procfs: mark thread stack correctly in proc/<pid>/maps

Stack for a new thread is mapped by userspace code and passed via
sys_clone.  This memory is currently seen as anonymous in
/proc/<pid>/maps, which makes it difficult to ascertain which mappings
are being used for thread stacks.  This patch uses the individual task
stack pointers to determine which vmas are actually thread stacks.

For a multithreaded program like the following:

	#include <pthread.h>

	void *thread_main(void *foo)
	{
		while(1);
	}

	int main()
	{
		pthread_t t;
		pthread_create(&t, NULL, thread_main, NULL);
		pthread_join(t, NULL);
	}

proc/PID/maps looks like the following:

    00400000-00401000 r-xp 00000000 fd:0a 3671804                            /home/siddhesh/a.out
    00600000-00601000 rw-p 00000000 fd:0a 3671804                            /home/siddhesh/a.out
    019ef000-01a10000 rw-p 00000000 00:00 0                                  [heap]
    7f8a44491000-7f8a44492000 ---p 00000000 00:00 0
    7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0
    7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0
    7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0
    7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0
    7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0
    7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0
    7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0                          [stack]
    7fff627ff000-7fff62800000 r-xp 00000000 00:00 0                          [vdso]
    ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0                  [vsyscall]

Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since
the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but
that is not always a reliable way to find out which vma is a thread
stack.  Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same
content.

With this patch in place, /proc/PID/task/TID/maps are treated as 'maps
as the task would see it' and hence, only the vma that that task uses as
stack is marked as [stack].  All other 'stack' vmas are marked as
anonymous memory.  /proc/PID/maps acts as a thread group level view,
where all thread stack vmas are marked as [stack:TID] where TID is the
process ID of the task that uses that vma as stack, while the process
stack is marked as [stack].

So /proc/PID/maps will look like this:

    00400000-00401000 r-xp 00000000 fd:0a 3671804                            /home/siddhesh/a.out
    00600000-00601000 rw-p 00000000 fd:0a 3671804                            /home/siddhesh/a.out
    019ef000-01a10000 rw-p 00000000 00:00 0                                  [heap]
    7f8a44491000-7f8a44492000 ---p 00000000 00:00 0
    7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0                          [stack:1442]
    7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0
    7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0
    7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0
    7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0
    7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0
    7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0                          [stack]
    7fff627ff000-7fff62800000 r-xp 00000000 00:00 0                          [vdso]
    ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0                  [vsyscall]

Thus marking all vmas that are used as stacks by the threads in the
thread group along with the process stack.  The task level maps will
however like this:

    00400000-00401000 r-xp 00000000 fd:0a 3671804                            /home/siddhesh/a.out
    00600000-00601000 rw-p 00000000 fd:0a 3671804                            /home/siddhesh/a.out
    019ef000-01a10000 rw-p 00000000 00:00 0                                  [heap]
    7f8a44491000-7f8a44492000 ---p 00000000 00:00 0
    7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0                          [stack]
    7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482                    /lib64/libc-2.14.90.so
    7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0
    7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938                    /lib64/libpthread-2.14.90.so
    7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0
    7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0
    7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0
    7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348                    /lib64/ld-2.14.90.so
    7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0
    7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0
    7fff627ff000-7fff62800000 r-xp 00000000 00:00 0                          [vdso]
    ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0                  [vsyscall]

where only the vma that is being used as a stack by *that* task is
marked as [stack].

Analogous changes have been made to /proc/PID/smaps,
/proc/PID/numa_maps, /proc/PID/task/TID/smaps and
/proc/PID/task/TID/numa_maps. Relevant snippets from smaps and
numa_maps:

    [siddhesh@localhost ~ ]$ pgrep a.out
    1441
    [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack"
    7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0                          [stack:1442]
    7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0                          [stack]
    [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack"
    7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0                          [stack]
    [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack"
    7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0                          [stack]
    [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack"
    7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2
    7fff6273a000 default stack anon=3 dirty=3 N0=3
    [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack"
    7f8a44492000 default stack anon=2 dirty=2 N0=2
    [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack"
    7fff6273a000 default stack anon=3 dirty=3 N0=3

[akpm@linux-foundation.org: checkpatch fixes]
[akpm@linux-foundation.org: fix build]
Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jamie Lokier <jamie@shareable.org>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 169 insertions, 41 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c7e3a163295..9694cc28351 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -209,16 +209,20 @@ static int do_maps_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+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;
 	unsigned long start, end;
 	dev_t dev = 0;
 	int len;
+	const char *name = NULL;
 
 	if (file) {
 		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
@@ -252,36 +256,57 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	if (file) {
 		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "\n");
-	} else {
-		const char *name = arch_vma_name(vma);
-		if (!name) {
-			if (mm) {
-				if (vma->vm_start <= mm->brk &&
-						vma->vm_end >= mm->start_brk) {
-					name = "[heap]";
-				} else if (vma->vm_start <= mm->start_stack &&
-					   vma->vm_end >= mm->start_stack) {
-					name = "[stack]";
-				}
+		goto done;
+	}
+
+	name = arch_vma_name(vma);
+	if (!name) {
+		pid_t tid;
+
+		if (!mm) {
+			name = "[vdso]";
+			goto done;
+		}
+
+		if (vma->vm_start <= mm->brk &&
+		    vma->vm_end >= mm->start_brk) {
+			name = "[heap]";
+			goto done;
+		}
+
+		tid = vm_is_stack(task, vma, is_pid);
+
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack)) {
+				name = "[stack]";
 			} else {
-				name = "[vdso]";
+				/* Thread stack in /proc/PID/maps */
+				pad_len_spaces(m, len);
+				seq_printf(m, "[stack:%d]", tid);
 			}
 		}
-		if (name) {
-			pad_len_spaces(m, len);
-			seq_puts(m, name);
-		}
+	}
+
+done:
+	if (name) {
+		pad_len_spaces(m, len);
+		seq_puts(m, name);
 	}
 	seq_putc(m, '\n');
 }
 
-static int show_map(struct seq_file *m, void *v)
+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);
+	show_map_vma(m, vma, is_pid);
 
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task->mm))
@@ -289,20 +314,49 @@ static int show_map(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_maps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static int pid_maps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_maps_op);
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -416,7 +470,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return 0;
 }
 
-static int show_smap(struct seq_file *m, void *v)
+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;
@@ -434,7 +488,7 @@ static int show_smap(struct seq_file *m, void *v)
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	seq_printf(m,
 		   "Size:           %8lu kB\n"
@@ -473,20 +527,49 @@ static int show_smap(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_smaps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_smap
+	.show	= show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_smap
 };
 
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_smaps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_smaps_op);
 }
 
-const struct file_operations proc_smaps_operations = {
-	.open		= smaps_open,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+	.open		= pid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -1039,7 +1122,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 /*
  * Display pages allocated per node and memory policy via /proc.
  */
-static int show_numa_map(struct seq_file *m, void *v)
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct numa_maps_private *numa_priv = m->private;
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
@@ -1076,9 +1159,19 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_path(m, &file->f_path, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_printf(m, " heap");
-	} else if (vma->vm_start <= mm->start_stack &&
-			vma->vm_end >= mm->start_stack) {
-		seq_printf(m, " stack");
+	} else {
+		pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, " stack");
+			else
+				seq_printf(m, " stack:%d", tid);
+		}
 	}
 
 	if (is_vm_hugetlb_page(vma))
@@ -1121,21 +1214,39 @@ out:
 	return 0;
 }
 
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_numa_maps_op = {
-        .start  = m_start,
-        .next   = m_next,
-        .stop   = m_stop,
-        .show   = show_numa_map,
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_pid_numa_map,
 };
 
-static int numa_maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_tid_numa_map,
+};
+
+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, &proc_pid_numa_maps_op);
+		ret = seq_open(file, ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = priv;
@@ -1146,8 +1257,25 @@ static int numa_maps_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-const struct file_operations proc_numa_maps_operations = {
-	.open		= numa_maps_open,
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+	.open		= pid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+	.open		= tid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,