From: Leon Romanovsky <leon@kernel.org>
To: Marek Szyprowski <m.szyprowski@samsung.com>,
Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
Keith Busch <kbusch@kernel.org>
Cc: "Jake Edge" <jake@lwn.net>, "Jonathan Corbet" <corbet@lwn.net>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Zhu Yanjun" <zyjzyj2000@gmail.com>,
"Robin Murphy" <robin.murphy@arm.com>,
"Joerg Roedel" <joro@8bytes.org>, "Will Deacon" <will@kernel.org>,
"Sagi Grimberg" <sagi@grimberg.me>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Logan Gunthorpe" <logang@deltatee.com>,
"Yishai Hadas" <yishaih@nvidia.com>,
"Shameer Kolothum" <shameerali.kolothum.thodi@huawei.com>,
"Kevin Tian" <kevin.tian@intel.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
iommu@lists.linux.dev, linux-nvme@lists.infradead.org,
linux-pci@vger.kernel.org, kvm@vger.kernel.org,
linux-mm@kvack.org, "Niklas Schnelle" <schnelle@linux.ibm.com>,
"Chuck Lever" <chuck.lever@oracle.com>,
"Luis Chamberlain" <mcgrof@kernel.org>,
"Matthew Wilcox" <willy@infradead.org>,
"Dan Williams" <dan.j.williams@intel.com>,
"Kanchan Joshi" <joshi.k@samsung.com>,
"Chaitanya Kulkarni" <kch@nvidia.com>,
"Leon Romanovsky" <leonro@nvidia.com>
Subject: [PATCH v10 22/24] nvme-pci: use a better encoding for small prp pool allocations
Date: Mon, 28 Apr 2025 12:22:28 +0300 [thread overview]
Message-ID: <e34650ec5a9de3f30079aa432dffa663298f67e7.1745831017.git.leon@kernel.org> (raw)
In-Reply-To: <cover.1745831017.git.leon@kernel.org>
From: Christoph Hellwig <hch@lst.de>
There is plenty of unused space in the iod next to nr_descriptors.
Add a separate flag to encode that the transfer is using the full
page sized pool, and use a normal 0..n count for the number of
descriptors.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Jens Axboe <axboe@kernel.dk>
[ Leon: changed original bool variable to be flag as was proposed by Kanchan ]
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/nvme/host/pci.c | 94 ++++++++++++++++++++---------------------
1 file changed, 47 insertions(+), 47 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 638e759b29ad..270fb5146b5b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -44,6 +44,7 @@
#define NVME_MAX_SEGS 128
#define NVME_MAX_META_SEGS 15
#define NVME_MAX_NR_DESCRIPTORS 5
+#define NVME_SMALL_DESCRIPTOR_SIZE 256
static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0444);
@@ -219,6 +220,10 @@ struct nvme_queue {
struct completion delete_done;
};
+enum {
+ IOD_LARGE_DESCRIPTORS = 1 << 0, /* uses the full page sized descriptor pool */
+};
+
/*
* The nvme_iod describes the data in an I/O.
*/
@@ -226,8 +231,8 @@ struct nvme_iod {
struct nvme_request req;
struct nvme_command cmd;
bool aborted;
- /* # of PRP/SGL descriptors: (0 for small pool) */
- s8 nr_descriptors;
+ u8 nr_descriptors; /* # of PRP/SGL descriptors */
+ u8 flags;
unsigned int dma_len; /* length of single DMA segment mapping */
dma_addr_t first_dma;
dma_addr_t meta_dma;
@@ -529,13 +534,27 @@ 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_dev *dev,
+ struct nvme_iod *iod)
+{
+ if (iod->flags & IOD_LARGE_DESCRIPTORS)
+ return dev->prp_page_pool;
+ return dev->prp_small_pool;
+}
+
+static void nvme_free_descriptors(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);
dma_addr_t dma_addr = iod->first_dma;
int i;
+ if (iod->nr_descriptors == 1) {
+ dma_pool_free(nvme_dma_pool(dev, 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]);
@@ -558,15 +577,7 @@ 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_descriptors == 0)
- dma_pool_free(dev->prp_small_pool, iod->descriptors[0],
- iod->first_dma);
- else if (iod->nr_descriptors == 1)
- dma_pool_free(dev->prp_page_pool, iod->descriptors[0],
- iod->first_dma);
- else
- nvme_free_prps(dev, req);
+ nvme_free_descriptors(dev, req);
mempool_free(iod->sgt.sgl, dev->iod_mempool);
}
@@ -588,7 +599,6 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
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);
@@ -596,7 +606,7 @@ 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) {
@@ -618,27 +628,23 @@ 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_descriptors = 0;
- } else {
- pool = dev->prp_page_pool;
- iod->nr_descriptors = 1;
- }
+ if (DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE) >
+ NVME_SMALL_DESCRIPTOR_SIZE / sizeof(__le64))
+ iod->flags |= IOD_LARGE_DESCRIPTORS;
- prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
- if (!prp_list) {
- iod->nr_descriptors = -1;
+ prp_list = dma_pool_alloc(nvme_dma_pool(dev, iod), GFP_ATOMIC,
+ &prp_dma);
+ if (!prp_list)
return BLK_STS_RESOURCE;
- }
- iod->descriptors[0] = 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(dev->prp_page_pool,
+ GFP_ATOMIC, &prp_dma);
if (!prp_list)
goto free_prps;
iod->descriptors[iod->nr_descriptors++] = prp_list;
@@ -665,7 +671,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
return BLK_STS_OK;
free_prps:
- nvme_free_prps(dev, req);
+ nvme_free_descriptors(dev, req);
return BLK_STS_RESOURCE;
bad_sgl:
WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents),
@@ -694,7 +700,6 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
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;
@@ -709,21 +714,13 @@ 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_descriptors = 0;
- } else {
- pool = dev->prp_page_pool;
- iod->nr_descriptors = 1;
- }
+ if (entries > NVME_SMALL_DESCRIPTOR_SIZE / sizeof(*sg_list))
+ iod->flags |= IOD_LARGE_DESCRIPTORS;
- sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
- if (!sg_list) {
- iod->nr_descriptors = -1;
+ sg_list = dma_pool_alloc(nvme_dma_pool(dev, iod), GFP_ATOMIC, &sgl_dma);
+ if (!sg_list)
return BLK_STS_RESOURCE;
- }
-
- iod->descriptors[0] = 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);
@@ -915,7 +912,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
blk_status_t ret;
iod->aborted = false;
- iod->nr_descriptors = -1;
+ iod->nr_descriptors = 0;
+ iod->flags = 0;
iod->sgt.nents = 0;
iod->meta_sgt.nents = 0;
@@ -2833,7 +2831,7 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
static int nvme_setup_prp_pools(struct nvme_dev *dev)
{
- size_t small_align = 256;
+ size_t small_align = NVME_SMALL_DESCRIPTOR_SIZE;
dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
NVME_CTRL_PAGE_SIZE,
@@ -2841,12 +2839,14 @@ static int nvme_setup_prp_pools(struct nvme_dev *dev)
if (!dev->prp_page_pool)
return -ENOMEM;
+ BUILD_BUG_ON(NVME_SMALL_DESCRIPTOR_SIZE != 256);
if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512)
- small_align = 512;
+ small_align *= 2;
/* Optimisation for I/Os between 4k and 128k */
dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev,
- 256, small_align, 0);
+ NVME_SMALL_DESCRIPTOR_SIZE,
+ small_align, 0);
if (!dev->prp_small_pool) {
dma_pool_destroy(dev->prp_page_pool);
return -ENOMEM;
--
2.49.0
