[deliverable/linux.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 */
	"x (dead)",		/*  64 */
	"K (wakekill)",		/* 128 */
	"W (waking)",		/* 256 */
};

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];

	BUILD_BUG_ON(1 + ilog2(TASK_STATE_MAX) != ARRAY_SIZE(task_state_array));

	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);
}

#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)
{
	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);
	}
}
#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)
{
	seq_printf(m, "Cpus_allowed:\t");
	seq_cpumask(m, &task->cpus_allowed);
	seq_printf(m, "\n");
	seq_printf(m, "Cpus_allowed_list:\t");
	seq_cpumask_list(m, &task->cpus_allowed);
	seq_printf(m, "\n");
}

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);
	task_cpus_allowed(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_struct *t = task;
			do {
				min_flt += t->min_flt;
				maj_flt += t->maj_flt;
				gtime = cputime_add(gtime, t->gtime);
				t = next_thread(t);
			} while (t != task);

			min_flt += sig->min_flt;
			maj_flt += sig->maj_flt;
			thread_group_times(task, &utime, &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;
		task_times(task, &utime, &stime);
		gtime = task->gtime;
	}

	/* 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 && mm) ? 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[] = {
e1781538 PZ	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	"x (dead)", /* 64 */
464763cf PZ	145	"K (wakekill)", /* 128 */
464763cf PZ	146	"W (waking)", /* 256 */
1da177e4 LT	147	};
1da177e4 LT	148
8ea02606	149	static inline const char get_task_state(struct task_struct tsk)
1da177e4	150	{
1587e2b1	151	unsigned int state = (tsk->state & TASK_REPORT) \| tsk->exit_state;
1da177e4 LT	152	const char **p = &task_state_array[0];
1da177e4 LT	153
e1781538 PZ	154	BUILD_BUG_ON(1 + ilog2(TASK_STATE_MAX) != ARRAY_SIZE(task_state_array));
e1781538 PZ	155
1da177e4 LT	156	while (state) {
	157	p++;
	158	state >>= 1;
	159	}
	160	return *p;
	161	}
	162
df5f8314 EB	163	static inline void task_state(struct seq_file m, struct pid_namespace ns,
df5f8314 EB	164	struct pid pid, struct task_struct p)
1da177e4 LT	165	{
	166	struct group_info *group_info;
	167	int g;
badf1662	168	struct fdtable *fdt = NULL;
c69e8d9c	169	const struct cred *cred;
b488893a	170	pid_t ppid, tpid;
1da177e4	171
b0fa9db6	172	rcu_read_lock();
b488893a PE	173	ppid = pid_alive(p) ?
b488893a PE	174	task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
0d094efe RM	175	tpid = 0;
	176	if (pid_alive(p)) {
	177	struct task_struct *tracer = tracehook_tracer_task(p);
	178	if (tracer)
	179	tpid = task_pid_nr_ns(tracer, ns);
	180	}
c69e8d9c	181	cred = get_cred((struct cred *) __task_cred(p));
df5f8314	182	seq_printf(m,
1da177e4	183	"State:\t%s\n"
1da177e4 LT	184	"Tgid:\t%d\n"
	185	"Pid:\t%d\n"
	186	"PPid:\t%d\n"
	187	"TracerPid:\t%d\n"
	188	"Uid:\t%d\t%d\t%d\t%d\n"
	189	"Gid:\t%d\t%d\t%d\t%d\n",
	190	get_task_state(p),
b488893a	191	task_tgid_nr_ns(p, ns),
df5f8314	192	pid_nr_ns(pid, ns),
b488893a	193	ppid, tpid,
c69e8d9c DH	194	cred->uid, cred->euid, cred->suid, cred->fsuid,
c69e8d9c DH	195	cred->gid, cred->egid, cred->sgid, cred->fsgid);
b0fa9db6	196
1da177e4	197	task_lock(p);
badf1662 DS	198	if (p->files)
badf1662 DS	199	fdt = files_fdtable(p->files);
df5f8314	200	seq_printf(m,
1da177e4 LT	201	"FDSize:\t%d\n"
1da177e4 LT	202	"Groups:\t",
badf1662	203	fdt ? fdt->max_fds : 0);
4fb3a538	204	rcu_read_unlock();
1da177e4	205
c69e8d9c	206	group_info = cred->group_info;
1da177e4 LT	207	task_unlock(p);
1da177e4 LT	208
8ea02606	209	for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
df5f8314	210	seq_printf(m, "%d ", GROUP_AT(group_info, g));
c69e8d9c	211	put_cred(cred);
1da177e4	212
df5f8314	213	seq_printf(m, "\n");
1da177e4 LT	214	}
1da177e4 LT	215
df5f8314 EB	216	static void render_sigset_t(struct seq_file m, const char header,
df5f8314 EB	217	sigset_t *set)
1da177e4	218	{
df5f8314	219	int i;
1da177e4	220
df5f8314	221	seq_printf(m, "%s", header);
1da177e4 LT	222
	223	i = _NSIG;
	224	do {
	225	int x = 0;
	226
	227	i -= 4;
	228	if (sigismember(set, i+1)) x \|= 1;
	229	if (sigismember(set, i+2)) x \|= 2;
	230	if (sigismember(set, i+3)) x \|= 4;
	231	if (sigismember(set, i+4)) x \|= 8;
df5f8314	232	seq_printf(m, "%x", x);
1da177e4 LT	233	} while (i >= 4);
1da177e4 LT	234
df5f8314	235	seq_printf(m, "\n");
1da177e4 LT	236	}
	237
	238	static void collect_sigign_sigcatch(struct task_struct p, sigset_t ign,
	239	sigset_t *catch)
	240	{
	241	struct k_sigaction *k;
	242	int i;
	243
	244	k = p->sighand->action;
	245	for (i = 1; i <= _NSIG; ++i, ++k) {
	246	if (k->sa.sa_handler == SIG_IGN)
	247	sigaddset(ign, i);
	248	else if (k->sa.sa_handler != SIG_DFL)
	249	sigaddset(catch, i);
	250	}
	251	}
	252
df5f8314	253	static inline void task_sig(struct seq_file m, struct task_struct p)
1da177e4	254	{
5e6b3f42	255	unsigned long flags;
1da177e4 LT	256	sigset_t pending, shpending, blocked, ignored, caught;
	257	int num_threads = 0;
	258	unsigned long qsize = 0;
	259	unsigned long qlim = 0;
	260
	261	sigemptyset(&pending);
	262	sigemptyset(&shpending);
	263	sigemptyset(&blocked);
	264	sigemptyset(&ignored);
	265	sigemptyset(&caught);
	266
5e6b3f42	267	if (lock_task_sighand(p, &flags)) {
1da177e4 LT	268	pending = p->pending.signal;
	269	shpending = p->signal->shared_pending.signal;
	270	blocked = p->blocked;
	271	collect_sigign_sigcatch(p, &ignored, &caught);
	272	num_threads = atomic_read(&p->signal->count);
c69e8d9c	273	qsize = atomic_read(&__task_cred(p)->user->sigpending);
1da177e4	274	qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
5e6b3f42	275	unlock_task_sighand(p, &flags);
1da177e4	276	}
1da177e4	277
df5f8314 EB	278	seq_printf(m, "Threads:\t%d\n", num_threads);
df5f8314 EB	279	seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
1da177e4 LT	280
1da177e4 LT	281	/* render them all */
df5f8314 EB	282	render_sigset_t(m, "SigPnd:\t", &pending);
	283	render_sigset_t(m, "ShdPnd:\t", &shpending);
	284	render_sigset_t(m, "SigBlk:\t", &blocked);
	285	render_sigset_t(m, "SigIgn:\t", &ignored);
	286	render_sigset_t(m, "SigCgt:\t", &caught);
1da177e4 LT	287	}
1da177e4 LT	288
df5f8314 EB	289	static void render_cap_t(struct seq_file m, const char header,
df5f8314 EB	290	kernel_cap_t *a)
e338d263 AM	291	{
	292	unsigned __capi;
	293
df5f8314	294	seq_printf(m, "%s", header);
e338d263	295	CAP_FOR_EACH_U32(__capi) {
df5f8314	296	seq_printf(m, "%08x",
ca05a99a	297	a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
e338d263	298	}
df5f8314	299	seq_printf(m, "\n");
e338d263 AM	300	}
e338d263 AM	301
df5f8314	302	static inline void task_cap(struct seq_file m, struct task_struct p)
1da177e4	303	{
c69e8d9c DH	304	const struct cred *cred;
c69e8d9c DH	305	kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset;
b6dff3ec	306
c69e8d9c DH	307	rcu_read_lock();
	308	cred = __task_cred(p);
	309	cap_inheritable = cred->cap_inheritable;
	310	cap_permitted = cred->cap_permitted;
	311	cap_effective = cred->cap_effective;
	312	cap_bset = cred->cap_bset;
	313	rcu_read_unlock();
	314
	315	render_cap_t(m, "CapInh:\t", &cap_inheritable);
	316	render_cap_t(m, "CapPrm:\t", &cap_permitted);
	317	render_cap_t(m, "CapEff:\t", &cap_effective);
	318	render_cap_t(m, "CapBnd:\t", &cap_bset);
1da177e4 LT	319	}
1da177e4 LT	320
df5f8314 EB	321	static inline void task_context_switch_counts(struct seq_file *m,
df5f8314 EB	322	struct task_struct *p)
b663a79c	323	{
df5f8314 EB	324	seq_printf(m, "voluntary_ctxt_switches:\t%lu\n"
	325	"nonvoluntary_ctxt_switches:\t%lu\n",
	326	p->nvcsw,
	327	p->nivcsw);
b663a79c MU	328	}
b663a79c MU	329
c44972f1 AM	330	#ifdef CONFIG_MMU
c44972f1 AM	331
d899bf7b SS	332	struct stack_stats {
	333	struct vm_area_struct *vma;
	334	unsigned long startpage;
	335	unsigned long usage;
	336	};
	337
	338	static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr,
	339	unsigned long end, struct mm_walk *walk)
	340	{
	341	struct stack_stats *ss = walk->private;
	342	struct vm_area_struct *vma = ss->vma;
	343	pte_t *pte, ptent;
	344	spinlock_t *ptl;
	345	int ret = 0;
	346
	347	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	348	for (; addr != end; pte++, addr += PAGE_SIZE) {
	349	ptent = *pte;
	350
	351	#ifdef CONFIG_STACK_GROWSUP
	352	if (pte_present(ptent) \|\| is_swap_pte(ptent))
	353	ss->usage = addr - ss->startpage + PAGE_SIZE;
	354	#else
	355	if (pte_present(ptent) \|\| is_swap_pte(ptent)) {
	356	ss->usage = ss->startpage - addr + PAGE_SIZE;
	357	pte++;
	358	ret = 1;
	359	break;
	360	}
	361	#endif
	362	}
	363	pte_unmap_unlock(pte - 1, ptl);
	364	cond_resched();
	365	return ret;
	366	}
	367
	368	static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma,
	369	struct task_struct *task)
	370	{
	371	struct stack_stats ss;
	372	struct mm_walk stack_walk = {
	373	.pmd_entry = stack_usage_pte_range,
	374	.mm = vma->vm_mm,
	375	.private = &ss,
	376	};
	377
	378	if (!vma->vm_mm \|\| is_vm_hugetlb_page(vma))
	379	return 0;
	380
	381	ss.vma = vma;
	382	ss.startpage = task->stack_start & PAGE_MASK;
	383	ss.usage = 0;
	384
	385	#ifdef CONFIG_STACK_GROWSUP
	386	walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end,
	387	&stack_walk);
	388	#else
	389	walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE,
	390	&stack_walk);
	391	#endif
	392	return ss.usage;
	393	}
	394
	395	static inline void task_show_stack_usage(struct seq_file *m,
396	struct task_struct *task)
397	{
398	struct vm_area_struct *vma;
399	struct mm_struct *mm = get_task_mm(task);
400
401	if (mm) {
402	down_read(&mm->mmap_sem);
403	vma = find_vma(mm, task->stack_start);
404	if (vma)
405	seq_printf(m, "Stack usage:\t%lu kB\n",
406	get_stack_usage_in_bytes(vma, task) >> 10);
407
408	up_read(&mm->mmap_sem);
409	mmput(mm);
410	}
411	}
c44972f1 AM	412	#else
	413	static void task_show_stack_usage(struct seq_file m, struct task_struct task)
	414	{
	415	}
	416	#endif /* CONFIG_MMU */
d899bf7b	417
d01d4827 HC	418	static void task_cpus_allowed(struct seq_file m, struct task_struct task)
	419	{
	420	seq_printf(m, "Cpus_allowed:\t");
	421	seq_cpumask(m, &task->cpus_allowed);
	422	seq_printf(m, "\n");
	423	seq_printf(m, "Cpus_allowed_list:\t");
	424	seq_cpumask_list(m, &task->cpus_allowed);
	425	seq_printf(m, "\n");
	426	}
	427
df5f8314 EB	428	int proc_pid_status(struct seq_file m, struct pid_namespace ns,
df5f8314 EB	429	struct pid pid, struct task_struct task)
1da177e4	430	{
1da177e4 LT	431	struct mm_struct *mm = get_task_mm(task);
1da177e4 LT	432
df5f8314 EB	433	task_name(m, task);
df5f8314 EB	434	task_state(m, ns, pid, task);
8ea02606	435
1da177e4	436	if (mm) {
df5f8314	437	task_mem(m, mm);
1da177e4 LT	438	mmput(mm);
1da177e4 LT	439	}
df5f8314 EB	440	task_sig(m, task);
df5f8314 EB	441	task_cap(m, task);
d01d4827	442	task_cpus_allowed(m, task);
df5f8314	443	cpuset_task_status_allowed(m, task);
347a8dc3	444	#if defined(CONFIG_S390)
df5f8314	445	task_show_regs(m, task);
1da177e4	446	#endif
df5f8314	447	task_context_switch_counts(m, task);
d899bf7b	448	task_show_stack_usage(m, task);
df5f8314	449	return 0;
1da177e4 LT	450	}
1da177e4 LT	451
ee992744 EB	452	static int do_task_stat(struct seq_file m, struct pid_namespace ns,
ee992744 EB	453	struct pid pid, struct task_struct task, int whole)
1da177e4 LT	454	{
	455	unsigned long vsize, eip, esp, wchan = ~0UL;
	456	long priority, nice;
	457	int tty_pgrp = -1, tty_nr = 0;
	458	sigset_t sigign, sigcatch;
	459	char state;
8ea02606	460	pid_t ppid = 0, pgid = -1, sid = -1;
1da177e4	461	int num_threads = 0;
f83ce3e6	462	int permitted;
1da177e4 LT	463	struct mm_struct *mm;
	464	unsigned long long start_time;
	465	unsigned long cmin_flt = 0, cmaj_flt = 0;
	466	unsigned long min_flt = 0, maj_flt = 0;
efe567fc	467	cputime_t cutime, cstime, utime, stime;
9ac52315	468	cputime_t cgtime, gtime;
1da177e4	469	unsigned long rsslim = 0;
1da177e4	470	char tcomm[sizeof(task->comm)];
a593d6ed	471	unsigned long flags;
1da177e4 LT	472
	473	state = *get_task_state(task);
	474	vsize = eip = esp = 0;
f83ce3e6	475	permitted = ptrace_may_access(task, PTRACE_MODE_READ);
1da177e4 LT	476	mm = get_task_mm(task);
	477	if (mm) {
	478	vsize = task_vsize(mm);
f83ce3e6 JE	479	if (permitted) {
	480	eip = KSTK_EIP(task);
	481	esp = KSTK_ESP(task);
	482	}
1da177e4 LT	483	}
	484
	485	get_task_comm(tcomm, task);
	486
	487	sigemptyset(&sigign);
	488	sigemptyset(&sigcatch);
efe567fc	489	cutime = cstime = utime = stime = cputime_zero;
9ac52315	490	cgtime = gtime = cputime_zero;
3cfd0885	491
a593d6ed ON	492	if (lock_task_sighand(task, &flags)) {
a593d6ed ON	493	struct signal_struct *sig = task->signal;
91593504 ON	494
91593504 ON	495	if (sig->tty) {
5d0fdf1e AC	496	struct pid *pgrp = tty_get_pgrp(sig->tty);
	497	tty_pgrp = pid_nr_ns(pgrp, ns);
	498	put_pid(pgrp);
91593504	499	tty_nr = new_encode_dev(tty_devnum(sig->tty));
a593d6ed ON	500	}
	501
	502	num_threads = atomic_read(&sig->count);
1da177e4 LT	503	collect_sigign_sigcatch(task, &sigign, &sigcatch);
1da177e4 LT	504
a593d6ed ON	505	cmin_flt = sig->cmin_flt;
	506	cmaj_flt = sig->cmaj_flt;
	507	cutime = sig->cutime;
	508	cstime = sig->cstime;
9ac52315	509	cgtime = sig->cgtime;
a593d6ed ON	510	rsslim = sig->rlim[RLIMIT_RSS].rlim_cur;
a593d6ed ON	511
1da177e4 LT	512	/* add up live thread stats at the group level */
1da177e4 LT	513	if (whole) {
a593d6ed	514	struct task_struct *t = task;
1da177e4 LT	515	do {
	516	min_flt += t->min_flt;
	517	maj_flt += t->maj_flt;
d5b7c78e	518	gtime = cputime_add(gtime, t->gtime);
1da177e4 LT	519	t = next_thread(t);
1da177e4 LT	520	} while (t != task);
1da177e4	521
a593d6ed ON	522	min_flt += sig->min_flt;
a593d6ed ON	523	maj_flt += sig->maj_flt;
0cf55e1e	524	thread_group_times(task, &utime, &stime);
f9e26291	525	gtime = cputime_add(gtime, sig->gtime);
1da177e4	526	}
a593d6ed	527
b488893a	528	sid = task_session_nr_ns(task, ns);
a98fdcef	529	ppid = task_tgid_nr_ns(task->real_parent, ns);
b488893a	530	pgid = task_pgrp_nr_ns(task, ns);
a593d6ed ON	531
a593d6ed ON	532	unlock_task_sighand(task, &flags);
1da177e4	533	}
1da177e4	534
f83ce3e6	535	if (permitted && (!whole \|\| num_threads < 2))
1da177e4 LT	536	wchan = get_wchan(task);
	537	if (!whole) {
	538	min_flt = task->min_flt;
	539	maj_flt = task->maj_flt;
d180c5bc	540	task_times(task, &utime, &stime);
d5b7c78e	541	gtime = task->gtime;
1da177e4 LT	542	}
	543
	544	/* scale priority and nice values from timeslices to -20..20 */
	545	/* to make it look like a "normal" Unix priority/nice value */
	546	priority = task_prio(task);
	547	nice = task_nice(task);
	548
	549	/* Temporary variable needed for gcc-2.96 */
	550	/* convert timespec -> nsec*/
924b42d5 TJ	551	start_time =
	552	(unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC
	553	+ task->real_start_time.tv_nsec;
1da177e4 LT	554	/* convert nsec -> ticks */
	555	start_time = nsec_to_clock_t(start_time);
	556
ee992744	557	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
4dee26b7	558	%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
9ac52315	559	%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
ee992744	560	pid_nr_ns(pid, ns),
1da177e4 LT	561	tcomm,
	562	state,
	563	ppid,
	564	pgid,
	565	sid,
	566	tty_nr,
	567	tty_pgrp,
	568	task->flags,
	569	min_flt,
	570	cmin_flt,
	571	maj_flt,
	572	cmaj_flt,
efe567fc CB	573	cputime_to_clock_t(utime),
efe567fc CB	574	cputime_to_clock_t(stime),
1da177e4 LT	575	cputime_to_clock_t(cutime),
	576	cputime_to_clock_t(cstime),
	577	priority,
	578	nice,
	579	num_threads,
1da177e4 LT	580	start_time,
1da177e4 LT	581	vsize,
4294621f	582	mm ? get_mm_rss(mm) : 0,
8ea02606	583	rsslim,
1da177e4 LT	584	mm ? mm->start_code : 0,
1da177e4 LT	585	mm ? mm->end_code : 0,
9ebd4eba	586	(permitted && mm) ? task->stack_start : 0,
1da177e4 LT	587	esp,
	588	eip,
	589	/* The signal information here is obsolete.
	590	* It must be decimal for Linux 2.0 compatibility.
	591	* Use /proc/#/status for real-time signals.
	592	*/
	593	task->pending.signal.sig[0] & 0x7fffffffUL,
	594	task->blocked.sig[0] & 0x7fffffffUL,
	595	sigign .sig[0] & 0x7fffffffUL,
	596	sigcatch .sig[0] & 0x7fffffffUL,
	597	wchan,
	598	0UL,
	599	0UL,
	600	task->exit_signal,
	601	task_cpu(task),
	602	task->rt_priority,
25890454	603	task->policy,
9ac52315 LV	604	(unsigned long long)delayacct_blkio_ticks(task),
	605	cputime_to_clock_t(gtime),
	606	cputime_to_clock_t(cgtime));
8ea02606	607	if (mm)
1da177e4	608	mmput(mm);
ee992744	609	return 0;
1da177e4 LT	610	}
1da177e4 LT	611
ee992744 EB	612	int proc_tid_stat(struct seq_file m, struct pid_namespace ns,
ee992744 EB	613	struct pid pid, struct task_struct task)
1da177e4	614	{
ee992744	615	return do_task_stat(m, ns, pid, task, 0);
1da177e4 LT	616	}
1da177e4 LT	617
ee992744 EB	618	int proc_tgid_stat(struct seq_file m, struct pid_namespace ns,
ee992744 EB	619	struct pid pid, struct task_struct task)
1da177e4	620	{
ee992744	621	return do_task_stat(m, ns, pid, task, 1);
1da177e4 LT	622	}
1da177e4 LT	623
a56d3fc7 EB	624	int proc_pid_statm(struct seq_file m, struct pid_namespace ns,
a56d3fc7 EB	625	struct pid pid, struct task_struct task)
1da177e4 LT	626	{
	627	int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0;
	628	struct mm_struct *mm = get_task_mm(task);
8ea02606	629
1da177e4 LT	630	if (mm) {
	631	size = task_statm(mm, &shared, &text, &data, &resident);
	632	mmput(mm);
	633	}
a56d3fc7 EB	634	seq_printf(m, "%d %d %d %d %d %d %d\n",
a56d3fc7 EB	635	size, resident, shared, text, lib, data, 0);
1da177e4	636
a56d3fc7	637	return 0;
1da177e4	638	}