procfs: provide stack information for threads

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.

[[e-mail]: fs/proc/array.c now needs walk_page_range()]
Signed-off-by: Stefani Seibold <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Alexey Dobriyan <[e-mail]>
Cc: "Eric W. Biederman" <[e-mail]>
Cc: Randy Dunlap <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

Documentation/filesystems/proc.txt

···
   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
···
  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)
···
 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          [threadstack: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
···
  [stack]                  = the stack of the main process
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
+ [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 
  or if empty, the mapping is anonymous.
 

fs/exec.c

···
 	if (retval < 0)
 		goto out;
 
+	current->stack_start = current->mm->start_stack;
+
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;

fs/proc/array.c

···
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/swapops.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
···
 			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;
+			pte++;
+			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)
 {
···
 	task_show_regs(m, task);
 #endif
 	task_context_switch_counts(m, task);
+	task_show_stack_usage(m, task);
 	return 0;
 }
 
···
 		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.

fs/proc/task_mmu.c

···
 				} 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,
+						 "[threadstack:%08lx]",
+#ifdef CONFIG_STACK_GROWSUP
+						 vma->vm_end - stack_start
+#else
+						 stack_start - vma->vm_start
+#endif
+						);
+					}
 				}
 			} else {
 				name = "[vdso]";

include/linux/sched.h

···
 	/* bitmask of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
+	unsigned long stack_start;
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */

kernel/fork.c

···
 
 	p->bts = NULL;
 
+	p->stack_start = stack_start;
+
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 

mm/Makefile

···
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   page_isolation.o mm_init.o mmu_context.o $(mmu-y)
+			   page_isolation.o mm_init.o mmu_context.o \
+			   pagewalk.o $(mmu-y)
 obj-y += init-mm.o
 
-obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o