[v4,01/12] mm: introduce AS_NO_DIRECT_MAP

Commit Message

Patrick Roy Feb. 21, 2025, 4:07 p.m. UTC

Add AS_NO_DIRECT_MAP for mappings where direct map entries of folios are
set to not present . Currently, mappings that match this description are
secretmem mappings (memfd_secret()). Later, some guest_memfd
configurations will also fall into this category.

Reject this new type of mappings in all locations that currently reject
secretmem mappings, on the assumption that if secretmem mappings are
rejected somewhere, it is precisely because of an inability to deal with
folios without direct map entries.

Use a new flag instead of overloading AS_INACCESSIBLE (which is already
set by guest_memfd) because not all guest_memfd mappings will end up
being direct map removed (e.g. in pKVM setups, parts of guest_memfd that
can be mapped to userspace should also be GUP-able, and generally not
have restrictions on who can access it).

Signed-off-by: Patrick Roy <[e-mail]>
---
 include/linux/pagemap.h | 16 ++++++++++++++++
 lib/buildid.c           |  4 ++--
 mm/gup.c                |  6 +++++-
 mm/mlock.c              |  3 ++-
 4 files changed, 25 insertions(+), 4 deletions(-)


base-commit: da40655874b54a2b563f8ceb3ed839c6cd38e0b4

Patch

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 47bfc6b1b632..903b41e89cf8 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -210,6 +210,7 @@  enum mapping_flags {
 	AS_STABLE_WRITES = 7,	/* must wait for writeback before modifying
 				   folio contents */
 	AS_INACCESSIBLE = 8,	/* Do not attempt direct R/W access to the mapping */
+	AS_NO_DIRECT_MAP = 9,	/* Folios in the mapping are not in the direct map */
 	/* Bits 16-25 are used for FOLIO_ORDER */
 	AS_FOLIO_ORDER_BITS = 5,
 	AS_FOLIO_ORDER_MIN = 16,
@@ -335,6 +336,21 @@  static inline bool mapping_inaccessible(struct address_space *mapping)
 	return test_bit(AS_INACCESSIBLE, &mapping->flags);
 }
 
+static inline void mapping_set_no_direct_map(struct address_space *mapping)
+{
+	set_bit(AS_NO_DIRECT_MAP, &mapping->flags);
+}
+
+static inline bool mapping_no_direct_map(struct address_space *mapping)
+{
+	return test_bit(AS_NO_DIRECT_MAP, &mapping->flags);
+}
+
+static inline bool vma_is_no_direct_map(const struct vm_area_struct *vma)
+{
+	return vma->vm_file && mapping_no_direct_map(vma->vm_file->f_mapping);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/lib/buildid.c b/lib/buildid.c
index c4b0f376fb34..80b5d805067f 100644
--- a/lib/buildid.c
+++ b/lib/buildid.c
@@ -65,8 +65,8 @@  static int freader_get_folio(struct freader *r, loff_t file_off)
 
 	freader_put_folio(r);
 
-	/* reject secretmem folios created with memfd_secret() */
-	if (secretmem_mapping(r->file->f_mapping))
+	/* reject secretmem folios created with memfd_secret() or guest_memfd() */
+	if (secretmem_mapping(r->file->f_mapping) || mapping_no_direct_map(r->file->f_mapping))
 		return -EFAULT;
 
 	r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT);
diff --git a/mm/gup.c b/mm/gup.c
index 3883b307780e..7ddaf93c5b6a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1283,7 +1283,7 @@  static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
 		return -EOPNOTSUPP;
 
-	if (vma_is_secretmem(vma))
+	if (vma_is_secretmem(vma) || vma_is_no_direct_map(vma))
 		return -EFAULT;
 
 	if (write) {
@@ -2849,6 +2849,10 @@  static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags)
 	 */
 	if (check_secretmem && secretmem_mapping(mapping))
 		return false;
+
+	if (mapping_no_direct_map(mapping))
+		return false;
+
 	/* The only remaining allowed file system is shmem. */
 	return !reject_file_backed || shmem_mapping(mapping);
 }
diff --git a/mm/mlock.c b/mm/mlock.c
index cde076fa7d5e..07a351491d9d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -474,7 +474,8 @@  static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
-	    vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE))
+	    vma_is_dax(vma) || vma_is_secretmem(vma) || vma_is_no_direct_map(vma) ||
+	    (oldflags & VM_DROPPABLE))
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;