Re: [PATCH] partial revert to show stack information in /proc/<pid>/status

[KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>]

> As announce here is the patch to partial revert the show stack
> information patch due a not accepted performance regression. It will be
> now show only the current stack usage, not the high water mark.
> 
> The path is only partial reverted because i need the other parts to do
> it in an other way.
> 
> There are now two possibilities solutions:
> 
> - create a new /proc/<pid>/stackinfo entry, which provides the reverted
> information and maybe others like the sigaltstack.
> - create a user space tool which use /proc/<pid>/pagemap
> 
> In both cases the information of task->stack_start and the KSTK_ESP is
> needed.
> 
> It will be also needed for an enhancement of the oom handler, where i
> free unused stack pages (the pages before the stack pointer) under high
> memory pressure. This is currently under work.

This explanation seems still strange. both task->stack_start and the KSTK_ESP are already exported
by /proc/{pid}/task/{tid}/stat. and This patch assume KSTK_ESP(task) - task->stack_start mean
StackUsage but it isn't the same as many people's assumption.

However, useless feature better than regression. probably I can ack this.


> 
> Andrew please apply this patch to 2.6.34-rc* tree.
> 
> Greetings,
> Stefani
> 
> Signed-off-by: Stefani Seibold <stefani@seibold.net>
> ---
>  Documentation/filesystems/proc.txt |    2 
>  fs/proc/array.c                    |   87 ++-----------------------------------
>  2 files changed, 8 insertions(+), 81 deletions(-)
> 
> diff -u -N -r -p linux-2.6.33-rc2.orig/fs/proc/array.c linux-2.6.33-rc2.new/fs/proc/array.c
> --- linux-2.6.33-rc2.orig/fs/proc/array.c	2009-12-27 23:37:04.817427024 +0100
> +++ linux-2.6.33-rc2.new/fs/proc/array.c	2010-01-02 14:36:53.794188418 +0100
> @@ -327,93 +327,20 @@ static inline void task_context_switch_c
>  			p->nivcsw);
>  }
>  
> -#ifdef CONFIG_MMU
> -
> -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)
> +static inline void task_show_stack_usage(struct seq_file *m,
> +						struct task_struct *task)
>  {
> -	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;
> +	unsigned long		usage;
>  
> +	if (task->mm) {
>  #ifdef CONFIG_STACK_GROWSUP
> -		if (pte_present(ptent) || is_swap_pte(ptent))
> -			ss->usage = addr - ss->startpage + PAGE_SIZE;
> +		usage = KSTK_ESP(task) - task->stack_start;
>  #else
> -		if (pte_present(ptent) || is_swap_pte(ptent)) {
> -			ss->usage = ss->startpage - addr + PAGE_SIZE;
> -			pte++;
> -			ret = 1;
> -			break;
> -		}
> +		usage = task->stack_start - KSTK_ESP(task);
>  #endif
> +		seq_printf(m, "Stack usage:\t%lu kB\n", (usage + 1023) >> 10);
>  	}
> -	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);
> -	}
> -}
> -#else
> -static void task_show_stack_usage(struct seq_file *m, struct task_struct *task)
> -{
>  }
> -#endif		/* CONFIG_MMU */
>  
>  static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
>  {
> diff -u -N -r -p linux-2.6.33-rc2.orig/Documentation/filesystems/proc.txt linux-2.6.33-rc2.new/Documentation/filesystems/proc.txt
> --- linux-2.6.33-rc2.orig/Documentation/filesystems/proc.txt	2009-12-27 23:37:01.098310709 +0100
> +++ linux-2.6.33-rc2.new/Documentation/filesystems/proc.txt	2010-01-02 14:30:39.059150340 +0100
> @@ -231,7 +231,7 @@ Table 1-2: Contents of the statm files (
>   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)
> + Stack usage:                stack usage in kB
>  ..............................................................................
>  
>  Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
> 
>