CRYPTO_MSG_ALG_LOADED, }; static inline void crypto_request_complete(struct crypto_async_request *req, int err) { req->complete(req->data, err); } static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK; } static inline bool crypto_tfm_req_virt(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_flags & CRYPTO_ALG_REQ_VIRT; } static inline u32 crypto_request_flags(struct crypto_async_request *req) { return req->flags & ~CRYPTO_TFM_REQ_ON_STACK; } #endif /* _CRYPTO_ALGAPI_H */ |
| 181 181 182 180 85 85 84 84 9 5 4 1 1 1 6 2 3 7 7 1 13 13 10 10 10 3 14 15 3 2 15 1 11 3 3 3 35 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/mount.c - kernfs mount 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/mount.h> #include <linux/init.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/seq_file.h> #include <linux/exportfs.h> #include <linux/uuid.h> #include <linux/statfs.h> #include "kernfs-internal.h" struct kmem_cache *kernfs_node_cache __ro_after_init; struct kmem_cache *kernfs_iattrs_cache __ro_after_init; struct kernfs_global_locks *kernfs_locks __ro_after_init; static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) { struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry)); struct kernfs_syscall_ops *scops = root->syscall_ops; if (scops && scops->show_options) return scops->show_options(sf, root); return 0; } static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry) { struct kernfs_node *node = kernfs_dentry_node(dentry); struct kernfs_root *root = kernfs_root(node); struct kernfs_syscall_ops *scops = root->syscall_ops; if (scops && scops->show_path) return scops->show_path(sf, node, root); seq_dentry(sf, dentry, " \t\n\\"); return 0; } static int kernfs_statfs(struct dentry *dentry, struct kstatfs *buf) { simple_statfs(dentry, buf); buf->f_fsid = uuid_to_fsid(dentry->d_sb->s_uuid.b); return 0; } const struct super_operations kernfs_sops = { .statfs = kernfs_statfs, .drop_inode = inode_just_drop, .evict_inode = kernfs_evict_inode, .show_options = kernfs_sop_show_options, .show_path = kernfs_sop_show_path, /* * sysfs is built on top of kernfs and sysfs provides the power * management infrastructure to support suspend/hibernate by * writing to various files in /sys/power/. As filesystems may * be automatically frozen during suspend/hibernate implementing * freeze/thaw support for kernfs generically will cause * deadlocks as the suspending/hibernation initiating task will * hold a VFS lock that it will then wait upon to be released. * If freeze/thaw for kernfs is needed talk to the VFS. */ .freeze_fs = NULL, .unfreeze_fs = NULL, .freeze_super = NULL, .thaw_super = NULL, }; static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent) { struct kernfs_node *kn = inode->i_private; if (*max_len < 2) { *max_len = 2; return FILEID_INVALID; } *max_len = 2; *(u64 *)fh = kn->id; return FILEID_KERNFS; } static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, bool get_parent) { struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_node *kn; struct inode *inode; u64 id; if (fh_len < 2) return NULL; switch (fh_type) { case FILEID_KERNFS: id = *(u64 *)fid; break; case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: /* * blk_log_action() exposes "LOW32,HIGH32" pair without * type and userland can call us with generic fid * constructed from them. Combine it back to ID. See * blk_log_action(). */ id = ((u64)fid->i32.gen << 32) | fid->i32.ino; break; default: return NULL; } kn = kernfs_find_and_get_node_by_id(info->root, id); if (!kn) return ERR_PTR(-ESTALE); if (get_parent) { struct kernfs_node *parent; parent = kernfs_get_parent(kn); kernfs_put(kn); kn = parent; if (!kn) return ERR_PTR(-ESTALE); } inode = kernfs_get_inode(sb, kn); kernfs_put(kn); return d_obtain_alias(inode); } static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false); } static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true); } static struct dentry *kernfs_get_parent_dentry(struct dentry *child) { struct kernfs_node *kn = kernfs_dentry_node(child); struct kernfs_root *root = kernfs_root(kn); guard(rwsem_read)(&root->kernfs_rwsem); return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn))); } static const struct export_operations kernfs_export_ops = { .encode_fh = kernfs_encode_fh, .fh_to_dentry = kernfs_fh_to_dentry, .fh_to_parent = kernfs_fh_to_parent, .get_parent = kernfs_get_parent_dentry, }; /** * kernfs_root_from_sb - determine kernfs_root associated with a super_block * @sb: the super_block in question * * Return: the kernfs_root associated with @sb. If @sb is not a kernfs one, * %NULL is returned. */ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { if (sb->s_op == &kernfs_sops) return kernfs_info(sb)->root; return NULL; } /* * find the next ancestor in the path down to @child, where @parent was the * ancestor whose descendant we want to find. * * Say the path is /a/b/c/d. @child is d, @parent is %NULL. We return the root * node. If @parent is b, then we return the node for c. * Passing in d as @parent is not ok. */ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child, struct kernfs_node *parent) { if (child == parent) { pr_crit_once("BUG in find_next_ancestor: called with parent == child"); return NULL; } while (kernfs_parent(child) != parent) { child = kernfs_parent(child); if (!child) return NULL; } return child; } /** * kernfs_node_dentry - get a dentry for the given kernfs_node * @kn: kernfs_node for which a dentry is needed * @sb: the kernfs super_block * * Return: the dentry pointer */ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb) { struct dentry *dentry; struct kernfs_node *knparent; struct kernfs_root *root; BUG_ON(sb->s_op != &kernfs_sops); dentry = dget(sb->s_root); /* Check if this is the root kernfs_node */ if (!rcu_access_pointer(kn->__parent)) return dentry; root = kernfs_root(kn); /* * As long as kn is valid, its parent can not vanish. This is cgroup's * kn so it can't have its parent replaced. Therefore it is safe to use * the ancestor node outside of the RCU or locked section. */ if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT))) return ERR_PTR(-EINVAL); scoped_guard(rcu) { knparent = find_next_ancestor(kn, NULL); } if (WARN_ON(!knparent)) { dput(dentry); return ERR_PTR(-EINVAL); } do { struct dentry *dtmp; struct kernfs_node *kntmp; const char *name; if (kn == knparent) return dentry; scoped_guard(rwsem_read, &root->kernfs_rwsem) { kntmp = find_next_ancestor(kn, knparent); if (WARN_ON(!kntmp)) { dput(dentry); return ERR_PTR(-EINVAL); } name = kstrdup(kernfs_rcu_name(kntmp), GFP_KERNEL); } if (!name) { dput(dentry); return ERR_PTR(-ENOMEM); } dtmp = lookup_noperm_positive_unlocked(&QSTR(name), dentry); dput(dentry); kfree(name); if (IS_ERR(dtmp)) return dtmp; knparent = kntmp; dentry = dtmp; } while (true); } static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc) { struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_root *kf_root = kfc->root; struct inode *inode; struct dentry *root; info->sb = sb; /* Userspace would break if executables or devices appear on sysfs */ sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = kfc->magic; sb->s_op = &kernfs_sops; sb->s_xattr = kernfs_xattr_handlers; if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP) sb->s_export_op = &kernfs_export_ops; sb->s_time_gran = 1; /* sysfs dentries and inodes don't require IO to create */ sb->s_shrink->seeks = 0; /* get root inode, initialize and unlock it */ down_read(&kf_root->kernfs_rwsem); inode = kernfs_get_inode(sb, info->root->kn); up_read(&kf_root->kernfs_rwsem); if (!inode) { pr_debug("kernfs: could not get root inode\n"); return -ENOMEM; } /* instantiate and link root dentry */ root = d_make_root(inode); if (!root) { pr_debug("%s: could not get root dentry!\n", __func__); return -ENOMEM; } sb->s_root = root; set_default_d_op(sb, &kernfs_dops); return 0; } static int kernfs_test_super(struct super_block *sb, struct fs_context *fc) { struct kernfs_super_info *sb_info = kernfs_info(sb); struct kernfs_super_info *info = fc->s_fs_info; return sb_info->root == info->root && sb_info->ns == info->ns; } static int kernfs_set_super(struct super_block *sb, struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; kfc->ns_tag = NULL; return set_anon_super_fc(sb, fc); } /** * kernfs_super_ns - determine the namespace tag of a kernfs super_block * @sb: super_block of interest * * Return: the namespace tag associated with kernfs super_block @sb. */ const void *kernfs_super_ns(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); return info->ns; } /** * kernfs_get_tree - kernfs filesystem access/retrieval helper * @fc: The filesystem context. * * This is to be called from each kernfs user's fs_context->ops->get_tree() * implementation, which should set the specified ->@fs_type and ->@flags, and * specify the hierarchy and namespace tag to mount via ->@root and ->@ns, * respectively. * * Return: %0 on success, -errno on failure. */ int kernfs_get_tree(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; struct super_block *sb; struct kernfs_super_info *info; int error; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; info->root = kfc->root; info->ns = kfc->ns_tag; INIT_LIST_HEAD(&info->node); fc->s_fs_info = info; sb = sget_fc(fc, kernfs_test_super, kernfs_set_super); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_root *root = kfc->root; kfc->new_sb_created = true; error = kernfs_fill_super(sb, kfc); if (error) { deactivate_locked_super(sb); return error; } sb->s_flags |= SB_ACTIVE; uuid_t uuid; uuid_gen(&uuid); super_set_uuid(sb, uuid.b, sizeof(uuid)); down_write(&root->kernfs_supers_rwsem); list_add(&info->node, &info->root->supers); up_write(&root->kernfs_supers_rwsem); } fc->root = dget(sb->s_root); return 0; } void kernfs_free_fs_context(struct fs_context *fc) { /* Note that we don't deal with kfc->ns_tag here. */ kfree(fc->s_fs_info); fc->s_fs_info = NULL; } /** * kernfs_kill_sb - kill_sb for kernfs * @sb: super_block being killed * * This can be used directly for file_system_type->kill_sb(). If a kernfs * user needs extra cleanup, it can implement its own kill_sb() and call * this function at the end. */ void kernfs_kill_sb(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_root *root = info->root; down_write(&root->kernfs_supers_rwsem); list_del(&info->node); up_write(&root->kernfs_supers_rwsem); /* * Remove the superblock from fs_supers/s_instances * so we can't find it, before freeing kernfs_super_info. */ kill_anon_super(sb); kfree(info); } static void __init kernfs_mutex_init(void) { int count; for (count = 0; count < NR_KERNFS_LOCKS; count++) mutex_init(&kernfs_locks->open_file_mutex[count]); } static void __init kernfs_lock_init(void) { kernfs_locks = kmalloc(sizeof(struct kernfs_global_locks), GFP_KERNEL); WARN_ON(!kernfs_locks); kernfs_mutex_init(); } void __init kernfs_init(void) { kernfs_node_cache = kmem_cache_create("kernfs_node_cache", sizeof(struct kernfs_node), 0, SLAB_PANIC, NULL); /* Creates slab cache for kernfs inode attributes */ kernfs_iattrs_cache = kmem_cache_create("kernfs_iattrs_cache", sizeof(struct kernfs_iattrs), 0, SLAB_PANIC, NULL); kernfs_lock_init(); } |
| 4 4 4 4 4 1 4 2 4 4 4 2 2 4 1 4 4 4 4 4 28 4 4 28 28 4 2 4 2 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | // SPDX-License-Identifier: GPL-2.0-or-later /* * linux/fs/fat/cache.c * * Written 1992,1993 by Werner Almesberger * * Mar 1999. AV. Changed cache, so that it uses the starting cluster instead * of inode number. * May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers. * Copyright (C) 2012-2013 Samsung Electronics Co., Ltd. */ #include <linux/slab.h> #include <linux/unaligned.h> #include <linux/buffer_head.h> #include "exfat_raw.h" #include "exfat_fs.h" #define EXFAT_MAX_CACHE 16 struct exfat_cache { struct list_head cache_list; unsigned int nr_contig; /* number of contiguous clusters */ unsigned int fcluster; /* cluster number in the file. */ unsigned int dcluster; /* cluster number on disk. */ }; struct exfat_cache_id { unsigned int id; unsigned int nr_contig; unsigned int fcluster; unsigned int dcluster; }; static struct kmem_cache *exfat_cachep; static void exfat_cache_init_once(void *c) { struct exfat_cache *cache = (struct exfat_cache *)c; INIT_LIST_HEAD(&cache->cache_list); } int exfat_cache_init(void) { exfat_cachep = kmem_cache_create("exfat_cache", sizeof(struct exfat_cache), 0, SLAB_RECLAIM_ACCOUNT, exfat_cache_init_once); if (!exfat_cachep) return -ENOMEM; return 0; } void exfat_cache_shutdown(void) { if (!exfat_cachep) return; kmem_cache_destroy(exfat_cachep); } static inline struct exfat_cache *exfat_cache_alloc(void) { return kmem_cache_alloc(exfat_cachep, GFP_NOFS); } static inline void exfat_cache_free(struct exfat_cache *cache) { WARN_ON(!list_empty(&cache->cache_list)); kmem_cache_free(exfat_cachep, cache); } static inline void exfat_cache_update_lru(struct inode *inode, struct exfat_cache *cache) { struct exfat_inode_info *ei = EXFAT_I(inode); if (ei->cache_lru.next != &cache->cache_list) list_move(&cache->cache_list, &ei->cache_lru); } static unsigned int exfat_cache_lookup(struct inode *inode, unsigned int fclus, struct exfat_cache_id *cid, unsigned int *cached_fclus, unsigned int *cached_dclus) { struct exfat_inode_info *ei = EXFAT_I(inode); static struct exfat_cache nohit = { .fcluster = 0, }; struct exfat_cache *hit = &nohit, *p; unsigned int offset = EXFAT_EOF_CLUSTER; spin_lock(&ei->cache_lru_lock); list_for_each_entry(p, &ei->cache_lru, cache_list) { /* Find the cache of "fclus" or nearest cache. */ if (p->fcluster <= fclus && hit->fcluster < p->fcluster) { hit = p; if (hit->fcluster + hit->nr_contig < fclus) { offset = hit->nr_contig; } else { offset = fclus - hit->fcluster; break; } } } if (hit != &nohit) { exfat_cache_update_lru(inode, hit); cid->id = ei->cache_valid_id; cid->nr_contig = hit->nr_contig; cid->fcluster = hit->fcluster; cid->dcluster = hit->dcluster; *cached_fclus = cid->fcluster + offset; *cached_dclus = cid->dcluster + offset; } spin_unlock(&ei->cache_lru_lock); return offset; } static struct exfat_cache *exfat_cache_merge(struct inode *inode, struct exfat_cache_id *new) { struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_cache *p; list_for_each_entry(p, &ei->cache_lru, cache_list) { /* Find the same part as "new" in cluster-chain. */ if (p->fcluster == new->fcluster) { if (new->nr_contig > p->nr_contig) p->nr_contig = new->nr_contig; return p; } } return NULL; } static void exfat_cache_add(struct inode *inode, struct exfat_cache_id *new) { struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_cache *cache, *tmp; if (new->fcluster == EXFAT_EOF_CLUSTER) /* dummy cache */ return; spin_lock(&ei->cache_lru_lock); if (new->id != EXFAT_CACHE_VALID && new->id != ei->cache_valid_id) goto unlock; /* this cache was invalidated */ cache = exfat_cache_merge(inode, new); if (cache == NULL) { if (ei->nr_caches < EXFAT_MAX_CACHE) { ei->nr_caches++; spin_unlock(&ei->cache_lru_lock); tmp = exfat_cache_alloc(); if (!tmp) { spin_lock(&ei->cache_lru_lock); ei->nr_caches--; spin_unlock(&ei->cache_lru_lock); return; } spin_lock(&ei->cache_lru_lock); cache = exfat_cache_merge(inode, new); if (cache != NULL) { ei->nr_caches--; exfat_cache_free(tmp); goto out_update_lru; } cache = tmp; } else { struct list_head *p = ei->cache_lru.prev; cache = list_entry(p, struct exfat_cache, cache_list); } cache->fcluster = new->fcluster; cache->dcluster = new->dcluster; cache->nr_contig = new->nr_contig; } out_update_lru: exfat_cache_update_lru(inode, cache); unlock: spin_unlock(&ei->cache_lru_lock); } /* * Cache invalidation occurs rarely, thus the LRU chain is not updated. It * fixes itself after a while. */ static void __exfat_cache_inval_inode(struct inode *inode) { struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_cache *cache; while (!list_empty(&ei->cache_lru)) { cache = list_entry(ei->cache_lru.next, struct exfat_cache, cache_list); list_del_init(&cache->cache_list); ei->nr_caches--; exfat_cache_free(cache); } /* Update. The copy of caches before this id is discarded. */ ei->cache_valid_id++; if (ei->cache_valid_id == EXFAT_CACHE_VALID) ei->cache_valid_id++; } void exfat_cache_inval_inode(struct inode *inode) { struct exfat_inode_info *ei = EXFAT_I(inode); spin_lock(&ei->cache_lru_lock); __exfat_cache_inval_inode(inode); spin_unlock(&ei->cache_lru_lock); } static inline int cache_contiguous(struct exfat_cache_id *cid, unsigned int dclus) { cid->nr_contig++; return cid->dcluster + cid->nr_contig == dclus; } static inline void cache_init(struct exfat_cache_id *cid, unsigned int fclus, unsigned int dclus) { cid->id = EXFAT_CACHE_VALID; cid->fcluster = fclus; cid->dcluster = dclus; cid->nr_contig = 0; } int exfat_get_cluster(struct inode *inode, unsigned int cluster, unsigned int *fclus, unsigned int *dclus, unsigned int *last_dclus, int allow_eof) { struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); unsigned int limit = sbi->num_clusters; struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_cache_id cid; unsigned int content; if (ei->start_clu == EXFAT_FREE_CLUSTER) { exfat_fs_error(sb, "invalid access to exfat cache (entry 0x%08x)", ei->start_clu); return -EIO; } *fclus = 0; *dclus = ei->start_clu; *last_dclus = *dclus; /* * Don`t use exfat_cache if zero offset or non-cluster allocation */ if (cluster == 0 || *dclus == EXFAT_EOF_CLUSTER) return 0; cache_init(&cid, EXFAT_EOF_CLUSTER, EXFAT_EOF_CLUSTER); if (exfat_cache_lookup(inode, cluster, &cid, fclus, dclus) == EXFAT_EOF_CLUSTER) { /* * dummy, always not contiguous * This is reinitialized by cache_init(), later. */ WARN_ON(cid.id != EXFAT_CACHE_VALID || cid.fcluster != EXFAT_EOF_CLUSTER || cid.dcluster != EXFAT_EOF_CLUSTER || cid.nr_contig != 0); } if (*fclus == cluster) return 0; while (*fclus < cluster) { /* prevent the infinite loop of cluster chain */ if (*fclus > limit) { exfat_fs_error(sb, "detected the cluster chain loop (i_pos %u)", (*fclus)); return -EIO; } if (exfat_ent_get(sb, *dclus, &content)) return -EIO; *last_dclus = *dclus; *dclus = content; (*fclus)++; if (content == EXFAT_EOF_CLUSTER) { if (!allow_eof) { exfat_fs_error(sb, "invalid cluster chain (i_pos %u, last_clus 0x%08x is EOF)", *fclus, (*last_dclus)); return -EIO; } break; } if (!cache_contiguous(&cid, *dclus)) cache_init(&cid, *fclus, *dclus); } exfat_cache_add(inode, &cid); return 0; } |
| 9 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key * numbers and masks have sufficient capacity. */ #define arch_max_pkey() (cpu_feature_enabled(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { return cpu_feature_enabled(X86_FEATURE_OSPKE); } /* * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); } extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey); static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return 0; return __arch_override_mprotect_pkey(vma, prot, pkey); } #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) #define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) #define mm_set_pkey_allocated(mm, pkey) do { \ mm_pkey_allocation_map(mm) |= (1U << pkey); \ } while (0) #define mm_set_pkey_free(mm, pkey) do { \ mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ } while (0) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned * from pkey_alloc() or pkey 0 which is allocated * implicitly when the mm is created. */ if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; /* * The exec-only pkey is set in the allocation map, but * is not available to any of the user interfaces like * mprotect_pkey(). */ if (pkey == mm->context.execute_only_pkey) return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } /* * Returns a positive, 4-bit key on success, or -1 on failure. */ static inline int mm_pkey_alloc(struct mm_struct *mm) { /* * Note: this is the one and only place we make sure * that the pkey is valid as far as the hardware is * concerned. The rest of the kernel trusts that * only good, valid pkeys come out of here. */ u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); int ret; /* * Are we out of pkeys? We must handle this specially * because ffz() behavior is undefined if there are no * zeros. */ if (mm_pkey_allocation_map(mm) == all_pkeys_mask) return -1; ret = ffz(mm_pkey_allocation_map(mm)); mm_set_pkey_allocated(mm, ret); return ret; } static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; mm_set_pkey_free(mm, pkey); return 0; } static inline int vma_pkey(struct vm_area_struct *vma) { unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3; return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; } #endif /*_ASM_X86_PKEYS_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_BLOCK_RSV_H #define BTRFS_BLOCK_RSV_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/spinlock.h> struct btrfs_trans_handle; struct btrfs_root; struct btrfs_space_info; struct btrfs_block_rsv; struct btrfs_fs_info; enum btrfs_reserve_flush_enum; /* * Types of block reserves */ enum btrfs_rsv_type { BTRFS_BLOCK_RSV_GLOBAL, BTRFS_BLOCK_RSV_DELALLOC, BTRFS_BLOCK_RSV_TRANS, BTRFS_BLOCK_RSV_CHUNK, BTRFS_BLOCK_RSV_DELOPS, BTRFS_BLOCK_RSV_DELREFS, BTRFS_BLOCK_RSV_TREELOG, BTRFS_BLOCK_RSV_EMPTY, BTRFS_BLOCK_RSV_TEMP, }; struct btrfs_block_rsv { u64 size; u64 reserved; struct btrfs_space_info *space_info; spinlock_t lock; bool full; bool failfast; /* Block reserve type, one of BTRFS_BLOCK_RSV_* */ enum btrfs_rsv_type type:8; /* * Qgroup equivalent for @size @reserved * * Unlike normal @size/@reserved for inode rsv, qgroup doesn't care * about things like csum size nor how many tree blocks it will need to * reserve. * * Qgroup cares more about net change of the extent usage. * * So for one newly inserted file extent, in worst case it will cause * leaf split and level increase, nodesize for each file extent is * already too much. * * In short, qgroup_size/reserved is the upper limit of possible needed * qgroup metadata reservation. */ u64 qgroup_rsv_size; u64 qgroup_rsv_reserved; }; void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, enum btrfs_rsv_type type); void btrfs_init_root_block_rsv(struct btrfs_root *root); struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info, enum btrfs_rsv_type type); void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv, enum btrfs_rsv_type type); void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); int btrfs_block_rsv_add(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u64 num_bytes, enum btrfs_reserve_flush_enum flush); int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_percent); int btrfs_block_rsv_refill(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u64 num_bytes, enum btrfs_reserve_flush_enum flush); int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv, struct btrfs_block_rsv *dst_rsv, u64 num_bytes, bool update_size); int btrfs_block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); void btrfs_block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes, bool update_size); u64 btrfs_block_rsv_release(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u64 num_bytes, u64 *qgroup_to_release); void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info); void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info); void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info); struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize); int btrfs_check_trunc_cache_free_space(const struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); static inline void btrfs_unuse_block_rsv(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u32 blocksize) { btrfs_block_rsv_add_bytes(block_rsv, blocksize, false); btrfs_block_rsv_release(fs_info, block_rsv, 0, NULL); } /* * Fast path to check if the reserve is full, may be carefully used outside of * locks. */ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv) { return data_race(rsv->full); } /* * Get the reserved mount of a block reserve in a context where getting a stale * value is acceptable, instead of accessing it directly and trigger data race * warning from KCSAN. */ static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv) { u64 ret; spin_lock(&rsv->lock); ret = rsv->reserved; spin_unlock(&rsv->lock); return ret; } /* * Get the size of a block reserve in a context where getting a stale value is * acceptable, instead of accessing it directly and trigger data race warning * from KCSAN. */ static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv) { u64 ret; spin_lock(&rsv->lock); ret = rsv->size; spin_unlock(&rsv->lock); return ret; } #endif /* BTRFS_BLOCK_RSV_H */ |
| 178 177 3 81 305 3 174 217 7 98 3 48 1 29 29 6 2 28 5 56 54 6 10 67 56 41 20 12 4 29 8 27 28 8 3 12 7 8 51 51 51 50 21 21 21 5 20 19 19 19 95 95 95 6 61 15 178 178 177 1 2 2 1 178 164 14 145 80 79 138 7 62 63 5 54 15 56 4 8 62 5 49 49 49 49 1 1 49 27 27 49 49 20 46 1 1 1 48 48 17 11 6 6 6 67 1 8 66 14 67 17 1 15 1 1 1 1 16 1 16 1 26 27 49 47 4 37 51 6 2 3 64 5 39 50 4 1 1 2 1 78 5 8 8 8 1 2 8 211 210 191 185 12 77 78 64 64 9 1 8 31 26 5 49 49 63 58 5 9 7 2 14 14 2 4 2 14 55 55 7 7 55 197 197 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * f2fs extent cache support * * Copyright (c) 2015 Motorola Mobility * Copyright (c) 2015 Samsung Electronics * Authors: Jaegeuk Kim <jaegeuk@kernel.org> * Chao Yu <chao2.yu@samsung.com> * * block_age-based extent cache added by: * Copyright (c) 2022 xiaomi Co., Ltd. * http://www.xiaomi.com/ */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include "f2fs.h" #include "node.h" #include <trace/events/f2fs.h> bool sanity_check_extent_cache(struct inode *inode, struct folio *ifolio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_extent *i_ext = &F2FS_INODE(ifolio)->i_ext; struct extent_info ei; int devi; get_read_extent_info(&ei, i_ext); if (!ei.len) return true; if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) || !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1, DATA_GENERIC_ENHANCE)) { f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix", __func__, inode->i_ino, ei.blk, ei.fofs, ei.len); return false; } if (!IS_DEVICE_ALIASING(inode)) return true; for (devi = 0; devi < sbi->s_ndevs; devi++) { if (FDEV(devi).start_blk != ei.blk || FDEV(devi).end_blk != ei.blk + ei.len - 1) continue; if (devi == 0) { f2fs_warn(sbi, "%s: inode (ino=%lx) is an alias of meta device", __func__, inode->i_ino); return false; } if (bdev_is_zoned(FDEV(devi).bdev)) { f2fs_warn(sbi, "%s: device alias inode (ino=%lx)'s extent info " "[%u, %u, %u] maps to zoned block device", __func__, inode->i_ino, ei.blk, ei.fofs, ei.len); return false; } return true; } f2fs_warn(sbi, "%s: device alias inode (ino=%lx)'s extent info " "[%u, %u, %u] is inconsistent w/ any devices", __func__, inode->i_ino, ei.blk, ei.fofs, ei.len); return false; } static void __set_extent_info(struct extent_info *ei, unsigned int fofs, unsigned int len, block_t blk, bool keep_clen, unsigned long age, unsigned long last_blocks, enum extent_type type) { ei->fofs = fofs; ei->len = len; if (type == EX_READ) { ei->blk = blk; if (keep_clen) return; #ifdef CONFIG_F2FS_FS_COMPRESSION ei->c_len = 0; #endif } else if (type == EX_BLOCK_AGE) { ei->age = age; ei->last_blocks = last_blocks; } } static bool __init_may_extent_tree(struct inode *inode, enum extent_type type) { if (type == EX_READ) return test_opt(F2FS_I_SB(inode), READ_EXTENT_CACHE) && S_ISREG(inode->i_mode); if (type == EX_BLOCK_AGE) return test_opt(F2FS_I_SB(inode), AGE_EXTENT_CACHE) && (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)); return false; } static bool __may_extent_tree(struct inode *inode, enum extent_type type) { if (IS_DEVICE_ALIASING(inode) && type == EX_READ) return true; /* * for recovered files during mount do not create extents * if shrinker is not registered. */ if (list_empty(&F2FS_I_SB(inode)->s_list)) return false; if (!__init_may_extent_tree(inode, type)) return false; if (type == EX_READ) { if (is_inode_flag_set(inode, FI_NO_EXTENT)) return false; if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && !f2fs_sb_has_readonly(F2FS_I_SB(inode))) return false; } else if (type == EX_BLOCK_AGE) { if (is_inode_flag_set(inode, FI_COMPRESSED_FILE)) return false; if (file_is_cold(inode)) return false; } return true; } static void __try_update_largest_extent(struct extent_tree *et, struct extent_node *en) { if (et->type != EX_READ) return; if (en->ei.len <= et->largest.len) return; et->largest = en->ei; et->largest_updated = true; } static bool __is_extent_mergeable(struct extent_info *back, struct extent_info *front, enum extent_type type) { if (type == EX_READ) { #ifdef CONFIG_F2FS_FS_COMPRESSION if (back->c_len && back->len != back->c_len) return false; if (front->c_len && front->len != front->c_len) return false; #endif return (back->fofs + back->len == front->fofs && back->blk + back->len == front->blk); } else if (type == EX_BLOCK_AGE) { return (back->fofs + back->len == front->fofs && abs(back->age - front->age) <= SAME_AGE_REGION && abs(back->last_blocks - front->last_blocks) <= SAME_AGE_REGION); } return false; } static bool __is_back_mergeable(struct extent_info *cur, struct extent_info *back, enum extent_type type) { return __is_extent_mergeable(back, cur, type); } static bool __is_front_mergeable(struct extent_info *cur, struct extent_info *front, enum extent_type type) { return __is_extent_mergeable(cur, front, type); } static struct extent_node *__lookup_extent_node(struct rb_root_cached *root, struct extent_node *cached_en, unsigned int fofs) { struct rb_node *node = root->rb_root.rb_node; struct extent_node *en; /* check a cached entry */ if (cached_en && cached_en->ei.fofs <= fofs && cached_en->ei.fofs + cached_en->ei.len > fofs) return cached_en; /* check rb_tree */ while (node) { en = rb_entry(node, struct extent_node, rb_node); if (fofs < en->ei.fofs) node = node->rb_left; else if (fofs >= en->ei.fofs + en->ei.len) node = node->rb_right; else return en; } return NULL; } /* * lookup rb entry in position of @fofs in rb-tree, * if hit, return the entry, otherwise, return NULL * @prev_ex: extent before fofs * @next_ex: extent after fofs * @insert_p: insert point for new extent at fofs * in order to simplify the insertion after. * tree must stay unchanged between lookup and insertion. */ static struct extent_node *__lookup_extent_node_ret(struct rb_root_cached *root, struct extent_node *cached_en, unsigned int fofs, struct extent_node **prev_entry, struct extent_node **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent, bool *leftmost) { struct rb_node **pnode = &root->rb_root.rb_node; struct rb_node *parent = NULL, *tmp_node; struct extent_node *en = cached_en; *insert_p = NULL; *insert_parent = NULL; *prev_entry = NULL; *next_entry = NULL; if (RB_EMPTY_ROOT(&root->rb_root)) return NULL; if (en && en->ei.fofs <= fofs && en->ei.fofs + en->ei.len > fofs) goto lookup_neighbors; *leftmost = true; while (*pnode) { parent = *pnode; en = rb_entry(*pnode, struct extent_node, rb_node); if (fofs < en->ei.fofs) { pnode = &(*pnode)->rb_left; } else if (fofs >= en->ei.fofs + en->ei.len) { pnode = &(*pnode)->rb_right; *leftmost = false; } else { goto lookup_neighbors; } } *insert_p = pnode; *insert_parent = parent; en = rb_entry(parent, struct extent_node, rb_node); tmp_node = parent; if (parent && fofs > en->ei.fofs) tmp_node = rb_next(parent); *next_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node); tmp_node = parent; if (parent && fofs < en->ei.fofs) tmp_node = rb_prev(parent); *prev_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node); return NULL; lookup_neighbors: if (fofs == en->ei.fofs) { /* lookup prev node for merging backward later */ tmp_node = rb_prev(&en->rb_node); *prev_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node); } if (fofs == en->ei.fofs + en->ei.len - 1) { /* lookup next node for merging frontward later */ tmp_node = rb_next(&en->rb_node); *next_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node); } return en; } static struct kmem_cache *extent_tree_slab; static struct kmem_cache *extent_node_slab; static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct rb_node *parent, struct rb_node **p, bool leftmost) { struct extent_tree_info *eti = &sbi->extent_tree[et->type]; struct extent_node *en; en = f2fs_kmem_cache_alloc(extent_node_slab, GFP_ATOMIC, false, sbi); if (!en) return NULL; en->ei = *ei; INIT_LIST_HEAD(&en->list); en->et = et; rb_link_node(&en->rb_node, parent, p); rb_insert_color_cached(&en->rb_node, &et->root, leftmost); atomic_inc(&et->node_cnt); atomic_inc(&eti->total_ext_node); return en; } static void __detach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_node *en) { struct extent_tree_info *eti = &sbi->extent_tree[et->type]; rb_erase_cached(&en->rb_node, &et->root); atomic_dec(&et->node_cnt); atomic_dec(&eti->total_ext_node); if (et->cached_en == en) et->cached_en = NULL; kmem_cache_free(extent_node_slab, en); } /* * Flow to release an extent_node: * 1. list_del_init * 2. __detach_extent_node * 3. kmem_cache_free. */ static void __release_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_node *en) { struct extent_tree_info *eti = &sbi->extent_tree[et->type]; spin_lock(&eti->extent_lock); f2fs_bug_on(sbi, list_empty(&en->list)); list_del_init(&en->list); spin_unlock(&eti->extent_lock); __detach_extent_node(sbi, et, en); } static struct extent_tree *__grab_extent_tree(struct inode *inode, enum extent_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree_info *eti = &sbi->extent_tree[type]; struct extent_tree *et; nid_t ino = inode->i_ino; mutex_lock(&eti->extent_tree_lock); et = radix_tree_lookup(&eti->extent_tree_root, ino); if (!et) { et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS, true, NULL); f2fs_radix_tree_insert(&eti->extent_tree_root, ino, et); memset(et, 0, sizeof(struct extent_tree)); et->ino = ino; et->type = type; et->root = RB_ROOT_CACHED; et->cached_en = NULL; rwlock_init(&et->lock); INIT_LIST_HEAD(&et->list); atomic_set(&et->node_cnt, 0); atomic_inc(&eti->total_ext_tree); } else { atomic_dec(&eti->total_zombie_tree); list_del_init(&et->list); } mutex_unlock(&eti->extent_tree_lock); /* never died until evict_inode */ F2FS_I(inode)->extent_tree[type] = et; return et; } static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, unsigned int nr_shrink) { struct rb_node *node, *next; struct extent_node *en; unsigned int count; node = rb_first_cached(&et->root); for (count = 0; node && count < nr_shrink; count++) { next = rb_next(node); en = rb_entry(node, struct extent_node, rb_node); __release_extent_node(sbi, et, en); node = next; } return count; } static void __drop_largest_extent(struct extent_tree *et, pgoff_t fofs, unsigned int len) { if (fofs < (pgoff_t)et->largest.fofs + et->largest.len && fofs + len > et->largest.fofs) { et->largest.len = 0; et->largest_updated = true; } } void f2fs_init_read_extent_tree(struct inode *inode, struct folio *ifolio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree_info *eti = &sbi->extent_tree[EX_READ]; struct f2fs_extent *i_ext = &F2FS_INODE(ifolio)->i_ext; struct extent_tree *et; struct extent_node *en; struct extent_info ei = {0}; if (!__may_extent_tree(inode, EX_READ)) { /* drop largest read extent */ if (i_ext->len) { f2fs_folio_wait_writeback(ifolio, NODE, true, true); i_ext->len = 0; folio_mark_dirty(ifolio); } set_inode_flag(inode, FI_NO_EXTENT); return; } et = __grab_extent_tree(inode, EX_READ); get_read_extent_info(&ei, i_ext); write_lock(&et->lock); if (atomic_read(&et->node_cnt) || !ei.len) goto skip; if (IS_DEVICE_ALIASING(inode)) { et->largest = ei; goto skip; } en = __attach_extent_node(sbi, et, &ei, NULL, &et->root.rb_root.rb_node, true); if (en) { et->largest = en->ei; et->cached_en = en; spin_lock(&eti->extent_lock); list_add_tail(&en->list, &eti->extent_list); spin_unlock(&eti->extent_lock); } skip: /* Let's drop, if checkpoint got corrupted. */ if (f2fs_cp_error(sbi)) { et->largest.len = 0; et->largest_updated = true; } write_unlock(&et->lock); } void f2fs_init_age_extent_tree(struct inode *inode) { if (!__init_may_extent_tree(inode, EX_BLOCK_AGE)) return; __grab_extent_tree(inode, EX_BLOCK_AGE); } void f2fs_init_extent_tree(struct inode *inode) { /* initialize read cache */ if (__init_may_extent_tree(inode, EX_READ)) __grab_extent_tree(inode, EX_READ); /* initialize block age cache */ if (__init_may_extent_tree(inode, EX_BLOCK_AGE)) __grab_extent_tree(inode, EX_BLOCK_AGE); } static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_info *ei, enum extent_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree_info *eti = &sbi->extent_tree[type]; struct extent_tree *et = F2FS_I(inode)->extent_tree[type]; struct extent_node *en; bool ret = false; if (!et) return false; trace_f2fs_lookup_extent_tree_start(inode, pgofs, type); read_lock(&et->lock); if (type == EX_READ && et->largest.fofs <= pgofs && (pgoff_t)et->largest.fofs + et->largest.len > pgofs) { *ei = et->largest; ret = true; stat_inc_largest_node_hit(sbi); goto out; } if (IS_DEVICE_ALIASING(inode)) { ret = false; goto out; } en = __lookup_extent_node(&et->root, et->cached_en, pgofs); if (!en) goto out; if (en == et->cached_en) stat_inc_cached_node_hit(sbi, type); else stat_inc_rbtree_node_hit(sbi, type); *ei = en->ei; spin_lock(&eti->extent_lock); if (!list_empty(&en->list)) { list_move_tail(&en->list, &eti->extent_list); et->cached_en = en; } spin_unlock(&eti->extent_lock); ret = true; out: stat_inc_total_hit(sbi, type); read_unlock(&et->lock); if (type == EX_READ) trace_f2fs_lookup_read_extent_tree_end(inode, pgofs, ei); else if (type == EX_BLOCK_AGE) trace_f2fs_lookup_age_extent_tree_end(inode, pgofs, ei); return ret; } static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct extent_node *prev_ex, struct extent_node *next_ex) { struct extent_tree_info *eti = &sbi->extent_tree[et->type]; struct extent_node *en = NULL; if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei, et->type)) { prev_ex->ei.len += ei->len; ei = &prev_ex->ei; en = prev_ex; } if (next_ex && __is_front_mergeable(ei, &next_ex->ei, et->type)) { next_ex->ei.fofs = ei->fofs; next_ex->ei.len += ei->len; if (et->type == EX_READ) next_ex->ei.blk = ei->blk; if (en) __release_extent_node(sbi, et, prev_ex); en = next_ex; } if (!en) return NULL; __try_update_largest_extent(et, en); spin_lock(&eti->extent_lock); if (!list_empty(&en->list)) { list_move_tail(&en->list, &eti->extent_list); et->cached_en = en; } spin_unlock(&eti->extent_lock); return en; } static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct rb_node **insert_p, struct rb_node *insert_parent, bool leftmost) { struct extent_tree_info *eti = &sbi->extent_tree[et->type]; struct rb_node **p = &et->root.rb_root.rb_node; struct rb_node *parent = NULL; struct extent_node *en = NULL; if (insert_p && insert_parent) { parent = insert_parent; p = insert_p; goto do_insert; } leftmost = true; /* look up extent_node in the rb tree */ while (*p) { parent = *p; en = rb_entry(parent, struct extent_node, rb_node); if (ei->fofs < en->ei.fofs) { p = &(*p)->rb_left; } else if (ei->fofs >= en->ei.fofs + en->ei.len) { p = &(*p)->rb_right; leftmost = false; } else { f2fs_err_ratelimited(sbi, "%s: corrupted extent, type: %d, " "extent node in rb tree [%u, %u, %u], age [%llu, %llu], " "extent node to insert [%u, %u, %u], age [%llu, %llu]", __func__, et->type, en->ei.fofs, en->ei.blk, en->ei.len, en->ei.age, en->ei.last_blocks, ei->fofs, ei->blk, ei->len, ei->age, ei->last_blocks); f2fs_bug_on(sbi, 1); return NULL; } } do_insert: en = __attach_extent_node(sbi, et, ei, parent, p, leftmost); if (!en) return NULL; __try_update_largest_extent(et, en); /* update in global extent list */ spin_lock(&eti->extent_lock); list_add_tail(&en->list, &eti->extent_list); et->cached_en = en; spin_unlock(&eti->extent_lock); return en; } static unsigned int __destroy_extent_node(struct inode *inode, enum extent_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree[type]; unsigned int nr_shrink = type == EX_READ ? READ_EXTENT_CACHE_SHRINK_NUMBER : AGE_EXTENT_CACHE_SHRINK_NUMBER; unsigned int node_cnt = 0; if (!et || !atomic_read(&et->node_cnt)) return 0; while (atomic_read(&et->node_cnt)) { write_lock(&et->lock); node_cnt += __free_extent_tree(sbi, et, nr_shrink); write_unlock(&et->lock); } f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); return node_cnt; } static void __update_extent_tree_range(struct inode *inode, struct extent_info *tei, enum extent_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree[type]; struct extent_node *en = NULL, *en1 = NULL; struct extent_node *prev_en = NULL, *next_en = NULL; struct extent_info ei, dei, prev; struct rb_node **insert_p = NULL, *insert_parent = NULL; unsigned int fofs = tei->fofs, len = tei->len; unsigned int end = fofs + len; bool updated = false; bool leftmost = false; if (!et) return; if (unlikely(len == 0)) { f2fs_err_ratelimited(sbi, "%s: extent len is zero, type: %d, " "extent [%u, %u, %u], age [%llu, %llu]", __func__, type, tei->fofs, tei->blk, tei->len, tei->age, tei->last_blocks); f2fs_bug_on(sbi, 1); return; } if (type == EX_READ) trace_f2fs_update_read_extent_tree_range(inode, fofs, len, tei->blk, 0); else if (type == EX_BLOCK_AGE) trace_f2fs_update_age_extent_tree_range(inode, fofs, len, tei->age, tei->last_blocks); write_lock(&et->lock); if (type == EX_READ) { if (is_inode_flag_set(inode, FI_NO_EXTENT)) { write_unlock(&et->lock); return; } prev = et->largest; dei.len = 0; /* * drop largest extent before lookup, in case it's already * been shrunk from extent tree */ __drop_largest_extent(et, fofs, len); } /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ en = __lookup_extent_node_ret(&et->root, et->cached_en, fofs, &prev_en, &next_en, &insert_p, &insert_parent, &leftmost); if (!en) en = next_en; /* 2. invalidate all extent nodes in range [fofs, fofs + len - 1] */ while (en && en->ei.fofs < end) { unsigned int org_end; int parts = 0; /* # of parts current extent split into */ next_en = en1 = NULL; dei = en->ei; org_end = dei.fofs + dei.len; f2fs_bug_on(sbi, fofs >= org_end); if (fofs > dei.fofs && (type != EX_READ || fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN)) { en->ei.len = fofs - en->ei.fofs; prev_en = en; parts = 1; } if (end < org_end && (type != EX_READ || (org_end - end >= F2FS_MIN_EXTENT_LEN && atomic_read(&et->node_cnt) < sbi->max_read_extent_count))) { if (parts) { __set_extent_info(&ei, end, org_end - end, end - dei.fofs + dei.blk, false, dei.age, dei.last_blocks, type); en1 = __insert_extent_tree(sbi, et, &ei, NULL, NULL, true); next_en = en1; } else { __set_extent_info(&en->ei, end, en->ei.len - (end - dei.fofs), en->ei.blk + (end - dei.fofs), true, dei.age, dei.last_blocks, type); next_en = en; } parts++; } if (!next_en) { struct rb_node *node = rb_next(&en->rb_node); next_en = rb_entry_safe(node, struct extent_node, rb_node); } if (parts) __try_update_largest_extent(et, en); else __release_extent_node(sbi, et, en); /* * if original extent is split into zero or two parts, extent * tree has been altered by deletion or insertion, therefore * invalidate pointers regard to tree. */ if (parts != 1) { insert_p = NULL; insert_parent = NULL; } en = next_en; } if (type == EX_BLOCK_AGE) goto update_age_extent_cache; /* 3. update extent in read extent cache */ BUG_ON(type != EX_READ); if (tei->blk) { __set_extent_info(&ei, fofs, len, tei->blk, false, 0, 0, EX_READ); if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en)) __insert_extent_tree(sbi, et, &ei, insert_p, insert_parent, leftmost); /* give up extent_cache, if split and small updates happen */ if (dei.len >= 1 && prev.len < F2FS_MIN_EXTENT_LEN && et->largest.len < F2FS_MIN_EXTENT_LEN) { et->largest.len = 0; et->largest_updated = true; set_inode_flag(inode, FI_NO_EXTENT); } } if (et->largest_updated) { et->largest_updated = false; updated = true; } goto out_read_extent_cache; update_age_extent_cache: if (!tei->last_blocks) goto out_read_extent_cache; __set_extent_info(&ei, fofs, len, 0, false, tei->age, tei->last_blocks, EX_BLOCK_AGE); if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en)) __insert_extent_tree(sbi, et, &ei, insert_p, insert_parent, leftmost); out_read_extent_cache: write_unlock(&et->lock); if (is_inode_flag_set(inode, FI_NO_EXTENT)) __destroy_extent_node(inode, EX_READ); if (updated) f2fs_mark_inode_dirty_sync(inode, true); } #ifdef CONFIG_F2FS_FS_COMPRESSION void f2fs_update_read_extent_tree_range_compressed(struct inode *inode, pgoff_t fofs, block_t blkaddr, unsigned int llen, unsigned int c_len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; struct extent_node *en = NULL; struct extent_node *prev_en = NULL, *next_en = NULL; struct extent_info ei; struct rb_node **insert_p = NULL, *insert_parent = NULL; bool leftmost = false; trace_f2fs_update_read_extent_tree_range(inode, fofs, llen, blkaddr, c_len); /* it is safe here to check FI_NO_EXTENT w/o et->lock in ro image */ if (is_inode_flag_set(inode, FI_NO_EXTENT)) return; write_lock(&et->lock); en = __lookup_extent_node_ret(&et->root, et->cached_en, fofs, &prev_en, &next_en, &insert_p, &insert_parent, &leftmost); if (en) goto unlock_out; __set_extent_info(&ei, fofs, llen, blkaddr, true, 0, 0, EX_READ); ei.c_len = c_len; if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en)) __insert_extent_tree(sbi, et, &ei, insert_p, insert_parent, leftmost); unlock_out: write_unlock(&et->lock); } #endif static unsigned long long __calculate_block_age(struct f2fs_sb_info *sbi, unsigned long long new, unsigned long long old) { unsigned int rem_old, rem_new; unsigned long long res; unsigned int weight = sbi->last_age_weight; res = div_u64_rem(new, 100, &rem_new) * (100 - weight) + div_u64_rem(old, 100, &rem_old) * weight; if (rem_new) res += rem_new * (100 - weight) / 100; if (rem_old) res += rem_old * weight / 100; return res; } /* This returns a new age and allocated blocks in ei */ static int __get_new_block_age(struct inode *inode, struct extent_info *ei, block_t blkaddr) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); loff_t f_size = i_size_read(inode); unsigned long long cur_blocks = atomic64_read(&sbi->allocated_data_blocks); struct extent_info tei = *ei; /* only fofs and len are valid */ /* * When I/O is not aligned to a PAGE_SIZE, update will happen to the last * file block even in seq write. So don't record age for newly last file * block here. */ if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) && blkaddr == NEW_ADDR) return -EINVAL; if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) { unsigned long long cur_age; if (cur_blocks >= tei.last_blocks) cur_age = cur_blocks - tei.last_blocks; else /* allocated_data_blocks overflow */ cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks; if (tei.age) ei->age = __calculate_block_age(sbi, cur_age, tei.age); else ei->age = cur_age; ei->last_blocks = cur_blocks; WARN_ON(ei->age > cur_blocks); return 0; } f2fs_bug_on(sbi, blkaddr == NULL_ADDR); /* the data block was allocated for the first time */ if (blkaddr == NEW_ADDR) goto out; if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) return -EINVAL; out: /* * init block age with zero, this can happen when the block age extent * was reclaimed due to memory constraint or system reboot */ ei->age = 0; ei->last_blocks = cur_blocks; return 0; } static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type) { struct extent_info ei = {}; if (!__may_extent_tree(dn->inode, type)) return; ei.fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_folio), dn->inode) + dn->ofs_in_node; ei.len = 1; if (type == EX_READ) { if (dn->data_blkaddr == NEW_ADDR) ei.blk = NULL_ADDR; else ei.blk = dn->data_blkaddr; } else if (type == EX_BLOCK_AGE) { if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr)) return; } __update_extent_tree_range(dn->inode, &ei, type); } static unsigned int __shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink, enum extent_type type) { struct extent_tree_info *eti = &sbi->extent_tree[type]; struct extent_tree *et, *next; struct extent_node *en; unsigned int node_cnt = 0, tree_cnt = 0; int remained; if (!atomic_read(&eti->total_zombie_tree)) goto free_node; if (!mutex_trylock(&eti->extent_tree_lock)) goto out; /* 1. remove unreferenced extent tree */ list_for_each_entry_safe(et, next, &eti->zombie_list, list) { if (atomic_read(&et->node_cnt)) { write_lock(&et->lock); node_cnt += __free_extent_tree(sbi, et, nr_shrink - node_cnt - tree_cnt); write_unlock(&et->lock); } if (atomic_read(&et->node_cnt)) goto unlock_out; list_del_init(&et->list); radix_tree_delete(&eti->extent_tree_root, et->ino); kmem_cache_free(extent_tree_slab, et); atomic_dec(&eti->total_ext_tree); atomic_dec(&eti->total_zombie_tree); tree_cnt++; if (node_cnt + tree_cnt >= nr_shrink) goto unlock_out; cond_resched(); } mutex_unlock(&eti->extent_tree_lock); free_node: /* 2. remove LRU extent entries */ if (!mutex_trylock(&eti->extent_tree_lock)) goto out; remained = nr_shrink - (node_cnt + tree_cnt); spin_lock(&eti->extent_lock); for (; remained > 0; remained--) { if (list_empty(&eti->extent_list)) break; en = list_first_entry(&eti->extent_list, struct extent_node, list); et = en->et; if (!write_trylock(&et->lock)) { /* refresh this extent node's position in extent list */ list_move_tail(&en->list, &eti->extent_list); continue; } list_del_init(&en->list); spin_unlock(&eti->extent_lock); __detach_extent_node(sbi, et, en); write_unlock(&et->lock); node_cnt++; spin_lock(&eti->extent_lock); } spin_unlock(&eti->extent_lock); unlock_out: mutex_unlock(&eti->extent_tree_lock); out: trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt, type); return node_cnt + tree_cnt; } /* read extent cache operations */ bool f2fs_lookup_read_extent_cache(struct inode *inode, pgoff_t pgofs, struct extent_info *ei) { if (!__may_extent_tree(inode, EX_READ)) return false; return __lookup_extent_tree(inode, pgofs, ei, EX_READ); } bool f2fs_lookup_read_extent_cache_block(struct inode *inode, pgoff_t index, block_t *blkaddr) { struct extent_info ei = {}; if (!f2fs_lookup_read_extent_cache(inode, index, &ei)) return false; *blkaddr = ei.blk + index - ei.fofs; return true; } void f2fs_update_read_extent_cache(struct dnode_of_data *dn) { return __update_extent_cache(dn, EX_READ); } void f2fs_update_read_extent_cache_range(struct dnode_of_data *dn, pgoff_t fofs, block_t blkaddr, unsigned int len) { struct extent_info ei = { .fofs = fofs, .len = len, .blk = blkaddr, }; if (!__may_extent_tree(dn->inode, EX_READ)) return; __update_extent_tree_range(dn->inode, &ei, EX_READ); } unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) { if (!test_opt(sbi, READ_EXTENT_CACHE)) return 0; return __shrink_extent_tree(sbi, nr_shrink, EX_READ); } /* block age extent cache operations */ bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs, struct extent_info *ei) { if (!__may_extent_tree(inode, EX_BLOCK_AGE)) return false; return __lookup_extent_tree(inode, pgofs, ei, EX_BLOCK_AGE); } void f2fs_update_age_extent_cache(struct dnode_of_data *dn) { return __update_extent_cache(dn, EX_BLOCK_AGE); } void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn, pgoff_t fofs, unsigned int len) { struct extent_info ei = { .fofs = fofs, .len = len, }; if (!__may_extent_tree(dn->inode, EX_BLOCK_AGE)) return; __update_extent_tree_range(dn->inode, &ei, EX_BLOCK_AGE); } unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) { if (!test_opt(sbi, AGE_EXTENT_CACHE)) return 0; return __shrink_extent_tree(sbi, nr_shrink, EX_BLOCK_AGE); } void f2fs_destroy_extent_node(struct inode *inode) { __destroy_extent_node(inode, EX_READ); __destroy_extent_node(inode, EX_BLOCK_AGE); } static void __drop_extent_tree(struct inode *inode, enum extent_type type) { struct extent_tree *et = F2FS_I(inode)->extent_tree[type]; bool updated = false; if (!__may_extent_tree(inode, type)) return; write_lock(&et->lock); if (type == EX_READ) { set_inode_flag(inode, FI_NO_EXTENT); if (et->largest.len) { et->largest.len = 0; updated = true; } } write_unlock(&et->lock); __destroy_extent_node(inode, type); if (updated) f2fs_mark_inode_dirty_sync(inode, true); } void f2fs_drop_extent_tree(struct inode *inode) { __drop_extent_tree(inode, EX_READ); __drop_extent_tree(inode, EX_BLOCK_AGE); } static void __destroy_extent_tree(struct inode *inode, enum extent_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree_info *eti = &sbi->extent_tree[type]; struct extent_tree *et = F2FS_I(inode)->extent_tree[type]; unsigned int node_cnt = 0; if (!et) return; if (inode->i_nlink && !is_bad_inode(inode) && atomic_read(&et->node_cnt)) { mutex_lock(&eti->extent_tree_lock); list_add_tail(&et->list, &eti->zombie_list); atomic_inc(&eti->total_zombie_tree); mutex_unlock(&eti->extent_tree_lock); return; } /* free all extent info belong to this extent tree */ node_cnt = __destroy_extent_node(inode, type); /* delete extent tree entry in radix tree */ mutex_lock(&eti->extent_tree_lock); f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); radix_tree_delete(&eti->extent_tree_root, inode->i_ino); kmem_cache_free(extent_tree_slab, et); atomic_dec(&eti->total_ext_tree); mutex_unlock(&eti->extent_tree_lock); F2FS_I(inode)->extent_tree[type] = NULL; trace_f2fs_destroy_extent_tree(inode, node_cnt, type); } void f2fs_destroy_extent_tree(struct inode *inode) { __destroy_extent_tree(inode, EX_READ); __destroy_extent_tree(inode, EX_BLOCK_AGE); } static void __init_extent_tree_info(struct extent_tree_info *eti) { INIT_RADIX_TREE(&eti->extent_tree_root, GFP_NOIO); mutex_init(&eti->extent_tree_lock); INIT_LIST_HEAD(&eti->extent_list); spin_lock_init(&eti->extent_lock); atomic_set(&eti->total_ext_tree, 0); INIT_LIST_HEAD(&eti->zombie_list); atomic_set(&eti->total_zombie_tree, 0); atomic_set(&eti->total_ext_node, 0); } void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi) { __init_extent_tree_info(&sbi->extent_tree[EX_READ]); __init_extent_tree_info(&sbi->extent_tree[EX_BLOCK_AGE]); /* initialize for block age extents */ atomic64_set(&sbi->allocated_data_blocks, 0); sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD; sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD; sbi->last_age_weight = LAST_AGE_WEIGHT; sbi->max_read_extent_count = DEF_MAX_READ_EXTENT_COUNT; } int __init f2fs_create_extent_cache(void) { extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", sizeof(struct extent_tree)); if (!extent_tree_slab) return -ENOMEM; extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node", sizeof(struct extent_node)); if (!extent_node_slab) { kmem_cache_destroy(extent_tree_slab); return -ENOMEM; } return 0; } void f2fs_destroy_extent_cache(void) { kmem_cache_destroy(extent_node_slab); kmem_cache_destroy(extent_tree_slab); } |
| 1499 1497 329 327 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/dir.c - sysfs core and dir operation implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #define pr_fmt(fmt) "sysfs: " fmt #include <linux/fs.h> #include <linux/kobject.h> #include <linux/slab.h> #include "sysfs.h" DEFINE_SPINLOCK(sysfs_symlink_target_lock); void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { char *buf; buf = kzalloc(PATH_MAX, GFP_KERNEL); if (buf) kernfs_path(parent, buf, PATH_MAX); pr_warn("cannot create duplicate filename '%s/%s'\n", buf, name); dump_stack(); kfree(buf); } /** * sysfs_create_dir_ns - create a directory for an object with a namespace tag * @kobj: object we're creating directory for * @ns: the namespace tag to use */ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { struct kernfs_node *parent, *kn; kuid_t uid; kgid_t gid; if (WARN_ON(!kobj)) return -EINVAL; if (kobj->parent) parent = kobj->parent->sd; else parent = sysfs_root_kn; if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid, kobj, ns); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, kobject_name(kobj)); return PTR_ERR(kn); } kobj->sd = kn; return 0; } /** * sysfs_remove_dir - remove an object's directory. * @kobj: object. * * The only thing special about this is that we remove any files in * the directory before we remove the directory, and we've inlined * what used to be sysfs_rmdir() below, instead of calling separately. */ void sysfs_remove_dir(struct kobject *kobj) { struct kernfs_node *kn = kobj->sd; /* * In general, kobject owner is responsible for ensuring removal * doesn't race with other operations and sysfs doesn't provide any * protection; however, when @kobj is used as a symlink target, the * symlinking entity usually doesn't own @kobj and thus has no * control over removal. @kobj->sd may be removed anytime * and symlink code may end up dereferencing an already freed node. * * sysfs_symlink_target_lock synchronizes @kobj->sd * disassociation against symlink operations so that symlink code * can safely dereference @kobj->sd. */ spin_lock(&sysfs_symlink_target_lock); kobj->sd = NULL; spin_unlock(&sysfs_symlink_target_lock); if (kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); kernfs_remove(kn); } } int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, const void *new_ns) { struct kernfs_node *parent; int ret; parent = kernfs_get_parent(kobj->sd); ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); kernfs_put(parent); return ret; } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns) { struct kernfs_node *kn = kobj->sd; struct kernfs_node *new_parent; new_parent = new_parent_kobj && new_parent_kobj->sd ? new_parent_kobj->sd : sysfs_root_kn; return kernfs_rename_ns(kn, new_parent, NULL, new_ns); } /** * sysfs_create_mount_point - create an always empty directory * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to add */ int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *kn, *parent = parent_kobj->sd; kn = kernfs_create_empty_dir(parent, name); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, name); return PTR_ERR(kn); } return 0; } EXPORT_SYMBOL_GPL(sysfs_create_mount_point); /** * sysfs_remove_mount_point - remove an always empty directory. * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to remove * */ void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *parent = parent_kobj->sd; kernfs_remove_by_name_ns(parent, name, NULL); } EXPORT_SYMBOL_GPL(sysfs_remove_mount_point); |
| 1 1 5 1 3 4 2 7 7 7 7 5 3 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 2 13 13 3 1 1 1 127 3 126 127 126 127 15 14 1 10 10 10 3 3 1 1 1 1 1 1 1 5 4 3 1 1 2 2 2 3 3 3 8 5 5 3 8 5 3 8 8 8 10 9 2 2 5 3 3 6 6 2 1 3 3 3 7 7 2 5 1 2 3 3 3 1 1 4 4 1 3 3 2 2 1 1 1 12 12 1 1 1 177 177 176 177 134 169 4 4 2 163 164 35 1 1 1 1 33 123 123 123 123 123 139 47 10 43 42 6 3 2 1 9 9 6 6 1 1 1 6 20 20 10 10 2 10 5 8 20 1 1 1 1 1 1 1 6 5 1 1 1 1 4 1 3 3 3 4 3 119 41 97 40 97 3 119 117 112 110 52 108 117 20 20 1 8 6 20 1 1 5 5 2 3 5 5 2 3 1 2 4 4 6 6 6 5 3 3 2 2 3 3 1 1 1 1 1 1 1 1 1 1 3 3 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 12 112 3 3 29 27 2 1 2 1 1 3 3 2 3 3 2 3 5 4 1 2 2 3 2 2 1 1 1 4 23 32 32 27 3 25 24 25 24 24 28 10 9 1 2 2 9 10 3 3 3 3 3 20 20 10 3 3 6 1 1 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/base.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc base directory handling functions * * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. * Instead of using magical inumbers to determine the kind of object * we allocate and fill in-core inodes upon lookup. They don't even * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. * * * Changelog: * 17-Jan-2005 * Allan Bezerra * Bruna Moreira <bruna.moreira@indt.org.br> * Edjard Mota <edjard.mota@indt.org.br> * Ilias Biris <ilias.biris@indt.org.br> * Mauricio Lin <mauricio.lin@indt.org.br> * * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * * A new process specific entry (smaps) included in /proc. It shows the * size of rss for each memory area. The maps entry lacks information * about physical memory size (rss) for each mapped file, i.e., * rss information for executables and library files. * This additional information is useful for any tools that need to know * about physical memory consumption for a process specific library. * * Changelog: * 21-Feb-2005 * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * Pud inclusion in the page table walking. * * ChangeLog: * 10-Mar-2005 * 10LE Instituto Nokia de Tecnologia - INdT: * A better way to walks through the page table as suggested by Hugh Dickins. * * Simo Piiroinen <simo.piiroinen@nokia.com>: * Smaps information related to shared, private, clean and dirty pages. * * Paul Mundt <paul.mundt@nokia.com>: * Overall revision about smaps. */ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/task_io_accounting_ops.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/generic-radix-tree.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> #include <linux/mnt_namespace.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> #include <linux/resource.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/printk.h> #include <linux/cache.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> #include <linux/nsproxy.h> #include <linux/oom.h> #include <linux/elf.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/fs_parser.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/debug.h> #include <linux/sched/stat.h> #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> #include <linux/cn_proc.h> #include <linux/ksm.h> #include <uapi/linux/lsm.h> #include <trace/events/oom.h> #include "internal.h" #include "fd.h" #include "../../lib/kstrtox.h" /* NOTE: * Implementing inode permission operations in /proc is almost * certainly an error. Permission checks need to happen during * each system call not at open time. The reason is that most of * what we wish to check for permissions in /proc varies at runtime. * * The classic example of a problem is opening file descriptors * in /proc for a task before it execs a suid executable. */ static u8 nlink_tid __ro_after_init; static u8 nlink_tgid __ro_after_init; enum proc_mem_force { PROC_MEM_FORCE_ALWAYS, PROC_MEM_FORCE_PTRACE, PROC_MEM_FORCE_NEVER }; static enum proc_mem_force proc_mem_force_override __ro_after_init = IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : PROC_MEM_FORCE_ALWAYS; static const struct constant_table proc_mem_force_table[] __initconst = { { "always", PROC_MEM_FORCE_ALWAYS }, { "ptrace", PROC_MEM_FORCE_PTRACE }, { "never", PROC_MEM_FORCE_NEVER }, { } }; static int __init early_proc_mem_force_override(char *buf) { if (!buf) return -EINVAL; /* * lookup_constant() defaults to proc_mem_force_override to preseve * the initial Kconfig choice in case an invalid param gets passed. */ proc_mem_force_override = lookup_constant(proc_mem_force_table, buf, proc_mem_force_override); return 0; } early_param("proc_mem.force_override", early_proc_mem_force_override); struct pid_entry { const char *name; unsigned int len; umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op; }; #define NOD(NAME, MODE, IOP, FOP, OP) { \ .name = (NAME), \ .len = sizeof(NAME) - 1, \ .mode = MODE, \ .iop = IOP, \ .fop = FOP, \ .op = OP, \ } #define DIR(NAME, MODE, iops, fops) \ NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} ) #define LNK(NAME, get_link) \ NOD(NAME, (S_IFLNK|S_IRWXUGO), \ &proc_pid_link_inode_operations, NULL, \ { .proc_get_link = get_link } ) #define REG(NAME, MODE, fops) \ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) #define ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } ) #define ATTR(LSMID, NAME, MODE) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_pid_attr_operations, \ { .lsmid = LSMID }) /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. */ static unsigned int __init pid_entry_nlink(const struct pid_entry *entries, unsigned int n) { unsigned int i; unsigned int count; count = 2; for (i = 0; i < n; ++i) { if (S_ISDIR(entries[i].mode)) ++count; } return count; } static int get_task_root(struct task_struct *task, struct path *root) { int result = -ENOENT; task_lock(task); if (task->fs) { get_fs_root(task->fs, root); result = 0; } task_unlock(task); return result; } static int proc_cwd_link(struct dentry *dentry, struct path *path) { struct task_struct *task = get_proc_task(d_inode(dentry)); int result = -ENOENT; if (task) { task_lock(task); if (task->fs) { get_fs_pwd(task->fs, path); result = 0; } task_unlock(task); put_task_struct(task); } return result; } static int proc_root_link(struct dentry *dentry, struct path *path) { struct task_struct *task = get_proc_task(d_inode(dentry)); int result = -ENOENT; if (task) { result = get_task_root(task, path); put_task_struct(task); } return result; } /* * If the user used setproctitle(), we just get the string from * user space at arg_start, and limit it to a maximum of one page. */ static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf, size_t count, unsigned long pos, unsigned long arg_start) { char *page; int ret, got; if (pos >= PAGE_SIZE) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON); if (got > 0) { int len = strnlen(page, got); /* Include the NUL character if it was found */ if (len < got) len++; if (len > pos) { len -= pos; if (len > count) len = count; len -= copy_to_user(buf, page+pos, len); if (!len) len = -EFAULT; ret = len; } } free_page((unsigned long)page); return ret; } static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, size_t count, loff_t *ppos) { unsigned long arg_start, arg_end, env_start, env_end; unsigned long pos, len; char *page, c; /* Check if process spawned far enough to have cmdline. */ if (!mm->env_end) return 0; spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); if (arg_start >= arg_end) return 0; /* * We allow setproctitle() to overwrite the argument * strings, and overflow past the original end. But * only when it overflows into the environment area. */ if (env_start != arg_end || env_end < env_start) env_start = env_end = arg_end; len = env_end - arg_start; /* We're not going to care if "*ppos" has high bits set */ pos = *ppos; if (pos >= len) return 0; if (count > len - pos) count = len - pos; if (!count) return 0; /* * Magical special case: if the argv[] end byte is not * zero, the user has overwritten it with setproctitle(3). * * Possible future enhancement: do this only once when * pos is 0, and set a flag in the 'struct file'. */ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c) return get_mm_proctitle(mm, buf, count, pos, arg_start); /* * For the non-setproctitle() case we limit things strictly * to the [arg_start, arg_end[ range. */ pos += arg_start; if (pos < arg_start || pos >= arg_end) return 0; if (count > arg_end - pos) count = arg_end - pos; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; len = 0; while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); got = access_remote_vm(mm, pos, page, size, FOLL_ANON); if (got <= 0) break; got -= copy_to_user(buf, page, got); if (unlikely(!got)) { if (!len) len = -EFAULT; break; } pos += got; buf += got; len += got; count -= got; } free_page((unsigned long)page); return len; } static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, size_t count, loff_t *pos) { struct mm_struct *mm; ssize_t ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); return ret; } static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct task_struct *tsk; ssize_t ret; BUG_ON(*pos < 0); tsk = get_proc_task(file_inode(file)); if (!tsk) return -ESRCH; ret = get_task_cmdline(tsk, buf, count, pos); put_task_struct(tsk); if (ret > 0) *pos += ret; return ret; } static const struct file_operations proc_pid_cmdline_ops = { .read = proc_pid_cmdline_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_KALLSYMS /* * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol to user space. */ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto print0; wchan = get_wchan(task); if (wchan && !lookup_symbol_name(wchan, symname)) { seq_puts(m, symname); return 0; } print0: seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ static int lock_trace(struct task_struct *task) { int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; } static void unlock_trace(struct task_struct *task) { up_read(&task->signal->exec_update_lock); } #ifdef CONFIG_STACKTRACE #define MAX_STACK_TRACE_DEPTH 64 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long *entries; int err; /* * The ability to racily run the kernel stack unwinder on a running task * and then observe the unwinder output is scary; while it is useful for * debugging kernel issues, it can also allow an attacker to leak kernel * stack contents. * Doing this in a manner that is at least safe from races would require * some work to ensure that the remote task can not be scheduled; and * even then, this would still expose the unwinder as local attack * surface. * Therefore, this interface is restricted to root. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; err = lock_trace(task); if (!err) { unsigned int i, nr_entries; nr_entries = stack_trace_save_tsk(task, entries, MAX_STACK_TRACE_DEPTH, 0); for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } kfree(entries); return err; } #endif #ifdef CONFIG_SCHED_INFO /* * Provides /proc/PID/schedstat */ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); return 0; } #endif #ifdef CONFIG_LATENCYTOP static int lstats_show_proc(struct seq_file *m, void *v) { int i; struct inode *inode = m->private; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; seq_puts(m, "Latency Top version : v0.1\n"); for (i = 0; i < LT_SAVECOUNT; i++) { struct latency_record *lr = &task->latency_record[i]; if (lr->backtrace[0]) { int q; seq_printf(m, "%i %li %li", lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; if (!bt) break; seq_printf(m, " %ps", (void *)bt); } seq_putc(m, '\n'); } } put_task_struct(task); return 0; } static int lstats_open(struct inode *inode, struct file *file) { return single_open(file, lstats_show_proc, inode); } static ssize_t lstats_write(struct file *file, const char __user *buf, size_t count, loff_t *offs) { struct task_struct *task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; clear_tsk_latency_tracing(task); put_task_struct(task); return count; } static const struct file_operations proc_lstats_operations = { .open = lstats_open, .read = seq_read, .write = lstats_write, .llseek = seq_lseek, .release = single_release, }; #endif static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; long badness; badness = oom_badness(task, totalpages); /* * Special case OOM_SCORE_ADJ_MIN for all others scale the * badness value into [0, 2000] range which we have been * exporting for a long time so userspace might depend on it. */ if (badness != LONG_MIN) points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3; seq_printf(m, "%lu\n", points); return 0; } struct limit_names { const char *name; const char *unit; }; static const struct limit_names lnames[RLIM_NLIMITS] = { [RLIMIT_CPU] = {"Max cpu time", "seconds"}, [RLIMIT_FSIZE] = {"Max file size", "bytes"}, [RLIMIT_DATA] = {"Max data size", "bytes"}, [RLIMIT_STACK] = {"Max stack size", "bytes"}, [RLIMIT_CORE] = {"Max core file size", "bytes"}, [RLIMIT_RSS] = {"Max resident set", "bytes"}, [RLIMIT_NPROC] = {"Max processes", "processes"}, [RLIMIT_NOFILE] = {"Max open files", "files"}, [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, [RLIMIT_AS] = {"Max address space", "bytes"}, [RLIMIT_LOCKS] = {"Max file locks", "locks"}, [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, [RLIMIT_NICE] = {"Max nice priority", NULL}, [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, }; /* Display limits for a process */ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned int i; unsigned long flags; struct rlimit rlim[RLIM_NLIMITS]; if (!lock_task_sighand(task, &flags)) return 0; memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); unlock_task_sighand(task, &flags); /* * print the file header */ seq_puts(m, "Limit " "Soft Limit " "Hard Limit " "Units \n"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) seq_printf(m, "%-25s %-20s ", lnames[i].name, "unlimited"); else seq_printf(m, "%-25s %-20lu ", lnames[i].name, rlim[i].rlim_cur); if (rlim[i].rlim_max == RLIM_INFINITY) seq_printf(m, "%-20s ", "unlimited"); else seq_printf(m, "%-20lu ", rlim[i].rlim_max); if (lnames[i].unit) seq_printf(m, "%-10s\n", lnames[i].unit); else seq_putc(m, '\n'); } return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct syscall_info info; u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); else if (info.data.nr < 0) seq_printf(m, "%d 0x%llx 0x%llx\n", info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ /************************************************************************/ /* Here the fs part begins */ /************************************************************************/ /* permission checks */ static bool proc_fd_access_allowed(struct inode *inode) { struct task_struct *task; bool allowed = false; /* Allow access to a task's file descriptors if it is us or we * may use ptrace attach to the process and find out that * information. */ task = get_proc_task(inode); if (task) { allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; } int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); if (attr->ia_valid & ATTR_MODE) return -EPERM; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, attr); return 0; } /* * May current process learn task's sched/cmdline info (for hide_pid_min=1) * or euid/egid (for hide_pid_min=2)? */ static bool has_pid_permissions(struct proc_fs_info *fs_info, struct task_struct *task, enum proc_hidepid hide_pid_min) { /* * If 'hidpid' mount option is set force a ptrace check, * we indicate that we are using a filesystem syscall * by passing PTRACE_MODE_READ_FSCREDS */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); if (fs_info->hide_pid < hide_pid_min) return true; if (in_group_p(fs_info->pid_gid)) return true; return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } static int proc_pid_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; bool has_perms; task = get_proc_task(inode); if (!task) return -ESRCH; has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { if (fs_info->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process * may not stat() a file, it shouldn't be seen * in procfs at all. */ return -ENOENT; } return -EPERM; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_def_inode_operations = { .setattr = proc_setattr, }; static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; ret = PROC_I(inode)->op.proc_show(m, ns, pid, task); put_task_struct(task); return ret; } static int proc_single_open(struct inode *inode, struct file *filp) { return single_open(filp, proc_single_show, inode); } static const struct file_operations proc_single_file_operations = { .open = proc_single_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; /* * proc_mem_open() can return errno, NULL or mm_struct*. * * - Returns NULL if the task has no mm (PF_KTHREAD or PF_EXITING) * - Returns mm_struct* on success * - Returns error code on failure */ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) { struct task_struct *task = get_proc_task(inode); struct mm_struct *mm; if (!task) return ERR_PTR(-ESRCH); mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (IS_ERR(mm)) return mm == ERR_PTR(-ESRCH) ? NULL : mm; /* ensure this mm_struct can't be freed */ mmgrab(mm); /* but do not pin its memory */ mmput(mm); return mm; } static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) { struct mm_struct *mm = proc_mem_open(inode, mode); if (IS_ERR_OR_NULL(mm)) return mm ? PTR_ERR(mm) : -ESRCH; file->private_data = mm; return 0; } static int mem_open(struct inode *inode, struct file *file) { if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) return -EINVAL; return __mem_open(inode, file, PTRACE_MODE_ATTACH); } static bool proc_mem_foll_force(struct file *file, struct mm_struct *mm) { struct task_struct *task; bool ptrace_active = false; switch (proc_mem_force_override) { case PROC_MEM_FORCE_NEVER: return false; case PROC_MEM_FORCE_PTRACE: task = get_proc_task(file_inode(file)); if (task) { ptrace_active = READ_ONCE(task->ptrace) && READ_ONCE(task->mm) == mm && READ_ONCE(task->parent) == current; put_task_struct(task); } return ptrace_active; default: return true; } } static ssize_t mem_rw(struct file *file, char __user *buf, size_t count, loff_t *ppos, int write) { struct mm_struct *mm = file->private_data; unsigned long addr = *ppos; ssize_t copied; char *page; unsigned int flags; if (!mm) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; copied = 0; if (!mmget_not_zero(mm)) goto free; flags = write ? FOLL_WRITE : 0; if (proc_mem_foll_force(file, mm)) flags |= FOLL_FORCE; while (count > 0) { size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; break; } this_len = access_remote_vm(mm, addr, page, this_len, flags); if (!this_len) { if (!copied) copied = -EIO; break; } if (!write && copy_to_user(buf, page, this_len)) { copied = -EFAULT; break; } buf += this_len; addr += this_len; copied += this_len; count -= this_len; } *ppos = addr; mmput(mm); free: free_page((unsigned long) page); return copied; } static ssize_t mem_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, buf, count, ppos, 0); } static ssize_t mem_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, (char __user*)buf, count, ppos, 1); } loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: file->f_pos = offset; break; case 1: file->f_pos += offset; break; default: return -EINVAL; } force_successful_syscall_return(); return file->f_pos; } static int mem_release(struct inode *inode, struct file *file) { struct mm_struct *mm = file->private_data; if (mm) mmdrop(mm); return 0; } static const struct file_operations proc_mem_operations = { .llseek = mem_lseek, .read = mem_read, .write = mem_write, .open = mem_open, .release = mem_release, .fop_flags = FOP_UNSIGNED_OFFSET, }; static int environ_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ); } static ssize_t environ_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *page; unsigned long src = *ppos; int ret = 0; struct mm_struct *mm = file->private_data; unsigned long env_start, env_end; /* Ensure the process spawned far enough to have an environment. */ if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; if (!mmget_not_zero(mm)) goto free; spin_lock(&mm->arg_lock); env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); while (count > 0) { size_t this_len, max_len; int retval; if (src >= (env_end - env_start)) break; this_len = env_end - (env_start + src); max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; break; } if (copy_to_user(buf, page, retval)) { ret = -EFAULT; break; } ret += retval; src += retval; buf += retval; count -= retval; } *ppos = src; mmput(mm); free: free_page((unsigned long) page); return ret; } static const struct file_operations proc_environ_operations = { .open = environ_open, .read = environ_read, .llseek = generic_file_llseek, .release = mem_release, }; static int auxv_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); } static ssize_t auxv_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct mm_struct *mm = file->private_data; unsigned int nwords = 0; if (!mm) return 0; do { nwords += 2; } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0])); } static const struct file_operations proc_auxv_operations = { .open = auxv_open, .read = auxv_read, .llseek = generic_file_llseek, .release = mem_release, }; static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; int oom_adj = OOM_ADJUST_MIN; size_t len; if (!task) return -ESRCH; if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) oom_adj = OOM_ADJUST_MAX; else oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); if (oom_adj > OOM_ADJUST_MAX) oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; mutex_lock(&oom_adj_mutex); if (legacy) { if (oom_adj < task->signal->oom_score_adj && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } /* * /proc/pid/oom_adj is provided for legacy purposes, ask users to use * /proc/pid/oom_score_adj instead. */ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); } else { if ((short)oom_adj < task->signal->oom_score_adj_min && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } } /* * Make sure we will check other processes sharing the mm if this is * not vfrok which wants its own oom_score_adj. * pin the mm so it doesn't go away and get reused after task_unlock */ if (!task->vfork_done) { struct task_struct *p = find_lock_task_mm(task); if (p) { if (mm_flags_test(MMF_MULTIPROCESS, p->mm)) { mm = p->mm; mmgrab(mm); } task_unlock(p); } } task->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = (short)oom_adj; trace_oom_score_adj_update(task); if (mm) { struct task_struct *p; rcu_read_lock(); for_each_process(p) { if (same_thread_group(task, p)) continue; /* do not touch kernel threads or the global init */ if (p->flags & PF_KTHREAD || is_global_init(p)) continue; task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; } task_unlock(p); } rcu_read_unlock(); mmdrop(mm); } err_unlock: mutex_unlock(&oom_adj_mutex); put_task_struct(task); return err; } /* * /proc/pid/oom_adj exists solely for backwards compatibility with previous * kernels. The effective policy is defined by oom_score_adj, which has a * different scale: oom_adj grew exponentially and oom_score_adj grows linearly. * Values written to oom_adj are simply mapped linearly to oom_score_adj. * Processes that become oom disabled via oom_adj will still be oom disabled * with this implementation. * * oom_adj cannot be removed since existing userspace binaries use it. */ static ssize_t oom_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_adj); if (err) goto out; if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && oom_adj != OOM_DISABLE) { err = -EINVAL; goto out; } /* * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum * value is always attainable. */ if (oom_adj == OOM_ADJUST_MAX) oom_adj = OOM_SCORE_ADJ_MAX; else oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; err = __set_oom_adj(file, oom_adj, true); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_adj_operations = { .read = oom_adj_read, .write = oom_adj_write, .llseek = generic_file_llseek, }; static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; short oom_score_adj = OOM_SCORE_ADJ_MIN; size_t len; if (!task) return -ESRCH; oom_score_adj = task->signal->oom_score_adj; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_score_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); if (err) goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || oom_score_adj > OOM_SCORE_ADJ_MAX) { err = -EINVAL; goto out; } err = __set_oom_adj(file, oom_score_adj, false); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_score_adj_operations = { .read = oom_score_adj_read, .write = oom_score_adj_write, .llseek = default_llseek, }; #ifdef CONFIG_AUDIT #define TMPBUFLEN 11 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", from_kuid(file->f_cred->user_ns, audit_get_loginuid(task))); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); uid_t loginuid; kuid_t kloginuid; int rv; /* Don't let kthreads write their own loginuid */ if (current->flags & PF_KTHREAD) return -EPERM; rcu_read_lock(); if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { rcu_read_unlock(); return -EPERM; } rcu_read_unlock(); if (*ppos != 0) { /* No partial writes. */ return -EINVAL; } rv = kstrtou32_from_user(buf, count, 10, &loginuid); if (rv < 0) return rv; /* is userspace tring to explicitly UNSET the loginuid? */ if (loginuid == AUDIT_UID_UNSET) { kloginuid = INVALID_UID; } else { kloginuid = make_kuid(file->f_cred->user_ns, loginuid); if (!uid_valid(kloginuid)) return -EINVAL; } rv = audit_set_loginuid(kloginuid); if (rv < 0) return rv; return count; } static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, .llseek = generic_file_llseek, }; static ssize_t proc_sessionid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", audit_get_sessionid(task)); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations proc_sessionid_operations = { .read = proc_sessionid_read, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_FAULT_INJECTION static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; size_t len; int make_it_fail; if (!task) return -ESRCH; make_it_fail = task->make_it_fail; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t proc_fault_inject_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task; char buffer[PROC_NUMBUF] = {}; int make_it_fail; int rv; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; rv = kstrtoint(strstrip(buffer), 0, &make_it_fail); if (rv < 0) return rv; if (make_it_fail < 0 || make_it_fail > 1) return -EINVAL; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->make_it_fail = make_it_fail; put_task_struct(task); return count; } static const struct file_operations proc_fault_inject_operations = { .read = proc_fault_inject_read, .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; int err; unsigned int n; err = kstrtouint_from_user(buf, count, 0, &n); if (err) return err; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->fail_nth = n; put_task_struct(task); return count; } static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; char numbuf[PROC_NUMBUF]; ssize_t len; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; len = snprintf(numbuf, sizeof(numbuf), "%u\n", task->fail_nth); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, numbuf, len); } static const struct file_operations proc_fail_nth_operations = { .read = proc_fail_nth_read, .write = proc_fail_nth_write, }; #endif /* * Print out various scheduling related per-task fields: */ static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_show_task(p, ns, m); put_task_struct(p); return 0; } static ssize_t sched_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_set_task(p); put_task_struct(p); return count; } static int sched_open(struct inode *inode, struct file *filp) { return single_open(filp, sched_show, inode); } static const struct file_operations proc_pid_sched_operations = { .open = sched_open, .read = seq_read, .write = sched_write, .llseek = seq_lseek, .release = single_release, }; #ifdef CONFIG_SCHED_AUTOGROUP /* * Print out autogroup related information: */ static int sched_autogroup_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_autogroup_show_task(p, m); put_task_struct(p); return 0; } static ssize_t sched_autogroup_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[PROC_NUMBUF] = {}; int nice; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; err = kstrtoint(strstrip(buffer), 0, &nice); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; put_task_struct(p); return count; } static int sched_autogroup_open(struct inode *inode, struct file *filp) { int ret; ret = single_open(filp, sched_autogroup_show, NULL); if (!ret) { struct seq_file *m = filp->private_data; m->private = inode; } return ret; } static const struct file_operations proc_pid_sched_autogroup_operations = { .open = sched_autogroup_open, .read = seq_read, .write = sched_autogroup_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_SCHED_AUTOGROUP */ #ifdef CONFIG_TIME_NS static int timens_offsets_show(struct seq_file *m, void *v) { struct task_struct *p; p = get_proc_task(file_inode(m->file)); if (!p) return -ESRCH; proc_timens_show_offsets(p, m); put_task_struct(p); return 0; } static ssize_t timens_offsets_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct proc_timens_offset offsets[2]; char *kbuf = NULL, *pos, *next_line; struct task_struct *p; int ret, noffsets; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* Parse the user data */ ret = -EINVAL; noffsets = 0; for (pos = kbuf; pos; pos = next_line) { struct proc_timens_offset *off = &offsets[noffsets]; char clock[10]; int err; /* Find the end of line and ensure we don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } err = sscanf(pos, "%9s %lld %lu", clock, &off->val.tv_sec, &off->val.tv_nsec); if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC) goto out; clock[sizeof(clock) - 1] = 0; if (strcmp(clock, "monotonic") == 0 || strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0) off->clockid = CLOCK_MONOTONIC; else if (strcmp(clock, "boottime") == 0 || strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0) off->clockid = CLOCK_BOOTTIME; else goto out; noffsets++; if (noffsets == ARRAY_SIZE(offsets)) { if (next_line) count = next_line - kbuf; break; } } ret = -ESRCH; p = get_proc_task(inode); if (!p) goto out; ret = proc_timens_set_offset(file, p, offsets, noffsets); put_task_struct(p); if (ret) goto out; ret = count; out: kfree(kbuf); return ret; } static int timens_offsets_open(struct inode *inode, struct file *filp) { return single_open(filp, timens_offsets_show, inode); } static const struct file_operations proc_timens_offsets_operations = { .open = timens_offsets_open, .read = seq_read, .write = timens_offsets_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_TIME_NS */ static ssize_t comm_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[TASK_COMM_LEN] = {}; const size_t maxlen = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) return -EFAULT; p = get_proc_task(inode); if (!p) return -ESRCH; if (same_thread_group(current, p)) { set_task_comm(p, buffer); proc_comm_connector(p); } else count = -EINVAL; put_task_struct(p); return count; } static int comm_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_task_name(m, p, false); seq_putc(m, '\n'); put_task_struct(p); return 0; } static int comm_open(struct inode *inode, struct file *filp) { return single_open(filp, comm_show, inode); } static const struct file_operations proc_pid_set_comm_operations = { .open = comm_open, .read = seq_read, .write = comm_write, .llseek = seq_lseek, .release = single_release, }; static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; exe_file = get_task_exe_file(task); put_task_struct(task); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); fput(exe_file); return 0; } else return -ENOENT; } static const char *proc_pid_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct path path; int error = -EACCES; if (!dentry) return ERR_PTR(-ECHILD); /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; error = nd_jump_link(&path); out: return ERR_PTR(error); } static int do_proc_readlink(const struct path *path, char __user *buffer, int buflen) { char *tmp = kmalloc(PATH_MAX, GFP_KERNEL); char *pathname; int len; if (!tmp) return -ENOMEM; pathname = d_path(path, tmp, PATH_MAX); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; len = tmp + PATH_MAX - 1 - pathname; if (len > buflen) len = buflen; if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: kfree(tmp); return len; } static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen) { int error = -EACCES; struct inode *inode = d_inode(dentry); struct path path; /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; error = do_proc_readlink(&path, buffer, buflen); path_put(&path); out: return error; } const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_pid_get_link, .setattr = proc_setattr, }; /* building an inode */ void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid) { /* Depending on the state of dumpable compute who should own a * proc file for a task. */ const struct cred *cred; kuid_t uid; kgid_t gid; if (unlikely(task->flags & PF_KTHREAD)) { *ruid = GLOBAL_ROOT_UID; *rgid = GLOBAL_ROOT_GID; return; } /* Default to the tasks effective ownership */ rcu_read_lock(); cred = __task_cred(task); uid = cred->euid; gid = cred->egid; rcu_read_unlock(); /* * Before the /proc/pid/status file was created the only way to read * the effective uid of a /process was to stat /proc/pid. Reading * /proc/pid/status is slow enough that procps and other packages * kept stating /proc/pid. To keep the rules in /proc simple I have * made this apply to all per process world readable and executable * directories. */ if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) { struct mm_struct *mm; task_lock(task); mm = task->mm; /* Make non-dumpable tasks owned by some root */ if (mm) { if (get_dumpable(mm) != SUID_DUMP_USER) { struct user_namespace *user_ns = mm->user_ns; uid = make_kuid(user_ns, 0); if (!uid_valid(uid)) uid = GLOBAL_ROOT_UID; gid = make_kgid(user_ns, 0); if (!gid_valid(gid)) gid = GLOBAL_ROOT_GID; } } else { uid = GLOBAL_ROOT_UID; gid = GLOBAL_ROOT_GID; } task_unlock(task); } *ruid = uid; *rgid = gid; } void proc_pid_evict_inode(struct proc_inode *ei) { struct pid *pid = ei->pid; if (S_ISDIR(ei->vfs_inode.i_mode)) { spin_lock(&pid->lock); hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(&pid->lock); } } struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; struct pid *pid; /* We need a new inode */ inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); inode->i_mode = mode; inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); inode->i_op = &proc_def_inode_operations; /* * grab the reference to task. */ pid = get_task_pid(task, PIDTYPE_PID); if (!pid) goto out_unlock; /* Let the pid remember us for quick removal */ ei->pid = pid; task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); out: return inode; out_unlock: iput(inode); return NULL; } /* * Generating an inode and adding it into @pid->inodes, so that task will * invalidate inode's dentry before being released. * * This helper is used for creating dir-type entries under '/proc' and * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' * can be released by invalidating '/proc/<tgid>' dentry. * In theory, dentries under '/proc/<tgid>/task' can also be released by * invalidating '/proc/<tgid>' dentry, we reserve it to handle single * thread exiting situation: Any one of threads should invalidate its * '/proc/<tgid>/task/<pid>' dentry before released. */ static struct inode *proc_pid_make_base_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode *inode; struct proc_inode *ei; struct pid *pid; inode = proc_pid_make_inode(sb, task, mode); if (!inode) return NULL; /* Let proc_flush_pid find this directory inode */ ei = PROC_I(inode); pid = ei->pid; spin_lock(&pid->lock); hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); spin_unlock(&pid->lock); return inode; } int pid_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 proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, * it only makes getattr() consistent with readdir(). */ return -ENOENT; } task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid); } rcu_read_unlock(); return 0; } /* dentry stuff */ /* * Set <pid>/... inode ownership (can change due to setuid(), etc.) */ void pid_update_inode(struct task_struct *task, struct inode *inode) { task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); } /* * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * */ static int pid_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; int ret = 0; rcu_read_lock(); inode = d_inode_rcu(dentry); if (!inode) goto out; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { pid_update_inode(task, inode); ret = 1; } out: rcu_read_unlock(); return ret; } static inline bool proc_inode_is_dead(struct inode *inode) { return !proc_pid(inode)->tasks[PIDTYPE_PID].first; } int pid_delete_dentry(const struct dentry *dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ return proc_inode_is_dead(d_inode(dentry)); } const struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; /* Lookups */ /* * Fill a directory entry. * * If possible create the dcache entry and derive our inode number and * file type from dcache entry. * * Since all of the proc inode numbers are dynamically generated, the inode * numbers do not exist until the inode is cache. This means creating * the dcache entry in readdir is necessary to keep the inode numbers * reported by readdir in sync with the inode numbers reported * by stat. */ bool proc_fill_cache(struct file *file, struct dir_context *ctx, const char *name, unsigned int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = file->f_path.dentry; struct qstr qname = QSTR_INIT(name, len); struct inode *inode; unsigned type = DT_UNKNOWN; ino_t ino = 1; child = try_lookup_noperm(&qname, dir); if (!child) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) goto end_instantiate; if (d_in_lookup(child)) { struct dentry *res; res = instantiate(child, task, ptr); d_lookup_done(child); if (unlikely(res)) { dput(child); child = res; if (IS_ERR(child)) goto end_instantiate; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; dput(child); end_instantiate: return dir_emit(ctx, name, len, ino, type); } /* * dname_to_vma_addr - maps a dentry name into two unsigned longs * which represent vma start and end addresses. */ static int dname_to_vma_addr(struct dentry *dentry, unsigned long *start, unsigned long *end) { const char *str = dentry->d_name.name; unsigned long long sval, eval; unsigned int len; if (str[0] == '0' && str[1] != '-') return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (sval != (unsigned long)sval) return -EINVAL; str += len; if (*str != '-') return -EINVAL; str++; if (str[0] == '0' && str[1]) return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (eval != (unsigned long)eval) return -EINVAL; str += len; if (*str != '\0') return -EINVAL; *start = sval; *end = eval; return 0; } static int map_files_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; struct mm_struct *mm = NULL; struct task_struct *task; struct inode *inode; int status = 0; if (flags & LOOKUP_RCU) return -ECHILD; inode = d_inode(dentry); task = get_proc_task(inode); if (!task) goto out_notask; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { status = mmap_read_lock_killable(mm); if (!status) { exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); mmap_read_unlock(mm); } } mmput(mm); if (exact_vma_exists) { task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); status = 1; } out: put_task_struct(task); out_notask: return status; } static const struct dentry_operations tid_map_files_dentry_operations = { .d_revalidate = map_files_d_revalidate, .d_delete = pid_delete_dentry, }; static int map_files_get_link(struct dentry *dentry, struct path *path) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; int rc; rc = -ENOENT; task = get_proc_task(d_inode(dentry)); if (!task) goto out; mm = get_task_mm(task); put_task_struct(task); if (!mm) goto out; rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); if (rc) goto out_mmput; rc = mmap_read_lock_killable(mm); if (rc) goto out_mmput; rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { *path = *file_user_path(vma->vm_file); path_get(path); rc = 0; } mmap_read_unlock(mm); out_mmput: mmput(mm); out: return rc; } struct map_files_info { unsigned long start; unsigned long end; fmode_t mode; }; /* * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due * to concerns about how the symlinks may be used to bypass permissions on * ancestor directories in the path to the file in question. */ static const char * proc_map_files_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { if (!checkpoint_restore_ns_capable(&init_user_ns)) return ERR_PTR(-EPERM); return proc_pid_get_link(dentry, inode, done); } /* * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_map_files_get_link, .setattr = proc_setattr, }; static struct dentry * proc_map_files_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { fmode_t mode = (fmode_t)(unsigned long)ptr; struct proc_inode *ei; struct inode *inode; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | ((mode & FMODE_READ ) ? S_IRUSR : 0) | ((mode & FMODE_WRITE) ? S_IWUSR : 0)); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; return proc_splice_unmountable(inode, dentry, &tid_map_files_dentry_operations); } static struct dentry *proc_map_files_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct dentry *result; struct mm_struct *mm; result = ERR_PTR(-ENOENT); task = get_proc_task(dir); if (!task) goto out; result = ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) goto out_put_task; mm = get_task_mm(task); if (!mm) goto out_put_task; result = ERR_PTR(-EINTR); if (mmap_read_lock_killable(mm)) goto out_put_mm; result = ERR_PTR(-ENOENT); vma = find_exact_vma(mm, vm_start, vm_end); if (!vma) goto out_no_vma; if (vma->vm_file) result = proc_map_files_instantiate(dentry, task, (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: mmap_read_unlock(mm); out_put_mm: mmput(mm); out_put_task: put_task_struct(task); out: return result; } static const struct inode_operations proc_map_files_inode_operations = { .lookup = proc_map_files_lookup, .permission = proc_fd_permission, .setattr = proc_setattr, }; static int proc_map_files_readdir(struct file *file, struct dir_context *ctx) { struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; unsigned long nr_files, pos, i; GENRADIX(struct map_files_info) fa; struct map_files_info *p; int ret; struct vma_iterator vmi; genradix_init(&fa); ret = -ENOENT; task = get_proc_task(file_inode(file)); if (!task) goto out; ret = -EACCES; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; if (!dir_emit_dots(file, ctx)) goto out_put_task; mm = get_task_mm(task); if (!mm) goto out_put_task; ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); goto out_put_task; } nr_files = 0; /* * We need two passes here: * * 1) Collect vmas of mapped files with mmap_lock taken * 2) Release mmap_lock and instantiate entries * * otherwise we get lockdep complained, since filldir() * routine might require mmap_lock taken in might_fault(). */ pos = 2; vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (++pos <= ctx->pos) continue; p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL); if (!p) { ret = -ENOMEM; mmap_read_unlock(mm); mmput(mm); goto out_put_task; } p->start = vma->vm_start; p->end = vma->vm_end; p->mode = vma->vm_file->f_mode; } mmap_read_unlock(mm); mmput(mm); for (i = 0; i < nr_files; i++) { char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ unsigned int len; p = genradix_ptr(&fa, i); len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end); if (!proc_fill_cache(file, ctx, buf, len, proc_map_files_instantiate, task, (void *)(unsigned long)p->mode)) break; ctx->pos++; } out_put_task: put_task_struct(task); out: genradix_free(&fa); return ret; } static const struct file_operations proc_map_files_operations = { .read = generic_read_dir, .iterate_shared = proc_map_files_readdir, .llseek = generic_file_llseek, }; #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; struct pid_namespace *ns; }; static void *timers_start(struct seq_file *m, loff_t *pos) { struct timers_private *tp = m->private; tp->task = get_pid_task(tp->pid, PIDTYPE_PID); if (!tp->task) return ERR_PTR(-ESRCH); rcu_read_lock(); return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; return seq_hlist_next_rcu(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) { struct timers_private *tp = m->private; if (tp->task) { put_task_struct(tp->task); tp->task = NULL; rcu_read_unlock(); } } static int show_timer(struct seq_file *m, void *v) { static const char * const nstr[] = { [SIGEV_SIGNAL] = "signal", [SIGEV_NONE] = "none", [SIGEV_THREAD] = "thread", }; struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); struct timers_private *tp = m->private; int notify = timer->it_sigev_notify; guard(spinlock_irq)(&timer->it_lock); if (!posixtimer_valid(timer)) return 0; seq_printf(m, "ID: %d\n", timer->it_id); seq_printf(m, "signal: %d/%px\n", timer->sigq.info.si_signo, timer->sigq.info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", pid_nr_ns(timer->it_pid, tp->ns)); seq_printf(m, "ClockID: %d\n", timer->it_clock); return 0; } static const struct seq_operations proc_timers_seq_ops = { .start = timers_start, .next = timers_next, .stop = timers_stop, .show = show_timer, }; static int proc_timers_open(struct inode *inode, struct file *file) { struct timers_private *tp; tp = __seq_open_private(file, &proc_timers_seq_ops, sizeof(struct timers_private)); if (!tp) return -ENOMEM; tp->pid = proc_pid(inode); tp->ns = proc_pid_ns(inode->i_sb); return 0; } static const struct file_operations proc_timers_operations = { .open = proc_timers_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; #endif static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; u64 slack_ns; int err; err = kstrtoull_from_user(buf, count, 10, &slack_ns); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); count = -EPERM; goto out; } rcu_read_unlock(); err = security_task_setscheduler(p); if (err) { count = err; goto out; } } task_lock(p); if (rt_or_dl_task_policy(p)) slack_ns = 0; else if (slack_ns == 0) slack_ns = p->default_timer_slack_ns; p->timer_slack_ns = slack_ns; task_unlock(p); out: put_task_struct(p); return count; } static int timerslack_ns_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; int err = 0; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; goto out; } rcu_read_unlock(); err = security_task_getscheduler(p); if (err) goto out; } task_lock(p); seq_printf(m, "%llu\n", p->timer_slack_ns); task_unlock(p); out: put_task_struct(p); return err; } static int timerslack_ns_open(struct inode *inode, struct file *filp) { return single_open(filp, timerslack_ns_show, inode); } static const struct file_operations proc_pid_set_timerslack_ns_operations = { .open = timerslack_ns_open, .read = seq_read, .write = timerslack_ns_write, .llseek = seq_lseek, .release = single_release, }; static struct dentry *proc_pident_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct pid_entry *p = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, p->mode); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); if (S_ISDIR(inode->i_mode)) set_nlink(inode, 2); /* Use getattr to fix if necessary */ if (p->iop) inode->i_op = p->iop; if (p->fop) inode->i_fop = p->fop; ei->op = p->op; pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static struct dentry *proc_pident_lookup(struct inode *dir, struct dentry *dentry, const struct pid_entry *p, const struct pid_entry *end) { struct task_struct *task = get_proc_task(dir); struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; /* * Yes, it does not scale. And it should not. Don't add * new entries into /proc/<tgid>/ without very good reasons. */ for (; p < end; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) { res = proc_pident_instantiate(dentry, task, p); break; } } put_task_struct(task); out_no_task: return res; } static int proc_pident_readdir(struct file *file, struct dir_context *ctx, const struct pid_entry *ents, unsigned int nents) { struct task_struct *task = get_proc_task(file_inode(file)); const struct pid_entry *p; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= nents + 2) goto out; for (p = ents + (ctx->pos - 2); p < ents + nents; p++) { if (!proc_fill_cache(file, ctx, p->name, p->len, proc_pident_instantiate, task, p)) break; ctx->pos++; } out: put_task_struct(task); return 0; } #ifdef CONFIG_SECURITY static int proc_pid_attr_open(struct inode *inode, struct file *file) { file->private_data = NULL; __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); return 0; } static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); char *p = NULL; ssize_t length; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; length = security_getprocattr(task, PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, &p); put_task_struct(task); if (length > 0) length = simple_read_from_buffer(buf, count, ppos, p, length); kfree(p); return length; } static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task; void *page; int rv; /* A task may only write when it was the opener. */ if (file->private_data != current->mm) return -EPERM; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { rcu_read_unlock(); return -ESRCH; } /* A task may only write its own attributes. */ if (current != task) { rcu_read_unlock(); return -EACCES; } /* Prevent changes to overridden credentials. */ if (current_cred() != current_real_cred()) { rcu_read_unlock(); return -EBUSY; } rcu_read_unlock(); if (count > PAGE_SIZE) count = PAGE_SIZE; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user(buf, count); if (IS_ERR(page)) { rv = PTR_ERR(page); goto out; } /* Guard against adverse ptrace interaction */ rv = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); if (rv < 0) goto out_free; rv = security_setprocattr(PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, page, count); mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); out: return rv; } static const struct file_operations proc_pid_attr_operations = { .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, .release = mem_release, }; #define LSM_DIR_OPS(LSM) \ static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ struct dir_context *ctx) \ { \ return proc_pident_readdir(filp, ctx, \ LSM##_attr_dir_stuff, \ ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct file_operations proc_##LSM##_attr_dir_ops = { \ .read = generic_read_dir, \ .iterate_shared = proc_##LSM##_attr_dir_iterate, \ .llseek = default_llseek, \ }; \ \ static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \ struct dentry *dentry, unsigned int flags) \ { \ return proc_pident_lookup(dir, dentry, \ LSM##_attr_dir_stuff, \ LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \ .lookup = proc_##LSM##_attr_dir_lookup, \ .getattr = pid_getattr, \ .setattr = proc_setattr, \ } #ifdef CONFIG_SECURITY_SMACK static const struct pid_entry smack_attr_dir_stuff[] = { ATTR(LSM_ID_SMACK, "current", 0666), }; LSM_DIR_OPS(smack); #endif #ifdef CONFIG_SECURITY_APPARMOR static const struct pid_entry apparmor_attr_dir_stuff[] = { ATTR(LSM_ID_APPARMOR, "current", 0666), ATTR(LSM_ID_APPARMOR, "prev", 0444), ATTR(LSM_ID_APPARMOR, "exec", 0666), }; LSM_DIR_OPS(apparmor); #endif static const struct pid_entry attr_dir_stuff[] = { ATTR(LSM_ID_UNDEF, "current", 0666), ATTR(LSM_ID_UNDEF, "prev", 0444), ATTR(LSM_ID_UNDEF, "exec", 0666), ATTR(LSM_ID_UNDEF, "fscreate", 0666), ATTR(LSM_ID_UNDEF, "keycreate", 0666), ATTR(LSM_ID_UNDEF, "sockcreate", 0666), #ifdef CONFIG_SECURITY_SMACK DIR("smack", 0555, proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), #endif #ifdef CONFIG_SECURITY_APPARMOR DIR("apparmor", 0555, proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops), #endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); } static const struct file_operations proc_attr_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_attr_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, attr_dir_stuff, attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff)); } static const struct inode_operations proc_attr_dir_inode_operations = { .lookup = proc_attr_dir_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; #endif #ifdef CONFIG_ELF_CORE static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; char buffer[PROC_NUMBUF]; size_t len; int ret; if (!task) return -ESRCH; ret = 0; mm = get_task_mm(task); if (mm) { unsigned long flags = __mm_flags_get_dumpable(mm); len = snprintf(buffer, sizeof(buffer), "%08lx\n", ((flags & MMF_DUMP_FILTER_MASK) >> MMF_DUMP_FILTER_SHIFT)); mmput(mm); ret = simple_read_from_buffer(buf, count, ppos, buffer, len); } put_task_struct(task); return ret; } static ssize_t proc_coredump_filter_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; struct mm_struct *mm; unsigned int val; int ret; int i; unsigned long mask; ret = kstrtouint_from_user(buf, count, 0, &val); if (ret < 0) return ret; ret = -ESRCH; task = get_proc_task(file_inode(file)); if (!task) goto out_no_task; mm = get_task_mm(task); if (!mm) goto out_no_mm; ret = 0; for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { if (val & mask) mm_flags_set(i + MMF_DUMP_FILTER_SHIFT, mm); else mm_flags_clear(i + MMF_DUMP_FILTER_SHIFT, mm); } mmput(mm); out_no_mm: put_task_struct(task); out_no_task: if (ret < 0) return ret; return count; } static const struct file_operations proc_coredump_filter_operations = { .read = proc_coredump_filter_read, .write = proc_coredump_filter_write, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_TASK_IO_ACCOUNTING static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole) { struct task_io_accounting acct; int result; result = down_read_killable(&task->signal->exec_update_lock); if (result) return result; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } if (whole) { struct signal_struct *sig = task->signal; struct task_struct *t; unsigned int seq = 1; unsigned long flags; rcu_read_lock(); do { seq++; /* 2 on the 1st/lockless path, otherwise odd */ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); acct = sig->ioac; __for_each_thread(sig, t) task_io_accounting_add(&acct, &t->ioac); } while (need_seqretry(&sig->stats_lock, seq)); done_seqretry_irqrestore(&sig->stats_lock, seq, flags); rcu_read_unlock(); } else { acct = task->ioac; } seq_printf(m, "rchar: %llu\n" "wchar: %llu\n" "syscr: %llu\n" "syscw: %llu\n" "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", (unsigned long long)acct.rchar, (unsigned long long)acct.wchar, (unsigned long long)acct.syscr, (unsigned long long)acct.syscw, (unsigned long long)acct.read_bytes, (unsigned long long)acct.write_bytes, (unsigned long long)acct.cancelled_write_bytes); result = 0; out_unlock: up_read(&task->signal->exec_update_lock); return result; } static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 0); } static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 1); } #endif /* CONFIG_TASK_IO_ACCOUNTING */ #ifdef CONFIG_USER_NS static int proc_id_map_open(struct inode *inode, struct file *file, const struct seq_operations *seq_ops) { struct user_namespace *ns = NULL; struct task_struct *task; struct seq_file *seq; int ret = -EINVAL; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; ret = seq_open(file, seq_ops); if (ret) goto err_put_ns; seq = file->private_data; seq->private = ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_id_map_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; put_user_ns(ns); return seq_release(inode, file); } static int proc_uid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_uid_seq_operations); } static int proc_gid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_gid_seq_operations); } static int proc_projid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_projid_seq_operations); } static const struct file_operations proc_uid_map_operations = { .open = proc_uid_map_open, .write = proc_uid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_gid_map_operations = { .open = proc_gid_map_open, .write = proc_gid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_projid_map_operations = { .open = proc_projid_map_open, .write = proc_projid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static int proc_setgroups_open(struct inode *inode, struct file *file) { struct user_namespace *ns = NULL; struct task_struct *task; int ret; ret = -ESRCH; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; if (file->f_mode & FMODE_WRITE) { ret = -EACCES; if (!ns_capable(ns, CAP_SYS_ADMIN)) goto err_put_ns; } ret = single_open(file, &proc_setgroups_show, ns); if (ret) goto err_put_ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_setgroups_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; int ret = single_release(inode, file); put_user_ns(ns); return ret; } static const struct file_operations proc_setgroups_operations = { .open = proc_setgroups_open, .write = proc_setgroups_write, .read = seq_read, .llseek = seq_lseek, .release = proc_setgroups_release, }; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { int err = lock_trace(task); if (!err) { seq_printf(m, "%08x\n", task->personality); unlock_trace(task); } return err; } #ifdef CONFIG_LIVEPATCH static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { seq_printf(m, "%d\n", task->patch_state); return 0; } #endif /* CONFIG_LIVEPATCH */ #ifdef CONFIG_KSM static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; mm = get_task_mm(task); if (mm) { seq_printf(m, "%lu\n", mm->ksm_merging_pages); mmput(mm); } return 0; } static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; int ret = 0; mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); seq_printf(m, "ksm_merge_any: %s\n", mm_flags_test(MMF_VM_MERGE_ANY, mm) ? "yes" : "no"); ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); return ret; } seq_printf(m, "ksm_mergeable: %s\n", ksm_process_mergeable(mm) ? "yes" : "no"); mmap_read_unlock(mm); mmput(mm); } return 0; } #endif /* CONFIG_KSM */ #ifdef CONFIG_KSTACK_ERASE_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long prev_depth = THREAD_SIZE - (task->prev_lowest_stack & (THREAD_SIZE - 1)); unsigned long depth = THREAD_SIZE - (task->lowest_stack & (THREAD_SIZE - 1)); seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", prev_depth, depth); return 0; } #endif /* CONFIG_KSTACK_ERASE_METRICS */ /* * Thread groups */ static const struct file_operations proc_task_operations; static const struct inode_operations proc_task_inode_operations; static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #ifdef CONFIG_SCHED_AUTOGROUP REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), #endif #ifdef CONFIG_TIME_NS REG("timens_offsets", S_IRUGO|S_IWUSR, proc_timens_offsets_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tgid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), REG("mountstats", S_IRUSR, proc_mountstats_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_ELF_CORE REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tgid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_KSTACK_ERASE_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tgid_base_readdir, .llseek = generic_file_llseek, }; struct pid *tgid_pidfd_to_pid(const struct file *file) { if (file->f_op != &proc_tgid_base_operations) return ERR_PTR(-EBADF); return proc_pid(file_inode(file)); } static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tgid_base_stuff, tgid_base_stuff + ARRAY_SIZE(tgid_base_stuff)); } static const struct inode_operations proc_tgid_base_inode_operations = { .lookup = proc_tgid_base_lookup, .getattr = pid_getattr, .setattr = proc_setattr, .permission = proc_pid_permission, }; /** * proc_flush_pid - Remove dcache entries for @pid from the /proc dcache. * @pid: pid that should be flushed. * * This function walks a list of inodes (that belong to any proc * filesystem) that are attached to the pid and flushes them from * the dentry cache. * * It is safe and reasonable to cache /proc entries for a task until * that task exits. After that they just clog up the dcache with * useless entries, possibly causing useful dcache entries to be * flushed instead. This routine is provided to flush those useless * dcache entries when a process is reaped. * * NOTE: This routine is just an optimization so it does not guarantee * that no dcache entries will exist after a process is reaped * it just makes it very unlikely that any will persist. */ void proc_flush_pid(struct pid *pid) { proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); } static struct dentry *proc_pid_instantiate(struct dentry * dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tgid_base_inode_operations; inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; set_nlink(inode, nlink_tgid); pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); tgid = name_to_int(&dentry->d_name); if (tgid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; /* Limit procfs to only ptraceable tasks */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) { if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS)) goto out_put_task; } result = proc_pid_instantiate(dentry, task, NULL); out_put_task: put_task_struct(task); out: return result; } /* * Find the first task with tgid >= tgid * */ struct tgid_iter { unsigned int tgid; struct task_struct *task; }; static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) { struct pid *pid; if (iter.task) put_task_struct(iter.task); rcu_read_lock(); retry: iter.task = NULL; pid = find_ge_pid(iter.tgid, ns); if (pid) { iter.tgid = pid_nr_ns(pid, ns); iter.task = pid_task(pid, PIDTYPE_TGID); if (!iter.task) { iter.tgid += 1; goto retry; } get_task_struct(iter.task); } rcu_read_unlock(); return iter; } #define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2) /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb); struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; if (pos == TGID_OFFSET - 2) { struct inode *inode = d_inode(fs_info->proc_self); if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } if (pos == TGID_OFFSET - 1) { struct inode *inode = d_inode(fs_info->proc_thread_self); if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } iter.tgid = pos - TGID_OFFSET; iter.task = NULL; for (iter = next_tgid(ns, iter); iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[10 + 1]; unsigned int len; cond_resched(); if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%u", iter.tgid); ctx->pos = iter.tgid + TGID_OFFSET; if (!proc_fill_cache(file, ctx, name, len, proc_pid_instantiate, iter.task, NULL)) { put_task_struct(iter.task); return 0; } } ctx->pos = PID_MAX_LIMIT + TGID_OFFSET; return 0; } /* * proc_tid_comm_permission is a special permission function exclusively * used for the node /proc/<pid>/task/<tid>/comm. * It bypasses generic permission checks in the case where a task of the same * task group attempts to access the node. * The rationale behind this is that glibc and bionic access this node for * cross thread naming (pthread_set/getname_np(!self)). However, if * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0, * which locks out the cross thread naming implementation. * This function makes sure that the node is always accessible for members of * same thread group. */ static int proc_tid_comm_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { bool is_same_tgroup; struct task_struct *task; task = get_proc_task(inode); if (!task) return -ESRCH; is_same_tgroup = same_thread_group(current, task); put_task_struct(task); if (likely(is_same_tgroup && !(mask & MAY_EXEC))) { /* This file (/proc/<pid>/task/<tid>/comm) can always be * read or written by the members of the corresponding * thread group. */ return 0; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { .setattr = proc_setattr, .permission = proc_tid_comm_permission, }; /* * Tasks */ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), NOD("comm", S_IFREG|S_IRUGO|S_IWUSR, &proc_tid_comm_inode_operations, &proc_pid_set_comm_operations, {}), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_PROC_CHILDREN REG("children", S_IRUGO, proc_tid_children_operations), #endif #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tid_base_stuff, tid_base_stuff + ARRAY_SIZE(tid_base_stuff)); } static const struct file_operations proc_tid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tid_base_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations proc_tid_base_inode_operations = { .lookup = proc_tid_base_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tid_base_inode_operations; inode->i_fop = &proc_tid_base_operations; inode->i_flags |= S_IMMUTABLE; set_nlink(inode, nlink_tid); pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); if (!leader) goto out_no_task; tid = name_to_int(&dentry->d_name); if (tid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; if (!same_thread_group(leader, task)) goto out_drop_task; result = proc_task_instantiate(dentry, task, NULL); out_drop_task: put_task_struct(task); out: put_task_struct(leader); out_no_task: return result; } /* * Find the first tid of a thread group to return to user space. * * Usually this is just the thread group leader, but if the users * buffer was too small or there was a seek into the middle of the * directory we have more work todo. * * In the case of a short read we start with find_task_by_pid. * * In the case of a seek we start with the leader and walk nr * threads past it. */ static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, struct pid_namespace *ns) { struct task_struct *pos, *task; unsigned long nr = f_pos; if (nr != f_pos) /* 32bit overflow? */ return NULL; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); if (!task) goto fail; /* Attempt to start with the tid of a thread */ if (tid && nr) { pos = find_task_by_pid_ns(tid, ns); if (pos && same_thread_group(pos, task)) goto found; } /* If nr exceeds the number of threads there is nothing todo */ if (nr >= get_nr_threads(task)) goto fail; /* If we haven't found our starting place yet start * with the leader and walk nr threads forward. */ for_each_thread(task, pos) { if (!nr--) goto found; } fail: pos = NULL; goto out; found: get_task_struct(pos); out: rcu_read_unlock(); return pos; } /* * Find the next thread in the thread list. * Return NULL if there is an error or no next thread. * * The reference to the input task_struct is released. */ static struct task_struct *next_tid(struct task_struct *start) { struct task_struct *pos = NULL; rcu_read_lock(); if (pid_alive(start)) { pos = __next_thread(start); if (pos) get_task_struct(pos); } rcu_read_unlock(); put_task_struct(start); return pos; } /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct task_struct *task; struct pid_namespace *ns; int tid; if (proc_inode_is_dead(inode)) return -ENOENT; if (!dir_emit_dots(file, ctx)) return 0; /* We cache the tgid value that the last readdir call couldn't * return and lseek resets it to 0. */ ns = proc_pid_ns(inode->i_sb); tid = (int)(intptr_t)file->private_data; file->private_data = NULL; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { char name[10 + 1]; unsigned int len; tid = task_pid_nr_ns(task, ns); if (!tid) continue; /* The task has just exited. */ len = snprintf(name, sizeof(name), "%d", tid); if (!proc_fill_cache(file, ctx, name, len, proc_task_instantiate, task, NULL)) { /* returning this tgid failed, save it as the first * pid for the next readir call */ file->private_data = (void *)(intptr_t)tid; put_task_struct(task); break; } } return 0; } static int proc_task_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 task_struct *p = get_proc_task(inode); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (p) { stat->nlink += get_nr_threads(p); put_task_struct(p); } return 0; } /* * proc_task_readdir() set @file->private_data to a positive integer * value, so casting that to u64 is safe. generic_llseek_cookie() will * set @cookie to 0, so casting to an int is safe. The WARN_ON_ONCE() is * here to catch any unexpected change in behavior either in * proc_task_readdir() or generic_llseek_cookie(). */ static loff_t proc_dir_llseek(struct file *file, loff_t offset, int whence) { u64 cookie = (u64)(intptr_t)file->private_data; loff_t off; off = generic_llseek_cookie(file, offset, whence, &cookie); WARN_ON_ONCE(cookie > INT_MAX); file->private_data = (void *)(intptr_t)cookie; /* serialized by f_pos_lock */ return off; } static const struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, .getattr = proc_task_getattr, .setattr = proc_setattr, .permission = proc_pid_permission, }; static const struct file_operations proc_task_operations = { .read = generic_read_dir, .iterate_shared = proc_task_readdir, .llseek = proc_dir_llseek, }; void __init set_proc_pid_nlink(void) { nlink_tid = pid_entry_nlink(tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); nlink_tgid = pid_entry_nlink(tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } |
| 2256 1807 692 627 105 3070 3075 3079 3047 80 4 1801 1805 159 159 159 159 238 239 3417 3420 3420 412 412 412 3908 3909 3902 1102 1103 923 922 1099 1099 779 777 131 145 239 239 239 239 239 159 159 158 239 239 105 21 85 1 1 4 256 257 1039 1041 1042 360 360 360 67 66 8 448 7 360 360 2492 2492 1 448 448 448 70 380 447 2 2 54 413 122 367 448 1028 768 329 1031 1 1031 1023 13 2 411 67 1 448 4 4 4 4 4 4 4 4 4 4505 4515 3501 207 3538 2470 1163 3539 3076 2938 4015 714 3831 5 1248 3639 761 3036 80 2279 1808 3068 715 1099 230 229 229 230 30 6 30 30 229 267 141 145 268 21 20 1 266 42 231 230 809 811 234 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 | // 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. */ static 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 { /* List of queued switching contexts for the wb */ struct llist_node list; /* * 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 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. * 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) { /* * We need to keep b_dirty list sorted by * dirtied_time_when. However properly sorting the * inode in the list gets too expensive when switching * many inodes. So just attach inode at the end of the * dirty list and clobber the dirtied_time_when. */ inode->dirtied_time_when = jiffies; inode_io_list_move_locked(inode, new_wb, &new_wb->b_dirty); } 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 process_inode_switch_wbs(struct bdi_writeback *new_wb, struct inode_switch_wbs_context *isw) { struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_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); inodep = isw->inodes; /* * 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. */ relock: 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); } while (*inodep) { WARN_ON_ONCE((*inodep)->i_wb != old_wb); if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) nr_switched++; inodep++; if (*inodep && need_resched()) { spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); cond_resched(); goto relock; } } 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); } void inode_switch_wbs_work_fn(struct work_struct *work) { struct bdi_writeback *new_wb = container_of(work, struct bdi_writeback, switch_work); struct inode_switch_wbs_context *isw, *next_isw; struct llist_node *list; /* * Grab out reference to wb so that it cannot get freed under us * after we process all the isw items. */ wb_get(new_wb); while (1) { list = llist_del_all(&new_wb->switch_wbs_ctxs); /* Nothing to do? */ if (!list) break; /* * 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. */ synchronize_rcu(); llist_for_each_entry_safe(isw, next_isw, list, list) process_inode_switch_wbs(new_wb, isw); } wb_put(new_wb); } 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; } static void wb_queue_isw(struct bdi_writeback *wb, struct inode_switch_wbs_context *isw) { if (llist_add(&isw->list, &wb->switch_wbs_ctxs)) queue_work(isw_wq, &wb->switch_work); } /** * 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; struct bdi_writeback *new_wb = NULL; /* 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; new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!new_wb) goto out_free; if (!inode_prepare_wbs_switch(inode, new_wb)) goto out_free; isw->inodes[0] = inode; trace_inode_switch_wbs_queue(inode->i_wb, new_wb, 1); wb_queue_isw(new_wb, isw); return; out_free: atomic_dec(&isw_nr_in_flight); if (new_wb) wb_put(new_wb); kfree(isw); } static bool isw_prepare_wbs_switch(struct bdi_writeback *new_wb, 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, 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; struct bdi_writeback *new_wb; 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) { new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); if (new_wb) break; } if (unlikely(!new_wb)) 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(new_wb, isw, &wb->b_attached, &nr); if (!restart) restart = isw_prepare_wbs_switch(new_wb, 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(new_wb); kfree(isw); return restart; } trace_inode_switch_wbs_queue(wb, new_wb, nr); wb_queue_isw(new_wb, isw); 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); 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", WQ_PERCPU, 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 (!icount_read(inode)) 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 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_percpu_wq, &dirtytime_work, 0); return ret; } static const struct ctl_table vm_fs_writeback_table[] = { { .procname = "dirtytime_expire_seconds", .data = &dirtytime_expire_interval, .maxlen = sizeof(dirtytime_expire_interval), .mode = 0644, .proc_handler = dirtytime_interval_handler, .extra1 = SYSCTL_ZERO, }, }; static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); register_sysctl_init("vm", vm_fs_writeback_table); return 0; } __initcall(start_dirtytime_writeback); /** * __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); /* * 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); spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); trace_writeback_dirty_inode_enqueue(inode); 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); |
| 15 2 13 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright(c) 2017 Intel Corporation. All rights reserved. * * This code is based in part on work published here: * * https://github.com/IAIK/KAISER * * The original work was written by and signed off by for the Linux * kernel by: * * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at> * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at> * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at> * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at> * * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com> * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and * Andy Lutomirsky <luto@amacapital.net> */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/cpu.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> #include <asm/vsyscall.h> #include <asm/cmdline.h> #include <asm/pti.h> #include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/sections.h> #include <asm/set_memory.h> #include <asm/bugs.h> #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt /* Backporting helper */ #ifndef __GFP_NOTRACK #define __GFP_NOTRACK 0 #endif /* * Define the page-table levels we clone for user-space on 32 * and 64 bit. */ #ifdef CONFIG_X86_64 #define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PMD #else #define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PTE #endif static void __init pti_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) pr_info("%s\n", reason); } static void __init pti_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) pr_info("%s\n", reason); } /* Assume mode is auto unless overridden via cmdline below. */ static enum pti_mode { PTI_AUTO = 0, PTI_FORCE_OFF, PTI_FORCE_ON } pti_mode; void __init pti_check_boottime_disable(void) { if (hypervisor_is_type(X86_HYPER_XEN_PV)) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on XEN PV."); return; } if (pti_mode == PTI_AUTO && !cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL)) pti_mode = PTI_FORCE_OFF; if (pti_mode == PTI_FORCE_OFF) { pti_print_if_insecure("disabled on command line."); return; } if (pti_mode == PTI_FORCE_ON) pti_print_if_secure("force enabled on command line."); if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return; setup_force_cpu_cap(X86_FEATURE_PTI); if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) { pr_debug("PTI enabled, disabling INVLPGB\n"); setup_clear_cpu_cap(X86_FEATURE_INVLPGB); } } static int __init pti_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) pti_mode = PTI_FORCE_OFF; else if (!strcmp(arg, "on")) pti_mode = PTI_FORCE_ON; else if (!strcmp(arg, "auto")) pti_mode = PTI_AUTO; else return -EINVAL; return 0; } early_param("pti", pti_parse_cmdline); static int __init pti_parse_cmdline_nopti(char *arg) { pti_mode = PTI_FORCE_OFF; return 0; } early_param("nopti", pti_parse_cmdline_nopti); pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { /* * Changes to the high (kernel) portion of the kernelmode page * tables are not automatically propagated to the usermode tables. * * Users should keep in mind that, unlike the kernelmode tables, * there is no vmalloc_fault equivalent for the usermode tables. * Top-level entries added to init_mm's usermode pgd after boot * will not be automatically propagated to other mms. */ if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW)) return pgd; /* * The user page tables get the full PGD, accessible from * userspace: */ kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd; /* * If this is normal user memory, make it NX in the kernel * pagetables so that, if we somehow screw up and return to * usermode with the kernel CR3 loaded, we'll get a page fault * instead of allowing user code to execute with the wrong CR3. * * As exceptions, we don't set NX if: * - _PAGE_USER is not set. This could be an executable * EFI runtime mapping or something similar, and the kernel * may execute from it * - we don't have NX support * - we're clearing the PGD (i.e. the new pgd is not present). */ if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) && (__supported_pte_mask & _PAGE_NX)) pgd.pgd |= _PAGE_NX; /* return the copy of the PGD we want the kernel to use: */ return pgd; } /* * Walk the user copy of the page tables (optionally) trying to allocate * page table pages on the way down. * * Returns a pointer to a P4D on success, or NULL on failure. */ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) { pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (address < PAGE_OFFSET) { WARN_ONCE(1, "attempt to walk user address\n"); return NULL; } if (pgd_none(*pgd)) { unsigned long new_p4d_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_p4d_page)) return NULL; set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); } BUILD_BUG_ON(pgd_leaf(*pgd)); return p4d_offset(pgd, address); } /* * Walk the user copy of the page tables (optionally) trying to allocate * page table pages on the way down. * * Returns a pointer to a PMD on success, or NULL on failure. */ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); p4d_t *p4d; pud_t *pud; p4d = pti_user_pagetable_walk_p4d(address); if (!p4d) return NULL; BUILD_BUG_ON(p4d_leaf(*p4d)); if (p4d_none(*p4d)) { unsigned long new_pud_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pud_page)) return NULL; set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); } pud = pud_offset(p4d, address); /* The user page tables do not use large mappings: */ if (pud_leaf(*pud)) { WARN_ON(1); return NULL; } if (pud_none(*pud)) { unsigned long new_pmd_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pmd_page)) return NULL; set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); } return pmd_offset(pud, address); } /* * Walk the shadow copy of the page tables (optionally) trying to allocate * page table pages on the way down. Does not support large pages. * * Note: this is only used when mapping *new* kernel data into the * user/shadow page tables. It is never used for userspace data. * * Returns a pointer to a PTE on success, or NULL on failure. */ static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; pte_t *pte; pmd = pti_user_pagetable_walk_pmd(address); if (!pmd) return NULL; /* Large PMD mapping found */ if (pmd_leaf(*pmd)) { /* Clear the PMD if we hit a large mapping from the first round */ if (late_text) { set_pmd(pmd, __pmd(0)); } else { WARN_ON_ONCE(1); return NULL; } } if (pmd_none(*pmd)) { unsigned long new_pte_page = __get_free_page(gfp); if (!new_pte_page) return NULL; set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); } pte = pte_offset_kernel(pmd, address); if (pte_flags(*pte) & _PAGE_USER) { WARN_ONCE(1, "attempt to walk to user pte\n"); return NULL; } return pte; } #ifdef CONFIG_X86_VSYSCALL_EMULATION static void __init pti_setup_vsyscall(void) { pte_t *pte, *target_pte; unsigned int level; pte = lookup_address(VSYSCALL_ADDR, &level); if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) return; target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false); if (WARN_ON(!target_pte)) return; *target_pte = *pte; set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir)); } #else static void __init pti_setup_vsyscall(void) { } #endif enum pti_clone_level { PTI_CLONE_PMD, PTI_CLONE_PTE, }; static void pti_clone_pgtable(unsigned long start, unsigned long end, enum pti_clone_level level, bool late_text) { unsigned long addr; /* * Clone the populated PMDs which cover start to end. These PMD areas * can have holes. */ for (addr = start; addr < end;) { pte_t *pte, *target_pte; pmd_t *pmd, *target_pmd; pgd_t *pgd; p4d_t *p4d; pud_t *pud; /* Overflow check */ if (addr < start) break; pgd = pgd_offset_k(addr); if (WARN_ON(pgd_none(*pgd))) return; p4d = p4d_offset(pgd, addr); if (WARN_ON(p4d_none(*p4d))) return; pud = pud_offset(p4d, addr); if (pud_none(*pud)) { WARN_ON_ONCE(addr & ~PUD_MASK); addr = round_up(addr + 1, PUD_SIZE); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { WARN_ON_ONCE(addr & ~PMD_MASK); addr = round_up(addr + 1, PMD_SIZE); continue; } if (pmd_leaf(*pmd) || level == PTI_CLONE_PMD) { target_pmd = pti_user_pagetable_walk_pmd(addr); if (WARN_ON(!target_pmd)) return; /* * Only clone present PMDs. This ensures only setting * _PAGE_GLOBAL on present PMDs. This should only be * called on well-known addresses anyway, so a non- * present PMD would be a surprise. */ if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT))) return; /* * Setting 'target_pmd' below creates a mapping in both * the user and kernel page tables. It is effectively * global, so set it as global in both copies. Note: * the X86_FEATURE_PGE check is not _required_ because * the CPU ignores _PAGE_GLOBAL when PGE is not * supported. The check keeps consistency with * code that only set this bit when supported. */ if (boot_cpu_has(X86_FEATURE_PGE)) *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL); /* * Copy the PMD. That is, the kernelmode and usermode * tables will share the last-level page tables of this * address range */ *target_pmd = *pmd; addr = round_up(addr + 1, PMD_SIZE); } else if (level == PTI_CLONE_PTE) { /* Walk the page-table down to the pte level */ pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { addr = round_up(addr + 1, PAGE_SIZE); continue; } /* Only clone present PTEs */ if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT))) return; /* Allocate PTE in the user page-table */ target_pte = pti_user_pagetable_walk_pte(addr, late_text); if (WARN_ON(!target_pte)) return; /* Set GLOBAL bit in both PTEs */ if (boot_cpu_has(X86_FEATURE_PGE)) *pte = pte_set_flags(*pte, _PAGE_GLOBAL); /* Clone the PTE */ *target_pte = *pte; addr = round_up(addr + 1, PAGE_SIZE); } else { BUG(); } } } #ifdef CONFIG_X86_64 /* * Clone a single p4d (i.e. a top-level entry on 4-level systems and a * next-level entry on 5-level systems. */ static void __init pti_clone_p4d(unsigned long addr) { p4d_t *kernel_p4d, *user_p4d; pgd_t *kernel_pgd; user_p4d = pti_user_pagetable_walk_p4d(addr); if (!user_p4d) return; kernel_pgd = pgd_offset_k(addr); kernel_p4d = p4d_offset(kernel_pgd, addr); *user_p4d = *kernel_p4d; } /* * Clone the CPU_ENTRY_AREA and associated data into the user space visible * page table. */ static void __init pti_clone_user_shared(void) { unsigned int cpu; pti_clone_p4d(CPU_ENTRY_AREA_BASE); for_each_possible_cpu(cpu) { /* * The SYSCALL64 entry code needs one word of scratch space * in which to spill a register. It lives in the sp2 slot * of the CPU's TSS. * * This is done for all possible CPUs during boot to ensure * that it's propagated to all mms. */ unsigned long va = (unsigned long)&per_cpu(cpu_tss_rw, cpu); phys_addr_t pa = per_cpu_ptr_to_phys((void *)va); pte_t *target_pte; target_pte = pti_user_pagetable_walk_pte(va, false); if (WARN_ON(!target_pte)) return; *target_pte = pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL); } } #else /* CONFIG_X86_64 */ /* * On 32 bit PAE systems with 1GB of Kernel address space there is only * one pgd/p4d for the whole kernel. Cloning that would map the whole * address space into the user page-tables, making PTI useless. So clone * the page-table on the PMD level to prevent that. */ static void __init pti_clone_user_shared(void) { unsigned long start, end; start = CPU_ENTRY_AREA_BASE; end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES); pti_clone_pgtable(start, end, PTI_CLONE_PMD, false); } #endif /* CONFIG_X86_64 */ /* * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { #ifdef CONFIG_X86_ESPFIX64 pti_clone_p4d(ESPFIX_BASE_ADDR); #endif } /* * Clone the populated PMDs of the entry text and force it RO. */ static void pti_clone_entry_text(bool late) { pti_clone_pgtable((unsigned long) __entry_text_start, (unsigned long) __entry_text_end, PTI_LEVEL_KERNEL_IMAGE, late); } /* * Global pages and PCIDs are both ways to make kernel TLB entries * live longer, reduce TLB misses and improve kernel performance. * But, leaving all kernel text Global makes it potentially accessible * to Meltdown-style attacks which make it trivial to find gadgets or * defeat KASLR. * * Only use global pages when it is really worth it. */ static inline bool pti_kernel_image_global_ok(void) { /* * Systems with PCIDs get little benefit from global * kernel text and are not worth the downsides. */ if (cpu_feature_enabled(X86_FEATURE_PCID)) return false; /* * Only do global kernel image for pti=auto. Do the most * secure thing (not global) if pti=on specified. */ if (pti_mode != PTI_AUTO) return false; /* * K8 may not tolerate the cleared _PAGE_RW on the userspace * global kernel image pages. Do the safe thing (disable * global kernel image). This is unlikely to ever be * noticed because PTI is disabled by default on AMD CPUs. */ if (boot_cpu_has(X86_FEATURE_K8)) return false; /* * RANDSTRUCT derives its hardening benefits from the * attacker's lack of knowledge about the layout of kernel * data structures. Keep the kernel image non-global in * cases where RANDSTRUCT is in use to help keep the layout a * secret. */ if (IS_ENABLED(CONFIG_RANDSTRUCT)) return false; return true; } /* * For some configurations, map all of kernel text into the user page * tables. This reduces TLB misses, especially on non-PCID systems. */ static void pti_clone_kernel_text(void) { /* * rodata is part of the kernel image and is normally * readable on the filesystem or on the web. But, do not * clone the areas past rodata, they might contain secrets. */ unsigned long start = PFN_ALIGN(_text); unsigned long end_clone = (unsigned long)__end_rodata_aligned; unsigned long end_global = PFN_ALIGN((unsigned long)_etext); if (!pti_kernel_image_global_ok()) return; pr_debug("mapping partial kernel image into user address space\n"); /* * Note that this will undo _some_ of the work that * pti_set_kernel_image_nonglobal() did to clear the * global bit. */ pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false); /* * pti_clone_pgtable() will set the global bit in any PMDs * that it clones, but we also need to get any PTEs in * the last level for areas that are not huge-page-aligned. */ /* Set the global bit for normal non-__init kernel text: */ set_memory_global(start, (end_global - start) >> PAGE_SHIFT); } static void pti_set_kernel_image_nonglobal(void) { /* * The identity map is created with PMDs, regardless of the * actual length of the kernel. We need to clear * _PAGE_GLOBAL up to a PMD boundary, not just to the end * of the image. */ unsigned long start = PFN_ALIGN(_text); unsigned long end = ALIGN((unsigned long)_end, PMD_SIZE); /* * This clears _PAGE_GLOBAL from the entire kernel image. * pti_clone_kernel_text() map put _PAGE_GLOBAL back for * areas that are mapped to userspace. */ set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT); } /* * Initialize kernel page table isolation */ void __init pti_init(void) { if (!boot_cpu_has(X86_FEATURE_PTI)) return; pr_info("enabled\n"); #ifdef CONFIG_X86_32 /* * We check for X86_FEATURE_PCID here. But the init-code will * clear the feature flag on 32 bit because the feature is not * supported on 32 bit anyway. To print the warning we need to * check with cpuid directly again. */ if (cpuid_ecx(0x1) & BIT(17)) { /* Use printk to work around pr_fmt() */ printk(KERN_WARNING "\n"); printk(KERN_WARNING "************************************************************\n"); printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); printk(KERN_WARNING "** **\n"); printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n"); printk(KERN_WARNING "** Your performance will increase dramatically if you **\n"); printk(KERN_WARNING "** switch to a 64-bit kernel! **\n"); printk(KERN_WARNING "** **\n"); printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); printk(KERN_WARNING "************************************************************\n"); } #endif pti_clone_user_shared(); /* Undo all global bits from the init pagetables in head_64.S: */ pti_set_kernel_image_nonglobal(); /* Replace some of the global bits just for shared entry text: */ /* * This is very early in boot. Device and Late initcalls can do * modprobe before free_initmem() and mark_readonly(). This * pti_clone_entry_text() allows those user-mode-helpers to function, * but notably the text is still RW. */ pti_clone_entry_text(false); pti_setup_espfix64(); pti_setup_vsyscall(); } /* * Finalize the kernel mappings in the userspace page-table. Some of the * mappings for the kernel image might have changed since pti_init() * cloned them. This is because parts of the kernel image have been * mapped RO and/or NX. These changes need to be cloned again to the * userspace page-table. */ void pti_finalize(void) { if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* * This is after free_initmem() (all initcalls are done) and we've done * mark_readonly(). Text is now NX which might've split some PMDs * relative to the early clone. */ pti_clone_entry_text(true); pti_clone_kernel_text(); debug_checkwx_user(); } |
