[linux-2.6-block.git] / fs / proc / array.c

/*
 *  linux/fs/proc/array.c
 *
 *  Copyright (C) 1992  by Linus Torvalds
 *  based on ideas by Darren Senn
 *
 * Fixes:
 * Michael. K. Johnson: stat,statm extensions.
 *                      <johnsonm@stolaf.edu>
 *
 * Pauline Middelink :  Made cmdline,envline only break at '\0's, to
 *                      make sure SET_PROCTITLE works. Also removed
 *                      bad '!' which forced address recalculation for
 *                      EVERY character on the current page.
 *                      <middelin@polyware.iaf.nl>
 *
 * Danny ter Haar    :	added cpuinfo
 *			<dth@cistron.nl>
 *
 * Alessandro Rubini :  profile extension.
 *                      <rubini@ipvvis.unipv.it>
 *
 * Jeff Tranter      :  added BogoMips field to cpuinfo
 *                      <Jeff_Tranter@Mitel.COM>
 *
 * Bruno Haible      :  remove 4K limit for the maps file
 *			<haible@ma2s2.mathematik.uni-karlsruhe.de>
 *
 * Yves Arrouye      :  remove removal of trailing spaces in get_array.
 *			<Yves.Arrouye@marin.fdn.fr>
 *
 * Jerome Forissier  :  added per-CPU time information to /proc/stat
 *                      and /proc/<pid>/cpu extension
 *                      <forissier@isia.cma.fr>
 *			- Incorporation and non-SMP safe operation
 *			of forissier patch in 2.1.78 by
 *			Hans Marcus <crowbar@concepts.nl>
 *
 * aeb@cwi.nl        :  /proc/partitions
 *
 *
 * Alan Cox	     :  security fixes.
 *			<alan@lxorguk.ukuu.org.uk>
 *
 * Al Viro           :  safe handling of mm_struct
 *
 * Gerhard Wichert   :  added BIGMEM support
 * Siemens AG           <Gerhard.Wichert@pdb.siemens.de>
 *
 * Al Viro & Jeff Garzik :  moved most of the thing into base.c and
 *			 :  proc_misc.c. The rest may eventually go into
 *			 :  base.c too.
 */

#include <linux/types.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/tty.h>
#include <linux/string.h>
#include <linux/mman.h>
#include <linux/proc_fs.h>
#include <linux/ioport.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/signal.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/times.h>
#include <linux/cpuset.h>
#include <linux/rcupdate.h>
#include <linux/delayacct.h>
#include <linux/seq_file.h>
#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>
#include "internal.h"

static inline void task_name(struct seq_file *m, struct task_struct *p)
{
	int i;
	char *buf, *end;
	char *name;
	char tcomm[sizeof(p->comm)];

	get_task_comm(tcomm, p);

	seq_printf(m, "Name:\t");
	end = m->buf + m->size;
	buf = m->buf + m->count;
	name = tcomm;
	i = sizeof(tcomm);
	while (i && (buf < end)) {
		unsigned char c = *name;
		name++;
		i--;
		*buf = c;
		if (!c)
			break;
		if (c == '\\') {
			buf++;
			if (buf < end)
				*buf++ = c;
			continue;
		}
		if (c == '\n') {
			*buf++ = '\\';
			if (buf < end)
				*buf++ = 'n';
			continue;
		}
		buf++;
	}
	m->count = buf - m->buf;
	seq_printf(m, "\n");
}

/*
 * The task state array is a strange "bitmap" of
 * reasons to sleep. Thus "running" is zero, and
 * you can test for combinations of others with
 * simple bit tests.
 */
static const char *task_state_array[] = {
	"R (running)",		/*  0 */
	"S (sleeping)",		/*  1 */
	"D (disk sleep)",	/*  2 */
	"T (stopped)",		/*  4 */
	"T (tracing stop)",	/*  8 */
	"Z (zombie)",		/* 16 */
	"X (dead)"		/* 32 */
};

static inline const char *get_task_state(struct task_struct *tsk)
{
	unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state;
	const char **p = &task_state_array[0];

	while (state) {
		p++;
		state >>= 1;
	}
	return *p;
}

static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
				struct pid *pid, struct task_struct *p)
{
	struct group_info *group_info;
	int g;
	struct fdtable *fdt = NULL;
	const struct cred *cred;
	pid_t ppid, tpid;

	rcu_read_lock();
	ppid = pid_alive(p) ?
		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
	tpid = 0;
	if (pid_alive(p)) {
		struct task_struct *tracer = tracehook_tracer_task(p);
		if (tracer)
			tpid = task_pid_nr_ns(tracer, ns);
	}
	cred = get_cred((struct cred *) __task_cred(p));
	seq_printf(m,
		"State:\t%s\n"
		"Tgid:\t%d\n"
		"Pid:\t%d\n"
		"PPid:\t%d\n"
		"TracerPid:\t%d\n"
		"Uid:\t%d\t%d\t%d\t%d\n"
		"Gid:\t%d\t%d\t%d\t%d\n",
		get_task_state(p),
		task_tgid_nr_ns(p, ns),
		pid_nr_ns(pid, ns),
		ppid, tpid,
		cred->uid, cred->euid, cred->suid, cred->fsuid,
		cred->gid, cred->egid, cred->sgid, cred->fsgid);

