mm: add PTE_MARKER_GUARD PTE marker

Add a new PTE marker that results in any access causing the accessing
process to segfault.

This is preferable to PTE_MARKER_POISONED, which results in the same
handling as hardware poisoned memory, and is thus undesirable for cases
where we simply wish to 'soft' poison a range.

This is in preparation for implementing the ability to specify guard pages
at the page table level, i.e.  ranges that, when accessed, should cause
process termination.

Additionally, rename zap_drop_file_uffd_wp() to zap_drop_markers() - the
function checks the ZAP_FLAG_DROP_MARKER flag so naming it for this single
purpose was simply incorrect.

We then reuse the same logic to determine whether a zap should clear a
guard entry - this should only be performed on teardown and never on
MADV_DONTNEED or MADV_FREE.

We additionally add a WARN_ON_ONCE() in hugetlb logic should a guard
marker be encountered there, as we explicitly do not support this
operation and this should not occur.

Link: https://lkml.kernel.org/r/f47f3d5acca2dcf9bbf655b6d33f3dc713e4a4a0.1730123433.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Vlastimil Babka <vbabkba@suse.cz>
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Suggested-by: Jann Horn <jannh@google.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Cc: Arnd Bergmann <arnd@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chris Zankel <chris@zankel.net>
Cc: Helge Deller <deller@gmx.de>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 47 insertions, 7 deletions

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 355cf46a01a6..1b6a917fffa4 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -544,7 +544,7 @@ static inline pte_marker copy_pte_marker(
 {
 	pte_marker srcm = pte_marker_get(entry);
 	/* Always copy error entries. */
-	pte_marker dstm = srcm & PTE_MARKER_POISONED;
+	pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD);
 
 	/* Only copy PTE markers if UFFD register matches. */
 	if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma))
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index cb468e418ea1..96f26e29fefe 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -426,9 +426,19 @@ typedef unsigned long pte_marker;
  * "Poisoned" here is meant in the very general sense of "future accesses are
  * invalid", instead of referring very specifically to hardware memory errors.
  * This marker is meant to represent any of various different causes of this.
+ *
+ * Note that, when encountered by the faulting logic, PTEs with this marker will
+ * result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error
+ * logic.
  */
 #define  PTE_MARKER_POISONED			BIT(1)
-#define  PTE_MARKER_MASK			(BIT(2) - 1)
+/*
+ * Indicates that, on fault, this PTE will case a SIGSEGV signal to be
+ * sent. This means guard markers behave in effect as if the region were mapped
+ * PROT_NONE, rather than if they were a memory hole or equivalent.
+ */
+#define  PTE_MARKER_GUARD			BIT(2)
+#define  PTE_MARKER_MASK			(BIT(3) - 1)
 
 static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
 {
@@ -464,6 +474,18 @@ static inline int is_poisoned_swp_entry(swp_entry_t entry)
 {
 	return is_pte_marker_entry(entry) &&
 	    (pte_marker_get(entry) & PTE_MARKER_POISONED);
+
+}
+
+static inline swp_entry_t make_guard_swp_entry(void)
+{
+	return make_pte_marker_entry(PTE_MARKER_GUARD);
+}
+
+static inline int is_guard_swp_entry(swp_entry_t entry)
+{
+	return is_pte_marker_entry(entry) &&
+		(pte_marker_get(entry) & PTE_MARKER_GUARD);
 }
 
 /*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 906294ac85dc..2c8c5da0f5d3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6353,6 +6353,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				ret = VM_FAULT_HWPOISON_LARGE |
 				      VM_FAULT_SET_HINDEX(hstate_index(h));
 				goto out_mutex;
+			} else if (WARN_ON_ONCE(marker & PTE_MARKER_GUARD)) {
+				/* This isn't supported in hugetlb. */
+				ret = VM_FAULT_SIGSEGV;
+				goto out_mutex;
 			}
 		}
 
diff --git a/mm/memory.c b/mm/memory.c
index 2d32023d4eb8..75c2dfd04f72 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1455,7 +1455,7 @@ static inline bool should_zap_folio(struct zap_details *details,
 	return !folio_test_anon(folio);
 }
 
-static inline bool zap_drop_file_uffd_wp(struct zap_details *details)
+static inline bool zap_drop_markers(struct zap_details *details)
 {
 	if (!details)
 		return false;
@@ -1476,7 +1476,7 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 	if (vma_is_anonymous(vma))
 		return;
 
-	if (zap_drop_file_uffd_wp(details))
+	if (zap_drop_markers(details))
 		return;
 
 	for (;;) {
@@ -1671,7 +1671,15 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			 * drop the marker if explicitly requested.
 			 */
 			if (!vma_is_anonymous(vma) &&
-			    !zap_drop_file_uffd_wp(details))
+			    !zap_drop_markers(details))
+				continue;
+		} else if (is_guard_swp_entry(entry)) {
+			/*
+			 * Ordinary zapping should not remove guard PTE
+			 * markers. Only do so if we should remove PTE markers
+			 * in general.
+			 */
+			if (!zap_drop_markers(details))
 				continue;
 		} else if (is_hwpoison_entry(entry) ||
 			   is_poisoned_swp_entry(entry)) {
@@ -4003,6 +4011,10 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
 	if (marker & PTE_MARKER_POISONED)
 		return VM_FAULT_HWPOISON;
 
+	/* Hitting a guard page is always a fatal condition. */
+	if (marker & PTE_MARKER_GUARD)
+		return VM_FAULT_SIGSEGV;
+
 	if (pte_marker_entry_uffd_wp(entry))
 		return pte_marker_handle_uffd_wp(vmf);
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 6f450af3252e..516b1d847e2c 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -236,9 +236,11 @@ static long change_pte_range(struct mmu_gather *tlb,
 			} else if (is_pte_marker_entry(entry)) {
 				/*
 				 * Ignore error swap entries unconditionally,
-				 * because any access should sigbus anyway.
+				 * because any access should sigbus/sigsegv
+				 * anyway.
 				 */
-				if (is_poisoned_swp_entry(entry))
+				if (is_poisoned_swp_entry(entry) ||
+				    is_guard_swp_entry(entry))
 					continue;
 				/*
 				 * If this is uffd-wp pte marker and we'd like