mm: add VM_UFFD_RWP VMA flag

Preparatory patch for userfaultfd read-write protection (RWP).  RWP
extends userfaultfd protection from plain write-protection (WP) to full
read-write protection: accesses to an RWP-protected range -- reads as well
as writes -- trap through userfaultfd.

Reserve VM_UFFD_RWP, add the userfaultfd_rwp() and userfaultfd_protected()
helpers, and wire up the smaps "ur" entry and the trace-flag table the
rest of the series will use.  The flag is gated on CONFIG_USERFAULTFD_RWP,
which is introduced together with the UAPI in a later patch; until then
VM_UFFD_RWP aliases VM_NONE and every downstream check folds to dead code.

Nothing sets or queries the flag yet.

Link: https://lore.kernel.org/20260708111417.173443-6-kirill@shutemov.name
Signed-off-by: Kiryl Shutsemau <kas@kernel.org>
Assisted-by: Claude:claude-opus-4-6
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Lorenzo Stoakes <ljs@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: James Houghton <jthoughton@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Liam Howlett <liam@infradead.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Kiryl Shutsemau (Meta)
2026-07-08 12:14:06 +01:00
committed by Andrew Morton
parent 2730ee209f
commit 134c1d031a
5 changed files with 74 additions and 23 deletions

View File

@@ -608,6 +608,7 @@ encoded manner. The codes are the following:
um userfaultfd missing tracking
uw userfaultfd wr-protect tracking
ui userfaultfd minor fault
ur userfaultfd read-write-protect tracking
ss shadow/guarded control stack page
sl sealed
lf lock on fault pages

View File

@@ -1237,6 +1237,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
[ilog2(VM_UFFD_MINOR)] = "ui",
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
#ifdef CONFIG_USERFAULTFD_RWP
[ilog2(VM_UFFD_RWP)] = "ur",
#endif
#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK
[ilog2(VM_SHADOW_STACK)] = "ss",
#endif

View File

@@ -354,6 +354,7 @@ enum {
#endif
DECLARE_VMA_BIT(UFFD_MINOR, 41),
DECLARE_VMA_BIT(SEALED, 42),
DECLARE_VMA_BIT(UFFD_RWP, 43),
/* Flags that reuse flags above. */
DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0),
DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1),
@@ -497,12 +498,17 @@ enum {
#else
#define VM_UFFD_MINOR VM_NONE
#endif
#ifdef CONFIG_USERFAULTFD_RWP
#define VM_UFFD_RWP INIT_VM_FLAG(UFFD_RWP)
#else
#define VM_UFFD_RWP VM_NONE
#endif
/*
* vma_flags_t masks for the userfaultfd VMA flags. VMA_UFFD_MINOR is gated on
* the same config as VM_UFFD_MINOR -- which implies 64BIT, where the bit fits
* -- so an out-of-range bit is never fed to mk_vma_flags() on a build whose
* bitmap cannot hold it.
* vma_flags_t masks for the userfaultfd VMA flags. The two high-bit modes are
* gated on the same configs as their VM_* flags above -- both of which imply
* 64BIT -- so an out-of-range bit is never fed to mk_vma_flags() on a build
* whose bitmap cannot hold it.
*/
#define VMA_UFFD_MISSING mk_vma_flags(VMA_UFFD_MISSING_BIT)
#define VMA_UFFD_WP mk_vma_flags(VMA_UFFD_WP_BIT)
@@ -511,6 +517,11 @@ enum {
#else
#define VMA_UFFD_MINOR EMPTY_VMA_FLAGS
#endif
#ifdef CONFIG_USERFAULTFD_RWP
#define VMA_UFFD_RWP mk_vma_flags(VMA_UFFD_RWP_BIT)
#else
#define VMA_UFFD_RWP EMPTY_VMA_FLAGS
#endif
#ifdef CONFIG_64BIT
#define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED)
@@ -649,22 +660,24 @@ enum {
* reconsistuted upon page fault, so necessitate page table copying upon fork.
*
* Note that these flags should be compared with the DESTINATION VMA not the
* source, as VM_UFFD_WP may not be propagated to destination, while all other
* flags will be.
* source: VM_UFFD_WP and VM_UFFD_RWP may be cleared on the destination
* (dup_userfaultfd() -> userfaultfd_reset_ctx() when the parent context did
* not negotiate UFFD_FEATURE_EVENT_FORK), while all other flags propagate.
*
* VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be
* reasonably reconstructed on page fault.
*
* VM_UFFD_WP - Encodes metadata about an installed uffd
* write protect handler, which cannot be
* reconstructed on page fault.
* VM_UFFD_RWP write- or read-write-protect handler, which
* cannot be reconstructed on page fault.
*
* We always copy pgtables when dst_vma has uffd-wp
* enabled even if it's file-backed
* (e.g. shmem). Because when uffd-wp is enabled,
* pgtable contains uffd-wp protection information,
* that's something we can't retrieve from page cache,
* and skip copying will lose those info.
* We always copy pgtables when dst_vma has the
* uffd PTE bit in use even if it's file-backed
* (e.g. shmem). Because when the uffd bit is
* in use, the pgtable contains the protection
* information, that's something we can't
* retrieve from page cache, and skip copying
* will lose those info.
*
* VM_MAYBE_GUARD - Could contain page guard region markers which
* by design are a property of the page tables