	task_lock(p);
	if (p->files)
		fdt = files_fdtable(p->files);
	seq_printf(m,
		"FDSize:\t%d\n"
		"Groups:\t",
		fdt ? fdt->max_fds : 0);
	rcu_read_unlock();

	group_info = cred->group_info;
	task_unlock(p);

	for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
		seq_printf(m, "%d ", GROUP_AT(group_info, g));
	put_cred(cred);

	seq_printf(m, "\n");
}

static void render_sigset_t(struct seq_file *m, const char *header,
				sigset_t *set)
{
	int i;

	seq_printf(m, "%s", header);

	i = _NSIG;
	do {
		int x = 0;

		i -= 4;
		if (sigismember(set, i+1)) x |= 1;
		if (sigismember(set, i+2)) x |= 2;
		if (sigismember(set, i+3)) x |= 4;
		if (sigismember(set, i+4)) x |= 8;
		seq_printf(m, "%x", x);
	} while (i >= 4);

	seq_printf(m, "\n");
}

static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
				    sigset_t *catch)
{
	struct k_sigaction *k;
	int i;

	k = p->sighand->action;
	for (i = 1; i <= _NSIG; ++i, ++k) {
		if (k->sa.sa_handler == SIG_IGN)
			sigaddset(ign, i);
		else if (k->sa.sa_handler != SIG_DFL)
			sigaddset(catch, i);
	}
}

static inline void task_sig(struct seq_file *m, struct task_struct *p)
{
	unsigned long flags;
	sigset_t pending, shpending, blocked, ignored, caught;
	int num_threads = 0;
	unsigned long qsize = 0;
	unsigned long qlim = 0;

	sigemptyset(&pending);
	sigemptyset(&shpending);
	sigemptyset(&blocked);
	sigemptyset(&ignored);
	sigemptyset(&caught);

	if (lock_task_sighand(p, &flags)) {
		pending = p->pending.signal;
		shpending = p->signal->shared_pending.signal;
		blocked = p->blocked;
		collect_sigign_sigcatch(p, &ignored, &caught);
		num_threads = atomic_read(&p->signal->count);
		qsize = atomic_read(&__task_cred(p)->user->sigpending);
		qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
		unlock_task_sighand(p, &flags);
	}

	seq_printf(m, "Threads:\t%d\n", num_threads);
	seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);

	/* render them all */
	render_sigset_t(m, "SigPnd:\t", &pending);
	render_sigset_t(m, "ShdPnd:\t", &shpending);
	render_sigset_t(m, "SigBlk:\t", &blocked);
	render_sigset_t(m, "SigIgn:\t", &ignored);
	render_sigset_t(m, "SigCgt:\t", &caught);
}

static void render_cap_t(struct seq_file *m, const char *header,
			kernel_cap_t *a)
{
	unsigned __capi;

	seq_printf(m, "%s", header);
	CAP_FOR_EACH_U32(__capi) {
		seq_printf(m, "%08x",
			   a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
	}
	seq_printf(m, "\n");
}

static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
	const struct cred *cred;
	kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset;

	rcu_read_lock();
	cred = __task_cred(p);
	cap_inheritable	= cred->cap_inheritable;
	cap_permitted	= cred->cap_permitted;
	cap_effective	= cred->cap_effective;
	cap_bset	= cred->cap_bset;
	rcu_read_unlock();

	render_cap_t(m, "CapInh:\t", &cap_inheritable);
	render_cap_t(m, "CapPrm:\t", &cap_permitted);
	render_cap_t(m, "CapEff:\t", &cap_effective);
	render_cap_t(m, "CapBnd:\t", &cap_bset);
}

static inline void task_context_switch_counts(struct seq_file *m,
						struct task_struct *p)
{
	seq_printf(m,	"voluntary_ctxt_switches:\t%lu\n"
			"nonvoluntary_ctxt_switches:\t%lu\n",
			p->nvcsw,
			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)
{
	struct mm_struct *mm = get_task_mm(task);

	task_name(m, task);
	task_state(m, ns, pid, task);

	if (mm) {
		task_mem(m, mm);
		mmput(mm);
	}
	task_sig(m, task);
	task_cap(m, task);
	cpuset_task_status_allowed(m, task);
#if defined(CONFIG_S390)
	task_show_regs(m, task);
#endif
	task_context_switch_counts(m, task);
	task_show_stack_usage(m, task);
	return 0;
}

static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task, int whole)
{
	unsigned long vsize, eip, esp, wchan = ~0UL;
	long priority, nice;
	int tty_pgrp = -1, tty_nr = 0;
	sigset_t sigign, sigcatch;
	char state;
	pid_t ppid = 0, pgid = -1, sid = -1;
	int num_threads = 0;
	int permitted;
	struct mm_struct *mm;
	unsigned long long start_time;
	unsigned long cmin_flt = 0, cmaj_flt = 0;
	unsigned long  min_flt = 0,  maj_flt = 0;
	cputime_t cutime, cstime, utime, stime;
	cputime_t cgtime, gtime;
	unsigned long rsslim = 0;
	char tcomm[sizeof(task->comm)];
	unsigned long flags;

