Re: [PATCH 2/2] block: allow different-pgmap pages as separate bvecs in bio_add_page

[Naman Jain]

On 4/2/2026 11:00 AM, Christoph Hellwig wrote:
> On Thu, Apr 02, 2026 at 10:51:05AM +0530, Naman Jain wrote:
> > When a direct I/O request spans pages from different chunks (different
> > pgmaps), the current code rejected the second page entirely:
> >
> >      if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
> >          return 0;  // Rejection - forces bio split or I/O error
> >
> > Both chunks are regular RAM from the DMA perspective
> > (MEMORY_DEVICE_GENERIC, not P2PDMA). The only requirement is that they not
> > be merged into the same bvec segment, which patch 1/2 enforces by adding
> > the pgmap check to biovec_phys_mergeable().
> >
> > This patch allows pages from different pgmaps to be added as separate bvec
> > entries in the same bio, eliminating bio splits and I/O failures
> > when buffers span pgmap boundaries.
>
> Which as I said we can't do in general, as different pgmaps cna have
> different DMA mapping requirements.  We might be able to relax this
> if we know multiple pgmaps can be mapped in the same way.  I.e.
> replace zone_device_pages_have_same_pgmap with
> zone_device_pages_compatible and add additional conditions to it.
>
> > --- a/block/bio-integrity.c
> > +++ b/block/bio-integrity.c
> > @@ -231,6 +231,9 @@ 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 (is_pci_p2pdma_page(bv->bv_page) !=
> > +                   is_pci_p2pdma_page(page))
> > +                       return 0;
> >                  if (zone_device_pages_have_same_pgmap(bv->bv_page, page) &&
>
> The above is implied by not having the same pgmap.

Thanks. If I understand correctly, here is how this would look like.
Please let me know if this is what you suggested.


diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index e79eaf0477943..e54c6e06e1cbb 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -231,10 +231,10 @@ 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 77067fa346d35..0e70bb912338c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1034,10 +1034,10 @@ 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 0cb3441638284..c5710ba4c81b9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -136,6 +136,23 @@ 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 and non-P2PDMA pages must never 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)
+{
+       return is_pci_p2pdma_page(a) == is_pci_p2pdma_page(b);
+}
+
 static inline bool __bvec_gap_to_prev(const struct queue_limits *lim,
                struct bio_vec *bprv, unsigned int offset)
 {