ext4: fix the might_sleep() warnings in kvfree()

[ Upstream commit 496bb99b7e66f48b178126626f47e9ba79e2d0fa ]

Use the kvfree() in the RCU read critical section can trigger
the following warnings:

EXT4-fs (vdb): unmounting filesystem cd983e5b-3c83-4f5a-a136-17b00eb9d018.

WARNING: suspicious RCU usage

./include/linux/rcupdate.h:409 Illegal context switch in RCU read-side critical section!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1

Call Trace:
 <TASK>
 dump_stack_lvl+0xbb/0xd0
 dump_stack+0x14/0x20
 lockdep_rcu_suspicious+0x15a/0x1b0
 __might_resched+0x375/0x4d0
 ? put_object.part.0+0x2c/0x50
 __might_sleep+0x108/0x160
 vfree+0x58/0x910
 ? ext4_group_desc_free+0x27/0x270
 kvfree+0x23/0x40
 ext4_group_desc_free+0x111/0x270
 ext4_put_super+0x3c8/0xd40
 generic_shutdown_super+0x14c/0x4a0
 ? __pfx_shrinker_free+0x10/0x10
 kill_block_super+0x40/0x90
 ext4_kill_sb+0x6d/0xb0
 deactivate_locked_super+0xb4/0x180
 deactivate_super+0x7e/0xa0
 cleanup_mnt+0x296/0x3e0
 __cleanup_mnt+0x16/0x20
 task_work_run+0x157/0x250
 ? __pfx_task_work_run+0x10/0x10
 ? exit_to_user_mode_loop+0x6a/0x550
 exit_to_user_mode_loop+0x102/0x550
 do_syscall_64+0x44a/0x500
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

BUG: sleeping function called from invalid context at mm/vmalloc.c:3441
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 556, name: umount
preempt_count: 1, expected: 0
CPU: 3 UID: 0 PID: 556 Comm: umount
Call Trace:
 <TASK>
 dump_stack_lvl+0xbb/0xd0
 dump_stack+0x14/0x20
 __might_resched+0x275/0x4d0
 ? put_object.part.0+0x2c/0x50
 __might_sleep+0x108/0x160
 vfree+0x58/0x910
 ? ext4_group_desc_free+0x27/0x270
 kvfree+0x23/0x40
 ext4_group_desc_free+0x111/0x270
 ext4_put_super+0x3c8/0xd40
 generic_shutdown_super+0x14c/0x4a0
 ? __pfx_shrinker_free+0x10/0x10
 kill_block_super+0x40/0x90
 ext4_kill_sb+0x6d/0xb0
 deactivate_locked_super+0xb4/0x180
 deactivate_super+0x7e/0xa0
 cleanup_mnt+0x296/0x3e0
 __cleanup_mnt+0x16/0x20
 task_work_run+0x157/0x250
 ? __pfx_task_work_run+0x10/0x10
 ? exit_to_user_mode_loop+0x6a/0x550
 exit_to_user_mode_loop+0x102/0x550
 do_syscall_64+0x44a/0x500
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The above scenarios occur in initialization failures and teardown
paths, there are no parallel operations on the resources released
by kvfree(), this commit therefore remove rcu_read_lock/unlock() and
use rcu_access_pointer() instead of rcu_dereference() operations.

Fixes: 7c990728b99e ("ext4: fix potential race between s_flex_groups online resizing and access")
Fixes: df3da4ea5a0f ("ext4: fix potential race between s_group_info online resizing and access")
Signed-off-by: Zqiang <qiang.zhang@linux.dev>
Reviewed-by: Baokun Li <libaokun@linux.alibaba.com>
Link: https://patch.msgid.link/20260319094545.19291-1-qiang.zhang@linux.dev
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
[ adapted fix to inlined teardown code ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 007a1928e2b2b6b75386b1382814eb8b0bd3e943..82a9121826ea15284a3659fffa022284bbe3b957 100644 (file)
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3353,9 +3353,7 @@ err_freebuddy:
        rcu_read_unlock();
        iput(sbi->s_buddy_cache);
 err_freesgi:
-       rcu_read_lock();
-       kvfree(rcu_dereference(sbi->s_group_info));
-       rcu_read_unlock();
+       kvfree(rcu_access_pointer(sbi->s_group_info));
        return -ENOMEM;
 }
 
