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
  ...

fs/nfs/delegation.c

@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/iversion.h>
 
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
@@ -347,7 +348,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	nfs4_stateid_copy(&delegation->stateid, &res->delegation);
 	delegation->type = res->delegation_type;
 	delegation->pagemod_limit = res->pagemod_limit;
-	delegation->change_attr = inode->i_version;
+	delegation->change_attr = inode_peek_iversion_raw(inode);
 	delegation->cred = get_rpccred(cred);
 	delegation->inode = inode;
 	delegation->flags = 1<<NFS_DELEGATION_REFERENCED;

fs/nfs/fscache-index.c

@@ -16,6 +16,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
 #include <linux/in6.h>
+#include <linux/iversion.h>
 
 #include "internal.h"
 #include "fscache.h"
@@ -211,7 +212,7 @@ static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data,
 	auxdata.ctime = nfsi->vfs_inode.i_ctime;
 
 	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = nfsi->vfs_inode.i_version;
+		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
 
 	if (bufmax > sizeof(auxdata))
 		bufmax = sizeof(auxdata);
@@ -243,7 +244,7 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
 	auxdata.ctime = nfsi->vfs_inode.i_ctime;
 
 	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = nfsi->vfs_inode.i_version;
+		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
 
 	if (memcmp(data, &auxdata, datalen) != 0)
 		return FSCACHE_CHECKAUX_OBSOLETE;

fs/nfs/inode.c

@@ -38,8 +38,8 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/freezer.h>
-
 #include <linux/uaccess.h>
+#include <linux/iversion.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -483,7 +483,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		memset(&inode->i_atime, 0, sizeof(inode->i_atime));
 		memset(&inode->i_mtime, 0, sizeof(inode->i_mtime));
 		memset(&inode->i_ctime, 0, sizeof(inode->i_ctime));
-		inode->i_version = 0;
+		inode_set_iversion_raw(inode, 0);
 		inode->i_size = 0;
 		clear_nlink(inode);
 		inode->i_uid = make_kuid(&init_user_ns, -2);
@@ -508,7 +508,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
-			inode->i_version = fattr->change_attr;
+			inode_set_iversion_raw(inode, fattr->change_attr);
 		else
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE);
@@ -1289,8 +1289,8 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 
 	if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
 			&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
-			&& inode->i_version == fattr->pre_change_attr) {
-		inode->i_version = fattr->change_attr;
+			&& !inode_cmp_iversion_raw(inode, fattr->pre_change_attr)) {
+		inode_set_iversion_raw(inode, fattr->change_attr);
 		if (S_ISDIR(inode->i_mode))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
 		ret |= NFS_INO_INVALID_ATTR;
@@ -1348,7 +1348,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 
 	if (!nfs_file_has_buffered_writers(nfsi)) {
 		/* Verify a few of the more important attributes */
-		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode->i_version != fattr->change_attr)
+		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode_cmp_iversion_raw(inode, fattr->change_attr))
 			invalid |= NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE;
 
 		if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
@@ -1642,7 +1642,7 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
 			(fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) {
-		fattr->pre_change_attr = inode->i_version;
+		fattr->pre_change_attr = inode_peek_iversion_raw(inode);
 		fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
@@ -1778,7 +1778,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 
 	/* More cache consistency checks */
 	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
-		if (inode->i_version != fattr->change_attr) {
+		if (inode_cmp_iversion_raw(inode, fattr->change_attr)) {
 			dprintk("NFS: change_attr change on server for file %s/%ld\n",
 					inode->i_sb->s_id, inode->i_ino);
 			/* Could it be a race with writeback? */
@@ -1790,7 +1790,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				if (S_ISDIR(inode->i_mode))
 					nfs_force_lookup_revalidate(inode);
 			}
-			inode->i_version = fattr->change_attr;
+			inode_set_iversion_raw(inode, fattr->change_attr);
 		}
 	} else {
 		nfsi->cache_validity |= save_cache_validity;

fs/nfs/nfs4proc.c

@@ -54,6 +54,7 @@
 #include <linux/xattr.h>
 #include <linux/utsname.h>
 #include <linux/freezer.h>
+#include <linux/iversion.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -1045,16 +1046,16 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo,
 
 	spin_lock(&dir->i_lock);
 	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-	if (cinfo->atomic && cinfo->before == dir->i_version) {
+	if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(dir)) {
 		nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
 		nfsi->attrtimeo_timestamp = jiffies;
 	} else {
 		nfs_force_lookup_revalidate(dir);
-		if (cinfo->before != dir->i_version)
+		if (cinfo->before != inode_peek_iversion_raw(dir))
 			nfsi->cache_validity |= NFS_INO_INVALID_ACCESS |
 				NFS_INO_INVALID_ACL;
 	}
-	dir->i_version = cinfo->after;
+	inode_set_iversion_raw(dir, cinfo->after);
 	nfsi->read_cache_jiffies = timestamp;
 	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
@@ -2454,7 +2455,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 			data->file_created = true;
 		else if (o_res->cinfo.before != o_res->cinfo.after)
 			data->file_created = true;
-		if (data->file_created || dir->i_version != o_res->cinfo.after)
+		if (data->file_created ||
+		    inode_peek_iversion_raw(dir) != o_res->cinfo.after)
 			update_changeattr(dir, &o_res->cinfo,
 					o_res->f_attr->time_start);
 	}

fs/nfs/nfstrace.h

@@ -9,6 +9,7 @@
 #define _TRACE_NFS_H
 
 #include <linux/tracepoint.h>
+#include <linux/iversion.h>
 
 #define nfs_show_file_type(ftype) \
 	__print_symbolic(ftype, \
@@ -61,7 +62,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event,
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
-			__entry->version = inode->i_version;
+			__entry->version = inode_peek_iversion_raw(inode);
 		),
 
 		TP_printk(
@@ -100,7 +101,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event_done,
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
 			__entry->type = nfs_umode_to_dtype(inode->i_mode);
-			__entry->version = inode->i_version;
+			__entry->version = inode_peek_iversion_raw(inode);
 			__entry->size = i_size_read(inode);
 			__entry->nfsi_flags = nfsi->flags;
 			__entry->cache_validity = nfsi->cache_validity;

fs/nfs/write.c

@@ -23,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/freezer.h>
 #include <linux/wait.h>
+#include <linux/iversion.h>
 
 #include <linux/uaccess.h>
 
@@ -753,11 +754,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	 */
 	spin_lock(&mapping->private_lock);
 	if (!nfs_have_writebacks(inode) &&
-	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) {
-		spin_lock(&inode->i_lock);
-		inode->i_version++;
-		spin_unlock(&inode->i_lock);
-	}
+	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
+		inode_inc_iversion_raw(inode);
 	if (likely(!PageSwapCache(req->wb_page))) {
 		set_bit(PG_MAPPED, &req->wb_flags);
 		SetPagePrivate(req->wb_page);