From 50a212ec906f7524620675f0c57357691c26c81f Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 16 Oct 2024 01:20:19 +0000
Subject: [PATCH] 修改GPIO导出默认初始值

---
 kernel/drivers/nvme/host/pci.c | 1733 ++++++++++++++++++++++++++++++++++++++--------------------
 1 files changed, 1,130 insertions(+), 603 deletions(-)

diff --git a/kernel/drivers/nvme/host/pci.c b/kernel/drivers/nvme/host/pci.c
index d7cf320..7afdab8 100644
--- a/kernel/drivers/nvme/host/pci.c
+++ b/kernel/drivers/nvme/host/pci.c
@@ -1,17 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * NVM Express device driver
  * Copyright (c) 2011-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
+#include <linux/acpi.h>
 #include <linux/aer.h>
 #include <linux/async.h>
 #include <linux/blkdev.h>
@@ -26,17 +19,21 @@
 #include <linux/mutex.h>
 #include <linux/once.h>
 #include <linux/pci.h>
+#include <linux/suspend.h>
 #include <linux/t10-pi.h>
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/sed-opal.h>
+#include <linux/pci-p2pdma.h>
 
+#include "trace.h"
 #include "nvme.h"
 
-#define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
-#define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
+#define SQ_SIZE(q)	((q)->q_depth << (q)->sqes)
+#define CQ_SIZE(q)	((q)->q_depth * sizeof(struct nvme_completion))
 
-#define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+#define SGES_PER_PAGE	(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
 
 /*
  * These can be higher, but we need to ensure that any command doesn't
@@ -66,17 +63,48 @@
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
 static const struct kernel_param_ops io_queue_depth_ops = {
 	.set = io_queue_depth_set,
-	.get = param_get_int,
+	.get = param_get_uint,
 };
 
-static int io_queue_depth = 1024;
+static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
+
+static int io_queue_count_set(const char *val, const struct kernel_param *kp)
+{
+	unsigned int n;
+	int ret;
+
+	ret = kstrtouint(val, 10, &n);
+	if (ret != 0 || n > num_possible_cpus())
+		return -EINVAL;
+	return param_set_uint(val, kp);
+}
+
+static const struct kernel_param_ops io_queue_count_ops = {
+	.set = io_queue_count_set,
+	.get = param_get_uint,
+};
+
+static unsigned int write_queues;
+module_param_cb(write_queues, &io_queue_count_ops, &write_queues, 0644);
+MODULE_PARM_DESC(write_queues,
+	"Number of queues to use for writes. If not set, reads and writes "
+	"will share a queue set.");
+
+static unsigned int poll_queues;
+module_param_cb(poll_queues, &io_queue_count_ops, &poll_queues, 0644);
+MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO.");
+
+static bool noacpi;
+module_param(noacpi, bool, 0444);
+MODULE_PARM_DESC(noacpi, "disable acpi bios quirks");
 
 struct nvme_dev;
 struct nvme_queue;
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
+static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode);
 
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
@@ -91,28 +119,29 @@
 	struct dma_pool *prp_small_pool;
 	unsigned online_queues;
 	unsigned max_qid;
+	unsigned io_queues[HCTX_MAX_TYPES];
 	unsigned int num_vecs;
-	int q_depth;
+	u32 q_depth;
+	int io_sqes;
 	u32 db_stride;
 	void __iomem *bar;
 	unsigned long bar_mapped_size;
 	struct work_struct remove_work;
 	struct mutex shutdown_lock;
 	bool subsystem;
-	void __iomem *cmb;
-	pci_bus_addr_t cmb_bus_addr;
 	u64 cmb_size;
+	bool cmb_use_sqes;
 	u32 cmbsz;
 	u32 cmbloc;
 	struct nvme_ctrl ctrl;
-	struct completion ioq_wait;
+	u32 last_ps;
 
 	mempool_t *iod_mempool;
 
 	/* shadow doorbell buffer support: */
-	u32 *dbbuf_dbs;
+	__le32 *dbbuf_dbs;
 	dma_addr_t dbbuf_dbs_dma_addr;
-	u32 *dbbuf_eis;
+	__le32 *dbbuf_eis;
 	dma_addr_t dbbuf_eis_dma_addr;
 
 	/* host memory buffer support: */
@@ -121,17 +150,21 @@
 	dma_addr_t host_mem_descs_dma;
 	struct nvme_host_mem_buf_desc *host_mem_descs;
 	void **host_mem_desc_bufs;
+	unsigned int nr_allocated_queues;
+	unsigned int nr_write_queues;
+	unsigned int nr_poll_queues;
 };
 
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
-	int n = 0, ret;
+	int ret;
+	u32 n;
 
-	ret = kstrtoint(val, 10, &n);
+	ret = kstrtou32(val, 10, &n);
 	if (ret != 0 || n < 2)
 		return -EINVAL;
 
-	return param_set_int(val, kp);
+	return param_set_uint(val, kp);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -154,78 +187,63 @@
  * commands and one for I/O commands).
  */
 struct nvme_queue {
-	struct device *q_dmadev;
 	struct nvme_dev *dev;
 	spinlock_t sq_lock;
-	struct nvme_command *sq_cmds;
-	struct nvme_command __iomem *sq_cmds_io;
-	spinlock_t cq_lock ____cacheline_aligned_in_smp;
-	volatile struct nvme_completion *cqes;
-	struct blk_mq_tags **tags;
+	void *sq_cmds;
+	 /* only used for poll queues: */
+	spinlock_t cq_poll_lock ____cacheline_aligned_in_smp;
+	struct nvme_completion *cqes;
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
-	u16 q_depth;
-	s16 cq_vector;
+	u32 q_depth;
+	u16 cq_vector;
 	u16 sq_tail;
+	u16 last_sq_tail;
 	u16 cq_head;
-	u16 last_cq_head;
 	u16 qid;
 	u8 cq_phase;
-	u32 *dbbuf_sq_db;
-	u32 *dbbuf_cq_db;
-	u32 *dbbuf_sq_ei;
-	u32 *dbbuf_cq_ei;
+	u8 sqes;
+	unsigned long flags;
+#define NVMEQ_ENABLED		0
+#define NVMEQ_SQ_CMB		1
+#define NVMEQ_DELETE_ERROR	2
+#define NVMEQ_POLLED		3
+	__le32 *dbbuf_sq_db;
+	__le32 *dbbuf_cq_db;
+	__le32 *dbbuf_sq_ei;
+	__le32 *dbbuf_cq_ei;
+	struct completion delete_done;
 };
 
 /*
- * The nvme_iod describes the data in an I/O, including the list of PRP
- * entries.  You can't see it in this data structure because C doesn't let
- * me express that.  Use nvme_init_iod to ensure there's enough space
- * allocated to store the PRP list.
+ * The nvme_iod describes the data in an I/O.
+ *
+ * The sg pointer contains the list of PRP/SGL chunk allocations in addition
+ * to the actual struct scatterlist.
  */
 struct nvme_iod {
 	struct nvme_request req;
+	struct nvme_command cmd;
 	struct nvme_queue *nvmeq;
 	bool use_sgl;
 	int aborted;
 	int npages;		/* In the PRP list. 0 means small pool in use */
 	int nents;		/* Used in scatterlist */
-	int length;		/* Of data, in bytes */
 	dma_addr_t first_dma;
-	struct scatterlist meta_sg; /* metadata requires single contiguous buffer */
+	unsigned int dma_len;	/* length of single DMA segment mapping */
+	dma_addr_t meta_dma;
 	struct scatterlist *sg;
-	struct scatterlist inline_sg[0];
 };
 
-/*
- * Check we didin't inadvertently grow the command struct
- */
-static inline void _nvme_check_size(void)
+static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev)
 {
-	BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
-	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
-	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
-	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
-}
-
-static inline unsigned int nvme_dbbuf_size(u32 stride)
-{
-	return ((num_possible_cpus() + 1) * 8 * stride);
+	return dev->nr_allocated_queues * 8 * dev->db_stride;
 }
 
 static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
 {
-	unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+	unsigned int mem_size = nvme_dbbuf_size(dev);
 
 	if (dev->dbbuf_dbs)
 		return 0;
@@ -250,7 +268,7 @@
 
 static void nvme_dbbuf_dma_free(struct nvme_dev *dev)
 {
-	unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+	unsigned int mem_size = nvme_dbbuf_size(dev);
 
 	if (dev->dbbuf_dbs) {
 		dma_free_coherent(dev->dev, mem_size,
@@ -316,11 +334,11 @@
 }
 
 /* Update dbbuf and return true if an MMIO is required */
-static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
-					      volatile u32 *dbbuf_ei)
+static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
+					      volatile __le32 *dbbuf_ei)
 {
 	if (dbbuf_db) {
-		u16 old_value;
+		u16 old_value, event_idx;
 
 		/*
 		 * Ensure that the queue is written before updating
@@ -328,8 +346,8 @@
 		 */
 		wmb();
 
-		old_value = *dbbuf_db;
-		*dbbuf_db = value;
+		old_value = le32_to_cpu(*dbbuf_db);
+		*dbbuf_db = cpu_to_le32(value);
 
 		/*
 		 * Ensure that the doorbell is updated before reading the event
@@ -339,7 +357,8 @@
 		 */
 		mb();
 
-		if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+		event_idx = le32_to_cpu(*dbbuf_ei);
+		if (!nvme_dbbuf_need_event(event_idx, value, old_value))
 			return false;
 	}
 
@@ -347,52 +366,25 @@
 }
 
 /*
- * Max size of iod being embedded in the request payload
- */
-#define NVME_INT_PAGES		2
-#define NVME_INT_BYTES(dev)	(NVME_INT_PAGES * (dev)->ctrl.page_size)
-
-/*
  * Will slightly overestimate the number of pages needed.  This is OK
  * as it only leads to a small amount of wasted memory for the lifetime of
  * the I/O.
  */
-static int nvme_npages(unsigned size, struct nvme_dev *dev)
+static int nvme_pci_npages_prp(void)
 {
-	unsigned nprps = DIV_ROUND_UP(size + dev->ctrl.page_size,
-				      dev->ctrl.page_size);
-	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
+	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
+	return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
 }
 
 /*
  * Calculates the number of pages needed for the SGL segments. For example a 4k
  * page can accommodate 256 SGL descriptors.
  */
-static int nvme_pci_npages_sgl(unsigned int num_seg)
+static int nvme_pci_npages_sgl(void)
 {
-	return DIV_ROUND_UP(num_seg * sizeof(struct nvme_sgl_desc), PAGE_SIZE);
-}
-
-static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev,
-		unsigned int size, unsigned int nseg, bool use_sgl)
-{
-	size_t alloc_size;
-
-	if (use_sgl)
-		alloc_size = sizeof(__le64 *) * nvme_pci_npages_sgl(nseg);
-	else
-		alloc_size = sizeof(__le64 *) * nvme_npages(size, dev);
-
-	return alloc_size + sizeof(struct scatterlist) * nseg;
-}
-
-static unsigned int nvme_pci_cmd_size(struct nvme_dev *dev, bool use_sgl)
-{
-	unsigned int alloc_size = nvme_pci_iod_alloc_size(dev,
-				    NVME_INT_BYTES(dev), NVME_INT_PAGES,
-				    use_sgl);
-
-	return sizeof(struct nvme_iod) + alloc_size;
+	return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc),
+			NVME_CTRL_PAGE_SIZE);
 }
 
