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, 63 insertions, 63 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index d4a4adcca01f..b85661cbdc4a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -59,6 +59,7 @@
 #include <linux/page-isolation.h>
 #include <linux/pagewalk.h>
 #include <linux/shmem_fs.h>
+#include "swap.h"
 #include "internal.h"
 #include "ras/ras_event.h"
 
@@ -484,7 +485,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct anon_vma *av;
 	pgoff_t pgoff;
 
-	av = folio_lock_anon_vma_read(folio);
+	av = folio_lock_anon_vma_read(folio, NULL);
 	if (av == NULL)	/* Not actually mapped anymore */
 		return;
 
@@ -622,7 +623,7 @@ static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr,
 static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
 			      unsigned long end, struct mm_walk *walk)
 {
-	struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
+	struct hwp_walk *hwp = walk->private;
 	int ret = 0;
 	pte_t *ptep, *mapped_pte;
 	spinlock_t *ptl;
@@ -656,7 +657,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
 			    unsigned long addr, unsigned long end,
 			    struct mm_walk *walk)
 {
-	struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
+	struct hwp_walk *hwp = walk->private;
 	pte_t pte = huge_ptep_get(ptep);
 	struct hstate *h = hstate_vma(walk->vma);
 
@@ -733,7 +734,6 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_DAX]			= "dax page",
 	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
-	[MF_MSG_DIFFERENT_PAGE_SIZE]	= "different page size",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1041,12 +1041,11 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 		res = MF_FAILED;
 		unlock_page(hpage);
 		/*
-		 * migration entry prevents later access on error anonymous
-		 * hugepage, so we can free and dissolve it into buddy to
-		 * save healthy subpages.
+		 * migration entry prevents later access on error hugepage,
+		 * so we can free and dissolve it into buddy to save healthy
+		 * subpages.
 		 */
-		if (PageAnon(hpage))
-			put_page(hpage);
+		put_page(hpage);
 		if (__page_handle_poison(p)) {
 			page_ref_inc(p);
 			res = MF_RECOVERED;
@@ -1133,6 +1132,7 @@ static void action_result(unsigned long pfn, enum mf_action_page_type type,
 {
 	trace_memory_failure_event(pfn, type, result);
 
+	num_poisoned_pages_inc();
 	pr_err("Memory failure: %#lx: recovery action for %s: %s\n",
 		pfn, action_page_types[type], action_name[result]);
 }
@@ -1179,13 +1179,11 @@ void ClearPageHWPoisonTakenOff(struct page *page)
  */
 static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 {
-	bool movable = false;
-
-	/* Soft offline could mirgate non-LRU movable pages */
+	/* Soft offline could migrate non-LRU movable pages */
 	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
-		movable = true;
+		return true;
 
-	return movable || PageLRU(page) || is_free_buddy_page(page);
+	return PageLRU(page) || is_free_buddy_page(page);
 }
 
 static int __get_hwpoison_page(struct page *page, unsigned long flags)
@@ -1521,7 +1519,9 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
 	if (flags & MF_COUNT_INCREASED) {
 		ret = 1;
 		count_increased = true;
-	} else if (HPageFreed(head) || HPageMigratable(head)) {
+	} else if (HPageFreed(head)) {
+		ret = 0;
+	} else if (HPageMigratable(head)) {
 		ret = get_page_unless_zero(head);
 		if (ret)
 			count_increased = true;
@@ -1588,8 +1588,6 @@ retry:
 		goto out;
 	}
 
-	num_poisoned_pages_inc();
-
 	/*
 	 * Handling free hugepage.  The possible race with hugepage allocation
 	 * or demotion can be prevented by PageHWPoison flag.
@@ -1605,16 +1603,6 @@ retry:
 		return res == MF_RECOVERED ? 0 : -EBUSY;
 	}
 
-	/*
-	 * The page could have changed compound pages due to race window.
-	 * If this happens just bail out.
-	 */
-	if (!PageHuge(p) || compound_head(p) != head) {
-		action_result(pfn, MF_MSG_DIFFERENT_PAGE_SIZE, MF_IGNORED);
-		res = -EBUSY;
-		goto out;
-	}
-
 	page_flags = head->flags;
 
 	/*
@@ -1762,7 +1750,7 @@ static DEFINE_MUTEX(mf_mutex);
  * enabled and no spinlocks hold.
  *
  * Return: 0 for successfully handled the memory error,
- *         -EOPNOTSUPP for memory_filter() filtered the error event,
+ *         -EOPNOTSUPP for hwpoison_filter() filtered the error event,
  *         < 0(except -EOPNOTSUPP) on failure.
  */
 int memory_failure(unsigned long pfn, int flags)
@@ -1811,11 +1799,12 @@ try_again:
 		res = -EHWPOISON;
 		if (flags & MF_ACTION_REQUIRED)
 			res = kill_accessing_process(current, pfn, flags);
+		if (flags & MF_COUNT_INCREASED)
+			put_page(p);
 		goto unlock_mutex;
 	}
 
 	hpage = compound_head(p);
-	num_poisoned_pages_inc();
 
