diff options
author | John Garry <john.garry@huawei.com> | 2020-08-19 23:20:24 +0800 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2020-09-03 15:20:47 -0600 |
commit | 32bc15afed04bd73e29d713d8db47818d6aa89af (patch) | |
tree | 5b7c59ec86d31c5b17a400dd8e5bd26445b7e33b /block/blk-mq-tag.c | |
parent | 222a5ae03cdd12e7643f2f64689a39ed547650cb (diff) | |
download | linux-32bc15afed04bd73e29d713d8db47818d6aa89af.tar.bz2 |
blk-mq: Facilitate a shared sbitmap per tagset
Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support
multiple reply queues with single hostwide tags.
In addition, these drivers want to use interrupt assignment in
pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0],
CPU hotplug may cause in-flight IO completion to not be serviced when an
interrupt is shutdown. That problem is solved in commit bf0beec0607d
("blk-mq: drain I/O when all CPUs in a hctx are offline").
However, to take advantage of that blk-mq feature, the HBA HW queuess are
required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW
queues need to be exposed to the upper layer.
In making that transition, the per-SCSI command request tags are no
longer unique per Scsi host - they are just unique per hctx. As such, the
HBA LLDD would have to generate this tag internally, which has a certain
performance overhead.
However another problem is that blk-mq assumes the host may accept
(Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi:
core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy
counter was removed, which would stop the LLDD being sent more than
.can_queue commands; however, it should still be ensured that the block
layer does not issue more than .can_queue commands to the Scsi host.
To solve this problem, introduce a shared sbitmap per blk_mq_tag_set,
which may be requested at init time.
New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the
tagset to indicate whether the shared sbitmap should be used.
Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests
are still allocated per hctx; the reason for this is that if tags and
requests were only allocated for a single hctx - like hctx0 - it may break
block drivers which expect a request be associated with a specific hctx,
i.e. not always hctx0. This will introduce extra memory usage.
This change is based on work originally from Ming Lei in [1] and from
Bart's suggestion in [2].
[0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/
[1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/
[2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-mq-tag.c')
-rw-r--r-- | block/blk-mq-tag.c | 51 |
1 files changed, 47 insertions, 4 deletions
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 77fbeae05745..c6d7ebc62bdb 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -197,7 +197,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (rq && rq->q == hctx->queue) + if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx) return iter_data->fn(hctx, rq, iter_data->data, reserved); return true; } @@ -450,6 +450,38 @@ free_bitmap_tags: return -ENOMEM; } +int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) +{ + unsigned int depth = set->queue_depth - set->reserved_tags; + int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); + bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; + int i, node = set->numa_node; + + if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node)) + return -ENOMEM; + if (bt_alloc(&set->__breserved_tags, set->reserved_tags, + round_robin, node)) + goto free_bitmap_tags; + + for (i = 0; i < set->nr_hw_queues; i++) { + struct blk_mq_tags *tags = set->tags[i]; + + tags->bitmap_tags = &set->__bitmap_tags; + tags->breserved_tags = &set->__breserved_tags; + } + + return 0; +free_bitmap_tags: + sbitmap_queue_free(&set->__bitmap_tags); + return -ENOMEM; +} + +void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) +{ + sbitmap_queue_free(&set->__bitmap_tags); + sbitmap_queue_free(&set->__breserved_tags); +} + struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, int node, unsigned int flags) @@ -469,6 +501,9 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + if (flags & BLK_MQ_F_TAG_HCTX_SHARED) + return tags; + if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) { kfree(tags); return NULL; @@ -478,8 +513,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags) { - sbitmap_queue_free(&tags->__bitmap_tags); - sbitmap_queue_free(&tags->__breserved_tags); + if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) { + sbitmap_queue_free(tags->bitmap_tags); + sbitmap_queue_free(tags->breserved_tags); + } kfree(tags); } @@ -498,7 +535,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; - unsigned int flags = set->flags; + /* Only sched tags can grow, so clear HCTX_SHARED flag */ + unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; struct blk_mq_tags *new; bool ret; @@ -537,6 +575,11 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, return 0; } +void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) +{ + sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags); +} + /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag |