2005-04-17 05:20:36 +07:00
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/hugetlb.h>
|
|
|
|
#include <linux/mount.h>
|
|
|
|
#include <linux/seq_file.h>
|
2005-09-04 05:55:10 +07:00
|
|
|
#include <linux/highmem.h>
|
2007-05-08 14:26:04 +07:00
|
|
|
#include <linux/ptrace.h>
|
2005-09-04 05:54:45 +07:00
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/mempolicy.h>
|
2008-02-05 13:29:04 +07:00
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/swapops.h>
|
2005-09-04 05:55:10 +07:00
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <asm/elf.h>
|
|
|
|
#include <asm/uaccess.h>
|
2005-09-04 05:55:10 +07:00
|
|
|
#include <asm/tlbflush.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
#include "internal.h"
|
|
|
|
|
2008-02-08 19:18:33 +07:00
|
|
|
void task_mem(struct seq_file *m, struct mm_struct *mm)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
unsigned long data, text, lib;
|
[PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability. Originally it was called whenever rss or
total_vm got raised. Then many of those callsites were replaced by a timer
tick call from account_system_time. Now Frank van Maarseveen reports that to
be found inadequate. How about this? Works for Frank.
Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm. Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths. Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit. Handle
mm->hiwater_vm in the same way, though it's much less of an issue. Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.
And there has been no collector of these hiwater statistics in the tree. The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).
There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high. A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.
What locking? None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact. But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 08:16:18 +07:00
|
|
|
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Note: to minimize their overhead, mm maintains hiwater_vm and
|
|
|
|
* hiwater_rss only when about to *lower* total_vm or rss. Any
|
|
|
|
* collector of these hiwater stats must therefore get total_vm
|
|
|
|
* and rss too, which will usually be the higher. Barriers? not
|
|
|
|
* worth the effort, such snapshots can always be inconsistent.
|
|
|
|
*/
|
|
|
|
hiwater_vm = total_vm = mm->total_vm;
|
|
|
|
if (hiwater_vm < mm->hiwater_vm)
|
|
|
|
hiwater_vm = mm->hiwater_vm;
|
|
|
|
hiwater_rss = total_rss = get_mm_rss(mm);
|
|
|
|
if (hiwater_rss < mm->hiwater_rss)
|
|
|
|
hiwater_rss = mm->hiwater_rss;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
data = mm->total_vm - mm->shared_vm - mm->stack_vm;
|
|
|
|
text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
|
|
|
|
lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
|
2008-02-08 19:18:33 +07:00
|
|
|
seq_printf(m,
|
[PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability. Originally it was called whenever rss or
total_vm got raised. Then many of those callsites were replaced by a timer
tick call from account_system_time. Now Frank van Maarseveen reports that to
be found inadequate. How about this? Works for Frank.
Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm. Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths. Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit. Handle
mm->hiwater_vm in the same way, though it's much less of an issue. Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.
And there has been no collector of these hiwater statistics in the tree. The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).
There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high. A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.
What locking? None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact. But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 08:16:18 +07:00
|
|
|
"VmPeak:\t%8lu kB\n"
|
2005-04-17 05:20:36 +07:00
|
|
|
"VmSize:\t%8lu kB\n"
|
|
|
|
"VmLck:\t%8lu kB\n"
|
[PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability. Originally it was called whenever rss or
total_vm got raised. Then many of those callsites were replaced by a timer
tick call from account_system_time. Now Frank van Maarseveen reports that to
be found inadequate. How about this? Works for Frank.
Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm. Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths. Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit. Handle
mm->hiwater_vm in the same way, though it's much less of an issue. Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.
And there has been no collector of these hiwater statistics in the tree. The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).
There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high. A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.
What locking? None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact. But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 08:16:18 +07:00
|
|
|
"VmHWM:\t%8lu kB\n"
|
2005-04-17 05:20:36 +07:00
|
|
|
"VmRSS:\t%8lu kB\n"
|
|
|
|
"VmData:\t%8lu kB\n"
|
|
|
|
"VmStk:\t%8lu kB\n"
|
|
|
|
"VmExe:\t%8lu kB\n"
|
|
|
|
"VmLib:\t%8lu kB\n"
|
|
|
|
"VmPTE:\t%8lu kB\n",
|
[PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability. Originally it was called whenever rss or
total_vm got raised. Then many of those callsites were replaced by a timer
tick call from account_system_time. Now Frank van Maarseveen reports that to
be found inadequate. How about this? Works for Frank.
Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm. Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths. Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit. Handle
mm->hiwater_vm in the same way, though it's much less of an issue. Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.
And there has been no collector of these hiwater statistics in the tree. The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).
There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high. A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.
What locking? None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact. But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 08:16:18 +07:00
|
|
|
hiwater_vm << (PAGE_SHIFT-10),
|
|
|
|
(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
|
2005-04-17 05:20:36 +07:00
|
|
|
mm->locked_vm << (PAGE_SHIFT-10),
|
[PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability. Originally it was called whenever rss or
total_vm got raised. Then many of those callsites were replaced by a timer
tick call from account_system_time. Now Frank van Maarseveen reports that to
be found inadequate. How about this? Works for Frank.
Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm. Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths. Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit. Handle
mm->hiwater_vm in the same way, though it's much less of an issue. Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.
And there has been no collector of these hiwater statistics in the tree. The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).
There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high. A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.
What locking? None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact. But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 08:16:18 +07:00
|
|
|
hiwater_rss << (PAGE_SHIFT-10),
|
|
|
|
total_rss << (PAGE_SHIFT-10),
|
2005-04-17 05:20:36 +07:00
|
|
|
data << (PAGE_SHIFT-10),
|
|
|
|
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
|
|
|
|
(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long task_vsize(struct mm_struct *mm)
|
|
|
|
{
|
|
|
|
return PAGE_SIZE * mm->total_vm;
|
|
|
|
}
|
|
|
|
|
|
|
|
int task_statm(struct mm_struct *mm, int *shared, int *text,
|
|
|
|
int *data, int *resident)
|
|
|
|
{
|
2005-10-30 08:16:05 +07:00
|
|
|
*shared = get_mm_counter(mm, file_rss);
|
2005-04-17 05:20:36 +07:00
|
|
|
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
|
|
|
|
>> PAGE_SHIFT;
|
|
|
|
*data = mm->total_vm - mm->shared_vm;
|
2005-10-30 08:16:05 +07:00
|
|
|
*resident = *shared + get_mm_counter(mm, anon_rss);
|
2005-04-17 05:20:36 +07:00
|
|
|
return mm->total_vm;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void pad_len_spaces(struct seq_file *m, int len)
|
|
|
|
{
|
|
|
|
len = 25 + sizeof(void*) * 6 - len;
|
|
|
|
if (len < 1)
|
|
|
|
len = 1;
|
|
|
|
seq_printf(m, "%*c", len, ' ');
|
|
|
|
}
|
|
|
|
|
2008-02-05 13:29:03 +07:00
|
|
|
static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
if (vma && vma != priv->tail_vma) {
|
|
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
mmput(mm);
|
|
|
|
}
|
|
|
|
}
|
2008-02-05 13:28:56 +07:00
|
|
|
|
2008-02-05 13:29:03 +07:00
|
|
|
static void *m_start(struct seq_file *m, loff_t *pos)
|
2005-09-04 05:55:10 +07:00
|
|
|
{
|
2008-02-05 13:29:03 +07:00
|
|
|
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
|
|
|
|
* mmap_cache 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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (last_addr == -1UL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
|
|
|
|
if (!priv->task)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
mm = mm_for_maps(priv->task);
|
|
|
|
if (!mm)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
tail_vma = get_gate_vma(priv->task);
|
|
|
|
priv->tail_vma = tail_vma;
|
|
|
|
|
|
|
|
/* Start with last addr hint */
|
|
|
|
vma = find_vma(mm, last_addr);
|
|
|
|
if (last_addr && vma) {
|
|
|
|
vma = vma->vm_next;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
vma = vma->vm_next;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (l != mm->map_count)
|
|
|
|
tail_vma = NULL; /* After gate vma */
|
|
|
|
|
|
|
|
out:
|
|
|
|
if (vma)
|
|
|
|
return vma;
|
|
|
|
|
|
|
|
/* End of vmas has been reached */
|
|
|
|
m->version = (tail_vma != NULL)? 0: -1UL;
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
mmput(mm);
|
|
|
|
return tail_vma;
|
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
|
|
|
|
(*pos)++;
|
|
|
|
if (vma && (vma != tail_vma) && vma->vm_next)
|
|
|
|
return vma->vm_next;
|
|
|
|
vma_stop(priv, vma);
|
|
|
|
return (vma != tail_vma)? tail_vma: NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void m_stop(struct seq_file *m, void *v)
|
|
|
|
{
|
|
|
|
struct proc_maps_private *priv = m->private;
|
|
|
|
struct vm_area_struct *vma = v;
|
|
|
|
|
|
|
|
vma_stop(priv, vma);
|
|
|
|
if (priv->task)
|
|
|
|
put_task_struct(priv->task);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int do_maps_open(struct inode *inode, struct file *file,
|
2008-02-08 19:21:19 +07:00
|
|
|
const struct seq_operations *ops)
|
2008-02-05 13:29:03 +07:00
|
|
|
{
|
|
|
|
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 ret;
|
|
|
|
}
|
2005-09-04 05:55:10 +07:00
|
|
|
|
2008-02-05 13:29:02 +07:00
|
|
|
static int show_map(struct seq_file *m, void *v)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2006-06-26 14:25:55 +07:00
|
|
|
struct proc_maps_private *priv = m->private;
|
|
|
|
struct task_struct *task = priv->task;
|
2005-09-04 05:55:10 +07:00
|
|
|
struct vm_area_struct *vma = v;
|
|
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
int flags = vma->vm_flags;
|
2005-04-17 05:20:36 +07:00
|
|
|
unsigned long ino = 0;
|
|
|
|
dev_t dev = 0;
|
|
|
|
int len;
|
|
|
|
|
Security: split proc ptrace checking into read vs. attach
Enable security modules to distinguish reading of process state via
proc from full ptrace access by renaming ptrace_may_attach to
ptrace_may_access and adding a mode argument indicating whether only
read access or full attach access is requested. This allows security
modules to permit access to reading process state without granting
full ptrace access. The base DAC/capability checking remains unchanged.
Read access to /proc/pid/mem continues to apply a full ptrace attach
check since check_mem_permission() already requires the current task
to already be ptracing the target. The other ptrace checks within
proc for elements like environ, maps, and fds are changed to pass the
read mode instead of attach.
In the SELinux case, we model such reading of process state as a
reading of a proc file labeled with the target process' label. This
enables SELinux policy to permit such reading of process state without
permitting control or manipulation of the target process, as there are
a number of cases where programs probe for such information via proc
but do not need to be able to control the target (e.g. procps,
lsof, PolicyKit, ConsoleKit). At present we have to choose between
allowing full ptrace in policy (more permissive than required/desired)
or breaking functionality (or in some cases just silencing the denials
via dontaudit rules but this can hide genuine attacks).
This version of the patch incorporates comments from Casey Schaufler
(change/replace existing ptrace_may_attach interface, pass access
mode), and Chris Wright (provide greater consistency in the checking).
Note that like their predecessors __ptrace_may_attach and
ptrace_may_attach, the __ptrace_may_access and ptrace_may_access
interfaces use different return value conventions from each other (0
or -errno vs. 1 or 0). I retained this difference to avoid any
changes to the caller logic but made the difference clearer by
changing the latter interface to return a bool rather than an int and
by adding a comment about it to ptrace.h for any future callers.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 19:32:49 +07:00
|
|
|
if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
|
2007-05-08 14:26:04 +07:00
|
|
|
return -EACCES;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
if (file) {
|
2006-12-08 17:36:36 +07:00
|
|
|
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
|
2005-04-17 05:20:36 +07:00
|
|
|
dev = inode->i_sb->s_dev;
|
|
|
|
ino = inode->i_ino;
|
|
|
|
}
|
|
|
|
|
/proc/self/maps doesn't display the real file offset
This addresses
http://bugzilla.kernel.org/show_bug.cgi?id=11318
In function show_map (file: fs/proc/task_mmu.c), if vma->vm_pgoff > 2^20
than (vma->vm_pgoff << PAGE_SIZE) is greater than 2^32 (with PAGE_SIZE
equal to 4096 (i.e. 2^12). The next seq_printf use an unsigned long for
the conversion of (vma->vm_pgoff << PAGE_SIZE), as a result the offset
value displayed in /proc/self/maps is truncated if the page offset is
greater than 2^20.
