1 files changed, 313 insertions, 199 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3ba9ae83bff5..8a74cdcc9af0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,6 +1,6 @@
 // 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>
 #include <linux/mount.h>
@@ -123,38 +123,28 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
-static void vma_stop(struct proc_maps_private *priv)
+static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
+						loff_t *ppos)
 {
-	struct mm_struct *mm = priv->mm;
-
-	release_task_mempolicy(priv);
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-}
+	struct vm_area_struct *vma = vma_next(&priv->iter);
 
-static struct vm_area_struct *
-m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma)
-{
-	if (vma == priv->tail_vma)
-		return NULL;
-	return vma->vm_next ?: priv->tail_vma;
-}
+	if (vma) {
+		*ppos = vma->vm_start;
+	} else {
+		*ppos = -2UL;
+		vma = get_gate_vma(priv->mm);
+	}
 
-static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma)
-{
-	if (m->count < m->size)	/* vma is copied successfully */
-		m->version = m_next_vma(m->private, vma) ? vma->vm_end : -1UL;
+	return vma;
 }
 
 static void *m_start(struct seq_file *m, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
-	unsigned long last_addr = m->version;
+	unsigned long last_addr = *ppos;
 	struct mm_struct *mm;
-	struct vm_area_struct *vma;
-	unsigned int pos = *ppos;
 
-	/* See m_cache_vma(). Zero at the start or after lseek. */
+	/* See m_next(). Zero at the start or after lseek. */
 	if (last_addr == -1UL)
 		return NULL;
 
@@ -163,64 +153,49 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 		return ERR_PTR(-ESRCH);
 
 	mm = priv->mm;
-	if (!mm || !mmget_not_zero(mm))
+	if (!mm || !mmget_not_zero(mm)) {
+		put_task_struct(priv->task);
+		priv->task = NULL;
 		return NULL;
+	}
 
-	if (down_read_killable(&mm->mmap_sem)) {
+	if (mmap_read_lock_killable(mm)) {
 		mmput(mm);
+		put_task_struct(priv->task);
+		priv->task = NULL;
 		return ERR_PTR(-EINTR);
 	}
 
+	vma_iter_init(&priv->iter, mm, last_addr);
 	hold_task_mempolicy(priv);
-	priv->tail_vma = get_gate_vma(mm);
-
-	if (last_addr) {
-		vma = find_vma(mm, last_addr - 1);
-		if (vma && vma->vm_start <= last_addr)
-			vma = m_next_vma(priv, vma);
-		if (vma)
-			return vma;
-	}
-
-	m->version = 0;
-	if (pos < mm->map_count) {
-		for (vma = mm->mmap; pos; pos--) {
-			m->version = vma->vm_start;
-			vma = vma->vm_next;
-		}
-		return vma;
-	}
+	if (last_addr == -2UL)
+		return get_gate_vma(mm);
 
-	/* we do not bother to update m->version in this case */
-	if (pos == mm->map_count && priv->tail_vma)
-		return priv->tail_vma;
-
-	vma_stop(priv);
-	return NULL;
+	return proc_get_vma(priv, ppos);
 }
 
-static void *m_next(struct seq_file *m, void *v, loff_t *pos)
+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;
-
-	(*pos)++;
-	next = m_next_vma(priv, v);
-	if (!next)
-		vma_stop(priv);
-	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)
 {
 	struct proc_maps_private *priv = m->private;
+	struct mm_struct *mm = priv->mm;
 
-	if (!IS_ERR_OR_NULL(v))
-		vma_stop(priv);
-	if (priv->task) {
-		put_task_struct(priv->task);
-		priv->task = NULL;
-	}
+	if (!priv->task)
+		return;
+
+	release_task_mempolicy(priv);
+	mmap_read_unlock(mm);
+	mmput(mm);
+	put_task_struct(priv->task);
+	priv->task = NULL;
 }
 
 static int proc_maps_open(struct inode *inode, struct file *file,
@@ -337,6 +312,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 
 	name = arch_vma_name(vma);
 	if (!name) {
+		struct anon_vma_name *anon_name;
+
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -348,8 +325,16 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 			goto done;
 		}
 
