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
  ...

1 files changed, 57 insertions, 232 deletions

diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index a7faf51b4bd4..162c9b1ca00f 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -13,6 +13,8 @@
 #include <linux/sched.h>
 #include <linux/workqueue.h>
 
+#include "modules-common.h"
+
 #ifdef MODULE_PARAM_PREFIX
 #undef MODULE_PARAM_PREFIX
 #endif
@@ -50,124 +52,35 @@ module_param(commit_inputs, bool, 0600);
 static unsigned long min_age __read_mostly = 120000000;
 module_param(min_age, ulong, 0600);
 
-/*
- * Limit of time for trying the reclamation in milliseconds.
- *
- * DAMON_RECLAIM tries to use only up to this time within a time window
- * (quota_reset_interval_ms) for trying reclamation of cold pages.  This can be
- * used for limiting CPU consumption of DAMON_RECLAIM.  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);
-
-/*
- * Limit of size of memory for the reclamation in bytes.
- *
- * DAMON_RECLAIM charges amount of memory which it tried to reclaim within a
- * time window (quota_reset_interval_ms) and makes no more than this limit is
- * tried.  This can be used for limiting consumption of CPU and IO.  If this
- * value is zero, the limit is disabled.
- *
- * 128 MiB by default.
- */
-static unsigned long quota_sz __read_mostly = 128 * 1024 * 1024;
-module_param(quota_sz, ulong, 0600);
-
-/*
- * The time/size quota charge reset interval in milliseconds.
- *
- * The charge reset interval for the quota of time (quota_ms) and size
- * (quota_sz).  That is, DAMON_RECLAIM does not try reclamation 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_RECLAIM 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_RECLAIM becomes inactive, so it does nothing but periodically
- * checks the watermarks.  500 (50%) by default.
- */
-static unsigned long wmarks_high __read_mostly = 500;
-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_RECLAIM becomes active, so starts the monitoring
- * and the reclaiming.  400 (40%) by default.
- */
-static unsigned long wmarks_mid __read_mostly = 400;
-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_RECLAIM becomes inactive, so it does nothing but periodically checks
- * the watermarks.  In the case, the system falls back to the LRU-based page
- * granularity reclamation logic.  200 (20%) by default.
- */
-static unsigned long wmarks_low __read_mostly = 200;
-module_param(wmarks_low, ulong, 0600);
-
-/*
- * Sampling interval for the monitoring in microseconds.
- *
- * The sampling interval of DAMON for the 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 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 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 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);
+static struct damos_quota damon_reclaim_quota = {
+	/* use up to 10 ms time, reclaim up to 128 MiB per 1 sec by default */
+	.ms = 10,
+	.sz = 128 * 1024 * 1024,
+	.reset_interval = 1000,
+	/* Within the quota, page out older regions first. */
+	.weight_sz = 0,
+	.weight_nr_accesses = 0,
+	.weight_age = 1
+};
+DEFINE_DAMON_MODULES_DAMOS_QUOTAS(damon_reclaim_quota);
+
+static struct damos_watermarks damon_reclaim_wmarks = {
+	.metric = DAMOS_WMARK_FREE_MEM_RATE,
+	.interval = 5000000,	/* 5 seconds */
+	.high = 500,		/* 50 percent */
+	.mid = 400,		/* 40 percent */
+	.low = 200,		/* 20 percent */
+};
+DEFINE_DAMON_MODULES_WMARKS_PARAMS(damon_reclaim_wmarks);
+
+static struct damon_attrs damon_reclaim_mon_attrs = {
+	.sample_interval = 5000,	/* 5 ms */
+	.aggr_interval = 100000,	/* 100 ms */
+	.ops_update_interval = 0,
+	.min_nr_regions = 10,
+	.max_nr_regions = 1000,
+};
+DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(damon_reclaim_mon_attrs);
 
 /*
  * Start of the target memory region in physical address.
@@ -196,119 +109,44 @@ module_param(monitor_region_end, ulong, 0600);
 static int kdamond_pid __read_mostly = -1;
 module_param(kdamond_pid, int, 0400);
 
-/*
- * Number of memory regions that tried to be reclaimed.
- */
-static unsigned long nr_reclaim_tried_regions __read_mostly;
-module_param(nr_reclaim_tried_regions, ulong, 0400);
-
-/*
- * Total bytes of memory regions that tried to be reclaimed.
- */
-static unsigned long bytes_reclaim_tried_regions __read_mostly;
-module_param(bytes_reclaim_tried_regions, ulong, 0400);
-
-/*
- * Number of memory regions that successfully be reclaimed.
- */
-static unsigned long nr_reclaimed_regions __read_mostly;
-module_param(nr_reclaimed_regions, ulong, 0400);
-
-/*
- * Total bytes of memory regions that successfully be reclaimed.
- */
-static unsigned long bytes_reclaimed_regions __read_mostly;
-module_param(bytes_reclaimed_regions, ulong, 0400);
-
-/*
- * Number of times that the time/space quota limits have exceeded
- */
-static unsigned long nr_quota_exceeds __read_mostly;
-module_param(nr_quota_exceeds, ulong, 0400);
+static struct damos_stat damon_reclaim_stat;
+DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_reclaim_stat,
+		reclaim_tried_regions, reclaimed_regions, quota_exceeds);
 
 static struct damon_ctx *ctx;
 static struct damon_target *target;
 
