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
  ...

4 files changed, 100 insertions, 63 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 2d9429bf51fa..9e479d7d202b 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2350,6 +2350,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	GENRADIX(struct map_files_info) fa;
 	struct map_files_info *p;
 	int ret;
+	struct vma_iterator vmi;
 
 	genradix_init(&fa);
 
@@ -2388,7 +2389,9 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	 * routine might require mmap_lock taken in might_fault().
 	 */
 
-	for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
+	pos = 2;
+	vma_iter_init(&vmi, mm, 0);
+	for_each_vma(vmi, vma) {
 		if (!vma->vm_file)
 			continue;
 		if (++pos <= ctx->pos)
@@ -3196,6 +3199,19 @@ static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *
 
 	return 0;
 }
+static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm;
+
+	mm = get_task_mm(task);
+	if (mm) {
+		seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
+		mmput(mm);
+	}
+
+	return 0;
+}
 #endif /* CONFIG_KSM */
 
 #ifdef CONFIG_STACKLEAK_METRICS
@@ -3331,6 +3347,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 #ifdef CONFIG_KSM
 	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
+	ONE("ksm_stat",  S_IRUSR, proc_pid_ksm_stat),
 #endif
 };
 
@@ -3668,6 +3685,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #endif
 #ifdef CONFIG_KSM
 	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
+	ONE("ksm_stat",  S_IRUSR, proc_pid_ksm_stat),
 #endif
 };
 
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 06a80f78433d..f03000764ce5 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -285,7 +285,7 @@ struct proc_maps_private {
 	struct task_struct *task;
 	struct mm_struct *mm;
 #ifdef CONFIG_MMU
-	struct vm_area_struct *tail_vma;
+	struct vma_iterator iter;
 #endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *task_mempolicy;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4e0023643f8b..8b4f3073f8f5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/pagewalk.h>
-#include <linux/vmacache.h>
 #include <linux/mm_inline.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
@@ -124,12 +123,26 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
+static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
+						loff_t *ppos)
+{
+	struct vm_area_struct *vma = vma_next(&priv->iter);
+
+	if (vma) {
+		*ppos = vma->vm_start;
+	} else {
+		*ppos = -2UL;
+		vma = get_gate_vma(priv->mm);
+	}
+
+	return vma;
+}
+
 static void *m_start(struct seq_file *m, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
 	unsigned long last_addr = *ppos;
 	struct mm_struct *mm;
-	struct vm_area_struct *vma;
 
 	/* See m_next(). Zero at the start or after lseek. */
 	if (last_addr == -1UL)
@@ -153,31 +166,21 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 		return ERR_PTR(-EINTR);
 	}
 
+	vma_iter_init(&priv->iter, mm, last_addr);
 	hold_task_mempolicy(priv);
-	priv->tail_vma = get_gate_vma(mm);
-
-	vma = find_vma(mm, last_addr);
-	if (vma)
-		return vma;
+	if (last_addr == -2UL)
+		return get_gate_vma(mm);
 
-	return priv->tail_vma;
+	return proc_get_vma(priv, ppos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
 {
-	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *next, *vma = v;
-
-	if (vma == priv->tail_vma)
-		next = NULL;
-	else if (vma->vm_next)
-		next = vma->vm_next;
-	else
-		next = priv->tail_vma;
-
-	*ppos = next ? next->vm_start : -1UL;
-
-	return next;
+	if (*ppos == -2UL) {
+		*ppos = -1UL;
+		return NULL;
+	}
+	return proc_get_vma(m->private, ppos);
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -864,7 +867,7 @@ static int show_smap(struct seq_file *m, void *v)
 	__show_smap(m, &mss, false);
 
 	seq_printf(m, "THPeligible:    %d\n",
-		   hugepage_vma_check(vma, vma->vm_flags, true, false));
+		   hugepage_vma_check(vma, vma->vm_flags, true, false, true));
 
 	if (arch_pkeys_enabled())
 		seq_printf(m, "ProtectionKey:  %8u\n", vma_pkey(vma));
@@ -877,16 +880,16 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
 	struct mem_size_stats mss;
-	struct mm_struct *mm;
+	struct mm_struct *mm = priv->mm;
 	struct vm_area_struct *vma;
-	unsigned long last_vma_end = 0;
+	unsigned long vma_start = 0, last_vma_end = 0;
 	int ret = 0;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	priv->task = get_proc_task(priv->inode);
 	if (!priv->task)
 		return -ESRCH;
 
-	mm = priv->mm;
 	if (!mm || !mmget_not_zero(mm)) {
 		ret = -ESRCH;
 		goto out_put_task;
@@ -899,8 +902,13 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 		goto out_put_mm;
 
 	hold_task_mempolicy(priv);
+	vma = mas_find(&mas, 0);
+
+	if (unlikely(!vma))
+		goto empty_set;
 
-	for (vma = priv->mm->mmap; vma;) {
+	vma_start = vma->vm_start;
+	do {
 		smap_gather_stats(vma, &mss, 0);
 		last_vma_end = vma->vm_end;
 
@@ -909,6 +917,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 		 * access it for write request.
 		 */
 		if (mmap_lock_is_contended(mm)) {
+			mas_pause(&mas);
 			mmap_read_unlock(mm);
 			ret = mmap_read_lock_killable(mm);
 			if (ret) {
@@ -952,7 +961,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 			 *    contains last_vma_end.
 			 *    Iterate VMA' from last_vma_end.
 			 */
-			vma = find_vma(mm, last_vma_end - 1);
+			vma = mas_find(&mas, ULONG_MAX);
 			/* Case 3 above */
 			if (!vma)
 				break;
@@ -966,11 +975,10 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 				smap_gather_stats(vma, &mss, last_vma_end);
 		}
 		/* Case 2 above */
-		vma = vma->vm_next;
-	}
+	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
 
