1 files changed, 202 insertions, 178 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dfc791c42d6..4e0388cffe3 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -87,32 +87,14 @@ unsigned long task_statm(struct mm_struct *mm,
 
 #ifdef CONFIG_NUMA
 /*
- * These functions are for numa_maps but called in generic **maps seq_file
- * ->start(), ->stop() ops.
- *
- * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
- * Each mempolicy object is controlled by reference counting. The problem here
- * is how to avoid accessing dead mempolicy object.
- *
- * Because we're holding mmap_sem while reading seq_file, it's safe to access
- * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
- *
- * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
- * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
- * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
- * gurantee the task never exits under us. But taking task_lock() around
- * get_vma_plicy() causes lock order problem.
- *
- * To access task->mempolicy without lock, we hold a reference count of an
- * object pointed by task->mempolicy and remember it. This will guarantee
- * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ * Save get_task_policy() for show_numa_map().
  */
 static void hold_task_mempolicy(struct proc_maps_private *priv)
 {
 	struct task_struct *task = priv->task;
 
 	task_lock(task);
-	priv->task_mempolicy = task->mempolicy;
+	priv->task_mempolicy = get_task_policy(task);
 	mpol_get(priv->task_mempolicy);
 	task_unlock(task);
 }
@@ -129,124 +111,154 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
-static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
+static void vma_stop(struct proc_maps_private *priv)
 {
-	if (vma && vma != priv->tail_vma) {
-		struct mm_struct *mm = vma->vm_mm;
-		release_task_mempolicy(priv);
-		up_read(&mm->mmap_sem);
-		mmput(mm);
-	}
+	struct mm_struct *mm = priv->mm;
+
+	release_task_mempolicy(priv);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+}
+
+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;
 }
 
-static void *m_start(struct seq_file *m, loff_t *pos)
+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_start : -1UL;
+}
+
+static void *m_start(struct seq_file *m, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
 	unsigned long last_addr = m->version;
 	struct mm_struct *mm;
-	struct vm_area_struct *vma, *tail_vma = NULL;
-	loff_t l = *pos;
-
-	/* Clear the per syscall fields in priv */
-	priv->task = NULL;
-	priv->tail_vma = NULL;
-
-	/*
-	 * We remember last_addr rather than next_addr to hit with
-	 * vmacache most of the time. We have zero last_addr at
-	 * the beginning and also after lseek. We will have -1 last_addr
-	 * after the end of the vmas.
-	 */
+	struct vm_area_struct *vma;
+	unsigned int pos = *ppos;
 
+	/* See m_cache_vma(). Zero at the start or after lseek. */
 	if (last_addr == -1UL)
 		return NULL;
 
-	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+	priv->task = get_proc_task(priv->inode);
 	if (!priv->task)
 		return ERR_PTR(-ESRCH);
 
-	mm = mm_access(priv->task, PTRACE_MODE_READ);
-	if (!mm || IS_ERR(mm))
-		return mm;
-	down_read(&mm->mmap_sem);
+	mm = priv->mm;
+	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+		return NULL;
 
-	tail_vma = get_gate_vma(priv->task->mm);
-	priv->tail_vma = tail_vma;
+	down_read(&mm->mmap_sem);
 	hold_task_mempolicy(priv);
-	/* Start with last addr hint */
-	vma = find_vma(mm, last_addr);
-	if (last_addr && vma) {
-		vma = vma->vm_next;
-		goto out;
+	priv->tail_vma = get_gate_vma(mm);
+
+	if (last_addr) {
+		vma = find_vma(mm, last_addr);
+		if (vma && (vma = m_next_vma(priv, vma)))
+			return vma;
 	}
 
-	/*
-	 * Check the vma index is within the range and do
-	 * sequential scan until m_index.
-	 */
-	vma = NULL;
-	if ((unsigned long)l < mm->map_count) {
-		vma = mm->mmap;
-		while (l-- && vma)
+	m->version = 0;
+	if (pos < mm->map_count) {
+		for (vma = mm->mmap; pos; pos--) {
+			m->version = vma->vm_start;
 			vma = vma->vm_next;
-		goto out;
+		}
+		return vma;
 	}
 
-	if (l != mm->map_count)
-		tail_vma = NULL; /* After gate vma */
-
-out:
-	if (vma)
-		return vma;
+	/* we do not bother to update m->version in this case */
+	if (pos == mm->map_count && priv->tail_vma)
+		return priv->tail_vma;
 
-	release_task_mempolicy(priv);
-	/* End of vmas has been reached */
-	m->version = (tail_vma != NULL)? 0: -1UL;
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-	return tail_vma;
+	vma_stop(priv);
+	return NULL;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *vma = v;
-	struct vm_area_struct *tail_vma = priv->tail_vma;
+	struct vm_area_struct *next;
 
 	(*pos)++;
-	if (vma && (vma != tail_vma) && vma->vm_next)
-		return vma->vm_next;
-	vma_stop(priv, vma);
-	return (vma != tail_vma)? tail_vma: NULL;
+	next = m_next_vma(priv, v);
+	if (!next)
+		vma_stop(priv);
+	return next;
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *vma = v;
 
-	if (!IS_ERR(vma))
-		vma_stop(priv, vma);
-	if (priv->task)
+	if (!IS_ERR_OR_NULL(v))
+		vma_stop(priv);
+	if (priv->task) {
 		put_task_struct(priv->task);
+		priv->task = NULL;
+	}
+}
+
+static int proc_maps_open(struct inode *inode, struct file *file,
+			const struct seq_operations *ops, int psize)
+{
+	struct proc_maps_private *priv = __seq_open_private(file, ops, psize);
+
+	if (!priv)
+		return -ENOMEM;
+
+	priv->inode = inode;
+	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR(priv->mm)) {
+		int err = PTR_ERR(priv->mm);
+
+		seq_release_private(inode, file);
+		return err;
+	}
+
+	return 0;
+}
+
+static int proc_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct proc_maps_private *priv = seq->private;
+
+	if (priv->mm)
+		mmdrop(priv->mm);
+
+	return seq_release_private(inode, file);
 }
 
 static int do_maps_open(struct inode *inode, struct file *file,
 			const struct seq_operations *ops)
 {
-	struct proc_maps_private *priv;
-	int ret = -ENOMEM;
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv) {
-		priv->pid = proc_pid(inode);
-		ret = seq_open(file, ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = priv;
-		} else {
-			kfree(priv);
-		}
+	return proc_maps_open(inode, file, ops,
+				sizeof(struct proc_maps_private));
+}
+
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
 	}
+	rcu_read_unlock();
+
 	return ret;
 }
 
@@ -256,7 +268,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
 	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
@@ -321,8 +332,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = vm_is_stack(task, vma, is_pid);
-
+		tid = pid_of_stack(priv, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
@@ -349,15 +359,8 @@ done:
 
 static int show_map(struct seq_file *m, void *v, int is_pid)
 {
-	struct vm_area_struct *vma = v;
-	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
-
-	show_map_vma(m, vma, is_pid);
-
-	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task->mm))
-			? vma->vm_start : 0;
+	show_map_vma(m, v, is_pid);
+	m_cache_vma(m, v);
 	return 0;
 }
 
@@ -399,14 +402,14 @@ const struct file_operations proc_pid_maps_operations = {
 	.open		= pid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 const struct file_operations proc_tid_maps_operations = {
 	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 /*
@@ -583,8 +586,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
-	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
@@ -637,10 +638,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 				mss.nonlinear >> 10);
 
 	show_smap_vma_flags(m, vma);
-
-	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task->mm))
-			? vma->vm_start : 0;
+	m_cache_vma(m, vma);
 	return 0;
 }
 
@@ -682,14 +680,14 @@ const struct file_operations proc_pid_smaps_operations = {
 	.open		= pid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 const struct file_operations proc_tid_smaps_operations = {
 	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 /*
@@ -829,8 +827,21 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
-		if (type == CLEAR_REFS_SOFT_DIRTY)
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
+			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+				if (!(vma->vm_flags & VM_SOFTDIRTY))
+					continue;
+				up_read(&mm->mmap_sem);
+				down_write(&mm->mmap_sem);
+				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;
+			}
 			mmu_notifier_invalidate_range_start(mm, 0, -1);
+		}
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			cp.vma = vma;
 			if (is_vm_hugetlb_page(vma))
@@ -850,10 +861,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				continue;
 			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
 				continue;
-			if (type == CLEAR_REFS_SOFT_DIRTY) {
-				if (vma->vm_flags & VM_SOFTDIRTY)
-					vma->vm_flags &= ~VM_SOFTDIRTY;
-			}
 			walk_page_range(vma->vm_start, vma->vm_end,
 					&clear_refs_walk);
 		}
@@ -931,23 +938,32 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	while (addr < end) {
 		struct vm_area_struct *vma = find_vma(walk->mm, addr);
 		pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
-		unsigned long vm_end;
-
-		if (!vma) {
-			vm_end = end;
-		} else {
-			vm_end = min(end, vma->vm_end);
-			if (vma->vm_flags & VM_SOFTDIRTY)
-				pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+		/* End of address space hole, which we mark as non-present. */
+		unsigned long hole_end;
+
+		if (vma)
+			hole_end = min(end, vma->vm_start);
+		else
+			hole_end = end;
+
+		for (; addr < hole_end; addr += PAGE_SIZE) {
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				goto out;
 		}
 
-		for (; addr < vm_end; addr += PAGE_SIZE) {
+		if (!vma)
+			break;
+
+		/* Addresses in the VMA. */
+		if (vma->vm_flags & VM_SOFTDIRTY)
+			pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
 				goto out;
 		}
 	}
-
 out:
 	return err;
 }
@@ -1020,7 +1036,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	spinlock_t *ptl;
 	pte_t *pte;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
@@ -1034,6 +1049,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
+			pagemap_entry_t pme;
 
 			offset = (addr & ~PAGEMAP_WALK_MASK) >>
 					PAGE_SHIFT;
@@ -1048,32 +1064,51 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
-	for (; addr != end; addr += PAGE_SIZE) {
-		int flags2;
-
-		/* check to see if we've left 'vma' behind
-		 * and need a new, higher one */
-		if (vma && (addr >= vma->vm_end)) {
-			vma = find_vma(walk->mm, addr);
-			if (vma && (vma->vm_flags & VM_SOFTDIRTY))
-				flags2 = __PM_SOFT_DIRTY;
-			else
-				flags2 = 0;
-			pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
+
+	while (1) {
+		/* End of address space hole, which we mark as non-present. */
+		unsigned long hole_end;
+
+		if (vma)
+			hole_end = min(end, vma->vm_start);
+		else
+			hole_end = end;
+
+		for (; addr < hole_end; addr += PAGE_SIZE) {
+			pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				return err;
 		}
 
-		/* check that 'vma' actually covers this address,
-		 * and that it isn't a huge page vma */
-		if (vma && (vma->vm_start <= addr) &&
-		    !is_vm_hugetlb_page(vma)) {
+		if (!vma || vma->vm_start >= end)
+			break;
+		/*
+		 * We can't possibly be in a hugetlb VMA. In general,
+		 * for a mm_walk with a pmd_entry and a hugetlb_entry,
+		 * the pmd_entry can only be called on addresses in a
+		 * hugetlb if the walk starts in a non-hugetlb VMA and
+		 * spans a hugepage VMA. Since pagemap_read walks are
+		 * PMD-sized and PMD-aligned, this will never be true.
+		 */
+		BUG_ON(is_vm_hugetlb_page(vma));
+
+		/* Addresses in the VMA. */
+		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+			pagemap_entry_t pme;
 			pte = pte_offset_map(pmd, addr);
 			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-			/* unmap before userspace copy */
 			pte_unmap(pte);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				return err;
 		}
-		err = add_to_pagemap(addr, &pme, pm);
-		if (err)
-			return err;
+
+		if (addr == end)
+			break;
+
+		vma = find_vma(walk->mm, addr);
 	}
 
 	cond_resched();
@@ -1406,7 +1441,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
-	struct task_struct *task = proc_priv->task;
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {};
 	struct mempolicy *pol;
@@ -1426,9 +1460,13 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	walk.private = md;
 	walk.mm = mm;
 
-	pol = get_vma_policy(task, vma, vma->vm_start);
-	mpol_to_str(buffer, sizeof(buffer), pol);
-	mpol_cond_put(pol);
+	pol = __get_vma_policy(vma, vma->vm_start);
+	if (pol) {
+		mpol_to_str(buffer, sizeof(buffer), pol);
+		mpol_cond_put(pol);
+	} else {
+		mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy);
+	}
 
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
@@ -1438,7 +1476,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
 	} else {
-		pid_t tid = vm_is_stack(task, vma, is_pid);
+		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
@@ -1486,9 +1524,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
 out:
 	seq_putc(m, '\n');
-
-	if (m->count < m->size)
-		m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+	m_cache_vma(m, vma);
 	return 0;
 }
 
@@ -1519,20 +1555,8 @@ static const struct seq_operations proc_tid_numa_maps_op = {
 static int numa_maps_open(struct inode *inode, struct file *file,
 			  const struct seq_operations *ops)
 {
-	struct numa_maps_private *priv;
-	int ret = -ENOMEM;
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv) {
-		priv->proc_maps.pid = proc_pid(inode);
-		ret = seq_open(file, ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = priv;
-		} else {
-			kfree(priv);
-		}
-	}
-	return ret;
+	return proc_maps_open(inode, file, ops,
+				sizeof(struct numa_maps_private));
 }
 
 static int pid_numa_maps_open(struct inode *inode, struct file *file)
@@ -1549,13 +1573,13 @@ const struct file_operations proc_pid_numa_maps_operations = {
 	.open		= pid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 const struct file_operations proc_tid_numa_maps_operations = {
 	.open		= tid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 #endif /* CONFIG_NUMA */