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, 172 insertions, 3 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5ffec4370602..e4a0b8bd941c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -40,6 +40,7 @@
 
 #include <linux/cpuidle.h>
 #include <linux/interrupt.h>
+#include <linux/memory-tiers.h>
 #include <linux/mempolicy.h>
 #include <linux/mutex_api.h>
 #include <linux/profile.h>
@@ -1090,6 +1091,12 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
+/* The page with hint page fault latency < threshold in ms is considered hot */
+unsigned int sysctl_numa_balancing_hot_threshold = MSEC_PER_SEC;
+
+/* Restrict the NUMA promotion throughput (MB/s) for each target node. */
+unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
+
 struct numa_group {
 	refcount_t refcount;
 
@@ -1432,6 +1439,120 @@ static inline unsigned long group_weight(struct task_struct *p, int nid,
 	return 1000 * faults / total_faults;
 }
 
+/*
+ * If memory tiering mode is enabled, cpupid of slow memory page is
+ * used to record scan time instead of CPU and PID.  When tiering mode
+ * is disabled at run time, the scan time (in cpupid) will be
+ * interpreted as CPU and PID.  So CPU needs to be checked to avoid to
+ * access out of array bound.
+ */
+static inline bool cpupid_valid(int cpupid)
+{
+	return cpupid_to_cpu(cpupid) < nr_cpu_ids;
+}
+
+/*
+ * For memory tiering mode, if there are enough free pages (more than
+ * enough watermark defined here) in fast memory node, to take full
+ * advantage of fast memory capacity, all recently accessed slow
+ * memory pages will be migrated to fast memory node without
+ * considering hot threshold.
+ */
+static bool pgdat_free_space_enough(struct pglist_data *pgdat)
+{
+	int z;
+	unsigned long enough_wmark;
+
+	enough_wmark = max(1UL * 1024 * 1024 * 1024 >> PAGE_SHIFT,
+			   pgdat->node_present_pages >> 4);
+	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
+		struct zone *zone = pgdat->node_zones + z;
+
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone_watermark_ok(zone, 0,
+				      wmark_pages(zone, WMARK_PROMO) + enough_wmark,
+				      ZONE_MOVABLE, 0))
+			return true;
+	}
+	return false;
+}
+
+/*
+ * For memory tiering mode, when page tables are scanned, the scan
+ * time will be recorded in struct page in addition to make page
+ * PROT_NONE for slow memory page.  So when the page is accessed, in
+ * hint page fault handler, the hint page fault latency is calculated
+ * via,
+ *
+ *	hint page fault latency = hint page fault time - scan time
+ *
+ * The smaller the hint page fault latency, the higher the possibility
+ * for the page to be hot.
+ */
+static int numa_hint_fault_latency(struct page *page)
+{
+	int last_time, time;
+
+	time = jiffies_to_msecs(jiffies);
+	last_time = xchg_page_access_time(page, time);
+
+	return (time - last_time) & PAGE_ACCESS_TIME_MASK;
+}
+
+/*
+ * For memory tiering mode, too high promotion/demotion throughput may
+ * hurt application latency.  So we provide a mechanism to rate limit
+ * the number of pages that are tried to be promoted.
+ */
+static bool numa_promotion_rate_limit(struct pglist_data *pgdat,
+				      unsigned long rate_limit, int nr)
+{
+	unsigned long nr_cand;
+	unsigned int now, start;
+
+	now = jiffies_to_msecs(jiffies);
+	mod_node_page_state(pgdat, PGPROMOTE_CANDIDATE, nr);
+	nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+	start = pgdat->nbp_rl_start;
+	if (now - start > MSEC_PER_SEC &&
+	    cmpxchg(&pgdat->nbp_rl_start, start, now) == start)
+		pgdat->nbp_rl_nr_cand = nr_cand;
+	if (nr_cand - pgdat->nbp_rl_nr_cand >= rate_limit)
+		return true;
+	return false;
+}
+
+#define NUMA_MIGRATION_ADJUST_STEPS	16
+
+static void numa_promotion_adjust_threshold(struct pglist_data *pgdat,
+					    unsigned long rate_limit,
+					    unsigned int ref_th)
+{
+	unsigned int now, start, th_period, unit_th, th;
+	unsigned long nr_cand, ref_cand, diff_cand;
+
+	now = jiffies_to_msecs(jiffies);
+	th_period = sysctl_numa_balancing_scan_period_max;
+	start = pgdat->nbp_th_start;
+	if (now - start > th_period &&
+	    cmpxchg(&pgdat->nbp_th_start, start, now) == start) {
+		ref_cand = rate_limit *
+			sysctl_numa_balancing_scan_period_max / MSEC_PER_SEC;
+		nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+		diff_cand = nr_cand - pgdat->nbp_th_nr_cand;
+		unit_th = ref_th * 2 / NUMA_MIGRATION_ADJUST_STEPS;
+		th = pgdat->nbp_threshold ? : ref_th;
+		if (diff_cand > ref_cand * 11 / 10)
+			th = max(th - unit_th, unit_th);
+		else if (diff_cand < ref_cand * 9 / 10)
+			th = min(th + unit_th, ref_th * 2);
+		pgdat->nbp_th_nr_cand = nr_cand;
+		pgdat->nbp_threshold = th;
+	}
+}
+
 bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 				int src_nid, int dst_cpu)
 {
@@ -1439,9 +1560,44 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 	int dst_nid = cpu_to_node(dst_cpu);
 	int last_cpupid, this_cpupid;
 
