blk-mq: make blk_mq_alloc_request_hctx() allocate a scheduler request

blk_mq_alloc_request_hctx() allocates a driver request directly, unlike
its blk_mq_alloc_request() counterpart. It also crashes because it
doesn't update the tags->rqs map.

Fix it by making it allocate a scheduler request.

Reported-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-by: Sagi Grimberg <sagi@grimberg.me>

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 46ca965..5697b23 100644 (file)
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -110,15 +110,14 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
                                         struct blk_mq_alloc_data *data)
 {
        struct elevator_queue *e = q->elevator;
-       struct blk_mq_hw_ctx *hctx;
-       struct blk_mq_ctx *ctx;
        struct request *rq;
 
        blk_queue_enter_live(q);
-       ctx = blk_mq_get_ctx(q);
-       hctx = blk_mq_map_queue(q, ctx->cpu);
-
-       blk_mq_set_alloc_data(data, q, data->flags, ctx, hctx);
+       data->q = q;
+       if (likely(!data->ctx))
+               data->ctx = blk_mq_get_ctx(q);
+       if (likely(!data->hctx))
+               data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 
        if (e) {
                data->flags |= BLK_MQ_REQ_INTERNAL;

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4df5fb4..85a7047 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -273,10 +273,9 @@ EXPORT_SYMBOL(blk_mq_alloc_request);
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
                unsigned int flags, unsigned int hctx_idx)
 {
-       struct blk_mq_hw_ctx *hctx;
-       struct blk_mq_ctx *ctx;
+       struct blk_mq_alloc_data alloc_data = { .flags = flags };
        struct request *rq;
-       struct blk_mq_alloc_data alloc_data;
+       unsigned int cpu;
        int ret;
 
        /*
@@ -299,25 +298,23 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
         * Check if the hardware context is actually mapped to anything.
         * If not tell the caller that it should skip this queue.
         */
-       hctx = q->queue_hw_ctx[hctx_idx];
-       if (!blk_mq_hw_queue_mapped(hctx)) {
-               ret = -EXDEV;
-               goto out_queue_exit;
+       alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
+       if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
+               blk_queue_exit(q);
+               return ERR_PTR(-EXDEV);
        }
-       ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
+       cpu = cpumask_first(alloc_data.hctx->cpumask);
+       alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
-       blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-       rq = __blk_mq_alloc_request(&alloc_data, rw);
-       if (!rq) {
-               ret = -EWOULDBLOCK;
-               goto out_queue_exit;
-       }
-
-       return rq;
+       rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
 
-out_queue_exit:
+       blk_mq_put_ctx(alloc_data.ctx);
        blk_queue_exit(q);
-       return ERR_PTR(ret);
+
+       if (!rq)
+               return ERR_PTR(-EWOULDBLOCK);
+
+       return rq;
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);