From 4e40eff0b5737c0de39e1ae5812509efbc0b986e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:18 -0400 Subject: [PATCH 01/13] fs: add infrastructure for multigrain timestamps The VFS has always used coarse-grained timestamps when updating the ctime and mtime after a change. This has the benefit of allowing filesystems to optimize away a lot metadata updates, down to around 1 per jiffy, even when a file is under heavy writes. Unfortunately, this has always been an issue when we're exporting via NFSv3, which relies on timestamps to validate caches. A lot of changes can happen in a jiffy, so timestamps aren't sufficient to help the client decide when to invalidate the cache. Even with NFSv4, a lot of exported filesystems don't properly support a change attribute and are subject to the same problems with timestamp granularity. Other applications have similar issues with timestamps (e.g backup applications). If fine-grained timestamps were always used, that would improve the situation, but that becomes rather expensive, as the underlying filesystem would have to log a lot more metadata updates. What is needed is a way to only use fine-grained timestamps when they are being actively queried. Use the (unused) top bit in inode->i_ctime_nsec as a flag that indicates whether the current timestamps have been queried via stat() or the like. When it's set, allow the update to use a fine-grained timestamp iff it's necessary to make the ctime show a different value. If it has been queried, then first see whether the current coarse time is later than the existing ctime. If it is, accept that value. If it isn't, then get a fine-grained timestamp and attempt to stamp the inode ctime with that value. If that races with another concurrent stamp, then abandon the update and take the new value without retrying. Filesystems can opt into this by setting the FS_MGTIME fstype flag. Others should be unaffected (other than being subject to the same floor value as multigrain filesystems). Tested-by: Randy Dunlap # documentation bits Reviewed-by: Jan Kara Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-3-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/inode.c | 141 ++++++++++++++++++++++++++++++++++++--------- fs/stat.c | 43 +++++++++++++- include/linux/fs.h | 34 ++++++++--- 3 files changed, 182 insertions(+), 36 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 10c4619faeef..53f56f6e1ff2 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2172,19 +2172,58 @@ int file_remove_privs(struct file *file) } EXPORT_SYMBOL(file_remove_privs); +/** + * current_time - Return FS time (possibly fine-grained) + * @inode: inode. + * + * Return the current time truncated to the time granularity supported by + * the fs, as suitable for a ctime/mtime change. If the ctime is flagged + * as having been QUERIED, get a fine-grained timestamp, but don't update + * the floor. + * + * For a multigrain inode, this is effectively an estimate of the timestamp + * that a file would receive. An actual update must go through + * inode_set_ctime_current(). + */ +struct timespec64 current_time(struct inode *inode) +{ + struct timespec64 now; + u32 cns; + + ktime_get_coarse_real_ts64_mg(&now); + + if (!is_mgtime(inode)) + goto out; + + /* If nothing has queried it, then coarse time is fine */ + cns = smp_load_acquire(&inode->i_ctime_nsec); + if (cns & I_CTIME_QUERIED) { + /* + * If there is no apparent change, then get a fine-grained + * timestamp. + */ + if (now.tv_nsec == (cns & ~I_CTIME_QUERIED)) + ktime_get_real_ts64(&now); + } +out: + return timestamp_truncate(now, inode); +} +EXPORT_SYMBOL(current_time); + static int inode_needs_update_time(struct inode *inode) { + struct timespec64 now, ts; int sync_it = 0; - struct timespec64 now = current_time(inode); - struct timespec64 ts; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; + now = current_time(inode); + ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) - sync_it = S_MTIME; + sync_it |= S_MTIME; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) @@ -2562,6 +2601,15 @@ void inode_nohighmem(struct inode *inode) } EXPORT_SYMBOL(inode_nohighmem); +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) +{ + set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec); + inode->i_ctime_sec = ts.tv_sec; + inode->i_ctime_nsec = ts.tv_nsec; + return ts; +} +EXPORT_SYMBOL(inode_set_ctime_to_ts); + /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec @@ -2593,37 +2641,78 @@ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) } EXPORT_SYMBOL(timestamp_truncate); -/** - * current_time - Return FS time - * @inode: inode. - * - * Return the current time truncated to the time granularity supported by - * the fs. - * - * Note that inode and inode->sb cannot be NULL. - * Otherwise, the function warns and returns time without truncation. - */ -struct timespec64 current_time(struct inode *inode) -{ - struct timespec64 now; - - ktime_get_coarse_real_ts64(&now); - return timestamp_truncate(now, inode); -} -EXPORT_SYMBOL(current_time); - /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * - * Set the inode->i_ctime to the current value for the inode. Returns - * the current value that was assigned to i_ctime. + * Set the inode's ctime to the current value for the inode. Returns the + * current value that was assigned. If this is not a multigrain inode, then we + * set it to the later of the coarse time and floor value. + * + * If it is multigrain, then we first see if the coarse-grained timestamp is + * distinct from what is already there. If so, then use that. Otherwise, get a + * fine-grained timestamp. + * + * After that, try to swap the new value into i_ctime_nsec. Accept the + * resulting ctime, regardless of the outcome of the swap. If it has + * already been replaced, then that timestamp is later than the earlier + * unacceptable one, and is thus acceptable. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { - struct timespec64 now = current_time(inode); + struct timespec64 now; + u32 cns, cur; - inode_set_ctime_to_ts(inode, now); + ktime_get_coarse_real_ts64_mg(&now); + now = timestamp_truncate(now, inode); + + /* Just return that if this is not a multigrain fs */ + if (!is_mgtime(inode)) { + inode_set_ctime_to_ts(inode, now); + goto out; + } + + /* + * A fine-grained time is only needed if someone has queried + * for timestamps, and the current coarse grained time isn't + * later than what's already there. + */ + cns = smp_load_acquire(&inode->i_ctime_nsec); + if (cns & I_CTIME_QUERIED) { + struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec, + .tv_nsec = cns & ~I_CTIME_QUERIED }; + + if (timespec64_compare(&now, &ctime) <= 0) { + ktime_get_real_ts64_mg(&now); + now = timestamp_truncate(now, inode); + } + } + + /* No need to cmpxchg if it's exactly the same */ + if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) + goto out; + cur = cns; +retry: + /* Try to swap the nsec value into place. */ + if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) { + /* If swap occurred, then we're (mostly) done */ + inode->i_ctime_sec = now.tv_sec; + } else { + /* + * Was the change due to someone marking the old ctime QUERIED? + * If so then retry the swap. This can only happen once since + * the only way to clear I_CTIME_QUERIED is to stamp the inode + * with a new ctime. + */ + if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) { + cns = cur; + goto retry; + } + /* Otherwise, keep the existing ctime */ + now.tv_sec = inode->i_ctime_sec; + now.tv_nsec = cur & ~I_CTIME_QUERIED; + } +out: return now; } EXPORT_SYMBOL(inode_set_ctime_current); diff --git a/fs/stat.c b/fs/stat.c index 89ce1be56310..dd480bf51a2a 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -26,6 +26,39 @@ #include "internal.h" #include "mount.h" +/** + * fill_mg_cmtime - Fill in the mtime and ctime and flag ctime as QUERIED + * @stat: where to store the resulting values + * @request_mask: STATX_* values requested + * @inode: inode from which to grab the c/mtime + * + * Given @inode, grab the ctime and mtime out if it and store the result + * in @stat. When fetching the value, flag it as QUERIED (if not already) + * so the next write will record a distinct timestamp. + * + * NB: The QUERIED flag is tracked in the ctime, but we set it there even + * if only the mtime was requested, as that ensures that the next mtime + * change will be distinct. + */ +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode) +{ + atomic_t *pcn = (atomic_t *)&inode->i_ctime_nsec; + + /* If neither time was requested, then don't report them */ + if (!(request_mask & (STATX_CTIME|STATX_MTIME))) { + stat->result_mask &= ~(STATX_CTIME|STATX_MTIME); + return; + } + + stat->mtime = inode_get_mtime(inode); + stat->ctime.tv_sec = inode->i_ctime_sec; + stat->ctime.tv_nsec = (u32)atomic_read(pcn); + if (!(stat->ctime.tv_nsec & I_CTIME_QUERIED)) + stat->ctime.tv_nsec = ((u32)atomic_fetch_or(I_CTIME_QUERIED, pcn)); + stat->ctime.tv_nsec &= ~I_CTIME_QUERIED; +} +EXPORT_SYMBOL(fill_mg_cmtime); + /** * generic_fillattr - Fill in the basic attributes from the inode struct * @idmap: idmap of the mount the inode was found from @@ -58,8 +91,14 @@ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode_get_atime(inode); - stat->mtime = inode_get_mtime(inode); - stat->ctime = inode_get_ctime(inode); + + if (is_mgtime(inode)) { + fill_mg_cmtime(stat, request_mask, inode); + } else { + stat->ctime = inode_get_ctime(inode); + stat->mtime = inode_get_mtime(inode); + } + stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; diff --git a/include/linux/fs.h b/include/linux/fs.h index 6ca11e241a24..eff688e75f2f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1613,6 +1613,17 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode, return inode_set_mtime_to_ts(inode, ts); } +/* + * Multigrain timestamps + * + * Conditionally use fine-grained ctime and mtime timestamps when there + * are users actively observing them via getattr. The primary use-case + * for this is NFS clients that use the ctime to distinguish between + * different states of the file, and that are often fooled by multiple + * operations that occur in the same coarse-grained timer tick. + */ +#define I_CTIME_QUERIED ((u32)BIT(31)) + static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; @@ -1620,7 +1631,7 @@ static inline time64_t inode_get_ctime_sec(const struct inode *inode) static inline long inode_get_ctime_nsec(const struct inode *inode) { - return inode->i_ctime_nsec; + return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) @@ -1631,13 +1642,7 @@ static inline struct timespec64 inode_get_ctime(const struct inode *inode) return ts; } -static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, - struct timespec64 ts) -{ - inode->i_ctime_sec = ts.tv_sec; - inode->i_ctime_nsec = ts.tv_nsec; - return ts; -} +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode @@ -2500,6 +2505,7 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ +#define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2523,6 +2529,17 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) +/** + * is_mgtime: is this inode using multigrain timestamps + * @inode: inode to test for multigrain timestamps + * + * Return true if the inode uses multigrain timestamps, false otherwise. + */ +static inline bool is_mgtime(const struct inode *inode) +{ + return inode->i_sb->s_type->fs_flags & FS_MGTIME; +} + extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -3262,6 +3279,7 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, From b82f92d5dd1a365ab1e13518c8bf799f6fec4518 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:19 -0400 Subject: [PATCH 02/13] fs: have setattr_copy handle multigrain timestamps appropriately The setattr codepath is still using coarse-grained timestamps, even on multigrain filesystems. To fix this, fetch the timestamp for ctime updates later, at the point where the assignment occurs in setattr_copy. On a multigrain inode, ignore the ia_ctime in the attrs, and always update the ctime to the current clock value. Update the atime and mtime with the same value (if needed) unless they are being set to other specific values, a'la utimes(). Do not do this universally however, as some filesystems (e.g. most networked fs) want to do an explicit update elsewhere before updating the local inode. Reviewed-by: Darrick J. Wong Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-4-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/attr.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 46 insertions(+), 6 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index c04d19b58f12..0309c2bd8afa 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -271,6 +271,42 @@ out_big: } EXPORT_SYMBOL(inode_newsize_ok); +/** + * setattr_copy_mgtime - update timestamps for mgtime inodes + * @inode: inode timestamps to be updated + * @attr: attrs for the update + * + * With multigrain timestamps, take more care to prevent races when + * updating the ctime. Always update the ctime to the very latest using + * the standard mechanism, and use that to populate the atime and mtime + * appropriately (unless those are being set to specific values). + */ +static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr) +{ + unsigned int ia_valid = attr->ia_valid; + struct timespec64 now; + + /* + * If the ctime isn't being updated then nothing else should be + * either. + */ + if (!