Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

66 files changed, 3396 insertions, 1716 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index b7a44b17c79f..e59cf5fe5ce9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -33,7 +33,7 @@ config ZSWAP
 	  pages that are in the process of being swapped out and attempts to
 	  compress them into a dynamically allocated RAM-based memory pool.
 	  This can result in a significant I/O reduction on swap device and,
-	  in the case where decompressing from RAM is faster that swap device
+	  in the case where decompressing from RAM is faster than swap device
 	  reads, can also improve workload performance.
 
 	  This is marked experimental because it is a new feature (as of
@@ -655,7 +655,7 @@ config KSM
 	  the many instances by a single page with that content, so
 	  saving memory until one or another app needs to modify the content.
 	  Recommended for use with KVM, or with other duplicative applications.
-	  See Documentation/vm/ksm.rst for more information: KSM is inactive
+	  See Documentation/mm/ksm.rst for more information: KSM is inactive
 	  until a program has madvised that an area is MADV_MERGEABLE, and
 	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
 
@@ -943,9 +943,6 @@ config ARCH_HAS_CURRENT_STACK_POINTER
 	  register alias named "current_stack_pointer", this config can be
 	  selected.
 
-config ARCH_HAS_VM_GET_PAGE_PROT
-	bool
-
 config ARCH_HAS_PTE_DEVMAP
 	bool
 
diff --git a/mm/Makefile b/mm/Makefile
index 6f9ffa968a1a..9a564f836403 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -133,3 +133,4 @@ obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
 obj-$(CONFIG_IO_MAPPING) += io-mapping.o
 obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
+obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index 2e7704955f4f..c3ffe253e055 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -163,7 +163,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(cma_alloc_fops, NULL, cma_alloc_write, "%llu\n");
 static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry)
 {
 	struct dentry *tmp;
-	char name[16];
+	char name[CMA_MAX_NAME];
 
 	scnprintf(name, sizeof(name), "cma-%s", cma->name);
 
diff --git a/mm/compaction.c b/mm/compaction.c
index a2c53fcf933e..640fa76228dd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -613,6 +613,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 			break;
 		set_page_private(page, order);
 
+		nr_scanned += isolated - 1;
 		total_isolated += isolated;
 		cc->nr_freepages += isolated;
 		list_add_tail(&page->lru, freelist);
@@ -1099,6 +1100,7 @@ isolate_success:
 isolate_success_no_list:
 		cc->nr_migratepages += compound_nr(page);
 		nr_isolated += compound_nr(page);
+		nr_scanned += compound_nr(page) - 1;
 
 		/*
 		 * Avoid isolating too much unless this block is being
@@ -1502,6 +1504,7 @@ fast_isolate_freepages(struct compact_control *cc)
 			if (__isolate_free_page(page, order)) {
 				set_page_private(page, order);
 				nr_isolated = 1 << order;
+				nr_scanned += nr_isolated - 1;
 				cc->nr_freepages += nr_isolated;
 				list_add_tail(&page->lru, &cc->freepages);
 				count_compact_events(COMPACTISOLATED, nr_isolated);
@@ -3009,7 +3012,7 @@ void kcompactd_run(int nid)
 
 /*
  * Called by memory hotplug when all memory in a node is offlined. Caller must
- * hold mem_hotplug_begin/end().
+ * be holding mem_hotplug_begin/done().
  */
 void kcompactd_stop(int nid)
 {
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index 9b559c76d6dd..66265e3a9c65 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -92,4 +92,12 @@ config DAMON_RECLAIM
 	  reclamation under light memory pressure, while the traditional page
 	  scanning-based reclamation is used for heavy pressure.
 
+config DAMON_LRU_SORT
+	bool "Build DAMON-based LRU-lists sorting (DAMON_LRU_SORT)"
+	depends on DAMON_PADDR
+	help
+	  This builds the DAMON-based LRU-lists sorting subsystem.  It tries to
+	  protect frequently accessed (hot) pages while rarely accessed (cold)
+	  pages reclaimed first under memory pressure.
+
 endmenu
diff --git a/mm/damon/Makefile b/mm/damon/Makefile
index dbf7190b4144..3e6b8ad73858 100644
--- a/mm/damon/Makefile
+++ b/mm/damon/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_DAMON_PADDR)	+= ops-common.o paddr.o
 obj-$(CONFIG_DAMON_SYSFS)	+= sysfs.o
 obj-$(CONFIG_DAMON_DBGFS)	+= dbgfs.o
 obj-$(CONFIG_DAMON_RECLAIM)	+= reclaim.o
+obj-$(CONFIG_DAMON_LRU_SORT)	+= lru_sort.o
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index a0dab8b5e45f..cb8a7e9926a4 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -97,6 +97,31 @@ out:
 	return ret;
 }
 
+/*
+ * Return corresponding dbgfs' scheme action value (int) for the given
+ * damos_action if the given damos_action value is valid and supported by
+ * dbgfs, negative error code otherwise.
+ */
+static int damos_action_to_dbgfs_scheme_action(enum damos_action action)
+{
+	switch (action) {
+	case DAMOS_WILLNEED:
+		return 0;
+	case DAMOS_COLD:
+		return 1;
+	case DAMOS_PAGEOUT:
+		return 2;
+	case DAMOS_HUGEPAGE:
+		return 3;
+	case DAMOS_NOHUGEPAGE:
+		return 4;
+	case DAMOS_STAT:
+		return 5;
+	default:
+		return -EINVAL;
+	}
+}
+
 static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len)
 {
 	struct damos *s;
@@ -109,7 +134,7 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len)
 				s->min_sz_region, s->max_sz_region,
 				s->min_nr_accesses, s->max_nr_accesses,
 				s->min_age_region, s->max_age_region,
-				s->action,
+				damos_action_to_dbgfs_scheme_action(s->action),
 				s->quota.ms, s->quota.sz,
 				s->quota.reset_interval,
 				s->quota.weight_sz,
@@ -160,18 +185,27 @@ static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes)
 	kfree(schemes);
 }
 
-static bool damos_action_valid(int action)
+/*
+ * Return corresponding damos_action for the given dbgfs input for a scheme
+ * action if the input is valid, negative error code otherwise.
+ */
+static enum damos_action dbgfs_scheme_action_to_damos_action(int dbgfs_action)
 {
-	switch (action) {
-	case DAMOS_WILLNEED:
-	case DAMOS_COLD:
-	case DAMOS_PAGEOUT:
-	case DAMOS_HUGEPAGE:
-	case DAMOS_NOHUGEPAGE:
-	case DAMOS_STAT:
-		return true;
+	switch (dbgfs_action) {
+	case 0:
+		return DAMOS_WILLNEED;
+	case 1:
+		return DAMOS_COLD;
+	case 2:
+		return DAMOS_PAGEOUT;
+	case 3:
+		return DAMOS_HUGEPAGE;
+	case 4:
+		return DAMOS_NOHUGEPAGE;
+	case 5:
+		return DAMOS_STAT;
 	default:
-		return false;
+		return -EINVAL;
 	}
 }
 
@@ -189,7 +223,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len,
 	int pos = 0, parsed, ret;
 	unsigned long min_sz, max_sz;
 	unsigned int min_nr_a, max_nr_a, min_age, max_age;
-	unsigned int action;
+	unsigned int action_input;
+	enum damos_action action;
 
 	schemes = kmalloc_array(max_nr_schemes, sizeof(scheme),
 			GFP_KERNEL);
@@ -204,7 +239,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len,
 		ret = sscanf(&str[pos],
 				"%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n",
 				&min_sz, &max_sz, &min_nr_a, &max_nr_a,
-				&min_age, &max_age, &action, &quota.ms,
+				&min_age, &max_age, &action_input, &quota.ms,
 				&quota.sz, &quota.reset_interval,
 				&quota.weight_sz, &quota.weight_nr_accesses,
 				&quota.weight_age, &wmarks.metric,
@@ -212,7 +247,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len,
 				&wmarks.low, &parsed);
 		if (ret != 18)
 			break;
-		if (!damos_action_valid(action))
+		action = dbgfs_scheme_action_to_damos_action(action_input);
+		if ((int)action < 0)
 			goto fail;
 
 		if (min_sz > max_sz || min_nr_a > max_nr_a || min_age > max_age)
@@ -275,11 +311,6 @@ out:
 	return ret;
 }
 
-static inline bool target_has_pid(const struct damon_ctx *ctx)
-{
-	return ctx->ops.id == DAMON_OPS_VADDR;
-}
-
 static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len)
 {
 	struct damon_target *t;
@@ -288,7 +319,7 @@ static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len)
 	int rc;
 
 	damon_for_each_target(t, ctx) {
-		if (target_has_pid(ctx))
+		if (damon_target_has_pid(ctx))
 			/* Show pid numbers to debugfs users */
 			id = pid_vnr(t->pid);
 		else
@@ -415,7 +446,7 @@ static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets,
 	struct damon_target *t, *next;
 
 	damon_for_each_target_safe(t, next, ctx) {
-		if (target_has_pid(ctx))
+		if (damon_target_has_pid(ctx))
 			put_pid(t->pid);
 		damon_destroy_target(t);
 	}
@@ -425,11 +456,11 @@ static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets,
 		if (!t) {
 			damon_for_each_target_safe(t, next, ctx)
 				damon_destroy_target(t);
-			if (target_has_pid(ctx))
+			if (damon_target_has_pid(ctx))
 				dbgfs_put_pids(pids, nr_targets);
 			return -ENOMEM;
 		}
-		if (target_has_pid(ctx))
+		if (damon_target_has_pid(ctx))
 			t->pid = pids[i];
 		damon_add_target(ctx, t);
 	}
@@ -722,7 +753,7 @@ static void dbgfs_before_terminate(struct damon_ctx *ctx)
 {
 	struct damon_target *t, *next;
 
-	if (!target_has_pid(ctx))
+	if (!damon_target_has_pid(ctx))
 		return;
 
 	mutex_lock(&ctx->kdamond_lock);
diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
new file mode 100644
index 000000000000..9de6f00a71c5
--- /dev/null
+++ b/mm/damon/lru_sort.c
@@ -0,0 +1,548 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON-based LRU-lists Sorting
+ *
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#define pr_fmt(fmt) "damon-lru-sort: " fmt
+
+#include <linux/damon.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "damon_lru_sort."
+
+/*
+ * Enable or disable DAMON_LRU_SORT.
+ *
+ * You can enable DAMON_LRU_SORT by setting the value of this parameter as
+ * ``Y``.  Setting it as ``N`` disables DAMON_LRU_SORT.  Note that
+ * DAMON_LRU_SORT could do no real monitoring and LRU-lists sorting due to the
+ * watermarks-based activation condition.  Refer to below descriptions for the
+ * watermarks parameter for this.
+ */
+static bool enabled __read_mostly;
+
+/*
+ * Make DAMON_LRU_SORT reads the input parameters again, except ``enabled``.
+ *
+ * Input parameters that updated while DAMON_LRU_SORT is running are not
+ * applied by default.  Once this parameter is set as ``Y``, DAMON_LRU_SORT
+ * reads values of parametrs except ``enabled`` again.  Once the re-reading is
+ * done, this parameter is set as ``N``.  If invalid parameters are found while
+ * the re-reading, DAMON_LRU_SORT will be disabled.
+ */
+static bool commit_inputs __read_mostly;
+module_param(commit_inputs, bool, 0600);
+
+/*
+ * Access frequency threshold for hot memory regions identification in permil.
+ *
+ * If a memory region is accessed in frequency of this or higher,
+ * DAMON_LRU_SORT identifies the region as hot, and mark it as accessed on the
+ * LRU list, so that it could not be reclaimed under memory pressure.  50% by
+ * default.
+ */
+static unsigned long hot_thres_access_freq = 500;
+module_param(hot_thres_access_freq, ulong, 0600);
+
+/*
+ * Time threshold for cold memory regions identification in microseconds.
+ *
+ * If a memory region is not accessed for this or longer time, DAMON_LRU_SORT
+ * identifies the region as cold, and mark it as unaccessed on the LRU list, so
+ * that it could be reclaimed first under memory pressure.  120 seconds by
+ * default.
+ */
+static unsigned long cold_min_age __read_mostly = 120000000;
+module_param(cold_min_age, ulong, 0600);
+
+/*
+ * Limit of time for trying the LRU lists sorting in milliseconds.
+ *
+ * DAMON_LRU_SORT tries to use only up to this time within a time window
+ * (quota_reset_interval_ms) for trying LRU lists sorting.  This can be used
+ * for limiting CPU consumption of DAMON_LRU_SORT.  If the value is zero, the
+ * limit is disabled.
+ *
+ * 10 ms by default.
+ */
+static unsigned long quota_ms __read_mostly = 10;
+module_param(quota_ms, ulong, 0600);
+
+/*
+ * The time quota charge reset interval in milliseconds.
+ *
+ * The charge reset interval for the quota of time (quota_ms).  That is,
+ * DAMON_LRU_SORT does not try LRU-lists sorting for more than quota_ms
+ * milliseconds or quota_sz bytes within quota_reset_interval_ms milliseconds.
+ *
+ * 1 second by default.
+ */
+static unsigned long quota_reset_interval_ms __read_mostly = 1000;
+module_param(quota_reset_interval_ms, ulong, 0600);
+
+/*
+ * The watermarks check time interval in microseconds.
+ *
+ * Minimal time to wait before checking the watermarks, when DAMON_LRU_SORT is
+ * enabled but inactive due to its watermarks rule.  5 seconds by default.
+ */
+static unsigned long wmarks_interval __read_mostly = 5000000;
