@@ -1706,6 +1706,8 @@ extern void user_shm_unlock(size_t, struct user_struct *);
#define ZAP_FLAG_CHECK_MAPPING BIT(0)
/* Whether to skip zapping swap entries */
#define ZAP_FLAG_SKIP_SWAP BIT(1)
+/* Whether to completely drop uffd-wp entries for file-backed memory */
+#define ZAP_FLAG_DROP_FILE_UFFD_WP BIT(2)
/*
* Parameter block passed down to zap_pte_range in exceptional cases.
@@ -1738,6 +1740,15 @@ zap_skip_swap(struct zap_details *details)
return details->zap_flags & ZAP_FLAG_SKIP_SWAP;
}
+static inline bool
+zap_drop_file_uffd_wp(struct zap_details *details)
+{
+ if (!details)
+ return false;
+
+ return details->zap_flags & ZAP_FLAG_DROP_FILE_UFFD_WP;
+}
+
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte);
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -4,6 +4,8 @@
#include <linux/huge_mm.h>
#include <linux/swap.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/swapops.h>
/**
* page_is_file_lru - should the page be on a file LRU or anon LRU?
@@ -104,4 +106,45 @@ static __always_inline void del_page_from_lru_list(struct page *page,
update_lru_size(lruvec, page_lru(page), page_zonenum(page),
-thp_nr_pages(page));
}
+
+/*
+ * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
+ * replace a none pte. NOTE! This should only be called when *pte is already
+ * cleared so we will never accidentally replace something valuable. Meanwhile
+ * none pte also means we are not demoting the pte so if tlb flushed then we
+ * don't need to do it again; otherwise if tlb flush is postponed then it's
+ * even better.
+ *
+ * Must be called with pgtable lock held.
+ */
+static inline void
+pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *pte, pte_t pteval)
+{
+#ifdef CONFIG_USERFAULTFD
+ bool arm_uffd_pte = false;
+
+ /* The current status of the pte should be "cleared" before calling */
+ WARN_ON_ONCE(!pte_none(*pte));
+
+ if (vma_is_anonymous(vma))
+ return;
+
+ /* A uffd-wp wr-protected normal pte */
+ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
+ arm_uffd_pte = true;
+
+ /*
+ * A uffd-wp wr-protected swap pte. Note: this should even work for
+ * pte_swp_uffd_wp_special() too.
+ */
+ if (unlikely(is_swap_pte(pteval) && pte_swp_uffd_wp(pteval)))
+ arm_uffd_pte = true;
+
+ if (unlikely(arm_uffd_pte))
+ set_pte_at(vma->vm_mm, addr, pte,
+ pte_swp_mkuffd_wp_special(vma));
+#endif
+}
+
#endif
@@ -73,6 +73,7 @@
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
#include <trace/events/kmem.h>
@@ -1210,6 +1211,21 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
return ret;
}
+/*
+ * 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,
@@ -1247,6 +1263,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
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;
@@ -1271,6 +1289,22 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
continue;
}
+ /*
+ * If this is a special uffd-wp marker pte... Drop it only if
+ * enforced to do so.
+ */
+ if (unlikely(is_swap_special_pte(ptent))) {
+ WARN_ON_ONCE(!pte_swp_uffd_wp_special(ptent));
+ /*
+ * If this is a common unmap of ptes, keep this as is.
+ * Drop it only if this is a whole-vma destruction.
+ */
+ if (zap_drop_file_uffd_wp(details))
+ ptep_get_and_clear_full(mm, addr, pte,
+ tlb->fullmm);
+ continue;
+ }
+
entry = pte_to_swp_entry(ptent);
if (is_device_private_entry(entry)) {
struct page *page = device_private_entry_to_page(entry);
@@ -1281,6 +1315,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
rss[mm_counter(page)]--;
page_remove_rmap(page, false);
put_page(page);
+ zap_install_uffd_wp_if_needed(vma, addr, pte, details,
+ ptent);
continue;
}
@@ -1298,6 +1334,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
if (unlikely(!free_swap_and_cache(entry)))
print_bad_pte(vma, addr, ptent, NULL);
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);
@@ -1497,12 +1534,15 @@ 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_FILE_UFFD_WP,
+ };
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);
}
@@ -72,6 +72,7 @@
#include <linux/page_idle.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
+#include <linux/mm_inline.h>
#include <asm/tlbflush.h>
@@ -1571,6 +1572,13 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
pteval = ptep_clear_flush(vma, address, pvmw.pte);
}
+ /*
+ * Now the pte is cleared. If this is uffd-wp armed pte, we
+ * may want to replace a none pte with a marker pte if it's
+ * file-backed, so we don't lose the tracking information.
+ */
+ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval);
+
/* Move the dirty bit to the page. Now the pte is gone. */
if (pte_dirty(pteval))
set_page_dirty(page);
@@ -173,7 +173,13 @@ truncate_cleanup_page(struct address_space *mapping, struct page *page)
if (page_mapped(page)) {
unsigned int nr = thp_nr_pages(page);
unmap_mapping_pages(mapping, page->index, nr,
- ZAP_FLAG_CHECK_MAPPING);
+ ZAP_FLAG_CHECK_MAPPING |
+ /*
+ * Now it's safe to drop uffd-wp because
+ * we're with page lock, and the page is
+ * being truncated.
+ */
+ ZAP_FLAG_DROP_FILE_UFFD_WP);
}
if (page_has_private(page))
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. Since the uffd-wp info cannot be stored in page cache or swap cache, persist this wr-protect information by installing the special uffd-wp marker pte when we're going to unmap a uffd wr-protected pte. When the pte is accessed again, we will know it's previously wr-protected by recognizing the special pte. Meanwhile add a new flag ZAP_FLAG_DROP_FILE_UFFD_WP 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 latter, we can only drop the uffd-wp bit when holding the page lock. It means the unmap_mapping_range() in shmem_fallocate() still reuqires to zap without ZAP_FLAG_DROP_FILE_UFFD_WP because that's still racy with the page faults. Signed-off-by: Peter Xu <peterx@redhat.com> --- include/linux/mm.h | 11 ++++++++++ include/linux/mm_inline.h | 43 +++++++++++++++++++++++++++++++++++++++ mm/memory.c | 42 +++++++++++++++++++++++++++++++++++++- mm/rmap.c | 8 ++++++++ mm/truncate.c | 8 +++++++- 5 files changed, 110 insertions(+), 2 deletions(-)