	state = *get_task_state(task);
	vsize = eip = esp = 0;
	permitted = ptrace_may_access(task, PTRACE_MODE_READ);
	mm = get_task_mm(task);
	if (mm) {
		vsize = task_vsize(mm);
		if (permitted) {
			eip = KSTK_EIP(task);
			esp = KSTK_ESP(task);
		}
	}

	get_task_comm(tcomm, task);

	sigemptyset(&sigign);
	sigemptyset(&sigcatch);
	cutime = cstime = utime = stime = cputime_zero;
	cgtime = gtime = cputime_zero;

	if (lock_task_sighand(task, &flags)) {
		struct signal_struct *sig = task->signal;

		if (sig->tty) {
			struct pid *pgrp = tty_get_pgrp(sig->tty);
			tty_pgrp = pid_nr_ns(pgrp, ns);
			put_pid(pgrp);
			tty_nr = new_encode_dev(tty_devnum(sig->tty));
		}

		num_threads = atomic_read(&sig->count);
		collect_sigign_sigcatch(task, &sigign, &sigcatch);

		cmin_flt = sig->cmin_flt;
		cmaj_flt = sig->cmaj_flt;
		cutime = sig->cutime;
		cstime = sig->cstime;
		cgtime = sig->cgtime;
		rsslim = sig->rlim[RLIMIT_RSS].rlim_cur;

		/* add up live thread stats at the group level */
		if (whole) {
			struct task_cputime cputime;
			struct task_struct *t = task;
			do {
				min_flt += t->min_flt;
				maj_flt += t->maj_flt;
				gtime = cputime_add(gtime, task_gtime(t));
				t = next_thread(t);
			} while (t != task);

			min_flt += sig->min_flt;
			maj_flt += sig->maj_flt;
			thread_group_cputime(task, &cputime);
			utime = cputime.utime;
			stime = cputime.stime;
			gtime = cputime_add(gtime, sig->gtime);
		}

		sid = task_session_nr_ns(task, ns);
		ppid = task_tgid_nr_ns(task->real_parent, ns);
		pgid = task_pgrp_nr_ns(task, ns);

		unlock_task_sighand(task, &flags);
	}

	if (permitted && (!whole || num_threads < 2))
		wchan = get_wchan(task);
	if (!whole) {
		min_flt = task->min_flt;
		maj_flt = task->maj_flt;
		utime = task_utime(task);
		stime = task_stime(task);
		gtime = task_gtime(task);
	}

	/* scale priority and nice values from timeslices to -20..20 */
	/* to make it look like a "normal" Unix priority/nice value  */
	priority = task_prio(task);
	nice = task_nice(task);

	/* Temporary variable needed for gcc-2.96 */
	/* convert timespec -> nsec*/
	start_time =
		(unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC
				+ task->real_start_time.tv_nsec;
	/* convert nsec -> ticks */
	start_time = nsec_to_clock_t(start_time);

	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
		pid_nr_ns(pid, ns),
		tcomm,
		state,
		ppid,
		pgid,
		sid,
		tty_nr,
		tty_pgrp,
		task->flags,
		min_flt,
		cmin_flt,
		maj_flt,
		cmaj_flt,
		cputime_to_clock_t(utime),
		cputime_to_clock_t(stime),
		cputime_to_clock_t(cutime),
		cputime_to_clock_t(cstime),
		priority,
		nice,
		num_threads,
		start_time,
		vsize,
		mm ? get_mm_rss(mm) : 0,
		rsslim,
		mm ? mm->start_code : 0,
		mm ? mm->end_code : 0,
		(permitted) ? task->stack_start : 0,
		esp,
		eip,
		/* The signal information here is obsolete.
		 * It must be decimal for Linux 2.0 compatibility.
		 * Use /proc/#/status for real-time signals.
		 */
		task->pending.signal.sig[0] & 0x7fffffffUL,
		task->blocked.sig[0] & 0x7fffffffUL,
		sigign      .sig[0] & 0x7fffffffUL,
		sigcatch    .sig[0] & 0x7fffffffUL,
		wchan,
		0UL,
		0UL,
		task->exit_signal,
		task_cpu(task),
		task->rt_priority,
		task->policy,
		(unsigned long long)delayacct_blkio_ticks(task),
		cputime_to_clock_t(gtime),
		cputime_to_clock_t(cgtime));
	if (mm)
		mmput(mm);
	return 0;
}

int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	return do_task_stat(m, ns, pid, task, 0);
}

int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	return do_task_stat(m, ns, pid, task, 1);
}

int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0;
	struct mm_struct *mm = get_task_mm(task);

	if (mm) {
		size = task_statm(mm, &shared, &text, &data, &resident);
		mmput(mm);
	}
	seq_printf(m, "%d %d %d %d %d %d %d\n",
			size, resident, shared, text, lib, data, 0);