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -403,18 +395,9 @@
 
 	WARN_ON(hctx_idx != 0);
 	WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
-	WARN_ON(nvmeq->tags);
 
 	hctx->driver_data = nvmeq;
-	nvmeq->tags = &dev->admin_tagset.tags[0];
 	return 0;
-}
-
-static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nvme_queue *nvmeq = hctx->driver_data;
-
-	nvmeq->tags = NULL;
 }
 
 static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -422,9 +405,6 @@
 {
 	struct nvme_dev *dev = data;
 	struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1];
-
-	if (!nvmeq->tags)
-		nvmeq->tags = &dev->tagset.tags[hctx_idx];
 
 	WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
 	hctx->driver_data = nvmeq;
@@ -446,33 +426,91 @@
 	return 0;
 }
 
+static int queue_irq_offset(struct nvme_dev *dev)
+{
+	/* if we have more than 1 vec, admin queue offsets us by 1 */
+	if (dev->num_vecs > 1)
+		return 1;
+
+	return 0;
+}
+
 static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_dev *dev = set->driver_data;
+	int i, qoff, offset;
 
-	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev),
-			dev->num_vecs > 1 ? 1 /* admin queue */ : 0);
+	offset = queue_irq_offset(dev);
+	for (i = 0, qoff = 0; i < set->nr_maps; i++) {
+		struct blk_mq_queue_map *map = &set->map[i];
+
+		map->nr_queues = dev->io_queues[i];
+		if (!map->nr_queues) {
+			BUG_ON(i == HCTX_TYPE_DEFAULT);
+			continue;
+		}
+
+		/*
+		 * The poll queue(s) doesn't have an IRQ (and hence IRQ
+		 * affinity), so use the regular blk-mq cpu mapping
+		 */
+		map->queue_offset = qoff;
+		if (i != HCTX_TYPE_POLL && offset)
+			blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
+		else
+			blk_mq_map_queues(map);
+		qoff += map->nr_queues;
+		offset += map->nr_queues;
+	}
+
+	return 0;
+}
+
+/*
+ * Write sq tail if we are asked to, or if the next command would wrap.
+ */
+static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
+{
+	if (!write_sq) {
+		u16 next_tail = nvmeq->sq_tail + 1;
+
+		if (next_tail == nvmeq->q_depth)
+			next_tail = 0;
+		if (next_tail != nvmeq->last_sq_tail)
+			return;
+	}
+
+	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
+			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
+		writel(nvmeq->sq_tail, nvmeq->q_db);
+	nvmeq->last_sq_tail = nvmeq->sq_tail;
 }
 
 /**
  * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
  * @cmd: The command to send
+ * @write_sq: whether to write to the SQ doorbell
  */
-static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
+			    bool write_sq)
 {
 	spin_lock(&nvmeq->sq_lock);
-	if (nvmeq->sq_cmds_io)
-		memcpy_toio(&nvmeq->sq_cmds_io[nvmeq->sq_tail], cmd,
-				sizeof(*cmd));
-	else
-		memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
-
+	memcpy(nvmeq->sq_cmds + (nvmeq->sq_tail << nvmeq->sqes),
+	       cmd, sizeof(*cmd));
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
-	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
-			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
-		writel(nvmeq->sq_tail, nvmeq->q_db);
+	nvme_write_sq_db(nvmeq, write_sq);
+	spin_unlock(&nvmeq->sq_lock);
+}
+
+static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	struct nvme_queue *nvmeq = hctx->driver_data;
+
+	spin_lock(&nvmeq->sq_lock);
+	if (nvmeq->sq_tail != nvmeq->last_sq_tail)
+		nvme_write_sq_db(nvmeq, true);
 	spin_unlock(&nvmeq->sq_lock);
 }
 
@@ -488,9 +526,6 @@
 	int nseg = blk_rq_nr_phys_segments(req);
 	unsigned int avg_seg_size;
 
-	if (nseg == 0)
-		return false;
-
 	avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);
 
 	if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1))))
@@ -502,62 +537,72 @@
 	return true;
 }
 
-static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev)
+static void nvme_free_prps(struct nvme_dev *dev, struct request *req)
 {
-	struct nvme_iod *iod = blk_mq_rq_to_pdu(rq);
-	int nseg = blk_rq_nr_phys_segments(rq);
-	unsigned int size = blk_rq_payload_bytes(rq);
-
-	iod->use_sgl = nvme_pci_use_sgls(dev, rq);
-
-	if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
-		iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
-		if (!iod->sg)
-			return BLK_STS_RESOURCE;
-	} else {
-		iod->sg = iod->inline_sg;
-	}
-
-	iod->aborted = 0;
-	iod->npages = -1;
-	iod->nents = 0;
-	iod->length = size;
-
-	return BLK_STS_OK;
-}
-
-static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
-{
+	const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1;
-	dma_addr_t dma_addr = iod->first_dma, next_dma_addr;
-
+	dma_addr_t dma_addr = iod->first_dma;
 	int i;
 
-	if (iod->npages == 0)
-		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
-			dma_addr);
-
 	for (i = 0; i < iod->npages; i++) {
-		void *addr = nvme_pci_iod_list(req)[i];
+		__le64 *prp_list = nvme_pci_iod_list(req)[i];
+		dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]);
 
-		if (iod->use_sgl) {
-			struct nvme_sgl_desc *sg_list = addr;
-
-			next_dma_addr =
-			    le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr);
-		} else {
-			__le64 *prp_list = addr;
-
-			next_dma_addr = le64_to_cpu(prp_list[last_prp]);
-		}
-
-		dma_pool_free(dev->prp_page_pool, addr, dma_addr);
+		dma_pool_free(dev->prp_page_pool, prp_list, dma_addr);
 		dma_addr = next_dma_addr;
 	}
 
-	if (iod->sg != iod->inline_sg)
-		mempool_free(iod->sg, dev->iod_mempool);
+}
+
+static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
+{
+	const int last_sg = SGES_PER_PAGE - 1;
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	dma_addr_t dma_addr = iod->first_dma;
+	int i;
+
+	for (i = 0; i < iod->npages; i++) {
+		struct nvme_sgl_desc *sg_list = nvme_pci_iod_list(req)[i];
+		dma_addr_t next_dma_addr = le64_to_cpu((sg_list[last_sg]).addr);
+
+		dma_pool_free(dev->prp_page_pool, sg_list, dma_addr);
+		dma_addr = next_dma_addr;
+	}
+
+}
+
+static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+	if (is_pci_p2pdma_page(sg_page(iod->sg)))
+		pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents,
+				    rq_dma_dir(req));
+	else
+		dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req));
+}
+
+static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+	if (iod->dma_len) {
+		dma_unmap_page(dev->dev, iod->first_dma, iod->dma_len,
+			       rq_dma_dir(req));
+		return;
+	}
+
+	WARN_ON_ONCE(!iod->nents);
+
+	nvme_unmap_sg(dev, req);
+	if (iod->npages == 0)
+		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
+			      iod->first_dma);
+	else if (iod->use_sgl)
+		nvme_free_sgls(dev, req);
+	else
+		nvme_free_prps(dev, req);
+	mempool_free(iod->sg, dev->iod_mempool);
 }
 
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
@@ -583,34 +628,33 @@
 	struct scatterlist *sg = iod->sg;
 	int dma_len = sg_dma_len(sg);
 	u64 dma_addr = sg_dma_address(sg);
-	u32 page_size = dev->ctrl.page_size;
-	int offset = dma_addr & (page_size - 1);
+	int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1);
 	__le64 *prp_list;
 	void **list = nvme_pci_iod_list(req);
 	dma_addr_t prp_dma;
 	int nprps, i;
 
-	length -= (page_size - offset);
+	length -= (NVME_CTRL_PAGE_SIZE - offset);
 	if (length <= 0) {
 		iod->first_dma = 0;
 		goto done;
 	}
 
-	dma_len -= (page_size - offset);
+	dma_len -= (NVME_CTRL_PAGE_SIZE - offset);
 	if (dma_len) {
-		dma_addr += (page_size - offset);
+		dma_addr += (NVME_CTRL_PAGE_SIZE - offset);
 	} else {
 		sg = sg_next(sg);
 		dma_addr = sg_dma_address(sg);
 		dma_len = sg_dma_len(sg);
 	}
 
-	if (length <= page_size) {
+	if (length <= NVME_CTRL_PAGE_SIZE) {
 		iod->first_dma = dma_addr;
 		goto done;
 	}
 
-	nprps = DIV_ROUND_UP(length, page_size);
+	nprps = DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE);
 	if (nprps <= (256 / 8)) {
 		pool = dev->prp_small_pool;
 		iod->npages = 0;
@@ -629,20 +673,20 @@
 	iod->first_dma = prp_dma;
 	i = 0;
 	for (;;) {
-		if (i == page_size >> 3) {
+		if (i == NVME_CTRL_PAGE_SIZE >> 3) {
 			__le64 *old_prp_list = prp_list;
 			prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
 			if (!prp_list)
-				return BLK_STS_RESOURCE;
+				goto free_prps;
 			list[iod->npages++] = prp_list;
 			prp_list[0] = old_prp_list[i - 1];
 			old_prp_list[i - 1] = cpu_to_le64(prp_dma);
 			i = 1;
 		}
 		prp_list[i++] = cpu_to_le64(dma_addr);
-		dma_len -= page_size;
-		dma_addr += page_size;
-		length -= page_size;
+		dma_len -= NVME_CTRL_PAGE_SIZE;
+		dma_addr += NVME_CTRL_PAGE_SIZE;
+		length -= NVME_CTRL_PAGE_SIZE;
 		if (length <= 0)
 			break;
 		if (dma_len > 0)
@@ -653,14 +697,14 @@
 		dma_addr = sg_dma_address(sg);
 		dma_len = sg_dma_len(sg);
 	}
-
 done:
 	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
 	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
-
 	return BLK_STS_OK;
-
- bad_sgl:
+free_prps:
+	nvme_free_prps(dev, req);
+	return BLK_STS_RESOURCE;
+bad_sgl:
 	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
 			"Invalid SGL for payload:%d nents:%d\n",
 			blk_rq_payload_bytes(req), iod->nents);
@@ -683,7 +727,7 @@
 		sge->length = cpu_to_le32(entries * sizeof(*sge));
 		sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
 	} else {
-		sge->length = cpu_to_le32(PAGE_SIZE);
+		sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE);
 		sge->type = NVME_SGL_FMT_SEG_DESC << 4;
 	}
 }
@@ -732,7 +776,7 @@
 
 			sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
 			if (!sg_list)
-				return BLK_STS_RESOURCE;
+				goto free_sgls;
 
 			i = 0;
 			nvme_pci_iod_list(req)[iod->npages++] = sg_list;
@@ -745,74 +789,117 @@
 	} while (--entries > 0);
 
 	return BLK_STS_OK;
+free_sgls:
+	nvme_free_sgls(dev, req);
+	return BLK_STS_RESOURCE;
+}
+
+static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
+		struct request *req, struct nvme_rw_command *cmnd,
+		struct bio_vec *bv)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	unsigned int offset = bv->bv_offset & (NVME_CTRL_PAGE_SIZE - 1);
+	unsigned int first_prp_len = NVME_CTRL_PAGE_SIZE - offset;
+
+	iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
+	if (dma_mapping_error(dev->dev, iod->first_dma))
+		return BLK_STS_RESOURCE;
+	iod->dma_len = bv->bv_len;
+
+	cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma);
+	if (bv->bv_len > first_prp_len)
+		cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len);
+	else
+		cmnd->dptr.prp2 = 0;
+	return BLK_STS_OK;
+}
+
+static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
+		struct request *req, struct nvme_rw_command *cmnd,
+		struct bio_vec *bv)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+	iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
+	if (dma_mapping_error(dev->dev, iod->first_dma))
+		return BLK_STS_RESOURCE;
+	iod->dma_len = bv->bv_len;
+
+	cmnd->flags = NVME_CMD_SGL_METABUF;
+	cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma);
+	cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len);
+	cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4;
+	return BLK_STS_OK;
 }
 
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		struct nvme_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	struct request_queue *q = req->q;
-	enum dma_data_direction dma_dir = rq_data_dir(req) ?
-			DMA_TO_DEVICE : DMA_FROM_DEVICE;
-	blk_status_t ret = BLK_STS_IOERR;
+	blk_status_t ret = BLK_STS_RESOURCE;
 	int nr_mapped;
 
+	if (blk_rq_nr_phys_segments(req) == 1) {
+		struct bio_vec bv = req_bvec(req);
+
+		if (!is_pci_p2pdma_page(bv.bv_page)) {
+			if (bv.bv_offset + bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
+				return nvme_setup_prp_simple(dev, req,
+							     &cmnd->rw, &bv);
+
+			if (iod->nvmeq->qid && sgl_threshold &&
+			    dev->ctrl.sgls & ((1 << 0) | (1 << 1)))
+				return nvme_setup_sgl_simple(dev, req,
+							     &cmnd->rw, &bv);
+		}
+	}
+
+	iod->dma_len = 0;
+	iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
+	if (!iod->sg)
+		return BLK_STS_RESOURCE;
 	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
-	iod->nents = blk_rq_map_sg(q, req, iod->sg);
+	iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
 	if (!iod->nents)
-		goto out;
+		goto out_free_sg;
 
-	ret = BLK_STS_RESOURCE;
-	nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir,
-			DMA_ATTR_NO_WARN);
+	if (is_pci_p2pdma_page(sg_page(iod->sg)))
+		nr_mapped = pci_p2pdma_map_sg_attrs(dev->dev, iod->sg,
+				iod->nents, rq_dma_dir(req), DMA_ATTR_NO_WARN);
+	else
+		nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents,
+					     rq_dma_dir(req), DMA_ATTR_NO_WARN);
 	if (!nr_mapped)
-		goto out;
+		goto out_free_sg;
 
+	iod->use_sgl = nvme_pci_use_sgls(dev, req);
 	if (iod->use_sgl)
 		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped);
 	else
 		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
-
 	if (ret != BLK_STS_OK)
-		goto out_unmap;
-
-	ret = BLK_STS_IOERR;
-	if (blk_integrity_rq(req)) {
-		if (blk_rq_count_integrity_sg(q, req->bio) != 1)
-			goto out_unmap;
-
-		sg_init_table(&iod->meta_sg, 1);
-		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)
-			goto out_unmap;
-
-		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))
-			goto out_unmap;
-	}
-
-	if (blk_integrity_rq(req))
-		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg));
+		goto out_unmap_sg;
 	return BLK_STS_OK;
 
-out_unmap:
-	dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
-out:
+out_unmap_sg:
+	nvme_unmap_sg(dev, req);
+out_free_sg:
+	mempool_free(iod->sg, dev->iod_mempool);
 	return ret;
 }
 
-static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
+static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
+		struct nvme_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	enum dma_data_direction dma_dir = rq_data_dir(req) ?
-			DMA_TO_DEVICE : DMA_FROM_DEVICE;
 
-	if (iod->nents) {
-		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
-		if (blk_integrity_rq(req))
-			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
-	}
-
-	nvme_cleanup_cmd(req);
-	nvme_free_iod(dev, req);
+	iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
+			rq_dma_dir(req), 0);
+	if (dma_mapping_error(dev->dev, iod->meta_dma))
+		return BLK_STS_IOERR;
+	cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
+	return BLK_STS_OK;
 }
 
 /*
@@ -825,35 +912,42 @@
 	struct nvme_queue *nvmeq = hctx->driver_data;
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *req = bd->rq;
-	struct nvme_command cmnd;
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	struct nvme_command *cmnd = &iod->cmd;
 	blk_status_t ret;
+
+	iod->aborted = 0;
+	iod->npages = -1;
+	iod->nents = 0;
 
 	/*
 	 * We should not need to do this, but we're still using this to
 	 * ensure we can drain requests on a dying queue.
 	 */
-	if (unlikely(nvmeq->cq_vector < 0))
+	if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
 		return BLK_STS_IOERR;
 
-	ret = nvme_setup_cmd(ns, req, &cmnd);
+	ret = nvme_setup_cmd(ns, req, cmnd);
 	if (ret)
 		return ret;
 
-	ret = nvme_init_iod(req, dev);
-	if (ret)
-		goto out_free_cmd;
-
 	if (blk_rq_nr_phys_segments(req)) {
-		ret = nvme_map_data(dev, req, &cmnd);
+		ret = nvme_map_data(dev, req, cmnd);
 		if (ret)
-			goto out_cleanup_iod;
+			goto out_free_cmd;
+	}
+
+	if (blk_integrity_rq(req)) {
+		ret = nvme_map_metadata(dev, req, cmnd);
+		if (ret)
+			goto out_unmap_data;
 	}
 
 	blk_mq_start_request(req);
-	nvme_submit_cmd(nvmeq, &cmnd);
+	nvme_submit_cmd(nvmeq, cmnd, bd->last);
 	return BLK_STS_OK;
-out_cleanup_iod:
-	nvme_free_iod(dev, req);
+out_unmap_data:
+	nvme_unmap_data(dev, req);
 out_free_cmd:
 	nvme_cleanup_cmd(req);
 	return ret;
@@ -862,16 +956,23 @@
 static void nvme_pci_complete_rq(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	struct nvme_dev *dev = iod->nvmeq->dev;
 
-	nvme_unmap_data(iod->nvmeq->dev, req);
+	if (blk_integrity_rq(req))
+		dma_unmap_page(dev->dev, iod->meta_dma,
+			       rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
+
+	if (blk_rq_nr_phys_segments(req))
+		nvme_unmap_data(dev, req);
 	nvme_complete_rq(req);
 }
 
 /* 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)
 {
-	return (le16_to_cpu(nvmeq->cqes[nvmeq->cq_head].status) & 1) ==
-			nvmeq->cq_phase;
+	struct nvme_completion *hcqe = &nvmeq->cqes[nvmeq->cq_head];
+
+	return (le16_to_cpu(READ_ONCE(hcqe->status)) & 1) == nvmeq->cq_phase;
 }
 
 static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
@@ -883,17 +984,18 @@
 		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
 }
 
+static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
+{
+	if (!nvmeq->qid)
+		return nvmeq->dev->admin_tagset.tags[0];
+	return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
+}
+
 static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 {
-	volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
+	struct nvme_completion *cqe = &nvmeq->cqes[idx];
+	__u16 command_id = READ_ONCE(cqe->command_id);
 	struct request *req;
-
-	if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
-		dev_warn(nvmeq->dev->ctrl.device,
-			"invalid id %d completed on queue %d\n",
-			cqe->command_id, le16_to_cpu(cqe->sq_id));
-		return;
-	}
 
 	/*
 	 * AEN requests are special as they don't time out and can
@@ -901,50 +1003,53 @@
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvmeq->qid == 0 &&
-			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) {
+	if (unlikely(nvme_is_aen_req(nvmeq->qid, command_id))) {
 		nvme_complete_async_event(&nvmeq->dev->ctrl,
 				cqe->status, &cqe->result);
 		return;
 	}
 
-	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
-	nvme_end_request(req, cqe->status, cqe->result);
-}
-
-static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
-{
-	while (start != end) {
-		nvme_handle_cqe(nvmeq, start);
-		if (++start == nvmeq->q_depth)
-			start = 0;
+	req = nvme_find_rq(nvme_queue_tagset(nvmeq), command_id);
+	if (unlikely(!req)) {
+		dev_warn(nvmeq->dev->ctrl.device,
+			"invalid id %d completed on queue %d\n",
+			command_id, le16_to_cpu(cqe->sq_id));
+		return;
 	}
+
+	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
+	if (!nvme_try_complete_req(req, cqe->status, cqe->result))
+		nvme_pci_complete_rq(req);
 }
 
 static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
 {
-	if (nvmeq->cq_head == nvmeq->q_depth - 1) {
+	u32 tmp = nvmeq->cq_head + 1;
+
+	if (tmp == nvmeq->q_depth) {
 		nvmeq->cq_head = 0;
-		nvmeq->cq_phase = !nvmeq->cq_phase;
+		nvmeq->cq_phase ^= 1;
 	} else {
-		nvmeq->cq_head++;
+		nvmeq->cq_head = tmp;
 	}
 }
 
-static inline bool nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
-		u16 *end, int tag)
+static inline int nvme_process_cq(struct nvme_queue *nvmeq)
 {
-	bool found = false;
+	int found = 0;
 
-	*start = nvmeq->cq_head;
-	while (!found && nvme_cqe_pending(nvmeq)) {
-		if (nvmeq->cqes[nvmeq->cq_head].command_id == tag)
-			found = true;
+	while (nvme_cqe_pending(nvmeq)) {
+		found++;
+		/*
+		 * load-load control dependency between phase and the rest of
+		 * the cqe requires a full read memory barrier
+		 */
+		dma_rmb();
+		nvme_handle_cqe(nvmeq, nvmeq->cq_head);
 		nvme_update_cq_head(nvmeq);
 	}
-	*end = nvmeq->cq_head;
 
-	if (*start != *end)
+	if (found)
 		nvme_ring_cq_doorbell(nvmeq);
 	return found;
 }
@@ -953,19 +1058,15 @@
 {
 	struct nvme_queue *nvmeq = data;
 	irqreturn_t ret = IRQ_NONE;
-	u16 start, end;
 
-	spin_lock(&nvmeq->cq_lock);
-	if (nvmeq->cq_head != nvmeq->last_cq_head)
+	/*
+	 * The rmb/wmb pair ensures we see all updates from a previous run of
+	 * the irq handler, even if that was on another CPU.
+	 */
+	rmb();
+	if (nvme_process_cq(nvmeq))
 		ret = IRQ_HANDLED;
-	nvme_process_cq(nvmeq, &start, &end, -1);
-	nvmeq->last_cq_head = nvmeq->cq_head;
-	spin_unlock(&nvmeq->cq_lock);
-
-	if (start != end) {
-		nvme_complete_cqes(nvmeq, start, end);
-		return IRQ_HANDLED;
-	}
+	wmb();
 
 	return ret;
 }
@@ -973,32 +1074,40 @@
 static irqreturn_t nvme_irq_check(int irq, void *data)
 {
 	struct nvme_queue *nvmeq = data;
+
 	if (nvme_cqe_pending(nvmeq))
 		return IRQ_WAKE_THREAD;
 	return IRQ_NONE;
 }
 
-static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
+/*
+ * Poll for completions for any interrupt driven queue
+ * Can be called from any context.
+ */
+static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 {
-	u16 start, end;
+	struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
+
+	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
+
+	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	nvme_process_cq(nvmeq);
+	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+}
+
+static int nvme_poll(struct blk_mq_hw_ctx *hctx)
+{
+	struct nvme_queue *nvmeq = hctx->driver_data;
 	bool found;
 
 	if (!nvme_cqe_pending(nvmeq))
 		return 0;
 
-	spin_lock_irq(&nvmeq->cq_lock);
-	found = nvme_process_cq(nvmeq, &start, &end, tag);
-	spin_unlock_irq(&nvmeq->cq_lock);
+	spin_lock(&nvmeq->cq_poll_lock);
+	found = nvme_process_cq(nvmeq);
+	spin_unlock(&nvmeq->cq_poll_lock);
 
-	nvme_complete_cqes(nvmeq, start, end);
 	return found;
-}
-
-static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
-{
-	struct nvme_queue *nvmeq = hctx->driver_data;
-
-	return __nvme_poll(nvmeq, tag);
 }
 
 static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
@@ -1010,7 +1119,7 @@
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
-	nvme_submit_cmd(nvmeq, &c);
+	nvme_submit_cmd(nvmeq, &c, true);
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1028,7 +1137,10 @@
 		struct nvme_queue *nvmeq, s16 vector)
 {
 	struct nvme_command c;
-	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
+	int flags = NVME_QUEUE_PHYS_CONTIG;
+
+	if (!test_bit(NVMEQ_POLLED, &nvmeq->flags))
+		flags |= NVME_CQ_IRQ_ENABLED;
 
 	/*
 	 * Note: we (ab)use the fact that the prp fields survive if no data
@@ -1098,7 +1210,6 @@
 
 static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 {
-
 	/* If true, indicates loss of adapter communication, possibly by a
 	 * NVMe Subsystem reset.
 	 */
@@ -1147,7 +1258,6 @@
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
 	struct nvme_command cmd;
-	bool shutdown = false;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 	/* If PCI error recovery process is happening, we cannot reset or
@@ -1170,7 +1280,12 @@
 	/*
 	 * Did we miss an interrupt?
 	 */
-	if (__nvme_poll(nvmeq, req->tag)) {
+	if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
+		nvme_poll(req->mq_hctx);
+	else
+		nvme_poll_irqdisable(nvmeq);
+
+	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, completion polled\n",
 			 req->tag, nvmeq->qid);
@@ -1184,33 +1299,35 @@
 	 * shutdown, so we return BLK_EH_DONE.
 	 */
 	switch (dev->ctrl.state) {
-	case NVME_CTRL_DELETING:
-		shutdown = true;
 	case NVME_CTRL_CONNECTING:
-	case NVME_CTRL_RESETTING:
+		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
+		fallthrough;
+	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, shutdown);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
+		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
+	case NVME_CTRL_RESETTING:
+		return BLK_EH_RESET_TIMER;
 	default:
 		break;
 	}
 
 	/*
- 	 * Shutdown the controller immediately and schedule a reset if the
- 	 * command was already aborted once before and still hasn't been
- 	 * returned to the driver, or if this is the admin queue.
+	 * Shutdown the controller immediately and schedule a reset if the
+	 * command was already aborted once before and still hasn't been
+	 * returned to the driver, or if this is the admin queue.
 	 */
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
+		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, false);
 		nvme_reset_ctrl(&dev->ctrl);
 
-		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
 	}
 
@@ -1222,7 +1339,7 @@
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
-	cmd.abort.cid = req->tag;
+	cmd.abort.cid = nvme_cid(req);
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
@@ -1230,13 +1347,12 @@
 		 req->tag, nvmeq->qid);
 
 	abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
-			BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
+			BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(abort_req)) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
 	}
 
-	abort_req->timeout = ADMIN_TIMEOUT;
 	abort_req->end_io_data = NULL;
 	blk_execute_rq_nowait(abort_req->q, NULL, abort_req, 0, abort_endio);
 
@@ -1250,11 +1366,18 @@
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
-	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
+	dma_free_coherent(nvmeq->dev->dev, CQ_SIZE(nvmeq),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	if (nvmeq->sq_cmds)
-		dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
-					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+	if (!nvmeq->sq_cmds)
+		return;
+
+	if (test_and_clear_bit(NVMEQ_SQ_CMB, &nvmeq->flags)) {
+		pci_free_p2pmem(to_pci_dev(nvmeq->dev->dev),
+				nvmeq->sq_cmds, SQ_SIZE(nvmeq));
+	} else {
+		dma_free_coherent(nvmeq->dev->dev, SQ_SIZE(nvmeq),
+				nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+	}
 }
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
@@ -1269,51 +1392,59 @@
 
 /**
  * nvme_suspend_queue - put queue into suspended state
- * @nvmeq - queue to suspend
+ * @nvmeq: queue to suspend
  */
 static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
-	int vector;
-
-	spin_lock_irq(&nvmeq->cq_lock);
-	if (nvmeq->cq_vector == -1) {
-		spin_unlock_irq(&nvmeq->cq_lock);
+	if (!test_and_clear_bit(NVMEQ_ENABLED, &nvmeq->flags))
 		return 1;
-	}
-	vector = nvmeq->cq_vector;
-	nvmeq->dev->online_queues--;
-	nvmeq->cq_vector = -1;
-	spin_unlock_irq(&nvmeq->cq_lock);
 
-	/*
-	 * Ensure that nvme_queue_rq() sees it ->cq_vector == -1 without
-	 * having to grab the lock.
-	 */
+	/* ensure that nvme_queue_rq() sees NVMEQ_ENABLED cleared */
 	mb();
 
+	nvmeq->dev->online_queues--;
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
 		blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
-
-	pci_free_irq(to_pci_dev(nvmeq->dev->dev), vector, nvmeq);
-
+	if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags))
+		pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq);
 	return 0;
+}
+
+static void nvme_suspend_io_queues(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--)
+		nvme_suspend_queue(&dev->queues[i]);
 }
 
 static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 {
 	struct nvme_queue *nvmeq = &dev->queues[0];
-	u16 start, end;
 
 	if (shutdown)
 		nvme_shutdown_ctrl(&dev->ctrl);
 	else
-		nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
+		nvme_disable_ctrl(&dev->ctrl);
 
-	spin_lock_irq(&nvmeq->cq_lock);
-	nvme_process_cq(nvmeq, &start, &end, -1);
-	spin_unlock_irq(&nvmeq->cq_lock);
+	nvme_poll_irqdisable(nvmeq);
+}
 
-	nvme_complete_cqes(nvmeq, start, end);
+/*
+ * Called only on a device that has been disabled and after all other threads
+ * that can check this device's completion queues have synced, except
+ * nvme_poll(). This is the last chance for the driver to see a natural
+ * completion before nvme_cancel_request() terminates all incomplete requests.
+ */
+static void nvme_reap_pending_cqes(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
+		spin_lock(&dev->queues[i].cq_poll_lock);
+		nvme_process_cq(&dev->queues[i]);
+		spin_unlock(&dev->queues[i].cq_poll_lock);
+	}
 }
 
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
@@ -1321,11 +1452,12 @@
 {
 	int q_depth = dev->q_depth;
 	unsigned q_size_aligned = roundup(q_depth * entry_size,
-					  dev->ctrl.page_size);
+					  NVME_CTRL_PAGE_SIZE);
 
 	if (q_size_aligned * nr_io_queues > dev->cmb_size) {
 		u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
-		mem_per_q = round_down(mem_per_q, dev->ctrl.page_size);
+
+		mem_per_q = round_down(mem_per_q, NVME_CTRL_PAGE_SIZE);
 		q_depth = div_u64(mem_per_q, entry_size);
 
 		/*
@@ -1341,14 +1473,26 @@
 }
 
 static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
-				int qid, int depth)
+				int qid)
 {
-	/* CMB SQEs will be mapped before creation */
-	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS))
-		return 0;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					    &nvmeq->sq_dma_addr, GFP_KERNEL);
+	if (qid && dev->cmb_use_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+		nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(nvmeq));
+		if (nvmeq->sq_cmds) {
+			nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
+							nvmeq->sq_cmds);
+			if (nvmeq->sq_dma_addr) {
+				set_bit(NVMEQ_SQ_CMB, &nvmeq->flags);
+				return 0;
+			}
+
+			pci_free_p2pmem(pdev, nvmeq->sq_cmds, SQ_SIZE(nvmeq));
+		}
+	}
+
+	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(nvmeq),
+				&nvmeq->sq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->sq_cmds)
 		return -ENOMEM;
 	return 0;
@@ -1361,31 +1505,30 @@
 	if (dev->ctrl.queue_count > qid)
 		return 0;
 
-	nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
-					  &nvmeq->cq_dma_addr, GFP_KERNEL);
+	nvmeq->sqes = qid ? dev->io_sqes : NVME_ADM_SQES;
+	nvmeq->q_depth = depth;
+	nvmeq->cqes = dma_alloc_coherent(dev->dev, CQ_SIZE(nvmeq),
+					 &nvmeq->cq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->cqes)
 		goto free_nvmeq;
 
-	if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
+	if (nvme_alloc_sq_cmds(dev, nvmeq, qid))
 		goto free_cqdma;
 
-	nvmeq->q_dmadev = dev->dev;
 	nvmeq->dev = dev;
 	spin_lock_init(&nvmeq->sq_lock);
-	spin_lock_init(&nvmeq->cq_lock);
+	spin_lock_init(&nvmeq->cq_poll_lock);
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
-	nvmeq->q_depth = depth;
 	nvmeq->qid = qid;
-	nvmeq->cq_vector = -1;
 	dev->ctrl.queue_count++;
 
 	return 0;
 
  free_cqdma:
-	dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq->cqes,
-							nvmeq->cq_dma_addr);
+	dma_free_coherent(dev->dev, CQ_SIZE(nvmeq), (void *)nvmeq->cqes,
+			  nvmeq->cq_dma_addr);
  free_nvmeq:
 	return -ENOMEM;
 }
@@ -1408,35 +1551,34 @@
 {
 	struct nvme_dev *dev = nvmeq->dev;
 
-	spin_lock_irq(&nvmeq->cq_lock);
 	nvmeq->sq_tail = 0;
+	nvmeq->last_sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
-	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq));
 	nvme_dbbuf_init(dev, nvmeq, qid);
 	dev->online_queues++;
-	spin_unlock_irq(&nvmeq->cq_lock);
+	wmb(); /* ensure the first interrupt sees the initialization */
 }
 
-static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
+static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 {
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
-	s16 vector;
+	u16 vector = 0;
 
-	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
-		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
-						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
-		nvmeq->sq_cmds_io = dev->cmb + offset;
-	}
+	clear_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags);
 