-		if (is_stack(vma))
+		if (is_stack(vma)) {
 			name = "[stack]";
+			goto done;
+		}
+
+		anon_name = anon_vma_name(vma);
+		if (anon_name) {
+			seq_pad(m, ' ');
+			seq_printf(m, "[anon:%s]", anon_name->name);
+		}
 	}
 
 done:
@@ -363,7 +348,6 @@ done:
 static int show_map(struct seq_file *m, void *v)
 {
 	show_map_vma(m, v);
-	m_cache_vma(m, v);
 	return 0;
 }
 
@@ -425,9 +409,9 @@ struct mem_size_stats {
 	u64 pss_anon;
 	u64 pss_file;
 	u64 pss_shmem;
+	u64 pss_dirty;
 	u64 pss_locked;
 	u64 swap_pss;
-	bool check_shmem_swap;
 };
 
 static void smaps_page_accumulate(struct mem_size_stats *mss,
@@ -447,6 +431,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss,
 		mss->pss_locked += pss;
 
 	if (dirty || PageDirty(page)) {
+		mss->pss_dirty += pss;
 		if (private)
 			mss->private_dirty += size;
 		else
@@ -460,7 +445,8 @@ static void smaps_page_accumulate(struct mem_size_stats *mss,
 }
 
 static void smaps_account(struct mem_size_stats *mss, struct page *page,
-		bool compound, bool young, bool dirty, bool locked)
+		bool compound, bool young, bool dirty, bool locked,
+		bool migration)
 {
 	int i, nr = compound ? compound_nr(page) : 1;
 	unsigned long size = nr * PAGE_SIZE;
@@ -487,8 +473,15 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	 * page_count(page) == 1 guarantees the page is mapped exactly once.
 	 * If any subpage of the compound page mapped with PTE it would elevate
 	 * page_count().
+	 *
+	 * The page_mapcount() is called to get a snapshot of the mapcount.
+	 * Without holding the page lock this snapshot can be slightly wrong as
+	 * we cannot always read the mapcount atomically.  It is not safe to
+	 * call page_mapcount() even with PTL held if the page is not mapped,
+	 * especially for migration entries.  Treat regular migration entries
+	 * as mapcount == 1.
 	 */
-	if (page_count(page) == 1) {
+	if ((page_count(page) == 1) || migration) {
 		smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty,
 			locked, true);
 		return;
@@ -508,9 +501,11 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
 			  __always_unused int depth, struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 
-	mss->swap += shmem_partial_swap_usage(
-			walk->vma->vm_file->f_mapping, addr, end);
+	mss->swap += shmem_partial_swap_usage(walk->vma->vm_file->f_mapping,
+					      linear_page_index(vma, addr),
+					      linear_page_index(vma, end));
 
 	return 0;
 }
@@ -518,6 +513,16 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
 #define smaps_pte_hole		NULL
 #endif /* CONFIG_SHMEM */
 
+static void smaps_pte_hole_lookup(unsigned long addr, struct mm_walk *walk)
+{
+#ifdef CONFIG_SHMEM
+	if (walk->ops->pte_hole) {
+		/* depth is not used */
+		smaps_pte_hole(addr, addr + PAGE_SIZE, 0, walk);
+	}
+#endif
+}
+
 static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
 {
@@ -525,9 +530,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
+	bool migration = false, young = false, dirty = false;
 
 	if (pte_present(*pte)) {
 		page = vm_normal_page(vma, addr, *pte);
+		young = pte_young(*pte);
+		dirty = pte_dirty(*pte);
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
@@ -544,29 +552,20 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 			} else {
 				mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
 			}
-		} else if (is_migration_entry(swpent))
-			page = migration_entry_to_page(swpent);
-		else if (is_device_private_entry(swpent))
-			page = device_private_entry_to_page(swpent);
-	} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
-							&& pte_none(*pte))) {
-		page = find_get_entry(vma->vm_file->f_mapping,
-						linear_page_index(vma, addr));
-		if (!page)
-			return;
-
-		if (xa_is_value(page))
-			mss->swap += PAGE_SIZE;
-		else
-			put_page(page);
-
+		} else if (is_pfn_swap_entry(swpent)) {
+			if (is_migration_entry(swpent))
+				migration = true;
+			page = pfn_swap_entry_to_page(swpent);
+		}
+	} else {
+		smaps_pte_hole_lookup(addr, walk);
 		return;
 	}
 
 	if (!page)
 		return;
 
