linux-hardened/fs/proc/task_nommu.c
Johannes Weiner 65376df582 proc: revert /proc/<pid>/maps [stack:TID] annotation
Commit b76437579d ("procfs: mark thread stack correctly in
proc/<pid>/maps") added [stack:TID] annotation to /proc/<pid>/maps.

Finding the task of a stack VMA requires walking the entire thread list,
turning this into quadratic behavior: a thousand threads means a
thousand stacks, so the rendering of /proc/<pid>/maps needs to look at a
million combinations.

The cost is not in proportion to the usefulness as described in the
patch.

Drop the [stack:TID] annotation to make /proc/<pid>/maps (and
/proc/<pid>/numa_maps) usable again for higher thread counts.

The [stack] annotation inside /proc/<pid>/task/<tid>/maps is retained, as
identifying the stack VMA there is an O(1) operation.

Siddesh said:
 "The end users needed a way to identify thread stacks programmatically and
  there wasn't a way to do that.  I'm afraid I no longer remember (or have
  access to the resources that would aid my memory since I changed
  employers) the details of their requirement.  However, I did do this on my
  own time because I thought it was an interesting project for me and nobody
  really gave any feedback then as to its utility, so as far as I am
  concerned you could roll back the main thread maps information since the
  information is available in the thread-specific files"

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com>
Cc: Shaohua Li <shli@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-03 08:28:43 -08:00

