Re: [PATCH] erofs: reuse superblock for file-backed mounts

[Giuseppe Scrivano <gscrivan@redhat.com>]

Giuseppe Scrivano <gscrivan@redhat.com> writes:

> Pedro Falcato <pfalcato@suse.de> writes:
>
>> On Thu, Jul 30, 2026 at 02:41:20PM +0200, Giuseppe Scrivano wrote:
>>> When the same file is mounted multiple times (via path or fd), 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, a separate superblock is created transparently as
>>> a fallback.
>>> 
>>> Tested by mounting a 177M Fedora EROFS image 20 times with full
>>> traversal:
>>> 
>>> ```
>>> \#!/bin/sh
>>> IMG=${1:-/root/fedora.erofs}
>>> N=20
>>> DIR=$(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 "$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"
>>> ```
>>> 
>>> unpatched kernel:
>>> 
>>> Superblocks: 20
>>> erofs_inode delta: +46368
>>> Slab delta: +39952 kB
>>> 0.08user 0.82system 0:00.98elapsed 93%CPU (0avgtext+0avgdata 4796maxresident)k
>>> 19168inputs+10304outputs (24major+16672minor)pagefaults 0swaps
>>> 
>>> patched kernel:
>>> 
>>> Superblocks: 1
>>> erofs_inode delta: +2044
>>> Slab delta: +1088 kB
>>> 0.07user 0.21system 0:00.31elapsed 91%CPU (0avgtext+0avgdata 4848maxresident)k
>>> 19024inputs+6784outputs (25major+16810minor)pagefaults 0swaps
>>> 
>>> 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.
>>
>> Doesn't this approach break-down as soon as you get to change SB flags (through
>> e.g mount -o remount)? It will change superblock flags for all of them, right?
>>
>> (I don't think you can switch off the superblock transparently on a
>> reconfigure?)
>
> This is the same preexisting behavior for block device mounts.  That
> said, I realize this can feel confusing since EROFS is not a block
> device and allowed this so far.
>
> One way to solve this could be an explicit mount option "share_sb" that
> is opt-in and, once set, blocks any remount operations.  Would that
> work?

Would something like the following fixup on top of the previous patch be
acceptable (suggestions for better names are welcome)?

Thanks,
Giuseppe

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 580f8d9f14e7..ac26daf4f78a 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -156,6 +156,7 @@ 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_SHARE_SB		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 cbd76727f0d3..dd2a351811c8 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_share_sb,
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
@@ -414,6 +414,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_flag_no("directio",		Opt_directio),
 	fsparam_u64("fsoffset",			Opt_fsoffset),
 	fsparam_flag("inode_share",		Opt_inode_share),
+	fsparam_flag("share_sb",		Opt_share_sb),
 	fsparam_file_or_string("source",	Opt_source),
 	{}
 };
@@ -560,6 +561,12 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		else
 			set_opt(&sbi->opt, INODE_SHARE);
 		break;
+	case Opt_share_sb:
+		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, SHARE_SB);
+		break;
 	case Opt_source:
 		return erofs_fc_parse_source(fc, param);
 	}
@@ -798,6 +805,8 @@ static int erofs_fc_test_file_super(struct super_block *sb,
 		return 0;
 	if (!sbi->dif0.file || !new_sbi->dif0.file)
 		return 0;
+	if (!test_opt(&new_sbi->opt, SHARE_SB))
+		return 0;
 	return file_inode(sbi->dif0.file) == file_inode(new_sbi->dif0.file) &&
 	       sbi->dif0.fsoff == new_sbi->dif0.fsoff &&
 	       sbi->opt.mount_opt == new_sbi->opt.mount_opt &&
@@ -874,6 +883,9 @@ static int erofs_fc_reconfigure(struct fs_context *fc)
 
 	DBG_BUGON(!sb_rdonly(sb));
 
+	if (test_opt(&sbi->opt, SHARE_SB))
+		return -EBUSY;
+
 	if (new_sbi->domain_id)
 		erofs_info(sb, "ignoring reconfiguration for domain_id.");