[PATCH v7 0/2] erofs: share the superblock for file-backed mounts

[PATCH v7 0/2] erofs: share the superblock for file-backed mounts

[Giuseppe Scrivano]

v6: https://lore.kernel.org/linux-fsdevel/20260812142907.1010046-1-gscrivan@redhat.com/
v5: https://lore.kernel.org/linux-fsdevel/20260811071241.389589-1-gscrivan@redhat.com/
v4: https://lore.kernel.org/linux-fsdevel/20260804060455.2928514-1-gscrivan@redhat.com/
v3: https://lore.kernel.org/linux-fsdevel/20260801075446.2508805-1-gscrivan@redhat.com/
v2: https://lore.kernel.org/linux-fsdevel/20260731160901.2276832-1-gscrivan@redhat.com/
v1: https://lore.kernel.org/linux-fsdevel/20260730124120.1501126-1-gscrivan@redhat.com/

Giuseppe Scrivano (2):
  fs: rename vfs_get_super() to get_tree_super() and export it
  erofs: reuse superblock for file-backed mounts

 Documentation/filesystems/erofs.rst |  7 ++++
 fs/erofs/internal.h                 |  1 +
 fs/erofs/super.c                    | 56 +++++++++++++++++++++++++++--
 fs/super.c                          | 19 +++++++---
 include/linux/fs_context.h          |  4 +++
 5 files changed, 80 insertions(+), 7 deletions(-)

-- 
2.55.0

[PATCH v7 1/2] fs: rename vfs_get_super() to get_tree_super() and export it

[Giuseppe Scrivano]

Rename and export it so filesystems that need a custom superblock
matching policy can reuse it directly instead of open-coding sget_fc()
+ fill_super().  No functional change.

This is a preparatory fix for the next patch.

Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org>
---
 fs/super.c                 | 19 +++++++++++++++----
 include/linux/fs_context.h |  4 ++++
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/fs/super.c b/fs/super.c
index 1d5ccf540a9b..a1dc4de1b657 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1374,7 +1374,17 @@ static int test_single_super(struct super_block *s, struct fs_context *fc)
 	return 1;
 }
 
-static int vfs_get_super(struct fs_context *fc,
+/**
+ * get_tree_super - Get a superblock, optionally sharing an existing one
+ * @fc: The filesystem context holding the parameters
+ * @test: Comparison function to find a matching existing superblock, or NULL
+ * @fill_super: Helper to initialise a new superblock
+ *
+ * If @test is non-NULL and matches an existing superblock, that superblock is
+ * reused; otherwise a new anonymous superblock is created and initialised with
+ * @fill_super.  Passing NULL for @test always creates a new superblock.
+ */
+int get_tree_super(struct fs_context *fc,
 		int (*test)(struct super_block *, struct fs_context *),
 		int (*fill_super)(struct super_block *sb,
 				  struct fs_context *fc))
@@ -1401,12 +1411,13 @@ static int vfs_get_super(struct fs_context *fc,
 	deactivate_locked_super(sb);
 	return err;
 }
+EXPORT_SYMBOL_GPL(get_tree_super);
 
 int get_tree_nodev(struct fs_context *fc,
 		  int (*fill_super)(struct super_block *sb,
 				    struct fs_context *fc))
 {
-	return vfs_get_super(fc, NULL, fill_super);
+	return get_tree_super(fc, NULL, fill_super);
 }
 EXPORT_SYMBOL(get_tree_nodev);
 
@@ -1414,7 +1425,7 @@ int get_tree_single(struct fs_context *fc,
 		  int (*fill_super)(struct super_block *sb,
 				    struct fs_context *fc))
 {
-	return vfs_get_super(fc, test_single_super, fill_super);
+	return get_tree_super(fc, test_single_super, fill_super);
 }
 EXPORT_SYMBOL(get_tree_single);
 
@@ -1424,7 +1435,7 @@ int get_tree_keyed(struct fs_context *fc,
 		void *key)
 {
 	fc->s_fs_info = key;
-	return vfs_get_super(fc, test_keyed_super, fill_super);
+	return get_tree_super(fc, test_keyed_super, fill_super);
 }
 EXPORT_SYMBOL(get_tree_keyed);
 
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index 0d6c8a6d7be2..d1727dffecc5 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -150,6 +150,10 @@ extern int vfs_parse_fs_param_source(struct fs_context *fc,
 				     struct fs_parameter *param);
 extern void fc_drop_locked(struct fs_context *fc);
 
+int get_tree_super(struct fs_context *fc,
+		   int (*test)(struct super_block *, struct fs_context *),
+		   int (*fill_super)(struct super_block *sb,
+				     struct fs_context *fc));
 extern int get_tree_nodev(struct fs_context *fc,
 			 int (*fill_super)(struct super_block *sb,
 					   struct fs_context *fc));
-- 
2.55.0

[PATCH v7 2/2] erofs: reuse superblock for file-backed mounts

[Giuseppe Scrivano]

When the same file-backed image is mounted multiple times (via path or
fd) with the superblock_share mount option, reuse the existing
superblock instead of creating a new one.  This allows multiple mounts
of the same image to share in-kernel data structures more efficiently.

The backing file is identified by its inode and fsoffset.  If mount
options conflict or extra devices are used, a separate superblock
is created transparently as a fallback.  Remount is not allowed on
shared superblocks.

Tested by mounting a 177M Fedora EROFS image 20 times with full
traversal:

  #!/bin/sh
  IMG=${1:-/root/fedora.erofs}
  OPTS=${2:+-o $2}
  N=20
  DIR=$(mktemp -d)
  trap "umount $DIR/m* 2>/dev/null; rm -rf $DIR" EXIT

  sync; echo 3 > /proc/sys/vm/drop_caches
  INODES_BEFORE=$(grep erofs_inode /proc/slabinfo | awk '{print $2}')
  MEM_BEFORE=$(grep ^Slab: /proc/meminfo | awk '{print $2}')

  for i in $(seq 1 $N); do
      mkdir $DIR/m$i
      mount -t erofs $OPTS "$IMG" $DIR/m$i
      find $DIR/m$i > /dev/null
  done

  echo "Superblocks: $(grep $DIR /proc/self/mountinfo | \
      awk '{print $3}' | sort -u | wc -l)"
  echo "erofs_inode delta: +$(( $(grep erofs_inode /proc/slabinfo | \
      awk '{print $2}') - INODES_BEFORE ))"
  echo "Slab delta: +$(( $(grep ^Slab: /proc/meminfo | \
      awk '{print $2}') - MEM_BEFORE )) kB"

without superblock_share:

  # time ./test.sh /root/fedora.erofs
  Superblocks: 20
  erofs_inode delta: +45864
  Slab delta: +37448 kB
  real	0m2.311s
  user	0m0.222s
  sys	0m1.998s

with superblock_share:

  # time ./test.sh /root/fedora.erofs superblock_share
  Superblocks: 1
  erofs_inode delta: +2044
  Slab delta: +284 kB
  real	0m0.679s
  user	0m0.157s
  sys	0m0.469s

The time difference shows that sharing the superblock also benefits
the page cache and inode cache, as subsequent mounts of the same image
avoid re-reading the backing file.  This is particularly useful for
container hosts running multiple containers from the same base image.

Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org>
---
 Documentation/filesystems/erofs.rst |  7 ++++
 fs/erofs/internal.h                 |  1 +
 fs/erofs/super.c                    | 56 +++++++++++++++++++++++++++--
 3 files changed, 61 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index d301d9ac946a..02caf3b061fe 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -139,6 +139,9 @@ inode_share            Enable inode page sharing for this filesystem.  Inodes wi
                        page cache.
 source=%s              (For file-backed mounts) Specify the backing image as a path
                        or as an already-opened file descriptor.
+superblock_share       (For file-backed mounts) Share the superblock when the same
+                       backing file is mounted more than once with compatible
+                       options.  Remount is not allowed on shared superblocks.
 ===================    =========================================================
 
 File-backed mounts
@@ -156,6 +159,10 @@ Only regular files are accepted as backing files; to mount an image that
 resides on a block device, use the traditional block device mount path
 instead.
 
+When superblock_share is specified, multiple mounts of the same backing
+file at the same fsoffset with compatible mount options can share a single
+superblock.  Remount is not allowed on shared superblocks.
+
 Sysfs Entries
 =============
 
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 12e3a5b80a5a..da58053c1116 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -150,6 +150,7 @@ struct erofs_sb_info {
 #define EROFS_MOUNT_DAX_NEVER		0x00000080
 #define EROFS_MOUNT_DIRECT_IO		0x00000100
 #define EROFS_MOUNT_INODE_SHARE		0x00000200
+#define EROFS_MOUNT_SUPERBLOCK_SHARE	0x00000400
 
