nvme-pci: report the actual number of tagset maps

We've been reporting 2 maps regardless of whether the module parameter
asked for anything beyond the default queues. A consequence of this
means that blk-mq will reinitialize the all the hardware contexts and io
schedulers on every controller reset when the mapping is exactly the
same as before. This unnecessary overhead is adding several milliseconds
on a reset for environments that don't need it. Report the actual number
of mappings in use.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index e4230f2..8dd1ddd 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2526,9 +2526,11 @@ static void nvme_pci_alloc_tag_set(struct nvme_dev *dev)
 
        set->ops = &nvme_mq_ops;
        set->nr_hw_queues = dev->online_queues - 1;
-       set->nr_maps = 2; /* default + read */
+       set->nr_maps = 1;
+       if (dev->io_queues[HCTX_TYPE_READ])
+               set->nr_maps = 2;
        if (dev->io_queues[HCTX_TYPE_POLL])
-               set->nr_maps++;
+               set->nr_maps = 3;
        set->timeout = NVME_IO_TIMEOUT;
        set->numa_node = dev->ctrl.numa_node;
        set->queue_depth = min_t(unsigned, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;