Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

1 files changed, 89 insertions, 49 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index f2fc0373b967..e1e621d0b6a0 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -81,6 +81,8 @@ static bool zswap_pool_reached_full;
 
 #define ZSWAP_PARAM_UNSET ""
 
+static int zswap_setup(void);
+
 /* Enable/disable zswap */
 static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON);
 static int zswap_enabled_param_set(const char *,
@@ -214,11 +216,16 @@ static DEFINE_SPINLOCK(zswap_pools_lock);
 /* pool counter to provide unique names to zpool */
 static atomic_t zswap_pools_count = ATOMIC_INIT(0);
 
-/* used by param callback function */
-static bool zswap_init_started;
+enum zswap_init_type {
+	ZSWAP_UNINIT,
+	ZSWAP_INIT_SUCCEED,
+	ZSWAP_INIT_FAILED
+};
+
+static enum zswap_init_type zswap_init_state;
 
-/* fatal error during init */
-static bool zswap_init_failed;
+/* used to ensure the integrity of initialization */
+static DEFINE_MUTEX(zswap_init_lock);
 
 /* init completed, but couldn't create the initial pool */
 static bool zswap_has_pool;
@@ -272,17 +279,6 @@ static void zswap_update_total_size(void)
 **********************************/
 static struct kmem_cache *zswap_entry_cache;
 
-static int __init zswap_entry_cache_create(void)
-{
-	zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
-	return zswap_entry_cache == NULL;
-}
-
-static void __init zswap_entry_cache_destroy(void)
-{
-	kmem_cache_destroy(zswap_entry_cache);
-}
-
 static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
 {
 	struct zswap_entry *entry;
@@ -663,7 +659,7 @@ error:
 	return NULL;
 }
 
-static __init struct zswap_pool *__zswap_pool_create_fallback(void)
+static struct zswap_pool *__zswap_pool_create_fallback(void)
 {
 	bool has_comp, has_zpool;
 
@@ -764,28 +760,43 @@ static void zswap_pool_put(struct zswap_pool *pool)
 * param callbacks
 **********************************/
 
+static bool zswap_pool_changed(const char *s, const struct kernel_param *kp)
+{
+	/* no change required */
+	if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool)
+		return false;
+	return true;
+}
+
 /* val must be a null-terminated string */
 static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 			     char *type, char *compressor)
 {
 	struct zswap_pool *pool, *put_pool = NULL;
 	char *s = strstrip((char *)val);
-	int ret;
-
-	if (zswap_init_failed) {
+	int ret = 0;
+	bool new_pool = false;
+
+	mutex_lock(&zswap_init_lock);
+	switch (zswap_init_state) {
+	case ZSWAP_UNINIT:
+		/* if this is load-time (pre-init) param setting,
+		 * don't create a pool; that's done during init.
+		 */
+		ret = param_set_charp(s, kp);
+		break;
+	case ZSWAP_INIT_SUCCEED:
+		new_pool = zswap_pool_changed(s, kp);
+		break;
+	case ZSWAP_INIT_FAILED:
 		pr_err("can't set param, initialization failed\n");
-		return -ENODEV;
+		ret = -ENODEV;
 	}
+	mutex_unlock(&zswap_init_lock);
 
-	/* no change required */
-	if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool)
-		return 0;
-
-	/* if this is load-time (pre-init) param setting,
-	 * don't create a pool; that's done during init.
-	 */
-	if (!zswap_init_started)
-		return param_set_charp(s, kp);
+	/* no need to create a new pool, return directly */
+	if (!new_pool)
+		return ret;
 
 	if (!type) {
 		if (!zpool_has_pool(s)) {
@@ -875,16 +886,30 @@ static int zswap_zpool_param_set(const char *val,
 static int zswap_enabled_param_set(const char *val,
 				   const struct kernel_param *kp)
 {
-	if (zswap_init_failed) {
+	int ret = -ENODEV;
+
+	/* if this is load-time (pre-init) param setting, only set param. */
+	if (system_state != SYSTEM_RUNNING)
+		return param_set_bool(val, kp);
+
+	mutex_lock(&zswap_init_lock);
+	switch (zswap_init_state) {
+	case ZSWAP_UNINIT:
+		if (zswap_setup())
+			break;
+		fallthrough;
+	case ZSWAP_INIT_SUCCEED:
+		if (!zswap_has_pool)
+			pr_err("can't enable, no pool configured\n");
+		else
+			ret = param_set_bool(val, kp);
+		break;
+	case ZSWAP_INIT_FAILED:
 		pr_err("can't enable, initialization failed\n");
-		return -ENODEV;
-	}
-	if (!zswap_has_pool && zswap_init_started) {
-		pr_err("can't enable, no pool configured\n");
-		return -ENODEV;
 	}
+	mutex_unlock(&zswap_init_lock);
 
-	return param_set_bool(val, kp);
+	return ret;
 }
 
 /*********************************
@@ -1073,15 +1098,23 @@ fail:
 
 static int zswap_is_page_same_filled(void *ptr, unsigned long *value)
 {
-	unsigned int pos;
 	unsigned long *page;
+	unsigned long val;
+	unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1;
 
 	page = (unsigned long *)ptr;
-	for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) {
-		if (page[pos] != page[0])
+	val = page[0];
+
+	if (val != page[last_pos])
+		return 0;
+
+	for (pos = 1; pos < last_pos; pos++) {
+		if (val != page[pos])
 			return 0;
 	}
-	*value = page[0];
+
+	*value = val;
+
 	return 1;
 }
 
@@ -1434,7 +1467,7 @@ static const struct frontswap_ops zswap_frontswap_ops = {
 
 static struct dentry *zswap_debugfs_root;
 
-static int __init zswap_debugfs_init(void)
+static int zswap_debugfs_init(void)
 {
 	if (!debugfs_initialized())
 		return -ENODEV;
@@ -1465,7 +1498,7 @@ static int __init zswap_debugfs_init(void)
 	return 0;
 }
 #else
-static int __init zswap_debugfs_init(void)
+static int zswap_debugfs_init(void)
 {
 	return 0;
 }
@@ -1474,14 +1507,13 @@ static int __init zswap_debugfs_init(void)
 /*********************************
 * module init and exit
 **********************************/
-static int __init init_zswap(void)
+static int zswap_setup(void)
 {
 	struct zswap_pool *pool;
 	int ret;
 
-	zswap_init_started = true;
-
-	if (zswap_entry_cache_create()) {
+	zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
+	if (!zswap_entry_cache) {
 		pr_err("entry cache creation failed\n");
 		goto cache_fail;
 	}
@@ -1520,6 +1552,7 @@ static int __init init_zswap(void)
 		goto destroy_wq;
 	if (zswap_debugfs_init())
 		pr_warn("debugfs initialization failed\n");
+	zswap_init_state = ZSWAP_INIT_SUCCEED;
 	return 0;
 
 destroy_wq:
@@ -1530,15 +1563,22 @@ fallback_fail:
 hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
-	zswap_entry_cache_destroy();
+	kmem_cache_destroy(zswap_entry_cache);
 cache_fail:
 	/* if built-in, we aren't unloaded on failure; don't allow use */
-	zswap_init_failed = true;
+	zswap_init_state = ZSWAP_INIT_FAILED;
 	zswap_enabled = false;
 	return -ENOMEM;
 }
+
+static int __init zswap_init(void)
+{
+	if (!zswap_enabled)
+		return 0;
+	return zswap_setup();
+}
 /* must be late so crypto has time to come up */
-late_initcall(init_zswap);
+late_initcall(zswap_init);
 
 MODULE_AUTHOR("Seth Jennings <sjennings@variantweb.net>");
 MODULE_DESCRIPTION("Compressed cache for swap pages");