 	/*
 	 * We need/can do nothing about count=0 pages.
@@ -1839,7 +1828,6 @@ try_again:
 					/* We lost the race, try again */
 					if (retry) {
 						ClearPageHWPoison(p);
-						num_poisoned_pages_dec();
 						retry = false;
 						goto try_again;
 					}
@@ -1902,8 +1890,7 @@ try_again:
 	 */
 	if (PageCompound(p)) {
 		if (retry) {
-			if (TestClearPageHWPoison(p))
-				num_poisoned_pages_dec();
+			ClearPageHWPoison(p);
 			unlock_page(p);
 			put_page(p);
 			flags &= ~MF_COUNT_INCREASED;
@@ -1925,8 +1912,7 @@ try_again:
 	page_flags = p->flags;
 
 	if (hwpoison_filter(p)) {
-		if (TestClearPageHWPoison(p))
-			num_poisoned_pages_dec();
+		TestClearPageHWPoison(p);
 		unlock_page(p);
 		put_page(p);
 		res = -EOPNOTSUPP;
@@ -2088,28 +2074,6 @@ core_initcall(memory_failure_init);
 		pr_info(fmt, pfn);			\
 })
 
-static inline int clear_page_hwpoison(struct ratelimit_state *rs, struct page *p)
-{
-	if (TestClearPageHWPoison(p)) {
-		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
-				 page_to_pfn(p), rs);
-		num_poisoned_pages_dec();
-		return 1;
-	}
-	return 0;
-}
-
-static inline int unpoison_taken_off_page(struct ratelimit_state *rs,
-					  struct page *p)
-{
-	if (put_page_back_buddy(p)) {
-		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
-				 page_to_pfn(p), rs);
-		return 0;
-	}
-	return -EBUSY;
-}
-
 /**
  * unpoison_memory - Unpoison a previously poisoned page
  * @pfn: Page number of the to be unpoisoned page
@@ -2127,6 +2091,7 @@ int unpoison_memory(unsigned long pfn)
 	struct page *page;
 	struct page *p;
 	int ret = -EBUSY;
+	int freeit = 0;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
 
@@ -2167,18 +2132,15 @@ int unpoison_memory(unsigned long pfn)
 
 	ret = get_hwpoison_page(p, MF_UNPOISON);
 	if (!ret) {
-		if (clear_page_hwpoison(&unpoison_rs, page))
-			ret = 0;
-		else
-			ret = -EBUSY;
+		ret = TestClearPageHWPoison(page) ? 0 : -EBUSY;
 	} else if (ret < 0) {
 		if (ret == -EHWPOISON) {
-			ret = unpoison_taken_off_page(&unpoison_rs, p);
+			ret = put_page_back_buddy(p) ? 0 : -EBUSY;
 		} else
 			unpoison_pr_info("Unpoison: failed to grab page %#lx\n",
 					 pfn, &unpoison_rs);
 	} else {
-		int freeit = clear_page_hwpoison(&unpoison_rs, p);
+		freeit = !!TestClearPageHWPoison(p);
 
 		put_page(page);
 		if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) {
@@ -2189,6 +2151,11 @@ int unpoison_memory(unsigned long pfn)
 
 unlock_mutex:
 	mutex_unlock(&mf_mutex);
+	if (!ret || freeit) {
+		num_poisoned_pages_dec();
+		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
+				 page_to_pfn(p), &unpoison_rs);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(unpoison_memory);
@@ -2323,7 +2290,9 @@ static void put_ref_page(struct page *page)
  * @pfn: pfn to soft-offline
  * @flags: flags. Same as memory_failure().
  *
- * Returns 0 on success, otherwise negated errno.
+ * Returns 0 on success
+ *         -EOPNOTSUPP for hwpoison_filter() filtered the error event
+ *         < 0 otherwise negated errno.
  *
  * Soft offline a page, by migration or invalidation,
  * without killing anything. This is for the case when
@@ -2374,6 +2343,16 @@ retry:
 	ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE);
 	put_online_mems();
 
+	if (hwpoison_filter(page)) {
+		if (ret > 0)
+			put_page(page);
+		else
+			put_ref_page(ref_page);
+
+		mutex_unlock(&mf_mutex);
+		return -EOPNOTSUPP;
+	}
+
 	if (ret > 0) {
 		ret = soft_offline_in_use_page(page);
 	} else if (ret == 0) {
@@ -2388,3 +2367,24 @@ retry:
 
 	return ret;
 }
+
+void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+	int i;
+
+	/*
+	 * A further optimization is to have per section refcounted
+	 * num_poisoned_pages.  But that would need more space per memmap, so
+	 * for now just do a quick global check to speed up this routine in the
+	 * absence of bad pages.
+	 */
+	if (atomic_long_read(&num_poisoned_pages) == 0)
+		return;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (PageHWPoison(&memmap[i])) {
+			num_poisoned_pages_dec();
+			ClearPageHWPoison(&memmap[i]);
+		}
+	}
+}