(ia_valid & ATTR_CTIME)) { + WARN_ON_ONCE(ia_valid & (ATTR_ATIME|ATTR_MTIME)); + return; + } + + now = inode_set_ctime_current(inode); + if (ia_valid & ATTR_ATIME_SET) + inode_set_atime_to_ts(inode, attr->ia_atime); + else if (ia_valid & ATTR_ATIME) + inode_set_atime_to_ts(inode, now); + + if (ia_valid & ATTR_MTIME_SET) + inode_set_mtime_to_ts(inode, attr->ia_mtime); + else if (ia_valid & ATTR_MTIME) + inode_set_mtime_to_ts(inode, now); +} + /** * setattr_copy - copy simple metadata updates into the generic inode * @idmap: idmap of the mount the inode was found from @@ -303,12 +339,6 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); - if (ia_valid & ATTR_ATIME) - inode_set_atime_to_ts(inode, attr->ia_atime); - if (ia_valid & ATTR_MTIME) - inode_set_mtime_to_ts(inode, attr->ia_mtime); - if (ia_valid & ATTR_CTIME) - inode_set_ctime_to_ts(inode, attr->ia_ctime); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_or_capable(idmap, inode, @@ -316,6 +346,16 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, mode &= ~S_ISGID; inode->i_mode = mode; } + + if (is_mgtime(inode)) + return setattr_copy_mgtime(inode, attr); + + if (ia_valid & ATTR_ATIME) + inode_set_atime_to_ts(inode, attr->ia_atime); + if (ia_valid & ATTR_MTIME) + inode_set_mtime_to_ts(inode, attr->ia_mtime); + if (ia_valid & ATTR_CTIME) + inode_set_ctime_to_ts(inode, attr->ia_ctime); } EXPORT_SYMBOL(setattr_copy); From ee3283c608dfa21251b0821d7bb198c7ae3189f6 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:16 -0400 Subject: [PATCH 03/13] timekeeping: Add interfaces for handling timestamps with a floor value Multigrain timestamps allow the kernel to use fine-grained timestamps when an inode's attributes is being actively observed via ->getattr(). With this support, it's possible for a file to get a fine-grained timestamp, and another modified after it to get a coarse-grained stamp that is earlier than the fine-grained time. If this happens then the files can appear to have been modified in reverse order, which breaks VFS ordering guarantees [1]. To prevent this, maintain a floor value for multigrain timestamps. Whenever a fine-grained timestamp is handed out, record it, and when later coarse-grained stamps are handed out, ensure they are not earlier than that value. If the coarse-grained timestamp is earlier than the fine-grained floor, return the floor value instead. Add a static singleton atomic64_t into timekeeper.c that is used to keep track of the latest fine-grained time ever handed out. This is tracked as a monotonic ktime_t value to ensure that it isn't affected by clock jumps. Because it is updated at different times than the rest of the timekeeper object, the floor value is managed independently of the timekeeper via a cmpxchg() operation, and sits on its own cacheline. Add two new public interfaces: - ktime_get_coarse_real_ts64_mg() fills a timespec64 with the later of the coarse-grained clock and the floor time - ktime_get_real_ts64_mg() gets the fine-grained clock value, and tries to swap it into the floor. A timespec64 is filled with the result. The floor value is global and updated via a single try_cmpxchg(). If that fails then the operation raced with a concurrent update. Any concurrent update must be later than the existing floor value, so any racing tasks can accept any resulting floor value without retrying. [1]: POSIX requires that files be stamped with realtime clock values, and makes no provision for dealing with backward clock jumps. If a backward realtime clock jump occurs, then files can appear to have been modified in reverse order. Signed-off-by: Jeff Layton Signed-off-by: Thomas Gleixner Tested-by: Randy Dunlap # documentation bits Acked-by: John Stultz Link: https://lore.kernel.org/all/20241002-mgtime-v10-1-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- include/linux/timekeeping.h | 4 ++ kernel/time/timekeeping.c | 104 ++++++++++++++++++++++++++++++++++++ 2 files changed, 108 insertions(+) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fc12a9ba2c88..7aa85246c183 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -45,6 +45,10 @@ extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +/* Multigrain timestamp interfaces */ +extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); +extern void ktime_get_real_ts64_mg(struct timespec64 *ts); + void getboottime64(struct timespec64 *ts); /* diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 7e6f409bf311..441792c907fa 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -114,6 +114,23 @@ static struct tk_fast tk_fast_raw ____cacheline_aligned = { .base[1] = FAST_TK_INIT, }; +/* + * Multigrain timestamps require tracking the latest fine-grained timestamp + * that has been issued, and never returning a coarse-grained timestamp that is + * earlier than that value. + * + * mg_floor represents the latest fine-grained time that has been handed out as + * a file timestamp on the system. This is tracked as a monotonic ktime_t, and + * converted to a realtime clock value on an as-needed basis. + * + * Maintaining mg_floor ensures the multigrain interfaces never issue a + * timestamp earlier than one that has been previously issued. + * + * The exception to this rule is when there is a backward realtime clock jump. If + * such an event occurs, a timestamp can appear to be earlier than a previous one. + */ +static __cacheline_aligned_in_smp atomic64_t mg_floor; + static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { @@ -2394,6 +2411,93 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts) } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); +/** + * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor + * @ts: timespec64 to be filled + * + * Fetch the global mg_floor value, convert it to realtime and compare it + * to the current coarse-grained time. Fill @ts with whichever is + * latest. Note that this is a filesystem-specific interface and should be + * avoided outside of that context. + */ +void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + u64 floor = atomic64_read(&mg_floor); + ktime_t f_real, offset, coarse; + unsigned int seq; + + do { + seq = read_seqcount_begin(&tk_core.seq); + *ts = tk_xtime(tk); + offset = tk_core.timekeeper.offs_real; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + coarse = timespec64_to_ktime(*ts); + f_real = ktime_add(floor, offset); + if (ktime_after(f_real, coarse)) + *ts = ktime_to_timespec64(f_real); +} + +/** + * ktime_get_real_ts64_mg - attempt to update floor value and return result + * @ts: pointer to the timespec to be set + * + * Get a monotonic fine-grained time value and attempt to swap it into + * mg_floor. If that succeeds then accept the new floor value. If it fails + * then another task raced in during the interim time and updated the + * floor. Since any update to the floor must be later than the previous + * floor, either outcome is acceptable. + * + * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), + * and determining that the resulting