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
  ...

2 files changed, 31 insertions, 22 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e551433cd107..7c74d8cba44f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -329,8 +329,8 @@ static ssize_t idle_store(struct device *dev,
 
 	if (!sysfs_streq(buf, "all")) {
 		/*
-		 * If it did not parse as 'all' try to treat it as an integer when
-		 * we have memory tracking enabled.
+		 * If it did not parse as 'all' try to treat it as an integer
+		 * when we have memory tracking enabled.
 		 */
 		u64 age_sec;
 
@@ -345,7 +345,10 @@ static ssize_t idle_store(struct device *dev,
 	if (!init_done(zram))
 		goto out_unlock;
 
-	/* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */
+	/*
+	 * A cutoff_time of 0 marks everything as idle, this is the
+	 * "all" behavior.
+	 */
 	mark_idle(zram, cutoff_time);
 	rv = len;
 
@@ -1410,9 +1413,19 @@ compress_again:
 		handle = zs_malloc(zram->mem_pool, comp_len,
 				GFP_NOIO | __GFP_HIGHMEM |
 				__GFP_MOVABLE);
-		if (!IS_ERR((void *)handle))
+		if (IS_ERR((void *)handle))
+			return PTR_ERR((void *)handle);
+
+		if (comp_len != PAGE_SIZE)
 			goto compress_again;
-		return PTR_ERR((void *)handle);
+		/*
+		 * If the page is not compressible, you need to acquire the
+		 * lock and execute the code below. The zcomp_stream_get()
+		 * call is needed to disable the cpu hotplug and grab the
+		 * zstrm buffer back. It is necessary that the dereferencing
+		 * of the zstrm variable below occurs correctly.
+		 */
+		zstrm = zcomp_stream_get(zram->comp);
 	}
 
 	alloced_pages = zs_get_total_pages(zram->mem_pool);
@@ -1710,9 +1723,6 @@ out:
 
 static void zram_reset_device(struct zram *zram)
 {
-	struct zcomp *comp;
-	u64 disksize;
-
 	down_write(&zram->init_lock);
 
 	zram->limit_pages = 0;
@@ -1722,17 +1732,15 @@ static void zram_reset_device(struct zram *zram)
 		return;
 	}
 
-	comp = zram->comp;
-	disksize = zram->disksize;
-	zram->disksize = 0;
-
 	set_capacity_and_notify(zram->disk, 0);
 	part_stat_set_all(zram->disk->part0, 0);
 
 	/* I/O operation under all of CPU are done so let's free */
-	zram_meta_free(zram, disksize);
+	zram_meta_free(zram, zram->disksize);
+	zram->disksize = 0;
 	memset(&zram->stats, 0, sizeof(zram->stats));
-	zcomp_destroy(comp);
+	zcomp_destroy(zram->comp);
+	zram->comp = NULL;
 	reset_bdev(zram);
 
 	up_write(&zram->init_lock);
@@ -2126,6 +2134,8 @@ static int __init zram_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON(__NR_ZRAM_PAGEFLAGS > BITS_PER_LONG);
+
 	ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
 				      zcomp_cpu_up_prepare, zcomp_cpu_dead);
 	if (ret < 0)
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 80c3b43b4828..a2bda53020fd 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -30,16 +30,15 @@
 
 
 /*
- * The lower ZRAM_FLAG_SHIFT bits of table.flags is for
- * object size (excluding header), the higher bits is for
- * zram_pageflags.
+ * ZRAM is mainly used for memory efficiency so we want to keep memory
+ * footprint small and thus squeeze size and zram pageflags into a flags
+ * member. The lower ZRAM_FLAG_SHIFT bits is for object size (excluding
+ * header), which cannot be larger than PAGE_SIZE (requiring PAGE_SHIFT
+ * bits), the higher bits are for zram_pageflags.
  *
- * zram is mainly used for memory efficiency so we want to keep memory
- * footprint small so we can squeeze size and flags into a field.
- * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header),
- * the higher bits is for zram_pageflags.
+ * We use BUILD_BUG_ON() to make sure that zram pageflags don't overflow.
  */
-#define ZRAM_FLAG_SHIFT 24
+#define ZRAM_FLAG_SHIFT (PAGE_SHIFT + 1)
 
 /* Flags for zram pages (table[page_no].flags) */
 enum zram_pageflags {