@@ -182,8 +182,7 @@ u64 stable_page_flags(struct page *page)
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
- u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
- if (PageTail(page) && PageSlab(compound_head(page)))
+ if (PageSlab(page) || PageSlab(compound_head(page)))
u |= 1 << KPF_SLAB;
u |= kpf_copy_bit(k, KPF_ERROR, PG_error);
@@ -107,7 +107,7 @@ enum pageflags {
PG_workingset,
PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
PG_error,
- PG_slab,
+ PG_slab, /* Slab page if !PageAnon() */
PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/
PG_arch_1,
PG_reserved,
@@ -142,6 +142,63 @@ enum pageflags {
PG_readahead = PG_reclaim,
+ /*
+ * Depending on the way an anonymous folio can be mapped into a page
+ * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped
+ * THP), PG_anon_exclusive may be set only for the head page or for
+ * subpages of an anonymous folio.
+ *
+ * PG_anon_exclusive is *usually* only expressive in combination with a
+ * page table entry. Depending on the page table entry type it might
+ * store the following information:
+ *
+ * Is what's mapped via this page table entry exclusive to the
+ * single process and can be mapped writable without further
+ * checks? If not, it might be shared and we might have to COW.
+ *
+ * For now, we only expect PTE-mapped THPs to make use of
+ * PG_anon_exclusive in subpages. For other anonymous compound
+ * folios (i.e., hugetlb), only the head page is logically mapped and
+ * holds this information.
+ *
+ * For example, an exclusive, PMD-mapped THP only has PG_anon_exclusive
+ * set on the head page. When replacing the PMD by a page table full
+ * of PTEs, PG_anon_exclusive, if set on the head page, will be set on
+ * all tail pages accordingly. Note that converting from a PTE-mapping
+ * to a PMD mapping using the same compound page is currently not
+ * possible and consequently doesn't require care.
+ *
+ * If GUP wants to take a reliable pin (FOLL_PIN) on an anonymous page,
+ * it should only pin if the relevant PG_anon_bit is set. In that case,
+ * the pin will be fully reliable and stay consistent with the pages
+ * mapped into the page table, as the bit cannot get cleared (e.g., by
+ * fork(), KSM) while the page is pinned. For anonymous pages that
+ * are mapped R/W, PG_anon_exclusive can be assumed to always be set
+ * because such pages cannot possibly be shared.
+ *
+ * The page table lock protecting the page table entry is the primary
+ * synchronization mechanism for PG_anon_exclusive; GUP-fast that does
+ * not take the PT lock needs special care when trying to clear the
+ * flag.
+ *
+ * Page table entry types and PG_anon_exclusive:
+ * * Present: PG_anon_exclusive applies.
+ * * Swap: the information is lost. PG_anon_exclusive was cleared.
+ * * Migration: the entry holds this information instead.
+ * PG_anon_exclusive was cleared.
+ * * Device private: PG_anon_exclusive applies.
+ * * Device exclusive: PG_anon_exclusive applies.
+ * * HW Poison: PG_anon_exclusive is stale and not changed.
+ *
+ * If the page may be pinned (FOLL_PIN), clearing PG_anon_exclusive is
+ * not allowed and the flag will stick around until the page is freed
+ * and folio->mapping is cleared.
+ *
+ * Before clearing folio->mapping, PG_anon_exclusive has to be cleared
+ * to not result in PageSlab() false positives.
+ */
+ PG_anon_exclusive = PG_slab,
+
/* Filesystems */
PG_checked = PG_owner_priv_1,
@@ -425,7 +482,6 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
TESTCLEARFLAG(Active, active, PF_HEAD)
PAGEFLAG(Workingset, workingset, PF_HEAD)
TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
-__PAGEFLAG(Slab, slab, PF_NO_TAIL)
__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
@@ -920,6 +976,70 @@ extern bool is_free_buddy_page(struct page *page);
__PAGEFLAG(Isolated, isolated, PF_ANY);
+static __always_inline bool folio_test_slab(struct folio *folio)
+{
+ return !folio_test_anon(folio) &&
+ test_bit(PG_slab, folio_flags(folio, FOLIO_PF_NO_TAIL));
+}
+
+static __always_inline int PageSlab(struct page *page)
+{
+ return !PageAnon(page) &&
+ test_bit(PG_slab, &PF_NO_TAIL(page, 0)->flags);
+}
+
+static __always_inline void __folio_set_slab(struct folio *folio)
+{
+ VM_BUG_ON(folio_test_anon(folio));
+ __set_bit(PG_slab, folio_flags(folio, FOLIO_PF_NO_TAIL));
+}
+
+static __always_inline void __SetPageSlab(struct page *page)
+{
+ VM_BUG_ON_PGFLAGS(PageAnon(page), page);
+ __set_bit(PG_slab, &PF_NO_TAIL(page, 1)->flags);
+}
+
+static __always_inline void __folio_clear_slab(struct folio *folio)
+{
+ VM_BUG_ON(folio_test_anon(folio));
+ __clear_bit(PG_slab, folio_flags(folio, FOLIO_PF_NO_TAIL));
+}
+
+static __always_inline void __ClearPageSlab(struct page *page)
+{
+ VM_BUG_ON_PGFLAGS(PageAnon(page), page);
+ __clear_bit(PG_slab, &PF_NO_TAIL(page, 1)->flags);
+}
+
+static __always_inline int PageAnonExclusive(struct page *page)
+{
+ VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
+ VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+ return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
+static __always_inline void SetPageAnonExclusive(struct page *page)
+{
+ VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page);
+ VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+ set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
+static __always_inline void ClearPageAnonExclusive(struct page *page)
+{
+ VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page);
+ VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+ clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
+static __always_inline void __ClearPageAnonExclusive(struct page *page)
+{
+ VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
+ VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+ __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
#ifdef CONFIG_MMU
#define __PG_MLOCKED (1UL << PG_mlocked)
#else
@@ -103,7 +103,7 @@
{1UL << PG_lru, "lru" }, \
{1UL << PG_active, "active" }, \
{1UL << PG_workingset, "workingset" }, \
- {1UL << PG_slab, "slab" }, \
+ {1UL << PG_slab, "slab/anon_exclusive" }, \
{1UL << PG_owner_priv_1, "owner_priv_1" }, \
{1UL << PG_arch_1, "arch_1" }, \
{1UL << PG_reserved, "reserved" }, \
@@ -1669,6 +1669,10 @@ void free_huge_page(struct page *page)
VM_BUG_ON_PAGE(page_mapcount(page), page);
hugetlb_set_page_subpool(page, NULL);
+ if (PageAnon(page)) {
+ __ClearPageAnonExclusive(page);
+ wmb(); /* avoid PageSlab() false positives */
+ }
page->mapping = NULL;
restore_reserve = HPageRestoreReserve(page);
ClearHPageRestoreReserve(page);
@@ -1470,17 +1470,29 @@ static int identify_page_state(unsigned long pfn, struct page *p,
* The first check uses the current page flags which may not have any
* relevant information. The second check with the saved page flags is
* carried out only if the first check can't determine the page status.
+ *
+ * Note that PG_slab is also used as PG_anon_exclusive for PageAnon()
+ * pages. Most of these pages should have been handled previously,
+ * however, let's play safe and verify via PageAnon().
*/
- for (ps = error_states;; ps++)
- if ((p->flags & ps->mask) == ps->res)
- break;
+ for (ps = error_states;; ps++) {
+ if ((p->flags & ps->mask) != ps->res)
+ continue;
+ if ((ps->type == MF_MSG_SLAB) && PageAnon(p))
+ continue;
+ break;
+ }
page_flags |= (p->flags & (1UL << PG_dirty));
if (!ps->mask)
- for (ps = error_states;; ps++)
- if ((page_flags & ps->mask) == ps->res)
- break;
+ for (ps = error_states;; ps++) {
+ if ((page_flags & ps->mask) != ps->res)
+ continue;
+ if ((ps->type == MF_MSG_SLAB) && PageAnon(p))
+ continue;
+ break;
+ }
return page_action(ps, p, pfn);
}
@@ -478,6 +478,17 @@ void free_devmap_managed_page(struct page *page)
mem_cgroup_uncharge(page_folio(page));
+ /*
+ * Note: we don't expect anonymous compound pages yet. Once supported
+ * and we could PTE-map them similar to THP, we'd have to clear
+ * PG_anon_exclusive on all tail pages.