A test that shows this issue:
#define _GNU_SOURCE
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <stdlib.h>
#include <stdio.h>
#include <fcntl.h>
#include <unistd.h>
#include <string.h>
#define PAGE_SIZE (getpagesize())
#if __i386__
# define U64_STR "%llx"
#elif __x86_64
# define U64_STR "%lx"
#else
# error "Architecture Unsupported"
#endif
int main(int argc, char *argv[])
{
int fd;
char *addr;
off64_t offset = 0x10000000;
char *filename = "/dev/zero";
fd = open(filename, O_RDONLY);
if (fd < 0) {
perror("open");
return 1;
}
offset *= 0x10;
printf("offset = " U64_STR "\n", offset);
addr = (char*)mmap64(NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd,
offset);
if ((void*)addr == MAP_FAILED) {
perror("mmap64");
return 1;
}
{
FILE *fmaps;
char *line = NULL;
size_t len = 0;
ssize_t read;
size_t filename_len = strlen(filename);
fmaps = fopen("/proc/self/maps", "r");
if (!fmaps) {
perror("fopen");
return 1;
}
while ((read = getline(&line, &len, fmaps)) != -1) {
if ((read > filename_len + 1)
&& (strncmp(&line[read - filename_len - 1], filename, filename_len) == 0))
printf("%s", line);
}
if (line)
free(line);
fclose(fmaps);
}
close(fd);
return 0;
}
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Clement Calmels <cboulte@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-21 04:09:00 +07:00
|
|
|
seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
|
2005-09-04 05:55:10 +07:00
|
|
|
vma->vm_start,
|
|
|
|
vma->vm_end,
|
2005-04-17 05:20:36 +07:00
|
|
|
flags & VM_READ ? 'r' : '-',
|
|
|
|
flags & VM_WRITE ? 'w' : '-',
|
|
|
|
flags & VM_EXEC ? 'x' : '-',
|
|
|
|
flags & VM_MAYSHARE ? 's' : 'p',
|
/proc/self/maps doesn't display the real file offset
This addresses
http://bugzilla.kernel.org/show_bug.cgi?id=11318
In function show_map (file: fs/proc/task_mmu.c), if vma->vm_pgoff > 2^20
than (vma->vm_pgoff << PAGE_SIZE) is greater than 2^32 (with PAGE_SIZE
equal to 4096 (i.e. 2^12). The next seq_printf use an unsigned long for
the conversion of (vma->vm_pgoff << PAGE_SIZE), as a result the offset
value displayed in /proc/self/maps is truncated if the page offset is
greater than 2^20.
A test that shows this issue:
#define _GNU_SOURCE
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <stdlib.h>
#include <stdio.h>
#include <fcntl.h>
#include <unistd.h>
#include <string.h>
#define PAGE_SIZE (getpagesize())
#if __i386__
# define U64_STR "%llx"
#elif __x86_64
# define U64_STR "%lx"
#else
# error "Architecture Unsupported"
#endif
int main(int argc, char *argv[])
{
int fd;
char *addr;
off64_t offset = 0x10000000;
char *filename = "/dev/zero";
fd = open(filename, O_RDONLY);
if (fd < 0) {
perror("open");
return 1;
}
offset *= 0x10;
printf("offset = " U64_STR "\n", offset);
addr = (char*)mmap64(NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd,
offset);
if ((void*)addr == MAP_FAILED) {
perror("mmap64");
return 1;
}
{
FILE *fmaps;
char *line = NULL;
size_t len = 0;
ssize_t read;
size_t filename_len = strlen(filename);
fmaps = fopen("/proc/self/maps", "r");
if (!fmaps) {
perror("fopen");
return 1;
}
while ((read = getline(&line, &len, fmaps)) != -1) {
if ((read > filename_len + 1)
&& (strncmp(&line[read - filename_len - 1], filename, filename_len) == 0))
printf("%s", line);
}
if (line)
free(line);
fclose(fmaps);
}
close(fd);
return 0;
}
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Clement Calmels <cboulte@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-21 04:09:00 +07:00
|
|
|
((loff_t)vma->vm_pgoff) << PAGE_SHIFT,
|
2005-04-17 05:20:36 +07:00
|
|
|
MAJOR(dev), MINOR(dev), ino, &len);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Print the dentry name for named mappings, and a
|
|
|
|
* special [heap] marker for the heap:
|
|
|
|
*/
|
2005-09-04 05:55:10 +07:00
|
|
|
if (file) {
|
2005-04-17 05:20:36 +07:00
|
|
|
pad_len_spaces(m, len);
|
2008-02-15 10:38:43 +07:00
|
|
|
seq_path(m, &file->f_path, "\n");
|
2005-04-17 05:20:36 +07:00
|
|
|
} else {
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 16:53:50 +07:00
|
|
|
const char *name = arch_vma_name(vma);
|
|
|
|
if (!name) {
|
|
|
|
if (mm) {
|
|
|
|
if (vma->vm_start <= mm->start_brk &&
|
2005-09-04 05:55:10 +07:00
|
|
|
vma->vm_end >= mm->brk) {
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 16:53:50 +07:00
|
|
|
name = "[heap]";
|
|
|
|
} else if (vma->vm_start <= mm->start_stack &&
|
|
|
|
vma->vm_end >= mm->start_stack) {
|
|
|
|
name = "[stack]";
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 16:53:50 +07:00
|
|
|
} else {
|
|
|
|
name = "[vdso]";
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 16:53:50 +07:00
|
|
|
}
|
|
|
|
if (name) {
|
2005-04-17 05:20:36 +07:00
|
|
|
pad_len_spaces(m, len);
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 16:53:50 +07:00
|
|
|
seq_puts(m, name);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
seq_putc(m, '\n');
|
2005-09-04 05:55:10 +07:00
|
|
|
|
|
|
|
if (m->count < m->size) /* vma is copied successfully */
|
|
|
|
m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
|
2005-04-17 05:20:36 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-02-08 19:21:19 +07:00
|
|
|
static const struct seq_operations proc_pid_maps_op = {
|
2008-02-05 13:29:03 +07:00
|
|
|
.start = m_start,
|
|
|
|
.next = m_next,
|
|
|
|
.stop = m_stop,
|
|
|
|
.show = show_map
|
|
|
|
};
|
|
|
|
|
|
|
|
static int 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,
|
|
|
|
.read = seq_read,
|
|
|
|
.llseek = seq_lseek,
|
|
|
|
.release = seq_release_private,
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Proportional Set Size(PSS): my share of RSS.