-	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked);
+	smaps_account(mss, page, false, young, dirty, locked, migration);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -576,10 +575,20 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
-	struct page *page;
+	struct page *page = NULL;
+	bool migration = false;
+
+	if (pmd_present(*pmd)) {
+		/* FOLL_DUMP will return -EFAULT on huge zero page */
+		page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+	} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
+		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
-	/* FOLL_DUMP will return -EFAULT on huge zero page */
-	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+		if (is_migration_entry(entry)) {
+			migration = true;
+			page = pfn_swap_entry_to_page(entry);
+		}
+	}
 	if (IS_ERR_OR_NULL(page))
 		return;
 	if (PageAnon(page))
@@ -590,7 +599,9 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 		/* pass */;
 	else
 		mss->file_thp += HPAGE_PMD_SIZE;
-	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked);
+
+	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd),
+		      locked, migration);
 }
 #else
 static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -608,8 +619,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
-		if (pmd_present(*pmd))
-			smaps_pmd_entry(pmd, addr, walk);
+		smaps_pmd_entry(pmd, addr, walk);
 		spin_unlock(ptl);
 		goto out;
 	}
@@ -617,7 +627,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	if (pmd_trans_unstable(pmd))
 		goto out;
 	/*
-	 * The mmap_sem held all the way back in m_start() is what
+	 * The mmap_lock held all the way back in m_start() is what
 	 * keeps khugepaged out of here and from collapsing things
 	 * in here.
 	 */
@@ -651,10 +661,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MAYSHARE)]	= "ms",
 		[ilog2(VM_GROWSDOWN)]	= "gd",
 		[ilog2(VM_PFNMAP)]	= "pf",
-		[ilog2(VM_DENYWRITE)]	= "dw",
-#ifdef CONFIG_X86_INTEL_MPX
-		[ilog2(VM_MPX)]		= "mp",
-#endif
 		[ilog2(VM_LOCKED)]	= "lo",
 		[ilog2(VM_IO)]		= "io",
 		[ilog2(VM_SEQ_READ)]	= "sr",
@@ -668,6 +674,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_ARCH_1)]	= "ar",
 		[ilog2(VM_WIPEONFORK)]	= "wf",
 		[ilog2(VM_DONTDUMP)]	= "dd",
+#ifdef CONFIG_ARM64_BTI
+		[ilog2(VM_ARM64_BTI)]	= "bt",
+#endif
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		[ilog2(VM_SOFTDIRTY)]	= "sd",
 #endif
@@ -677,6 +686,10 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MERGEABLE)]	= "mg",
 		[ilog2(VM_UFFD_MISSING)]= "um",
 		[ilog2(VM_UFFD_WP)]	= "uw",
+#ifdef CONFIG_ARM64_MTE
+		[ilog2(VM_MTE)]		= "mt",
+		[ilog2(VM_MTE_ALLOWED)]	= "",
+#endif
 #ifdef CONFIG_ARCH_HAS_PKEYS
 		/* These come out via ProtectionKey: */
 		[ilog2(VM_PKEY_BIT0)]	= "",
@@ -687,6 +700,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_PKEY_BIT4)]	= "",
 #endif
 #endif /* CONFIG_ARCH_HAS_PKEYS */
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+		[ilog2(VM_UFFD_MINOR)]	= "ui",
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
 	};
 	size_t i;
 
@@ -717,10 +733,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
-		if (is_migration_entry(swpent))
-			page = migration_entry_to_page(swpent);
-		else if (is_device_private_entry(swpent))
-			page = device_private_entry_to_page(swpent);
+		if (is_pfn_swap_entry(swpent))
+			page = pfn_swap_entry_to_page(swpent);
 	}
 	if (page) {
 		int mapcount = page_mapcount(page);
@@ -747,12 +761,22 @@ static const struct mm_walk_ops smaps_shmem_walk_ops = {
 	.pte_hole		= smaps_pte_hole,
 };
 