	return 0;
}
Commit	Line	Data
1da177e4 LT	1	/*
	2	* linux/fs/proc/array.c
	3	*
	4	* Copyright (C) 1992 by Linus Torvalds
	5	* based on ideas by Darren Senn
	6	*
	7	* Fixes:
	8	* Michael. K. Johnson: stat,statm extensions.
	9	* <johnsonm@stolaf.edu>
	10	*
	11	* Pauline Middelink : Made cmdline,envline only break at '\0's, to
	12	* make sure SET_PROCTITLE works. Also removed
	13	* bad '!' which forced address recalculation for
	14	* EVERY character on the current page.
	15	* <middelin@polyware.iaf.nl>
	16	*
	17	* Danny ter Haar : added cpuinfo
	18	* <dth@cistron.nl>
	19	*
	20	* Alessandro Rubini : profile extension.
	21	* <rubini@ipvvis.unipv.it>
	22	*
	23	* Jeff Tranter : added BogoMips field to cpuinfo
	24	* <Jeff_Tranter@Mitel.COM>
	25	*
	26	* Bruno Haible : remove 4K limit for the maps file
	27	* <haible@ma2s2.mathematik.uni-karlsruhe.de>
	28	*
	29	* Yves Arrouye : remove removal of trailing spaces in get_array.
	30	* <Yves.Arrouye@marin.fdn.fr>
	31	*
	32	* Jerome Forissier : added per-CPU time information to /proc/stat
	33	* and /proc/<pid>/cpu extension
	34	* <forissier@isia.cma.fr>
	35	* - Incorporation and non-SMP safe operation
	36	* of forissier patch in 2.1.78 by
	37	* Hans Marcus <crowbar@concepts.nl>
	38	*
	39	* aeb@cwi.nl : /proc/partitions
	40	*
	41	*
	42	* Alan Cox : security fixes.
526719ba	43	* <alan@lxorguk.ukuu.org.uk>
1da177e4 LT	44	*
	45	* Al Viro : safe handling of mm_struct
	46	*
	47	* Gerhard Wichert : added BIGMEM support
	48	* Siemens AG <Gerhard.Wichert@pdb.siemens.de>
	49	*
	50	* Al Viro & Jeff Garzik : moved most of the thing into base.c and
	51	* : proc_misc.c. The rest may eventually go into
	52	* : base.c too.
	53	*/
	54
1da177e4 LT	55	#include <linux/types.h>
	56	#include <linux/errno.h>
	57	#include <linux/time.h>
	58	#include <linux/kernel.h>
	59	#include <linux/kernel_stat.h>
	60	#include <linux/tty.h>
	61	#include <linux/string.h>
	62	#include <linux/mman.h>
	63	#include <linux/proc_fs.h>
	64	#include <linux/ioport.h>
8ea02606 IM	65	#include <linux/uaccess.h>
8ea02606 IM	66	#include <linux/io.h>
1da177e4 LT	67	#include <linux/mm.h>
	68	#include <linux/hugetlb.h>
	69	#include <linux/pagemap.h>
	70	#include <linux/swap.h>
	71	#include <linux/slab.h>
	72	#include <linux/smp.h>
	73	#include <linux/signal.h>
	74	#include <linux/highmem.h>
	75	#include <linux/file.h>
9f3acc31	76	#include <linux/fdtable.h>
1da177e4 LT	77	#include <linux/times.h>
1da177e4 LT	78	#include <linux/cpuset.h>
4fb3a538	79	#include <linux/rcupdate.h>
25890454	80	#include <linux/delayacct.h>
ee992744	81	#include <linux/seq_file.h>
b488893a	82	#include <linux/pid_namespace.h>
f83ce3e6	83	#include <linux/ptrace.h>
0d094efe	84	#include <linux/tracehook.h>
d899bf7b	85	#include <linux/swapops.h>
1da177e4	86
1da177e4	87	#include <asm/pgtable.h>
1da177e4 LT	88	#include <asm/processor.h>
	89	#include "internal.h"
	90
df5f8314	91	static inline void task_name(struct seq_file m, struct task_struct p)
1da177e4 LT	92	{
1da177e4 LT	93	int i;
df5f8314	94	char buf, end;
8ea02606	95	char *name;
1da177e4 LT	96	char tcomm[sizeof(p->comm)];
	97
	98	get_task_comm(tcomm, p);
	99
df5f8314 EB	100	seq_printf(m, "Name:\t");
	101	end = m->buf + m->size;
	102	buf = m->buf + m->count;
1da177e4 LT	103	name = tcomm;
1da177e4 LT	104	i = sizeof(tcomm);
df5f8314	105	while (i && (buf < end)) {
1da177e4 LT	106	unsigned char c = *name;
	107	name++;
	108	i--;
	109	*buf = c;
	110	if (!c)
	111	break;
	112	if (c == '\\') {
df5f8314 EB	113	buf++;
	114	if (buf < end)
	115	*buf++ = c;
1da177e4 LT	116	continue;
	117	}
	118	if (c == '\n') {
df5f8314 EB	119	*buf++ = '\\';
	120	if (buf < end)
	121	*buf++ = 'n';
1da177e4 LT	122	continue;
	123	}
	124	buf++;
df5f8314 EB	125	}
	126	m->count = buf - m->buf;
	127	seq_printf(m, "\n");
1da177e4 LT	128	}
	129
	130	/*
	131	* The task state array is a strange "bitmap" of
	132	* reasons to sleep. Thus "running" is zero, and
