mm/uffd: UFFD_FEATURE_WP_UNPOPULATED

Patch series "mm/uffd: Add feature bit UFFD_FEATURE_WP_UNPOPULATED", v4.

The new feature bit makes anonymous memory acts the same as file memory on
userfaultfd-wp in that it'll also wr-protect none ptes.

It can be useful in two cases:

(1) Uffd-wp app that needs to wr-protect none ptes like QEMU snapshot,
    so pre-fault can be replaced by enabling this flag and speed up
    protections

(2) It helps to implement async uffd-wp mode that Muhammad is working on [1]

It's debatable whether this is the most ideal solution because with the
new feature bit set, wr-protect none pte needs to pre-populate the
pgtables to the last level (PAGE_SIZE).  But it seems fine so far to
service either purpose above, so we can leave optimizations for later.

The series brings pte markers to anonymous memory too.  There's some
change in the common mm code path in the 1st patch, great to have some eye
looking at it, but hopefully they're still relatively straightforward.


This patch (of 2):

This is a new feature that controls how uffd-wp handles none ptes.  When
it's set, the kernel will handle anonymous memory the same way as file
memory, by allowing the user to wr-protect unpopulated ptes.

File memories handles none ptes consistently by allowing wr-protecting of
none ptes because of the unawareness of page cache being exist or not. 
For anonymous it was not as persistent because we used to assume that we
don't need protections on none ptes or known zero pages.

One use case of such a feature bit was VM live snapshot, where if without
wr-protecting empty ptes the snapshot can contain random rubbish in the
holes of the anonymous memory, which can cause misbehave of the guest when
the guest OS assumes the pages should be all zeros.

QEMU worked it around by pre-populate the section with reads to fill in
zero page entries before starting the whole snapshot process [1].

Recently there's another need raised on using userfaultfd wr-protect for
detecting dirty pages (to replace soft-dirty in some cases) [2].  In that
case if without being able to wr-protect none ptes by default, the dirty
info can get lost, since we cannot treat every none pte to be dirty (the
current design is identify a page dirty based on uffd-wp bit being
cleared).

In general, we want to be able to wr-protect empty ptes too even for
anonymous.

This patch implements UFFD_FEATURE_WP_UNPOPULATED so that it'll make
uffd-wp handling on none ptes being consistent no matter what the memory
type is underneath.  It doesn't have any impact on file memories so far
because we already have pte markers taking care of that.  So it only
affects anonymous.

The feature bit is by default off, so the old behavior will be maintained.
Sometimes it may be wanted because the wr-protect of none ptes will
contain overheads not only during UFFDIO_WRITEPROTECT (by applying pte
markers to anonymous), but also on creating the pgtables to store the pte
markers.  So there's potentially less chance of using thp on the first
fault for a none pmd or larger than a pmd.

The major implementation part is teaching the whole kernel to understand
pte markers even for anonymously mapped ranges, meanwhile allowing the
UFFDIO_WRITEPROTECT ioctl to apply pte markers for anonymous too when the
new feature bit is set.

Note that even if the patch subject starts with mm/uffd, there're a few
small refactors to major mm path of handling anonymous page faults.  But
they should be straightforward.

With WP_UNPOPUATED, application like QEMU can avoid pre-read faults all
the memory before wr-protect during taking a live snapshot.  Quotting from
Muhammad's test result here [3] based on a simple program [4]:

  (1) With huge page disabled
  echo madvise > /sys/kernel/mm/transparent_hugepage/enabled
  ./uffd_wp_perf
  Test DEFAULT: 4
  Test PRE-READ: 1111453 (pre-fault 1101011)
  Test MADVISE: 278276 (pre-fault 266378)
  Test WP-UNPOPULATE: 11712

  (2) With Huge page enabled
  echo always > /sys/kernel/mm/transparent_hugepage/enabled
  ./uffd_wp_perf
  Test DEFAULT: 4
  Test PRE-READ: 22521 (pre-fault 22348)
  Test MADVISE: 4909 (pre-fault 4743)
  Test WP-UNPOPULATE: 14448

There'll be a great perf boost for no-thp case, while for thp enabled with
extreme case of all-thp-zero WP_UNPOPULATED can be slower than MADVISE,
but that's low possibility in reality, also the overhead was not reduced
but postponed until a follow up write on any huge zero thp, so potentially
it is faster by making the follow up writes slower.

