Initial import

34 files changed, 13639 insertions, 0 deletions

diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
new file mode 100644
index 000000000..2183fcf41
--- /dev/null
+++ b/fs/proc/Kconfig
@@ -0,0 +1,73 @@
+config PROC_FS
+	bool "/proc file system support" if EXPERT
+	default y
+	help
+	  This is a virtual file system providing information about the status
+	  of the system. "Virtual" means that it doesn't take up any space on
+	  your hard disk: the files are created on the fly by the kernel when
+	  you try to access them. Also, you cannot read the files with older
+	  version of the program less: you need to use more or cat.
+
+	  It's totally cool; for example, "cat /proc/interrupts" gives
+	  information about what the different IRQs are used for at the moment
+	  (there is a small number of Interrupt ReQuest lines in your computer
+	  that are used by the attached devices to gain the CPU's attention --
+	  often a source of trouble if two devices are mistakenly configured
+	  to use the same IRQ). The program procinfo to display some
+	  information about your system gathered from the /proc file system.
+
+	  Before you can use the /proc file system, it has to be mounted,
+	  meaning it has to be given a location in the directory hierarchy.
+	  That location should be /proc. A command such as "mount -t proc proc
+	  /proc" or the equivalent line in /etc/fstab does the job.
+
+	  The /proc file system is explained in the file
+	  <file:Documentation/filesystems/proc.txt> and on the proc(5) manpage
+	  ("man 5 proc").
+
+	  This option will enlarge your kernel by about 67 KB. Several
+	  programs depend on this, so everyone should say Y here.
+
+config PROC_KCORE
+	bool "/proc/kcore support" if !ARM
+	depends on PROC_FS && MMU
+	help
+	  Provides a virtual ELF core file of the live kernel.  This can
+	  be read with gdb and other ELF tools.  No modifications can be
+	  made using this mechanism.
+
+config PROC_VMCORE
+	bool "/proc/vmcore support"
+	depends on PROC_FS && CRASH_DUMP
+	default y
+        help
+        Exports the dump image of crashed kernel in ELF format.
+
+config PROC_SYSCTL
+	bool "Sysctl support (/proc/sys)" if EXPERT
+	depends on PROC_FS
+	select SYSCTL
+	default y
+	---help---
+	  The sysctl interface provides a means of dynamically changing
+	  certain kernel parameters and variables on the fly without requiring
+	  a recompile of the kernel or reboot of the system.  The primary
+	  interface is through /proc/sys.  If you say Y here a tree of
+	  modifiable sysctl entries will be generated beneath the
+          /proc/sys directory. They are explained in the files
+	  in <file:Documentation/sysctl/>.  Note that enabling this
+	  option will enlarge the kernel by at least 8 KB.
+
+	  As it is generally a good thing, you should say Y here unless
+	  building a kernel for install/rescue disks or your system is very
+	  limited in memory.
+
+config PROC_PAGE_MONITOR
+ 	default y
+	depends on PROC_FS && MMU
+	bool "Enable /proc page monitoring" if EXPERT
+ 	help
+	  Various /proc files exist to monitor process memory utilization:
+	  /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
+	  /proc/kpagecount, and /proc/kpageflags. Disabling these
+          interfaces will reduce the size of the kernel by approximately 4kb.
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
new file mode 100644
index 000000000..7151ea428
--- /dev/null
+++ b/fs/proc/Makefile
@@ -0,0 +1,32 @@
+#
+# Makefile for the Linux proc filesystem routines.
+#
+
+obj-y   += proc.o
+
+proc-y			:= nommu.o task_nommu.o
+proc-$(CONFIG_MMU)	:= task_mmu.o
+
+proc-y       += inode.o root.o base.o generic.o array.o \
+		fd.o
+proc-$(CONFIG_TTY)      += proc_tty.o
+proc-y	+= cmdline.o
+proc-y	+= consoles.o
+proc-y	+= cpuinfo.o
+proc-y	+= devices.o
+proc-y	+= interrupts.o
+proc-y	+= loadavg.o
+proc-y	+= meminfo.o
+proc-y	+= stat.o
+proc-y	+= uptime.o
+proc-y	+= version.o
+proc-y	+= softirqs.o
+proc-y	+= namespaces.o
+proc-y	+= self.o
+proc-y	+= thread_self.o
+proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
+proc-$(CONFIG_NET)		+= proc_net.o
+proc-$(CONFIG_PROC_KCORE)	+= kcore.o
+proc-$(CONFIG_PROC_VMCORE)	+= vmcore.o
+proc-$(CONFIG_PRINTK)	+= kmsg.o
+proc-$(CONFIG_PROC_PAGE_MONITOR)	+= page.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
new file mode 100644
index 000000000..fd02a9ebf
--- /dev/null
+++ b/fs/proc/array.c
@@ -0,0 +1,695 @@
+/*
+ *  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/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/string_helpers.h>
+#include <linux/user_namespace.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)
+{
+	char *buf;
+	char tcomm[sizeof(p->comm)];
+
+	get_task_comm(tcomm, p);
+
+	seq_puts(m, "Name:\t");
+	buf = m->buf + m->count;
+
+	/* Ignore error for now */
+	buf += string_escape_str(tcomm, buf, m->size - m->count,
+				 ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+
+	m->count = buf - m->buf;
+	seq_putc(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 * const task_state_array[] = {
+	"R (running)",		/*   0 */
+	"S (sleeping)",		/*   1 */
+	"D (disk sleep)",	/*   2 */
+	"T (stopped)",		/*   4 */
+	"t (tracing stop)",	/*   8 */
+	"X (dead)",		/*  16 */
+	"Z (zombie)",		/*  32 */
+};
+
+static inline const char *get_task_state(struct task_struct *tsk)
+{
+	unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
+
+	BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
+
+	return task_state_array[fls(state)];
+}
+
+static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *p)
+{
+	struct user_namespace *user_ns = seq_user_ns(m);
+	struct group_info *group_info;
+	int g;
+	struct task_struct *tracer;
+	const struct cred *cred;
+	pid_t ppid, tpid = 0, tgid, ngid;
+	unsigned int max_fds = 0;
+
+	rcu_read_lock();
+	ppid = pid_alive(p) ?
+		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
+
+	tracer = ptrace_parent(p);
+	if (tracer)
+		tpid = task_pid_nr_ns(tracer, ns);
+
+	tgid = task_tgid_nr_ns(p, ns);
+	ngid = task_numa_group_id(p);
+	cred = get_task_cred(p);
+
+	task_lock(p);
+	if (p->files)
+		max_fds = files_fdtable(p->files)->max_fds;
+	task_unlock(p);
+	rcu_read_unlock();
+
+	seq_printf(m,
+		"State:\t%s\n"
+		"Tgid:\t%d\n"
+		"Ngid:\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"
+		"FDSize:\t%d\nGroups:\t",
+		get_task_state(p),
+		tgid, ngid, pid_nr_ns(pid, ns), ppid, tpid,
+		from_kuid_munged(user_ns, cred->uid),
+		from_kuid_munged(user_ns, cred->euid),
+		from_kuid_munged(user_ns, cred->suid),
+		from_kuid_munged(user_ns, cred->fsuid),
+		from_kgid_munged(user_ns, cred->gid),
+		from_kgid_munged(user_ns, cred->egid),
+		from_kgid_munged(user_ns, cred->sgid),
+		from_kgid_munged(user_ns, cred->fsgid),
+		max_fds);
+
+	group_info = cred->group_info;
+	for (g = 0; g < group_info->ngroups; g++)
+		seq_printf(m, "%d ",
+			   from_kgid_munged(user_ns, GROUP_AT(group_info, g)));
+	put_cred(cred);
+
+#ifdef CONFIG_PID_NS
+	seq_puts(m, "\nNStgid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_printf(m, "\t%d",
+			task_tgid_nr_ns(p, pid->numbers[g].ns));
+	seq_puts(m, "\nNSpid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_printf(m, "\t%d",
+			task_pid_nr_ns(p, pid->numbers[g].ns));
+	seq_puts(m, "\nNSpgid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_printf(m, "\t%d",
+			task_pgrp_nr_ns(p, pid->numbers[g].ns));
+	seq_puts(m, "\nNSsid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_printf(m, "\t%d",
+			task_session_nr_ns(p, pid->numbers[g].ns));
+#endif
+	seq_putc(m, '\n');
+}
+
+void render_sigset_t(struct seq_file *m, const char *header,
+				sigset_t *set)
+{
+	int i;
+
+	seq_puts(m, 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_putc(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 = get_nr_threads(p);
+		rcu_read_lock();  /* FIXME: is this correct? */
+		qsize = atomic_read(&__task_cred(p)->user->sigpending);
+		rcu_read_unlock();
+		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
+		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_puts(m, header);
+	CAP_FOR_EACH_U32(__capi) {
+		seq_printf(m, "%08x",
+			   a->cap[CAP_LAST_U32 - __capi]);
+	}
+	seq_putc(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_seccomp(struct seq_file *m, struct task_struct *p)
+{
+#ifdef CONFIG_SECCOMP
+	seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode);
+#endif
+}
+
+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);
+}
+
+static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
+{
+	seq_printf(m, "Cpus_allowed:\t%*pb\n",
+		   cpumask_pr_args(&task->cpus_allowed));
+	seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
+		   cpumask_pr_args(&task->cpus_allowed));
+}
+
+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_seccomp(m, task);
+	task_cpus_allowed(m, task);
+	cpuset_task_status_allowed(m, task);
+	task_context_switch_counts(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;
+	int 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 | PTRACE_MODE_NOAUDIT);
+	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 = 0;
+	cgtime = gtime = 0;
+
+	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 = get_nr_threads(task);
+		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 = ACCESS_ONCE(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 += task_gtime(t);
+			} while_each_thread(task, t);
+
+			min_flt += sig->min_flt;
+			maj_flt += sig->maj_flt;
+			thread_group_cputime_adjusted(task, &utime, &stime);
+			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_cputime_adjusted(task, &utime, &stime);
+		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);
+
+	/* convert nsec -> ticks */
+	start_time = nsec_to_clock_t(task->real_start_time);
+
+	seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state);
+	seq_put_decimal_ll(m, ' ', ppid);
+	seq_put_decimal_ll(m, ' ', pgid);
+	seq_put_decimal_ll(m, ' ', sid);
+	seq_put_decimal_ll(m, ' ', tty_nr);
+	seq_put_decimal_ll(m, ' ', tty_pgrp);
+	seq_put_decimal_ull(m, ' ', task->flags);
+	seq_put_decimal_ull(m, ' ', min_flt);
+	seq_put_decimal_ull(m, ' ', cmin_flt);
+	seq_put_decimal_ull(m, ' ', maj_flt);
+	seq_put_decimal_ull(m, ' ', cmaj_flt);
+	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime));
+	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime));
+	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime));
+	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime));
+	seq_put_decimal_ll(m, ' ', priority);
+	seq_put_decimal_ll(m, ' ', nice);
+	seq_put_decimal_ll(m, ' ', num_threads);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ull(m, ' ', start_time);
+	seq_put_decimal_ull(m, ' ', vsize);
+	seq_put_decimal_ull(m, ' ', mm ? get_mm_rss(mm) : 0);
+	seq_put_decimal_ull(m, ' ', rsslim);
+	seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0);
+	seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0);
+	seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0);
+	seq_put_decimal_ull(m, ' ', esp);
+	seq_put_decimal_ull(m, ' ', eip);
+	/* The signal information here is obsolete.
+	 * It must be decimal for Linux 2.0 compatibility.
+	 * Use /proc/#/status for real-time signals.
+	 */
+	seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', wchan);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ll(m, ' ', task->exit_signal);
+	seq_put_decimal_ll(m, ' ', task_cpu(task));
+	seq_put_decimal_ull(m, ' ', task->rt_priority);
+	seq_put_decimal_ull(m, ' ', task->policy);
+	seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task));
+	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime));
+	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime));
+
+	if (mm && permitted) {
+		seq_put_decimal_ull(m, ' ', mm->start_data);
+		seq_put_decimal_ull(m, ' ', mm->end_data);
+		seq_put_decimal_ull(m, ' ', mm->start_brk);
+		seq_put_decimal_ull(m, ' ', mm->arg_start);
+		seq_put_decimal_ull(m, ' ', mm->arg_end);
+		seq_put_decimal_ull(m, ' ', mm->env_start);
+		seq_put_decimal_ull(m, ' ', mm->env_end);
+	} else
+		seq_printf(m, " 0 0 0 0 0 0 0");
+
+	if (permitted)
+		seq_put_decimal_ll(m, ' ', task->exit_code);
+	else
+		seq_put_decimal_ll(m, ' ', 0);
+
+	seq_putc(m, '\n');
+	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)
+{
+	unsigned long size = 0, resident = 0, shared = 0, text = 0, data = 0;
+	struct mm_struct *mm = get_task_mm(task);
+
+	if (mm) {
+		size = task_statm(mm, &shared, &text, &data, &resident);
+		mmput(mm);
+	}
+	/*
+	 * For quick read, open code by putting numbers directly
+	 * expected format is
+	 * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
+	 *               size, resident, shared, text, data);
+	 */
+	seq_put_decimal_ull(m, 0, size);
+	seq_put_decimal_ull(m, ' ', resident);
+	seq_put_decimal_ull(m, ' ', shared);
+	seq_put_decimal_ull(m, ' ', text);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ull(m, ' ', data);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct pid *
+get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
+{
+	struct task_struct *start, *task;
+	struct pid *pid = NULL;
+
+	read_lock(&tasklist_lock);
+
+	start = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (!start)
+		goto out;
+
+	/*
+	 * Lets try to continue searching first, this gives
+	 * us significant speedup on children-rich processes.
+	 */
+	if (pid_prev) {
+		task = pid_task(pid_prev, PIDTYPE_PID);
+		if (task && task->real_parent == start &&
+		    !(list_empty(&task->sibling))) {
+			if (list_is_last(&task->sibling, &start->children))
+				goto out;
+			task = list_first_entry(&task->sibling,
+						struct task_struct, sibling);
+			pid = get_pid(task_pid(task));
+			goto out;
+		}
+	}
+
+	/*
+	 * Slow search case.
+	 *
+	 * We might miss some children here if children
+	 * are exited while we were not holding the lock,
+	 * but it was never promised to be accurate that
+	 * much.
+	 *
+	 * "Just suppose that the parent sleeps, but N children
+	 *  exit after we printed their tids. Now the slow paths
+	 *  skips N extra children, we miss N tasks." (c)
+	 *
+	 * So one need to stop or freeze the leader and all
+	 * its children to get a precise result.
+	 */
+	list_for_each_entry(task, &start->children, sibling) {
+		if (pos-- == 0) {
+			pid = get_pid(task_pid(task));
+			break;
+		}
+	}
+
+out:
+	read_unlock(&tasklist_lock);
+	return pid;
+}
+
+static int children_seq_show(struct seq_file *seq, void *v)
+{
+	struct inode *inode = seq->private;
+	pid_t pid;
+
+	pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
+	seq_printf(seq, "%d ", pid);
+
+	return 0;
+}
+
+static void *children_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return get_children_pid(seq->private, NULL, *pos);
+}
+
+static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct pid *pid;
+
+	pid = get_children_pid(seq->private, v, *pos + 1);
+	put_pid(v);
+
+	++*pos;
+	return pid;
+}
+
+static void children_seq_stop(struct seq_file *seq, void *v)
+{
+	put_pid(v);
+}
+
+static const struct seq_operations children_seq_ops = {
+	.start	= children_seq_start,
+	.next	= children_seq_next,
+	.stop	= children_seq_stop,
+	.show	= children_seq_show,
+};
+
+static int children_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &children_seq_ops);
+	if (ret)
+		return ret;
+
+	m = file->private_data;
+	m->private = inode;
+
+	return ret;
+}
+
+int children_seq_release(struct inode *inode, struct file *file)
+{
+	seq_release(inode, file);
+	return 0;
+}
+
+const struct file_operations proc_tid_children_operations = {
+	.open    = children_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = children_seq_release,
+};
+#endif /* CONFIG_CHECKPOINT_RESTORE */
diff --git a/fs/proc/base.c b/fs/proc/base.c
new file mode 100644
index 000000000..c439a9dcc
--- /dev/null
+++ b/fs/proc/base.c
@@ -0,0 +1,3214 @@
+/*
+ *  linux/fs/proc/base.c
+ *
+ *  Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ *  proc base directory handling functions
+ *
+ *  1999, Al Viro. Rewritten. Now it covers the whole per-process part.
+ *  Instead of using magical inumbers to determine the kind of object
+ *  we allocate and fill in-core inodes upon lookup. They don't even
+ *  go into icache. We cache the reference to task_struct upon lookup too.
+ *  Eventually it should become a filesystem in its own. We don't use the
+ *  rest of procfs anymore.
+ *
+ *
+ *  Changelog:
+ *  17-Jan-2005
+ *  Allan Bezerra
+ *  Bruna Moreira <bruna.moreira@indt.org.br>
+ *  Edjard Mota <edjard.mota@indt.org.br>
+ *  Ilias Biris <ilias.biris@indt.org.br>
+ *  Mauricio Lin <mauricio.lin@indt.org.br>
+ *
+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *
+ *  A new process specific entry (smaps) included in /proc. It shows the
+ *  size of rss for each memory area. The maps entry lacks information
+ *  about physical memory size (rss) for each mapped file, i.e.,
+ *  rss information for executables and library files.
+ *  This additional information is useful for any tools that need to know
+ *  about physical memory consumption for a process specific library.
+ *
+ *  Changelog:
+ *  21-Feb-2005
+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *  Pud inclusion in the page table walking.
+ *
+ *  ChangeLog:
+ *  10-Mar-2005
+ *  10LE Instituto Nokia de Tecnologia - INdT:
+ *  A better way to walks through the page table as suggested by Hugh Dickins.
+ *
+ *  Simo Piiroinen <simo.piiroinen@nokia.com>:
+ *  Smaps information related to shared, private, clean and dirty pages.
+ *
+ *  Paul Mundt <paul.mundt@nokia.com>:
+ *  Overall revision about smaps.
+ */
+
+#include <asm/uaccess.h>
+
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/init.h>
+#include <linux/capability.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/namei.h>
+#include <linux/mnt_namespace.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/rcupdate.h>
+#include <linux/kallsyms.h>
+#include <linux/stacktrace.h>
+#include <linux/resource.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/security.h>
+#include <linux/ptrace.h>
+#include <linux/tracehook.h>
+#include <linux/printk.h>
+#include <linux/cgroup.h>
+#include <linux/cpuset.h>
+#include <linux/audit.h>
+#include <linux/poll.h>
+#include <linux/nsproxy.h>
+#include <linux/oom.h>
+#include <linux/elf.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include <linux/fs_struct.h>
+#include <linux/slab.h>
+#include <linux/flex_array.h>
+#include <linux/posix-timers.h>
+#ifdef CONFIG_HARDWALL
+#include <asm/hardwall.h>
+#endif
+#include <trace/events/oom.h>
+#include "internal.h"
+#include "fd.h"
+
+/* NOTE:
+ *	Implementing inode permission operations in /proc is almost
+ *	certainly an error.  Permission checks need to happen during
+ *	each system call not at open time.  The reason is that most of
+ *	what we wish to check for permissions in /proc varies at runtime.
+ *
+ *	The classic example of a problem is opening file descriptors
+ *	in /proc for a task before it execs a suid executable.
+ */
+
+struct pid_entry {
+	const char *name;
+	int len;
+	umode_t mode;
+	const struct inode_operations *iop;
+	const struct file_operations *fop;
+	union proc_op op;
+};
+
+#define NOD(NAME, MODE, IOP, FOP, OP) {			\
+	.name = (NAME),					\
+	.len  = sizeof(NAME) - 1,			\
+	.mode = MODE,					\
+	.iop  = IOP,					\
+	.fop  = FOP,					\
+	.op   = OP,					\
+}
+
+#define DIR(NAME, MODE, iops, fops)	\
+	NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} )
+#define LNK(NAME, get_link)					\
+	NOD(NAME, (S_IFLNK|S_IRWXUGO),				\
+		&proc_pid_link_inode_operations, NULL,		\
+		{ .proc_get_link = get_link } )
+#define REG(NAME, MODE, fops)				\
+	NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
+#define ONE(NAME, MODE, show)				\
+	NOD(NAME, (S_IFREG|(MODE)), 			\
+		NULL, &proc_single_file_operations,	\
+		{ .proc_show = show } )
+
+/*
+ * Count the number of hardlinks for the pid_entry table, excluding the .
+ * and .. links.
+ */
+static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
+	unsigned int n)
+{
+	unsigned int i;
+	unsigned int count;
+
+	count = 0;
+	for (i = 0; i < n; ++i) {
+		if (S_ISDIR(entries[i].mode))
+			++count;
+	}
+
+	return count;
+}
+
+static int get_task_root(struct task_struct *task, struct path *root)
+{
+	int result = -ENOENT;
+
+	task_lock(task);
+	if (task->fs) {
+		get_fs_root(task->fs, root);
+		result = 0;
+	}
+	task_unlock(task);
+	return result;
+}
+
+static int proc_cwd_link(struct dentry *dentry, struct path *path)
+{
+	struct task_struct *task = get_proc_task(d_inode(dentry));
+	int result = -ENOENT;
+
+	if (task) {
+		task_lock(task);
+		if (task->fs) {
+			get_fs_pwd(task->fs, path);
+			result = 0;
+		}
+		task_unlock(task);
+		put_task_struct(task);
+	}
+	return result;
+}
+
+static int proc_root_link(struct dentry *dentry, struct path *path)
+{
+	struct task_struct *task = get_proc_task(d_inode(dentry));
+	int result = -ENOENT;
+
+	if (task) {
+		result = get_task_root(task, path);
+		put_task_struct(task);
+	}
+	return result;
+}
+
+static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *task)
+{
+	/*
+	 * Rely on struct seq_operations::show() being called once
+	 * per internal buffer allocation. See single_open(), traverse().
+	 */
+	BUG_ON(m->size < PAGE_SIZE);
+	m->count += get_cmdline(task, m->buf, PAGE_SIZE);
+	return 0;
+}
+
+static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
+			 struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+	if (mm && !IS_ERR(mm)) {
+		unsigned int nwords = 0;
+		do {
+			nwords += 2;
+		} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
+		seq_write(m, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0]));
+		mmput(mm);
+		return 0;
+	} else
+		return PTR_ERR(mm);
+}
+
+
+#ifdef CONFIG_KALLSYMS
+/*
+ * Provides a wchan file via kallsyms in a proper one-value-per-file format.
+ * Returns the resolved symbol.  If that fails, simply return the address.
+ */
+static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
+			  struct pid *pid, struct task_struct *task)
+{
+	unsigned long wchan;
+	char symname[KSYM_NAME_LEN];
+
+	wchan = get_wchan(task);
+
+	if (lookup_symbol_name(wchan, symname) < 0) {
+		if (!ptrace_may_access(task, PTRACE_MODE_READ))
+			return 0;
+		seq_printf(m, "%lu", wchan);
+	} else {
+		seq_printf(m, "%s", symname);
+	}
+
+	return 0;
+}
+#endif /* CONFIG_KALLSYMS */
+
+static int lock_trace(struct task_struct *task)
+{
+	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	if (err)
+		return err;
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		return -EPERM;
+	}
+	return 0;
+}
+
+static void unlock_trace(struct task_struct *task)
+{
+	mutex_unlock(&task->signal->cred_guard_mutex);
+}
+
+#ifdef CONFIG_STACKTRACE
+
+#define MAX_STACK_TRACE_DEPTH	64
+
+static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
+			  struct pid *pid, struct task_struct *task)
+{
+	struct stack_trace trace;
+	unsigned long *entries;
+	int err;
+	int i;
+
+	entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
+	trace.entries		= entries;
+	trace.skip		= 0;
+
+	err = lock_trace(task);
+	if (!err) {
+		save_stack_trace_tsk(task, &trace);
+
+		for (i = 0; i < trace.nr_entries; i++) {
+			seq_printf(m, "[<%pK>] %pS\n",
+				   (void *)entries[i], (void *)entries[i]);
+		}
+		unlock_trace(task);
+	}
+	kfree(entries);
+
+	return err;
+}
+#endif
+
+#ifdef CONFIG_SCHEDSTATS
+/*
+ * Provides /proc/PID/schedstat
+ */
+static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
+			      struct pid *pid, struct task_struct *task)
+{
+	seq_printf(m, "%llu %llu %lu\n",
+		   (unsigned long long)tsk_seruntime(task),
+		   (unsigned long long)task->sched_info.run_delay,
+		   task->sched_info.pcount);
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_LATENCYTOP
+static int lstats_show_proc(struct seq_file *m, void *v)
+{
+	int i;
+	struct inode *inode = m->private;
+	struct task_struct *task = get_proc_task(inode);
+
+	if (!task)
+		return -ESRCH;
+	seq_puts(m, "Latency Top version : v0.1\n");
+	for (i = 0; i < 32; i++) {
+		struct latency_record *lr = &task->latency_record[i];
+		if (lr->backtrace[0]) {
+			int q;
+			seq_printf(m, "%i %li %li",
+				   lr->count, lr->time, lr->max);
+			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
+				unsigned long bt = lr->backtrace[q];
+				if (!bt)
+					break;
+				if (bt == ULONG_MAX)
+					break;
+				seq_printf(m, " %ps", (void *)bt);
+			}
+			seq_putc(m, '\n');
+		}
+
+	}
+	put_task_struct(task);
+	return 0;
+}
+
+static int lstats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, lstats_show_proc, inode);
+}
+
+static ssize_t lstats_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *offs)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+
+	if (!task)
+		return -ESRCH;
+	clear_all_latency_tracing(task);
+	put_task_struct(task);
+
+	return count;
+}
+
+static const struct file_operations proc_lstats_operations = {
+	.open		= lstats_open,
+	.read		= seq_read,
+	.write		= lstats_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#endif
+
+static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
+			  struct pid *pid, struct task_struct *task)
+{
+	unsigned long totalpages = totalram_pages + total_swap_pages;
+	unsigned long points = 0;
+
+	read_lock(&tasklist_lock);
+	if (pid_alive(task))
+		points = oom_badness(task, NULL, NULL, totalpages) *
+						1000 / totalpages;
+	read_unlock(&tasklist_lock);
+	seq_printf(m, "%lu\n", points);
+
+	return 0;
+}
+
+struct limit_names {
+	const char *name;
+	const char *unit;
+};
+
+static const struct limit_names lnames[RLIM_NLIMITS] = {
+	[RLIMIT_CPU] = {"Max cpu time", "seconds"},
+	[RLIMIT_FSIZE] = {"Max file size", "bytes"},
+	[RLIMIT_DATA] = {"Max data size", "bytes"},
+	[RLIMIT_STACK] = {"Max stack size", "bytes"},
+	[RLIMIT_CORE] = {"Max core file size", "bytes"},
+	[RLIMIT_RSS] = {"Max resident set", "bytes"},
+	[RLIMIT_NPROC] = {"Max processes", "processes"},
+	[RLIMIT_NOFILE] = {"Max open files", "files"},
+	[RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"},
+	[RLIMIT_AS] = {"Max address space", "bytes"},
+	[RLIMIT_LOCKS] = {"Max file locks", "locks"},
+	[RLIMIT_SIGPENDING] = {"Max pending signals", "signals"},
+	[RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"},
+	[RLIMIT_NICE] = {"Max nice priority", NULL},
+	[RLIMIT_RTPRIO] = {"Max realtime priority", NULL},
+	[RLIMIT_RTTIME] = {"Max realtime timeout", "us"},
+};
+
+/* Display limits for a process */
+static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task)
+{
+	unsigned int i;
+	unsigned long flags;
+
+	struct rlimit rlim[RLIM_NLIMITS];
+
+	if (!lock_task_sighand(task, &flags))
+		return 0;
+	memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
+	unlock_task_sighand(task, &flags);
+
+	/*
+	 * print the file header
+	 */
+       seq_printf(m, "%-25s %-20s %-20s %-10s\n",
+		  "Limit", "Soft Limit", "Hard Limit", "Units");
+
+	for (i = 0; i < RLIM_NLIMITS; i++) {
+		if (rlim[i].rlim_cur == RLIM_INFINITY)
+			seq_printf(m, "%-25s %-20s ",
+				   lnames[i].name, "unlimited");
+		else
+			seq_printf(m, "%-25s %-20lu ",
+				   lnames[i].name, rlim[i].rlim_cur);
+
+		if (rlim[i].rlim_max == RLIM_INFINITY)
+			seq_printf(m, "%-20s ", "unlimited");
+		else
+			seq_printf(m, "%-20lu ", rlim[i].rlim_max);
+
+		if (lnames[i].unit)
+			seq_printf(m, "%-10s\n", lnames[i].unit);
+		else
+			seq_putc(m, '\n');
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *task)
+{
+	long nr;
+	unsigned long args[6], sp, pc;
+	int res;
+
+	res = lock_trace(task);
+	if (res)
+		return res;
+
+	if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
+		seq_puts(m, "running\n");
+	else if (nr < 0)
+		seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+	else
+		seq_printf(m,
+		       "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
+		       nr,
+		       args[0], args[1], args[2], args[3], args[4], args[5],
+		       sp, pc);
+	unlock_trace(task);
+
+	return 0;
+}
+#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
+
+/************************************************************************/
+/*                       Here the fs part begins                        */
+/************************************************************************/
+
+/* permission checks */
+static int proc_fd_access_allowed(struct inode *inode)
+{
+	struct task_struct *task;
+	int allowed = 0;
+	/* Allow access to a task's file descriptors if it is us or we
+	 * may use ptrace attach to the process and find out that
+	 * information.
+	 */
+	task = get_proc_task(inode);
+	if (task) {
+		allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+		put_task_struct(task);
+	}
+	return allowed;
+}
+
+int proc_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	int error;
+	struct inode *inode = d_inode(dentry);
+
+	if (attr->ia_valid & ATTR_MODE)
+		return -EPERM;
+
+	error = inode_change_ok(inode, attr);
+	if (error)
+		return error;
+
+	setattr_copy(inode, attr);
+	mark_inode_dirty(inode);
+	return 0;
+}
+
+/*
+ * May current process learn task's sched/cmdline info (for hide_pid_min=1)
+ * or euid/egid (for hide_pid_min=2)?
+ */
+static bool has_pid_permissions(struct pid_namespace *pid,
+				 struct task_struct *task,
+				 int hide_pid_min)
+{
+	if (pid->hide_pid < hide_pid_min)
+		return true;
+	if (in_group_p(pid->pid_gid))
+		return true;
+	return ptrace_may_access(task, PTRACE_MODE_READ);
+}
+
+
+static int proc_pid_permission(struct inode *inode, int mask)
+{
+	struct pid_namespace *pid = inode->i_sb->s_fs_info;
+	struct task_struct *task;
+	bool has_perms;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return -ESRCH;
+	has_perms = has_pid_permissions(pid, task, 1);
+	put_task_struct(task);
+
+	if (!has_perms) {
+		if (pid->hide_pid == 2) {
+			/*
+			 * Let's make getdents(), stat(), and open()
+			 * consistent with each other.  If a process
+			 * may not stat() a file, it shouldn't be seen
+			 * in procfs at all.
+			 */
+			return -ENOENT;
+		}
+
+		return -EPERM;
+	}
+	return generic_permission(inode, mask);
+}
+
+
+
+static const struct inode_operations proc_def_inode_operations = {
+	.setattr	= proc_setattr,
+};
+
+static int proc_single_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct pid_namespace *ns;
+	struct pid *pid;
+	struct task_struct *task;
+	int ret;
+
+	ns = inode->i_sb->s_fs_info;
+	pid = proc_pid(inode);
+	task = get_pid_task(pid, PIDTYPE_PID);
+	if (!task)
+		return -ESRCH;
+
+	ret = PROC_I(inode)->op.proc_show(m, ns, pid, task);
+
+	put_task_struct(task);
+	return ret;
+}
+
+static int proc_single_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, proc_single_show, inode);
+}
+
+static const struct file_operations proc_single_file_operations = {
+	.open		= proc_single_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
+{
+	struct task_struct *task = get_proc_task(inode);
+	struct mm_struct *mm = ERR_PTR(-ESRCH);
+
+	if (task) {
+		mm = mm_access(task, mode);
+		put_task_struct(task);
+
+		if (!IS_ERR_OR_NULL(mm)) {
+			/* ensure this mm_struct can't be freed */
+			atomic_inc(&mm->mm_count);
+			/* but do not pin its memory */
+			mmput(mm);
+		}
+	}
+
+	return mm;
+}
+
+static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+{
+	struct mm_struct *mm = proc_mem_open(inode, mode);
+
+	if (IS_ERR(mm))
+		return PTR_ERR(mm);
+
+	file->private_data = mm;
+	return 0;
+}
+
+static int mem_open(struct inode *inode, struct file *file)
+{
+	int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH);
+
+	/* OK to pass negative loff_t, we can catch out-of-range */
+	file->f_mode |= FMODE_UNSIGNED_OFFSET;
+
+	return ret;
+}
+
+static ssize_t mem_rw(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos, int write)
+{
+	struct mm_struct *mm = file->private_data;
+	unsigned long addr = *ppos;
+	ssize_t copied;
+	char *page;
+
+	if (!mm)
+		return 0;
+
+	page = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!page)
+		return -ENOMEM;
+
+	copied = 0;
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		goto free;
+
+	while (count > 0) {
+		int this_len = min_t(int, count, PAGE_SIZE);
+
+		if (write && copy_from_user(page, buf, this_len)) {
+			copied = -EFAULT;
+			break;
+		}
+
+		this_len = access_remote_vm(mm, addr, page, this_len, write);
+		if (!this_len) {
+			if (!copied)
+				copied = -EIO;
+			break;
+		}
+
+		if (!write && copy_to_user(buf, page, this_len)) {
+			copied = -EFAULT;
+			break;
+		}
+
+		buf += this_len;
+		addr += this_len;
+		copied += this_len;
+		count -= this_len;
+	}
+	*ppos = addr;
+
+	mmput(mm);
+free:
+	free_page((unsigned long) page);
+	return copied;
+}
+
+static ssize_t mem_read(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	return mem_rw(file, buf, count, ppos, 0);
+}
+
+static ssize_t mem_write(struct file *file, const char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	return mem_rw(file, (char __user*)buf, count, ppos, 1);
+}
+
+loff_t mem_lseek(struct file *file, loff_t offset, int orig)
+{
+	switch (orig) {
+	case 0:
+		file->f_pos = offset;
+		break;
+	case 1:
+		file->f_pos += offset;
+		break;
+	default:
+		return -EINVAL;
+	}
+	force_successful_syscall_return();
+	return file->f_pos;
+}
+
+static int mem_release(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = file->private_data;
+	if (mm)
+		mmdrop(mm);
+	return 0;
+}
+
+static const struct file_operations proc_mem_operations = {
+	.llseek		= mem_lseek,
+	.read		= mem_read,
+	.write		= mem_write,
+	.open		= mem_open,
+	.release	= mem_release,
+};
+
+static int environ_open(struct inode *inode, struct file *file)
+{
+	return __mem_open(inode, file, PTRACE_MODE_READ);
+}
+
+static ssize_t environ_read(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	char *page;
+	unsigned long src = *ppos;
+	int ret = 0;
+	struct mm_struct *mm = file->private_data;
+
+	if (!mm)
+		return 0;
+
+	page = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!page)
+		return -ENOMEM;
+
+	ret = 0;
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		goto free;
+	while (count > 0) {
+		size_t this_len, max_len;
+		int retval;
+
+		if (src >= (mm->env_end - mm->env_start))
+			break;
+
+		this_len = mm->env_end - (mm->env_start + src);
+
+		max_len = min_t(size_t, PAGE_SIZE, count);
+		this_len = min(max_len, this_len);
+
+		retval = access_remote_vm(mm, (mm->env_start + src),
+			page, this_len, 0);
+
+		if (retval <= 0) {
+			ret = retval;
+			break;
+		}
+
+		if (copy_to_user(buf, page, retval)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		ret += retval;
+		src += retval;
+		buf += retval;
+		count -= retval;
+	}
+	*ppos = src;
+	mmput(mm);
+
+free:
+	free_page((unsigned long) page);
+	return ret;
+}
+
+static const struct file_operations proc_environ_operations = {
+	.open		= environ_open,
+	.read		= environ_read,
+	.llseek		= generic_file_llseek,
+	.release	= mem_release,
+};
+
+static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	char buffer[PROC_NUMBUF];
+	int oom_adj = OOM_ADJUST_MIN;
+	size_t len;
+	unsigned long flags;
+
+	if (!task)
+		return -ESRCH;
+	if (lock_task_sighand(task, &flags)) {
+		if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+			oom_adj = OOM_ADJUST_MAX;
+		else
+			oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+				  OOM_SCORE_ADJ_MAX;
+		unlock_task_sighand(task, &flags);
+	}
+	put_task_struct(task);
+	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
+	return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_adj_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF];
+	int oom_adj;
+	unsigned long flags;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err = kstrtoint(strstrip(buffer), 0, &oom_adj);
+	if (err)
+		goto out;
+	if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) &&
+	     oom_adj != OOM_DISABLE) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	task = get_proc_task(file_inode(file));
+	if (!task) {
+		err = -ESRCH;
+		goto out;
+	}
+
+	task_lock(task);
+	if (!task->mm) {
+		err = -EINVAL;
+		goto err_task_lock;
+	}
+
+	if (!lock_task_sighand(task, &flags)) {
+		err = -ESRCH;
+		goto err_task_lock;
+	}
+
+	/*
+	 * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+	 * value is always attainable.
+	 */
+	if (oom_adj == OOM_ADJUST_MAX)
+		oom_adj = OOM_SCORE_ADJ_MAX;
+	else
+		oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+
+	if (oom_adj < task->signal->oom_score_adj &&
+	    !capable(CAP_SYS_RESOURCE)) {
+		err = -EACCES;
+		goto err_sighand;
+	}
+
+	/*
+	 * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+	 * /proc/pid/oom_score_adj instead.
+	 */
+	pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+		  current->comm, task_pid_nr(current), task_pid_nr(task),
+		  task_pid_nr(task));
+
+	task->signal->oom_score_adj = oom_adj;
+	trace_oom_score_adj_update(task);
+err_sighand:
+	unlock_task_sighand(task, &flags);
+err_task_lock:
+	task_unlock(task);
+	put_task_struct(task);
+out:
+	return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_adj_operations = {
+	.read		= oom_adj_read,
+	.write		= oom_adj_write,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	char buffer[PROC_NUMBUF];
+	short oom_score_adj = OOM_SCORE_ADJ_MIN;
+	unsigned long flags;
+	size_t len;
+
+	if (!task)
+		return -ESRCH;
+	if (lock_task_sighand(task, &flags)) {
+		oom_score_adj = task->signal->oom_score_adj;
+		unlock_task_sighand(task, &flags);
+	}
+	put_task_struct(task);
+	len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
+	return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF];
+	unsigned long flags;
+	int oom_score_adj;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err = kstrtoint(strstrip(buffer), 0, &oom_score_adj);
+	if (err)
+		goto out;
+	if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
+			oom_score_adj > OOM_SCORE_ADJ_MAX) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	task = get_proc_task(file_inode(file));
+	if (!task) {
+		err = -ESRCH;
+		goto out;
+	}
+
+	task_lock(task);
+	if (!task->mm) {
+		err = -EINVAL;
+		goto err_task_lock;
+	}
+
+	if (!lock_task_sighand(task, &flags)) {
+		err = -ESRCH;
+		goto err_task_lock;
+	}
+
+	if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
+			!capable(CAP_SYS_RESOURCE)) {
+		err = -EACCES;
+		goto err_sighand;
+	}
+
+	task->signal->oom_score_adj = (short)oom_score_adj;
+	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
+		task->signal->oom_score_adj_min = (short)oom_score_adj;
+	trace_oom_score_adj_update(task);
+
+err_sighand:
+	unlock_task_sighand(task, &flags);
+err_task_lock:
+	task_unlock(task);
+	put_task_struct(task);
+out:
+	return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_score_adj_operations = {
+	.read		= oom_score_adj_read,
+	.write		= oom_score_adj_write,
+	.llseek		= default_llseek,
+};
+
+#ifdef CONFIG_AUDITSYSCALL
+#define TMPBUFLEN 21
+static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
+				  size_t count, loff_t *ppos)
+{
+	struct inode * inode = file_inode(file);
+	struct task_struct *task = get_proc_task(inode);
+	ssize_t length;
+	char tmpbuf[TMPBUFLEN];
+
+	if (!task)
+		return -ESRCH;
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
+			   from_kuid(file->f_cred->user_ns,
+				     audit_get_loginuid(task)));
+	put_task_struct(task);
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
+				   size_t count, loff_t *ppos)
+{
+	struct inode * inode = file_inode(file);
+	char *page, *tmp;
+	ssize_t length;
+	uid_t loginuid;
+	kuid_t kloginuid;
+
+	rcu_read_lock();
+	if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
+		rcu_read_unlock();
+		return -EPERM;
+	}
+	rcu_read_unlock();
+
+	if (count >= PAGE_SIZE)
+		count = PAGE_SIZE - 1;
+
+	if (*ppos != 0) {
+		/* No partial writes. */
+		return -EINVAL;
+	}
+	page = (char*)__get_free_page(GFP_TEMPORARY);
+	if (!page)
+		return -ENOMEM;
+	length = -EFAULT;
+	if (copy_from_user(page, buf, count))
+		goto out_free_page;
+
+	page[count] = '\0';
+	loginuid = simple_strtoul(page, &tmp, 10);
+	if (tmp == page) {
+		length = -EINVAL;
+		goto out_free_page;
+
+	}
+
+	/* is userspace tring to explicitly UNSET the loginuid? */
+	if (loginuid == AUDIT_UID_UNSET) {
+		kloginuid = INVALID_UID;
+	} else {
+		kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
+		if (!uid_valid(kloginuid)) {
+			length = -EINVAL;
+			goto out_free_page;
+		}
+	}
+
+	length = audit_set_loginuid(kloginuid);
+	if (likely(length == 0))
+		length = count;
+
+out_free_page:
+	free_page((unsigned long) page);
+	return length;
+}
+
+static const struct file_operations proc_loginuid_operations = {
+	.read		= proc_loginuid_read,
+	.write		= proc_loginuid_write,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t proc_sessionid_read(struct file * file, char __user * buf,
+				  size_t count, loff_t *ppos)
+{
+	struct inode * inode = file_inode(file);
+	struct task_struct *task = get_proc_task(inode);
+	ssize_t length;
+	char tmpbuf[TMPBUFLEN];
+
+	if (!task)
+		return -ESRCH;
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
+				audit_get_sessionid(task));
+	put_task_struct(task);
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static const struct file_operations proc_sessionid_operations = {
+	.read		= proc_sessionid_read,
+	.llseek		= generic_file_llseek,
+};
+#endif
+
+#ifdef CONFIG_FAULT_INJECTION
+static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
+				      size_t count, loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	char buffer[PROC_NUMBUF];
+	size_t len;
+	int make_it_fail;
+
+	if (!task)
+		return -ESRCH;
+	make_it_fail = task->make_it_fail;
+	put_task_struct(task);
+
+	len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail);
+
+	return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t proc_fault_inject_write(struct file * file,
+			const char __user * buf, size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF], *end;
+	int make_it_fail;
+
+	if (!capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+	make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
+	if (*end)
+		return -EINVAL;
+	if (make_it_fail < 0 || make_it_fail > 1)
+		return -EINVAL;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+	task->make_it_fail = make_it_fail;
+	put_task_struct(task);
+
+	return count;
+}
+
+static const struct file_operations proc_fault_inject_operations = {
+	.read		= proc_fault_inject_read,
+	.write		= proc_fault_inject_write,
+	.llseek		= generic_file_llseek,
+};
+#endif
+
+
+#ifdef CONFIG_SCHED_DEBUG
+/*
+ * Print out various scheduling related per-task fields:
+ */
+static int sched_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+	proc_sched_show_task(p, m);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static ssize_t
+sched_write(struct file *file, const char __user *buf,
+	    size_t count, loff_t *offset)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *p;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+	proc_sched_set_task(p);
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int sched_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_show, inode);
+}
+
+static const struct file_operations proc_pid_sched_operations = {
+	.open		= sched_open,
+	.read		= seq_read,
+	.write		= sched_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#endif
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+/*
+ * Print out autogroup related information:
+ */
+static int sched_autogroup_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+	proc_sched_autogroup_show_task(p, m);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static ssize_t
+sched_autogroup_write(struct file *file, const char __user *buf,
+	    size_t count, loff_t *offset)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *p;
+	char buffer[PROC_NUMBUF];
+	int nice;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+
+	err = kstrtoint(strstrip(buffer), 0, &nice);
+	if (err < 0)
+		return err;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	err = proc_sched_autogroup_set_nice(p, nice);
+	if (err)
+		count = err;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int sched_autogroup_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+
+	ret = single_open(filp, sched_autogroup_show, NULL);
+	if (!ret) {
+		struct seq_file *m = filp->private_data;
+
+		m->private = inode;
+	}
+	return ret;
+}
+
+static const struct file_operations proc_pid_sched_autogroup_operations = {
+	.open		= sched_autogroup_open,
+	.read		= seq_read,
+	.write		= sched_autogroup_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
+
+static ssize_t comm_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *offset)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *p;
+	char buffer[TASK_COMM_LEN];
+	const size_t maxlen = sizeof(buffer) - 1;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count))
+		return -EFAULT;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (same_thread_group(current, p))
+		set_task_comm(p, buffer);
+	else
+		count = -EINVAL;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int comm_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	task_lock(p);
+	seq_printf(m, "%s\n", p->comm);
+	task_unlock(p);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static int comm_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, comm_show, inode);
+}
+
+static const struct file_operations proc_pid_set_comm_operations = {
+	.open		= comm_open,
+	.read		= seq_read,
+	.write		= comm_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
+{
+	struct task_struct *task;
+	struct mm_struct *mm;
+	struct file *exe_file;
+
+	task = get_proc_task(d_inode(dentry));
+	if (!task)
+		return -ENOENT;
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	if (!mm)
+		return -ENOENT;
+	exe_file = get_mm_exe_file(mm);
+	mmput(mm);
+	if (exe_file) {
+		*exe_path = exe_file->f_path;
+		path_get(&exe_file->f_path);
+		fput(exe_file);
+		return 0;
+	} else
+		return -ENOENT;
+}
+
+static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct inode *inode = d_inode(dentry);
+	struct path path;
+	int error = -EACCES;
+
+	/* Are we allowed to snoop on the tasks file descriptors? */
+	if (!proc_fd_access_allowed(inode))
+		goto out;
+
+	error = PROC_I(inode)->op.proc_get_link(dentry, &path);
+	if (error)
+		goto out;
+
+	nd_jump_link(nd, &path);
+	return NULL;
+out:
+	return ERR_PTR(error);
+}
+
+static int do_proc_readlink(struct path *path, char __user *buffer, int buflen)
+{
+	char *tmp = (char*)__get_free_page(GFP_TEMPORARY);
+	char *pathname;
+	int len;
+
+	if (!tmp)
+		return -ENOMEM;
+
+	pathname = d_path(path, tmp, PAGE_SIZE);
+	len = PTR_ERR(pathname);
+	if (IS_ERR(pathname))
+		goto out;
+	len = tmp + PAGE_SIZE - 1 - pathname;
+
+	if (len > buflen)
+		len = buflen;
+	if (copy_to_user(buffer, pathname, len))
+		len = -EFAULT;
+ out:
+	free_page((unsigned long)tmp);
+	return len;
+}
+
+static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen)
+{
+	int error = -EACCES;
+	struct inode *inode = d_inode(dentry);
+	struct path path;
+
+	/* Are we allowed to snoop on the tasks file descriptors? */
+	if (!proc_fd_access_allowed(inode))
+		goto out;
+
+	error = PROC_I(inode)->op.proc_get_link(dentry, &path);
+	if (error)
+		goto out;
+
+	error = do_proc_readlink(&path, buffer, buflen);
+	path_put(&path);
+out:
+	return error;
+}
+
+const struct inode_operations proc_pid_link_inode_operations = {
+	.readlink	= proc_pid_readlink,
+	.follow_link	= proc_pid_follow_link,
+	.setattr	= proc_setattr,
+};
+
+
+/* building an inode */
+
+struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
+{
+	struct inode * inode;
+	struct proc_inode *ei;
+	const struct cred *cred;
+
+	/* We need a new inode */
+
+	inode = new_inode(sb);
+	if (!inode)
+		goto out;
+
+	/* Common stuff */
+	ei = PROC_I(inode);
+	inode->i_ino = get_next_ino();
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_op = &proc_def_inode_operations;
+
+	/*
+	 * grab the reference to task.
