diff mbox series

[v3,10/20] nvme-pci: convert to using dma_map_sgtable()

Message ID 20210916234100.122368-11-logang@deltatee.com (mailing list archive)
State New
Headers show
Series Userspace P2PDMA with O_DIRECT NVMe devices | expand

Commit Message

Logan Gunthorpe Sept. 16, 2021, 11:40 p.m. UTC 
The dma_map operations now support P2PDMA pages directly. So remove
the calls to pci_p2pdma_[un]map_sg_attrs() and replace them with calls
to dma_map_sgtable().

dma_map_sgtable() returns more complete error codes than dma_map_sg()
and allows differentiating EREMOTEIO errors in case an unsupported
P2PDMA transfer is requested. When this happens, return BLK_STS_TARGET
so the request isn't retried.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
---
 drivers/nvme/host/pci.c | 69 +++++++++++++++++------------------------
 1 file changed, 29 insertions(+), 40 deletions(-)

Comments

Max Gurtovoy Oct. 5, 2021, 10:29 p.m. UTC | #1 
Logan,

On 9/17/2021 2:40 AM, Logan Gunthorpe wrote:
> The dma_map operations now support P2PDMA pages directly. So remove
> the calls to pci_p2pdma_[un]map_sg_attrs() and replace them with calls
> to dma_map_sgtable().
>
> dma_map_sgtable() returns more complete error codes than dma_map_sg()
> and allows differentiating EREMOTEIO errors in case an unsupported
> P2PDMA transfer is requested. When this happens, return BLK_STS_TARGET
> so the request isn't retried.
>
> Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
> ---
>   drivers/nvme/host/pci.c | 69 +++++++++++++++++------------------------
>   1 file changed, 29 insertions(+), 40 deletions(-)

Looks good,

Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
diff mbox series

Patch

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 7d1ef66eac2e..e2cd73129a88 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -228,11 +228,10 @@  struct nvme_iod {
 	bool use_sgl;
 	int aborted;
 	int npages;		/* In the PRP list. 0 means small pool in use */
-	int nents;		/* Used in scatterlist */
 	dma_addr_t first_dma;
 	unsigned int dma_len;	/* length of single DMA segment mapping */
 	dma_addr_t meta_dma;
-	struct scatterlist *sg;
+	struct sg_table sgt;
 };
 
 static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev)
@@ -523,7 +522,7 @@  static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
 static void **nvme_pci_iod_list(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	return (void **)(iod->sg + blk_rq_nr_phys_segments(req));
+	return (void **)(iod->sgt.sgl + blk_rq_nr_phys_segments(req));
 }
 
 static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
@@ -575,17 +574,6 @@  static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
 	}
 }
 
-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);
@@ -596,9 +584,10 @@  static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		return;
 	}
 
-	WARN_ON_ONCE(!iod->nents);
+	WARN_ON_ONCE(!iod->sgt.nents);
+
+	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
 
-	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);
@@ -606,7 +595,7 @@  static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		nvme_free_sgls(dev, req);
 	else
 		nvme_free_prps(dev, req);
-	mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 }
 
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
@@ -629,7 +618,7 @@  static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 	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->sg;
+	struct scatterlist *sg = iod->sgt.sgl;
 	int dma_len = sg_dma_len(sg);
 	u64 dma_addr = sg_dma_address(sg);
 	int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1);
@@ -702,16 +691,16 @@  static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 		dma_len = sg_dma_len(sg);
 	}
 done:
-	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sgt.sgl));
 	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
 	return BLK_STS_OK;
 free_prps:
 	nvme_free_prps(dev, req);
 	return BLK_STS_RESOURCE;
 bad_sgl:
-	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+	WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents),
 			"Invalid SGL for payload:%d nents:%d\n",
-			blk_rq_payload_bytes(req), iod->nents);
+			blk_rq_payload_bytes(req), iod->sgt.nents);
 	return BLK_STS_IOERR;
 }
 
@@ -737,12 +726,13 @@  static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
 }
 
 static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
-		struct request *req, struct nvme_rw_command *cmd, int entries)
+		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->sg;
+	struct scatterlist *sg = iod->sgt.sgl;
+	int entries = iod->sgt.nents;
 	dma_addr_t sgl_dma;
 	int i = 0;
 
@@ -840,7 +830,7 @@  static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	blk_status_t ret = BLK_STS_RESOURCE;
-	int nr_mapped;
+	int rc;
 
 	if (blk_rq_nr_phys_segments(req) == 1) {
 		struct bio_vec bv = req_bvec(req);
@@ -858,26 +848,25 @@  static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	}
 
 	iod->dma_len = 0;
-	iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
-	if (!iod->sg)
+	iod->sgt.sgl = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
+	if (!iod->sgt.sgl)
 		return BLK_STS_RESOURCE;
-	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
-	iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
-	if (!iod->nents)
+	sg_init_table(iod->sgt.sgl, blk_rq_nr_phys_segments(req));
+	iod->sgt.orig_nents = blk_rq_map_sg(req->q, req, iod->sgt.sgl);
+	if (!iod->sgt.orig_nents)
 		goto out_free_sg;
 
-	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)
+	rc = dma_map_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req),
+			     DMA_ATTR_NO_WARN);
+	if (rc) {
+		if (rc == -EREMOTEIO)
+			ret = BLK_STS_TARGET;
 		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);
+		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw);
 	else
 		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
 	if (ret != BLK_STS_OK)
@@ -885,9 +874,9 @@  static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	return BLK_STS_OK;
 
 out_unmap_sg:
-	nvme_unmap_sg(dev, req);
+	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
 out_free_sg:
-	mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 	return ret;
 }
 
@@ -920,7 +909,7 @@  static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	iod->aborted = 0;
 	iod->npages = -1;
-	iod->nents = 0;
+	iod->sgt.nents = 0;
 
 	/*
 	 * We should not need to do this, but we're still using this to