Two page table walkers resolve the folio behind a PMD with pmd_folio(),
which is only valid for a PMD mapping a refcounted struct page:

  madvise_cold_or_pageout_pte_range()   mm/madvise.c
  queue_folios_pmd()                    mm/mempolicy.c

vmf_insert_pfn_pmd() installs special PMDs holding a raw pfn that need not
have a memmap entry at all.  Both walkers can reach one and fault on the
first folio field read.  The PTE halves of both already use
vm_normal_folio(); these two patches make the PMD halves match.

The four callers of vmf_insert_pfn_pmd(), and which walker each reaches:

  drivers/vfio/pci/vfio_pci_core.c        VM_PFNMAP     mempolicy
  drivers/gpu/drm/drm_gem_shmem_helper.c  VM_PFNMAP     mempolicy
  drivers/gpu/drm/panthor/panthor_gem.c   VM_PFNMAP     mempolicy
  drivers/hv/mshv_vtl_main.c              VM_MIXEDMAP   both

can_madv_lru_vma() rejects VM_PFNMAP, so only mshv_vtl_low reaches the
madvise walker, and that needs CAP_SYS_ADMIN.  queue_pages_walk_ops
supplies its own ->test_walk, so walk_page_test()'s generic VM_PFNMAP skip
never runs and vfio-pci is reachable by any process holding the device fd.
Hence the different stable tags.

One behaviour change: mbind(MPOL_MF_STRICT) over a PMD mapped VM_PFNMAP
region now returns 0 rather than -EIO.  The PTE loop already returned 0
there.  drm_gem_shmem and panthor are where this is observable, since they
PMD map pages that do have a memmap entry and so never faulted.

Reproducer
==========

No hardware needed.  An out of tree module stands in for the drivers above:
three misc devices, each with a ->huge_fault calling vmf_insert_pfn_pmd(),
plus VM_HUGEPAGE so the fault path takes the PMD branch.

  /dev/pmdspec_mixed    VM_MIXEDMAP, pfn at the 1 TiB mark, no memmap
  /dev/pmdspec_pfnmap   VM_PFNMAP,   pfn at the 1 TiB mark, no memmap
  /dev/pmdspec_real     VM_PFNMAP,   real alloc_pages(PMD_ORDER) on node 0

Userspace maps the device into a PMD aligned window, reads one byte to
fault the PMD in, checks a module parameter to confirm it went in, then
issues the operation.

  vng --run <bzImage> --user root --memory 4G --verbose \
      --append "numa=fake=2" \
      --exec "insmod pmdspec.ko && ./pmdspec_test <subtest>"

numa=fake=2 gives a node 1 to bind to; the module allocates its real page
on node 0, which is what makes queue_folio_required() true.

  subtest        operation                              parent   series
  --------------------------------------------------------------------
  madv_cold      madvise(MADV_COLD)                     oops     ret=0
  madv_pageout   madvise(MADV_PAGEOUT)                  oops     ret=0
  mbind_mixed    mbind(MPOL_BIND, n1, MPOL_MF_MOVE)     oops     ret=0
  mbind_pfnmap   mbind(MPOL_BIND, n1, MPOL_MF_STRICT)   oops     ret=0
  mbind_real     mbind(MPOL_BIND, n1, MPOL_MF_STRICT)   -EIO     ret=0

Two things the table shows that are easy to miss in the code:

  - mbind_mixed passes only MPOL_MF_MOVE.  MPOL_MF_STRICT is not needed for
    a VM_MIXEDMAP vma: walk_page_test() only skips VM_PFNMAP, and
    vma_migratable() is true for VM_MIXEDMAP.

  - mbind_real demonstrates the user visible change (-EIO -> 0)

Reported-by: sashiko-bot <sashiko-bot@kernel.org>
Closes: https://sashiko.dev/#/patchset/20260817220810.1175596-1-gourry%40gourry.net
Assisted-by: LLM

---
v3: improvements from Lorenzo
v2: improvements from David

Gregory Price (2):
  mm/mempolicy: use vm_normal_folio_pmd() in queue_folios_pmd()
  mm/madvise: use vm_normal_folio_pmd() in cold/pageout PMD range

 mm/madvise.c   |  7 +++----
 mm/mempolicy.c | 13 +++++--------
 2 files changed, 8 insertions(+), 12 deletions(-)

-- 
2.55.0

On Sat, 26 Sep 2026 06:51:08 -0400 Gregory Price <gourry@gourry.net> wrote:

> Two page table walkers resolve the folio behind a PMD with pmd_folio(),
> which is only valid for a PMD mapping a refcounted struct page:
> 
>   madvise_cold_or_pageout_pte_range()   mm/madvise.c
>   queue_folios_pmd()                    mm/mempolicy.c
> 
> vmf_insert_pfn_pmd() installs special PMDs holding a raw pfn that need not
> have a memmap entry at all.  Both walkers can reach one and fault on the
> first folio field read.  The PTE halves of both already use
> vm_normal_folio(); these two patches make the PMD halves match.
> 
> The four callers of vmf_insert_pfn_pmd(), and which walker each reaches:
> 
>   drivers/vfio/pci/vfio_pci_core.c        VM_PFNMAP     mempolicy
>   drivers/gpu/drm/drm_gem_shmem_helper.c  VM_PFNMAP     mempolicy
>   drivers/gpu/drm/panthor/panthor_gem.c   VM_PFNMAP     mempolicy
>   drivers/hv/mshv_vtl_main.c              VM_MIXEDMAP   both
> 
> can_madv_lru_vma() rejects VM_PFNMAP, so only mshv_vtl_low reaches the
> madvise walker, and that needs CAP_SYS_ADMIN.  queue_pages_walk_ops
> supplies its own ->test_walk, so walk_page_test()'s generic VM_PFNMAP skip
> never runs and vfio-pci is reachable by any process holding the device fd.
> Hence the different stable tags.
> 
> One behaviour change: mbind(MPOL_MF_STRICT) over a PMD mapped VM_PFNMAP
> region now returns 0 rather than -EIO.  The PTE loop already returned 0
> there.  drm_gem_shmem and panthor are where this is observable, since they
> PMD map pages that do have a memmap entry and so never faulted.

Thanks, I've updated mm-unstable to this version.

> v3: improvements from Lorenzo

Here's how v3 altered mm.git:


 mm/mempolicy.c |    9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

--- a/mm/mempolicy.c~b
+++ a/mm/mempolicy.c
@@ -668,7 +668,7 @@ static inline bool queue_folio_required(
 }
 
 static void queue_folios_pmd(pmd_t *pmd, unsigned long addr,
-			     struct mm_walk *walk)
+		struct mm_walk *walk)
 {
 	struct folio *folio;
 	struct queue_pages *qp = walk->private;
@@ -680,12 +680,7 @@ static void queue_folios_pmd(pmd_t *pmd,
 		return;
 	}
 	folio = vm_normal_folio_pmd(walk->vma, addr, pmdval);
-	if (!folio) {
-		if (is_huge_zero_pmd(pmdval))
-			walk->action = ACTION_CONTINUE;
-		return;
-	}
-	if (folio_is_zone_device(folio))
+	if (!folio || folio_is_zone_device(folio))
 		return;
 	if (!queue_folio_required(folio, qp))
 		return;
_