+	 */
+	ei->pid = get_task_pid(task, PIDTYPE_PID);
+	if (!ei->pid)
+		goto out_unlock;
+
+	if (task_dumpable(task)) {
+		rcu_read_lock();
+		cred = __task_cred(task);
+		inode->i_uid = cred->euid;
+		inode->i_gid = cred->egid;
+		rcu_read_unlock();
+	}
+	security_task_to_inode(task, inode);
+
+out:
+	return inode;
+
+out_unlock:
+	iput(inode);
+	return NULL;
+}
+
+int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	struct task_struct *task;
+	const struct cred *cred;
+	struct pid_namespace *pid = dentry->d_sb->s_fs_info;
+
+	generic_fillattr(inode, stat);
+
+	rcu_read_lock();
+	stat->uid = GLOBAL_ROOT_UID;
+	stat->gid = GLOBAL_ROOT_GID;
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		if (!has_pid_permissions(pid, task, 2)) {
+			rcu_read_unlock();
+			/*
+			 * This doesn't prevent learning whether PID exists,
+			 * it only makes getattr() consistent with readdir().
+			 */
+			return -ENOENT;
+		}
+		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
+		    task_dumpable(task)) {
+			cred = __task_cred(task);
+			stat->uid = cred->euid;
+			stat->gid = cred->egid;
+		}
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+/* dentry stuff */
+
+/*
+ *	Exceptional case: normally we are not allowed to unhash a busy
+ * directory. In this case, however, we can do it - no aliasing problems
+ * due to the way we treat inodes.
+ *
+ * Rewrite the inode's ownerships here because the owning task may have
+ * performed a setuid(), etc.
+ *
+ * Before the /proc/pid/status file was created the only way to read
+ * the effective uid of a /process was to stat /proc/pid.  Reading
+ * /proc/pid/status is slow enough that procps and other packages
+ * kept stating /proc/pid.  To keep the rules in /proc simple I have
+ * made this apply to all per process world readable and executable
+ * directories.
+ */
+int pid_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *inode;
+	struct task_struct *task;
+	const struct cred *cred;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = d_inode(dentry);
+	task = get_proc_task(inode);
+
+	if (task) {
+		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
+		    task_dumpable(task)) {
+			rcu_read_lock();
+			cred = __task_cred(task);
+			inode->i_uid = cred->euid;
+			inode->i_gid = cred->egid;
+			rcu_read_unlock();
+		} else {
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+		}
+		inode->i_mode &= ~(S_ISUID | S_ISGID);
+		security_task_to_inode(task, inode);
+		put_task_struct(task);
+		return 1;
+	}
+	return 0;
+}
+
+static inline bool proc_inode_is_dead(struct inode *inode)
+{
+	return !proc_pid(inode)->tasks[PIDTYPE_PID].first;
+}
+
+int pid_delete_dentry(const struct dentry *dentry)
+{
+	/* Is the task we represent dead?
+	 * If so, then don't put the dentry on the lru list,
+	 * kill it immediately.
+	 */
+	return proc_inode_is_dead(d_inode(dentry));
+}
+
+const struct dentry_operations pid_dentry_operations =
+{
+	.d_revalidate	= pid_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+/* Lookups */
+
+/*
+ * Fill a directory entry.
+ *
+ * If possible create the dcache entry and derive our inode number and
+ * file type from dcache entry.
+ *
+ * Since all of the proc inode numbers are dynamically generated, the inode
+ * numbers do not exist until the inode is cache.  This means creating the
+ * the dcache entry in readdir is necessary to keep the inode numbers
+ * reported by readdir in sync with the inode numbers reported
+ * by stat.
+ */
+bool proc_fill_cache(struct file *file, struct dir_context *ctx,
+	const char *name, int len,
+	instantiate_t instantiate, struct task_struct *task, const void *ptr)
+{
+	struct dentry *child, *dir = file->f_path.dentry;
+	struct qstr qname = QSTR_INIT(name, len);
+	struct inode *inode;
+	unsigned type;
+	ino_t ino;
+
+	child = d_hash_and_lookup(dir, &qname);
+	if (!child) {
+		child = d_alloc(dir, &qname);
+		if (!child)
+			goto end_instantiate;
+		if (instantiate(d_inode(dir), child, task, ptr) < 0) {
+			dput(child);
+			goto end_instantiate;
+		}
+	}
+	inode = d_inode(child);
+	ino = inode->i_ino;
+	type = inode->i_mode >> 12;
+	dput(child);
+	return dir_emit(ctx, name, len, ino, type);
+
+end_instantiate:
+	return dir_emit(ctx, name, len, 1, DT_UNKNOWN);
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+
+/*
+ * dname_to_vma_addr - maps a dentry name into two unsigned longs
+ * which represent vma start and end addresses.
+ */
+static int dname_to_vma_addr(struct dentry *dentry,
+			     unsigned long *start, unsigned long *end)
+{
+	if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	unsigned long vm_start, vm_end;
+	bool exact_vma_exists = false;
+	struct mm_struct *mm = NULL;
+	struct task_struct *task;
+	const struct cred *cred;
+	struct inode *inode;
+	int status = 0;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (!capable(CAP_SYS_ADMIN)) {
+		status = -EPERM;
+		goto out_notask;
+	}
+
+	inode = d_inode(dentry);
+	task = get_proc_task(inode);
+	if (!task)
+		goto out_notask;
+
+	mm = mm_access(task, PTRACE_MODE_READ);
+	if (IS_ERR_OR_NULL(mm))
+		goto out;
+
+	if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
+		down_read(&mm->mmap_sem);
+		exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end);
+		up_read(&mm->mmap_sem);
+	}
+
+	mmput(mm);
+
+	if (exact_vma_exists) {
+		if (task_dumpable(task)) {
+			rcu_read_lock();
+			cred = __task_cred(task);
+			inode->i_uid = cred->euid;
+			inode->i_gid = cred->egid;
+			rcu_read_unlock();
+		} else {
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+		}
+		security_task_to_inode(task, inode);
+		status = 1;
+	}
+
+out:
+	put_task_struct(task);
+
+out_notask:
+	return status;
+}
+
+static const struct dentry_operations tid_map_files_dentry_operations = {
+	.d_revalidate	= map_files_d_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
+{
+	unsigned long vm_start, vm_end;
+	struct vm_area_struct *vma;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	int rc;
+
+	rc = -ENOENT;
+	task = get_proc_task(d_inode(dentry));
+	if (!task)
+		goto out;
+
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	if (!mm)
+		goto out;
+
+	rc = dname_to_vma_addr(dentry, &vm_start, &vm_end);
+	if (rc)
+		goto out_mmput;
+
+	rc = -ENOENT;
+	down_read(&mm->mmap_sem);
+	vma = find_exact_vma(mm, vm_start, vm_end);
+	if (vma && vma->vm_file) {
+		*path = vma_pr_or_file(vma)->f_path;
+		path_get(path);
+		rc = 0;
+	}
+	up_read(&mm->mmap_sem);
+
+out_mmput:
+	mmput(mm);
+out:
+	return rc;
+}
+
+struct map_files_info {
+	fmode_t		mode;
+	unsigned long	len;
+	unsigned char	name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
+};
+
+static int
+proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
+			   struct task_struct *task, const void *ptr)
+{
+	fmode_t mode = (fmode_t)(unsigned long)ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		return -ENOENT;
+
+	ei = PROC_I(inode);
+	ei->op.proc_get_link = proc_map_files_get_link;
+
+	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_size = 64;
+	inode->i_mode = S_IFLNK;
+
+	if (mode & FMODE_READ)
+		inode->i_mode |= S_IRUSR;
+	if (mode & FMODE_WRITE)
+		inode->i_mode |= S_IWUSR;
+
+	d_set_d_op(dentry, &tid_map_files_dentry_operations);
+	d_add(dentry, inode);
+
+	return 0;
+}
+
+static struct dentry *proc_map_files_lookup(struct inode *dir,
+		struct dentry *dentry, unsigned int flags)
+{
+	unsigned long vm_start, vm_end;
+	struct vm_area_struct *vma;
+	struct task_struct *task;
+	int result;
+	struct mm_struct *mm;
+
+	result = -EPERM;
+	if (!capable(CAP_SYS_ADMIN))
+		goto out;
+
+	result = -ENOENT;
+	task = get_proc_task(dir);
+	if (!task)
+		goto out;
+
+	result = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out_put_task;
+
+	result = -ENOENT;
+	if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
+		goto out_put_task;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_put_task;
+
+	down_read(&mm->mmap_sem);
+	vma = find_exact_vma(mm, vm_start, vm_end);
+	if (!vma)
+		goto out_no_vma;
+
+	if (vma->vm_file)
+		result = proc_map_files_instantiate(dir, dentry, task,
+				(void *)(unsigned long)vma->vm_file->f_mode);
+
+out_no_vma:
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+out_put_task:
+	put_task_struct(task);
+out:
+	return ERR_PTR(result);
+}
+
+static const struct inode_operations proc_map_files_inode_operations = {
+	.lookup		= proc_map_files_lookup,
+	.permission	= proc_fd_permission,
+	.setattr	= proc_setattr,
+};
+
+static int
+proc_map_files_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct vm_area_struct *vma;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	unsigned long nr_files, pos, i;
+	struct flex_array *fa = NULL;
+	struct map_files_info info;
+	struct map_files_info *p;
+	int ret;
+
+	ret = -EPERM;
+	if (!capable(CAP_SYS_ADMIN))
+		goto out;
+
+	ret = -ENOENT;
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		goto out;
+
+	ret = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out_put_task;
+
+	ret = 0;
+	if (!dir_emit_dots(file, ctx))
+		goto out_put_task;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_put_task;
+	down_read(&mm->mmap_sem);
+
+	nr_files = 0;
+
+	/*
+	 * We need two passes here:
+	 *
+	 *  1) Collect vmas of mapped files with mmap_sem taken
+	 *  2) Release mmap_sem and instantiate entries
+	 *
+	 * otherwise we get lockdep complained, since filldir()
+	 * routine might require mmap_sem taken in might_fault().
+	 */
+
+	for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
+		if (vma->vm_file && ++pos > ctx->pos)
+			nr_files++;
+	}
+
+	if (nr_files) {
+		fa = flex_array_alloc(sizeof(info), nr_files,
+					GFP_KERNEL);
+		if (!fa || flex_array_prealloc(fa, 0, nr_files,
+						GFP_KERNEL)) {
+			ret = -ENOMEM;
+			if (fa)
+				flex_array_free(fa);
+			up_read(&mm->mmap_sem);
+			mmput(mm);
+			goto out_put_task;
+		}
+		for (i = 0, vma = mm->mmap, pos = 2; vma;
+				vma = vma->vm_next) {
+			if (!vma->vm_file)
+				continue;
+			if (++pos <= ctx->pos)
+				continue;
+
+			info.mode = vma->vm_file->f_mode;
+			info.len = snprintf(info.name,
+					sizeof(info.name), "%lx-%lx",
+					vma->vm_start, vma->vm_end);
+			if (flex_array_put(fa, i++, &info, GFP_KERNEL))
+				BUG();
+		}
+	}
+	up_read(&mm->mmap_sem);
+
+	for (i = 0; i < nr_files; i++) {
+		p = flex_array_get(fa, i);
+		if (!proc_fill_cache(file, ctx,
+				      p->name, p->len,
+				      proc_map_files_instantiate,
+				      task,
+				      (void *)(unsigned long)p->mode))
+			break;
+		ctx->pos++;
+	}
+	if (fa)
+		flex_array_free(fa);
+	mmput(mm);
+
+out_put_task:
+	put_task_struct(task);
+out:
+	return ret;
+}
+
+static const struct file_operations proc_map_files_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_map_files_readdir,
+	.llseek		= default_llseek,
+};
+
+struct timers_private {
+	struct pid *pid;
+	struct task_struct *task;
+	struct sighand_struct *sighand;
+	struct pid_namespace *ns;
+	unsigned long flags;
+};
+
+static void *timers_start(struct seq_file *m, loff_t *pos)
+{
+	struct timers_private *tp = m->private;
+
+	tp->task = get_pid_task(tp->pid, PIDTYPE_PID);
+	if (!tp->task)
+		return ERR_PTR(-ESRCH);
+
+	tp->sighand = lock_task_sighand(tp->task, &tp->flags);
+	if (!tp->sighand)
+		return ERR_PTR(-ESRCH);
+
+	return seq_list_start(&tp->task->signal->posix_timers, *pos);
+}
+
+static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct timers_private *tp = m->private;
+	return seq_list_next(v, &tp->task->signal->posix_timers, pos);
+}
+
+static void timers_stop(struct seq_file *m, void *v)
+{
+	struct timers_private *tp = m->private;
+
+	if (tp->sighand) {
+		unlock_task_sighand(tp->task, &tp->flags);
+		tp->sighand = NULL;
+	}
+
+	if (tp->task) {
+		put_task_struct(tp->task);
+		tp->task = NULL;
+	}
+}
+
+static int show_timer(struct seq_file *m, void *v)
+{
+	struct k_itimer *timer;
+	struct timers_private *tp = m->private;
+	int notify;
+	static const char * const nstr[] = {
+		[SIGEV_SIGNAL] = "signal",
+		[SIGEV_NONE] = "none",
+		[SIGEV_THREAD] = "thread",
+	};
+
+	timer = list_entry((struct list_head *)v, struct k_itimer, list);
+	notify = timer->it_sigev_notify;
+
+	seq_printf(m, "ID: %d\n", timer->it_id);
+	seq_printf(m, "signal: %d/%p\n",
+		   timer->sigq->info.si_signo,
+		   timer->sigq->info.si_value.sival_ptr);
+	seq_printf(m, "notify: %s/%s.%d\n",
+		   nstr[notify & ~SIGEV_THREAD_ID],
+		   (notify & SIGEV_THREAD_ID) ? "tid" : "pid",
+		   pid_nr_ns(timer->it_pid, tp->ns));
+	seq_printf(m, "ClockID: %d\n", timer->it_clock);
+
+	return 0;
+}
+
+static const struct seq_operations proc_timers_seq_ops = {
+	.start	= timers_start,
+	.next	= timers_next,
+	.stop	= timers_stop,
+	.show	= show_timer,
+};
+
+static int proc_timers_open(struct inode *inode, struct file *file)
+{
+	struct timers_private *tp;
+
+	tp = __seq_open_private(file, &proc_timers_seq_ops,
+			sizeof(struct timers_private));
+	if (!tp)
+		return -ENOMEM;
+
+	tp->pid = proc_pid(inode);
+	tp->ns = inode->i_sb->s_fs_info;
+	return 0;
+}
+
+static const struct file_operations proc_timers_operations = {
+	.open		= proc_timers_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
+static int proc_pident_instantiate(struct inode *dir,
+	struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+	const struct pid_entry *p = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	inode->i_mode = p->mode;
+	if (S_ISDIR(inode->i_mode))
+		set_nlink(inode, 2);	/* Use getattr to fix if necessary */
+	if (p->iop)
+		inode->i_op = p->iop;
+	if (p->fop)
+		inode->i_fop = p->fop;
+	ei->op = p->op;
+	d_set_d_op(dentry, &pid_dentry_operations);
+	d_add(dentry, inode);
+	/* Close the race of the process dying before we return the dentry */
+	if (pid_revalidate(dentry, 0))
+		return 0;
+out:
+	return -ENOENT;
+}
+
+static struct dentry *proc_pident_lookup(struct inode *dir, 
+					 struct dentry *dentry,
+					 const struct pid_entry *ents,
+					 unsigned int nents)
+{
+	int error;
+	struct task_struct *task = get_proc_task(dir);
+	const struct pid_entry *p, *last;
+
+	error = -ENOENT;
+
+	if (!task)
+		goto out_no_task;
+
+	/*
+	 * Yes, it does not scale. And it should not. Don't add
+	 * new entries into /proc/<tgid>/ without very good reasons.
