@@ -1003,6 +1003,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
#define arch_start_context_switch(prev) do {} while (0)
#endif
+/*
+ * When replacing an anonymous page by a real (!non) swap entry, we clear
+ * PG_anon_exclusive from the page and instead remember whether the flag was
+ * set in the swp pte. During fork(), we have to mark the entry as !exclusive
+ * (possibly shared). On swapin, we use that information to restore
+ * PG_anon_exclusive, which is very helpful in cases where we might have
+ * additional (e.g., FOLL_GET) references on a page and wouldn't be able to
+ * detect exclusivity.
+ *
+ * These functions don't apply to non-swap entries (e.g., migration, hwpoison,
+ * ...).
+ */
+#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+ return pte;
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+ return false;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+ return pte;
+}
+#endif
+
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
@@ -26,6 +26,8 @@
/* Clear all flags but only keep swp_entry_t related information */
static inline pte_t pte_swp_clear_flags(pte_t pte)
{
+ if (pte_swp_exclusive(pte))
+ pte = pte_swp_clear_exclusive(pte);
if (pte_swp_soft_dirty(pte))
pte = pte_swp_clear_soft_dirty(pte);
if (pte_swp_uffd_wp(pte))
@@ -795,6 +795,11 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
&src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
+ /* Mark the swap entry as shared. */
+ if (pte_swp_exclusive(*src_pte)) {
+ pte = pte_swp_clear_exclusive(*src_pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
+ }
rss[MM_SWAPENTS]++;
} else if (is_migration_entry(entry)) {
page = pfn_swap_entry_to_page(entry);
@@ -3567,6 +3572,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
struct page *page = NULL, *swapcache;
struct swap_info_struct *si = NULL;
rmap_t rmap_flags = RMAP_NONE;
+ bool exclusive = false;
swp_entry_t entry;
pte_t pte;
int locked;
@@ -3732,6 +3738,46 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
BUG_ON(PageAnon(page) && PageAnonExclusive(page));
+ /*
+ * Check under PT lock (to protect against concurrent fork() sharing
+ * the swap entry concurrently) for certainly exclusive pages.
+ */
+ if (!PageKsm(page)) {
+ /*
+ * Note that pte_swp_exclusive() == false for architectures
+ * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE.
+ */
+ exclusive = pte_swp_exclusive(vmf->orig_pte);
+ if (page != swapcache) {
+ /*
+ * We have a fresh page that is not exposed to the
+ * swapcache -> certainly exclusive.
+ */
+ exclusive = true;
+ } else if (exclusive && PageWriteback(page) &&
+ !(swp_swap_info(entry)->flags & SWP_STABLE_WRITES)) {
+ /*
+ * This is tricky: not all swap backends support
+ * concurrent page modifications while under writeback.
+ *
+ * So if we stumble over such a page in the swapcache
+ * we must not set the page exclusive, otherwise we can
+ * map it writable without further checks and modify it
+ * while still under writeback.
+ *
+ * For these problematic swap backends, simply drop the
+ * exclusive marker: this is perfectly fine as we start
+ * writeback only if we fully unmapped the page and
+ * there are no unexpected references on the page after
+ * unmapping succeeded. After fully unmapped, no
+ * further GUP references (FOLL_GET and FOLL_PIN) can
+ * appear, so dropping the exclusive marker and mapping
+ * it only R/O is fine.
+ */
+ exclusive = false;
+ }
+ }
+
/*
* Remove the swap entry and conditionally try to free up the swapcache.
* We're already holding a reference on the page but haven't mapped it
@@ -3746,11 +3792,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
pte = mk_pte(page, vma->vm_page_prot);
/*
- * Same logic as in do_wp_page(); however, optimize for fresh pages
- * that are certainly not shared because we just allocated them without
- * exposing them to the swapcache.
+ * Same logic as in do_wp_page(); however, optimize for pages that are
+ * certainly not shared either because we just allocated them without
+ * exposing them to the swapcache or because the swap entry indicates
+ * exclusivity.
*/
- if (!PageKsm(page) && (page != swapcache || page_count(page) == 1)) {
+ if (!PageKsm(page) && (exclusive || page_count(page) == 1)) {
if (vmf->flags & FAULT_FLAG_WRITE) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
vmf->flags &= ~FAULT_FLAG_WRITE;
@@ -1643,14 +1643,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
break;
}
/*
- * Note: We *don't* remember yet if the page was mapped
- * exclusively in the swap entry, so swapin code has
- * to re-determine that manually and might detect the
- * page as possibly shared, for example, if there are
- * other references on the page or if the page is under
- * writeback. We made sure that there are no GUP pins
- * on the page that would rely on it, so for GUP pins
- * this is fine.
+ * Note: We *don't* remember if the page was mapped
+ * exclusively in the swap pte if the architecture
+ * doesn't support __HAVE_ARCH_PTE_SWP_EXCLUSIVE. In
+ * that case, swapin code has to re-determine that
+ * manually and might detect the page as possibly
+ * shared, for example, if there are other references on
+ * the page or if the page is under writeback. We made
+ * sure that there are no GUP pins on the page that
+ * would rely on it, so for GUP pins this is fine.