 #define clear_opt(opt, option)	((opt)->mount_opt &= ~EROFS_MOUNT_##option)
 #define set_opt(opt, option)	((opt)->mount_opt |= EROFS_MOUNT_##option)
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 0967aace9f7f..16fa3b853f1b 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -386,7 +386,7 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
 enum {
 	Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
 	Opt_device, Opt_domain_id, Opt_directio, Opt_fsoffset, Opt_inode_share,
-	Opt_source,
+	Opt_source, Opt_superblock_share,
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
@@ -415,6 +415,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_u64("fsoffset",			Opt_fsoffset),
 	fsparam_flag("inode_share",		Opt_inode_share),
 	fsparam_file_or_string("source",	Opt_source),
+	fsparam_flag("superblock_share",	Opt_superblock_share),
 	{}
 };
 
@@ -560,6 +561,12 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		else
 			set_opt(&sbi->opt, INODE_SHARE);
 		break;
+	case Opt_superblock_share:
+		if (!IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE))
+			errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+		else
+			set_opt(&sbi->opt, SUPERBLOCK_SHARE);
+		break;
 	case Opt_source:
 		return erofs_fc_parse_source(fc, param);
 	}
@@ -667,6 +674,16 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		errorfc(fc, "FSDAX is not allowed when inode_share is on");
 		return -EINVAL;
 	}
+	if (test_opt(&sbi->opt, SUPERBLOCK_SHARE) &&
+	    test_opt(&sbi->opt, INODE_SHARE)) {
+		errorfc(fc, "superblock_share is not allowed when inode_share is on");
+		return -EINVAL;
+	}
+	if (test_opt(&sbi->opt, SUPERBLOCK_SHARE) &&
+	    sbi->devs->extra_devices) {
+		errorfc(fc, "superblock_share does not support extra devices");
+		return -EINVAL;
+	}
 
 	sbi->blkszbits = PAGE_SHIFT;
 	if (erofs_is_fileio_mode(sbi)) {
@@ -794,6 +811,35 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	return 0;
 }
 
+/*
+ * The function is used only with a sbi that has SUPERBLOCK_SHARE set,
+ * so that the memcmp later ensures new_sbi is also shareable.
+ */
+static int erofs_sb_share_test_super(struct super_block *sb,
+				     struct fs_context *fc)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	struct erofs_sb_info *new_sbi = fc->s_fs_info;
+
+	if (sb->s_iflags & SB_I_RETIRED)
+		return 0;
+	if (!sbi->dif0.file || !new_sbi->dif0.file)
+		return 0;
+	return file_inode(sbi->dif0.file) == file_inode(new_sbi->dif0.file) &&
+	       sbi->dif0.fsoff == new_sbi->dif0.fsoff &&
+	       !memcmp(&sbi->opt, &new_sbi->opt, sizeof(sbi->opt));
+}
+
+static int erofs_file_get_tree(struct fs_context *fc)
+{
+	struct erofs_sb_info *sbi = fc->s_fs_info;
+
+	if (!test_opt(&sbi->opt, SUPERBLOCK_SHARE))
+		return get_tree_nodev(fc, erofs_fc_fill_super);
+
+	return get_tree_super(fc, erofs_sb_share_test_super, erofs_fc_fill_super);
+}
+
 static int erofs_fc_get_tree(struct fs_context *fc)
 {
 	struct erofs_sb_info *sbi = fc->s_fs_info;
@@ -809,7 +855,7 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 			errorfc(fc, "source is unsupported");
 			return -EINVAL;
 		}
-		return get_tree_nodev(fc, erofs_fc_fill_super);
+		return erofs_file_get_tree(fc);
 	}
 
 	ret = get_tree_bdev_flags(fc, erofs_fc_fill_super,
@@ -827,7 +873,7 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 
 		if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) &&
 		    sbi->dif0.file->f_mapping->a_ops->read_folio)
-			return get_tree_nodev(fc, erofs_fc_fill_super);
+			return erofs_file_get_tree(fc);
 	}
 	return ret;
 }
@@ -840,6 +886,10 @@ static int erofs_fc_reconfigure(struct fs_context *fc)
 
 	DBG_BUGON(!sb_rdonly(sb));
 
+	/* Shared superblocks must not be reconfigured.  */
+	if (test_opt(&sbi->opt, SUPERBLOCK_SHARE))
+		return -EBUSY;
+
 	if (new_sbi->domain_id)
 		erofs_info(sb, "ignoring reconfiguration for domain_id.");
 
-- 
2.55.0

Re: [PATCH v7 1/2] fs: rename vfs_get_super() to get_tree_super() and export it

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH v7 1/2] fs: rename vfs_get_super() to get_tree_super() and export it

[Jan Kara]

