OpenVZ / Virtuozzo kernel development (devel@openvz.org)
 help / color / mirror / Atom feed
From: Eva Kurchatova <eva.kurchatova@virtuozzo.com>
To: khorenko@virtuozzo.com
Cc: devel@openvz.org
Subject: [Devel] [PATCH hci-8.1 1/2] ms/ext4: free the sbi after a grace period
Date: Tue, 17 Nov 2026 07:52:12 +0200	[thread overview]
Message-ID: <20261117055330.810827-2-eva.kurchatova@virtuozzo.com> (raw)
In-Reply-To: <20261117055330.810827-1-eva.kurchatova@virtuozzo.com>

From: Christian Brauner <brauner@kernel.org>

[ Upstream commit c17b44266a1f9fcb49b894d4611d1254bf1aa313 ]

ext4_get_link() follows a symlink that keeps its target in a data block
in rcu pathwalk mode with ext4_getblk(EXT4_GET_BLOCKS_CACHED_NOWAIT).
That reads s_mount_state in the ASSERT() of ext4_getblk() and again in
ext4_es_lookup_extent(), and the lookup bumps the extent status hit or
miss counter, all through sb->s_fs_info.

ext4_put_super() destroys those counters, clears sb->s_fs_info and frees
the sbi without waiting for a grace period. A pathwalk that is still in
ext4_get_link() when the last reference to the mount goes away then
dereferences a NULL s_fs_info, the freed sbi or the destroyed percpu
counters.

With a pathwalk held up in ext4_get_link() while the last reference
goes away:

  KASAN: null-ptr-deref in range [0x00000000000000a8-0x00000000000000af]
  RIP: 0010:ext4_getblk+0xf0/0x640
  Call Trace:
   <TASK>
   ext4_get_link+0x26c/0x410
   pick_link+0xf96/0x1780
   step_into_slowpath+0x9b8/0x1250
   path_lookupat+0x484/0xb00
   filename_lookup+0x1f1/0x5b0
   vfs_statx+0xd7/0x3b0
   vfs_fstatat+0x4d/0x90
   __do_sys_newfstatat+0xa0/0x100
   do_syscall_64+0x10e/0x5e0
   entry_SYSCALL_64_after_hwframe+0x77/0x7f

So far that has been hard to hit. umount(2) waits for a grace period in
namespace_unlock() before it drops the mount, so only a mount whose last
reference goes away elsewhere, like the close of a file or a chdir out of
a lazily unmounted directory, can race a walker.

Keep sb->s_fs_info and free the sbi together with the extent status
counters after a grace period. Split the counters out of
ext4_es_unregister_shrinker() for that. The shrinker still gets wasted
in ext4_put_super(), the counters go with the sbi.

Fixes: 6493792d3299 ("ext4: convert symlink external data block mapping to bdev")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20261009-work-fixes-rcu-v1-1-7446d2d335e6@kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
[ sashal: omitted ext4_es_destroy_stats() integration with the extent KUnit tests ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
(cherry picked from commit 4ce0e27ea610663a9cdc04e3bca38559147428d4)

https://virtuozzo.atlassian.net/browse/VSTOR-155414
Feature: fix ms/fs

Signed-off-by: Eva Kurchatova <eva.kurchatova@virtuozzo.com>
---
 fs/ext4/ext4.h           |  2 ++
 fs/ext4/extents_status.c |  7 ++++++-
 fs/ext4/extents_status.h |  1 +
 fs/ext4/super.c          | 13 +++++++++++--
 4 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3fe70a19e2a7..3de0fc6e77f2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1690,6 +1690,8 @@ struct ext4_sb_info {
 	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
 	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
+	/* ext4_get_link() reads the sbi in rcu pathwalk */
+	struct rcu_head s_rcu;
 	struct mb_cache *s_ea_block_cache;
 	struct mb_cache *s_ea_inode_cache;
 	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 89fc81a80f9a..cb3432b812a6 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -1804,12 +1804,17 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
 }
 
 void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
+{
+	shrinker_free(sbi->s_es_shrinker);
+}
+
+/* ext4_get_link() bumps the hit and miss counters in rcu pathwalk */
+void ext4_es_destroy_stats(struct ext4_sb_info *sbi)
 {
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
-	shrinker_free(sbi->s_es_shrinker);
 }
 
 /*
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 8f9c008d11e8..502d9110a73c 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -238,6 +238,7 @@ static inline void ext4_es_store_pblock_status(struct extent_status *es,
 
 extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
+extern void ext4_es_destroy_stats(struct ext4_sb_info *sbi);
 
 extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v);
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e292c0597eaf..e450ea1df71d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1273,6 +1273,14 @@ static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
 	rcu_read_unlock();
 }
 
+static void ext4_put_sbi_rcu(struct rcu_head *head)
+{
+	struct ext4_sb_info *sbi = container_of(head, struct ext4_sb_info, s_rcu);
+
+	ext4_es_destroy_stats(sbi);
+	kfree(sbi);
+}
+
 static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1369,7 +1377,6 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_stop_mmpd(sbi);
 
 	brelse(sbi->s_sbh);
-	sb->s_fs_info = NULL;
 	/*
 	 * Now that we are completely done shutting down the
 	 * superblock, we need to actually destroy the kobject.
@@ -1382,7 +1389,8 @@ static void ext4_put_super(struct super_block *sb)
 #if IS_ENABLED(CONFIG_UNICODE)
 	utf8_unload(sb->s_encoding);
 #endif
-	kfree(sbi);
+	/* ext4_get_link() reads the sbi and the counters in rcu pathwalk */
+	call_rcu(&sbi->s_rcu, ext4_put_sbi_rcu);
 }
 
 static struct kmem_cache *ext4_inode_cachep;
@@ -5777,6 +5785,7 @@ failed_mount8: __maybe_unused
 	}
 failed_mount3a:
 	ext4_es_unregister_shrinker(sbi);
+	ext4_es_destroy_stats(sbi);
 failed_mount3:
 	/* flush s_sb_upd_work before sbi destroy */
 	flush_work(&sbi->s_sb_upd_work);
-- 
2.56.1

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel

  reply	other threads:[~2026-11-17  5:55 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-17  5:52 [Devel] [PATCH hci-8.1 0/2] ms/fs: backport RCU pathwalk UAF fixes Eva Kurchatova
2026-11-17  5:52 ` Eva Kurchatova [this message]
2026-11-17  6:02   ` [Devel] [PATCH hci-8.1 1/2] ms/ext4: free the sbi after a grace period no-reply
2026-11-17  5:52 ` [Devel] [PATCH hci-8.1 2/2] ms/unicode: free the map " Eva Kurchatova
2026-11-17  5:59   ` no-reply
2026-11-17 15:15 ` [Devel] [PATCH hci-8.1 0/2] ms/fs: backport RCU pathwalk UAF fixes Konstantin Khorenko
2026-11-17 15:15 ` Konstantin Khorenko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261117055330.810827-2-eva.kurchatova@virtuozzo.com \
    --to=eva.kurchatova@virtuozzo.com \
    --cc=devel@openvz.org \
    --cc=khorenko@virtuozzo.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox