1 files changed, 167 insertions, 133 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index f1dd804151b1..e0bfe04a2bc2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/nodemask.h>
 #include <linux/once.h>
 #include <linux/pci.h>
 #include <linux/suspend.h>
@@ -34,16 +35,31 @@
 #define SQ_SIZE(q)	((q)->q_depth << (q)->sqes)
 #define CQ_SIZE(q)	((q)->q_depth * sizeof(struct nvme_completion))
 
-#define SGES_PER_PAGE	(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+/* Optimisation for I/Os between 4k and 128k */
+#define NVME_SMALL_POOL_SIZE	256
 
 /*
  * These can be higher, but we need to ensure that any command doesn't
  * require an sg allocation that needs more than a page of data.
  */
 #define NVME_MAX_KB_SZ	8192
-#define NVME_MAX_SEGS	128
-#define NVME_MAX_META_SEGS 15
-#define NVME_MAX_NR_ALLOCATIONS	5
+#define NVME_MAX_NR_DESCRIPTORS	5
+
+/*
+ * For data SGLs we support a single descriptors worth of SGL entries, but for
+ * now we also limit it to avoid an allocation larger than PAGE_SIZE for the
+ * scatterlist.
+ */
+#define NVME_MAX_SEGS \
+	min(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc), \
+	    (PAGE_SIZE / sizeof(struct scatterlist)))
+
+/*
+ * For metadata SGLs, only the small descriptor is supported, and the first
+ * entry is the segment descriptor, which for the data pointer sits in the SQE.
+ */
+#define NVME_MAX_META_SEGS \
+	((NVME_SMALL_POOL_SIZE / sizeof(struct nvme_sgl_desc)) - 1)
 
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0444);
@@ -112,6 +128,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
 static void nvme_delete_io_queues(struct nvme_dev *dev);
 static void nvme_update_attrs(struct nvme_dev *dev);
 
+struct nvme_descriptor_pools {
+	struct dma_pool *large;
+	struct dma_pool *small;
+};
+
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
  */
@@ -121,8 +142,6 @@ struct nvme_dev {
 	struct blk_mq_tag_set admin_tagset;
 	u32 __iomem *dbs;
 	struct device *dev;
-	struct dma_pool *prp_page_pool;
-	struct dma_pool *prp_small_pool;
 	unsigned online_queues;
 	unsigned max_qid;
 	unsigned io_queues[HCTX_MAX_TYPES];
@@ -162,6 +181,7 @@ struct nvme_dev {
 	unsigned int nr_allocated_queues;
 	unsigned int nr_write_queues;
 	unsigned int nr_poll_queues;
+	struct nvme_descriptor_pools descriptor_pools[];
 };
 
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
@@ -191,6 +211,7 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
  */
 struct nvme_queue {
 	struct nvme_dev *dev;
+	struct nvme_descriptor_pools descriptor_pools;
 	spinlock_t sq_lock;
 	void *sq_cmds;
 	 /* only used for poll queues: */
@@ -219,30 +240,30 @@ struct nvme_queue {
 	struct completion delete_done;
 };
 
-union nvme_descriptor {
-	struct nvme_sgl_desc	*sg_list;
-	__le64			*prp_list;
+/* bits for iod->flags */
+enum nvme_iod_flags {
+	/* this command has been aborted by the timeout handler */
+	IOD_ABORTED		= 1U << 0,
+
+	/* uses the small descriptor pool */
+	IOD_SMALL_DESCRIPTOR		= 1U << 1,
 };
 
 /*
  * 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;
-	bool aborted;
-	s8 nr_allocations;	/* PRP list pool allocations. 0 means small
-				   pool in use */
+	u8 flags;
+	u8 nr_descriptors;
 	unsigned int dma_len;	/* length of single DMA segment mapping */
 	dma_addr_t first_dma;
 	dma_addr_t meta_dma;
 	struct sg_table sgt;
 	struct sg_table meta_sgt;
-	union nvme_descriptor meta_list;
-	union nvme_descriptor list[NVME_MAX_NR_ALLOCATIONS];
+	struct nvme_sgl_desc *meta_descriptor;
+	void *descriptors[NVME_MAX_NR_DESCRIPTORS];
 };
 
 static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev)
@@ -397,30 +418,78 @@ static __always_inline int nvme_pci_npages_prp(void)
 	return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
 }
 
