Merge tag 'iversion-v4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux

Pull inode->i_version rework from Jeff Layton:
 "This pile of patches is a rework of the inode->i_version field. We
  have traditionally incremented that field on every inode data or
  metadata change. Typically this increment needs to be logged on disk
  even when nothing else has changed, which is rather expensive.

  It turns out though that none of the consumers of that field actually
  require this behavior. The only real requirement for all of them is
  that it be different iff the inode has changed since the last time the
  field was checked.

  Given that, we can optimize away most of the i_version increments and
  avoid dirtying inode metadata when the only change is to the i_version
  and no one is querying it. Queries of the i_version field are rather
  rare, so we can help write performance under many common workloads.

  This patch series converts existing accesses of the i_version field to
  a new API, and then converts all of the in-kernel filesystems to use
  it. The last patch in the series then converts the backend
  implementation to a scheme that optimizes away a large portion of the
  metadata updates when no one is looking at it.

  In my own testing this series significantly helps performance with
  small I/O sizes. I also got this email for Christmas this year from
  the kernel test robot (a 244% r/w bandwidth improvement with XFS over
  DAX, with 4k writes):

    https://lkml.org/lkml/2017/12/25/8

  A few of the earlier patches in this pile are also flowing to you via
  other trees (mm, integrity, and nfsd trees in particular)".

* tag 'iversion-v4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux: (22 commits)
  fs: handle inode->i_version more efficiently
  btrfs: only dirty the inode in btrfs_update_time if something was changed
  xfs: avoid setting XFS_ILOG_CORE if i_version doesn't need incrementing
  fs: only set S_VERSION when updating times if necessary
  IMA: switch IMA over to new i_version API
  xfs: convert to new i_version API
  ufs: use new i_version API
  ocfs2: convert to new i_version API
  nfsd: convert to new i_version API
  nfs: convert to new i_version API
  ext4: convert to new i_version API
  ext2: convert to new i_version API
  exofs: switch to new i_version API
  btrfs: convert to new i_version API
  afs: convert to new i_version API
  affs: convert to new i_version API
  fat: convert to new i_version API
  fs: don't take the i_lock in inode_inc_iversion
  fs: new API for handling inode->i_version
  ntfs: remove i_version handling
  ...

5 files changed, 22 insertions, 12 deletions

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 6b7989038d75..b9c0bf80669c 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -32,6 +32,8 @@
 #include "xfs_ialloc.h"
 #include "xfs_dir2.h"
 
+#include <linux/iversion.h>
+
 /*
  * Check that none of the inode's in the buffer have a next
  * unlinked field of 0.
@@ -264,7 +266,8 @@ xfs_inode_from_disk(
 	to->di_flags	= be16_to_cpu(from->di_flags);
 
 	if (to->di_version == 3) {
-		inode->i_version = be64_to_cpu(from->di_changecount);
+		inode_set_iversion_queried(inode,
+					   be64_to_cpu(from->di_changecount));
 		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
 		to->di_flags2 = be64_to_cpu(from->di_flags2);
@@ -314,7 +317,7 @@ xfs_inode_to_disk(
 	to->di_flags = cpu_to_be16(from->di_flags);
 
 	if (from->di_version == 3) {
-		to->di_changecount = cpu_to_be64(inode->i_version);
+		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
 		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 3861d61fb265..3bcb8fd2a826 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -37,6 +37,7 @@
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/iversion.h>
 
 /*
  * Allocate and initialise an xfs_inode.
@@ -293,14 +294,14 @@ xfs_reinit_inode(
 	int		error;
 	uint32_t	nlink = inode->i_nlink;
 	uint32_t	generation = inode->i_generation;
-	uint64_t	version = inode->i_version;
+	uint64_t	version = inode_peek_iversion(inode);
 	umode_t		mode = inode->i_mode;
 
 	error = inode_init_always(mp->m_super, inode);
 
 	set_nlink(inode, nlink);
 	inode->i_generation = generation;
-	inode->i_version = version;
+	inode_set_iversion_queried(inode, version);
 	inode->i_mode = mode;
 	return error;
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 6f95bdb408ce..9f424e0aef1f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -16,6 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/log2.h>
+#include <linux/iversion.h>
 
 #include "xfs.h"
 #include "xfs_fs.h"
@@ -832,7 +833,7 @@ xfs_ialloc(
 	ip->i_d.di_flags = 0;
 
 	if (ip->i_d.di_version == 3) {
-		inode->i_version = 1;
+		inode_set_iversion(inode, 1);
 		ip->i_d.di_flags2 = 0;
 		ip->i_d.di_cowextsize = 0;
 		ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec;
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 6ee5c3bf19ad..7571abf5dfb3 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -30,6 +30,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
 
+#include <linux/iversion.h>
 
 kmem_zone_t	*xfs_ili_zone;		/* inode log item zone */
 
@@ -354,7 +355,7 @@ xfs_inode_to_log_dinode(
 	to->di_next_unlinked = NULLAGINO;
 
 	if (from->di_version == 3) {
-		to->di_changecount = inode->i_version;
+		to->di_changecount = inode_peek_iversion(inode);
 		to->di_crtime.t_sec = from->di_crtime.t_sec;
 		to->di_crtime.t_nsec = from->di_crtime.t_nsec;
 		to->di_flags2 = from->di_flags2;
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index daa7615497f9..4a89da4b6fe7 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -28,6 +28,8 @@
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
 
+#include <linux/iversion.h>
+
 /*
  * Add a locked inode to the transaction.
  *
@@ -110,15 +112,17 @@ xfs_trans_log_inode(
 
 	/*
 	 * First time we log the inode in a transaction, bump the inode change
-	 * counter if it is configured for this to occur. We don't use
-	 * inode_inc_version() because there is no need for extra locking around
-	 * i_version as we already hold the inode locked exclusively for
-	 * metadata modification.
+	 * counter if it is configured for this to occur. While we have the
+	 * inode locked exclusively for metadata modification, we can usually
+	 * avoid setting XFS_ILOG_CORE if no one has queried the value since
+	 * the last time it was incremented. If we have XFS_ILOG_CORE already
+	 * set however, then go ahead and bump the i_version counter
+	 * unconditionally.
 	 */
 	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
 	    IS_I_VERSION(VFS_I(ip))) {
-		VFS_I(ip)->i_version++;
-		flags |= XFS_ILOG_CORE;
+		if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
+			flags |= XFS_ILOG_CORE;
 	}
 
 	tp->t_flags |= XFS_TRANS_DIRTY;