+	 */
+	last = &ents[nents - 1];
+	for (p = ents; p <= last; p++) {
+		if (p->len != dentry->d_name.len)
+			continue;
+		if (!memcmp(dentry->d_name.name, p->name, p->len))
+			break;
+	}
+	if (p > last)
+		goto out;
+
+	error = proc_pident_instantiate(dir, dentry, task, p);
+out:
+	put_task_struct(task);
+out_no_task:
+	return ERR_PTR(error);
+}
+
+static int proc_pident_readdir(struct file *file, struct dir_context *ctx,
+		const struct pid_entry *ents, unsigned int nents)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct pid_entry *p;
+
+	if (!task)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+
+	if (ctx->pos >= nents + 2)
+		goto out;
+
+	for (p = ents + (ctx->pos - 2); p <= ents + nents - 1; p++) {
+		if (!proc_fill_cache(file, ctx, p->name, p->len,
+				proc_pident_instantiate, task, p))
+			break;
+		ctx->pos++;
+	}
+out:
+	put_task_struct(task);
+	return 0;
+}
+
+#ifdef CONFIG_SECURITY
+static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
+				  size_t count, loff_t *ppos)
+{
+	struct inode * inode = file_inode(file);
+	char *p = NULL;
+	ssize_t length;
+	struct task_struct *task = get_proc_task(inode);
+
+	if (!task)
+		return -ESRCH;
+
+	length = security_getprocattr(task,
+				      (char*)file->f_path.dentry->d_name.name,
+				      &p);
+	put_task_struct(task);
+	if (length > 0)
+		length = simple_read_from_buffer(buf, count, ppos, p, length);
+	kfree(p);
+	return length;
+}
+
+static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
+				   size_t count, loff_t *ppos)
+{
+	struct inode * inode = file_inode(file);
+	char *page;
+	ssize_t length;
+	struct task_struct *task = get_proc_task(inode);
+
+	length = -ESRCH;
+	if (!task)
+		goto out_no_task;
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	/* No partial writes. */
+	length = -EINVAL;
+	if (*ppos != 0)
+		goto out;
+
+	length = -ENOMEM;
+	page = (char*)__get_free_page(GFP_TEMPORARY);
+	if (!page)
+		goto out;
+
+	length = -EFAULT;
+	if (copy_from_user(page, buf, count))
+		goto out_free;
+
+	/* Guard against adverse ptrace interaction */
+	length = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+	if (length < 0)
+		goto out_free;
+
+	length = security_setprocattr(task,
+				      (char*)file->f_path.dentry->d_name.name,
+				      (void*)page, count);
+	mutex_unlock(&task->signal->cred_guard_mutex);
+out_free:
+	free_page((unsigned long) page);
+out:
+	put_task_struct(task);
+out_no_task:
+	return length;
+}
+
+static const struct file_operations proc_pid_attr_operations = {
+	.read		= proc_pid_attr_read,
+	.write		= proc_pid_attr_write,
+	.llseek		= generic_file_llseek,
+};
+
+static const struct pid_entry attr_dir_stuff[] = {
+	REG("current",    S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+	REG("prev",       S_IRUGO,	   proc_pid_attr_operations),
+	REG("exec",       S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+	REG("fscreate",   S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+	REG("keycreate",  S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+	REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+};
+
+static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	return proc_pident_readdir(file, ctx, 
+				   attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
+}
+
+static const struct file_operations proc_attr_dir_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_attr_dir_readdir,
+	.llseek		= default_llseek,
+};
+
+static struct dentry *proc_attr_dir_lookup(struct inode *dir,
+				struct dentry *dentry, unsigned int flags)
+{
+	return proc_pident_lookup(dir, dentry,
+				  attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
+}
+
+static const struct inode_operations proc_attr_dir_inode_operations = {
+	.lookup		= proc_attr_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_setattr,
+};
+
+#endif
+
+#ifdef CONFIG_ELF_CORE
+static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf,
+					 size_t count, loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	struct mm_struct *mm;
+	char buffer[PROC_NUMBUF];
+	size_t len;
+	int ret;
+
+	if (!task)
+		return -ESRCH;
+
+	ret = 0;
+	mm = get_task_mm(task);
+	if (mm) {
+		len = snprintf(buffer, sizeof(buffer), "%08lx\n",
+			       ((mm->flags & MMF_DUMP_FILTER_MASK) >>
+				MMF_DUMP_FILTER_SHIFT));
+		mmput(mm);
+		ret = simple_read_from_buffer(buf, count, ppos, buffer, len);
+	}
+
+	put_task_struct(task);
+
+	return ret;
+}
+
+static ssize_t proc_coredump_filter_write(struct file *file,
+					  const char __user *buf,
+					  size_t count,
+					  loff_t *ppos)
+{
+	struct task_struct *task;
+	struct mm_struct *mm;
+	char buffer[PROC_NUMBUF], *end;
+	unsigned int val;
+	int ret;
+	int i;
+	unsigned long mask;
+
+	ret = -EFAULT;
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		goto out_no_task;
+
+	ret = -EINVAL;
+	val = (unsigned int)simple_strtoul(buffer, &end, 0);
+	if (*end == '\n')
+		end++;
+	if (end - buffer == 0)
+		goto out_no_task;
+
+	ret = -ESRCH;
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		goto out_no_task;
+
+	ret = end - buffer;
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_no_mm;
+
+	for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
+		if (val & mask)
+			set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
+		else
+			clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
+	}
+
+	mmput(mm);
+ out_no_mm:
+	put_task_struct(task);
+ out_no_task:
+	return ret;
+}
+
+static const struct file_operations proc_coredump_filter_operations = {
+	.read		= proc_coredump_filter_read,
+	.write		= proc_coredump_filter_write,
+	.llseek		= generic_file_llseek,
+};
+#endif
+
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole)
+{
+	struct task_io_accounting acct = task->ioac;
+	unsigned long flags;
+	int result;
+
+	result = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	if (result)
+		return result;
+
+	if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+		result = -EACCES;
+		goto out_unlock;
+	}
+
+	if (whole && lock_task_sighand(task, &flags)) {
+		struct task_struct *t = task;
+
+		task_io_accounting_add(&acct, &task->signal->ioac);
+		while_each_thread(task, t)
+			task_io_accounting_add(&acct, &t->ioac);
+
+		unlock_task_sighand(task, &flags);
+	}
+	seq_printf(m,
+		   "rchar: %llu\n"
+		   "wchar: %llu\n"
+		   "syscr: %llu\n"
+		   "syscw: %llu\n"
+		   "read_bytes: %llu\n"
+		   "write_bytes: %llu\n"
+		   "cancelled_write_bytes: %llu\n",
+		   (unsigned long long)acct.rchar,
+		   (unsigned long long)acct.wchar,
+		   (unsigned long long)acct.syscr,
+		   (unsigned long long)acct.syscw,
+		   (unsigned long long)acct.read_bytes,
+		   (unsigned long long)acct.write_bytes,
+		   (unsigned long long)acct.cancelled_write_bytes);
+	result = 0;
+
+out_unlock:
+	mutex_unlock(&task->signal->cred_guard_mutex);
+	return result;
+}
+
+static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns,
+				  struct pid *pid, struct task_struct *task)
+{
+	return do_io_accounting(task, m, 0);
+}
+
+static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns,
+				   struct pid *pid, struct task_struct *task)
+{
+	return do_io_accounting(task, m, 1);
+}
+#endif /* CONFIG_TASK_IO_ACCOUNTING */
+
+#ifdef CONFIG_USER_NS
+static int proc_id_map_open(struct inode *inode, struct file *file,
+	const struct seq_operations *seq_ops)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	struct seq_file *seq;
+	int ret = -EINVAL;
+
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	ret = seq_open(file, seq_ops);
+	if (ret)
+		goto err_put_ns;
+
+	seq = file->private_data;
+	seq->private = ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_id_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	put_user_ns(ns);
+	return seq_release(inode, file);
+}
+
+static int proc_uid_map_open(struct inode *inode, struct file *file)
+{
+	return proc_id_map_open(inode, file, &proc_uid_seq_operations);
+}
+
+static int proc_gid_map_open(struct inode *inode, struct file *file)
+{
+	return proc_id_map_open(inode, file, &proc_gid_seq_operations);
+}
+
+static int proc_projid_map_open(struct inode *inode, struct file *file)
+{
+	return proc_id_map_open(inode, file, &proc_projid_seq_operations);
+}
+
+static const struct file_operations proc_uid_map_operations = {
+	.open		= proc_uid_map_open,
+	.write		= proc_uid_map_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_id_map_release,
+};
+
+static const struct file_operations proc_gid_map_operations = {
+	.open		= proc_gid_map_open,
+	.write		= proc_gid_map_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_id_map_release,
+};
+
+static const struct file_operations proc_projid_map_operations = {
+	.open		= proc_projid_map_open,
+	.write		= proc_projid_map_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_id_map_release,
+};
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	int ret;
+
+	ret = -ESRCH;
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	if (file->f_mode & FMODE_WRITE) {
+		ret = -EACCES;
+		if (!ns_capable(ns, CAP_SYS_ADMIN))
+			goto err_put_ns;
+	}
+
+	ret = single_open(file, &proc_setgroups_show, ns);
+	if (ret)
+		goto err_put_ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	int ret = single_release(inode, file);
+	put_user_ns(ns);
+	return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+	.open		= proc_setgroups_open,
+	.write		= proc_setgroups_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_setgroups_release,
+};
+#endif /* CONFIG_USER_NS */
+
+static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	int err = lock_trace(task);
+	if (!err) {
+		seq_printf(m, "%08x\n", task->personality);
+		unlock_trace(task);
+	}
+	return err;
+}
+
+/*
+ * Thread groups
+ */
+static const struct file_operations proc_task_operations;
+static const struct inode_operations proc_task_inode_operations;
+
+static const struct pid_entry tgid_base_stuff[] = {
+	DIR("task",       S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
+	DIR("fd",         S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	DIR("map_files",  S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
+#endif
+	DIR("fdinfo",     S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+	DIR("ns",	  S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
+#ifdef CONFIG_NET
+	DIR("net",        S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
+#endif
+	REG("environ",    S_IRUSR, proc_environ_operations),
+	ONE("auxv",       S_IRUSR, proc_pid_auxv),
+	ONE("status",     S_IRUGO, proc_pid_status),
+	ONE("personality", S_IRUSR, proc_pid_personality),
+	ONE("limits",	  S_IRUGO, proc_pid_limits),
+#ifdef CONFIG_SCHED_DEBUG
+	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
+#endif
+#ifdef CONFIG_SCHED_AUTOGROUP
+	REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
+#endif
+	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+	ONE("syscall",    S_IRUSR, proc_pid_syscall),
+#endif
+	ONE("cmdline",    S_IRUGO, proc_pid_cmdline),
+	ONE("stat",       S_IRUGO, proc_tgid_stat),
+	ONE("statm",      S_IRUGO, proc_pid_statm),
+	REG("maps",       S_IRUGO, proc_pid_maps_operations),
+#ifdef CONFIG_NUMA
+	REG("numa_maps",  S_IRUGO, proc_pid_numa_maps_operations),
+#endif
+	REG("mem",        S_IRUSR|S_IWUSR, proc_mem_operations),
+	LNK("cwd",        proc_cwd_link),
+	LNK("root",       proc_root_link),
+	LNK("exe",        proc_exe_link),
+	REG("mounts",     S_IRUGO, proc_mounts_operations),
+	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
+	REG("mountstats", S_IRUSR, proc_mountstats_operations),
+#ifdef CONFIG_PROC_PAGE_MONITOR
+	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
+	REG("smaps",      S_IRUGO, proc_pid_smaps_operations),
+	REG("pagemap",    S_IRUSR, proc_pagemap_operations),
+#endif
+#ifdef CONFIG_SECURITY
+	DIR("attr",       S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
+#endif
+#ifdef CONFIG_KALLSYMS
+	ONE("wchan",      S_IRUGO, proc_pid_wchan),
+#endif
+#ifdef CONFIG_STACKTRACE
+	ONE("stack",      S_IRUSR, proc_pid_stack),
+#endif
+#ifdef CONFIG_SCHEDSTATS
+	ONE("schedstat",  S_IRUGO, proc_pid_schedstat),
+#endif
+#ifdef CONFIG_LATENCYTOP
+	REG("latency",  S_IRUGO, proc_lstats_operations),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
+	ONE("cpuset",     S_IRUGO, proc_cpuset_show),
+#endif
+#ifdef CONFIG_CGROUPS
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
+#endif
+	ONE("oom_score",  S_IRUGO, proc_oom_score),
+	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
+	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+#ifdef CONFIG_AUDITSYSCALL
+	REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
+	REG("sessionid",  S_IRUGO, proc_sessionid_operations),
+#endif
+#ifdef CONFIG_FAULT_INJECTION
+	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+#endif
+#ifdef CONFIG_ELF_CORE
+	REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations),
+#endif
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+	ONE("io",	S_IRUSR, proc_tgid_io_accounting),
+#endif
+#ifdef CONFIG_HARDWALL
+	ONE("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
+#ifdef CONFIG_USER_NS
+	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
+	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
+	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
+#endif
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REG("timers",	  S_IRUGO, proc_timers_operations),
+#endif
+};
+
+static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
+{
+	return proc_pident_readdir(file, ctx,
+				   tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
+}
+
+static const struct file_operations proc_tgid_base_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_tgid_base_readdir,
+	.llseek		= default_llseek,
+};
+
+static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return proc_pident_lookup(dir, dentry,
+				  tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
+}
+
+static const struct inode_operations proc_tgid_base_inode_operations = {
+	.lookup		= proc_tgid_base_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_setattr,
+	.permission	= proc_pid_permission,
+};
+
+static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
+{
+	struct dentry *dentry, *leader, *dir;
+	char buf[PROC_NUMBUF];
+	struct qstr name;
+
+	name.name = buf;
+	name.len = snprintf(buf, sizeof(buf), "%d", pid);
+	/* no ->d_hash() rejects on procfs */
+	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
+	if (dentry) {
+		d_invalidate(dentry);
+		dput(dentry);
+	}
+
+	if (pid == tgid)
+		return;
+
+	name.name = buf;
+	name.len = snprintf(buf, sizeof(buf), "%d", tgid);
+	leader = d_hash_and_lookup(mnt->mnt_root, &name);
+	if (!leader)
+		goto out;
+
+	name.name = "task";
+	name.len = strlen(name.name);
+	dir = d_hash_and_lookup(leader, &name);
+	if (!dir)
+		goto out_put_leader;
+
+	name.name = buf;
+	name.len = snprintf(buf, sizeof(buf), "%d", pid);
+	dentry = d_hash_and_lookup(dir, &name);
+	if (dentry) {
+		d_invalidate(dentry);
+		dput(dentry);
+	}
+
+	dput(dir);
+out_put_leader:
+	dput(leader);
+out:
+	return;
+}
+
+/**
+ * proc_flush_task -  Remove dcache entries for @task from the /proc dcache.
+ * @task: task that should be flushed.
+ *
+ * When flushing dentries from proc, one needs to flush them from global
+ * proc (proc_mnt) and from all the namespaces' procs this task was seen
+ * in. This call is supposed to do all of this job.
+ *
+ * Looks in the dcache for
+ * /proc/@pid
+ * /proc/@tgid/task/@pid
+ * if either directory is present flushes it and all of it'ts children
+ * from the dcache.
+ *
+ * It is safe and reasonable to cache /proc entries for a task until
+ * that task exits.  After that they just clog up the dcache with
+ * useless entries, possibly causing useful dcache entries to be
+ * flushed instead.  This routine is proved to flush those useless
+ * dcache entries at process exit time.
+ *
+ * NOTE: This routine is just an optimization so it does not guarantee
+ *       that no dcache entries will exist at process exit time it
+ *       just makes it very unlikely that any will persist.
+ */
+
+void proc_flush_task(struct task_struct *task)
+{
+	int i;
+	struct pid *pid, *tgid;
+	struct upid *upid;
+
+	pid = task_pid(task);
+	tgid = task_tgid(task);
+
+	for (i = 0; i <= pid->level; i++) {
+		upid = &pid->numbers[i];
+		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
+					tgid->numbers[i].nr);
+	}
+}
+
+static int proc_pid_instantiate(struct inode *dir,
+				   struct dentry * dentry,
+				   struct task_struct *task, const void *ptr)
+{
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
+	inode->i_op = &proc_tgid_base_inode_operations;
+	inode->i_fop = &proc_tgid_base_operations;
+	inode->i_flags|=S_IMMUTABLE;
+
+	set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff,
+						  ARRAY_SIZE(tgid_base_stuff)));
+
+	d_set_d_op(dentry, &pid_dentry_operations);
+
+	d_add(dentry, inode);
+	/* Close the race of the process dying before we return the dentry */
+	if (pid_revalidate(dentry, 0))
+		return 0;
+out:
+	return -ENOENT;
+}
+
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
+{
+	int result = -ENOENT;
+	struct task_struct *task;
+	unsigned tgid;
+	struct pid_namespace *ns;
+
+	tgid = name_to_int(&dentry->d_name);
+	if (tgid == ~0U)
+		goto out;
+
+	ns = dentry->d_sb->s_fs_info;
+	rcu_read_lock();
+	task = find_task_by_pid_ns(tgid, ns);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+	if (!task)
+		goto out;
+
+	result = proc_pid_instantiate(dir, dentry, task, NULL);
+	put_task_struct(task);
+out:
+	return ERR_PTR(result);
+}
+
+/*
+ * Find the first task with tgid >= tgid
+ *
+ */
+struct tgid_iter {
+	unsigned int tgid;
+	struct task_struct *task;
+};
+static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter)
+{
+	struct pid *pid;
+
+	if (iter.task)
+		put_task_struct(iter.task);
+	rcu_read_lock();
+retry:
+	iter.task = NULL;
+	pid = find_ge_pid(iter.tgid, ns);
+	if (pid) {
+		iter.tgid = pid_nr_ns(pid, ns);
+		iter.task = pid_task(pid, PIDTYPE_PID);
+		/* What we to know is if the pid we have find is the
+		 * pid of a thread_group_leader.  Testing for task
+		 * being a thread_group_leader is the obvious thing
+		 * todo but there is a window when it fails, due to
+		 * the pid transfer logic in de_thread.
+		 *
+		 * So we perform the straight forward test of seeing
+		 * if the pid we have found is the pid of a thread
+		 * group leader, and don't worry if the task we have
+		 * found doesn't happen to be a thread group leader.
+		 * As we don't care in the case of readdir.
+		 */
+		if (!iter.task || !has_group_leader_pid(iter.task)) {
+			iter.tgid += 1;
+			goto retry;
+		}
+		get_task_struct(iter.task);
+	}
+	rcu_read_unlock();
+	return iter;
+}
+
+#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2)
+
+/* for the /proc/ directory itself, after non-process stuff has been done */
+int proc_pid_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct tgid_iter iter;
+	struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info;
+	loff_t pos = ctx->pos;
+
+	if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
+		return 0;
+
+	if (pos == TGID_OFFSET - 2) {
+		struct inode *inode = d_inode(ns->proc_self);
+		if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
+			return 0;
+		ctx->pos = pos = pos + 1;
+	}
+	if (pos == TGID_OFFSET - 1) {
+		struct inode *inode = d_inode(ns->proc_thread_self);
+		if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK))
+			return 0;
+		ctx->pos = pos = pos + 1;
+	}
+	iter.tgid = pos - TGID_OFFSET;
+	iter.task = NULL;
+	for (iter = next_tgid(ns, iter);
+	     iter.task;
+	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
+		char name[PROC_NUMBUF];
+		int len;
+		if (!has_pid_permissions(ns, iter.task, 2))
+			continue;
+
+		len = snprintf(name, sizeof(name), "%d", iter.tgid);
+		ctx->pos = iter.tgid + TGID_OFFSET;
+		if (!proc_fill_cache(file, ctx, name, len,
+				     proc_pid_instantiate, iter.task, NULL)) {
+			put_task_struct(iter.task);
+			return 0;
+		}
+	}
+	ctx->pos = PID_MAX_LIMIT + TGID_OFFSET;
+	return 0;
+}
+
+/*
+ * Tasks
+ */
+static const struct pid_entry tid_base_stuff[] = {
+	DIR("fd",        S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
+	DIR("fdinfo",    S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+	DIR("ns",	 S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
+#ifdef CONFIG_NET
+	DIR("net",        S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
+#endif
+	REG("environ",   S_IRUSR, proc_environ_operations),
+	ONE("auxv",      S_IRUSR, proc_pid_auxv),
+	ONE("status",    S_IRUGO, proc_pid_status),
+	ONE("personality", S_IRUSR, proc_pid_personality),
+	ONE("limits",	 S_IRUGO, proc_pid_limits),
+#ifdef CONFIG_SCHED_DEBUG
+	REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
+#endif
+	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+	ONE("syscall",   S_IRUSR, proc_pid_syscall),
+#endif
+	ONE("cmdline",   S_IRUGO, proc_pid_cmdline),
+	ONE("stat",      S_IRUGO, proc_tid_stat),
+	ONE("statm",     S_IRUGO, proc_pid_statm),
+	REG("maps",      S_IRUGO, proc_tid_maps_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REG("children",  S_IRUGO, proc_tid_children_operations),
+#endif
+#ifdef CONFIG_NUMA
+	REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
+#endif
+	REG("mem",       S_IRUSR|S_IWUSR, proc_mem_operations),
+	LNK("cwd",       proc_cwd_link),
+	LNK("root",      proc_root_link),
+	LNK("exe",       proc_exe_link),
+	REG("mounts",    S_IRUGO, proc_mounts_operations),
+	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
+#ifdef CONFIG_PROC_PAGE_MONITOR
+	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
+	REG("smaps",     S_IRUGO, proc_tid_smaps_operations),
+	REG("pagemap",    S_IRUSR, proc_pagemap_operations),
+#endif
+#ifdef CONFIG_SECURITY
+	DIR("attr",      S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
+#endif
+#ifdef CONFIG_KALLSYMS
+	ONE("wchan",     S_IRUGO, proc_pid_wchan),
+#endif
+#ifdef CONFIG_STACKTRACE
+	ONE("stack",      S_IRUSR, proc_pid_stack),
+#endif
+#ifdef CONFIG_SCHEDSTATS
+	ONE("schedstat", S_IRUGO, proc_pid_schedstat),
+#endif
+#ifdef CONFIG_LATENCYTOP
+	REG("latency",  S_IRUGO, proc_lstats_operations),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
+	ONE("cpuset",    S_IRUGO, proc_cpuset_show),
+#endif
+#ifdef CONFIG_CGROUPS
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
+#endif
+	ONE("oom_score", S_IRUGO, proc_oom_score),
+	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
+	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+#ifdef CONFIG_AUDITSYSCALL
+	REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
+	REG("sessionid",  S_IRUGO, proc_sessionid_operations),
+#endif
+#ifdef CONFIG_FAULT_INJECTION
+	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+#endif
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+	ONE("io",	S_IRUSR, proc_tid_io_accounting),
+#endif
+#ifdef CONFIG_HARDWALL
+	ONE("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
+#ifdef CONFIG_USER_NS
+	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
+	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
+	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
+#endif
+};
+
+static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
+{
+	return proc_pident_readdir(file, ctx,
+				   tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
+}
+
+static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return proc_pident_lookup(dir, dentry,
+				  tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
+}
+
+static const struct file_operations proc_tid_base_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_tid_base_readdir,
+	.llseek		= default_llseek,
+};
+
+static const struct inode_operations proc_tid_base_inode_operations = {
+	.lookup		= proc_tid_base_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_setattr,
+};
+
+static int proc_task_instantiate(struct inode *dir,
+	struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+	struct inode *inode;
+	inode = proc_pid_make_inode(dir->i_sb, task);
+
+	if (!inode)
+		goto out;
+	inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
+	inode->i_op = &proc_tid_base_inode_operations;
+	inode->i_fop = &proc_tid_base_operations;
+	inode->i_flags|=S_IMMUTABLE;
+
+	set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff,
+						  ARRAY_SIZE(tid_base_stuff)));
+
+	d_set_d_op(dentry, &pid_dentry_operations);
+
+	d_add(dentry, inode);
+	/* Close the race of the process dying before we return the dentry */
+	if (pid_revalidate(dentry, 0))
+		return 0;
+out:
+	return -ENOENT;
+}
+
+static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
+{
+	int result = -ENOENT;
+	struct task_struct *task;
+	struct task_struct *leader = get_proc_task(dir);
+	unsigned tid;
+	struct pid_namespace *ns;
+
+	if (!leader)
+		goto out_no_task;
+
+	tid = name_to_int(&dentry->d_name);
+	if (tid == ~0U)
+		goto out;
+
+	ns = dentry->d_sb->s_fs_info;
+	rcu_read_lock();
+	task = find_task_by_pid_ns(tid, ns);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+	if (!task)
+		goto out;
+	if (!same_thread_group(leader, task))
+		goto out_drop_task;
+
+	result = proc_task_instantiate(dir, dentry, task, NULL);
+out_drop_task:
+	put_task_struct(task);
+out:
+	put_task_struct(leader);
+out_no_task:
+	return ERR_PTR(result);
+}
+
+/*
+ * Find the first tid of a thread group to return to user space.
+ *
+ * Usually this is just the thread group leader, but if the users
+ * buffer was too small or there was a seek into the middle of the
+ * directory we have more work todo.
+ *
+ * In the case of a short read we start with find_task_by_pid.
+ *
+ * In the case of a seek we start with the leader and walk nr
+ * threads past it.
+ */
+static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos,
+					struct pid_namespace *ns)
+{
+	struct task_struct *pos, *task;
+	unsigned long nr = f_pos;
+
+	if (nr != f_pos)	/* 32bit overflow? */
+		return NULL;
+
+	rcu_read_lock();
+	task = pid_task(pid, PIDTYPE_PID);
+	if (!task)
+		goto fail;
+
+	/* Attempt to start with the tid of a thread */
+	if (tid && nr) {
+		pos = find_task_by_pid_ns(tid, ns);
+		if (pos && same_thread_group(pos, task))
+			goto found;
+	}
+
+	/* If nr exceeds the number of threads there is nothing todo */
+	if (nr >= get_nr_threads(task))
+		goto fail;
+
+	/* If we haven't found our starting place yet start
+	 * with the leader and walk nr threads forward.
+	 */
+	pos = task = task->group_leader;
+	do {
+		if (!nr--)
+			goto found;
+	} while_each_thread(task, pos);
+fail:
+	pos = NULL;
+	goto out;
+found:
+	get_task_struct(pos);
+out:
+	rcu_read_unlock();
+	return pos;
+}
+
+/*
+ * Find the next thread in the thread list.