+module_param(wmarks_interval, ulong, 0600);
+
+/*
+ * Free memory rate (per thousand) for the high watermark.
+ *
+ * If free memory of the system in bytes per thousand bytes is higher than
+ * this, DAMON_LRU_SORT becomes inactive, so it does nothing but periodically
+ * checks the watermarks.  200 (20%) by default.
+ */
+static unsigned long wmarks_high __read_mostly = 200;
+module_param(wmarks_high, ulong, 0600);
+
+/*
+ * Free memory rate (per thousand) for the middle watermark.
+ *
+ * If free memory of the system in bytes per thousand bytes is between this and
+ * the low watermark, DAMON_LRU_SORT becomes active, so starts the monitoring
+ * and the LRU-lists sorting.  150 (15%) by default.
+ */
+static unsigned long wmarks_mid __read_mostly = 150;
+module_param(wmarks_mid, ulong, 0600);
+
+/*
+ * Free memory rate (per thousand) for the low watermark.
+ *
+ * If free memory of the system in bytes per thousand bytes is lower than this,
+ * DAMON_LRU_SORT becomes inactive, so it does nothing but periodically checks
+ * the watermarks.  50 (5%) by default.
+ */
+static unsigned long wmarks_low __read_mostly = 50;
+module_param(wmarks_low, ulong, 0600);
+
+/*
+ * Sampling interval for the monitoring in microseconds.
+ *
+ * The sampling interval of DAMON for the hot/cold memory monitoring.  Please
+ * refer to the DAMON documentation for more detail.  5 ms by default.
+ */
+static unsigned long sample_interval __read_mostly = 5000;
+module_param(sample_interval, ulong, 0600);
+
+/*
+ * Aggregation interval for the monitoring in microseconds.
+ *
+ * The aggregation interval of DAMON for the hot/cold memory monitoring.
+ * Please refer to the DAMON documentation for more detail.  100 ms by default.
+ */
+static unsigned long aggr_interval __read_mostly = 100000;
+module_param(aggr_interval, ulong, 0600);
+
+/*
+ * Minimum number of monitoring regions.
+ *
+ * The minimal number of monitoring regions of DAMON for the hot/cold memory
+ * monitoring.  This can be used to set lower-bound of the monitoring quality.
+ * But, setting this too high could result in increased monitoring overhead.
+ * Please refer to the DAMON documentation for more detail.  10 by default.
+ */
+static unsigned long min_nr_regions __read_mostly = 10;
+module_param(min_nr_regions, ulong, 0600);
+
+/*
+ * Maximum number of monitoring regions.
+ *
+ * The maximum number of monitoring regions of DAMON for the hot/cold memory
+ * monitoring.  This can be used to set upper-bound of the monitoring overhead.
+ * However, setting this too low could result in bad monitoring quality.
+ * Please refer to the DAMON documentation for more detail.  1000 by default.
+ */
+static unsigned long max_nr_regions __read_mostly = 1000;
+module_param(max_nr_regions, ulong, 0600);
+
+/*
+ * Start of the target memory region in physical address.
+ *
+ * The start physical address of memory region that DAMON_LRU_SORT will do work
+ * against.  By default, biggest System RAM is used as the region.
+ */
+static unsigned long monitor_region_start __read_mostly;
+module_param(monitor_region_start, ulong, 0600);
+
+/*
+ * End of the target memory region in physical address.
+ *
+ * The end physical address of memory region that DAMON_LRU_SORT will do work
+ * against.  By default, biggest System RAM is used as the region.
+ */
+static unsigned long monitor_region_end __read_mostly;
+module_param(monitor_region_end, ulong, 0600);
+
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+static int kdamond_pid __read_mostly = -1;
+module_param(kdamond_pid, int, 0400);
+
+/*
+ * Number of hot memory regions that tried to be LRU-sorted.
+ */
+static unsigned long nr_lru_sort_tried_hot_regions __read_mostly;
+module_param(nr_lru_sort_tried_hot_regions, ulong, 0400);
+
+/*
+ * Total bytes of hot memory regions that tried to be LRU-sorted.
+ */
+static unsigned long bytes_lru_sort_tried_hot_regions __read_mostly;
+module_param(bytes_lru_sort_tried_hot_regions, ulong, 0400);
+
+/*
+ * Number of hot memory regions that successfully be LRU-sorted.
+ */
+static unsigned long nr_lru_sorted_hot_regions __read_mostly;
+module_param(nr_lru_sorted_hot_regions, ulong, 0400);
+
+/*
+ * Total bytes of hot memory regions that successfully be LRU-sorted.
+ */
+static unsigned long bytes_lru_sorted_hot_regions __read_mostly;