| 4 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H #include <linux/bug.h> #include <linux/kasan-enabled.h> #include <linux/kasan-tags.h> #include <linux/kernel.h> #include <linux/static_key.h> #include <linux/types.h> struct kmem_cache; struct page; struct slab; struct vm_struct; struct task_struct; #ifdef CONFIG_KASAN #include <linux/linkage.h> #include <asm/kasan.h> #endif typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u) #define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) #define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ #define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> /* Software KASAN implementations use shadow memory. */ #ifdef CONFIG_KASAN_SW_TAGS /* This matches KASAN_TAG_INVALID. */ #define KASAN_SHADOW_INIT 0xFE #else #define KASAN_SHADOW_INIT 0 #endif #ifndef PTE_HWTABLE_PTRS #define PTE_HWTABLE_PTRS 0 #endif extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS]; extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD]; extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD]; extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); #ifndef kasan_mem_to_shadow static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET; } #endif int kasan_add_zero_shadow(void *start, unsigned long size); void kasan_remove_zero_shadow(void *start, unsigned long size); /* Enable reporting bugs after kasan_disable_current() */ extern void kasan_enable_current(void); /* Disable reporting bugs for current task */ extern void kasan_disable_current(void); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline int kasan_add_zero_shadow(void *start, unsigned long size) { return 0; } static inline void kasan_remove_zero_shadow(void *start, unsigned long size) {} static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ #ifdef CONFIG_KASAN_HW_TAGS #else /* CONFIG_KASAN_HW_TAGS */ #endif /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_has_integrated_init(void) { return kasan_hw_tags_enabled(); } #ifdef CONFIG_KASAN void __kasan_unpoison_range(const void *addr, size_t size); static __always_inline void kasan_unpoison_range(const void *addr, size_t size) { if (kasan_enabled()) __kasan_unpoison_range(addr, size); } void __kasan_poison_pages(struct page *page, unsigned int order, bool init); static __always_inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) __kasan_poison_pages(page, order, init); } bool __kasan_unpoison_pages(struct page *page, unsigned int order, bool init); static __always_inline bool kasan_unpoison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) return __kasan_unpoison_pages(page, order, init); return false; } void __kasan_poison_slab(struct slab *slab); static __always_inline void kasan_poison_slab(struct slab *slab) { if (kasan_enabled()) __kasan_poison_slab(slab); } void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object); /** * kasan_unpoison_new_object - Temporarily unpoison a new slab object. * @cache: Cache the object belong to. * @object: Pointer to the object. * * This function is intended for the slab allocator's internal use. It * temporarily unpoisons an object from a newly allocated slab without doing * anything else. The object must later be repoisoned by * kasan_poison_new_object(). */ static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache, void *object) { if (kasan_enabled()) __kasan_unpoison_new_object(cache, object); } void __kasan_poison_new_object(struct kmem_cache *cache, void *object); /** * kasan_poison_new_object - Repoison a new slab object. * @cache: Cache the object belong to. * @object: Pointer to the object. * * This function is intended for the slab allocator's internal use. It * repoisons an object that was previously unpoisoned by * kasan_unpoison_new_object() without doing anything else. */ static __always_inline void kasan_poison_new_object(struct kmem_cache *cache, void *object) { if (kasan_enabled()) __kasan_poison_new_object(cache, object); } void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache, const void *object); static __always_inline void * __must_check kasan_init_slab_obj( struct kmem_cache *cache, const void *object) { if (kasan_enabled()) return __kasan_init_slab_obj(cache, object); return (void *)object; } bool __kasan_slab_pre_free(struct kmem_cache *s, void *object, unsigned long ip); /** * kasan_slab_pre_free - Check whether freeing a slab object is safe. * @object: Object to be freed. * * This function checks whether freeing the given object is safe. It may * check for double-free and invalid-free bugs and report them. * * This function is intended only for use by the slab allocator. * * @Return true if freeing the object is unsafe; false otherwise. */ static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object) { if (kasan_enabled()) return __kasan_slab_pre_free(s, object, _RET_IP_); return false; } bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init, bool still_accessible, bool no_quarantine); /** * kasan_slab_free - Poison, initialize, and quarantine a slab object. * @object: Object to be freed. * @init: Whether to initialize the object. * @still_accessible: Whether the object contents are still accessible. * * This function informs that a slab object has been freed and is not * supposed to be accessed anymore, except when @still_accessible is set * (indicating that the object is in a SLAB_TYPESAFE_BY_RCU cache and an RCU * grace period might not have passed yet). * * For KASAN modes that have integrated memory initialization * (kasan_has_integrated_init() == true), this function also initializes * the object's memory. For other modes, the @init argument is ignored. * * This function might also take ownership of the object to quarantine it. * When this happens, KASAN will defer freeing the object to a later * stage and handle it internally until then. The return value indicates * whether KASAN took ownership of the object. * * This function is intended only for use by the slab allocator. * * @Return true if KASAN took ownership of the object; false otherwise. */ static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init, bool still_accessible, bool no_quarantine) { if (kasan_enabled()) return __kasan_slab_free(s, object, init, still_accessible, no_quarantine); return false; } void __kasan_kfree_large(void *ptr, unsigned long ip); static __always_inline void kasan_kfree_large(void *ptr) { if (kasan_enabled()) __kasan_kfree_large(ptr, _RET_IP_); } void * __must_check __kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags, bool init); static __always_inline void * __must_check kasan_slab_alloc( struct kmem_cache *s, void *object, gfp_t flags, bool init) { if (kasan_enabled()) return __kasan_slab_alloc(s, object, flags, init); return object; } void * __must_check __kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags); static __always_inline void * __must_check kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags) { if (kasan_enabled()) return __kasan_kmalloc(s, object, size, flags); return (void *)object; } void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); static __always_inline void * __must_check kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) { if (kasan_enabled()) return __kasan_kmalloc_large(ptr, size, flags); return (void *)ptr; } void * __must_check __kasan_krealloc(const void *object, size_t new_size, gfp_t flags); static __always_inline void * __must_check kasan_krealloc(const void *object, size_t new_size, gfp_t flags) { if (kasan_enabled()) return __kasan_krealloc(object, new_size, flags); return (void *)object; } bool __kasan_mempool_poison_pages(struct page *page, unsigned int order, unsigned long ip); /** * kasan_mempool_poison_pages - Check and poison a mempool page allocation. * @page: Pointer to the page allocation. * @order: Order of the allocation. * * This function is intended for kernel subsystems that cache page allocations * to reuse them instead of freeing them back to page_alloc (e.g. mempool). * * This function is similar to kasan_mempool_poison_object() but operates on * page allocations. * * Before the poisoned allocation can be reused, it must be unpoisoned via * kasan_mempool_unpoison_pages(). * * Return: true if the allocation can be safely reused; false otherwise. */ static __always_inline bool kasan_mempool_poison_pages(struct page *page, unsigned int order) { if (kasan_enabled()) return __kasan_mempool_poison_pages(page, order, _RET_IP_); return true; } void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order, unsigned long ip); /** * kasan_mempool_unpoison_pages - Unpoison a mempool page allocation. * @page: Pointer to the page allocation. * @order: Order of the allocation. * * This function is intended for kernel subsystems that cache page allocations * to reuse them instead of freeing them back to page_alloc (e.g. mempool). * * This function unpoisons a page allocation that was previously poisoned by * kasan_mempool_poison_pages() without zeroing the allocation's memory. For * the tag-based modes, this function assigns a new tag to the allocation. */ static __always_inline void kasan_mempool_unpoison_pages(struct page *page, unsigned int order) { if (kasan_enabled()) __kasan_mempool_unpoison_pages(page, order, _RET_IP_); } bool __kasan_mempool_poison_object(void *ptr, unsigned long ip); /** * kasan_mempool_poison_object - Check and poison a mempool slab allocation. * @ptr: Pointer to the slab allocation. * * This function is intended for kernel subsystems that cache slab allocations * to reuse them instead of freeing them back to the slab allocator (e.g. * mempool). * * This function poisons a slab allocation and saves a free stack trace for it * without initializing the allocation's memory and without putting it into the * quarantine (for the Generic mode). * * This function also performs checks to detect double-free and invalid-free * bugs and reports them. The caller can use the return value of this function * to find out if the allocation is buggy. * * Before the poisoned allocation can be reused, it must be unpoisoned via * kasan_mempool_unpoison_object(). * * This function operates on all slab allocations including large kmalloc * allocations (the ones returned by kmalloc_large() or by kmalloc() with the * size > KMALLOC_MAX_SIZE). * * Return: true if the allocation can be safely reused; false otherwise. */ static __always_inline bool kasan_mempool_poison_object(void *ptr) { if (kasan_enabled()) return __kasan_mempool_poison_object(ptr, _RET_IP_); return true; } void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip); /** * kasan_mempool_unpoison_object - Unpoison a mempool slab allocation. * @ptr: Pointer to the slab allocation. * @size: Size to be unpoisoned. * * This function is intended for kernel subsystems that cache slab allocations * to reuse them instead of freeing them back to the slab allocator (e.g. * mempool). * * This function unpoisons a slab allocation that was previously poisoned via * kasan_mempool_poison_object() and saves an alloc stack trace for it without * initializing the allocation's memory. For the tag-based modes, this function * does not assign a new tag to the allocation and instead restores the * original tags based on the pointer value. * * This function operates on all slab allocations including large kmalloc * allocations (the ones returned by kmalloc_large() or by kmalloc() with the * size > KMALLOC_MAX_SIZE). */ static __always_inline void kasan_mempool_unpoison_object(void *ptr, size_t size) { if (kasan_enabled()) __kasan_mempool_unpoison_object(ptr, size, _RET_IP_); } /* * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for * the hardware tag-based mode that doesn't rely on compiler instrumentation. */ bool __kasan_check_byte(const void *addr, unsigned long ip); static __always_inline bool kasan_check_byte(const void *addr) { if (kasan_enabled()) return __kasan_check_byte(addr, _RET_IP_); return true; } #else /* CONFIG_KASAN */ static inline void kasan_unpoison_range(const void *address, size_t size) {} static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} static inline bool kasan_unpoison_pages(struct page *page, unsigned int order, bool init) { return false; } static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_new_object(struct kmem_cache *cache, void *object) {} static inline void kasan_poison_new_object(struct kmem_cache *cache, void *object) {} static inline void *kasan_init_slab_obj(struct kmem_cache *cache, const void *object) { return (void *)object; } static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object) { return false; } static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init, bool still_accessible, bool no_quarantine) { return false; } static inline void kasan_kfree_large(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags, bool init) { return object; } static inline void *kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags) { return (void *)object; } static inline void *kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) { return (void *)ptr; } static inline void *kasan_krealloc(const void *object, size_t new_size, gfp_t flags) { return (void *)object; } static inline bool kasan_mempool_poison_pages(struct page *page, unsigned int order) { return true; } static inline void kasan_mempool_unpoison_pages(struct page *page, unsigned int order) {} static inline bool kasan_mempool_poison_object(void *ptr) { return true; } static inline void kasan_mempool_unpoison_object(void *ptr, size_t size) {} static inline bool kasan_check_byte(const void *address) { return true; } #endif /* CONFIG_KASAN */ #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} static inline void kasan_unpoison_task_stack_below(const void *watermark) {} #endif #ifdef CONFIG_KASAN_GENERIC struct kasan_cache { int alloc_meta_offset; int free_meta_offset; }; size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object); void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags); void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); #else /* CONFIG_KASAN_GENERIC */ /* Tag-based KASAN modes do not use per-object metadata. */ static inline size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object) { return 0; } /* And no cache-related metadata initialization is required. */ static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) static inline void *kasan_reset_tag(const void *addr) { return (void *)arch_kasan_reset_tag(addr); } /** * kasan_report - print a report about a bad memory access detected by KASAN * @addr: address of the bad access * @size: size of the bad access * @is_write: whether the bad access is a write or a read * @ip: instruction pointer for the accessibility check or the bad access itself */ bool kasan_report(const void *addr, size_t size, bool is_write, unsigned long ip); #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline void *kasan_reset_tag(const void *addr) { return (void *)addr; } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS*/ #ifdef CONFIG_KASAN_HW_TAGS void kasan_report_async(void); #endif /* CONFIG_KASAN_HW_TAGS */ #ifdef CONFIG_KASAN_GENERIC void __init kasan_init_generic(void); #else static inline void kasan_init_generic(void) { } #endif #ifdef CONFIG_KASAN_SW_TAGS void __init kasan_init_sw_tags(void); #else static inline void kasan_init_sw_tags(void) { } #endif #ifdef CONFIG_KASAN_HW_TAGS void kasan_init_hw_tags_cpu(void); void __init kasan_init_hw_tags(void); #else static inline void kasan_init_hw_tags_cpu(void) { } static inline void kasan_init_hw_tags(void) { } #endif #ifdef CONFIG_KASAN_VMALLOC #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, unsigned long flags); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size, gfp_t gfp_mask) { return 0; } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, unsigned long flags) { } #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags); static __always_inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags) { if (kasan_enabled()) return __kasan_unpoison_vmalloc(start, size, flags); return (void *)start; } void __kasan_poison_vmalloc(const void *start, unsigned long size); static __always_inline void kasan_poison_vmalloc(const void *start, unsigned long size) { if (kasan_enabled()) __kasan_poison_vmalloc(start, size); } #else /* CONFIG_KASAN_VMALLOC */ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size, gfp_t gfp_mask) { return 0; } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, unsigned long flags) { } static inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags) { return (void *)start; } static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) /* * These functions allocate and free shadow memory for kernel modules. * They are only required when KASAN_VMALLOC is not supported, as otherwise * shadow memory is allocated by the generic vmalloc handlers. */ int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask); void kasan_free_module_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ static inline int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask) { return 0; } static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_non_canonical_hook(unsigned long addr); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline void kasan_non_canonical_hook(unsigned long addr) { } #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ #endif /* LINUX_KASAN_H */ |
| 274 1 3 279 271 274 10 274 273 376 164 161 99 222 222 59 59 8 8 8 263 227 36 232 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/err.h> #include <linux/uuid.h> #include "ctree.h" #include "fs.h" #include "messages.h" #include "transaction.h" #include "disk-io.h" #include "qgroup.h" #include "space-info.h" #include "accessors.h" #include "root-tree.h" #include "orphan.h" /* * Read a root item from the tree. In case we detect a root item smaller then * sizeof(root_item), we know it's an old version of the root structure and * initialize all new fields to zero. The same happens if we detect mismatching * generation numbers as then we know the root was once mounted with an older * kernel that was not aware of the root item structure change. */ static void btrfs_read_root_item(struct extent_buffer *eb, int slot, struct btrfs_root_item *item) { u32 len; int need_reset = 0; len = btrfs_item_size(eb, slot); read_extent_buffer(eb, item, btrfs_item_ptr_offset(eb, slot), min_t(u32, len, sizeof(*item))); if (len < sizeof(*item)) need_reset = 1; if (!need_reset && btrfs_root_generation(item) != btrfs_root_generation_v2(item)) { if (btrfs_root_generation_v2(item) != 0) { btrfs_warn(eb->fs_info, "mismatching generation and generation_v2 found in root item. This root was probably mounted with an older kernel. Resetting all new fields."); } need_reset = 1; } if (need_reset) { /* Clear all members from generation_v2 onwards. */ memset_startat(item, 0, generation_v2); generate_random_guid(item->uuid); } } /* * Lookup the root by the key. * * root: the root of the root tree * search_key: the key to search * path: the path we search * root_item: the root item of the tree we look for * root_key: the root key of the tree we look for * * If ->offset of 'search_key' is -1ULL, it means we are not sure the offset * of the search key, just lookup the root with the highest offset for a * given objectid. * * If we find something return 0, otherwise > 0, < 0 on error. */ int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key, struct btrfs_path *path, struct btrfs_root_item *root_item, struct btrfs_key *root_key) { struct btrfs_key found_key; struct extent_buffer *l; int ret; int slot; ret = btrfs_search_slot(NULL, root, search_key, path, 0, 0); if (ret < 0) return ret; if (search_key->offset != -1ULL) { /* the search key is exact */ if (ret > 0) goto out; } else { /* * Key with offset -1 found, there would have to exist a root * with such id, but this is out of the valid range. */ if (unlikely(ret == 0)) { ret = -EUCLEAN; goto out; } if (path->slots[0] == 0) goto out; path->slots[0]--; ret = 0; } l = path->nodes[0]; slot = path->slots[0]; btrfs_item_key_to_cpu(l, &found_key, slot); if (found_key.objectid != search_key->objectid || found_key.type != BTRFS_ROOT_ITEM_KEY) { ret = 1; goto out; } if (root_item) btrfs_read_root_item(l, slot, root_item); if (root_key) memcpy(root_key, &found_key, sizeof(found_key)); out: btrfs_release_path(path); return ret; } void btrfs_set_root_node(struct btrfs_root_item *item, struct extent_buffer *node) { btrfs_set_root_bytenr(item, node->start); btrfs_set_root_level(item, btrfs_header_level(node)); btrfs_set_root_generation(item, btrfs_header_generation(node)); } /* * copy the data in 'item' into the btree */ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_key *key, struct btrfs_root_item *item) { struct btrfs_fs_info *fs_info = root->fs_info; BTRFS_PATH_AUTO_FREE(path); struct extent_buffer *l; int ret; int slot; unsigned long ptr; u32 old_len; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(trans, root, key, path, 0, 1); if (ret < 0) return ret; if (unlikely(ret > 0)) { btrfs_crit(fs_info, "unable to find root key (%llu %u %llu) in tree %llu", key->objectid, key->type, key->offset, btrfs_root_id(root)); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } l = path->nodes[0]; slot = path->slots[0]; ptr = btrfs_item_ptr_offset(l, slot); old_len = btrfs_item_size(l, slot); /* * If this is the first time we update the root item which originated * from an older kernel, we need to enlarge the item size to make room * for the added fields. */ if (old_len < sizeof(*item)) { btrfs_release_path(path); ret = btrfs_search_slot(trans, root, key, path, -1, 1); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_del_item(trans, root, path); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } btrfs_release_path(path); ret = btrfs_insert_empty_item(trans, root, path, key, sizeof(*item)); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } l = path->nodes[0]; slot = path->slots[0]; ptr = btrfs_item_ptr_offset(l, slot); } /* * Update generation_v2 so at the next mount we know the new root * fields are valid. */ btrfs_set_root_generation_v2(item, btrfs_root_generation(item)); write_extent_buffer(l, item, ptr, sizeof(*item)); return ret; } int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_root_item *item) { /* * Make sure generation v1 and v2 match. See update_root for details. */ btrfs_set_root_generation_v2(item, btrfs_root_generation(item)); return btrfs_insert_item(trans, root, key, item, sizeof(*item)); } int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info) { struct btrfs_root *tree_root = fs_info->tree_root; struct extent_buffer *leaf; BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct btrfs_root *root; int err = 0; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = BTRFS_ORPHAN_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = 0; while (1) { u64 root_objectid; ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); if (ret < 0) { err = ret; break; } leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(tree_root, path); if (ret < 0) err = ret; if (ret != 0) break; leaf = path->nodes[0]; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); btrfs_release_path(path); if (key.objectid != BTRFS_ORPHAN_OBJECTID || key.type != BTRFS_ORPHAN_ITEM_KEY) break; root_objectid = key.offset; key.offset++; root = btrfs_get_fs_root(fs_info, root_objectid, false); err = PTR_ERR_OR_ZERO(root); if (err && err != -ENOENT) { break; } else if (err == -ENOENT) { struct btrfs_trans_handle *trans; btrfs_release_path(path); trans = btrfs_join_transaction(tree_root); if (IS_ERR(trans)) { err = PTR_ERR(trans); btrfs_handle_fs_error(fs_info, err, "Failed to start trans to delete orphan item"); break; } err = btrfs_del_orphan_item(trans, tree_root, root_objectid); btrfs_end_transaction(trans); if (err) { btrfs_handle_fs_error(fs_info, err, "Failed to delete root orphan item"); break; } continue; } WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)); if (btrfs_root_refs(&root->root_item) == 0) { struct btrfs_key drop_key; btrfs_disk_key_to_cpu(&drop_key, &root->root_item.drop_progress); /* * If we have a non-zero drop_progress then we know we * made it partly through deleting this snapshot, and * thus we need to make sure we block any balance from * happening until this snapshot is completely dropped. */ if (drop_key.objectid != 0 || drop_key.type != 0 || drop_key.offset != 0) { set_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags); set_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state); } set_bit(BTRFS_ROOT_DEAD_TREE, &root->state); btrfs_add_dead_root(root); } btrfs_put_root(root); } return err; } /* drop the root item for 'key' from the tree root */ int btrfs_del_root(struct btrfs_trans_handle *trans, const struct btrfs_key *key) { struct btrfs_root *root = trans->fs_info->tree_root; BTRFS_PATH_AUTO_FREE(path); int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(trans, root, key, path, -1, 1); if (ret < 0) return ret; if (unlikely(ret > 0)) /* The root must exist but we did not find it by the key. */ return -EUCLEAN; return btrfs_del_item(trans, root, path); } int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 *sequence, const struct fscrypt_str *name) { struct btrfs_root *tree_root = trans->fs_info->tree_root; BTRFS_PATH_AUTO_FREE(path); struct btrfs_root_ref *ref; struct extent_buffer *leaf; struct btrfs_key key; unsigned long ptr; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = root_id; key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) { return ret; } else if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); ptr = (unsigned long)(ref + 1); if ((btrfs_root_ref_dirid(leaf, ref) != dirid) || (btrfs_root_ref_name_len(leaf, ref) != name->len) || memcmp_extent_buffer(leaf, name->name, ptr, name->len)) return -ENOENT; *sequence = btrfs_root_ref_sequence(leaf, ref); ret = btrfs_del_item(trans, tree_root, path); if (ret) return ret; } else { return -ENOENT; } if (key.type == BTRFS_ROOT_BACKREF_KEY) { btrfs_release_path(path); key.objectid = ref_id; key.type = BTRFS_ROOT_REF_KEY; key.offset = root_id; goto again; } return ret; } /* * add a btrfs_root_ref item. type is either BTRFS_ROOT_REF_KEY * or BTRFS_ROOT_BACKREF_KEY. * * The dirid, sequence, name and name_len refer to the directory entry * that is referencing the root. * * For a forward ref, the root_id is the id of the tree referencing * the root and ref_id is the id of the subvol or snapshot. * * For a back ref the root_id is the id of the subvol or snapshot and * ref_id is the id of the tree referencing it. * * Will return 0, -ENOMEM, or anything from the CoW path */ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 sequence, const struct fscrypt_str *name) { struct btrfs_root *tree_root = trans->fs_info->tree_root; struct btrfs_key key; int ret; BTRFS_PATH_AUTO_FREE(path); struct btrfs_root_ref *ref; struct extent_buffer *leaf; unsigned long ptr; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = root_id; key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = ref_id; again: ret = btrfs_insert_empty_item(trans, tree_root, path, &key, sizeof(*ref) + name->len); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); btrfs_set_root_ref_dirid(leaf, ref, dirid); btrfs_set_root_ref_sequence(leaf, ref, sequence); btrfs_set_root_ref_name_len(leaf, ref, name->len); ptr = (unsigned long)(ref + 1); write_extent_buffer(leaf, name->name, ptr, name->len); if (key.type == BTRFS_ROOT_BACKREF_KEY) { btrfs_release_path(path); key.objectid = ref_id; key.type = BTRFS_ROOT_REF_KEY; key.offset = root_id; goto again; } return 0; } /* * Old btrfs forgets to init root_item->flags and root_item->byte_limit * for subvolumes. To work around this problem, we steal a bit from * root_item->inode_item->flags, and use it to indicate if those fields * have been properly initialized. */ void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item) { u64 inode_flags = btrfs_stack_inode_flags(&root_item->inode); if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) { inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT; btrfs_set_stack_inode_flags(&root_item->inode, inode_flags); btrfs_set_root_flags(root_item, 0); btrfs_set_root_limit(root_item, 0); } } void btrfs_update_root_times(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_root_item *item = &root->root_item; struct timespec64 ct; ktime_get_real_ts64(&ct); spin_lock(&root->root_item_lock); btrfs_set_root_ctransid(item, trans->transid); btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec); btrfs_set_stack_timespec_nsec(&item->ctime, ct.tv_nsec); spin_unlock(&root->root_item_lock); } /* * Reserve space for subvolume operation. * * root: the root of the parent directory * rsv: block reservation * items: the number of items that we need do reservation * use_global_rsv: allow fallback to the global block reservation * * This function is used to reserve the space for snapshot/subvolume * creation and deletion. Those operations are different with the * common file/directory operations, they change two fs/file trees * and root tree, the number of items that the qgroup reserves is * different with the free space reservation. So we can not use * the space reservation mechanism in start_transaction(). */ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int items, bool use_global_rsv) { u64 qgroup_num_bytes = 0; u64 num_bytes; int ret; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; if (btrfs_qgroup_enabled(fs_info)) { /* One for parent inode, two for dir entries */ qgroup_num_bytes = 3 * fs_info->nodesize; ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true, false); if (ret) return ret; } num_bytes = btrfs_calc_insert_metadata_size(fs_info, items); rsv->space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); ret = btrfs_block_rsv_add(fs_info, rsv, num_bytes, BTRFS_RESERVE_FLUSH_ALL); if (ret == -ENOSPC && use_global_rsv) ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, true); if (ret && qgroup_num_bytes) btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes); if (!ret) { spin_lock(&rsv->lock); rsv->qgroup_rsv_reserved += qgroup_num_bytes; spin_unlock(&rsv->lock); } return ret; } |
| 13 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> #include <asm/cpufeature.h> #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* * In case of Page Table Isolation active, we acquire two PGDs instead of one. * Being order-1, it is both 8k in size and 8k-aligned. That lets us just * flip bit 12 in a pointer to swap between the two 4k halves. */ static inline unsigned int pgd_allocation_order(void) { if (cpu_feature_enabled(X86_FEATURE_PTI)) return 1; return 0; } /* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pgtable_t pte_alloc_one(struct mm_struct *); extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, unsigned long address) { ___pte_free_tlb(tlb, pte); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate_kernel_safe(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { unsigned long pfn = page_to_pfn(pte); paravirt_alloc_pte(mm, pfn); set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { ___pmd_free_tlb(tlb, pmd); } #ifdef CONFIG_X86_PAE extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); #else /* !CONFIG_X86_PAE */ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); } #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { ___pud_free_tlb(tlb, pud); } #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { if (pgtable_l5_enabled()) ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_H */ |
| 35 82 82 35 35 1 2 82 4 86 6 6 18 18 18 96 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 79 29 5 5 85 92 90 90 90 90 90 2 1 78 80 80 78 85 85 1 85 84 4 85 85 2 83 83 83 83 83 83 83 78 78 78 80 80 80 4 4 54 50 4 143 141 3 81 108 112 37 33 33 81 81 1 3 26 24 1 2 1 3 26 25 3 3 18 18 16 2 6 3 7 82 65 35 82 15 15 15 4 1 3 7 10 7 18 5 5 15 15 15 15 18 18 1 17 18 18 18 8 3 3 8 5 3 86 16 86 43 23 20 23 41 31 26 9 82 82 82 41 2 22 18 1 9 10 10 10 82 82 41 2 82 65 1 16 21 26 10 12 6 23 23 23 26 3 15 2 15 15 36 4 12 34 36 15 21 17 16 23 72 55 15 8 18 5 2 6 18 2 2 14 41 41 36 3 36 36 36 41 36 36 41 41 34 25 1 26 7 84 2 2 17 80 80 20 71 27 48 46 28 4 28 34 19 37 39 40 1 40 2 18 18 7 1 5 5 1 5 5 5 6 5 1 2 1 1 86 1 1 86 39 36 65 19 65 41 35 40 40 39 2 2 27 62 65 65 17 24 39 18 36 19 50 16 16 18 18 6 1 16 16 5 5 2 5 18 17 13 5 18 18 16 12 86 19 85 86 2 86 18 1 85 7 10 5 49 3 42 8 2 11 64 18 66 1 66 20 49 65 21 22 41 16 65 40 85 18 86 16 86 85 18 7 6 5 5 5 3 2 2 3 49 2 1 48 51 49 2 2 2 2 2 90 3 87 86 14 74 47 7 47 5 1 50 1 86 90 22 19 3 2 21 7 18 4 3 17 4 2 2 2 4 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 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/list_sort.h> #include <linux/iversion.h> #include "misc.h" #include "ctree.h" #include "tree-log.h" #include "disk-io.h" #include "locking.h" #include "backref.h" #include "compression.h" #include "qgroup.h" #include "block-group.h" #include "space-info.h" #include "inode-item.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" #include "dir-item.h" #include "file-item.h" #include "file.h" #include "orphan.h" #include "print-tree.h" #include "tree-checker.h" #define MAX_CONFLICT_INODES 10 /* magic values for the inode_only field in btrfs_log_inode: * * LOG_INODE_ALL means to log everything * LOG_INODE_EXISTS means to log just enough to recreate the inode * during log replay */ enum { LOG_INODE_ALL, LOG_INODE_EXISTS, }; /* * directory trouble cases * * 1) on rename or unlink, if the inode being unlinked isn't in the fsync * log, we must force a full commit before doing an fsync of the directory * where the unlink was done. * ---> record transid of last unlink/rename per directory * * mkdir foo/some_dir * normal commit * rename foo/some_dir foo2/some_dir * mkdir foo/some_dir * fsync foo/some_dir/some_file * * The fsync above will unlink the original some_dir without recording * it in its new location (foo2). After a crash, some_dir will be gone * unless the fsync of some_file forces a full commit * * 2) we must log any new names for any file or dir that is in the fsync * log. ---> check inode while renaming/linking. * * 2a) we must log any new names for any file or dir during rename * when the directory they are being removed from was logged. * ---> check inode and old parent dir during rename * * 2a is actually the more important variant. With the extra logging * a crash might unlink the old name without recreating the new one * * 3) after a crash, we must go through any directories with a link count * of zero and redo the rm -rf * * mkdir f1/foo * normal commit * rm -rf f1/foo * fsync(f1) * * The directory f1 was fully removed from the FS, but fsync was never * called on f1, only its parent dir. After a crash the rm -rf must * be replayed. This must be able to recurse down the entire * directory tree. The inode link count fixup code takes care of the * ugly details. */ /* * stages for the tree walking. The first * stage (0) is to only pin down the blocks we find * the second stage (1) is to make sure that all the inodes * we find in the log are created in the subvolume. * * The last stage is to deal with directories and links and extents * and all the other fun semantics */ enum { LOG_WALK_PIN_ONLY, LOG_WALK_REPLAY_INODES, LOG_WALK_REPLAY_DIR_INDEX, LOG_WALK_REPLAY_ALL, }; /* * The walk control struct is used to pass state down the chain when processing * the log tree. The stage field tells us which part of the log tree processing * we are currently doing. */ struct walk_control { /* * Signal that we are freeing the metadata extents of a log tree. * This is used at transaction commit time while freeing a log tree. */ bool free; /* * Signal that we are pinning the metadata extents of a log tree and the * data extents its leaves point to (if using mixed block groups). * This happens in the first stage of log replay to ensure that during * replay, while we are modifying subvolume trees, we don't overwrite * the metadata extents of log trees. */ bool pin; /* What stage of the replay code we're currently in. */ int stage; /* * Ignore any items from the inode currently being processed. Needs * to be set every time we find a BTRFS_INODE_ITEM_KEY. */ bool ignore_cur_inode; /* * The root we are currently replaying to. This is NULL for the replay * stage LOG_WALK_PIN_ONLY. */ struct btrfs_root *root; /* The log tree we are currently processing (not NULL for any stage). */ struct btrfs_root *log; /* The transaction handle used for replaying all log trees. */ struct btrfs_trans_handle *trans; /* * The function that gets used to process blocks we find in the tree. * Note the extent_buffer might not be up to date when it is passed in, * and it must be checked or read if you need the data inside it. */ int (*process_func)(struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level); /* * The following are used only when stage is >= LOG_WALK_REPLAY_INODES * and by the replay_one_buffer() callback. */ /* The current log leaf being processed. */ struct extent_buffer *log_leaf; /* The key being processed of the current log leaf. */ struct btrfs_key log_key; /* The slot being processed of the current log leaf. */ int log_slot; /* A path used for searches and modifications to subvolume trees. */ struct btrfs_path *subvol_path; }; static void do_abort_log_replay(struct walk_control *wc, const char *function, unsigned int line, int error, const char *fmt, ...) { struct btrfs_fs_info *fs_info = wc->trans->fs_info; struct va_format vaf; va_list args; /* * Do nothing if we already aborted, to avoid dumping leaves again which * can be verbose. Further more, only the first call is useful since it * is where we have a problem. Note that we do not use the flag * BTRFS_FS_STATE_TRANS_ABORTED because log replay calls functions that * are outside of tree-log.c that can abort transactions (such as * btrfs_add_link() for example), so if that happens we still want to * dump all log replay specific information below. */ if (test_and_set_bit(BTRFS_FS_STATE_LOG_REPLAY_ABORTED, &fs_info->fs_state)) return; btrfs_abort_transaction(wc->trans, error); if (wc->subvol_path->nodes[0]) { btrfs_crit(fs_info, "subvolume (root %llu) leaf currently being processed:", btrfs_root_id(wc->root)); btrfs_print_leaf(wc->subvol_path->nodes[0]); } if (wc->log_leaf) { btrfs_crit(fs_info, "log tree (for root %llu) leaf currently being processed (slot %d key %llu %u %llu):", btrfs_root_id(wc->root), wc->log_slot, wc->log_key.objectid, wc->log_key.type, wc->log_key.offset); btrfs_print_leaf(wc->log_leaf); } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; btrfs_crit(fs_info, "log replay failed in %s:%u for root %llu, stage %d, with error %d: %pV", function, line, btrfs_root_id(wc->root), wc->stage, error, &vaf); va_end(args); } /* * Use this for aborting a transaction during log replay while we are down the * call chain of replay_one_buffer(), so that we get a lot more useful * information for debugging issues when compared to a plain call to * btrfs_abort_transaction(). */ #define btrfs_abort_log_replay(wc, error, fmt, args...) \ do_abort_log_replay((wc), __func__, __LINE__, (error), fmt, ##args) static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, int inode_only, struct btrfs_log_ctx *ctx); static int link_to_fixup_dir(struct walk_control *wc, u64 objectid); static noinline int replay_dir_deletes(struct walk_control *wc, u64 dirid, bool del_all); static void wait_log_commit(struct btrfs_root *root, int transid); /* * tree logging is a special write ahead log used to make sure that * fsyncs and O_SYNCs can happen without doing full tree commits. * * Full tree commits are expensive because they require commonly * modified blocks to be recowed, creating many dirty pages in the * extent tree an 4x-6x higher write load than ext3. * * Instead of doing a tree commit on every fsync, we use the * key ranges and transaction ids to find items for a given file or directory * that have changed in this transaction. Those items are copied into * a special tree (one per subvolume root), that tree is written to disk * and then the fsync is considered complete. * * After a crash, items are copied out of the log-tree back into the * subvolume tree. Any file data extents found are recorded in the extent * allocation tree, and the log-tree freed. * * The log tree is read three times, once to pin down all the extents it is * using in ram and once, once to create all the inodes logged in the tree * and once to do all the other items. */ static struct btrfs_inode *btrfs_iget_logging(u64 objectid, struct btrfs_root *root) { unsigned int nofs_flag; struct btrfs_inode *inode; /* Only meant to be called for subvolume roots and not for log roots. */ ASSERT(btrfs_is_fstree(btrfs_root_id(root))); /* * We're holding a transaction handle whether we are logging or * replaying a log tree, so we must make sure NOFS semantics apply * because btrfs_alloc_inode() may be triggered and it uses GFP_KERNEL * to allocate an inode, which can recurse back into the filesystem and * attempt a transaction commit, resulting in a deadlock. */ nofs_flag = memalloc_nofs_save(); inode = btrfs_iget(objectid, root); memalloc_nofs_restore(nofs_flag); return inode; } /* * start a sub transaction and setup the log tree * this increments the log tree writer count to make the people * syncing the tree wait for us to finish */ static int start_log_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *tree_root = fs_info->tree_root; const bool zoned = btrfs_is_zoned(fs_info); int ret = 0; bool created = false; /* * First check if the log root tree was already created. If not, create * it before locking the root's log_mutex, just to keep lockdep happy. */ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state)) { mutex_lock(&tree_root->log_mutex); if (!fs_info->log_root_tree) { ret = btrfs_init_log_root_tree(trans, fs_info); if (!ret) { set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state); created = true; } } mutex_unlock(&tree_root->log_mutex); if (ret) return ret; } mutex_lock(&root->log_mutex); again: if (root->log_root) { int index = (root->log_transid + 1) % 2; if (btrfs_need_log_full_commit(trans)) { ret = BTRFS_LOG_FORCE_COMMIT; goto out; } if (zoned && atomic_read(&root->log_commit[index])) { wait_log_commit(root, root->log_transid - 1); goto again; } if (!root->log_start_pid) { clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } else if (root->log_start_pid != current->pid) { set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); } } else { /* * This means fs_info->log_root_tree was already created * for some other FS trees. Do the full commit not to mix * nodes from multiple log transactions to do sequential * writing. */ if (zoned && !created) { ret = BTRFS_LOG_FORCE_COMMIT; goto out; } ret = btrfs_add_log_tree(trans, root); if (ret) goto out; set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } atomic_inc(&root->log_writers); if (!ctx->logging_new_name) { int index = root->log_transid % 2; list_add_tail(&ctx->list, &root->log_ctxs[index]); ctx->log_transid = root->log_transid; } out: mutex_unlock(&root->log_mutex); return ret; } /* * returns 0 if there was a log transaction running and we were able * to join, or returns -ENOENT if there were not transactions * in progress */ static int join_running_log_trans(struct btrfs_root *root) { const bool zoned = btrfs_is_zoned(root->fs_info); int ret = -ENOENT; if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) return ret; mutex_lock(&root->log_mutex); again: if (root->log_root) { int index = (root->log_transid + 1) % 2; ret = 0; if (zoned && atomic_read(&root->log_commit[index])) { wait_log_commit(root, root->log_transid - 1); goto again; } atomic_inc(&root->log_writers); } mutex_unlock(&root->log_mutex); return ret; } /* * This either makes the current running log transaction wait * until you call btrfs_end_log_trans() or it makes any future * log transactions wait until you call btrfs_end_log_trans() */ void btrfs_pin_log_trans(struct btrfs_root *root) { atomic_inc(&root->log_writers); } /* * indicate we're done making changes to the log tree * and wake up anyone waiting to do a sync */ void btrfs_end_log_trans(struct btrfs_root *root) { if (atomic_dec_and_test(&root->log_writers)) { /* atomic_dec_and_test implies a barrier */ cond_wake_up_nomb(&root->log_writer_wait); } } /* * process_func used to pin down extents, write them or wait on them */ static int process_one_buffer(struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { struct btrfs_root *log = wc->log; struct btrfs_trans_handle *trans = wc->trans; struct btrfs_fs_info *fs_info = log->fs_info; int ret = 0; /* * If this fs is mixed then we need to be able to process the leaves to * pin down any logged extents, so we have to read the block. */ if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) { struct btrfs_tree_parent_check check = { .level = level, .transid = gen }; ret = btrfs_read_extent_buffer(eb, &check); if (unlikely(ret)) { if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(fs_info, ret, NULL); return ret; } } if (wc->pin) { ASSERT(trans != NULL); ret = btrfs_pin_extent_for_log_replay(trans, eb); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } if (btrfs_buffer_uptodate(eb, gen, false) && level == 0) { ret = btrfs_exclude_logged_extents(eb); if (ret) btrfs_abort_transaction(trans, ret); } } return ret; } /* * Item overwrite used by log replay. The given log tree leaf, slot and key * from the walk_control structure all refer to the source data we are copying * out. * * The given root is for the tree we are copying into, and path is a scratch * path for use in this function (it should be released on entry and will be * released on exit). * * If the key is already in the destination tree the existing item is * overwritten. If the existing item isn't big enough, it is extended. * If it is too large, it is truncated. * * If the key isn't in the destination yet, a new item is inserted. */ static int overwrite_item(struct walk_control *wc) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; int ret; u32 item_size; u64 saved_i_size = 0; int save_old_i_size = 0; unsigned long src_ptr; unsigned long dst_ptr; struct extent_buffer *dst_eb; int dst_slot; const bool is_inode_item = (wc->log_key.type == BTRFS_INODE_ITEM_KEY); /* * This is only used during log replay, so the root is always from a * fs/subvolume tree. In case we ever need to support a log root, then * we'll have to clone the leaf in the path, release the path and use * the leaf before writing into the log tree. See the comments at * copy_items() for more details. */ ASSERT(btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID); item_size = btrfs_item_size(wc->log_leaf, wc->log_slot); src_ptr = btrfs_item_ptr_offset(wc->log_leaf, wc->log_slot); /* Look for the key in the destination tree. */ ret = btrfs_search_slot(NULL, root, &wc->log_key, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to search subvolume tree for key (%llu %u %llu) root %llu", wc->log_key.objectid, wc->log_key.type, wc->log_key.offset, btrfs_root_id(root)); return ret; } dst_eb = wc->subvol_path->nodes[0]; dst_slot = wc->subvol_path->slots[0]; if (ret == 0) { char *src_copy; const u32 dst_size = btrfs_item_size(dst_eb, dst_slot); if (dst_size != item_size) goto insert; if (item_size == 0) { btrfs_release_path(wc->subvol_path); return 0; } src_copy = kmalloc(item_size, GFP_NOFS); if (!src_copy) { btrfs_abort_log_replay(wc, -ENOMEM, "failed to allocate memory for log leaf item"); return -ENOMEM; } read_extent_buffer(wc->log_leaf, src_copy, src_ptr, item_size); dst_ptr = btrfs_item_ptr_offset(dst_eb, dst_slot); ret = memcmp_extent_buffer(dst_eb, src_copy, dst_ptr, item_size); kfree(src_copy); /* * they have the same contents, just return, this saves * us from cowing blocks in the destination tree and doing * extra writes that may not have been done by a previous * sync */ if (ret == 0) { btrfs_release_path(wc->subvol_path); return 0; } /* * We need to load the old nbytes into the inode so when we * replay the extents we've logged we get the right nbytes. */ if (is_inode_item) { struct btrfs_inode_item *item; u64 nbytes; u32 mode; item = btrfs_item_ptr(dst_eb, dst_slot, struct btrfs_inode_item); nbytes = btrfs_inode_nbytes(dst_eb, item); item = btrfs_item_ptr(wc->log_leaf, wc->log_slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(wc->log_leaf, item, nbytes); /* * If this is a directory we need to reset the i_size to * 0 so that we can set it up properly when replaying * the rest of the items in this log. */ mode = btrfs_inode_mode(wc->log_leaf, item); if (S_ISDIR(mode)) btrfs_set_inode_size(wc->log_leaf, item, 0); } } else if (is_inode_item) { struct btrfs_inode_item *item; u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out * properly when we replay the extents. */ item = btrfs_item_ptr(wc->log_leaf, wc->log_slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(wc->log_leaf, item, 0); /* * If this is a directory we need to reset the i_size to 0 so * that we can set it up properly when replaying the rest of * the items in this log. */ mode = btrfs_inode_mode(wc->log_leaf, item); if (S_ISDIR(mode)) btrfs_set_inode_size(wc->log_leaf, item, 0); } insert: btrfs_release_path(wc->subvol_path); /* try to insert the key into the destination tree */ wc->subvol_path->skip_release_on_error = 1; ret = btrfs_insert_empty_item(trans, root, wc->subvol_path, &wc->log_key, item_size); wc->subvol_path->skip_release_on_error = 0; dst_eb = wc->subvol_path->nodes[0]; dst_slot = wc->subvol_path->slots[0]; /* make sure any existing item is the correct size */ if (ret == -EEXIST || ret == -EOVERFLOW) { const u32 found_size = btrfs_item_size(dst_eb, dst_slot); if (found_size > item_size) btrfs_truncate_item(trans, wc->subvol_path, item_size, 1); else if (found_size < item_size) btrfs_extend_item(trans, wc->subvol_path, item_size - found_size); } else if (ret) { btrfs_abort_log_replay(wc, ret, "failed to insert item for key (%llu %u %llu)", wc->log_key.objectid, wc->log_key.type, wc->log_key.offset); return ret; } dst_ptr = btrfs_item_ptr_offset(dst_eb, dst_slot); /* don't overwrite an existing inode if the generation number * was logged as zero. This is done when the tree logging code * is just logging an inode to make sure it exists after recovery. * * Also, don't overwrite i_size on directories during replay. * log replay inserts and removes directory items based on the * state of the tree found in the subvolume, and i_size is modified * as it goes */ if (is_inode_item && ret == -EEXIST) { struct btrfs_inode_item *src_item; struct btrfs_inode_item *dst_item; src_item = (struct btrfs_inode_item *)src_ptr; dst_item = (struct btrfs_inode_item *)dst_ptr; if (btrfs_inode_generation(wc->log_leaf, src_item) == 0) { const u64 ino_size = btrfs_inode_size(wc->log_leaf, src_item); /* * For regular files an ino_size == 0 is used only when * logging that an inode exists, as part of a directory * fsync, and the inode wasn't fsynced before. In this * case don't set the size of the inode in the fs/subvol * tree, otherwise we would be throwing valid data away. */ if (S_ISREG(btrfs_inode_mode(wc->log_leaf, src_item)) && S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) && ino_size != 0) btrfs_set_inode_size(dst_eb, dst_item, ino_size); goto no_copy; } if (S_ISDIR(btrfs_inode_mode(wc->log_leaf, src_item)) && S_ISDIR(btrfs_inode_mode(dst_eb, dst_item))) { save_old_i_size = 1; saved_i_size = btrfs_inode_size(dst_eb, dst_item); } } copy_extent_buffer(dst_eb, wc->log_leaf, dst_ptr, src_ptr, item_size); if (save_old_i_size) { struct btrfs_inode_item *dst_item; dst_item = (struct btrfs_inode_item *)dst_ptr; btrfs_set_inode_size(dst_eb, dst_item, saved_i_size); } /* make sure the generation is filled in */ if (is_inode_item) { struct btrfs_inode_item *dst_item; dst_item = (struct btrfs_inode_item *)dst_ptr; if (btrfs_inode_generation(dst_eb, dst_item) == 0) btrfs_set_inode_generation(dst_eb, dst_item, trans->transid); } no_copy: btrfs_release_path(wc->subvol_path); return 0; } static int read_alloc_one_name(struct extent_buffer *eb, void *start, int len, struct fscrypt_str *name) { char *buf; buf = kmalloc(len, GFP_NOFS); if (!buf) return -ENOMEM; read_extent_buffer(eb, buf, (unsigned long)start, len); name->name = buf; name->len = len; return 0; } /* replays a single extent in 'eb' at 'slot' with 'key' into the * subvolume 'root'. path is released on entry and should be released * on exit. * * extents in the log tree have not been allocated out of the extent * tree yet. So, this completes the allocation, taking a reference * as required if the extent already exists or creating a new extent * if it isn't in the extent allocation tree yet. * * The extent is inserted into the file, dropping any existing extents * from the file that overlap the new one. */ static noinline int replay_one_extent(struct walk_control *wc) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_fs_info *fs_info = root->fs_info; int found_type; u64 extent_end; const u64 start = wc->log_key.offset; u64 nbytes = 0; u64 csum_start; u64 csum_end; LIST_HEAD(ordered_sums); u64 offset; unsigned long dest_offset; struct btrfs_key ins; struct btrfs_file_extent_item *item; struct btrfs_inode *inode = NULL; int ret = 0; item = btrfs_item_ptr(wc->log_leaf, wc->log_slot, struct btrfs_file_extent_item); found_type = btrfs_file_extent_type(wc->log_leaf, item); if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { extent_end = start + btrfs_file_extent_num_bytes(wc->log_leaf, item); /* Holes don't take up space. */ if (btrfs_file_extent_disk_bytenr(wc->log_leaf, item) != 0) nbytes = btrfs_file_extent_num_bytes(wc->log_leaf, item); } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { nbytes = btrfs_file_extent_ram_bytes(wc->log_leaf, item); extent_end = ALIGN(start + nbytes, fs_info->sectorsize); } else { btrfs_abort_log_replay(wc, -EUCLEAN, "unexpected extent type=%d root=%llu inode=%llu offset=%llu", found_type, btrfs_root_id(root), wc->log_key.objectid, wc->log_key.offset); return -EUCLEAN; } inode = btrfs_iget_logging(wc->log_key.objectid, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); btrfs_abort_log_replay(wc, ret, "failed to get inode %llu for root %llu", wc->log_key.objectid, btrfs_root_id(root)); return ret; } /* * first check to see if we already have this extent in the * file. This must be done before the btrfs_drop_extents run * so we don't try to drop this extent. */ ret = btrfs_lookup_file_extent(trans, root, wc->subvol_path, btrfs_ino(inode), start, 0); if (ret == 0 && (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC)) { struct extent_buffer *leaf = wc->subvol_path->nodes[0]; struct btrfs_file_extent_item existing; unsigned long ptr; ptr = btrfs_item_ptr_offset(leaf, wc->subvol_path->slots[0]); read_extent_buffer(leaf, &existing, ptr, sizeof(existing)); /* * we already have a pointer to this exact extent, * we don't have to do anything */ if (memcmp_extent_buffer(wc->log_leaf, &existing, (unsigned long)item, sizeof(existing)) == 0) { btrfs_release_path(wc->subvol_path); goto out; } } btrfs_release_path(wc->subvol_path); /* drop any overlapping extents */ drop_args.start = start; drop_args.end = extent_end; drop_args.drop_cache = true; drop_args.path = wc->subvol_path; ret = btrfs_drop_extents(trans, root, inode, &drop_args); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to drop extents for inode %llu range [%llu, %llu) root %llu", wc->log_key.objectid, start, extent_end, btrfs_root_id(root)); goto out; } if (found_type == BTRFS_FILE_EXTENT_INLINE) { /* inline extents are easy, we just overwrite them */ ret = overwrite_item(wc); if (ret) goto out; goto update_inode; } /* * If not an inline extent, it can only be a regular or prealloc one. * We have checked that above and returned -EUCLEAN if not. */ /* A hole and NO_HOLES feature enabled, nothing else to do. */ if (btrfs_file_extent_disk_bytenr(wc->log_leaf, item) == 0 && btrfs_fs_incompat(fs_info, NO_HOLES)) goto update_inode; ret = btrfs_insert_empty_item(trans, root, wc->subvol_path, &wc->log_key, sizeof(*item)); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to insert item with key (%llu %u %llu) root %llu", wc->log_key.objectid, wc->log_key.type, wc->log_key.offset, btrfs_root_id(root)); goto out; } dest_offset = btrfs_item_ptr_offset(wc->subvol_path->nodes[0], wc->subvol_path->slots[0]); copy_extent_buffer(wc->subvol_path->nodes[0], wc->log_leaf, dest_offset, (unsigned long)item, sizeof(*item)); /* * We have an explicit hole and NO_HOLES is not enabled. We have added * the hole file extent item to the subvolume tree, so we don't have * anything else to do other than update the file extent item range and * update the inode item. */ if (btrfs_file_extent_disk_bytenr(wc->log_leaf, item) == 0) { btrfs_release_path(wc->subvol_path); goto update_inode; } ins.objectid = btrfs_file_extent_disk_bytenr(wc->log_leaf, item); ins.type = BTRFS_EXTENT_ITEM_KEY; ins.offset = btrfs_file_extent_disk_num_bytes(wc->log_leaf, item); offset = wc->log_key.offset - btrfs_file_extent_offset(wc->log_leaf, item); /* * Manually record dirty extent, as here we did a shallow file extent * item copy and skip normal backref update, but modifying extent tree * all by ourselves. So need to manually record dirty extent for qgroup, * as the owner of the file extent changed from log tree (doesn't affect * qgroup) to fs/file tree (affects qgroup). */ ret = btrfs_qgroup_trace_extent(trans, ins.objectid, ins.offset); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to trace extent for bytenr %llu disk_num_bytes %llu inode %llu root %llu", ins.objectid, ins.offset, wc->log_key.objectid, btrfs_root_id(root)); goto out; } /* * Is this extent already allocated in the extent tree? * If so, just add a reference. */ ret = btrfs_lookup_data_extent(fs_info, ins.objectid, ins.offset); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to lookup data extent for bytenr %llu disk_num_bytes %llu inode %llu root %llu", ins.objectid, ins.offset, wc->log_key.objectid, btrfs_root_id(root)); goto out; } else if (ret == 0) { struct btrfs_ref ref = { .action = BTRFS_ADD_DELAYED_REF, .bytenr = ins.objectid, .num_bytes = ins.offset, .owning_root = btrfs_root_id(root), .ref_root = btrfs_root_id(root), }; btrfs_init_data_ref(&ref, wc->log_key.objectid, offset, 0, false); ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to increment data extent for bytenr %llu disk_num_bytes %llu inode %llu root %llu", ins.objectid, ins.offset, wc->log_key.objectid, btrfs_root_id(root)); goto out; } } else { /* Insert the extent pointer in the extent tree. */ ret = btrfs_alloc_logged_file_extent(trans, btrfs_root_id(root), wc->log_key.objectid, offset, &ins); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to allocate logged data extent for bytenr %llu disk_num_bytes %llu offset %llu inode %llu root %llu", ins.objectid, ins.offset, offset, wc->log_key.objectid, btrfs_root_id(root)); goto out; } } btrfs_release_path(wc->subvol_path); if (btrfs_file_extent_compression(wc->log_leaf, item)) { csum_start = ins.objectid; csum_end = csum_start + ins.offset; } else { csum_start = ins.objectid + btrfs_file_extent_offset(wc->log_leaf, item); csum_end = csum_start + btrfs_file_extent_num_bytes(wc->log_leaf, item); } ret = btrfs_lookup_csums_list(root->log_root, csum_start, csum_end - 1, &ordered_sums, false); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to lookups csums for range [%llu, %llu) inode %llu root %llu", csum_start, csum_end, wc->log_key.objectid, btrfs_root_id(root)); goto out; } ret = 0; /* * Now delete all existing cums in the csum root that cover our range. * We do this because we can have an extent that is completely * referenced by one file extent item and partially referenced by * another file extent item (like after using the clone or extent_same * ioctls). In this case if we end up doing the replay of the one that * partially references the extent first, and we do not do the csum * deletion below, we can get 2 csum items in the csum tree that overlap * each other. For example, imagine our log has the two following file * extent items: * * key (257 EXTENT_DATA 409600) * extent data disk byte 12845056 nr 102400 * extent data offset 20480 nr 20480 ram 102400 * * key (257 EXTENT_DATA 819200) * extent data disk byte 12845056 nr 102400 * extent data offset 0 nr 102400 ram 102400 * * Where the second one fully references the 100K extent that starts at * disk byte 12845056, and the log tree has a single csum item that * covers the entire range of the extent: * * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100 * * After the first file extent item is replayed, the csum tree gets the * following csum item: * * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20 * * Which covers the 20K sub-range starting at offset 20K of our extent. * Now when we replay the second file extent item, if we do not delete * existing csum items that cover any of its blocks, we end up getting * two csum items in our csum tree that overlap each other: * * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100 * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20 * * Which is a problem, because after this anyone trying to lookup for * the checksum of any block of our extent starting at an offset of 40K * or higher, will end up looking at the second csum item only, which * does not contain the checksum for any block starting at offset 40K or * higher of our extent. */ while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums; struct btrfs_root *csum_root; sums = list_first_entry(&ordered_sums, struct btrfs_ordered_sum, list); csum_root = btrfs_csum_root(fs_info, sums->logical); if (!ret) { ret = btrfs_del_csums(trans, csum_root, sums->logical, sums->len); if (ret) btrfs_abort_log_replay(wc, ret, "failed to delete csums for range [%llu, %llu) inode %llu root %llu", sums->logical, sums->logical + sums->len, wc->log_key.objectid, btrfs_root_id(root)); } if (!ret) { ret = btrfs_csum_file_blocks(trans, csum_root, sums); if (ret) btrfs_abort_log_replay(wc, ret, "failed to add csums for range [%llu, %llu) inode %llu root %llu", sums->logical, sums->logical + sums->len, wc->log_key.objectid, btrfs_root_id(root)); } list_del(&sums->list); kfree(sums); } if (ret) goto out; update_inode: ret = btrfs_inode_set_file_extent_range(inode, start, extent_end - start); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to set file extent range [%llu, %llu) inode %llu root %llu", start, extent_end, wc->log_key.objectid, btrfs_root_id(root)); goto out; } btrfs_update_inode_bytes(inode, nbytes, drop_args.bytes_found); ret = btrfs_update_inode(trans, inode); if (ret) btrfs_abort_log_replay(wc, ret, "failed to update inode %llu root %llu", wc->log_key.objectid, btrfs_root_id(root)); out: iput(&inode->vfs_inode); return ret; } static int unlink_inode_for_log_replay(struct walk_control *wc, struct btrfs_inode *dir, struct btrfs_inode *inode, const struct fscrypt_str *name) { struct btrfs_trans_handle *trans = wc->trans; int ret; ret = btrfs_unlink_inode(trans, dir, inode, name); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to unlink inode %llu parent dir %llu name %.*s root %llu", btrfs_ino(inode), btrfs_ino(dir), name->len, name->name, btrfs_root_id(inode->root)); return ret; } /* * Whenever we need to check if a name exists or not, we check the * fs/subvolume tree. So after an unlink we must run delayed items, so * that future checks for a name during log replay see that the name * does not exists anymore. */ ret = btrfs_run_delayed_items(trans); if (ret) btrfs_abort_log_replay(wc, ret, "failed to run delayed items current inode %llu parent dir %llu name %.*s root %llu", btrfs_ino(inode), btrfs_ino(dir), name->len, name->name, btrfs_root_id(inode->root)); return ret; } /* * when cleaning up conflicts between the directory names in the * subvolume, directory names in the log and directory names in the * inode back references, we may have to unlink inodes from directories. * * This is a helper function to do the unlink of a specific directory * item */ static noinline int drop_one_dir_item(struct walk_control *wc, struct btrfs_inode *dir, struct btrfs_dir_item *di) { struct btrfs_root *root = dir->root; struct btrfs_inode *inode; struct fscrypt_str name; struct extent_buffer *leaf = wc->subvol_path->nodes[0]; struct btrfs_key location; int ret; btrfs_dir_item_key_to_cpu(leaf, di, &location); ret = read_alloc_one_name(leaf, di + 1, btrfs_dir_name_len(leaf, di), &name); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to allocate name for dir %llu root %llu", btrfs_ino(dir), btrfs_root_id(root)); return ret; } btrfs_release_path(wc->subvol_path); inode = btrfs_iget_logging(location.objectid, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); btrfs_abort_log_replay(wc, ret, "failed to open inode %llu parent dir %llu name %.*s root %llu", location.objectid, btrfs_ino(dir), name.len, name.name, btrfs_root_id(root)); inode = NULL; goto out; } ret = link_to_fixup_dir(wc, location.objectid); if (ret) goto out; ret = unlink_inode_for_log_replay(wc, dir, inode, &name); out: kfree(name.name); if (inode) iput(&inode->vfs_inode); return ret; } /* * See if a given name and sequence number found in an inode back reference are * already in a directory and correctly point to this inode. * * Returns: < 0 on error, 0 if the directory entry does not exists and 1 if it * exists. */ static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 objectid, u64 index, struct fscrypt_str *name) { struct btrfs_dir_item *di; struct btrfs_key location; int ret = 0; di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid != objectid) goto out; } else { goto out; } btrfs_release_path(path); di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid == objectid) ret = 1; } out: btrfs_release_path(path); return ret; } /* * helper function to check a log tree for a named back reference in * an inode. This is used to decide if a back reference that is * found in the subvolume conflicts with what we find in the log. * * inode backreferences may have multiple refs in a single item, * during replay we process one reference at a time, and we don't * want to delete valid links to a file from the subvolume if that * link is also in the log. */ static noinline int backref_in_log(struct btrfs_root *log, struct btrfs_key *key, u64 ref_objectid, const struct fscrypt_str *name) { BTRFS_PATH_AUTO_FREE(path); int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(NULL, log, key, path, 0, 0); if (ret < 0) return ret; if (ret == 1) return 0; if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], ref_objectid, name); else ret = !!btrfs_find_name_in_backref(path->nodes[0], path->slots[0], name); return ret; } static int unlink_refs_not_in_log(struct walk_control *wc, struct btrfs_key *search_key, struct btrfs_inode *dir, struct btrfs_inode *inode) { struct extent_buffer *leaf = wc->subvol_path->nodes[0]; unsigned long ptr; unsigned long ptr_end; /* * Check all the names in this back reference to see if they are in the * log. If so, we allow them to stay otherwise they must be unlinked as * a conflict. */ ptr = btrfs_item_ptr_offset(leaf, wc->subvol_path->slots[0]); ptr_end = ptr + btrfs_item_size(leaf, wc->subvol_path->slots[0]); while (ptr < ptr_end) { struct fscrypt_str victim_name; struct btrfs_inode_ref *victim_ref; int ret; victim_ref = (struct btrfs_inode_ref *)ptr; ret = read_alloc_one_name(leaf, (victim_ref + 1), btrfs_inode_ref_name_len(leaf, victim_ref), &victim_name); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to allocate name for inode %llu parent dir %llu root %llu", btrfs_ino(inode), btrfs_ino(dir), btrfs_root_id(inode->root)); return ret; } ret = backref_in_log(wc->log, search_key, btrfs_ino(dir), &victim_name); if (ret) { if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to check if backref is in log tree for inode %llu parent dir %llu name %.*s root %llu", btrfs_ino(inode), btrfs_ino(dir), victim_name.len, victim_name.name, btrfs_root_id(inode->root)); kfree(victim_name.name); return ret; } kfree(victim_name.name); ptr = (unsigned long)(victim_ref + 1) + victim_name.len; continue; } inc_nlink(&inode->vfs_inode); btrfs_release_path(wc->subvol_path); ret = unlink_inode_for_log_replay(wc, dir, inode, &victim_name); kfree(victim_name.name); if (ret) return ret; return -EAGAIN; } return 0; } static int unlink_extrefs_not_in_log(struct walk_control *wc, struct btrfs_key *search_key, struct btrfs_inode *dir, struct btrfs_inode *inode) { struct extent_buffer *leaf = wc->subvol_path->nodes[0]; const unsigned long base = btrfs_item_ptr_offset(leaf, wc->subvol_path->slots[0]); const u32 item_size = btrfs_item_size(leaf, wc->subvol_path->slots[0]); u32 cur_offset = 0; while (cur_offset < item_size) { struct btrfs_root *log_root = wc->log; struct btrfs_inode_extref *extref; struct fscrypt_str victim_name; int ret; extref = (struct btrfs_inode_extref *)(base + cur_offset); victim_name.len = btrfs_inode_extref_name_len(leaf, extref); if (btrfs_inode_extref_parent(leaf, extref) != btrfs_ino(dir)) goto next; ret = read_alloc_one_name(leaf, &extref->name, victim_name.len, &victim_name); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to allocate name for inode %llu parent dir %llu root %llu", btrfs_ino(inode), btrfs_ino(dir), btrfs_root_id(inode->root)); return ret; } search_key->objectid = btrfs_ino(inode); search_key->type = BTRFS_INODE_EXTREF_KEY; search_key->offset = btrfs_extref_hash(btrfs_ino(dir), victim_name.name, victim_name.len); ret = backref_in_log(log_root, search_key, btrfs_ino(dir), &victim_name); if (ret) { if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to check if backref is in log tree for inode %llu parent dir %llu name %.*s root %llu", btrfs_ino(inode), btrfs_ino(dir), victim_name.len, victim_name.name, btrfs_root_id(inode->root)); kfree(victim_name.name); return ret; } kfree(victim_name.name); next: cur_offset += victim_name.len + sizeof(*extref); continue; } inc_nlink(&inode->vfs_inode); btrfs_release_path(wc->subvol_path); ret = unlink_inode_for_log_replay(wc, dir, inode, &victim_name); kfree(victim_name.name); if (ret) return ret; return -EAGAIN; } return 0; } static inline int __add_inode_ref(struct walk_control *wc, struct btrfs_inode *dir, struct btrfs_inode *inode, u64 ref_index, struct fscrypt_str *name) { int ret; struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct btrfs_dir_item *di; struct btrfs_key search_key; struct btrfs_inode_extref *extref; again: /* Search old style refs */ search_key.objectid = btrfs_ino(inode); search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = btrfs_ino(dir); ret = btrfs_search_slot(NULL, root, &search_key, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to search subvolume tree for key (%llu %u %llu) root %llu", search_key.objectid, search_key.type, search_key.offset, btrfs_root_id(root)); return ret; } else if (ret == 0) { /* * Are we trying to overwrite a back ref for the root directory? * If so, we're done. */ if (search_key.objectid == search_key.offset) return 1; ret = unlink_refs_not_in_log(wc, &search_key, dir, inode); if (ret == -EAGAIN) goto again; else if (ret) return ret; } btrfs_release_path(wc->subvol_path); /* Same search but for extended refs */ extref = btrfs_lookup_inode_extref(root, wc->subvol_path, name, btrfs_ino(inode), btrfs_ino(dir)); if (IS_ERR(extref)) { return PTR_ERR(extref); } else if (extref) { ret = unlink_extrefs_not_in_log(wc, &search_key, dir, inode); if (ret == -EAGAIN) goto again; else if (ret) return ret; } btrfs_release_path(wc->subvol_path); /* look for a conflicting sequence number */ di = btrfs_lookup_dir_index_item(trans, root, wc->subvol_path, btrfs_ino(dir), ref_index, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); btrfs_abort_log_replay(wc, ret, "failed to lookup dir index item for dir %llu ref_index %llu name %.*s root %llu", btrfs_ino(dir), ref_index, name->len, name->name, btrfs_root_id(root)); return ret; } else if (di) { ret = drop_one_dir_item(wc, dir, di); if (ret) return ret; } btrfs_release_path(wc->subvol_path); /* look for a conflicting name */ di = btrfs_lookup_dir_item(trans, root, wc->subvol_path, btrfs_ino(dir), name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); btrfs_abort_log_replay(wc, ret, "failed to lookup dir item for dir %llu name %.