+ * Return NULL if there is an error or no next thread.
+ *
+ * The reference to the input task_struct is released.
+ */
+static struct task_struct *next_tid(struct task_struct *start)
+{
+	struct task_struct *pos = NULL;
+	rcu_read_lock();
+	if (pid_alive(start)) {
+		pos = next_thread(start);
+		if (thread_group_leader(pos))
+			pos = NULL;
+		else
+			get_task_struct(pos);
+	}
+	rcu_read_unlock();
+	put_task_struct(start);
+	return pos;
+}
+
+/* for the /proc/TGID/task/ directories */
+static int proc_task_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *task;
+	struct pid_namespace *ns;
+	int tid;
+
+	if (proc_inode_is_dead(inode))
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	/* f_version caches the tgid value that the last readdir call couldn't
+	 * return. lseek aka telldir automagically resets f_version to 0.
+	 */
+	ns = inode->i_sb->s_fs_info;
+	tid = (int)file->f_version;
+	file->f_version = 0;
+	for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
+	     task;
+	     task = next_tid(task), ctx->pos++) {
+		char name[PROC_NUMBUF];
+		int len;
+		tid = task_pid_nr_ns(task, ns);
+		len = snprintf(name, sizeof(name), "%d", tid);
+		if (!proc_fill_cache(file, ctx, name, len,
+				proc_task_instantiate, task, NULL)) {
+			/* returning this tgid failed, save it as the first
+			 * pid for the next readir call */
+			file->f_version = (u64)tid;
+			put_task_struct(task);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	struct task_struct *p = get_proc_task(inode);
+	generic_fillattr(inode, stat);
+
+	if (p) {
+		stat->nlink += get_nr_threads(p);
+		put_task_struct(p);
+	}
+
+	return 0;
+}
+
+static const struct inode_operations proc_task_inode_operations = {
+	.lookup		= proc_task_lookup,
+	.getattr	= proc_task_getattr,
+	.setattr	= proc_setattr,
+	.permission	= proc_pid_permission,
+};
+
+static const struct file_operations proc_task_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_task_readdir,
+	.llseek		= default_llseek,
+};
diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c
new file mode 100644
index 000000000..cbd82dff7
--- /dev/null
+++ b/fs/proc/cmdline.c
@@ -0,0 +1,29 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+static int cmdline_proc_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "%s\n", saved_command_line);
+	return 0;
+}
+
+static int cmdline_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, cmdline_proc_show, NULL);
+}
+
+static const struct file_operations cmdline_proc_fops = {
+	.open		= cmdline_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_cmdline_init(void)
+{
+	proc_create("cmdline", 0, NULL, &cmdline_proc_fops);
+	return 0;
+}
+fs_initcall(proc_cmdline_init);
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
new file mode 100644
index 000000000..290ba85cb
--- /dev/null
+++ b/fs/proc/consoles.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright (c) 2010 Werner Fink, Jiri Slaby
+ *
+ * Licensed under GPLv2
+ */
+
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/tty_driver.h>
+
+/*
+ * This is handler for /proc/consoles
+ */
+static int show_console_dev(struct seq_file *m, void *v)
+{
+	static const struct {
+		short flag;
+		char name;
+	} con_flags[] = {
+		{ CON_ENABLED,		'E' },
+		{ CON_CONSDEV,		'C' },
+		{ CON_BOOT,		'B' },
+		{ CON_PRINTBUFFER,	'p' },
+		{ CON_BRL,		'b' },
+		{ CON_ANYTIME,		'a' },
+	};
+	char flags[ARRAY_SIZE(con_flags) + 1];
+	struct console *con = v;
+	unsigned int a;
+	dev_t dev = 0;
+
+	if (con->device) {
+		const struct tty_driver *driver;
+		int index;
+		driver = con->device(con, &index);
+		if (driver) {
+			dev = MKDEV(driver->major, driver->minor_start);
+			dev += index;
+		}
+	}
+
+	for (a = 0; a < ARRAY_SIZE(con_flags); a++)
+		flags[a] = (con->flags & con_flags[a].flag) ?
+			con_flags[a].name : ' ';
+	flags[a] = 0;
+
+	seq_setwidth(m, 21 - 1);
+	seq_printf(m, "%s%d", con->name, con->index);
+	seq_pad(m, ' ');
+	seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-',
+			con->write ? 'W' : '-', con->unblank ? 'U' : '-',
+			flags);
+	if (dev)
+		seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev));
+
+	seq_printf(m, "\n");
+
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	struct console *con;
+	loff_t off = 0;
+
+	console_lock();
+	for_each_console(con)
+		if (off++ == *pos)
+			break;
+
+	return con;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct console *con = v;
+	++*pos;
+	return con->next;
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+	console_unlock();
+}
+
+static const struct seq_operations consoles_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_console_dev
+};
+
+static int consoles_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &consoles_op);
+}
+
+static const struct file_operations proc_consoles_operations = {
+	.open		= consoles_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init proc_consoles_init(void)
+{
+	proc_create("consoles", 0, NULL, &proc_consoles_operations);
+	return 0;
+}
+fs_initcall(proc_consoles_init);
diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c
new file mode 100644
index 000000000..06f4d31e0
--- /dev/null
+++ b/fs/proc/cpuinfo.c
@@ -0,0 +1,24 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+extern const struct seq_operations cpuinfo_op;
+static int cpuinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &cpuinfo_op);
+}
+
+static const struct file_operations proc_cpuinfo_operations = {
+	.open		= cpuinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init proc_cpuinfo_init(void)
+{
+	proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
+	return 0;
+}
+fs_initcall(proc_cpuinfo_init);
diff --git a/fs/proc/devices.c b/fs/proc/devices.c
new file mode 100644
index 000000000..50493edc3
--- /dev/null
+++ b/fs/proc/devices.c
@@ -0,0 +1,70 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+static int devinfo_show(struct seq_file *f, void *v)
+{
+	int i = *(loff_t *) v;
+
+	if (i < CHRDEV_MAJOR_HASH_SIZE) {
+		if (i == 0)
+			seq_puts(f, "Character devices:\n");
+		chrdev_show(f, i);
+	}
+#ifdef CONFIG_BLOCK
+	else {
+		i -= CHRDEV_MAJOR_HASH_SIZE;
+		if (i == 0)
+			seq_puts(f, "\nBlock devices:\n");
+		blkdev_show(f, i);
+	}
+#endif
+	return 0;
+}
+
+static void *devinfo_start(struct seq_file *f, loff_t *pos)
+{
+	if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE))
+		return pos;
+	return NULL;
+}
+
+static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	(*pos)++;
+	if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE))
+		return NULL;
+	return pos;
+}
+
+static void devinfo_stop(struct seq_file *f, void *v)
+{
+	/* Nothing to do */
+}
+
+static const struct seq_operations devinfo_ops = {
+	.start = devinfo_start,
+	.next  = devinfo_next,
+	.stop  = devinfo_stop,
+	.show  = devinfo_show
+};
+
+static int devinfo_open(struct inode *inode, struct file *filp)
+{
+	return seq_open(filp, &devinfo_ops);
+}
+
+static const struct file_operations proc_devinfo_operations = {
+	.open		= devinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init proc_devices_init(void)
+{
+	proc_create("devices", 0, NULL, &proc_devinfo_operations);
+	return 0;
+}
+fs_initcall(proc_devices_init);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
new file mode 100644
index 000000000..6e5fcd007
--- /dev/null
+++ b/fs/proc/fd.c
@@ -0,0 +1,357 @@
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/dcache.h>
+#include <linux/path.h>
+#include <linux/fdtable.h>
+#include <linux/namei.h>
+#include <linux/pid.h>
+#include <linux/security.h>
+#include <linux/file.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+
+#include <linux/proc_fs.h>
+
+#include "../mount.h"
+#include "internal.h"
+#include "fd.h"
+
+static int seq_show(struct seq_file *m, void *v)
+{
+	struct files_struct *files = NULL;
+	int f_flags = 0, ret = -ENOENT;
+	struct file *file = NULL;
+	struct task_struct *task;
+
+	task = get_proc_task(m->private);
+	if (!task)
+		return -ENOENT;
+
+	files = get_files_struct(task);
+	put_task_struct(task);
+
+	if (files) {
+		int fd = proc_fd(m->private);
+
+		spin_lock(&files->file_lock);
+		file = fcheck_files(files, fd);
+		if (file) {
+			struct fdtable *fdt = files_fdtable(files);
+
+			f_flags = file->f_flags;
+			if (close_on_exec(fd, fdt))
+				f_flags |= O_CLOEXEC;
+
+			get_file(file);
+			ret = 0;
+		}
+		spin_unlock(&files->file_lock);
+		put_files_struct(files);
+	}
+
+	if (ret)
+		return ret;
+
+	seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n",
+		   (long long)file->f_pos, f_flags,
+		   real_mount(file->f_path.mnt)->mnt_id);
+
+	show_fd_locks(m, file, files);
+	if (seq_has_overflowed(m))
+		goto out;
+
+	if (file->f_op->show_fdinfo)
+		file->f_op->show_fdinfo(m, file);
+
+out:
+	fput(file);
+	return 0;
+}
+
+static int seq_fdinfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, seq_show, inode);
+}
+
+static const struct file_operations proc_fdinfo_file_operations = {
+	.open		= seq_fdinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct files_struct *files;
+	struct task_struct *task;
+	const struct cred *cred;
+	struct inode *inode;
+	int fd;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = d_inode(dentry);
+	task = get_proc_task(inode);
+	fd = proc_fd(inode);
+
+	if (task) {
+		files = get_files_struct(task);
+		if (files) {
+			struct file *file;
+
+			rcu_read_lock();
+			file = fcheck_files(files, fd);
+			if (file) {
+				unsigned f_mode = file->f_mode;
+
+				rcu_read_unlock();
+				put_files_struct(files);
+
+				if (task_dumpable(task)) {
+					rcu_read_lock();
+					cred = __task_cred(task);
+					inode->i_uid = cred->euid;
+					inode->i_gid = cred->egid;
+					rcu_read_unlock();
+				} else {
+					inode->i_uid = GLOBAL_ROOT_UID;
+					inode->i_gid = GLOBAL_ROOT_GID;
+				}
+
+				if (S_ISLNK(inode->i_mode)) {
+					unsigned i_mode = S_IFLNK;
+					if (f_mode & FMODE_READ)
+						i_mode |= S_IRUSR | S_IXUSR;
+					if (f_mode & FMODE_WRITE)
+						i_mode |= S_IWUSR | S_IXUSR;
+					inode->i_mode = i_mode;
+				}
+
+				security_task_to_inode(task, inode);
+				put_task_struct(task);
+				return 1;
+			}
+			rcu_read_unlock();
+			put_files_struct(files);
+		}
+		put_task_struct(task);
+	}
+	return 0;
+}
+
+static const struct dentry_operations tid_fd_dentry_operations = {
+	.d_revalidate	= tid_fd_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+static int proc_fd_link(struct dentry *dentry, struct path *path)
+{
+	struct files_struct *files = NULL;
+	struct task_struct *task;
+	int ret = -ENOENT;
+
+	task = get_proc_task(d_inode(dentry));
+	if (task) {
+		files = get_files_struct(task);
+		put_task_struct(task);
+	}
+
+	if (files) {
+		int fd = proc_fd(d_inode(dentry));
+		struct file *fd_file;
+
+		spin_lock(&files->file_lock);
+		fd_file = fcheck_files(files, fd);
+		if (fd_file) {
+			*path = fd_file->f_path;
+			path_get(&fd_file->f_path);
+			ret = 0;
+		}
+		spin_unlock(&files->file_lock);
+		put_files_struct(files);
+	}
+
+	return ret;
+}
+
+static int
+proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
+		    struct task_struct *task, const void *ptr)
+{
+	unsigned fd = (unsigned long)ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	ei->fd = fd;
+
+	inode->i_mode = S_IFLNK;
+	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_size = 64;
+
+	ei->op.proc_get_link = proc_fd_link;
+
+	d_set_d_op(dentry, &tid_fd_dentry_operations);
+	d_add(dentry, inode);
+
+	/* Close the race of the process dying before we return the dentry */
+	if (tid_fd_revalidate(dentry, 0))
+		return 0;
+ out:
+	return -ENOENT;
+}
+
+static struct dentry *proc_lookupfd_common(struct inode *dir,
+					   struct dentry *dentry,
+					   instantiate_t instantiate)
+{
+	struct task_struct *task = get_proc_task(dir);
+	int result = -ENOENT;
+	unsigned fd = name_to_int(&dentry->d_name);
+
+	if (!task)
+		goto out_no_task;
+	if (fd == ~0U)
+		goto out;
+
+	result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
+out:
+	put_task_struct(task);
+out_no_task:
+	return ERR_PTR(result);
+}
+
+static int proc_readfd_common(struct file *file, struct dir_context *ctx,
+			      instantiate_t instantiate)
+{
+	struct task_struct *p = get_proc_task(file_inode(file));
+	struct files_struct *files;
+	unsigned int fd;
+
+	if (!p)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	files = get_files_struct(p);
+	if (!files)
+		goto out;
+
+	rcu_read_lock();
+	for (fd = ctx->pos - 2;
+	     fd < files_fdtable(files)->max_fds;
+	     fd++, ctx->pos++) {
+		char name[PROC_NUMBUF];
+		int len;
+
+		if (!fcheck_files(files, fd))
+			continue;
+		rcu_read_unlock();
+
+		len = snprintf(name, sizeof(name), "%d", fd);
+		if (!proc_fill_cache(file, ctx,
+				     name, len, instantiate, p,
+				     (void *)(unsigned long)fd))
+			goto out_fd_loop;
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+out_fd_loop:
+	put_files_struct(files);
+out:
+	put_task_struct(p);
+	return 0;
+}
+
+static int proc_readfd(struct file *file, struct dir_context *ctx)
+{
+	return proc_readfd_common(file, ctx, proc_fd_instantiate);
+}
+
+const struct file_operations proc_fd_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_readfd,
+	.llseek		= default_llseek,
+};
+
+static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
+}
+
+/*
+ * /proc/pid/fd needs a special permission handler so that a process can still
+ * access /proc/self/fd after it has executed a setuid().
+ */
+int proc_fd_permission(struct inode *inode, int mask)
+{
+	int rv = generic_permission(inode, mask);
+	if (rv == 0)
+		return 0;
+	if (task_tgid(current) == proc_pid(inode))
+		rv = 0;
+	return rv;
+}
+
+const struct inode_operations proc_fd_inode_operations = {
+	.lookup		= proc_lookupfd,
+	.permission	= proc_fd_permission,
+	.setattr	= proc_setattr,
+};
+
+static int
+proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
+			struct task_struct *task, const void *ptr)
+{
+	unsigned fd = (unsigned long)ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	ei->fd = fd;
+
+	inode->i_mode = S_IFREG | S_IRUSR;
+	inode->i_fop = &proc_fdinfo_file_operations;
+
+	d_set_d_op(dentry, &tid_fd_dentry_operations);
+	d_add(dentry, inode);
+
+	/* Close the race of the process dying before we return the dentry */
+	if (tid_fd_revalidate(dentry, 0))
+		return 0;
+ out:
+	return -ENOENT;
+}
+
+static struct dentry *
+proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
+}
+
+static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
+{
+	return proc_readfd_common(file, ctx,
+				  proc_fdinfo_instantiate);
+}
+
+const struct inode_operations proc_fdinfo_inode_operations = {
+	.lookup		= proc_lookupfdinfo,
+	.setattr	= proc_setattr,
+};
+
+const struct file_operations proc_fdinfo_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_readfdinfo,
+	.llseek		= default_llseek,
+};
diff --git a/fs/proc/fd.h b/fs/proc/fd.h
new file mode 100644
index 000000000..7c047f256
--- /dev/null
+++ b/fs/proc/fd.h
@@ -0,0 +1,19 @@
+#ifndef __PROCFS_FD_H__
+#define __PROCFS_FD_H__
+
+#include <linux/fs.h>
+
+extern const struct file_operations proc_fd_operations;
+extern const struct inode_operations proc_fd_inode_operations;
+
+extern const struct file_operations proc_fdinfo_operations;
+extern const struct inode_operations proc_fdinfo_inode_operations;
+
+extern int proc_fd_permission(struct inode *inode, int mask);
+
+static inline int proc_fd(struct inode *inode)
+{
+	return PROC_I(inode)->fd;
+}
+
+#endif /* __PROCFS_FD_H__ */
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
new file mode 100644
index 000000000..e5dee5c31
--- /dev/null
+++ b/fs/proc/generic.c
@@ -0,0 +1,645 @@
+/*
+ * proc/fs/generic.c --- generic routines for the proc-fs
+ *
+ * This file contains generic proc-fs routines for handling
+ * directories and files.
+ * 
+ * Copyright (C) 1991, 1992 Linus Torvalds.
+ * Copyright (C) 1997 Theodore Ts'o
+ */
+
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/printk.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/idr.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+static DEFINE_SPINLOCK(proc_subdir_lock);
+
+static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
+{
+	if (len < de->namelen)
+		return -1;
+	if (len > de->namelen)
+		return 1;
+
+	return memcmp(name, de->name, len);
+}
+
+static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
+{
+	return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
+			     subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
+{
+	return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry,
+			     subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
+					      const char *name,
+					      unsigned int len)
+{
+	struct rb_node *node = dir->subdir.rb_node;
+
+	while (node) {
+		struct proc_dir_entry *de = container_of(node,
+							 struct proc_dir_entry,
+							 subdir_node);
+		int result = proc_match(len, name, de);
+
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return de;
+	}
+	return NULL;
+}
+
+static bool pde_subdir_insert(struct proc_dir_entry *dir,
+			      struct proc_dir_entry *de)
+{
+	struct rb_root *root = &dir->subdir;
+	struct rb_node **new = &root->rb_node, *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct proc_dir_entry *this =
+			container_of(*new, struct proc_dir_entry, subdir_node);
+		int result = proc_match(de->namelen, de->name, this);
+
+		parent = *new;
+		if (result < 0)
+			new = &(*new)->rb_left;
+		else if (result > 0)
+			new = &(*new)->rb_right;
+		else
+			return false;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&de->subdir_node, parent, new);
+	rb_insert_color(&de->subdir_node, root);
+	return true;
+}
+
+static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = d_inode(dentry);
+	struct proc_dir_entry *de = PDE(inode);
+	int error;
+
+	error = inode_change_ok(inode, iattr);
+	if (error)
+		return error;
+
+	setattr_copy(inode, iattr);
+	mark_inode_dirty(inode);
+
+	proc_set_user(de, inode->i_uid, inode->i_gid);
+	de->mode = inode->i_mode;
+	return 0;
+}
+
+static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	struct proc_dir_entry *de = PDE(inode);
+	if (de && de->nlink)
+		set_nlink(inode, de->nlink);
+
+	generic_fillattr(inode, stat);
+	return 0;
+}
+
+static const struct inode_operations proc_file_inode_operations = {
+	.setattr	= proc_notify_change,
+};
+
+/*
+ * This function parses a name such as "tty/driver/serial", and
+ * returns the struct proc_dir_entry for "/proc/tty/driver", and
+ * returns "serial" in residual.
+ */
+static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+			     const char **residual)
+{
+	const char     		*cp = name, *next;
+	struct proc_dir_entry	*de;
+	unsigned int		len;
+
+	de = *ret;
+	if (!de)
+		de = &proc_root;
+
+	while (1) {
+		next = strchr(cp, '/');
+		if (!next)
+			break;
+
+		len = next - cp;
+		de = pde_subdir_find(de, cp, len);
+		if (!de) {
+			WARN(1, "name '%s'\n", name);
+			return -ENOENT;
+		}
+		cp += len + 1;
+	}
+	*residual = cp;
+	*ret = de;
+	return 0;
+}
+
+static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+			   const char **residual)
+{
+	int rv;
+
+	spin_lock(&proc_subdir_lock);
+	rv = __xlate_proc_name(name, ret, residual);
+	spin_unlock(&proc_subdir_lock);
+	return rv;
+}
+
+static DEFINE_IDA(proc_inum_ida);
+static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
+
+#define PROC_DYNAMIC_FIRST 0xF0000000U
+
+/*
+ * Return an inode number between PROC_DYNAMIC_FIRST and
+ * 0xffffffff, or zero on failure.
+ */
+int proc_alloc_inum(unsigned int *inum)
+{
+	unsigned int i;
+	int error;
+
+retry:
+	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	spin_lock_irq(&proc_inum_lock);
+	error = ida_get_new(&proc_inum_ida, &i);
+	spin_unlock_irq(&proc_inum_lock);
+	if (error == -EAGAIN)
+		goto retry;
+	else if (error)
+		return error;
+
+	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
+		spin_lock_irq(&proc_inum_lock);
+		ida_remove(&proc_inum_ida, i);
+		spin_unlock_irq(&proc_inum_lock);
+		return -ENOSPC;
+	}
+	*inum = PROC_DYNAMIC_FIRST + i;
+	return 0;
+}
+
+void proc_free_inum(unsigned int inum)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&proc_inum_lock, flags);
+	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
+	spin_unlock_irqrestore(&proc_inum_lock, flags);
+}
+
+/*
+ * Don't create negative dentries here, return -ENOENT by hand
+ * instead.
+ */
+struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
+		struct dentry *dentry)
+{
+	struct inode *inode;
+
+	spin_lock(&proc_subdir_lock);
+	de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
+	if (de) {
+		pde_get(de);
+		spin_unlock(&proc_subdir_lock);
+		inode = proc_get_inode(dir->i_sb, de);
+		if (!inode)
+			return ERR_PTR(-ENOMEM);
+		d_set_d_op(dentry, &simple_dentry_operations);
+		d_add(dentry, inode);
+		return NULL;
+	}
+	spin_unlock(&proc_subdir_lock);
+	return ERR_PTR(-ENOENT);
+}
+
+struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
+		unsigned int flags)
+{
+	return proc_lookup_de(PDE(dir), dir, dentry);
+}
+
+/*
+ * This returns non-zero if at EOF, so that the /proc
+ * root directory can use this and check if it should
+ * continue with the <pid> entries..
+ *
+ * Note that the VFS-layer doesn't care about the return
+ * value of the readdir() call, as long as it's non-negative
+ * for success..
+ */
+int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
+		    struct dir_context *ctx)
+{
+	int i;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	spin_lock(&proc_subdir_lock);
+	de = pde_subdir_first(de);
+	i = ctx->pos - 2;
+	for (;;) {
+		if (!de) {
+			spin_unlock(&proc_subdir_lock);
+			return 0;
+		}
+		if (!i)
+			break;
+		de = pde_subdir_next(de);
+		i--;
+	}
+
+	do {
+		struct proc_dir_entry *next;
+		pde_get(de);
+		spin_unlock(&proc_subdir_lock);
+		if (!dir_emit(ctx, de->name, de->namelen,
+			    de->low_ino, de->mode >> 12)) {
+			pde_put(de);
+			return 0;
+		}
+		spin_lock(&proc_subdir_lock);
+		ctx->pos++;
+		next = pde_subdir_next(de);
+		pde_put(de);
+		de = next;
+	} while (de);
+	spin_unlock(&proc_subdir_lock);
+	return 1;
+}
+
+int proc_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct inode *inode = file_inode(file);
+
+	return proc_readdir_de(PDE(inode), file, ctx);
+}
+
+/*
+ * These are the generic /proc directory operations. They
+ * use the in-memory "struct proc_dir_entry" tree to parse
+ * the /proc directory.
