Merge tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - mq-deadline accounting improvements (Bart)

 - blk-wbt timer fix (Andrea)

 - Untangle the block layer includes (Christoph)

 - Rework the poll support to be bio based, which will enable adding
   support for polling for bio based drivers (Christoph)

 - Block layer core support for multi-actuator drives (Damien)

 - blk-crypto improvements (Eric)

 - Batched tag allocation support (me)

 - Request completion batching support (me)

 - Plugging improvements (me)

 - Shared tag set improvements (John)

 - Concurrent queue quiesce support (Ming)

 - Cache bdev in ->private_data for block devices (Pavel)

 - bdev dio improvements (Pavel)

 - Block device invalidation and block size improvements (Xie)

 - Various cleanups, fixes, and improvements (Christoph, Jackie,
   Masahira, Tejun, Yu, Pavel, Zheng, me)

* tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block: (174 commits)
  blk-mq-debugfs: Show active requests per queue for shared tags
  block: improve readability of blk_mq_end_request_batch()
  virtio-blk: Use blk_validate_block_size() to validate block size
  loop: Use blk_validate_block_size() to validate block size
  nbd: Use blk_validate_block_size() to validate block size
  block: Add a helper to validate the block size
  block: re-flow blk_mq_rq_ctx_init()
  block: prefetch request to be initialized
  block: pass in blk_mq_tags to blk_mq_rq_ctx_init()
  block: add rq_flags to struct blk_mq_alloc_data
  block: add async version of bio_set_polled
  block: kill DIO_MULTI_BIO
  block: kill unused polling bits in __blkdev_direct_IO()
  block: avoid extra iter advance with async iocb
  block: Add independent access ranges support
  blk-mq: don't issue request directly in case that current is to be blocked
  sbitmap: silence data race warning
  blk-cgroup: synchronize blkg creation against policy deactivation
  block: refactor bio_iov_bvec_set()
  block: add single bio async direct IO helper
  ...

1 files changed, 34 insertions, 15 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 149ecf73df38..fde36c137900 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -10,6 +10,7 @@
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-mq-pci.h>
+#include <linux/blk-integrity.h>
 #include <linux/dmi.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -958,7 +959,7 @@ out_free_cmd:
 	return ret;
 }
 
-static void nvme_pci_complete_rq(struct request *req)
+static __always_inline 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;
@@ -968,9 +969,19 @@ 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_comp_batch *iob)
+{
+	nvme_complete_batch(iob, nvme_pci_unmap_rq);
+}
+
 /* We read the CQE phase first to check if the rest of the entry is valid */
 static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
 {
@@ -995,7 +1006,8 @@ static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
 	return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
 }
 
-static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
+static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
+				   struct io_comp_batch *iob, u16 idx)
 {
 	struct nvme_completion *cqe = &nvmeq->cqes[idx];
 	__u16 command_id = READ_ONCE(cqe->command_id);
@@ -1022,7 +1034,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 	}
 
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
-	if (!nvme_try_complete_req(req, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
+	    !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
+					nvme_pci_complete_batch))
 		nvme_pci_complete_rq(req);
 }
 
@@ -1038,7 +1052,8 @@ static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
 	}
 }
 
-static inline int nvme_process_cq(struct nvme_queue *nvmeq)
+static inline int nvme_poll_cq(struct nvme_queue *nvmeq,
+			       struct io_comp_batch *iob)
 {
 	int found = 0;
 
@@ -1049,7 +1064,7 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq)
 		 * the cqe requires a full read memory barrier
 		 */
 		dma_rmb();
-		nvme_handle_cqe(nvmeq, nvmeq->cq_head);
+		nvme_handle_cqe(nvmeq, iob, nvmeq->cq_head);
 		nvme_update_cq_head(nvmeq);
 	}
 
@@ -1061,9 +1076,13 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq)
 static irqreturn_t nvme_irq(int irq, void *data)
 {
 	struct nvme_queue *nvmeq = data;
+	DEFINE_IO_COMP_BATCH(iob);
 
-	if (nvme_process_cq(nvmeq))
+	if (nvme_poll_cq(nvmeq, &iob)) {
+		if (!rq_list_empty(iob.req_list))
+			nvme_pci_complete_batch(&iob);
 		return IRQ_HANDLED;
+	}
 	return IRQ_NONE;
 }
 
@@ -1087,11 +1106,11 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
 	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
-	nvme_process_cq(nvmeq);
+	nvme_poll_cq(nvmeq, NULL);
 	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
 }
 
-static int nvme_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_queue *nvmeq = hctx->driver_data;
 	bool found;
@@ -1100,7 +1119,7 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx)
 		return 0;
 
 	spin_lock(&nvmeq->cq_poll_lock);
-	found = nvme_process_cq(nvmeq);
+	found = nvme_poll_cq(nvmeq, iob);
 	spin_unlock(&nvmeq->cq_poll_lock);
 
 	return found;
@@ -1273,7 +1292,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * Did we miss an interrupt?
 	 */
 	if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
-		nvme_poll(req->mq_hctx);
+		nvme_poll(req->mq_hctx, NULL);
 	else
 		nvme_poll_irqdisable(nvmeq);
 
@@ -1395,7 +1414,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 
 	nvmeq->dev->online_queues--;
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
-		blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
+		nvme_stop_admin_queue(&nvmeq->dev->ctrl);
 	if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags))
 		pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq);
 	return 0;
@@ -1433,7 +1452,7 @@ static void nvme_reap_pending_cqes(struct nvme_dev *dev)
 
 	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
 		spin_lock(&dev->queues[i].cq_poll_lock);
-		nvme_process_cq(&dev->queues[i]);
+		nvme_poll_cq(&dev->queues[i], NULL);
 		spin_unlock(&dev->queues[i].cq_poll_lock);
 	}
 }
@@ -1654,7 +1673,7 @@ static void nvme_dev_remove_admin(struct nvme_dev *dev)
 		 * user requests may be waiting on a stopped queue. Start the
 		 * queue to flush these to completion.
 		 */
-		blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+		nvme_start_admin_queue(&dev->ctrl);
 		blk_cleanup_queue(dev->ctrl.admin_q);
 		blk_mq_free_tag_set(&dev->admin_tagset);
 	}
@@ -1688,7 +1707,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 			return -ENODEV;
 		}
 	} else
-		blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+		nvme_start_admin_queue(&dev->ctrl);
 
 	return 0;
 }
@@ -2623,7 +2642,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	if (shutdown) {
 		nvme_start_queues(&dev->ctrl);
 		if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
-			blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+			nvme_start_admin_queue(&dev->ctrl);
 	}
 	mutex_unlock(&dev->shutdown_lock);
 }