-struct damon_reclaim_ram_walk_arg {
-	unsigned long start;
-	unsigned long end;
-};
-
-static int walk_system_ram(struct resource *res, void *arg)
-{
-	struct damon_reclaim_ram_walk_arg *a = arg;
-
-	if (a->end - a->start < resource_size(res)) {
-		a->start = res->start;
-		a->end = res->end;
-	}
-	return 0;
-}
-
-/*
- * Find biggest 'System RAM' resource and store its start and end address in
- * @start and @end, respectively.  If no System RAM is found, returns false.
- */
-static bool get_monitoring_region(unsigned long *start, unsigned long *end)
-{
-	struct damon_reclaim_ram_walk_arg arg = {};
-
-	walk_system_ram_res(0, ULONG_MAX, &arg, walk_system_ram);
-	if (arg.end <= arg.start)
-		return false;
-
-	*start = arg.start;
-	*end = arg.end;
-	return true;
-}
-
 static struct damos *damon_reclaim_new_scheme(void)
 {
-	struct damos_watermarks wmarks = {
-		.metric = DAMOS_WMARK_FREE_MEM_RATE,
-		.interval = wmarks_interval,
-		.high = wmarks_high,
-		.mid = wmarks_mid,
-		.low = wmarks_low,
-	};
-	struct damos_quota quota = {
-		/*
-		 * Do not try reclamation for more than quota_ms milliseconds
-		 * or quota_sz bytes within quota_reset_interval_ms.
-		 */
-		.ms = quota_ms,
-		.sz = quota_sz,
-		.reset_interval = quota_reset_interval_ms,
-		/* Within the quota, page out older regions first. */
-		.weight_sz = 0,
-		.weight_nr_accesses = 0,
-		.weight_age = 1
+	struct damos_access_pattern pattern = {
+		/* Find regions having PAGE_SIZE or larger size */
+		.min_sz_region = PAGE_SIZE,
+		.max_sz_region = ULONG_MAX,
+		/* and not accessed at all */
+		.min_nr_accesses = 0,
+		.max_nr_accesses = 0,
+		/* for min_age or more micro-seconds */
+		.min_age_region = min_age /
+			damon_reclaim_mon_attrs.aggr_interval,
+		.max_age_region = UINT_MAX,
 	};
-	struct damos *scheme = damon_new_scheme(
-			/* Find regions having PAGE_SIZE or larger size */
-			PAGE_SIZE, ULONG_MAX,
-			/* and not accessed at all */
-			0, 0,
-			/* for min_age or more micro-seconds, and */
-			min_age / aggr_interval, UINT_MAX,
+
+	return damon_new_scheme(
+			&pattern,
 			/* page out those, as soon as found */
 			DAMOS_PAGEOUT,
 			/* under the quota. */
-			&quota,
+			&damon_reclaim_quota,
 			/* (De)activate this according to the watermarks. */
-			&wmarks);
-
-	return scheme;
+			&damon_reclaim_wmarks);
 }
 
 static int damon_reclaim_apply_parameters(void)
 {
 	struct damos *scheme;
-	struct damon_addr_range addr_range;
 	int err = 0;
 
-	err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0,
-			min_nr_regions, max_nr_regions);
+	err = damon_set_attrs(ctx, &damon_reclaim_mon_attrs);
 	if (err)
 		return err;
 
@@ -316,19 +154,11 @@ static int damon_reclaim_apply_parameters(void)
 	scheme = damon_reclaim_new_scheme();
 	if (!scheme)
 		return -ENOMEM;
-	err = damon_set_schemes(ctx, &scheme, 1);
-	if (err)
-		return err;
+	damon_set_schemes(ctx, &scheme, 1);
 
-	if (monitor_region_start > monitor_region_end)
-		return -EINVAL;
-	if (!monitor_region_start && !monitor_region_end &&
-			!get_monitoring_region(&monitor_region_start,
-				&monitor_region_end))
-		return -EINVAL;
-	addr_range.start = monitor_region_start;
-	addr_range.end = monitor_region_end;
-	return damon_set_regions(target, &addr_range, 1);
+	return damon_set_region_biggest_system_ram_default(target,
+					&monitor_region_start,
+					&monitor_region_end);
 }
 
 static int damon_reclaim_turn(bool on)
@@ -413,13 +243,8 @@ static int damon_reclaim_after_aggregation(struct damon_ctx *c)
 	struct damos *s;
 
 	/* update the stats parameter */
-	damon_for_each_scheme(s, c) {
-		nr_reclaim_tried_regions = s->stat.nr_tried;
-		bytes_reclaim_tried_regions = s->stat.sz_tried;
-		nr_reclaimed_regions = s->stat.nr_applied;
-		bytes_reclaimed_regions = s->stat.sz_applied;
-		nr_quota_exceeds = s->stat.qt_exceeds;
-	}
+	damon_for_each_scheme(s, c)
+		damon_reclaim_stat = s->stat;
 
 	return damon_reclaim_handle_commit_inputs();
 }