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
  ...

11 files changed, 30 insertions, 49 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 7222ff9b5e05..084d67fd55cc 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -636,10 +636,9 @@ static int __add_memory_block(struct memory_block *memory)
 	}
 	ret = xa_err(xa_store(&memory_blocks, memory->dev.id, memory,
 			      GFP_KERNEL));
-	if (ret) {
-		put_device(&memory->dev);
+	if (ret)
 		device_unregister(&memory->dev);
-	}
+
 	return ret;
 }
 
diff --git a/drivers/base/node.c b/drivers/base/node.c
index ec8bb24a5a22..0ac6376ef7a1 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -682,6 +682,7 @@ static int register_node(struct node *node, int num)
  */
 void unregister_node(struct node *node)
 {
+	compaction_unregister_node(node);
 	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
 	node_remove_accesses(node);
 	node_remove_caches(node);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index e2cb51810e89..f1dda4ef22cc 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -190,8 +190,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 	 */
 	if (dio) {
 		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-				!(lo->lo_offset & dio_align) &&
-				mapping->a_ops->direct_IO)
+		    !(lo->lo_offset & dio_align) &&
+		    (file->f_mode & FMODE_CAN_ODIRECT))
 			use_dio = true;
 		else
 			use_dio = false;
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
index 668c6bf2554d..d4100b0c083e 100644
--- a/drivers/block/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -1,8 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 config ZRAM
 	tristate "Compressed RAM block device support"
-	depends on BLOCK && SYSFS && ZSMALLOC && CRYPTO
+	depends on BLOCK && SYSFS && MMU
 	depends on CRYPTO_LZO || CRYPTO_ZSTD || CRYPTO_LZ4 || CRYPTO_LZ4HC || CRYPTO_842
+	select ZSMALLOC
 	help
 	  Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
 	  Pages written to these disks are compressed and stored in memory
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 6853dd3c7d3a..b8549c61ff2c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -639,8 +639,8 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
 #define PAGE_WB_SIG "page_index="
 
 #define PAGE_WRITEBACK 0
-#define HUGE_WRITEBACK 1
-#define IDLE_WRITEBACK 2
+#define HUGE_WRITEBACK (1<<0)
+#define IDLE_WRITEBACK (1<<1)
 
 
 static ssize_t writeback_store(struct device *dev,
@@ -660,6 +660,8 @@ static ssize_t writeback_store(struct device *dev,
 		mode = IDLE_WRITEBACK;
 	else if (sysfs_streq(buf, "huge"))
 		mode = HUGE_WRITEBACK;
+	else if (sysfs_streq(buf, "huge_idle"))
+		mode = IDLE_WRITEBACK | HUGE_WRITEBACK;
 	else {
 		if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
 			return -EINVAL;
@@ -721,10 +723,10 @@ static ssize_t writeback_store(struct device *dev,
 				zram_test_flag(zram, index, ZRAM_UNDER_WB))
 			goto next;
 
-		if (mode == IDLE_WRITEBACK &&
+		if (mode & IDLE_WRITEBACK &&
 			  !zram_test_flag(zram, index, ZRAM_IDLE))
 			goto next;
-		if (mode == HUGE_WRITEBACK &&
+		if (mode & HUGE_WRITEBACK &&
 			  !zram_test_flag(zram, index, ZRAM_HUGE))
 			goto next;
 		/*
@@ -1142,15 +1144,14 @@ static ssize_t bd_stat_show(struct device *dev,
 static ssize_t debug_stat_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	int version = 1;
+	int version = 2;
 	struct zram *zram = dev_to_zram(dev);
 	ssize_t ret;
 
 	down_read(&zram->init_lock);
 	ret = scnprintf(buf, PAGE_SIZE,
-			"version: %d\n%8llu %8llu\n",
+			"version: %d\n%8llu\n",
 			version,
-			(u64)atomic64_read(&zram->stats.writestall),
 			(u64)atomic64_read(&zram->stats.miss_free));
 	up_read(&zram->init_lock);
 
@@ -1366,7 +1367,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 	}
 	kunmap_atomic(mem);
 