*s root %llu", btrfs_ino(dir), name->len, name->name, btrfs_root_id(root)); return ret; } else if (di) { ret = drop_one_dir_item(wc, dir, di); if (ret) return ret; } btrfs_release_path(wc->subvol_path); return 0; } static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, struct fscrypt_str *name, u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; int ret; extref = (struct btrfs_inode_extref *)ref_ptr; ret = read_alloc_one_name(eb, &extref->name, btrfs_inode_extref_name_len(eb, extref), name); if (ret) return ret; if (index) *index = btrfs_inode_extref_index(eb, extref); if (parent_objectid) *parent_objectid = btrfs_inode_extref_parent(eb, extref); return 0; } static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, struct fscrypt_str *name, u64 *index) { struct btrfs_inode_ref *ref; int ret; ref = (struct btrfs_inode_ref *)ref_ptr; ret = read_alloc_one_name(eb, ref + 1, btrfs_inode_ref_name_len(eb, ref), name); if (ret) return ret; if (index) *index = btrfs_inode_ref_index(eb, ref); return 0; } /* * Take an inode reference item from the log tree and iterate all names from the * inode reference item in the subvolume tree with the same key (if it exists). * For any name that is not in the inode reference item from the log tree, do a * proper unlink of that name (that is, remove its entry from the inode * reference item and both dir index keys). */ static int unlink_old_inode_refs(struct walk_control *wc, struct btrfs_inode *inode) { struct btrfs_root *root = wc->root; int ret; unsigned long ref_ptr; unsigned long ref_end; struct extent_buffer *eb; again: btrfs_release_path(wc->subvol_path); ret = btrfs_search_slot(NULL, root, &wc->log_key, wc->subvol_path, 0, 0); if (ret > 0) { ret = 0; goto out; } if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to search subvolume tree for key (%llu %u %llu) root %llu", wc->log_key.objectid, wc->log_key.type, wc->log_key.offset, btrfs_root_id(root)); goto out; } eb = wc->subvol_path->nodes[0]; ref_ptr = btrfs_item_ptr_offset(eb, wc->subvol_path->slots[0]); ref_end = ref_ptr + btrfs_item_size(eb, wc->subvol_path->slots[0]); while (ref_ptr < ref_end) { struct fscrypt_str name; u64 parent_id; if (wc->log_key.type == BTRFS_INODE_EXTREF_KEY) { ret = extref_get_fields(eb, ref_ptr, &name, NULL, &parent_id); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to get extref details for inode %llu root %llu", btrfs_ino(inode), btrfs_root_id(root)); goto out; } } else { parent_id = wc->log_key.offset; ret = ref_get_fields(eb, ref_ptr, &name, NULL); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to get ref details for inode %llu parent_id %llu root %llu", btrfs_ino(inode), parent_id, btrfs_root_id(root)); goto out; } } if (wc->log_key.type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(wc->log_leaf, wc->log_slot, parent_id, &name); else ret = !!btrfs_find_name_in_backref(wc->log_leaf, wc->log_slot, &name); if (!ret) { struct btrfs_inode *dir; btrfs_release_path(wc->subvol_path); dir = btrfs_iget_logging(parent_id, root); if (IS_ERR(dir)) { ret = PTR_ERR(dir); kfree(name.name); btrfs_abort_log_replay(wc, ret, "failed to lookup dir inode %llu root %llu", parent_id, btrfs_root_id(root)); goto out; } ret = unlink_inode_for_log_replay(wc, dir, inode, &name); kfree(name.name); iput(&dir->vfs_inode); if (ret) goto out; goto again; } kfree(name.name); ref_ptr += name.len; if (wc->log_key.type == BTRFS_INODE_EXTREF_KEY) ref_ptr += sizeof(struct btrfs_inode_extref); else ref_ptr += sizeof(struct btrfs_inode_ref); } ret = 0; out: btrfs_release_path(wc->subvol_path); return ret; } /* * Replay one inode back reference item found in the log tree. * Path is for temporary use by this function (it should be released on return). */ static noinline int add_inode_ref(struct walk_control *wc) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct btrfs_inode *dir = NULL; struct btrfs_inode *inode = NULL; unsigned long ref_ptr; unsigned long ref_end; struct fscrypt_str name = { 0 }; int ret; const bool is_extref_item = (wc->log_key.type == BTRFS_INODE_EXTREF_KEY); u64 parent_objectid; u64 inode_objectid; u64 ref_index = 0; int ref_struct_size; ref_ptr = btrfs_item_ptr_offset(wc->log_leaf, wc->log_slot); ref_end = ref_ptr + btrfs_item_size(wc->log_leaf, wc->log_slot); if (is_extref_item) { struct btrfs_inode_extref *r; ref_struct_size = sizeof(struct btrfs_inode_extref); r = (struct btrfs_inode_extref *)ref_ptr; parent_objectid = btrfs_inode_extref_parent(wc->log_leaf, r); } else { ref_struct_size = sizeof(struct btrfs_inode_ref); parent_objectid = wc->log_key.offset; } inode_objectid = wc->log_key.objectid; /* * it is possible that we didn't log all the parent directories * for a given inode. If we don't find the dir, just don't * copy the back ref in. The link count fixup code will take * care of the rest */ dir = btrfs_iget_logging(parent_objectid, root); if (IS_ERR(dir)) { ret = PTR_ERR(dir); if (ret == -ENOENT) ret = 0; else btrfs_abort_log_replay(wc, ret, "failed to lookup dir inode %llu root %llu", parent_objectid, btrfs_root_id(root)); dir = NULL; goto out; } inode = btrfs_iget_logging(inode_objectid, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); btrfs_abort_log_replay(wc, ret, "failed to lookup inode %llu root %llu", inode_objectid, btrfs_root_id(root)); inode = NULL; goto out; } while (ref_ptr < ref_end) { if (is_extref_item) { ret = extref_get_fields(wc->log_leaf, ref_ptr, &name, &ref_index, &parent_objectid); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to get extref details for inode %llu root %llu", btrfs_ino(inode), btrfs_root_id(root)); goto out; } /* * parent object can change from one array * item to another. */ if (!dir) { dir = btrfs_iget_logging(parent_objectid, root); if (IS_ERR(dir)) { ret = PTR_ERR(dir); dir = NULL; /* * A new parent dir may have not been * logged and not exist in the subvolume * tree, see the comment above before * the loop when getting the first * parent dir. */ if (ret == -ENOENT) { /* * The next extref may refer to * another parent dir that * exists, so continue. */ ret = 0; goto next; } else { btrfs_abort_log_replay(wc, ret, "failed to lookup dir inode %llu root %llu", parent_objectid, btrfs_root_id(root)); } goto out; } } } else { ret = ref_get_fields(wc->log_leaf, ref_ptr, &name, &ref_index); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to get ref details for inode %llu parent_objectid %llu root %llu", btrfs_ino(inode), parent_objectid, btrfs_root_id(root)); goto out; } } ret = inode_in_dir(root, wc->subvol_path, btrfs_ino(dir), btrfs_ino(inode), ref_index, &name); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to check if inode %llu is in dir %llu ref_index %llu name %.*s root %llu", btrfs_ino(inode), btrfs_ino(dir), ref_index, name.len, name.name, btrfs_root_id(root)); goto out; } else if (ret == 0) { /* * look for a conflicting back reference in the * metadata. if we find one we have to unlink that name * of the file before we add our new link. Later on, we * overwrite any existing back reference, and we don't * want to create dangling pointers in the directory. */ ret = __add_inode_ref(wc, dir, inode, ref_index, &name); if (ret) { if (ret == 1) ret = 0; goto out; } /* insert our name */ ret = btrfs_add_link(trans, dir, inode, &name, 0, ref_index); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to add link for inode %llu in dir %llu ref_index %llu name %.*s root %llu", btrfs_ino(inode), btrfs_ino(dir), ref_index, name.len, name.name, btrfs_root_id(root)); goto out; } ret = btrfs_update_inode(trans, inode); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to update inode %llu root %llu", btrfs_ino(inode), btrfs_root_id(root)); goto out; } } /* Else, ret == 1, we already have a perfect match, we're done. */ next: ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + name.len; kfree(name.name); name.name = NULL; if (is_extref_item && dir) { iput(&dir->vfs_inode); dir = NULL; } } /* * Before we overwrite the inode reference item in the subvolume tree * with the item from the log tree, we must unlink all names from the * parent directory that are in the subvolume's tree inode reference * item, otherwise we end up with an inconsistent subvolume tree where * dir index entries exist for a name but there is no inode reference * item with the same name. */ ret = unlink_old_inode_refs(wc, inode); if (ret) goto out; /* finally write the back reference in the inode */ ret = overwrite_item(wc); out: btrfs_release_path(wc->subvol_path); kfree(name.name); if (dir) iput(&dir->vfs_inode); if (inode) iput(&inode->vfs_inode); return ret; } static int count_inode_extrefs(struct btrfs_inode *inode, struct btrfs_path *path) { int ret = 0; int name_len; unsigned int nlink = 0; u32 item_size; u32 cur_offset = 0; u64 inode_objectid = btrfs_ino(inode); u64 offset = 0; unsigned long ptr; struct btrfs_inode_extref *extref; struct extent_buffer *leaf; while (1) { ret = btrfs_find_one_extref(inode->root, inode_objectid, offset, path, &extref, &offset); if (ret) break; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); cur_offset = 0; while (cur_offset < item_size) { extref = (struct btrfs_inode_extref *) (ptr + cur_offset); name_len = btrfs_inode_extref_name_len(leaf, extref); nlink++; cur_offset += name_len + sizeof(*extref); } offset++; btrfs_release_path(path); } btrfs_release_path(path); if (ret < 0 && ret != -ENOENT) return ret; return nlink; } static int count_inode_refs(struct btrfs_inode *inode, struct btrfs_path *path) { int ret; struct btrfs_key key; unsigned int nlink = 0; unsigned long ptr; unsigned long ptr_end; int name_len; u64 ino = btrfs_ino(inode); key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0); if (ret < 0) break; if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } process_slot: btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_INODE_REF_KEY) break; ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); ptr_end = ptr + btrfs_item_size(path->nodes[0], path->slots[0]); while (ptr < ptr_end) { struct btrfs_inode_ref *ref; ref = (struct btrfs_inode_ref *)ptr; name_len = btrfs_inode_ref_name_len(path->nodes[0], ref); ptr = (unsigned long)(ref + 1) + name_len; nlink++; } if (key.offset == 0) break; if (path->slots[0] > 0) { path->slots[0]--; goto process_slot; } key.offset--; btrfs_release_path(path); } btrfs_release_path(path); return nlink; } /* * There are a few corners where the link count of the file can't * be properly maintained during replay. So, instead of adding * lots of complexity to the log code, we just scan the backrefs * for any file that has been through replay. * * The scan will update the link count on the inode to reflect the * number of back refs found. If it goes down to zero, the iput * will free the inode. */ static noinline int fixup_inode_link_count(struct walk_control *wc, struct btrfs_inode *inode) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = inode->root; int ret; u64 nlink = 0; const u64 ino = btrfs_ino(inode); ret = count_inode_refs(inode, wc->subvol_path); if (ret < 0) goto out; nlink = ret; ret = count_inode_extrefs(inode, wc->subvol_path); if (ret < 0) goto out; nlink += ret; ret = 0; if (nlink != inode->vfs_inode.i_nlink) { set_nlink(&inode->vfs_inode, nlink); ret = btrfs_update_inode(trans, inode); if (ret) goto out; } if (S_ISDIR(inode->vfs_inode.i_mode)) inode->index_cnt = (u64)-1; if (inode->vfs_inode.i_nlink == 0) { if (S_ISDIR(inode->vfs_inode.i_mode)) { ret = replay_dir_deletes(wc, ino, true); if (ret) goto out; } ret = btrfs_insert_orphan_item(trans, root, ino); if (ret == -EEXIST) ret = 0; } out: btrfs_release_path(wc->subvol_path); return ret; } static noinline int fixup_inode_link_counts(struct walk_control *wc) { int ret; struct btrfs_key key; key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = (u64)-1; while (1) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct btrfs_inode *inode; ret = btrfs_search_slot(trans, root, &key, wc->subvol_path, -1, 1); if (ret < 0) break; if (ret == 1) { ret = 0; if (wc->subvol_path->slots[0] == 0) break; wc->subvol_path->slots[0]--; } btrfs_item_key_to_cpu(wc->subvol_path->nodes[0], &key, wc->subvol_path->slots[0]); if (key.objectid != BTRFS_TREE_LOG_FIXUP_OBJECTID || key.type != BTRFS_ORPHAN_ITEM_KEY) break; ret = btrfs_del_item(trans, root, wc->subvol_path); if (ret) break; btrfs_release_path(wc->subvol_path); inode = btrfs_iget_logging(key.offset, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); break; } ret = fixup_inode_link_count(wc, inode); iput(&inode->vfs_inode); if (ret) break; /* * fixup on a directory may create new entries, * make sure we always look for the highest possible * offset */ key.offset = (u64)-1; } btrfs_release_path(wc->subvol_path); return ret; } /* * record a given inode in the fixup dir so we can check its link * count when replay is done. The link count is incremented here * so the inode won't go away until we check it */ static noinline int link_to_fixup_dir(struct walk_control *wc, u64 objectid) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct btrfs_key key; int ret = 0; struct btrfs_inode *inode; struct inode *vfs_inode; inode = btrfs_iget_logging(objectid, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); btrfs_abort_log_replay(wc, ret, "failed to lookup inode %llu root %llu", objectid, btrfs_root_id(root)); return ret; } vfs_inode = &inode->vfs_inode; key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = objectid; ret = btrfs_insert_empty_item(trans, root, wc->subvol_path, &key, 0); btrfs_release_path(wc->subvol_path); if (ret == 0) { if (!vfs_inode->i_nlink) set_nlink(vfs_inode, 1); else inc_nlink(vfs_inode); ret = btrfs_update_inode(trans, inode); if (ret) btrfs_abort_log_replay(wc, ret, "failed to update inode %llu root %llu", objectid, btrfs_root_id(root)); } else if (ret == -EEXIST) { ret = 0; } else { btrfs_abort_log_replay(wc, ret, "failed to insert fixup item for inode %llu root %llu", objectid, btrfs_root_id(root)); } iput(vfs_inode); return ret; } /* * when replaying the log for a directory, we only insert names * for inodes that actually exist. This means an fsync on a directory * does not implicitly fsync all the new files in it */ static noinline int insert_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 dirid, u64 index, const struct fscrypt_str *name, struct btrfs_key *location) { struct btrfs_inode *inode; struct btrfs_inode *dir; int ret; inode = btrfs_iget_logging(location->objectid, root); if (IS_ERR(inode)) return PTR_ERR(inode); dir = btrfs_iget_logging(dirid, root); if (IS_ERR(dir)) { iput(&inode->vfs_inode); return PTR_ERR(dir); } ret = btrfs_add_link(trans, dir, inode, name, 1, index); /* FIXME, put inode into FIXUP list */ iput(&inode->vfs_inode); iput(&dir->vfs_inode); return ret; } static int delete_conflicting_dir_entry(struct walk_control *wc, struct btrfs_inode *dir, struct btrfs_dir_item *dst_di, const struct btrfs_key *log_key, u8 log_flags, bool exists) { struct btrfs_key found_key; btrfs_dir_item_key_to_cpu(wc->subvol_path->nodes[0], dst_di, &found_key); /* The existing dentry points to the same inode, don't delete it. */ if (found_key.objectid == log_key->objectid && found_key.type == log_key->type && found_key.offset == log_key->offset && btrfs_dir_flags(wc->subvol_path->nodes[0], dst_di) == log_flags) return 1; /* * Don't drop the conflicting directory entry if the inode for the new * entry doesn't exist. */ if (!exists) return 0; return drop_one_dir_item(wc, dir, dst_di); } /* * take a single entry in a log directory item and replay it into * the subvolume. * * if a conflicting item exists in the subdirectory already, * the inode it points to is unlinked and put into the link count * fix up tree. * * If a name from the log points to a file or directory that does * not exist in the FS, it is skipped. fsyncs on directories * do not force down inodes inside that directory, just changes to the * names or unlinks in a directory. * * Returns < 0 on error, 0 if the name wasn't replayed (dentry points to a * non-existing inode) and 1 if the name was replayed. */ static noinline int replay_one_name(struct walk_control *wc, struct btrfs_dir_item *di) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct fscrypt_str name = { 0 }; struct btrfs_dir_item *dir_dst_di; struct btrfs_dir_item *index_dst_di; bool dir_dst_matches = false; bool index_dst_matches = false; struct btrfs_key log_key; struct btrfs_key search_key; struct btrfs_inode *dir; u8 log_flags; bool exists; int ret; bool update_size = true; bool name_added = false; dir = btrfs_iget_logging(wc->log_key.objectid, root); if (IS_ERR(dir)) { ret = PTR_ERR(dir); btrfs_abort_log_replay(wc, ret, "failed to lookup dir inode %llu root %llu", wc->log_key.objectid, btrfs_root_id(root)); return ret; } ret = read_alloc_one_name(wc->log_leaf, di + 1, btrfs_dir_name_len(wc->log_leaf, di), &name); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to allocate name for dir %llu root %llu", btrfs_ino(dir), btrfs_root_id(root)); goto out; } log_flags = btrfs_dir_flags(wc->log_leaf, di); btrfs_dir_item_key_to_cpu(wc->log_leaf, di, &log_key); ret = btrfs_lookup_inode(trans, root, wc->subvol_path, &log_key, 0); btrfs_release_path(wc->subvol_path); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to lookup inode %llu root %llu", log_key.objectid, btrfs_root_id(root)); goto out; } exists = (ret == 0); ret = 0; dir_dst_di = btrfs_lookup_dir_item(trans, root, wc->subvol_path, wc->log_key.objectid, &name, 1); if (IS_ERR(dir_dst_di)) { ret = PTR_ERR(dir_dst_di); btrfs_abort_log_replay(wc, ret, "failed to lookup dir item for dir %llu name %.*s root %llu", wc->log_key.objectid, name.len, name.name, btrfs_root_id(root)); goto out; } else if (dir_dst_di) { ret = delete_conflicting_dir_entry(wc, dir, dir_dst_di, &log_key, log_flags, exists); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to delete conflicting entry for dir %llu name %.*s root %llu", btrfs_ino(dir), name.len, name.name, btrfs_root_id(root)); goto out; } dir_dst_matches = (ret == 1); } btrfs_release_path(wc->subvol_path); index_dst_di = btrfs_lookup_dir_index_item(trans, root, wc->subvol_path, wc->log_key.objectid, wc->log_key.offset, &name, 1); if (IS_ERR(index_dst_di)) { ret = PTR_ERR(index_dst_di); btrfs_abort_log_replay(wc, ret, "failed to lookup dir index item for dir %llu name %.*s root %llu", wc->log_key.objectid, name.len, name.name, btrfs_root_id(root)); goto out; } else if (index_dst_di) { ret = delete_conflicting_dir_entry(wc, dir, index_dst_di, &log_key, log_flags, exists); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to delete conflicting entry for dir %llu name %.*s root %llu", btrfs_ino(dir), name.len, name.name, btrfs_root_id(root)); goto out; } index_dst_matches = (ret == 1); } btrfs_release_path(wc->subvol_path); if (dir_dst_matches && index_dst_matches) { ret = 0; update_size = false; goto out; } /* * Check if the inode reference exists in the log for the given name, * inode and parent inode */ search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = wc->log_key.objectid; ret = backref_in_log(root->log_root, &search_key, 0, &name); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to check if ref item is logged for inode %llu dir %llu name %.*s root %llu", search_key.objectid, btrfs_ino(dir), name.len, name.name, btrfs_root_id(root)); goto out; } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; goto out; } search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = btrfs_extref_hash(wc->log_key.objectid, name.name, name.len); ret = backref_in_log(root->log_root, &search_key, wc->log_key.objectid, &name); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to check if extref item is logged for inode %llu dir %llu name %.*s root %llu", search_key.objectid, btrfs_ino(dir), name.len, name.name, btrfs_root_id(root)); goto out; } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; goto out; } ret = insert_one_name(trans, root, wc->log_key.objectid, wc->log_key.offset, &name, &log_key); if (ret && ret != -ENOENT && ret != -EEXIST) { btrfs_abort_log_replay(wc, ret, "failed to insert name %.*s for inode %llu dir %llu root %llu", name.len, name.name, log_key.objectid, btrfs_ino(dir), btrfs_root_id(root)); goto out; } if (!ret) name_added = true; update_size = false; ret = 0; out: if (!ret && update_size) { btrfs_i_size_write(dir, dir->vfs_inode.i_size + name.len * 2); ret = btrfs_update_inode(trans, dir); if (ret) btrfs_abort_log_replay(wc, ret, "failed to update dir inode %llu root %llu", btrfs_ino(dir), btrfs_root_id(root)); } kfree(name.name); iput(&dir->vfs_inode); if (!ret && name_added) ret = 1; return ret; } /* Replay one dir item from a BTRFS_DIR_INDEX_KEY key. */ static noinline int replay_one_dir_item(struct walk_control *wc) { int ret; struct btrfs_dir_item *di; /* We only log dir index keys, which only contain a single dir item. */ ASSERT(wc->log_key.type == BTRFS_DIR_INDEX_KEY); di = btrfs_item_ptr(wc->log_leaf, wc->log_slot, struct btrfs_dir_item); ret = replay_one_name(wc, di); if (ret < 0) return ret; /* * If this entry refers to a non-directory (directories can not have a * link count > 1) and it was added in the transaction that was not * committed, make sure we fixup the link count of the inode the entry * points to. Otherwise something like the following would result in a * directory pointing to an inode with a wrong link that does not account * for this dir entry: * * mkdir testdir * touch testdir/foo * touch testdir/bar * sync * * ln testdir/bar testdir/bar_link * ln testdir/foo testdir/foo_link * xfs_io -c "fsync" testdir/bar * * <power failure> * * mount fs, log replay happens * * File foo would remain with a link count of 1 when it has two entries * pointing to it in the directory testdir. This would make it impossible * to ever delete the parent directory has it would result in stale * dentries that can never be deleted. */ if (ret == 1 && btrfs_dir_ftype(wc->log_leaf, di) != BTRFS_FT_DIR) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(wc->log_leaf, di, &di_key); ret = link_to_fixup_dir(wc, di_key.objectid); } return ret; } /* * directory replay has two parts. There are the standard directory * items in the log copied from the subvolume, and range items * created in the log while the subvolume was logged. * * The range items tell us which parts of the key space the log * is authoritative for. During replay, if a key in the subvolume * directory is in a logged range item, but not actually in the log * that means it was deleted from the directory before the fsync * and should be removed. */ static noinline int find_dir_range(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 *start_ret, u64 *end_ret) { struct btrfs_key key; u64 found_end; struct btrfs_dir_log_item *item; int ret; int nritems; if (*start_ret == (u64)-1) return 1; key.objectid = dirid; key.type = BTRFS_DIR_LOG_INDEX_KEY; key.offset = *start_ret; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; if (ret > 0) { if (path->slots[0] == 0) goto out; path->slots[0]--; } if (ret != 0) btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto next; } item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); found_end = btrfs_dir_log_end(path->nodes[0], item); if (*start_ret >= key.offset && *start_ret <= found_end) { ret = 0; *start_ret = key.offset; *end_ret = found_end; goto out; } ret = 1; next: /* check the next slot in the tree to see if it is a valid item */ nritems = btrfs_header_nritems(path->nodes[0]); path->slots[0]++; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) goto out; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto out; } item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); found_end = btrfs_dir_log_end(path->nodes[0], item); *start_ret = key.offset; *end_ret = found_end; ret = 0; out: btrfs_release_path(path); return ret; } /* * this looks for a given directory item in the log. If the directory * item is not in the log, the item is removed and the inode it points * to is unlinked */ static noinline int check_item_in_log(struct walk_control *wc, struct btrfs_path *log_path, struct btrfs_inode *dir, struct btrfs_key *dir_key, bool force_remove) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = dir->root; int ret; struct extent_buffer *eb; int slot; struct btrfs_dir_item *di; struct fscrypt_str name = { 0 }; struct btrfs_inode *inode = NULL; struct btrfs_key location; /* * Currently we only log dir index keys. Even if we replay a log created * by an older kernel that logged both dir index and dir item keys, all * we need to do is process the dir index keys, we (and our caller) can * safely ignore dir item keys (key type BTRFS_DIR_ITEM_KEY). */ ASSERT(dir_key->type == BTRFS_DIR_INDEX_KEY); eb = wc->subvol_path->nodes[0]; slot = wc->subvol_path->slots[0]; di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to allocate name for dir %llu index %llu root %llu", btrfs_ino(dir), dir_key->offset, btrfs_root_id(root)); goto out; } if (!force_remove) { struct btrfs_dir_item *log_di; log_di = btrfs_lookup_dir_index_item(trans, wc->log, log_path, dir_key->objectid, dir_key->offset, &name, 0); if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); btrfs_abort_log_replay(wc, ret, "failed to lookup dir index item for dir %llu index %llu name %.*s root %llu", btrfs_ino(dir), dir_key->offset, name.len, name.name, btrfs_root_id(root)); goto out; } else if (log_di) { /* The dentry exists in the log, we have nothing to do. */ ret = 0; goto out; } } btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(wc->subvol_path); btrfs_release_path(log_path); inode = btrfs_iget_logging(location.objectid, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); inode = NULL; btrfs_abort_log_replay(wc, ret, "failed to lookup inode %llu root %llu", location.objectid, btrfs_root_id(root)); goto out; } ret = link_to_fixup_dir(wc, location.objectid); if (ret) goto out; inc_nlink(&inode->vfs_inode); ret = unlink_inode_for_log_replay(wc, dir, inode, &name); /* * Unlike dir item keys, dir index keys can only have one name (entry) in * them, as there are no key collisions since each key has a unique offset * (an index number), so we're done. */ out: btrfs_release_path(wc->subvol_path); btrfs_release_path(log_path); kfree(name.name); if (inode) iput(&inode->vfs_inode); return ret; } static int replay_xattr_deletes(struct walk_control *wc) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_root *root = wc->root; struct btrfs_root *log = wc->log; struct btrfs_key search_key; BTRFS_PATH_AUTO_FREE(log_path); const u64 ino = wc->log_key.objectid; int nritems; int ret; log_path = btrfs_alloc_path(); if (!log_path) { btrfs_abort_log_replay(wc, -ENOMEM, "failed to allocate path"); return -ENOMEM; } search_key.objectid = ino; search_key.type = BTRFS_XATTR_ITEM_KEY; search_key.offset = 0; again: ret = btrfs_search_slot(NULL, root, &search_key, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to search xattrs for inode %llu root %llu", ino, btrfs_root_id(root)); goto out; } process_leaf: nritems = btrfs_header_nritems(wc->subvol_path->nodes[0]); for (int i = wc->subvol_path->slots[0]; i < nritems; i++) { struct btrfs_key key; struct btrfs_dir_item *di; struct btrfs_dir_item *log_di; u32 total_size; u32 cur; btrfs_item_key_to_cpu(wc->subvol_path->nodes[0], &key, i); if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) { ret = 0; goto out; } di = btrfs_item_ptr(wc->subvol_path->nodes[0], i, struct btrfs_dir_item); total_size = btrfs_item_size(wc->subvol_path->nodes[0], i); cur = 0; while (cur < total_size) { u16 name_len = btrfs_dir_name_len(wc->subvol_path->nodes[0], di); u16 data_len = btrfs_dir_data_len(wc->subvol_path->nodes[0], di); u32 this_len = sizeof(*di) + name_len + data_len; char *name; name = kmalloc(name_len, GFP_NOFS); if (!name) { ret = -ENOMEM; btrfs_abort_log_replay(wc, ret, "failed to allocate memory for name of length %u", name_len); goto out; } read_extent_buffer(wc->subvol_path->nodes[0], name, (unsigned long)(di + 1), name_len); log_di = btrfs_lookup_xattr(NULL, log, log_path, ino, name, name_len, 0); btrfs_release_path(log_path); if (!log_di) { /* Doesn't exist in log tree, so delete it. */ btrfs_release_path(wc->subvol_path); di = btrfs_lookup_xattr(trans, root, wc->subvol_path, ino, name, name_len, -1); if (IS_ERR(di)) { ret = PTR_ERR(di); btrfs_abort_log_replay(wc, ret, "failed to lookup xattr with name %.*s for inode %llu root %llu", name_len, name, ino, btrfs_root_id(root)); kfree(name); goto out; } ASSERT(di); ret = btrfs_delete_one_dir_name(trans, root, wc->subvol_path, di); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to delete xattr with name %.*s for inode %llu root %llu", name_len, name, ino, btrfs_root_id(root)); kfree(name); goto out; } btrfs_release_path(wc->subvol_path); kfree(name); search_key = key; goto again; } if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); btrfs_abort_log_replay(wc, ret, "failed to lookup xattr in log tree with name %.*s for inode %llu root %llu", name_len, name, ino, btrfs_root_id(root)); kfree(name); goto out; } kfree(name); cur += this_len; di = (struct btrfs_dir_item *)((char *)di + this_len); } } ret = btrfs_next_leaf(root, wc->subvol_path); if (ret > 0) ret = 0; else if (ret == 0) goto process_leaf; else btrfs_abort_log_replay(wc, ret, "failed to get next leaf in subvolume root %llu", btrfs_root_id(root)); out: btrfs_release_path(wc->subvol_path); return ret; } /* * deletion replay happens before we copy any new directory items * out of the log or out of backreferences from inodes. It * scans the log to find ranges of keys that log is authoritative for, * and then scans the directory to find items in those ranges that are * not present in the log. * * Anything we don't find in the log is unlinked and removed from the * directory. */ static noinline int replay_dir_deletes(struct walk_control *wc, u64 dirid, bool del_all) { struct btrfs_root *root = wc->root; struct btrfs_root *log = (del_all ? NULL : wc->log); u64 range_start; u64 range_end; int ret = 0; struct btrfs_key dir_key; struct btrfs_key found_key; struct btrfs_path *log_path; struct btrfs_inode *dir; dir_key.objectid = dirid; dir_key.type = BTRFS_DIR_INDEX_KEY; log_path = btrfs_alloc_path(); if (!log_path) { btrfs_abort_log_replay(wc, -ENOMEM, "failed to allocate path"); return -ENOMEM; } dir = btrfs_iget_logging(dirid, root); /* * It isn't an error if the inode isn't there, that can happen because * we replay the deletes before we copy in the inode item from the log. */ if (IS_ERR(dir)) { btrfs_free_path(log_path); ret = PTR_ERR(dir); if (ret == -ENOENT) ret = 0; else btrfs_abort_log_replay(wc, ret, "failed to lookup dir inode %llu root %llu", dirid, btrfs_root_id(root)); return ret; } range_start = 0; range_end = 0; while (1) { if (del_all) range_end = (u64)-1; else { ret = find_dir_range(log, wc->subvol_path, dirid, &range_start, &range_end); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to find range for dir %llu in log tree root %llu", dirid, btrfs_root_id(root)); goto out; } else if (ret > 0) { break; } } dir_key.offset = range_start; while (1) { int nritems; ret = btrfs_search_slot(NULL, root, &dir_key, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to search root %llu for key (%llu %u %llu)", btrfs_root_id(root), dir_key.objectid, dir_key.type, dir_key.offset); goto out; } nritems = btrfs_header_nritems(wc->subvol_path->nodes[0]); if (wc->subvol_path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, wc->subvol_path); if (ret == 1) { break; } else if (ret < 0) { btrfs_abort_log_replay(wc, ret, "failed to get next leaf in subvolume root %llu", btrfs_root_id(root)); goto out; } } btrfs_item_key_to_cpu(wc->subvol_path->nodes[0], &found_key, wc->subvol_path->slots[0]); if (found_key.objectid != dirid || found_key.type != dir_key.type) { ret = 0; goto out; } if (found_key.offset > range_end) break; ret = check_item_in_log(wc, log_path, dir, &found_key, del_all); if (ret) goto out; if (found_key.offset == (u64)-1) break; dir_key.offset = found_key.offset + 1; } btrfs_release_path(wc->subvol_path); if (range_end == (u64)-1) break; range_start = range_end + 1; } ret = 0; out: btrfs_release_path(wc->subvol_path); btrfs_free_path(log_path); iput(&dir->vfs_inode); return ret; } /* * the process_func used to replay items from the log tree. This * gets called in two different stages. The first stage just looks * for inodes and makes sure they are all copied into the subvolume. * * The second stage copies all the other item types from the log into * the subvolume. The two stage approach is slower, but gets rid of * lots of complexity around inodes referencing other inodes that exist * only in the log (references come from either directory items or inode * back refs). */ static int replay_one_buffer(struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { int nritems; struct btrfs_tree_parent_check check = { .transid = gen, .level = level }; struct btrfs_root *root = wc->root; struct btrfs_trans_handle *trans = wc->trans; int ret; if (level != 0) return 0; /* * Set to NULL since it was not yet read and in case we abort log replay * on error, we have no valid log tree leaf to dump. */ wc->log_leaf = NULL; ret = btrfs_read_extent_buffer(eb, &check); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to read log tree leaf %llu for root %llu", eb->start, btrfs_root_id(root)); return ret; } ASSERT(wc->subvol_path == NULL); wc->subvol_path = btrfs_alloc_path(); if (!wc->subvol_path) { btrfs_abort_log_replay(wc, -ENOMEM, "failed to allocate path"); return -ENOMEM; } wc->log_leaf = eb; nritems = btrfs_header_nritems(eb); for (wc->log_slot = 0; wc->log_slot < nritems; wc->log_slot++) { struct btrfs_inode_item *inode_item; btrfs_item_key_to_cpu(eb, &wc->log_key, wc->log_slot); if (wc->log_key.type == BTRFS_INODE_ITEM_KEY) { inode_item = btrfs_item_ptr(eb, wc->log_slot, struct btrfs_inode_item); /* * An inode with no links is either: * * 1) A tmpfile (O_TMPFILE) that got fsync'ed and never * got linked before the fsync, skip it, as replaying * it is pointless since it would be deleted later. * We skip logging tmpfiles, but it's always possible * we are replaying a log created with a kernel that * used to log tmpfiles; * * 2) A non-tmpfile which got its last link deleted * while holding an open fd on it and later got * fsynced through that fd. We always log the * parent inodes when inode->last_unlink_trans is * set to the current transaction, so ignore all the * inode items for this inode. We will delete the * inode when processing the parent directory with * replay_dir_deletes(). */ if (btrfs_inode_nlink(eb, inode_item) == 0) { wc->ignore_cur_inode = true; continue; } else { wc->ignore_cur_inode = false; } } /* Inode keys are done during the first stage. */ if (wc->log_key.type == BTRFS_INODE_ITEM_KEY && wc->stage == LOG_WALK_REPLAY_INODES) { u32 mode; ret = replay_xattr_deletes(wc); if (ret) break; mode = btrfs_inode_mode(eb, inode_item); if (S_ISDIR(mode)) { ret = replay_dir_deletes(wc, wc->log_key.objectid, false); if (ret) break; } ret = overwrite_item(wc); if (ret) break; /* * Before replaying extents, truncate the inode to its * size. We need to do it now and not after log replay * because before an fsync we can have prealloc extents * added beyond the inode's i_size. If we did it after, * through orphan cleanup for example, we would drop * those prealloc extents just after replaying them. */ if (S_ISREG(mode)) { struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_inode *inode; u64 from; inode = btrfs_iget_logging(wc->log_key.objectid, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); btrfs_abort_log_replay(wc, ret, "failed to lookup inode %llu root %llu", wc->log_key.objectid, btrfs_root_id(root)); break; } from = ALIGN(i_size_read(&inode->vfs_inode), root->fs_info->sectorsize); drop_args.start = from; drop_args.end = (u64)-1; drop_args.drop_cache = true; drop_args.path = wc->subvol_path; ret = btrfs_drop_extents(trans, root, inode, &drop_args); if (ret) { btrfs_abort_log_replay(wc, ret, "failed to drop extents for inode %llu root %llu offset %llu", btrfs_ino(inode), btrfs_root_id(root), from); } else { inode_sub_bytes(&inode->vfs_inode, drop_args.bytes_found); /* Update the inode's nbytes. */ ret = btrfs_update_inode(trans, inode); if (ret) btrfs_abort_log_replay(wc, ret, "failed to update inode %llu root %llu", btrfs_ino(inode), btrfs_root_id(root)); } iput(&inode->vfs_inode); if (ret) break; } ret = link_to_fixup_dir(wc, wc->log_key.objectid); if (ret) break; } if (wc->ignore_cur_inode) continue; if (wc->log_key.type == BTRFS_DIR_INDEX_KEY && wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { ret = replay_one_dir_item(wc); if (ret) break; } if (wc->stage < LOG_WALK_REPLAY_ALL) continue; /* these keys are simply copied */ if (wc->log_key.type == BTRFS_XATTR_ITEM_KEY) { ret = overwrite_item(wc); if (ret) break; } else if (wc->log_key.type == BTRFS_INODE_REF_KEY || wc->log_key.type == BTRFS_INODE_EXTREF_KEY) { ret = add_inode_ref(wc); if (ret) break; } else if (wc->log_key.type == BTRFS_EXTENT_DATA_KEY) { ret = replay_one_extent(wc); if (ret) break; } /* * We don't log BTRFS_DIR_ITEM_KEY keys anymore, only the * BTRFS_DIR_INDEX_KEY items which we use to derive the * BTRFS_DIR_ITEM_KEY items. If we are replaying a log from an * older kernel with such keys, ignore them. */ } btrfs_free_path(wc->subvol_path); wc->subvol_path = NULL; return ret; } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_block_group *bg; btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); if (trans) { int ret; ret = btrfs_pin_reserved_extent(trans, eb); if (ret) btrfs_abort_transaction(trans, ret); return ret; } bg = btrfs_lookup_block_group(fs_info, eb->start); if (!bg) { btrfs_err(fs_info, "unable to find block group for %llu", eb->start); btrfs_handle_fs_error(fs_info, -ENOENT, NULL); return -ENOENT; } spin_lock(&bg->space_info->lock); spin_lock(&bg->lock); bg->reserved -= fs_info->nodesize; bg->space_info->bytes_reserved -= fs_info->nodesize; spin_unlock(&bg->lock); spin_unlock(&bg->space_info->lock); btrfs_put_block_group(bg); return 0; } static noinline int walk_down_log_tree(struct btrfs_path *path, int *level, struct walk_control *wc) { struct btrfs_trans_handle *trans = wc->trans; struct btrfs_fs_info *fs_info = wc->log->fs_info; u64 bytenr; u64 ptr_gen; struct extent_buffer *next; struct extent_buffer *cur; int ret = 0; while (*level > 0) { struct btrfs_tree_parent_check check = { 0 }; cur = path->nodes[*level]; WARN_ON(btrfs_header_level(cur) != *level); if (path->slots[*level] >= btrfs_header_nritems(cur)) break; bytenr = btrfs_node_blockptr(cur, path->slots[*level]); ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]); check.transid = ptr_gen; check.level = *level - 1; check.has_first_key = true; btrfs_node_key_to_cpu(cur, &check.first_key, path->slots[*level]); next = btrfs_find_create_tree_block(fs_info, bytenr, btrfs_header_owner(cur), *level - 1); if (IS_ERR(next)) { ret = PTR_ERR(next); if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(fs_info, ret, NULL); return ret; } if (*level == 1) { ret = wc->process_func(next, wc, ptr_gen, *level - 1); if (ret) { free_extent_buffer(next); return ret; } path->slots[*level]++; if (wc->free) { ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(fs_info, ret, NULL); return ret; } ret = clean_log_buffer(trans, next); if (ret) { free_extent_buffer(next); return ret; } } free_extent_buffer(next); continue; } ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(fs_info, ret, NULL); return ret; } if (path->nodes[*level-1]) free_extent_buffer(path->nodes[*level-1]); path->nodes[*level-1] = next; *level = btrfs_header_level(next); path->slots[*level] = 0; cond_resched(); } path->slots[*level] = btrfs_header_nritems(path->nodes[*level]); cond_resched(); return 0; } static noinline int walk_up_log_tree(struct btrfs_path *path, int *level, struct walk_control *wc) { int i; int slot; int ret; for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) { slot = path->slots[i]; if (slot + 1 < btrfs_header_nritems(path->nodes[i])) { path->slots[i]++; *level = i; WARN_ON(*level == 0); return 0; } else { ret = wc->process_func(path->nodes[*level], wc, btrfs_header_generation(path->nodes[*level]), *level); if (ret) return ret; if (wc->free) { ret = clean_log_buffer(wc->trans, path->nodes[*level]); if (ret) return ret; } free_extent_buffer(path->nodes[*level]); path->nodes[*level] = NULL; *level = i + 1; } } return 1; } /* * drop the reference count on the tree rooted at 'snap'. This traverses * the tree freeing any blocks that have a ref count of zero after being * decremented. */ static int walk_log_tree(struct walk_control *wc) { struct btrfs_root *log = wc->log; int ret = 0; int wret; int level; BTRFS_PATH_AUTO_FREE(path); int orig_level; path = btrfs_alloc_path(); if (!path) return -ENOMEM; level = btrfs_header_level(log->node); orig_level = level; path->nodes[level] = log->node; refcount_inc(&log->node->refs); path->slots[level] = 0; while (1) { wret = walk_down_log_tree(path, &level, wc); if (wret > 0) break; if (wret < 0) return wret; wret = walk_up_log_tree(path, &level, wc); if (wret > 0) break; if (wret < 0) return wret; } /* was the root node processed? if not, catch it here */ if (path->nodes[orig_level]) { ret = wc->process_func(path->nodes[orig_level], wc, btrfs_header_generation(path->nodes[orig_level]), orig_level); if (ret) return ret; if (wc->free) ret = clean_log_buffer(wc->trans, path->nodes[orig_level]); } return ret; } /* * helper function to update the item for a given subvolumes log root * in the tree of log roots */ static int update_log_root(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_root_item *root_item) { struct btrfs_fs_info *fs_info = log->fs_info; int ret; if (log->log_transid == 1) { /* insert root item on the first sync */ ret = btrfs_insert_root(trans, fs_info->log_root_tree, &log->root_key, root_item); } else { ret = btrfs_update_root(trans, fs_info->log_root_tree, &log->root_key, root_item); } return ret; } static void wait_log_commit(struct btrfs_root *root, int transid) { DEFINE_WAIT(wait); int index = transid % 2; /* * we only allow two pending log transactions at a time, * so we know that if ours is more than 2 older than the * current transaction, we're done */ for (;;) { prepare_to_wait(&root->log_commit_wait[index], &wait, TASK_UNINTERRUPTIBLE); if (!(root->log_transid_committed < transid && atomic_read(&root->log_commit[index]))) break; mutex_unlock(&root->log_mutex); schedule(); mutex_lock(&root->log_mutex); } finish_wait(&root->log_commit_wait[index], &wait); } static void wait_for_writer(struct btrfs_root *root) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&root->log_writer_wait, &wait, TASK_UNINTERRUPTIBLE); if (!atomic_read(&root->log_writers)) break; mutex_unlock(&root->log_mutex); schedule(); mutex_lock(&root->log_mutex); } finish_wait(&root->log_writer_wait, &wait); } void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct btrfs_inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->log_new_dentries = false; ctx->logging_new_name = false; ctx->logging_new_delayed_dentries = false; ctx->logged_before = false; ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); INIT_LIST_HEAD(&ctx->ordered_extents); INIT_LIST_HEAD(&ctx->conflict_inodes); ctx->num_conflict_inodes = 0; ctx->logging_conflict_inodes = false; ctx->scratch_eb = NULL; } void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx) { struct btrfs_inode *inode = ctx->inode; if (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return; /* * Don't care about allocation failure. This is just for optimization, * if we fail to allocate here, we will try again later if needed. */ ctx->scratch_eb = alloc_dummy_extent_buffer(inode->root->fs_info, 0); } void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; btrfs_assert_inode_locked(ctx->inode); list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); btrfs_put_ordered_extent(ordered); } } static inline void btrfs_remove_log_ctx(struct btrfs_root *root, struct btrfs_log_ctx *ctx) { mutex_lock(&root->log_mutex); list_del_init(&ctx->list); mutex_unlock(&root->log_mutex); } /* * Invoked in log mutex context, or be sure there is no other task which * can access the list. */ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; struct btrfs_log_ctx *safe; list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { list_del_init(&ctx->list); ctx->log_ret = error; } } /* * Sends a given tree log down to the disk and updates the super blocks to * record it. When this call is done, you know that any inodes previously * logged are safely on disk only if it returns 0. * * Any other return value means you need to call btrfs_commit_transaction. * Some of the edge cases for fsyncing directories that have had unlinks * or renames done in the past mean that sometimes the only safe * fsync is to commit the whole FS. When btrfs_sync_log returns -EAGAIN, * that has happened. */ int btrfs_sync_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { int index1; int index2; int mark; int ret; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log = root->log_root; struct btrfs_root *log_root_tree = fs_info->log_root_tree; struct btrfs_root_item new_root_item; int log_transid = 0; struct btrfs_log_ctx root_log_ctx; struct blk_plug plug; u64 log_root_start; u64 log_root_level; mutex_lock(&root->log_mutex); log_transid = ctx->log_transid; if (root->log_transid_committed >= log_transid) { mutex_unlock(&root->log_mutex); return ctx->log_ret; } index1 = log_transid % 2; if (atomic_read(&root->log_commit[index1])) { wait_log_commit(root, log_transid); mutex_unlock(&root->log_mutex); return ctx->log_ret; } ASSERT(log_transid == root->log_transid); atomic_set(&root->log_commit[index1], 1); /* wait for previous tree log sync to complete */ if (atomic_read(&root->log_commit[(index1 + 1) % 2])) wait_log_commit(root, log_transid - 1); while (1) { int batch = atomic_read(&root->log_batch); /* when we're on an ssd, just kick the log commit out */ if (!btrfs_test_opt(fs_info, SSD) && test_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state)) { mutex_unlock(&root->log_mutex); schedule_timeout_uninterruptible(1); mutex_lock(&root->log_mutex); } wait_for_writer(root); if (batch == atomic_read(&root->log_batch)) break; } /* bail out if we need to do a full commit */ if (btrfs_need_log_full_commit(trans)) { ret = BTRFS_LOG_FORCE_COMMIT; mutex_unlock(&root->log_mutex); goto out; } if (log_transid % 2 == 0) mark = EXTENT_DIRTY_LOG1; else mark = EXTENT_DIRTY_LOG2; /* we start IO on all the marked extents here, but we don't actually * wait for them until later. */ blk_start_plug(&plug); ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark); /* * -EAGAIN happens when someone, e.g., a concurrent transaction * commit, writes a dirty extent in this tree-log commit. This * concurrent write will create a hole writing out the extents, * and we cannot proceed on a zoned filesystem, requiring * sequential writing. While we can bail out to a full commit * here, but we can continue hoping the concurrent writing fills * the hole. */ if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) ret = 0; if (ret) { blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); mutex_unlock(&root->log_mutex); goto out; } /* * We _must_ update under the root->log_mutex in order to make sure we * have a consistent view of the log root we are trying to commit at * this moment. * * We _must_ copy this into a local copy, because we are not holding the * log_root_tree->log_mutex yet. This is important because when we * commit the log_root_tree we must have a consistent view of the * log_root_tree when we update the super block to point at the * log_root_tree bytenr. If we update the log_root_tree here we'll race * with the commit and possibly point at the new block which we may not * have written out. */ btrfs_set_root_node(&log->root_item, log->node); memcpy(&new_root_item, &log->root_item, sizeof(new_root_item)); btrfs_set_root_log_transid(root, root->log_transid + 1); log->log_transid = root->log_transid; root->log_start_pid = 0; /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. */ mutex_unlock(&root->log_mutex); if (btrfs_is_zoned(fs_info)) { mutex_lock(&fs_info->tree_root->log_mutex); if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); blk_finish_plug(&plug); goto out; } } mutex_unlock(&fs_info->tree_root->log_mutex); } btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); index2 = log_root_tree->log_transid % 2; list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit * open until we drop the log_mutex. */ ret = update_log_root(trans, log, &new_root_item); if (ret) { list_del_init(&root_log_ctx.list); blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); if (ret != -ENOSPC) btrfs_err(fs_info, "failed to update log for root %llu ret %d", btrfs_root_id(root), ret); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); goto out; } if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { blk_finish_plug(&plug); list_del_init(&root_log_ctx.list); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; } if (atomic_read(&log_root_tree->log_commit[index2])) { blk_finish_plug(&plug); ret = btrfs_wait_tree_log_extents(log, mark); wait_log_commit(log_root_tree, root_log_ctx.log_transid); mutex_unlock(&log_root_tree->log_mutex); if (!ret) ret = root_log_ctx.log_ret; goto out; } ASSERT(root_log_ctx.log_transid == log_root_tree->log_transid); atomic_set(&log_root_tree->log_commit[index2], 1); if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2])) { wait_log_commit(log_root_tree, root_log_ctx.log_transid - 1); } /* * now that we've moved on to the tree of log tree roots, * check the full commit flag again */ if (btrfs_need_log_full_commit(trans)) { blk_finish_plug(&plug); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); ret = BTRFS_LOG_FORCE_COMMIT; goto out_wake_log_root; } ret = btrfs_write_marked_extents(fs_info, &log_root_tree->dirty_log_pages, EXTENT_DIRTY_LOG1 | EXTENT_DIRTY_LOG2); blk_finish_plug(&plug); /* * As described above, -EAGAIN indicates a hole in the extents. We * cannot wait for these write outs since the waiting cause a * deadlock. Bail out to the full commit instead. */ if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) { btrfs_set_log_full_commit(trans); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } else if (ret) { btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } ret = btrfs_wait_tree_log_extents(log, mark); if (!ret) ret = btrfs_wait_tree_log_extents(log_root_tree, EXTENT_DIRTY_LOG1 | EXTENT_DIRTY_LOG2); if (ret) { btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } log_root_start = log_root_tree->node->start; log_root_level = btrfs_header_level(log_root_tree->node); log_root_tree->log_transid++; mutex_unlock(&log_root_tree->log_mutex); /* * Here we are guaranteed that nobody is going to write the superblock * for the current transaction before us and that neither we do write * our superblock before the previous transaction finishes its commit * and writes its superblock, because: * * 1) We are holding a handle on the current transaction, so no body * can commit it until we release the handle; * * 2) Before writing our superblock we acquire the tree_log_mutex, so * if the previous transaction is still committing, and hasn't yet * written its superblock, we wait for it to do it, because a * transaction commit acquires the tree_log_mutex when the commit * begins and releases it only after writing its superblock. */ mutex_lock(&fs_info->tree_log_mutex); /* * The previous transaction writeout phase could have failed, and thus * marked the fs in an error state. We must not commit here, as we * could have updated our generation in the super_for_commit and * writing the super here would result in transid mismatches. If there * is an error here just bail. */ if (BTRFS_FS_ERROR(fs_info)) { ret = -EIO; btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&fs_info->tree_log_mutex); goto out_wake_log_root; } btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start); btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level); ret = write_all_supers(fs_info, 1); mutex_unlock(&fs_info->tree_log_mutex); if (unlikely(ret)) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); goto out_wake_log_root; } /* * We know there can only be one task here, since we have not yet set * root->log_commit[index1] to 0 and any task attempting to sync the * log must wait for the previous log transaction to commit if it's * still in progress or wait for the current log transaction commit if * someone else already started it. We use <= and not < because the * first log transaction has an ID of 0. */ ASSERT(btrfs_get_root_last_log_commit(root) <= log_transid); btrfs_set_root_last_log_commit(root, log_transid); out_wake_log_root: mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); /* * The barrier before waitqueue_active (in cond_wake_up) is needed so * all the updates above are seen by the woken threads. It might not be * necessary, but proving that seems to be hard. */ cond_wake_up(&log_root_tree->log_commit_wait[index2]); out: mutex_lock(&root->log_mutex); btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); /* * The barrier before waitqueue_active (in cond_wake_up) is needed so * all the updates above are seen by the woken threads. It might not be * necessary, but proving that seems to be hard. */ cond_wake_up(&root->log_commit_wait[index1]); return ret; } static void free_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *log) { int ret; struct walk_control wc = { .free = true, .process_func = process_one_buffer, .log = log, .trans = trans, }; if (log->node) { ret = walk_log_tree(&wc); if (ret) { /* * We weren't able to traverse the entire log tree, the * typical scenario is getting an -EIO when reading an * extent buffer of the tree, due to a previous writeback * failure of it. */ set_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, &log->fs_info->fs_state); /* * Some extent buffers of the log tree may still be dirty * and not yet written back to storage, because we may * have updates to a log tree without syncing a log tree, * such as during rename and link operations. So flush * them out and wait for their writeback to complete, so * that we properly cleanup their state and pages. */ btrfs_write_marked_extents(log->fs_info, &log->dirty_log_pages, EXTENT_DIRTY_LOG1 | EXTENT_DIRTY_LOG2); btrfs_wait_tree_log_extents(log, EXTENT_DIRTY_LOG1 | EXTENT_DIRTY_LOG2); if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(log->fs_info, ret, NULL); } } btrfs_extent_io_tree_release(&log->dirty_log_pages); btrfs_extent_io_tree_release(&log->log_csum_range); btrfs_put_root(log); } /* * free all the extents used by the tree log. This should be called * at commit time of the full transaction */ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root) { if (root->log_root) { free_log_tree(trans, root->log_root); root->log_root = NULL; clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); } return 0; } int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { if (fs_info->log_root_tree) { free_log_tree(trans, fs_info->log_root_tree); fs_info->log_root_tree = NULL; clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &fs_info->tree_root->state); } return 0; } static bool mark_inode_as_not_logged(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { bool ret = false; /* * Do this only if ->logged_trans is still 0 to prevent races with * concurrent logging as we may see the inode not logged when * inode_logged() is called but it gets logged after inode_logged() did * not find it in the log tree and we end up setting ->logged_trans to a * value less than trans->transid after the concurrent logging task has * set it to trans->transid. As a consequence, subsequent rename, unlink * and link operations may end up not logging new names and removing old * names from the log. */ spin_lock(&inode->lock); if (inode->logged_trans == 0) inode->logged_trans = trans->transid - 1; else if (inode->logged_trans == trans->transid) ret = true; spin_unlock(&inode->lock); return ret; } /* * Check if an inode was logged in the current transaction. This correctly deals * with the case where the inode was logged but has a logged_trans of 0, which * happens if the inode is evicted and loaded again, as logged_trans is an in * memory only field (not persisted). * * Returns 1 if the inode was logged before in the transaction, 0 if it was not, * and < 0 on error. */ static int inode_logged(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path_in) { struct btrfs_path *path = path_in; struct btrfs_key key; int ret; /* * Quick lockless call, since once ->logged_trans is set to the current * transaction, we never set it to a lower value anywhere else. */ if (data_race(inode->logged_trans) == trans->transid) return 1; /* * If logged_trans is not 0 and not trans->transid, then we know the * inode was not logged in this transaction, so we can return false * right away. We take the lock to avoid a race caused by load/store * tearing with a concurrent btrfs_log_inode() call or a concurrent task * in this function further below - an update to trans->transid can be * teared into two 32 bits updates for example, in which case we could * see a positive value that is not trans->transid and assume the inode * was not logged when it was. */ spin_lock(&inode->lock); if (inode->logged_trans == trans->transid) { spin_unlock(&inode->lock); return 1; } else if (inode->logged_trans > 0) { spin_unlock(&inode->lock); return 0; } spin_unlock(&inode->lock); /* * If no log tree was created for this root in this transaction, then * the inode can not have been logged in this transaction. In that case * set logged_trans to anything greater than 0 and less than the current * transaction's ID, to avoid the search below in a future call in case * a log tree gets created after this. */ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) return mark_inode_as_not_logged(trans, inode); /* * We have a log tree and the inode's logged_trans is 0. We can't tell * for sure if the inode was logged before in this transaction by looking * only at logged_trans. We could be pessimistic and assume it was, but * that can lead to unnecessarily logging an inode during rename and link * operations, and then further updating the log in followup rename and * link operations, specially if it's a directory, which adds latency * visible to applications doing a series of rename or link operations. * * A logged_trans of 0 here can mean several things: * * 1) The inode was never logged since the filesystem was mounted, and may * or may have not been evicted and loaded again; * * 2) The inode was logged in a previous transaction, then evicted and * then loaded again; * * 3) The inode was logged in the current transaction, then evicted and * then loaded again. * * For cases 1) and 2) we don't want to return true, but we need to detect * case 3) and return true. So we do a search in the log root for the inode * item. */ key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; if (!path) { path = btrfs_alloc_path(); if (!path) return -ENOMEM; } ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); if (path_in) btrfs_release_path(path); else btrfs_free_path(path); /* * Logging an inode always results in logging its inode item. So if we * did not find the item we know the inode was not logged for sure. */ if (ret < 0) { return ret; } else if (ret > 0) { /* * Set logged_trans to a value greater than 0 and less then the * current transaction to avoid doing the search in future calls. */ return mark_inode_as_not_logged(trans, inode); } /* * The inode was previously logged and then evicted, set logged_trans to * the current transaction's ID, to avoid future tree searches as long as * the inode is not evicted again. */ spin_lock(&inode->lock); inode->logged_trans = trans->transid; spin_unlock(&inode->lock); return 1; } /* * Delete a directory entry from the log if it exists. * * Returns < 0 on error * 1 if the entry does not exists * 0 if the entry existed and was successfully deleted */ static int del_logged_dentry(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dir_ino, const struct fscrypt_str *name, u64 index) { struct btrfs_dir_item *di; /* * We only log dir index items of a directory, so we don't need to look * for dir item keys. */ di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino, index, name, -1); if (IS_ERR(di)) return PTR_ERR(di); else if (!di) return 1; /* * We do not need to update the size field of the directory's * inode item because on log replay we update the field to reflect * all existing entries in the directory (see overwrite_item()). */ return btrfs_del_item(trans, log, path); } /* * If both a file and directory are logged, and unlinks or renames are * mixed in, we have a few interesting corners: * * create file X in dir Y * link file X to X.link in dir Y * fsync file X * unlink file X but leave X.link * fsync dir Y * * After a crash we would expect only X.link to exist. But file X * didn't get fsync'd again so the log has back refs for X and X.link. * * We solve this by removing directory entries and inode backrefs from the * log when a file that was logged in the current transaction is * unlinked. Any later fsync will include the updated log entries, and * we'll be able to reconstruct the proper directory items from backrefs. * * This optimizations allows us to avoid relogging the entire inode * or the entire directory. */ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *dir, u64 index) { BTRFS_PATH_AUTO_FREE(path); int ret; ret = inode_logged(trans, dir, NULL); if (ret == 0) return; if (ret < 0) { btrfs_set_log_full_commit(trans); return; } path = btrfs_alloc_path(); if (!path) { btrfs_set_log_full_commit(trans); return; } ret = join_running_log_trans(root); ASSERT(ret == 0, "join_running_log_trans() ret=%d", ret); if (WARN_ON(ret)) return; mutex_lock(&dir->log_mutex); ret = del_logged_dentry(trans, root->log_root, path, btrfs_ino(dir), name, index); mutex_unlock(&dir->log_mutex); if (ret < 0) btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); } /* see comments for btrfs_del_dir_entries_in_log */ void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *inode, u64 dirid) { struct btrfs_root *log; int ret; ret = inode_logged(trans, inode, NULL); if (ret == 0) return; else if (ret < 0) { btrfs_set_log_full_commit(trans); return; } ret = join_running_log_trans(root); ASSERT(ret == 0, "join_running_log_trans() ret=%d", ret); if (WARN_ON(ret)) return; log = root->log_root; mutex_lock(&inode->log_mutex); ret = btrfs_del_inode_ref(trans, log, name, btrfs_ino(inode), dirid, NULL); mutex_unlock(&inode->log_mutex); if (ret < 0 && ret != -ENOENT) btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); } /* * creates a range item in the log for 'dirid'. first_offset and * last_offset tell us which parts of the key space the log should * be considered authoritative for. */ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, u64 first_offset, u64 last_offset) { int ret; struct btrfs_key key; struct btrfs_dir_log_item *item; key.objectid = dirid; key.type = BTRFS_DIR_LOG_INDEX_KEY; key.offset = first_offset; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item)); /* * -EEXIST is fine and can happen sporadically when we are logging a * directory and have concurrent insertions in the subvolume's tree for * items from other inodes and that result in pushing off some dir items * from one leaf to another in order to accommodate for the new items. * This results in logging the same dir index range key. */ if (ret && ret != -EEXIST) return ret; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); if (ret == -EEXIST) { const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item); /* * btrfs_del_dir_entries_in_log() might have been called during * an unlink between the initial insertion of this key and the * current update, or we might be logging a single entry deletion * during a rename, so set the new last_offset to the max value. */ last_offset = max(last_offset, curr_end); } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); btrfs_release_path(path); return 0; } static int flush_dir_items_batch(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct extent_buffer *src, struct btrfs_path *dst_path, int start_slot, int count) { struct btrfs_root *log = inode->root->log_root; char *ins_data = NULL; struct btrfs_item_batch batch; struct extent_buffer *dst; unsigned long src_offset; unsigned long dst_offset; u64 last_index; struct btrfs_key key; u32 item_size; int ret; int i; ASSERT(count > 0); batch.nr = count; if (count == 1) { btrfs_item_key_to_cpu(src, &key, start_slot); item_size = btrfs_item_size(src, start_slot); batch.keys = &key; batch.data_sizes = &item_size; batch.total_data_size = item_size; } else { struct btrfs_key *ins_keys; u32 *ins_sizes; ins_data = kmalloc_array(count, sizeof(u32) + sizeof(struct btrfs_key), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + count * sizeof(u32)); batch.keys = ins_keys; batch.data_sizes = ins_sizes; batch.total_data_size = 0; for (i = 0; i < count; i++) { const int slot = start_slot + i; btrfs_item_key_to_cpu(src, &ins_keys[i], slot); ins_sizes[i] = btrfs_item_size(src, slot); batch.total_data_size += ins_sizes[i]; } } ret = btrfs_insert_empty_items(trans, log, dst_path, &batch); if (ret) goto out; dst = dst_path->nodes[0]; /* * Copy all the items in bulk, in a single copy operation. Item data is * organized such that it's placed at the end of a leaf and from right * to left. For example, the data for the second item ends at an offset * that matches the offset where the data for the first item starts, the * data for the third item ends at an offset that matches the offset * where the data of the second items starts, and so on. * Therefore our source and destination start offsets for copy match the * offsets of the last items (highest slots). */ dst_offset = btrfs_item_ptr_offset(dst, dst_path->slots[0] + count - 1); src_offset = btrfs_item_ptr_offset(src, start_slot + count - 1); copy_extent_buffer(dst, src, dst_offset, src_offset, batch.total_data_size); btrfs_release_path(dst_path); last_index = batch.keys[count - 1].offset; ASSERT(last_index > inode->last_dir_index_offset); /* * If for some unexpected reason the last item's index is not greater * than the last index we logged, warn and force a transaction commit. */ if (WARN_ON(last_index <= inode->last_dir_index_offset)) ret = BTRFS_LOG_FORCE_COMMIT; else inode->last_dir_index_offset = last_index; if (btrfs_get_first_dir_index_to_log(inode) == 0) btrfs_set_first_dir_index_to_log(inode, batch.keys[0].offset); out: kfree(ins_data); return ret; } static int clone_leaf(struct btrfs_path *path, struct btrfs_log_ctx *ctx) { const int slot = path->slots[0]; if (ctx->scratch_eb) { copy_extent_buffer_full(ctx->scratch_eb, path->nodes[0]); } else { ctx->scratch_eb = btrfs_clone_extent_buffer(path->nodes[0]); if (!ctx->scratch_eb) return -ENOMEM; } btrfs_release_path(path); path->nodes[0] = ctx->scratch_eb; path->slots[0] = slot; /* * Add extra ref to scratch eb so that it is not freed when callers * release the path, so we can reuse it later if needed. */ refcount_inc(&ctx->scratch_eb->refs); return 0; } static int process_dir_items_leaf(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx, u64 *last_old_dentry_offset) { struct btrfs_root *log = inode->root->log_root; struct extent_buffer *src; const int nritems = btrfs_header_nritems(path->nodes[0]); const u64 ino = btrfs_ino(inode); bool last_found = false; int batch_start = 0; int batch_size = 0; int ret; /* * We need to clone the leaf, release the read lock on it, and use the * clone before modifying the log tree. See the comment at copy_items() * about why we need to do this. */ ret = clone_leaf(path, ctx); if (ret < 0) return ret; src = path->nodes[0]; for (int i = path->slots[0]; i < nritems; i++) { struct btrfs_dir_item *di; struct btrfs_key key; int ret; btrfs_item_key_to_cpu(src, &key, i); if (key.objectid != ino || key.type != BTRFS_DIR_INDEX_KEY) { last_found = true; break; } di = btrfs_item_ptr(src, i, struct btrfs_dir_item); /* * Skip ranges of items that consist only of dir item keys created * in past transactions. However if we find a gap, we must log a * dir index range item for that gap, so that index keys in that * gap are deleted during log replay. */ if (btrfs_dir_transid(src, di) < trans->transid) { if (key.offset > *last_old_dentry_offset + 1) { ret = insert_dir_log_key(trans, log, dst_path, ino, *last_old_dentry_offset + 1, key.offset - 1); if (ret < 0) return ret; } *last_old_dentry_offset = key.offset; continue; } /* If we logged this dir index item before, we can skip it. */ if (key.offset <= inode->last_dir_index_offset) continue; /* * We must make sure that when we log a directory entry, the * corresponding inode, after log replay, has a matching link * count. For example: * * touch foo * mkdir mydir * sync * ln foo mydir/bar * xfs_io -c "fsync" mydir * <crash> * <mount fs and log replay> * * Would result in a fsync log that when replayed, our file inode * would have a link count of 1, but we get two directory entries * pointing to the same inode. After removing one of the names, * it would not be possible to remove the other name, which * resulted always in stale file handle errors, and would not be * possible to rmdir the parent directory, since its i_size could * never be decremented to the value BTRFS_EMPTY_DIR_SIZE, * resulting in -ENOTEMPTY errors. */ if (!ctx->log_new_dentries) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(src, di, &di_key); if (di_key.type != BTRFS_ROOT_ITEM_KEY) ctx->log_new_dentries = true; } if (batch_size == 0) batch_start = i; batch_size++; } if (batch_size > 0) { int ret; ret = flush_dir_items_batch(trans, inode, src, dst_path, batch_start, batch_size); if (ret < 0) return ret; } return last_found ? 1 : 0; } /* * log all the items included in the current transaction for a given * directory. This also creates the range items in the log tree required * to replay anything deleted before the fsync */ static noinline int log_dir_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx, u64 min_offset, u64 *last_offset_ret) { struct btrfs_key min_key; struct btrfs_root *root = inode->root; struct btrfs_root *log = root->log_root; int ret; u64 last_old_dentry_offset = min_offset - 1; u64 last_offset = (u64)-1; u64 ino = btrfs_ino(inode); min_key.objectid = ino; min_key.type = BTRFS_DIR_INDEX_KEY; min_key.offset = min_offset; ret = btrfs_search_forward(root, &min_key, path, trans->transid); /* * we didn't find anything from this transaction, see if there * is anything at all */ if (ret != 0 || min_key.objectid != ino || min_key.type != BTRFS_DIR_INDEX_KEY) { min_key.objectid = ino; min_key.type = BTRFS_DIR_INDEX_KEY; min_key.offset = (u64)-1; btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret < 0) { btrfs_release_path(path); return ret; } ret = btrfs_previous_item(root, path, ino, BTRFS_DIR_INDEX_KEY); /* if ret == 0 there are items for this type, * create a range to tell us the last key of this type. * otherwise, there are no items in this directory after * *min_offset, and we create a range to indicate that. */ if (ret == 0) { struct btrfs_key tmp; btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; } else if (ret > 0) { ret = 0; } goto done; } /* go backward to find any previous key */ ret = btrfs_previous_item(root, path, ino, BTRFS_DIR_INDEX_KEY); if (ret == 0) { struct btrfs_key tmp; btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); /* * The dir index key before the first one we found that needs to * be logged might be in a previous leaf, and there might be a * gap between these keys, meaning that we had deletions that * happened. So the key range item we log (key type * BTRFS_DIR_LOG_INDEX_KEY) must cover a range that starts at the * previous key's offset plus 1, so that those deletes are replayed. */ if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; } else if (ret < 0) { goto done; } btrfs_release_path(path); /* * Find the first key from this transaction again or the one we were at * in the loop below in case we had to reschedule. We may be logging the * directory without holding its VFS lock, which happen when logging new * dentries (through log_new_dir_dentries()) or in some cases when we * need to log the parent directory of an inode. This means a dir index * key might be deleted from the inode's root, and therefore we may not * find it anymore. If we can't find it, just move to the next key. We * can not bail out and ignore, because if we do that we will simply * not log dir index keys that come after the one that was just deleted * and we can end up logging a dir index range that ends at (u64)-1 * (@last_offset is initialized to that), resulting in removing dir * entries we should not remove at log replay time. */ search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret > 0) { ret = btrfs_next_item(root, path); if (ret > 0) { /* There are no more keys in the inode's root. */ ret = 0; goto done; } } if (ret < 0) goto done; /* * we have a block from this transaction, log every item in it * from our directory */ while (1) { ret = process_dir_items_leaf(trans, inode, path, dst_path, ctx, &last_old_dentry_offset); if (ret != 0) { if (ret > 0) ret = 0; goto done; } path->slots[0] = btrfs_header_nritems(path->nodes[0]); /* * look ahead to the next item and see if it is also * from this directory and from this transaction */ ret = btrfs_next_leaf(root, path); if (ret) { if (ret == 1) { last_offset = (u64)-1; ret = 0; } goto done; } btrfs_item_key_to_cpu(path->nodes[0], &min_key, path->slots[0]); if (min_key.objectid != ino || min_key.type != BTRFS_DIR_INDEX_KEY) { last_offset = (u64)-1; goto done; } if (btrfs_header_generation(path->nodes[0]) != trans->transid) { /* * The next leaf was not changed in the current transaction * and has at least one dir index key. * We check for the next key because there might have been * one or more deletions between the last key we logged and * that next key. So the key range item we log (key type * BTRFS_DIR_LOG_INDEX_KEY) must end at the next key's * offset minus 1, so that those deletes are replayed. */ last_offset = min_key.offset - 1; goto done; } if (need_resched()) { btrfs_release_path(path); cond_resched(); goto search; } } done: btrfs_release_path(path); btrfs_release_path(dst_path); if (ret == 0) { *last_offset_ret = last_offset; /* * In case the leaf was changed in the current transaction but * all its dir items are from a past transaction, the last item * in the leaf is a dir item and there's no gap between that last * dir item and the first one on the next leaf (which did not * change in the current transaction), then we don't need to log * a range, last_old_dentry_offset is == to last_offset. */ ASSERT(last_old_dentry_offset <= last_offset); if (last_old_dentry_offset < last_offset) ret = insert_dir_log_key(trans, log, path, ino, last_old_dentry_offset + 1, last_offset); } return ret; } /* * If the inode was logged before and it was evicted, then its * last_dir_index_offset is 0, so we don't know the value of the last index * key offset. If that's the case, search for it and update the inode. This * is to avoid lookups in the log tree every time we try to insert a dir index * key from a leaf changed in the current transaction, and to allow us to always * do batch insertions of dir index keys. */ static int update_last_dir_index_offset(struct btrfs_inode *inode, struct btrfs_path *path, const struct btrfs_log_ctx *ctx) { const u64 ino = btrfs_ino(inode); struct btrfs_key key; int ret; lockdep_assert_held(&inode->log_mutex); if (inode->last_dir_index_offset != 0) return 0; if (!ctx->logged_before) { inode->last_dir_index_offset = BTRFS_DIR_START_INDEX - 1; return 0; } key.objectid = ino; key.type = BTRFS_DIR_INDEX_KEY; key.offset = (u64)-1; ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); /* * An error happened or we actually have an index key with an offset * value of (u64)-1. Bail out, we're done. */ if (ret <= 0) goto out; ret = 0; inode->last_dir_index_offset = BTRFS_DIR_START_INDEX - 1; /* * No dir index items, bail out and leave last_dir_index_offset with * the value right before the first valid index value. */ if (path->slots[0] == 0) goto out; /* * btrfs_search_slot() left us at one slot beyond the slot with the last * index key, or beyond the last key of the directory that is not an * index key. If we have an index key before, set last_dir_index_offset * to its offset value, otherwise leave it with a value right before the * first valid index value, as it means we have an empty directory. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); if (key.objectid == ino && key.type == BTRFS_DIR_INDEX_KEY) inode->last_dir_index_offset = key.offset; out: btrfs_release_path(path); return ret; } /* * logging directories is very similar to logging inodes, We find all the items * from the current transaction and write them to the log. * * The recovery code scans the directory in the subvolume, and if it finds a * key in the range logged that is not present in the log tree, then it means * that dir entry was unlinked during the transaction. * * In order for that scan to work, we must include one key smaller than * the smallest logged by this transaction and one key larger than the largest * key logged by this transaction. */ static noinline int log_directory_changes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) { u64 min_key; u64 max_key; int ret; ret = update_last_dir_index_offset(inode, path, ctx); if (ret) return ret; min_key = BTRFS_DIR_START_INDEX; max_key = 0; while (1) { ret = log_dir_items(trans, inode, path, dst_path, ctx, min_key, &max_key); if (ret) return ret; if (max_key == (u64)-1) break; min_key = max_key + 1; } return 0; } /* * a helper function to drop items from the log before we relog an * inode. max_key_type indicates the highest item type to remove. * This cannot be run for file data extents because it does not * free the extents they point to. */ static int drop_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_inode *inode, int max_key_type) { int ret; struct btrfs_key key; struct btrfs_key found_key; int start_slot; key.objectid = btrfs_ino(inode); key.type = max_key_type; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(trans, log, &key, path, -1, 1); if (ret < 0) { break; } else if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); if (found_key.objectid != key.objectid) break; found_key.offset = 0; found_key.type = 0; ret = btrfs_bin_search(path->nodes[0], 0, &found_key, &start_slot); if (ret < 0) break; ret = btrfs_del_items(trans, log, path, start_slot, path->slots[0] - start_slot + 1); /* * If start slot isn't 0 then we don't need to re-search, we've * found the last guy with the objectid in this tree. */ if (ret || start_slot != 0) break; btrfs_release_path(path); } btrfs_release_path(path); if (ret > 0) ret = 0; return ret; } static int truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *log_root, struct btrfs_inode *inode, u64 new_size, u32 min_type) { struct btrfs_truncate_control control = { .new_size = new_size, .ino = btrfs_ino(inode), .min_type = min_type, .skip_ref_updates = true, }; return btrfs_truncate_inode_items(trans, log_root, &control); } static void fill_inode_item(struct btrfs_trans_handle *trans, struct extent_buffer *leaf, struct btrfs_inode_item *item, struct inode *inode, bool log_inode_only, u64 logged_isize) { u64 flags; if (log_inode_only) { /* set the generation to zero so the recover code * can tell the difference between an logging * just to say 'this inode exists' and a logging * to say 'update this inode with these values' */ btrfs_set_inode_generation(leaf, item, 0); btrfs_set_inode_size(leaf, item, logged_isize); } else { btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation); btrfs_set_inode_size(leaf, item, inode->i_size); } btrfs_set_inode_uid(leaf, item, i_uid_read(inode)); btrfs_set_inode_gid(leaf, item, i_gid_read(inode)); btrfs_set_inode_mode(leaf, item, inode->i_mode); btrfs_set_inode_nlink(leaf, item, inode->i_nlink); btrfs_set_timespec_sec(leaf, &item->atime, inode_get_atime_sec(inode)); btrfs_set_timespec_nsec(leaf, &item->atime, inode_get_atime_nsec(inode)); btrfs_set_timespec_sec(leaf, &item->mtime, inode_get_mtime_sec(inode)); btrfs_set_timespec_nsec(leaf, &item->mtime, inode_get_mtime_nsec(inode)); btrfs_set_timespec_sec(leaf, &item->ctime, inode_get_ctime_sec(inode)); btrfs_set_timespec_nsec(leaf, &item->ctime, inode_get_ctime_nsec(inode)); btrfs_set_timespec_sec(leaf, &item->otime, BTRFS_I(inode)->i_otime_sec); btrfs_set_timespec_nsec(leaf, &item->otime, BTRFS_I(inode)->i_otime_nsec); /* * We do not need to set the nbytes field, in fact during a fast fsync * its value may not even be correct, since a fast fsync does not wait * for ordered extent completion, which is where we update nbytes, it * only waits for writeback to complete. During log replay as we find * file extent items and replay them, we adjust the nbytes field of the * inode item in subvolume tree as needed (see overwrite_item()). */ btrfs_set_inode_sequence(leaf, item, inode_peek_iversion(inode)); btrfs_set_inode_transid(leaf, item, trans->transid); btrfs_set_inode_rdev(leaf, item, inode->i_rdev); flags = btrfs_inode_combine_flags(BTRFS_I(inode)->flags, BTRFS_I(inode)->ro_flags); btrfs_set_inode_flags(leaf, item, flags); btrfs_set_inode_block_group(leaf, item, 0); } static int log_inode_item(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_inode *inode, bool inode_item_dropped) { struct btrfs_inode_item *inode_item; struct btrfs_key key; int ret; btrfs_get_inode_key(inode, &key); /* * If we are doing a fast fsync and the inode was logged before in the * current transaction, then we know the inode was previously logged and * it exists in the log tree. For performance reasons, in this case use * btrfs_search_slot() directly with ins_len set to 0 so that we never * attempt a write lock on the leaf's parent, which adds unnecessary lock * contention in case there are concurrent fsyncs for other inodes of the * same subvolume. Using btrfs_insert_empty_item() when the inode item * already exists can also result in unnecessarily splitting a leaf. */ if (!inode_item_dropped && inode->logged_trans == trans->transid) { ret = btrfs_search_slot(trans, log, &key, path, 0, 1); ASSERT(ret <= 0); if (ret > 0) ret = -ENOENT; } else { /* * This means it is the first fsync in the current transaction, * so the inode item is not in the log and we need to insert it. * We can never get -EEXIST because we are only called for a fast * fsync and in case an inode eviction happens after the inode was * logged before in the current transaction, when we load again * the inode, we set BTRFS_INODE_NEEDS_FULL_SYNC on its runtime * flags and set ->logged_trans to 0. */ ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*inode_item)); ASSERT(ret != -EEXIST); } if (ret) return ret; inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); fill_inode_item(trans, path->nodes[0], inode_item, &inode->vfs_inode, false, 0); btrfs_release_path(path); return 0; } static int log_csums(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_root *log_root, struct btrfs_ordered_sum *sums) { const u64 lock_end = sums->logical + sums->len - 1; struct extent_state *cached_state = NULL; int ret; /* * If this inode was not used for reflink operations in the current * transaction with new extents, then do the fast path, no need to * worry about logging checksum items with overlapping ranges. */ if (inode->last_reflink_trans < trans->transid) return btrfs_csum_file_blocks(trans, log_root, sums); /* * Serialize logging for checksums. This is to avoid racing with the * same checksum being logged by another task that is logging another * file which happens to refer to the same extent as well. Such races * can leave checksum items in the log with overlapping ranges. */ ret = btrfs_lock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); if (ret) return ret; /* * Due to extent cloning, we might have logged a csum item that covers a * subrange of a cloned extent, and later we can end up logging a csum * item for a larger subrange of the same extent or the entire range. * This would leave csum items in the log tree that cover the same range * and break the searches for checksums in the log tree, resulting in * some checksums missing in the fs/subvolume tree. So just delete (or * trim and adjust) any existing csum items in the log for this range. */ ret = btrfs_del_csums(trans, log_root, sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, log_root, sums); btrfs_unlock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); return ret; } static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, struct btrfs_path *src_path, int start_slot, int nr, int inode_only, u64 logged_isize, struct btrfs_log_ctx *ctx) { struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item *extent; struct extent_buffer *src; int ret; struct btrfs_key *ins_keys; u32 *ins_sizes; struct btrfs_item_batch batch; char *ins_data; int dst_index; const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM); const u64 i_size = i_size_read(&inode->vfs_inode); /* * To keep lockdep happy and avoid deadlocks, clone the source leaf and * use the clone. This is because otherwise we would be changing the log * tree, to insert items from the subvolume tree or insert csum items, * while holding a read lock on a leaf from the subvolume tree, which * creates a nasty lock dependency when COWing log tree nodes/leaves: * * 1) Modifying the log tree triggers an extent buffer allocation while * holding a write lock on a parent extent buffer from the log tree. * Allocating the pages for an extent buffer, or the extent buffer * struct, can trigger inode eviction and finally the inode eviction * will trigger a release/remove of a delayed node, which requires * taking the delayed node's mutex; * * 2) Allocating a metadata extent for a log tree can trigger the async * reclaim thread and make us wait for it to release enough space and * unblock our reservation ticket. The reclaim thread can start * flushing delayed items, and that in turn results in the need to * lock delayed node mutexes and in the need to write lock extent * buffers of a subvolume tree - all this while holding a write lock * on the parent extent buffer in the log tree. * * So one task in scenario 1) running in parallel with another task in * scenario 2) could lead to a deadlock, one wanting to lock a delayed * node mutex while having a read lock on a leaf from the subvolume, * while the other is holding the delayed node's mutex and wants to * write lock the same subvolume leaf for flushing delayed items. */ ret = clone_leaf(src_path, ctx); if (ret < 0) return ret; src = src_path->nodes[0]; ins_data = kmalloc_array(nr, sizeof(struct btrfs_key) + sizeof(u32), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32)); batch.keys = ins_keys; batch.data_sizes = ins_sizes; batch.total_data_size = 0; batch.nr = 0; dst_index = 0; for (int i = 0; i < nr; i++) { const int src_slot = start_slot + i; struct btrfs_root *csum_root; struct btrfs_ordered_sum *sums; struct btrfs_ordered_sum *sums_next; LIST_HEAD(ordered_sums); u64 disk_bytenr; u64 disk_num_bytes; u64 extent_offset; u64 extent_num_bytes; bool is_old_extent; btrfs_item_key_to_cpu(src, &ins_keys[dst_index], src_slot); if (ins_keys[dst_index].type != BTRFS_EXTENT_DATA_KEY) goto add_to_batch; extent = btrfs_item_ptr(src, src_slot, struct btrfs_file_extent_item); is_old_extent = (btrfs_file_extent_generation(src, extent) < trans->transid); /* * Don't copy extents from past generations. That would make us * log a lot more metadata for common cases like doing only a * few random writes into a file and then fsync it for the first * time or after the full sync flag is set on the inode. We can * get leaves full of extent items, most of which are from past * generations, so we can skip them - as long as the inode has * not been the target of a reflink operation in this transaction, * as in that case it might have had file extent items with old * generations copied into it. We also must always log prealloc * extents that start at or beyond eof, otherwise we would lose * them on log replay. */ if (is_old_extent && ins_keys[dst_index].offset < i_size && inode->last_reflink_trans < trans->transid) continue; if (skip_csum) goto add_to_batch; /* Only regular extents have checksums. */ if (btrfs_file_extent_type(src, extent) != BTRFS_FILE_EXTENT_REG) goto add_to_batch; /* * If it's an extent created in a past transaction, then its * checksums are already accessible from the committed csum tree, * no need to log them. */ if (is_old_extent) goto add_to_batch; disk_bytenr = btrfs_file_extent_disk_bytenr(src, extent); /* If it's an explicit hole, there are no checksums. */ if (disk_bytenr == 0) goto add_to_batch; disk_num_bytes = btrfs_file_extent_disk_num_bytes(src, extent); if (btrfs_file_extent_compression(src, extent)) { extent_offset = 0; extent_num_bytes = disk_num_bytes; } else { extent_offset = btrfs_file_extent_offset(src, extent); extent_num_bytes = btrfs_file_extent_num_bytes(src, extent); } csum_root = btrfs_csum_root(trans->fs_info, disk_bytenr); disk_bytenr += extent_offset; ret = btrfs_lookup_csums_list(csum_root, disk_bytenr, disk_bytenr + extent_num_bytes - 1, &ordered_sums, false); if (ret < 0) goto out; ret = 0; list_for_each_entry_safe(sums, sums_next, &ordered_sums, list) { if (!ret) ret = log_csums(trans, inode, log, sums); list_del(&sums->list); kfree(sums); } if (ret) goto out; add_to_batch: ins_sizes[dst_index] = btrfs_item_size(src, src_slot); batch.total_data_size += ins_sizes[dst_index]; batch.nr++; dst_index++; } /* * We have a leaf full of old extent items that don't need to be logged, * so we don't need to do anything. */ if (batch.nr == 0) goto out; ret = btrfs_insert_empty_items(trans, log, dst_path, &batch); if (ret) goto out; dst_index = 0; for (int i = 0; i < nr; i++) { const int src_slot = start_slot + i; const int dst_slot = dst_path->slots[0] + dst_index; struct btrfs_key key; unsigned long src_offset; unsigned long dst_offset; /* * We're done, all the remaining items in the source leaf * correspond to old file extent items. */ if (dst_index >= batch.nr) break; btrfs_item_key_to_cpu(src, &key, src_slot); if (key.type != BTRFS_EXTENT_DATA_KEY) goto copy_item; extent = btrfs_item_ptr(src, src_slot, struct btrfs_file_extent_item); /* See the comment in the previous loop, same logic. */ if (btrfs_file_extent_generation(src, extent) < trans->transid && key.offset < i_size && inode->last_reflink_trans < trans->transid) continue; copy_item: dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0], dst_slot); src_offset = btrfs_item_ptr_offset(src, src_slot); if (key.type == BTRFS_INODE_ITEM_KEY) { struct btrfs_inode_item *inode_item; inode_item = btrfs_item_ptr(dst_path->nodes[0], dst_slot, struct btrfs_inode_item); fill_inode_item(trans, dst_path->nodes[0], inode_item, &inode->vfs_inode, inode_only == LOG_INODE_EXISTS, logged_isize); } else { copy_extent_buffer(dst_path->nodes[0], src, dst_offset, src_offset, ins_sizes[dst_index]); } dst_index++; } btrfs_release_path(dst_path); out: kfree(ins_data); return ret; } static int extent_cmp(void *priv, const struct list_head *a, const struct list_head *b) { const struct extent_map *em1, *em2; em1 = list_entry(a, struct extent_map, list); em2 = list_entry(b, struct extent_map, list); if (em1->start < em2->start) return -1; else if (em1->start > em2->start) return 1; return 0; } static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_root *log_root, const struct extent_map *em, struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_root *csum_root; u64 block_start; u64 csum_offset; u64 csum_len; u64 mod_start = em->start; u64 mod_len = em->len; LIST_HEAD(ordered_sums); int ret = 0; if (inode->flags & BTRFS_INODE_NODATASUM || (em->flags & EXTENT_FLAG_PREALLOC) || em->disk_bytenr == EXTENT_MAP_HOLE) return 0; list_for_each_entry(ordered, &ctx->ordered_extents, log_list) { const u64 ordered_end = ordered->file_offset + ordered->num_bytes; const u64 mod_end = mod_start + mod_len; struct btrfs_ordered_sum *sums; if (mod_len == 0) break; if (ordered_end <= mod_start) continue; if (mod_end <= ordered->file_offset) break; /* * We are going to copy all the csums on this ordered extent, so * go ahead and adjust mod_start and mod_len in case this ordered * extent has already been logged. */ if (ordered->file_offset > mod_start) { if (ordered_end >= mod_end) mod_len = ordered->file_offset - mod_start; /* * If we have this case * * |--------- logged extent ---------| * |----- ordered extent ----| * * Just don't mess with mod_start and mod_len, we'll * just end up logging more csums than we need and it * will be ok. */ } else { if (ordered_end < mod_end) { mod_len = mod_end - ordered_end; mod_start = ordered_end; } else { mod_len = 0; } } /* * To keep us from looping for the above case of an ordered * extent that falls inside of the logged extent. */ if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM, &ordered->flags)) continue; list_for_each_entry(sums, &ordered->list, list) { ret = log_csums(trans, inode, log_root, sums); if (ret) return ret; } } /* We're done, found all csums in the ordered extents. */ if (mod_len == 0) return 0; /* If we're compressed we have to save the entire range of csums. */ if (btrfs_extent_map_is_compressed(em)) { csum_offset = 0; csum_len = em->disk_num_bytes; } else { csum_offset = mod_start - em->start; csum_len = mod_len; } /* block start is already adjusted for the file extent offset. */ block_start = btrfs_extent_map_block_start(em); csum_root = btrfs_csum_root(trans->fs_info, block_start); ret = btrfs_lookup_csums_list(csum_root, block_start + csum_offset, block_start + csum_offset + csum_len - 1, &ordered_sums, false); if (ret < 0) return ret; ret = 0; while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums = list_first_entry(&ordered_sums, struct btrfs_ordered_sum, list); if (!ret) ret = log_csums(trans, inode, log_root, sums); list_del(&sums->list); kfree(sums); } return ret; } static int log_one_extent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, const struct extent_map *em, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item fi = { 0 }; struct extent_buffer *leaf; struct btrfs_key key; enum btrfs_compression_type compress_type; u64 extent_offset = em->offset; u64 block_start = btrfs_extent_map_block_start(em); u64 block_len; int ret; btrfs_set_stack_file_extent_generation(&fi, trans->transid); if (em->flags & EXTENT_FLAG_PREALLOC) btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_PREALLOC); else btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_REG); block_len = em->disk_num_bytes; compress_type = btrfs_extent_map_compression(em); if (compress_type != BTRFS_COMPRESS_NONE) { btrfs_set_stack_file_extent_disk_bytenr(&fi, block_start); btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len); } else if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) { btrfs_set_stack_file_extent_disk_bytenr(&fi, block_start - extent_offset); btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len); } btrfs_set_stack_file_extent_offset(&fi, extent_offset); btrfs_set_stack_file_extent_num_bytes(&fi, em->len); btrfs_set_stack_file_extent_ram_bytes(&fi, em->ram_bytes); btrfs_set_stack_file_extent_compression(&fi, compress_type); ret = log_extent_csums(trans, inode, log, em, ctx); if (ret) return ret; /* * If this is the first time we are logging the inode in the current * transaction, we can avoid btrfs_drop_extents(), which is expensive * because it does a deletion search, which always acquires write locks * for extent buffers at levels 2, 1 and 0. This not only wastes time * but also adds significant contention in a log tree, since log trees * are small, with a root at level 2 or 3 at most, due to their short * life span. */ if (ctx->logged_before) { drop_args.path = path; drop_args.start = em->start; drop_args.end = em->start + em->len; drop_args.replace_extent = true; drop_args.extent_item_size = sizeof(fi); ret = btrfs_drop_extents(trans, log, inode, &drop_args); if (ret) return ret; } if (!drop_args.extent_inserted) { key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = em->start; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(fi)); if (ret) return ret; } leaf = path->nodes[0]; write_extent_buffer(leaf, &fi, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(fi)); btrfs_release_path(path); return ret; } /* * Log all prealloc extents beyond the inode's i_size to make sure we do not * lose them after doing a full/fast fsync and replaying the log. We scan the * subvolume's root instead of iterating the inode's extent map tree because * otherwise we can log incorrect extent items based on extent map conversion. * That can happen due to the fact that extent maps are merged when they * are not in the extent map tree's list of modified extents. */ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct btrfs_key key; const u64 i_size = i_size_read(&inode->vfs_inode); const u64 ino = btrfs_ino(inode); BTRFS_PATH_AUTO_FREE(dst_path); bool dropped_extents = false; u64 truncate_offset = i_size; struct extent_buffer *leaf; int slot; int ins_nr = 0; int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) return 0; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = i_size; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; /* * We must check if there is a prealloc extent that starts before the * i_size and crosses the i_size boundary. This is to ensure later we * truncate down to the end of that extent and not to the i_size, as * otherwise we end up losing part of the prealloc extent after a log * replay and with an implicit hole if there is another prealloc extent * that starts at an offset beyond i_size. */ ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY); if (ret < 0) goto out; if (ret == 0) { struct btrfs_file_extent_item *ei; leaf = path->nodes[0]; slot = path->slots[0]; ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_PREALLOC) { u64 extent_end; btrfs_item_key_to_cpu(leaf, &key, slot); extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, ei); if (extent_end > i_size) truncate_offset = extent_end; } } else { ret = 0; } while (true) { leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) goto out; ins_nr = 0; } ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; if (ret > 0) { ret = 0; break; } continue; } btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid > ino) break; if (WARN_ON_ONCE(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY || key.offset < i_size) { path->slots[0]++; continue; } /* * Avoid overlapping items in the log tree. The first time we * get here, get rid of everything from a past fsync. After * that, if the current extent starts before the end of the last * extent we copied, truncate the last one. This can happen if * an ordered extent completion modifies the subvolume tree * while btrfs_next_leaf() has the tree unlocked. */ if (!dropped_extents || key.offset < truncate_offset) { ret = truncate_inode_items(trans, root->log_root, inode, min(key.offset, truncate_offset), BTRFS_EXTENT_DATA_KEY); if (ret) goto out; dropped_extents = true; } truncate_offset = btrfs_file_extent_end(path); if (ins_nr == 0) start_slot = slot; ins_nr++; path->slots[0]++; if (!dst_path) { dst_path = btrfs_alloc_path(); if (!dst_path) { ret = -ENOMEM; goto out; } } } if (ins_nr > 0) ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); out: btrfs_release_path(path); return ret; } static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; struct extent_map *em, *n; LIST_HEAD(extents); struct extent_map_tree *tree = &inode->extent_tree; int ret = 0; int num = 0; write_lock(&tree->lock); list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we * have a bunch of extents we just want to commit since it will * be faster. */ if (++num > 32768) { list_del_init(&tree->modified_extents); ret = -EFBIG; goto process; } if (em->generation < trans->transid) continue; /* We log prealloc extents beyond eof later. */ if ((em->flags & EXTENT_FLAG_PREALLOC) && em->start >= i_size_read(&inode->vfs_inode)) continue; /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); em->flags |= EXTENT_FLAG_LOGGING; list_add_tail(&em->list, &extents); num++; } list_sort(NULL, &extents, extent_cmp); process: while (!list_empty(&extents)) { em = list_first_entry(&extents, struct extent_map, list); list_del_init(&em->list); /* * If we had an error we just need to delete everybody from our * private list. */ if (ret) { btrfs_clear_em_logging(inode, em); btrfs_free_extent_map(em); continue; } write_unlock(&tree->lock); ret = log_one_extent(trans, inode, em, path, ctx); write_lock(&tree->lock); btrfs_clear_em_logging(inode, em); btrfs_free_extent_map(em); } WARN_ON(!list_empty(&extents)); write_unlock(&tree->lock); if (!ret) ret = btrfs_log_prealloc_extents(trans, inode, path, ctx); if (ret) return ret; /* * We have logged all extents successfully, now make sure the commit of * the current transaction waits for the ordered extents to complete * before it commits and wipes out the log trees, otherwise we would * lose data if an ordered extents completes after the transaction * commits and a power failure happens after the transaction commit. */ list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags); if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { spin_lock_irq(&inode->ordered_tree_lock); if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { set_bit(BTRFS_ORDERED_PENDING, &ordered->flags); atomic_inc(&trans->transaction->pending_ordered); } spin_unlock_irq(&inode->ordered_tree_lock); } btrfs_put_ordered_extent(ordered); } return 0; } static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, struct btrfs_path *path, u64 *size_ret) { struct btrfs_key key; int ret; key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, log, &key, path, 0, 0); if (ret < 0) { return ret; } else if (ret > 0) { *size_ret = 0; } else { struct btrfs_inode_item *item; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); *size_ret = btrfs_inode_size(path->nodes[0], item); /* * If the in-memory inode's i_size is smaller then the inode * size stored in the btree, return the inode's i_size, so * that we get a correct inode size after replaying the log * when before a power failure we had a shrinking truncate * followed by addition of a new name (rename / new hard link). * Otherwise return the inode size from the btree, to avoid * data loss when replaying a log due to previously doing a * write that expands the inode's size and logging a new name * immediately after. */ if (*size_ret > inode->vfs_inode.i_size) *size_ret = inode->vfs_inode.i_size; } btrfs_release_path(path); return 0; } /* * At the moment we always log all xattrs. This is to figure out at log replay * time which xattrs must have their deletion replayed. If a xattr is missing * in the log tree and exists in the fs/subvol tree, we delete it. This is * because if a xattr is deleted, the inode is fsynced and a power failure * happens, causing the log to be replayed the next time the fs is mounted, * we want the xattr to not exist anymore (same behaviour as other filesystems * with a journal, ext3/4, xfs, f2fs, etc). */ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; int ret; struct btrfs_key key; const u64 ino = btrfs_ino(inode); int ins_nr = 0; int start_slot = 0; bool found_xattrs = false; if (test_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags)) return 0; key.objectid = ino; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { int slot = path->slots[0]; struct extent_buffer *leaf = path->nodes[0]; int nritems = btrfs_header_nritems(leaf); if (slot >= nritems) { if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) return ret; ins_nr = 0; } ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) break; if (ins_nr == 0) start_slot = slot; ins_nr++; path->slots[0]++; found_xattrs = true; cond_resched(); } if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) return ret; } if (!found_xattrs) set_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags); return 0; } /* * When using the NO_HOLES feature if we punched a hole that causes the * deletion of entire leafs or all the extent items of the first leaf (the one * that contains the inode item and references) we may end up not processing * any extents, because there are no leafs with a generation matching the * current transaction that have extent items for our inode. So we need to find * if any holes exist and then log them. We also need to log holes after any * truncate operation that changes the inode's size. */ static int btrfs_log_holes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; const u64 ino = btrfs_ino(inode); const u64 i_size = i_size_read(&inode->vfs_inode); u64 prev_extent_end = 0; int ret; if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0) return 0; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { struct extent_buffer *leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; if (ret > 0) { ret = 0; break; } leaf = path->nodes[0]; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) break; /* We have a hole, log it. */ if (prev_extent_end < key.offset) { const u64 hole_len = key.offset - prev_extent_end; /* * Release the path to avoid deadlocks with other code * paths that search the root while holding locks on * leafs from the log root. */ btrfs_release_path(path); ret = btrfs_insert_hole_extent(trans, root->log_root, ino, prev_extent_end, hole_len); if (ret < 0) return ret; /* * Search for the same key again in the root. Since it's * an extent item and we are holding the inode lock, the * key must still exist. If it doesn't just emit warning * and return an error to fall back to a transaction * commit. */ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; if (WARN_ON(ret > 0)) return -ENOENT; leaf = path->nodes[0]; } prev_extent_end = btrfs_file_extent_end(path); path->slots[0]++; cond_resched(); } if (prev_extent_end < i_size) { u64 hole_len; btrfs_release_path(path); hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize); ret = btrfs_insert_hole_extent(trans, root->log_root, ino, prev_extent_end, hole_len); if (ret < 0) return ret; } return 0; } /* * When we are logging a new inode X, check if it doesn't have a reference that * matches the reference from some other inode Y created in a past transaction * and that was renamed in the current transaction. If we don't do this, then at * log replay time we can lose inode Y (and all its files if it's a directory): * * mkdir /mnt/x * echo "hello world" > /mnt/x/foobar * sync * mv /mnt/x /mnt/y * mkdir /mnt/x # or touch /mnt/x * xfs_io -c fsync /mnt/x * <power fail> * mount fs, trigger log replay * * After the log replay procedure, we would lose the first directory and all its * files (file foobar). * For the case where inode Y is not a directory we simply end up losing it: * * echo "123" > /mnt/foo * sync * mv /mnt/foo /mnt/bar * echo "abc" > /mnt/foo * xfs_io -c fsync /mnt/foo * <power fail> * * We also need this for cases where a snapshot entry is replaced by some other * entry (file or directory) otherwise we end up with an unreplayable log due to * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as * if it were a regular entry: * * mkdir /mnt/x * btrfs subvolume snapshot /mnt /mnt/x/snap * btrfs subvolume delete /mnt/x/snap * rmdir /mnt/x * mkdir /mnt/x * fsync /mnt/x or fsync some new file inside it * <power fail> * * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in * the same transaction. */ static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, struct btrfs_inode *inode, u64 *other_ino, u64 *other_parent) { int ret; BTRFS_PATH_AUTO_FREE(search_path); char *name = NULL; u32 name_len = 0; u32 item_size = btrfs_item_size(eb, slot); u32 cur_offset = 0; unsigned long ptr = btrfs_item_ptr_offset(eb, slot); search_path = btrfs_alloc_path(); if (!search_path) return -ENOMEM; search_path->search_commit_root = 1; search_path->skip_locking = 1; while (cur_offset < item_size) { u64 parent; u32 this_name_len; u32 this_len; unsigned long name_ptr; struct btrfs_dir_item *di; struct fscrypt_str name_str; if (key->type == BTRFS_INODE_REF_KEY) { struct btrfs_inode_ref *iref; iref = (struct btrfs_inode_ref *)(ptr + cur_offset); parent = key->offset; this_name_len = btrfs_inode_ref_name_len(eb, iref); name_ptr = (unsigned long)(iref + 1); this_len = sizeof(*iref) + this_name_len; } else { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *)(ptr + cur_offset); parent = btrfs_inode_extref_parent(eb, extref); this_name_len = btrfs_inode_extref_name_len(eb, extref); name_ptr = (unsigned long)&extref->name; this_len = sizeof(*extref) + this_name_len; } if (this_name_len > name_len) { char *new_name; new_name = krealloc(name, this_name_len, GFP_NOFS); if (!new_name) { ret = -ENOMEM; goto out; } name_len = this_name_len; name = new_name; } read_extent_buffer(eb, name, name_ptr, this_name_len); name_str.name = name; name_str.len = this_name_len; di = btrfs_lookup_dir_item(NULL, inode->root, search_path, parent, &name_str, 0); if (di && !IS_ERR(di)) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(search_path->nodes[0], di, &di_key); if (di_key.type == BTRFS_INODE_ITEM_KEY) { if (di_key.objectid != key->objectid) { ret = 1; *other_ino = di_key.objectid; *other_parent = parent; } else { ret = 0; } } else { ret = -EAGAIN; } goto out; } else if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } btrfs_release_path(search_path); cur_offset += this_len; } ret = 0; out: kfree(name); return ret; } /* * Check if we need to log an inode. This is used in contexts where while * logging an inode we need to log another inode (either that it exists or in * full mode). This is used instead of btrfs_inode_in_log() because the later * requires the inode to be in the log and have the log transaction committed, * while here we do not care if the log transaction was already committed - our * caller will commit the log later - and we want to avoid logging an inode * multiple times when multiple tasks have joined the same log transaction. */ static bool need_log_inode(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { /* * If a directory was not modified, no dentries added or removed, we can * and should avoid logging it. */ if (S_ISDIR(inode->vfs_inode.i_mode) && inode->last_trans < trans->transid) return false; /* * If this inode does not have new/updated/deleted xattrs since the last * time it was logged and is flagged as logged in the current transaction, * we can skip logging it. As for new/deleted names, those are updated in * the log by link/unlink/rename operations. * In case the inode was logged and then evicted and reloaded, its * logged_trans will be 0, in which case we have to fully log it since * logged_trans is a transient field, not persisted. */ if (inode_logged(trans, inode, NULL) == 1 && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return false; return true; } struct btrfs_dir_list { u64 ino; struct list_head list; }; /* * Log the inodes of the new dentries of a directory. * See process_dir_items_leaf() for details about why it is needed. * This is a recursive operation - if an existing dentry corresponds to a * directory, that directory's new entries are logged too (same behaviour as * ext3/4, xfs, f2fs, nilfs2). Note that when logging the inodes * the dentries point to we do not acquire their VFS lock, otherwise lockdep * complains about the following circular lock dependency / possible deadlock: * * CPU0 CPU1 * ---- ---- * lock(&type->i_mutex_dir_key#3/2); * lock(sb_internal#2); * lock(&type->i_mutex_dir_key#3/2); * lock(&sb->s_type->i_mutex_key#14); * * Where sb_internal is the lock (a counter that works as a lock) acquired by * sb_start_intwrite() in btrfs_start_transaction(). * Not acquiring the VFS lock of the inodes is still safe because: * * 1) For regular files we log with a mode of LOG_INODE_EXISTS. It's possible * that while logging the inode new references (names) are added or removed * from the inode, leaving the logged inode item with a link count that does * not match the number of logged inode reference items. This is fine because * at log replay time we compute the real number of links and correct the * link count in the inode item (see replay_one_buffer() and * link_to_fixup_dir()); * * 2) For directories we log with a mode of LOG_INODE_ALL. It's possible that * while logging the inode's items new index items (key type * BTRFS_DIR_INDEX_KEY) are added to fs/subvol tree and the logged inode item * has a size that doesn't match the sum of the lengths of all the logged * names - this is ok, not a problem, because at log replay time we set the * directory's i_size to the correct value (see replay_one_name() and * overwrite_item()). */ static int log_new_dir_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *start_inode, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = start_inode->root; struct btrfs_path *path; LIST_HEAD(dir_list); struct btrfs_dir_list *dir_elem; u64 ino = btrfs_ino(start_inode); struct btrfs_inode *curr_inode = start_inode; int ret = 0; /* * If we are logging a new name, as part of a link or rename operation, * don't bother logging new dentries, as we just want to log the names * of an inode and that any new parents exist. */ if (ctx->logging_new_name) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* Pairs with btrfs_add_delayed_iput below. */ ihold(&curr_inode->vfs_inode); while (true) { struct btrfs_key key; struct btrfs_key found_key; u64 next_index; bool continue_curr_inode = true; int iter_ret; key.objectid = ino; key.type = BTRFS_DIR_INDEX_KEY; key.offset = btrfs_get_first_dir_index_to_log(curr_inode); next_index = key.offset; again: btrfs_for_each_slot(root->log_root, &key, &found_key, path, iter_ret) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_dir_item *di; struct btrfs_key di_key; struct btrfs_inode *di_inode; int log_mode = LOG_INODE_EXISTS; int type; if (found_key.objectid != ino || found_key.type != BTRFS_DIR_INDEX_KEY) { continue_curr_inode = false; break; } next_index = found_key.offset + 1; di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); type = btrfs_dir_ftype(leaf, di); if (btrfs_dir_transid(leaf, di) < trans->transid) continue; btrfs_dir_item_key_to_cpu(leaf, di, &di_key); if (di_key.type == BTRFS_ROOT_ITEM_KEY) continue; btrfs_release_path(path); di_inode = btrfs_iget_logging(di_key.objectid, root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); goto out; } if (!need_log_inode(trans, di_inode)) { btrfs_add_delayed_iput(di_inode); break; } ctx->log_new_dentries = false; if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, di_inode, log_mode, ctx); btrfs_add_delayed_iput(di_inode); if (ret) goto out; if (ctx->log_new_dentries) { dir_elem = kmalloc(sizeof(*dir_elem), GFP_NOFS); if (!dir_elem) { ret = -ENOMEM; goto out; } dir_elem->ino = di_key.objectid; list_add_tail(&dir_elem->list, &dir_list); } break; } btrfs_release_path(path); if (iter_ret < 0) { ret = iter_ret; goto out; } else if (iter_ret > 0) { continue_curr_inode = false; } else { key = found_key; } if (continue_curr_inode && key.offset < (u64)-1) { key.offset++; goto again; } btrfs_set_first_dir_index_to_log(curr_inode, next_index); if (list_empty(&dir_list)) break; dir_elem = list_first_entry(&dir_list, struct btrfs_dir_list, list); ino = dir_elem->ino; list_del(&dir_elem->list); kfree(dir_elem); btrfs_add_delayed_iput(curr_inode); curr_inode = btrfs_iget_logging(ino, root); if (IS_ERR(curr_inode)) { ret = PTR_ERR(curr_inode); curr_inode = NULL; break; } } out: btrfs_free_path(path); if (curr_inode) btrfs_add_delayed_iput(curr_inode); if (ret) { struct btrfs_dir_list *next; list_for_each_entry_safe(dir_elem, next, &dir_list, list) kfree(dir_elem); } return ret; } struct btrfs_ino_list { u64 ino; u64 parent; struct list_head list; }; static void free_conflicting_inodes(struct btrfs_log_ctx *ctx) { struct btrfs_ino_list *curr; struct btrfs_ino_list *next; list_for_each_entry_safe(curr, next, &ctx->conflict_inodes, list) { list_del(&curr->list); kfree(curr); } } static int conflicting_inode_is_dir(struct btrfs_root *root, u64 ino, struct btrfs_path *path) { struct btrfs_key key; int ret; key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; path->search_commit_root = 1; path->skip_locking = 1; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (WARN_ON_ONCE(ret > 0)) { /* * We have previously found the inode through the commit root * so this should not happen. If it does, just error out and * fallback to a transaction commit. */ ret = -ENOENT; } else if (ret == 0) { struct btrfs_inode_item *item; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); if (S_ISDIR(btrfs_inode_mode(path->nodes[0], item))) ret = 1; } btrfs_release_path(path); path->search_commit_root = 0; path->skip_locking = 0; return ret; } static int add_conflicting_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 ino, u64 parent, struct btrfs_log_ctx *ctx) { struct btrfs_ino_list *ino_elem; struct btrfs_inode *inode; /* * It's rare to have a lot of conflicting inodes, in practice it is not * common to have more than 1 or 2. We don't want to collect too many, * as we could end up logging too many inodes (even if only in * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction * commits. */ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) return BTRFS_LOG_FORCE_COMMIT; inode = btrfs_iget_logging(ino, root); /* * If the other inode that had a conflicting dir entry was deleted in * the current transaction then we either: * * 1) Log the parent directory (later after adding it to the list) if * the inode is a directory. This is because it may be a deleted * subvolume/snapshot or it may be a regular directory that had * deleted subvolumes/snapshots (or subdirectories that had them), * and at the moment we can't deal with dropping subvolumes/snapshots * during log replay. So we just log the parent, which will result in * a fallback to a transaction commit if we are dealing with those * cases (last_unlink_trans will match the current transaction); * * 2) Do nothing if it's not a directory. During log replay we simply * unlink the conflicting dentry from the parent directory and then * add the dentry for our inode. Like this we can avoid logging the * parent directory (and maybe fallback to a transaction commit in * case it has a last_unlink_trans == trans->transid, due to moving * some inode from it to some other directory). */ if (IS_ERR(inode)) { int ret = PTR_ERR(inode); if (ret != -ENOENT) return ret; ret = conflicting_inode_is_dir(root, ino, path); /* Not a directory or we got an error. */ if (ret <= 0) return ret; /* Conflicting inode is a directory, so we'll log its parent. */ ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); if (!ino_elem) return -ENOMEM; ino_elem->ino = ino; ino_elem->parent = parent; list_add_tail(&ino_elem->list, &ctx->conflict_inodes); ctx->num_conflict_inodes++; return 0; } /* * If the inode was already logged skip it - otherwise we can hit an * infinite loop. Example: * * From the commit root (previous transaction) we have the following * inodes: * * inode 257 a directory * inode 258 with references "zz" and "zz_link" on inode 257 * inode 259 with reference "a" on inode 257 * * And in the current (uncommitted) transaction we have: * * inode 257 a directory, unchanged * inode 258 with references "a" and "a2" on inode 257 * inode 259 with reference "zz_link" on inode 257 * inode 261 with reference "zz" on inode 257 * * When logging inode 261 the following infinite loop could * happen if we don't skip already logged inodes: * * - we detect inode 258 as a conflicting inode, with inode 261 * on reference "zz", and log it; * * - we detect inode 259 as a conflicting inode, with inode 258 * on reference "a", and log it; * * - we detect inode 258 as a conflicting inode, with inode 259 * on reference "zz_link", and log it - again! After this we * repeat the above steps forever. * * Here we can use need_log_inode() because we only need to log the * inode in LOG_INODE_EXISTS mode and rename operations update the log, * so that the log ends up with the new name and without the old name. */ if (!need_log_inode(trans, inode)) { btrfs_add_delayed_iput(inode); return 0; } btrfs_add_delayed_iput(inode); ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); if (!ino_elem) return -ENOMEM; ino_elem->ino = ino; ino_elem->parent = parent; list_add_tail(&ino_elem->list, &ctx->conflict_inodes); ctx->num_conflict_inodes++; return 0; } static int log_conflicting_inodes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { int ret = 0; /* * Conflicting inodes are logged by the first call to btrfs_log_inode(), * otherwise we could have unbounded recursion of btrfs_log_inode() * calls. This check guarantees we can have only 1 level of recursion. */ if (ctx->logging_conflict_inodes) return 0; ctx->logging_conflict_inodes = true; /* * New conflicting inodes may be found and added to the list while we * are logging a conflicting inode, so keep iterating while the list is * not empty. */ while (!list_empty(&ctx->conflict_inodes)) { struct btrfs_ino_list *curr; struct btrfs_inode *inode; u64 ino; u64 parent; curr = list_first_entry(&ctx->conflict_inodes, struct btrfs_ino_list, list); ino = curr->ino; parent = curr->parent; list_del(&curr->list); kfree(curr); inode = btrfs_iget_logging(ino, root); /* * If the other inode that had a conflicting dir entry was * deleted in the current transaction, we need to log its parent * directory. See the comment at add_conflicting_inode(). */ if (IS_ERR(inode)) { ret = PTR_ERR(inode); if (ret != -ENOENT) break; inode = btrfs_iget_logging(parent, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); break; } /* * Always log the directory, we cannot make this * conditional on need_log_inode() because the directory * might have been logged in LOG_INODE_EXISTS mode or * the dir index of the conflicting inode is not in a * dir index key range logged for the directory. So we * must make sure the deletion is recorded. */ ret = btrfs_log_inode(trans, inode, LOG_INODE_ALL, ctx); btrfs_add_delayed_iput(inode); if (ret) break; continue; } /* * Here we can use need_log_inode() because we only need to log * the inode in LOG_INODE_EXISTS mode and rename operations * update the log, so that the log ends up with the new name and * without the old name. * * We did this check at add_conflicting_inode(), but here we do * it again because if some other task logged the inode after * that, we can avoid doing it again. */ if (!need_log_inode(trans, inode)) { btrfs_add_delayed_iput(inode); continue; } /* * We are safe logging the other inode without acquiring its * lock as long as we log with the LOG_INODE_EXISTS mode. We * are safe against concurrent renames of the other inode as * well because during a rename we pin the log and update the * log with the new name before we unpin it. */ ret = btrfs_log_inode(trans, inode, LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(inode); if (ret) break; } ctx->logging_conflict_inodes = false; if (ret) free_conflicting_inodes(ctx); return ret; } static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_key *min_key, const struct btrfs_key *max_key, struct btrfs_path *path, struct btrfs_path *dst_path, const u64 logged_isize, const int inode_only, struct btrfs_log_ctx *ctx, bool *need_log_inode_item) { const u64 i_size = i_size_read(&inode->vfs_inode); struct btrfs_root *root = inode->root; int ins_start_slot = 0; int ins_nr = 0; int ret; while (1) { ret = btrfs_search_forward(root, min_key, path, trans->transid); if (ret < 0) return ret; if (ret > 0) { ret = 0; break; } again: /* Note, ins_nr might be > 0 here, cleanup outside the loop */ if (min_key->objectid != max_key->objectid) break; if (min_key->type > max_key->type) break; if (min_key->type == BTRFS_INODE_ITEM_KEY) { *need_log_inode_item = false; } else if (min_key->type == BTRFS_EXTENT_DATA_KEY && min_key->offset >= i_size) { /* * Extents at and beyond eof are logged with * btrfs_log_prealloc_extents(). * Only regular files have BTRFS_EXTENT_DATA_KEY keys, * and no keys greater than that, so bail out. */ break; } else if ((min_key->type == BTRFS_INODE_REF_KEY || min_key->type == BTRFS_INODE_EXTREF_KEY) && (inode->generation == trans->transid || ctx->logging_conflict_inodes)) { u64 other_ino = 0; u64 other_parent = 0; ret = btrfs_check_ref_name_override(path->nodes[0], path->slots[0], min_key, inode, &other_ino, &other_parent); if (ret < 0) { return ret; } else if (ret > 0 && other_ino != btrfs_ino(ctx->inode)) { if (ins_nr > 0) { ins_nr++; } else { ins_nr = 1; ins_start_slot = path->slots[0]; } ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; btrfs_release_path(path); ret = add_conflicting_inode(trans, root, path, other_ino, other_parent, ctx); if (ret) return ret; goto next_key; } } else if (min_key->type == BTRFS_XATTR_ITEM_KEY) { /* Skip xattrs, logged later with btrfs_log_all_xattrs() */ if (ins_nr == 0) goto next_slot; ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; goto next_slot; } if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { ins_nr++; goto next_slot; } else if (!ins_nr) { ins_start_slot = path->slots[0]; ins_nr = 1; goto next_slot; } ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 1; ins_start_slot = path->slots[0]; next_slot: path->slots[0]++; if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { btrfs_item_key_to_cpu(path->nodes[0], min_key, path->slots[0]); goto again; } if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; } btrfs_release_path(path); next_key: if (min_key->offset < (u64)-1) { min_key->offset++; } else if (min_key->type < max_key->type) { min_key->type++; min_key->offset = 0; } else { break; } /* * We may process many leaves full of items for our inode, so * avoid monopolizing a cpu for too long by rescheduling while * not holding locks on any tree. */ cond_resched(); } if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret) return ret; } if (inode_only == LOG_INODE_ALL && S_ISREG(inode->vfs_inode.i_mode)) { /* * Release the path because otherwise we might attempt to double * lock the same leaf with btrfs_log_prealloc_extents() below. */ btrfs_release_path(path); ret = btrfs_log_prealloc_extents(trans, inode, dst_path, ctx); } return ret; } static int insert_delayed_items_batch(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, const struct btrfs_item_batch *batch, const struct btrfs_delayed_item *first_item) { const struct btrfs_delayed_item *curr = first_item; int ret; ret = btrfs_insert_empty_items(trans, log, path, batch); if (ret) return ret; for (int i = 0; i < batch->nr; i++) { char *data_ptr; data_ptr = btrfs_item_ptr(path->nodes[0], path->slots[0], char); write_extent_buffer(path->nodes[0], &curr->data, (unsigned long)data_ptr, curr->data_len); curr = list_next_entry(curr, log_list); path->slots[0]++; } btrfs_release_path(path); return 0; } static int log_delayed_insertion_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_ins_list, struct btrfs_log_ctx *ctx) { /* 195 (4095 bytes of keys and sizes) fits in a single 4K page. */ const int max_batch_size = 195; const int leaf_data_size = BTRFS_LEAF_DATA_SIZE(trans->fs_info); const u64 ino = btrfs_ino(inode); struct btrfs_root *log = inode->root->log_root; struct btrfs_item_batch batch = { .nr = 0, .total_data_size = 0, }; const struct btrfs_delayed_item *first = NULL; const struct btrfs_delayed_item *curr; char *ins_data; struct btrfs_key *ins_keys; u32 *ins_sizes; u64 curr_batch_size = 0; int batch_idx = 0; int ret; /* We are adding dir index items to the log tree. */ lockdep_assert_held(&inode->log_mutex); /* * We collect delayed items before copying index keys from the subvolume * to the log tree. However just after we collected them, they may have * been flushed (all of them or just some of them), and therefore we * could have copied them from the subvolume tree to the log tree. * So find the first delayed item that was not yet logged (they are * sorted by index number). */ list_for_each_entry(curr, delayed_ins_list, log_list) { if (curr->index > inode->last_dir_index_offset) { first = curr; break; } } /* Empty list or all delayed items were already logged. */ if (!first) return 0; ins_data = kmalloc_array(max_batch_size, sizeof(u32) + sizeof(struct btrfs_key), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; batch.data_sizes = ins_sizes; ins_keys = (struct btrfs_key *)(ins_data + max_batch_size * sizeof(u32)); batch.keys = ins_keys; curr = first; while (!list_entry_is_head(curr, delayed_ins_list, log_list)) { const u32 curr_size = curr->data_len + sizeof(struct btrfs_item); if (curr_batch_size + curr_size > leaf_data_size || batch.nr == max_batch_size) { ret = insert_delayed_items_batch(trans, log, path, &batch, first); if (ret) goto out; batch_idx = 0; batch.nr = 0; batch.total_data_size = 0; curr_batch_size = 0; first = curr; } ins_sizes[batch_idx] = curr->data_len; ins_keys[batch_idx].objectid = ino; ins_keys[batch_idx].type = BTRFS_DIR_INDEX_KEY; ins_keys[batch_idx].offset = curr->index; curr_batch_size += curr_size; batch.total_data_size += curr->data_len; batch.nr++; batch_idx++; curr = list_next_entry(curr, log_list); } ASSERT(batch.nr >= 1); ret = insert_delayed_items_batch(trans, log, path, &batch, first); curr = list_last_entry(delayed_ins_list, struct btrfs_delayed_item, log_list); inode->last_dir_index_offset = curr->index; out: kfree(ins_data); return ret; } static int log_delayed_deletions_full(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { const u64 ino = btrfs_ino(inode); const struct btrfs_delayed_item *curr; curr = list_first_entry(delayed_del_list, struct btrfs_delayed_item, log_list); while (!list_entry_is_head(curr, delayed_del_list, log_list)) { u64 first_dir_index = curr->index; u64 last_dir_index; const struct btrfs_delayed_item *next; int ret; /* * Find a range of consecutive dir index items to delete. Like * this we log a single dir range item spanning several contiguous * dir items instead of logging one range item per dir index item. */ next = list_next_entry(curr, log_list); while (!list_entry_is_head(next, delayed_del_list, log_list)) { if (next->index != curr->index + 1) break; curr = next; next = list_next_entry(next, log_list); } last_dir_index = curr->index; ASSERT(last_dir_index >= first_dir_index); ret = insert_dir_log_key(trans, inode->root->log_root, path, ino, first_dir_index, last_dir_index); if (ret) return ret; curr = list_next_entry(curr, log_list); } return 0; } static int batch_delete_dir_index_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, const struct btrfs_delayed_item *first, const struct btrfs_delayed_item **last_ret) { const struct btrfs_delayed_item *next; struct extent_buffer *leaf = path->nodes[0]; const int last_slot = btrfs_header_nritems(leaf) - 1; int slot = path->slots[0] + 1; const u64 ino = btrfs_ino(inode); next = list_next_entry(first, log_list); while (slot < last_slot && !list_entry_is_head(next, delayed_del_list, log_list)) { struct btrfs_key key; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino || key.type != BTRFS_DIR_INDEX_KEY || key.offset != next->index) break; slot++; *last_ret = next; next = list_next_entry(next, log_list); } return btrfs_del_items(trans, inode->root->log_root, path, path->slots[0], slot - path->slots[0]); } static int log_delayed_deletions_incremental(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { struct btrfs_root *log = inode->root->log_root; const struct btrfs_delayed_item *curr; u64 last_range_start = 0; u64 last_range_end = 0; struct btrfs_key key; key.objectid = btrfs_ino(inode); key.type = BTRFS_DIR_INDEX_KEY; curr = list_first_entry(delayed_del_list, struct btrfs_delayed_item, log_list); while (!list_entry_is_head(curr, delayed_del_list, log_list)) { const struct btrfs_delayed_item *last = curr; u64 first_dir_index = curr->index; u64 last_dir_index; bool deleted_items = false; int ret; key.offset = curr->index; ret = btrfs_search_slot(trans, log, &key, path, -1, 1); if (ret < 0) { return ret; } else if (ret == 0) { ret = batch_delete_dir_index_items(trans, inode, path, delayed_del_list, curr, &last); if (ret) return ret; deleted_items = true; } btrfs_release_path(path); /* * If we deleted items from the leaf, it means we have a range * item logging their range, so no need to add one or update an * existing one. Otherwise we have to log a dir range item. */ if (deleted_items) goto next_batch; last_dir_index = last->index; ASSERT(last_dir_index >= first_dir_index); /* * If this range starts right after where the previous one ends, * then we want to reuse the previous range item and change its * end offset to the end of this range. This is just to minimize * leaf space usage, by avoiding adding a new range item. */ if (last_range_end != 0 && first_dir_index == last_range_end + 1) first_dir_index = last_range_start; ret = insert_dir_log_key(trans, log, path, key.objectid, first_dir_index, last_dir_index); if (ret) return ret; last_range_start = first_dir_index; last_range_end = last_dir_index; next_batch: curr = list_next_entry(last, log_list); } return 0; } static int log_delayed_deletion_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { /* * We are deleting dir index items from the log tree or adding range * items to it. */ lockdep_assert_held(&inode->log_mutex); if (list_empty(delayed_del_list)) return 0; if (ctx->logged_before) return log_delayed_deletions_incremental(trans, inode, path, delayed_del_list, ctx); return log_delayed_deletions_full(trans, inode, path, delayed_del_list, ctx); } /* * Similar logic as for log_new_dir_dentries(), but it iterates over the delayed * items instead of the subvolume tree. */ static int log_new_delayed_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, const struct list_head *delayed_ins_list, struct btrfs_log_ctx *ctx) { const bool orig_log_new_dentries = ctx->log_new_dentries; struct btrfs_delayed_item *item; int ret = 0; /* * No need for the log mutex, plus to avoid potential deadlocks or * lockdep annotations due to nesting of delayed inode mutexes and log * mutexes. */ lockdep_assert_not_held(&inode->log_mutex); ASSERT(!ctx->logging_new_delayed_dentries); ctx->logging_new_delayed_dentries = true; list_for_each_entry(item, delayed_ins_list, log_list) { struct btrfs_dir_item *dir_item; struct btrfs_inode *di_inode; struct btrfs_key key; int log_mode = LOG_INODE_EXISTS; dir_item = (struct btrfs_dir_item *)item->data; btrfs_disk_key_to_cpu(&key, &dir_item->location); if (key.type == BTRFS_ROOT_ITEM_KEY) continue; di_inode = btrfs_iget_logging(key.objectid, inode->root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); break; } if (!need_log_inode(trans, di_inode)) { btrfs_add_delayed_iput(di_inode); continue; } if (btrfs_stack_dir_ftype(dir_item) == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, di_inode, log_mode, ctx); if (!ret && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, di_inode, ctx); btrfs_add_delayed_iput(di_inode); if (ret) break; } ctx->log_new_dentries = orig_log_new_dentries; ctx->logging_new_delayed_dentries = false; return ret; } /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. * * Any items from this inode changed by the current transaction are copied * to the log tree. An extra reference is taken on any extents in this * file, allowing us to avoid a whole pile of corner cases around logging * blocks that have been removed from the tree. * * See LOG_INODE_ALL and related defines for a description of what inode_only * does. * * This handles both files and directories. */ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, int inode_only, struct btrfs_log_ctx *ctx) { struct btrfs_path *path; struct btrfs_path *dst_path; struct btrfs_key min_key; struct btrfs_key max_key; struct btrfs_root *log = inode->root->log_root; int ret; bool fast_search = false; u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &inode->extent_tree; u64 logged_isize = 0; bool need_log_inode_item = true; bool xattrs_logged = false; bool inode_item_dropped = true; bool full_dir_logging = false; LIST_HEAD(delayed_ins_list); LIST_HEAD(delayed_del_list); path = btrfs_alloc_path(); if (!path) return -ENOMEM; dst_path = btrfs_alloc_path(); if (!dst_path) { btrfs_free_path(path); return -ENOMEM; } min_key.objectid = ino; min_key.type = BTRFS_INODE_ITEM_KEY; min_key.offset = 0; max_key.objectid = ino; /* today the code can only do partial logging of directories */ if (S_ISDIR(inode->vfs_inode.i_mode) || (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && inode_only >= LOG_INODE_EXISTS)) max_key.type = BTRFS_XATTR_ITEM_KEY; else max_key.type = (u8)-1; max_key.offset = (u64)-1; if (S_ISDIR(inode->vfs_inode.i_mode) && inode_only == LOG_INODE_ALL) full_dir_logging = true; /* * If we are logging a directory while we are logging dentries of the * delayed items of some other inode, then we need to flush the delayed * items of this directory and not log the delayed items directly. This * is to prevent more than one level of recursion into btrfs_log_inode() * by having something like this: * * $ mkdir -p a/b/c/d/e/f/g/h/... * $ xfs_io -c "fsync" a * * Where all directories in the path did not exist before and are * created in the current transaction. * So in such a case we directly log the delayed items of the main * directory ("a") without flushing them first, while for each of its * subdirectories we flush their delayed items before logging them. * This prevents a potential unbounded recursion like this: * * btrfs_log_inode() * log_new_delayed_dentries() * btrfs_log_inode() * log_new_delayed_dentries() * btrfs_log_inode() * log_new_delayed_dentries() * (...) * * We have thresholds for the maximum number of delayed items to have in * memory, and once they are hit, the items are flushed asynchronously. * However the limit is quite high, so lets prevent deep levels of * recursion to happen by limiting the maximum depth to be 1. */ if (full_dir_logging && ctx->logging_new_delayed_dentries) { ret = btrfs_commit_inode_delayed_items(trans, inode); if (ret) goto out; } mutex_lock(&inode->log_mutex); /* * For symlinks, we must always log their content, which is stored in an * inline extent, otherwise we could end up with an empty symlink after * log replay, which is invalid on linux (symlink(2) returns -ENOENT if * one attempts to create an empty symlink). * We don't need to worry about flushing delalloc, because when we create * the inline extent when the symlink is created (we never have delalloc * for symlinks). */ if (S_ISLNK(inode->vfs_inode.i_mode)) inode_only = LOG_INODE_ALL; /* * Before logging the inode item, cache the value returned by * inode_logged(), because after that we have the need to figure out if * the inode was previously logged in this transaction. */ ret = inode_logged(trans, inode, path); if (ret < 0) goto out_unlock; ctx->logged_before = (ret == 1); ret = 0; /* * This is for cases where logging a directory could result in losing a * a file after replaying the log. For example, if we move a file from a * directory A to a directory B, then fsync directory A, we have no way * to known the file was moved from A to B, so logging just A would * result in losing the file after a log replay. */ if (full_dir_logging && inode->last_unlink_trans >= trans->transid) { ret = BTRFS_LOG_FORCE_COMMIT; goto out_unlock; } /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ if (S_ISDIR(inode->vfs_inode.i_mode)) { clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, BTRFS_XATTR_ITEM_KEY); } else { if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) { /* * Make sure the new inode item we write to the log has * the same isize as the current one (if it exists). * This is necessary to prevent data loss after log * replay, and also to prevent doing a wrong expanding * truncate - for e.g. create file, write 4K into offset * 0, fsync, write 4K into offset 4096, add hard link, * fsync some other file (to sync log), power fail - if * we use the inode's current i_size, after log replay * we get a 8Kb file, with the last 4Kb extent as a hole * (zeroes), as if an expanding truncate happened, * instead of getting a file of 4Kb only. */ ret = logged_inode_size(log, inode, path, &logged_isize); if (ret) goto out_unlock; } if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) { if (inode_only == LOG_INODE_EXISTS) { max_key.type = BTRFS_XATTR_ITEM_KEY; if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, max_key.type); } else { clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (ctx->logged_before) ret = truncate_inode_items(trans, log, inode, 0, 0); } } else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags) || inode_only == LOG_INODE_EXISTS) { if (inode_only == LOG_INODE_ALL) fast_search = true; max_key.type = BTRFS_XATTR_ITEM_KEY; if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, max_key.type); } else { if (inode_only == LOG_INODE_ALL) fast_search = true; inode_item_dropped = false; goto log_extents; } } if (ret) goto out_unlock; /* * If we are logging a directory in full mode, collect the delayed items * before iterating the subvolume tree, so that we don't miss any new * dir index items in case they get flushed while or right after we are * iterating the subvolume tree. */ if (full_dir_logging && !ctx->logging_new_delayed_dentries) btrfs_log_get_delayed_items(inode, &delayed_ins_list, &delayed_del_list); /* * If we are fsyncing a file with 0 hard links, then commit the delayed * inode because the last inode ref (or extref) item may still be in the * subvolume tree and if we log it the file will still exist after a log * replay. So commit the delayed inode to delete that last ref and we * skip logging it. */ if (inode->vfs_inode.i_nlink == 0) { ret = btrfs_commit_inode_delayed_inode(inode); if (ret) goto out_unlock; } ret = copy_inode_items_to_log(trans, inode, &min_key, &max_key, path, dst_path, logged_isize, inode_only, ctx, &need_log_inode_item); if (ret) goto out_unlock; btrfs_release_path(path); btrfs_release_path(dst_path); ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; xattrs_logged = true; if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) { btrfs_release_path(path); btrfs_release_path(dst_path); ret = btrfs_log_holes(trans, inode, path); if (ret) goto out_unlock; } log_extents: btrfs_release_path(path); btrfs_release_path(dst_path); if (need_log_inode_item) { ret = log_inode_item(trans, log, dst_path, inode, inode_item_dropped); if (ret) goto out_unlock; /* * If we are doing a fast fsync and the inode was logged before * in this transaction, we don't need to log the xattrs because * they were logged before. If xattrs were added, changed or * deleted since the last time we logged the inode, then we have * already logged them because the inode had the runtime flag * BTRFS_INODE_COPY_EVERYTHING set. */ if (!xattrs_logged && inode->logged_trans < trans->transid) { ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; btrfs_release_path(path); } } if (fast_search) { ret = btrfs_log_changed_extents(trans, inode, dst_path, ctx); if (ret) goto out_unlock; } else if (inode_only == LOG_INODE_ALL) { struct extent_map *em, *n; write_lock(&em_tree->lock); list_for_each_entry_safe(em, n, &em_tree->modified_extents, list) list_del_init(&em->list); write_unlock(&em_tree->lock); } if (full_dir_logging) { ret = log_directory_changes(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; ret = log_delayed_insertion_items(trans, inode, path, &delayed_ins_list, ctx); if (ret) goto out_unlock; ret = log_delayed_deletion_items(trans, inode, path, &delayed_del_list, ctx); if (ret) goto out_unlock; } spin_lock(&inode->lock); inode->logged_trans = trans->transid; /* * Don't update last_log_commit if we logged that an inode exists. * We do this for three reasons: * * 1) We might have had buffered writes to this inode that were * flushed and had their ordered extents completed in this * transaction, but we did not previously log the inode with * LOG_INODE_ALL. Later the inode was evicted and after that * it was loaded again and this LOG_INODE_EXISTS log operation * happened. We must make sure that if an explicit fsync against * the inode is performed later, it logs the new extents, an * updated inode item, etc, and syncs the log. The same logic * applies to direct IO writes instead of buffered writes. * * 2) When we log the inode with LOG_INODE_EXISTS, its inode item * is logged with an i_size of 0 or whatever value was logged * before. If later the i_size of the inode is increased by a * truncate operation, the log is synced through an fsync of * some other inode and then finally an explicit fsync against * this inode is made, we must make sure this fsync logs the * inode with the new i_size, the hole between old i_size and * the new i_size, and syncs the log. * * 3) If we are logging that an ancestor inode exists as part of * logging a new name from a link or rename operation, don't update * its last_log_commit - otherwise if an explicit fsync is made * against an ancestor, the fsync considers the inode in the log * and doesn't sync the log, resulting in the ancestor missing after * a power failure unless the log was synced as part of an fsync * against any other unrelated inode. */ if (inode_only != LOG_INODE_EXISTS) inode->last_log_commit = inode->last_sub_trans; spin_unlock(&inode->lock); /* * Reset the last_reflink_trans so that the next fsync does not need to * go through the slower path when logging extents and their checksums. */ if (inode_only == LOG_INODE_ALL) inode->last_reflink_trans = 0; out_unlock: mutex_unlock(&inode->log_mutex); out: btrfs_free_path(path); btrfs_free_path(dst_path); if (ret) free_conflicting_inodes(ctx); else ret = log_conflicting_inodes(trans, inode->root, ctx); if (full_dir_logging && !ctx->logging_new_delayed_dentries) { if (!ret) ret = log_new_delayed_dentries(trans, inode, &delayed_ins_list, ctx); btrfs_log_put_delayed_items(inode, &delayed_ins_list, &delayed_del_list); } return ret; } static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_log_ctx *ctx) { int ret; BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct btrfs_root *root = inode->root; const u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) return -ENOMEM; path->skip_locking = 1; path->search_commit_root = 1; key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; u32 cur_offset = 0; u32 item_size; unsigned long ptr; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &key, slot); /* BTRFS_INODE_EXTREF_KEY is BTRFS_INODE_REF_KEY + 1 */ if (key.objectid != ino || key.type > BTRFS_INODE_EXTREF_KEY) break; item_size = btrfs_item_size(leaf, slot); ptr = btrfs_item_ptr_offset(leaf, slot); while (cur_offset < item_size) { struct btrfs_key inode_key; struct btrfs_inode *dir_inode; inode_key.type = BTRFS_INODE_ITEM_KEY; inode_key.offset = 0; if (key.type == BTRFS_INODE_EXTREF_KEY) { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *) (ptr + cur_offset); inode_key.objectid = btrfs_inode_extref_parent( leaf, extref); cur_offset += sizeof(*extref); cur_offset += btrfs_inode_extref_name_len(leaf, extref); } else { inode_key.objectid = key.offset; cur_offset = item_size; } dir_inode = btrfs_iget_logging(inode_key.objectid, root); /* * If the parent inode was deleted, return an error to * fallback to a transaction commit. This is to prevent * getting an inode that was moved from one parent A to * a parent B, got its former parent A deleted and then * it got fsync'ed, from existing at both parents after * a log replay (and the old parent still existing). * Example: * * mkdir /mnt/A * mkdir /mnt/B * touch /mnt/B/bar * sync * mv /mnt/B/bar /mnt/A/bar * mv -T /mnt/A /mnt/B * fsync /mnt/B/bar * <power fail> * * If we ignore the old parent B which got deleted, * after a log replay we would have file bar linked * at both parents and the old parent B would still * exist. */ if (IS_ERR(dir_inode)) return PTR_ERR(dir_inode); if (!need_log_inode(trans, dir_inode)) { btrfs_add_delayed_iput(dir_inode); continue; } ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, dir_inode, LOG_INODE_ALL, ctx); if (!ret && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, dir_inode, ctx); btrfs_add_delayed_iput(dir_inode); if (ret) return ret; } path->slots[0]++; } return 0; } static int log_new_ancestors(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_key found_key; btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); while (true) { struct extent_buffer *leaf; int slot; struct btrfs_key search_key; struct btrfs_inode *inode; u64 ino; int ret = 0; btrfs_release_path(path); ino = found_key.offset; search_key.objectid = found_key.offset; search_key.type = BTRFS_INODE_ITEM_KEY; search_key.offset = 0; inode = btrfs_iget_logging(ino, root); if (IS_ERR(inode)) return PTR_ERR(inode); if (inode->generation >= trans->transid && need_log_inode(trans, inode)) ret = btrfs_log_inode(trans, inode, LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(inode); if (ret) return ret; if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID) break; search_key.type = BTRFS_INODE_REF_KEY; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) return ret; leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) return -ENOENT; leaf = path->nodes[0]; slot = path->slots[0]; } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != search_key.objectid || found_key.type != BTRFS_INODE_REF_KEY) return -ENOENT; } return 0; } static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct dentry *old_parent = NULL; struct super_block *sb = inode->vfs_inode.i_sb; int ret = 0; while (true) { if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; inode = BTRFS_I(d_inode(parent)); if (root != inode->root) break; if (inode->generation >= trans->transid && need_log_inode(trans, inode)) { ret = btrfs_log_inode(trans, inode, LOG_INODE_EXISTS, ctx); if (ret) break; } if (IS_ROOT(parent)) break; parent = dget_parent(parent); dput(old_parent); old_parent = parent; } dput(old_parent); return ret; } static int log_all_new_ancestors(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; const u64 ino = btrfs_ino(inode); BTRFS_PATH_AUTO_FREE(path); struct btrfs_key search_key; int ret; /* * For a single hard link case, go through a fast path that does not * need to iterate the fs/subvolume tree. */ if (inode->vfs_inode.i_nlink < 2) return log_new_ancestors_fast(trans, inode, parent, ctx); path = btrfs_alloc_path(); if (!path) return -ENOMEM; search_key.objectid = ino; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = 0; again: ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) path->slots[0]++; while (true) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; struct btrfs_key found_key; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != ino || found_key.type > BTRFS_INODE_EXTREF_KEY) break; /* * Don't deal with extended references because they are rare * cases and too complex to deal with (we would need to keep * track of which subitem we are processing for each item in * this loop, etc). So just return some error to fallback to * a transaction commit. */ if (found_key.type == BTRFS_INODE_EXTREF_KEY) return -EMLINK; /* * Logging ancestors needs to do more searches on the fs/subvol * tree, so it releases the path as needed to avoid deadlocks. * Keep track of the last inode ref key and resume from that key * after logging all new ancestors for the current hard link. */ memcpy(&search_key, &found_key, sizeof(search_key)); ret = log_new_ancestors(trans, root, path, ctx); if (ret) return ret; btrfs_release_path(path); goto again; } return 0; } /* * helper function around btrfs_log_inode to make sure newly created * parent directories also end up in the log. A minimal inode and backref * only logging is done of any parent directories that are older than * the last committed transaction */ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, int inode_only, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; bool log_dentries; if (btrfs_test_opt(fs_info, NOTREELOG)) return BTRFS_LOG_FORCE_COMMIT; if (btrfs_root_refs(&root->root_item) == 0) return BTRFS_LOG_FORCE_COMMIT; /* * If we're logging an inode from a subvolume created in the current * transaction we must force a commit since the root is not persisted. */ if (btrfs_root_generation(&root->root_item) == trans->transid) return BTRFS_LOG_FORCE_COMMIT; /* Skip already logged inodes and without new extents. */ if (btrfs_inode_in_log(inode, trans->transid) && list_empty(&ctx->ordered_extents)) return BTRFS_NO_LOG_SYNC; ret = start_log_trans(trans, root, ctx); if (ret) return ret; ret = btrfs_log_inode(trans, inode, inode_only, ctx); if (ret) goto end_trans; /* * for regular files, if its inode is already on disk, we don't * have to worry about the parents at all. This is because * we can use the last_unlink_trans field to record renames * and other fun in this file. */ if (S_ISREG(inode->vfs_inode.i_mode) && inode->generation < trans->transid && inode->last_unlink_trans < trans->transid) { ret = 0; goto end_trans; } /* * Track if we need to log dentries because ctx->log_new_dentries can * be modified in the call chains below. */ log_dentries = ctx->log_new_dentries; /* * On unlink we must make sure all our current and old parent directory * inodes are fully logged. This is to prevent leaving dangling * directory index entries in directories that were our parents but are * not anymore. Not doing this results in old parent directory being * impossible to delete after log replay (rmdir will always fail with * error -ENOTEMPTY). * * Example 1: * * mkdir testdir * touch testdir/foo * ln testdir/foo testdir/bar * sync * unlink testdir/bar * xfs_io -c fsync testdir/foo * <power failure> * mount fs, triggers log replay * * If we don't log the parent directory (testdir), after log replay the * directory still has an entry pointing to the file inode using the bar * name, but a matching BTRFS_INODE_[REF|EXTREF]_KEY does not exist and * the file inode has a link count of 1. * * Example 2: * * mkdir testdir * touch foo * ln foo testdir/foo2 * ln foo testdir/foo3 * sync * unlink testdir/foo3 * xfs_io -c fsync foo * <power failure> * mount fs, triggers log replay * * Similar as the first example, after log replay the parent directory * testdir still has an entry pointing to the inode file with name foo3 * but the file inode does not have a matching BTRFS_INODE_REF_KEY item * and has a link count of 2. */ if (inode->last_unlink_trans >= trans->transid) { ret = btrfs_log_all_parents(trans, inode, ctx); if (ret) goto end_trans; } ret = log_all_new_ancestors(trans, inode, parent, ctx); if (ret) goto end_trans; if (log_dentries) ret = log_new_dir_dentries(trans, inode, ctx); end_trans: if (ret < 0) { btrfs_set_log_full_commit(trans); ret = BTRFS_LOG_FORCE_COMMIT; } if (ret) btrfs_remove_log_ctx(root, ctx); btrfs_end_log_trans(root); return ret; } /* * it is not safe to log dentry if the chunk root has added new * chunks. This returns 0 if the dentry was logged, and 1 otherwise. * If this returns 1, you must commit the transaction to safely get your * data on disk. */ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct dentry *dentry, struct btrfs_log_ctx *ctx) { struct dentry *parent = dget_parent(dentry); int ret; ret = btrfs_log_inode_parent(trans, BTRFS_I(d_inode(dentry)), parent, LOG_INODE_ALL, ctx); dput(parent); return ret; } /* * should be called during mount to recover any replay any log trees * from the FS */ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) { int ret; struct btrfs_path *path; struct btrfs_trans_handle *trans; struct btrfs_key key; struct btrfs_fs_info *fs_info = log_root_tree->fs_info; struct walk_control wc = { .process_func = process_one_buffer, .stage = LOG_WALK_PIN_ONLY, }; path = btrfs_alloc_path(); if (!path) return -ENOMEM; set_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); trans = btrfs_start_transaction(fs_info->tree_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto error; } wc.trans = trans; wc.pin = true; wc.log = log_root_tree; ret = walk_log_tree(&wc); wc.log = NULL; if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto error; } again: key.objectid = BTRFS_TREE_LOG_OBJECTID; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; while (1) { struct btrfs_key found_key; ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto error; } if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); btrfs_release_path(path); if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID) break; wc.log = btrfs_read_tree_root(log_root_tree, &found_key); if (IS_ERR(wc.log)) { ret = PTR_ERR(wc.log); wc.log = NULL; btrfs_abort_transaction(trans, ret); goto error; } wc.root = btrfs_get_fs_root(fs_info, found_key.offset, true); if (IS_ERR(wc.root)) { ret = PTR_ERR(wc.root); wc.root = NULL; if (unlikely(ret != -ENOENT)) { btrfs_abort_transaction(trans, ret); goto error; } /* * We didn't find the subvol, likely because it was * deleted. This is ok, simply skip this log and go to * the next one. * * We need to exclude the root because we can't have * other log replays overwriting this log as we'll read * it back in a few more times. This will keep our * block from being modified, and we'll just bail for * each subsequent pass. */ ret = btrfs_pin_extent_for_log_replay(trans, wc.log->node); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto error; } goto next; } wc.root->log_root = wc.log; ret = btrfs_record_root_in_trans(trans, wc.root); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto next; } ret = walk_log_tree(&wc); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto next; } if (wc.stage == LOG_WALK_REPLAY_ALL) { struct btrfs_root *root = wc.root; wc.subvol_path = path; ret = fixup_inode_link_counts(&wc); wc.subvol_path = NULL; if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto next; } /* * We have just replayed everything, and the highest * objectid of fs roots probably has changed in case * some inode_item's got replayed. * * root->objectid_mutex is not acquired as log replay * could only happen during mount. */ ret = btrfs_init_root_free_objectid(root); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto next; } } next: if (wc.root) { wc.root->log_root = NULL; btrfs_put_root(wc.root); } btrfs_put_root(wc.log); wc.log = NULL; if (ret) goto error; if (found_key.offset == 0) break; key.offset = found_key.offset - 1; } btrfs_release_path(path); /* step one is to pin it all, step two is to replay just inodes */ if (wc.pin) { wc.pin = false; wc.process_func = replay_one_buffer; wc.stage = LOG_WALK_REPLAY_INODES; goto again; } /* step three is to replay everything */ if (wc.stage < LOG_WALK_REPLAY_ALL) { wc.stage++; goto again; } btrfs_free_path(path); /* step 4: commit the transaction, which also unpins the blocks */ ret = btrfs_commit_transaction(trans); if (ret) return ret; clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); return 0; error: if (wc.trans) btrfs_end_transaction(wc.trans); btrfs_put_root(wc.log); clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); btrfs_free_path(path); return ret; } /* * there are some corner cases where we want to force a full * commit instead of allowing a directory to be logged. * * They revolve around files there were unlinked from the directory, and * this function updates the parent directory so that a full commit is * properly done if it is fsync'd later after the unlinks are done. * * Must be called before the unlink operations (updates to the subvolume tree, * inodes, etc) are done. */ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, bool for_rename) { /* * when we're logging a file, if it hasn't been renamed * or unlinked, and its inode is fully committed on disk, * we don't have to worry about walking up the directory chain * to log its parents. * * So, we use the last_unlink_trans field to put this transid * into the file. When the file is logged we check it and * don't log the parents if the file is fully on disk. */ mutex_lock(&inode->log_mutex); inode->last_unlink_trans = trans->transid; mutex_unlock(&inode->log_mutex); if (!for_rename) return; /* * If this directory was already logged, any new names will be logged * with btrfs_log_new_name() and old names will be deleted from the log * tree with btrfs_del_dir_entries_in_log() or with * btrfs_del_inode_ref_in_log(). */ if (inode_logged(trans, dir, NULL) == 1) return; /* * If the inode we're about to unlink was logged before, the log will be * properly updated with the new name with btrfs_log_new_name() and the * old name removed with btrfs_del_dir_entries_in_log() or with * btrfs_del_inode_ref_in_log(). */ if (inode_logged(trans, inode, NULL) == 1) return; /* * when renaming files across directories, if the directory * there we're unlinking from gets fsync'd later on, there's * no way to find the destination directory later and fsync it * properly. So, we have to be conservative and force commits * so the new name gets discovered. */ mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Make sure that if someone attempts to fsync the parent directory of a deleted * snapshot, it ends up triggering a transaction commit. This is to guarantee * that after replaying the log tree of the parent directory's root we will not * see the snapshot anymore and at log replay time we will not see any log tree * corresponding to the deleted snapshot's root, which could lead to replaying * it after replaying the log tree of the parent directory (which would replay * the snapshot delete operation). * * Must be called before the actual snapshot destroy operation (updates to the * parent root and tree of tree roots trees, etc) are done. */ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir) { mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Call this when creating a subvolume in a directory. * Because we don't commit a transaction when creating a subvolume, we can't * allow the directory pointing to the subvolume to be logged with an entry that * points to an unpersisted root if we are still in the transaction used to * create the subvolume, so make any attempt to log the directory to result in a * full log sync. * Also we don't need to worry with renames, since btrfs_rename() marks the log * for full commit when renaming a subvolume. * * Must be called before creating the subvolume entry in its parent directory. */ void btrfs_record_new_subvolume(const struct btrfs_trans_handle *trans, struct btrfs_inode *dir) { mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Update the log after adding a new name for an inode. * * @trans: Transaction handle. * @old_dentry: The dentry associated with the old name and the old * parent directory. * @old_dir: The inode of the previous parent directory for the case * of a rename. For a link operation, it must be NULL. * @old_dir_index: The index number associated with the old name, meaningful * only for rename operations (when @old_dir is not NULL). * Ignored for link operations. * @parent: The dentry associated with the directory under which the * new name is located. * * Call this after adding a new name for an inode, as a result of a link or * rename operation, and it will properly update the log to reflect the new name. */ void btrfs_log_new_name(struct btrfs_trans_handle *trans, struct dentry *old_dentry, struct btrfs_inode *old_dir, u64 old_dir_index, struct dentry *parent) { struct btrfs_inode *inode = BTRFS_I(d_inode(old_dentry)); struct btrfs_root *root = inode->root; struct btrfs_log_ctx ctx; bool log_pinned = false; int ret; btrfs_init_log_ctx(&ctx, inode); ctx.logging_new_name = true; /* * this will force the logging code to walk the dentry chain * up for the file */ if (!S_ISDIR(inode->vfs_inode.i_mode)) inode->last_unlink_trans = trans->transid; /* * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ ret = inode_logged(trans, inode, NULL); if (ret < 0) { goto out; } else if (ret == 0) { if (!old_dir) return; /* * If the inode was not logged and we are doing a rename (old_dir is not * NULL), check if old_dir was logged - if it was not we can return and * do nothing. */ ret = inode_logged(trans, old_dir, NULL); if (ret < 0) goto out; else if (ret == 0) return; } ret = 0; /* * Now that we know we need to update the log, allocate the scratch eb * for the context before joining a log transaction below, as this can * take time and therefore we could delay log commits from other tasks. */ btrfs_init_log_ctx_scratch_eb(&ctx); /* * If we are doing a rename (old_dir is not NULL) from a directory that * was previously logged, make sure that on log replay we get the old * dir entry deleted. This is needed because we will also log the new * name of the renamed inode, so we need to make sure that after log * replay we don't end up with both the new and old dir entries existing. */ if (old_dir && old_dir->logged_trans == trans->transid) { struct btrfs_root *log = old_dir->root->log_root; struct btrfs_path *path; struct fscrypt_name fname; ASSERT(old_dir_index >= BTRFS_DIR_START_INDEX); ret = fscrypt_setup_filename(&old_dir->vfs_inode, &old_dentry->d_name, 0, &fname); if (ret) goto out; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; fscrypt_free_filename(&fname); goto out; } /* * We have two inodes to update in the log, the old directory and * the inode that got renamed, so we must pin the log to prevent * anyone from syncing the log until we have updated both inodes * in the log. */ ret = join_running_log_trans(root); /* * At least one of the inodes was logged before, so this should * not fail, but if it does, it's not serious, just bail out and * mark the log for a full commit. */ if (WARN_ON_ONCE(ret < 0)) { btrfs_free_path(path); fscrypt_free_filename(&fname); goto out; } log_pinned = true; /* * Other concurrent task might be logging the old directory, * as it can be triggered when logging other inode that had or * still has a dentry in the old directory. We lock the old * directory's log_mutex to ensure the deletion of the old * name is persisted, because during directory logging we * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of * the old name's dir index item is in the delayed items, so * it could be missed by an in progress directory logging. */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), &fname.disk_name, old_dir_index); if (ret > 0) { /* * The dentry does not exist in the log, so record its * deletion. */ btrfs_release_path(path); ret = insert_dir_log_key(trans, log, path, btrfs_ino(old_dir), old_dir_index, old_dir_index); } mutex_unlock(&old_dir->log_mutex); btrfs_free_path(path); fscrypt_free_filename(&fname); if (ret < 0) goto out; } /* * We don't care about the return value. If we fail to log the new name * then we know the next attempt to sync the log will fallback to a full * transaction commit (due to a call to btrfs_set_log_full_commit()), so * we don't need to worry about getting a log committed that has an * inconsistent state after a rename operation. */ btrfs_log_inode_parent(trans, inode, parent, LOG_INODE_EXISTS, &ctx); ASSERT(list_empty(&ctx.conflict_inodes)); out: /* * If an error happened mark the log for a full commit because it's not * consistent and up to date or we couldn't find out if one of the * inodes was logged before in this transaction. Do it before unpinning * the log, to avoid any races with someone else trying to commit it. */ if (ret < 0) btrfs_set_log_full_commit(trans); if (log_pinned) btrfs_end_log_trans(root); free_extent_buffer(ctx.scratch_eb); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pcm_local.h - a local header file for snd-pcm module. * * Copyright (c) Takashi Sakamoto <o-takashi@sakamocchi.jp> */ #ifndef __SOUND_CORE_PCM_LOCAL_H #define __SOUND_CORE_PCM_LOCAL_H extern const struct snd_pcm_hw_constraint_list snd_pcm_known_rates; void snd_interval_mul(const struct snd_interval *a, const struct snd_interval *b, struct snd_interval *c); void snd_interval_div(const struct snd_interval *a, const struct snd_interval *b, struct snd_interval *c); void snd_interval_muldivk(const struct snd_interval *a, const struct snd_interval *b, unsigned int k, struct snd_interval *c); void snd_interval_mulkdiv(const struct snd_interval *a, unsigned int k, const struct snd_interval *b, struct snd_interval *c); int snd_pcm_hw_constraint_mask(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, u_int32_t mask); int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, snd_pcm_uframes_t appl_ptr); int snd_pcm_update_state(struct snd_pcm_substream *substream, struct snd_pcm_runtime *runtime); int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream); void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_uframes_t new_hw_ptr); static inline snd_pcm_uframes_t snd_pcm_avail(struct snd_pcm_substream *substream) { if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) return snd_pcm_playback_avail(substream->runtime); else return snd_pcm_capture_avail(substream->runtime); } static inline snd_pcm_uframes_t snd_pcm_hw_avail(struct snd_pcm_substream *substream) { if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) return snd_pcm_playback_hw_avail(substream->runtime); else return snd_pcm_capture_hw_avail(substream->runtime); } #ifdef CONFIG_SND_PCM_TIMER void snd_pcm_timer_resolution_change(struct snd_pcm_substream *substream); void snd_pcm_timer_init(struct snd_pcm_substream *substream); void snd_pcm_timer_done(struct snd_pcm_substream *substream); #else static inline void snd_pcm_timer_resolution_change(struct snd_pcm_substream *substream) {} static inline void snd_pcm_timer_init(struct snd_pcm_substream *substream) {} static inline void snd_pcm_timer_done(struct snd_pcm_substream *substream) {} #endif void __snd_pcm_xrun(struct snd_pcm_substream *substream); void snd_pcm_group_init(struct snd_pcm_group *group); void snd_pcm_sync_stop(struct snd_pcm_substream *substream, bool sync_irq); #define PCM_RUNTIME_CHECK(sub) snd_BUG_ON(!(sub) || !(sub)->runtime) /* loop over all PCM substreams */ #define for_each_pcm_substream(pcm, str, subs) \ for ((str) = 0; (str) < 2; (str)++) \ for ((subs) = (pcm)->streams[str].substream; (subs); \ (subs) = (subs)->next) static inline void snd_pcm_dma_buffer_sync(struct snd_pcm_substream *substream, enum snd_dma_sync_mode mode) { if (substream->runtime->info & SNDRV_PCM_INFO_EXPLICIT_SYNC) snd_dma_buffer_sync(snd_pcm_get_dma_buf(substream), mode); } #endif /* __SOUND_CORE_PCM_LOCAL_H */ |
| 8041 4881 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * security/tomoyo/common.h * * Header file for TOMOYO. * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H #define _SECURITY_TOMOYO_COMMON_H #define pr_fmt(fmt) fmt #include <linux/ctype.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/list.h> #include <linux/cred.h> #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/lsm_hooks.h> #include <net/sock.h> #include <net/af_unix.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> /********** Constants definitions. **********/ /* * TOMOYO uses this hash only when appending a string into the string * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. * Therefore, we don't need SOCK_MAX. */ #define TOMOYO_SOCK_MAX 6 #define TOMOYO_EXEC_TMPSIZE 4096 /* Garbage collector is trying to kfree() this element. */ #define TOMOYO_GC_IN_PROGRESS -1 /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 /* Group number is an integer between 0 and 255. */ #define TOMOYO_MAX_ACL_GROUPS 256 /* Index numbers for "struct tomoyo_condition". */ enum tomoyo_conditions_index { TOMOYO_TASK_UID, /* current_uid() */ TOMOYO_TASK_EUID, /* current_euid() */ TOMOYO_TASK_SUID, /* current_suid() */ TOMOYO_TASK_FSUID, /* current_fsuid() */ TOMOYO_TASK_GID, /* current_gid() */ TOMOYO_TASK_EGID, /* current_egid() */ TOMOYO_TASK_SGID, /* current_sgid() */ TOMOYO_TASK_FSGID, /* current_fsgid() */ TOMOYO_TASK_PID, /* sys_getpid() */ TOMOYO_TASK_PPID, /* sys_getppid() */ TOMOYO_EXEC_ARGC, /* "struct linux_binprm *"->argc */ TOMOYO_EXEC_ENVC, /* "struct linux_binprm *"->envc */ TOMOYO_TYPE_IS_SOCKET, /* S_IFSOCK */ TOMOYO_TYPE_IS_SYMLINK, /* S_IFLNK */ TOMOYO_TYPE_IS_FILE, /* S_IFREG */ TOMOYO_TYPE_IS_BLOCK_DEV, /* S_IFBLK */ TOMOYO_TYPE_IS_DIRECTORY, /* S_IFDIR */ TOMOYO_TYPE_IS_CHAR_DEV, /* S_IFCHR */ TOMOYO_TYPE_IS_FIFO, /* S_IFIFO */ TOMOYO_MODE_SETUID, /* S_ISUID */ TOMOYO_MODE_SETGID, /* S_ISGID */ TOMOYO_MODE_STICKY, /* S_ISVTX */ TOMOYO_MODE_OWNER_READ, /* S_IRUSR */ TOMOYO_MODE_OWNER_WRITE, /* S_IWUSR */ TOMOYO_MODE_OWNER_EXECUTE, /* S_IXUSR */ TOMOYO_MODE_GROUP_READ, /* S_IRGRP */ TOMOYO_MODE_GROUP_WRITE, /* S_IWGRP */ TOMOYO_MODE_GROUP_EXECUTE, /* S_IXGRP */ TOMOYO_MODE_OTHERS_READ, /* S_IROTH */ TOMOYO_MODE_OTHERS_WRITE, /* S_IWOTH */ TOMOYO_MODE_OTHERS_EXECUTE, /* S_IXOTH */ TOMOYO_EXEC_REALPATH, TOMOYO_SYMLINK_TARGET, TOMOYO_PATH1_UID, TOMOYO_PATH1_GID, TOMOYO_PATH1_INO, TOMOYO_PATH1_MAJOR, TOMOYO_PATH1_MINOR, TOMOYO_PATH1_PERM, TOMOYO_PATH1_TYPE, TOMOYO_PATH1_DEV_MAJOR, TOMOYO_PATH1_DEV_MINOR, TOMOYO_PATH2_UID, TOMOYO_PATH2_GID, TOMOYO_PATH2_INO, TOMOYO_PATH2_MAJOR, TOMOYO_PATH2_MINOR, TOMOYO_PATH2_PERM, TOMOYO_PATH2_TYPE, TOMOYO_PATH2_DEV_MAJOR, TOMOYO_PATH2_DEV_MINOR, TOMOYO_PATH1_PARENT_UID, TOMOYO_PATH1_PARENT_GID, TOMOYO_PATH1_PARENT_INO, TOMOYO_PATH1_PARENT_PERM, TOMOYO_PATH2_PARENT_UID, TOMOYO_PATH2_PARENT_GID, TOMOYO_PATH2_PARENT_INO, TOMOYO_PATH2_PARENT_PERM, TOMOYO_MAX_CONDITION_KEYWORD, TOMOYO_NUMBER_UNION, TOMOYO_NAME_UNION, TOMOYO_ARGV_ENTRY, TOMOYO_ENVP_ENTRY, }; /* Index numbers for stat(). */ enum tomoyo_path_stat_index { /* Do not change this order. */ TOMOYO_PATH1, TOMOYO_PATH1_PARENT, TOMOYO_PATH2, TOMOYO_PATH2_PARENT, TOMOYO_MAX_PATH_STAT }; /* Index numbers for operation mode. */ enum tomoyo_mode_index { TOMOYO_CONFIG_DISABLED, TOMOYO_CONFIG_LEARNING, TOMOYO_CONFIG_PERMISSIVE, TOMOYO_CONFIG_ENFORCING, TOMOYO_CONFIG_MAX_MODE, TOMOYO_CONFIG_WANT_REJECT_LOG = 64, TOMOYO_CONFIG_WANT_GRANT_LOG = 128, TOMOYO_CONFIG_USE_DEFAULT = 255, }; /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, TOMOYO_ID_AGGREGATOR, TOMOYO_ID_MANAGER, TOMOYO_ID_CONDITION, TOMOYO_ID_NAME, TOMOYO_ID_ACL, TOMOYO_ID_DOMAIN, TOMOYO_MAX_POLICY }; /* Index numbers for domain's attributes. */ enum tomoyo_domain_info_flags_index { /* Quota warnning flag. */ TOMOYO_DIF_QUOTA_WARNED, /* * This domain was unable to create a new domain at * tomoyo_find_next_domain() because the name of the domain to be * created was too long or it could not allocate memory. * More than one process continued execve() without domain transition. */ TOMOYO_DIF_TRANSITION_FAILED, TOMOYO_MAX_DOMAIN_INFO_FLAGS }; /* Index numbers for audit type. */ enum tomoyo_grant_log { /* Follow profile's configuration. */ TOMOYO_GRANTLOG_AUTO, /* Do not generate grant log. */ TOMOYO_GRANTLOG_NO, /* Generate grant_log. */ TOMOYO_GRANTLOG_YES, }; /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; /* Index numbers for type of numeric values. */ enum tomoyo_value_type { TOMOYO_VALUE_TYPE_INVALID, TOMOYO_VALUE_TYPE_DECIMAL, TOMOYO_VALUE_TYPE_OCTAL, TOMOYO_VALUE_TYPE_HEXADECIMAL, }; /* Index numbers for domain transition control keywords. */ enum tomoyo_transition_type { /* Do not change this order, */ TOMOYO_TRANSITION_CONTROL_NO_RESET, TOMOYO_TRANSITION_CONTROL_RESET, TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE, TOMOYO_TRANSITION_CONTROL_INITIALIZE, TOMOYO_TRANSITION_CONTROL_NO_KEEP, TOMOYO_TRANSITION_CONTROL_KEEP, TOMOYO_MAX_TRANSITION_TYPE }; /* Index numbers for Access Controls. */ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_ACL, TOMOYO_TYPE_PATH2_ACL, TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, TOMOYO_TYPE_INET_ACL, TOMOYO_TYPE_UNIX_ACL, TOMOYO_TYPE_ENV_ACL, TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ enum tomoyo_path_acl_index { TOMOYO_TYPE_EXECUTE, TOMOYO_TYPE_READ, TOMOYO_TYPE_WRITE, TOMOYO_TYPE_APPEND, TOMOYO_TYPE_UNLINK, TOMOYO_TYPE_GETATTR, TOMOYO_TYPE_RMDIR, TOMOYO_TYPE_TRUNCATE, TOMOYO_TYPE_SYMLINK, TOMOYO_TYPE_CHROOT, TOMOYO_TYPE_UMOUNT, TOMOYO_MAX_PATH_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_memory_stat_type { TOMOYO_MEMORY_POLICY, TOMOYO_MEMORY_AUDIT, TOMOYO_MEMORY_QUERY, TOMOYO_MAX_MEMORY_STAT }; enum tomoyo_mkdev_acl_index { TOMOYO_TYPE_MKBLOCK, TOMOYO_TYPE_MKCHAR, TOMOYO_MAX_MKDEV_OPERATION }; /* Index numbers for socket operations. */ enum tomoyo_network_acl_index { TOMOYO_NETWORK_BIND, /* bind() operation. */ TOMOYO_NETWORK_LISTEN, /* listen() operation. */ TOMOYO_NETWORK_CONNECT, /* connect() operation. */ TOMOYO_NETWORK_SEND, /* send() operation. */ TOMOYO_MAX_NETWORK_OPERATION }; /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, TOMOYO_TYPE_RENAME, TOMOYO_TYPE_PIVOT_ROOT, TOMOYO_MAX_PATH2_OPERATION }; /* Index numbers for access controls with one pathname and one number. */ enum tomoyo_path_number_acl_index { TOMOYO_TYPE_CREATE, TOMOYO_TYPE_MKDIR, TOMOYO_TYPE_MKFIFO, TOMOYO_TYPE_MKSOCK, TOMOYO_TYPE_IOCTL, TOMOYO_TYPE_CHMOD, TOMOYO_TYPE_CHOWN, TOMOYO_TYPE_CHGRP, TOMOYO_MAX_PATH_NUMBER_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */ enum tomoyo_securityfs_interface_index { TOMOYO_DOMAINPOLICY, TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, TOMOYO_QUERY, TOMOYO_MANAGER }; /* Index numbers for special mount operations. */ enum tomoyo_special_mount { TOMOYO_MOUNT_BIND, /* mount --bind /source /dest */ TOMOYO_MOUNT_MOVE, /* mount --move /old /new */ TOMOYO_MOUNT_REMOUNT, /* mount -o remount /dir */ TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */ TOMOYO_MOUNT_MAKE_PRIVATE, /* mount --make-private /dir */ TOMOYO_MOUNT_MAKE_SLAVE, /* mount --make-slave /dir */ TOMOYO_MOUNT_MAKE_SHARED, /* mount --make-shared /dir */ TOMOYO_MAX_SPECIAL_MOUNT }; /* Index numbers for functionality. */ enum tomoyo_mac_index { TOMOYO_MAC_FILE_EXECUTE, TOMOYO_MAC_FILE_OPEN, TOMOYO_MAC_FILE_CREATE, TOMOYO_MAC_FILE_UNLINK, TOMOYO_MAC_FILE_GETATTR, TOMOYO_MAC_FILE_MKDIR, TOMOYO_MAC_FILE_RMDIR, TOMOYO_MAC_FILE_MKFIFO, TOMOYO_MAC_FILE_MKSOCK, TOMOYO_MAC_FILE_TRUNCATE, TOMOYO_MAC_FILE_SYMLINK, TOMOYO_MAC_FILE_MKBLOCK, TOMOYO_MAC_FILE_MKCHAR, TOMOYO_MAC_FILE_LINK, TOMOYO_MAC_FILE_RENAME, TOMOYO_MAC_FILE_CHMOD, TOMOYO_MAC_FILE_CHOWN, TOMOYO_MAC_FILE_CHGRP, TOMOYO_MAC_FILE_IOCTL, TOMOYO_MAC_FILE_CHROOT, TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, TOMOYO_MAC_NETWORK_INET_STREAM_BIND, TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, TOMOYO_MAC_NETWORK_INET_RAW_BIND, TOMOYO_MAC_NETWORK_INET_RAW_SEND, TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, TOMOYO_MAC_CATEGORY_NETWORK, TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; /* * Retry this request. Returned by tomoyo_supervisor() if policy violation has * occurred in enforcing mode and the userspace daemon decided to retry. * * We must choose a positive value in order to distinguish "granted" (which is * 0) and "rejected" (which is a negative value) and "retry". */ #define TOMOYO_RETRY_REQUEST 1 /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_policy_stat_type { /* Do not change this order. */ TOMOYO_STAT_POLICY_UPDATES, TOMOYO_STAT_POLICY_LEARNING, /* == TOMOYO_CONFIG_LEARNING */ TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */ TOMOYO_STAT_POLICY_ENFORCING, /* == TOMOYO_CONFIG_ENFORCING */ TOMOYO_MAX_POLICY_STAT }; /* Index numbers for profile's PREFERENCE values. */ enum tomoyo_pref_index { TOMOYO_PREF_MAX_AUDIT_LOG, TOMOYO_PREF_MAX_LEARNING_ENTRY, TOMOYO_MAX_PREF }; /********** Structure definitions. **********/ /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ struct tomoyo_shared_acl_head { struct list_head list; atomic_t users; } __packed; struct tomoyo_policy_namespace; /* Structure for request info. */ struct tomoyo_request_info { /* * For holding parameters specific to operations which deal files. * NULL if not dealing files. */ struct tomoyo_obj_info *obj; /* * For holding parameters specific to execve() request. * NULL if not dealing execve(). */ struct tomoyo_execve *ee; struct tomoyo_domain_info *domain; /* For holding parameters. */ union { struct { const struct tomoyo_path_info *filename; /* For using wildcards at tomoyo_find_next_domain(). */ const struct tomoyo_path_info *matched_path; /* One of values in "enum tomoyo_path_acl_index". */ u8 operation; } path; struct { const struct tomoyo_path_info *filename1; const struct tomoyo_path_info *filename2; /* One of values in "enum tomoyo_path2_acl_index". */ u8 operation; } path2; struct { const struct tomoyo_path_info *filename; unsigned int mode; unsigned int major; unsigned int minor; /* One of values in "enum tomoyo_mkdev_acl_index". */ u8 operation; } mkdev; struct { const struct tomoyo_path_info *filename; unsigned long number; /* * One of values in * "enum tomoyo_path_number_acl_index". */ u8 operation; } path_number; struct { const struct tomoyo_path_info *name; } environ; struct { const __be32 *address; u16 port; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; bool is_ipv6; } inet_network; struct { const struct tomoyo_path_info *address; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; } unix_network; struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; struct { const struct tomoyo_path_info *domainname; } task; } param; struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; u8 profile; u8 mode; /* One of tomoyo_mode_index . */ u8 type; }; /* Structure for holding a token. */ struct tomoyo_path_info { const char *name; u32 hash; /* = full_name_hash(name, strlen(name)) */ u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ }; /* Structure for holding string data. */ struct tomoyo_name { struct tomoyo_shared_acl_head head; struct tomoyo_path_info entry; }; /* Structure for holding a word. */ struct tomoyo_name_union { /* Either @filename or @group is NULL. */ const struct tomoyo_path_info *filename; struct tomoyo_group *group; }; /* Structure for holding a number. */ struct tomoyo_number_union { unsigned long values[2]; struct tomoyo_group *group; /* Maybe NULL. */ /* One of values in "enum tomoyo_value_type". */ u8 value_type[2]; }; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union { struct in6_addr ip[2]; /* Big endian. */ struct tomoyo_group *group; /* Pointer to address group. */ bool is_ipv6; /* Valid only if @group == NULL. */ }; /* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; struct list_head member_list; }; /* Structure for "path_group" directive. */ struct tomoyo_path_group { struct tomoyo_acl_head head; const struct tomoyo_path_info *member_name; }; /* Structure for "number_group" directive. */ struct tomoyo_number_group { struct tomoyo_acl_head head; struct tomoyo_number_union number; }; /* Structure for "address_group" directive. */ struct tomoyo_address_group { struct tomoyo_acl_head head; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union address; }; /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { kuid_t uid; kgid_t gid; ino_t ino; umode_t mode; dev_t dev; dev_t rdev; }; /* Structure for dumping argv[] and envp[] of "struct linux_binprm". */ struct tomoyo_page_dump { struct page *page; /* Previously dumped page. */ char *data; /* Contents of "page". Size is PAGE_SIZE. */ }; /* Structure for attribute checks in addition to pathname checks. */ struct tomoyo_obj_info { /* * True if tomoyo_get_attributes() was already called, false otherwise. */ bool validate_done; /* True if @stat[] is valid. */ bool stat_valid[TOMOYO_MAX_PATH_STAT]; /* First pathname. Initialized with { NULL, NULL } if no path. */ struct path path1; /* Second pathname. Initialized with { NULL, NULL } if no path. */ struct path path2; /* * Information on @path1, @path1's parent directory, @path2, @path2's * parent directory. */ struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT]; /* * Content of symbolic link to be created. NULL for operations other * than symlink(). */ struct tomoyo_path_info *symlink_target; }; /* Structure for argv[]. */ struct tomoyo_argv { unsigned long index; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for envp[]. */ struct tomoyo_envp { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for execve() operation. */ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ }; /* Structure for entries which follows "struct tomoyo_condition". */ struct tomoyo_condition_element { /* * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail * of the array of this struct. */ u8 left; /* * Right hand operand. A "struct tomoyo_number_union" for * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for * TOMOYO_NAME_UNION is attached to the tail of the array of this * struct. */ u8 right; /* Equation operator. True if equals or overlaps, false otherwise. */ bool equals; }; /* Structure for optional arguments. */ struct tomoyo_condition { struct tomoyo_shared_acl_head head; u32 size; /* Memory size allocated for this entry. */ u16 condc; /* Number of conditions in this struct. */ u16 numbers_count; /* Number of "struct tomoyo_number_union values". */ u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; * struct tomoyo_name_union names[names_count]; * struct tomoyo_argv argv[argc]; * struct tomoyo_envp envp[envc]; */ }; /* Common header for individual entries. */ struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; /* Structure for domain information. */ struct tomoyo_domain_info { struct list_head list; struct list_head acl_info_list; /* Name of this domain. Never NULL. */ const struct tomoyo_path_info *domainname; /* Namespace for this domain. Never NULL. */ struct tomoyo_policy_namespace *ns; /* Group numbers to use. */ unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG]; u8 profile; /* Profile number to use. */ bool is_deleted; /* Delete flag. */ bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; atomic_t users; /* Number of referring tasks. */ }; /* * Structure for "task manual_domain_transition" directive. */ struct tomoyo_task_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ /* Pointer to domainname. */ const struct tomoyo_path_info *domainname; }; /* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. */ struct tomoyo_path_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */ u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */ struct tomoyo_name_union name; }; /* * Structure for "file create", "file mkdir", "file mkfifo", "file mksock", * "file ioctl", "file chmod", "file chown" and "file chgrp" directive. */ struct tomoyo_path_number_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */ /* Bitmask of values in "enum tomoyo_path_number_acl_index". */ u8 perm; struct tomoyo_name_union name; struct tomoyo_number_union number; }; /* Structure for "file mkblock" and "file mkchar" directive. */ struct tomoyo_mkdev_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */ struct tomoyo_name_union name; struct tomoyo_number_union mode; struct tomoyo_number_union major; struct tomoyo_number_union minor; }; /* * Structure for "file rename", "file link" and "file pivot_root" directive. */ struct tomoyo_path2_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */ struct tomoyo_name_union name1; struct tomoyo_name_union name2; }; /* Structure for "file mount" directive. */ struct tomoyo_mount_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */ struct tomoyo_name_union dev_name; struct tomoyo_name_union dir_name; struct tomoyo_name_union fs_type; struct tomoyo_number_union flags; }; /* Structure for "misc env" directive in domain policy. */ struct tomoyo_env_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ const struct tomoyo_path_info *env; /* environment variable */ }; /* Structure for "network inet" directive. */ struct tomoyo_inet_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_ipaddr_union address; struct tomoyo_number_union port; }; /* Structure for "network unix" directive. */ struct tomoyo_unix_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_name_union name; }; /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; struct list_head *list; struct tomoyo_policy_namespace *ns; bool is_delete; }; #define TOMOYO_MAX_IO_READ_QUEUE 64 /* * Structure for reading/writing policy via /sys/kernel/security/tomoyo * interfaces. */ struct tomoyo_io_buffer { void (*read)(struct tomoyo_io_buffer *head); int (*write)(struct tomoyo_io_buffer *head); __poll_t (*poll)(struct file *file, poll_table *wait); /* Exclusive lock for this structure. */ struct mutex io_sem; char __user *read_user_buf; size_t read_user_buf_avail; struct { struct list_head *ns; struct list_head *domain; struct list_head *group; struct list_head *acl; size_t avail; unsigned int step; unsigned int query_index; u16 index; u16 cond_index; u8 acl_group_index; u8 cond_step; u8 bit; u8 w_pos; bool eof; bool print_this_domain_only; bool print_transition_related_only; bool print_cond_part; const char *w[TOMOYO_MAX_IO_READ_QUEUE]; } r; struct { struct tomoyo_policy_namespace *ns; /* The position currently writing to. */ struct tomoyo_domain_info *domain; /* Bytes available for writing. */ size_t avail; bool is_delete; } w; /* Buffer for reading. */ char *read_buf; /* Size of read buffer. */ size_t readbuf_size; /* Buffer for writing. */ char *write_buf; /* Size of write buffer. */ size_t writebuf_size; /* Type of this interface. */ enum tomoyo_securityfs_interface_index type; /* Users counter protected by tomoyo_io_buffer_list_lock. */ u8 users; /* List for telling GC not to kfree() elements. */ struct list_head list; }; /* * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/ * "no_keep_domain" keyword. */ struct tomoyo_transition_control { struct tomoyo_acl_head head; u8 type; /* One of values in "enum tomoyo_transition_type". */ /* True if the domainname is tomoyo_get_last_name(). */ bool is_last_name; const struct tomoyo_path_info *domainname; /* Maybe NULL */ const struct tomoyo_path_info *program; /* Maybe NULL */ }; /* Structure for "aggregator" keyword. */ struct tomoyo_aggregator { struct tomoyo_acl_head head; const struct tomoyo_path_info *original_name; const struct tomoyo_path_info *aggregated_name; }; /* Structure for policy manager. */ struct tomoyo_manager { struct tomoyo_acl_head head; /* A path to program or a domainname. */ const struct tomoyo_path_info *manager; }; struct tomoyo_preference { unsigned int learning_max_entry; bool enforcing_verbose; bool learning_verbose; bool permissive_verbose; }; /* Structure for /sys/kernel/security/tomnoyo/profile interface. */ struct tomoyo_profile { const struct tomoyo_path_info *comment; struct tomoyo_preference *learning; struct tomoyo_preference *permissive; struct tomoyo_preference *enforcing; struct tomoyo_preference preference; u8 default_config; u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; unsigned int pref[TOMOYO_MAX_PREF]; }; /* Structure for representing YYYY/MM/DD hh/mm/ss. */ struct tomoyo_time { u16 year; u8 month; u8 day; u8 hour; u8 min; u8 sec; }; /* Structure for policy namespace. */ struct tomoyo_policy_namespace { /* Profile table. Memory is allocated as needed. */ struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES]; /* List of "struct tomoyo_group". */ struct list_head group_list[TOMOYO_MAX_GROUP]; /* List of policy. */ struct list_head policy_list[TOMOYO_MAX_POLICY]; /* The global ACL referred by "use_group" keyword. */ struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; /* Profile version. Currently only 20150505 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; }; /* Structure for "struct task_struct"->security. */ struct tomoyo_task { struct tomoyo_domain_info *domain_info; struct tomoyo_domain_info *old_domain_info; }; /********** Function prototypes. **********/ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond); bool tomoyo_correct_domain(const unsigned char *domainname); bool tomoyo_correct_path(const char *filename); bool tomoyo_correct_word(const char *string); bool tomoyo_domain_def(const unsigned char *buffer); bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r); bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump); bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr); bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern); bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); char *tomoyo_read_token(struct tomoyo_acl_param *param); char *tomoyo_realpath_from_path(const struct path *path); char *tomoyo_realpath_nofollow(const char *pathname); const char *tomoyo_get_exe(void); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag); void tomoyo_close_control(struct tomoyo_io_buffer *head); int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env); int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename); int tomoyo_find_next_domain(struct linux_binprm *bprm); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page); int tomoyo_open_control(const u8 type, struct file *file); int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2); int tomoyo_path_number_perm(const u8 operation, const struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); __poll_t tomoyo_poll_control(struct file *file, poll_table *wait); __poll_t tomoyo_poll_log(struct file *file, poll_table *wait); int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_listen_permission(struct socket *sock); int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate) (struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)); int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)); int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_misc(struct tomoyo_acl_param *param); int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len); struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param); struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit); struct tomoyo_domain_info *tomoyo_domain(void); struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname); struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, const u8 idx); struct tomoyo_policy_namespace *tomoyo_assign_namespace (const char *domainname); struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile); u8 tomoyo_parse_ulong(unsigned long *result, char **str); void *tomoyo_commit_ok(void *data, const unsigned int size); void __init tomoyo_load_builtin_policy(void); void __init tomoyo_mm_init(void); void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)); void tomoyo_check_profile(void); void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp); void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); void tomoyo_load_policy(const char *filename); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); void tomoyo_put_number_union(struct tomoyo_number_union *ptr); void tomoyo_read_log(struct tomoyo_io_buffer *head); void tomoyo_update_stat(const u8 index); void tomoyo_warn_oom(const char *function); void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); /********** External variable definitions. **********/ extern bool tomoyo_policy_loaded; extern int tomoyo_enabled; extern const char * const tomoyo_condition_keyword [TOMOYO_MAX_CONDITION_KEYWORD]; extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION]; extern struct list_head tomoyo_condition_list; extern struct list_head tomoyo_domain_list; extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH]; extern struct list_head tomoyo_namespace_list; extern struct mutex tomoyo_policy_lock; extern struct srcu_struct tomoyo_ss; extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Inlined functions. **********/ /** * tomoyo_read_lock - Take lock for protecting policy. * * Returns index number for tomoyo_read_unlock(). */ static inline int tomoyo_read_lock(void) { return srcu_read_lock(&tomoyo_ss); } /** * tomoyo_read_unlock - Release lock for protecting policy. * * @idx: Index number returned by tomoyo_read_lock(). * * Returns nothing. */ static inline void tomoyo_read_unlock(int idx) { srcu_read_unlock(&tomoyo_ss, idx); } /** * tomoyo_sys_getppid - Copy of getppid(). * * Returns parent process's PID. * * Alpha does not have getppid() defined. To be able to build this module on * Alpha, I have to copy getppid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getppid(void) { pid_t pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } /** * tomoyo_sys_getpid - Copy of getpid(). * * Returns current thread's PID. * * Alpha does not have getpid() defined. To be able to build this module on * Alpha, I have to copy getpid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getpid(void) { return task_tgid_vnr(current); } /** * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure. * * @a: Pointer to "struct tomoyo_path_info". * @b: Pointer to "struct tomoyo_path_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a, const struct tomoyo_path_info *b) { return a->hash != b->hash || strcmp(a->name, b->name); } /** * tomoyo_put_name - Drop reference on "struct tomoyo_name". * * @name: Pointer to "struct tomoyo_path_info". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_name(const struct tomoyo_path_info *name) { if (name) { struct tomoyo_name *ptr = container_of(name, typeof(*ptr), entry); atomic_dec(&ptr->head.users); } } /** * tomoyo_put_condition - Drop reference on "struct tomoyo_condition". * * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_condition(struct tomoyo_condition *cond) { if (cond) atomic_dec(&cond->head.users); } /** * tomoyo_put_group - Drop reference on "struct tomoyo_group". * * @group: Pointer to "struct tomoyo_group". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_group(struct tomoyo_group *group) { if (group) atomic_dec(&group->head.users); } /** * tomoyo_task - Get "struct tomoyo_task" for specified thread. * * @task - Pointer to "struct task_struct". * * Returns pointer to "struct tomoyo_task" for specified thread. */ static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. * * @a: Pointer to "struct tomoyo_name_union". * @b: Pointer to "struct tomoyo_name_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_name_union (const struct tomoyo_name_union *a, const struct tomoyo_name_union *b) { return a->filename == b->filename && a->group == b->group; } /** * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry. * * @a: Pointer to "struct tomoyo_number_union". * @b: Pointer to "struct tomoyo_number_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_number_union (const struct tomoyo_number_union *a, const struct tomoyo_number_union *b) { return a->values[0] == b->values[0] && a->values[1] == b->values[1] && a->group == b->group && a->value_type[0] == b->value_type[0] && a->value_type[1] == b->value_type[1]; } /** * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. * * @a: Pointer to "struct tomoyo_ipaddr_union". * @b: Pointer to "struct tomoyo_ipaddr_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_ipaddr_union (const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) { return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && a->is_ipv6 == b->is_ipv6; } /** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. */ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) { return tomoyo_domain()->ns; } /** * list_for_each_cookie - iterate over a list with cookie. * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_cookie(pos, head) \ if (!pos) \ pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */ |
| 7 1 1 15 10 7 1 3 1 9 4 9 9 8 10 9 1 6 4 3 6 1 8 8 8 4 9 16 10 7 15 2 9 16 2 5 1 6 6 5 7 2 13 13 4 1 13 2 13 1 9 9 1 1 13 4 9 9 15 33 33 33 2 1 30 12 8 2 10 9 1 9 1 19 11 7 14 14 14 7 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fsverity.h> #include <linux/iomap.h> #include "ctree.h" #include "delalloc-space.h" #include "direct-io.h" #include "extent-tree.h" #include "file.h" #include "fs.h" #include "transaction.h" #include "volumes.h" struct btrfs_dio_data { ssize_t submitted; struct extent_changeset *data_reserved; struct btrfs_ordered_extent *ordered; bool data_space_reserved; bool nocow_done; }; struct btrfs_dio_private { /* Range of I/O */ u64 file_offset; u32 bytes; /* This must be last */ struct btrfs_bio bbio; }; static struct bio_set btrfs_dio_bioset; static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, struct extent_state **cached_state, unsigned int iomap_flags) { const bool writing = (iomap_flags & IOMAP_WRITE); const bool nowait = (iomap_flags & IOMAP_NOWAIT); struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; int ret = 0; /* Direct lock must be taken before the extent lock. */ if (nowait) { if (!btrfs_try_lock_dio_extent(io_tree, lockstart, lockend, cached_state)) return -EAGAIN; } else { btrfs_lock_dio_extent(io_tree, lockstart, lockend, cached_state); } while (1) { if (nowait) { if (!btrfs_try_lock_extent(io_tree, lockstart, lockend, cached_state)) { ret = -EAGAIN; break; } } else { btrfs_lock_extent(io_tree, lockstart, lockend, cached_state); } /* * We're concerned with the entire range that we're going to be * doing DIO to, so we need to make sure there's no ordered * extents in this range. */ ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart, lockend - lockstart + 1); /* * We need to make sure there are no buffered pages in this * range either, we could have raced between the invalidate in * generic_file_direct_write and locking the extent. The * invalidate needs to happen so that reads after a write do not * get stale data. */ if (!ordered && (!writing || !filemap_range_has_page(inode->i_mapping, lockstart, lockend))) break; btrfs_unlock_extent(io_tree, lockstart, lockend, cached_state); if (ordered) { if (nowait) { btrfs_put_ordered_extent(ordered); ret = -EAGAIN; break; } /* * If we are doing a DIO read and the ordered extent we * found is for a buffered write, we can not wait for it * to complete and retry, because if we do so we can * deadlock with concurrent buffered writes on page * locks. This happens only if our DIO read covers more * than one extent map, if at this point has already * created an ordered extent for a previous extent map * and locked its range in the inode's io tree, and a * concurrent write against that previous extent map's * range and this range started (we unlock the ranges * in the io tree only when the bios complete and * buffered writes always lock pages before attempting * to lock range in the io tree). */ if (writing || test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) btrfs_start_ordered_extent(ordered); else ret = nowait ? -EAGAIN : -ENOTBLK; btrfs_put_ordered_extent(ordered); } else { /* * We could trigger writeback for this range (and wait * for it to complete) and then invalidate the pages for * this range (through invalidate_inode_pages2_range()), * but that can lead us to a deadlock with a concurrent * call to readahead (a buffered read or a defrag call * triggered a readahead) on a page lock due to an * ordered dio extent we created before but did not have * yet a corresponding bio submitted (whence it can not * complete), which makes readahead wait for that * ordered extent to complete while holding a lock on * that page. */ ret = nowait ? -EAGAIN : -ENOTBLK; } if (ret) break; cond_resched(); } if (ret) btrfs_unlock_dio_extent(io_tree, lockstart, lockend, cached_state); return ret; } static struct extent_map *btrfs_create_dio_extent(struct btrfs_inode *inode, struct btrfs_dio_data *dio_data, const u64 start, const struct btrfs_file_extent *file_extent, const int type) { struct extent_map *em = NULL; struct btrfs_ordered_extent *ordered; if (type != BTRFS_ORDERED_NOCOW) { em = btrfs_create_io_em(inode, start, file_extent, type); if (IS_ERR(em)) goto out; } ordered = btrfs_alloc_ordered_extent(inode, start, file_extent, (1U << type) | (1U << BTRFS_ORDERED_DIRECT)); if (IS_ERR(ordered)) { if (em) { btrfs_free_extent_map(em); btrfs_drop_extent_map_range(inode, start, start + file_extent->num_bytes - 1, false); } em = ERR_CAST(ordered); } else { ASSERT(!dio_data->ordered); dio_data->ordered = ordered; } out: return em; } static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, struct btrfs_dio_data *dio_data, u64 start, u64 len) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_file_extent file_extent; struct extent_map *em; struct btrfs_key ins; u64 alloc_hint; int ret; alloc_hint = btrfs_get_extent_allocation_hint(inode, start, len); again: ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret == -EAGAIN) { ASSERT(btrfs_is_zoned(fs_info)); wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH, TASK_UNINTERRUPTIBLE); goto again; } if (ret) return ERR_PTR(ret); file_extent.disk_bytenr = ins.objectid; file_extent.disk_num_bytes = ins.offset; file_extent.num_bytes = ins.offset; file_extent.ram_bytes = ins.offset; file_extent.offset = 0; file_extent.compression = BTRFS_COMPRESS_NONE; em = btrfs_create_dio_extent(inode, dio_data, start, &file_extent, BTRFS_ORDERED_REGULAR); btrfs_dec_block_group_reservations(fs_info, ins.objectid); if (IS_ERR(em)) btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, true); return em; } static int btrfs_get_blocks_direct_write(struct extent_map **map, struct inode *inode, struct btrfs_dio_data *dio_data, u64 start, u64 *lenp, unsigned int iomap_flags) { const bool nowait = (iomap_flags & IOMAP_NOWAIT); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_file_extent file_extent; struct extent_map *em = *map; int type; u64 block_start; struct btrfs_block_group *bg; bool can_nocow = false; bool space_reserved = false; u64 len = *lenp; u64 prev_len; int ret = 0; /* * We don't allocate a new extent in the following cases * * 1) The inode is marked as NODATACOW. In this case we'll just use the * existing extent. * 2) The extent is marked as PREALLOC. We're good to go here and can * just use the extent. * */ if ((em->flags & EXTENT_FLAG_PREALLOC) || ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && em->disk_bytenr != EXTENT_MAP_HOLE)) { if (em->flags & EXTENT_FLAG_PREALLOC) type = BTRFS_ORDERED_PREALLOC; else type = BTRFS_ORDERED_NOCOW; len = min(len, em->len - (start - em->start)); block_start = btrfs_extent_map_block_start(em) + (start - em->start); if (can_nocow_extent(BTRFS_I(inode), start, &len, &file_extent, false) == 1) { bg = btrfs_inc_nocow_writers(fs_info, block_start); if (bg) can_nocow = true; } } prev_len = len; if (can_nocow) { struct extent_map *em2; /* We can NOCOW, so only need to reserve metadata space. */ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len, nowait); if (ret < 0) { /* Our caller expects us to free the input extent map. */ btrfs_free_extent_map(em); *map = NULL; btrfs_dec_nocow_writers(bg); if (nowait && (ret == -ENOSPC || ret == -EDQUOT)) ret = -EAGAIN; goto out; } space_reserved = true; em2 = btrfs_create_dio_extent(BTRFS_I(inode), dio_data, start, &file_extent, type); btrfs_dec_nocow_writers(bg); if (type == BTRFS_ORDERED_PREALLOC) { btrfs_free_extent_map(em); *map = em2; em = em2; } if (IS_ERR(em2)) { ret = PTR_ERR(em2); goto out; } dio_data->nocow_done = true; } else { /* Our caller expects us to free the input extent map. */ btrfs_free_extent_map(em); *map = NULL; if (nowait) { ret = -EAGAIN; goto out; } /* * If we could not allocate data space before locking the file * range and we can't do a NOCOW write, then we have to fail. */ if (!dio_data->data_space_reserved) { ret = -ENOSPC; goto out; } /* * We have to COW and we have already reserved data space before, * so now we reserve only metadata. */ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len, false); if (ret < 0) goto out; space_reserved = true; em = btrfs_new_extent_direct(BTRFS_I(inode), dio_data, start, len); if (IS_ERR(em)) { ret = PTR_ERR(em); goto out; } *map = em; len = min(len, em->len - (start - em->start)); if (len < prev_len) btrfs_delalloc_release_metadata(BTRFS_I(inode), prev_len - len, true); } /* * We have created our ordered extent, so we can now release our reservation * for an outstanding extent. */ btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len); /* * Need to update the i_size under the extent lock so buffered * readers will get the updated i_size when we unlock. */ if (start + len > i_size_read(inode)) i_size_write(inode, start + len); out: if (ret && space_reserved) { btrfs_delalloc_release_extents(BTRFS_I(inode), len); btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true); } *lenp = len; return ret; } static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_map *em; struct extent_state *cached_state = NULL; struct btrfs_dio_data *dio_data = iter->private; u64 lockstart, lockend; const bool write = !!(flags & IOMAP_WRITE); int ret = 0; u64 len = length; const u64 data_alloc_len = length; u32 unlock_bits = EXTENT_LOCKED; /* * We could potentially fault if we have a buffer > PAGE_SIZE, and if * we're NOWAIT we may submit a bio for a partial range and return * EIOCBQUEUED, which would result in an errant short read. * * The best way to handle this would be to allow for partial completions * of iocb's, so we could submit the partial bio, return and fault in * the rest of the pages, and then submit the io for the rest of the * range. However we don't have that currently, so simply return * -EAGAIN at this point so that the normal path is used. */ if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE) return -EAGAIN; /* * Cap the size of reads to that usually seen in buffered I/O as we need * to allocate a contiguous array for the checksums. */ if (!write) len = min_t(u64, len, fs_info->sectorsize * BTRFS_MAX_BIO_SECTORS); lockstart = start; lockend = start + len - 1; /* * iomap_dio_rw() only does filemap_write_and_wait_range(), which isn't * enough if we've written compressed pages to this area, so we need to * flush the dirty pages again to make absolutely sure that any * outstanding dirty pages are on disk - the first flush only starts * compression on the data, while keeping the pages locked, so by the * time the second flush returns we know bios for the compressed pages * were submitted and finished, and the pages no longer under writeback. * * If we have a NOWAIT request and we have any pages in the range that * are locked, likely due to compression still in progress, we don't want * to block on page locks. We also don't want to block on pages marked as * dirty or under writeback (same as for the non-compression case). * iomap_dio_rw() did the same check, but after that and before we got * here, mmap'ed writes may have happened or buffered reads started * (readpage() and readahead(), which lock pages), as we haven't locked * the file range yet. */ if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags)) { if (flags & IOMAP_NOWAIT) { if (filemap_range_needs_writeback(inode->i_mapping, lockstart, lockend)) return -EAGAIN; } else { ret = filemap_fdatawrite_range(inode->i_mapping, start, start + length - 1); if (ret) return ret; } } memset(dio_data, 0, sizeof(*dio_data)); /* * We always try to allocate data space and must do it before locking * the file range, to avoid deadlocks with concurrent writes to the same * range if the range has several extents and the writes don't expand the * current i_size (the inode lock is taken in shared mode). If we fail to * allocate data space here we continue and later, after locking the * file range, we fail with ENOSPC only if we figure out we can not do a * NOCOW write. */ if (write && !(flags & IOMAP_NOWAIT)) { ret = btrfs_check_data_free_space(BTRFS_I(inode), &dio_data->data_reserved, start, data_alloc_len, false); if (!ret) dio_data->data_space_reserved = true; else if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) goto err; } /* * If this errors out it's because we couldn't invalidate pagecache for * this range and we need to fallback to buffered IO, or we are doing a * NOWAIT read/write and we need to block. */ ret = lock_extent_direct(inode, lockstart, lockend, &cached_state, flags); if (ret < 0) goto err; em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); if (IS_ERR(em)) { ret = PTR_ERR(em); goto unlock_err; } /* * Ok for INLINE and COMPRESSED extents we need to fallback on buffered * io. INLINE is special, and we could probably kludge it in here, but * it's still buffered so for safety lets just fall back to the generic * buffered path. * * For COMPRESSED we _have_ to read the entire extent in so we can * decompress it, so there will be buffering required no matter what we * do, so go ahead and fallback to buffered. * * We return -ENOTBLK because that's what makes DIO go ahead and go back * to buffered IO. Don't blame me, this is the price we pay for using * the generic code. */ if (btrfs_extent_map_is_compressed(em) || em->disk_bytenr == EXTENT_MAP_INLINE) { btrfs_free_extent_map(em); /* * If we are in a NOWAIT context, return -EAGAIN in order to * fallback to buffered IO. This is not only because we can * block with buffered IO (no support for NOWAIT semantics at * the moment) but also to avoid returning short reads to user * space - this happens if we were able to read some data from * previous non-compressed extents and then when we fallback to * buffered IO, at btrfs_file_read_iter() by calling * filemap_read(), we fail to fault in pages for the read buffer, * in which case filemap_read() returns a short read (the number * of bytes previously read is > 0, so it does not return -EFAULT). */ ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK; goto unlock_err; } len = min(len, em->len - (start - em->start)); /* * If we have a NOWAIT request and the range contains multiple extents * (or a mix of extents and holes), then we return -EAGAIN to make the * caller fallback to a context where it can do a blocking (without * NOWAIT) request. This way we avoid doing partial IO and returning * success to the caller, which is not optimal for writes and for reads * it can result in unexpected behaviour for an application. * * When doing a read, because we use IOMAP_DIO_PARTIAL when calling * iomap_dio_rw(), we can end up returning less data then what the caller * asked for, resulting in an unexpected, and incorrect, short read. * That is, the caller asked to read N bytes and we return less than that, * which is wrong unless we are crossing EOF. This happens if we get a * page fault error when trying to fault in pages for the buffer that is * associated to the struct iov_iter passed to iomap_dio_rw(), and we * have previously submitted bios for other extents in the range, in * which case iomap_dio_rw() may return us EIOCBQUEUED if not all of * those bios have completed by the time we get the page fault error, * which we return back to our caller - we should only return EIOCBQUEUED * after we have submitted bios for all the extents in the range. */ if ((flags & IOMAP_NOWAIT) && len < length) { btrfs_free_extent_map(em); ret = -EAGAIN; goto unlock_err; } if (write) { ret = btrfs_get_blocks_direct_write(&em, inode, dio_data, start, &len, flags); if (ret < 0) goto unlock_err; /* Recalc len in case the new em is smaller than requested */ len = min(len, em->len - (start - em->start)); if (dio_data->data_space_reserved) { u64 release_offset; u64 release_len = 0; if (dio_data->nocow_done) { release_offset = start; release_len = data_alloc_len; } else if (len < data_alloc_len) { release_offset = start + len; release_len = data_alloc_len - len; } if (release_len > 0) btrfs_free_reserved_data_space(BTRFS_I(inode), dio_data->data_reserved, release_offset, release_len); } } /* * Translate extent map information to iomap. * We trim the extents (and move the addr) even though iomap code does * that, since we have locked only the parts we are performing I/O in. */ if ((em->disk_bytenr == EXTENT_MAP_HOLE) || ((em->flags & EXTENT_FLAG_PREALLOC) && !write)) { iomap->addr = IOMAP_NULL_ADDR; iomap->type = IOMAP_HOLE; } else { iomap->addr = btrfs_extent_map_block_start(em) + (start - em->start); iomap->type = IOMAP_MAPPED; } iomap->offset = start; iomap->bdev = fs_info->fs_devices->latest_dev->bdev; iomap->length = len; btrfs_free_extent_map(em); /* * Reads will hold the EXTENT_DIO_LOCKED bit until the io is completed, * writes only hold it for this part. We hold the extent lock until * we're completely done with the extent map to make sure it remains * valid. */ if (write) unlock_bits |= EXTENT_DIO_LOCKED; btrfs_clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, &cached_state); /* We didn't use everything, unlock the dio extent for the remainder. */ if (!write && (start + len) < lockend) btrfs_unlock_dio_extent(&BTRFS_I(inode)->io_tree, start + len, lockend, NULL); return 0; unlock_err: /* * Don't use EXTENT_LOCK_BITS here in case we extend it later and forget * to update this, be explicit that we expect EXTENT_LOCKED and * EXTENT_DIO_LOCKED to be set here, and so that's what we're clearing. */ btrfs_clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, EXTENT_LOCKED | EXTENT_DIO_LOCKED, &cached_state); err: if (dio_data->data_space_reserved) { btrfs_free_reserved_data_space(BTRFS_I(inode), dio_data->data_reserved, start, data_alloc_len); extent_changeset_free(dio_data->data_reserved); } return ret; } static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned int flags, struct iomap *iomap) { struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); struct btrfs_dio_data *dio_data = iter->private; size_t submitted = dio_data->submitted; const bool write = !!