[patch 2/2] procfs: provide stack information for threads V0.9
From: Stefani Seibold
Date: Wed Jun 24 2009 - 08:04:28 EST
Hi,
this is the newest version of the formaly named "detailed stack info"
patch which give you a better overview of the userland application stack
usage, especially for embedded linux.
Currently you are only able to dump the main process/thread stack usage
which is showed in /proc/pid/status by the "VmStk" Value. But you get no
information about the consumed stack memory of the the threads.
There is an enhancement in the /proc/<pid>/{task/*,}/*maps and which
marks the vm mapping where the thread stack pointer reside with "[thread
stack xxxxxxxx]". xxxxxxxx is the maximum size of stack. This is a
value information, because libpthread doesn't set the start of the stack
to the top of the mapped area, depending of the pthread usage.
A sample output of /proc/<pid>/task/<tid>/maps looks like:
08048000-08049000 r-xp 00000000 03:00 8312 /opt/z
08049000-0804a000 rw-p 00001000 03:00 8312 /opt/z
0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
a7d12000-a7d13000 ---p 00000000 00:00 0
a7d13000-a7f13000 rw-p 00000000 00:00 0 [thread stack: 001ff4b4]
a7f13000-a7f14000 ---p 00000000 00:00 0
a7f14000-a7f36000 rw-p 00000000 00:00 0
a7f36000-a8069000 r-xp 00000000 03:00 4222 /lib/libc.so.6
a8069000-a806b000 r--p 00133000 03:00 4222 /lib/libc.so.6
a806b000-a806c000 rw-p 00135000 03:00 4222 /lib/libc.so.6
a806c000-a806f000 rw-p 00000000 00:00 0
a806f000-a8083000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
a8083000-a8084000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
a8084000-a8085000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
a8085000-a8088000 rw-p 00000000 00:00 0
a8088000-a80a4000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
a80a4000-a80a5000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
a80a5000-a80a6000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
afaf5000-afb0a000 rw-p 00000000 00:00 0 [stack]
ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
Also there is a new entry "stack usage" in /proc/<pid>/{task/*,}/status
which will you give the current stack usage in kb.
A sample output of /proc/self/status looks like:
Name: cat
State: R (running)
Tgid: 507
Pid: 507
.
.
.
CapBnd: fffffffffffffeff
voluntary_ctxt_switches: 0
nonvoluntary_ctxt_switches: 0
Stack usage: 12 kB
I also fixed stack base address in /proc/<pid>/{task/*,}/stat to the
base address of the associated thread stack and not the one of the main
process. This makes more sense.
Changes since last posting:
- use walk_page_range() to determinate the stack usage high water mark
- include swapped pages to the stack usage high water mark
The patch is against 2.6.30-rc7 and tested with on intel and ppc
architectures.
ChangeLog:
20. Jan 2009 V0.1
- First Version for Kernel 2.6.28.1
31. Mar 2009 V0.2
- Ported to Kernel 2.6.29
03. Jun 2009 V0.3
- Ported to Kernel 2.6.30
- Redesigned what was suggested by Ingo Molnar
- the thread watch monitor is gone
- the /proc/stackmon entry is also gone
- slim down
04. Jun 2009 V0.4
- Redesigned everything that was suggested by Andrew Morton
- slim down
04. Jun 2009 V0.5
- Code cleanup
06. Jun 2009 V0.6
- Fix missing mm->mmap_sem locking in function task_show_stack_usage()
- Code cleanup
10. Jun 2009 V0.7
- update Documentation/filesystem/proc.txt
10. Jun 2009 V0.8
- change maps/smaps output, displays now the max. stack size
Documentation/filesystems/proc.txt | 5 +-
fs/exec.c | 2
fs/proc/array.c | 85 ++++++++++++++++++++++++++++++++++++-
fs/proc/task_mmu.c | 19 ++++++++
include/linux/sched.h | 1
kernel/fork.c | 2
6 files changed, 112 insertions(+), 2 deletions(-)
Signed-off-by: Stefani Seibold <stefani@xxxxxxxxxxx>
diff -u -N -r linux-2.6.30.orig/Documentation/filesystems/proc.txt linux-2.6.30/Documentation/filesystems/proc.txt
--- linux-2.6.30.orig/Documentation/filesystems/proc.txt 2009-06-10 09:09:27.000000000 +0200
+++ linux-2.6.30/Documentation/filesystems/proc.txt 2009-06-10 09:07:46.000000000 +0200
@@ -176,6 +176,7 @@
CapBnd: ffffffffffffffff
voluntary_ctxt_switches: 0
nonvoluntary_ctxt_switches: 1
+ Stack usage: 12 kB
This shows you nearly the same information you would get if you viewed it with
the ps command. In fact, ps uses the proc file system to obtain its
@@ -229,6 +230,7 @@
Mems_allowed_list Same as previous, but in "list format"
voluntary_ctxt_switches number of voluntary context switches
nonvoluntary_ctxt_switches number of non voluntary context switches
+ Stack usage: stack usage high water mark (round up to page size)
..............................................................................
Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
@@ -307,7 +309,7 @@
08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0 [thread stack: 001ff4b4]
a7eb2000-a7eb3000 ---p 00000000 00:00 0
a7eb3000-a7ed5000 rw-p 00000000 00:00 0
a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
@@ -343,6 +345,7 @@
[stack] = the stack of the main process
[vdso] = the "virtual dynamic shared object",
the kernel system call handler
+ [thread stack, xxxxxxxx] = the stack of the thread, xxxxxxxx is the stack size
or if empty, the mapping is anonymous.
diff -u -N -r linux-2.6.30.orig/fs/exec.c linux-2.6.30/fs/exec.c
--- linux-2.6.30.orig/fs/exec.c 2009-06-04 09:29:47.000000000 +0200
+++ linux-2.6.30/fs/exec.c 2009-06-04 09:32:35.000000000 +0200
@@ -1328,6 +1328,8 @@
if (retval < 0)
goto out;
+ current->stack_start = current->mm->start_stack;
+
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
diff -u -N -r linux-2.6.30.orig/fs/proc/array.c linux-2.6.30/fs/proc/array.c
--- linux-2.6.30.orig/fs/proc/array.c 2009-06-04 09:29:47.000000000 +0200
+++ linux-2.6.30/fs/proc/array.c 2009-06-24 13:53:27.000000000 +0200
@@ -83,6 +83,8 @@
#include <linux/ptrace.h>
#include <linux/tracehook.h>
+#include <linux/swapops.h>
+
#include <asm/pgtable.h>
#include <asm/processor.h>
#include "internal.h"
@@ -321,6 +323,86 @@
p->nivcsw);
}
+struct stack_stats {
+ struct vm_area_struct *vma;
+ unsigned long startpage;
+ unsigned long usage;
+};
+
+static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ struct stack_stats *ss = walk->private;
+ struct vm_area_struct *vma = ss->vma;
+ pte_t *pte, ptent;
+ spinlock_t *ptl;
+ int ret = 0;
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ for (; addr != end; pte++, addr += PAGE_SIZE) {
+ ptent = *pte;
+
+#ifdef CONFIG_STACK_GROWSUP
+ if (pte_present(ptent) || is_swap_pte(ptent))
+ ss->usage = addr - ss->startpage + PAGE_SIZE;
+#else
+ if (pte_present(ptent) || is_swap_pte(ptent)) {
+ ss->usage = ss->startpage - addr + PAGE_SIZE;
+ ret = 1;
+ break;
+ }
+#endif
+ }
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+ return ret;
+}
+
+static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma,
+ struct task_struct *task)
+{
+ struct stack_stats ss;
+ struct mm_walk stack_walk = {
+ .pmd_entry = stack_usage_pte_range,
+ .mm = vma->vm_mm,
+ .private = &ss,
+ };
+
+ if (!vma->vm_mm || is_vm_hugetlb_page(vma))
+ return 0;
+
+ ss.vma = vma;
+ ss.startpage = task->stack_start & PAGE_MASK;
+ ss.usage = 0;
+
+#ifdef CONFIG_STACK_GROWSUP
+ walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end,
+ &stack_walk);
+#else
+ walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE,
+ &stack_walk);
+#endif
+ return ss.usage;
+}
+
+static inline void task_show_stack_usage(struct seq_file *m,
+ struct task_struct *task)
+{
+ struct vm_area_struct *vma;
+ struct mm_struct *mm = get_task_mm(task);
+
+ if (mm) {
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, task->stack_start);
+ if (vma)
+ seq_printf(m, "Stack usage:\t%lu kB\n",
+ get_stack_usage_in_bytes(vma, task) >> 10);
+
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ }
+}
+
int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -340,6 +422,7 @@
task_show_regs(m, task);
#endif
task_context_switch_counts(m, task);
+ task_show_stack_usage(m, task);
return 0;
}
@@ -481,7 +564,7 @@
rsslim,
mm ? mm->start_code : 0,
mm ? mm->end_code : 0,
- (permitted && mm) ? mm->start_stack : 0,
+ (permitted) ? task->stack_start : 0,
esp,
eip,
/* The signal information here is obsolete.
diff -u -N -r linux-2.6.30.orig/fs/proc/task_mmu.c linux-2.6.30/fs/proc/task_mmu.c
--- linux-2.6.30.orig/fs/proc/task_mmu.c 2009-06-04 09:29:47.000000000 +0200
+++ linux-2.6.30/fs/proc/task_mmu.c 2009-06-10 09:02:40.000000000 +0200
@@ -242,6 +242,25 @@
} else if (vma->vm_start <= mm->start_stack &&
vma->vm_end >= mm->start_stack) {
name = "[stack]";
+ } else {
+ unsigned long stack_start;
+ struct proc_maps_private *pmp;
+
+ pmp = m->private;
+ stack_start = pmp->task->stack_start;
+
+ if (vma->vm_start <= stack_start &&
+ vma->vm_end >= stack_start) {
+ pad_len_spaces(m, len);
+ seq_printf(m,
+ "[thread stack: %08lx]",
+#ifdef CONFIG_STACK_GROWSUP
+ vma->vm_end - stack_start
+#else
+ stack_start - vma->vm_start
+#endif
+ );
+ }
}
} else {
name = "[vdso]";
diff -u -N -r linux-2.6.30.orig/include/linux/sched.h linux-2.6.30/include/linux/sched.h
--- linux-2.6.30.orig/include/linux/sched.h 2009-06-04 09:29:47.000000000 +0200
+++ linux-2.6.30/include/linux/sched.h 2009-06-04 09:32:35.000000000 +0200
@@ -1429,6 +1429,7 @@
/* state flags for use by tracers */
unsigned long trace;
#endif
+ unsigned long stack_start;
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
diff -u -N -r linux-2.6.30.orig/kernel/fork.c linux-2.6.30/kernel/fork.c
--- linux-2.6.30.orig/kernel/fork.c 2009-06-04 09:29:47.000000000 +0200
+++ linux-2.6.30/kernel/fork.c 2009-06-04 13:15:35.000000000 +0200
@@ -1092,6 +1092,8 @@
if (unlikely(current->ptrace))
ptrace_fork(p, clone_flags);
+ p->stack_start = stack_start;
+
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/