85 lines
3.2 KiB
Diff
85 lines
3.2 KiB
Diff
From 31dab97ff138fe413355fcf23f5d72149243e0fa Mon Sep 17 00:00:00 2001
|
|
Message-Id: <31dab97ff138fe413355fcf23f5d72149243e0fa.1601675152.git.zanussi@kernel.org>
|
|
In-Reply-To: <5b5a156f9808b1acf1205606e03da117214549ea.1601675151.git.zanussi@kernel.org>
|
|
References: <5b5a156f9808b1acf1205606e03da117214549ea.1601675151.git.zanussi@kernel.org>
|
|
From: Mikulas Patocka <mpatocka@redhat.com>
|
|
Date: Mon, 13 Nov 2017 12:56:53 -0500
|
|
Subject: [PATCH 150/333] locking/rt-mutex: fix deadlock in device mapper /
|
|
block-IO
|
|
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.148-rt64.tar.xz
|
|
|
|
When some block device driver creates a bio and submits it to another
|
|
block device driver, the bio is added to current->bio_list (in order to
|
|
avoid unbounded recursion).
|
|
|
|
However, this queuing of bios can cause deadlocks, in order to avoid them,
|
|
device mapper registers a function flush_current_bio_list. This function
|
|
is called when device mapper driver blocks. It redirects bios queued on
|
|
current->bio_list to helper workqueues, so that these bios can proceed
|
|
even if the driver is blocked.
|
|
|
|
The problem with CONFIG_PREEMPT_RT_FULL is that when the device mapper
|
|
driver blocks, it won't call flush_current_bio_list (because
|
|
tsk_is_pi_blocked returns true in sched_submit_work), so deadlocks in
|
|
block device stack can happen.
|
|
|
|
Note that we can't call blk_schedule_flush_plug if tsk_is_pi_blocked
|
|
returns true - that would cause
|
|
BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in
|
|
task_blocks_on_rt_mutex when flush_current_bio_list attempts to take a
|
|
spinlock.
|
|
|
|
So the proper fix is to call blk_schedule_flush_plug in rt_mutex_fastlock,
|
|
when fast acquire failed and when the task is about to block.
|
|
|
|
CC: stable-rt@vger.kernel.org
|
|
[bigeasy: The deadlock is not device-mapper specific, it can also occur
|
|
in plain EXT4]
|
|
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
|
|
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
|
|
---
|
|
kernel/locking/rtmutex.c | 13 +++++++++++++
|
|
1 file changed, 13 insertions(+)
|
|
|
|
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
|
|
index 1f2dc2dfe2e7..b38c3a92dce8 100644
|
|
--- a/kernel/locking/rtmutex.c
|
|
+++ b/kernel/locking/rtmutex.c
|
|
@@ -24,6 +24,7 @@
|
|
#include <linux/sched/debug.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/ww_mutex.h>
|
|
+#include <linux/blkdev.h>
|
|
|
|
#include "rtmutex_common.h"
|
|
|
|
@@ -1919,6 +1920,15 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state,
|
|
if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
|
|
return 0;
|
|
|
|
+ /*
|
|
+ * If rt_mutex blocks, the function sched_submit_work will not call
|
|
+ * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true).
|
|
+ * We must call blk_schedule_flush_plug here, if we don't call it,
|
|
+ * a deadlock in I/O may happen.
|
|
+ */
|
|
+ if (unlikely(blk_needs_flush_plug(current)))
|
|
+ blk_schedule_flush_plug(current);
|
|
+
|
|
return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx);
|
|
}
|
|
|
|
@@ -1936,6 +1946,9 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
|
|
likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
|
|
return 0;
|
|
|
|
+ if (unlikely(blk_needs_flush_plug(current)))
|
|
+ blk_schedule_flush_plug(current);
|
|
+
|
|
return slowfn(lock, state, timeout, chwalk, ww_ctx);
|
|
}
|
|
|
|
--
|
|
2.17.1
|
|
|