This is a note to let you know that I've just added the patch titled
RDMA/mlx5: Fix mkey cache possible deadlock on cleanup
to the 6.5-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
rdma-mlx5-fix-mkey-cache-possible-deadlock-on-cleanup.patch
and it can be found in the queue-6.5 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 374012b0045780b7ad498be62e85153009bb7fe9 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@xxxxxxxxxx>
Date: Tue, 12 Sep 2023 13:07:45 +0300
Subject: RDMA/mlx5: Fix mkey cache possible deadlock on cleanup
From: Shay Drory <shayd@xxxxxxxxxx>
commit 374012b0045780b7ad498be62e85153009bb7fe9 upstream.
Fix the deadlock by refactoring the MR cache cleanup flow to flush the
workqueue without holding the rb_lock.
This adds a race between cache cleanup and creation of new entries which
we solve by denied creation of new entries after cache cleanup started.
Lockdep:
WARNING: possible circular locking dependency detected
[ 2785.326074 ] 6.2.0-rc6_for_upstream_debug_2023_01_31_14_02 #1 Not tainted
[ 2785.339778 ] ------------------------------------------------------
[ 2785.340848 ] devlink/53872 is trying to acquire lock:
[ 2785.341701 ] ffff888124f8c0c8 ((work_completion)(&(&ent->dwork)->work)){+.+.}-{0:0}, at: __flush_work+0xc8/0x900
[ 2785.343403 ]
[ 2785.343403 ] but task is already holding lock:
[ 2785.344464 ] ffff88817e8f1260 (&dev->cache.rb_lock){+.+.}-{3:3}, at: mlx5_mkey_cache_cleanup+0x77/0x250 [mlx5_ib]
[ 2785.346273 ]
[ 2785.346273 ] which lock already depends on the new lock.
[ 2785.346273 ]
[ 2785.347720 ]
[ 2785.347720 ] the existing dependency chain (in reverse order) is:
[ 2785.349003 ]
[ 2785.349003 ] -> #1 (&dev->cache.rb_lock){+.+.}-{3:3}:
[ 2785.350160 ] __mutex_lock+0x14c/0x15c0
[ 2785.350962 ] delayed_cache_work_func+0x2d1/0x610 [mlx5_ib]
[ 2785.352044 ] process_one_work+0x7c2/0x1310
[ 2785.352879 ] worker_thread+0x59d/0xec0
[ 2785.353636 ] kthread+0x28f/0x330
[ 2785.354370 ] ret_from_fork+0x1f/0x30
[ 2785.355135 ]
[ 2785.355135 ] -> #0 ((work_completion)(&(&ent->dwork)->work)){+.+.}-{0:0}:
[ 2785.356515 ] __lock_acquire+0x2d8a/0x5fe0
[ 2785.357349 ] lock_acquire+0x1c1/0x540
[ 2785.358121 ] __flush_work+0xe8/0x900
[ 2785.358852 ] __cancel_work_timer+0x2c7/0x3f0
[ 2785.359711 ] mlx5_mkey_cache_cleanup+0xfb/0x250 [mlx5_ib]
[ 2785.360781 ] mlx5_ib_stage_pre_ib_reg_umr_cleanup+0x16/0x30 [mlx5_ib]
[ 2785.361969 ] __mlx5_ib_remove+0x68/0x120 [mlx5_ib]
[ 2785.362960 ] mlx5r_remove+0x63/0x80 [mlx5_ib]
[ 2785.363870 ] auxiliary_bus_remove+0x52/0x70
[ 2785.364715 ] device_release_driver_internal+0x3c1/0x600
[ 2785.365695 ] bus_remove_device+0x2a5/0x560
[ 2785.366525 ] device_del+0x492/0xb80
[ 2785.367276 ] mlx5_detach_device+0x1a9/0x360 [mlx5_core]
[ 2785.368615 ] mlx5_unload_one_devl_locked+0x5a/0x110 [mlx5_core]
[ 2785.369934 ] mlx5_devlink_reload_down+0x292/0x580 [mlx5_core]
[ 2785.371292 ] devlink_reload+0x439/0x590
[ 2785.372075 ] devlink_nl_cmd_reload+0xaef/0xff0
[ 2785.372973 ] genl_family_rcv_msg_doit.isra.0+0x1bd/0x290
[ 2785.374011 ] genl_rcv_msg+0x3ca/0x6c0
[ 2785.374798 ] netlink_rcv_skb+0x12c/0x360
[ 2785.375612 ] genl_rcv+0x24/0x40
[ 2785.376295 ] netlink_unicast+0x438/0x710
[ 2785.377121 ] netlink_sendmsg+0x7a1/0xca0
[ 2785.377926 ] sock_sendmsg+0xc5/0x190
[ 2785.378668 ] __sys_sendto+0x1bc/0x290
