summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-06 10:56:45 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-06 10:56:45 -0700
commitc993e07be023acdeec8e84e2e0743c52adb5fc94 (patch)
tree873b039ee47b424a31829ffcda3c316c52bf78e4 /drivers/nvme
parent1d239c1eb873c7d6c6cbc80d68330c939fd86136 (diff)
parent5c850d31880e00f063fa2a3746ba212c4bcc510f (diff)
Merge tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping updates from Christoph Hellwig: - convert arm32 to the common dma-direct code (Arnd Bergmann, Robin Murphy, Christoph Hellwig) - restructure the PCIe peer to peer mapping support (Logan Gunthorpe) - allow the IOMMU code to communicate an optional DMA mapping length and use that in scsi and libata (John Garry) - split the global swiotlb lock (Tianyu Lan) - various fixes and cleanup (Chao Gao, Dan Carpenter, Dongli Zhang, Lukas Bulwahn, Robin Murphy) * tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping: (45 commits) swiotlb: fix passing local variable to debugfs_create_ulong() dma-mapping: reformat comment to suppress htmldoc warning PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg() RDMA/rw: drop pci_p2pdma_[un]map_sg() RDMA/core: introduce ib_dma_pci_p2p_dma_supported() nvme-pci: convert to using dma_map_sgtable() nvme-pci: check DMA ops when indicating support for PCI P2PDMA iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg iommu: Explicitly skip bus address marked segments in __iommu_map_sg() dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support dma-direct: support PCI P2PDMA pages in dma-direct map_sg dma-mapping: allow EREMOTEIO return code for P2PDMA transfers PCI/P2PDMA: Introduce helpers for dma_map_sg implementations PCI/P2PDMA: Attempt to set map_type if it has not been set lib/scatterlist: add flag for indicating P2PDMA segments in an SGL swiotlb: clean up some coding style and minor issues dma-mapping: update comment after dmabounce removal scsi: sd: Add a comment about limiting max_sectors to shost optimal limit ata: libata-scsi: cap ata_device->max_sectors according to shost->max_sectors scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit ...
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/core.c3
-rw-r--r--drivers/nvme/host/nvme.h2
-rw-r--r--drivers/nvme/host/pci.c81
-rw-r--r--drivers/nvme/target/rdma.c2
4 files changed, 42 insertions, 46 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2429b11eb9a8..af367b22871b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4198,7 +4198,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
- if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
+ if (ctrl->ops->supports_pci_p2pdma &&
+ ctrl->ops->supports_pci_p2pdma(ctrl))
blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
ns->ctrl = ctrl;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bdc0ff7ed9ab..1bdf714dcd9e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -504,7 +504,6 @@ struct nvme_ctrl_ops {
unsigned int flags;
#define NVME_F_FABRICS (1 << 0)
#define NVME_F_METADATA_SUPPORTED (1 << 1)
-#define NVME_F_PCI_P2PDMA (1 << 2)
int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
@@ -514,6 +513,7 @@ struct nvme_ctrl_ops {
void (*stop_ctrl)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
void (*print_device_info)(struct nvme_ctrl *ctrl);
+ bool (*supports_pci_p2pdma)(struct nvme_ctrl *ctrl);
};
/*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 71a4f26ba476..de1b4463142d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -230,11 +230,10 @@ 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)
@@ -524,7 +523,7 @@ 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)
@@ -576,17 +575,6 @@ 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);
@@ -597,9 +585,10 @@ 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);
@@ -607,7 +596,7 @@ 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)
@@ -630,7 +619,7 @@ 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;
+ unsigned 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;
}
@@ -911,7 +900,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
iod->aborted = 0;
iod->npages = -1;
- iod->nents = 0;
+ iod->sgt.nents = 0;
ret = nvme_setup_cmd(req->q->queuedata, req);
if (ret)
@@ -2992,7 +2981,6 @@ static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
}
-
static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
{
struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
@@ -3007,11 +2995,17 @@ static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
subsys->firmware_rev);
}
+static bool nvme_pci_supports_pci_p2pdma(struct nvme_ctrl *ctrl)
+{
+ struct nvme_dev *dev = to_nvme_dev(ctrl);
+
+ return dma_pci_p2pdma_supported(dev->dev);
+}
+
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.name = "pcie",
.module = THIS_MODULE,
- .flags = NVME_F_METADATA_SUPPORTED |
- NVME_F_PCI_P2PDMA,
+ .flags = NVME_F_METADATA_SUPPORTED,
.reg_read32 = nvme_pci_reg_read32,
.reg_write32 = nvme_pci_reg_write32,
.reg_read64 = nvme_pci_reg_read64,
@@ -3019,6 +3013,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.submit_async_event = nvme_pci_submit_async_event,
.get_address = nvme_pci_get_address,
.print_device_info = nvme_pci_print_device_info,
+ .supports_pci_p2pdma = nvme_pci_supports_pci_p2pdma,
};
static int nvme_dev_map(struct nvme_dev *dev)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 09fdcac87d17..4597bca43a6d 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -415,7 +415,7 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
if (ib_dma_mapping_error(ndev->device, r->send_sge.addr))
goto out_free_rsp;
- if (!ib_uses_virt_dma(ndev->device))
+ if (ib_dma_pci_p2p_dma_supported(ndev->device))
r->req.p2p_client = &ndev->device->dev;
r->send_sge.length = sizeof(*r->req.cqe);
r->send_sge.lkey = ndev->pd->local_dma_lkey;