Commit 3204de64 authored by Stefani Seibold's avatar Stefani Seibold Committed by James Toy

A patch to give 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.
Signed-off-by: default avatarStefani Seibold <stefani@seibold.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 037c2f68
...@@ -176,6 +176,7 @@ read the file /proc/PID/status: ...@@ -176,6 +176,7 @@ read the file /proc/PID/status:
CapBnd: ffffffffffffffff CapBnd: ffffffffffffffff
voluntary_ctxt_switches: 0 voluntary_ctxt_switches: 0
nonvoluntary_ctxt_switches: 1 nonvoluntary_ctxt_switches: 1
Stack usage: 12 kB
This shows you nearly the same information you would get if you viewed it with 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 the ps command. In fact, ps uses the proc file system to obtain its
...@@ -229,6 +230,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7) ...@@ -229,6 +230,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
Mems_allowed_list Same as previous, but in "list format" Mems_allowed_list Same as previous, but in "list format"
voluntary_ctxt_switches number of voluntary context switches voluntary_ctxt_switches number of voluntary context switches
nonvoluntary_ctxt_switches number of non 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) Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
...@@ -307,7 +309,7 @@ address perms offset dev inode pathname ...@@ -307,7 +309,7 @@ address perms offset dev inode pathname
08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
0804a000-0806b000 rw-p 00000000 00:00 0 [heap] 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
a7cb1000-a7cb2000 ---p 00000000 00:00 0 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 a7eb2000-a7eb3000 ---p 00000000 00:00 0
a7eb3000-a7ed5000 rw-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 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
...@@ -343,6 +345,7 @@ is not associated with a file: ...@@ -343,6 +345,7 @@ is not associated with a file:
[stack] = the stack of the main process [stack] = the stack of the main process
[vdso] = the "virtual dynamic shared object", [vdso] = the "virtual dynamic shared object",
the kernel system call handler 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. or if empty, the mapping is anonymous.
......
...@@ -1357,6 +1357,8 @@ int do_execve(char * filename, ...@@ -1357,6 +1357,8 @@ int do_execve(char * filename,
if (retval < 0) if (retval < 0)
goto out; goto out;
current->stack_start = current->mm->start_stack;
/* execve succeeded */ /* execve succeeded */
current->fs->in_exec = 0; current->fs->in_exec = 0;
current->in_execve = 0; current->in_execve = 0;
......
...@@ -321,6 +321,54 @@ static inline void task_context_switch_counts(struct seq_file *m, ...@@ -321,6 +321,54 @@ static inline void task_context_switch_counts(struct seq_file *m,
p->nivcsw); p->nivcsw);
} }
static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma,
struct task_struct *p)
{
unsigned long i;
struct page *page;
unsigned long stkpage;
stkpage = KSTK_ESP(p) & PAGE_MASK;
#ifdef CONFIG_STACK_GROWSUP
for (i = vma->vm_end; i-PAGE_SIZE > stkpage; i -= PAGE_SIZE) {
page = follow_page(vma, i-PAGE_SIZE, 0);
if (!IS_ERR(page) && page)
break;
}
return i - (p->stack_start & PAGE_MASK);
#else
for (i = vma->vm_start; i+PAGE_SIZE <= stkpage; i += PAGE_SIZE) {
page = follow_page(vma, i, 0);
if (!IS_ERR(page) && page)
break;
}
return (p->stack_start & PAGE_MASK) - i + PAGE_SIZE;
#endif
}
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, int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task) struct pid *pid, struct task_struct *task)
{ {
...@@ -340,6 +388,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, ...@@ -340,6 +388,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
task_show_regs(m, task); task_show_regs(m, task);
#endif #endif
task_context_switch_counts(m, task); task_context_switch_counts(m, task);
task_show_stack_usage(m, task);
return 0; return 0;
} }
...@@ -481,7 +530,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, ...@@ -481,7 +530,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
rsslim, rsslim,
mm ? mm->start_code : 0, mm ? mm->start_code : 0,
mm ? mm->end_code : 0, mm ? mm->end_code : 0,
(permitted && mm) ? mm->start_stack : 0, (permitted) ? task->stack_start : 0,
esp, esp,
eip, eip,
/* The signal information here is obsolete. /* The signal information here is obsolete.
......
...@@ -243,6 +243,25 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) ...@@ -243,6 +243,25 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
} else if (vma->vm_start <= mm->start_stack && } else if (vma->vm_start <= mm->start_stack &&
vma->vm_end >= mm->start_stack) { vma->vm_end >= mm->start_stack) {
name = "[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 { } else {
name = "[vdso]"; name = "[vdso]";
......
...@@ -1532,6 +1532,7 @@ struct task_struct { ...@@ -1532,6 +1532,7 @@ struct task_struct {
/* bitmask of trace recursion */ /* bitmask of trace recursion */
unsigned long trace_recursion; unsigned long trace_recursion;
#endif /* CONFIG_TRACING */ #endif /* CONFIG_TRACING */
unsigned long stack_start;
}; };
/* Future-safe accessor for struct task_struct's cpus_allowed. */ /* Future-safe accessor for struct task_struct's cpus_allowed. */
......
...@@ -1096,6 +1096,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, ...@@ -1096,6 +1096,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->bts = NULL; p->bts = NULL;
p->stack_start = stack_start;
/* Perform scheduler related setup. Assign this task to a CPU. */ /* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags); sched_fork(p, clone_flags);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment