1 files changed, 209 insertions, 52 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 38a5a3e9cba2..3d6d8a9f13fc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -29,6 +29,9 @@
 #include <asm/tlbflush.h>
 #include "internal.h"
 
+#define SENTINEL_VMA_END	-1
+#define SENTINEL_VMA_GATE	-2
+
 #define SEQ_PUT_DEC(str, val) \
 		seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8)
 void task_mem(struct seq_file *m, struct mm_struct *mm)
@@ -36,9 +39,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	unsigned long text, lib, swap, anon, file, shmem;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
-	anon = get_mm_counter(mm, MM_ANONPAGES);
-	file = get_mm_counter(mm, MM_FILEPAGES);
-	shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+	anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+	file = get_mm_counter_sum(mm, MM_FILEPAGES);
+	shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
 
 	/*
 	 * Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -59,7 +62,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	text = min(text, mm->exec_vm << PAGE_SHIFT);
 	lib = (mm->exec_vm << PAGE_SHIFT) - text;
 
-	swap = get_mm_counter(mm, MM_SWAPENTS);
+	swap = get_mm_counter_sum(mm, MM_SWAPENTS);
 	SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
 	SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
 	SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -92,12 +95,12 @@ unsigned long task_statm(struct mm_struct *mm,
 			 unsigned long *shared, unsigned long *text,
 			 unsigned long *data, unsigned long *resident)
 {
-	*shared = get_mm_counter(mm, MM_FILEPAGES) +
-			get_mm_counter(mm, MM_SHMEMPAGES);
+	*shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+			get_mm_counter_sum(mm, MM_SHMEMPAGES);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
 								>> PAGE_SHIFT;
 	*data = mm->data_vm + mm->stack_vm;
-	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+	*resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
 	return mm->total_vm;
 }
 
@@ -127,15 +130,134 @@ 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)
+#ifdef CONFIG_PER_VMA_LOCK
+
+static void unlock_vma(struct proc_maps_private *priv)
+{
+	if (priv->locked_vma) {
+		vma_end_read(priv->locked_vma);
+		priv->locked_vma = NULL;
+	}
+}
+
+static const struct seq_operations proc_pid_maps_op;
+
+static inline bool lock_vma_range(struct seq_file *m,
+				  struct proc_maps_private *priv)
 {
-	struct vm_area_struct *vma = vma_next(&priv->iter);
+	/*
+	 * smaps and numa_maps perform page table walk, therefore require
+	 * mmap_lock but maps can be read with locking just the vma and
+	 * walking the vma tree under rcu read protection.
+	 */
+	if (m->op != &proc_pid_maps_op) {
+		if (mmap_read_lock_killable(priv->mm))
+			return false;
 
+		priv->mmap_locked = true;
+	} else {
+		rcu_read_lock();
+		priv->locked_vma = NULL;
+		priv->mmap_locked = false;
+	}
+
+	return true;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+	if (priv->mmap_locked) {
+		mmap_read_unlock(priv->mm);
+	} else {
+		unlock_vma(priv);
+		rcu_read_unlock();
+	}
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+					   loff_t last_pos)
+{
+	struct vm_area_struct *vma;
+
+	if (priv->mmap_locked)
+		return vma_next(&priv->iter);
+
+	unlock_vma(priv);
+	vma = lock_next_vma(priv->mm, &priv->iter, last_pos);
+	if (!IS_ERR_OR_NULL(vma))
+		priv->locked_vma = vma;
+
+	return vma;
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+					 loff_t pos)
+{
+	if (priv->mmap_locked)
+		return false;
+
+	rcu_read_unlock();
+	mmap_read_lock(priv->mm);
+	/* Reinitialize the iterator after taking mmap_lock */
+	vma_iter_set(&priv->iter, pos);
+	priv->mmap_locked = true;
+
+	return true;
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline bool lock_vma_range(struct seq_file *m,
+				  struct proc_maps_private *priv)
+{
+	return mmap_read_lock_killable(priv->mm) == 0;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+	mmap_read_unlock(priv->mm);
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+					   loff_t last_pos)
+{
+	return vma_next(&priv->iter);
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+					 loff_t pos)
+{
+	return false;
+}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
+static struct vm_area_struct *proc_get_vma(struct seq_file *m, loff_t *ppos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma;
+
+retry:
+	vma = get_next_vma(priv, *ppos);
+	/* EINTR of EAGAIN is possible */
+	if (IS_ERR(vma)) {
+		if (PTR_ERR(vma) == -EAGAIN && fallback_to_mmap_lock(priv, *ppos))
+			goto retry;
+
+		return vma;
+	}
+
+	/* Store previous position to be able to restart if needed */
+	priv->last_pos = *ppos;
 	if (vma) {
-		*ppos = vma->vm_start;
+		/*
+		 * Track the end of the reported vma to ensure position changes
+		 * even if previous vma was merged with the next vma and we
+		 * found the extended vma with the same vm_start.
+		 */
+		*ppos = vma->vm_end;
 	} else {
-		*ppos = -2UL;
+		*ppos = SENTINEL_VMA_GATE;
 		vma = get_gate_vma(priv->mm);
 	}
 