|
|
|
|
*
|
|
|
|
* PSS of a process is the count of pages it has in memory, where each
|
|
|
|
* page is divided by the number of processes sharing it. So if a
|
|
|
|
* process has 1000 pages all to itself, and 1000 shared with one other
|
|
|
|
* process, its PSS will be 1500.
|
|
|
|
*
|
|
|
|
* To keep (accumulated) division errors low, we adopt a 64bit
|
|
|
|
* fixed-point pss counter to minimize division errors. So (pss >>
|
|
|
|
* PSS_SHIFT) would be the real byte count.
|
|
|
|
*
|
|
|
|
* A shift of 12 before division means (assuming 4K page size):
|
|
|
|
* - 1M 3-user-pages add up to 8KB errors;
|
|
|
|
* - supports mapcount up to 2^24, or 16M;
|
|
|
|
* - supports PSS up to 2^52 bytes, or 4PB.
|
|
|
|
*/
|
|
|
|
#define PSS_SHIFT 12
|
|
|
|
|
2008-02-05 13:29:07 +07:00
|
|
|
#ifdef CONFIG_PROC_PAGE_MONITOR
|
2008-04-28 16:12:55 +07:00
|
|
|
struct mem_size_stats {
|
2008-02-05 13:29:03 +07:00
|
|
|
struct vm_area_struct *vma;
|
|
|
|
unsigned long resident;
|
|
|
|
unsigned long shared_clean;
|
|
|
|
unsigned long shared_dirty;
|
|
|
|
unsigned long private_clean;
|
|
|
|
unsigned long private_dirty;
|
|
|
|
unsigned long referenced;
|
2008-04-28 16:12:55 +07:00
|
|
|
unsigned long swap;
|
2008-02-05 13:29:03 +07:00
|
|
|
u64 pss;
|
|
|
|
};
|
|
|
|
|
2008-02-05 13:29:01 +07:00
|
|
|
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
|
2008-06-13 05:21:47 +07:00
|
|
|
struct mm_walk *walk)
|
2005-09-04 05:55:10 +07:00
|
|
|
{
|
2008-06-13 05:21:47 +07:00
|
|
|
struct mem_size_stats *mss = walk->private;
|
2008-02-05 13:29:01 +07:00
|
|
|
struct vm_area_struct *vma = mss->vma;
|
2005-09-04 05:55:10 +07:00
|
|
|
pte_t *pte, ptent;
|
2005-10-30 08:16:27 +07:00
|
|
|
spinlock_t *ptl;
|
2005-09-04 05:55:10 +07:00
|
|
|
struct page *page;
|
2008-02-05 13:28:56 +07:00
|
|
|
int mapcount;
|
2005-09-04 05:55:10 +07:00
|
|
|
|
2005-10-30 08:16:27 +07:00
|
|
|
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
|
smaps: extract pmd walker from smaps code
Extracts the pmd walker from smaps-specific code in fs/proc/task_mmu.c.
The new struct pmd_walker includes the struct vm_area_struct of the memory to
walk over. Iteration begins at the vma->vm_start and completes at
vma->vm_end. A pointer to another data structure may be stored in the private
field such as struct mem_size_stats, which acts as the smaps accumulator. For
each pmd in the VMA, the action function is called with a pointer to its
struct vm_area_struct, a pointer to the pmd_t, its start and end addresses,
and the private field.
The interface for walking pmd's in a VMA for fs/proc/task_mmu.c is now:
void for_each_pmd(struct vm_area_struct *vma,
void (*action)(struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr,
unsigned long end,
void *private),
void *private);
Since the pmd walker is now extracted from the smaps code, smaps_one_pmd() is
invoked for each pmd in the VMA. Its behavior and efficiency is identical to
the existing implementation.
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-07 04:49:21 +07:00
|
|
|
for (; addr != end; pte++, addr += PAGE_SIZE) {
|
2005-09-04 05:55:10 +07:00
|
|
|
ptent = *pte;
|
2008-04-28 16:12:55 +07:00
|
|
|
|
|
|
|
if (is_swap_pte(ptent)) {
|
|
|
|
mss->swap += PAGE_SIZE;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2005-10-30 08:16:27 +07:00
|
|
|
if (!pte_present(ptent))
|
2005-09-04 05:55:10 +07:00
|
|
|
continue;
|
|
|
|
|
|
|
|
mss->resident += PAGE_SIZE;
|
2006-03-07 06:42:58 +07:00
|
|
|
|
|
|
|
page = vm_normal_page(vma, addr, ptent);
|
|
|
|
if (!page)
|
2005-09-04 05:55:10 +07:00
|
|
|
continue;
|
|
|
|
|
2007-05-07 04:49:22 +07:00
|
|
|
/* Accumulate the size in pages that have been accessed. */
|
|
|
|
if (pte_young(ptent) || PageReferenced(page))
|
|
|
|
mss->referenced += PAGE_SIZE;
|
2008-02-05 13:28:56 +07:00
|
|
|
mapcount = page_mapcount(page);
|
|
|
|
if (mapcount >= 2) {
|
2005-09-04 05:55:10 +07:00
|
|
|
if (pte_dirty(ptent))
|
|
|
|
mss->shared_dirty += PAGE_SIZE;
|
|
|
|
else
|
|
|
|
mss->shared_clean += PAGE_SIZE;
|
2008-02-05 13:28:56 +07:00
|
|
|
mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
|
2005-09-04 05:55:10 +07:00
|
|
|
} else {
|
|
|
|
if (pte_dirty(ptent))
|
|
|
|
mss->private_dirty += PAGE_SIZE;
|
|
|
|
else
|
|
|
|
mss->private_clean += PAGE_SIZE;
|
2008-02-05 13:28:56 +07:00
|
|
|
mss->pss += (PAGE_SIZE << PSS_SHIFT);
|
2005-09-04 05:55:10 +07:00
|
|
|
}
|
smaps: extract pmd walker from smaps code
Extracts the pmd walker from smaps-specific code in fs/proc/task_mmu.c.