-static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
-				unsigned int hctx_idx)
+static struct nvme_descriptor_pools *
+nvme_setup_descriptor_pools(struct nvme_dev *dev, unsigned numa_node)
 {
-	struct nvme_dev *dev = to_nvme_dev(data);
-	struct nvme_queue *nvmeq = &dev->queues[0];
+	struct nvme_descriptor_pools *pools = &dev->descriptor_pools[numa_node];
+	size_t small_align = NVME_SMALL_POOL_SIZE;
 
-	WARN_ON(hctx_idx != 0);
-	WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
+	if (pools->small)
+		return pools; /* already initialized */
 
-	hctx->driver_data = nvmeq;
-	return 0;
+	pools->large = dma_pool_create_node("nvme descriptor page", dev->dev,
+			NVME_CTRL_PAGE_SIZE, NVME_CTRL_PAGE_SIZE, 0, numa_node);
+	if (!pools->large)
+		return ERR_PTR(-ENOMEM);
+
+	if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512)
+		small_align = 512;
+
+	pools->small = dma_pool_create_node("nvme descriptor small", dev->dev,
+			NVME_SMALL_POOL_SIZE, small_align, 0, numa_node);
+	if (!pools->small) {
+		dma_pool_destroy(pools->large);
+		pools->large = NULL;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return pools;
 }
 
-static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
-			  unsigned int hctx_idx)
+static void nvme_release_descriptor_pools(struct nvme_dev *dev)
+{
+	unsigned i;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		struct nvme_descriptor_pools *pools = &dev->descriptor_pools[i];
+
+		dma_pool_destroy(pools->large);
+		dma_pool_destroy(pools->small);
+	}
+}
+
+static int nvme_init_hctx_common(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned qid)
 {
 	struct nvme_dev *dev = to_nvme_dev(data);
-	struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1];
+	struct nvme_queue *nvmeq = &dev->queues[qid];
+	struct nvme_descriptor_pools *pools;
+	struct blk_mq_tags *tags;
+
+	tags = qid ? dev->tagset.tags[qid - 1] : dev->admin_tagset.tags[0];
+	WARN_ON(tags != hctx->tags);
+	pools = nvme_setup_descriptor_pools(dev, hctx->numa_node);
+	if (IS_ERR(pools))
+		return PTR_ERR(pools);
 
-	WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
+	nvmeq->descriptor_pools = *pools;
 	hctx->driver_data = nvmeq;
 	return 0;
 }
 
+static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+				unsigned int hctx_idx)
+{
+	WARN_ON(hctx_idx != 0);
+	return nvme_init_hctx_common(hctx, data, 0);
+}
+
+static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+			     unsigned int hctx_idx)
+{
+	return nvme_init_hctx_common(hctx, data, hctx_idx + 1);
+}
+
 static int nvme_pci_init_request(struct blk_mq_tag_set *set,
 		struct request *req, unsigned int hctx_idx,
 		unsigned int numa_node)
@@ -537,23 +606,39 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
 	return true;
 }
 
-static void nvme_free_prps(struct nvme_dev *dev, struct request *req)
+static inline struct dma_pool *nvme_dma_pool(struct nvme_queue *nvmeq,
+		struct nvme_iod *iod)
+{
+	if (iod->flags & IOD_SMALL_DESCRIPTOR)
+		return nvmeq->descriptor_pools.small;
+	return nvmeq->descriptor_pools.large;
+}
+
+static void nvme_free_descriptors(struct nvme_queue *nvmeq, struct request *req)
 {
 	const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 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->nr_allocations; i++) {
-		__le64 *prp_list = iod->list[i].prp_list;
+	if (iod->nr_descriptors == 1) {
+		dma_pool_free(nvme_dma_pool(nvmeq, iod), iod->descriptors[0],
+				dma_addr);
+		return;
+	}
+
+	for (i = 0; i < iod->nr_descriptors; i++) {
+		__le64 *prp_list = iod->descriptors[i];
 		dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]);
 
-		dma_pool_free(dev->prp_page_pool, prp_list, dma_addr);
+		dma_pool_free(nvmeq->descriptor_pools.large, prp_list,
+				dma_addr);
 		dma_addr = next_dma_addr;
 	}
 }
 
-static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
+static void nvme_unmap_data(struct nvme_dev *dev, struct nvme_queue *nvmeq,
+			    struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
@@ -566,15 +651,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 	WARN_ON_ONCE(!iod->sgt.nents);
 
