Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

1 files changed, 55 insertions, 36 deletions

diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 8833359556f3..1e616a8c6a9c 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -238,6 +238,8 @@ static int cg_test_proc_killed(const char *cgroup)
 	return -1;
 }
 
+static bool reclaim_until(const char *memcg, long goal);
+
 /*
  * First, this test creates the following hierarchy:
  * A       memory.min = 0,    memory.max = 200M
@@ -266,6 +268,12 @@ static int cg_test_proc_killed(const char *cgroup)
  * unprotected memory in A available, and checks that:
  * a) memory.min protects pagecache even in this case,
  * b) memory.low allows reclaiming page cache with low events.
+ *
+ * Then we try to reclaim from A/B/C using memory.reclaim until its
+ * usage reaches 10M.
+ * This makes sure that:
+ * (a) We ignore the protection of the reclaim target memcg.
+ * (b) The previously calculated emin value (~29M) should be dismissed.
  */
 static int test_memcg_protection(const char *root, bool min)
 {
@@ -385,6 +393,9 @@ static int test_memcg_protection(const char *root, bool min)
 	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
 		goto cleanup;
 
+	if (!reclaim_until(children[0], MB(10)))
+		goto cleanup;
+
 	if (min) {
 		ret = KSFT_PASS;
 		goto cleanup;
@@ -646,6 +657,48 @@ cleanup:
 }
 
 /*
+ * Reclaim from @memcg until usage reaches @goal by writing to
+ * memory.reclaim.
+ *
+ * This function will return false if the usage is already below the
+ * goal.
+ *
+ * This function assumes that writing to memory.reclaim is the only
+ * source of change in memory.current (no concurrent allocations or
+ * reclaim).
+ *
+ * This function makes sure memory.reclaim is sane. It will return
+ * false if memory.reclaim's error codes do not make sense, even if
+ * the usage goal was satisfied.
+ */
+static bool reclaim_until(const char *memcg, long goal)
+{
+	char buf[64];
+	int retries, err;
+	long current, to_reclaim;
+	bool reclaimed = false;
+
+	for (retries = 5; retries > 0; retries--) {
+		current = cg_read_long(memcg, "memory.current");
+
+		if (current < goal || values_close(current, goal, 3))
+			break;
+		/* Did memory.reclaim return 0 incorrectly? */
+		else if (reclaimed)
+			return false;
+
+		to_reclaim = current - goal;
+		snprintf(buf, sizeof(buf), "%ld", to_reclaim);
+		err = cg_write(memcg, "memory.reclaim", buf);
+		if (!err)
+			reclaimed = true;
+		else if (err != -EAGAIN)
+			return false;
+	}
+	return reclaimed;
+}
+
+/*
  * This test checks that memory.reclaim reclaims the given
  * amount of memory (from both anon and file, if possible).
  */
@@ -653,8 +706,7 @@ static int test_memcg_reclaim(const char *root)
 {
 	int ret = KSFT_FAIL, fd, retries;
 	char *memcg;
-	long current, expected_usage, to_reclaim;
-	char buf[64];
+	long current, expected_usage;
 
 	memcg = cg_name(root, "memcg_test");
 	if (!memcg)
@@ -705,41 +757,8 @@ static int test_memcg_reclaim(const char *root)
 	 * Reclaim until current reaches 30M, this makes sure we hit both anon
 	 * and file if swap is enabled.
 	 */
-	retries = 5;
-	while (true) {
-		int err;
-
-		current = cg_read_long(memcg, "memory.current");
-		to_reclaim = current - MB(30);
-
-		/*
-		 * We only keep looping if we get EAGAIN, which means we could
-		 * not reclaim the full amount.
-		 */
-		if (to_reclaim <= 0)
-			goto cleanup;
-
-
-		snprintf(buf, sizeof(buf), "%ld", to_reclaim);
-		err = cg_write(memcg, "memory.reclaim", buf);
-		if (!err) {
-			/*
-			 * If writing succeeds, then the written amount should have been
-			 * fully reclaimed (and maybe more).
-			 */
-			current = cg_read_long(memcg, "memory.current");
-			if (!values_close(current, MB(30), 3) && current > MB(30))
-				goto cleanup;
-			break;
-		}
-
-		/* The kernel could not reclaim the full amount, try again. */
-		if (err == -EAGAIN && retries--)
-			continue;
-
-		/* We got an unexpected error or ran out of retries. */
+	if (!reclaim_until(memcg, MB(30)))
 		goto cleanup;
-	}
 
 	ret = KSFT_PASS;
 cleanup: