diff options
| author | Christoph Hellwig <hch@lst.de> | 2025-06-25 13:34:58 +0200 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2025-06-30 15:50:32 -0600 |
| commit | 38446014648c9f7b2843f87517c8f2b73906bb40 (patch) | |
| tree | 9b2a6eea78ce6da1abcbe45ca53c0a88afdcc596 /block | |
| parent | 409f9287dab3b53bffe8d28d883a529028aa6a42 (diff) | |
block: don't merge different kinds of P2P transfers in a single bio
To get out of the DMA mapping helpers having to check every segment for
it's P2P status, ensure that bios either contain P2P transfers or non-P2P
transfers, and that a P2P bio only contains ranges from a single device.
This means we do the page zone access in the bio add path where it should
be still page hot, and will only have do the fairly expensive P2P topology
lookup once per bio down in the DMA mapping path, and only for already
marked bios.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20250625113531.522027-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
| -rw-r--r-- | block/bio-integrity.c | 3 | ||||
| -rw-r--r-- | block/bio.c | 20 |
2 files changed, 16 insertions, 7 deletions
diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 10912988c8f5..6b077ca937f6 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -128,6 +128,9 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, if (bip->bip_vcnt > 0) { struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1]; + if (!zone_device_pages_have_same_pgmap(bv->bv_page, page)) + return 0; + if (bvec_try_merge_hw_page(q, bv, page, len, offset)) { bip->bip_iter.bi_size += len; return len; diff --git a/block/bio.c b/block/bio.c index 3c0a558c90f5..92c512e876c8 100644 --- a/block/bio.c +++ b/block/bio.c @@ -930,8 +930,6 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, return false; if (xen_domain() && !xen_biovec_phys_mergeable(bv, page)) return false; - if (!zone_device_pages_have_same_pgmap(bv->bv_page, page)) - return false; if ((vec_end_addr & PAGE_MASK) != ((page_addr + off) & PAGE_MASK)) { if (IS_ENABLED(CONFIG_KMSAN)) @@ -982,6 +980,9 @@ void __bio_add_page(struct bio *bio, struct page *page, WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); + if (is_pci_p2pdma_page(page)) + bio->bi_opf |= REQ_P2PDMA | REQ_NOMERGE; + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off); bio->bi_iter.bi_size += len; bio->bi_vcnt++; @@ -1022,11 +1023,16 @@ int bio_add_page(struct bio *bio, struct page *page, if (bio->bi_iter.bi_size > UINT_MAX - len) return 0; - if (bio->bi_vcnt > 0 && - bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], - page, len, offset)) { - bio->bi_iter.bi_size += len; - return len; + if (bio->bi_vcnt > 0) { + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + + if (!zone_device_pages_have_same_pgmap(bv->bv_page, page)) + return 0; + + if (bvec_try_merge_page(bv, page, len, offset)) { + bio->bi_iter.bi_size += len; + return len; + } } if (bio->bi_vcnt >= bio->bi_max_vecs) |