Re: [RFC 05/11] mm/memory/fault: Add support for zone device THP fault handling

[David Hildenbrand]

On 06.03.25 05:42, Balbir Singh wrote:

When the CPU touches a zone device THP entry, the data needs to
be migrated back to the CPU, call migrate_to_ram() on these pages
via do_huge_pmd_device_private() fault handling helper.

Signed-off-by: Balbir Singh <balb...@nvidia.com>
---
  include/linux/huge_mm.h |  7 +++++++
  mm/huge_memory.c        | 35 +++++++++++++++++++++++++++++++++++
  mm/memory.c             |  6 ++++--
  3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e893d546a49f..ad0c0ccfcbc2 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -479,6 +479,8 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, 
unsigned long addr,

vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); +vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf);

+
  extern struct folio *huge_zero_folio;
  extern unsigned long huge_zero_pfn;

@@ -634,6 +636,11 @@ static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)

        return 0;
  }

+static inline vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf)

+{
+       return 0;
+}
+
  static inline bool is_huge_zero_folio(const struct folio *folio)
  {
        return false;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d8e018d1bdbd..995ac8be5709 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1375,6 +1375,41 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault 
*vmf)
        return __do_huge_pmd_anonymous_page(vmf);
  }

+vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf)

+{
+       struct vm_area_struct *vma = vmf->vma;
+       unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+       vm_fault_t ret;
+       spinlock_t *ptl;
+       swp_entry_t swp_entry;
+       struct page *page;
+
+       if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
+               return VM_FAULT_FALLBACK;

I'm confused. Why is that required when we already have a PMD entry?

Apart from that, nothing jumped at me.


--
Cheers,

David / dhildenb