 	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
-
-	if (iod->nr_allocations == 0)
-		dma_pool_free(dev->prp_small_pool, iod->list[0].sg_list,
-			      iod->first_dma);
-	else if (iod->nr_allocations == 1)
-		dma_pool_free(dev->prp_page_pool, iod->list[0].sg_list,
-			      iod->first_dma);
-	else
-		nvme_free_prps(dev, req);
+	nvme_free_descriptors(nvmeq, req);
 	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 }
 
@@ -592,11 +669,10 @@ static void nvme_print_sgl(struct scatterlist *sgl, int nents)
 	}
 }
 
-static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
+static blk_status_t nvme_pci_setup_prps(struct nvme_queue *nvmeq,
 		struct request *req, struct nvme_rw_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	struct dma_pool *pool;
 	int length = blk_rq_payload_bytes(req);
 	struct scatterlist *sg = iod->sgt.sgl;
 	int dma_len = sg_dma_len(sg);
@@ -604,7 +680,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 	int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1);
 	__le64 *prp_list;
 	dma_addr_t prp_dma;
-	int nprps, i;
+	int i;
 
 	length -= (NVME_CTRL_PAGE_SIZE - offset);
 	if (length <= 0) {
@@ -626,30 +702,26 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 		goto done;
 	}
 
-	nprps = DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE);
-	if (nprps <= (256 / 8)) {
-		pool = dev->prp_small_pool;
-		iod->nr_allocations = 0;
-	} else {
-		pool = dev->prp_page_pool;
-		iod->nr_allocations = 1;
-	}
+	if (DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE) <=
+	    NVME_SMALL_POOL_SIZE / sizeof(__le64))
+		iod->flags |= IOD_SMALL_DESCRIPTOR;
 
-	prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
-	if (!prp_list) {
-		iod->nr_allocations = -1;
+	prp_list = dma_pool_alloc(nvme_dma_pool(nvmeq, iod), GFP_ATOMIC,
+			&prp_dma);
+	if (!prp_list)
 		return BLK_STS_RESOURCE;
-	}
-	iod->list[0].prp_list = prp_list;
+	iod->descriptors[iod->nr_descriptors++] = prp_list;
 	iod->first_dma = prp_dma;
 	i = 0;
 	for (;;) {
 		if (i == NVME_CTRL_PAGE_SIZE >> 3) {
 			__le64 *old_prp_list = prp_list;
-			prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
+
+			prp_list = dma_pool_alloc(nvmeq->descriptor_pools.large,
+					GFP_ATOMIC, &prp_dma);
 			if (!prp_list)
 				goto free_prps;
-			iod->list[iod->nr_allocations++].prp_list = prp_list;
+			iod->descriptors[iod->nr_descriptors++] = prp_list;
 			prp_list[0] = old_prp_list[i - 1];
 			old_prp_list[i - 1] = cpu_to_le64(prp_dma);
 			i = 1;
@@ -673,7 +745,7 @@ done:
 	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
 	return BLK_STS_OK;
 free_prps:
-	nvme_free_prps(dev, req);
+	nvme_free_descriptors(nvmeq, req);
 	return BLK_STS_RESOURCE;
 bad_sgl:
 	WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents),
@@ -698,11 +770,10 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
 	sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
 }
 
-static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
+static blk_status_t nvme_pci_setup_sgls(struct nvme_queue *nvmeq,
 		struct request *req, struct nvme_rw_command *cmd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	struct dma_pool *pool;
 	struct nvme_sgl_desc *sg_list;
 	struct scatterlist *sg = iod->sgt.sgl;
 	unsigned int entries = iod->sgt.nents;
@@ -717,21 +788,14 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
 		return BLK_STS_OK;
 	}
 
-	if (entries <= (256 / sizeof(struct nvme_sgl_desc))) {
-		pool = dev->prp_small_pool;
-		iod->nr_allocations = 0;
-	} else {
-		pool = dev->prp_page_pool;
-		iod->nr_allocations = 1;
-	}
+	if (entries <= NVME_SMALL_POOL_SIZE / sizeof(*sg_list))
+		iod->flags |= IOD_SMALL_DESCRIPTOR;
 
