From: Mikulas Patocka <mpatocka@xxxxxxxxxx>
If we allocate a bio that is larger than NVMe maximum request size,
attach integrity metadata to it and send it to the NVMe subsystem, the
integrity metadata will be corrupted.
Splitting the bio works correctly. The function bio_split will clone the
bio, trim the iterator of the first bio and advance the iterator of the
second bio.
However, the function rq_integrity_vec has a bug - it returns the first
vector of the bio's metadata and completely disregards the metadata
iterator that was advanced when the bio was split. Thus, the second bio
uses the same metadata as the first bio and this leads to metadata
corruption.
This commit changes rq_integrity_vec, so that it calls mp_bvec_iter_bvec
instead of returning the first vector. mp_bvec_iter_bvec reads the
iterator and uses it to build a bvec for the current position in the
iterator.
The "queue_max_integrity_segments(rq->q) > 1" check was removed, because
the updated rq_integrity_vec function works correctly with multiple
segments.
Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
Reviewed-by: Anuj Gupta <anuj20.g@xxxxxxxxxxx>
---
drivers/nvme/host/pci.c | 6 +++---
include/linux/blk-integrity.h | 16 ++++++++--------
2 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 102a9fb0c65f..5d8035218de9 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -826,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
struct nvme_command *cmnd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+ struct bio_vec bv = rq_integrity_vec(req);
- iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
- rq_dma_dir(req), 0);
+ iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->meta_dma))
return BLK_STS_IOERR;
cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
@@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
dma_unmap_page(dev->dev, iod->meta_dma,
- rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
+ rq_integrity_vec(req).bv_len, rq_dma_dir(req));
}
if (blk_rq_nr_phys_segments(req))
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index d201140d77a3..c58634924782 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -90,14 +90,13 @@ static inline bool blk_integrity_rq(struct request *rq)
}
/*
- * Return the first bvec that contains integrity data. Only drivers that are
- * limited to a single integrity segment should use this helper.
+ * Return the current bvec that contains the integrity data. bip_iter may be
+ * advanced to iterate over the integrity data.
*/
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+static inline struct bio_vec rq_integrity_vec(struct request *rq)
{
- if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
- return NULL;
- return rq->bio->bi_integrity->bip_vec;
+ return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec,
+ rq->bio->bi_integrity->bip_iter);
}
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline int blk_rq_count_integrity_sg(struct request_queue *q,
@@ -146,9 +145,10 @@ static inline int blk_integrity_rq(struct request *rq)
return 0;
}
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+static inline struct bio_vec rq_integrity_vec(struct request *rq)
{
- return NULL;
+ /* the optimizer will remove all calls to this function */
+ return (struct bio_vec){ };
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
--
2.25.1
