Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

1 files changed, 73 insertions, 35 deletions

diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 98b949c279be..7d722265dcd7 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -26,10 +26,6 @@
 #include <sys/mman.h>
 #include <sys/ioctl.h>
 
-#include "./local_config.h"
-#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
-#include <hugetlbfs.h>
-#endif
 
 /*
  * This is a private UAPI to the kernel test module so it isn't exported
@@ -733,7 +729,54 @@ TEST_F(hmm, anon_write_huge)
 	hmm_buffer_free(buffer);
 }
 
-#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
+/*
+ * Read numeric data from raw and tagged kernel status files.  Used to read
+ * /proc and /sys data (without a tag) and from /proc/meminfo (with a tag).
+ */
+static long file_read_ulong(char *file, const char *tag)
+{
+	int fd;
+	char buf[2048];
+	int len;
+	char *p, *q;
+	long val;
+
+	fd = open(file, O_RDONLY);
+	if (fd < 0) {
+		/* Error opening the file */
+		return -1;
+	}
+
+	len = read(fd, buf, sizeof(buf));
+	close(fd);
+	if (len < 0) {
+		/* Error in reading the file */
+		return -1;
+	}
+	if (len == sizeof(buf)) {
+		/* Error file is too large */
+		return -1;
+	}
+	buf[len] = '\0';
+
+	/* Search for a tag if provided */
+	if (tag) {
+		p = strstr(buf, tag);
+		if (!p)
+			return -1; /* looks like the line we want isn't there */
+		p += strlen(tag);
+	} else
+		p = buf;
+
+	val = strtol(p, &q, 0);
+	if (*q != ' ') {
+		/* Error parsing the file */
+		return -1;
+	}
+
+	return val;
+}
+
 /*
  * Write huge TLBFS page.
  */
@@ -742,29 +785,27 @@ TEST_F(hmm, anon_write_hugetlbfs)
 	struct hmm_buffer *buffer;
 	unsigned long npages;
 	unsigned long size;
+	unsigned long default_hsize;
 	unsigned long i;
 	int *ptr;
 	int ret;
-	long pagesizes[4];
-	int n, idx;
-
-	/* Skip test if we can't allocate a hugetlbfs page. */
 
-	n = gethugepagesizes(pagesizes, 4);
-	if (n <= 0)
+	default_hsize = file_read_ulong("/proc/meminfo", "Hugepagesize:");
+	if (default_hsize < 0 || default_hsize*1024 < default_hsize)
 		SKIP(return, "Huge page size could not be determined");
-	for (idx = 0; --n > 0; ) {
-		if (pagesizes[n] < pagesizes[idx])
-			idx = n;
-	}
-	size = ALIGN(TWOMEG, pagesizes[idx]);
+	default_hsize = default_hsize*1024; /* KB to B */
+
+	size = ALIGN(TWOMEG, default_hsize);
 	npages = size >> self->page_shift;
 
 	buffer = malloc(sizeof(*buffer));
 	ASSERT_NE(buffer, NULL);
 
-	buffer->ptr = get_hugepage_region(size, GHR_STRICT);
-	if (buffer->ptr == NULL) {
+	buffer->ptr = mmap(NULL, size,
+				   PROT_READ | PROT_WRITE,
+				   MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+				   -1, 0);
+	if (buffer->ptr == MAP_FAILED) {
 		free(buffer);
 		SKIP(return, "Huge page could not be allocated");
 	}
@@ -788,11 +829,10 @@ TEST_F(hmm, anon_write_hugetlbfs)
 	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
 		ASSERT_EQ(ptr[i], i);
 
-	free_hugepage_region(buffer->ptr);
+	munmap(buffer->ptr, buffer->size);
 	buffer->ptr = NULL;
 	hmm_buffer_free(buffer);
 }
-#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */
 
 /*
  * Read mmap'ed file memory.
@@ -1467,7 +1507,6 @@ TEST_F(hmm2, snapshot)
 	hmm_buffer_free(buffer);
 }
 
-#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
 /*
  * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that
  * should be mapped by a large page table entry.
@@ -1477,30 +1516,30 @@ TEST_F(hmm, compound)
 	struct hmm_buffer *buffer;
 	unsigned long npages;
 	unsigned long size;
+	unsigned long default_hsize;
 	int *ptr;
 	unsigned char *m;
 	int ret;
-	long pagesizes[4];
-	int n, idx;
 	unsigned long i;
 
 	/* Skip test if we can't allocate a hugetlbfs page. */
 
-	n = gethugepagesizes(pagesizes, 4);
-	if (n <= 0)
-		return;
-	for (idx = 0; --n > 0; ) {
-		if (pagesizes[n] < pagesizes[idx])
-			idx = n;
-	}
-	size = ALIGN(TWOMEG, pagesizes[idx]);
+	default_hsize = file_read_ulong("/proc/meminfo", "Hugepagesize:");
+	if (default_hsize < 0 || default_hsize*1024 < default_hsize)
+		SKIP(return, "Huge page size could not be determined");
+	default_hsize = default_hsize*1024; /* KB to B */
+
+	size = ALIGN(TWOMEG, default_hsize);
 	npages = size >> self->page_shift;
 
 	buffer = malloc(sizeof(*buffer));
 	ASSERT_NE(buffer, NULL);
 
-	buffer->ptr = get_hugepage_region(size, GHR_STRICT);
-	if (buffer->ptr == NULL) {
+	buffer->ptr = mmap(NULL, size,
+				   PROT_READ | PROT_WRITE,
+				   MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+				   -1, 0);
+	if (buffer->ptr == MAP_FAILED) {
 		free(buffer);
 		return;
 	}
@@ -1539,11 +1578,10 @@ TEST_F(hmm, compound)
 		ASSERT_EQ(m[i], HMM_DMIRROR_PROT_READ |
 				HMM_DMIRROR_PROT_PMD);
 
-	free_hugepage_region(buffer->ptr);
+	munmap(buffer->ptr, buffer->size);
 	buffer->ptr = NULL;
 	hmm_buffer_free(buffer);
 }
-#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */
 
 /*
  * Test two devices reading the same memory (double mapped).