The new struct pmd_walker includes the struct vm_area_struct of the memory to
walk over. Iteration begins at the vma->vm_start and completes at
vma->vm_end. A pointer to another data structure may be stored in the private
field such as struct mem_size_stats, which acts as the smaps accumulator. For
each pmd in the VMA, the action function is called with a pointer to its
struct vm_area_struct, a pointer to the pmd_t, its start and end addresses,
and the private field.
The interface for walking pmd's in a VMA for fs/proc/task_mmu.c is now:
void for_each_pmd(struct vm_area_struct *vma,
void (*action)(struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr,
unsigned long end,
void *private),
void *private);
Since the pmd walker is now extracted from the smaps code, smaps_one_pmd() is
invoked for each pmd in the VMA. Its behavior and efficiency is identical to
the existing implementation.
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-07 04:49:21 +07:00
|
|
|
}
|
2005-10-30 08:16:27 +07:00
|
|
|
pte_unmap_unlock(pte - 1, ptl);
|
|
|
|
cond_resched();
|
2008-02-05 13:29:01 +07:00
|
|
|
return 0;
|
2005-09-04 05:55:10 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static int show_smap(struct seq_file *m, void *v)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma = v;
|
|
|
|
struct mem_size_stats mss;
|
2008-02-05 13:29:02 +07:00
|
|
|
int ret;
|
2008-06-13 05:21:47 +07:00
|
|
|
struct mm_walk smaps_walk = {
|
|
|
|
.pmd_entry = smaps_pte_range,
|
|
|
|
.mm = vma->vm_mm,
|
|
|
|
.private = &mss,
|
|
|
|
};
|
2005-09-04 05:55:10 +07:00
|
|
|
|
|
|
|
memset(&mss, 0, sizeof mss);
|
2008-02-05 13:29:01 +07:00
|
|
|
mss.vma = vma;
|
2006-03-07 06:42:57 +07:00
|
|
|
if (vma->vm_mm && !is_vm_hugetlb_page(vma))
|
2008-06-13 05:21:47 +07:00
|
|
|
walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
|
2008-02-05 13:29:02 +07:00
|
|
|
|
|
|
|
ret = show_map(m, v);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
seq_printf(m,
|
|
|
|
"Size: %8lu kB\n"
|
|
|
|
"Rss: %8lu kB\n"
|
|
|
|
"Pss: %8lu kB\n"
|
|
|
|
"Shared_Clean: %8lu kB\n"
|
|
|
|
"Shared_Dirty: %8lu kB\n"
|
|
|
|
"Private_Clean: %8lu kB\n"
|
|
|
|
"Private_Dirty: %8lu kB\n"
|
2008-04-28 16:12:55 +07:00
|
|
|
"Referenced: %8lu kB\n"
|
|
|
|
"Swap: %8lu kB\n",
|
2008-02-05 13:29:02 +07:00
|
|
|
(vma->vm_end - vma->vm_start) >> 10,
|
|
|
|
mss.resident >> 10,
|
|
|
|
(unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
|
|
|
|
mss.shared_clean >> 10,
|
|
|
|
mss.shared_dirty >> 10,
|
|
|
|
mss.private_clean >> 10,
|
|
|
|
mss.private_dirty >> 10,
|
2008-04-28 16:12:55 +07:00
|
|
|
mss.referenced >> 10,
|
|
|
|
mss.swap >> 10);
|
2008-02-05 13:29:02 +07:00
|
|
|
|
|
|
|
return ret;
|
2005-09-04 05:55:10 +07:00
|
|
|
}
|
|
|
|
|
2008-02-08 19:21:19 +07:00
|
|
|
static const struct seq_operations proc_pid_smaps_op = {
|
2008-02-05 13:29:03 +07:00
|
|
|
.start = m_start,
|
|
|
|
.next = m_next,
|
|
|
|
.stop = m_stop,
|
|
|
|
.show = show_smap
|
|
|
|
};
|
|
|
|
|
|
|
|
static int 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,
|
|
|
|
.read = seq_read,
|
|
|
|
.llseek = seq_lseek,
|
|
|
|
.release = seq_release_private,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
|
2008-06-13 05:21:47 +07:00
|
|
|
unsigned long end, struct mm_walk *walk)
|
2008-02-05 13:29:03 +07:00
|
|
|
{
|
2008-06-13 05:21:47 +07:00
|
|
|
struct vm_area_struct *vma = walk->private;
|
2008-02-05 13:29:03 +07:00
|
|
|
pte_t *pte, ptent;
|
|
|
|
spinlock_t *ptl;
|
|
|
|
struct page *page;
|
|
|
|
|
|
|
|
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
|
|
|
|
for (; addr != end; pte++, addr += PAGE_SIZE) {
|
|
|
|
ptent = *pte;
|
|
|
|
if (!pte_present(ptent))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
page = vm_normal_page(vma, addr, ptent);
|
|
|
|
if (!page)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/* Clear accessed and referenced bits. */
|
|
|
|
ptep_test_and_clear_young(vma, addr, pte);
|
|
|
|
ClearPageReferenced(page);
|
|
|
|
}
|
|
|
|
pte_unmap_unlock(pte - 1, ptl);
|
|
|
|
cond_resched();
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-02-05 13:29:03 +07:00
|
|
|
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
|
|
|
|
size_t count, loff_t *ppos)
|
2007-05-07 04:49:24 +07:00
|
|
|
{
|
2008-02-05 13:29:03 +07:00
|
|
|
struct task_struct *task;
|
|
|
|
char buffer[PROC_NUMBUF], *end;
|
|
|
|
struct mm_struct *mm;
|
2007-05-07 04:49:24 +07:00
|
|
|
struct vm_area_struct *vma;
|
|
|
|
|
2008-02-05 13:29:03 +07:00
|
|
|
memset(buffer, 0, sizeof(buffer));
|
|
|
|
if (count > sizeof(buffer) - 1)
|
|
|
|
count = sizeof(buffer) - 1;
|
|
|
|
if (copy_from_user(buffer, buf, count))
|
|
|
|
return -EFAULT;
|
|
|
|
if (!simple_strtol(buffer, &end, 0))
|
|
|
|
return -EINVAL;
|
|
|
|
if (*end == '\n')
|
|
|
|
end++;
|
|
|
|
task = get_proc_task(file->f_path.dentry->d_inode);
|
|
|
|
if (!task)
|
|
|
|
return -ESRCH;
|
|
|
|
mm = get_task_mm(task);
|
|
|
|
if (mm) {
|
2008-07-06 02:29:05 +07:00
|
|
|
struct mm_walk clear_refs_walk = {
|
|
|
|
.pmd_entry = clear_refs_pte_range,
|
|
|
|
.mm = mm,
|
|
|
|
};
|
2008-02-05 13:29:03 +07:00
|
|
|
down_read(&mm->mmap_sem);
|
2008-06-13 05:21:47 +07:00
|
|
|
for (vma = mm->mmap; vma; vma = vma->vm_next) {
|
|
|
|
clear_refs_walk.private = vma;