336 lines
7.4 KiB
C

#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fs_struct.h>
#include <linux/mount.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include "internal.h"
/*
* Logic: we've got two memory sums for each process, "shared", and
* "non-shared". Shared memory may get counted more than once, for
* each process that owns it. Non-shared memory is counted
* accurately.
*/
void task_mem(struct seq_file *m, struct mm_struct *mm)
{
struct vm_area_struct *vma;
struct vm_region *region;
struct rb_node *p;
unsigned long bytes = 0, sbytes = 0, slack = 0, size;
down_read(&mm->mmap_sem);
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
vma = rb_entry(p, struct vm_area_struct, vm_rb);
bytes += kobjsize(vma);
region = vma->vm_region;
if (region) {
size = kobjsize(region);
size += region->vm_end - region->vm_start;
} else {
size = vma->vm_end - vma->vm_start;
}
if (atomic_read(&mm->mm_count) > 1 ||
vma->vm_flags & VM_MAYSHARE) {
sbytes += size;
} else {
bytes += size;
if (region)
slack = region->vm_end - vma->vm_end;
}
}
if (atomic_read(&mm->mm_count) > 1)
sbytes += kobjsize(mm);
else
bytes += kobjsize(mm);
if (current->fs && current->fs->users > 1)
sbytes += kobjsize(current->fs);
else
bytes += kobjsize(current->fs);
if (current->files && atomic_read(&current->files->count) > 1)
sbytes += kobjsize(current->files);
else
bytes += kobjsize(current->files);
if (current->sighand && atomic_read(&current->sighand->count) > 1)
sbytes += kobjsize(current->sighand);
else
bytes += kobjsize(current->sighand);
bytes += kobjsize(current); /* includes kernel stack */
seq_printf(m,
"Mem:\t%8lu bytes\n"
"Slack:\t%8lu bytes\n"
"Shared:\t%8lu bytes\n",
bytes, slack, sbytes);
up_read(&mm->mmap_sem);
}
unsigned long task_vsize(struct mm_struct *mm)
{
struct vm_area_struct *vma;
struct rb_node *p;
unsigned long vsize = 0;
down_read(&mm->mmap_sem);
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
vma = rb_entry(p, struct vm_area_struct, vm_rb);
vsize += vma->vm_end - vma->vm_start;
}
up_read(&mm->mmap_sem);
return vsize;
}
unsigned long task_statm(struct mm_struct *mm,
unsigned long *shared, unsigned long *text,
unsigned long *data, unsigned long *resident)
{
struct vm_area_struct *vma;
struct vm_region *region;
struct rb_node *p;
unsigned long size = kobjsize(mm);
down_read(&mm->mmap_sem);
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
vma = rb_entry(p, struct vm_area_struct, vm_rb);
size += kobjsize(vma);
region = vma->vm_region;
if (region) {
size += kobjsize(region);
size += region->vm_end - region->vm_start;
}
}
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = (PAGE_ALIGN(mm->start_stack) - (mm->start_data & PAGE_MASK))
>> PAGE_SHIFT;
up_read(&mm->mmap_sem);
size >>= PAGE_SHIFT;
size += *text + *data;
*resident = size;
return size;
}
static int is_stack(struct proc_maps_private *priv,
struct vm_area_struct *vma, int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
int stack = 0;
if (is_pid) {
stack = vma->vm_start <= mm->start_stack &&
vma->vm_end >= mm->start_stack;
} else {
struct inode *inode = priv->inode;
struct task_struct *task;
rcu_read_lock();
task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task)
stack = vma_is_stack_for_task(vma, task);
rcu_read_unlock();
}
return stack;
}
/*
* display a single VMA to a sequenced file
*/
static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
struct proc_maps_private *priv = m->private;
unsigned long ino = 0;
struct file *file;
dev_t dev = 0;
int flags;
unsigned long long pgoff = 0;
flags = vma->vm_flags;
file = vma->vm_file;
if (file) {
struct inode *inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
}
seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
seq_printf(m,
"%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
vma->vm_start,
vma->vm_end,
flags & VM_READ ? 'r' : '-',
flags & VM_WRITE ? 'w' : '-',
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
pgoff,
MAJOR(dev), MINOR(dev), ino);
if (file) {
seq_pad(m, ' ');
seq_file_path(m, file, "");
} else if (mm && is_stack(priv, vma, is_pid)) {
seq_pad(m, ' ');
seq_printf(m, "[stack]");
}
seq_putc(m, '\n');
return 0;
}
/*
* display mapping lines for a particular process's /proc/pid/maps
*/
static int show_map(struct seq_file *m, void *_p, int is_pid)
{
struct rb_node *p = _p;
return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb),
is_pid);
}
static int show_pid_map(struct seq_file *m, void *_p)
{
return show_map(m, _p, 1);
}
static int show_tid_map(struct seq_file *m, void *_p)
{
return show_map(m, _p, 0);
}
static void *m_start(struct seq_file *m, loff_t *pos)
{
struct proc_maps_private *priv = m->private;
struct mm_struct *mm;
struct rb_node *p;
loff_t n = *pos;
/* pin the task and mm whilst we play with them */
priv->task = get_proc_task(priv->inode);
if (!priv->task)
return ERR_PTR(-ESRCH);
mm = priv->mm;
if (!mm || !atomic_inc_not_zero(&mm->mm_users))
return NULL;
down_read(&mm->mmap_sem);
/* start from the Nth VMA */
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
if (n-- == 0)
return p;
up_read(&mm->mmap_sem);
mmput(mm);
return NULL;
}
static void m_stop(struct seq_file *m, void *_vml)
{
struct proc_maps_private *priv = m->private;
if (!IS_ERR_OR_NULL(_vml)) {
up_read(&priv->mm->mmap_sem);
mmput(priv->mm);
}
if (priv->task) {
put_task_struct(priv->task);
priv->task = NULL;
}
}
static void *m_next(struct seq_file *m, void *_p, loff_t *pos)
{
struct rb_node *p = _p;
(*pos)++;
return p ? rb_next(p) : NULL;
}
static const struct seq_operations proc_pid_maps_ops = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_pid_map
};
static const struct seq_operations proc_tid_maps_ops = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_tid_map
};
static int maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
struct proc_maps_private *priv;
priv = __seq_open_private(file, ops, sizeof(*priv));
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 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 pid_maps_open(struct inode *inode, struct file *file)
{
return maps_open(inode, file, &proc_pid_maps_ops);
}
static int tid_maps_open(struct inode *inode, struct file *file)
{
return maps_open(inode, file, &proc_tid_maps_ops);
}
const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = map_release,
};
const struct file_operations proc_tid_maps_operations = {
.open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = map_release,
};