1 files changed, 177 insertions, 59 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 8fefb69e1f84..35fd688168c5 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -16,7 +16,6 @@
 #include <linux/fsnotify.h>
 #include <linux/mount.h>
 #include <linux/posix_acl.h>
-#include <linux/prefetch.h>
 #include <linux/buffer_head.h> /* for inode_has_buffers */
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
@@ -752,16 +751,11 @@ EXPORT_SYMBOL_GPL(evict_inodes);
 /**
  * invalidate_inodes	- attempt to free all inodes on a superblock
  * @sb:		superblock to operate on
- * @kill_dirty: flag to guide handling of dirty inodes
  *
- * Attempts to free all inodes for a given superblock.  If there were any
- * busy inodes return a non-zero value, else zero.
- * If @kill_dirty is set, discard dirty inodes too, otherwise treat
- * them as busy.
+ * Attempts to free all inodes (including dirty inodes) for a given superblock.
  */
-int invalidate_inodes(struct super_block *sb, bool kill_dirty)
+void invalidate_inodes(struct super_block *sb)
 {
-	int busy = 0;
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
@@ -773,14 +767,8 @@ again:
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
-		if (inode->i_state & I_DIRTY_ALL && !kill_dirty) {
-			spin_unlock(&inode->i_lock);
-			busy = 1;
-			continue;
-		}
 		if (atomic_read(&inode->i_count)) {
 			spin_unlock(&inode->i_lock);
-			busy = 1;
 			continue;
 		}
 
@@ -798,8 +786,6 @@ again:
 	spin_unlock(&sb->s_inode_list_lock);
 
 	dispose_list(&dispose);
-
-	return busy;
 }
 
 /*
@@ -1041,8 +1027,6 @@ struct inode *new_inode(struct super_block *sb)
 {
 	struct inode *inode;
 
-	spin_lock_prefetch(&sb->s_inode_list_lock);
-
 	inode = new_inode_pseudo(sb);
 	if (inode)
 		inode_sb_list_add(inode);
@@ -1853,6 +1837,7 @@ EXPORT_SYMBOL(bmap);
 static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 			     struct timespec64 now)
 {
+	struct timespec64 ctime;
 
 	if (!(mnt->mnt_flags & MNT_RELATIME))
 		return 1;
@@ -1864,7 +1849,8 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 	/*
 	 * Is ctime younger than or equal to atime? If yes, update atime:
 	 */
-	if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0)
+	ctime = inode_get_ctime(inode);
+	if (timespec64_compare(&ctime, &inode->i_atime) >= 0)
 		return 1;
 
 	/*
@@ -1879,29 +1865,76 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 	return 0;
 }
 
-int generic_update_time(struct inode *inode, struct timespec64 *time, int flags)
+/**
+ * inode_update_timestamps - update the timestamps on the inode
+ * @inode: inode to be updated
+ * @flags: S_* flags that needed to be updated
+ *
+ * The update_time function is called when an inode's timestamps need to be
+ * updated for a read or write operation. This function handles updating the
+ * actual timestamps. It's up to the caller to ensure that the inode is marked
+ * dirty appropriately.
+ *
+ * In the case where any of S_MTIME, S_CTIME, or S_VERSION need to be updated,
+ * attempt to update all three of them. S_ATIME updates can be handled
+ * independently of the rest.
+ *
+ * Returns a set of S_* flags indicating which values changed.
+ */
+int inode_update_timestamps(struct inode *inode, int flags)
 {
-	int dirty_flags = 0;
+	int updated = 0;
+	struct timespec64 now;
 
-	if (flags & (S_ATIME | S_CTIME | S_MTIME)) {
-		if (flags & S_ATIME)
-			inode->i_atime = *time;
-		if (flags & S_CTIME)
-			inode->i_ctime = *time;
-		if (flags & S_MTIME)
-			inode->i_mtime = *time;
-
-		if (inode->i_sb->s_flags & SB_LAZYTIME)
-			dirty_flags |= I_DIRTY_TIME;
-		else
-			dirty_flags |= I_DIRTY_SYNC;
+	if (flags & (S_MTIME|S_CTIME|S_VERSION)) {
+		struct timespec64 ctime = inode_get_ctime(inode);
+
+		now = inode_set_ctime_current(inode);
+		if (!timespec64_equal(&now, &ctime))
+			updated |= S_CTIME;
+		if (!timespec64_equal(&now, &inode->i_mtime)) {
+			inode->i_mtime = now;
+			updated |= S_MTIME;
+		}
+		if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated))
+			updated |= S_VERSION;
+	} else {
+		now = current_time(inode);
 	}
 
-	if ((flags & S_VERSION) && inode_maybe_inc_iversion(inode, false))
-		dirty_flags |= I_DIRTY_SYNC;
+	if (flags & S_ATIME) {
+		if (!timespec64_equal(&now, &inode->i_atime)) {
+			inode->i_atime = now;
+			updated |= S_ATIME;
+		}
+	}
+	return updated;
+}
+EXPORT_SYMBOL(inode_update_timestamps);
 
+/**
+ * generic_update_time - update the timestamps on the inode
+ * @inode: inode to be updated
+ * @flags: S_* flags that needed to be updated
+ *
+ * The update_time function is called when an inode's timestamps need to be
+ * updated for a read or write operation. In the case where any of S_MTIME, S_CTIME,
+ * or S_VERSION need to be updated we attempt to update all three of them. S_ATIME
+ * updates can be handled done independently of the rest.
+ *
+ * Returns a S_* mask indicating which fields were updated.
+ */
+int generic_update_time(struct inode *inode, int flags)
+{
+	int updated = inode_update_timestamps(inode, flags);
+	int dirty_flags = 0;
+
+	if (updated & (S_ATIME|S_MTIME|S_CTIME))
+		dirty_flags = inode->i_sb->s_flags & SB_LAZYTIME ? I_DIRTY_TIME : I_DIRTY_SYNC;
+	if (updated & S_VERSION)
+		dirty_flags |= I_DIRTY_SYNC;
 	__mark_inode_dirty(inode, dirty_flags);
-	return 0;
+	return updated;
 }
 EXPORT_SYMBOL(generic_update_time);
 
@@ -1909,11 +1942,12 @@ EXPORT_SYMBOL(generic_update_time);
  * This does the actual work of updating an inodes time or version.  Must have
  * had called mnt_want_write() before calling this.
  */
-int inode_update_time(struct inode *inode, struct timespec64 *time, int flags)
+int inode_update_time(struct inode *inode, int flags)
 {
 	if (inode->i_op->update_time)
-		return inode->i_op->update_time(inode, time, flags);
-	return generic_update_time(inode, time, flags);
+		return inode->i_op->update_time(inode, flags);
+	generic_update_time(inode, flags);
+	return 0;
 }
 EXPORT_SYMBOL(inode_update_time);
 
@@ -1965,7 +1999,6 @@ void touch_atime(const struct path *path)
 {
 	struct vfsmount *mnt = path->mnt;
 	struct inode *inode = d_inode(path->dentry);
-	struct timespec64 now;
 
 	if (!atime_needs_update(path, inode))
 		return;
@@ -1984,8 +2017,7 @@ void touch_atime(const struct path *path)
 	 * We may also fail on filesystems that have the ability to make parts
 	 * of the fs read only, e.g. subvolumes in Btrfs.
 	 */
-	now = current_time(inode);
-	inode_update_time(inode, &now, S_ATIME);
+	inode_update_time(inode, S_ATIME);
 	__mnt_drop_write(mnt);
 skip_update:
 	sb_end_write(inode->i_sb);
@@ -2070,18 +2102,63 @@ int file_remove_privs(struct file *file)
 }
 EXPORT_SYMBOL(file_remove_privs);
 
-static int inode_needs_update_time(struct inode *inode, struct timespec64 *now)
+/**
+ * current_mgtime - 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_mgtime(struct inode *inode)
+{
+	struct timespec64 now, ctime;
+	atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec;
+	long nsec = atomic_long_read(pnsec);
+
+	if (nsec & I_CTIME_QUERIED) {
+		ktime_get_real_ts64(&now);
+		return timestamp_truncate(now, inode);
+	}
+
+	ktime_get_coarse_real_ts64(&now);
+	now = timestamp_truncate(now, inode);
+
+	/*
+	 * If we've recently fetched a fine-grained timestamp
+	 * then the coarse-grained one may still be earlier than the
+	 * existing ctime. Just keep the existing value if so.
+	 */
+	ctime = inode_get_ctime(inode);
+	if (timespec64_compare(&ctime, &now) > 0)
+		now = ctime;
+
+	return now;
+}
+EXPORT_SYMBOL(current_mgtime);
+
+static struct timespec64 current_ctime(struct inode *inode)
+{
+	if (is_mgtime(inode))
+		return current_mgtime(inode);
+	return current_time(inode);
+}
+
+static int inode_needs_update_time(struct inode *inode)
 {
 	int sync_it = 0;
+	struct timespec64 now = current_ctime(inode);
+	struct timespec64 ctime;
 