+ */
+static const struct file_operations proc_dir_operations = {
+	.llseek			= generic_file_llseek,
+	.read			= generic_read_dir,
+	.iterate		= proc_readdir,
+};
+
+/*
+ * proc directories can do almost nothing..
+ */
+static const struct inode_operations proc_dir_inode_operations = {
+	.lookup		= proc_lookup,
+	.getattr	= proc_getattr,
+	.setattr	= proc_notify_change,
+};
+
+static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
+{
+	int ret;
+
+	ret = proc_alloc_inum(&dp->low_ino);
+	if (ret)
+		return ret;
+
+	spin_lock(&proc_subdir_lock);
+	dp->parent = dir;
+	if (pde_subdir_insert(dir, dp) == false) {
+		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+		     dir->name, dp->name);
+		spin_unlock(&proc_subdir_lock);
+		proc_free_inum(dp->low_ino);
+		return -EEXIST;
+	}
+	spin_unlock(&proc_subdir_lock);
+
+	return 0;
+}
+
+static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
+					  const char *name,
+					  umode_t mode,
+					  nlink_t nlink)
+{
+	struct proc_dir_entry *ent = NULL;
+	const char *fn;
+	struct qstr qstr;
+
+	if (xlate_proc_name(name, parent, &fn) != 0)
+		goto out;
+	qstr.name = fn;
+	qstr.len = strlen(fn);
+	if (qstr.len == 0 || qstr.len >= 256) {
+		WARN(1, "name len %u\n", qstr.len);
+		return NULL;
+	}
+	if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
+		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
+		return NULL;
+	}
+	if (is_empty_pde(*parent)) {
+		WARN(1, "attempt to add to permanently empty directory");
+		return NULL;
+	}
+
+	ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL);
+	if (!ent)
+		goto out;
+
+	memcpy(ent->name, fn, qstr.len + 1);
+	ent->namelen = qstr.len;
+	ent->mode = mode;
+	ent->nlink = nlink;
+	ent->subdir = RB_ROOT;
+	atomic_set(&ent->count, 1);
+	spin_lock_init(&ent->pde_unload_lock);
+	INIT_LIST_HEAD(&ent->pde_openers);
+out:
+	return ent;
+}
+
+struct proc_dir_entry *proc_symlink(const char *name,
+		struct proc_dir_entry *parent, const char *dest)
+{
+	struct proc_dir_entry *ent;
+
+	ent = __proc_create(&parent, name,
+			  (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1);
+
+	if (ent) {
+		ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL);
+		if (ent->data) {
+			strcpy((char*)ent->data,dest);
+			ent->proc_iops = &proc_link_inode_operations;
+			if (proc_register(parent, ent) < 0) {
+				kfree(ent->data);
+				kfree(ent);
+				ent = NULL;
+			}
+		} else {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+EXPORT_SYMBOL(proc_symlink);
+
+struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data)
+{
+	struct proc_dir_entry *ent;
+
+	if (mode == 0)
+		mode = S_IRUGO | S_IXUGO;
+
+	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
+	if (ent) {
+		ent->data = data;
+		ent->proc_fops = &proc_dir_operations;
+		ent->proc_iops = &proc_dir_inode_operations;
+		parent->nlink++;
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			parent->nlink--;
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+EXPORT_SYMBOL_GPL(proc_mkdir_data);
+
+struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
+				       struct proc_dir_entry *parent)
+{
+	return proc_mkdir_data(name, mode, parent, NULL);
+}
+EXPORT_SYMBOL(proc_mkdir_mode);
+
+struct proc_dir_entry *proc_mkdir(const char *name,
+		struct proc_dir_entry *parent)
+{
+	return proc_mkdir_data(name, 0, parent, NULL);
+}
+EXPORT_SYMBOL(proc_mkdir);
+
+struct proc_dir_entry *proc_create_mount_point(const char *name)
+{
+	umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	struct proc_dir_entry *ent, *parent = NULL;
+
+	ent = __proc_create(&parent, name, mode, 2);
+	if (ent) {
+		ent->data = NULL;
+		ent->proc_fops = NULL;
+		ent->proc_iops = NULL;
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			parent->nlink--;
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
+struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
+					struct proc_dir_entry *parent,
+					const struct file_operations *proc_fops,
+					void *data)
+{
+	struct proc_dir_entry *pde;
+	if ((mode & S_IFMT) == 0)
+		mode |= S_IFREG;
+
+	if (!S_ISREG(mode)) {
+		WARN_ON(1);	/* use proc_mkdir() */
+		return NULL;
+	}
+
+	BUG_ON(proc_fops == NULL);
+
+	if ((mode & S_IALLUGO) == 0)
+		mode |= S_IRUGO;
+	pde = __proc_create(&parent, name, mode, 1);
+	if (!pde)
+		goto out;
+	pde->proc_fops = proc_fops;
+	pde->data = data;
+	pde->proc_iops = &proc_file_inode_operations;
+	if (proc_register(parent, pde) < 0)
+		goto out_free;
+	return pde;
+out_free:
+	kfree(pde);
+out:
+	return NULL;
+}
+EXPORT_SYMBOL(proc_create_data);
+ 
+void proc_set_size(struct proc_dir_entry *de, loff_t size)
+{
+	de->size = size;
+}
+EXPORT_SYMBOL(proc_set_size);
+
+void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
+{
+	de->uid = uid;
+	de->gid = gid;
+}
+EXPORT_SYMBOL(proc_set_user);
+
+static void free_proc_entry(struct proc_dir_entry *de)
+{
+	proc_free_inum(de->low_ino);
+
+	if (S_ISLNK(de->mode))
+		kfree(de->data);
+	kfree(de);
+}
+
+void pde_put(struct proc_dir_entry *pde)
+{
+	if (atomic_dec_and_test(&pde->count))
+		free_proc_entry(pde);
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *de = NULL;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return;
+	}
+	len = strlen(fn);
+
+	de = pde_subdir_find(parent, fn, len);
+	if (de)
+		rb_erase(&de->subdir_node, &parent->subdir);
+	spin_unlock(&proc_subdir_lock);
+	if (!de) {
+		WARN(1, "name '%s'\n", name);
+		return;
+	}
+
+	proc_entry_rundown(de);
+
+	if (S_ISDIR(de->mode))
+		parent->nlink--;
+	de->nlink = 0;
+	WARN(pde_subdir_first(de),
+	     "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
+	     __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
+	pde_put(de);
+}
+EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *root = NULL, *de, *next;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	len = strlen(fn);
+
+	root = pde_subdir_find(parent, fn, len);
+	if (!root) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	rb_erase(&root->subdir_node, &parent->subdir);
+
+	de = root;
+	while (1) {
+		next = pde_subdir_first(de);
+		if (next) {
+			rb_erase(&next->subdir_node, &de->subdir);
+			de = next;
+			continue;
+		}
+		spin_unlock(&proc_subdir_lock);
+
+		proc_entry_rundown(de);
+		next = de->parent;
+		if (S_ISDIR(de->mode))
+			next->nlink--;
+		de->nlink = 0;
+		if (de == root)
+			break;
+		pde_put(de);
+
+		spin_lock(&proc_subdir_lock);
+		de = next;
+	}
+	pde_put(root);
+	return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
+
+void *proc_get_parent_data(const struct inode *inode)
+{
+	struct proc_dir_entry *de = PDE(inode);
+	return de->parent->data;
+}
+EXPORT_SYMBOL_GPL(proc_get_parent_data);
+
+void proc_remove(struct proc_dir_entry *de)
+{
+	if (de)
+		remove_proc_subtree(de->name, de->parent);
+}
+EXPORT_SYMBOL(proc_remove);
+
+void *PDE_DATA(const struct inode *inode)
+{
+	return __PDE_DATA(inode);
+}
+EXPORT_SYMBOL(PDE_DATA);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
new file mode 100644
index 000000000..e3eb55246
--- /dev/null
+++ b/fs/proc/inode.c
@@ -0,0 +1,489 @@
+/*
+ *  linux/fs/proc/inode.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/kernel.h>
+#include <linux/pid_namespace.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/completion.h>
+#include <linux/poll.h>
+#include <linux/printk.h>
+#include <linux/file.h>
+#include <linux/limits.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/magic.h>
+#include <linux/namei.h>
+
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+static void proc_evict_inode(struct inode *inode)
+{
+	struct proc_dir_entry *de;
+	struct ctl_table_header *head;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+
+	/* Stop tracking associated processes */
+	put_pid(PROC_I(inode)->pid);
+
+	/* Let go of any associated proc directory entry */
+	de = PDE(inode);
+	if (de)
+		pde_put(de);
+	head = PROC_I(inode)->sysctl;
+	if (head) {
+		RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL);
+		sysctl_head_put(head);
+	}
+}
+
+static struct kmem_cache * proc_inode_cachep;
+
+static struct inode *proc_alloc_inode(struct super_block *sb)
+{
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
+	if (!ei)
+		return NULL;
+	ei->pid = NULL;
+	ei->fd = 0;
+	ei->op.proc_get_link = NULL;
+	ei->pde = NULL;
+	ei->sysctl = NULL;
+	ei->sysctl_entry = NULL;
+	ei->ns_ops = NULL;
+	inode = &ei->vfs_inode;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	return inode;
+}
+
+static void proc_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
+}
+
+static void proc_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, proc_i_callback);
+}
+
+static void init_once(void *foo)
+{
+	struct proc_inode *ei = (struct proc_inode *) foo;
+
+	inode_init_once(&ei->vfs_inode);
+}
+
+void __init proc_init_inodecache(void)
+{
+	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
+					     sizeof(struct proc_inode),
+					     0, (SLAB_RECLAIM_ACCOUNT|
+						SLAB_MEM_SPREAD|SLAB_PANIC),
+					     init_once);
+}
+
+static int proc_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct super_block *sb = root->d_sb;
+	struct pid_namespace *pid = sb->s_fs_info;
+
+	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
+	if (pid->hide_pid != 0)
+		seq_printf(seq, ",hidepid=%u", pid->hide_pid);
+
+	return 0;
+}
+
+static const struct super_operations proc_sops = {
+	.alloc_inode	= proc_alloc_inode,
+	.destroy_inode	= proc_destroy_inode,
+	.drop_inode	= generic_delete_inode,
+	.evict_inode	= proc_evict_inode,
+	.statfs		= simple_statfs,
+	.remount_fs	= proc_remount,
+	.show_options	= proc_show_options,
+};
+
+enum {BIAS = -1U<<31};
+
+static inline int use_pde(struct proc_dir_entry *pde)
+{
+	return atomic_inc_unless_negative(&pde->in_use);
+}
+
+static void unuse_pde(struct proc_dir_entry *pde)
+{
+	if (atomic_dec_return(&pde->in_use) == BIAS)
+		complete(pde->pde_unload_completion);
+}
+
+/* pde is locked */
+static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
+{
+	if (pdeo->closing) {
+		/* somebody else is doing that, just wait */
+		DECLARE_COMPLETION_ONSTACK(c);
+		pdeo->c = &c;
+		spin_unlock(&pde->pde_unload_lock);
+		wait_for_completion(&c);
+		spin_lock(&pde->pde_unload_lock);
+	} else {
+		struct file *file;
+		pdeo->closing = 1;
+		spin_unlock(&pde->pde_unload_lock);
+		file = pdeo->file;
+		pde->proc_fops->release(file_inode(file), file);
+		spin_lock(&pde->pde_unload_lock);
+		list_del_init(&pdeo->lh);
+		if (pdeo->c)
+			complete(pdeo->c);
+		kfree(pdeo);
+	}
+}
+
+void proc_entry_rundown(struct proc_dir_entry *de)
+{
+	DECLARE_COMPLETION_ONSTACK(c);
+	/* Wait until all existing callers into module are done. */
+	de->pde_unload_completion = &c;
+	if (atomic_add_return(BIAS, &de->in_use) != BIAS)
+		wait_for_completion(&c);
+
+	spin_lock(&de->pde_unload_lock);
+	while (!list_empty(&de->pde_openers)) {
+		struct pde_opener *pdeo;
+		pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+		close_pdeo(de, pdeo);
+	}
+	spin_unlock(&de->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	loff_t rv = -EINVAL;
+	if (use_pde(pde)) {
+		loff_t (*llseek)(struct file *, loff_t, int);
+		llseek = pde->proc_fops->llseek;
+		if (!llseek)
+			llseek = default_llseek;
+		rv = llseek(file, offset, whence);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+	if (use_pde(pde)) {
+		read = pde->proc_fops->read;
+		if (read)
+			rv = read(file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+	if (use_pde(pde)) {
+		write = pde->proc_fops->write;
+		if (write)
+			rv = write(file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	unsigned int rv = DEFAULT_POLLMASK;
+	unsigned int (*poll)(struct file *, struct poll_table_struct *);
+	if (use_pde(pde)) {
+		poll = pde->proc_fops->poll;
+		if (poll)
+			rv = poll(file, pts);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	long rv = -ENOTTY;
+	long (*ioctl)(struct file *, unsigned int, unsigned long);
+	if (use_pde(pde)) {
+		ioctl = pde->proc_fops->unlocked_ioctl;
+		if (ioctl)
+			rv = ioctl(file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+#ifdef CONFIG_COMPAT
+static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	long rv = -ENOTTY;
+	long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
+	if (use_pde(pde)) {
+		compat_ioctl = pde->proc_fops->compat_ioctl;
+		if (compat_ioctl)
+			rv = compat_ioctl(file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+#endif
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	int rv = -EIO;
+	int (*mmap)(struct file *, struct vm_area_struct *);
+	if (use_pde(pde)) {
+		mmap = pde->proc_fops->mmap;
+		if (mmap)
+			rv = mmap(file, vma);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static unsigned long
+proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
+			   unsigned long len, unsigned long pgoff,
+			   unsigned long flags)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	unsigned long rv = -EIO;
+
+	if (use_pde(pde)) {
+		typeof(proc_reg_get_unmapped_area) *get_area;
+
+		get_area = pde->proc_fops->get_unmapped_area;
+#ifdef CONFIG_MMU
+		if (!get_area)
+			get_area = current->mm->get_unmapped_area;
+#endif
+
+		if (get_area)
+			rv = get_area(file, orig_addr, len, pgoff, flags);
+		else
+			rv = orig_addr;
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static int proc_reg_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	int rv = 0;
+	int (*open)(struct inode *, struct file *);
+	int (*release)(struct inode *, struct file *);
+	struct pde_opener *pdeo;
+
+	/*
+	 * What for, you ask? Well, we can have open, rmmod, remove_proc_entry
+	 * sequence. ->release won't be called because ->proc_fops will be
+	 * cleared. Depending on complexity of ->release, consequences vary.
+	 *
+	 * We can't wait for mercy when close will be done for real, it's
+	 * deadlockable: rmmod foo </proc/foo . So, we're going to do ->release
+	 * by hand in remove_proc_entry(). For this, save opener's credentials
+	 * for later.
+	 */
+	pdeo = kzalloc(sizeof(struct pde_opener), GFP_KERNEL);
+	if (!pdeo)
+		return -ENOMEM;
+
+	if (!use_pde(pde)) {
+		kfree(pdeo);
+		return -ENOENT;
+	}
+	open = pde->proc_fops->open;
+	release = pde->proc_fops->release;
+
+	if (open)
+		rv = open(inode, file);
+
+	if (rv == 0 && release) {
+		/* To know what to release. */
+		pdeo->file = file;
+		/* Strictly for "too late" ->release in proc_reg_release(). */
+		spin_lock(&pde->pde_unload_lock);
+		list_add(&pdeo->lh, &pde->pde_openers);
+		spin_unlock(&pde->pde_unload_lock);
+	} else
+		kfree(pdeo);
+
+	unuse_pde(pde);
+	return rv;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	struct pde_opener *pdeo;
+	spin_lock(&pde->pde_unload_lock);
+	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+		if (pdeo->file == file) {
+			close_pdeo(pde, pdeo);
+			break;
+		}
+	}
+	spin_unlock(&pde->pde_unload_lock);
+	return 0;
+}
+
+static const struct file_operations proc_reg_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read		= proc_reg_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= proc_reg_compat_ioctl,
+#endif
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+#ifdef CONFIG_COMPAT
+static const struct file_operations proc_reg_file_ops_no_compat = {
+	.llseek		= proc_reg_llseek,
+	.read		= proc_reg_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+#endif
+
+static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct proc_dir_entry *pde = PDE(d_inode(dentry));
+	if (unlikely(!use_pde(pde)))
+		return ERR_PTR(-EINVAL);
+	nd_set_link(nd, pde->data);
+	return pde;
+}
+
+static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+{
+	unuse_pde(p);
+}
+
+const struct inode_operations proc_link_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= proc_follow_link,
+	.put_link	= proc_put_link,
+};
+
+struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
+{
+	struct inode *inode = new_inode_pseudo(sb);
+
+	if (inode) {
+		inode->i_ino = de->low_ino;
+		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		PROC_I(inode)->pde = de;
+
+		if (is_empty_pde(de)) {
+			make_empty_dir_inode(inode);
+			return inode;
+		}
+		if (de->mode) {
+			inode->i_mode = de->mode;
+			inode->i_uid = de->uid;
+			inode->i_gid = de->gid;
+		}
+		if (de->size)
+			inode->i_size = de->size;
+		if (de->nlink)
+			set_nlink(inode, de->nlink);
+		WARN_ON(!de->proc_iops);
+		inode->i_op = de->proc_iops;
+		if (de->proc_fops) {
+			if (S_ISREG(inode->i_mode)) {
+#ifdef CONFIG_COMPAT
+				if (!de->proc_fops->compat_ioctl)
+					inode->i_fop =
+						&proc_reg_file_ops_no_compat;
+				else
+#endif
+					inode->i_fop = &proc_reg_file_ops;
+			} else {
+				inode->i_fop = de->proc_fops;
+			}
+		}
+	} else
+	       pde_put(de);
+	return inode;
+}
+
+int proc_fill_super(struct super_block *s)
+{
+	struct inode *root_inode;
+	int ret;
+
+	s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
+	s->s_blocksize = 1024;
+	s->s_blocksize_bits = 10;
+	s->s_magic = PROC_SUPER_MAGIC;
+	s->s_op = &proc_sops;
+	s->s_time_gran = 1;
+	
+	pde_get(&proc_root);
+	root_inode = proc_get_inode(s, &proc_root);
+	if (!root_inode) {
+		pr_err("proc_fill_super: get root inode failed\n");
+		return -ENOMEM;
+	}
+
+	s->s_root = d_make_root(root_inode);
+	if (!s->s_root) {
+		pr_err("proc_fill_super: allocate dentry failed\n");
+		return -ENOMEM;
+	}
+
+	ret = proc_setup_self(s);
+	if (ret) {
+		return ret;
+	}
+	return proc_setup_thread_self(s);
+}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
new file mode 100644
index 000000000..aa2781095
--- /dev/null
+++ b/fs/proc/internal.h
@@ -0,0 +1,305 @@
+/* Internal procfs definitions
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/proc_ns.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <linux/binfmts.h>
+
+struct ctl_table_header;
+struct mempolicy;
+
+/*
+ * This is not completely implemented yet. The idea is to
+ * create an in-memory tree (like the actual /proc filesystem
+ * tree) of these proc_dir_entries, so that we can dynamically
+ * add new files to /proc.
+ *
+ * parent/subdir are used for the directory structure (every /proc file has a
+ * parent, but "subdir" is empty for all non-directory entries).
+ * subdir_node is used to build the rb tree "subdir" of the parent.
+ */
+struct proc_dir_entry {
+	unsigned int low_ino;
+	umode_t mode;
+	nlink_t nlink;
+	kuid_t uid;
+	kgid_t gid;
+	loff_t size;
+	const struct inode_operations *proc_iops;
+	const struct file_operations *proc_fops;
+	struct proc_dir_entry *parent;
+	struct rb_root subdir;
+	struct rb_node subdir_node;
+	void *data;
+	atomic_t count;		/* use count */
+	atomic_t in_use;	/* number of callers into module in progress; */
+			/* negative -> it's going away RSN */
+	struct completion *pde_unload_completion;
+	struct list_head pde_openers;	/* who did ->open, but not ->release */
+	spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
+	u8 namelen;
+	char name[];
+};
+
+union proc_op {
+	int (*proc_get_link)(struct dentry *, struct path *);
+	int (*proc_show)(struct seq_file *m,
+		struct pid_namespace *ns, struct pid *pid,
+		struct task_struct *task);
+};
+
+struct proc_inode {
+	struct pid *pid;
+	int fd;
+	union proc_op op;
+	struct proc_dir_entry *pde;
+	struct ctl_table_header *sysctl;
+	struct ctl_table *sysctl_entry;
+	const struct proc_ns_operations *ns_ops;
+	struct inode vfs_inode;
+};
+
+/*
+ * General functions
+ */
+static inline struct proc_inode *PROC_I(const struct inode *inode)
+{
+	return container_of(inode, struct proc_inode, vfs_inode);
+}
+
+static inline struct proc_dir_entry *PDE(const struct inode *inode)
+{
+	return PROC_I(inode)->pde;
+}
+
+static inline void *__PDE_DATA(const struct inode *inode)
+{
+	return PDE(inode)->data;
+}
+
+static inline struct pid *proc_pid(struct inode *inode)
+{
+	return PROC_I(inode)->pid;
+}
+
+static inline struct task_struct *get_proc_task(struct inode *inode)
+{
+	return get_pid_task(proc_pid(inode), PIDTYPE_PID);
+}
+
+static inline int task_dumpable(struct task_struct *task)
+{
+	int dumpable = 0;
+	struct mm_struct *mm;
+
+	task_lock(task);
+	mm = task->mm;
+	if (mm)
+		dumpable = get_dumpable(mm);
+	task_unlock(task);
+	if (dumpable == SUID_DUMP_USER)
+		return 1;
+	return 0;
+}
+
+static inline unsigned name_to_int(const struct qstr *qstr)
+{
+	const char *name = qstr->name;
+	int len = qstr->len;
+	unsigned n = 0;
+
+	if (len > 1 && *name == '0')
+		goto out;
+	while (len-- > 0) {
+		unsigned c = *name++ - '0';
+		if (c > 9)
+			goto out;
+		if (n >= (~0U-9)/10)
+			goto out;
+		n *= 10;
+		n += c;
+	}
+	return n;
+out:
+	return ~0U;
+}
+
+/*
+ * Offset of the first process in the /proc root directory..