-	show_vma_header_prefix(m, priv->mm->mmap->vm_start,
-			       last_vma_end, 0, 0, 0, 0);
+empty_set:
+	show_vma_header_prefix(m, vma_start, last_vma_end, 0, 0, 0, 0);
 	seq_pad(m, ' ');
 	seq_puts(m, "[rollup]\n");
 
@@ -1263,6 +1271,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		return -ESRCH;
 	mm = get_task_mm(task);
 	if (mm) {
+		MA_STATE(mas, &mm->mm_mt, 0, 0);
 		struct mmu_notifier_range range;
 		struct clear_refs_private cp = {
 			.type = type,
@@ -1282,7 +1291,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		}
 
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
-			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			mas_for_each(&mas, vma, ULONG_MAX) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
 					continue;
 				vma->vm_flags &= ~VM_SOFTDIRTY;
@@ -1294,8 +1303,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 						0, NULL, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
-		walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops,
-				&cp);
+		walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
 			flush_tlb_mm(mm);
@@ -1418,9 +1426,19 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		if (pte_swp_uffd_wp(pte))
 			flags |= PM_UFFD_WP;
 		entry = pte_to_swp_entry(pte);
-		if (pm->show_pfn)
+		if (pm->show_pfn) {
+			pgoff_t offset;
+			/*
+			 * For PFN swap offsets, keeping the offset field
+			 * to be PFN only to be compatible with old smaps.
+			 */
+			if (is_pfn_swap_entry(entry))
+				offset = swp_offset_pfn(entry);
+			else
+				offset = swp_offset(entry);
 			frame = swp_type(entry) |
-				(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+			    (offset << MAX_SWAPFILES_SHIFT);
+		}
 		flags |= PM_SWAP;
 		migration = is_migration_entry(entry);
 		if (is_pfn_swap_entry(entry))
@@ -1477,7 +1495,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			unsigned long offset;
 
 			if (pm->show_pfn) {
-				offset = swp_offset(entry) +
+				if (is_pfn_swap_entry(entry))
+					offset = swp_offset_pfn(entry);
+				else
+					offset = swp_offset(entry);
+				offset = offset +
 					((addr & ~PMD_MASK) >> PAGE_SHIFT);
 				frame = swp_type(entry) |
 					(offset << MAX_SWAPFILES_SHIFT);
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index a6d21fc0033c..2fd06f52b6a4 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -20,15 +20,13 @@
  */
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 	struct vm_region *region;
-	struct rb_node *p;
 	unsigned long bytes = 0, sbytes = 0, slack = 0, size;
-        
-	mmap_read_lock(mm);
-	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
-		vma = rb_entry(p, struct vm_area_struct, vm_rb);
 
+	mmap_read_lock(mm);
+	for_each_vma(vmi, vma) {
 		bytes += kobjsize(vma);
 
 		region = vma->vm_region;
@@ -82,15 +80,13 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 
 unsigned long task_vsize(struct mm_struct *mm)
 {
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
-	struct rb_node *p;
 	unsigned long vsize = 0;
 
 	mmap_read_lock(mm);
-	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
-		vma = rb_entry(p, struct vm_area_struct, vm_rb);
+	for_each_vma(vmi, vma)
 		vsize += vma->vm_end - vma->vm_start;
-	}
 	mmap_read_unlock(mm);
 	return vsize;
 }
@@ -99,14 +95,13 @@ unsigned long task_statm(struct mm_struct *mm,
 			 unsigned long *shared, unsigned long *text,
 			 unsigned long *data, unsigned long *resident)
 {
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 	struct vm_region *region;
-	struct rb_node *p;
 	unsigned long size = kobjsize(mm);
 
 	mmap_read_lock(mm);
-	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
-		vma = rb_entry(p, struct vm_area_struct, vm_rb);
+	for_each_vma(vmi, vma) {
 		size += kobjsize(vma);
 		region = vma->vm_region;
 		if (region) {
@@ -190,17 +185,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
  */
 static int show_map(struct seq_file *m, void *_p)
 {
-	struct rb_node *p = _p;
-
-	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
+	return nommu_vma_show(m, _p);
 }
 
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_maps_private *priv = m->private;
 	struct mm_struct *mm;
-	struct rb_node *p;
-	loff_t n = *pos;
+	struct vm_area_struct *vma;
+	unsigned long addr = *pos;
+
+	/* See m_next(). Zero at the start or after lseek. */
+	if (addr == -1UL)
+		return NULL;
 
 	/* pin the task and mm whilst we play with them */
 	priv->task = get_proc_task(priv->inode);
@@ -216,10 +213,10 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 		return ERR_PTR(-EINTR);
 	}
 
-	/* start from the Nth VMA */
-	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
-		if (n-- == 0)
-			return p;
+	/* start the next element from addr */
+	vma = find_vma(mm, addr);
+	if (vma)
+		return vma;
 
 	mmap_read_unlock(mm);
 	mmput(mm);
@@ -242,10 +239,10 @@ static void m_stop(struct seq_file *m, void *_vml)
 
 static void *m_next(struct seq_file *m, void *_p, loff_t *pos)
 {
-	struct rb_node *p = _p;
+	struct vm_area_struct *vma = _p;
 
-	(*pos)++;
-	return p ? rb_next(p) : NULL;
+	*pos = vma->vm_end;
+	return find_vma(vma->vm_mm, vma->vm_end);
 }
 
 static const struct seq_operations proc_pid_maps_ops = {