|
2008-02-05 13:29:03 +07:00
|
|
|
if (!is_vm_hugetlb_page(vma))
|
2008-06-13 05:21:47 +07:00
|
|
|
walk_page_range(vma->vm_start, vma->vm_end,
|
|
|
|
&clear_refs_walk);
|
|
|
|
}
|
2008-02-05 13:29:03 +07:00
|
|
|
flush_tlb_mm(mm);
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
mmput(mm);
|
|
|
|
}
|
|
|
|
put_task_struct(task);
|
|
|
|
if (end - buffer == 0)
|
|
|
|
return -EIO;
|
|
|
|
return end - buffer;
|
2007-05-07 04:49:24 +07:00
|
|
|
}
|
|
|
|
|
2008-02-05 13:29:03 +07:00
|
|
|
const struct file_operations proc_clear_refs_operations = {
|
|
|
|
.write = clear_refs_write,
|
|
|
|
};
|
|
|
|
|
2008-02-05 13:29:04 +07:00
|
|
|
struct pagemapread {
|
2008-06-06 12:46:31 +07:00
|
|
|
u64 __user *out, *end;
|
2008-02-05 13:29:04 +07:00
|
|
|
};
|
|
|
|
|
2008-03-22 06:46:59 +07:00
|
|
|
#define PM_ENTRY_BYTES sizeof(u64)
|
|
|
|
#define PM_STATUS_BITS 3
|
|
|
|
#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
|
|
|
|
#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
|
|
|
|
#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
|
|
|
|
#define PM_PSHIFT_BITS 6
|
|
|
|
#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
|
|
|
|
#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
|
|
|
|
#define PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
|
|
|
|
#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1)
|
|
|
|
#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK)
|
|
|
|
|
|
|
|
#define PM_PRESENT PM_STATUS(4LL)
|
|
|
|
#define PM_SWAP PM_STATUS(2LL)
|
|
|
|
#define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT)
|
2008-02-05 13:29:04 +07:00
|
|
|
#define PM_END_OF_BUFFER 1
|
|
|
|
|
|
|
|
static int add_to_pagemap(unsigned long addr, u64 pfn,
|
|
|
|
struct pagemapread *pm)
|
|
|
|
{
|
|
|
|
if (put_user(pfn, pm->out))
|
|
|
|
return -EFAULT;
|
2008-06-06 12:46:31 +07:00
|
|
|
pm->out++;
|
|
|
|
if (pm->out >= pm->end)
|
|
|
|
return PM_END_OF_BUFFER;
|
2008-02-05 13:29:04 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int pagemap_pte_hole(unsigned long start, unsigned long end,
|
2008-06-13 05:21:47 +07:00
|
|
|
struct mm_walk *walk)
|
2008-02-05 13:29:04 +07:00
|
|
|
{
|
2008-06-13 05:21:47 +07:00
|
|
|
struct pagemapread *pm = walk->private;
|
2008-02-05 13:29:04 +07:00
|
|
|
unsigned long addr;
|
|
|
|
int err = 0;
|
|
|
|
for (addr = start; addr < end; addr += PAGE_SIZE) {
|
|
|
|
err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2008-04-28 16:12:11 +07:00
|
|
|
static u64 swap_pte_to_pagemap_entry(pte_t pte)
|
2008-02-05 13:29:04 +07:00
|
|
|
{
|
|
|
|
swp_entry_t e = pte_to_swp_entry(pte);
|
2008-03-22 06:46:59 +07:00
|
|
|
return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
|
2008-02-05 13:29:04 +07:00
|
|
|
}
|
|
|
|
|
2008-06-13 05:21:48 +07:00
|
|
|
static unsigned long pte_to_pagemap_entry(pte_t pte)
|
|
|
|
{
|
|
|
|
unsigned long pme = 0;
|
|
|
|
if (is_swap_pte(pte))
|
|
|
|
pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
|
|
|
|
| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
|
|
|
|
else if (pte_present(pte))
|
|
|
|
pme = PM_PFRAME(pte_pfn(pte))
|
|
|
|
| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
|
|
|
|
return pme;
|
|
|
|
}
|
|
|
|
|
2008-02-05 13:29:04 +07:00
|
|
|
static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
|
2008-06-13 05:21:47 +07:00
|
|
|
struct mm_walk *walk)
|
2008-02-05 13:29:04 +07:00
|
|
|
{
|
2008-06-13 05:21:48 +07:00
|
|
|
struct vm_area_struct *vma;
|
2008-06-13 05:21:47 +07:00
|
|
|
struct pagemapread *pm = walk->private;
|
2008-02-05 13:29:04 +07:00
|
|
|
pte_t *pte;
|
|
|
|
int err = 0;
|
|
|
|
|
2008-06-13 05:21:48 +07:00
|
|
|
/* find the first VMA at or above 'addr' */
|
|
|
|
vma = find_vma(walk->mm, addr);
|
2008-02-05 13:29:04 +07:00
|
|
|
for (; addr != end; addr += PAGE_SIZE) {
|
|
|
|
u64 pfn = PM_NOT_PRESENT;
|
2008-06-13 05:21:48 +07:00
|
|
|
|
|
|
|
/* 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);
|
|
|
|
|
|
|
|
/* 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)) {
|
|
|
|
pte = pte_offset_map(pmd, addr);
|
|
|
|
pfn = pte_to_pagemap_entry(*pte);
|
|
|
|
/* unmap before userspace copy */
|
|
|
|
pte_unmap(pte);
|
|
|
|
}
|
2008-02-05 13:29:04 +07:00
|
|
|
err = add_to_pagemap(addr, pfn, pm);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
cond_resched();
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* /proc/pid/pagemap - an array mapping virtual pages to pfns
|
|
|
|
*
|
2008-03-22 06:46:59 +07:00
|
|
|
* For each page in the address space, this file contains one 64-bit entry
|
|
|
|
* consisting of the following:
|
|
|
|
*
|
|
|
|
* Bits 0-55 page frame number (PFN) if present
|
|
|
|
* Bits 0-4 swap type if swapped
|
|
|
|
* Bits 5-55 swap offset if swapped
|
|
|
|
* Bits 55-60 page shift (page size = 1<<page shift)
|
|
|
|
* Bit 61 reserved for future use
|
|
|
|
* Bit 62 page swapped
|
|
|
|
* Bit 63 page present
|
|
|
|
*
|
|
|
|
* If the page is not present but in swap, then the PFN contains an
|
|
|
|
* encoding of the swap file number and the page's offset into the
|
|
|
|
* swap. Unmapped pages return a null PFN. This allows determining
|
2008-02-05 13:29:04 +07:00
|
|
|
* precisely which pages are mapped (or in swap) and comparing mapped
|
|
|
|
* pages between processes.
