[v5,2/8] ext4: fix i_version handling in ext4

Commit Message

Jeffrey Layton Sept. 8, 2022, 5:24 p.m. UTC

ext4 currently updates the i_version counter when the atime is updated
during a read. This is less than ideal as it can cause unnecessary cache
invalidations with NFSv4 and unnecessary remeasurements for IMA.

The increment in ext4_mark_iloc_dirty is also problematic since it can
corrupt the i_version counter for ea_inodes. We aren't bumping the file
times in ext4_mark_iloc_dirty, so changing the i_version there seems
wrong, and is the cause of both problems.

Remove that callsite and add increments to the setattr, setxattr and
ioctl codepaths, at the same times that we update the ctime. The
i_version bump that already happens during timestamp updates should take
care of the rest.

In ext4_move_extents, increment the i_version on both inodes, and also
add in missing ctime updates.

Cc: Lukas Czerner <[e-mail]>
Reviewed-by: Jan Kara <[e-mail]>
Reviewed-by: Christian Brauner (Microsoft) <[e-mail]>
Signed-off-by: Jeff Layton <[e-mail]>
---
 fs/ext4/inode.c       | 15 +++++----------
 fs/ext4/ioctl.c       |  8 ++++++++
 fs/ext4/move_extent.c |  8 ++++++++
 fs/ext4/xattr.c       |  2 ++
 4 files changed, 23 insertions(+), 10 deletions(-)

Comments

Theodore Ts'o Sept. 30, 2022, 1:22 a.m. UTC | #1

On Thu, Sep 08, 2022 at 01:24:42PM -0400, Jeff Layton wrote:
> ext4 currently updates the i_version counter when the atime is updated
> during a read. This is less than ideal as it can cause unnecessary cache
> invalidations with NFSv4 and unnecessary remeasurements for IMA.
> 
> The increment in ext4_mark_iloc_dirty is also problematic since it can
> corrupt the i_version counter for ea_inodes. We aren't bumping the file
> times in ext4_mark_iloc_dirty, so changing the i_version there seems
> wrong, and is the cause of both problems.
> 
> Remove that callsite and add increments to the setattr, setxattr and
> ioctl codepaths, at the same times that we update the ctime. The
> i_version bump that already happens during timestamp updates should take
> care of the rest.
> 
> In ext4_move_extents, increment the i_version on both inodes, and also
> add in missing ctime updates.
> 
> Cc: Lukas Czerner <[e-mail]>
> Reviewed-by: Jan Kara <[e-mail]>
> Reviewed-by: Christian Brauner (Microsoft) <[e-mail]>
> Signed-off-by: Jeff Layton <[e-mail]>

Thanks, I've applied just this patch from this patch series.  I made
some minor adjustments since we've already enabled the i_version
counter unconditionally via another patch series from Lukas.

			    	    	  - Ted

Patch

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2a220be34caa..aa37bce4c541 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5342,6 +5342,7 @@  int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	int error, rc = 0;
 	int orphan = 0;
 	const unsigned int ia_valid = attr->ia_valid;
+	bool inc_ivers = IS_I_VERSION(inode);
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
@@ -5425,8 +5426,8 @@  int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 			return -EINVAL;
 		}
 
-		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
-			inode_inc_iversion(inode);
+		if (attr->ia_size == inode->i_size)
+			inc_ivers = false;
 
 		if (shrink) {
 			if (ext4_should_order_data(inode)) {
@@ -5528,6 +5529,8 @@  int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	}
 
 	if (!error) {
+		if (inc_ivers)
+			inode_inc_iversion(inode);
 		setattr_copy(mnt_userns, inode, attr);
 		mark_inode_dirty(inode);
 	}
@@ -5731,14 +5734,6 @@  int ext4_mark_iloc_dirty(handle_t *handle,
 	}
 	ext4_fc_track_inode(handle, inode);
 
-	/*
-	 * ea_inodes are using i_version for storing reference count, don't
-	 * mess with it
-	 */
-	if (IS_I_VERSION(inode) &&
-	    !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
-		inode_inc_iversion(inode);
-
 	/* the do_update_inode consumes one bh->b_count */
 	get_bh(iloc->bh);
 
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 3cf3ec4b1c21..60e77ae9342d 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -452,6 +452,8 @@  static long swap_inode_boot_loader(struct super_block *sb,
 	swap_inode_data(inode, inode_bl);
 
 	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
+	if (IS_I_VERSION(inode))
+		inode_inc_iversion(inode);
 
 	inode->i_generation = prandom_u32();
 	inode_bl->i_generation = prandom_u32();
@@ -665,6 +667,8 @@  static int ext4_ioctl_setflags(struct inode *inode,
 	ext4_set_inode_flags(inode, false);
 
 	inode->i_ctime = current_time(inode);
+	if (IS_I_VERSION(inode))
+		inode_inc_iversion(inode);
 
 	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 flags_err:
@@ -775,6 +779,8 @@  static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
 
 	EXT4_I(inode)->i_projid = kprojid;
 	inode->i_ctime = current_time(inode);
+	if (IS_I_VERSION(inode))
+		inode_inc_iversion(inode);
 out_dirty:
 	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	if (!err)
@@ -1257,6 +1263,8 @@  static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
 			inode->i_ctime = current_time(inode);
+			if (IS_I_VERSION(inode))
+				inode_inc_iversion(inode);
 			inode->i_generation = generation;
 			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		}
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 701f1d6a217f..d73ab3153218 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -6,6 +6,7 @@ 
  */
 
 #include <linux/fs.h>
+#include <linux/iversion.h>
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
@@ -683,6 +684,13 @@  ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 			break;
 		o_start += cur_len;
 		d_start += cur_len;
+
+		orig_inode->i_ctime = current_time(orig_inode);
+		donor_inode->i_ctime = current_time(donor_inode);
+		if (IS_I_VERSION(orig_inode))
+			inode_inc_iversion(orig_inode);
+		if (IS_I_VERSION(donor_inode))
+			inode_inc_iversion(donor_inode);
 	}
 	*moved_len = o_start - orig_blk;
 	if (*moved_len > len)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 533216e80fa2..e975442e4ab2 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2412,6 +2412,8 @@  ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	if (!error) {
 		ext4_xattr_update_super_block(handle, inode->i_sb);
 		inode->i_ctime = current_time(inode);
+		if (IS_I_VERSION(inode))
+			inode_inc_iversion(inode);
 		if (!value)
 			no_expand = 0;
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);