blk-mq: fix potential stall during CPU unplug with IO pending
When a CPU is unplugged, we move the blk_mq_ctx request entries
to the current queue. The current code forgets to remap the
blk_mq_hw_ctx before marking the software context pending,
which breaks if old-cpu and new-cpu don't map to the same
hardware queue.
Additionally, if we mark entries as pending in the new
hardware queue, then make sure we schedule it for running.
Otherwise request could be sitting there until someone else
queues IO for that hardware queue.
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b1bcc61..1d2a9bd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -956,6 +956,7 @@
unsigned int cpu)
{
struct blk_mq_hw_ctx *hctx = data;
+ struct request_queue *q = hctx->queue;
struct blk_mq_ctx *ctx;
LIST_HEAD(tmp);
@@ -965,7 +966,7 @@
/*
* Move ctx entries to new CPU, if this one is going away.
*/
- ctx = __blk_mq_get_ctx(hctx->queue, cpu);
+ ctx = __blk_mq_get_ctx(q, cpu);
spin_lock(&ctx->lock);
if (!list_empty(&ctx->rq_list)) {
@@ -977,7 +978,7 @@
if (list_empty(&tmp))
return;
- ctx = blk_mq_get_ctx(hctx->queue);
+ ctx = blk_mq_get_ctx(q);
spin_lock(&ctx->lock);
while (!list_empty(&tmp)) {
@@ -988,10 +989,13 @@
list_move_tail(&rq->queuelist, &ctx->rq_list);
}
+ hctx = q->mq_ops->map_queue(q, ctx->cpu);
blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
blk_mq_put_ctx(ctx);
+
+ blk_mq_run_hw_queue(hctx, true);
}
static int blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