|
|
|
|
*
|
|
|
|
* Efficient users of this interface will use /proc/pid/maps to
|
|
|
|
* determine which areas of memory are actually mapped and llseek to
|
|
|
|
* skip over unmapped regions.
|
|
|
|
*/
|
|
|
|
static ssize_t pagemap_read(struct file *file, char __user *buf,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
|
|
|
|
struct page **pages, *page;
|
|
|
|
unsigned long uaddr, uend;
|
|
|
|
struct mm_struct *mm;
|
|
|
|
struct pagemapread pm;
|
|
|
|
int pagecount;
|
|
|
|
int ret = -ESRCH;
|
2008-07-22 04:21:36 +07:00
|
|
|
struct mm_walk pagemap_walk = {};
|
2008-07-05 15:02:01 +07:00
|
|
|
unsigned long src;
|
|
|
|
unsigned long svpfn;
|
|
|
|
unsigned long start_vaddr;
|
|
|
|
unsigned long end_vaddr;
|
2008-02-05 13:29:04 +07:00
|
|
|
|
|
|
|
if (!task)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EACCES;
|
Security: split proc ptrace checking into read vs. attach
Enable security modules to distinguish reading of process state via
proc from full ptrace access by renaming ptrace_may_attach to
ptrace_may_access and adding a mode argument indicating whether only
read access or full attach access is requested. This allows security
modules to permit access to reading process state without granting
full ptrace access. The base DAC/capability checking remains unchanged.
Read access to /proc/pid/mem continues to apply a full ptrace attach
check since check_mem_permission() already requires the current task
to already be ptracing the target. The other ptrace checks within
proc for elements like environ, maps, and fds are changed to pass the
read mode instead of attach.
In the SELinux case, we model such reading of process state as a
reading of a proc file labeled with the target process' label. This
enables SELinux policy to permit such reading of process state without
permitting control or manipulation of the target process, as there are
a number of cases where programs probe for such information via proc
but do not need to be able to control the target (e.g. procps,
lsof, PolicyKit, ConsoleKit). At present we have to choose between
allowing full ptrace in policy (more permissive than required/desired)
or breaking functionality (or in some cases just silencing the denials
via dontaudit rules but this can hide genuine attacks).
This version of the patch incorporates comments from Casey Schaufler
(change/replace existing ptrace_may_attach interface, pass access
mode), and Chris Wright (provide greater consistency in the checking).
Note that like their predecessors __ptrace_may_attach and
ptrace_may_attach, the __ptrace_may_access and ptrace_may_access
interfaces use different return value conventions from each other (0
or -errno vs. 1 or 0). I retained this difference to avoid any
changes to the caller logic but made the difference clearer by
changing the latter interface to return a bool rather than an int and
by adding a comment about it to ptrace.h for any future callers.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 19:32:49 +07:00
|
|
|
if (!ptrace_may_access(task, PTRACE_MODE_READ))
|
2008-03-14 02:32:35 +07:00
|
|
|
goto out_task;
|
2008-02-05 13:29:04 +07:00
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
/* file position must be aligned */
|
2008-06-06 12:46:31 +07:00
|
|
|
if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
|
2008-03-14 02:32:35 +07:00
|
|
|
goto out_task;
|
2008-02-05 13:29:04 +07:00
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
mm = get_task_mm(task);
|
|
|
|
if (!mm)
|
2008-03-14 02:32:35 +07:00
|
|
|
goto out_task;
|
2008-02-05 13:29:04 +07:00
|
|
|
|
2008-07-05 15:02:01 +07:00
|
|
|
|
2008-02-05 13:29:04 +07:00
|
|
|
uaddr = (unsigned long)buf & PAGE_MASK;
|
|
|
|
uend = (unsigned long)(buf + count);
|
|
|
|
pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
|
2008-07-05 15:02:01 +07:00
|
|
|
ret = 0;
|
|
|
|
if (pagecount == 0)
|
|
|
|
goto out_mm;
|
|
|
|
pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
|
|
|
|
ret = -ENOMEM;
|
2008-02-05 13:29:04 +07:00
|
|
|
if (!pages)
|
2008-03-14 02:32:35 +07:00
|
|
|
goto out_mm;
|
2008-02-05 13:29:04 +07:00
|
|
|
|
|
|
|
down_read(¤t->mm->mmap_sem);
|
|
|
|
ret = get_user_pages(current, current->mm, uaddr, pagecount,
|
|
|
|
1, 0, pages, NULL);
|
|
|
|
up_read(¤t->mm->mmap_sem);
|
|
|
|
|
|
|
|
if (ret < 0)
|
|
|
|
goto out_free;
|
|
|
|
|
2008-03-14 02:32:35 +07:00
|
|
|
if (ret != pagecount) {
|
|
|
|
pagecount = ret;
|
|
|
|
ret = -EFAULT;
|
|
|
|
goto out_pages;
|
|
|
|
}
|
|
|
|
|
2008-06-06 12:46:31 +07:00
|
|
|
pm.out = (u64 *)buf;
|
|
|
|
pm.end = (u64 *)(buf + count);
|
2008-02-05 13:29:04 +07:00
|
|
|
|
2008-07-05 15:02:01 +07:00
|
|
|
pagemap_walk.pmd_entry = pagemap_pte_range;
|
|
|
|
pagemap_walk.pte_hole = pagemap_pte_hole;
|
|
|
|
pagemap_walk.mm = mm;
|
|
|
|
pagemap_walk.private = ±
|
|
|
|
|
|
|
|
src = *ppos;
|
|
|
|
svpfn = src / PM_ENTRY_BYTES;
|
|
|
|
start_vaddr = svpfn << PAGE_SHIFT;
|
|
|
|
end_vaddr = TASK_SIZE_OF(task);
|
|
|
|
|
|
|
|
/* watch out for wraparound */
|
|
|
|
if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
|
|
|
|
start_vaddr = end_vaddr;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The odds are that this will stop walking way
|
|
|
|
* before end_vaddr, because the length of the
|
|
|
|
* user buffer is tracked in "pm", and the walk
|
|
|
|
* will stop when we hit the end of the buffer.