@@ -145,11 +267,11 @@ static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
 static void *m_start(struct seq_file *m, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
-	unsigned long last_addr = *ppos;
+	loff_t last_addr = *ppos;
 	struct mm_struct *mm;
 
 	/* See m_next(). Zero at the start or after lseek. */
-	if (last_addr == -1UL)
+	if (last_addr == SENTINEL_VMA_END)
 		return NULL;
 
 	priv->task = get_proc_task(priv->inode);
@@ -163,28 +285,34 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 		return NULL;
 	}
 
-	if (mmap_read_lock_killable(mm)) {
+	if (!lock_vma_range(m, priv)) {
 		mmput(mm);
 		put_task_struct(priv->task);
 		priv->task = NULL;
 		return ERR_PTR(-EINTR);
 	}
 
-	vma_iter_init(&priv->iter, mm, last_addr);
+	/*
+	 * Reset current position if last_addr was set before
+	 * and it's not a sentinel.
+	 */
+	if (last_addr > 0)
+		*ppos = last_addr = priv->last_pos;
+	vma_iter_init(&priv->iter, mm, (unsigned long)last_addr);
 	hold_task_mempolicy(priv);
-	if (last_addr == -2UL)
+	if (last_addr == SENTINEL_VMA_GATE)
 		return get_gate_vma(mm);
 
-	return proc_get_vma(priv, ppos);
+	return proc_get_vma(m, ppos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
 {
-	if (*ppos == -2UL) {
-		*ppos = -1UL;
+	if (*ppos == SENTINEL_VMA_GATE) {
+		*ppos = SENTINEL_VMA_END;
 		return NULL;
 	}
-	return proc_get_vma(m->private, ppos);
+	return proc_get_vma(m, ppos);
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -196,7 +324,7 @@ static void m_stop(struct seq_file *m, void *v)
 		return;
 
 	release_task_mempolicy(priv);
-	mmap_read_unlock(mm);
+	unlock_vma_range(priv);
 	mmput(mm);
 	put_task_struct(priv->task);
 	priv->task = NULL;
@@ -212,8 +340,8 @@ static int proc_maps_open(struct inode *inode, struct file *file,
 
 	priv->inode = inode;
 	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
-	if (IS_ERR(priv->mm)) {
-		int err = PTR_ERR(priv->mm);
+	if (IS_ERR_OR_NULL(priv->mm)) {
+		int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH;
 
 		seq_release_private(inode, file);
 		return err;
@@ -707,6 +835,8 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	struct folio *folio = page_folio(page);
 	int i, nr = compound ? compound_nr(page) : 1;
 	unsigned long size = nr * PAGE_SIZE;
+	bool exclusive;
+	int mapcount;
 