coarse-grained timestamp did not effect + * a change in ctime. Any more recent floor value would effect a change to + * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. + * + * @ts will be filled with the latest floor value, regardless of the outcome of + * the cmpxchg. Note that this is a filesystem specific interface and should be + * avoided outside of that context. + */ +void ktime_get_real_ts64_mg(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + ktime_t old = atomic64_read(&mg_floor); + ktime_t offset, mono; + unsigned int seq; + u64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + ts->tv_sec = tk->xtime_sec; + mono = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); + offset = tk_core.timekeeper.offs_real; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + mono = ktime_add_ns(mono, nsecs); + + /* + * Attempt to update the floor with the new time value. As any + * update must be later then the existing floor, and would effect + * a change to ctime from the perspective of the current task, + * accept the resulting floor value regardless of the outcome of + * the swap. + */ + if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsecs); + } else { + /* + * Another task changed mg_floor since "old" was fetched. + * "old" has been updated with the latest value of "mg_floor". + * That value is newer than the previous floor value, which + * is enough to effect a change to ctime. Accept it. + */ + *ts = ktime_to_timespec64(ktime_add(old, offset)); + } +} + void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; From 2a15385742c689a271345dcbb4c28b9c568bc7ce Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:17 -0400 Subject: [PATCH 04/13] timekeeping: Add percpu counter for tracking floor swap events The mgtime_floor value is a global variable for tracking the latest fine-grained timestamp handed out. Because it's a global, track the number of times that a new floor value is assigned. Add a new percpu counter to the timekeeping code to track the number of floor swap events that have occurred. A later patch will add a debugfs file to display this counter alongside other stats involving multigrain timestamps. Signed-off-by: Jeff Layton Signed-off-by: Thomas Gleixner Tested-by: Randy Dunlap # documentation bits Link: https://lore.kernel.org/all/20241002-mgtime-v10-2-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- include/linux/timekeeping.h | 1 + kernel/time/timekeeping.c | 1 + kernel/time/timekeeping_debug.c | 13 +++++++++++++ kernel/time/timekeeping_internal.h | 15 +++++++++++++++ 4 files changed, 30 insertions(+) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7aa85246c183..84a035e86ac8 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -48,6 +48,7 @@ extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); +extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 441792c907fa..962b2a31f015 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2487,6 +2487,7 @@ void ktime_get_real_ts64_mg(struct timespec64 *ts) if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); + timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index b73e8850e58d..badeb222eab9 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -17,6 +17,9 @@ #define NUM_BINS 32 +/* Incremented every time mg_floor is updated */ +DEFINE_PER_CPU(unsigned long, timekeeping_mg_floor_swaps); + static unsigned int sleep_time_bin[NUM_BINS] = {0}; static int tk_debug_sleep_time_show(struct seq_file *s, void *data) @@ -53,3 +56,13 @@ void tk_debug_account_sleep_time(const struct timespec64 *t) (s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC); } +unsigned long timekeeping_get_mg_floor_swaps(void) +{ + unsigned long sum = 0; + int cpu; + + for_each_possible_cpu(cpu) + sum += data_race(per_cpu(timekeeping_mg_floor_swaps, cpu)); + + return sum; +} diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 4ca2787d1642..0bbae825bc02 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -10,9 +10,24 @@ * timekeeping debug functions */ #ifdef CONFIG_DEBUG_FS + +DECLARE_PER_CPU(unsigned long, timekeeping_mg_floor_swaps); + +static inline void timekeeping_inc_mg_floor_swaps(void) +{ + this_cpu_inc(timekeeping_mg_floor_swaps); +} + extern void tk_debug_account_sleep_time(const struct timespec64 *t); + #else + #define tk_debug_account_sleep_time(x) + +static inline void timekeeping_inc_mg_floor_swaps(void) +{ +} + #endif #ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE From 7f2c86cba3c584c7227cddaabdf0ab54c8151e60 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:20 -0400 Subject: [PATCH 05/13] fs: handle delegated timestamps in setattr_copy_mgtime An update to the inode ctime typically requires the latest clock value possible. The exception to this rule is when there is a nfsd write delegation and the server is proxying timestamps from the client. When nfsd gets a CB_GETATTR response, update the timestamp value in the inode to the values that the client is tracking. The client doesn't send a ctime value (since that's always determined by the exported filesystem), but it can send a mtime value. In the case where it does, update the ctime to a value commensurate with that instead of the current time. If ATTR_DELEG is set, then use ia_ctime value instead of setting the timestamp to the current time. With the addition of delegated timestamps, the server may receive a request to update only the atime, which doesn't involve a ctime update. Trust the ATTR_CTIME flag in the update and only update the ctime when it's set. Tested-by: Randy Dunlap # documentation bits Reviewed-by: Jan Kara Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-5-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/attr.c | 29 +++++++++++------- fs/inode.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 2 ++ 3 files changed, 94 insertions(+), 10 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index 0309c2bd8afa..9caf63d20d03 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -286,16 +286,21 @@ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr) unsigned int ia_valid = attr->ia_valid; struct timespec64 now; - /* - * If the ctime isn't being updated then nothing else should be - * either. - */ - if (!(ia_valid & ATTR_CTIME)) { - WARN_ON_ONCE(ia_valid & (ATTR_ATIME|ATTR_MTIME)); - return; + if (ia_valid & ATTR_CTIME) { + /* + * In the case of an update for a write delegation, we must respect + * the value in ia_ctime and not use the current time. + */ + if (ia_valid & ATTR_DELEG) + now = inode_set_ctime_deleg(inode, attr->ia_ctime); + else + now = inode_set_ctime_current(inode); + } else { + /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */ + WARN_ON_ONCE(ia_valid & ATTR_MTIME); + now = current_time(inode); } - now = inode_set_ctime_current(inode); if (ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); else if (ia_valid & ATTR_ATIME) @@ -354,8 +359,12 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, attr->ia_mtime); - if (ia_valid & ATTR_CTIME) - inode_set_ctime_to_ts(inode, attr->ia_ctime); + if (ia_valid & ATTR_CTIME) { + if (ia_valid & ATTR_DELEG) + inode_set_ctime_deleg(inode, attr->ia_ctime); + else + inode_set_ctime_to_ts(inode, attr->ia_ctime); + } } EXPORT_SYMBOL(setattr_copy); diff --git a/fs/inode.c b/fs/inode.c index 53f56f6e1ff2..7d1ede60e549 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2717,6 +2717,79 @@ out: } EXPORT_SYMBOL(inode_set_ctime_current); +/** + * inode_set_ctime_deleg - try to update the ctime on a delegated inode + * @inode: inode to update + * @update: timespec64 to set the ctime + * + * Attempt to atomically update the ctime on behalf of a delegation holder. + * + * The nfs server can call back the holder of a delegation to get updated + * inode attributes, including the mtime. When updating the mtime, update + * the ctime to a value at least equal to that. + * + * This can race with concurrent updates to the inode, in which + * case the update is skipped. + * + * Note that this works even when multigrain timestamps are not enabled, + * so it is used in either case. + */ +struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update) +{ + struct timespec64 now, cur_ts; + u32 cur, old; + + /* pairs with try_cmpxchg below */ + cur = smp_load_acquire(&inode->i_ctime_nsec); + cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; + cur_ts.tv_sec = inode->i_ctime_sec; + + /* If the update is older than the existing value, skip it. */ + if (timespec64_compare(&update, &cur_ts) <= 0) + return cur_ts; + + ktime_get_coarse_real_ts64_mg(&now); + + /* Clamp the update to "now" if it's in the future */ + if (timespec64_compare(&update, &now) > 0) + update = now; + + update = timestamp_truncate(update, inode); + + /* No need to update if the values are already the same */ + if (timespec64_equal(&update, &cur_ts)) + return cur_ts; + + /* + * Try to swap the nsec value into place. If it fails, that means + * it raced with an update due to a write or similar activity. That + * stamp takes precedence, so just skip the update. + */ +retry: + old = cur; + if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) { + inode->i_ctime_sec = update.tv_sec; + mgtime_counter_inc(mg_ctime_swaps); + return update; + } + + /* + * Was the change due to another task marking the old ctime QUERIED? + * + * If so, then retry the swap. This can only happen once since + * the only way to clear I_CTIME_QUERIED is to stamp the inode + * with a new ctime. + */ + if (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED))) + goto retry; + + /* Otherwise, it was a new timestamp. */ + cur_ts.tv_sec = inode->i_ctime_sec; + cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; + return cur_ts; +} +EXPORT_SYMBOL(inode_set_ctime_deleg); + /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @idmap: idmap of the mount @inode was found from diff --git a/include/linux/fs.h b/include/linux/fs.h index eff688e75f2f..ea7ed437d2b1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1544,6 +1544,8 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); +struct timespec64 inode_set_ctime_deleg(struct inode *inode, + struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { From c86e3c47187ad7fa17f8533a4142453991684b46 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:21 -0400 Subject: [PATCH 06/13] fs: tracepoints around multigrain timestamp events Add some tracepoints around various multigrain timestamp events. Reviewed-by: Josef Bacik Reviewed-by: Darrick J. Wong Reviewed-by: Jan Kara Reviewed-by: Steven Rostedt (Google) Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-6-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/inode.c | 9 ++- fs/stat.c | 3 + include/trace/events/timestamp.h | 124 +++++++++++++++++++++++++++++++ 3 files changed, 135 insertions(+), 1 deletion(-) create mode 100644 include/trace/events/timestamp.h diff --git a/fs/inode.c b/fs/inode.c index 7d1ede60e549..f7a25c511d6b 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -22,6 +22,9 @@ #include #include #include +#define CREATE_TRACE_POINTS +#include + #include "internal.h" /* @@ -2603,6 +2606,7 @@ EXPORT_SYMBOL(inode_nohighmem); struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { + trace_inode_set_ctime_to_ts(inode, &ts); set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec); inode->i_ctime_sec = ts.tv_sec; inode->i_ctime_nsec = ts.tv_nsec; @@ -2689,14 +2693,17 @@ struct timespec64 inode_set_ctime_current(struct inode *inode) } /* No need to cmpxchg if it's exactly the same */ - if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) + if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { + trace_ctime_xchg_skip(inode, &now); goto out; + } cur = cns; retry: /* Try to swap the nsec value into place. */ if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) { /* If swap occurred, then we're (mostly) done */ inode->i_ctime_sec = now.tv_sec; + trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); } else { /* * Was the change due to someone marking the old ctime QUERIED? diff --git a/fs/stat.c b/fs/stat.c index dd480bf51a2a..6eb6c39d0037 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -23,6 +23,8 @@ #include #include +#include + #include "internal.h" #include "mount.h" @@ -56,6 +58,7 @@ void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode) if (!(stat->ctime.tv_nsec & I_CTIME_QUERIED)) stat->ctime.tv_nsec = ((u32)atomic_fetch_or(I_CTIME_QUERIED, pcn)); stat->ctime.tv_nsec &= ~I_CTIME_QUERIED; + trace_fill_mg_cmtime(inode, &stat->ctime, &stat->mtime); } EXPORT_SYMBOL(fill_mg_cmtime); diff --git a/include/trace/events/timestamp.h b/include/trace/events/timestamp.h new file mode 100644 index 000000000000..c9e5ec930054 --- /dev/null +++ b/include/trace/events/timestamp.