Revert "blk-mq: remove code for dealing with remapping queue"

This reverts commit 37c7c6c76d431dd7ef9c29d95f6052bd425f004c.

Turns out some drivers(most are FC drivers) may not use managed
IRQ affinity, and has their customized .map_queues meantime, so
still keep this code for avoiding regression.

Reported-by: Laurence Oberman <loberman@redhat.com>
Tested-by: Laurence Oberman <loberman@redhat.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Stefan Haberland <sth@linux.vnet.ibm.com>
Cc: Ewan Milne <emilne@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index e4aa3681736788b8e4924805a56c885685829bff..c3621453ad87991ce712e5eadabe3ee3b98fc25b 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2336,7 +2336,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 
 static void blk_mq_map_swqueue(struct request_queue *q)
 {
-       unsigned int i;
+       unsigned int i, hctx_idx;
        struct blk_mq_hw_ctx *hctx;
        struct blk_mq_ctx *ctx;
        struct blk_mq_tag_set *set = q->tag_set;
@@ -2353,8 +2353,23 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
        /*
         * Map software to hardware queues.
+        *
+        * If the cpu isn't present, the cpu is mapped to first hctx.
         */
        for_each_possible_cpu(i) {
+               hctx_idx = q->mq_map[i];
+               /* unmapped hw queue can be remapped after CPU topo changed */
+               if (!set->tags[hctx_idx] &&
+                   !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+                       /*
+                        * If tags initialization fail for some hctx,
+                        * that hctx won't be brought online.  In this
+                        * case, remap the current ctx to hctx[0] which
+                        * is guaranteed to always have tags allocated
+                        */
+                       q->mq_map[i] = 0;
+               }
+
                ctx = per_cpu_ptr(q->queue_ctx, i);
                hctx = blk_mq_map_queue(q, i);
 
@@ -2366,8 +2381,21 @@ static void blk_mq_map_swqueue(struct request_queue *q)
        mutex_unlock(&q->sysfs_lock);
 
        queue_for_each_hw_ctx(q, hctx, i) {
-               /* every hctx should get mapped by at least one CPU */
-               WARN_ON(!hctx->nr_ctx);
+               /*
+                * If no software queues are mapped to this hardware queue,
+                * disable it and free the request entries.
+                */
+               if (!hctx->nr_ctx) {
+                       /* Never unmap queue 0.  We need it as a
+                        * fallback in case of a new remap fails
+                        * allocation
+                        */
+                       if (i && set->tags[i])
+                               blk_mq_free_map_and_requests(set, i);
+
+                       hctx->tags = NULL;
+                       continue;
+               }
 
                hctx->tags = set->tags[i];
                WARN_ON(!hctx->tags);