[PATCH 00/10] fs: multigrain timestamp redux

@@ -662,11 +662,10 @@ struct inode {
 	loff_t			i_size;
 	time64_t		i_atime_sec;
 	time64_t		i_mtime_sec;
-	time64_t		i_ctime_sec;
 	u32			i_atime_nsec;
 	u32			i_mtime_nsec;
-	u32			i_ctime_nsec;
-	u32			i_generation;
+	ktime_t			__i_ctime;
+	atomic64_t		i_version;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	u8			i_blkbits;

@@ -701,7 +700,6 @@ struct inode {
 		struct hlist_head	i_dentry;
 		struct rcu_head		i_rcu;
 	};
-	atomic64_t		i_version;
 	atomic64_t		i_sequence; /* see futex */
 	atomic_t		i_count;
 	atomic_t		i_dio_count;

@@ -724,6 +722,8 @@ struct inode {
 	};
 
 
+	u32			i_generation;
+
 #ifdef CONFIG_FSNOTIFY
 	__u32			i_fsnotify_mask; /* all events this inode cares about */
 	/* 32-bit hole reserved for expanding i_fsnotify_mask */

@@ -1608,29 +1608,25 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode,
 	return inode_set_mtime_to_ts(inode, ts);
 }
 
-static inline time64_t inode_get_ctime_sec(const struct inode *inode)
+static inline struct timespec64 inode_get_ctime(const struct inode *inode)
 {
-	return inode->i_ctime_sec;
+	return ktime_to_timespec64(inode->__i_ctime);
 }
 
-static inline long inode_get_ctime_nsec(const struct inode *inode)
+static inline time64_t inode_get_ctime_sec(const struct inode *inode)
 {
-	return inode->i_ctime_nsec;
+	return inode_get_ctime(inode).tv_sec;
 }
 
-static inline struct timespec64 inode_get_ctime(const struct inode *inode)
+static inline long inode_get_ctime_nsec(const struct inode *inode)
 {
-	struct timespec64 ts = { .tv_sec  = inode_get_ctime_sec(inode),
-				 .tv_nsec = inode_get_ctime_nsec(inode) };
-
-	return ts;
+	return inode_get_ctime(inode).tv_nsec;
 }
 
 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;
+	inode->__i_ctime = ktime_set(ts.tv_sec, ts.tv_nsec);
 	return ts;
 }
 

@@ -2501,6 +2501,31 @@ struct timespec64 current_time(struct inode *inode)
 }
 EXPORT_SYMBOL(current_time);
 
+/**
+ * inode_get_ctime - fetch the current ctime from the inode
+ * @inode: inode from which to fetch ctime
+ *
+ * Grab the current ctime tv_nsec field from the inode, mask off the
+ * I_CTIME_QUERIED flag and return it. This is mostly intended for use by
+ * internal consumers of the ctime that aren't concerned with ensuring a
+ * fine-grained update on the next change (e.g. when preparing to store
+ * the value in the backing store for later retrieval).
+ */
+struct timespec64 inode_get_ctime(const struct inode *inode)
+{
+	ktime_t ctime = inode->__i_ctime;
+
+	return ktime_to_timespec64(ctime);
+}
+EXPORT_SYMBOL(inode_get_ctime);
+
+struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts)
+{
+	inode->__i_ctime = ktime_set(ts.tv_sec, ts.tv_nsec);
+	return ts;
+}
+EXPORT_SYMBOL(inode_set_ctime_to_ts);
+
 /**
  * inode_set_ctime_current - set the ctime to current_time
  * @inode: inode

@@ -1608,10 +1608,8 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode,
 	return inode_set_mtime_to_ts(inode, ts);
 }
 
-static inline struct timespec64 inode_get_ctime(const struct inode *inode)
-{
-	return ktime_to_timespec64(inode->__i_ctime);
-}
+struct timespec64 inode_get_ctime(const struct inode *inode);
+struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts);
 
 static inline time64_t inode_get_ctime_sec(const struct inode *inode)
 {

@@ -1623,13 +1621,6 @@ static inline long inode_get_ctime_nsec(const struct inode *inode)
 	return inode_get_ctime(inode).tv_nsec;
 }
 