 	/*
 	 * First accumulate quantities that depend only on |size| and the type
@@ -747,18 +877,29 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 				      dirty, locked, present);
 		return;
 	}
+
+	if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
+		mapcount = folio_average_page_mapcount(folio);
+		exclusive = !folio_maybe_mapped_shared(folio);
+	}
+
 	/*
 	 * We obtain a snapshot of the mapcount. Without holding the folio lock
 	 * this snapshot can be slightly wrong as we cannot always read the
 	 * mapcount atomically.
 	 */
 	for (i = 0; i < nr; i++, page++) {
-		int mapcount = folio_precise_page_mapcount(folio, page);
 		unsigned long pss = PAGE_SIZE << PSS_SHIFT;
+
+		if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) {
+			mapcount = folio_precise_page_mapcount(folio, page);
+			exclusive = mapcount < 2;
+		}
+
 		if (mapcount >= 2)
 			pss /= mapcount;
 		smaps_page_accumulate(mss, folio, PAGE_SIZE, pss,
-				dirty, locked, mapcount < 2);
+				dirty, locked, exclusive);
 	}
 }
 
@@ -1023,7 +1164,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 
 	if (folio) {
 		/* We treat non-present entries as "maybe shared". */
-		if (!present || folio_likely_mapped_shared(folio) ||
+		if (!present || folio_maybe_mapped_shared(folio) ||
 		    hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else
@@ -1312,8 +1453,8 @@ static int smaps_rollup_open(struct inode *inode, struct file *file)
 
 	priv->inode = inode;
 	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
-	if (IS_ERR(priv->mm)) {
-		ret = PTR_ERR(priv->mm);
+	if (IS_ERR_OR_NULL(priv->mm)) {
+		ret = priv->mm ? PTR_ERR(priv->mm) : -ESRCH;
 
 		single_release(inode, file);
 		goto out_free;
@@ -1632,6 +1773,7 @@ struct pagemapread {
 #define PM_SOFT_DIRTY		BIT_ULL(55)
 #define PM_MMAP_EXCLUSIVE	BIT_ULL(56)
 #define PM_UFFD_WP		BIT_ULL(57)
+#define PM_GUARD_REGION		BIT_ULL(58)
 #define PM_FILE			BIT_ULL(61)
 #define PM_SWAP			BIT_ULL(62)
 #define PM_PRESENT		BIT_ULL(63)
@@ -1651,6 +1793,13 @@ static int add_to_pagemap(pagemap_entry_t *pme, struct pagemapread *pm)
 	return 0;
 }
 
+static bool __folio_page_mapped_exclusively(struct folio *folio, struct page *page)
+{
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		return folio_precise_page_mapcount(folio, page) == 1;
+	return !folio_maybe_mapped_shared(folio);
+}
+
 static int pagemap_pte_hole(unsigned long start, unsigned long end,
 			    __always_unused int depth, struct mm_walk *walk)
 {
@@ -1732,6 +1881,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 			page = pfn_swap_entry_to_page(entry);
 		if (pte_marker_entry_uffd_wp(entry))
 			flags |= PM_UFFD_WP;
+		if (is_guard_swp_entry(entry))
+			flags |=  PM_GUARD_REGION;
 	}
 
 	if (page) {
@@ -1739,7 +1890,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		if (!folio_test_anon(folio))
 			flags |= PM_FILE;
 		if ((flags & PM_PRESENT) &&
-		    folio_precise_page_mapcount(folio, page) == 1)
+		    __folio_page_mapped_exclusively(folio, page))
 			flags |= PM_MMAP_EXCLUSIVE;
 	}
 	if (vma->vm_flags & VM_SOFTDIRTY)
@@ -1810,11 +1961,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		}
 
 		for (; addr != end; addr += PAGE_SIZE, idx++) {
-			unsigned long cur_flags = flags;
+			u64 cur_flags = flags;
 			pagemap_entry_t pme;
 
 			if (folio && (flags & PM_PRESENT) &&
-			    folio_precise_page_mapcount(folio, page + idx) == 1)
+			    __folio_page_mapped_exclusively(folio, page))
 				cur_flags |= PM_MMAP_EXCLUSIVE;
 
 			pme = make_pme(frame, cur_flags);
@@ -1879,7 +2030,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
 		if (!folio_test_anon(folio))
 			flags |= PM_FILE;
 
-		if (!folio_likely_mapped_shared(folio) &&
+		if (!folio_maybe_mapped_shared(folio) &&
 		    !hugetlb_pmd_shared(ptep))
 			flags |= PM_MMAP_EXCLUSIVE;
 