next prev parent reply other threads:[~2025-04-28 9:24 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-28 9:22 [PATCH v10 00/24] Provide a new two step DMA mapping API Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 01/24] PCI/P2PDMA: Refactor the p2pdma mapping helpers Leon Romanovsky
2025-04-29 2:08 ` Baolu Lu
2025-04-28 9:22 ` [PATCH v10 02/24] dma-mapping: move the PCI P2PDMA mapping helpers to pci-p2pdma.h Leon Romanovsky
2025-04-29 2:09 ` Baolu Lu
2025-04-28 9:22 ` [PATCH v10 03/24] iommu: generalize the batched sync after map interface Leon Romanovsky
2025-04-29 2:19 ` Baolu Lu
2025-04-29 6:09 ` Leon Romanovsky
2025-04-29 11:53 ` Jason Gunthorpe
2025-04-28 9:22 ` [PATCH v10 04/24] iommu: add kernel-doc for iommu_unmap_fast Leon Romanovsky
2025-04-29 2:37 ` Baolu Lu
2025-04-28 9:22 ` [PATCH v10 05/24] dma-mapping: Provide an interface to allow allocate IOVA Leon Romanovsky
2025-04-29 3:10 ` Baolu Lu
2025-04-29 5:46 ` Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 06/24] iommu/dma: Factor out a iommu_dma_map_swiotlb helper Leon Romanovsky
2025-04-29 4:58 ` Baolu Lu
2025-04-29 5:53 ` Leon Romanovsky
2025-04-29 5:58 ` Baolu Lu
2025-04-29 6:18 ` Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 07/24] dma-mapping: Implement link/unlink ranges API Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 08/24] dma-mapping: add a dma_need_unmap helper Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 09/24] docs: core-api: document the IOVA-based API Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 10/24] mm/hmm: let users to tag specific PFN with DMA mapped bit Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 11/24] mm/hmm: provide generic DMA managing logic Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 12/24] RDMA/umem: Store ODP access mask information in PFN Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 13/24] RDMA/core: Convert UMEM ODP DMA mapping to caching IOVA and page linkage Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 14/24] RDMA/umem: Separate implicit ODP initialization from explicit ODP Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 15/24] vfio/mlx5: Explicitly use number of pages instead of allocated length Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 16/24] vfio/mlx5: Rewrite create mkey flow to allow better code reuse Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 17/24] vfio/mlx5: Enable the DMA link API Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 18/24] block: share more code for bio addition helper Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 19/24] block: don't merge different kinds of P2P transfers in a single bio Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 20/24] blk-mq: add scatterlist-less DMA mapping helpers Leon Romanovsky
2025-04-28 9:22 ` [PATCH v10 21/24] nvme-pci: remove struct nvme_descriptor Leon Romanovsky
2025-04-28 9:22 ` Leon Romanovsky [this message]
2025-04-28 9:22 ` [PATCH v10 23/24] nvme-pci: convert to blk_rq_dma_map Leon Romanovsky
2025-04-28 16:46 ` Keith Busch
2025-04-28 17:22 ` Leon Romanovsky
2025-04-28 17:30 ` Keith Busch
2025-04-28 9:22 ` [PATCH v10 24/24] nvme-pci: store aborted state in flags variable Leon Romanovsky
2025-05-12 10:07 ` (subset) [PATCH v10 00/24] Provide a new two step DMA mapping API Leon Romanovsky
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=e34650ec5a9de3f30079aa432dffa663298f67e7.1745831017.git.leon@kernel.org \
--to=leon@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=axboe@kernel.dk \
--cc=bhelgaas@google.com \
--cc=chuck.lever@oracle.com \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=hch@lst.de \
--cc=iommu@lists.linux.dev \
--cc=jake@lwn.net \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=joro@8bytes.org \
--cc=joshi.k@samsung.com \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=leonro@nvidia.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=m.szyprowski@samsung.com \
--cc=mcgrof@kernel.org \
--cc=robin.murphy@arm.com \
--cc=sagi@grimberg.me \
--cc=schnelle@linux.ibm.com \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=yishaih@nvidia.com \
--cc=zyjzyj2000@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox