[PATCH v2] ocfs2/dlm: Protect the recovery list during debugfs reads

[Cen Zhang <zzzccc427@gmail.com>]

Recovery participant records must remain alive while debug_state_print()
walks reco.node_data and formats their fields. The formatter holds
dlm->spinlock, but the recovery participant list is protected by
dlm_reco_state_lock. In particular, dlm_destroy_recovery_area() detaches
the list under dlm_reco_state_lock and frees the detached records after
releasing it. A concurrent debugfs open can therefore read freed memory.

Protect the participant traversal and field reads in debug_state_print()
with dlm_reco_state_lock, matching the existing list writers. This also
serializes the traversal against list_add_tail() during recovery-area
initialization. Make the existing lock available to the debug code
through dlmcommon.h; the lock remains internal to the OCFS2 DLM module.

Release dlm->spinlock after formatting the other domain state and before
acquiring dlm_reco_state_lock, so the debug reader does not nest the two
locks. Leave recovery list insertion, detachment and freeing unchanged.

KASAN report as below:

    BUG: KASAN: slab-use-after-free in debug_state_open+0x1169/0x12d0
    Read of size 4 at addr ffff88810662ef80 by task dlm-state-stres/896

    CPU: 1 UID: 0 PID: 896 Comm: dlm-state-stres Not tainted 7.3.0-rc4-next-20260921-pmb-ocfs2-functional-v1+ #1 PREEMPT(lazy)
    Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
    Call Trace:
     <TASK>
     dump_stack_lvl+0x93/0xd0
     print_report+0xce/0x630
     ? debug_state_open+0x1169/0x12d0
     ? srso_alias_return_thunk+0x5/0xfbef5
     ? __virt_addr_valid+0x20e/0x420
     ? debug_state_open+0x1169/0x12d0
     kasan_report+0xe0/0x110
     ? debug_state_open+0x1169/0x12d0
     debug_state_open+0x1169/0x12d0
     ? __pfx_debug_state_open+0x10/0x10
     full_proxy_open_regular+0x193/0x310
     do_dentry_open+0x595/0x12d0
     ? __pfx_full_proxy_open_regular+0x10/0x10
     vfs_open_consume+0xd1/0x400
     ? srso_alias_return_thunk+0x5/0xfbef5
     path_openat+0x18d0/0x2020
     ? __pfx_path_openat+0x10/0x10
     do_file_open+0x21e/0x470
     ? __pfx_do_file_open+0x10/0x10
     ? _raw_spin_unlock+0x23/0x40
     ? srso_alias_return_thunk+0x5/0xfbef5
     ? alloc_fd+0x3a6/0x6b0
     do_sys_openat2+0xf4/0x1b0
     ? __pfx_do_sys_openat2+0x10/0x10
     ? srso_alias_return_thunk+0x5/0xfbef5
     ? __fput+0x5b5/0xa60
     __x64_sys_openat+0x136/0x1e0
     ? __pfx___x64_sys_openat+0x10/0x10
     do_syscall_64+0x114/0x620
     entry_SYSCALL_64_after_hwframe+0x77/0x7f
    [Register dump omitted.]
     </TASK>

    Allocated by task 880:
     kasan_save_stack+0x33/0x60
     kasan_save_track+0x14/0x30
     __kasan_kmalloc+0xaa/0xb0
     __kmalloc_cache_noprof+0x28d/0x610
     dlm_remaster_locks+0x147/0x1d90
     dlm_do_recovery+0xde1/0x1580
     dlm_recovery_thread+0x109/0x300
     kthread+0x351/0x460
     ret_from_fork+0x659/0x940
     ret_from_fork_asm+0x1a/0x30

    Freed by task 880:
     kasan_save_stack+0x33/0x60
     kasan_save_track+0x14/0x30
     kasan_save_free_info+0x3b/0x60
     __kasan_slab_free+0x5f/0x80
     kfree+0x308/0x580
     dlm_destroy_recovery_area+0x285/0x460
     dlm_remaster_locks+0x17c4/0x1d90
     dlm_do_recovery+0xde1/0x1580
     dlm_recovery_thread+0x109/0x300
     kthread+0x351/0x460
     ret_from_fork+0x659/0x940
     ret_from_fork_asm+0x1a/0x30

    The buggy address belongs to the object at ffff88810662ef80
     which belongs to the cache kmalloc-32 of size 32
    The buggy address is located 0 bytes inside of
     freed 32-byte region [ffff88810662ef80, ffff88810662efa0)

    [Page and memory-state dumps omitted.]

Fixes: 007dce53a29c ("ocfs2/dlm: Dump the dlm state in a debugfs file")
Assisted-by: LLM
Signed-off-by: Cen Zhang <zzzccc427@gmail.com>
---
Changes in v2:
- Use dlm_reco_state_lock in debug_state_print() to protect recovery
  participant traversal and field reads.
- Serialize the read with recovery participant insertion, and leave list
  teardown unchanged.
- Release dlm->spinlock before acquiring the recovery list lock.

Link to v1: https://lore.kernel.org/r/pm-ocfs2-objects-candidate-0049-v2-a5d5091b8900dc3f9849@gmail.com

 fs/ocfs2/dlm/dlmcommon.h   | 2 ++
 fs/ocfs2/dlm/dlmdebug.c    | 5 ++++-
 fs/ocfs2/dlm/dlmrecovery.c | 2 +-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 20f790a47484a72cba1cd71b3d505f36c1b2d5a4..58b28dfa8d34ef237df7b1eb789f0b461187174e 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -435,6 +435,8 @@ enum {
 	DLM_DEREF_LOCKRES_DONE		= 522,
 };
 
+extern spinlock_t dlm_reco_state_lock;
+
 struct dlm_reco_node_data
 {
 	int state;
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index ce6d301cb9420385211d20d59637069154a89993..a91f167ed683931da0e44638875b36debe4eb702 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -736,8 +736,11 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 				 buf + out, len - out);
 	out += scnprintf(buf + out, len - out, "\n");
 
+	spin_unlock(&dlm->spinlock);
+
 	/* Recovery Node State: */
 	out += scnprintf(buf + out, len - out, "Recovery Node State:\n");
+	spin_lock(&dlm_reco_state_lock);
 	list_for_each_entry(node, &dlm->reco.node_data, list) {
 		switch (node->state) {
 		case DLM_RECO_NODE_DATA_INIT:
@@ -769,7 +772,7 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 				node->node_num, state);
 	}
 
-	spin_unlock(&dlm->spinlock);
+	spin_unlock(&dlm_reco_state_lock);
 
 	return out;
 }
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 9d4a2695b9594d1ad8bd60de9cec8ee701355f09..7d519e31fcf17e96116315ac33ab3f5baace354f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -80,7 +80,7 @@ static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
 
 static u64 dlm_get_next_mig_cookie(void);
 
-static DEFINE_SPINLOCK(dlm_reco_state_lock);
+DEFINE_SPINLOCK(dlm_reco_state_lock);
 static DEFINE_SPINLOCK(dlm_mig_cookie_lock);
 static u64 dlm_mig_cookie = 1;