(flags & IOMAP_WRITE); int ret = 0; if (!write && (iomap->type == IOMAP_HOLE)) { /* If reading from a hole, unlock and return */ btrfs_unlock_dio_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1, NULL); return 0; } if (submitted < length) { pos += submitted; length -= submitted; if (write) btrfs_finish_ordered_extent(dio_data->ordered, NULL, pos, length, false); else btrfs_unlock_dio_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1, NULL); ret = -ENOTBLK; } if (write) { btrfs_put_ordered_extent(dio_data->ordered); dio_data->ordered = NULL; } if (write) extent_changeset_free(dio_data->data_reserved); return ret; } static void btrfs_dio_end_io(struct btrfs_bio *bbio) { struct btrfs_dio_private *dip = container_of(bbio, struct btrfs_dio_private, bbio); struct btrfs_inode *inode = bbio->inode; struct bio *bio = &bbio->bio; if (bio->bi_status) { btrfs_warn(inode->root->fs_info, "direct IO failed ino %llu op 0x%0x offset %#llx len %u err no %d", btrfs_ino(inode), bio->bi_opf, dip->file_offset, dip->bytes, bio->bi_status); } if (btrfs_op(bio) == BTRFS_MAP_WRITE) { btrfs_finish_ordered_extent(bbio->ordered, NULL, dip->file_offset, dip->bytes, !bio->bi_status); } else { btrfs_unlock_dio_extent(&inode->io_tree, dip->file_offset, dip->file_offset + dip->bytes - 1, NULL); } bbio->bio.bi_private = bbio->private; iomap_dio_bio_end_io(bio); } static int btrfs_extract_ordered_extent(struct btrfs_bio *bbio, struct btrfs_ordered_extent *ordered) { u64 start = (u64)bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; u64 len = bbio->bio.bi_iter.bi_size; struct btrfs_ordered_extent *new; int ret; /* Must always be called for the beginning of an ordered extent. */ if (WARN_ON_ONCE(start != ordered->disk_bytenr)) return -EINVAL; /* No need to split if the ordered extent covers the entire bio. */ if (ordered->disk_num_bytes == len) { refcount_inc(&ordered->refs); bbio->ordered = ordered; return 0; } /* * Don't split the extent_map for NOCOW extents, as we're writing into * a pre-existing one. */ if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) { ret = btrfs_split_extent_map(bbio->inode, bbio->file_offset, ordered->num_bytes, len, ordered->disk_bytenr); if (ret) return ret; } new = btrfs_split_ordered_extent(ordered, len); if (IS_ERR(new)) return PTR_ERR(new); bbio->ordered = new; return 0; } static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio, loff_t file_offset) { struct btrfs_bio *bbio = btrfs_bio(bio); struct btrfs_dio_private *dip = container_of(bbio, struct btrfs_dio_private, bbio); struct btrfs_dio_data *dio_data = iter->private; btrfs_bio_init(bbio, BTRFS_I(iter->inode)->root->fs_info, btrfs_dio_end_io, bio->bi_private); bbio->inode = BTRFS_I(iter->inode); bbio->file_offset = file_offset; dip->file_offset = file_offset; dip->bytes = bio->bi_iter.bi_size; dio_data->submitted += bio->bi_iter.bi_size; /* * Check if we are doing a partial write. If we are, we need to split * the ordered extent to match the submitted bio. Hang on to the * remaining unfinishable ordered_extent in dio_data so that it can be * cancelled in iomap_end to avoid a deadlock wherein faulting the * remaining pages is blocked on the outstanding ordered extent. */ if (iter->flags & IOMAP_WRITE) { int ret; ret = btrfs_extract_ordered_extent(bbio, dio_data->ordered); if (ret) { btrfs_finish_ordered_extent(dio_data->ordered, NULL, file_offset, dip->bytes, !ret); bio->bi_status = errno_to_blk_status(ret); iomap_dio_bio_end_io(bio); return; } } btrfs_submit_bbio(bbio, 0); } static const struct iomap_ops btrfs_dio_iomap_ops = { .iomap_begin = btrfs_dio_iomap_begin, .iomap_end = btrfs_dio_iomap_end, }; static const struct iomap_dio_ops btrfs_dio_ops = { .submit_io = btrfs_dio_submit_io, .bio_set = &btrfs_dio_bioset, }; static ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) { struct btrfs_dio_data data = { 0 }; return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, IOMAP_DIO_PARTIAL, &data, done_before); } static struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) { struct btrfs_dio_data data = { 0 }; return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, IOMAP_DIO_PARTIAL, &data, done_before); } static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, const struct iov_iter *iter, loff_t offset) { const u32 blocksize_mask = fs_info->sectorsize - 1; if (offset & blocksize_mask) return -EINVAL; if (iov_iter_alignment(iter) & blocksize_mask) return -EINVAL; /* * For bs > ps support, we heavily rely on large folios to make sure no * block will cross large folio boundaries. * * But memory provided by direct IO is only virtually contiguous, not * physically contiguous, and will break the btrfs' large folio requirement. * * So for bs > ps support, all direct IOs should fallback to buffered ones. */ if (fs_info->sectorsize > PAGE_SIZE) return -EINVAL; return 0; } ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); loff_t pos; ssize_t written = 0; ssize_t written_buffered; size_t prev_left = 0; loff_t endbyte; ssize_t ret; unsigned int ilock_flags = 0; struct iomap_dio *dio; if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; /* * If the write DIO is within EOF, use a shared lock and also only if * security bits will likely not be dropped by file_remove_privs() called * from btrfs_write_check(). Either will need to be rechecked after the * lock was acquired. */ if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode) && IS_NOSEC(inode)) ilock_flags |= BTRFS_ILOCK_SHARED; relock: ret = btrfs_inode_lock(BTRFS_I(inode), ilock_flags); if (ret < 0) return ret; /* Shared lock cannot be used with security bits set. */ if ((ilock_flags & BTRFS_ILOCK_SHARED) && !IS_NOSEC(inode)) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); ilock_flags &= ~BTRFS_ILOCK_SHARED; goto relock; } ret = generic_write_checks(iocb, from); if (ret <= 0) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); return ret; } ret = btrfs_write_check(iocb, ret); if (ret < 0) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); goto out; } pos = iocb->ki_pos; /* * Re-check since file size may have changed just before taking the * lock or pos may have changed because of O_APPEND in generic_write_check() */ if ((ilock_flags & BTRFS_ILOCK_SHARED) && pos + iov_iter_count(from) > i_size_read(inode)) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); ilock_flags &= ~BTRFS_ILOCK_SHARED; goto relock; } if (check_direct_IO(fs_info, from, pos)) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); goto buffered; } /* * We can't control the folios being passed in, applications can write * to them while a direct IO write is in progress. This means the * content might change after we calculated the data checksum. * Therefore we can end up storing a checksum that doesn't match the * persisted data. * * To be extra safe and avoid false data checksum mismatch, if the * inode requires data checksum, just fallback to buffered IO. * For buffered IO we have full control of page cache and can ensure * no one is modifying the content during writeback. */ if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); goto buffered; } /* * The iov_iter can be mapped to the same file range we are writing to. * If that's the case, then we will deadlock in the iomap code, because * it first calls our callback btrfs_dio_iomap_begin(), which will create * an ordered extent, and after that it will fault in the pages that the * iov_iter refers to. During the fault in we end up in the readahead * pages code (starting at btrfs_readahead()), which will lock the range, * find that ordered extent and then wait for it to complete (at * btrfs_lock_and_flush_ordered_range()), resulting in a deadlock since * obviously the ordered extent can never complete as we didn't submit * yet the respective bio(s). This always happens when the buffer is * memory mapped to the same file range, since the iomap DIO code always * invalidates pages in the target file range (after starting and waiting * for any writeback). * * So here we disable page faults in the iov_iter and then retry if we * got -EFAULT, faulting in the pages before the retry. */ again: from->nofault = true; dio = btrfs_dio_write(iocb, from, written); from->nofault = false; if (IS_ERR_OR_NULL(dio)) { ret = PTR_ERR_OR_ZERO(dio); } else { /* * If we have a synchronous write, we must make sure the fsync * triggered by the iomap_dio_complete() call below doesn't * deadlock on the inode lock - we are already holding it and we * can't call it after unlocking because we may need to complete * partial writes due to the input buffer (or parts of it) not * being already faulted in. */ ASSERT(current->journal_info == NULL); current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB; ret = iomap_dio_complete(dio); current->journal_info = NULL; } /* No increment (+=) because iomap returns a cumulative value. */ if (ret > 0) written = ret; if (iov_iter_count(from) > 0 && (ret == -EFAULT || ret > 0)) { const size_t left = iov_iter_count(from); /* * We have more data left to write. Try to fault in as many as * possible of the remainder pages and retry. We do this without * releasing and locking again the inode, to prevent races with * truncate. * * Also, in case the iov refers to pages in the file range of the * file we want to write to (due to a mmap), we could enter an * infinite loop if we retry after faulting the pages in, since * iomap will invalidate any pages in the range early on, before * it tries to fault in the pages of the iov. So we keep track of * how much was left of iov in the previous EFAULT and fallback * to buffered IO in case we haven't made any progress. */ if (left == prev_left) { ret = -ENOTBLK; } else { fault_in_iov_iter_readable(from, left); prev_left = left; goto again; } } btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); /* * If 'ret' is -ENOTBLK or we have not written all data, then it means * we must fallback to buffered IO. */ if ((ret < 0 && ret != -ENOTBLK) || !iov_iter_count(from)) goto out; buffered: /* * If we are in a NOWAIT context, then return -EAGAIN to signal the caller * it must retry the operation in a context where blocking is acceptable, * because even if we end up not blocking during the buffered IO attempt * below, we will block when flushing and waiting for the IO. */ if (iocb->ki_flags & IOCB_NOWAIT) { ret = -EAGAIN; goto out; } pos = iocb->ki_pos; written_buffered = btrfs_buffered_write(iocb, from); if (written_buffered < 0) { ret = written_buffered; goto out; } /* * Ensure all data is persisted. We want the next direct IO read to be * able to read what was just written. */ endbyte = pos + written_buffered - 1; ret = btrfs_fdatawrite_range(BTRFS_I(inode), pos, endbyte); if (ret) goto out; ret = filemap_fdatawait_range(inode->i_mapping, pos, endbyte); if (ret) goto out; written += written_buffered; iocb->ki_pos = pos + written_buffered; invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); out: return ret < 0 ? ret : written; } static int check_direct_read(struct btrfs_fs_info *fs_info, const struct iov_iter *iter, loff_t offset) { int ret; int i, seg; ret = check_direct_IO(fs_info, iter, offset); if (ret < 0) return ret; if (!iter_is_iovec(iter)) return 0; for (seg = 0; seg < iter->nr_segs; seg++) { for (i = seg + 1; i < iter->nr_segs; i++) { const struct iovec *iov1 = iter_iov(iter) + seg; const struct iovec *iov2 = iter_iov(iter) + i; if (iov1->iov_base == iov2->iov_base) return -EINVAL; } } return 0; } ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); size_t prev_left = 0; ssize_t read = 0; ssize_t ret; if (fsverity_active(inode)) return 0; if (check_direct_read(inode_to_fs_info(inode), to, iocb->ki_pos)) return 0; btrfs_inode_lock(BTRFS_I(inode), BTRFS_ILOCK_SHARED); again: /* * This is similar to what we do for direct IO writes, see the comment * at btrfs_direct_write(), but we also disable page faults in addition * to disabling them only at the iov_iter level. This is because when * reading from a hole or prealloc extent, iomap calls iov_iter_zero(), * which can still trigger page fault ins despite having set ->nofault * to true of our 'to' iov_iter. * * The difference to direct IO writes is that we deadlock when trying * to lock the extent range in the inode's tree during he page reads * triggered by the fault in (while for writes it is due to waiting for * our own ordered extent). This is because for direct IO reads, * btrfs_dio_iomap_begin() returns with the extent range locked, which * is only unlocked in the endio callback (end_bio_extent_readpage()). */ pagefault_disable(); to->nofault = true; ret = btrfs_dio_read(iocb, to, read); to->nofault = false; pagefault_enable(); /* No increment (+=) because iomap returns a cumulative value. */ if (ret > 0) read = ret; if (iov_iter_count(to) > 0 && (ret == -EFAULT || ret > 0)) { const size_t left = iov_iter_count(to); if (left == prev_left) { /* * We didn't make any progress since the last attempt, * fallback to a buffered read for the remainder of the * range. This is just to avoid any possibility of looping * for too long. */ ret = read; } else { /* * We made some progress since the last retry or this is * the first time we are retrying. Fault in as many pages * as possible and retry. */ fault_in_iov_iter_writeable(to, left); prev_left = left; goto again; } } btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_SHARED); return ret < 0 ? ret : read; } int __init btrfs_init_dio(void) { if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE, offsetof(struct btrfs_dio_private, bbio.bio), BIOSET_NEED_BVECS)) return -ENOMEM; return 0; } void __cold btrfs_destroy_dio(void) { bioset_exit(&btrfs_dio_bioset); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #ifndef ZSTD_BITS_H #define ZSTD_BITS_H #include "mem.h" MEM_STATIC unsigned ZSTD_countTrailingZeros32_fallback(U32 val) { assert(val != 0); { static const U32 DeBruijnBytePos[32] = {0, 1, 28, 2, 29, 14, 24, 3, 30, 22, 20, 15, 25, 17, 4, 8, 31, 27, 13, 23, 21, 19, 16, 7, 26, 12, 18, 6, 11, 5, 10, 9}; return DeBruijnBytePos[((U32) ((val & -(S32) val) * 0x077CB531U)) >> 27]; } } MEM_STATIC unsigned ZSTD_countTrailingZeros32(U32 val) { assert(val != 0); #if (__GNUC__ >= 4) return (unsigned)__builtin_ctz(val); #else return ZSTD_countTrailingZeros32_fallback(val); #endif } MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val) { assert(val != 0); { static const U32 DeBruijnClz[32] = {0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31}; val |= val >> 1; val |= val >> 2; val |= val >> 4; val |= val >> 8; val |= val >> 16; return 31 - DeBruijnClz[(val * 0x07C4ACDDU) >> 27]; } } MEM_STATIC unsigned ZSTD_countLeadingZeros32(U32 val) { assert(val != 0); #if (__GNUC__ >= 4) return (unsigned)__builtin_clz(val); #else return ZSTD_countLeadingZeros32_fallback(val); #endif } MEM_STATIC unsigned ZSTD_countTrailingZeros64(U64 val) { assert(val != 0); #if (__GNUC__ >= 4) && defined(__LP64__) return (unsigned)__builtin_ctzll(val); #else { U32 mostSignificantWord = (U32)(val >> 32); U32 leastSignificantWord = (U32)val; if (leastSignificantWord == 0) { return 32 + ZSTD_countTrailingZeros32(mostSignificantWord); } else { return ZSTD_countTrailingZeros32(leastSignificantWord); } } #endif } MEM_STATIC unsigned ZSTD_countLeadingZeros64(U64 val) { assert(val != 0); #if (__GNUC__ >= 4) return (unsigned)(__builtin_clzll(val)); #else { U32 mostSignificantWord = (U32)(val >> 32); U32 leastSignificantWord = (U32)val; if (mostSignificantWord == 0) { return 32 + ZSTD_countLeadingZeros32(leastSignificantWord); } else { return ZSTD_countLeadingZeros32(mostSignificantWord); } } #endif } MEM_STATIC unsigned ZSTD_NbCommonBytes(size_t val) { if (MEM_isLittleEndian()) { if (MEM_64bits()) { return ZSTD_countTrailingZeros64((U64)val) >> 3; } else { return ZSTD_countTrailingZeros32((U32)val) >> 3; } } else { /* Big Endian CPU */ if (MEM_64bits()) { return ZSTD_countLeadingZeros64((U64)val) >> 3; } else { return ZSTD_countLeadingZeros32((U32)val) >> 3; } } } MEM_STATIC unsigned ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus */ { assert(val != 0); return 31 - ZSTD_countLeadingZeros32(val); } /* ZSTD_rotateRight_*(): * Rotates a bitfield to the right by "count" bits. * https://en.wikipedia.org/w/index.php?title=Circular_shift&oldid=991635599#Implementing_circular_shifts */ MEM_STATIC U64 ZSTD_rotateRight_U64(U64 const value, U32 count) { assert(count < 64); count &= 0x3F; /* for fickle pattern recognition */ return (value >> count) | (U64)(value << ((0U - count) & 0x3F)); } MEM_STATIC U32 ZSTD_rotateRight_U32(U32 const value, U32 count) { assert(count < 32); count &= 0x1F; /* for fickle pattern recognition */ return (value >> count) | (U32)(value << ((0U - count) & 0x1F)); } MEM_STATIC U16 ZSTD_rotateRight_U16(U16 const value, U32 count) { assert(count < 16); count &= 0x0F; /* for fickle pattern recognition */ return (value >> count) | (U16)(value << ((0U - count) & 0x0F)); } #endif /* ZSTD_BITS_H */ |
| 114 114 114 159 112 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * CRC32C chksum * *@Article{castagnoli-crc, * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 * and 32 Parity Bits}}, * journal = IEEE Transactions on Communication, * year = {1993}, * volume = {41}, * number = {6}, * pages = {}, * month = {June}, *} * Used by the iSCSI driver, possibly others, and derived from * the iscsi-crc.c module of the linux-iscsi driver at * http://linux-iscsi.sourceforge.net. * * Following the example of lib/crc32, this function is intended to be * flexible and useful for all users. Modules that currently have their * own crc32c, but hopefully may be able to use this one are: * net/sctp (please add all your doco to here if you change to * use this one!) * <endoflist> * * Copyright (c) 2004 Cisco Systems, Inc. * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/crc32.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 struct chksum_ctx { u32 key; }; struct chksum_desc_ctx { u32 crc; }; /* * Steps through buffer one byte at a time, calculates reflected * crc using table. */ static int chksum_init(struct shash_desc *desc) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = mctx->key; return 0; } /* * Setting the seed allows arbitrary accumulators and flexible XOR policy * If your algorithm starts with ~0, then XOR with ~0 before you set * the seed. */ static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct chksum_ctx *mctx = crypto_shash_ctx(tfm); if (keylen != sizeof(mctx->key)) return -EINVAL; mctx->key = get_unaligned_le32(key); return 0; } static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = crc32c(ctx->crc, data, length); return 0; } static int chksum_final(struct shash_desc *desc, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); put_unaligned_le32(~ctx->crc, out); return 0; } static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { put_unaligned_le32(~crc32c(*crcp, data, len), out); return 0; } static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); return __chksum_finup(&ctx->crc, data, len, out); } static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); return __chksum_finup(&mctx->key, data, length, out); } static int crc32c_cra_init(struct crypto_tfm *tfm) { struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); mctx->key = ~0; return 0; } static struct shash_alg alg = { .digestsize = CHKSUM_DIGEST_SIZE, .setkey = chksum_setkey, .init = chksum_init, .update = chksum_update, .final = chksum_final, .finup = chksum_finup, .digest = chksum_digest, .descsize = sizeof(struct chksum_desc_ctx), .base.cra_name = "crc32c", .base.cra_driver_name = "crc32c-lib", .base.cra_priority = 100, .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .base.cra_blocksize = CHKSUM_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct chksum_ctx), .base.cra_module = THIS_MODULE, .base.cra_init = crc32c_cra_init, }; static int __init crc32c_mod_init(void) { return crypto_register_shash(&alg); } static void __exit crc32c_mod_fini(void) { crypto_unregister_shash(&alg); } module_init(crc32c_mod_init); module_exit(crc32c_mod_fini); MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("crc32c"); |
| 2 2 2 1 1 1 2 2 2 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vhost transport for vsock * * Copyright (C) 2013-2015 Red Hat, Inc. * Author: Asias He <asias@redhat.com> * Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/miscdevice.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <net/sock.h> #include <linux/virtio_vsock.h> #include <linux/vhost.h> #include <linux/hashtable.h> #include <net/af_vsock.h> #include "vhost.h" #define VHOST_VSOCK_DEFAULT_HOST_CID 2 /* Max number of bytes transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others. */ #define VHOST_VSOCK_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others with * small pkts. */ #define VHOST_VSOCK_PKT_WEIGHT 256 enum { VHOST_VSOCK_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_F_ACCESS_PLATFORM) | (1ULL << VIRTIO_VSOCK_F_SEQPACKET) }; enum { VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) }; /* Used to track all the vhost_vsock instances on the system. */ static DEFINE_MUTEX(vhost_vsock_mutex); static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8); struct vhost_vsock { struct vhost_dev dev; struct vhost_virtqueue vqs[2]; /* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */ struct hlist_node hash; struct vhost_work send_pkt_work; struct sk_buff_head send_pkt_queue; /* host->guest pending packets */ atomic_t queued_replies; u32 guest_cid; bool seqpacket_allow; }; static u32 vhost_transport_get_local_cid(void) { return VHOST_VSOCK_DEFAULT_HOST_CID; } /* Callers that dereference the return value must hold vhost_vsock_mutex or the * RCU read lock. */ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) { struct vhost_vsock *vsock; hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) { u32 other_cid = vsock->guest_cid; /* Skip instances that have no CID yet */ if (other_cid == 0) continue; if (other_cid == guest_cid) return vsock; } return NULL; } static void vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct vhost_virtqueue *vq) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; int pkts = 0, total_len = 0; bool added = false; bool restart_tx = false; mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq)) goto out; if (!vq_meta_prefetch(vq)) goto out; /* Avoid further vmexits, we're already processing the virtqueue */ vhost_disable_notify(&vsock->dev, vq); do { struct virtio_vsock_hdr *hdr; size_t iov_len, payload_len; struct iov_iter iov_iter; u32 flags_to_restore = 0; struct sk_buff *skb; unsigned out, in; size_t nbytes; u32 offset; int head; skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); if (!skb) { vhost_enable_notify(&vsock->dev, vq); break; } head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } if (head == vq->num) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); /* We cannot finish yet if more buffers snuck in while * re-enabling notify. */ if (unlikely(vhost_enable_notify(&vsock->dev, vq))) { vhost_disable_notify(&vsock->dev, vq); continue; } break; } if (out) { kfree_skb(skb); vq_err(vq, "Expected 0 output buffers, got %u\n", out); break; } iov_len = iov_length(&vq->iov[out], in); if (iov_len < sizeof(*hdr)) { kfree_skb(skb); vq_err(vq, "Buffer len [%zu] too small\n", iov_len); break; } iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[out], in, iov_len); offset = VIRTIO_VSOCK_SKB_CB(skb)->offset; payload_len = skb->len - offset; hdr = virtio_vsock_hdr(skb); /* If the packet is greater than the space available in the * buffer, we split it using multiple buffers. */ if (payload_len > iov_len - sizeof(*hdr)) { payload_len = iov_len - sizeof(*hdr); /* As we are copying pieces of large packet's buffer to * small rx buffers, headers of packets in rx queue are * created dynamically and are initialized with header * of current packet(except length). But in case of * SOCK_SEQPACKET, we also must clear message delimeter * bit (VIRTIO_VSOCK_SEQ_EOM) and MSG_EOR bit * (VIRTIO_VSOCK_SEQ_EOR) if set. Otherwise, * there will be sequence of packets with these * bits set. After initialized header will be copied to * rx buffer, these required bits will be restored. */ if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM; if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) { hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR; } } } /* Set the correct length in the header */ hdr->len = cpu_to_le32(payload_len); nbytes = copy_to_iter(hdr, sizeof(*hdr), &iov_iter); if (nbytes != sizeof(*hdr)) { kfree_skb(skb); vq_err(vq, "Faulted on copying pkt hdr\n"); break; } if (skb_copy_datagram_iter(skb, offset, &iov_iter, payload_len)) { kfree_skb(skb); vq_err(vq, "Faulted on copying pkt buf\n"); break; } /* Deliver to monitoring devices all packets that we * will transmit. */ virtio_transport_deliver_tap_pkt(skb); vhost_add_used(vq, head, sizeof(*hdr) + payload_len); added = true; VIRTIO_VSOCK_SKB_CB(skb)->offset += payload_len; total_len += payload_len; /* If we didn't send all the payload we can requeue the packet * to send it with the next available buffer. */ if (VIRTIO_VSOCK_SKB_CB(skb)->offset < skb->len) { hdr->flags |= cpu_to_le32(flags_to_restore); /* We are queueing the same skb to handle * the remaining bytes, and we want to deliver it * to monitoring devices in the next iteration. */ virtio_vsock_skb_clear_tap_delivered(skb); virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); } else { if (virtio_vsock_skb_reply(skb)) { int val; val = atomic_dec_return(&vsock->queued_replies); /* Do we have resources to resume tx * processing? */ if (val + 1 == tx_vq->num) restart_tx = true; } virtio_transport_consume_skb_sent(skb, true); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); out: mutex_unlock(&vq->mutex); if (restart_tx) vhost_poll_queue(&tx_vq->poll); } static void vhost_transport_send_pkt_work(struct vhost_work *work) { struct vhost_virtqueue *vq; struct vhost_vsock *vsock; vsock = container_of(work, struct vhost_vsock, send_pkt_work); vq = &vsock->vqs[VSOCK_VQ_RX]; vhost_transport_do_send_pkt(vsock, vq); } static int vhost_transport_send_pkt(struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vhost_vsock *vsock; int len = skb->len; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid)); if (!vsock) { rcu_read_unlock(); kfree_skb(skb); return -ENODEV; } if (virtio_vsock_skb_reply(skb)) atomic_inc(&vsock->queued_replies); virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work); rcu_read_unlock(); return len; } static int vhost_transport_cancel_pkt(struct vsock_sock *vsk) { struct vhost_vsock *vsock; int cnt = 0; int ret = -ENODEV; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ vsock = vhost_vsock_get(vsk->remote_addr.svm_cid); if (!vsock) goto out; cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue); if (cnt) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; int new_cnt; new_cnt = atomic_sub_return(cnt, &vsock->queued_replies); if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num) vhost_poll_queue(&tx_vq->poll); } ret = 0; out: rcu_read_unlock(); return ret; } static struct sk_buff * vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, unsigned int out, unsigned int in) { struct virtio_vsock_hdr *hdr; struct iov_iter iov_iter; struct sk_buff *skb; size_t payload_len; size_t nbytes; size_t len; if (in != 0) { vq_err(vq, "Expected 0 input buffers, got %u\n", in); return NULL; } len = iov_length(vq->iov, out); if (len < VIRTIO_VSOCK_SKB_HEADROOM || len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM) return NULL; /* len contains both payload and hdr */ skb = virtio_vsock_alloc_skb(len, GFP_KERNEL); if (!skb) return NULL; iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len); hdr = virtio_vsock_hdr(skb); nbytes = copy_from_iter(hdr, sizeof(*hdr), &iov_iter); if (nbytes != sizeof(*hdr)) { vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n", sizeof(*hdr), nbytes); kfree_skb(skb); return NULL; } payload_len = le32_to_cpu(hdr->len); /* No payload */ if (!payload_len) return skb; /* The pkt is too big or the length in the header is invalid */ if (payload_len + sizeof(*hdr) > len) { kfree_skb(skb); return NULL; } virtio_vsock_skb_put(skb, payload_len); if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) { vq_err(vq, "Failed to copy %zu byte payload\n", payload_len); kfree_skb(skb); return NULL; } return skb; } /* Is there space left for replies to rx packets? */ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) { struct vhost_virtqueue *vq = &vsock->vqs[VSOCK_VQ_TX]; int val; smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */ val = atomic_read(&vsock->queued_replies); return val < vq->num; } static bool vhost_transport_msgzerocopy_allow(void) { return true; } static bool vhost_transport_seqpacket_allow(u32 remote_cid); static struct virtio_transport vhost_transport = { .transport = { .module = THIS_MODULE, .get_local_cid = vhost_transport_get_local_cid, .init = virtio_transport_do_socket_init, .destruct = virtio_transport_destruct, .release = virtio_transport_release, .connect = virtio_transport_connect, .shutdown = virtio_transport_shutdown, .cancel_pkt = vhost_transport_cancel_pkt, .dgram_enqueue = virtio_transport_dgram_enqueue, .dgram_dequeue = virtio_transport_dgram_dequeue, .dgram_bind = virtio_transport_dgram_bind, .dgram_allow = virtio_transport_dgram_allow, .stream_enqueue = virtio_transport_stream_enqueue, .stream_dequeue = virtio_transport_stream_dequeue, .stream_has_data = virtio_transport_stream_has_data, .stream_has_space = virtio_transport_stream_has_space, .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, .seqpacket_allow = vhost_transport_seqpacket_allow, .seqpacket_has_data = virtio_transport_seqpacket_has_data, .msgzerocopy_allow = vhost_transport_msgzerocopy_allow, .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, .notify_send_init = virtio_transport_notify_send_init, .notify_send_pre_block = virtio_transport_notify_send_pre_block, .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, .unsent_bytes = virtio_transport_unsent_bytes, .read_skb = virtio_transport_read_skb, }, .send_pkt = vhost_transport_send_pkt, }; static bool vhost_transport_seqpacket_allow(u32 remote_cid) { struct vhost_vsock *vsock; bool seqpacket_allow = false; rcu_read_lock(); vsock = vhost_vsock_get(remote_cid); if (vsock) seqpacket_allow = vsock->seqpacket_allow; rcu_read_unlock(); return seqpacket_allow; } static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); int head, pkts = 0, total_len = 0; unsigned int out, in; struct sk_buff *skb; bool added = false; mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq)) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&vsock->dev, vq); do { struct virtio_vsock_hdr *hdr; if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue * callbacks disabled. */ goto no_more_replies; } head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) break; if (head == vq->num) { if (unlikely(vhost_enable_notify(&vsock->dev, vq))) { vhost_disable_notify(&vsock->dev, vq); continue; } break; } skb = vhost_vsock_alloc_skb(vq, out, in); if (!skb) { vq_err(vq, "Faulted on pkt\n"); continue; } total_len += sizeof(*hdr) + skb->len; /* Deliver to monitoring devices all received packets */ virtio_transport_deliver_tap_pkt(skb); hdr = virtio_vsock_hdr(skb); /* Only accept correctly addressed packets */ if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid && le64_to_cpu(hdr->dst_cid) == vhost_transport_get_local_cid()) virtio_transport_recv_pkt(&vhost_transport, skb); else kfree_skb(skb); vhost_add_used(vq, head, 0); added = true; } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); no_more_replies: if (added) vhost_signal(&vsock->dev, vq); out: mutex_unlock(&vq->mutex); } static void vhost_vsock_handle_rx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); vhost_transport_do_send_pkt(vsock, vq); } static int vhost_vsock_start(struct vhost_vsock *vsock) { struct vhost_virtqueue *vq; size_t i; int ret; mutex_lock(&vsock->dev.mutex); ret = vhost_dev_check_owner(&vsock->dev); if (ret) goto err; for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); if (!vhost_vq_access_ok(vq)) { ret = -EFAULT; goto err_vq; } if (!vhost_vq_get_backend(vq)) { vhost_vq_set_backend(vq, vsock); ret = vhost_vq_init_access(vq); if (ret) goto err_vq; } mutex_unlock(&vq->mutex); } /* Some packets may have been queued before the device was started, * let's kick the send worker to send them. */ vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work); mutex_unlock(&vsock->dev.mutex); return 0; err_vq: vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: mutex_unlock(&vsock->dev.mutex); return ret; } static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner) { size_t i; int ret = 0; mutex_lock(&vsock->dev.mutex); if (check_owner) { ret = vhost_dev_check_owner(&vsock->dev); if (ret) goto err; } for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { struct vhost_virtqueue *vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: mutex_unlock(&vsock->dev.mutex); return ret; } static void vhost_vsock_free(struct vhost_vsock *vsock) { kvfree(vsock); } static int vhost_vsock_dev_open(struct inode *inode, struct file *file) { struct vhost_virtqueue **vqs; struct vhost_vsock *vsock; int ret; /* This struct is large and allocation could fail, fall back to vmalloc * if there is no other way. */ vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!vsock) return -ENOMEM; vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL); if (!vqs) { ret = -ENOMEM; goto out; } vsock->guest_cid = 0; /* no CID assigned yet */ vsock->seqpacket_allow = false; atomic_set(&vsock->queued_replies, 0); vqs[VSOCK_VQ_TX] = &vsock->vqs[VSOCK_VQ_TX]; vqs[VSOCK_VQ_RX] = &vsock->vqs[VSOCK_VQ_RX]; vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick; vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick; vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT, VHOST_VSOCK_WEIGHT, true, NULL); file->private_data = vsock; skb_queue_head_init(&vsock->send_pkt_queue); vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work); return 0; out: vhost_vsock_free(vsock); return ret; } static void vhost_vsock_flush(struct vhost_vsock *vsock) { vhost_dev_flush(&vsock->dev); } static void vhost_vsock_reset_orphans(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); /* vmci_transport.c doesn't take sk_lock here either. At least we're * under vsock_table_lock so the sock cannot disappear while we're * executing. */ /* If the peer is still valid, no need to reset connection */ if (vhost_vsock_get(vsk->remote_addr.svm_cid)) return; /* If the close timeout is pending, let it expire. This avoids races * with the timeout callback. */ if (vsk->close_work_scheduled) return; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; sk_error_report(sk); } static int vhost_vsock_dev_release(struct inode *inode, struct file *file) { struct vhost_vsock *vsock = file->private_data; mutex_lock(&vhost_vsock_mutex); if (vsock->guest_cid) hash_del_rcu(&vsock->hash); mutex_unlock(&vhost_vsock_mutex); /* Wait for other CPUs to finish using vsock */ synchronize_rcu(); /* Iterating over all connections for all CIDs to find orphans is * inefficient. Room for improvement here. */ vsock_for_each_connected_socket(&vhost_transport.transport, vhost_vsock_reset_orphans); /* Don't check the owner, because we are in the release path, so we * need to stop the vsock device in any case. * vhost_vsock_stop() can not fail in this case, so we don't need to * check the return code. */ vhost_vsock_stop(vsock, false); vhost_vsock_flush(vsock); vhost_dev_stop(&vsock->dev); virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue); vhost_dev_cleanup(&vsock->dev); kfree(vsock->dev.vqs); vhost_vsock_free(vsock); return 0; } static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) { struct vhost_vsock *other; /* Refuse reserved CIDs */ if (guest_cid <= VMADDR_CID_HOST || guest_cid == U32_MAX) return -EINVAL; /* 64-bit CIDs are not yet supported */ if (guest_cid > U32_MAX) return -EINVAL; /* Refuse if CID is assigned to the guest->host transport (i.e. nested * VM), to make the loopback work. */ if (vsock_find_cid(guest_cid)) return -EADDRINUSE; /* Refuse if CID is already in use */ mutex_lock(&vhost_vsock_mutex); other = vhost_vsock_get(guest_cid); if (other && other != vsock) { mutex_unlock(&vhost_vsock_mutex); return -EADDRINUSE; } if (vsock->guest_cid) hash_del_rcu(&vsock->hash); vsock->guest_cid = guest_cid; hash_add_rcu(vhost_vsock_hash, &vsock->hash, vsock->guest_cid); mutex_unlock(&vhost_vsock_mutex); return 0; } static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) { struct vhost_virtqueue *vq; int i; if (features & ~VHOST_VSOCK_FEATURES) return -EOPNOTSUPP; mutex_lock(&vsock->dev.mutex); if ((features & (1 << VHOST_F_LOG_ALL)) && !vhost_log_access_ok(&vsock->dev)) { goto err; } if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&vsock->dev)) goto err; } vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vq->acked_features = features; mutex_unlock(&vq->mutex); } mutex_unlock(&vsock->dev.mutex); return 0; err: mutex_unlock(&vsock->dev.mutex); return -EFAULT; } static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { struct vhost_vsock *vsock = f->private_data; void __user *argp = (void __user *)arg; u64 guest_cid; u64 features; int start; int r; switch (ioctl) { case VHOST_VSOCK_SET_GUEST_CID: if (copy_from_user(&guest_cid, argp, sizeof(guest_cid))) return -EFAULT; return vhost_vsock_set_cid(vsock, guest_cid); case VHOST_VSOCK_SET_RUNNING: if (copy_from_user(&start, argp, sizeof(start))) return -EFAULT; if (start) return vhost_vsock_start(vsock); else return vhost_vsock_stop(vsock, true); case VHOST_GET_FEATURES: features = VHOST_VSOCK_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_FEATURES: if (copy_from_user(&features, argp, sizeof(features))) return -EFAULT; return vhost_vsock_set_features(vsock, features); case VHOST_GET_BACKEND_FEATURES: features = VHOST_VSOCK_BACKEND_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_BACKEND_FEATURES: if (copy_from_user(&features, argp, sizeof(features))) return -EFAULT; if (features & ~VHOST_VSOCK_BACKEND_FEATURES) return -EOPNOTSUPP; vhost_set_backend_features(&vsock->dev, features); return 0; default: mutex_lock(&vsock->dev.mutex); r = vhost_dev_ioctl(&vsock->dev, ioctl, argp); if (r == -ENOIOCTLCMD) r = vhost_vring_ioctl(&vsock->dev, ioctl, argp); else vhost_vsock_flush(vsock); mutex_unlock(&vsock->dev.mutex); return r; } } static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; int noblock = file->f_flags & O_NONBLOCK; return vhost_chr_read_iter(dev, to, noblock); } static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; return vhost_chr_write_iter(dev, from); } static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait) { struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; return vhost_chr_poll(file, dev, wait); } static const struct file_operations vhost_vsock_fops = { .owner = THIS_MODULE, .open = vhost_vsock_dev_open, .release = vhost_vsock_dev_release, .llseek = noop_llseek, .unlocked_ioctl = vhost_vsock_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, .read_iter = vhost_vsock_chr_read_iter, .write_iter = vhost_vsock_chr_write_iter, .poll = vhost_vsock_chr_poll, }; static struct miscdevice vhost_vsock_misc = { .minor = VHOST_VSOCK_MINOR, .name = "vhost-vsock", .fops = &vhost_vsock_fops, }; static int __init vhost_vsock_init(void) { int ret; ret = vsock_core_register(&vhost_transport.transport, VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; ret = misc_register(&vhost_vsock_misc); if (ret) { vsock_core_unregister(&vhost_transport.transport); return ret; } return 0; }; static void __exit vhost_vsock_exit(void) { misc_deregister(&vhost_vsock_misc); vsock_core_unregister(&vhost_transport.transport); }; module_init(vhost_vsock_init); module_exit(vhost_vsock_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Asias He"); MODULE_DESCRIPTION("vhost transport for vsock "); MODULE_ALIAS_MISCDEV(VHOST_VSOCK_MINOR); MODULE_ALIAS("devname:vhost-vsock"); |
| 196 132 122 128 162 171 171 15 159 54 16 6 33 38 54 22 33 14 2 12 2 2 18 2 16 8 8 8 6 6 1 8 6 3 21 14 8 2 18 16 1 1 2 12 2 5 6 2 1 1 20 20 7 12 2 13 13 79 17 7 19 73 69 73 73 27 11 17 22 6 19 26 13 75 19 68 4 60 20 20 20 59 4 68 4 4 4 6 63 10 4 10 10 3 10 10 10 73 73 71 73 70 62 62 73 1 1 55 12 31 70 70 14 14 15 13 59 32 69 17 6 61 63 46 19 63 63 11 52 73 73 73 62 61 15 1 63 1 2 63 13 15 19 19 13 5 13 19 17 16 14 5 4 2 16 63 57 54 45 15 23 4 4 12 49 37 37 63 54 6 46 46 2 51 50 51 4 10 3 7 10 10 21 21 15 15 3 43 1 1 1 5 144 5 5 143 33 109 78 46 96 23 119 33 117 109 33 33 142 86 66 31 116 4 142 112 89 25 10 12 9 53 53 23 30 11 42 44 10 44 53 1 3 26 27 40 13 13 13 13 52 1 20 28 3 1 2 1 1 52 30 23 154 9 1 151 69 31 69 69 20 14 61 150 151 124 118 151 37 146 194 102 190 193 167 164 119 183 58 126 82 166 37 37 37 36 29 29 13 13 30 30 30 179 179 179 35 15 171 171 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * inode.c * * PURPOSE * Inode handling routines for the OSTA-UDF(tm) filesystem. * * COPYRIGHT * (C) 1998 Dave Boynton * (C) 1998-2004 Ben Fennema * (C) 1999-2000 Stelias Computing Inc * * HISTORY * * 10/04/98 dgb Added rudimentary directory functions * 10/07/98 Fully working udf_block_map! It works! * 11/25/98 bmap altered to better support extents * 12/06/98 blf partition support in udf_iget, udf_block_map * and udf_read_inode * 12/12/98 rewrote udf_block_map to handle next extents and descs across * block boundaries (which is not actually allowed) * 12/20/98 added support for strategy 4096 * 03/07/99 rewrote udf_block_map (again) * New funcs, inode_bmap, udf_next_aext * 04/19/99 Support for writing device EA's for major/minor # */ #include "udfdecl.h" #include <linux/mm.h> #include <linux/module.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/slab.h> #include <linux/crc-itu-t.h> #include <linux/mpage.h> #include <linux/uio.h> #include <linux/bio.h> #include "udf_i.h" #include "udf_sb.h" #define EXTENT_MERGE_SIZE 5 #define FE_MAPPED_PERMS (FE_PERM_U_READ | FE_PERM_U_WRITE | FE_PERM_U_EXEC | \ FE_PERM_G_READ | FE_PERM_G_WRITE | FE_PERM_G_EXEC | \ FE_PERM_O_READ | FE_PERM_O_WRITE | FE_PERM_O_EXEC) #define FE_DELETE_PERMS (FE_PERM_U_DELETE | FE_PERM_G_DELETE | \ FE_PERM_O_DELETE) struct udf_map_rq; static umode_t udf_convert_permissions(struct fileEntry *); static int udf_update_inode(struct inode *, int); static int udf_sync_inode(struct inode *inode); static int udf_alloc_i_data(struct inode *inode, size_t size); static int inode_getblk(struct inode *inode, struct udf_map_rq *map); static int udf_insert_aext(struct inode *, struct extent_position, struct kernel_lb_addr, uint32_t); static void udf_split_extents(struct inode *, int *, int, udf_pblk_t, struct kernel_long_ad *, int *); static void udf_prealloc_extents(struct inode *, int, int, struct kernel_long_ad *, int *); static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *); static int udf_update_extents(struct inode *, struct kernel_long_ad *, int, int, struct extent_position *); static int udf_get_block_wb(struct inode *inode, sector_t block, struct buffer_head *bh_result, int create); static void __udf_clear_extent_cache(struct inode *inode) { struct udf_inode_info *iinfo = UDF_I(inode); if (iinfo->cached_extent.lstart != -1) { brelse(iinfo->cached_extent.epos.bh); iinfo->cached_extent.lstart = -1; } } /* Invalidate extent cache */ static void udf_clear_extent_cache(struct inode *inode) { struct udf_inode_info *iinfo = UDF_I(inode); spin_lock(&iinfo->i_extent_cache_lock); __udf_clear_extent_cache(inode); spin_unlock(&iinfo->i_extent_cache_lock); } /* Return contents of extent cache */ static int udf_read_extent_cache(struct inode *inode, loff_t bcount, loff_t *lbcount, struct extent_position *pos) { struct udf_inode_info *iinfo = UDF_I(inode); int ret = 0; spin_lock(&iinfo->i_extent_cache_lock); if ((iinfo->cached_extent.lstart <= bcount) && (iinfo->cached_extent.lstart != -1)) { /* Cache hit */ *lbcount = iinfo->cached_extent.lstart; memcpy(pos, &iinfo->cached_extent.epos, sizeof(struct extent_position)); if (pos->bh) get_bh(pos->bh); ret = 1; } spin_unlock(&iinfo->i_extent_cache_lock); return ret; } /* Add extent to extent cache */ static void udf_update_extent_cache(struct inode *inode, loff_t estart, struct extent_position *pos) { struct udf_inode_info *iinfo = UDF_I(inode); spin_lock(&iinfo->i_extent_cache_lock); /* Invalidate previously cached extent */ __udf_clear_extent_cache(inode); if (pos->bh) get_bh(pos->bh); memcpy(&iinfo->cached_extent.epos, pos, sizeof(*pos)); iinfo->cached_extent.lstart = estart; switch (iinfo->i_alloc_type) { case ICBTAG_FLAG_AD_SHORT: iinfo->cached_extent.epos.offset -= sizeof(struct short_ad); break; case ICBTAG_FLAG_AD_LONG: iinfo->cached_extent.epos.offset -= sizeof(struct long_ad); break; } spin_unlock(&iinfo->i_extent_cache_lock); } void udf_evict_inode(struct inode *inode) { struct udf_inode_info *iinfo = UDF_I(inode); int want_delete = 0; if (!is_bad_inode(inode)) { if (!inode->i_nlink) { want_delete = 1; udf_setsize(inode, 0); udf_update_inode(inode, IS_SYNC(inode)); } if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && inode->i_size != iinfo->i_lenExtents) { udf_warn(inode->i_sb, "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", inode->i_ino, inode->i_mode, (unsigned long long)inode->i_size, (unsigned long long)iinfo->i_lenExtents); } } truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); kfree(iinfo->i_data); iinfo->i_data = NULL; udf_clear_extent_cache(inode); if (want_delete) { udf_free_inode(inode); } } static void udf_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; struct udf_inode_info *iinfo = UDF_I(inode); loff_t isize = inode->i_size; if (to > isize) { truncate_pagecache(inode, isize); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); } } } static int udf_adinicb_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct udf_inode_info *iinfo = UDF_I(inode); struct folio *folio = NULL; int error = 0; while ((folio = writeback_iter(mapping, wbc, folio, &error))) { BUG_ON(!folio_test_locked(folio)); BUG_ON(folio->index != 0); memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio, 0, i_size_read(inode)); folio_unlock(folio); } mark_inode_dirty(inode); return 0; } static int udf_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct udf_inode_info *iinfo = UDF_I(inode); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) return udf_adinicb_writepages(mapping, wbc); return mpage_writepages(mapping, wbc, udf_get_block_wb); } static void udf_adinicb_read_folio(struct folio *folio) { struct inode *inode = folio->mapping->host; struct udf_inode_info *iinfo = UDF_I(inode); loff_t isize = i_size_read(inode); folio_fill_tail(folio, 0, iinfo->i_data + iinfo->i_lenEAttr, isize); folio_mark_uptodate(folio); } static int udf_read_folio(struct file *file, struct folio *folio) { struct udf_inode_info *iinfo = UDF_I(file_inode(file)); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { udf_adinicb_read_folio(folio); folio_unlock(folio); return 0; } return mpage_read_folio(folio, udf_get_block); } static void udf_readahead(struct readahead_control *rac) { struct udf_inode_info *iinfo = UDF_I(rac->mapping->host); /* * No readahead needed for in-ICB files and udf_get_block() would get * confused for such file anyway. */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) return; mpage_readahead(rac, udf_get_block); } static int udf_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct file *file = iocb->ki_filp; struct udf_inode_info *iinfo = UDF_I(file_inode(file)); struct folio *folio; int ret; if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { ret = block_write_begin(mapping, pos, len, foliop, udf_get_block); if (unlikely(ret)) udf_write_failed(mapping, pos + len); return ret; } if (WARN_ON_ONCE(pos >= PAGE_SIZE)) return -EIO; folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); *foliop = folio; if (!folio_test_uptodate(folio)) udf_adinicb_read_folio(folio); return 0; } static int udf_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = file_inode(iocb->ki_filp); loff_t last_pos; if (UDF_I(inode)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) return generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata); last_pos = pos + copied; if (last_pos > inode->i_size) i_size_write(inode, last_pos); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); return copied; } static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; /* Fallback to buffered IO for in-ICB files */ if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) return 0; ret = blockdev_direct_IO(iocb, inode, iter, udf_get_block); if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE)) udf_write_failed(mapping, iocb->ki_pos + count); return ret; } static sector_t udf_bmap(struct address_space *mapping, sector_t block) { struct udf_inode_info *iinfo = UDF_I(mapping->host); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) return -EINVAL; return generic_block_bmap(mapping, block, udf_get_block); } const struct address_space_operations udf_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, .read_folio = udf_read_folio, .readahead = udf_readahead, .writepages = udf_writepages, .write_begin = udf_write_begin, .write_end = udf_write_end, .direct_IO = udf_direct_IO, .bmap = udf_bmap, .migrate_folio = buffer_migrate_folio, }; /* * Expand file stored in ICB to a normal one-block-file * * This function requires i_mutex held */ int udf_expand_file_adinicb(struct inode *inode) { struct folio *folio; struct udf_inode_info *iinfo = UDF_I(inode); int err; WARN_ON_ONCE(!inode_is_locked(inode)); if (!iinfo->i_lenAlloc) { down_write(&iinfo->i_data_sem); if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; up_write(&iinfo->i_data_sem); mark_inode_dirty(inode); return 0; } folio = __filemap_get_folio(inode->i_mapping, 0, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_KERNEL); if (IS_ERR(folio)) return PTR_ERR(folio); if (!folio_test_uptodate(folio)) udf_adinicb_read_folio(folio); down_write(&iinfo->i_data_sem); memset(iinfo->i_data + iinfo->i_lenEAttr, 0x00, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; folio_mark_dirty(folio); folio_unlock(folio); up_write(&iinfo->i_data_sem); err = filemap_fdatawrite(inode->i_mapping); if (err) { /* Restore everything back so that we don't lose data... */ folio_lock(folio); down_write(&iinfo->i_data_sem); memcpy_from_folio(iinfo->i_data + iinfo->i_lenEAttr, folio, 0, inode->i_size); folio_unlock(folio); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; iinfo->i_lenAlloc = inode->i_size; up_write(&iinfo->i_data_sem); } folio_put(folio); mark_inode_dirty(inode); return err; } #define UDF_MAP_CREATE 0x01 /* Mapping can allocate new blocks */ #define UDF_MAP_NOPREALLOC 0x02 /* Do not preallocate blocks */ #define UDF_BLK_MAPPED 0x01 /* Block was successfully mapped */ #define UDF_BLK_NEW 0x02 /* Block was freshly allocated */ struct udf_map_rq { sector_t lblk; udf_pblk_t pblk; int iflags; /* UDF_MAP_ flags determining behavior */ int oflags; /* UDF_BLK_ flags reporting results */ }; static int udf_map_block(struct inode *inode, struct udf_map_rq *map) { int ret; struct udf_inode_info *iinfo = UDF_I(inode); if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) return -EFSCORRUPTED; map->oflags = 0; if (!(map->iflags & UDF_MAP_CREATE)) { struct kernel_lb_addr eloc; uint32_t elen; sector_t offset; struct extent_position epos = {}; int8_t etype; down_read(&iinfo->i_data_sem); ret = inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset, &etype); if (ret < 0) goto out_read; if (ret > 0 && etype == (EXT_RECORDED_ALLOCATED >> 30)) { map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc, offset); map->oflags |= UDF_BLK_MAPPED; ret = 0; } out_read: up_read(&iinfo->i_data_sem); brelse(epos.bh); return ret; } down_write(&iinfo->i_data_sem); /* * Block beyond EOF and prealloc extents? Just discard preallocation * as it is not useful and complicates things. */ if (((loff_t)map->lblk) << inode->i_blkbits >= iinfo->i_lenExtents) udf_discard_prealloc(inode); udf_clear_extent_cache(inode); ret = inode_getblk(inode, map); up_write(&iinfo->i_data_sem); return ret; } static int __udf_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_result, int flags) { int err; struct udf_map_rq map = { .lblk = block, .iflags = flags, }; err = udf_map_block(inode, &map); if (err < 0) return err; if (map.oflags & UDF_BLK_MAPPED) { map_bh(bh_result, inode->i_sb, map.pblk); if (map.oflags & UDF_BLK_NEW) set_buffer_new(bh_result); } return 0; } int udf_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_result, int create) { int flags = create ? UDF_MAP_CREATE : 0; /* * We preallocate blocks only for regular files. It also makes sense * for directories but there's a problem when to drop the * preallocation. We might use some delayed work for that but I feel * it's overengineering for a filesystem like UDF. */ if (!S_ISREG(inode->i_mode)) flags |= UDF_MAP_NOPREALLOC; return __udf_get_block(inode, block, bh_result, flags); } /* * We shouldn't be allocating blocks on page writeback since we allocate them * on page fault. We can spot dirty buffers without allocated blocks though * when truncate expands file. These however don't have valid data so we can * safely ignore them. So never allocate blocks from page writeback. */ static int udf_get_block_wb(struct inode *inode, sector_t block, struct buffer_head *bh_result, int create) { return __udf_get_block(inode, block, bh_result, 0); } /* Extend the file with new blocks totaling 'new_block_bytes', * return the number of extents added */ static int udf_do_extend_file(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, loff_t new_block_bytes) { uint32_t add; int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK); struct super_block *sb = inode->i_sb; struct udf_inode_info *iinfo; int err; /* The previous extent is fake and we should not extend by anything * - there's nothing to do... */ if (!new_block_bytes && fake) return 0; iinfo = UDF_I(inode); /* Round the last extent up to a multiple of block size */ if (last_ext->extLength & (sb->s_blocksize - 1)) { last_ext->extLength = (last_ext->extLength & UDF_EXTENT_FLAG_MASK) | (((last_ext->extLength & UDF_EXTENT_LENGTH_MASK) + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1)); iinfo->i_lenExtents = (iinfo->i_lenExtents + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1); } add = 0; /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { add = (1 << 30) - sb->s_blocksize - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); if (add > new_block_bytes) add = new_block_bytes; new_block_bytes -= add; last_ext->extLength += add; } if (fake) { err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err < 0) goto out_err; count++; } else { struct kernel_lb_addr tmploc; uint32_t tmplen; int8_t tmptype; udf_write_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); /* * We've rewritten the last extent. If we are going to add * more extents, we may need to enter possible following * empty indirect extent. */ if (new_block_bytes) { err = udf_next_aext(inode, last_pos, &tmploc, &tmplen, &tmptype, 0); if (err < 0) goto out_err; } } iinfo->i_lenExtents += add; /* Managed to do everything necessary? */ if (!new_block_bytes) goto out; /* All further extents will be NOT_RECORDED_NOT_ALLOCATED */ last_ext->extLocation.logicalBlockNum = 0; last_ext->extLocation.partitionReferenceNum = 0; add = (1 << 30) - sb->s_blocksize; last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | add; /* Create enough extents to cover the whole hole */ while (new_block_bytes > add) { new_block_bytes -= add; err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) goto out_err; iinfo->i_lenExtents += add; count++; } if (new_block_bytes) { last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | new_block_bytes; err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) goto out_err; iinfo->i_lenExtents += new_block_bytes; count++; } out: /* last_pos should point to the last written extent... */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) last_pos->offset -= sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) last_pos->offset -= sizeof(struct long_ad); else return -EIO; return count; out_err: /* Remove extents we've created so far */ udf_clear_extent_cache(inode); udf_truncate_extents(inode); return err; } /* Extend the final block of the file to final_block_len bytes */ static void udf_do_extend_final_block(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, uint32_t new_elen) { uint32_t added_bytes; /* * Extent already large enough? It may be already rounded up to block * size... */ if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) return; added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); last_ext->extLength += added_bytes; UDF_I(inode)->i_lenExtents += added_bytes; udf_write_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); } static int udf_extend_file(struct inode *inode, loff_t newsize) { struct extent_position epos; struct kernel_lb_addr eloc; uint32_t elen; int8_t etype; struct super_block *sb = inode->i_sb; sector_t first_block = newsize >> sb->s_blocksize_bits, offset; loff_t new_elen; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); struct kernel_long_ad extent; int err = 0; bool within_last_ext; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); else BUG(); down_write(&iinfo->i_data_sem); /* * When creating hole in file, just don't bother with preserving * preallocation. It likely won't be very useful anyway. */ udf_discard_prealloc(inode); err = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype); if (err < 0) goto out; within_last_ext = (err == 1); /* We don't expect extents past EOF... */ WARN_ON_ONCE(within_last_ext && elen > ((loff_t)offset + 1) << inode->i_blkbits); if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || (epos.bh && epos.offset == sizeof(struct allocExtDesc))) { /* File has no extents at all or has empty last * indirect extent! Create a fake extent... */ extent.extLocation.logicalBlockNum = 0; extent.extLocation.partitionReferenceNum = 0; extent.extLength = EXT_NOT_RECORDED_NOT_ALLOCATED; } else { epos.offset -= adsize; err = udf_next_aext(inode, &epos, &extent.extLocation, &extent.extLength, &etype, 0); if (err <= 0) goto out; extent.extLength |= etype << 30; } new_elen = ((loff_t)offset << inode->i_blkbits) | (newsize & (sb->s_blocksize - 1)); /* File has extent covering the new size (could happen when extending * inside a block)? */ if (within_last_ext) { /* Extending file within the last file block */ udf_do_extend_final_block(inode, &epos, &extent, new_elen); } else { err = udf_do_extend_file(inode, &epos, &extent, new_elen); } if (err < 0) goto out; err = 0; out: brelse(epos.bh); up_write(&iinfo->i_data_sem); return err; } static int inode_getblk(struct inode *inode, struct udf_map_rq *map) { struct kernel_long_ad laarr[EXTENT_MERGE_SIZE]; struct extent_position prev_epos, cur_epos, next_epos; int count = 0, startnum = 0, endnum = 0; uint32_t elen = 0, tmpelen; struct kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; udf_pblk_t newblocknum; sector_t offset = 0; int8_t etype, tmpetype; struct udf_inode_info *iinfo = UDF_I(inode); udf_pblk_t goal = 0, pgoal = iinfo->i_location.logicalBlockNum; int lastblock = 0; bool isBeyondEOF = false; int ret = 0; prev_epos.offset = udf_file_entry_alloc_offset(inode); prev_epos.block = iinfo->i_location; prev_epos.bh = NULL; cur_epos = next_epos = prev_epos; b_off = (loff_t)map->lblk << inode->i_sb->s_blocksize_bits; /* find the extent which contains the block we are looking for. alternate between laarr[0] and laarr[1] for locations of the current extent, and the previous extent */ do { if (prev_epos.bh != cur_epos.bh) { brelse(prev_epos.bh); get_bh(cur_epos.bh); prev_epos.bh = cur_epos.bh; } if (cur_epos.bh != next_epos.bh) { brelse(cur_epos.bh); get_bh(next_epos.bh); cur_epos.bh = next_epos.bh; } lbcount += elen; prev_epos.block = cur_epos.block; cur_epos.block = next_epos.block; prev_epos.offset = cur_epos.offset; cur_epos.offset = next_epos.offset; ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 1); if (ret < 0) { goto out_free; } else if (ret == 0) { isBeyondEOF = true; break; } c = !c; laarr[c].extLength = (etype << 30) | elen; laarr[c].extLocation = eloc; if (etype != (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) pgoal = eloc.logicalBlockNum + ((elen + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits); count++; } while (lbcount + elen <= b_off); b_off -= lbcount; offset = b_off >> inode->i_sb->s_blocksize_bits; /* * Move prev_epos and cur_epos into indirect extent if we are at * the pointer to it */ ret = udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, &tmpetype, 0); if (ret < 0) goto out_free; ret = udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, &tmpetype, 0); if (ret < 0) goto out_free; /* if the extent is allocated and recorded, return the block if the extent is not a multiple of the blocksize, round up */ if (!isBeyondEOF && etype == (EXT_RECORDED_ALLOCATED >> 30)) { if (elen & (inode->i_sb->s_blocksize - 1)) { elen = EXT_RECORDED_ALLOCATED | ((elen + inode->i_sb->s_blocksize - 1) & ~(inode->i_sb->s_blocksize - 1)); iinfo->i_lenExtents = ALIGN(iinfo->i_lenExtents, inode->i_sb->s_blocksize); udf_write_aext(inode, &cur_epos, &eloc, elen, 1); } map->oflags = UDF_BLK_MAPPED; map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc, offset); ret = 0; goto out_free; } /* Are we beyond EOF and preallocated extent? */ if (isBeyondEOF) { loff_t hole_len; if (count) { if (c) laarr[0] = laarr[1]; startnum = 1; } else { /* Create a fake extent when there's not one */ memset(&laarr[0].extLocation, 0x00, sizeof(struct kernel_lb_addr)); laarr[0].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED; /* Will udf_do_extend_file() create real extent from a fake one? */ startnum = (offset > 0); } /* Create extents for the hole between EOF and offset */ hole_len = (loff_t)offset << inode->i_blkbits; ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) goto out_free; c = 0; offset = 0; count += ret; /* * Is there any real extent? - otherwise we overwrite the fake * one... */ if (count) c = !c; laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | inode->i_sb->s_blocksize; memset(&laarr[c].extLocation, 0x00, sizeof(struct kernel_lb_addr)); count++; endnum = c + 1; lastblock = 1; } else { endnum = startnum = ((count > 2) ? 2 : count); /* if the current extent is in position 0, swap it with the previous */ if (!c && count != 1) { laarr[2] = laarr[0]; laarr[0] = laarr[1]; laarr[1] = laarr[2]; c = 1; } /* if the current block is located in an extent, read the next extent */ ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 0); if (ret > 0) { laarr[c + 1].extLength = (etype << 30) | elen; laarr[c + 1].extLocation = eloc; count++; startnum++; endnum++; } else if (ret == 0) lastblock = 1; else goto out_free; } /* if the current extent is not recorded but allocated, get the * block in the extent corresponding to the requested block */ if ((laarr[c].extLength >> 30) == (EXT_NOT_RECORDED_ALLOCATED >> 30)) newblocknum = laarr[c].extLocation.logicalBlockNum + offset; else { /* otherwise, allocate a new block */ if (iinfo->i_next_alloc_block == map->lblk) goal = iinfo->i_next_alloc_goal; if (!goal) { if (!(goal = pgoal)) /* XXX: what was intended here? */ goal = iinfo->i_location.logicalBlockNum + 1; } newblocknum = udf_new_block(inode->i_sb, inode, iinfo->i_location.partitionReferenceNum, goal, &ret); if (!newblocknum) goto out_free; if (isBeyondEOF) iinfo->i_lenExtents += inode->i_sb->s_blocksize; } /* if the extent the requsted block is located in contains multiple * blocks, split the extent into at most three extents. blocks prior * to requested block, requested block, and blocks after requested * block */ udf_split_extents(inode, &c, offset, newblocknum, laarr, &endnum); if (!(map->iflags & UDF_MAP_NOPREALLOC)) udf_prealloc_extents(inode, c, lastblock, laarr, &endnum); /* merge any continuous blocks in laarr */ udf_merge_extents(inode, laarr, &endnum); /* write back the new extents, inserting new extents if the new number * of extents is greater than the old number, and deleting extents if * the new number of extents is less than the old number */ ret = udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); if (ret < 0) goto out_free; map->pblk = udf_get_pblock(inode->i_sb, newblocknum, iinfo->i_location.partitionReferenceNum, 0); if (!map->pblk) { ret = -EFSCORRUPTED; goto out_free; } map->oflags = UDF_BLK_NEW | UDF_BLK_MAPPED; iinfo->i_next_alloc_block = map->lblk + 1; iinfo->i_next_alloc_goal = newblocknum + 1; inode_set_ctime_current(inode); if (IS_SYNC(inode)) udf_sync_inode(inode); else mark_inode_dirty(inode); ret = 0; out_free: brelse(prev_epos.bh); brelse(cur_epos.bh); brelse(next_epos.bh); return ret; } static void udf_split_extents(struct inode *inode, int *c, int offset, udf_pblk_t newblocknum, struct kernel_long_ad *laarr, int *endnum) { unsigned long blocksize = inode->i_sb->s_blocksize; unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; if ((laarr[*c].extLength >> 30) == (EXT_NOT_RECORDED_ALLOCATED >> 30) || (laarr[*c].extLength >> 30) == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) { int curr = *c; int blen = ((laarr[curr].extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) >> blocksize_bits; int8_t etype = (laarr[curr].extLength >> 30); if (blen == 1) ; else if (!offset || blen == offset + 1) { laarr[curr + 2] = laarr[curr + 1]; laarr[curr + 1] = laarr[curr]; } else { laarr[curr + 3] = laarr[curr + 1]; laarr[curr + 2] = laarr[curr + 1] = laarr[curr]; } if (offset) { if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { udf_free_blocks(inode->i_sb, inode, &laarr[curr].extLocation, 0, offset); laarr[curr].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | (offset << blocksize_bits); laarr[curr].extLocation.logicalBlockNum = 0; laarr[curr].extLocation. partitionReferenceNum = 0; } else laarr[curr].extLength = (etype << 30) | (offset << blocksize_bits); curr++; (*c)++; (*endnum)++; } laarr[curr].extLocation.logicalBlockNum = newblocknum; if (etype == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) laarr[curr].extLocation.partitionReferenceNum = UDF_I(inode)->i_location.partitionReferenceNum; laarr[curr].extLength = EXT_RECORDED_ALLOCATED | blocksize; curr++; if (blen != offset + 1) { if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) laarr[curr].extLocation.logicalBlockNum += offset + 1; laarr[curr].extLength = (etype << 30) | ((blen - (offset + 1)) << blocksize_bits); curr++; (*endnum)++; } } } static void udf_prealloc_extents(struct inode *inode, int c, int lastblock, struct kernel_long_ad *laarr, int *endnum) { int start, length = 0, currlength = 0, i; if (*endnum >= (c + 1)) { if (!lastblock) return; else start = c; } else { if ((laarr[c + 1].extLength >> 30) == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { start = c + 1; length = currlength = (((laarr[c + 1].extLength & UDF_EXTENT_LENGTH_MASK) + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits); } else start = c; } for (i = start + 1; i <= *endnum; i++) { if (i == *endnum) { if (lastblock) length += UDF_DEFAULT_PREALLOC_BLOCKS; } else if ((laarr[i].extLength >> 30) == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) { length += (((laarr[i].extLength & UDF_EXTENT_LENGTH_MASK) + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits); } else break; } if (length) { int next = laarr[start].extLocation.logicalBlockNum + (((laarr[start].extLength & UDF_EXTENT_LENGTH_MASK) + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits); int numalloc = udf_prealloc_blocks(inode->i_sb, inode, laarr[start].extLocation.partitionReferenceNum, next, (UDF_DEFAULT_PREALLOC_BLOCKS > length ? length : UDF_DEFAULT_PREALLOC_BLOCKS) - currlength); if (numalloc) { if (start == (c + 1)) laarr[start].extLength += (numalloc << inode->i_sb->s_blocksize_bits); else { memmove(&laarr[c + 2], &laarr[c + 1], sizeof(struct long_ad) * (*endnum - (c + 1))); (*endnum)++; laarr[c + 1].extLocation.logicalBlockNum = next; laarr[c + 1].extLocation.partitionReferenceNum = laarr[c].extLocation. partitionReferenceNum; laarr[c + 1].extLength = EXT_NOT_RECORDED_ALLOCATED | (numalloc << inode->i_sb->s_blocksize_bits); start = c + 1; } for (i = start + 1; numalloc && i < *endnum; i++) { int elen = ((laarr[i].extLength & UDF_EXTENT_LENGTH_MASK) + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (elen > numalloc) { laarr[i].extLength -= (numalloc << inode->i_sb->s_blocksize_bits); numalloc = 0; } else { numalloc -= elen; if (*endnum > (i + 1)) memmove(&laarr[i], &laarr[i + 1], sizeof(struct long_ad) * (*endnum - (i + 1))); i--; (*endnum)--; } } UDF_I(inode)->i_lenExtents += numalloc << inode->i_sb->s_blocksize_bits; } } } static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, int *endnum) { int i; unsigned long blocksize = inode->i_sb->s_blocksize; unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; for (i = 0; i < (*endnum - 1); i++) { struct kernel_long_ad *li /*l[i]*/ = &laarr[i]; struct kernel_long_ad *lip1 /*l[i plus 1]*/ = &laarr[i + 1]; if (((li->extLength >> 30) == (lip1->extLength >> 30)) && (((li->extLength >> 30) == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) || ((lip1->extLocation.logicalBlockNum - li->extLocation.logicalBlockNum) == (((li->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) >> blocksize_bits)))) { if (((li->extLength & UDF_EXTENT_LENGTH_MASK) + (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) <= UDF_EXTENT_LENGTH_MASK) { li->extLength = lip1->extLength + (((li->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) & ~(blocksize - 1)); if (*endnum > (i + 2)) memmove(&laarr[i + 1], &laarr[i + 2], sizeof(struct long_ad) * (*endnum - (i + 2))); i--; (*endnum)--; } } else if (((li->extLength >> 30) == (EXT_NOT_RECORDED_ALLOCATED >> 30)) && ((lip1->extLength >> 30) == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30))) { udf_free_blocks(inode->i_sb, inode, &li->extLocation, 0, ((li->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) >> blocksize_bits); li->extLocation.logicalBlockNum = 0; li->extLocation.partitionReferenceNum = 0; if (((li->extLength & UDF_EXTENT_LENGTH_MASK) + (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) & ~UDF_EXTENT_LENGTH_MASK) { lip1->extLength = (lip1->extLength - (li->extLength & UDF_EXTENT_LENGTH_MASK) + UDF_EXTENT_LENGTH_MASK) & ~(blocksize - 1); li->extLength = (li->extLength & UDF_EXTENT_FLAG_MASK) + (UDF_EXTENT_LENGTH_MASK + 1) - blocksize; } else { li->extLength = lip1->extLength + (((li->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) & ~(blocksize - 1)); if (*endnum > (i + 2)) memmove(&laarr[i + 1], &laarr[i + 2], sizeof(struct long_ad) * (*endnum - (i + 2))); i--; (*endnum)--; } } else if ((li->extLength >> 30) == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { udf_free_blocks(inode->i_sb, inode, &li->extLocation, 0, ((li->extLength & UDF_EXTENT_LENGTH_MASK) + blocksize - 1) >> blocksize_bits); li->extLocation.logicalBlockNum = 0; li->extLocation.partitionReferenceNum = 0; li->extLength = (li->extLength & UDF_EXTENT_LENGTH_MASK) | EXT_NOT_RECORDED_NOT_ALLOCATED; } } } static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, int startnum, int endnum, struct extent_position *epos) { int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; int8_t tmpetype; int err; if (startnum > endnum) { for (i = 0; i < (startnum - endnum); i++) udf_delete_aext(inode, *epos); } else if (startnum < endnum) { for (i = 0; i < (endnum - startnum); i++) { err = udf_insert_aext(inode, *epos, laarr[i].extLocation, laarr[i].extLength); /* * If we fail here, we are likely corrupting the extent * list and leaking blocks. At least stop early to * limit the damage. */ if (err < 0) return err; err = udf_next_aext(inode, epos, &laarr[i].extLocation, &laarr[i].extLength, &tmpetype, 1); if (err < 0) return err; start++; } } for (i = start; i < endnum; i++) { err = udf_next_aext(inode, epos, &tmploc, &tmplen, &tmpetype, 0); if (err < 0) return err; udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } return 0; } struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, int create, int *err) { struct buffer_head *bh = NULL; struct udf_map_rq map = { .lblk = block, .iflags = UDF_MAP_NOPREALLOC | (create ? UDF_MAP_CREATE : 0), }; *err = udf_map_block(inode, &map); if (*err || !