[PATCH v2 7/7] nvme-rdma: return BLK_STS_TARGET for unsupported P2P transfers

[Mykola Marzhan]

Since commit 23528aa3320a ("nvme: enable PCI P2PDMA support for RDMA
transport") nvme-rdma accepts P2PDMA bios, but a mapping failure for
peer memory the HCA cannot reach is misreported as a path error:
ib_dma_map_sg() returns 0, discarding the -EREMOTEIO that
dma_map_sgtable() documents for exactly this case, and the driver
converts it to -EIO -> nvme_host_path_error().

Under the default multipath configuration (the multipath head node
advertises BLK_FEAT_PCI_P2PDMA since commit fb0eeeed91f3
("nvme-multipath: enable PCI P2PDMA for multipath devices")) the
path-error status makes nvme_failover_req() requeue the bios with a
fresh retry budget each cycle, and since the mapping failure is a
deterministic property of the peer/device pairing the I/O simply
never completes: a hot requeue livelock, and a stacked md mirror
hangs instead of failing over to its other leg.  With
nvme_core.multipath=N the request burns nvme_max_retries requeues --
nothing ever reaching the wire -- and completes as
BLK_STS_TRANSPORT, which blk_path_error() classifies as retryable
and md/raid1,raid10 treat as a genuine device error: retry storms on
writes, read-error-budget eviction of a healthy member on reads (see
the preceding md patches, whose mapping-failure handling keys on
BLK_STS_TARGET).

Map both the data and the metadata scatterlists with
ib_dma_map_sgtable_attrs() so the DMA layer's error code is
preserved, and translate -EREMOTEIO to BLK_STS_TARGET: the
classification nvme-pci established in commit 91fb2b6052f7
("nvme-pci: convert to using dma_map_sgtable()") and the preceding
blk-mq-dma patch restores.  The metadata path needs the same
treatment because integrity buffers are not always host memory:
bio_integrity_map_user() allows P2P pages whenever the queue
advertises P2PDMA, and nvme-pci already maps P2P metadata.

Returning BLK_STS_TARGET from queue_rq is a deliberate trade-off: it
forecloses failover for a configuration where a sibling path through
a different HCA could reach the peer.  This matches nvme-pci, which
has returned BLK_STS_TARGET for unsupported P2P mappings since
that same commit and equally forecloses cross-controller failover;
distinguishing this-path-unreachable from all-paths-unreachable at
completion time would cost a spurious requeue cycle per I/O, and a
stacking consumer (md) routes around the leg one layer up.

Start the request only after mapping succeeds, as nvme-pci does: a
mapping failure now errors out of queue_rq on a not-yet-started
request, so nvme_mpath_start_request() accounting is never taken and
cannot leak on the direct blk-mq completion (this also closes the same
latent leak for mapping-failure BLK_STS_IOERR returns; the post-send
error tail is untouched). A mapping -ENOMEM now takes the existing
BLK_STS_RESOURCE branch instead of masquerading as a path error, and a
DMA-layer -EINVAL completes as BLK_STS_IOERR instead of a path error;
generic -EIO keeps today's host-path-error behavior, and virt-DMA
devices are unaffected. Ratelimit the map-failure message -- with an md
mirror steering peer-memory I/O around an unreachable leg it fires per
redirected I/O, not per rare event.

Fixes: 23528aa3320a ("nvme: enable PCI P2PDMA support for RDMA transport")
Cc: stable@xxxxxxxxxxxxxxx # v7.1
Assisted-by: Claude:claude-fable-5
Signed-off-by: Mykola Marzhan <mykola@xxxxxxxxxxx>
---
 drivers/nvme/host/rdma.c | 42 +++++++++++++++++++++++++---------------
 1 file changed, 26 insertions(+), 16 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 6909e3542794..9017d927edc4 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1469,6 +1469,7 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
 		int *count, int *pi_count)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct sg_table sgt;
 	int ret;
 
 	req->data_sgl.sg_table.sgl = (struct scatterlist *)(req + 1);
@@ -1480,12 +1481,14 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
 
 	req->data_sgl.nents = blk_rq_map_sg(rq, req->data_sgl.sg_table.sgl);
 
-	*count = ib_dma_map_sg(ibdev, req->data_sgl.sg_table.sgl,
-			       req->data_sgl.nents, rq_dma_dir(rq));
-	if (unlikely(*count <= 0)) {
-		ret = -EIO;
+	sgt = (struct sg_table) {
+		.sgl		= req->data_sgl.sg_table.sgl,
+		.orig_nents	= req->data_sgl.nents,
+	};
+	ret = ib_dma_map_sgtable_attrs(ibdev, &sgt, rq_dma_dir(rq), 0);
+	if (unlikely(ret))
 		goto out_free_table;
-	}
+	*count = sgt.nents;
 
 	if (blk_integrity_rq(rq)) {
 		req->metadata_sgl->sg_table.sgl =
@@ -1501,14 +1504,14 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
 
 		req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq,
 				req->metadata_sgl->sg_table.sgl);
-		*pi_count = ib_dma_map_sg(ibdev,
-					  req->metadata_sgl->sg_table.sgl,
-					  req->metadata_sgl->nents,
-					  rq_dma_dir(rq));
-		if (unlikely(*pi_count <= 0)) {
-			ret = -EIO;
+		sgt = (struct sg_table) {
+			.sgl		= req->metadata_sgl->sg_table.sgl,
+			.orig_nents	= req->metadata_sgl->nents,
+		};
+		ret = ib_dma_map_sgtable_attrs(ibdev, &sgt, rq_dma_dir(rq), 0);
+		if (unlikely(ret))
 			goto out_free_pi_table;
-		}
+		*pi_count = sgt.nents;
 	}
 
 	return 0;
@@ -2026,8 +2029,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (ret)
 		goto unmap_qe;
 
-	nvme_start_request(rq);
-
 	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
 	    queue->pi_support &&
 	    (c->common.opcode == nvme_cmd_write ||
@@ -2039,11 +2040,13 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	err = nvme_rdma_map_data(queue, rq, c);
 	if (unlikely(err < 0)) {
-		dev_err(queue->ctrl->ctrl.device,
-			     "Failed to map data (%d)\n", err);
+		dev_err_ratelimited(queue->ctrl->ctrl.device,
+				    "Failed to map data (%d)\n", err);
 		goto err;
 	}
 
+	nvme_start_request(rq);
+
 	sqe->cqe.done = nvme_rdma_send_done;
 
 	ib_dma_sync_single_for_device(dev, sqe->dma,
@@ -2063,6 +2066,13 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 		ret = nvme_host_path_error(rq);
 	else if (err == -ENOMEM || err == -EAGAIN)
 		ret = BLK_STS_RESOURCE;
+	/*
+	 * The DMA layer refused to map peer memory to this device: a
+	 * property of the pairing, not a path failure.  Match nvme-pci
+	 * and do not retry (see blk_path_error()).
+	 */
+	else if (err == -EREMOTEIO)
+		ret = BLK_STS_TARGET;
 	else
 		ret = BLK_STS_IOERR;
 	nvme_cleanup_cmd(rq);
-- 
2.43.0