+	/*
+	 * The pages in slow memory node should be migrated according
+	 * to hot/cold instead of private/shared.
+	 */
+	if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
+	    !node_is_toptier(src_nid)) {
+		struct pglist_data *pgdat;
+		unsigned long rate_limit;
+		unsigned int latency, th, def_th;
+
+		pgdat = NODE_DATA(dst_nid);
+		if (pgdat_free_space_enough(pgdat)) {
+			/* workload changed, reset hot threshold */
+			pgdat->nbp_threshold = 0;
+			return true;
+		}
+
+		def_th = sysctl_numa_balancing_hot_threshold;
+		rate_limit = sysctl_numa_balancing_promote_rate_limit << \
+			(20 - PAGE_SHIFT);
+		numa_promotion_adjust_threshold(pgdat, rate_limit, def_th);
+
+		th = pgdat->nbp_threshold ? : def_th;
+		latency = numa_hint_fault_latency(page);
+		if (latency >= th)
+			return false;
+
+		return !numa_promotion_rate_limit(pgdat, rate_limit,
+						  thp_nr_pages(page));
+	}
+
 	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
 	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
 
+	if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
+	    !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))
+		return false;
+
 	/*
 	 * Allow first faults or private faults to migrate immediately early in
 	 * the lifetime of a task. The magic number 4 is based on waiting for
@@ -2681,6 +2837,15 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	if (!p->mm)
 		return;
 
+	/*
+	 * NUMA faults statistics are unnecessary for the slow memory
+	 * node for memory tiering mode.
+	 */
+	if (!node_is_toptier(mem_node) &&
+	    (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ||
+	     !cpupid_valid(last_cpupid)))
+		return;
+
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults)) {
 		int size = sizeof(*p->numa_faults) *
@@ -2761,6 +2926,7 @@ static void task_numa_work(struct callback_head *work)
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
 	u64 runtime = p->se.sum_exec_runtime;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 	struct vm_area_struct *vma;
 	unsigned long start, end;
 	unsigned long nr_pte_updates = 0;
@@ -2817,13 +2983,16 @@ static void task_numa_work(struct callback_head *work)
 
 	if (!mmap_read_trylock(mm))
 		return;
-	vma = find_vma(mm, start);
+	mas_set(&mas, start);
+	vma = mas_find(&mas, ULONG_MAX);
 	if (!vma) {
 		reset_ptenuma_scan(p);
 		start = 0;
-		vma = mm->mmap;
+		mas_set(&mas, start);
+		vma = mas_find(&mas, ULONG_MAX);
 	}
-	for (; vma; vma = vma->vm_next) {
+
+	for (; vma; vma = mas_find(&mas, ULONG_MAX)) {
 		if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
 			is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
 			continue;