Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

1 files changed, 119 insertions, 8 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 501bc150792c..551264407624 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,6 +29,39 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+static inline void sanity_check_pinned_pages(struct page **pages,
+					     unsigned long npages)
+{
+	if (!IS_ENABLED(CONFIG_DEBUG_VM))
+		return;
+
+	/*
+	 * We only pin anonymous pages if they are exclusive. Once pinned, we
+	 * can no longer turn them possibly shared and PageAnonExclusive() will
+	 * stick around until the page is freed.
+	 *
+	 * We'd like to verify that our pinned anonymous pages are still mapped
+	 * exclusively. The issue with anon THP is that we don't know how
+	 * they are/were mapped when pinning them. However, for anon
+	 * THP we can assume that either the given page (PTE-mapped THP) or
+	 * the head page (PMD-mapped THP) should be PageAnonExclusive(). If
+	 * neither is the case, there is certainly something wrong.
+	 */
+	for (; npages; npages--, pages++) {
+		struct page *page = *pages;
+		struct folio *folio = page_folio(page);
+
+		if (!folio_test_anon(folio))
+			continue;
+		if (!folio_test_large(folio) || folio_test_hugetlb(folio))
+			VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page);
+		else
+			/* Either a PTE-mapped or a PMD-mapped THP. */
+			VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) &&
+				       !PageAnonExclusive(page), page);
+	}
+}
+
 /*
  * Return the folio with ref appropriately incremented,
  * or NULL if that failed.
@@ -204,6 +237,7 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags)
  */
 void unpin_user_page(struct page *page)
 {
+	sanity_check_pinned_pages(&page, 1);
 	gup_put_folio(page_folio(page), 1, FOLL_PIN);
 }
 EXPORT_SYMBOL(unpin_user_page);
@@ -272,6 +306,7 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		return;
 	}
 
+	sanity_check_pinned_pages(pages, npages);
 	for (i = 0; i < npages; i += nr) {
 		folio = gup_folio_next(pages, npages, i, &nr);
 		/*
@@ -344,6 +379,23 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
 }
 EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
 
+static void unpin_user_pages_lockless(struct page **pages, unsigned long npages)
+{
+	unsigned long i;
+	struct folio *folio;
+	unsigned int nr;
+
+	/*
+	 * Don't perform any sanity checks because we might have raced with
+	 * fork() and some anonymous pages might now actually be shared --
+	 * which is why we're unpinning after all.
+	 */
+	for (i = 0; i < npages; i += nr) {
+		folio = gup_folio_next(pages, npages, i, &nr);
+		gup_put_folio(folio, nr, FOLL_PIN);
+	}
+}
+
 /**
  * unpin_user_pages() - release an array of gup-pinned pages.
  * @pages:  array of pages to be marked dirty and released.
@@ -367,6 +419,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
 	if (WARN_ON(IS_ERR_VALUE(npages)))
 		return;
 
+	sanity_check_pinned_pages(pages, npages);
 	for (i = 0; i < npages; i += nr) {
 		folio = gup_folio_next(pages, npages, i, &nr);
 		gup_put_folio(folio, nr, FOLL_PIN);
@@ -506,6 +559,14 @@ retry:
 		}
 	}
 
+	if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+		page = ERR_PTR(-EMLINK);
+		goto out;
+	}
+
+	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
+		       !PageAnonExclusive(page), page);
+
 	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
 	if (unlikely(!try_grab_page(page, flags))) {
 		page = ERR_PTR(-ENOMEM);
@@ -732,6 +793,11 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
  * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
  * the device's dev_pagemap metadata to avoid repeating expensive lookups.
  *
+ * When getting an anonymous page and the caller has to trigger unsharing
+ * of a shared anonymous page first, -EMLINK is returned. The caller should
+ * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
+ * relevant with FOLL_PIN and !FOLL_WRITE.
+ *
  * On output, the @ctx->page_mask is set according to the size of the page.
  *
  * Return: the mapped (struct page *), %NULL if no mapping exists, or
@@ -787,6 +853,9 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	if (vma_is_secretmem(vma))
 		return NULL;
 