+ */
+ VM_BUG_ON_PAGE(PageAnon(page) && PageCompound(page), page);
+ if (PageAnon(page)) {
+ __ClearPageAnonExclusive(page);
+ wmb(); /* avoid PageSlab() false positives */
+ }
+
/*
* When a device_private page is freed, the page->mapping field
* may still contain a (stale) mapping value. For example, the
@@ -1297,6 +1297,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
{
int bad = 0;
bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
+ const bool anon = PageAnon(page);
VM_BUG_ON_PAGE(PageTail(page), page);
@@ -1329,6 +1330,14 @@ static __always_inline bool free_pages_prepare(struct page *page,
ClearPageHasHWPoisoned(page);
}
for (i = 1; i < (1 << order); i++) {
+ /*
+ * Freeing a previously PTE-mapped THP can have
+ * PG_anon_exclusive set on tail pages. Clear it
+ * manually as it's overloaded with PG_slab that we
+ * want to catch in check_free_page().
+ */
+ if (anon)
+ __ClearPageAnonExclusive(page + i);
if (compound)
bad += free_tail_pages_check(page, page + i);
if (unlikely(check_free_page(page + i))) {
@@ -1338,6 +1347,10 @@ static __always_inline bool free_pages_prepare(struct page *page,
(page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
}
}
+ if (anon) {
+ __ClearPageAnonExclusive(page);
+ wmb(); /* avoid PageSlab() false positives */
+ }
if (PageMappingFlags(page))
page->mapping = NULL;
if (memcg_kmem_enabled() && PageMemcgKmem(page))
The basic question we would like to have a reliable and efficient answer to is: is this anonymous page exclusive to a single process or might it be shared? In an ideal world, we'd have a spare pageflag. Unfortunately, pageflags don't grow on trees, so we have to get a little creative for the time being. Introduce a way to mark an anonymous page as exclusive, with the ultimate goal of teaching our COW logic to not do "wrong COWs", whereby GUP pins lose consistency with the pages mapped into the page table, resulting in reported memory corruptions. Most pageflags already have semantics for anonymous pages, so we're left with reusing PG_slab for our purpose: for PageAnon() pages PG_slab now translates to PG_anon_exclusive, teach some in-kernel code that manually handles PG_slab about that. Add a spoiler on the semantics of PG_anon_exclusive as documentation. More documentation will be contained in the code that actually makes use of PG_anon_exclusive. We won't be clearing PG_anon_exclusive on destructive unmapping (i.e., zapping) of page table entries, page freeing code will handle that when also invalidate page->mapping to not indicate PageAnon() anymore. Letting information about exclusivity stick around will be an important property when adding sanity checks to unpinning code. RFC notes: in-tree tools/cgroup/memcg_slabinfo.py looks like it might need some care. We'd have to lookup the head page and check if PageAnon() is set. Similarly, tools living outside the kernel repository like crash and makedumpfile might need adaptions. Cc: Roman Gushchin <guro@fb.com> Signed-off-by: David Hildenbrand <david@redhat.com> --- fs/proc/page.c | 3 +- include/linux/page-flags.h | 124 ++++++++++++++++++++++++++++++++- include/trace/events/mmflags.h | 2 +- mm/hugetlb.c | 4 ++ mm/memory-failure.c | 24 +++++-- mm/memremap.c | 11 +++ mm/page_alloc.c | 13 ++++ 7 files changed, 170 insertions(+), 11 deletions(-)