-	sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
-	if (!sg_list) {
-		iod->nr_allocations = -1;
+	sg_list = dma_pool_alloc(nvme_dma_pool(nvmeq, iod), GFP_ATOMIC,
+			&sgl_dma);
+	if (!sg_list)
 		return BLK_STS_RESOURCE;
-	}
-
-	iod->list[0].sg_list = sg_list;
+	iod->descriptors[iod->nr_descriptors++] = sg_list;
 	iod->first_dma = sgl_dma;
 
 	nvme_pci_sgl_set_seg(&cmd->dptr.sgl, sgl_dma, entries);
@@ -785,12 +849,12 @@ static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		struct nvme_command *cmnd)
 {
+	struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	blk_status_t ret = BLK_STS_RESOURCE;
 	int rc;
 
 	if (blk_rq_nr_phys_segments(req) == 1) {
-		struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
 		struct bio_vec bv = req_bvec(req);
 
 		if (!is_pci_p2pdma_page(bv.bv_page)) {
@@ -825,9 +889,9 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	}
 
 	if (nvme_pci_use_sgls(dev, req, iod->sgt.nents))
-		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw);
+		ret = nvme_pci_setup_sgls(nvmeq, req, &cmnd->rw);
 	else
-		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
+		ret = nvme_pci_setup_prps(nvmeq, req, &cmnd->rw);
 	if (ret != BLK_STS_OK)
 		goto out_unmap_sg;
 	return BLK_STS_OK;
@@ -842,6 +906,7 @@ out_free_sg:
 static blk_status_t nvme_pci_setup_meta_sgls(struct nvme_dev *dev,
 					     struct request *req)
 {
+	struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_rw_command *cmnd = &iod->cmd.rw;
 	struct nvme_sgl_desc *sg_list;
@@ -865,12 +930,13 @@ static blk_status_t nvme_pci_setup_meta_sgls(struct nvme_dev *dev,
 	if (rc)
 		goto out_free_sg;
 
-	sg_list = dma_pool_alloc(dev->prp_small_pool, GFP_ATOMIC, &sgl_dma);
+	sg_list = dma_pool_alloc(nvmeq->descriptor_pools.small, GFP_ATOMIC,
+			&sgl_dma);
 	if (!sg_list)
 		goto out_unmap_sg;
 
 	entries = iod->meta_sgt.nents;
-	iod->meta_list.sg_list = sg_list;
+	iod->meta_descriptor = sg_list;
 	iod->meta_dma = sgl_dma;
 
 	cmnd->flags = NVME_CMD_SGL_METASEG;
@@ -912,7 +978,10 @@ static blk_status_t nvme_pci_setup_meta_mptr(struct nvme_dev *dev,
 
 static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req)
 {
-	if (nvme_pci_metadata_use_sgls(dev, req))
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+	if ((iod->cmd.common.flags & NVME_CMD_SGL_METABUF) &&
+	    nvme_pci_metadata_use_sgls(dev, req))
 		return nvme_pci_setup_meta_sgls(dev, req);
 	return nvme_pci_setup_meta_mptr(dev, req);
 }
@@ -922,8 +991,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	blk_status_t ret;
 
-	iod->aborted = false;
-	iod->nr_allocations = -1;
+	iod->flags = 0;
+	iod->nr_descriptors = 0;
 	iod->sgt.nents = 0;
 	iod->meta_sgt.nents = 0;
 
@@ -947,7 +1016,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	return BLK_STS_OK;
 out_unmap_data:
 	if (blk_rq_nr_phys_segments(req))
-		nvme_unmap_data(dev, req);
+		nvme_unmap_data(dev, req->mq_hctx->driver_data, req);
 out_free_cmd:
 	nvme_cleanup_cmd(req);
 	return ret;
@@ -1037,6 +1106,7 @@ static void nvme_queue_rqs(struct rq_list *rqlist)
 }
 
 static __always_inline void nvme_unmap_metadata(struct nvme_dev *dev,
+						struct nvme_queue *nvmeq,
 						struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -1048,8 +1118,8 @@ static __always_inline void nvme_unmap_metadata(struct nvme_dev *dev,
 		return;
 	}
 