View File

@@ -21,10 +21,11 @@
#include <linux/hugetlb_inline.h>
/* The set of all possible UFFD-related VM flags. */
#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR)
#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_MINOR | \
VM_UFFD_WP | VM_UFFD_RWP)
#define __VMA_UFFD_FLAGS mk_vma_flags_from_masks(VMA_UFFD_MISSING, VMA_UFFD_WP, \
VMA_UFFD_MINOR)
VMA_UFFD_MINOR, VMA_UFFD_RWP)
/*
* CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
@@ -168,7 +169,8 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
/*
* Never enable huge pmd sharing on some uffd registered vmas:
*
* - VM_UFFD_WP VMAs, because write protect information is per pgtable entry.
* - VM_UFFD_WP and VM_UFFD_RWP VMAs, because the write protect / access
* tracking information is per pgtable entry.
*
* - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for
* VMAs which share huge pmds. (If you have two mappings to the same
@@ -179,20 +181,25 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma)
{
return vma_test_any_mask(vma,
mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_MINOR));
mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_RWP,
VMA_UFFD_MINOR));
}
/*
* Don't do fault around for either WP or MINOR registered uffd range. For
* Don't do fault around for WP, RWP or MINOR registered uffd range. For
* MINOR registered range, fault around will be a total disaster and ptes can
* be installed without notifications; for WP it should mostly be fine as long
* as the fault around checks for pte_none() before the installation, however
* to be super safe we just forbid it.
* to be super safe we just forbid it; for RWP, pre-faulted neighbours would
* be indistinguishable from accessed pages in PAGEMAP_SCAN (PAGE_IS_ACCESSED)
* and pollute the tracked working set, so each page must be populated by its
* own fault.
*/
static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
{
return vma_test_any_mask(vma,
mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_MINOR));
mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_RWP,
VMA_UFFD_MINOR));
}
static inline bool userfaultfd_missing(struct vm_area_struct *vma)
@@ -210,6 +217,16 @@ static inline bool userfaultfd_minor(struct vm_area_struct *vma)
return vma_test_any_mask(vma, VMA_UFFD_MINOR);
}
static inline bool userfaultfd_rwp(struct vm_area_struct *vma)
{
return vma_test_single_mask(vma, VMA_UFFD_RWP);
}
static inline bool userfaultfd_protected(struct vm_area_struct *vma)
{
return userfaultfd_wp(vma) || userfaultfd_rwp(vma);
}
static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
pte_t pte)
{
@@ -330,6 +347,16 @@ static inline bool userfaultfd_minor(struct vm_area_struct *vma)
return false;
}
static inline bool userfaultfd_rwp(struct vm_area_struct *vma)
{
return false;
}
static inline bool userfaultfd_protected(struct vm_area_struct *vma)
{
return false;
}
static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
pte_t pte)
{
@@ -423,8 +450,8 @@ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
}
/*
* Returns true if this is a swap pte and was uffd-wp wr-protected in either
* forms (pte marker or a normal swap pte), false otherwise.
* Returns true if this swap pte carries uffd-tracked state in either
* form (pte marker or a normal swap pte), false otherwise.
*/
static inline bool pte_swp_uffd_any(pte_t pte)
{

View File

@@ -186,6 +186,12 @@ IF_HAVE_PG_ARCH_3(arch_3)
# define IF_HAVE_UFFD_MINOR(flag, name)
#endif
#ifdef CONFIG_USERFAULTFD_RWP
# define IF_HAVE_UFFD_RWP(flag, name) {flag, name},
#else
# define IF_HAVE_UFFD_RWP(flag, name)
#endif
#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32)
# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name},
#else
@@ -207,6 +213,7 @@ IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR, "uffd_minor" ) \
{VM_PFNMAP, "pfnmap" }, \
{VM_MAYBE_GUARD, "maybe_guard" }, \
{VM_UFFD_WP, "uffd_wp" }, \
IF_HAVE_UFFD_RWP(VM_UFFD_RWP, "uffd_rwp" ) \
{VM_LOCKED, "locked" }, \
{VM_IO, "io" }, \
{VM_SEQ_READ, "seqread" }, \