+	if (foll_flags & FOLL_PIN)
+		return NULL;
+
 	page = follow_page_mask(vma, address, foll_flags, &ctx);
 	if (ctx.pgmap)
 		put_dev_pagemap(ctx.pgmap);
@@ -852,7 +921,8 @@ unmap:
  * is, *@locked will be set to 0 and -EBUSY returned.
  */
 static int faultin_page(struct vm_area_struct *vma,
-		unsigned long address, unsigned int *flags, int *locked)
+		unsigned long address, unsigned int *flags, bool unshare,
+		int *locked)
 {
 	unsigned int fault_flags = 0;
 	vm_fault_t ret;
@@ -874,6 +944,11 @@ static int faultin_page(struct vm_area_struct *vma,
 		 */
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
+	if (unshare) {
+		fault_flags |= FAULT_FLAG_UNSHARE;
+		/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
+		VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
+	}
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	if (ret & VM_FAULT_ERROR) {
@@ -1095,8 +1170,9 @@ retry:
 		cond_resched();
 
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
-		if (!page) {
-			ret = faultin_page(vma, start, &foll_flags, locked);
+		if (!page || PTR_ERR(page) == -EMLINK) {
+			ret = faultin_page(vma, start, &foll_flags,
+					   PTR_ERR(page) == -EMLINK, locked);
 			switch (ret) {
 			case 0:
 				goto retry;
@@ -2227,6 +2303,11 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			goto pte_unmap;
 		}
 
+		if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+			gup_put_folio(folio, 1, flags);
+			goto pte_unmap;
+		}
+
 		/*
 		 * We need to make the page accessible if and only if we are
 		 * going to access its content (the FOLL_PIN case).  Please
@@ -2407,6 +2488,11 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		return 0;
 	}
 
+	if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2468,6 +2554,11 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
+	if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2503,6 +2594,11 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
+	if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2740,8 +2836,10 @@ static unsigned long lockless_pages_from_mm(unsigned long start,
 	 */
 	if (gup_flags & FOLL_PIN) {
 		if (read_seqcount_retry(&current->mm->write_protect_seq, seq)) {
-			unpin_user_pages(pages, nr_pinned);
+			unpin_user_pages_lockless(pages, nr_pinned);
 			return 0;
+		} else {
+			sanity_check_pinned_pages(pages, nr_pinned);
 		}
 	}
 	return nr_pinned;
@@ -2900,6 +2998,9 @@ int pin_user_pages_fast(unsigned long start, int nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(!pages))
+		return -EINVAL;
+
 	gup_flags |= FOLL_PIN;
 	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
 }
@@ -2922,6 +3023,9 @@ int pin_user_pages_fast_only(unsigned long start, int nr_pages,
 	 */
 	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
 		return 0;
+
+	if (WARN_ON_ONCE(!pages))
+		return 0;
 	/*
 	 * FOLL_FAST_ONLY is required in order to match the API description of
 	 * this routine: no fall back to regular ("slow") GUP.
@@ -2949,8 +3053,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
  * @nr_pages:	number of pages from start to pin
  * @gup_flags:	flags modifying lookup behaviour
  * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long. Or NULL, if caller
- *		only intends to ensure the pages are faulted in.
+ *		Should be at least nr_pages long.
  * @vmas:	array of pointers to vmas corresponding to each page.
  *		Or NULL if the caller does not require them.
  * @locked:	pointer to lock flag indicating whether lock is held and
@@ -2973,6 +3076,9 @@ long pin_user_pages_remote(struct mm_struct *mm,
 	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(!pages))
+		return -EINVAL;
+
 	gup_flags |= FOLL_PIN;
 	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
 				       pages, vmas, locked);
@@ -2986,8 +3092,7 @@ EXPORT_SYMBOL(pin_user_pages_remote);
  * @nr_pages:	number of pages from start to pin
  * @gup_flags:	flags modifying lookup behaviour
  * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long. Or NULL, if caller
- *		only intends to ensure the pages are faulted in.
+ *		Should be at least nr_pages long.
  * @vmas:	array of pointers to vmas corresponding to each page.
  *		Or NULL if the caller does not require them.
  *
@@ -3005,6 +3110,9 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(!pages))
+		return -EINVAL;
+
 	gup_flags |= FOLL_PIN;
 	return __gup_longterm_locked(current->mm, start, nr_pages,
 				     pages, vmas, gup_flags);
@@ -3023,6 +3131,9 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(!pages))
+		return -EINVAL;
+
 	gup_flags |= FOLL_PIN;
 	return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
 }