@@ -3634,7 +3632,8 @@ int ext4_mb_release(struct super_block *sb)
        flush_work(&sbi->s_discard_work);
        WARN_ON_ONCE(!list_empty(&sbi->s_discard_list));
 
-       if (sbi->s_group_info) {
+       group_info = rcu_access_pointer(sbi->s_group_info);
+       if (group_info) {
                for (i = 0; i < ngroups; i++) {
                        cond_resched();
                        grinfo = ext4_get_group_info(sb, i);
@@ -3652,12 +3651,9 @@ int ext4_mb_release(struct super_block *sb)
                num_meta_group_infos = (ngroups +
                                EXT4_DESC_PER_BLOCK(sb) - 1) >>
                        EXT4_DESC_PER_BLOCK_BITS(sb);
-               rcu_read_lock();
-               group_info = rcu_dereference(sbi->s_group_info);
                for (i = 0; i < num_meta_group_infos; i++)
                        kfree(group_info[i]);
                kvfree(group_info);
-               rcu_read_unlock();
        }
        kfree(sbi->s_mb_largest_free_orders);
        kfree(sbi->s_mb_largest_free_orders_locks);

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d616a5e5d035989ef2192f3b4bf296e6fab00599..b4274f8185961b38d59648dc170b6c38d44928cc 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1220,18 +1220,16 @@ static void ext4_put_super(struct super_block *sb)
        if (!sb_rdonly(sb))
                ext4_commit_super(sb);
 
-       rcu_read_lock();
-       group_desc = rcu_dereference(sbi->s_group_desc);
+       group_desc = rcu_access_pointer(sbi->s_group_desc);
        for (i = 0; i < sbi->s_gdb_count; i++)
                brelse(group_desc[i]);
        kvfree(group_desc);
-       flex_groups = rcu_dereference(sbi->s_flex_groups);
+       flex_groups = rcu_access_pointer(sbi->s_flex_groups);
        if (flex_groups) {
                for (i = 0; i < sbi->s_flex_groups_allocated; i++)
                        kvfree(flex_groups[i]);
                kvfree(flex_groups);
        }
-       rcu_read_unlock();
        percpu_counter_destroy(&sbi->s_freeclusters_counter);
        percpu_counter_destroy(&sbi->s_freeinodes_counter);
        percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -5075,14 +5073,12 @@ failed_mount7:
        ext4_unregister_li_request(sb);
 failed_mount6:
        ext4_mb_release(sb);
-       rcu_read_lock();
-       flex_groups = rcu_dereference(sbi->s_flex_groups);
+       flex_groups = rcu_access_pointer(sbi->s_flex_groups);
        if (flex_groups) {
                for (i = 0; i < sbi->s_flex_groups_allocated; i++)
                        kvfree(flex_groups[i]);
                kvfree(flex_groups);
        }
-       rcu_read_unlock();
        percpu_counter_destroy(&sbi->s_freeclusters_counter);
        percpu_counter_destroy(&sbi->s_freeinodes_counter);
        percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -5120,12 +5116,10 @@ failed_mount3:
        ext4_stop_mmpd(sbi);
        del_timer_sync(&sbi->s_err_report);
 failed_mount2:
-       rcu_read_lock();
-       group_desc = rcu_dereference(sbi->s_group_desc);
+       group_desc = rcu_access_pointer(sbi->s_group_desc);
        for (i = 0; i < db_count; i++)
                brelse(group_desc[i]);
        kvfree(group_desc);
-       rcu_read_unlock();
 failed_mount:
        if (sbi->s_chksum_driver)
                crypto_free_shash(sbi->s_chksum_driver);