(map.oflags & UDF_BLK_MAPPED)) return NULL; bh = sb_getblk(inode->i_sb, map.pblk); if (!bh) { *err = -ENOMEM; return NULL; } if (map.oflags & UDF_BLK_NEW) { lock_buffer(bh); memset(bh->b_data, 0x00, inode->i_sb->s_blocksize); set_buffer_uptodate(bh); unlock_buffer(bh); mark_buffer_dirty_inode(bh, inode); return bh; } if (bh_read(bh, 0) >= 0) return bh; brelse(bh); *err = -EIO; return NULL; } int udf_setsize(struct inode *inode, loff_t newsize) { int err = 0; struct udf_inode_info *iinfo; unsigned int bsize = i_blocksize(inode); if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) return -EINVAL; iinfo = UDF_I(inode); if (newsize > inode->i_size) { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { if (bsize >= (udf_file_entry_alloc_offset(inode) + newsize)) { down_write(&iinfo->i_data_sem); iinfo->i_lenAlloc = newsize; up_write(&iinfo->i_data_sem); goto set_size; } err = udf_expand_file_adinicb(inode); if (err) return err; } err = udf_extend_file(inode, newsize); if (err) return err; set_size: truncate_setsize(inode, newsize); } else { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); memset(iinfo->i_data + iinfo->i_lenEAttr + newsize, 0x00, bsize - newsize - udf_file_entry_alloc_offset(inode)); iinfo->i_lenAlloc = newsize; truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); goto update_time; } err = block_truncate_page(inode->i_mapping, newsize, udf_get_block); if (err) return err; truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); err = udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); if (err) return err; } update_time: inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (IS_SYNC(inode)) udf_sync_inode(inode); else mark_inode_dirty(inode); return err; } /* * Maximum length of linked list formed by ICB hierarchy. The chosen number is * arbitrary - just that we hopefully don't limit any real use of rewritten * inode on write-once media but avoid looping for too long on corrupted media. */ #define UDF_MAX_ICB_NESTING 1024 static int udf_read_inode(struct inode *inode, bool hidden_inode) { struct buffer_head *bh = NULL; struct fileEntry *fe; struct extendedFileEntry *efe; uint16_t ident; struct udf_inode_info *iinfo = UDF_I(inode); struct udf_sb_info *sbi = UDF_SB(inode->i_sb); struct kernel_lb_addr *iloc = &iinfo->i_location; unsigned int link_count; unsigned int indirections = 0; int bs = inode->i_sb->s_blocksize; int ret = -EIO; uint32_t uid, gid; struct timespec64 ts; reread: if (iloc->partitionReferenceNum >= sbi->s_partitions) { udf_debug("partition reference: %u > logical volume partitions: %u\n", iloc->partitionReferenceNum, sbi->s_partitions); return -EIO; } if (iloc->logicalBlockNum >= sbi->s_partmaps[iloc->partitionReferenceNum].s_partition_len) { udf_debug("block=%u, partition=%u out of range\n", iloc->logicalBlockNum, iloc->partitionReferenceNum); return -EIO; } /* * Set defaults, but the inode is still incomplete! * Note: get_new_inode() sets the following on a new inode: * i_sb = sb * i_no = ino * i_flags = sb->s_flags * i_state = 0 * clean_inode(): zero fills and sets * i_count = 1 * i_nlink = 1 * i_op = NULL; */ bh = udf_read_ptagged(inode->i_sb, iloc, 0, &ident); if (!bh) { udf_err(inode->i_sb, "(ino %lu) failed !bh\n", inode->i_ino); return -EIO; } if (ident != TAG_IDENT_FE && ident != TAG_IDENT_EFE && ident != TAG_IDENT_USE) { udf_err(inode->i_sb, "(ino %lu) failed ident=%u\n", inode->i_ino, ident); goto out; } fe = (struct fileEntry *)bh->b_data; efe = (struct extendedFileEntry *)bh->b_data; if (fe->icbTag.strategyType == cpu_to_le16(4096)) { struct buffer_head *ibh; ibh = udf_read_ptagged(inode->i_sb, iloc, 1, &ident); if (ident == TAG_IDENT_IE && ibh) { struct kernel_lb_addr loc; struct indirectEntry *ie; ie = (struct indirectEntry *)ibh->b_data; loc = lelb_to_cpu(ie->indirectICB.extLocation); if (ie->indirectICB.extLength) { brelse(ibh); memcpy(&iinfo->i_location, &loc, sizeof(struct kernel_lb_addr)); if (++indirections > UDF_MAX_ICB_NESTING) { udf_err(inode->i_sb, "too many ICBs in ICB hierarchy" " (max %d supported)\n", UDF_MAX_ICB_NESTING); goto out; } brelse(bh); goto reread; } } brelse(ibh); } else if (fe->icbTag.strategyType != cpu_to_le16(4)) { udf_err(inode->i_sb, "unsupported strategy type: %u\n", le16_to_cpu(fe->icbTag.strategyType)); goto out; } if (fe->icbTag.strategyType == cpu_to_le16(4)) iinfo->i_strat4096 = 0; else /* if (fe->icbTag.strategyType == cpu_to_le16(4096)) */ iinfo->i_strat4096 = 1; iinfo->i_alloc_type = le16_to_cpu(fe->icbTag.flags) & ICBTAG_FLAG_AD_MASK; if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_SHORT && iinfo->i_alloc_type != ICBTAG_FLAG_AD_LONG && iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { ret = -EIO; goto out; } iinfo->i_hidden = hidden_inode; iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; iinfo->i_lenAlloc = 0; iinfo->i_next_alloc_block = 0; iinfo->i_next_alloc_goal = 0; if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_EFE)) { iinfo->i_efe = 1; iinfo->i_use = 0; ret = udf_alloc_i_data(inode, bs - sizeof(struct extendedFileEntry)); if (ret) goto out; memcpy(iinfo->i_data, bh->b_data + sizeof(struct extendedFileEntry), bs - sizeof(struct extendedFileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) { iinfo->i_efe = 0; iinfo->i_use = 0; ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry)); if (ret) goto out; memcpy(iinfo->i_data, bh->b_data + sizeof(struct fileEntry), bs - sizeof(struct fileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { iinfo->i_efe = 0; iinfo->i_use = 1; iinfo->i_lenAlloc = le32_to_cpu( ((struct unallocSpaceEntry *)bh->b_data)-> lengthAllocDescs); ret = udf_alloc_i_data(inode, bs - sizeof(struct unallocSpaceEntry)); if (ret) goto out; memcpy(iinfo->i_data, bh->b_data + sizeof(struct unallocSpaceEntry), bs - sizeof(struct unallocSpaceEntry)); return 0; } ret = -EIO; read_lock(&sbi->s_cred_lock); uid = le32_to_cpu(fe->uid); if (uid == UDF_INVALID_ID || UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_SET)) inode->i_uid = sbi->s_uid; else i_uid_write(inode, uid); gid = le32_to_cpu(fe->gid); if (gid == UDF_INVALID_ID || UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_GID_SET)) inode->i_gid = sbi->s_gid; else i_gid_write(inode, gid); if (fe->icbTag.fileType != ICBTAG_FILE_TYPE_DIRECTORY && sbi->s_fmode != UDF_INVALID_MODE) inode->i_mode = sbi->s_fmode; else if (fe->icbTag.fileType == ICBTAG_FILE_TYPE_DIRECTORY && sbi->s_dmode != UDF_INVALID_MODE) inode->i_mode = sbi->s_dmode; else inode->i_mode = udf_convert_permissions(fe); inode->i_mode &= ~sbi->s_umask; iinfo->i_extraPerms = le32_to_cpu(fe->permissions) & ~FE_MAPPED_PERMS; read_unlock(&sbi->s_cred_lock); link_count = le16_to_cpu(fe->fileLinkCount); if (!link_count) { if (!hidden_inode) { ret = -ESTALE; goto out; } link_count = 1; } set_nlink(inode, link_count); inode->i_size = le64_to_cpu(fe->informationLength); iinfo->i_lenExtents = inode->i_size; if (iinfo->i_efe == 0) { inode->i_blocks = le64_to_cpu(fe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); udf_disk_stamp_to_time(&ts, fe->accessTime); inode_set_atime_to_ts(inode, ts); udf_disk_stamp_to_time(&ts, fe->modificationTime); inode_set_mtime_to_ts(inode, ts); udf_disk_stamp_to_time(&ts, fe->attrTime); inode_set_ctime_to_ts(inode, ts); iinfo->i_unique = le64_to_cpu(fe->uniqueID); iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr); iinfo->i_lenAlloc = le32_to_cpu(fe->lengthAllocDescs); iinfo->i_checkpoint = le32_to_cpu(fe->checkpoint); iinfo->i_streamdir = 0; iinfo->i_lenStreams = 0; } else { inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); udf_disk_stamp_to_time(&ts, efe->accessTime); inode_set_atime_to_ts(inode, ts); udf_disk_stamp_to_time(&ts, efe->modificationTime); inode_set_mtime_to_ts(inode, ts); udf_disk_stamp_to_time(&ts, efe->attrTime); inode_set_ctime_to_ts(inode, ts); udf_disk_stamp_to_time(&iinfo->i_crtime, efe->createTime); iinfo->i_unique = le64_to_cpu(efe->uniqueID); iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr); iinfo->i_lenAlloc = le32_to_cpu(efe->lengthAllocDescs); iinfo->i_checkpoint = le32_to_cpu(efe->checkpoint); /* Named streams */ iinfo->i_streamdir = (efe->streamDirectoryICB.extLength != 0); iinfo->i_locStreamdir = lelb_to_cpu(efe->streamDirectoryICB.extLocation); iinfo->i_lenStreams = le64_to_cpu(efe->objectSize); if (iinfo->i_lenStreams >= inode->i_size) iinfo->i_lenStreams -= inode->i_size; else iinfo->i_lenStreams = 0; } inode->i_generation = iinfo->i_unique; /* * Sanity check length of allocation descriptors and extended attrs to * avoid integer overflows */ if (iinfo->i_lenEAttr > bs || iinfo->i_lenAlloc > bs) goto out; /* Now do exact checks */ if (udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc > bs) goto out; /* Sanity checks for files in ICB so that we don't get confused later */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { /* * For file in ICB data is stored in allocation descriptor * so sizes should match */ if (iinfo->i_lenAlloc != inode->i_size) goto out; /* File in ICB has to fit in there... */ if (inode->i_size > bs - udf_file_entry_alloc_offset(inode)) goto out; } switch (fe->icbTag.fileType) { case ICBTAG_FILE_TYPE_DIRECTORY: inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; inode->i_mode |= S_IFDIR; inc_nlink(inode); break; case ICBTAG_FILE_TYPE_REALTIME: case ICBTAG_FILE_TYPE_REGULAR: case ICBTAG_FILE_TYPE_UNDEF: case ICBTAG_FILE_TYPE_VAT20: inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; inode->i_mode |= S_IFREG; break; case ICBTAG_FILE_TYPE_BLOCK: inode->i_mode |= S_IFBLK; break; case ICBTAG_FILE_TYPE_CHAR: inode->i_mode |= S_IFCHR; break; case ICBTAG_FILE_TYPE_FIFO: init_special_inode(inode, inode->i_mode | S_IFIFO, 0); break; case ICBTAG_FILE_TYPE_SOCKET: init_special_inode(inode, inode->i_mode | S_IFSOCK, 0); break; case ICBTAG_FILE_TYPE_SYMLINK: inode->i_data.a_ops = &udf_symlink_aops; inode->i_op = &udf_symlink_inode_operations; inode_nohighmem(inode); inode->i_mode = S_IFLNK | 0777; break; case ICBTAG_FILE_TYPE_MAIN: udf_debug("METADATA FILE-----\n"); break; case ICBTAG_FILE_TYPE_MIRROR: udf_debug("METADATA MIRROR FILE-----\n"); break; case ICBTAG_FILE_TYPE_BITMAP: udf_debug("METADATA BITMAP FILE-----\n"); break; default: udf_err(inode->i_sb, "(ino %lu) failed unknown file type=%u\n", inode->i_ino, fe->icbTag.fileType); goto out; } if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { struct deviceSpec *dsea = (struct deviceSpec *)udf_get_extendedattr(inode, 12, 1); if (dsea) { init_special_inode(inode, inode->i_mode, MKDEV(le32_to_cpu(dsea->majorDeviceIdent), le32_to_cpu(dsea->minorDeviceIdent))); /* Developer ID ??? */ } else goto out; } ret = 0; out: brelse(bh); return ret; } static int udf_alloc_i_data(struct inode *inode, size_t size) { struct udf_inode_info *iinfo = UDF_I(inode); iinfo->i_data = kmalloc(size, GFP_KERNEL); if (!iinfo->i_data) return -ENOMEM; return 0; } static umode_t udf_convert_permissions(struct fileEntry *fe) { umode_t mode; uint32_t permissions; uint32_t flags; permissions = le32_to_cpu(fe->permissions); flags = le16_to_cpu(fe->icbTag.flags); mode = ((permissions) & 0007) | ((permissions >> 2) & 0070) | ((permissions >> 4) & 0700) | ((flags & ICBTAG_FLAG_SETUID) ? S_ISUID : 0) | ((flags & ICBTAG_FLAG_SETGID) ? S_ISGID : 0) | ((flags & ICBTAG_FLAG_STICKY) ? S_ISVTX : 0); return mode; } void udf_update_extra_perms(struct inode *inode, umode_t mode) { struct udf_inode_info *iinfo = UDF_I(inode); /* * UDF 2.01 sec. 3.3.3.3 Note 2: * In Unix, delete permission tracks write */ iinfo->i_extraPerms &= ~FE_DELETE_PERMS; if (mode & 0200) iinfo->i_extraPerms |= FE_PERM_U_DELETE; if (mode & 0020) iinfo->i_extraPerms |= FE_PERM_G_DELETE; if (mode & 0002) iinfo->i_extraPerms |= FE_PERM_O_DELETE; } int udf_write_inode(struct inode *inode, struct writeback_control *wbc) { return udf_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } static int udf_sync_inode(struct inode *inode) { return udf_update_inode(inode, 1); } static void udf_adjust_time(struct udf_inode_info *iinfo, struct timespec64 time) { if (iinfo->i_crtime.tv_sec > time.tv_sec || (iinfo->i_crtime.tv_sec == time.tv_sec && iinfo->i_crtime.tv_nsec > time.tv_nsec)) iinfo->i_crtime = time; } static int udf_update_inode(struct inode *inode, int do_sync) { struct buffer_head *bh = NULL; struct fileEntry *fe; struct extendedFileEntry *efe; uint64_t lb_recorded; uint32_t udfperms; uint16_t icbflags; uint16_t crclen; int err = 0; struct udf_sb_info *sbi = UDF_SB(inode->i_sb); unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; struct udf_inode_info *iinfo = UDF_I(inode); bh = sb_getblk(inode->i_sb, udf_get_lb_pblock(inode->i_sb, &iinfo->i_location, 0)); if (!bh) { udf_debug("getblk failure\n"); return -EIO; } lock_buffer(bh); memset(bh->b_data, 0, inode->i_sb->s_blocksize); fe = (struct fileEntry *)bh->b_data; efe = (struct extendedFileEntry *)bh->b_data; if (iinfo->i_use) { struct unallocSpaceEntry *use = (struct unallocSpaceEntry *)bh->b_data; use->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc); memcpy(bh->b_data + sizeof(struct unallocSpaceEntry), iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct unallocSpaceEntry)); use->descTag.tagIdent = cpu_to_le16(TAG_IDENT_USE); crclen = sizeof(struct unallocSpaceEntry); goto finish; } if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_FORGET)) fe->uid = cpu_to_le32(UDF_INVALID_ID); else fe->uid = cpu_to_le32(i_uid_read(inode)); if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_GID_FORGET)) fe->gid = cpu_to_le32(UDF_INVALID_ID); else fe->gid = cpu_to_le32(i_gid_read(inode)); udfperms = ((inode->i_mode & 0007)) | ((inode->i_mode & 0070) << 2) | ((inode->i_mode & 0700) << 4); udfperms |= iinfo->i_extraPerms; fe->permissions = cpu_to_le32(udfperms); if (S_ISDIR(inode->i_mode) && inode->i_nlink > 0) fe->fileLinkCount = cpu_to_le16(inode->i_nlink - 1); else { if (iinfo->i_hidden) fe->fileLinkCount = cpu_to_le16(0); else fe->fileLinkCount = cpu_to_le16(inode->i_nlink); } fe->informationLength = cpu_to_le64(inode->i_size); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { struct regid *eid; struct deviceSpec *dsea = (struct deviceSpec *)udf_get_extendedattr(inode, 12, 1); if (!dsea) { dsea = (struct deviceSpec *) udf_add_extendedattr(inode, sizeof(struct deviceSpec) + sizeof(struct regid), 12, 0x3); dsea->attrType = cpu_to_le32(12); dsea->attrSubtype = 1; dsea->attrLength = cpu_to_le32( sizeof(struct deviceSpec) + sizeof(struct regid)); dsea->impUseLength = cpu_to_le32(sizeof(struct regid)); } eid = (struct regid *)dsea->impUse; memset(eid, 0, sizeof(*eid)); strcpy(eid->ident, UDF_ID_DEVELOPER); eid->identSuffix[0] = UDF_OS_CLASS_UNIX; eid->identSuffix[1] = UDF_OS_ID_LINUX; dsea->majorDeviceIdent = cpu_to_le32(imajor(inode)); dsea->minorDeviceIdent = cpu_to_le32(iminor(inode)); } if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) lb_recorded = 0; /* No extents => no blocks! */ else lb_recorded = (inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >> (blocksize_bits - 9); if (iinfo->i_efe == 0) { memcpy(bh->b_data + sizeof(struct fileEntry), iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct fileEntry)); fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); udf_time_to_disk_stamp(&fe->accessTime, inode_get_atime(inode)); udf_time_to_disk_stamp(&fe->modificationTime, inode_get_mtime(inode)); udf_time_to_disk_stamp(&fe->attrTime, inode_get_ctime(inode)); memset(&(fe->impIdent), 0, sizeof(struct regid)); strcpy(fe->impIdent.ident, UDF_ID_DEVELOPER); fe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; fe->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; fe->uniqueID = cpu_to_le64(iinfo->i_unique); fe->lengthExtendedAttr = cpu_to_le32(iinfo->i_lenEAttr); fe->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc); fe->checkpoint = cpu_to_le32(iinfo->i_checkpoint); fe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_FE); crclen = sizeof(struct fileEntry); } else { memcpy(bh->b_data + sizeof(struct extendedFileEntry), iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct extendedFileEntry)); efe->objectSize = cpu_to_le64(inode->i_size + iinfo->i_lenStreams); efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); if (iinfo->i_streamdir) { struct long_ad *icb_lad = &efe->streamDirectoryICB; icb_lad->extLocation = cpu_to_lelb(iinfo->i_locStreamdir); icb_lad->extLength = cpu_to_le32(inode->i_sb->s_blocksize); } udf_adjust_time(iinfo, inode_get_atime(inode)); udf_adjust_time(iinfo, inode_get_mtime(inode)); udf_adjust_time(iinfo, inode_get_ctime(inode)); udf_time_to_disk_stamp(&efe->accessTime, inode_get_atime(inode)); udf_time_to_disk_stamp(&efe->modificationTime, inode_get_mtime(inode)); udf_time_to_disk_stamp(&efe->createTime, iinfo->i_crtime); udf_time_to_disk_stamp(&efe->attrTime, inode_get_ctime(inode)); memset(&(efe->impIdent), 0, sizeof(efe->impIdent)); strcpy(efe->impIdent.ident, UDF_ID_DEVELOPER); efe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; efe->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; efe->uniqueID = cpu_to_le64(iinfo->i_unique); efe->lengthExtendedAttr = cpu_to_le32(iinfo->i_lenEAttr); efe->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc); efe->checkpoint = cpu_to_le32(iinfo->i_checkpoint); efe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_EFE); crclen = sizeof(struct extendedFileEntry); } finish: if (iinfo->i_strat4096) { fe->icbTag.strategyType = cpu_to_le16(4096); fe->icbTag.strategyParameter = cpu_to_le16(1); fe->icbTag.numEntries = cpu_to_le16(2); } else { fe->icbTag.strategyType = cpu_to_le16(4); fe->icbTag.numEntries = cpu_to_le16(1); } if (iinfo->i_use) fe->icbTag.fileType = ICBTAG_FILE_TYPE_USE; else if (S_ISDIR(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_DIRECTORY; else if (S_ISREG(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_REGULAR; else if (S_ISLNK(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_SYMLINK; else if (S_ISBLK(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_BLOCK; else if (S_ISCHR(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_CHAR; else if (S_ISFIFO(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_FIFO; else if (S_ISSOCK(inode->i_mode)) fe->icbTag.fileType = ICBTAG_FILE_TYPE_SOCKET; icbflags = iinfo->i_alloc_type | ((inode->i_mode & S_ISUID) ? ICBTAG_FLAG_SETUID : 0) | ((inode->i_mode & S_ISGID) ? ICBTAG_FLAG_SETGID : 0) | ((inode->i_mode & S_ISVTX) ? ICBTAG_FLAG_STICKY : 0) | (le16_to_cpu(fe->icbTag.flags) & ~(ICBTAG_FLAG_AD_MASK | ICBTAG_FLAG_SETUID | ICBTAG_FLAG_SETGID | ICBTAG_FLAG_STICKY)); fe->icbTag.flags = cpu_to_le16(icbflags); if (sbi->s_udfrev >= 0x0200) fe->descTag.descVersion = cpu_to_le16(3); else fe->descTag.descVersion = cpu_to_le16(2); fe->descTag.tagSerialNum = cpu_to_le16(sbi->s_serial_number); fe->descTag.tagLocation = cpu_to_le32( iinfo->i_location.logicalBlockNum); crclen += iinfo->i_lenEAttr + iinfo->i_lenAlloc - sizeof(struct tag); fe->descTag.descCRCLength = cpu_to_le16(crclen); fe->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)fe + sizeof(struct tag), crclen)); fe->descTag.tagChecksum = udf_tag_checksum(&fe->descTag); set_buffer_uptodate(bh); unlock_buffer(bh); /* write the data blocks */ mark_buffer_dirty(bh); if (do_sync) { sync_dirty_buffer(bh); if (buffer_write_io_error(bh)) { udf_warn(inode->i_sb, "IO error syncing udf inode [%08lx]\n", inode->i_ino); err = -EIO; } } brelse(bh); return err; } struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, bool hidden_inode) { unsigned long block = udf_get_lb_pblock(sb, ino, 0); struct inode *inode = iget_locked(sb, block); int err; if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) { if (UDF_I(inode)->i_hidden != hidden_inode) { iput(inode); return ERR_PTR(-EFSCORRUPTED); } return inode; } memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr)); err = udf_read_inode(inode, hidden_inode); if (err < 0) { iget_failed(inode); return ERR_PTR(err); } unlock_new_inode(inode); return inode; } int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, struct extent_position *epos) { struct super_block *sb = inode->i_sb; struct buffer_head *bh; struct allocExtDesc *aed; struct extent_position nepos; struct kernel_lb_addr neloc; int ver, adsize; int err = 0; if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); else if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); else return -EIO; neloc.logicalBlockNum = block; neloc.partitionReferenceNum = epos->block.partitionReferenceNum; bh = sb_getblk(sb, udf_get_lb_pblock(sb, &neloc, 0)); if (!bh) return -EIO; lock_buffer(bh); memset(bh->b_data, 0x00, sb->s_blocksize); set_buffer_uptodate(bh); unlock_buffer(bh); mark_buffer_dirty_inode(bh, inode); aed = (struct allocExtDesc *)(bh->b_data); if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT)) { aed->previousAllocExtLocation = cpu_to_le32(epos->block.logicalBlockNum); } aed->lengthAllocDescs = cpu_to_le32(0); if (UDF_SB(sb)->s_udfrev >= 0x0200) ver = 3; else ver = 2; udf_new_tag(bh->b_data, TAG_IDENT_AED, ver, 1, block, sizeof(struct tag)); nepos.block = neloc; nepos.offset = sizeof(struct allocExtDesc); nepos.bh = bh; /* * Do we have to copy current last extent to make space for indirect * one? */ if (epos->offset + adsize > sb->s_blocksize) { struct kernel_lb_addr cp_loc; uint32_t cp_len; int8_t cp_type; epos->offset -= adsize; err = udf_current_aext(inode, epos, &cp_loc, &cp_len, &cp_type, 0); if (err <= 0) goto err_out; cp_len |= ((uint32_t)cp_type) << 30; __udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1); udf_write_aext(inode, epos, &nepos.block, sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDESCS, 0); } else { __udf_add_aext(inode, epos, &nepos.block, sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDESCS, 0); } brelse(epos->bh); *epos = nepos; return 0; err_out: brelse(bh); return err; } /* * Append extent at the given position - should be the first free one in inode * / indirect extent. This function assumes there is enough space in the inode * or indirect extent. Use udf_add_aext() if you didn't check for this before. */ int __udf_add_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t elen, int inc) { struct udf_inode_info *iinfo = UDF_I(inode); struct allocExtDesc *aed; int adsize; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); else return -EIO; if (!epos->bh) { WARN_ON(iinfo->i_lenAlloc != epos->offset - udf_file_entry_alloc_offset(inode)); } else { aed = (struct allocExtDesc *)epos->bh->b_data; WARN_ON(le32_to_cpu(aed->lengthAllocDescs) != epos->offset - sizeof(struct allocExtDesc)); WARN_ON(epos->offset + adsize > inode->i_sb->s_blocksize); } udf_write_aext(inode, epos, eloc, elen, inc); if (!epos->bh) { iinfo->i_lenAlloc += adsize; mark_inode_dirty(inode); } else { aed = (struct allocExtDesc *)epos->bh->b_data; le32_add_cpu(&aed->lengthAllocDescs, adsize); if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) udf_update_tag(epos->bh->b_data, epos->offset + (inc ? 0 : adsize)); else udf_update_tag(epos->bh->b_data, sizeof(struct allocExtDesc)); mark_buffer_dirty_inode(epos->bh, inode); } return 0; } /* * Append extent at given position - should be the first free one in inode * / indirect extent. Takes care of allocating and linking indirect blocks. */ int udf_add_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t elen, int inc) { int adsize; struct super_block *sb = inode->i_sb; if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); else if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); else return -EIO; if (epos->offset + (2 * adsize) > sb->s_blocksize) { int err; udf_pblk_t new_block; new_block = udf_new_block(sb, NULL, epos->block.partitionReferenceNum, epos->block.logicalBlockNum, &err); if (!new_block) return -ENOSPC; err = udf_setup_indirect_aext(inode, new_block, epos); if (err) return err; } return __udf_add_aext(inode, epos, eloc, elen, inc); } void udf_write_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t elen, int inc) { int adsize; uint8_t *ptr; struct short_ad *sad; struct long_ad *lad; struct udf_inode_info *iinfo = UDF_I(inode); if (!epos->bh) ptr = iinfo->i_data + epos->offset - udf_file_entry_alloc_offset(inode) + iinfo->i_lenEAttr; else ptr = epos->bh->b_data + epos->offset; switch (iinfo->i_alloc_type) { case ICBTAG_FLAG_AD_SHORT: sad = (struct short_ad *)ptr; sad->extLength = cpu_to_le32(elen); sad->extPosition = cpu_to_le32(eloc->logicalBlockNum); adsize = sizeof(struct short_ad); break; case ICBTAG_FLAG_AD_LONG: lad = (struct long_ad *)ptr; lad->extLength = cpu_to_le32(elen); lad->extLocation = cpu_to_lelb(*eloc); memset(lad->impUse, 0x00, sizeof(lad->impUse)); adsize = sizeof(struct long_ad); break; default: return; } if (epos->bh) { if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) { struct allocExtDesc *aed = (struct allocExtDesc *)epos->bh->b_data; udf_update_tag(epos->bh->b_data, le32_to_cpu(aed->lengthAllocDescs) + sizeof(struct allocExtDesc)); } mark_buffer_dirty_inode(epos->bh, inode); } else { mark_inode_dirty(inode); } if (inc) epos->offset += adsize; } /* * Only 1 indirect extent in a row really makes sense but allow upto 16 in case * someone does some weird stuff. */ #define UDF_MAX_INDIR_EXTS 16 /* * Returns 1 on success, -errno on error, 0 on hit EOF. */ int udf_next_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype, int inc) { unsigned int indirections = 0; int ret = 0; udf_pblk_t block; while (1) { ret = udf_current_aext(inode, epos, eloc, elen, etype, inc); if (ret <= 0) return ret; if (*etype != (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) return ret; if (++indirections > UDF_MAX_INDIR_EXTS) { udf_err(inode->i_sb, "too many indirect extents in inode %lu\n", inode->i_ino); return -EFSCORRUPTED; } epos->block = *eloc; epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); block = udf_get_lb_pblock(inode->i_sb, &epos->block, 0); epos->bh = sb_bread(inode->i_sb, block); if (!epos->bh) { udf_debug("reading block %u failed!\n", block); return -EIO; } } } /* * Returns 1 on success, -errno on error, 0 on hit EOF. */ int udf_current_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype, int inc) { int alen; uint8_t *ptr; struct short_ad *sad; struct long_ad *lad; struct udf_inode_info *iinfo = UDF_I(inode); if (!epos->bh) { if (!epos->offset) epos->offset = udf_file_entry_alloc_offset(inode); ptr = iinfo->i_data + epos->offset - udf_file_entry_alloc_offset(inode) + iinfo->i_lenEAttr; alen = udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc; } else { struct allocExtDesc *header = (struct allocExtDesc *)epos->bh->b_data; if (!epos->offset) epos->offset = sizeof(struct allocExtDesc); ptr = epos->bh->b_data + epos->offset; if (check_add_overflow(sizeof(struct allocExtDesc), le32_to_cpu(header->lengthAllocDescs), &alen)) return -1; if (alen > epos->bh->b_size) return -1; } switch (iinfo->i_alloc_type) { case ICBTAG_FLAG_AD_SHORT: sad = udf_get_fileshortad(ptr, alen, &epos->offset, inc); if (!sad) return 0; *etype = le32_to_cpu(sad->extLength) >> 30; eloc->logicalBlockNum = le32_to_cpu(sad->extPosition); eloc->partitionReferenceNum = iinfo->i_location.partitionReferenceNum; *elen = le32_to_cpu(sad->extLength) & UDF_EXTENT_LENGTH_MASK; break; case ICBTAG_FLAG_AD_LONG: lad = udf_get_filelongad(ptr, alen, &epos->offset, inc); if (!lad) return 0; *etype = le32_to_cpu(lad->extLength) >> 30; *eloc = lelb_to_cpu(lad->extLocation); *elen = le32_to_cpu(lad->extLength) & UDF_EXTENT_LENGTH_MASK; break; default: udf_debug("alloc_type = %u unsupported\n", iinfo->i_alloc_type); return -EINVAL; } return 1; } static int udf_insert_aext(struct inode *inode, struct extent_position epos, struct kernel_lb_addr neloc, uint32_t nelen) { struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; int ret; if (epos.bh) get_bh(epos.bh); while (1) { ret = udf_next_aext(inode, &epos, &oeloc, &oelen, &etype, 0); if (ret <= 0) break; udf_write_aext(inode, &epos, &neloc, nelen, 1); neloc = oeloc; nelen = (etype << 30) | oelen; } if (ret == 0) ret = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); return ret; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) { struct extent_position oepos; int adsize; int8_t etype; struct allocExtDesc *aed; struct udf_inode_info *iinfo; struct kernel_lb_addr eloc; uint32_t elen; int ret; if (epos.bh) { get_bh(epos.bh); get_bh(epos.bh); } iinfo = UDF_I(inode); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); else adsize = 0; oepos = epos; if (udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1) <= 0) return -1; while (1) { ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1); if (ret < 0) { brelse(epos.bh); brelse(oepos.bh); return -1; } if (ret == 0) break; udf_write_aext(inode, &oepos, &eloc, (etype << 30) | elen, 1); if (oepos.bh != epos.bh) { oepos.block = epos.block; brelse(oepos.bh); get_bh(epos.bh); oepos.bh = epos.bh; oepos.offset = epos.offset - adsize; } } memset(&eloc, 0x00, sizeof(struct kernel_lb_addr)); elen = 0; if (epos.bh != oepos.bh) { udf_free_blocks(inode->i_sb, inode, &epos.block, 0, 1); udf_write_aext(inode, &oepos, &eloc, elen, 1); udf_write_aext(inode, &oepos, &eloc, elen, 1); if (!oepos.bh) { iinfo->i_lenAlloc -= (adsize * 2); mark_inode_dirty(inode); } else { aed = (struct allocExtDesc *)oepos.bh->b_data; le32_add_cpu(&aed->lengthAllocDescs, -(2 * adsize)); if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) udf_update_tag(oepos.bh->b_data, oepos.offset - (2 * adsize)); else udf_update_tag(oepos.bh->b_data, sizeof(struct allocExtDesc)); mark_buffer_dirty_inode(oepos.bh, inode); } } else { udf_write_aext(inode, &oepos, &eloc, elen, 1); if (!oepos.bh) { iinfo->i_lenAlloc -= adsize; mark_inode_dirty(inode); } else { aed = (struct allocExtDesc *)oepos.bh->b_data; le32_add_cpu(&aed->lengthAllocDescs, -adsize); if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) udf_update_tag(oepos.bh->b_data, epos.offset - adsize); else udf_update_tag(oepos.bh->b_data, sizeof(struct allocExtDesc)); mark_buffer_dirty_inode(oepos.bh, inode); } } brelse(epos.bh); brelse(oepos.bh); return (elen >> 30); } /* * Returns 1 on success, -errno on error, 0 on hit EOF. */ int inode_bmap(struct inode *inode, sector_t block, struct extent_position *pos, struct kernel_lb_addr *eloc, uint32_t *elen, sector_t *offset, int8_t *etype) { unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits; struct udf_inode_info *iinfo; int err = 0; iinfo = UDF_I(inode); if (!udf_read_extent_cache(inode, bcount, &lbcount, pos)) { pos->offset = 0; pos->block = iinfo->i_location; pos->bh = NULL; } *elen = 0; do { err = udf_next_aext(inode, pos, eloc, elen, etype, 1); if (err <= 0) { if (err == 0) { *offset = (bcount - lbcount) >> blocksize_bits; iinfo->i_lenExtents = lbcount; } return err; } lbcount += *elen; } while (lbcount <= bcount); /* update extent cache */ udf_update_extent_cache(inode, lbcount - *elen, pos); *offset = (bcount + *elen - lbcount) >> blocksize_bits; return 1; } |
| 2 6 2 6 2 2 907 905 909 2 907 906 906 906 2 909 2 907 906 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <linux/mmu_notifier.h> #include <linux/parser.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ int *proactive_swappiness; /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Not allow cache_trim_mode to be turned on as part of reclaim? */ unsigned int no_cache_trim_mode:1; /* Has cache_trim_mode failed at least once? */ unsigned int cache_trim_mode_failed:1; /* Proactive reclaim invoked by userspace */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; /* Shared cgroup tree walk failed, rescan the whole tree */ unsigned int memcg_full_walk:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness = 60; #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /* * Returns true for reclaim on the root cgroup. This is true for direct * allocator reclaim and reclaim through cgroup interfaces on the root cgroup. */ static bool root_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup); } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { if (sc->proactive && sc->proactive_swappiness) return *sc->proactive_swappiness; return mem_cgroup_swappiness(memcg); } #else static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool root_reclaim(struct scan_control *sc) { return true; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { return READ_ONCE(vm_swappiness); } #endif /* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to * and including the specified highidx * @zone: The current zone in the iterator * @pgdat: The pgdat which node_zones are being iterated * @idx: The index variable * @highidx: The index of the highest zone to return * * This macro iterates through all managed zones up to and including the specified highidx. * The zone iterator enters an invalid state after macro call and must be reinitialized * before it can be used again. */ #define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx) \ for ((idx) = 0, (zone) = (pgdat)->node_zones; \ (idx) <= (highidx); \ (idx)++, (zone)++) \ if (!managed_zone(zone)) \ continue; \ else static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. */ static void flush_reclaim_state(struct scan_control *sc) { /* * Currently, reclaim_state->reclaimed includes three types of pages * freed outside of vmscan: * (1) Slab pages. * (2) Clean file pages from pruned inodes (on highmem systems). * (3) XFS freed buffer pages. * * For all of these cases, we cannot universally link the pages to a * single memcg. For example, a memcg-aware shrinker can free one object * charged to the target memcg, causing an entire page to be freed. * If we count the entire page as reclaimed from the memcg, we end up * overestimating the reclaimed amount (potentially under-reclaiming). * * Only count such pages for global reclaim to prevent under-reclaiming * from the target memcg; preventing unnecessary retries during memcg * charging and false positives from proactive reclaim. * * For uncommon cases where the freed pages were actually mostly * charged to the target memcg, we end up underestimating the reclaimed * amount. This should be fine. The freed pages will be uncharged * anyway, even if they are not counted here properly, and we will be * able to make forward progress in charging (which is usually in a * retry loop). * * We can go one step further, and report the uncharged objcg pages in * memcg reclaim, to make reporting more accurate and reduce * underestimation, but it's probably not worth the complexity for now. */ if (current->reclaim_state && root_reclaim(sc)) { sc->nr_reclaimed += current->reclaim_state->reclaimed; current->reclaim_state->reclaimed = 0; } } static bool can_demote(int nid, struct scan_control *sc, struct mem_cgroup *memcg) { int demotion_nid; if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; demotion_nid = next_demotion_node(nid); if (demotion_nid == NUMA_NO_NODE) return false; /* If demotion node isn't in the cgroup's mems_allowed, fall back */ return mem_cgroup_node_allowed(memcg, demotion_nid); } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc, memcg); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; struct zone *zone; for_each_managed_zone_pgdat(zone, lruvec_pgdat(lruvec), zid, zone_idx) { if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; struct mem_cgroup *memcg = NULL; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); return freed; } void drop_slab(void) { int nid; int shift = 0; unsigned long freed; do { freed = 0; for_each_online_node(nid) { if (fatal_signal_pending(current)) return; freed += drop_slab_node(nid); } } while ((freed >> shift++) > 1); } #define CHECK_RECLAIMER_OFFSET(type) \ do { \ BUILD_BUG_ON(PGSTEAL_##type - PGSTEAL_KSWAPD != \ PGDEMOTE_##type - PGDEMOTE_KSWAPD); \ BUILD_BUG_ON(PGSTEAL_##type - PGSTEAL_KSWAPD != \ PGSCAN_##type - PGSCAN_KSWAPD); \ } while (0) static int reclaimer_offset(struct scan_control *sc) { CHECK_RECLAIMER_OFFSET(DIRECT); CHECK_RECLAIMER_OFFSET(KHUGEPAGED); CHECK_RECLAIMER_OFFSET(PROACTIVE); if (current_is_kswapd()) return 0; if (current_is_khugepaged()) return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; if (sc->proactive) return PGSTEAL_PROACTIVE - PGSTEAL_KSWAPD; return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; struct zone *zone; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for_each_managed_zone_pgdat(zone, pgdat, i, MAX_NR_ZONES - 1) { reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle user workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_USER_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; static pageout_t writeout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug, struct list_head *folio_list) { int res; folio_set_reclaim(folio); /* * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled * or we failed to allocate contiguous swap entries, in which case * the split out folios get added back to folio_list. */ if (shmem_mapping(mapping)) res = shmem_writeout(folio, plug, folio_list); else res = swap_writeout(folio, plug); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } /* synchronous write? */ if (!folio_test_writeback(folio)) folio_clear_reclaim(folio); trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } /* * pageout is called by shrink_folio_list() for each dirty folio. */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug, struct list_head *folio_list) { /* * We no longer attempt to writeback filesystem folios here, other * than tmpfs/shmem. That's taken care of in page-writeback. * If we find a dirty filesystem folio at the end of the LRU list, * typically that means the filesystem is saturating the storage * with contiguous writes and telling it to write a folio here * would only make the situation worse by injecting an element * of random access. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (!shmem_mapping(mapping) && !folio_test_anon(folio)) return PAGE_ACTIVATE; if (!folio_clear_dirty_for_io(folio)) return PAGE_CLEAN; return writeout(folio, mapping, plug, folio_list); } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; struct swap_cluster_info *ci; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (folio_test_swapcache(folio)) { ci = swap_cluster_get_and_lock_irq(folio); } else { spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); } /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio->swap; if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); __swap_cache_del_folio(ci, folio, swap, shadow); memcg1_swapout(folio, swap); swap_cluster_unlock_irq(ci); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: if (folio_test_swapcache(folio)) { swap_cluster_unlock_irq(ci); } else { xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); } return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; #ifdef CONFIG_LRU_GEN /* * Only used on a mapped folio in the eviction (rmap walk) path, where promotion * needs to be done by taking the folio off the LRU list and then adding it back * with PG_active set. In contrast, the aging (page table walk) path uses * folio_update_gen(). */ static bool lru_gen_set_refs(struct folio *folio) { /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); return false; } set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS, BIT(PG_workingset)); return true; } #else static bool lru_gen_set_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; vm_flags_t vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* * There are two cases to consider. * 1) Rmap lock contention: rotate. * 2) Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (lru_gen_enabled()) { if (!referenced_ptes) return FOLIOREF_RECLAIM; return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP; } referenced_folio = folio_test_clear_referenced(folio); if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } static struct folio *alloc_demote_folio(struct folio *src, unsigned long private) { struct folio *dst; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; dst = alloc_migration_target(src, (unsigned long)mtc); if (dst) return dst; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(src, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask, .reason = MR_DEMOTION, }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_demote_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references, struct mem_cgroup *memcg) { struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0, nr_demoted = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; folio_batch_init(&free_folios); memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc, memcg); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; if (folio_contain_hwpoisoned_page(folio)) { /* * unmap_poisoned_folio() can't handle large * folio, just skip it. memory_failure() will * handle it if the UCE is triggered again. */ if (folio_test_large(folio)) goto keep_locked; unmap_poisoned_folio(folio, folio_pfn(folio), false); folio_unlock(folio); folio_put(folio); continue; } VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs), or the folio belongs to a mapping where * waiting on writeback during reclaim may lead to a deadlock. * In this case mark the folio for immediate reclaim and * continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { mapping = folio_mapping(folio); /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask) || (mapping && mapping_writeback_may_deadlock_on_reclaim(mapping))) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, 1, NULL)) goto activate_locked; /* * Split partially mapped folios right away. * We can free the unmapped pages without IO. */ if (data_race(!list_empty(&folio->_deferred_list) && folio_test_partially_mapped(folio)) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOWARN)) { int __maybe_unused order = folio_order(folio); if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (nr_pages >= HPAGE_PMD_NR) { count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } #endif count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); if (folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOWARN)) goto activate_locked_split; } /* * Normally the folio will be dirtied in unmap because its * pte should be dirty. A special case is MADV_FREE page. The * page's pte could have dirty bit cleared but the folio's * SwapBacked flag is still set because clearing the dirty bit * and SwapBacked flag has no lock protected. For such folio, * unmap will not set dirty bit for it, so folio reclaim will * not write the folio out. This can cause data corruption when * the folio is swapped in later. Always setting the dirty flag * for the folio solves the problem. */ folio_mark_dirty(folio); } } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; /* * Without TTU_SYNC, try_to_unmap will only begin to * hold PTL from the first present PTE within a large * folio. Some initial PTEs might be skipped due to * races with parallel PTE writes in which PTEs can be * cleared temporarily before being written new present * values. This will lead to a large folio is still * mapped while some subpages have been partially * unmapped after try_to_unmap; TTU_SYNC helps * try_to_unmap acquire PTL from the first PTE, * eliminating the influence of temporary PTE values. */ if (folio_test_large(folio)) flags |= TTU_SYNC; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } /* * Folio is unmapped now so it cannot be newly pinned anymore. * No point in trying to reclaim folio if it is pinned. * Furthermore we don't want to reclaim underlying fs metadata * if the folio is pinned and thus potentially modified by the * pinning process as that may upset the filesystem. */ if (folio_maybe_dma_pinned(folio)) goto activate_locked; mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug, folio_list)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: /* * If shmem folio is split when writeback to swap, * the tail pages will make their own pass through * this function and be accounted then. */ if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } goto activate_locked; case PAGE_SUCCESS: if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); } continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ nr_demoted = demote_folio_list(&demote_folios, pgdat); nr_reclaimed += nr_demoted; stat->nr_demoted += nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ list_splice_init(&demote_folios, folio_list); /* * goto retry to reclaim the undemoted folios in folio_list if * desired. * * Reclaiming directly from top tier nodes is not often desired * due to it breaking the LRU ordering: in general memory * should be reclaimed from lower tier nodes and demoted from * top tier nodes. * * However, disabling reclaim from top tier nodes entirely * would cause ooms in edge scenarios where lower tier memory * is unreclaimable for whatever reason, eg memory being * mlocked or too hot to reclaim. We can disable reclaim * from top tier nodes in proactive reclaim though as that is * not real memory pressure. */ if (!sc->proactive) { do_demote_pass = false; goto retry; } } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { /* TODO: these pages should not even appear in this list. */ if (page_has_movable_ops(&folio->page)) continue; if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true, NULL); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0, total_scan = 0, scan = 0; unsigned long nr_pages; unsigned long max_nr_skipped = 0; LIST_HEAD(folios_skipped); while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; /* Using max_nr_skipped to prevent hard LOCKUP*/ if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED && (folio_zonenum(folio) > sc->reclaim_idx)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; max_nr_skipped++; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: true if the folio was removed from an LRU list. * false if the folio was not on an LRU list. */ bool folio_isolate_lru(struct folio *folio) { bool ret = false; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = true; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static bool too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return false; if (!writeback_throttling_sane(sc)) return false; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if (gfp_has_io_fs(sc->gfp_mask)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; struct folio_batch free_folios; folio_batch_init(&free_folios); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } if (free_folios.nr) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = PGSCAN_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false, lruvec_memcg(lruvec)); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc), stat.nr_demoted); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); lru_note_cost_unlock_irq(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; vm_flags_t vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; bool file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_needs_release(folio) && folio_trylock(folio)) { filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); __count_vm_events(PGDEACTIVATE, nr_deactivate); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); lru_note_cost_unlock_irq(lruvec, file, 0, nr_rotated); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &stat, true, NULL); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } trace_mm_vmscan_reclaim_pages(pgdat->node_id, sc.nr_scanned, nr_reclaimed, &stat); return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats in rate-limited way as we don't need * most accurate stats here. We may switch to regular stats flushing * in the future once it is cheap enough. */ mem_cgroup_flush_stats_ratelimited(sc->target_mem_cgroup); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) && !sc->no_cache_trim_mode) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; struct zone *zone; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for_each_managed_zone_pgdat(zone, pgdat, z, MAX_NR_ZONES - 1) { total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } static inline void calculate_pressure_balance(struct scan_control *sc, int swappiness, u64 *fraction, u64 *denominator) { unsigned long anon_cost, file_cost, total_cost; unsigned long ap, fp; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[WORKINGSET_ANON] = ap; fraction[WORKINGSET_FILE] = fp; *denominator = ap + fp; } static unsigned long apply_proportional_protection(struct mem_cgroup *memcg, struct scan_control *sc, unsigned long scan) { unsigned long min, low; mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan -= scan * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } return scan; } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); int swappiness = sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* Proactive reclaim initiated by userspace for anonymous memory only */ if (swappiness == SWAPPINESS_ANON_ONLY) { WARN_ON_ONCE(!sc->proactive); scan_balance = SCAN_ANON; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now to make sure * a streaming file access pattern doesn't cause swapping. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; calculate_pressure_balance(sc, swappiness, fraction, &denominator); out: for_each_evictable_lru(lru) { bool file = is_file_lru(lru); unsigned long lruvec_size; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); scan = apply_proportional_protection(memcg, sc, lruvec_size); scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct lruvec *lruvec, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(lruvec_pgdat(lruvec)->node_id, sc, lruvec_memcg(lruvec)); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif static bool should_walk_mmu(void) { return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK); } static bool should_clear_pmd_young(void) { return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG); } /****************************************************************************** * shorthand helpers ******************************************************************************/ #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } /* Get the min/max evictable type based on swappiness */ #define min_type(swappiness) (!(swappiness)) #define max_type(swappiness) ((swappiness) < SWAPPINESS_ANON_ONLY) #define evictable_min_seq(min_seq, swappiness) \ min((min_seq)[min_type(swappiness)], (min_seq)[max_type(swappiness)]) #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) #define for_each_evictable_type(type, swappiness) \ for ((type) = min_type(swappiness); (type) <= max_type(swappiness); (type)++) #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* see the comment in mem_cgroup_lruvec() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &pgdat->__lruvec; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!sc->may_swap) return 0; if (!can_demote(pgdat->node_id, sc, memcg) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return sc_swappiness(sc, memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { int type; for (type = 0; type < ANON_AND_FILE; type++) { int n = get_nr_gens(lruvec, type); if (n < MIN_NR_GENS || n > MAX_NR_GENS) return false; } return true; } /****************************************************************************** * Bloom filters ******************************************************************************/ /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = mm_state->filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(mm_state->filters[gen], filter); } /****************************************************************************** * mm_struct list ******************************************************************************/ #ifdef CONFIG_LRU_GEN_WALKS_MMU static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return &lruvec->mm_state; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { int key; struct mm_struct *mm; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return NULL; clear_bit(key, &mm->lru_gen.bitmap); return mmget_not_zero(mm) ? mm : NULL; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* the first addition since the last iteration */ if (mm_state->tail == &mm_list->fifo) mm_state->tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* where the current iteration continues after */ if (mm_state->head == &mm->lru_gen.list) mm_state->head = mm_state->head->prev; /* where the last iteration ended before */ if (mm_state->tail == &mm->lru_gen.list) mm_state->tail = mm_state->tail->next; } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; /* migration can happen before addition */ if (!mm->lru_gen.memcg) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { return NULL; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return NULL; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { return NULL; } #endif static void reset_mm_stats(struct lru_gen_mm_walk *walk, bool last) { int i; int hist; struct lruvec *lruvec = walk->lruvec; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); hist = lru_hist_from_seq(walk->seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(mm_state->stats[hist][i], mm_state->stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(walk->seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(mm_state->stats[hist][i], 0); } } static bool iterate_mm_list(struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = false; struct mm_struct *mm = NULL; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* * mm_state->seq is incremented after each iteration of mm_list. There * are three interesting cases for this page table walker: * 1. It tries to start a new iteration with a stale max_seq: there is * nothing left to do. * 2. It started the next iteration: it needs to reset the Bloom filter * so that a fresh set of PTE tables can be recorded. * 3. It ended the current iteration: it needs to reset the mm stats * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->seq); if (walk->seq <= mm_state->seq) goto done; if (!mm_state->head) mm_state->head = &mm_list->fifo; if (mm_state->head == &mm_list->fifo) first = true; do { mm_state->head = mm_state->head->next; if (mm_state->head == &mm_list->fifo) { WRITE_ONCE(mm_state->seq, mm_state->seq + 1); last = true; break; } /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == mm_state->head) { mm_state->tail = mm_state->head->next; walk->force_scan = true; } } while (!(mm = get_next_mm(walk))); done: if (*iter || last) reset_mm_stats(walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(mm_state, walk->seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < seq); if (seq > mm_state->seq) { mm_state->head = NULL; mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * PID controller ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { int i; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->gain = gain; pos->refaulted = pos->total = 0; for (i = tier % MAX_NR_TIERS; i <= min(tier, MAX_NR_TIERS - 1); i++) { pos->refaulted += lrugen->avg_refaulted[type][i] + atomic_long_read(&lrugen->refaulted[hist][type][i]); pos->total += lrugen->avg_total[type][i] + lrugen->protected[hist][type][i] + atomic_long_read(&lrugen->evicted[hist][type][i]); } } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + lrugen->protected[hist][type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); WRITE_ONCE(lrugen->protected[hist][type][tier], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); return -1; } do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) return -1; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset); } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lruvec *lruvec = walk->lruvec; struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (!vma_has_recency(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->swappiness; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->swappiness; if (walk->swappiness > MAX_SWAPPINESS) return true; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_special(pte))) return -1; if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return -1; return pfn; } static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return -1; return pfn; } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct folio *folio = pfn_folio(pfn); if (folio_lru_gen(folio) < 0) return NULL; if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg(folio) != memcg) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio, int new_gen, bool dirty) { int old_gen; if (!folio) return; if (dirty && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); if (walk) { old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } else if (lru_gen_set_refs(folio)) { old_gen = folio_lru_gen(folio); if (old_gen >= 0 && old_gen != new_gen) folio_activate(folio); } } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; bool dirty; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int gen = lru_gen_from_seq(max_seq); pmd_t pmdval; pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { pte_unmap(pte); return true; } if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { pte_unmap_unlock(pte, ptl); return false; } arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; pte_t ptent = ptep_get(pte + i); total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(args->vma, addr, pte + i)) continue; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pte_dirty(ptent)) dirty = true; young++; walk->mm_stats[MM_LEAF_YOUNG]++; } walk_update_folio(walk, last, gen, dirty); last = NULL; if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte, ptl); return suitable_to_scan(total, young); } static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; bool dirty; pmd_t *pmd; spinlock_t *ptl; struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int gen = lru_gen_from_seq(max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*first == -1) { *first = addr; bitmap_zero(bitmap, MIN_LRU_BATCH); return; } i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *first); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; if (!pmd_present(pmd[i])) goto next; if (!pmd_trans_huge(pmd[i])) { if (!walk->force_scan && should_clear_pmd_young() && !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); if (pfn == -1) goto next; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) goto next; if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pmd_dirty(pmd[i])) dirty = true; walk->mm_stats[MM_LEAF_YOUNG]++; next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); walk_update_folio(walk, last, gen, dirty); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *first = -1; } static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; DECLARE_BITMAP(bitmap, MIN_LRU_BATCH); unsigned long first = -1; struct lru_gen_mm_walk *walk = args->private; struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmdp_get_lockless(pmd + i); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } if (pmd_trans_huge(val)) { struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; if (pfn != -1) walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } if (!walk->force_scan && should_clear_pmd_young() && !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); } if (!walk->force_scan && !test_bloom_filter(mm_state, walk->seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(mm_state, walk->seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; int err; struct lruvec *lruvec = walk->lruvec; walk->next_addr = FIRST_USER_ADDRESS; do { DEFINE_MAX_SEQ(lruvec); err = -EBUSY; /* another thread might have called inc_max_seq() */ if (walk->seq != max_seq) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!walk && force_alloc) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); /* For file type, skip the check if swappiness is anon only */ if (type && (swappiness == SWAPPINESS_ANON_ONLY)) goto done; /* For anon type, skip the check if swappiness is zero (file only) */ if (!type && !swappiness) goto done; /* prevent cold/hot inversion if the type is evictable */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); /* don't count the workingset being lazily promoted */ if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { int tier = lru_tier_from_refs(refs, workingset); int delta = folio_nr_pages(folio); WRITE_ONCE(lrugen->protected[hist][type][tier], lrugen->protected[hist][type][tier] + delta); } if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness) { int gen, type, zone; bool success = false; bool seq_inc_flag = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for_each_evictable_type(type, swappiness) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } min_seq[type]++; seq_inc_flag = true; } next: ; } /* * If min_seq[type] of both anonymous and file is not increased, * we can directly return false to avoid unnecessary checking * overhead later. */ if (!seq_inc_flag) return success; /* see the comment on lru_gen_folio */ if (swappiness && swappiness <= MAX_SWAPPINESS) { unsigned long seq = lrugen->max_seq - MIN_NR_GENS; if (min_seq[LRU_GEN_ANON] > seq && min_seq[LRU_GEN_FILE] < seq) min_seq[LRU_GEN_ANON] = seq; else if (min_seq[LRU_GEN_FILE] > seq && min_seq[LRU_GEN_ANON] < seq) min_seq[LRU_GEN_FILE] = seq; } for_each_evictable_type(type, swappiness) { if (min_seq[type] <= lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness) { bool success; int prev, next; int type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; restart: if (seq < READ_ONCE(lrugen->max_seq)) return false; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); success = seq == lrugen->max_seq; if (!success) goto unlock; for (type = 0; type < ANON_AND_FILE; type++) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; if (inc_min_seq(lruvec, type, swappiness)) continue; spin_unlock_irq(&lruvec->lru_lock); cond_resched(); goto restart; } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); unlock: spin_unlock_irq(&lruvec->lru_lock); return success; } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) return inc_max_seq(lruvec, seq, swappiness); /* see the comment in iterate_mm_list() */ if (seq <= READ_ONCE(mm_state->seq)) return false; /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!should_walk_mmu()) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk = set_mm_walk(NULL, true); if (!walk) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk->lruvec = lruvec; walk->seq = seq; walk->swappiness = swappiness; walk->force_scan = force_scan; do { success = iterate_mm_list(walk, &mm); if (mm) walk_mm(mm, walk); } while (mm); done: if (success) { success = inc_max_seq(lruvec, seq, swappiness); WARN_ON_ONCE(!success); } return success; } /****************************************************************************** * working set protection ******************************************************************************/ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) { int priority; unsigned long reclaimable; if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* * Determine the initial priority based on * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); /* * The estimation is based on LRU pages only, so cap it to prevent * overshoots of shrinker objects by large margins. */ sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); } static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; int swappiness = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } /* whether the size is big enough to be helpful */ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total; } static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { int gen; unsigned long birth; int swappiness = get_swappiness(lruvec, sc); struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; gen = lru_gen_from_seq(evictable_min_seq(min_seq, swappiness)); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); mem_cgroup_calculate_protection(NULL, memcg); if (!reclaimable) reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /****************************************************************************** * rmap/PT walk feedback ******************************************************************************/ /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; bool dirty; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; struct folio *last = NULL; int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); int gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (!ptep_clear_young_notify(vma, addr, pte)) return false; if (spin_is_contended(pvmw->ptl)) return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start == PAGE_SIZE) return true; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2; end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2; } } arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pte_t ptent = ptep_get(pte + i); pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(vma, addr, pte + i)) continue; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pte_dirty(ptent)) dirty = true; young++; } walk_update_folio(walk, last, gen, dirty); arch_leave_lazy_mmu_mode(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); return true; } /****************************************************************************** * memcg LRU ******************************************************************************/ /* see the comment on MEMCG_NR_GENS */ enum { MEMCG_LRU_NOP, MEMCG_LRU_HEAD, MEMCG_LRU_TAIL, MEMCG_LRU_OLD, MEMCG_LRU_YOUNG, }; static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); seg = 0; new = old = lruvec->lrugen.gen; /* see the comment on MEMCG_NR_GENS */ if (op == MEMCG_LRU_HEAD) seg = MEMCG_LRU_HEAD; else if (op == MEMCG_LRU_TAIL) seg = MEMCG_LRU_TAIL; else if (op == MEMCG_LRU_OLD) new = get_memcg_gen(pgdat->memcg_lru.seq); else if (op == MEMCG_LRU_YOUNG) new = get_memcg_gen(pgdat->memcg_lru.seq + 1); else VM_WARN_ON_ONCE(true); WRITE_ONCE(lruvec->lrugen.seg, seg); WRITE_ONCE(lruvec->lrugen.gen, new); hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); else hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } #ifdef CONFIG_MEMCG void lru_gen_online_memcg(struct mem_cgroup *memcg) { int gen; int nid; int bin = get_random_u32_below(MEMCG_NR_BINS); for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); gen = get_memcg_gen(pgdat->memcg_lru.seq); lruvec->lrugen.gen = gen; hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_offline_memcg(struct mem_cgroup *memcg) { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); } } void lru_gen_release_memcg(struct mem_cgroup *memcg) { int gen; int nid; for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); if (hlist_nulls_unhashed(&lruvec->lrugen.list)) goto unlock; gen = lruvec->lrugen.gen; hlist_nulls_del_init_rcu(&lruvec->lrugen.list); pgdat->memcg_lru.nr_memcgs[gen]--; if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); unlock: spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); } #endif /* CONFIG_MEMCG */ /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, int tier_idx) { bool success; bool dirty, writeback; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); int tier = lru_tier_from_refs(refs, workingset); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) { gen = folio_inc_gen(lruvec, folio, false); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); /* don't count the workingset being lazily promoted */ if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); WRITE_ONCE(lrugen->protected[hist][type][tier], lrugen->protected[hist][type][tier] + delta); } return true; } /* ineligible */ if (zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } dirty = folio_test_dirty(folio); writeback = folio_test_writeback(folio); if (type == LRU_GEN_FILE && dirty) { sc->nr.file_taken += delta; if (!writeback) sc->nr.unqueued_dirty += delta; } /* waiting for writeback */ if (writeback || (type == LRU_GEN_FILE && dirty)) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* swap constrained */ if (!(sc->gfp_mask & __GFP_IO) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags.f, LRU_REFS_MASK, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int i; int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int skipped = 0; int remaining = min(nr_to_scan, MAX_LRU_BATCH); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped_zone += delta; } if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } if (skipped_zone) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = PGSCAN_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } count_memcg_events(memcg, item, isolated); count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); if (type == LRU_GEN_FILE) sc->nr.file_taken += isolated; /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (2:3). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 2, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 3, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness) { struct ctrl_pos sp, pv; if (swappiness <= MIN_SWAPPINESS + 1) return LRU_GEN_FILE; if (swappiness >= MAX_SWAPPINESS) return LRU_GEN_ANON; /* * Compare the sum of all tiers of anon with that of file to determine * which type to scan. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv); return positive_ctrl_err(&sp, &pv); } static int isolate_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type = get_type_to_scan(lruvec, swappiness); for_each_evictable_type(i, swappiness) { int scanned; int tier = get_tier_idx(lruvec, type); *type_scanned = type; scanned = scan_folios(nr_to_scan, lruvec, sc, type, tier, list); if (scanned) return scanned; type = !type; } return 0; } static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, int swappiness) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(nr_to_scan, lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (evictable_min_seq(lrugen->min_seq, swappiness) + MIN_NR_GENS > lrugen->max_seq) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false, memcg); sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { DEFINE_MIN_SEQ(lruvec); if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) && !folio_test_dirty(folio) && !folio_test_writeback(folio)) { list_move(&folio->lru, &clean); continue; } /* don't add rejected folios to the oldest generation */ if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type]) set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS, BIT(PG_active)); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) { walk->lruvec = lruvec; reset_batch_size(walk); } __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc), stat.nr_demoted); item = PGSTEAL_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } return scanned; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, int swappiness, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long size = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); *nr_to_scan = 0; /* have to run aging, since eviction is not possible anymore */ if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq) return true; for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } *nr_to_scan = size; /* better to run aging even though eviction is still possible */ return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { bool success; unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; success = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan); /* try to scrape all its memory if this memcg was deleted */ if (nr_to_scan && !mem_cgroup_online(memcg)) return nr_to_scan; nr_to_scan = apply_proportional_protection(memcg, sc, nr_to_scan); /* try to get away with not aging at the default priority */ if (!success || sc->priority == DEF_PRIORITY) return nr_to_scan >> sc->priority; /* stop scanning this lruvec as it's low on cold folios */ return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { int i; enum zone_watermarks mark; /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) return false; if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; /* check the order to exclude compaction-induced reclaim */ if (!current_is_kswapd() || sc->order) return false; mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? WMARK_PROMO : WMARK_HIGH; for (i = 0; i <= sc->reclaim_idx; i++) { struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) return false; } /* kswapd should abort if all eligible zones are safe */ return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; int swappiness = get_swappiness(lruvec, sc); while (true) { int delta; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); if (nr_to_scan <= 0) break; delta = evict_folios(nr_to_scan, lruvec, sc, swappiness); if (!delta) break; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, sc)) break; cond_resched(); } /* * If too many file cache in the coldest generation can't be evicted * due to being dirty, wake up the flusher. */ if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) wakeup_flusher_threads(WB_REASON_VMSCAN); /* whether this lruvec should be rotated */ return nr_to_scan < 0; } static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) { bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); } success = try_to_shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); flush_reclaim_state(sc); if (success && mem_cgroup_online(memcg)) return MEMCG_LRU_YOUNG; if (!success && lruvec_is_sizable(lruvec, sc)) return 0; /* one retry if offlined or too small */ return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) { int op; int gen; int bin; int first_bin; struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct hlist_nulls_node *pos; gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; rcu_read_lock(); hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { if (op) { lru_gen_rotate_memcg(lruvec, op); op = 0; } mem_cgroup_put(memcg); memcg = NULL; if (gen != READ_ONCE(lrugen->gen)) continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); if (!mem_cgroup_tryget(memcg)) { lru_gen_release_memcg(memcg); memcg = NULL; continue; } rcu_read_unlock(); op = shrink_one(lruvec, sc); rcu_read_lock(); if (should_abort_scan(lruvec, sc)) break; } rcu_read_unlock(); if (op) lru_gen_rotate_memcg(lruvec, op); mem_cgroup_put(memcg); if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ if (gen != get_nulls_value(pos)) goto restart; /* try the rest of the bins of the current generation */ bin = get_memcg_bin(bin + 1); if (bin != first_bin) goto restart; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; VM_WARN_ON_ONCE(root_reclaim(sc)); VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(NULL, sc->proactive); if (try_to_shrink_lruvec(lruvec, sc)) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); clear_mm_walk(); blk_finish_plug(&plug); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; unsigned long reclaimed = sc->nr_reclaimed; VM_WARN_ON_ONCE(!root_reclaim(sc)); /* * Unmapped clean folios are already prioritized. Scanning for more of * them is likely futile and can cause high reclaim latency when there * is a large number of memcgs. */ if (!sc->may_writepage || !sc->may_unmap) goto done; lru_add_drain(); blk_start_plug(&plug); set_mm_walk(pgdat, sc->proactive); set_initial_priority(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed = 0; if (mem_cgroup_disabled()) shrink_one(&pgdat->__lruvec, sc); else shrink_many(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed += reclaimed; clear_mm_walk(); blk_finish_plug(&plug); done: if (sc->nr_reclaimed > reclaimed) atomic_set(&pgdat->kswapd_failures, 0); } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (should_walk_mmu()) caps |= BIT(LRU_GEN_MM_WALK); if (should_clear_pmd_young()) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return sysfs_emit(buf, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); n[2] = READ_ONCE(lrugen->protected[hist][type][tier]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } if (!mm_state) return; seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = debugfs_get_aux_num(m->file); struct lruvec *lruvec = v; struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = evictable_min_seq(min_seq, MAX_SWAPPINESS / 2); else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, int swappiness, bool force_scan) { DEFINE_MAX_SEQ(lruvec); if (seq > max_seq) return -EINVAL; return try_to_inc_max_seq(lruvec, max_seq, swappiness, force_scan) ? 0 : -EEXIST; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < evictable_min_seq(min_seq, swappiness)) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(nr_to_reclaim - sc->nr_reclaimed, lruvec, sc, swappiness)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); if (!mem_cgroup_tryget(memcg)) memcg = NULL; rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; sc->target_mem_cgroup = memcg; lruvec = get_lruvec(memcg, nid); if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); else if (swappiness > SWAPPINESS_ANON_ONLY) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, .proactive = true, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL, true)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd, swap_string[5]; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %4s %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, swap_string, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } if (n == 4) { swappiness = -1; } else if (!strcmp("max", swap_string)) { /* set by userspace for anonymous memory only */ swappiness = SWAPPINESS_ANON_ONLY; } else { err = kstrtouint(swap_string, 0, &swappiness); if (err) break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_pgdat(struct pglist_data *pgdat) { int i, j; spin_lock_init(&pgdat->memcg_lru.lock); for (i = 0; i < MEMCG_NR_GENS; i++) { for (j = 0; j < MEMCG_NR_BINS; j++) INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); } } void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); if (mm_state) mm_state->seq = MIN_NR_GENS; } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { struct lru_gen_mm_list *mm_list = get_mm_list(memcg); if (!mm_list) return; INIT_LIST_HEAD(&mm_list->fifo); spin_lock_init(&mm_list->lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo)); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); lruvec->lrugen.list.next = LIST_POISON1; if (!mm_state) continue; for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(mm_state->filters[i]); mm_state->filters[i] = NULL; } } } #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, false, &lru_gen_rw_fops); debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, true, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled() && !root_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec, sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; struct zone *zone; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for_each_managed_zone_pgdat(zone, pgdat, z, sc->reclaim_idx) { unsigned long watermark = min_wmark_pages(zone); /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, watermark, sc->reclaim_idx, 0)) return false; if (compaction_suitable(zone, sc->order, watermark, sc->reclaim_idx)) return false; } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, }; struct mem_cgroup_reclaim_cookie *partial = &reclaim; struct mem_cgroup *memcg; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree, using an iterator state that * persists across invocations. This strikes a balance between * fairness and allocation latency. * |