	133	* you can test for combinations of others with
	134	* simple bit tests.
	135	*/
	136	static const char *task_state_array[] = {
	137	"R (running)", /* 0 */
	138	"S (sleeping)", /* 1 */
	139	"D (disk sleep)", /* 2 */
	140	"T (stopped)", /* 4 */
	141	"T (tracing stop)", /* 8 */
	142	"Z (zombie)", /* 16 */
	143	"X (dead)" /* 32 */
	144	};
	145
8ea02606	146	static inline const char get_task_state(struct task_struct tsk)
1da177e4	147	{
1587e2b1	148	unsigned int state = (tsk->state & TASK_REPORT) \| tsk->exit_state;
1da177e4 LT	149	const char **p = &task_state_array[0];
	150
	151	while (state) {
	152	p++;
	153	state >>= 1;
	154	}
	155	return *p;
	156	}
	157
df5f8314 EB	158	static inline void task_state(struct seq_file m, struct pid_namespace ns,
df5f8314 EB	159	struct pid pid, struct task_struct p)
1da177e4 LT	160	{
	161	struct group_info *group_info;
	162	int g;
badf1662	163	struct fdtable *fdt = NULL;
c69e8d9c	164	const struct cred *cred;
b488893a	165	pid_t ppid, tpid;
1da177e4	166
b0fa9db6	167	rcu_read_lock();
b488893a PE	168	ppid = pid_alive(p) ?
b488893a PE	169	task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
0d094efe RM	170	tpid = 0;
	171	if (pid_alive(p)) {
	172	struct task_struct *tracer = tracehook_tracer_task(p);
	173	if (tracer)
	174	tpid = task_pid_nr_ns(tracer, ns);
	175	}
c69e8d9c	176	cred = get_cred((struct cred *) __task_cred(p));
df5f8314	177	seq_printf(m,
1da177e4	178	"State:\t%s\n"
1da177e4 LT	179	"Tgid:\t%d\n"
	180	"Pid:\t%d\n"
	181	"PPid:\t%d\n"
	182	"TracerPid:\t%d\n"
	183	"Uid:\t%d\t%d\t%d\t%d\n"
	184	"Gid:\t%d\t%d\t%d\t%d\n",
	185	get_task_state(p),
b488893a	186	task_tgid_nr_ns(p, ns),
df5f8314	187	pid_nr_ns(pid, ns),
b488893a	188	ppid, tpid,
c69e8d9c DH	189	cred->uid, cred->euid, cred->suid, cred->fsuid,
c69e8d9c DH	190	cred->gid, cred->egid, cred->sgid, cred->fsgid);
b0fa9db6	191
1da177e4	192	task_lock(p);
badf1662 DS	193	if (p->files)
badf1662 DS	194	fdt = files_fdtable(p->files);
df5f8314	195	seq_printf(m,
1da177e4 LT	196	"FDSize:\t%d\n"
1da177e4 LT	197	"Groups:\t",
badf1662	198	fdt ? fdt->max_fds : 0);
4fb3a538	199	rcu_read_unlock();
1da177e4	200
c69e8d9c	201	group_info = cred->group_info;
1da177e4 LT	202	task_unlock(p);
1da177e4 LT	203
8ea02606	204	for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
df5f8314	205	seq_printf(m, "%d ", GROUP_AT(group_info, g));
c69e8d9c	206	put_cred(cred);
1da177e4	207
df5f8314	208	seq_printf(m, "\n");
1da177e4 LT	209	}
1da177e4 LT	210
df5f8314 EB	211	static void render_sigset_t(struct seq_file m, const char header,
df5f8314 EB	212	sigset_t *set)
1da177e4	213	{
df5f8314	214	int i;
1da177e4	215
df5f8314	216	seq_printf(m, "%s", header);
1da177e4 LT	217
	218	i = _NSIG;
	219	do {
	220	int x = 0;
	221
	222	i -= 4;
	223	if (sigismember(set, i+1)) x \|= 1;
	224	if (sigismember(set, i+2)) x \|= 2;
	225	if (sigismember(set, i+3)) x \|= 4;
	226	if (sigismember(set, i+4)) x \|= 8;
df5f8314	227	seq_printf(m, "%x", x);
1da177e4 LT	228	} while (i >= 4);
1da177e4 LT	229
df5f8314	230	seq_printf(m, "\n");
1da177e4 LT	231	}
	232
	233	static void collect_sigign_sigcatch(struct task_struct p, sigset_t ign,
	234	sigset_t *catch)
	235	{
	236	struct k_sigaction *k;
	237	int i;
	238
	239	k = p->sighand->action;
	240	for (i = 1; i <= _NSIG; ++i, ++k) {
	241	if (k->sa.sa_handler == SIG_IGN)
	242	sigaddset(ign, i);
	243	else if (k->sa.sa_handler != SIG_DFL)
	244	sigaddset(catch, i);
	245	}
	246	}
	247
df5f8314	248	static inline void task_sig(struct seq_file m, struct task_struct p)
1da177e4	249	{
5e6b3f42	250	unsigned long flags;
1da177e4 LT	251	sigset_t pending, shpending, blocked, ignored, caught;
	252	int num_threads = 0;
	253	unsigned long qsize = 0;
	254	unsigned long qlim = 0;
	255
	256	sigemptyset(&pending);
	257	sigemptyset(&shpending);
	258	sigemptyset(&blocked);
	259	sigemptyset(&ignored);
	260	sigemptyset(&caught);
	261
5e6b3f42	262	if (lock_task_sighand(p, &flags)) {