+/*
+ * Gather mem stats from @vma with the indicated beginning
+ * address @start, and keep them in @mss.
+ *
+ * Use vm_start of @vma as the beginning address if @start is 0.
+ */
 static void smap_gather_stats(struct vm_area_struct *vma,
-			     struct mem_size_stats *mss)
+		struct mem_size_stats *mss, unsigned long start)
 {
+	const struct mm_walk_ops *ops = &smaps_walk_ops;
+
+	/* Invalid start */
+	if (start >= vma->vm_end)
+		return;
+
 #ifdef CONFIG_SHMEM
-	/* In case of smaps_rollup, reset the value from previous vma */
-	mss->check_shmem_swap = false;
 	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
 		/*
 		 * For shared or readonly shmem mappings we know that all
@@ -766,18 +790,19 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 		 */
 		unsigned long shmem_swapped = shmem_swap_usage(vma);
 
-		if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
-					!(vma->vm_flags & VM_WRITE)) {
+		if (!start && (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
+					!(vma->vm_flags & VM_WRITE))) {
 			mss->swap += shmem_swapped;
 		} else {
-			mss->check_shmem_swap = true;
-			walk_page_vma(vma, &smaps_shmem_walk_ops, mss);
-			return;
+			ops = &smaps_shmem_walk_ops;
 		}
 	}
 #endif
-	/* mmap_sem is held in m_start */
-	walk_page_vma(vma, &smaps_walk_ops, mss);
+	/* mmap_lock is held in m_start */
+	if (!start)
+		walk_page_vma(vma, ops, mss);
+	else
+		walk_page_range(vma->vm_mm, start, vma->vm_end, ops, mss);
 }
 
 #define SEQ_PUT_DEC(str, val) \
@@ -789,6 +814,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss,
 {
 	SEQ_PUT_DEC("Rss:            ", mss->resident);
 	SEQ_PUT_DEC(" kB\nPss:            ", mss->pss >> PSS_SHIFT);
+	SEQ_PUT_DEC(" kB\nPss_Dirty:      ", mss->pss_dirty >> PSS_SHIFT);
 	if (rollup_mode) {
 		/*
 		 * These are meaningful only for smaps_rollup, otherwise two of
@@ -810,7 +836,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss,
 	SEQ_PUT_DEC(" kB\nLazyFree:       ", mss->lazyfree);
 	SEQ_PUT_DEC(" kB\nAnonHugePages:  ", mss->anonymous_thp);
 	SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp);
-	SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp);
+	SEQ_PUT_DEC(" kB\nFilePmdMapped:  ", mss->file_thp);
 	SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb);
 	seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ",
 				  mss->private_hugetlb >> 10, 7);
@@ -829,7 +855,7 @@ static int show_smap(struct seq_file *m, void *v)
 
 	memset(&mss, 0, sizeof(mss));
 
-	smap_gather_stats(vma, &mss);
+	smap_gather_stats(vma, &mss, 0);
 
 	show_map_vma(m, vma);
 
@@ -840,15 +866,13 @@ static int show_smap(struct seq_file *m, void *v)
 
 	__show_smap(m, &mss, false);
 
-	seq_printf(m, "THPeligible:		%d\n",
-		   transparent_hugepage_enabled(vma));
+	seq_printf(m, "THPeligible:    %d\n",
+		   hugepage_vma_check(vma, vma->vm_flags, true, false, true));
 
 	if (arch_pkeys_enabled())
 		seq_printf(m, "ProtectionKey:  %8u\n", vma_pkey(vma));
 	show_smap_vma_flags(m, vma);
 
-	m_cache_vma(m, vma);
-
 	return 0;
 }
 
@@ -856,16 +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;
@@ -873,26 +897,95 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 
 	memset(&mss, 0, sizeof(mss));
 
-	ret = down_read_killable(&mm->mmap_sem);
+	ret = mmap_read_lock_killable(mm);
 	if (ret)
 		goto out_put_mm;
 
 	hold_task_mempolicy(priv);
+	vma = mas_find(&mas, ULONG_MAX);
+
+	if (unlikely(!vma))
+		goto empty_set;
 
-	for (vma = priv->mm->mmap; vma; vma = vma->vm_next) {
-		smap_gather_stats(vma, &mss);
+	vma_start = vma->vm_start;
+	do {
+		smap_gather_stats(vma, &mss, 0);
 		last_vma_end = vma->vm_end;
-	}
 
-	show_vma_header_prefix(m, priv->mm->mmap->vm_start,
-			       last_vma_end, 0, 0, 0, 0);
+		/*
+		 * Release mmap_lock temporarily if someone wants to
+		 * 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) {
+				release_task_mempolicy(priv);
+				goto out_put_mm;
+			}
+
+			/*
+			 * After dropping the lock, there are four cases to
+			 * consider. See the following example for explanation.
+			 *
+			 *   +------+------+-----------+
+			 *   | VMA1 | VMA2 | VMA3      |
+			 *   +------+------+-----------+
+			 *   |      |      |           |
+			 *  4k     8k     16k         400k
+			 *
+			 * Suppose we drop the lock after reading VMA2 due to
+			 * contention, then we get:
+			 *
+			 *	last_vma_end = 16k
+			 *
+			 * 1) VMA2 is freed, but VMA3 exists:
+			 *
+			 *    find_vma(mm, 16k - 1) will return VMA3.
+			 *    In this case, just continue from VMA3.
+			 *
+			 * 2) VMA2 still exists:
+			 *
+			 *    find_vma(mm, 16k - 1) will return VMA2.
+			 *    Iterate the loop like the original one.
+			 *
+			 * 3) No more VMAs can be found:
+			 *
+			 *    find_vma(mm, 16k - 1) will return NULL.
+			 *    No more things to do, just break.
+			 *
+			 * 4) (last_vma_end - 1) is the middle of a vma (VMA'):
+			 *
+			 *    find_vma(mm, 16k - 1) will return VMA' whose range
+			 *    contains last_vma_end.
+			 *    Iterate VMA' from last_vma_end.
+			 */
+			vma = mas_find(&mas, ULONG_MAX);
+			/* Case 3 above */
+			if (!vma)
+				break;
+
+			/* Case 1 above */
+			if (vma->vm_start >= last_vma_end)
+				continue;
+
+			/* Case 4 above */
+			if (vma->vm_end > last_vma_end)
+				smap_gather_stats(vma, &mss, last_vma_end);
+		}
+		/* Case 2 above */
+	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
+
+empty_set:
+	show_vma_header_prefix(m, vma_start, last_vma_end, 0, 0, 0, 0);
 	seq_pad(m, ' ');
 	seq_puts(m, "[rollup]\n");
 
 	__show_smap(m, &mss, true);
 
 	release_task_mempolicy(priv);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 out_put_mm:
 	mmput(mm);
@@ -985,6 +1078,23 @@ struct clear_refs_private {
 };
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
+
+static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+	struct page *page;
+
+	if (!pte_write(pte))
+		return false;
+	if (!is_cow_mapping(vma->vm_flags))
+		return false;
+	if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)))
+		return false;
+	page = vm_normal_page(vma, addr, pte);
+	if (!page)
+		return false;
+	return page_maybe_dma_pinned(page);
+}
+
 static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *pte)
 {
@@ -999,6 +1109,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	if (pte_present(ptent)) {
 		pte_t old_pte;
 
+		if (pte_is_pinned(vma, addr, ptent))
+			return;
 		old_pte = ptep_modify_prot_start(vma, addr, pte);
 		ptent = pte_wrprotect(old_pte);
 		ptent = pte_clear_soft_dirty(ptent);
@@ -1139,7 +1251,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	enum clear_refs_types type;
-	struct mmu_gather tlb;
 	int itype;
 	int rv;
 
@@ -1160,76 +1271,46 @@ 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,
 		};
 
+		if (mmap_write_lock_killable(mm)) {
+			count = -EINTR;
+			goto out_mm;
+		}
 		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
-			if (down_write_killable(&mm->mmap_sem)) {
-				count = -EINTR;
-				goto out_mm;
-			}
-
 			/*
 			 * Writing 5 to /proc/pid/clear_refs resets the peak
 			 * resident set size to this mm's current rss value.
 			 */
 			reset_mm_hiwater_rss(mm);
-			up_write(&mm->mmap_sem);
-			goto out_mm;
+			goto out_unlock;
 		}
 
-		if (down_read_killable(&mm->mmap_sem)) {
-			count = -EINTR;
-			goto out_mm;
-		}
-		tlb_gather_mmu(&tlb, mm, 0, -1);
 		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;
-				up_read(&mm->mmap_sem);
-				if (down_write_killable(&mm->mmap_sem)) {
-					count = -EINTR;
-					goto out_mm;
-				}
-				/*
-				 * Avoid to modify vma->vm_flags
-				 * without locked ops while the
-				 * coredump reads the vm_flags.
-				 */
-				if (!mmget_still_valid(mm)) {
-					/*
-					 * Silently return "count"
-					 * like if get_task_mm()
-					 * failed. FIXME: should this
-					 * function have returned
-					 * -ESRCH if get_task_mm()
-					 * failed like if
-					 * get_proc_task() fails?
-					 */
-					up_write(&mm->mmap_sem);
-					goto out_mm;
-				}
-				for (vma = mm->mmap; vma; vma = vma->vm_next) {
-					vma->vm_flags &= ~VM_SOFTDIRTY;
-					vma_set_page_prot(vma);
-				}
-				downgrade_write(&mm->mmap_sem);
-				break;
+				vma->vm_flags &= ~VM_SOFTDIRTY;
+				vma_set_page_prot(vma);
 			}
 
+			inc_tlb_flush_pending(mm);
 			mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
 						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);
-		if (type == CLEAR_REFS_SOFT_DIRTY)
+		walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp);
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
-		tlb_finish_mmu(&tlb, 0, -1);
-		up_read(&mm->mmap_sem);
+			flush_tlb_mm(mm);
+			dec_tlb_flush_pending(mm);
+		}
+out_unlock:
+		mmap_write_unlock(mm);
 out_mm:
 		mmput(mm);
 	}
@@ -1261,6 +1342,7 @@ struct pagemapread {
 #define PM_PFRAME_MASK		GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
 #define PM_SOFT_DIRTY		BIT_ULL(55)
 #define PM_MMAP_EXCLUSIVE	BIT_ULL(56)
+#define PM_UFFD_WP		BIT_ULL(57)
 #define PM_FILE			BIT_ULL(61)
 #define PM_SWAP			BIT_ULL(62)
 #define PM_PRESENT		BIT_ULL(63)
@@ -1326,6 +1408,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 {
 	u64 frame = 0, flags = 0;
 	struct page *page = NULL;
+	bool migration = false;
 
 	if (pte_present(pte)) {
 		if (pm->show_pfn)
@@ -1334,25 +1417,39 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		page = vm_normal_page(vma, addr, pte);
 		if (pte_soft_dirty(pte))
 			flags |= PM_SOFT_DIRTY;
+		if (pte_uffd_wp(pte))
+			flags |= PM_UFFD_WP;
 	} else if (is_swap_pte(pte)) {
 		swp_entry_t entry;
 		if (pte_swp_soft_dirty(pte))
 			flags |= PM_SOFT_DIRTY;
+		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;
-		if (is_migration_entry(entry))
-			page = migration_entry_to_page(entry);
-
-		if (is_device_private_entry(entry))
-			page = device_private_entry_to_page(entry);
+		migration = is_migration_entry(entry);
+		if (is_pfn_swap_entry(entry))
+			page = pfn_swap_entry_to_page(entry);
+		if (pte_marker_entry_uffd_wp(entry))
+			flags |= PM_UFFD_WP;
 	}
 
 	if (page && !PageAnon(page))
 		flags |= PM_FILE;
-	if (page && page_mapcount(page) == 1)
+	if (page && !migration && page_mapcount(page) == 1)
 		flags |= PM_MMAP_EXCLUSIVE;
 	if (vma->vm_flags & VM_SOFTDIRTY)
 		flags |= PM_SOFT_DIRTY;
@@ -1368,8 +1465,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 	spinlock_t *ptl;
 	pte_t *pte, *orig_pte;
 	int err = 0;
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	bool migration = false;
+
 	ptl = pmd_trans_huge_lock(pmdp, vma);
 	if (ptl) {
 		u64 flags = 0, frame = 0;
@@ -1385,6 +1483,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			flags |= PM_PRESENT;
 			if (pmd_soft_dirty(pmd))
 				flags |= PM_SOFT_DIRTY;
+			if (pmd_uffd_wp(pmd))
+				flags |= PM_UFFD_WP;
 			if (pm->show_pfn)
 				frame = pmd_pfn(pmd) +
 					((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1395,7 +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);
@@ -1403,12 +1507,15 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			flags |= PM_SWAP;
 			if (pmd_swp_soft_dirty(pmd))
 				flags |= PM_SOFT_DIRTY;
+			if (pmd_swp_uffd_wp(pmd))
+				flags |= PM_UFFD_WP;
 			VM_BUG_ON(!is_pmd_migration_entry(pmd));
-			page = migration_entry_to_page(entry);
+			migration = is_migration_entry(entry);
+			page = pfn_swap_entry_to_page(entry);
 		}
 #endif
 
-		if (page && page_mapcount(page) == 1)
+		if (page && !migration && page_mapcount(page) == 1)
 			flags |= PM_MMAP_EXCLUSIVE;
 
 		for (; addr != end; addr += PAGE_SIZE) {
@@ -1477,10 +1584,15 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
 		if (page_mapcount(page) == 1)
 			flags |= PM_MMAP_EXCLUSIVE;
 
+		if (huge_pte_uffd_wp(pte))
+			flags |= PM_UFFD_WP;
+
 		flags |= PM_PRESENT;
 		if (pm->show_pfn)
 			frame = pte_pfn(pte) +
 				((addr & ~hmask) >> PAGE_SHIFT);
+	} else if (pte_swp_uffd_wp_any(pte)) {
+		flags |= PM_UFFD_WP;
 	}
 
 	for (; addr != end; addr += PAGE_SIZE) {
@@ -1518,7 +1630,8 @@ static const struct mm_walk_ops pagemap_ops = {
  * Bits 5-54  swap offset if swapped
  * Bit  55    pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
  * Bit  56    page exclusively mapped
- * Bits 57-60 zero
+ * Bit  57    pte is uffd-wp write-protected
+ * Bits 58-60 zero
  * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
@@ -1567,11 +1680,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 
 	src = *ppos;
 	svpfn = src / PM_ENTRY_BYTES;
-	start_vaddr = svpfn << PAGE_SHIFT;
 	end_vaddr = mm->task_size;
 
 	/* watch out for wraparound */
-	if (svpfn > mm->task_size >> PAGE_SHIFT)
+	start_vaddr = end_vaddr;
+	if (svpfn <= (ULONG_MAX >> PAGE_SHIFT))
+		start_vaddr = untagged_addr(svpfn << PAGE_SHIFT);
+
+	/* Ensure the address is inside the task */
+	if (start_vaddr > mm->task_size)
 		start_vaddr = end_vaddr;
 
 	/*
@@ -1590,11 +1707,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		/* overflow ? */
 		if (end < start_vaddr || end > end_vaddr)
 			end = end_vaddr;
-		ret = down_read_killable(&mm->mmap_sem);
+		ret = mmap_read_lock_killable(mm);
 		if (ret)
 			goto out_free;
 		ret = walk_page_range(mm, start_vaddr, end, &pagemap_ops, &pm);
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		start_vaddr = end;
 
 		len = min(count, PM_ENTRY_BYTES * pm.pos);
@@ -1701,7 +1818,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 		return NULL;
 
 	page = vm_normal_page(vma, addr, pte);
-	if (!page)
+	if (!page || is_zone_device_page(page))
 		return NULL;
 
 	if (PageReserved(page))
@@ -1789,8 +1906,6 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		return 0;
 
 	page = pte_page(huge_pte);
-	if (!page)
-		return 0;
 
 	md = walk->private;
 	gather_stats(page, md, pte_dirty(huge_pte), 1);
@@ -1853,7 +1968,7 @@ static int show_numa_map(struct seq_file *m, void *v)
 	if (is_vm_hugetlb_page(vma))
 		seq_puts(m, " huge");
 
-	/* mmap_sem is held by m_start */
+	/* mmap_lock is held by m_start */
 	walk_page_vma(vma, &show_numa_ops, md);
 
 	if (!md->pages)
@@ -1887,7 +2002,6 @@ static int show_numa_map(struct seq_file *m, void *v)
 	seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10);
 out:
 	seq_putc(m, '\n');
-	m_cache_vma(m, vma);
 	return 0;
 }