1 files changed, 151 insertions, 23 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 27972c0749e7..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)
+{
+	/*
+	 * 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)
 {
-	struct vm_area_struct *vma = vma_next(&priv->iter);
+	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;
@@ -2182,7 +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;