+ */
+#define FIRST_PROCESS_ENTRY 256
+
+/* Worst case buffer size needed for holding an integer. */
+#define PROC_NUMBUF 13
+
+/*
+ * array.c
+ */
+extern const struct file_operations proc_tid_children_operations;
+
+extern int proc_tid_stat(struct seq_file *, struct pid_namespace *,
+			 struct pid *, struct task_struct *);
+extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *,
+			  struct pid *, struct task_struct *);
+extern int proc_pid_status(struct seq_file *, struct pid_namespace *,
+			   struct pid *, struct task_struct *);
+extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
+			  struct pid *, struct task_struct *);
+
+/*
+ * base.c
+ */
+extern const struct dentry_operations pid_dentry_operations;
+extern int pid_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int proc_setattr(struct dentry *, struct iattr *);
+extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *);
+extern int pid_revalidate(struct dentry *, unsigned int);
+extern int pid_delete_dentry(const struct dentry *);
+extern int proc_pid_readdir(struct file *, struct dir_context *);
+extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
+extern loff_t mem_lseek(struct file *, loff_t, int);
+
+/* Lookups */
+typedef int instantiate_t(struct inode *, struct dentry *,
+				     struct task_struct *, const void *);
+extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int,
+			   instantiate_t, struct task_struct *, const void *);
+
+/*
+ * generic.c
+ */
+extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
+extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *,
+				     struct dentry *);
+extern int proc_readdir(struct file *, struct dir_context *);
+extern int proc_readdir_de(struct proc_dir_entry *, struct file *, struct dir_context *);
+
+static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
+{
+	atomic_inc(&pde->count);
+	return pde;
+}
+extern void pde_put(struct proc_dir_entry *);
+
+static inline bool is_empty_pde(const struct proc_dir_entry *pde)
+{
+	return S_ISDIR(pde->mode) && !pde->proc_iops;
+}
+struct proc_dir_entry *proc_create_mount_point(const char *name);
+
+/*
+ * inode.c
+ */
+struct pde_opener {
+	struct file *file;
+	struct list_head lh;
+	int closing;
+	struct completion *c;
+};
+extern const struct inode_operations proc_link_inode_operations;
+
+extern const struct inode_operations proc_pid_link_inode_operations;
+
+extern void proc_init_inodecache(void);
+extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
+extern int proc_fill_super(struct super_block *);
+extern void proc_entry_rundown(struct proc_dir_entry *);
+
+/*
+ * proc_namespaces.c
+ */
+extern const struct inode_operations proc_ns_dir_inode_operations;
+extern const struct file_operations proc_ns_dir_operations;
+
+/*
+ * proc_net.c
+ */
+extern const struct file_operations proc_net_operations;
+extern const struct inode_operations proc_net_inode_operations;
+
+#ifdef CONFIG_NET
+extern int proc_net_init(void);
+#else
+static inline int proc_net_init(void) { return 0; }
+#endif
+
+/*
+ * proc_self.c
+ */
+extern int proc_setup_self(struct super_block *);
+
+/*
+ * proc_thread_self.c
+ */
+extern int proc_setup_thread_self(struct super_block *);
+extern void proc_thread_self_init(void);
+
+/*
+ * proc_sysctl.c
+ */
+#ifdef CONFIG_PROC_SYSCTL
+extern int proc_sys_init(void);
+extern void sysctl_head_put(struct ctl_table_header *);
+#else
+static inline void proc_sys_init(void) { }
+static inline void sysctl_head_put(struct ctl_table_header *head) { }
+#endif
+
+/*
+ * proc_tty.c
+ */
+#ifdef CONFIG_TTY
+extern void proc_tty_init(void);
+#else
+static inline void proc_tty_init(void) {}
+#endif
+
+/*
+ * root.c
+ */
+extern struct proc_dir_entry proc_root;
+
+extern void proc_self_init(void);
+extern int proc_remount(struct super_block *, int *, char *);
+
+/*
+ * task_[no]mmu.c
+ */
+struct proc_maps_private {
+	struct inode *inode;
+	struct task_struct *task;
+	struct mm_struct *mm;
+#ifdef CONFIG_MMU
+	struct vm_area_struct *tail_vma;
+#endif
+#ifdef CONFIG_NUMA
+	struct mempolicy *task_mempolicy;
+#endif
+};
+
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
+
+extern const struct file_operations proc_pid_maps_operations;
+extern const struct file_operations proc_tid_maps_operations;
+extern const struct file_operations proc_pid_numa_maps_operations;
+extern const struct file_operations proc_tid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_tid_smaps_operations;
+extern const struct file_operations proc_clear_refs_operations;
+extern const struct file_operations proc_pagemap_operations;
+
+extern unsigned long task_vsize(struct mm_struct *);
+extern unsigned long task_statm(struct mm_struct *,
+				unsigned long *, unsigned long *,
+				unsigned long *, unsigned long *);
+extern void task_mem(struct seq_file *, struct mm_struct *);
diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c
new file mode 100644
index 000000000..a352d5703
--- /dev/null
+++ b/fs/proc/interrupts.c
@@ -0,0 +1,53 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irqnr.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+/*
+ * /proc/interrupts
+ */
+static void *int_seq_start(struct seq_file *f, loff_t *pos)
+{
+	return (*pos <= nr_irqs) ? pos : NULL;
+}
+
+static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	(*pos)++;
+	if (*pos > nr_irqs)
+		return NULL;
+	return pos;
+}
+
+static void int_seq_stop(struct seq_file *f, void *v)
+{
+	/* Nothing to do */
+}
+
+static const struct seq_operations int_seq_ops = {
+	.start = int_seq_start,
+	.next  = int_seq_next,
+	.stop  = int_seq_stop,
+	.show  = show_interrupts
+};
+
+static int interrupts_open(struct inode *inode, struct file *filp)
+{
+	return seq_open(filp, &int_seq_ops);
+}
+
+static const struct file_operations proc_interrupts_operations = {
+	.open		= interrupts_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init proc_interrupts_init(void)
+{
+	proc_create("interrupts", 0, NULL, &proc_interrupts_operations);
+	return 0;
+}
+fs_initcall(proc_interrupts_init);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
new file mode 100644
index 000000000..91a4e6426
--- /dev/null
+++ b/fs/proc/kcore.c
@@ -0,0 +1,644 @@
+/*
+ *	fs/proc/kcore.c kernel ELF core dumper
+ *
+ *	Modelled on fs/exec.c:aout_core_dump()
+ *	Jeremy Fitzhardinge <jeremy@sw.oz.au>
+ *	ELF version written by David Howells <David.Howells@nexor.co.uk>
+ *	Modified and incorporated into 2.3.x by Tigran Aivazian <tigran@veritas.com>
+ *	Support to dump vmalloc'd areas (ELF only), Tigran Aivazian <tigran@veritas.com>
+ *	Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/kcore.h>
+#include <linux/user.h>
+#include <linux/capability.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/notifier.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+#include <linux/printk.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <linux/list.h>
+#include <linux/ioport.h>
+#include <linux/memory.h>
+#include <asm/sections.h>
+#include "internal.h"
+
+#define CORE_STR "CORE"
+
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS	0
+#endif
+
+static struct proc_dir_entry *proc_root_kcore;
+
+
+#ifndef kc_vaddr_to_offset
+#define	kc_vaddr_to_offset(v) ((v) - PAGE_OFFSET)
+#endif
+#ifndef	kc_offset_to_vaddr
+#define	kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET)
+#endif
+
+/* An ELF note in memory */
+struct memelfnote
+{
+	const char *name;
+	int type;
+	unsigned int datasz;
+	void *data;
+};
+
+static LIST_HEAD(kclist_head);
+static DEFINE_RWLOCK(kclist_lock);
+static int kcore_need_update = 1;
+
+void
+kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
+{
+	new->addr = (unsigned long)addr;
+	new->size = size;
+	new->type = type;
+
+	write_lock(&kclist_lock);
+	list_add_tail(&new->list, &kclist_head);
+	write_unlock(&kclist_lock);
+}
+
+static size_t get_kcore_size(int *nphdr, size_t *elf_buflen)
+{
+	size_t try, size;
+	struct kcore_list *m;
+
+	*nphdr = 1; /* PT_NOTE */
+	size = 0;
+
+	list_for_each_entry(m, &kclist_head, list) {
+		try = kc_vaddr_to_offset((size_t)m->addr + m->size);
+		if (try > size)
+			size = try;
+		*nphdr = *nphdr + 1;
+	}
+	*elf_buflen =	sizeof(struct elfhdr) + 
+			(*nphdr + 2)*sizeof(struct elf_phdr) + 
+			3 * ((sizeof(struct elf_note)) +
+			     roundup(sizeof(CORE_STR), 4)) +
+			roundup(sizeof(struct elf_prstatus), 4) +
+			roundup(sizeof(struct elf_prpsinfo), 4) +
+			roundup(sizeof(struct task_struct), 4);
+	*elf_buflen = PAGE_ALIGN(*elf_buflen);
+	return size + *elf_buflen;
+}
+
+static void free_kclist_ents(struct list_head *head)
+{
+	struct kcore_list *tmp, *pos;
+
+	list_for_each_entry_safe(pos, tmp, head, list) {
+		list_del(&pos->list);
+		kfree(pos);
+	}
+}
+/*
+ * Replace all KCORE_RAM/KCORE_VMEMMAP information with passed list.
+ */
+static void __kcore_update_ram(struct list_head *list)
+{
+	int nphdr;
+	size_t size;
+	struct kcore_list *tmp, *pos;
+	LIST_HEAD(garbage);
+
+	write_lock(&kclist_lock);
+	if (kcore_need_update) {
+		list_for_each_entry_safe(pos, tmp, &kclist_head, list) {
+			if (pos->type == KCORE_RAM
+				|| pos->type == KCORE_VMEMMAP)
+				list_move(&pos->list, &garbage);
+		}
+		list_splice_tail(list, &kclist_head);
+	} else
+		list_splice(list, &garbage);
+	kcore_need_update = 0;
+	proc_root_kcore->size = get_kcore_size(&nphdr, &size);
+	write_unlock(&kclist_lock);
+
+	free_kclist_ents(&garbage);
+}
+
+
+#ifdef CONFIG_HIGHMEM
+/*
+ * If no highmem, we can assume [0...max_low_pfn) continuous range of memory
+ * because memory hole is not as big as !HIGHMEM case.
+ * (HIGHMEM is special because part of memory is _invisible_ from the kernel.)
+ */
+static int kcore_update_ram(void)
+{
+	LIST_HEAD(head);
+	struct kcore_list *ent;
+	int ret = 0;
+
+	ent = kmalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return -ENOMEM;
+	ent->addr = (unsigned long)__va(0);
+	ent->size = max_low_pfn << PAGE_SHIFT;
+	ent->type = KCORE_RAM;
+	list_add(&ent->list, &head);
+	__kcore_update_ram(&head);
+	return ret;
+}
+
+#else /* !CONFIG_HIGHMEM */
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+/* calculate vmemmap's address from given system ram pfn and register it */
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+{
+	unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT;
+	unsigned long nr_pages = ent->size >> PAGE_SHIFT;
+	unsigned long start, end;
+	struct kcore_list *vmm, *tmp;
+
+
+	start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK;
+	end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1;
+	end = PAGE_ALIGN(end);
+	/* overlap check (because we have to align page */
+	list_for_each_entry(tmp, head, list) {
+		if (tmp->type != KCORE_VMEMMAP)
+			continue;
+		if (start < tmp->addr + tmp->size)
+			if (end > tmp->addr)
+				end = tmp->addr;
+	}
+	if (start < end) {
+		vmm = kmalloc(sizeof(*vmm), GFP_KERNEL);
+		if (!vmm)
+			return 0;
+		vmm->addr = start;
+		vmm->size = end - start;
+		vmm->type = KCORE_VMEMMAP;
+		list_add_tail(&vmm->list, head);
+	}
+	return 1;
+
+}
+#else
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+{
+	return 1;
+}
+
+#endif
+
+static int
+kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
+{
+	struct list_head *head = (struct list_head *)arg;
+	struct kcore_list *ent;
+
+	ent = kmalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return -ENOMEM;
+	ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT));
+	ent->size = nr_pages << PAGE_SHIFT;
+
+	/* Sanity check: Can happen in 32bit arch...maybe */
+	if (ent->addr < (unsigned long) __va(0))
+		goto free_out;
+
+	/* cut not-mapped area. ....from ppc-32 code. */
+	if (ULONG_MAX - ent->addr < ent->size)
+		ent->size = ULONG_MAX - ent->addr;
+
+	/* cut when vmalloc() area is higher than direct-map area */
+	if (VMALLOC_START > (unsigned long)__va(0)) {
+		if (ent->addr > VMALLOC_START)
+			goto free_out;
+		if (VMALLOC_START - ent->addr < ent->size)
+			ent->size = VMALLOC_START - ent->addr;
+	}
+
+	ent->type = KCORE_RAM;
+	list_add_tail(&ent->list, head);
+
+	if (!get_sparsemem_vmemmap_info(ent, head)) {
+		list_del(&ent->list);
+		goto free_out;
+	}
+
+	return 0;
+free_out:
+	kfree(ent);
+	return 1;
+}
+
+static int kcore_update_ram(void)
+{
+	int nid, ret;
+	unsigned long end_pfn;
+	LIST_HEAD(head);
+
+	/* Not inialized....update now */
+	/* find out "max pfn" */
+	end_pfn = 0;
+	for_each_node_state(nid, N_MEMORY) {
+		unsigned long node_end;
+		node_end = node_end_pfn(nid);
+		if (end_pfn < node_end)
+			end_pfn = node_end;
+	}
+	/* scan 0 to max_pfn */
+	ret = walk_system_ram_range(0, end_pfn, &head, kclist_add_private);
+	if (ret) {
+		free_kclist_ents(&head);
+		return -ENOMEM;
+	}
+	__kcore_update_ram(&head);
+	return ret;
+}
+#endif /* CONFIG_HIGHMEM */
+
+/*****************************************************************************/
+/*
+ * determine size of ELF note
+ */
+static int notesize(struct memelfnote *en)
+{
+	int sz;
+
+	sz = sizeof(struct elf_note);
+	sz += roundup((strlen(en->name) + 1), 4);
+	sz += roundup(en->datasz, 4);
+
+	return sz;
+} /* end notesize() */
+
+/*****************************************************************************/
+/*
+ * store a note in the header buffer
+ */
+static char *storenote(struct memelfnote *men, char *bufp)
+{
+	struct elf_note en;
+
+#define DUMP_WRITE(addr,nr) do { memcpy(bufp,addr,nr); bufp += nr; } while(0)
+
+	en.n_namesz = strlen(men->name) + 1;
+	en.n_descsz = men->datasz;
+	en.n_type = men->type;
+
+	DUMP_WRITE(&en, sizeof(en));
+	DUMP_WRITE(men->name, en.n_namesz);
+
+	/* XXX - cast from long long to long to avoid need for libgcc.a */
+	bufp = (char*) roundup((unsigned long)bufp,4);
+	DUMP_WRITE(men->data, men->datasz);
+	bufp = (char*) roundup((unsigned long)bufp,4);
+
+#undef DUMP_WRITE
+
+	return bufp;
+} /* end storenote() */
+
+/*
+ * store an ELF coredump header in the supplied buffer
+ * nphdr is the number of elf_phdr to insert
+ */
+static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
+{
+	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
+	struct elf_prpsinfo prpsinfo;	/* NT_PRPSINFO */
+	struct elf_phdr *nhdr, *phdr;
+	struct elfhdr *elf;
+	struct memelfnote notes[3];
+	off_t offset = 0;
+	struct kcore_list *m;
+
+	/* setup ELF header */
+	elf = (struct elfhdr *) bufp;
+	bufp += sizeof(struct elfhdr);
+	offset += sizeof(struct elfhdr);
+	memcpy(elf->e_ident, ELFMAG, SELFMAG);
+	elf->e_ident[EI_CLASS]	= ELF_CLASS;
+	elf->e_ident[EI_DATA]	= ELF_DATA;
+	elf->e_ident[EI_VERSION]= EV_CURRENT;
+	elf->e_ident[EI_OSABI] = ELF_OSABI;
+	memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+	elf->e_type	= ET_CORE;
+	elf->e_machine	= ELF_ARCH;
+	elf->e_version	= EV_CURRENT;
+	elf->e_entry	= 0;
+	elf->e_phoff	= sizeof(struct elfhdr);
+	elf->e_shoff	= 0;
+	elf->e_flags	= ELF_CORE_EFLAGS;
+	elf->e_ehsize	= sizeof(struct elfhdr);
+	elf->e_phentsize= sizeof(struct elf_phdr);
+	elf->e_phnum	= nphdr;
+	elf->e_shentsize= 0;
+	elf->e_shnum	= 0;
+	elf->e_shstrndx	= 0;
+
+	/* setup ELF PT_NOTE program header */
+	nhdr = (struct elf_phdr *) bufp;
+	bufp += sizeof(struct elf_phdr);
+	offset += sizeof(struct elf_phdr);
+	nhdr->p_type	= PT_NOTE;
+	nhdr->p_offset	= 0;
+	nhdr->p_vaddr	= 0;
+	nhdr->p_paddr	= 0;
+	nhdr->p_filesz	= 0;
+	nhdr->p_memsz	= 0;
+	nhdr->p_flags	= 0;
+	nhdr->p_align	= 0;
+
+	/* setup ELF PT_LOAD program header for every area */
+	list_for_each_entry(m, &kclist_head, list) {
+		phdr = (struct elf_phdr *) bufp;
+		bufp += sizeof(struct elf_phdr);
+		offset += sizeof(struct elf_phdr);
+
+		phdr->p_type	= PT_LOAD;
+		phdr->p_flags	= PF_R|PF_W|PF_X;
+		phdr->p_offset	= kc_vaddr_to_offset(m->addr) + dataoff;
+		phdr->p_vaddr	= (size_t)m->addr;
+		phdr->p_paddr	= 0;
+		phdr->p_filesz	= phdr->p_memsz	= m->size;
+		phdr->p_align	= PAGE_SIZE;
+	}
+
+	/*
+	 * Set up the notes in similar form to SVR4 core dumps made
+	 * with info from their /proc.
+	 */
+	nhdr->p_offset	= offset;
+
+	/* set up the process status */
+	notes[0].name = CORE_STR;
+	notes[0].type = NT_PRSTATUS;
+	notes[0].datasz = sizeof(struct elf_prstatus);
+	notes[0].data = &prstatus;
+
+	memset(&prstatus, 0, sizeof(struct elf_prstatus));
+
+	nhdr->p_filesz	= notesize(&notes[0]);
+	bufp = storenote(&notes[0], bufp);
+
+	/* set up the process info */
+	notes[1].name	= CORE_STR;
+	notes[1].type	= NT_PRPSINFO;
+	notes[1].datasz	= sizeof(struct elf_prpsinfo);
+	notes[1].data	= &prpsinfo;
+
+	memset(&prpsinfo, 0, sizeof(struct elf_prpsinfo));
+	prpsinfo.pr_state	= 0;
+	prpsinfo.pr_sname	= 'R';
+	prpsinfo.pr_zomb	= 0;
+
+	strcpy(prpsinfo.pr_fname, "vmlinux");
+	strlcpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs));
+
+	nhdr->p_filesz	+= notesize(&notes[1]);
+	bufp = storenote(&notes[1], bufp);
+
+	/* set up the task structure */
+	notes[2].name	= CORE_STR;
+	notes[2].type	= NT_TASKSTRUCT;
+	notes[2].datasz	= sizeof(struct task_struct);
+	notes[2].data	= current;
+
+	nhdr->p_filesz	+= notesize(&notes[2]);
+	bufp = storenote(&notes[2], bufp);
+
+} /* end elf_kcore_store_hdr() */
+
+/*****************************************************************************/
+/*
+ * read from the ELF header and then kernel memory
+ */
+static ssize_t
+read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
+{
+	ssize_t acc = 0;
+	size_t size, tsz;
+	size_t elf_buflen;
+	int nphdr;
+	unsigned long start;
+
+	read_lock(&kclist_lock);
+	size = get_kcore_size(&nphdr, &elf_buflen);
+
+	if (buflen == 0 || *fpos >= size) {
+		read_unlock(&kclist_lock);
+		return 0;
+	}
+
+	/* trim buflen to not go beyond EOF */
+	if (buflen > size - *fpos)
+		buflen = size - *fpos;
+
+	/* construct an ELF core header if we'll need some of it */
+	if (*fpos < elf_buflen) {
+		char * elf_buf;
+
+		tsz = elf_buflen - *fpos;
+		if (buflen < tsz)
+			tsz = buflen;
+		elf_buf = kzalloc(elf_buflen, GFP_ATOMIC);
+		if (!elf_buf) {
+			read_unlock(&kclist_lock);
+			return -ENOMEM;
+		}
+		elf_kcore_store_hdr(elf_buf, nphdr, elf_buflen);
+		read_unlock(&kclist_lock);
+		if (copy_to_user(buffer, elf_buf + *fpos, tsz)) {
+			kfree(elf_buf);
+			return -EFAULT;
+		}
+		kfree(elf_buf);
+		buflen -= tsz;
+		*fpos += tsz;
+		buffer += tsz;
+		acc += tsz;
+
+		/* leave now if filled buffer already */
+		if (buflen == 0)
+			return acc;
+	} else
+		read_unlock(&kclist_lock);
+
+	/*
+	 * Check to see if our file offset matches with any of
+	 * the addresses in the elf_phdr on our list.
+	 */
+	start = kc_offset_to_vaddr(*fpos - elf_buflen);
+	if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
+		tsz = buflen;
+		
+	while (buflen) {
+		struct kcore_list *m;
+
+		read_lock(&kclist_lock);
+		list_for_each_entry(m, &kclist_head, list) {
+			if (start >= m->addr && start < (m->addr+m->size))
+				break;
+		}
+		read_unlock(&kclist_lock);
+
+		if (&m->list == &kclist_head) {
+			if (clear_user(buffer, tsz))
+				return -EFAULT;
+		} else if (is_vmalloc_or_module_addr((void *)start)) {
+			char * elf_buf;
+
+			elf_buf = kzalloc(tsz, GFP_KERNEL);
+			if (!elf_buf)
+				return -ENOMEM;
+			vread(elf_buf, (char *)start, tsz);
+			/* we have to zero-fill user buffer even if no read */
+			if (copy_to_user(buffer, elf_buf, tsz)) {
+				kfree(elf_buf);
+				return -EFAULT;
+			}
+			kfree(elf_buf);
+		} else {
+			if (kern_addr_valid(start)) {
+				unsigned long n;
+
+				n = copy_to_user(buffer, (char *)start, tsz);
+				/*
+				 * We cannot distinguish between fault on source
+				 * and fault on destination. When this happens
+				 * we clear too and hope it will trigger the
+				 * EFAULT again.