*/
if (list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
@@ -1661,6 +1662,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
dec_mm_counter(mm, MM_ANONPAGES);
inc_mm_counter(mm, MM_SWAPENTS);
swp_pte = swp_entry_to_pte(entry);
+ if (anon_exclusive)
+ swp_pte = pte_swp_mkexclusive(swp_pte);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
if (pte_uffd_wp(pteval))
@@ -1804,7 +1804,18 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
get_page(page);
if (page == swapcache) {
- page_add_anon_rmap(page, vma, addr, RMAP_NONE);
+ rmap_t rmap_flags = RMAP_NONE;
+
+ /*
+ * See do_swap_page(): PageWriteback() would be problematic.
+ * However, we do a wait_on_page_writeback() just before this
+ * call and have the page locked.
+ */
+ VM_BUG_ON_PAGE(PageWriteback(page), page);
+ if (pte_swp_exclusive(*pte))
+ rmap_flags |= RMAP_EXCLUSIVE;
+
+ page_add_anon_rmap(page, vma, addr, rmap_flags);
} else { /* ksm created a completely new copy */
page_add_new_anon_rmap(page, vma, addr);
lru_cache_add_inactive_or_unevictable(page, vma);
Currently, we clear PG_anon_exclusive in try_to_unmap() and forget about it. We do this, to keep fork() logic on swap entries easy and efficient: for example, if we wouldn't clear it when unmapping, we'd have to lookup the page in the swapcache for each and every swap entry during fork() and clear PG_anon_exclusive if set. Instead, we want to store that information directly in the swap pte, protected by the page table lock, similarly to how we handle SWP_MIGRATION_READ_EXCLUSIVE for migration entries. However, for actual swap entries, we don't want to mess with the swap type (e.g., still one bit) because it overcomplicates swap code. In try_to_unmap(), we already reject to unmap in case the page might be pinned, because we must not lose PG_anon_exclusive on pinned pages ever. Checking if there are other unexpected references reliably *before* completely unmapping a page is unfortunately not really possible: THP heavily overcomplicate the situation. Once fully unmapped it's easier -- we, for example, make sure that there are no unexpected references *after* unmapping a page before starting writeback on that page. So, we currently might end up unmapping a page and clearing PG_anon_exclusive if that page has additional references, for example, due to a FOLL_GET. do_swap_page() has to re-determine if a page is exclusive, which will easily fail if there are other references on a page, most prominently GUP references via FOLL_GET. This can currently result in memory corruptions when taking a FOLL_GET | FOLL_WRITE reference on a page even when fork() is never involved: try_to_unmap() will succeed, and when refaulting the page, it cannot be marked exclusive and will get replaced by a copy in the page tables on the next write access, resulting in writes via the GUP reference to the page being lost. In an ideal world, everybody that uses GUP and wants to modify page content, such as O_DIRECT, would properly use FOLL_PIN. However, that conversion will take a while. It's easier to fix what used to work in the past (FOLL_GET | FOLL_WRITE) remembering PG_anon_exclusive. In addition, by remembering PG_anon_exclusive we can further reduce unnecessary COW in some cases, so it's the natural thing to do. So let's transfer the PG_anon_exclusive information to the swap pte and store it via an architecture-dependant pte bit; use that information when restoring the swap pte in do_swap_page() and unuse_pte(). During fork(), we simply have to clear the pte bit and are done. Of course, there is one corner case to handle: swap backends that don't support concurrent page modifications while the page is under writeback. Special case these, and drop the exclusive marker. Add a comment why that is just fine (also, reuse_swap_page() would have done the same in the past). In the future, we'll hopefully have all architectures support __HAVE_ARCH_PTE_SWP_EXCLUSIVE, such that we can get rid of the empty stubs and the define completely. Then, we can also convert SWP_MIGRATION_READ_EXCLUSIVE. For architectures it's fairly easy to support: either simply use a yet unused pte bit that can be used for swap entries, steal one from the arch type bits if they exceed 5, or steal one from the offset bits. Note: R/O FOLL_GET references were never really reliable, especially when taking one on a shared page and then writing to the page (e.g., GUP after fork()). FOLL_GET, including R/W references, were never really reliable once fork was involved (e.g., GUP before fork(), GUP during fork()). KSM steps back in case it stumbles over unexpected references and is, therefore, fine. Signed-off-by: David Hildenbrand <david@redhat.com> --- include/linux/pgtable.h | 29 ++++++++++++++++++++++ include/linux/swapops.h | 2 ++ mm/memory.c | 55 ++++++++++++++++++++++++++++++++++++++--- mm/rmap.c | 19 ++++++++------ mm/swapfile.c | 13 +++++++++- 5 files changed, 105 insertions(+), 13 deletions(-)