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM timestamp + +#if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TIMESTAMP_H + +#include +#include + +#define CTIME_QUERIED_FLAGS \ + { I_CTIME_QUERIED, "Q" } + +DECLARE_EVENT_CLASS(ctime, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + + TP_ARGS(inode, ctime), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(time64_t, ctime_s) + __field(u32, ctime_ns) + __field(u32, gen) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->ctime_s = ctime->tv_sec; + __entry->ctime_ns = ctime->tv_nsec; + ), + + TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->ctime_s, __entry->ctime_ns + ) +); + +DEFINE_EVENT(ctime, inode_set_ctime_to_ts, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + TP_ARGS(inode, ctime)); + +DEFINE_EVENT(ctime, ctime_xchg_skip, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + TP_ARGS(inode, ctime)); + +TRACE_EVENT(ctime_ns_xchg, + TP_PROTO(struct inode *inode, + u32 old, + u32 new, + u32 cur), + + TP_ARGS(inode, old, new, cur), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(u32, gen) + __field(u32, old) + __field(u32, new) + __field(u32, cur) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->old = old; + __entry->new = new; + __entry->cur = cur; + ), + + TP_printk("ino=%d:%d:%ld:%u old=%u:%s new=%u cur=%u:%s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->old & ~I_CTIME_QUERIED, + __print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS), + __entry->new, + __entry->cur & ~I_CTIME_QUERIED, + __print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS) + ) +); + +TRACE_EVENT(fill_mg_cmtime, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime, + struct timespec64 *mtime), + + TP_ARGS(inode, ctime, mtime), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(time64_t, ctime_s) + __field(time64_t, mtime_s) + __field(u32, ctime_ns) + __field(u32, mtime_ns) + __field(u32, gen) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->ctime_s = ctime->tv_sec; + __entry->mtime_s = mtime->tv_sec; + __entry->ctime_ns = ctime->tv_nsec; + __entry->mtime_ns = mtime->tv_nsec; + ), + + TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u mtime=%lld.%u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->ctime_s, __entry->ctime_ns, + __entry->mtime_s, __entry->mtime_ns + ) +); +#endif /* _TRACE_TIMESTAMP_H */ + +/* This part must be outside protection */ +#include From 73a47cf40f84312cb6ea2b3583825d671930b24f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:22 -0400 Subject: [PATCH 07/13] fs: add percpu counters for significant multigrain timestamp events New percpu counters for counting various stats around multigrain timestamp events, and a new debugfs file for displaying them when CONFIG_DEBUG_FS is enabled: - number of attempted ctime updates - number of successful i_ctime_nsec swaps - number of fine-grained timestamp fetches - number of floor value swap events Reviewed-by: Josef Bacik Reviewed-by: Darrick J. Wong Reviewed-by: Jan Kara Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-7-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/inode.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/fs/inode.c b/fs/inode.c index f7a25c511d6b..6d501c7308ae 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -21,6 +21,8 @@ #include #include #include +#include +#include #include #define CREATE_TRACE_POINTS #include @@ -101,6 +103,70 @@ long get_nr_dirty_inodes(void) return nr_dirty > 0 ? nr_dirty : 0; } +#ifdef CONFIG_DEBUG_FS +static DEFINE_PER_CPU(long, mg_ctime_updates); +static DEFINE_PER_CPU(long, mg_fine_stamps); +static DEFINE_PER_CPU(long, mg_ctime_swaps); + +static unsigned long get_mg_ctime_updates(void) +{ + unsigned long sum = 0; + int i; + + for_each_possible_cpu(i) + sum += data_race(per_cpu(mg_ctime_updates, i)); + return sum; +} + +static unsigned long get_mg_fine_stamps(void) +{ + unsigned long sum = 0; + int i; + + for_each_possible_cpu(i) + sum += data_race(per_cpu(mg_fine_stamps, i)); + return sum; +} + +static unsigned long get_mg_ctime_swaps(void) +{ + unsigned long sum = 0; + int i; + + for_each_possible_cpu(i) + sum += data_race(per_cpu(mg_ctime_swaps, i)); + return sum; +} + +#define mgtime_counter_inc(__var) this_cpu_inc(__var) + +static int mgts_show(struct seq_file *s, void *p) +{ + unsigned long ctime_updates = get_mg_ctime_updates(); + unsigned long ctime_swaps = get_mg_ctime_swaps(); + unsigned long fine_stamps = get_mg_fine_stamps(); + unsigned long floor_swaps = timekeeping_get_mg_floor_swaps(); + + seq_printf(s, "%lu %lu %lu %lu\n", + ctime_updates, ctime_swaps, fine_stamps, floor_swaps); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(mgts); + +static int __init mg_debugfs_init(void) +{ + debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops); + return 0; +} +late_initcall(mg_debugfs_init); + +#else /* ! CONFIG_DEBUG_FS */ + +#define mgtime_counter_inc(__var) do { } while (0) + +#endif /* CONFIG_DEBUG_FS */ + /* * Handle nr_inode sysctl */ @@ -2689,8 +2755,10 @@ struct timespec64 inode_set_ctime_current(struct inode *inode) if (timespec64_compare(&now, &ctime) <= 0) { ktime_get_real_ts64_mg(&now); now = timestamp_truncate(now, inode); + mgtime_counter_inc(mg_fine_stamps); } } + mgtime_counter_inc(mg_ctime_updates); /* No need to cmpxchg if it's exactly the same */ if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { @@ -2704,6 +2772,7 @@ retry: /* If swap occurred, then we're (mostly) done */ inode->i_ctime_sec = now.tv_sec; trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); + mgtime_counter_inc(mg_ctime_swaps); } else { /* * Was the change due to someone marking the old ctime QUERIED? From e3fad0376d80f91b45e0db3f3634f15e1dd22768 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:23 -0400 Subject: [PATCH 08/13] Documentation: add a new file documenting multigrain timestamps Add a high-level document that describes how multigrain timestamps work, rationale for them, and some info about implementation and tradeoffs. Reviewed-by: Josef Bacik Reviewed-by: Darrick J. Wong Reviewed-by: Randy Dunlap Reviewed-by: Jan Kara Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-8-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- Documentation/filesystems/index.rst | 1 + Documentation/filesystems/multigrain-ts.rst | 125 ++++++++++++++++++++ 2 files changed, 126 insertions(+) create mode 100644 Documentation/filesystems/multigrain-ts.rst diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index e8e496d23e1d..44e9e77ffe0d 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -29,6 +29,7 @@ algorithms work. fiemap files locks + multigrain-ts mount_api quota seq_file diff --git a/Documentation/filesystems/multigrain-ts.rst b/Documentation/filesystems/multigrain-ts.rst new file mode 100644 index 000000000000..c779e47284e8 --- /dev/null +++ b/Documentation/filesystems/multigrain-ts.rst @@ -0,0 +1,125 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +Multigrain Timestamps +===================== + +Introduction +============ +Historically, the kernel has always used coarse time values to stamp inodes. +This value is updated every jiffy, so any change that happens within that jiffy +will end up with the same timestamp. + +When the kernel goes to stamp an inode (due to a read or write), it first gets +the current time and then compares it to the existing timestamp(s) to see +whether anything will change. If nothing changed, then it can avoid updating +the inode's metadata. + +Coarse timestamps are therefore good from a performance standpoint, since they +reduce the need for metadata updates, but bad from the standpoint of +determining whether anything has changed, since a lot of things can happen in a +jiffy. + +They are particularly troublesome