|
|
|
|
*/
|
|
|
|
ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk);
|
|
|
|
if (ret == PM_END_OF_BUFFER)
|
|
|
|
ret = 0;
|
|
|
|
/* don't need mmap_sem for these, but this looks cleaner */
|
|
|
|
*ppos += (char *)pm.out - buf;
|
|
|
|
if (!ret)
|
|
|
|
ret = (char *)pm.out - buf;
|
2008-02-05 13:29:04 +07:00
|
|
|
|
2008-03-14 02:32:35 +07:00
|
|
|
out_pages:
|
2008-02-05 13:29:04 +07:00
|
|
|
for (; pagecount; pagecount--) {
|
|
|
|
page = pages[pagecount-1];
|
|
|
|
if (!PageReserved(page))
|
|
|
|
SetPageDirty(page);
|
|
|
|
page_cache_release(page);
|
|
|
|
}
|
|
|
|
out_free:
|
|
|
|
kfree(pages);
|
2008-03-14 02:32:35 +07:00
|
|
|
out_mm:
|
|
|
|
mmput(mm);
|
2008-02-05 13:29:04 +07:00
|
|
|
out_task:
|
|
|
|
put_task_struct(task);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
const struct file_operations proc_pagemap_operations = {
|
|
|
|
.llseek = mem_lseek, /* borrow this */
|
|
|
|
.read = pagemap_read,
|
|
|
|
};
|
2008-02-05 13:29:07 +07:00
|
|
|
#endif /* CONFIG_PROC_PAGE_MONITOR */
|
2008-02-05 13:29:04 +07:00
|
|
|
|
2005-09-04 05:54:45 +07:00
|
|
|
#ifdef CONFIG_NUMA
|
2006-01-08 16:01:02 +07:00
|
|
|
extern int show_numa_map(struct seq_file *m, void *v);
|
2005-09-04 05:54:45 +07:00
|
|
|
|
2007-05-08 14:26:04 +07:00
|
|
|
static int show_numa_map_checked(struct seq_file *m, void *v)
|
|
|
|
{
|
|
|
|
struct proc_maps_private *priv = m->private;
|
|
|
|
struct task_struct *task = priv->task;
|
|
|
|
|
Security: split proc ptrace checking into read vs. attach
Enable security modules to distinguish reading of process state via
proc from full ptrace access by renaming ptrace_may_attach to
ptrace_may_access and adding a mode argument indicating whether only
read access or full attach access is requested. This allows security
modules to permit access to reading process state without granting
full ptrace access. The base DAC/capability checking remains unchanged.
Read access to /proc/pid/mem continues to apply a full ptrace attach
check since check_mem_permission() already requires the current task
to already be ptracing the target. The other ptrace checks within
proc for elements like environ, maps, and fds are changed to pass the
read mode instead of attach.
In the SELinux case, we model such reading of process state as a
reading of a proc file labeled with the target process' label. This
enables SELinux policy to permit such reading of process state without
permitting control or manipulation of the target process, as there are
a number of cases where programs probe for such information via proc
but do not need to be able to control the target (e.g. procps,
lsof, PolicyKit, ConsoleKit). At present we have to choose between
allowing full ptrace in policy (more permissive than required/desired)
or breaking functionality (or in some cases just silencing the denials
via dontaudit rules but this can hide genuine attacks).
This version of the patch incorporates comments from Casey Schaufler
(change/replace existing ptrace_may_attach interface, pass access
mode), and Chris Wright (provide greater consistency in the checking).
Note that like their predecessors __ptrace_may_attach and
ptrace_may_attach, the __ptrace_may_access and ptrace_may_access
interfaces use different return value conventions from each other (0
or -errno vs. 1 or 0). I retained this difference to avoid any
changes to the caller logic but made the difference clearer by
changing the latter interface to return a bool rather than an int and
by adding a comment about it to ptrace.h for any future callers.
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 19:32:49 +07:00
|
|
|
if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
|
2007-05-08 14:26:04 +07:00
|
|
|
return -EACCES;
|
|
|
|
|
|
|
|
return show_numa_map(m, v);
|
|
|
|
}
|
|
|
|
|
2008-02-08 19:21:19 +07:00
|
|
|
static const struct seq_operations proc_pid_numa_maps_op = {
|
2006-01-08 16:01:02 +07:00
|
|
|
.start = m_start,
|
|
|
|
.next = m_next,
|
|
|
|
.stop = m_stop,
|
2007-05-08 14:26:04 +07:00
|
|
|
.show = show_numa_map_checked
|
2005-09-04 05:54:45 +07:00
|
|
|
};
|
2006-06-26 14:25:48 +07:00
|
|
|
|
|
|
|
static int numa_maps_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
return do_maps_open(inode, file, &proc_pid_numa_maps_op);
|
|
|
|
}
|
|
|
|
|
2007-02-12 15:55:34 +07:00
|
|
|
const struct file_operations proc_numa_maps_operations = {
|
2006-06-26 14:25:48 +07:00
|
|
|
.open = numa_maps_open,
|
|
|
|
.read = seq_read,
|
|
|
|
.llseek = seq_lseek,
|
2006-06-26 14:25:55 +07:00
|
|
|
.release = seq_release_private,
|
2006-06-26 14:25:48 +07:00
|
|
|
};
|
2005-09-04 05:54:45 +07:00
|
|
|
#endif
|