[1] https://lore.kernel.org/all/20210401092226.102804-4-andrey.gruzdev@virtuozzo.com/
[2] https://lore.kernel.org/all/Y+v2HJ8+3i%2FKzDBu@x1n/
[3] https://lore.kernel.org/all/d0eb0a13-16dc-1ac1-653a-78b7273781e3@collabora.com/
[4] https://github.com/xzpeter/clibs/blob/master/uffd-test/uffd-wp-perf.c

[peterx@redhat.com: comment changes, oneliner fix to khugepaged]
  Link: https://lkml.kernel.org/r/ZB2/8jPhD3fpx5U8@x1n
Link: https://lkml.kernel.org/r/20230309223711.823547-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20230309223711.823547-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 84 insertions, 25 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 074ea534f786..c7317678cb10 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1177,7 +1177,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 				 * enabled swap entries.  Please see
 				 * comment below for pte_uffd_wp().
 				 */
-				if (pte_swp_uffd_wp(pteval)) {
+				if (pte_swp_uffd_wp_any(pteval)) {
 					result = SCAN_PTE_UFFD_WP;
 					goto out_unmap;
 				}
diff --git a/mm/memory.c b/mm/memory.c
index 6285cad1f4fb..a890b2951b53 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -104,6 +104,20 @@ EXPORT_SYMBOL(mem_map);
 #endif
 
 static vm_fault_t do_fault(struct vm_fault *vmf);
+static vm_fault_t do_anonymous_page(struct vm_fault *vmf);
+static bool vmf_pte_changed(struct vm_fault *vmf);
+
+/*
+ * Return true if the original pte was a uffd-wp pte marker (so the pte was
+ * wr-protected).
+ */
+static bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf)
+{
+	if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID))
+		return false;
+
+	return pte_marker_uffd_wp(vmf->orig_pte);
+}
 
 /*
  * A number of key systems in x86 including ioremap() rely on the assumption
@@ -1346,6 +1360,10 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 			      unsigned long addr, pte_t *pte,
 			      struct zap_details *details, pte_t pteval)
 {
+	/* Zap on anonymous always means dropping everything */
+	if (vma_is_anonymous(vma))
+		return;
+
 	if (zap_drop_file_uffd_wp(details))
 		return;
 
@@ -1452,8 +1470,12 @@ again:
 				continue;
 			rss[mm_counter(page)]--;
 		} else if (pte_marker_entry_uffd_wp(entry)) {
-			/* Only drop the uffd-wp marker if explicitly requested */
-			if (!zap_drop_file_uffd_wp(details))
+			/*
+			 * For anon: always drop the marker; for file: only
+			 * drop the marker if explicitly requested.
+			 */
+			if (!vma_is_anonymous(vma) &&
+			    !zap_drop_file_uffd_wp(details))
 				continue;
 		} else if (is_hwpoison_entry(entry) ||
 			   is_swapin_error_entry(entry)) {
@@ -3620,6 +3642,14 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
 	return 0;
 }
 
+static vm_fault_t do_pte_missing(struct vm_fault *vmf)
+{
+	if (vma_is_anonymous(vmf->vma))
+		return do_anonymous_page(vmf);
+	else
+		return do_fault(vmf);
+}
+
 /*
  * This is actually a page-missing access, but with uffd-wp special pte
  * installed.  It means this pte was wr-protected before being unmapped.
@@ -3630,11 +3660,10 @@ static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf)
 	 * Just in case there're leftover special ptes even after the region
 	 * got unregistered - we can simply clear them.
 	 */
-	if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma)))
+	if (unlikely(!userfaultfd_wp(vmf->vma)))
 		return pte_marker_clear(vmf);
 
-	/* do_fault() can handle pte markers too like none pte */
-	return do_fault(vmf);
+	return do_pte_missing(vmf);
 }
 
 static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
@@ -3999,6 +4028,7 @@ out_release:
  */
 static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
+	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	struct vm_area_struct *vma = vmf->vma;
 	struct folio *folio;
 	vm_fault_t ret = 0;
@@ -4032,7 +4062,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 						vma->vm_page_prot));
 		vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 				vmf->address, &vmf->ptl);
-		if (!pte_none(*vmf->pte)) {
+		if (vmf_pte_changed(vmf)) {
 			update_mmu_tlb(vma, vmf->address, vmf->pte);
 			goto unlock;
 		}
@@ -4072,7 +4102,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
-	if (!pte_none(*vmf->pte)) {
+	if (vmf_pte_changed(vmf)) {
 		update_mmu_tlb(vma, vmf->address, vmf->pte);
 		goto release;
 	}
@@ -4092,6 +4122,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	folio_add_new_anon_rmap(folio, vma, vmf->address);
 	folio_add_lru_vma(folio, vma);
 setpte:
+	if (uffd_wp)
+		entry = pte_mkuffd_wp(entry);
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
 	/* No need to invalidate - it was non-present before */
@@ -4259,7 +4291,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte);
+	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	bool prefault = vmf->address != addr;
 	pte_t entry;
@@ -4903,12 +4935,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		}
 	}
 
-	if (!vmf->pte) {
-		if (vma_is_anonymous(vmf->vma))
-			return do_anonymous_page(vmf);
-		else
-			return do_fault(vmf);
-	}
+	if (!vmf->pte)
+		return do_pte_missing(vmf);
 
 	if (!pte_present(vmf->orig_pte))
 		return do_swap_page(vmf);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 13e84d8c0797..b9da9a5f87fe 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -276,7 +276,15 @@ static long change_pte_range(struct mmu_gather *tlb,
 		} else {
 			/* It must be an none page, or what else?.. */
 			WARN_ON_ONCE(!pte_none(oldpte));
-			if (unlikely(uffd_wp && !vma_is_anonymous(vma))) {
+
+			/*
+			 * Nobody plays with any none ptes besides
+			 * userfaultfd when applying the protections.
+			 */
+			if (likely(!uffd_wp))
+				continue;
+
+			if (userfaultfd_wp_use_markers(vma)) {
 				/*
 				 * For file-backed mem, we need to be able to
 				 * wr-protect a none pte, because even if the
@@ -320,23 +328,46 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
 	return 0;
 }
 
-/* Return true if we're uffd wr-protecting file-backed memory, or false */
+/*
+ * Return true if we want to split THPs into PTE mappings in change
+ * protection procedure, false otherwise.
+ */
 static inline bool
-uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags)
+pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags)
 {
+	/*
+	 * pte markers only resides in pte level, if we need pte markers,
+	 * we need to split.  We cannot wr-protect shmem thp because file
+	 * thp is handled differently when split by erasing the pmd so far.
+	 */
 	return (cp_flags & MM_CP_UFFD_WP) && !vma_is_anonymous(vma);
 }
 
 /*
- * If wr-protecting the range for file-backed, populate pgtable for the case
- * when pgtable is empty but page cache exists.  When {pte|pmd|...}_alloc()
- * failed we treat it the same way as pgtable allocation failures during
- * page faults by kicking OOM and returning error.
+ * Return true if we want to populate pgtables in change protection
+ * procedure, false otherwise
+ */
+static inline bool
+pgtable_populate_needed(struct vm_area_struct *vma, unsigned long cp_flags)
+{
+	/* If not within ioctl(UFFDIO_WRITEPROTECT), then don't bother */
+	if (!(cp_flags & MM_CP_UFFD_WP))
+		return false;
+
+	/* Populate if the userfaultfd mode requires pte markers */
+	return userfaultfd_wp_use_markers(vma);
+}
+
+/*
+ * Populate the pgtable underneath for whatever reason if requested.
+ * When {pte|pmd|...}_alloc() failed we treat it the same way as pgtable
+ * allocation failures during page faults by kicking OOM and returning
+ * error.
  */
 #define  change_pmd_prepare(vma, pmd, cp_flags)				\
 	({								\
 		long err = 0;						\
-		if (unlikely(uffd_wp_protect_file(vma, cp_flags))) {	\
+		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
 			if (pte_alloc(vma->vm_mm, pmd))			\
 				err = -ENOMEM;				\
 		}							\
@@ -351,7 +382,7 @@ uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags)
 #define  change_prepare(vma, high, low, addr, cp_flags)			\
 	  ({								\
 		long err = 0;						\
-		if (unlikely(uffd_wp_protect_file(vma, cp_flags))) {	\
+		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
 			low##_t *p = low##_alloc(vma->vm_mm, high, addr); \
 			if (p == NULL)					\
 				err = -ENOMEM;				\
@@ -404,7 +435,7 @@ static inline long change_pmd_range(struct mmu_gather *tlb,
 
 		if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
 			if ((next - addr != HPAGE_PMD_SIZE) ||
-			    uffd_wp_protect_file(vma, cp_flags)) {
+			    pgtable_split_needed(vma, cp_flags)) {
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 				/*
 				 * For file-backed, the pmd could have been