Re: [RFC PATCH] sbitmap: fix io hung due to race on sbitmap_word::cleared

From: YangYang
Date: Wed May 29 2024 - 06:31:34 EST


On 2024/5/27 12:26, Yang Yang wrote:
Configuration for sbq:
depth=64, wake_batch=6, shift=6, map_nr=1

1. There are 64 requests in progress:
map->word = 0xFFFFFFFFFFFFFFFF
2. After all the 64 requests complete, and no more requests come:
map->word = 0xFFFFFFFFFFFFFFFF, map->cleared = 0xFFFFFFFFFFFFFFFF
3. Now two tasks try to allocate requests:
T1: T2:
__blk_mq_get_tag .
__sbitmap_queue_get .
sbitmap_get .
sbitmap_find_bit .
sbitmap_find_bit_in_word .
__sbitmap_get_word -> nr=-1 __blk_mq_get_tag
sbitmap_deferred_clear __sbitmap_queue_get
/* map->cleared=0xFFFFFFFFFFFFFFFF */ sbitmap_find_bit
if (!READ_ONCE(map->cleared)) sbitmap_find_bit_in_word
return false; __sbitmap_get_word -> nr=-1
mask = xchg(&map->cleared, 0) sbitmap_deferred_clear
atomic_long_andnot() /* map->cleared=0 */
if (!(map->cleared))
return false;
/*
* map->cleared is cleared by T1
* T2 fail to acquire the tag
*/

4. T2 is the sole tag waiter. When T1 puts the tag, T2 cannot be woken
up due to the wake_batch being set at 6. If no more requests come, T1
will wait here indefinitely.

Right at this moment, if a new task attempts to switch the elevator, these
tasks may hang forever.

T2: T3: T4:
blk_mq_submit_bio . .
__blk_mq_alloc_requests . .
blk_mq_get_tag . .
io_schedule . .
elevator_switch .
blk_mq_freeze_queue .
blk_freeze_queue_start .
q->mq_freeze_depth=1 .
blk_mq_freeze_queue_wait .
blk_mq_submit_bio
__bio_queue_enter
wait_event(!q->mq_freeze_depth)


Fix this issue by adding a new flag swap_inprogress to indicate whether
the swap is ongoing.

Fixes: 661d4f55a794 ("sbitmap: remove swap_lock")
Signed-off-by: Yang Yang <yang.yang@xxxxxxxx>
---
include/linux/sbitmap.h | 5 +++++
lib/sbitmap.c | 22 ++++++++++++++++++++--
2 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index d662cf136021..b88a9e4997ab 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -36,6 +36,11 @@ struct sbitmap_word {
* @cleared: word holding cleared bits
*/
unsigned long cleared ____cacheline_aligned_in_smp;
+
+ /**
+ * @swap_inprogress: set to 1 when swapping word <-> cleared
+ */
+ atomic_t swap_inprogress;
} ____cacheline_aligned_in_smp;
/**
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 1e453f825c05..d4bb258fe8b0 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -62,10 +62,19 @@ static inline void update_alloc_hint_after_get(struct sbitmap *sb,
*/
static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
{
- unsigned long mask;
+ unsigned long mask, flags;
+ int zero = 0;
- if (!READ_ONCE(map->cleared))
+ if (!READ_ONCE(map->cleared)) {
+ if (atomic_read(&map->swap_inprogress))
+ goto out_wait;
return false;
+ }
+
+ if (!atomic_try_cmpxchg(&map->swap_inprogress, &zero, 1))
+ goto out_wait;
+
+ local_irq_save(flags);
/*
* First get a stable cleared mask, setting the old mask to 0.
@@ -77,6 +86,15 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
*/
atomic_long_andnot(mask, (atomic_long_t *)&map->word);
BUILD_BUG_ON(sizeof(atomic_long_t) != sizeof(map->word));
+
+ atomic_set(&map->swap_inprogress, 0);
+ smp_mb__after_atomic();
+ local_irq_restore(flags);
+ return true;
+
+out_wait:
+ while (atomic_read(&map->swap_inprogress))
+ ;
return true;
}