-compress_again:
 	zstrm = zcomp_stream_get(zram->comp);
 	src = kmap_atomic(page);
 	ret = zcomp_compress(zstrm, src, &comp_len);
@@ -1375,39 +1375,20 @@ compress_again:
 	if (unlikely(ret)) {
 		zcomp_stream_put(zram->comp);
 		pr_err("Compression failed! err=%d\n", ret);
-		zs_free(zram->mem_pool, handle);
 		return ret;
 	}
 
 	if (comp_len >= huge_class_size)
 		comp_len = PAGE_SIZE;
-	/*
-	 * handle allocation has 2 paths:
-	 * a) fast path is executed with preemption disabled (for
-	 *  per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear,
-	 *  since we can't sleep;
-	 * b) slow path enables preemption and attempts to allocate
-	 *  the page with __GFP_DIRECT_RECLAIM bit set. we have to
-	 *  put per-cpu compression stream and, thus, to re-do
-	 *  the compression once handle is allocated.
-	 *
-	 * if we have a 'non-null' handle here then we are coming
-	 * from the slow path and handle has already been allocated.
-	 */
-	if (!handle)
-		handle = zs_malloc(zram->mem_pool, comp_len,
-				__GFP_KSWAPD_RECLAIM |
-				__GFP_NOWARN |
-				__GFP_HIGHMEM |
-				__GFP_MOVABLE);
-	if (!handle) {
+
+	handle = zs_malloc(zram->mem_pool, comp_len,
+			__GFP_KSWAPD_RECLAIM |
+			__GFP_NOWARN |
+			__GFP_HIGHMEM |
+			__GFP_MOVABLE);
+
+	if (unlikely(!handle)) {
 		zcomp_stream_put(zram->comp);
-		atomic64_inc(&zram->stats.writestall);
-		handle = zs_malloc(zram->mem_pool, comp_len,
-				GFP_NOIO | __GFP_HIGHMEM |
-				__GFP_MOVABLE);
-		if (handle)
-			goto compress_again;
 		return -ENOMEM;
 	}
 
@@ -1965,7 +1946,6 @@ static int zram_add(void)
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
-	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
 	if (ret)
 		goto out_cleanup_disk;
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 80c3b43b4828..158c91e54850 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -81,7 +81,6 @@ struct zram_stats {
 	atomic64_t huge_pages_since;	/* no. of huge pages since zram set up */
 	atomic64_t pages_stored;	/* no. of pages currently stored */
 	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
-	atomic64_t writestall;		/* no. of write slow paths */
 	atomic64_t miss_free;		/* no. of missed free */
 #ifdef	CONFIG_ZRAM_WRITEBACK
 	atomic64_t bd_count;		/* no. of pages in backing device */
diff --git a/drivers/firmware/smccc/kvm_guest.c b/drivers/firmware/smccc/kvm_guest.c
index 2d3e866decaa..89a68e7eeaa6 100644
--- a/drivers/firmware/smccc/kvm_guest.c
+++ b/drivers/firmware/smccc/kvm_guest.c
@@ -4,6 +4,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/bitmap.h>
+#include <linux/cache.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 65552bb7d2f2..e83cb1c09610 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -184,7 +184,7 @@ static int kgd_hqd_load(struct amdgpu_device *adev, void *mqd,
 
 	/* read_user_ptr may take the mm->mmap_lock.
 	 * release srbm_mutex to avoid circular dependency between
-	 * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex.
+	 * srbm_mutex->mmap_lock->reservation_ww_class_mutex->srbm_mutex.
 	 */
 	release_queue(adev);
 	valid_wptr = read_user_wptr(mm, wptr, wptr_val);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 9dc5f2a0cc07..870f352837fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -208,7 +208,7 @@ static int kgd_hqd_load(struct amdgpu_device *adev, void *mqd,
 
 	/* read_user_ptr may take the mm->mmap_lock.
 	 * release srbm_mutex to avoid circular dependency between
-	 * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex.
+	 * srbm_mutex->mmap_lock->reservation_ww_class_mutex->srbm_mutex.
 	 */
 	release_queue(adev);
 	valid_wptr = read_user_wptr(mm, wptr, wptr_val);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 5b324f245265..38119311284d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -102,7 +102,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
  * @bo: The buffer object
  * @vmf: The fault structure handed to the callback
  *
- * vm callbacks like fault() and *_mkwrite() allow for the mm_sem to be dropped
+ * vm callbacks like fault() and *_mkwrite() allow for the mmap_lock to be dropped
  * during long waits, and after the wait the callback will be restarted. This
  * is to allow other threads using the same virtual memory space concurrent
  * access to map(), unmap() completely unrelated buffer objects. TTM buffer
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index e7d6b679596d..e07486f01999 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -2476,10 +2476,10 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm)
 				      VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD);
 
 	/*
-	 * TODO: once alloc_contig_range() works reliably with pageblock
-	 * granularity on ZONE_NORMAL, use pageblock_nr_pages instead.
+	 * alloc_contig_range() works reliably with pageblock
+	 * granularity on ZONE_NORMAL, use pageblock_nr_pages.
 	 */
-	sb_size = PAGE_SIZE * MAX_ORDER_NR_PAGES;
+	sb_size = PAGE_SIZE * pageblock_nr_pages;
 	sb_size = max_t(uint64_t, vm->device_block_size, sb_size);
 
 	if (sb_size < memory_block_size_bytes() && !force_bbm) {