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: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 10912988c8f5c735249f1228530ef1b8cafe85fa..6b077ca937f6b6c826a1d801f6eb3401e83a7dad 100644 (file)
--- 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 3c0a558c90f52eef5f4c34b25e34bd6f0d9ed9d8..92c512e876c8d49a742e61b08a711ea64523f25e 100644 (file)
--- 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)

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3d1577f07c1c827f127e109388066ff55c8eb7dd..2a02972dc17c5fe0580973a9d9171b662ba834e9 100644 (file)
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -386,6 +386,7 @@ enum req_flag_bits {
        __REQ_DRV,              /* for driver use */
        __REQ_FS_PRIVATE,       /* for file system (submitter) use */
        __REQ_ATOMIC,           /* for atomic write operations */
+       __REQ_P2PDMA,           /* contains P2P DMA pages */
        /*
         * Command specific flags, keep last:
         */
@@ -418,6 +419,7 @@ enum req_flag_bits {
 #define REQ_DRV                (__force blk_opf_t)(1ULL << __REQ_DRV)
 #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE)
 #define REQ_ATOMIC     (__force blk_opf_t)(1ULL << __REQ_ATOMIC)
+#define REQ_P2PDMA     (__force blk_opf_t)(1ULL << __REQ_P2PDMA)
 
 #define REQ_NOUNMAP    (__force blk_opf_t)(1ULL << __REQ_NOUNMAP)