-	dma_pool_free(dev->prp_small_pool, iod->meta_list.sg_list,
-		      iod->meta_dma);
+	dma_pool_free(nvmeq->descriptor_pools.small, iod->meta_descriptor,
+			iod->meta_dma);
 	dma_unmap_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req), 0);
 	mempool_free(iod->meta_sgt.sgl, dev->iod_meta_mempool);
 }
@@ -1060,10 +1130,10 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
 	struct nvme_dev *dev = nvmeq->dev;
 
 	if (blk_integrity_rq(req))
-		nvme_unmap_metadata(dev, req);
+		nvme_unmap_metadata(dev, nvmeq, req);
 
 	if (blk_rq_nr_phys_segments(req))
-		nvme_unmap_data(dev, req);
+		nvme_unmap_data(dev, nvmeq, req);
 }
 
 static void nvme_pci_complete_rq(struct request *req)
@@ -1490,7 +1560,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * returned to the driver, or if this is the admin queue.
 	 */
 	opcode = nvme_req(req)->cmd->common.opcode;
-	if (!nvmeq->qid || iod->aborted) {
+	if (!nvmeq->qid || (iod->flags & IOD_ABORTED)) {
 		dev_warn(dev->ctrl.device,
 			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
 			 req->tag, nvme_cid(req), opcode,
@@ -1503,7 +1573,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
 	}
-	iod->aborted = true;
+	iod->flags |= IOD_ABORTED;
 
 	cmd.abort.opcode = nvme_admin_abort_cmd;
 	cmd.abort.cid = nvme_cid(req);
@@ -2842,35 +2912,6 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
 	return 0;
 }
 
-static int nvme_setup_prp_pools(struct nvme_dev *dev)
-{
-	size_t small_align = 256;
-
-	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
-						NVME_CTRL_PAGE_SIZE,
-						NVME_CTRL_PAGE_SIZE, 0);
-	if (!dev->prp_page_pool)
-		return -ENOMEM;
-
-	if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512)
-		small_align = 512;
-
-	/* Optimisation for I/Os between 4k and 128k */
-	dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev,
-						256, small_align, 0);
-	if (!dev->prp_small_pool) {
-		dma_pool_destroy(dev->prp_page_pool);
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-static void nvme_release_prp_pools(struct nvme_dev *dev)
-{
-	dma_pool_destroy(dev->prp_page_pool);
-	dma_pool_destroy(dev->prp_small_pool);
-}
-
 static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
 {
 	size_t meta_size = sizeof(struct scatterlist) * (NVME_MAX_META_SEGS + 1);
@@ -3185,7 +3226,8 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 	struct nvme_dev *dev;
 	int ret = -ENOMEM;
 
-	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
+	dev = kzalloc_node(struct_size(dev, descriptor_pools, nr_node_ids),
+			GFP_KERNEL, node);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 	INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work);
@@ -3260,13 +3302,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto out_uninit_ctrl;
 
-	result = nvme_setup_prp_pools(dev);
-	if (result)
-		goto out_dev_unmap;
-
 	result = nvme_pci_alloc_iod_mempool(dev);
 	if (result)
-		goto out_release_prp_pools;
+		goto out_dev_unmap;
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
@@ -3342,8 +3380,6 @@ out_disable:
 out_release_iod_mempool:
 	mempool_destroy(dev->iod_mempool);
 	mempool_destroy(dev->iod_meta_mempool);
-out_release_prp_pools:
-	nvme_release_prp_pools(dev);
 out_dev_unmap:
 	nvme_dev_unmap(dev);
 out_uninit_ctrl:
@@ -3408,7 +3444,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_free_queues(dev, 0);
 	mempool_destroy(dev->iod_mempool);
 	mempool_destroy(dev->iod_meta_mempool);
-	nvme_release_prp_pools(dev);
+	nvme_release_descriptor_pools(dev);
 	nvme_dev_unmap(dev);
 	nvme_uninit_ctrl(&dev->ctrl);
 }
@@ -3809,9 +3845,7 @@ static int __init nvme_init(void)
 	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);
-	BUILD_BUG_ON(NVME_MAX_SEGS > SGES_PER_PAGE);
-	BUILD_BUG_ON(sizeof(struct scatterlist) * NVME_MAX_SEGS > PAGE_SIZE);
-	BUILD_BUG_ON(nvme_pci_npages_prp() > NVME_MAX_NR_ALLOCATIONS);
+	BUILD_BUG_ON(nvme_pci_npages_prp() > NVME_MAX_NR_DESCRIPTORS);
 
 	return pci_register_driver(&nvme_driver);
 }