ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown.patch removed from -mm tree
The quilt patch titled
Subject: ocfs2: synchronize heartbeat callbacks with o2net teardown
has been removed from the -mm tree. Its filename was
ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown.patch
This patch was dropped because it was merged into the mm-nonmm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Cen Zhang <[email protected]>
Subject: ocfs2: synchronize heartbeat callbacks with o2net teardown
Date: Wed, 24 Jun 2026 17:53:09 +0800
Patch series "ocfs2: harden heartbeat teardown races".
This series fixes two OCFS2 heartbeat/o2net teardown races found by KASAN.
This patch (of 2):
Heartbeat callbacks stay registered while configfs local-node teardown enters o2net_stop_listening(). A node-down event can still run through o2net_disconnect_node() and o2net_set_nn_state() while teardown is destroying o2net_wq, so the later queue/flush operations can hit a dead workqueue. KASAN has caught this as a slab-use-after-free in __queue_work() with the call chain:
KASAN slab-use-after-free in __queue_work+0x56/0xa90
Read of size 4 Call trace: dump_stack_lvl+0x66/0xa0 print_report+0xce/0x630 __queue_work+0x56/0xa90 srso_alias_return_thunk+0x5/0xfbef5 __virt_addr_valid+0x19f/0x330 kasan_report+0xe0/0x110 __queue_delayed_work+0x58/0x1e0 queue_delayed_work_on+0xb4/0xc0 o2net_set_nn_state+0x467/0x840 o2net_disconnect_node+0x7b/0xe0 o2net_hb_node_down_cb+0x54/0x60 o2hb_run_event_list+0x236/0x2d0 o2hb_check_slot+0xad4/0xbc0 lock_release+0xc8/0x290 o2hb_check_slot+0x9ea/0xbc0 trace_hardirqs_on+0x18/0x130 o2hb_do_disk_heartbeat+0x646/0xb30 (fs/ocfs2/cluster/heartbeat.c:1079) __lock_acquire+0x466/0x2260 lockdep_hardirqs_on_prepare+0xea/0x1a0 ktime_get_with_offset+0xe9/0x230 o2hb_thread+0x14e/0x770 kthread+0x1ad/0x1f0 ret_from_fork+0x3c9/0x540 __switch_to+0x2e9/0x730 ret_from_fork_asm+0x1a/0x30 Allocated by task stack: kasan_save_stack+0x33/0x60 kasan_save_track+0x14/0x30 __kasan_kmalloc+0xaa/0xb0 __kmalloc_noprof+0x292/0x760 __alloc_workqueue+0x736/0xc60 alloc_workqueue_noprof+0xb1/0x110 o2net_start_listening+0xe5/0x430 o2nm_node_local_store+0x184/0x310 configfs_write_iter+0x18a/0x210 vfs_write+0x469/0x810 ksys_write+0xd2/0x170 do_syscall_64+0x115/0x6a0 (arch/x86/entry/syscall_64.c:87) entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task stack: kasan_save_stack+0x33/0x60 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x5f/0x80 kfree+0x313/0x590 rcu_core+0x4f4/0x1320 handle_softirqs+0x156/0x660
queue_delayed_work_ono2net_set_nn_stateo2net_disconnect_nodeo2net_hb_node_down_cbo2hb_run_event_list
Keep heartbeat callbacks registered so quorum state still tracks node state, but stop them from driving o2net reconnect/disconnect work once local teardown starts. Mark the transport offline before destroying o2net_wq, wait for any in-flight heartbeat callback to finish, and delay bring-up replay until the new local node is published through o2nm_this_node().
The replay also has to stay serialized with heartbeat callback delivery. Otherwise a live-node snapshot can be copied, a real hb_down callback can install -ENOTCONN for a peer, and the stale replay can call o2net_hb_node_up() for that same peer and queue reconnect work even though heartbeat is already down.
The buggy scenario involves two paths, with each column showing the order within that path:
local-node teardown: heartbeat node-down callback:
1. configfs local-off enters 1. o2hb_run_event_list() invokes
o2net_stop_listening(). o2net_hb_node_down_cb().
2. teardown heads for 2. the callback reaches
destroy_workqueue(o2net_wq). o2net_disconnect_node() and
o2net_set_nn_state().
3. teardown destroys and NULLs 3. the callback flushes or queues
o2net_wq. work through o2net_wq.
