From: Jeff Layton <[email protected]>
The original i_version implementation was pretty expensive, requiring a
log flush on every change. Because of this, it was gated behind a mount
option (implemented via the MS_I_VERSION mountoption flag).
Commit ae5e165d855d (fs: new API for handling inode->i_version) made the
i_version flag much less expensive, so there is no longer a performance
penalty from enabling it. xfs and btrfs already enable it
unconditionally when the on-disk format can support it.
Have ext4 ignore the SB_I_VERSION flag, and just enable it
unconditionally. While we're in here, remove the handling of
Opt_i_version as well, since we're almost to 5.20 anyway.
Ideally, we'd couple this change with a way to disable the i_version
counter (just in case), but the way the iversion mount option was
implemented makes that difficult to do. We'd need to add a new mount
option altogether or do something with tune2fs. That's probably best
left to later patches if it turns out to be needed.
[ Removed leftover bits of i_version from ext4_apply_options() since it
now can't ever be set in ctx->mask_s_flags -- lczerner ]
Cc: Dave Chinner <[email protected]>
Cc: Benjamin Coddington <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Darrick J. Wong <[email protected]>
Signed-off-by: Jeff Layton <[email protected]>
Signed-off-by: Lukas Czerner <[email protected]>
---
v3: Removed leftover bits of i_version from ext4_apply_options
fs/ext4/inode.c | 5 ++---
fs/ext4/super.c | 21 ++++-----------------
2 files changed, 6 insertions(+), 20 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b76554124224..acd00300a697 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5411,7 +5411,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
return -EINVAL;
}
- if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
+ if (attr->ia_size != inode->i_size)
inode_inc_iversion(inode);
if (shrink) {
@@ -5721,8 +5721,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
* 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))
+ if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
inode_inc_iversion(inode);
/* the do_update_inode consumes one bh->b_count */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 845f2f8aee5f..4c3e6021e772 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1585,7 +1585,7 @@ enum {
Opt_inlinecrypt,
Opt_usrjquota, Opt_grpjquota, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
- Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
+ Opt_usrquota, Opt_grpquota, Opt_prjquota,
Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize,
@@ -1694,7 +1694,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
fsparam_flag ("barrier", Opt_barrier),
fsparam_u32 ("barrier", Opt_barrier),
fsparam_flag ("nobarrier", Opt_nobarrier),
- fsparam_flag ("i_version", Opt_i_version),
fsparam_flag ("dax", Opt_dax),
fsparam_enum ("dax", Opt_dax_type, ext4_param_dax),
fsparam_u32 ("stripe", Opt_stripe),
@@ -2140,11 +2139,6 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_abort:
ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
return 0;
- case Opt_i_version:
- ext4_msg(NULL, KERN_WARNING, deprecated_msg, param->key, "5.20");
- ext4_msg(NULL, KERN_WARNING, "Use iversion instead\n");
- ctx_set_flags(ctx, SB_I_VERSION);
- return 0;
case Opt_inlinecrypt:
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
ctx_set_flags(ctx, SB_INLINECRYPT);
@@ -2814,14 +2808,6 @@ static void ext4_apply_options(struct fs_context *fc, struct super_block *sb)
sb->s_flags &= ~ctx->mask_s_flags;
sb->s_flags |= ctx->vals_s_flags;
- /*
- * i_version differs from common mount option iversion so we have
- * to let vfs know that it was set, otherwise it would get cleared
- * on remount
- */
- if (ctx->mask_s_flags & SB_I_VERSION)
- fc->sb_flags |= SB_I_VERSION;
-
#define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; })
APPLY(s_commit_interval);
APPLY(s_stripe);
@@ -2970,8 +2956,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
- if (sb->s_flags & SB_I_VERSION)
- SEQ_OPTS_PUTS("i_version");
if (nodefs || sbi->s_stripe)
SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
if (nodefs || EXT4_MOUNT_DATA_FLAGS &
@@ -4630,6 +4614,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
+ /* i_version is always enabled now */
+ sb->s_flags |= SB_I_VERSION;
+
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(ext4_has_compat_features(sb) ||
ext4_has_ro_compat_features(sb) ||
--
2.37.1
On Wed, 2022-08-03 at 12:53 +0200, Lukas Czerner wrote:
> From: Jeff Layton <[email protected]>
>
> The original i_version implementation was pretty expensive, requiring a
> log flush on every change. Because of this, it was gated behind a mount
> option (implemented via the MS_I_VERSION mountoption flag).
>
> Commit ae5e165d855d (fs: new API for handling inode->i_version) made the
> i_version flag much less expensive, so there is no longer a performance
> penalty from enabling it. xfs and btrfs already enable it
> unconditionally when the on-disk format can support it.
>
> Have ext4 ignore the SB_I_VERSION flag, and just enable it
> unconditionally. While we're in here, remove the handling of
> Opt_i_version as well, since we're almost to 5.20 anyway.
>
> Ideally, we'd couple this change with a way to disable the i_version
> counter (just in case), but the way the iversion mount option was
> implemented makes that difficult to do. We'd need to add a new mount
> option altogether or do something with tune2fs. That's probably best
> left to later patches if it turns out to be needed.
>
> [ Removed leftover bits of i_version from ext4_apply_options() since it
> now can't ever be set in ctx->mask_s_flags -- lczerner ]
>
> Cc: Dave Chinner <[email protected]>
> Cc: Benjamin Coddington <[email protected]>
> Cc: Christoph Hellwig <[email protected]>
> Cc: Darrick J. Wong <[email protected]>
> Signed-off-by: Jeff Layton <[email protected]>
> Signed-off-by: Lukas Czerner <[email protected]>
> ---
> v3: Removed leftover bits of i_version from ext4_apply_options
>
> fs/ext4/inode.c | 5 ++---
> fs/ext4/super.c | 21 ++++-----------------
> 2 files changed, 6 insertions(+), 20 deletions(-)
>
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index b76554124224..acd00300a697 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -5411,7 +5411,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
> return -EINVAL;
> }
>
> - if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
> + if (attr->ia_size != inode->i_size)
> inode_inc_iversion(inode);
>
> if (shrink) {
> @@ -5721,8 +5721,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
> * 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))
> + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
> inode_inc_iversion(inode);
>
> /* the do_update_inode consumes one bh->b_count */
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 845f2f8aee5f..4c3e6021e772 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -1585,7 +1585,7 @@ enum {
> Opt_inlinecrypt,
> Opt_usrjquota, Opt_grpjquota, Opt_quota,
> Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
> - Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
> + Opt_usrquota, Opt_grpquota, Opt_prjquota,
> Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
> Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
> Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize,
> @@ -1694,7 +1694,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
> fsparam_flag ("barrier", Opt_barrier),
> fsparam_u32 ("barrier", Opt_barrier),
> fsparam_flag ("nobarrier", Opt_nobarrier),
> - fsparam_flag ("i_version", Opt_i_version),
> fsparam_flag ("dax", Opt_dax),
> fsparam_enum ("dax", Opt_dax_type, ext4_param_dax),
> fsparam_u32 ("stripe", Opt_stripe),
> @@ -2140,11 +2139,6 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
> case Opt_abort:
> ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
> return 0;
> - case Opt_i_version:
> - ext4_msg(NULL, KERN_WARNING, deprecated_msg, param->key, "5.20");
> - ext4_msg(NULL, KERN_WARNING, "Use iversion instead\n");
> - ctx_set_flags(ctx, SB_I_VERSION);
> - return 0;
> case Opt_inlinecrypt:
> #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
> ctx_set_flags(ctx, SB_INLINECRYPT);
> @@ -2814,14 +2808,6 @@ static void ext4_apply_options(struct fs_context *fc, struct super_block *sb)
> sb->s_flags &= ~ctx->mask_s_flags;
> sb->s_flags |= ctx->vals_s_flags;
>
> - /*
> - * i_version differs from common mount option iversion so we have
> - * to let vfs know that it was set, otherwise it would get cleared
> - * on remount
> - */
> - if (ctx->mask_s_flags & SB_I_VERSION)
> - fc->sb_flags |= SB_I_VERSION;
> -
> #define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; })
> APPLY(s_commit_interval);
> APPLY(s_stripe);
> @@ -2970,8 +2956,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
> SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
> if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
> SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
> - if (sb->s_flags & SB_I_VERSION)
> - SEQ_OPTS_PUTS("i_version");
> if (nodefs || sbi->s_stripe)
> SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
> if (nodefs || EXT4_MOUNT_DATA_FLAGS &
> @@ -4630,6 +4614,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
> sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
> (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
>
> + /* i_version is always enabled now */
> + sb->s_flags |= SB_I_VERSION;
> +
> if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
> (ext4_has_compat_features(sb) ||
> ext4_has_ro_compat_features(sb) ||
Looks good to me. Thanks for picking this up, Lukas!
--
Jeff Layton <[email protected]>