with NFSv3, where unchanging timestamps can +make it difficult to tell whether to invalidate caches. NFSv4 provides a +dedicated change attribute that should always show a visible change, but not +all filesystems implement this properly, causing the NFS server to substitute +the ctime in many cases. + +Multigrain timestamps aim to remedy this by selectively using fine-grained +timestamps when a file has had its timestamps queried recently, and the current +coarse-grained time does not cause a change. + +Inode Timestamps +================ +There are currently 3 timestamps in the inode that are updated to the current +wallclock time on different activity: + +ctime: + The inode change time. This is stamped with the current time whenever + the inode's metadata is changed. Note that this value is not settable + from userland. + +mtime: + The inode modification time. This is stamped with the current time + any time a file's contents change. + +atime: + The inode access time. This is stamped whenever an inode's contents are + read. Widely considered to be a terrible mistake. Usually avoided with + options like noatime or relatime. + +Updating the mtime always implies a change to the ctime, but updating the +atime due to a read request does not. + +Multigrain timestamps are only tracked for the ctime and the mtime. atimes are +not affected and always use the coarse-grained value (subject to the floor). + +Inode Timestamp Ordering +======================== + +In addition to just providing info about changes to individual files, file +timestamps also serve an important purpose in applications like "make". These +programs measure timestamps in order to determine whether source files might be +newer than cached objects. + +Userland applications like make can only determine ordering based on +operational boundaries. For a syscall those are the syscall entry and exit +points. For io_uring or nfsd operations, that's the request submission and +response. In the case of concurrent operations, userland can make no +determination about the order in which things will occur. + +For instance, if a single thread modifies one file, and then another file in +sequence, the second file must show an equal or later mtime than the first. The +same is true if two threads are issuing similar operations that do not overlap +in time. + +If however, two threads have racing syscalls that overlap in time, then there +is no such guarantee, and the second file may appear to have been modified +before, after or at the same time as the first, regardless of which one was +submitted first. + +Note that the above assumes that the system doesn't experience a backward jump +of the realtime clock. If that occurs at an inopportune time, then timestamps +can appear to go backward, even on a properly functioning system. + +Multigrain Timestamp Implementation +=================================== +Multigrain timestamps are aimed at ensuring that changes to a single file are +always recognizable, without violating the ordering guarantees when multiple +different files are modified. This affects the mtime and the ctime, but the +atime will always use coarse-grained timestamps. + +It uses an unused bit in the i_ctime_nsec field to indicate whether the mtime +or ctime has been queried. If either or both have, then the kernel takes +special care to ensure the next timestamp update will display a visible change. +This ensures tight cache coherency for use-cases like NFS, without sacrificing +the benefits of reduced metadata updates when files aren't being watched. + +The Ctime Floor Value +===================== +It's not sufficient to simply use fine or coarse-grained timestamps based on +whether the mtime or ctime has been queried. A file could get a fine grained +timestamp, and then a second file modified later could get a coarse-grained one +that appears earlier than the first, which would break the kernel's timestamp +ordering guarantees. + +To mitigate this problem, maintain a global floor value that ensures that +this can't happen. The two files in the above example may appear to have been +modified at the same time in such a case, but they will never show the reverse +order. To avoid problems with realtime clock jumps, the floor is managed as a +monotonic ktime_t, and the values are converted to realtime clock values as +needed. + +Implementation Notes +==================== +Multigrain timestamps are intended for use by local filesystems that get +ctime values from the local clock. This is in contrast to network filesystems +and the like that just mirror timestamp values from a server. + +For most filesystems, it's sufficient to just set the FS_MGTIME flag in the +fstype->fs_flags in order to opt-in, providing the ctime is only ever set via +inode_set_ctime_current(). If the filesystem has a ->getattr routine that +doesn't call generic_fillattr, then it should call fill_mg_cmtime() to +fill those values. For setattr, it should use setattr_copy() to update the +timestamps, or otherwise mimic its behavior. From 1cf7e834a6fb84de9d1e038d6cf4c5bd0d202ffa Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:24 -0400 Subject: [PATCH 09/13] xfs: switch to multigrain timestamps Enable multigrain timestamps, which should ensure that there is an apparent change to the timestamp whenever it has been written after being actively observed via getattr. Also, anytime the mtime changes, the ctime must also change, and those are now the only two options for xfs_trans_ichgtime. Have that function unconditionally bump the ctime, and ASSERT that XFS_ICHGTIME_CHG is always set. Finally, stop setting STATX_CHANGE_COOKIE in getattr, since the ctime should give us better semantics now. Reviewed-by: Josef Bacik Reviewed-by: Darrick J. Wong Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-9-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/xfs/libxfs/xfs_trans_inode.c | 6 +++--- fs/xfs/xfs_iops.c | 10 +++------- fs/xfs/xfs_super.c | 2 +- 3 files changed, 7 insertions(+), 11 deletions(-) diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 3c40f37e82c7..c962ad64b0c1 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -62,12 +62,12 @@ xfs_trans_ichgtime( ASSERT(tp); xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); - tv = current_time(inode); + /* If the mtime changes, then ctime must also change */ + ASSERT(flags & XFS_ICHGTIME_CHG); + tv = inode_set_ctime_current(inode); if (flags & XFS_ICHGTIME_MOD) inode_set_mtime_to_ts(inode, tv); - if (flags & XFS_ICHGTIME_CHG) - inode_set_ctime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_ACCESS) inode_set_atime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CREATE) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 1cdc8034f54d..a1c4a350a6db 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -597,8 +597,9 @@ xfs_vn_getattr( stat->gid = vfsgid_into_kgid(vfsgid); stat->ino = ip->i_ino; stat->atime = inode_get_atime(inode); - stat->mtime = inode_get_mtime(inode); - stat->ctime = inode_get_ctime(inode); + + fill_mg_cmtime(stat, request_mask, inode); + stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks); if (xfs_has_v3inodes(mp)) { @@ -608,11 +609,6 @@ xfs_vn_getattr( } } - if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { - stat->change_cookie = inode_query_iversion(inode); - stat->result_mask |= STATX_CHANGE_COOKIE; - } - /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 27e9f749c4c7..210481b03fdb 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -2052,7 +2052,7 @@ static struct file_system_type xfs_fs_type = { .init_fs_context = xfs_init_fs_context, .parameters = xfs_fs_parameters, .kill_sb = xfs_kill_sb, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, }; MODULE_ALIAS_FS("xfs"); From d0382c698f9c9c80483987e1b4661b5d97a805d4 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:25 -0400 Subject: [PATCH 10/13] ext4: switch to multigrain timestamps Enable multigrain timestamps, which should ensure that there is an apparent change to the timestamp whenever it has been written after being actively observed via getattr. For ext4, we only need to enable the FS_MGTIME flag. Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-10-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e72145c4ae5a..a125d9435b8a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -7298,7 +7298,7 @@ static struct file_system_type ext4_fs_type = { .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, }; MODULE_ALIAS_FS("ext4"); From e2e801d6e62507c297ec2c102e24d09c90618e8b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:26 -0400 Subject: [PATCH 11/13] btrfs: convert to multigrain timestamps Enable multigrain timestamps, which should ensure that there is an apparent change to the timestamp whenever it has been written after being actively observed via getattr. Beyond enabling the FS_MGTIME flag, this patch eliminates update_time_for_write, which goes to great pains to avoid in-memory stores. Just have it overwrite the timestamps unconditionally. Note that this also drops the IS_I_VERSION check and unconditionally bumps the change attribute, since SB_I_VERSION is always set on btrfs. Reviewed-by: Josef Bacik Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-11-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/btrfs/file.c | 25 ++++--------------------- fs/btrfs/super.c | 3 ++- 2 files changed, 6 insertions(+), 22 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 2aeb8116549c..1656ad7498b8 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1120,26 +1120,6 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode) btrfs_drew_write_unlock(&inode->root->snapshot_lock); } -static void update_time_for_write(struct inode *inode) -{ - struct timespec64 now, ts; - - if (IS_NOCMTIME(inode)) - return; - - now = current_time(inode); - ts = inode_get_mtime(inode); - if (!timespec64_equal(&ts, &now)) - inode_set_mtime_to_ts(inode, now); - - ts = inode_get_ctime(inode); - if (!timespec64_equal(&ts, &now)) - inode_set_ctime_to_ts(inode, now); - - if (IS_I_VERSION(inode)) - inode_inc_iversion(inode); -} - int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, size_t count) { struct file *file = iocb->ki_filp; @@ -1170,7 +1150,10 @@ int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, size_t count) * need to start yet another transaction to update the inode as we will * update the inode when we finish writing whatever data we write. */ - update_time_for_write(inode); + if (!IS_NOCMTIME(inode)) { + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + inode_inc_iversion(inode); + } start_pos = round_down(pos, fs_info->sectorsize); oldsize = i_size_read(inode); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 98fa0f382480..d423acfe11d0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2198,7 +2198,8 @@ static struct file_system_type btrfs_fs_type = { .init_fs_context = btrfs_init_fs_context, .parameters = btrfs_fs_parameters, .kill_sb = btrfs_kill_super, - .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP, + .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | + FS_ALLOW_IDMAP | FS_MGTIME, }; MODULE_ALIAS_FS("btrfs"); From 234d8895e3ad8ddb93d687d665086bd303901d87 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:27 -0400 Subject: [PATCH 12/13] tmpfs: add support for multigrain timestamps Enable multigrain timestamps, which should ensure that there is an apparent change to the timestamp whenever it has been written after being actively observed via getattr. tmpfs only requires the FS_MGTIME flag. Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-12-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- mm/shmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/shmem.c b/mm/shmem.c index 5a77acf6ac6a..5f17eaaa32e2 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4804,7 +4804,7 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, - .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP, + .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP | FS_MGTIME, }; void __init shmem_init(void) From 9fed2c0f2f0771b990d068ef0a2b32e770ae6d48 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 13 Nov 2024 09:17:51 -0500 Subject: [PATCH 13/13] fs: reduce pointer chasing in is_mgtime() test The is_mgtime test checks whether the FS_MGTIME flag is set in the fstype. To get there from the inode though, we have to dereference 3 pointers. Add a new IOP_MGTIME flag, and have inode_init_always() set that flag when the fstype flag is set. Then, make is_mgtime test for IOP_MGTIME instead. Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241113-mgtime-v1-1-84e256980e11@kernel.org Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- fs/inode.c | 2 ++ include/linux/fs.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/inode.c b/fs/inode.c index 3b66082afe22..bb0117e679de 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -241,6 +241,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; + if (sb->s_type->fs_flags & FS_MGTIME) + inode->i_opflags |= IOP_MGTIME; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); diff --git a/include/linux/fs.h b/include/linux/fs.h index b1a3bd07711b..a9c6c8cbda50 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -623,6 +623,7 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 +#define IOP_MGTIME 0x0020 /* * Keep mostly read-only and often accessed (especially for @@ -2581,7 +2582,7 @@ struct file_system_type { */ static inline bool is_mgtime(const struct inode *inode) { - return inode->i_sb->s_type->fs_flags & FS_MGTIME; + return inode->i_opflags & IOP_MGTIME; } extern struct dentry *mount_bdev(struct file_system_type *fs_type,