---
fs/ocfs2/cluster/heartbeat.c | 43 ++++++++++++---- fs/ocfs2/cluster/heartbeat.h | 5 + fs/ocfs2/cluster/nodemanager.c | 4 + fs/ocfs2/cluster/tcp.c | 83 ++++++++++++++++++++++++------- fs/ocfs2/cluster/tcp.h | 1 5 files changed, 109 insertions(+), 27 deletions(-)
fs/ocfs2/cluster/heartbeat.c renamed from fs/ocfs2/cluster/heartbeat.c~ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown +33 -10
@@ -1492,13 +1492,38 @@ void o2hb_init(void)o2hb_debug_init (); } -/* if we're already in a callback then we're already serialized by the sem */ -static void o2hb_fill_node_map_from_callback (unsigned long *map, -unsigned int bits) +static void __o2hb_fill_node_map (unsigned long *map,unsigned int bits) {bitmap_copy (map, o2hb_live_node_bitmap, bits); } +void o2hb_callback_read_lock (void ) +{ +down_read (&o2hb_callback_sem); +} + +void o2hb_callback_read_unlock (void ) +{ +up_read (&o2hb_callback_sem); +} + +void o2hb_synchronize_callbacks (void ) +{ +down_write (&o2hb_callback_sem); +up_write (&o2hb_callback_sem); +} + +/* +* Callers must already hold o2hb_callback_sem for read or write so the copy +* stays serialized with callback delivery. +*/ +void o2hb_fill_node_map_locked (unsigned long *map,unsigned int bits) +{ +spin_lock (&o2hb_live_lock); +__o2hb_fill_node_map (map, bits); +spin_unlock (&o2hb_live_lock); +} +/* * get a map of all nodes that are heartbeating in any regions */
@@ -1506,11 +1531,9 @@ void o2hb_fill_node_map(unsigned long *m {/* callers want to serialize this map and callbacks so that they * can trust that they don't miss nodes coming to the party */ -down_read (&o2hb_callback_sem); -spin_lock (&o2hb_live_lock); -o2hb_fill_node_map_from_callback (map, bits); -spin_unlock (&o2hb_live_lock); -up_read (&o2hb_callback_sem); +o2hb_callback_read_lock (); +o2hb_fill_node_map_locked (map, bits); +o2hb_callback_read_unlock (); }EXPORT_SYMBOL_GPL (o2hb_fill_node_map);
@@ -2609,7 +2632,7 @@ int o2hb_check_node_heartbeating_no_sem(unsigned long testing_map[BITS_TO_LONGS (O2NM_MAX_NODES )];spin_lock (&o2hb_live_lock); -o2hb_fill_node_map_from_callback (testing_map,O2NM_MAX_NODES ); +__o2hb_fill_node_map (testing_map,O2NM_MAX_NODES );spin_unlock (&o2hb_live_lock);if (!test_bit (node_num, testing_map)) { mlog(ML_HEARTBEAT,
@@ -2626,7 +2649,7 @@ int o2hb_check_node_heartbeating_from_ca {unsigned long testing_map[BITS_TO_LONGS (O2NM_MAX_NODES )]; -o2hb_fill_node_map_from_callback (testing_map,O2NM_MAX_NODES ); +o2hb_fill_node_map_locked (testing_map,O2NM_MAX_NODES );if (!test_bit (node_num, testing_map)) { mlog(ML_HEARTBEAT, "node (%u) does not have heartbeating enabled.\n",
fs/ocfs2/cluster/heartbeat.h renamed from fs/ocfs2/cluster/heartbeat.h~ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown +5 -0
@@ -58,6 +58,11 @@ int o2hb_register_callback(const char *r struct o2hb_callback_func *hc);void o2hb_unregister_callback (const char *region_uuid,struct o2hb_callback_func *hc); +void o2hb_callback_read_lock (void ); +void o2hb_callback_read_unlock (void ); +void o2hb_synchronize_callbacks (void ); +void o2hb_fill_node_map_locked (unsigned long *map, +unsigned int bits);void o2hb_fill_node_map (unsigned long *map,unsigned int bits);void o2hb_exit (void );
fs/ocfs2/cluster/nodemanager.c renamed from fs/ocfs2/cluster/nodemanager.c~ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown +4 -0
@@ -326,6 +326,7 @@ static ssize_t o2nm_node_local_store(strstruct o2nm_node *node =to_o2nm_node (item);struct o2nm_cluster *cluster;unsigned long tmp; +bool starting = false;char *p = (char *)page;ssize_t ret;
@@ -362,6 +363,7 @@ static ssize_t o2nm_node_local_store(str ret =o2net_start_listening (node);if (ret) goto out; + starting = true; } if (!tmp && cluster->cl_has_local &&
@@ -375,6 +377,8 @@ static ssize_t o2nm_node_local_store(strif (node->nd_local) { cluster->cl_has_local = tmp; cluster->cl_local_node = node->nd_num; +if (starting) +o2net_complete_start_listening (node); } ret = count;
fs/ocfs2/cluster/tcp.c renamed from fs/ocfs2/cluster/tcp.c~ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown +66 -17
137 lines not on this page · raw message
fs/ocfs2/cluster/tcp.h renamed from fs/ocfs2/cluster/tcp.h~ocfs2-synchronize-heartbeat-callbacks-with-o2net-teardown +1 -0
@@ -96,6 +96,7 @@ struct o2nm_node;int o2net_register_hb_callbacks (void );void o2net_unregister_hb_callbacks (void );int o2net_start_listening (struct o2nm_node *node); +void o2net_complete_start_listening (struct o2nm_node *node);void o2net_stop_listening (struct o2nm_node *node);void o2net_disconnect_node (struct o2nm_node *node);int o2net_num_connected_peers (void );
_
Patches currently in -mm which might be from [email protected] are