-static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode,
-						      struct timespec64 ts)
-{
-	inode->__i_ctime = ktime_set(ts.tv_sec, ts.tv_nsec);
-	return ts;
-}
-
 /**
  * inode_set_ctime - set the ctime in the inode
  * @inode: inode in which to set the ctime

@@ -22,6 +22,8 @@
 #include <linux/iversion.h>
 #include <linux/rw_hint.h>
 #include <trace/events/writeback.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/timestamp.h>
 #include "internal.h"
 
 /*

@@ -2096,6 +2098,7 @@ static int inode_needs_update_time(struct inode *inode)
 	if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
 		sync_it |= S_VERSION;
 
+	trace_inode_needs_update_time(inode, &now, &ts, sync_it);
 	return sync_it;
 }
 

@@ -2522,6 +2525,7 @@ EXPORT_SYMBOL(inode_get_ctime);
 struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts)
 {
 	inode->__i_ctime = ktime_set(ts.tv_sec, ts.tv_nsec);
+	trace_inode_set_ctime_to_ts(inode, &ts);
 	return ts;
 }
 EXPORT_SYMBOL(inode_set_ctime_to_ts);

@@ -0,0 +1,76 @@
+/* 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>
+
+TRACE_EVENT(inode_needs_update_time,
+	TP_PROTO(struct inode *inode,
+		 struct timespec64 *now,
+		 struct timespec64 *ctime,
+		 int sync_it),
+
+	TP_ARGS(inode, now, ctime, sync_it),
+
+	TP_STRUCT__entry(
+		__field(dev_t,			dev)
+		__field(ino_t,			ino)
+		__field(time64_t,		now_sec)
+		__field(time64_t,		ctime_sec)
+		__field(long,			now_nsec)
+		__field(long,			ctime_nsec)
+		__field(int,			sync_it)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->sync_it	= sync_it;
+		__entry->now_sec	= now->tv_sec;
+		__entry->ctime_sec	= ctime->tv_sec;
+		__entry->now_nsec	= now->tv_nsec;
+		__entry->ctime_nsec	= ctime->tv_nsec;
+		__entry->sync_it	= sync_it;
+	),
+
+	TP_printk("ino=%d:%d:%ld sync_it=%d now=%llu.%ld ctime=%llu.%lu",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino,
+		__entry->sync_it,
+		__entry->now_sec, __entry->now_nsec,
+		__entry->ctime_sec, __entry->ctime_nsec
+	)
+);
+
+TRACE_EVENT(inode_set_ctime_to_ts,
+	TP_PROTO(struct inode *inode,
+		 struct timespec64 *ts),
+
+	TP_ARGS(inode, ts),
+
+	TP_STRUCT__entry(
+		__field(dev_t,			dev)
+		__field(ino_t,			ino)
+		__field(time64_t,		ts_sec)
+		__field(long,			ts_nsec)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->ts_sec		= ts->tv_sec;
+		__entry->ts_nsec	= ts->tv_nsec;
+	),
+
+	TP_printk("ino=%d:%d:%ld ts=%llu.%lu",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino,
+		__entry->ts_sec, __entry->ts_nsec
+	)
+);
+#endif /* _TRACE_TIMESTAMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

@@ -62,6 +62,8 @@ static unsigned int i_hash_shift __ro_after_init;
 static struct hlist_head *inode_hashtable __ro_after_init;
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
+/* Don't send out a ctime lower than this (modulo backward clock jumps). */
+static __cacheline_aligned_in_smp ktime_t ctime_floor;
 /*
  * Empty aops. Can be used for the cases where the user does not
  * define any of the address_space operations.

@@ -2077,19 +2079,86 @@ int file_remove_privs(struct file *file)
 }
 EXPORT_SYMBOL(file_remove_privs);
 
