Re: [PATCH v2 3/5] mm: introduce VM_FAULT_UFFD_MINOR fault reason

[Nikita Kalyazin]

On 25/11/2025 18:38, Mike Rapoport wrote:
From: "Mike Rapoport (Microsoft)" <r...@kernel.org>

When a VMA is registered with userfaulfd in minor mode, its ->fault()
method should check if a folio exists in the page cache and if yes
->fault() should call handle_userfault(VM_UFFD_MISSING).

Instead of calling handle_userfault() directly from a specific ->fault()
implementation introduce new fault reason VM_FAULT_UFFD_MINOR that will
notify the core page fault handler that it should call
handle_userfaultfd(VM_UFFD_MISSING) to complete a page fault.

Replace a call to handle_userfault(VM_UFFD_MISSING) in shmem and use the
new VM_FAULT_UFFD_MINOR there instead.

For configurations that don't enable CONFIG_USERFAULTFD,
VM_FAULT_UFFD_MINOR is set to 0.

Suggested-by: David Hildenbrand (Red Hat) <da...@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <r...@kernel.org>
---
  include/linux/mm_types.h | 10 +++++++++-
  mm/memory.c              |  2 ++
  mm/shmem.c               |  2 +-
  3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 90e5790c318f..df71b057111b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1523,6 +1523,8 @@ typedef __bitwise unsigned int vm_fault_t;
   *                             fsync() to complete (for synchronous page 
faults
   *                             in DAX)
   * @VM_FAULT_COMPLETED:                ->fault completed, meanwhile mmap lock 
released
+ * @VM_FAULT_UFFD_MINOR:       ->fault did not modify page tables and needs
+ *                             handle_userfault(VM_UFFD_MINOR) to complete
   * @VM_FAULT_HINDEX_MASK:      mask HINDEX value
   *
   */
@@ -1540,6 +1542,11 @@ enum vm_fault_reason {
         VM_FAULT_DONE_COW       = (__force vm_fault_t)0x001000,
         VM_FAULT_NEEDDSYNC      = (__force vm_fault_t)0x002000,
         VM_FAULT_COMPLETED      = (__force vm_fault_t)0x004000,
+#ifdef CONFIG_USERFAULTFD
+       VM_FAULT_UFFD_MINOR     = (__force vm_fault_t)0x008000,
+#else
+       VM_FAULT_UFFD_MINOR     = (__force vm_fault_t)0x000000,
+#endif
         VM_FAULT_HINDEX_MASK    = (__force vm_fault_t)0x0f0000,
  };

@@ -1564,7 +1571,8 @@ enum vm_fault_reason {
         { VM_FAULT_FALLBACK,            "FALLBACK" },   \
         { VM_FAULT_DONE_COW,            "DONE_COW" },   \
         { VM_FAULT_NEEDDSYNC,           "NEEDDSYNC" },  \
-       { VM_FAULT_COMPLETED,           "COMPLETED" }
+       { VM_FAULT_COMPLETED,           "COMPLETED" },  \
+       { VM_FAULT_UFFD_MINOR,          "UFFD_MINOR" }, \

It looks like we have to keep the last element comma-less, otherwise I'm 
seeing compile errors somewhere in fs/dax.c.


  struct vm_special_mapping {
         const char *name;       /* The name, e.g. "[vdso]". */
diff --git a/mm/memory.c b/mm/memory.c
index b59ae7ce42eb..94acbac8cefb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5279,6 +5279,8 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
         }

         ret = vma->vm_ops->fault(vmf);
+       if (unlikely(ret & VM_FAULT_UFFD_MINOR))
+               return handle_userfault(vmf, VM_UFFD_MINOR);
         if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
                             VM_FAULT_DONE_COW)))
                 return ret;
diff --git a/mm/shmem.c b/mm/shmem.c
index e16c7c8c3e1e..a9a31c0b5979 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2461,7 +2461,7 @@ static int shmem_get_folio_gfp(struct inode *inode, 
pgoff_t index,
         if (folio && vma && userfaultfd_minor(vma)) {
                 if (!xa_is_value(folio))
                         folio_put(folio);
-               *fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
+               *fault_type = VM_FAULT_UFFD_MINOR;
                 return 0;
         }

--
2.50.1