[ 2785.379440 ] __x64_sys_sendto+0xdc/0x1b0
[ 2785.380255 ] do_syscall_64+0x3d/0x90
[ 2785.381031 ] entry_SYSCALL_64_after_hwframe+0x46/0xb0
[ 2785.381967 ]
[ 2785.381967 ] other info that might help us debug this:
[ 2785.381967 ]
[ 2785.383448 ] Possible unsafe locking scenario:
[ 2785.383448 ]
[ 2785.384544 ] CPU0 CPU1
[ 2785.385383 ] ---- ----
[ 2785.386193 ] lock(&dev->cache.rb_lock);
[ 2785.386940 ] lock((work_completion)(&(&ent->dwork)->work));
[ 2785.388327 ] lock(&dev->cache.rb_lock);
[ 2785.389425 ] lock((work_completion)(&(&ent->dwork)->work));
[ 2785.390414 ]
[ 2785.390414 ] *** DEADLOCK ***
[ 2785.390414 ]
[ 2785.391579 ] 6 locks held by devlink/53872:
[ 2785.392341 ] #0: ffffffff84c17a50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40
[ 2785.393630 ] #1: ffff888142280218 (&devlink->lock_key){+.+.}-{3:3}, at: devlink_get_from_attrs_lock+0x12d/0x2d0
[ 2785.395324 ] #2: ffff8881422d3c38 (&dev->lock_key){+.+.}-{3:3}, at: mlx5_unload_one_devl_locked+0x4a/0x110 [mlx5_core]
[ 2785.397322 ] #3: ffffffffa0e59068 (mlx5_intf_mutex){+.+.}-{3:3}, at: mlx5_detach_device+0x60/0x360 [mlx5_core]
[ 2785.399231 ] #4: ffff88810e3cb0e8 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x8d/0x600
[ 2785.400864 ] #5: ffff88817e8f1260 (&dev->cache.rb_lock){+.+.}-{3:3}, at: mlx5_mkey_cache_cleanup+0x77/0x250 [mlx5_ib]
Fixes: b95845178328 ("RDMA/mlx5: Change the cache structure to an RB-tree")
Signed-off-by: Shay Drory <shayd@xxxxxxxxxx>
Signed-off-by: Michael Guralnik <michaelgur@xxxxxxxxxx>
Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 +
drivers/infiniband/hw/mlx5/mr.c | 16 ++++++++++++++--
2 files changed, 15 insertions(+), 2 deletions(-)
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -797,6 +797,7 @@ struct mlx5_mkey_cache {
struct dentry *fs_root;
unsigned long last_add;
struct delayed_work remove_ent_dwork;
+ u8 disable: 1;
};
struct mlx5_ib_port_resources {
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1024,19 +1024,27 @@ void mlx5_mkey_cache_cleanup(struct mlx5
if (!dev->cache.wq)
return;
- cancel_delayed_work_sync(&dev->cache.remove_ent_dwork);
mutex_lock(&dev->cache.rb_lock);
+ dev->cache.disable = true;
for (node = rb_first(root); node; node = rb_next(node)) {
ent = rb_entry(node, struct mlx5_cache_ent, node);
xa_lock_irq(&ent->mkeys);
ent->disabled = true;
xa_unlock_irq(&ent->mkeys);
- cancel_delayed_work_sync(&ent->dwork);
}
+ mutex_unlock(&dev->cache.rb_lock);
+
+ /*
+ * After all entries are disabled and will not reschedule on WQ,
+ * flush it and all async commands.
+ */
+ flush_workqueue(dev->cache.wq);
mlx5_mkey_cache_debugfs_cleanup(dev);
mlx5_cmd_cleanup_async_ctx(&dev->async_ctx);
+ /* At this point all entries are disabled and have no concurrent work. */
+ mutex_lock(&dev->cache.rb_lock);
node = rb_first(root);
while (node) {
ent = rb_entry(node, struct mlx5_cache_ent, node);
@@ -1815,6 +1823,10 @@ static int cache_ent_find_and_store(stru
}
mutex_lock(&cache->rb_lock);
+ if (cache->disable) {
+ mutex_unlock(&cache->rb_lock);
+ return 0;
+ }
ent = mkey_cache_ent_from_rb_key(dev, mr->mmkey.rb_key);
if (ent) {
if (ent->rb_key.ndescs == mr->mmkey.rb_key.ndescs) {
Patches currently in stable-queue which might be from shayd@xxxxxxxxxx are
queue-6.5/rdma-mlx5-fix-null-string-error.patch
queue-6.5/rdma-mlx5-fix-mkey-cache-possible-deadlock-on-cleanup.patch