 	/*
 	 * A queue's vector matches the queue identifier unless the controller
 	 * has only one vector available.
 	 */
-	vector = dev->num_vecs == 1 ? 0 : qid;
+	if (!polled)
+		vector = dev->num_vecs == 1 ? 0 : qid;
+	else
+		set_bit(NVMEQ_POLLED, &nvmeq->flags);
+
 	result = adapter_alloc_cq(dev, qid, nvmeq, vector);
 	if (result)
 		return result;
@@ -1444,24 +1586,22 @@
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
 		return result;
-	else if (result)
+	if (result)
 		goto release_cq;
 
-	/*
-	 * Set cq_vector after alloc cq/sq, otherwise nvme_suspend_queue will
-	 * invoke free_irq for it and cause a 'Trying to free already-free IRQ
-	 * xxx' warning if the create CQ/SQ command times out.
-	 */
 	nvmeq->cq_vector = vector;
 	nvme_init_queue(nvmeq, qid);
-	result = queue_request_irq(nvmeq);
-	if (result < 0)
-		goto release_sq;
 
+	if (!polled) {
+		result = queue_request_irq(nvmeq);
+		if (result < 0)
+			goto release_sq;
+	}
+
+	set_bit(NVMEQ_ENABLED, &nvmeq->flags);
 	return result;
 
 release_sq:
-	nvmeq->cq_vector = -1;
 	dev->online_queues--;
 	adapter_delete_sq(dev, qid);
 release_cq:
@@ -1473,7 +1613,6 @@
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_pci_complete_rq,
 	.init_hctx	= nvme_admin_init_hctx,
-	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_init_request,
 	.timeout	= nvme_timeout,
 };
@@ -1481,6 +1620,7 @@
 static const struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_pci_complete_rq,
+	.commit_rqs	= nvme_commit_rqs,
 	.init_hctx	= nvme_init_hctx,
 	.init_request	= nvme_init_request,
 	.map_queues	= nvme_pci_map_queues,
@@ -1510,8 +1650,8 @@
 
 		dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
-		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
-		dev->admin_tagset.cmd_size = nvme_pci_cmd_size(dev, false);
+		dev->admin_tagset.numa_node = dev->ctrl.numa_node;
+		dev->admin_tagset.cmd_size = sizeof(struct nvme_iod);
 		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
@@ -1522,6 +1662,7 @@
 		dev->ctrl.admin_q = blk_mq_init_queue(&dev->admin_tagset);
 		if (IS_ERR(dev->ctrl.admin_q)) {
 			blk_mq_free_tag_set(&dev->admin_tagset);
+			dev->ctrl.admin_q = NULL;
 			return -ENOMEM;
 		}
 		if (!blk_get_queue(dev->ctrl.admin_q)) {
@@ -1578,13 +1719,15 @@
 	    (readl(dev->bar + NVME_REG_CSTS) & NVME_CSTS_NSSRO))
 		writel(NVME_CSTS_NSSRO, dev->bar + NVME_REG_CSTS);
 
-	result = nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
+	result = nvme_disable_ctrl(&dev->ctrl);
 	if (result < 0)
 		return result;
 
 	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
 	if (result)
 		return result;
+
+	dev->ctrl.numa_node = dev_to_node(dev->dev);
 
 	nvmeq = &dev->queues[0];
 	aqa = nvmeq->q_depth - 1;
@@ -1594,7 +1737,7 @@
 	lo_hi_writeq(nvmeq->sq_dma_addr, dev->bar + NVME_REG_ASQ);
 	lo_hi_writeq(nvmeq->cq_dma_addr, dev->bar + NVME_REG_ACQ);
 
-	result = nvme_enable_ctrl(&dev->ctrl, dev->ctrl.cap);
+	result = nvme_enable_ctrl(&dev->ctrl);
 	if (result)
 		return result;
 
@@ -1602,16 +1745,17 @@
 	nvme_init_queue(nvmeq, 0);
 	result = queue_request_irq(nvmeq);
 	if (result) {
-		nvmeq->cq_vector = -1;
+		dev->online_queues--;
 		return result;
 	}
 
+	set_bit(NVMEQ_ENABLED, &nvmeq->flags);
 	return result;
 }
 
 static int nvme_create_io_queues(struct nvme_dev *dev)
 {
-	unsigned i, max;
+	unsigned i, max, rw_queues;
 	int ret = 0;
 
 	for (i = dev->ctrl.queue_count; i <= dev->max_qid; i++) {
@@ -1622,8 +1766,17 @@
 	}
 
 	max = min(dev->max_qid, dev->ctrl.queue_count - 1);
+	if (max != 1 && dev->io_queues[HCTX_TYPE_POLL]) {
+		rw_queues = dev->io_queues[HCTX_TYPE_DEFAULT] +
+				dev->io_queues[HCTX_TYPE_READ];
+	} else {
+		rw_queues = max;
+	}
+
 	for (i = dev->online_queues; i <= max; i++) {
-		ret = nvme_create_queue(&dev->queues[i], i);
+		bool polled = i > rw_queues;
+
+		ret = nvme_create_queue(&dev->queues[i], i, polled);
 		if (ret)
 			break;
 	}
@@ -1670,13 +1823,13 @@
 	if (dev->cmb_size)
 		return;
 
+	if (NVME_CAP_CMBS(dev->ctrl.cap))
+		writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC);
+
 	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
 	if (!dev->cmbsz)
 		return;
 	dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
-
-	if (!use_cmb_sqes)
-		return;
 
 	size = nvme_cmb_size_unit(dev) * nvme_cmb_size(dev);
 	offset = nvme_cmb_size_unit(dev) * NVME_CMB_OFST(dev->cmbloc);
@@ -1687,6 +1840,16 @@
 		return;
 
 	/*
+	 * Tell the controller about the host side address mapping the CMB,
+	 * and enable CMB decoding for the NVMe 1.4+ scheme:
+	 */
+	if (NVME_CAP_CMBS(dev->ctrl.cap)) {
+		hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE |
+			     (pci_bus_address(pdev, bar) + offset),
+			     dev->bar + NVME_REG_CMBMSC);
+	}
+
+	/*
 	 * Controllers may support a CMB size larger than their BAR,
 	 * for example, due to being behind a bridge. Reduce the CMB to
 	 * the reported size of the BAR
@@ -1694,11 +1857,18 @@
 	if (size > bar_size - offset)
 		size = bar_size - offset;
 
-	dev->cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size);
-	if (!dev->cmb)
+	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
+		dev_warn(dev->ctrl.device,
+			 "failed to register the CMB\n");
 		return;
-	dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset;
+	}
+
 	dev->cmb_size = size;
+	dev->cmb_use_sqes = use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS);
+
+	if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
+			(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
+		pci_p2pmem_publish(pdev, true);
 
 	if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
 				    &dev_attr_cmb.attr, NULL))
@@ -1708,17 +1878,16 @@
 
 static inline void nvme_release_cmb(struct nvme_dev *dev)
 {
-	if (dev->cmb) {
-		iounmap(dev->cmb);
-		dev->cmb = NULL;
+	if (dev->cmb_size) {
 		sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
 					     &dev_attr_cmb.attr, NULL);
-		dev->cmbsz = 0;
+		dev->cmb_size = 0;
 	}
 }
 
 static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
 {
+	u32 host_mem_size = dev->host_mem_size >> NVME_CTRL_PAGE_SHIFT;
 	u64 dma_addr = dev->host_mem_descs_dma;
 	struct nvme_command c;
 	int ret;
@@ -1727,8 +1896,7 @@
 	c.features.opcode	= nvme_admin_set_features;
 	c.features.fid		= cpu_to_le32(NVME_FEAT_HOST_MEM_BUF);
 	c.features.dword11	= cpu_to_le32(bits);
-	c.features.dword12	= cpu_to_le32(dev->host_mem_size >>
-					      ilog2(dev->ctrl.page_size));
+	c.features.dword12	= cpu_to_le32(host_mem_size);
 	c.features.dword13	= cpu_to_le32(lower_32_bits(dma_addr));
 	c.features.dword14	= cpu_to_le32(upper_32_bits(dma_addr));
 	c.features.dword15	= cpu_to_le32(dev->nr_host_mem_descs);
@@ -1748,7 +1916,7 @@
 
 	for (i = 0; i < dev->nr_host_mem_descs; i++) {
 		struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i];
-		size_t size = le32_to_cpu(desc->size) * dev->ctrl.page_size;
+		size_t size = le32_to_cpu(desc->size) * NVME_CTRL_PAGE_SIZE;
 
 		dma_free_attrs(dev->dev, size, dev->host_mem_desc_bufs[i],
 			       le64_to_cpu(desc->addr),
@@ -1781,8 +1949,8 @@
 	if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
 		max_entries = dev->ctrl.hmmaxd;
 
-	descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs),
-			&descs_dma, GFP_KERNEL);
+	descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs),
+				   &descs_dma, GFP_KERNEL);
 	if (!descs)
 		goto out;
 
@@ -1800,7 +1968,7 @@
 			break;
 
 		descs[i].addr = cpu_to_le64(dma_addr);
-		descs[i].size = cpu_to_le32(len / dev->ctrl.page_size);
+		descs[i].size = cpu_to_le32(len / NVME_CTRL_PAGE_SIZE);
 		i++;
 	}
 
@@ -1816,7 +1984,7 @@
 
 out_free_bufs:
 	while (--i >= 0) {
-		size_t size = le32_to_cpu(descs[i].size) * dev->ctrl.page_size;
+		size_t size = le32_to_cpu(descs[i].size) * NVME_CTRL_PAGE_SIZE;
 
 		dma_free_attrs(dev->dev, size, bufs[i],
 			       le64_to_cpu(descs[i].addr),
@@ -1834,12 +2002,12 @@
 
 static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 {
-	u32 chunk_size;
+	u64 min_chunk = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
+	u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
+	u64 chunk_size;
 
 	/* start big and work our way down */
-	for (chunk_size = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
-	     chunk_size >= max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
-	     chunk_size /= 2) {
+	for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) {
 		if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
 			if (!min || dev->host_mem_size >= min)
 				return 0;
@@ -1895,32 +2063,132 @@
 	return ret;
 }
 
+/*
+ * nirqs is the number of interrupts available for write and read
+ * queues. The core already reserved an interrupt for the admin queue.
+ */
+static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs)
+{
+	struct nvme_dev *dev = affd->priv;
+	unsigned int nr_read_queues, nr_write_queues = dev->nr_write_queues;
+
+	/*
+	 * If there is no interrupt available for queues, ensure that
+	 * the default queue is set to 1. The affinity set size is
+	 * also set to one, but the irq core ignores it for this case.
+	 *
+	 * If only one interrupt is available or 'write_queue' == 0, combine
+	 * write and read queues.
+	 *
+	 * If 'write_queues' > 0, ensure it leaves room for at least one read
+	 * queue.
+	 */
+	if (!nrirqs) {
+		nrirqs = 1;
+		nr_read_queues = 0;
+	} else if (nrirqs == 1 || !nr_write_queues) {
+		nr_read_queues = 0;
+	} else if (nr_write_queues >= nrirqs) {
+		nr_read_queues = 1;
+	} else {
+		nr_read_queues = nrirqs - nr_write_queues;
+	}
+
+	dev->io_queues[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;
+	affd->set_size[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;
+	dev->io_queues[HCTX_TYPE_READ] = nr_read_queues;
+	affd->set_size[HCTX_TYPE_READ] = nr_read_queues;
+	affd->nr_sets = nr_read_queues ? 2 : 1;
+}
+
+static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
+{
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	struct irq_affinity affd = {
+		.pre_vectors	= 1,
+		.calc_sets	= nvme_calc_irq_sets,
+		.priv		= dev,
+	};
+	unsigned int irq_queues, poll_queues;
+
+	/*
+	 * Poll queues don't need interrupts, but we need at least one I/O queue
+	 * left over for non-polled I/O.
+	 */
+	poll_queues = min(dev->nr_poll_queues, nr_io_queues - 1);
+	dev->io_queues[HCTX_TYPE_POLL] = poll_queues;
+
+	/*
+	 * Initialize for the single interrupt case, will be updated in
+	 * nvme_calc_irq_sets().
+	 */
+	dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
+	dev->io_queues[HCTX_TYPE_READ] = 0;
+
+	/*
+	 * We need interrupts for the admin queue and each non-polled I/O queue,
+	 * but some Apple controllers require all queues to use the first
+	 * vector.
+	 */
+	irq_queues = 1;
+	if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
+		irq_queues += (nr_io_queues - poll_queues);
+	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
+			      PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+}
+
+static void nvme_disable_io_queues(struct nvme_dev *dev)
+{
+	if (__nvme_disable_io_queues(dev, nvme_admin_delete_sq))
+		__nvme_disable_io_queues(dev, nvme_admin_delete_cq);
+}
+
+static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
+{
+	return num_possible_cpus() + dev->nr_write_queues + dev->nr_poll_queues;
+}
+
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct nvme_queue *adminq = &dev->queues[0];
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	int result, nr_io_queues;
+	unsigned int nr_io_queues;
 	unsigned long size;
+	int result;
 
-	struct irq_affinity affd = {
-		.pre_vectors = 1
-	};
+	/*
+	 * Sample the module parameters once at reset time so that we have
+	 * stable values to work with.
+	 */
+	dev->nr_write_queues = write_queues;
+	dev->nr_poll_queues = poll_queues;
 
-	nr_io_queues = num_possible_cpus();
+	/*
+	 * If tags are shared with admin queue (Apple bug), then
+	 * make sure we only use one IO queue.
+	 */
+	if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
+		nr_io_queues = 1;
+	else
+		nr_io_queues = min(nvme_max_io_queues(dev),
+				   dev->nr_allocated_queues - 1);
+
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
 	if (result < 0)
 		return result;
 
 	if (nr_io_queues == 0)
 		return 0;
+	
+	clear_bit(NVMEQ_ENABLED, &adminq->flags);
 
-	if (dev->cmb && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
 				sizeof(struct nvme_command));
 		if (result > 0)
 			dev->q_depth = result;
 		else
-			nvme_release_cmb(dev);
+			dev->cmb_use_sqes = false;
 	}
 
 	do {
@@ -1933,6 +2201,7 @@
 	} while (1);
 	adminq->q_db = dev->dbs;
 
+ retry:
 	/* Deregister the admin queue's interrupt */
 	pci_free_irq(pdev, 0, adminq);
 
@@ -1941,12 +2210,14 @@
 	 * setting up the full range we need.
 	 */
 	pci_free_irq_vectors(pdev);
-	result = pci_alloc_irq_vectors_affinity(pdev, 1, nr_io_queues + 1,
-			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+
+	result = nvme_setup_irqs(dev, nr_io_queues);
 	if (result <= 0)
 		return -EIO;
+
 	dev->num_vecs = result;
-	dev->max_qid = max(result - 1, 1);
+	result = max(result - 1, 1);
+	dev->max_qid = result + dev->io_queues[HCTX_TYPE_POLL];
 
 	/*
 	 * Should investigate if there's a performance win from allocating
@@ -1954,13 +2225,26 @@
 	 * path to scale better, even if the receive path is limited by the
 	 * number of interrupts.
 	 */
-
 	result = queue_request_irq(adminq);
-	if (result) {
-		adminq->cq_vector = -1;
+	if (result)
 		return result;
+	set_bit(NVMEQ_ENABLED, &adminq->flags);
+
+	result = nvme_create_io_queues(dev);
+	if (result || dev->online_queues < 2)
+		return result;
+
+	if (dev->online_queues - 1 < dev->max_qid) {
+		nr_io_queues = dev->online_queues - 1;
+		nvme_disable_io_queues(dev);
+		nvme_suspend_io_queues(dev);
+		goto retry;
 	}
-	return nvme_create_io_queues(dev);
+	dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
+					dev->io_queues[HCTX_TYPE_DEFAULT],
+					dev->io_queues[HCTX_TYPE_READ],
+					dev->io_queues[HCTX_TYPE_POLL]);
+	return 0;
 }
 
 static void nvme_del_queue_end(struct request *req, blk_status_t error)
@@ -1968,23 +2252,15 @@
 	struct nvme_queue *nvmeq = req->end_io_data;
 
 	blk_mq_free_request(req);
-	complete(&nvmeq->dev->ioq_wait);
+	complete(&nvmeq->delete_done);
 }
 
 static void nvme_del_cq_end(struct request *req, blk_status_t error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
-	u16 start, end;
 
-	if (!error) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&nvmeq->cq_lock, flags);
-		nvme_process_cq(nvmeq, &start, &end, -1);
-		spin_unlock_irqrestore(&nvmeq->cq_lock, flags);
-
-		nvme_complete_cqes(nvmeq, start, end);
-	}
+	if (error)
+		set_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags);
 
 	nvme_del_queue_end(req, error);
 }
@@ -1999,77 +2275,80 @@
 	cmd.delete_queue.opcode = opcode;
 	cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
-	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
+	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	req->timeout = ADMIN_TIMEOUT;
 	req->end_io_data = nvmeq;
 
+	init_completion(&nvmeq->delete_done);
 	blk_execute_rq_nowait(q, NULL, req, false,
 			opcode == nvme_admin_delete_cq ?
 				nvme_del_cq_end : nvme_del_queue_end);
 	return 0;
 }
 
-static void nvme_disable_io_queues(struct nvme_dev *dev)
+static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
 {
-	int pass, queues = dev->online_queues - 1;
+	int nr_queues = dev->online_queues - 1, sent = 0;
 	unsigned long timeout;
-	u8 opcode = nvme_admin_delete_sq;
 
-	for (pass = 0; pass < 2; pass++) {
-		int sent = 0, i = queues;
-
-		reinit_completion(&dev->ioq_wait);
  retry:
-		timeout = ADMIN_TIMEOUT;
-		for (; i > 0; i--, sent++)
-			if (nvme_delete_queue(&dev->queues[i], opcode))
-				break;
-
-		while (sent--) {
-			timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout);
-			if (timeout == 0)
-				return;
-			if (i)
-				goto retry;
-		}
-		opcode = nvme_admin_delete_cq;
+	timeout = ADMIN_TIMEOUT;
+	while (nr_queues > 0) {
+		if (nvme_delete_queue(&dev->queues[nr_queues], opcode))
+			break;
+		nr_queues--;
+		sent++;
 	}
+	while (sent) {
+		struct nvme_queue *nvmeq = &dev->queues[nr_queues + sent];
+
+		timeout = wait_for_completion_io_timeout(&nvmeq->delete_done,
+				timeout);
+		if (timeout == 0)
+			return false;
+
+		sent--;
+		if (nr_queues)
+			goto retry;
+	}
+	return true;
 }
 
-/*
- * return error value only when tagset allocation failed
- */
-static int nvme_dev_add(struct nvme_dev *dev)
+static void nvme_dev_add(struct nvme_dev *dev)
 {
 	int ret;
 
 	if (!dev->ctrl.tagset) {
 		dev->tagset.ops = &nvme_mq_ops;
 		dev->tagset.nr_hw_queues = dev->online_queues - 1;
+		dev->tagset.nr_maps = 2; /* default + read */
+		if (dev->io_queues[HCTX_TYPE_POLL])
+			dev->tagset.nr_maps++;
 		dev->tagset.timeout = NVME_IO_TIMEOUT;
-		dev->tagset.numa_node = dev_to_node(dev->dev);
-		dev->tagset.queue_depth =
-				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
-		dev->tagset.cmd_size = nvme_pci_cmd_size(dev, false);
-		if ((dev->ctrl.sgls & ((1 << 0) | (1 << 1))) && sgl_threshold) {
-			dev->tagset.cmd_size = max(dev->tagset.cmd_size,
-					nvme_pci_cmd_size(dev, true));
-		}
+		dev->tagset.numa_node = dev->ctrl.numa_node;
+		dev->tagset.queue_depth = min_t(unsigned int, dev->q_depth,
+						BLK_MQ_MAX_DEPTH) - 1;
+		dev->tagset.cmd_size = sizeof(struct nvme_iod);
 		dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
 		dev->tagset.driver_data = dev;
+
+		/*
+		 * Some Apple controllers requires tags to be unique
+		 * across admin and IO queue, so reserve the first 32
+		 * tags of the IO queue.
+		 */
+		if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
+			dev->tagset.reserved_tags = NVME_AQ_DEPTH;
 
 		ret = blk_mq_alloc_tag_set(&dev->tagset);
 		if (ret) {
 			dev_warn(dev->ctrl.device,
 				"IO queues tagset allocation failed %d\n", ret);
-			return ret;
+			return;
 		}
 		dev->ctrl.tagset = &dev->tagset;
-
-		nvme_dbbuf_set(dev);
 	} else {
 		blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
 
@@ -2077,7 +2356,7 @@
 		nvme_free_queues(dev, dev->online_queues);
 	}
 
-	return 0;
+	nvme_dbbuf_set(dev);
 }
 
 static int nvme_pci_enable(struct nvme_dev *dev)
@@ -2090,8 +2369,7 @@
 
 	pci_set_master(pdev);
 
-	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
-	    dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
+	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)))
 		goto disable;
 
 	if (readl(dev->bar + NVME_REG_CSTS) == -1) {
@@ -2110,10 +2388,24 @@
 
 	dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
-	dev->q_depth = min_t(int, NVME_CAP_MQES(dev->ctrl.cap) + 1,
+	if (dev->ctrl.quirks & NVME_QUIRK_LIMIT_IOQD32)
+		io_queue_depth = 32;
+
+	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
+	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
 	dev->dbs = dev->bar + 4096;
+
+	/*
+	 * Some Apple controllers require a non-standard SQE size.
+	 * Interestingly they also seem to ignore the CC:IOSQES register
+	 * so we don't bother updating it here.
+	 */
+	if (dev->ctrl.quirks & NVME_QUIRK_128_BYTES_SQES)
+		dev->io_sqes = 7;
+	else
+		dev->io_sqes = NVME_NVM_IOSQES;
 
 	/*
 	 * Temporary fix for the Apple controller found in the MacBook8,1 and
@@ -2131,6 +2423,18 @@
 		dev_err(dev->ctrl.device, "detected PM1725 NVMe controller, "
                         "set queue depth=%u\n", dev->q_depth);
 	}
+
+	/*
+	 * Controllers with the shared tags quirk need the IO queue to be
+	 * big enough so that we get 32 tags for the admin queue
+	 */
+	if ((dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS) &&
+	    (dev->q_depth < (NVME_AQ_DEPTH + 2))) {
+		dev->q_depth = NVME_AQ_DEPTH + 2;
+		dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
+			 dev->q_depth);
+	}
+
 
 	nvme_map_cmb(dev);
 
@@ -2164,8 +2468,7 @@
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
-	int i;
-	bool dead = true;
+	bool dead = true, freeze = false;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	mutex_lock(&dev->shutdown_lock);
@@ -2173,8 +2476,10 @@
 		u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 		if (dev->ctrl.state == NVME_CTRL_LIVE ||
-		    dev->ctrl.state == NVME_CTRL_RESETTING)
+		    dev->ctrl.state == NVME_CTRL_RESETTING) {
+			freeze = true;
 			nvme_start_freeze(&dev->ctrl);
+		}
 		dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
 			pdev->error_state  != pci_channel_io_normal);
 	}
@@ -2183,10 +2488,8 @@
 	 * Give the controller a chance to complete all entered requests if
 	 * doing a safe shutdown.
 	 */
-	if (!dead) {
-		if (shutdown)
-			nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
-	}
+	if (!dead && shutdown && freeze)
+		nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
 
 	nvme_stop_queues(&dev->ctrl);
 
@@ -2194,13 +2497,15 @@
 		nvme_disable_io_queues(dev);
 		nvme_disable_admin_queue(dev, shutdown);
 	}
-	for (i = dev->ctrl.queue_count - 1; i >= 0; i--)
-		nvme_suspend_queue(&dev->queues[i]);
-
+	nvme_suspend_io_queues(dev);
+	nvme_suspend_queue(&dev->queues[0]);
 	nvme_pci_disable(dev);
+	nvme_reap_pending_cqes(dev);
 
 	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
 	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
+	blk_mq_tagset_wait_completed_request(&dev->tagset);
+	blk_mq_tagset_wait_completed_request(&dev->admin_tagset);
 
 	/*
 	 * The driver will not be starting up queues again if shutting down so
@@ -2215,10 +2520,19 @@
 	mutex_unlock(&dev->shutdown_lock);
 }
 
+static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
+{
+	if (!nvme_wait_reset(&dev->ctrl))
+		return -EBUSY;
+	nvme_dev_disable(dev, shutdown);
+	return 0;
+}
+
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
 	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
-						PAGE_SIZE, PAGE_SIZE, 0);
+						NVME_CTRL_PAGE_SIZE,
+						NVME_CTRL_PAGE_SIZE, 0);
 	if (!dev->prp_page_pool)
 		return -ENOMEM;
 
@@ -2238,26 +2552,52 @@
 	dma_pool_destroy(dev->prp_small_pool);
 }
 
+static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
+{
+	size_t npages = max(nvme_pci_npages_prp(), nvme_pci_npages_sgl());
+	size_t alloc_size = sizeof(__le64 *) * npages +
+			    sizeof(struct scatterlist) * NVME_MAX_SEGS;
+
+	WARN_ON_ONCE(alloc_size > PAGE_SIZE);
+	dev->iod_mempool = mempool_create_node(1,
+			mempool_kmalloc, mempool_kfree,
+			(void *)alloc_size, GFP_KERNEL,
+			dev_to_node(dev->dev));
+	if (!dev->iod_mempool)
+		return -ENOMEM;
+	return 0;
+}
+
+static void nvme_free_tagset(struct nvme_dev *dev)
+{
+	if (dev->tagset.tags)
+		blk_mq_free_tag_set(&dev->tagset);
+	dev->ctrl.tagset = NULL;
+}
+
+/* pairs with nvme_pci_alloc_dev */
 static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 {
 	struct nvme_dev *dev = to_nvme_dev(ctrl);
 
 	nvme_dbbuf_dma_free(dev);
-	put_device(dev->dev);
-	if (dev->tagset.tags)
-		blk_mq_free_tag_set(&dev->tagset);
+	nvme_free_tagset(dev);
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
-	kfree(dev->queues);
 	free_opal_dev(dev->ctrl.opal_dev);
 	mempool_destroy(dev->iod_mempool);
+	put_device(dev->dev);
+	kfree(dev->queues);
 	kfree(dev);
 }
 
-static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
+static void nvme_remove_dead_ctrl(struct nvme_dev *dev)
 {
-	dev_warn(dev->ctrl.device, "Removing after probe failure status: %d\n", status);
-
+	/*
+	 * Set state to deleting now to avoid blocking nvme_wait_reset(), which
+	 * may be holding this pci_dev's device lock.
+	 */
+	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 	nvme_get_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, false);
 	nvme_kill_queues(&dev->ctrl);
@@ -2271,7 +2611,6 @@
 		container_of(work, struct nvme_dev, ctrl.reset_work);
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
-	enum nvme_ctrl_state new_state = NVME_CTRL_LIVE;
 
 	if (dev->ctrl.state != NVME_CTRL_RESETTING) {
 		dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
@@ -2286,6 +2625,7 @@
 	 */
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
+	nvme_sync_queues(&dev->ctrl);
 
 	mutex_lock(&dev->shutdown_lock);
 	result = nvme_pci_enable(dev);
@@ -2300,12 +2640,21 @@
 	if (result)
 		goto out_unlock;
 
+	dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1);
+
 	/*
 	 * Limit the max command size to prevent iod->sg allocations going
 	 * over a single page.
 	 */
-	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+	dev->ctrl.max_hw_sectors = min_t(u32,
+		NVME_MAX_KB_SZ << 1, dma_max_mapping_size(dev->dev) >> 9);
 	dev->ctrl.max_segments = NVME_MAX_SEGS;
+
+	/*
+	 * Don't limit the IOMMU merged segment size.
+	 */
+	dma_set_max_seg_size(dev->dev, 0xffffffff);
+
 	mutex_unlock(&dev->shutdown_lock);
 
 	/*
@@ -2318,6 +2667,12 @@
 		result = -EBUSY;
 		goto out;
 	}
+
+	/*
+	 * We do not support an SGL for metadata (yet), so we are limited to a
+	 * single integrity segment for the separate metadata pointer.
+	 */
+	dev->ctrl.max_integrity_segments = 1;
 
 	result = nvme_init_identify(&dev->ctrl);
 	if (result)
@@ -2359,13 +2714,11 @@
 		dev_warn(dev->ctrl.device, "IO queues not created\n");
 		nvme_kill_queues(&dev->ctrl);
 		nvme_remove_namespaces(&dev->ctrl);
-		new_state = NVME_CTRL_ADMIN_ONLY;
+		nvme_free_tagset(dev);
 	} else {
 		nvme_start_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
-		/* hit this only when allocate tagset fails */
-		if (nvme_dev_add(dev))
-			new_state = NVME_CTRL_ADMIN_ONLY;
+		nvme_dev_add(dev);
 		nvme_unfreeze(&dev->ctrl);
 	}
 
@@ -2373,9 +2726,9 @@
 	 * If only admin queue live, keep it to do further investigation or
 	 * recovery.
 	 */
-	if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) {
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
 		dev_warn(dev->ctrl.device,
-			"failed to mark controller state %d\n", new_state);
+			"failed to mark controller live state\n");
 		result = -ENODEV;
 		goto out;
 	}
@@ -2386,7 +2739,10 @@
  out_unlock:
 	mutex_unlock(&dev->shutdown_lock);
  out:
-	nvme_remove_dead_ctrl(dev, result);
+	if (result)
+		dev_warn(dev->ctrl.device,
+			 "Removing after probe failure status: %d\n", result);
+	nvme_remove_dead_ctrl(dev);
 }
 
 static void nvme_remove_dead_ctrl_work(struct work_struct *work)
@@ -2421,13 +2777,14 @@
 {
 	struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
 
-	return snprintf(buf, size, "%s", dev_name(&pdev->dev));
+	return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
 }
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
-	.flags			= NVME_F_METADATA_SUPPORTED,
+	.flags			= NVME_F_METADATA_SUPPORTED |
+				  NVME_F_PCI_P2PDMA,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
@@ -2478,6 +2835,18 @@
 		    (dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") ||
 		     dmi_match(DMI_BOARD_NAME, "PRIME Z370-A")))
 			return NVME_QUIRK_NO_APST;
+	} else if ((pdev->vendor == 0x144d && (pdev->device == 0xa801 ||
+		    pdev->device == 0xa808 || pdev->device == 0xa809)) ||
+		   (pdev->vendor == 0x1e0f && pdev->device == 0x0001)) {
+		/*
+		 * Forcing to use host managed nvme power settings for
+		 * lowest idle power with quick resume latency on
+		 * Samsung and Toshiba SSDs based on suspend behavior
+		 * on Coffee Lake board for LENOVO C640
+		 */
+		if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) &&
+		     dmi_match(DMI_BOARD_NAME, "LNVNB161216"))
+			return NVME_QUIRK_SIMPLE_SUSPEND;
 	}
 
 	return 0;
@@ -2492,104 +2861,118 @@
 	nvme_put_ctrl(&dev->ctrl);
 }
 
-static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
+		const struct pci_device_id *id)
 {
-	int node, result = -ENOMEM;
-	struct nvme_dev *dev;
 	unsigned long quirks = id->driver_data;
-	size_t alloc_size;
-
-	node = dev_to_node(&pdev->dev);
-	if (node == NUMA_NO_NODE)
-		set_dev_node(&pdev->dev, first_memory_node);
+	int node = dev_to_node(&pdev->dev);
+	struct nvme_dev *dev;
+	int ret = -ENOMEM;
 
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
-		return -ENOMEM;
-
-	dev->queues = kcalloc_node(num_possible_cpus() + 1,
-			sizeof(struct nvme_queue), GFP_KERNEL, node);
-	if (!dev->queues)
-		goto free;
-
-	dev->dev = get_device(&pdev->dev);
-	pci_set_drvdata(pdev, dev);
-
-	result = nvme_dev_map(dev);
-	if (result)
-		goto put_pci;
-
+		return ERR_PTR(-ENOMEM);
 	INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work);
 	INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work);
 	mutex_init(&dev->shutdown_lock);
-	init_completion(&dev->ioq_wait);
+
+	dev->nr_write_queues = write_queues;
+	dev->nr_poll_queues = poll_queues;
+	dev->nr_allocated_queues = nvme_max_io_queues(dev) + 1;
+	dev->queues = kcalloc_node(dev->nr_allocated_queues,
+			sizeof(struct nvme_queue), GFP_KERNEL, node);
+	if (!dev->queues)
+		goto out_free_dev;
+
+	dev->dev = get_device(&pdev->dev);
+
+	quirks |= check_vendor_combination_bug(pdev);
+	if (!noacpi && acpi_storage_d3(&pdev->dev)) {
+		/*
+		 * Some systems use a bios work around to ask for D3 on
+		 * platforms that support kernel managed suspend.
+		 */
+		dev_info(&pdev->dev,
+			 "platform quirk: setting simple suspend\n");
+		quirks |= NVME_QUIRK_SIMPLE_SUSPEND;
+	}
+	ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
+			     quirks);
+	if (ret)
+		goto out_put_device;
+	return dev;
+
+out_put_device:
+	put_device(dev->dev);
+	kfree(dev->queues);
+out_free_dev:
+	kfree(dev);
+	return ERR_PTR(ret);
+}
+
+static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct nvme_dev *dev;
+	int result = -ENOMEM;
+
+	dev = nvme_pci_alloc_dev(pdev, id);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	result = nvme_dev_map(dev);
+	if (result)
+		goto out_uninit_ctrl;
 
 	result = nvme_setup_prp_pools(dev);
 	if (result)
-		goto unmap;
+		goto out_dev_unmap;
 
-	quirks |= check_vendor_combination_bug(pdev);
-
-	/*
-	 * Double check that our mempool alloc size will cover the biggest
-	 * command we support.
-	 */
-	alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
-						NVME_MAX_SEGS, true);
-	WARN_ON_ONCE(alloc_size > PAGE_SIZE);
-
-	dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
-						mempool_kfree,
-						(void *) alloc_size,
-						GFP_KERNEL, node);
-	if (!dev->iod_mempool) {
-		result = -ENOMEM;
-		goto release_pools;
-	}
-
-	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
-			quirks);
+	result = nvme_pci_alloc_iod_mempool(dev);
 	if (result)
-		goto release_mempool;
+		goto out_release_prp_pools;
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
+	pci_set_drvdata(pdev, dev);
 
 	nvme_reset_ctrl(&dev->ctrl);
-	nvme_get_ctrl(&dev->ctrl);
 	async_schedule(nvme_async_probe, dev);
-
 	return 0;
 
- release_mempool:
-	mempool_destroy(dev->iod_mempool);
- release_pools:
+out_release_prp_pools:
 	nvme_release_prp_pools(dev);
- unmap:
+out_dev_unmap:
 	nvme_dev_unmap(dev);
- put_pci:
-	put_device(dev->dev);
- free:
-	kfree(dev->queues);
-	kfree(dev);
+out_uninit_ctrl:
+	nvme_uninit_ctrl(&dev->ctrl);
 	return result;
 }
 
 static void nvme_reset_prepare(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_dev_disable(dev, false);
+
+	/*
+	 * We don't need to check the return value from waiting for the reset
+	 * state as pci_dev device lock is held, making it impossible to race
+	 * with ->remove().
+	 */
+	nvme_disable_prepare_reset(dev, false);
+	nvme_sync_queues(&dev->ctrl);
 }
 
 static void nvme_reset_done(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_reset_ctrl_sync(&dev->ctrl);
+
+	if (!nvme_try_sched_reset(&dev->ctrl))
+		flush_work(&dev->ctrl.reset_work);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_dev_disable(dev, true);
+
+	nvme_disable_prepare_reset(dev, true);
 }
 
 /*
@@ -2617,33 +3000,128 @@
 	nvme_free_host_mem(dev);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
-	nvme_uninit_ctrl(&dev->ctrl);
 	nvme_release_prp_pools(dev);
 	nvme_dev_unmap(dev);
-	nvme_put_ctrl(&dev->ctrl);
+	nvme_uninit_ctrl(&dev->ctrl);
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int nvme_suspend(struct device *dev)
+static int nvme_get_power_state(struct nvme_ctrl *ctrl, u32 *ps)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct nvme_dev *ndev = pci_get_drvdata(pdev);
+	return nvme_get_features(ctrl, NVME_FEAT_POWER_MGMT, 0, NULL, 0, ps);
+}
 
-	nvme_dev_disable(ndev, true);
-	return 0;
+static int nvme_set_power_state(struct nvme_ctrl *ctrl, u32 ps)
+{
+	return nvme_set_features(ctrl, NVME_FEAT_POWER_MGMT, ps, NULL, 0, NULL);
 }
 
 static int nvme_resume(struct device *dev)
 {
+	struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
+	struct nvme_ctrl *ctrl = &ndev->ctrl;
+
+	if (ndev->last_ps == U32_MAX ||
+	    nvme_set_power_state(ctrl, ndev->last_ps) != 0)
+		return nvme_try_sched_reset(&ndev->ctrl);
+	return 0;
+}
+
+static int nvme_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct nvme_dev *ndev = pci_get_drvdata(pdev);
+	struct nvme_ctrl *ctrl = &ndev->ctrl;
+	int ret = -EBUSY;
+
+	ndev->last_ps = U32_MAX;
+
+	/*
+	 * The platform does not remove power for a kernel managed suspend so
+	 * use host managed nvme power settings for lowest idle power if
+	 * possible. This should have quicker resume latency than a full device
+	 * shutdown.  But if the firmware is involved after the suspend or the
+	 * device does not support any non-default power states, shut down the
+	 * device fully.
+	 *
+	 * If ASPM is not enabled for the device, shut down the device and allow
+	 * the PCI bus layer to put it into D3 in order to take the PCIe link
+	 * down, so as to allow the platform to achieve its minimum low-power
+	 * state (which may not be possible if the link is up).
+	 *
+	 * If a host memory buffer is enabled, shut down the device as the NVMe
+	 * specification allows the device to access the host memory buffer in
+	 * host DRAM from all power states, but hosts will fail access to DRAM
+	 * during S3.
+	 */
+	if (pm_suspend_via_firmware() || !ctrl->npss ||
+	    !pcie_aspm_enabled(pdev) ||
+	    ndev->nr_host_mem_descs ||
+	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
+		return nvme_disable_prepare_reset(ndev, true);
+
+	nvme_start_freeze(ctrl);
+	nvme_wait_freeze(ctrl);
+	nvme_sync_queues(ctrl);
+
+	if (ctrl->state != NVME_CTRL_LIVE)
+		goto unfreeze;
+
+	ret = nvme_get_power_state(ctrl, &ndev->last_ps);
+	if (ret < 0)
+		goto unfreeze;
+
+	/*
+	 * A saved state prevents pci pm from generically controlling the
+	 * device's power. If we're using protocol specific settings, we don't
+	 * want pci interfering.
+	 */
+	pci_save_state(pdev);
+
+	ret = nvme_set_power_state(ctrl, ctrl->npss);
+	if (ret < 0)
+		goto unfreeze;
+
+	if (ret) {
+		/* discard the saved state */
+		pci_load_saved_state(pdev, NULL);
+
+		/*
+		 * Clearing npss forces a controller reset on resume. The
+		 * correct value will be rediscovered then.
+		 */
+		ret = nvme_disable_prepare_reset(ndev, true);
+		ctrl->npss = 0;
+	}
+unfreeze:
+	nvme_unfreeze(ctrl);
+	return ret;
+}
+
+static int nvme_simple_suspend(struct device *dev)
+{
+	struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
+
+	return nvme_disable_prepare_reset(ndev, true);
+}
+
+static int nvme_simple_resume(struct device *dev)
+{
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-	nvme_reset_ctrl(&ndev->ctrl);
-	return 0;
+	return nvme_try_sched_reset(&ndev->ctrl);
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
+static const struct dev_pm_ops nvme_dev_pm_ops = {
+	.suspend	= nvme_suspend,
+	.resume		= nvme_resume,
+	.freeze		= nvme_simple_suspend,
+	.thaw		= nvme_simple_resume,
+	.poweroff	= nvme_simple_suspend,
+	.restore	= nvme_simple_resume,
+};
+#endif /* CONFIG_PM_SLEEP */
 
 static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
 						pci_channel_state_t state)
@@ -2686,7 +3164,6 @@
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
 	flush_work(&dev->ctrl.reset_work);
-	pci_cleanup_aer_uncorrect_error_status(pdev);
 }
 
 static const struct pci_error_handlers nvme_err_handler = {
@@ -2698,25 +3175,37 @@
 };
 
 static const struct pci_device_id nvme_id_table[] = {
-	{ PCI_VDEVICE(INTEL, 0x0953),
+	{ PCI_VDEVICE(INTEL, 0x0953),	/* Intel 750/P3500/P3600/P3700 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
-	{ PCI_VDEVICE(INTEL, 0x0a53),
+	{ PCI_VDEVICE(INTEL, 0x0a53),	/* Intel P3520 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
-	{ PCI_VDEVICE(INTEL, 0x0a54),
+	{ PCI_VDEVICE(INTEL, 0x0a54),	/* Intel P4500/P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DEALLOCATE_ZEROES, },
-	{ PCI_VDEVICE(INTEL, 0x0a55),
+				NVME_QUIRK_DEALLOCATE_ZEROES |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_VDEVICE(INTEL, 0x0a55),	/* Dell Express Flash P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
-				NVME_QUIRK_MEDIUM_PRIO_SQ },
+				NVME_QUIRK_MEDIUM_PRIO_SQ |
+				NVME_QUIRK_NO_TEMP_THRESH_CHANGE |
+				NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_VDEVICE(INTEL, 0xf1a6),	/* Intel 760p/Pro 7600p */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
-		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+		.driver_data = NVME_QUIRK_IDENTIFY_CNS |
+				NVME_QUIRK_DISABLE_WRITE_ZEROES |
+				NVME_QUIRK_BOGUS_NID, },
+	{ PCI_VDEVICE(REDHAT, 0x0010),	/* Qemu emulated controller */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x126f, 0x2263),	/* Silicon Motion unidentified */
+		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST, },
 	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
-		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+				NVME_QUIRK_NO_NS_DESC_LIST, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c58, 0x0023),	/* WDC SN200 adapter */
@@ -2726,18 +3215,50 @@
 	{ PCI_DEVICE(0x144d, 0xa821),   /* Samsung PM1725 */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x144d, 0xa822),   /* Samsung PM1725a */
-		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+				NVME_QUIRK_DISABLE_WRITE_ZEROES|
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1987, 0x5013),	/* Phison E13 */
+		.driver_data = NVME_QUIRK_LIMIT_IOQD32},
+	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
+				NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1b4b, 0x1092),	/* Lexar 256 GB SSD */
+		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1d1d, 0x1f1f),	/* LighNVM qemu device */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
-	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
+	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
+				NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	 { PCI_DEVICE(0x1344, 0x5407), /* Micron Technology Inc NVMe SSD */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN },
+	 { PCI_DEVICE(0x1344, 0x6001),   /* Micron Nitro NVMe */
+		 .driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x2646, 0x2262),   /* KINGSTON SKC2000 NVMe SSD */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0x2646, 0x2263),   /* KINGSTON A2000 NVMe SSD  */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
-	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
+		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
+		.driver_data = NVME_QUIRK_SINGLE_VECTOR |
+				NVME_QUIRK_128_BYTES_SQES |
+				NVME_QUIRK_SHARED_TAGS |
+				NVME_QUIRK_SKIP_CID_GEN },
+	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, nvme_id_table);
@@ -2748,15 +3269,22 @@
 	.probe		= nvme_probe,
 	.remove		= nvme_remove,
 	.shutdown	= nvme_shutdown,
+#ifdef CONFIG_PM_SLEEP
 	.driver		= {
 		.pm	= &nvme_dev_pm_ops,
 	},
+#endif
 	.sriov_configure = pci_sriov_configure_simple,
 	.err_handler	= &nvme_err_handler,
 };
 
 static int __init nvme_init(void)
 {
+	BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
+	BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2);
+
 	return pci_register_driver(&nvme_driver);
 }
 
@@ -2764,7 +3292,6 @@
 {
 	pci_unregister_driver(&nvme_driver);
 	flush_workqueue(nvme_wq);
-	_nvme_check_size();
 }
 
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");

--
Gitblit v1.6.2