+/*
+ * The coarse-grained clock ticks once per jiffy (every 2ms or so). If the
+ * current floor is >6ms in the future, assume that the clock has jumped
+ * backward.
+ */
+#define CTIME_FLOOR_MAX_NS	6000000
+
+/**
+ * coarse_ctime - return the current coarse-grained time
+ * @floor: current ctime_floor value
+ *
+ * Get the coarse-grained time, and then determine whether to
+ * return it or the current floor value. Returns the later of the
+ * floor and coarse grained time, unless the floor value is too
+ * far into the future. If that happens, assume the clock has jumped
+ * backward, and that the floor should be ignored.
+ */
+static ktime_t coarse_ctime(ktime_t floor)
+{
+	ktime_t now = ktime_get_coarse_real() & ~I_CTIME_QUERIED;
+
+	/* If coarse time is already newer, return that */
+	if (ktime_before(floor, now))
+		return now;
+
+	/* Ensure floor is not _too_ far in the future */
+	if (ktime_after(floor, now + CTIME_FLOOR_MAX_NS))
+		return now;
+
+	return floor;
+}
+
+/**
+ * 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.
+ */
+struct timespec64 current_time(struct inode *inode)
+{
+	ktime_t ctime, floor = smp_load_acquire(&ctime_floor);
+	ktime_t now = coarse_ctime(floor);
+	struct timespec64 now_ts = ktime_to_timespec64(now);
+
+	if (!is_mgtime(inode))
+		goto out;
+
+	/* If nothing has queried it, then coarse time is fine */
+	ctime = smp_load_acquire(&inode->__i_ctime);
+	if (ctime & I_CTIME_QUERIED) {
+		/*
+		 * If there is no apparent change, then
+		 * get a fine-grained timestamp.
+		 */
+		if ((now | I_CTIME_QUERIED) == ctime) {
+			ktime_get_real_ts64(&now_ts);
+			now_ts.tv_nsec &= ~I_CTIME_QUERIED;
+		}
+	}
+out:
+	return timestamp_truncate(now_ts, 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))

@@ -2485,25 +2554,6 @@ 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_get_ctime - fetch the current ctime from the inode
  * @inode: inode from which to fetch ctime

@@ -2518,12 +2568,18 @@ struct timespec64 inode_get_ctime(const struct inode *inode)
 {
 	ktime_t ctime = inode->__i_ctime;
 
+	if (is_mgtime(inode))
+		ctime &= ~I_CTIME_QUERIED;
 	return ktime_to_timespec64(ctime);
 }
 EXPORT_SYMBOL(inode_get_ctime);
 
 struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts)
 {
+	trace_inode_set_ctime_to_ts(inode, &ts);
+
+	if (is_mgtime(inode))
+		ts.tv_nsec &= ~I_CTIME_QUERIED;
 	inode->__i_ctime = ktime_set(ts.tv_sec, ts.tv_nsec);
 	trace_inode_set_ctime_to_ts(inode, &ts);
 	return ts;

@@ -2535,14 +2591,74 @@ EXPORT_SYMBOL(inode_set_ctime_to_ts);
  * @inode: inode
  *
  * Set the inode->i_ctime to the current value for the inode. Returns
- * the current value that was assigned to i_ctime.
+ * the current value that was assigned to i_ctime. If this is a not
+ * multigrain inode, then we just set it to whatever the coarse time is.
+ *
+ * If it is multigrain, then we first see if the coarse-grained
+ * timestamp is distinct from what we have. If so, then we'll just use
+ * that. If we have to get a fine-grained timestamp, then do so, and
+ * try to swap it into the floor. We accept the new floor value
+ * regardless of the outcome of the cmpxchg. After that, we try to
+ * swap the new value into __i_ctime. Again, we take the resulting
+ * ctime, regardless of the outcome of the swap.
  */
 struct timespec64 inode_set_ctime_current(struct inode *inode)
 {
-	struct timespec64 now = current_time(inode);
+	ktime_t ctime, now, cur, floor = smp_load_acquire(&ctime_floor);
+
+	now = coarse_ctime(floor);
 
-	inode_set_ctime_to_ts(inode, now);
-	return now;
+	/* Just return that if this is not a multigrain fs */
+	if (!is_mgtime(inode)) {
+		inode->__i_ctime = now;
+		goto out;
+	}
+
+	/*
+	 * We only need a fine-grained time if someone has queried it,
+	 * and the current coarse grained time isn't later than what's
+	 * already there.
+	 */
+	ctime = smp_load_acquire(&inode->__i_ctime);
+	if ((ctime & I_CTIME_QUERIED) && !ktime_after(now, ctime & ~I_CTIME_QUERIED)) {
+		ktime_t old;
+
+		/* Get a fine-grained time */
+		now = ktime_get_real() & ~I_CTIME_QUERIED;
+
+		/*
+		 * If the cmpxchg works, we take the new floor value. If
+		 * not, then that means that someone else changed it after we
+		 * fetched it but before we got here. That value is just
+		 * as good, so keep it.
+		 */
+		old = cmpxchg(&ctime_floor, floor, now);
+		trace_ctime_floor_update(inode, floor, now, old);
+		if (old != floor)
+			now = old;
+	}
+retry:
+	/* Try to swap the ctime into place. */
+	cur = cmpxchg(&inode->__i_ctime, ctime, now);
+	trace_ctime_inode_update(inode, ctime, now, cur);
+
+	/* If swap occurred, then we're done */
+	if (cur != ctime) {
+		/*
+		 * 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 (!(ctime & I_CTIME_QUERIED) && (ctime | I_CTIME_QUERIED) == cur) {
+			ctime = cur;
+			goto retry;
+		}
+		/* Otherwise, take the new ctime */
+		now = cur & ~I_CTIME_QUERIED;
+	}
+out:
+	return timestamp_truncate(ktime_to_timespec64(now), inode);
 }
 EXPORT_SYMBOL(inode_set_ctime_current);
 

@@ -22,10 +22,39 @@
 
 #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 so the next write
+ * will ensure a distinct timestamp.
+ */
+void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode)
+{
+	atomic_long_t *pc = (atomic_long_t *)&inode->__i_ctime;
+
+	/* 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.tv_sec = inode->i_mtime_sec;
+	stat->mtime.tv_nsec = inode->i_mtime_nsec;
+	stat->ctime = ktime_to_timespec64(atomic_long_fetch_or(I_CTIME_QUERIED, pc) &
+						~I_CTIME_QUERIED);
+	trace_fill_mg_cmtime(inode, atomic_long_read(pc));
+}
+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 +87,14 @@ 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;
 

@@ -1608,6 +1608,23 @@ 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.
+ *
+ * We use the least significant bit of the ktime_t to track the QUERIED
+ * flag. This means that filesystems with multigrain timestamps effectively
+ * have 2ns resolution for the ctime, even if they advertise 1ns s_time_gran.
+ */
+#define I_CTIME_QUERIED		(1LL)
+
+static inline bool is_mgtime(const struct inode *inode);
+
 struct timespec64 inode_get_ctime(const struct inode *inode);
 struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts);
 

@@ -2477,6 +2494,7 @@ 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;

@@ -2500,6 +2518,17 @@ 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));

@@ -3234,6 +3263,7 @@ 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);
 extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);

@@ -8,6 +8,78 @@
 #include <linux/tracepoint.h>
 #include <linux/fs.h>
 
+TRACE_EVENT(ctime_floor_update,
+	TP_PROTO(struct inode *inode,
+		 ktime_t old,
+		 ktime_t new,
+		 ktime_t cur),
+
+	TP_ARGS(inode, old, new, cur),
+
+	TP_STRUCT__entry(
+		__field(dev_t,				dev)
+		__field(ino_t,				ino)
+		__field(ktime_t,			old)
+		__field(ktime_t,			new)
+		__field(ktime_t,			cur)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->old		= old;
+		__entry->new		= new;
+		__entry->cur		= cur;
+	),
+
+	TP_printk("ino=%d:%d:%lu old=%llu.%lu new=%llu.%lu cur=%llu.%lu swp=%c",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino,
+		ktime_to_timespec64(__entry->old).tv_sec,
+		ktime_to_timespec64(__entry->old).tv_nsec,
+		ktime_to_timespec64(__entry->new).tv_sec,
+		ktime_to_timespec64(__entry->new).tv_nsec,
+		ktime_to_timespec64(__entry->cur).tv_sec,
+		ktime_to_timespec64(__entry->cur).tv_nsec,
+		(__entry->old == __entry->cur) ? 'Y' : 'N'
+	)
+);
+
+TRACE_EVENT(ctime_inode_update,
+	TP_PROTO(struct inode *inode,
+		 ktime_t old,
+		 ktime_t new,
+		 ktime_t cur),
+
+	TP_ARGS(inode, old, new, cur),
+
+	TP_STRUCT__entry(
+		__field(dev_t,				dev)
+		__field(ino_t,				ino)
+		__field(ktime_t,			old)
+		__field(ktime_t,			new)
+		__field(ktime_t,			cur)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->old		= old;
+		__entry->new		= new;
+		__entry->cur		= cur;
+	),
+
+	TP_printk("ino=%d:%d:%ld old=%llu.%ld new=%llu.%ld cur=%llu.%ld swp=%c",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino,
+		ktime_to_timespec64(__entry->old).tv_sec,
+		ktime_to_timespec64(__entry->old).tv_nsec,
+		ktime_to_timespec64(__entry->new).tv_sec,
+		ktime_to_timespec64(__entry->new).tv_nsec,
+		ktime_to_timespec64(__entry->cur).tv_sec,
+		ktime_to_timespec64(__entry->cur).tv_nsec,
+		(__entry->old == __entry->cur ? 'Y' : 'N')
+	)
+);
+
 TRACE_EVENT(inode_needs_update_time,
 	TP_PROTO(struct inode *inode,
 		 struct timespec64 *now,

@@ -70,6 +142,31 @@ TRACE_EVENT(inode_set_ctime_to_ts,
 		__entry->ts_sec, __entry->ts_nsec
 	)
 );
+
+TRACE_EVENT(fill_mg_cmtime,
+	TP_PROTO(struct inode *inode,
+		 ktime_t ctime),
+
+	TP_ARGS(inode, ctime),
+
+	TP_STRUCT__entry(
+		__field(dev_t,			dev)
+		__field(ino_t,			ino)
+		__field(ktime_t,		ctime)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->ctime		= ctime;
+	),
+
+	TP_printk("ino=%d:%d:%ld ctime=%llu.%lu",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino,
+		ktime_to_timespec64(__entry->ctime).tv_sec,
+		ktime_to_timespec64(__entry->ctime).tv_nsec
+	)
+);
 #endif /* _TRACE_TIMESTAMP_H */
 
 /* This part must be outside protection */

@@ -21,6 +21,8 @@
 #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>

@@ -64,6 +66,11 @@ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
 /* Don't send out a ctime lower than this (modulo backward clock jumps). */
 static __cacheline_aligned_in_smp ktime_t ctime_floor;
+
+/* Keep track of the number of fine vs. coarse timestamp fetches */
+static struct percpu_counter mg_fine_ts;
+static struct percpu_counter mg_coarse_ts;
+
 /*
  * Empty aops. Can be used for the cases where the user does not
  * define any of the address_space operations.

@@ -2636,6 +2643,9 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
 		trace_ctime_floor_update(inode, floor, now, old);
 		if (old != floor)
 			now = old;
+		percpu_counter_inc(&mg_fine_ts);
+	} else {
+		percpu_counter_inc(&mg_coarse_ts);
 	}
 retry:
 	/* Try to swap the ctime into place. */

@@ -2711,3 +2721,32 @@ umode_t mode_strip_sgid(struct mnt_idmap *idmap,
 	return mode & ~S_ISGID;
 }
 EXPORT_SYMBOL(mode_strip_sgid);
+
+static int mgts_show(struct seq_file *s, void *p)
+{
+	u64 fine = percpu_counter_sum(&mg_fine_ts);
+	u64 coarse = percpu_counter_sum(&mg_coarse_ts);
+
+	seq_printf(s, "%llu %llu\n", fine, coarse);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mgts);
+
+static int __init mg_debugfs_init(void)
+{
+	int ret = percpu_counter_init(&mg_fine_ts, 0, GFP_KERNEL);
+
+	if (ret)
+		return ret;
+
+	ret = percpu_counter_init(&mg_coarse_ts, 0, GFP_KERNEL);
+	if (ret) {
+		percpu_counter_destroy(&mg_fine_ts);
+		return ret;
+	}
+
+	debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops);
+	return 0;
+}
+late_initcall(mg_debugfs_init);

@@ -271,6 +271,42 @@ int inode_newsize_ok(const struct inode *inode, loff_t offset)
 }
 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, we need to 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 we're setting those 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);
 

@@ -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_CREATE)
 		ip->i_crtime = tv;
 }

@@ -590,10 +590,12 @@ 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)) {
 		if (request_mask & STATX_BTIME) {
 			stat->result_mask |= STATX_BTIME;