1da177e4 LT	263	pending = p->pending.signal;
	264	shpending = p->signal->shared_pending.signal;
	265	blocked = p->blocked;
	266	collect_sigign_sigcatch(p, &ignored, &caught);
	267	num_threads = atomic_read(&p->signal->count);
c69e8d9c	268	qsize = atomic_read(&__task_cred(p)->user->sigpending);
1da177e4	269	qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
5e6b3f42	270	unlock_task_sighand(p, &flags);
1da177e4	271	}
1da177e4	272
df5f8314 EB	273	seq_printf(m, "Threads:\t%d\n", num_threads);
df5f8314 EB	274	seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
1da177e4 LT	275
1da177e4 LT	276	/* render them all */
df5f8314 EB	277	render_sigset_t(m, "SigPnd:\t", &pending);
	278	render_sigset_t(m, "ShdPnd:\t", &shpending);
	279	render_sigset_t(m, "SigBlk:\t", &blocked);
	280	render_sigset_t(m, "SigIgn:\t", &ignored);
	281	render_sigset_t(m, "SigCgt:\t", &caught);
1da177e4 LT	282	}
1da177e4 LT	283
df5f8314 EB	284	static void render_cap_t(struct seq_file m, const char header,
df5f8314 EB	285	kernel_cap_t *a)
e338d263 AM	286	{
	287	unsigned __capi;
	288
df5f8314	289	seq_printf(m, "%s", header);
e338d263	290	CAP_FOR_EACH_U32(__capi) {
df5f8314	291	seq_printf(m, "%08x",
ca05a99a	292	a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
e338d263	293	}
df5f8314	294	seq_printf(m, "\n");
e338d263 AM	295	}
e338d263 AM	296
df5f8314	297	static inline void task_cap(struct seq_file m, struct task_struct p)
1da177e4	298	{
c69e8d9c DH	299	const struct cred *cred;
c69e8d9c DH	300	kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset;
b6dff3ec	301
c69e8d9c DH	302	rcu_read_lock();
	303	cred = __task_cred(p);
	304	cap_inheritable = cred->cap_inheritable;
	305	cap_permitted = cred->cap_permitted;
	306	cap_effective = cred->cap_effective;
	307	cap_bset = cred->cap_bset;
	308	rcu_read_unlock();
	309
	310	render_cap_t(m, "CapInh:\t", &cap_inheritable);
	311	render_cap_t(m, "CapPrm:\t", &cap_permitted);
	312	render_cap_t(m, "CapEff:\t", &cap_effective);
	313	render_cap_t(m, "CapBnd:\t", &cap_bset);
1da177e4 LT	314	}
1da177e4 LT	315
df5f8314 EB	316	static inline void task_context_switch_counts(struct seq_file *m,
df5f8314 EB	317	struct task_struct *p)
b663a79c	318	{
df5f8314 EB	319	seq_printf(m, "voluntary_ctxt_switches:\t%lu\n"
	320	"nonvoluntary_ctxt_switches:\t%lu\n",
	321	p->nvcsw,
	322	p->nivcsw);
b663a79c MU	323	}
b663a79c MU	324
d899bf7b SS	325	struct stack_stats {
	326	struct vm_area_struct *vma;
	327	unsigned long startpage;
	328	unsigned long usage;
	329	};
	330
	331	static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr,
	332	unsigned long end, struct mm_walk *walk)
	333	{
	334	struct stack_stats *ss = walk->private;
	335	struct vm_area_struct *vma = ss->vma;
	336	pte_t *pte, ptent;
	337	spinlock_t *ptl;
	338	int ret = 0;
	339
	340	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	341	for (; addr != end; pte++, addr += PAGE_SIZE) {
	342	ptent = *pte;
	343
	344	#ifdef CONFIG_STACK_GROWSUP
	345	if (pte_present(ptent) \|\| is_swap_pte(ptent))
	346	ss->usage = addr - ss->startpage + PAGE_SIZE;
	347	#else
	348	if (pte_present(ptent) \|\| is_swap_pte(ptent)) {
	349	ss->usage = ss->startpage - addr + PAGE_SIZE;
	350	pte++;
	351	ret = 1;
	352	break;
	353	}
	354	#endif
	355	}
	356	pte_unmap_unlock(pte - 1, ptl);
	357	cond_resched();
	358	return ret;
	359	}
	360
	361	static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma,
	362	struct task_struct *task)
	363	{
	364	struct stack_stats ss;
	365	struct mm_walk stack_walk = {
	366	.pmd_entry = stack_usage_pte_range,
	367	.mm = vma->vm_mm,
	368	.private = &ss,
	369	};
	370
	371	if (!vma->vm_mm \|\| is_vm_hugetlb_page(vma))
	372	return 0;
	373
	374	ss.vma = vma;
	375	ss.startpage = task->stack_start & PAGE_MASK;
	376	ss.usage = 0;
	377
	378	#ifdef CONFIG_STACK_GROWSUP
	379	walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end,
	380	&stack_walk);
	381	#else
	382	walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE,
	383	&stack_walk);
	384	#endif
	385	return ss.usage;
	386	}
	387
	388	static inline void task_show_stack_usage(struct seq_file *m,
389	struct task_struct *task)
390	{
391	struct vm_area_struct *vma;
392	struct mm_struct *mm = get_task_mm(task);
393
394	if (mm) {
395	down_read(&mm->mmap_sem);
396	vma = find_vma(mm, task->stack_start);
397	if (vma)
398	seq_printf(m, "Stack usage:\t%lu kB\n",
399	get_stack_usage_in_bytes(vma, task) >> 10);
400
401	up_read(&mm->mmap_sem);
402	mmput(mm);
403	}
404	}
405
df5f8314 EB	406	int proc_pid_status(struct seq_file m, struct pid_namespace ns,
df5f8314 EB	407	struct pid pid, struct task_struct task)
1da177e4	408	{
1da177e4 LT	409	struct mm_struct *mm = get_task_mm(task);
1da177e4 LT	410
df5f8314 EB	411	task_name(m, task);
df5f8314 EB	412	task_state(m, ns, pid, task);
8ea02606	413
1da177e4	414	if (mm) {
df5f8314	415	task_mem(m, mm);
1da177e4 LT	416	mmput(mm);
1da177e4 LT	417	}
df5f8314 EB	418	task_sig(m, task);
	419	task_cap(m, task);
	420	cpuset_task_status_allowed(m, task);
347a8dc3	421	#if defined(CONFIG_S390)
df5f8314	422	task_show_regs(m, task);
1da177e4	423	#endif
df5f8314	424	task_context_switch_counts(m, task);
d899bf7b	425	task_show_stack_usage(m, task);
df5f8314	426	return 0;
1da177e4 LT	427	}
1da177e4 LT	428
ee992744 EB	429	static int do_task_stat(struct seq_file m, struct pid_namespace ns,
ee992744 EB	430	struct pid pid, struct task_struct task, int whole)
1da177e4 LT	431	{
	432	unsigned long vsize, eip, esp, wchan = ~0UL;
	433	long priority, nice;
	434	int tty_pgrp = -1, tty_nr = 0;
	435	sigset_t sigign, sigcatch;
	436	char state;
8ea02606	437	pid_t ppid = 0, pgid = -1, sid = -1;
1da177e4	438	int num_threads = 0;
f83ce3e6	439	int permitted;
1da177e4 LT	440	struct mm_struct *mm;
	441	unsigned long long start_time;
	442	unsigned long cmin_flt = 0, cmaj_flt = 0;
	443	unsigned long min_flt = 0, maj_flt = 0;
efe567fc	444	cputime_t cutime, cstime, utime, stime;
9ac52315	445	cputime_t cgtime, gtime;
1da177e4	446	unsigned long rsslim = 0;
1da177e4	447	char tcomm[sizeof(task->comm)];
a593d6ed	448	unsigned long flags;
1da177e4 LT	449
	450	state = *get_task_state(task);
	451	vsize = eip = esp = 0;
f83ce3e6	452	permitted = ptrace_may_access(task, PTRACE_MODE_READ);
1da177e4 LT	453	mm = get_task_mm(task);
	454	if (mm) {
	455	vsize = task_vsize(mm);
f83ce3e6 JE	456	if (permitted) {
	457	eip = KSTK_EIP(task);
	458	esp = KSTK_ESP(task);
	459	}
1da177e4 LT	460	}
	461
	462	get_task_comm(tcomm, task);
	463
	464	sigemptyset(&sigign);
	465	sigemptyset(&sigcatch);
efe567fc	466	cutime = cstime = utime = stime = cputime_zero;
9ac52315	467	cgtime = gtime = cputime_zero;
3cfd0885	468
a593d6ed ON	469	if (lock_task_sighand(task, &flags)) {
a593d6ed ON	470	struct signal_struct *sig = task->signal;
91593504 ON	471
91593504 ON	472	if (sig->tty) {
5d0fdf1e AC	473	struct pid *pgrp = tty_get_pgrp(sig->tty);
	474	tty_pgrp = pid_nr_ns(pgrp, ns);
	475	put_pid(pgrp);
91593504	476	tty_nr = new_encode_dev(tty_devnum(sig->tty));
a593d6ed ON	477	}
	478
	479	num_threads = atomic_read(&sig->count);
1da177e4 LT	480	collect_sigign_sigcatch(task, &sigign, &sigcatch);
1da177e4 LT	481
a593d6ed ON	482	cmin_flt = sig->cmin_flt;
	483	cmaj_flt = sig->cmaj_flt;
	484	cutime = sig->cutime;
	485	cstime = sig->cstime;
9ac52315	486	cgtime = sig->cgtime;
a593d6ed ON	487	rsslim = sig->rlim[RLIMIT_RSS].rlim_cur;
a593d6ed ON	488
1da177e4 LT	489	/* add up live thread stats at the group level */
1da177e4 LT	490	if (whole) {
f06febc9	491	struct task_cputime cputime;
a593d6ed	492	struct task_struct *t = task;
1da177e4 LT	493	do {
	494	min_flt += t->min_flt;
	495	maj_flt += t->maj_flt;
9ac52315	496	gtime = cputime_add(gtime, task_gtime(t));
1da177e4 LT	497	t = next_thread(t);
1da177e4 LT	498	} while (t != task);
1da177e4	499
a593d6ed ON	500	min_flt += sig->min_flt;
a593d6ed ON	501	maj_flt += sig->maj_flt;
f06febc9 FM	502	thread_group_cputime(task, &cputime);
	503	utime = cputime.utime;
	504	stime = cputime.stime;
f9e26291	505	gtime = cputime_add(gtime, sig->gtime);
1da177e4	506	}
a593d6ed	507
b488893a	508	sid = task_session_nr_ns(task, ns);
a98fdcef	509	ppid = task_tgid_nr_ns(task->real_parent, ns);
b488893a	510	pgid = task_pgrp_nr_ns(task, ns);
a593d6ed ON	511
a593d6ed ON	512	unlock_task_sighand(task, &flags);
1da177e4	513	}
1da177e4	514
f83ce3e6	515	if (permitted && (!whole \|\| num_threads < 2))
1da177e4 LT	516	wchan = get_wchan(task);
	517	if (!whole) {
	518	min_flt = task->min_flt;
	519	maj_flt = task->maj_flt;
b27f03d4 IM	520	utime = task_utime(task);
b27f03d4 IM	521	stime = task_stime(task);
9ac52315	522	gtime = task_gtime(task);
1da177e4 LT	523	}
	524
	525	/* scale priority and nice values from timeslices to -20..20 */
	526	/* to make it look like a "normal" Unix priority/nice value */
	527	priority = task_prio(task);
	528	nice = task_nice(task);
	529
	530	/* Temporary variable needed for gcc-2.96 */
	531	/* convert timespec -> nsec*/
924b42d5 TJ	532	start_time =
	533	(unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC
	534	+ task->real_start_time.tv_nsec;
1da177e4 LT	535	/* convert nsec -> ticks */
	536	start_time = nsec_to_clock_t(start_time);
	537
ee992744	538	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
4dee26b7	539	%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
9ac52315	540	%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
ee992744	541	pid_nr_ns(pid, ns),
1da177e4 LT	542	tcomm,
	543	state,
	544	ppid,
	545	pgid,
	546	sid,
	547	tty_nr,
	548	tty_pgrp,
	549	task->flags,
	550	min_flt,
	551	cmin_flt,
	552	maj_flt,
	553	cmaj_flt,
efe567fc CB	554	cputime_to_clock_t(utime),
efe567fc CB	555	cputime_to_clock_t(stime),
1da177e4 LT	556	cputime_to_clock_t(cutime),
	557	cputime_to_clock_t(cstime),
	558	priority,
	559	nice,
	560	num_threads,
1da177e4 LT	561	start_time,
1da177e4 LT	562	vsize,
4294621f	563	mm ? get_mm_rss(mm) : 0,
8ea02606	564	rsslim,
1da177e4 LT	565	mm ? mm->start_code : 0,
1da177e4 LT	566	mm ? mm->end_code : 0,
d899bf7b	567	(permitted) ? task->stack_start : 0,
1da177e4 LT	568	esp,
	569	eip,
	570	/* The signal information here is obsolete.
	571	* It must be decimal for Linux 2.0 compatibility.
	572	* Use /proc/#/status for real-time signals.
	573	*/
	574	task->pending.signal.sig[0] & 0x7fffffffUL,
	575	task->blocked.sig[0] & 0x7fffffffUL,
	576	sigign .sig[0] & 0x7fffffffUL,
	577	sigcatch .sig[0] & 0x7fffffffUL,
	578	wchan,
	579	0UL,
	580	0UL,
	581	task->exit_signal,
	582	task_cpu(task),
	583	task->rt_priority,
25890454	584	task->policy,
9ac52315 LV	585	(unsigned long long)delayacct_blkio_ticks(task),
	586	cputime_to_clock_t(gtime),
	587	cputime_to_clock_t(cgtime));
8ea02606	588	if (mm)
1da177e4	589	mmput(mm);
ee992744	590	return 0;
1da177e4 LT	591	}
1da177e4 LT	592
ee992744 EB	593	int proc_tid_stat(struct seq_file m, struct pid_namespace ns,
ee992744 EB	594	struct pid pid, struct task_struct task)
1da177e4	595	{
ee992744	596	return do_task_stat(m, ns, pid, task, 0);
1da177e4 LT	597	}
1da177e4 LT	598
ee992744 EB	599	int proc_tgid_stat(struct seq_file m, struct pid_namespace ns,
ee992744 EB	600	struct pid pid, struct task_struct task)
1da177e4	601	{
ee992744	602	return do_task_stat(m, ns, pid, task, 1);
1da177e4 LT	603	}
1da177e4 LT	604
a56d3fc7 EB	605	int proc_pid_statm(struct seq_file m, struct pid_namespace ns,
a56d3fc7 EB	606	struct pid pid, struct task_struct task)
1da177e4 LT	607	{
	608	int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0;
	609	struct mm_struct *mm = get_task_mm(task);
8ea02606	610
1da177e4 LT	611	if (mm) {
	612	size = task_statm(mm, &shared, &text, &data, &resident);
	613	mmput(mm);
	614	}
a56d3fc7 EB	615	seq_printf(m, "%d %d %d %d %d %d %d\n",
a56d3fc7 EB	616	size, resident, shared, text, lib, data, 0);
1da177e4	617
a56d3fc7	618	return 0;
1da177e4	619	}