Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

1 files changed, 27 insertions, 59 deletions

diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 9b06a5034808..558c9cd8901c 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include <fcntl.h>
+#include <dirent.h>
 #include <sys/ioctl.h>
 #include <linux/userfaultfd.h>
 #include <sys/syscall.h>
@@ -198,6 +199,32 @@ unsigned long default_huge_page_size(void)
 	return hps;
 }
 
+int detect_hugetlb_page_sizes(size_t sizes[], int max)
+{
+	DIR *dir = opendir("/sys/kernel/mm/hugepages/");
+	int count = 0;
+
+	if (!dir)
+		return 0;
+
+	while (count < max) {
+		struct dirent *entry = readdir(dir);
+		size_t kb;
+
+		if (!entry)
+			break;
+		if (entry->d_type != DT_DIR)
+			continue;
+		if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1)
+			continue;
+		sizes[count++] = kb * 1024;
+		ksft_print_msg("[INFO] detected hugetlb page size: %zu KiB\n",
+			       kb);
+	}
+	closedir(dir);
+	return count;
+}
+
 /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */
 int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
 			      bool miss, bool wp, bool minor, uint64_t *ioctls)
@@ -242,62 +269,3 @@ int uffd_unregister(int uffd, void *addr, uint64_t len)
 
 	return ret;
 }
-
-int uffd_open_dev(unsigned int flags)
-{
-	int fd, uffd;
-
-	fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC);
-	if (fd < 0)
-		return fd;
-	uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags);
-	close(fd);
-
-	return uffd;
-}
-
-int uffd_open_sys(unsigned int flags)
-{
-#ifdef __NR_userfaultfd
-	return syscall(__NR_userfaultfd, flags);
-#else
-	return -1;
-#endif
-}
-
-int uffd_open(unsigned int flags)
-{
-	int uffd = uffd_open_sys(flags);
-
-	if (uffd < 0)
-		uffd = uffd_open_dev(flags);
-
-	return uffd;
-}
-
-int uffd_get_features(uint64_t *features)
-{
-	struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 };
-	/*
-	 * This should by default work in most kernels; the feature list
-	 * will be the same no matter what we pass in here.
-	 */
-	int fd = uffd_open(UFFD_USER_MODE_ONLY);
-
-	if (fd < 0)
-		/* Maybe the kernel is older than user-only mode? */
-		fd = uffd_open(0);
-
-	if (fd < 0)
-		return fd;
-
-	if (ioctl(fd, UFFDIO_API, &uffdio_api)) {
-		close(fd);
-		return -errno;
-	}
-
-	*features = uffdio_api.features;
-	close(fd);
-
-	return 0;
-}