Re: [PATCH 6/9] nvme: add support for batched completion of polled IO
From: John Garry <hidden>
Date: 2021-10-13 09:06:33
On 12/10/2021 19:17, Jens Axboe wrote:
quoted hunk ↗ jump to hunk
Signed-off-by: Jens Axboe<axboe@kernel.dk> --- drivers/nvme/host/pci.c | 69 +++++++++++++++++++++++++++++++++++++---- 1 file changed, 63 insertions(+), 6 deletions(-)diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4ad63bb9f415..4713da708cd4 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c@@ -959,7 +959,7 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, return ret; } -static void nvme_pci_complete_rq(struct request *req) +static void nvme_pci_unmap_rq(struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_dev *dev = iod->nvmeq->dev;@@ -969,9 +969,34 @@ static void nvme_pci_complete_rq(struct request *req) rq_integrity_vec(req)->bv_len, rq_data_dir(req)); if (blk_rq_nr_phys_segments(req)) nvme_unmap_data(dev, req); +} + +static void nvme_pci_complete_rq(struct request *req) +{ + nvme_pci_unmap_rq(req); nvme_complete_rq(req); } +static void nvme_pci_complete_batch(struct io_batch *ib) +{ + struct request *req; + + req = ib->req_list; + while (req) { + nvme_pci_unmap_rq(req);
This will do the DMA SG unmap per request. Often this is a performance bottle neck when we have an IOMMU enabled in strict mode. So since we complete in batches, could we combine all the SGs in the batch to do one big DMA unmap SG, and not one-by-one? Just a thought.
+ if (req->rq_flags & RQF_SPECIAL_PAYLOAD) + nvme_cleanup_cmd(req); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + req_op(req) == REQ_OP_ZONE_APPEND) + req->__sector = nvme_lba_to_sect(req->q->queuedata, + le64_to_cpu(nvme_req(req)->result.u64)); + req->status = nvme_error_status(nvme_req(req)->status); + req = req->rq_next; + } + + blk_mq_end_request_batch(ib); +}