Commit f7f1fc36 authored by Max Gurtovoy's avatar Max Gurtovoy Committed by Jens Axboe
Browse files

nvme: use blk API to remap ref tags for IOs with metadata 



Also moved the logic of the remapping to the nvme core driver instead
of implementing it in the nvme pci driver. This way all the other nvme
transport drivers will benefit from it (in case they'll implement metadata
support).

Suggested-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
Acked-by: default avatarKeith Busch <keith.busch@intel.com>
Signed-off-by: default avatarMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 10c41ddd

drivers/nvme/host/core.c

+18 −0
Original line number Diff line number Diff line
@@ -601,6 +601,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, 
			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))

				return BLK_STS_NOTSUPP;

			control |= NVME_RW_PRINFO_PRACT;

		} else if (req_op(req) == REQ_OP_WRITE) {

			t10_pi_prepare(req, ns->pi_type);

		}



		switch (ns->pi_type) {
@@ -621,6 +623,22 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, 
	return 0;

}



void nvme_cleanup_cmd(struct request *req)

{

	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&

	    nvme_req(req)->status == 0) {

		struct nvme_ns *ns = req->rq_disk->private_data;



		t10_pi_complete(req, ns->pi_type,

				blk_rq_bytes(req) >> ns->lba_shift);

	}

	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {

		kfree(page_address(req->special_vec.bv_page) +

		      req->special_vec.bv_offset);

	}

}

EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);



blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,

		struct nvme_command *cmd)

{

drivers/nvme/host/nvme.h

+1 −8
Original line number Diff line number Diff line
@@ -364,14 +364,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) 
	return (sector >> (ns->lba_shift - 9));

}



static inline void nvme_cleanup_cmd(struct request *req)

{

	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {

		kfree(page_address(req->special_vec.bv_page) +

		      req->special_vec.bv_offset);

	}

}



static inline void nvme_end_request(struct request *req, __le16 status,

		union nvme_result result)

{
@@ -428,6 +420,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl); 
#define NVME_QID_ANY -1

struct request *nvme_alloc_request(struct request_queue *q,

		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);

void nvme_cleanup_cmd(struct request *req);

blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,

		struct nvme_command *cmd);

int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,

drivers/nvme/host/pci.c

+1 −74
Original line number Diff line number Diff line
@@ -537,73 +537,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req) 
		mempool_free(iod->sg, dev->iod_mempool);

}



#ifdef CONFIG_BLK_DEV_INTEGRITY

static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)

{

	if (be32_to_cpu(pi->ref_tag) == v)

		pi->ref_tag = cpu_to_be32(p);

}



static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)

{

	if (be32_to_cpu(pi->ref_tag) == p)

		pi->ref_tag = cpu_to_be32(v);

}



/**

 * nvme_dif_remap - remaps ref tags to bip seed and physical lba

 *

 * The virtual start sector is the one that was originally submitted by the

 * block layer.	Due to partitioning, MD/DM cloning, etc. the actual physical

 * start sector may be different. Remap protection information to match the

 * physical LBA on writes, and back to the original seed on reads.

 *

 * Type 0 and 3 do not have a ref tag, so no remapping required.

 */

static void nvme_dif_remap(struct request *req,

			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))

{

	struct nvme_ns *ns = req->rq_disk->private_data;

	struct bio_integrity_payload *bip;

	struct t10_pi_tuple *pi;

	void *p, *pmap;

	u32 i, nlb, ts, phys, virt;



	if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)

		return;



	bip = bio_integrity(req->bio);

	if (!bip)

		return;



	pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;



	p = pmap;

	virt = bip_get_seed(bip);

	phys = nvme_block_nr(ns, blk_rq_pos(req));

	nlb = (blk_rq_bytes(req) >> ns->lba_shift);

	ts = ns->disk->queue->integrity.tuple_size;



	for (i = 0; i < nlb; i++, virt++, phys++) {

		pi = (struct t10_pi_tuple *)p;

		dif_swap(phys, virt, pi);

		p += ts;

	}

	kunmap_atomic(pmap);

}

#else /* CONFIG_BLK_DEV_INTEGRITY */

static void nvme_dif_remap(struct request *req,

			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))

{

}

static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)

{

}

static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)

{

}

#endif



static void nvme_print_sgl(struct scatterlist *sgl, int nents)

{

	int i;
@@ -829,9 +762,6 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, 
		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)

			goto out_unmap;



		if (req_op(req) == REQ_OP_WRITE)

			nvme_dif_remap(req, nvme_dif_prep);



		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))

			goto out_unmap;

	}
@@ -854,12 +784,9 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) 


	if (iod->nents) {

		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);

		if (blk_integrity_rq(req)) {

			if (req_op(req) == REQ_OP_READ)

				nvme_dif_remap(req, nvme_dif_complete);

		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);

CRA Git | Maintained and supported by SUSTech CRA and CCSE