diff options
| -rw-r--r-- | Documentation/filesystems/index.rst | 1 | ||||
| -rw-r--r-- | Documentation/filesystems/multigrain-ts.rst | 125 | ||||
| -rw-r--r-- | fs/attr.c | 61 | ||||
| -rw-r--r-- | fs/btrfs/file.c | 25 | ||||
| -rw-r--r-- | fs/btrfs/super.c | 3 | ||||
| -rw-r--r-- | fs/ext4/super.c | 2 | ||||
| -rw-r--r-- | fs/inode.c | 284 | ||||
| -rw-r--r-- | fs/stat.c | 46 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_trans_inode.c | 6 | ||||
| -rw-r--r-- | fs/xfs/xfs_iops.c | 10 | ||||
| -rw-r--r-- | fs/xfs/xfs_super.c | 2 | ||||
| -rw-r--r-- | include/linux/fs.h | 37 | ||||
| -rw-r--r-- | include/linux/timekeeping.h | 5 | ||||
| -rw-r--r-- | include/trace/events/timestamp.h | 124 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 105 | ||||
| -rw-r--r-- | kernel/time/timekeeping_debug.c | 13 | ||||
| -rw-r--r-- | kernel/time/timekeeping_internal.h | 15 | ||||
| -rw-r--r-- | mm/shmem.c | 2 |
18 files changed, 793 insertions, 73 deletions
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. diff --git a/fs/attr.c b/fs/attr.c index c04d19b58f12..9caf63d20d03 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -272,6 +272,47 @@ 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 (ia_valid & ATTR_CTIME) { + /* + * In the case of an update for a write delegation, we must respect + * the value in ia_ctime and not use the current time. + */ + if (ia_valid & ATTR_DELEG) + now = inode_set_ctime_deleg(inode, attr->ia_ctime); + else + now = inode_set_ctime_current(inode); + } else { + /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */ + WARN_ON_ONCE(ia_valid & ATTR_MTIME); + now = current_time(inode); + } + + if (ia_valid & ATTR_ATIME_SET) + inode_set_atime_to_ts(inode, attr->ia_atime); + else if (ia_valid & ATTR_ATIME) + inode_set_atime_to_ts(inode, now); + + if (ia_valid & ATTR_MTIME_SET) + inode_set_mtime_to_ts(inode, attr->ia_mtime); + else if (ia_valid & ATTR_MTIME) + inode_set_mtime_to_ts(inode, now); +} + +/** * setattr_copy - copy simple metadata updates into the generic inode * @idmap: idmap of the mount the inode was found from * @inode: the inode to be updated @@ -303,12 +344,6 @@ 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 +351,20 @@ 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) { + 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/btrfs/file.c b/fs/btrfs/file.c index 4fb521d91b06..e5384ceb8acf 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 c64d07134122..881d62d81b9f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2191,7 +2191,8 @@ 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"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 16a4ce704460..b77acba4a719 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -7329,7 +7329,7 @@ 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"); diff --git a/fs/inode.c b/fs/inode.c index 8dabb224f941..70a2f8c717e0 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -21,7 +21,12 @@ #include <linux/list_lru.h> #include <linux/iversion.h> #include <linux/rw_hint.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> #include <trace/events/writeback.h> +#define CREATE_TRACE_POINTS +#include <trace/events/timestamp.h> + #include "internal.h" /* @@ -98,6 +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 */ @@ -174,6 +243,8 @@ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp 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); @@ -2211,19 +2282,58 @@ 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)) @@ -2600,6 +2710,16 @@ void inode_nohighmem(struct inode *inode) } 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; + return ts; +} +EXPORT_SYMBOL(inode_set_ctime_to_ts); + /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec @@ -2632,39 +2752,159 @@ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) EXPORT_SYMBOL(timestamp_truncate); /** - * current_time - Return FS time - * @inode: inode. + * inode_set_ctime_current - set the ctime to current_time + * @inode: inode * - * Return the current time truncated to the time granularity supported by - * the fs. + * 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. * - * Note that inode and inode->sb cannot be NULL. - * Otherwise, the function warns and returns time without truncation. + * 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 current_time(struct inode *inode) +struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now; + u32 cns, cur; - ktime_get_coarse_real_ts64(&now); - return timestamp_truncate(now, inode); + 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); + 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) { + 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); + mgtime_counter_inc(mg_ctime_swaps); + } 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(current_time); +EXPORT_SYMBOL(inode_set_ctime_current); /** - * inode_set_ctime_current - set the ctime to current_time - * @inode: inode + * inode_set_ctime_deleg - try to update the ctime on a delegated inode + * @inode: inode to update + * @update: timespec64 to set the ctime * - * Set the inode->i_ctime to the current value for the inode. Returns - * the current value that was assigned to i_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_current(struct inode *inode) +struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update) { - struct timespec64 now = current_time(inode); + struct timespec64 now, cur_ts; + u32 cur, old; - inode_set_ctime_to_ts(inode, now); - return now; + /* 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_current); +EXPORT_SYMBOL(inode_set_ctime_deleg); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged diff --git a/fs/stat.c b/fs/stat.c index 41e598376d7e..5ef213343834 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -23,10 +23,46 @@ #include <linux/uaccess.h> #include <asm/unistd.h> +#include <trace/events/timestamp.h> + #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; + trace_fill_mg_cmtime(inode, &stat->ctime, &stat->mtime); +} +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 * @request_mask: statx request_mask @@ -58,8 +94,14 @@ 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/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 ee79cf161312..b5d0c5c157e7 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 fbb3a1594c0d..fda75db739b1 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -2063,7 +2063,7 @@ 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"); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3559446279c1..d32c6f6298b1 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 @@ -1584,6 +1585,8 @@ 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) { @@ -1653,6 +1656,17 @@ 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; @@ -1660,7 +1674,7 @@ 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) @@ -1671,13 +1685,7 @@ 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 @@ -2542,6 +2550,7 @@ 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; @@ -2565,6 +2574,17 @@ 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_opflags & IOP_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)); @@ -3326,6 +3346,7 @@ 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, diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fc12a9ba2c88..84a035e86ac8 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -45,6 +45,11 @@ extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +/* Multigrain timestamp interfaces */ +extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); +extern void ktime_get_real_ts64_mg(struct timespec64 *ts); +extern unsigned long timekeeping_get_mg_floor_swaps(void); + void getboottime64(struct timespec64 *ts); /* 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 <linux/tracepoint.h> +#include <linux/fs.h> + +#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 <trace/define_trace.h> diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 7e6f409bf311..962b2a31f015 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 +2411,94 @@ 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); + timekeeping_inc_mg_floor_swaps(); + } else { + /* + * Another task changed mg_floor since "old" was fetched. + * "old" has been updated with the latest value of "mg_floor". + * That value is newer than the previous floor value, which + * is enough to effect a change to ctime. Accept it. + */ + *ts = ktime_to_timespec64(ktime_add(old, offset)); + } +} + void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; 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 diff --git a/mm/shmem.c b/mm/shmem.c index 568bb290bdce..87c9e38c0763 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4943,7 +4943,7 @@ 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) |