mm/shmem: persist uffd-wp bit across zapping for file-backed

File-backed memory is prone to being unmapped at any time.  It means all
information in the pte will be dropped, including the uffd-wp flag.

To persist the uffd-wp flag, we'll use the pte markers.  This patch
teaches the zap code to understand uffd-wp and know when to keep or drop
the uffd-wp bit.

Add a new flag ZAP_FLAG_DROP_MARKER and set it in zap_details when we
don't want to persist such an information, for example, when destroying
the whole vma, or punching a hole in a shmem file.  For the rest cases we
should never drop the uffd-wp bit, or the wr-protect information will get
lost.

The new ZAP_FLAG_DROP_MARKER needs to be put into mm.h rather than
memory.c because it'll be further referenced in hugetlb files later.

Link: https://lkml.kernel.org/r/20220405014847.14295-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 46 insertions, 3 deletions

diff --git a/mm/memory.c b/mm/memory.c
index c16f873373a2..ecb1d58dcaef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -74,6 +74,7 @@
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
 
 #include <trace/events/kmem.h>
 
@@ -1306,6 +1307,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 struct zap_details {
 	struct folio *single_folio;	/* Locked folio to be unmapped */
 	bool even_cows;			/* Zap COWed private pages too? */
+	zap_flags_t zap_flags;		/* Extra flags for zapping */
 };
 
 /* Whether we should zap all COWed (private) pages too */
@@ -1334,6 +1336,29 @@ static inline bool should_zap_page(struct zap_details *details, struct page *pag
 	return !PageAnon(page);
 }
 
+static inline bool zap_drop_file_uffd_wp(struct zap_details *details)
+{
+	if (!details)
+		return false;
+
+	return details->zap_flags & ZAP_FLAG_DROP_MARKER;
+}
+
+/*
+ * This function makes sure that we'll replace the none pte with an uffd-wp
+ * swap special pte marker when necessary. Must be with the pgtable lock held.
+ */
+static inline void
+zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
+			      unsigned long addr, pte_t *pte,
+			      struct zap_details *details, pte_t pteval)
+{
+	if (zap_drop_file_uffd_wp(details))
+		return;
+
+	pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
+}
+
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
@@ -1371,6 +1396,8 @@ again:
 			ptent = ptep_get_and_clear_full(mm, addr, pte,
 							tlb->fullmm);
 			tlb_remove_tlb_entry(tlb, pte, addr);
+			zap_install_uffd_wp_if_needed(vma, addr, pte, details,
+						      ptent);
 			if (unlikely(!page))
 				continue;
 
@@ -1401,6 +1428,13 @@ again:
 			page = pfn_swap_entry_to_page(entry);
 			if (unlikely(!should_zap_page(details, page)))
 				continue;
+			/*
+			 * Both device private/exclusive mappings should only
+			 * work with anonymous page so far, so we don't need to
+			 * consider uffd-wp bit when zap. For more information,
+			 * see zap_install_uffd_wp_if_needed().
+			 */
+			WARN_ON_ONCE(!vma_is_anonymous(vma));
 			rss[mm_counter(page)]--;
 			if (is_device_private_entry(entry))
 				page_remove_rmap(page, vma, false);
@@ -1417,8 +1451,10 @@ again:
 			if (!should_zap_page(details, page))
 				continue;
 			rss[mm_counter(page)]--;
-		} else if (is_pte_marker_entry(entry)) {
-			/* By default, simply drop all pte markers when zap */
+		} else if (pte_marker_entry_uffd_wp(entry)) {
+			/* Only drop the uffd-wp marker if explicitly requested */
+			if (!zap_drop_file_uffd_wp(details))
+				continue;
 		} else if (is_hwpoison_entry(entry)) {
 			if (!should_zap_cows(details))
 				continue;
@@ -1427,6 +1463,7 @@ again:
 			WARN_ON_ONCE(1);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+		zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
 	add_mm_rss_vec(mm, rss);
@@ -1637,12 +1674,17 @@ void unmap_vmas(struct mmu_gather *tlb,
 		unsigned long end_addr)
 {
 	struct mmu_notifier_range range;
+	struct zap_details details = {
+		.zap_flags = ZAP_FLAG_DROP_MARKER,
+		/* Careful - we need to zap private pages too! */
+		.even_cows = true,
+	};
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
-		unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
+		unmap_single_vma(tlb, vma, start_addr, end_addr, &details);
 	mmu_notifier_invalidate_range_end(&range);
 }
 
@@ -3438,6 +3480,7 @@ void unmap_mapping_folio(struct folio *folio)
 
 	details.even_cows = false;
 	details.single_folio = folio;
+	details.zap_flags = ZAP_FLAG_DROP_MARKER;
 
 	i_mmap_lock_read(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))