From 283f3cfc1ac3bd83aa969a8ec6f001a93809969e Mon Sep 17 00:00:00 2001 From: Naman Jain Date: Fri, 10 Apr 2026 15:34:13 +0000 Subject: [PATCH 1/2] block: add pgmap check to biovec_phys_mergeable biovec_phys_mergeable() is used by the request merge, DMA mapping, and integrity merge paths to decide if two physically contiguous bvec segments can be coalesced into one. It currently has no check for whether the segments belong to different dev_pagemaps. When zone device memory is registered in multiple chunks, each chunk gets its own dev_pagemap. A single bio can legitimately contain bvecs from different pgmaps -- iov_iter_extract_bvecs() breaks at pgmap boundaries but the outer loop in bio_iov_iter_get_pages() continues filling the same bio. If such bvecs are physically contiguous, biovec_phys_mergeable() will coalesce them, making it impossible to recover the correct pgmap for the merged segment via page_pgmap(). Add a zone_device_pages_have_same_pgmap() check to prevent merging bvec segments that span different pgmaps. Fixes: 49580e690755 ("block: add check when merging zone device pages") Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Naman Jain --- block/blk.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/blk.h b/block/blk.h index f6053e9dd2aac..ef02409f3a74f 100644 --- a/block/blk.h +++ b/block/blk.h @@ -132,6 +132,8 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, if (addr1 + vec1->bv_len != addr2) return false; + if (!zone_device_pages_have_same_pgmap(vec1->bv_page, vec2->bv_page)) + return false; if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page)) return false; if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask)) From a47e9cc78b761793f127a2630b9215cda27f2d6a Mon Sep 17 00:00:00 2001 From: Naman Jain Date: Fri, 10 Apr 2026 15:34:14 +0000 Subject: [PATCH 2/2] block: relax pgmap check in bio_add_page for compatible zone device pages bio_add_page() and bio_integrity_add_page() reject pages from different dev_pagemaps entirely, returning 0 even when those pages have compatible DMA mapping requirements. This forces callers to start a new bio when buffers span pgmap boundaries, even though the pages could safely coexist as separate bvec entries. This matters for guests where memory is registered through devm_memremap_pages() with MEMORY_DEVICE_GENERIC in multiple calls, creating separate dev_pagemaps for each chunk. When a direct I/O buffer spans two such chunks, bio_add_page() rejects the second page, forcing an unnecessary bio split or I/O failure. Introduce zone_device_pages_compatible() in blk.h to check whether two pages can coexist in the same bio as separate bvec entries. The block DMA iterator (blk_dma_map_iter_start) caches the P2PDMA mapping state from the first segment and applies it to all others, so P2PDMA pages from different pgmaps must not be mixed, and neither must P2PDMA and non-P2PDMA pages. All other combinations (MEMORY_DEVICE_GENERIC pages from different pgmaps, or MEMORY_DEVICE_GENERIC with normal RAM) use the same dma_map_phys path and are safe. Replace the blanket zone_device_pages_have_same_pgmap() rejection with zone_device_pages_compatible(), while keeping zone_device_pages_have_same_pgmap() as a merge guard. Pages from different pgmaps can be added as separate bvec entries but must not be coalesced into the same segment, as that would make it impossible to recover the correct pgmap via page_pgmap(). Fixes: 49580e690755 ("block: add check when merging zone device pages") Cc: stable@vger.kernel.org Signed-off-by: Naman Jain --- block/bio-integrity.c | 6 +++--- block/bio.c | 6 +++--- block/blk.h | 19 +++++++++++++++++++ 3 files changed, 25 insertions(+), 6 deletions(-) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 20f5d301d32dd..a319362217037 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -167,10 +167,10 @@ 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)) + if (!zone_device_pages_compatible(bv->bv_page, page)) return 0; - - if (bvec_try_merge_hw_page(q, bv, page, len, offset)) { + if (zone_device_pages_have_same_pgmap(bv->bv_page, page) && + 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 d80d5d26804e3..3acd216bbc2ee 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1070,10 +1070,10 @@ int bio_add_page(struct bio *bio, struct page *page, 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)) + if (!zone_device_pages_compatible(bv->bv_page, page)) return 0; - - if (bvec_try_merge_page(bv, page, len, offset)) { + if (zone_device_pages_have_same_pgmap(bv->bv_page, page) && + bvec_try_merge_page(bv, page, len, offset)) { bio->bi_iter.bi_size += len; return len; } diff --git a/block/blk.h b/block/blk.h index ef02409f3a74f..a7abf3be34ef8 100644 --- a/block/blk.h +++ b/block/blk.h @@ -141,6 +141,25 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, return true; } +/* + * Check if two pages from potentially different zone device pgmaps can + * coexist as separate bvec entries in the same bio. + * + * The block DMA iterator (blk_dma_map_iter_start) caches the P2PDMA mapping + * state from the first segment and applies it to all subsequent segments, so + * P2PDMA pages from different pgmaps must not be mixed in the same bio. + * + * Other zone device types (FS_DAX, GENERIC) use the same dma_map_phys() path + * as normal RAM. PRIVATE and COHERENT pages never appear in bios. + */ +static inline bool zone_device_pages_compatible(const struct page *a, + const struct page *b) +{ + if (is_pci_p2pdma_page(a) || is_pci_p2pdma_page(b)) + return zone_device_pages_have_same_pgmap(a, b); + return true; +} + static inline bool __bvec_gap_to_prev(const struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) {