 	/* First try to exhaust all avenues to not sync */
 	if (IS_NOCMTIME(inode))
 		return 0;
 
-	if (!timespec64_equal(&inode->i_mtime, now))
+	if (!timespec64_equal(&inode->i_mtime, &now))
 		sync_it = S_MTIME;
 
-	if (!timespec64_equal(&inode->i_ctime, now))
+	ctime = inode_get_ctime(inode);
+	if (!timespec64_equal(&ctime, &now))
 		sync_it |= S_CTIME;
 
 	if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
@@ -2090,15 +2167,14 @@ static int inode_needs_update_time(struct inode *inode, struct timespec64 *now)
 	return sync_it;
 }
 
-static int __file_update_time(struct file *file, struct timespec64 *now,
-			int sync_mode)
+static int __file_update_time(struct file *file, int sync_mode)
 {
 	int ret = 0;
 	struct inode *inode = file_inode(file);
 
 	/* try to update time settings */
 	if (!__mnt_want_write_file(file)) {
-		ret = inode_update_time(inode, now, sync_mode);
+		ret = inode_update_time(inode, sync_mode);
 		__mnt_drop_write_file(file);
 	}
 
@@ -2123,13 +2199,12 @@ int file_update_time(struct file *file)
 {
 	int ret;
 	struct inode *inode = file_inode(file);
-	struct timespec64 now = current_time(inode);
 
-	ret = inode_needs_update_time(inode, &now);
+	ret = inode_needs_update_time(inode);
 	if (ret <= 0)
 		return ret;
 
-	return __file_update_time(file, &now, ret);
+	return __file_update_time(file, ret);
 }
 EXPORT_SYMBOL(file_update_time);
 
@@ -2152,7 +2227,6 @@ static int file_modified_flags(struct file *file, int flags)
 {
 	int ret;
 	struct inode *inode = file_inode(file);
-	struct timespec64 now = current_time(inode);
 
 	/*
 	 * Clear the security bits if the process is not being run by root.
@@ -2165,13 +2239,13 @@ static int file_modified_flags(struct file *file, int flags)
 	if (unlikely(file->f_mode & FMODE_NOCMTIME))
 		return 0;
 
-	ret = inode_needs_update_time(inode, &now);
+	ret = inode_needs_update_time(inode);
 	if (ret <= 0)
 		return ret;
 	if (flags & IOCB_NOWAIT)
 		return -EAGAIN;
 
-	return __file_update_time(file, &now, ret);
+	return __file_update_time(file, ret);
 }
 
 /**
@@ -2491,15 +2565,59 @@ 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);
 
-	if (unlikely(!inode->i_sb)) {
-		WARN(1, "current_time() called with uninitialized super_block in the inode");
+/**
+ * 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.
+ */
+struct timespec64 inode_set_ctime_current(struct inode *inode)
+{
+	struct timespec64 now;
+	struct timespec64 ctime;
+
+	ctime.tv_nsec = READ_ONCE(inode->__i_ctime.tv_nsec);
+	if (!(ctime.tv_nsec & I_CTIME_QUERIED)) {
+		now = current_time(inode);
+
+		/* Just copy it into place if it's not multigrain */
+		if (!is_mgtime(inode)) {
+			inode_set_ctime_to_ts(inode, now);
+			return now;
+		}
+
+		/*
+		 * If we've recently updated with a fine-grained timestamp,
+		 * then the coarse-grained one may still be earlier than the
+		 * existing ctime. Just keep the existing value if so.
+		 */
+		ctime.tv_sec = inode->__i_ctime.tv_sec;
+		if (timespec64_compare(&ctime, &now) > 0)
+			return ctime;
+
+		/*
+		 * Ctime updates are usually protected by the inode_lock, but
+		 * we can still race with someone setting the QUERIED flag.
+		 * Try to swap the new nsec value into place. If it's changed
+		 * in the interim, then just go with a fine-grained timestamp.
+		 */
+		if (cmpxchg(&inode->__i_ctime.tv_nsec, ctime.tv_nsec,
+			    now.tv_nsec) != ctime.tv_nsec)
+			goto fine_grained;
+		inode->__i_ctime.tv_sec = now.tv_sec;
 		return now;
 	}
-
-	return timestamp_truncate(now, inode);
+fine_grained:
+	ktime_get_real_ts64(&now);
+	inode_set_ctime_to_ts(inode, timestamp_truncate(now, inode));
+	return now;
 }
-EXPORT_SYMBOL(current_time);
+EXPORT_SYMBOL(inode_set_ctime_current);
 
 /**
  * in_group_or_capable - check whether caller is CAP_FSETID privileged