@@ -1931,7 +2082,8 @@ static const struct mm_walk_ops pagemap_ops = {
  * Bit  55    pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
  * Bit  56    page exclusively mapped
  * Bit  57    pte is uffd-wp write-protected
- * Bits 58-60 zero
+ * Bit  58    pte is a guard region
+ * Bits 59-60 zero
  * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
@@ -2045,8 +2197,8 @@ static int pagemap_open(struct inode *inode, struct file *file)
 	struct mm_struct *mm;
 
 	mm = proc_mem_open(inode, PTRACE_MODE_READ);
-	if (IS_ERR(mm))
-		return PTR_ERR(mm);
+	if (IS_ERR_OR_NULL(mm))
+		return mm ? PTR_ERR(mm) : -ESRCH;
 	file->private_data = mm;
 	return 0;
 }
@@ -2063,7 +2215,8 @@ static int pagemap_release(struct inode *inode, struct file *file)
 #define PM_SCAN_CATEGORIES	(PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN |	\
 				 PAGE_IS_FILE |	PAGE_IS_PRESENT |	\
 				 PAGE_IS_SWAPPED | PAGE_IS_PFNZERO |	\
-				 PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY)
+				 PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY |	\
+				 PAGE_IS_GUARD)
 #define PM_SCAN_FLAGS		(PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
 
 struct pagemap_scan_private {
@@ -2104,12 +2257,14 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 		if (!pte_swp_uffd_wp_any(pte))
 			categories |= PAGE_IS_WRITTEN;
 
-		if (p->masks_of_interest & PAGE_IS_FILE) {
-			swp = pte_to_swp_entry(pte);
-			if (is_pfn_swap_entry(swp) &&
-			    !folio_test_anon(pfn_swap_entry_folio(swp)))
-				categories |= PAGE_IS_FILE;
-		}
+		swp = pte_to_swp_entry(pte);
+		if (is_guard_swp_entry(swp))
+			categories |= PAGE_IS_GUARD;
+		else if ((p->masks_of_interest & PAGE_IS_FILE) &&
+			 is_pfn_swap_entry(swp) &&
+			 !folio_test_anon(pfn_swap_entry_folio(swp)))
+			categories |= PAGE_IS_FILE;
+
 		if (pte_swp_soft_dirty(pte))
 			categories |= PAGE_IS_SOFT_DIRTY;
 	}
@@ -2155,7 +2310,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 				categories |= PAGE_IS_FILE;
 		}
 
-		if (is_zero_pfn(pmd_pfn(pmd)))
+		if (is_huge_zero_pmd(pmd))
 			categories |= PAGE_IS_PFNZERO;
 		if (pmd_soft_dirty(pmd))
 			categories |= PAGE_IS_SOFT_DIRTY;
@@ -2455,22 +2610,19 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 	spinlock_t *ptl;
 	int ret;
 
-	arch_enter_lazy_mmu_mode();
-
 	ret = pagemap_scan_thp_entry(pmd, start, end, walk);
-	if (ret != -ENOENT) {
-		arch_leave_lazy_mmu_mode();
+	if (ret != -ENOENT)
 		return ret;
-	}
 
 	ret = 0;
 	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
 	if (!pte) {
-		arch_leave_lazy_mmu_mode();
 		walk->action = ACTION_AGAIN;
 		return 0;
 	}
 
+	arch_enter_lazy_mmu_mode();
+
 	if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
 		/* Fast path for performing exclusive WP */
 		for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
@@ -2539,8 +2691,8 @@ flush_and_return:
 	if (flush_end)
 		flush_tlb_range(vma, start, addr);
 
-	pte_unmap_unlock(start_pte, ptl);
 	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(start_pte, ptl);
 
 	cond_resched();
 	return ret;
@@ -2855,7 +3007,12 @@ static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
 			unsigned long nr_pages)
 {
 	struct folio *folio = page_folio(page);
-	int count = folio_precise_page_mapcount(folio, page);
+	int count;
+
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		count = folio_precise_page_mapcount(folio, page);
+	else
+		count = folio_average_page_mapcount(folio);
 
 	md->pages += nr_pages;
 	if (pte_dirty || folio_test_dirty(folio))