On Fri 02-10-26 18:31:43, Giuseppe Scrivano wrote:
> Rename and export it so filesystems that need a custom superblock
> matching policy can reuse it directly instead of open-coding sget_fc()
> + fill_super().  No functional change.
> 
> This is a preparatory fix for the next patch.
> 
> Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org>

OK, AFAIU you are essentially implementing kind of bind-mounting for
your file-backed mounts, aren't you? I guess makes sense. Feel free to add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  fs/super.c                 | 19 +++++++++++++++----
>  include/linux/fs_context.h |  4 ++++
>  2 files changed, 19 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/super.c b/fs/super.c
> index 1d5ccf540a9b..a1dc4de1b657 100644
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -1374,7 +1374,17 @@ static int test_single_super(struct super_block *s, struct fs_context *fc)
>  	return 1;
>  }
>  
> -static int vfs_get_super(struct fs_context *fc,
> +/**
> + * get_tree_super - Get a superblock, optionally sharing an existing one
> + * @fc: The filesystem context holding the parameters
> + * @test: Comparison function to find a matching existing superblock, or NULL
> + * @fill_super: Helper to initialise a new superblock
> + *
> + * If @test is non-NULL and matches an existing superblock, that superblock is
> + * reused; otherwise a new anonymous superblock is created and initialised with
> + * @fill_super.  Passing NULL for @test always creates a new superblock.
> + */
> +int get_tree_super(struct fs_context *fc,
>  		int (*test)(struct super_block *, struct fs_context *),
>  		int (*fill_super)(struct super_block *sb,
>  				  struct fs_context *fc))
> @@ -1401,12 +1411,13 @@ static int vfs_get_super(struct fs_context *fc,
>  	deactivate_locked_super(sb);
>  	return err;
>  }
> +EXPORT_SYMBOL_GPL(get_tree_super);
>  
>  int get_tree_nodev(struct fs_context *fc,
>  		  int (*fill_super)(struct super_block *sb,
>  				    struct fs_context *fc))
>  {
> -	return vfs_get_super(fc, NULL, fill_super);
> +	return get_tree_super(fc, NULL, fill_super);
>  }
>  EXPORT_SYMBOL(get_tree_nodev);
>  
> @@ -1414,7 +1425,7 @@ int get_tree_single(struct fs_context *fc,
>  		  int (*fill_super)(struct super_block *sb,
>  				    struct fs_context *fc))
>  {
> -	return vfs_get_super(fc, test_single_super, fill_super);
> +	return get_tree_super(fc, test_single_super, fill_super);
>  }
>  EXPORT_SYMBOL(get_tree_single);
>  
> @@ -1424,7 +1435,7 @@ int get_tree_keyed(struct fs_context *fc,
>  		void *key)
>  {
>  	fc->s_fs_info = key;
> -	return vfs_get_super(fc, test_keyed_super, fill_super);
> +	return get_tree_super(fc, test_keyed_super, fill_super);
>  }
>  EXPORT_SYMBOL(get_tree_keyed);
>  
> diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
> index 0d6c8a6d7be2..d1727dffecc5 100644
> --- a/include/linux/fs_context.h
> +++ b/include/linux/fs_context.h
> @@ -150,6 +150,10 @@ extern int vfs_parse_fs_param_source(struct fs_context *fc,
>  				     struct fs_parameter *param);
>  extern void fc_drop_locked(struct fs_context *fc);
>  
> +int get_tree_super(struct fs_context *fc,
> +		   int (*test)(struct super_block *, struct fs_context *),
> +		   int (*fill_super)(struct super_block *sb,
> +				     struct fs_context *fc));
>  extern int get_tree_nodev(struct fs_context *fc,
>  			 int (*fill_super)(struct super_block *sb,
>  					   struct fs_context *fc));
> -- 
> 2.55.0
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR

Re: [PATCH v7 1/2] fs: rename vfs_get_super() to get_tree_super() and export it

[Gao Xiang]

Hi Christian,

On Fri, Oct 02, 2026 at 06:31:43PM +0200, Giuseppe Scrivano wrote:
> Rename and export it so filesystems that need a custom superblock
> matching policy can reuse it directly instead of open-coding sget_fc()
> + fill_super().  No functional change.
> 
> This is a preparatory fix for the next patch.
> 
> Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org>

Could you replace the previous patch in
https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git/log/?h=vfs-7.4.shared.super

with this version?

It addresses Christoph's previous review, I could pick up the
updated branch then:
https://lore.kernel.org/r/arY9FCatWwCw418K@infradead.org

Thanks for Christoph and Jan's review here again!

Thanks,
Gao Xiang