+				 */
+				if (n) { 
+					if (clear_user(buffer + tsz - n,
+								n))
+						return -EFAULT;
+				}
+			} else {
+				if (clear_user(buffer, tsz))
+					return -EFAULT;
+			}
+		}
+		buflen -= tsz;
+		*fpos += tsz;
+		buffer += tsz;
+		acc += tsz;
+		start += tsz;
+		tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen);
+	}
+
+	return acc;
+}
+
+
+static int open_kcore(struct inode *inode, struct file *filp)
+{
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+	if (kcore_need_update)
+		kcore_update_ram();
+	if (i_size_read(inode) != proc_root_kcore->size) {
+		mutex_lock(&inode->i_mutex);
+		i_size_write(inode, proc_root_kcore->size);
+		mutex_unlock(&inode->i_mutex);
+	}
+	return 0;
+}
+
+
+static const struct file_operations proc_kcore_operations = {
+	.read		= read_kcore,
+	.open		= open_kcore,
+	.llseek		= default_llseek,
+};
+
+/* just remember that we have to update kcore */
+static int __meminit kcore_callback(struct notifier_block *self,
+				    unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		write_lock(&kclist_lock);
+		kcore_need_update = 1;
+		write_unlock(&kclist_lock);
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kcore_callback_nb __meminitdata = {
+	.notifier_call = kcore_callback,
+	.priority = 0,
+};
+
+static struct kcore_list kcore_vmalloc;
+
+#ifdef CONFIG_ARCH_PROC_KCORE_TEXT
+static struct kcore_list kcore_text;
+/*
+ * If defined, special segment is used for mapping kernel text instead of
+ * direct-map area. We need to create special TEXT section.
+ */
+static void __init proc_kcore_text_init(void)
+{
+	kclist_add(&kcore_text, _text, _end - _text, KCORE_TEXT);
+}
+#else
+static void __init proc_kcore_text_init(void)
+{
+}
+#endif
+
+#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
+/*
+ * MODULES_VADDR has no intersection with VMALLOC_ADDR.
+ */
+struct kcore_list kcore_modules;
+static void __init add_modules_range(void)
+{
+	if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
+		kclist_add(&kcore_modules, (void *)MODULES_VADDR,
+			MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
+	}
+}
+#else
+static void __init add_modules_range(void)
+{
+}
+#endif
+
+static int __init proc_kcore_init(void)
+{
+	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL,
+				      &proc_kcore_operations);
+	if (!proc_root_kcore) {
+		pr_err("couldn't create /proc/kcore\n");
+		return 0; /* Always returns 0. */
+	}
+	/* Store text area if it's special */
+	proc_kcore_text_init();
+	/* Store vmalloc area */
+	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
+		VMALLOC_END - VMALLOC_START, KCORE_VMALLOC);
+	add_modules_range();
+	/* Store direct-map area from physical memory map */
+	kcore_update_ram();
+	register_hotmemory_notifier(&kcore_callback_nb);
+
+	return 0;
+}
+fs_initcall(proc_kcore_init);
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
new file mode 100644
index 000000000..05f8dcdb0
--- /dev/null
+++ b/fs/proc/kmsg.c
@@ -0,0 +1,64 @@
+/*
+ *  linux/fs/proc/kmsg.c
+ *
+ *  Copyright (C) 1992  by Linus Torvalds
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/fs.h>
+#include <linux/syslog.h>
+
+#include <asm/uaccess.h>
+#include <asm/io.h>
+
+extern wait_queue_head_t log_wait;
+
+static int kmsg_open(struct inode * inode, struct file * file)
+{
+	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC);
+}
+
+static int kmsg_release(struct inode * inode, struct file * file)
+{
+	(void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC);
+	return 0;
+}
+
+static ssize_t kmsg_read(struct file *file, char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	if ((file->f_flags & O_NONBLOCK) &&
+	    !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
+		return -EAGAIN;
+	return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC);
+}
+
+static unsigned int kmsg_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &log_wait, wait);
+	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
+
+static const struct file_operations proc_kmsg_operations = {
+	.read		= kmsg_read,
+	.poll		= kmsg_poll,
+	.open		= kmsg_open,
+	.release	= kmsg_release,
+	.llseek		= generic_file_llseek,
+};
+
+static int __init proc_kmsg_init(void)
+{
+	proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
+	return 0;
+}
+fs_initcall(proc_kmsg_init);
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
new file mode 100644
index 000000000..aec66e6c2
--- /dev/null
+++ b/fs/proc/loadavg.c
@@ -0,0 +1,45 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/pid_namespace.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/seqlock.h>
+#include <linux/time.h>
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+
+static int loadavg_proc_show(struct seq_file *m, void *v)
+{
+	unsigned long avnrun[3];
+
+	get_avenrun(avnrun, FIXED_1/200, 0);
+
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
+		nr_running(), nr_threads,
+		task_active_pid_ns(current)->last_pid);
+	return 0;
+}
+
+static int loadavg_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, loadavg_proc_show, NULL);
+}
+
+static const struct file_operations loadavg_proc_fops = {
+	.open		= loadavg_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_loadavg_init(void)
+{
+	proc_create("loadavg", 0, NULL, &loadavg_proc_fops);
+	return 0;
+}
+fs_initcall(proc_loadavg_init);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
new file mode 100644
index 000000000..f151d216c
--- /dev/null
+++ b/fs/proc/meminfo.c
@@ -0,0 +1,240 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/mmzone.h>
+#include <linux/proc_fs.h>
+#include <linux/quicklist.h>
+#include <linux/seq_file.h>
+#include <linux/swap.h>
+#include <linux/vmstat.h>
+#include <linux/atomic.h>
+#include <linux/vmalloc.h>
+#ifdef CONFIG_CMA
+#include <linux/cma.h>
+#endif
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include "internal.h"
+
+void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
+{
+}
+
+static int meminfo_proc_show(struct seq_file *m, void *v)
+{
+	struct sysinfo i;
+	unsigned long committed;
+	struct vmalloc_info vmi;
+	long cached;
+	long available;
+	unsigned long pagecache;
+	unsigned long wmark_low = 0;
+	unsigned long pages[NR_LRU_LISTS];
+	struct zone *zone;
+	int lru;
+
+/*
+ * display in kilobytes.
+ */
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+	si_meminfo(&i);
+	si_swapinfo(&i);
+	committed = percpu_counter_read_positive(&vm_committed_as);
+
+	cached = global_page_state(NR_FILE_PAGES) -
+			total_swapcache_pages() - i.bufferram;
+	if (cached < 0)
+		cached = 0;
+
+	get_vmalloc_info(&vmi);
+
+	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+		pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
+	for_each_zone(zone)
+		wmark_low += zone->watermark[WMARK_LOW];
+
+	/*
+	 * Estimate the amount of memory available for userspace allocations,
+	 * without causing swapping.
+	 *
+	 * Free memory cannot be taken below the low watermark, before the
+	 * system starts swapping.
+	 */
+	available = i.freeram - wmark_low;
+
+	/*
+	 * Not all the page cache can be freed, otherwise the system will
+	 * start swapping. Assume at least half of the page cache, or the
+	 * low watermark worth of cache, needs to stay.
+	 */
+	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
+	pagecache -= min(pagecache / 2, wmark_low);
+	available += pagecache;
+
+	/*
+	 * Part of the reclaimable slab consists of items that are in use,
+	 * and cannot be freed. Cap this estimate at the low watermark.
+	 */
+	available += global_page_state(NR_SLAB_RECLAIMABLE) -
+		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+
+	if (available < 0)
+		available = 0;
+
+	/*
+	 * Tagged format, for easy grepping and expansion.
+	 */
+	seq_printf(m,
+		"MemTotal:       %8lu kB\n"
+		"MemFree:        %8lu kB\n"
+		"MemAvailable:   %8lu kB\n"
+		"Buffers:        %8lu kB\n"
+		"Cached:         %8lu kB\n"
+		"SwapCached:     %8lu kB\n"
+		"Active:         %8lu kB\n"
+		"Inactive:       %8lu kB\n"
+		"Active(anon):   %8lu kB\n"
+		"Inactive(anon): %8lu kB\n"
+		"Active(file):   %8lu kB\n"
+		"Inactive(file): %8lu kB\n"
+		"Unevictable:    %8lu kB\n"
+		"Mlocked:        %8lu kB\n"
+#ifdef CONFIG_HIGHMEM
+		"HighTotal:      %8lu kB\n"
+		"HighFree:       %8lu kB\n"
+		"LowTotal:       %8lu kB\n"
+		"LowFree:        %8lu kB\n"
+#endif
+#ifndef CONFIG_MMU
+		"MmapCopy:       %8lu kB\n"
+#endif
+		"SwapTotal:      %8lu kB\n"
+		"SwapFree:       %8lu kB\n"
+		"Dirty:          %8lu kB\n"
+		"Writeback:      %8lu kB\n"
+		"AnonPages:      %8lu kB\n"
+		"Mapped:         %8lu kB\n"
+		"Shmem:          %8lu kB\n"
+		"Slab:           %8lu kB\n"
+		"SReclaimable:   %8lu kB\n"
+		"SUnreclaim:     %8lu kB\n"
+		"KernelStack:    %8lu kB\n"
+		"PageTables:     %8lu kB\n"
+#ifdef CONFIG_UKSM
+		"KsmZeroPages:   %8lu kB\n"
+#endif
+#ifdef CONFIG_QUICKLIST
+		"Quicklists:     %8lu kB\n"
+#endif
+		"NFS_Unstable:   %8lu kB\n"
+		"Bounce:         %8lu kB\n"
+		"WritebackTmp:   %8lu kB\n"
+		"CommitLimit:    %8lu kB\n"
+		"Committed_AS:   %8lu kB\n"
+		"VmallocTotal:   %8lu kB\n"
+		"VmallocUsed:    %8lu kB\n"
+		"VmallocChunk:   %8lu kB\n"
+#ifdef CONFIG_MEMORY_FAILURE
+		"HardwareCorrupted: %5lu kB\n"
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		"AnonHugePages:  %8lu kB\n"
+#endif
+#ifdef CONFIG_CMA
+		"CmaTotal:       %8lu kB\n"
+		"CmaFree:        %8lu kB\n"
+#endif
+		,
+		K(i.totalram),
+		K(i.freeram),
+		K(available),
+		K(i.bufferram),
+		K(cached),
+		K(total_swapcache_pages()),
+		K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+		K(pages[LRU_ACTIVE_ANON]),
+		K(pages[LRU_INACTIVE_ANON]),
+		K(pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_FILE]),
+		K(pages[LRU_UNEVICTABLE]),
+		K(global_page_state(NR_MLOCK)),
+#ifdef CONFIG_HIGHMEM
+		K(i.totalhigh),
+		K(i.freehigh),
+		K(i.totalram-i.totalhigh),
+		K(i.freeram-i.freehigh),
+#endif
+#ifndef CONFIG_MMU
+		K((unsigned long) atomic_long_read(&mmap_pages_allocated)),
+#endif
+		K(i.totalswap),
+		K(i.freeswap),
+		K(global_page_state(NR_FILE_DIRTY)),
+		K(global_page_state(NR_WRITEBACK)),
+		K(global_page_state(NR_ANON_PAGES)),
+		K(global_page_state(NR_FILE_MAPPED)),
+		K(i.sharedram),
+		K(global_page_state(NR_SLAB_RECLAIMABLE) +
+				global_page_state(NR_SLAB_UNRECLAIMABLE)),
+		K(global_page_state(NR_SLAB_RECLAIMABLE)),
+		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+		global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
+		K(global_page_state(NR_PAGETABLE)),
+#ifdef CONFIG_UKSM
+		K(global_page_state(NR_UKSM_ZERO_PAGES)),
+#endif
+#ifdef CONFIG_QUICKLIST
+		K(quicklist_total_size()),
+#endif
+		K(global_page_state(NR_UNSTABLE_NFS)),
+		K(global_page_state(NR_BOUNCE)),
+		K(global_page_state(NR_WRITEBACK_TEMP)),
+		K(vm_commit_limit()),
+		K(committed),
+		(unsigned long)VMALLOC_TOTAL >> 10,
+		vmi.used >> 10,
+		vmi.largest_chunk >> 10
+#ifdef CONFIG_MEMORY_FAILURE
+		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		, K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+		   HPAGE_PMD_NR)
+#endif
+#ifdef CONFIG_CMA
+		, K(totalcma_pages)
+		, K(global_page_state(NR_FREE_CMA_PAGES))
+#endif
+		);
+
+	hugetlb_report_meminfo(m);
+
+	arch_report_meminfo(m);
+
+	return 0;
+#undef K
+}
+
+static int meminfo_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, meminfo_proc_show, NULL);
+}
+
+static const struct file_operations meminfo_proc_fops = {
+	.open		= meminfo_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_meminfo_init(void)
+{
+	proc_create("meminfo", 0, NULL, &meminfo_proc_fops);
+	return 0;
+}
+fs_initcall(proc_meminfo_init);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
new file mode 100644
index 000000000..e512642db
--- /dev/null
+++ b/fs/proc/namespaces.c
@@ -0,0 +1,172 @@
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/ptrace.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+#ifdef CONFIG_PID_NS
+	&pidns_operations,
+#endif
+#ifdef CONFIG_USER_NS
+	&userns_operations,
+#endif
+	&mntns_operations,
+};
+
+static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct inode *inode = d_inode(dentry);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	struct path ns_path;
+	void *error = ERR_PTR(-EACCES);
+
+	task = get_proc_task(inode);
+	if (!task)
+		return error;
+
+	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+		error = ns_get_path(&ns_path, task, ns_ops);
+		if (!error)
+			nd_jump_link(nd, &ns_path);
+	}
+	put_task_struct(task);
+	return error;
+}
+
+static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	struct inode *inode = d_inode(dentry);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	char name[50];
+	int res = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return res;
+
+	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+		res = ns_get_name(name, sizeof(name), task, ns_ops);
+		if (res >= 0)
+			res = readlink_copy(buffer, buflen, name);
+	}
+	put_task_struct(task);
+	return res;
+}
+
+static const struct inode_operations proc_ns_link_inode_operations = {
+	.readlink	= proc_ns_readlink,
+	.follow_link	= proc_ns_follow_link,
+	.setattr	= proc_setattr,
+};
+
+static int proc_ns_instantiate(struct inode *dir,
+	struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	inode->i_mode = S_IFLNK|S_IRWXUGO;
+	inode->i_op = &proc_ns_link_inode_operations;
+	ei->ns_ops = ns_ops;
+
+	d_set_d_op(dentry, &pid_dentry_operations);
+	d_add(dentry, inode);
+	/* Close the race of the process dying before we return the dentry */
+	if (pid_revalidate(dentry, 0))
+		return 0;
+out:
+	return -ENOENT;
+}
+
+static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct proc_ns_operations **entry, **last;
+
+	if (!task)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
+		goto out;
+	entry = ns_entries + (ctx->pos - 2);
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	while (entry <= last) {
+		const struct proc_ns_operations *ops = *entry;
+		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
+				     proc_ns_instantiate, task, ops))
+			break;
+		ctx->pos++;
+		entry++;
+	}
+out:
+	put_task_struct(task);
+	return 0;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_ns_dir_readdir,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, unsigned int flags)
+{
+	int error;
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations **entry, **last;
+	unsigned int len = dentry->d_name.len;
+
+	error = -ENOENT;
+
+	if (!task)
+		goto out_no_task;
+
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	if (entry == last)
+		goto out;
+
+	error = proc_ns_instantiate(dir, dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return ERR_PTR(error);
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_setattr,
+};
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
new file mode 100644
index 000000000..139718132
--- /dev/null
+++ b/fs/proc/nommu.c
@@ -0,0 +1,137 @@
+/* nommu.c: mmu-less memory info files
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/mman.h>
+#include <linux/proc_fs.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+#include <asm/div64.h>
+#include "internal.h"
+
+/*
+ * display a single region to a sequenced file
+ */
+static int nommu_region_show(struct seq_file *m, struct vm_region *region)
+{
+	unsigned long ino = 0;
+	struct file *file;
+	dev_t dev = 0;
+	int flags;
+
+	flags = region->vm_flags;
+	file = region->vm_file;
+
+	if (file) {
+		struct inode *inode;
+
+		file = vmr_pr_or_file(region);
+		inode = file_inode(file);
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+	}
+
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+		   region->vm_start,
+		   region->vm_end,
+		   flags & VM_READ ? 'r' : '-',
+		   flags & VM_WRITE ? 'w' : '-',
+		   flags & VM_EXEC ? 'x' : '-',
+		   flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
+		   ((loff_t)region->vm_pgoff) << PAGE_SHIFT,
+		   MAJOR(dev), MINOR(dev), ino);
+
+	if (file) {
+		seq_pad(m, ' ');
+		seq_path(m, &file->f_path, "");
+	}
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+/*
+ * display a list of all the REGIONs the kernel knows about
+ * - nommu kernels have a single flat list
+ */
+static int nommu_region_list_show(struct seq_file *m, void *_p)
+{
+	struct rb_node *p = _p;
+
+	return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb));
+}
+
+static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct rb_node *p;
+	loff_t pos = *_pos;
+
+	down_read(&nommu_region_sem);
+
+	for (p = rb_first(&nommu_region_tree); p; p = rb_next(p))
+		if (pos-- == 0)
+			return p;
+	return NULL;
+}
+
+static void nommu_region_list_stop(struct seq_file *m, void *v)
+{
+	up_read(&nommu_region_sem);
+}
+
+static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return rb_next((struct rb_node *) v);
+}
+
+static const struct seq_operations proc_nommu_region_list_seqop = {
+	.start	= nommu_region_list_start,
+	.next	= nommu_region_list_next,
+	.stop	= nommu_region_list_stop,
+	.show	= nommu_region_list_show
+};
+
+static int proc_nommu_region_list_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &proc_nommu_region_list_seqop);
+}
+
+static const struct file_operations proc_nommu_region_list_operations = {
+	.open    = proc_nommu_region_list_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+static int __init proc_nommu_init(void)
+{
+	proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations);
+	return 0;
+}
+
+fs_initcall(proc_nommu_init);
diff --git a/fs/proc/page.c b/fs/proc/page.c
new file mode 100644
index 000000000..7eee2d8b9
--- /dev/null
+++ b/fs/proc/page.c
@@ -0,0 +1,234 @@
+#include <linux/bootmem.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/ksm.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/huge_mm.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.h>
+#include <linux/kernel-page-flags.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+#define KPMSIZE sizeof(u64)
+#define KPMMASK (KPMSIZE - 1)
+
+/* /proc/kpagecount - an array exposing page counts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page count.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	u64 __user *out = (u64 __user *)buf;
+	struct page *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 pcount;
+
+	pfn = src / KPMSIZE;
+	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+
+	while (count > 0) {
+		if (pfn_valid(pfn))
+			ppage = pfn_to_page(pfn);
+		else
+			ppage = NULL;
+		if (!ppage || PageSlab(ppage))
+			pcount = 0;
+		else
+			pcount = page_mapcount(ppage);
+
+		if (put_user(pcount, out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+static const struct file_operations proc_kpagecount_operations = {
+	.llseek = mem_lseek,
+	.read = kpagecount_read,
+};
+
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
+
+static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
+{
+	return ((kflags >> kbit) & 1) << ubit;
+}
+
+u64 stable_page_flags(struct page *page)
+{
+	u64 k;
+	u64 u;
+
+	/*
+	 * pseudo flag: KPF_NOPAGE
+	 * it differentiates a memory hole from a page with no flags
+	 */
+	if (!page)
+		return 1 << KPF_NOPAGE;
+
+	k = page->flags;
+	u = 0;
+
+	/*
+	 * pseudo flags for the well known (anonymous) memory mapped pages
+	 *
+	 * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
+	 * simple test in page_mapped() is not enough.
+	 */
+	if (!PageSlab(page) && page_mapped(page))
+		u |= 1 << KPF_MMAP;
+	if (PageAnon(page))
+		u |= 1 << KPF_ANON;
+	if (PageKsm(page))
+		u |= 1 << KPF_KSM;
+
+	/*
+	 * compound pages: export both head/tail info
+	 * they together define a compound page's start/end pos and order
+	 */
+	if (PageHead(page))
+		u |= 1 << KPF_COMPOUND_HEAD;
+	if (PageTail(page))
+		u |= 1 << KPF_COMPOUND_TAIL;
+	if (PageHuge(page))
+		u |= 1 << KPF_HUGE;
+	/*
+	 * PageTransCompound can be true for non-huge compound pages (slab
+	 * pages or pages allocated by drivers with __GFP_COMP) because it
+	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
+	 * to make sure a given page is a thp, not a non-huge compound page.
+	 */
+	else if (PageTransCompound(page)) {
+		struct page *head = compound_head(page);
+
+		if (PageLRU(head) || PageAnon(head))
+			u |= 1 << KPF_THP;
+		else if (is_huge_zero_page(head)) {
+			u |= 1 << KPF_ZERO_PAGE;
+			u |= 1 << KPF_THP;
+		}
+	} else if (is_zero_pfn(page_to_pfn(page)))
+		u |= 1 << KPF_ZERO_PAGE;
+
+
+	/*
+	 * Caveats on high order pages: page->_count will only be set
+	 * -1 on the head page; SLUB/SLQB do the same for PG_slab;
+	 * SLOB won't set PG_slab at all on compound pages.
+	 */
+	if (PageBuddy(page))
+		u |= 1 << KPF_BUDDY;
+
+	if (PageBalloon(page))
+		u |= 1 << KPF_BALLOON;
+
+	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
+
+	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
+
+	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
+	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
+	u |= kpf_copy_bit(k, KPF_UPTODATE,	PG_uptodate);
+	u |= kpf_copy_bit(k, KPF_WRITEBACK,	PG_writeback);
+
+	u |= kpf_copy_bit(k, KPF_LRU,		PG_lru);
+	u |= kpf_copy_bit(k, KPF_REFERENCED,	PG_referenced);
+	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
+	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);
+
+	u |= kpf_copy_bit(k, KPF_SWAPCACHE,	PG_swapcache);
+	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);
+
+	u |= kpf_copy_bit(k, KPF_UNEVICTABLE,	PG_unevictable);
+	u |= kpf_copy_bit(k, KPF_MLOCKED,	PG_mlocked);
+
+#ifdef CONFIG_MEMORY_FAILURE
+	u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
+#endif
+
+#ifdef CONFIG_ARCH_USES_PG_UNCACHED
+	u |= kpf_copy_bit(k, KPF_UNCACHED,	PG_uncached);
+#endif
+
+	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);
+	u |= kpf_copy_bit(k, KPF_MAPPEDTODISK,	PG_mappedtodisk);
+	u |= kpf_copy_bit(k, KPF_PRIVATE,	PG_private);
+	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
+	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
+	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
+
+	return u;
+};
+
+static ssize_t kpageflags_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	u64 __user *out = (u64 __user *)buf;
+	struct page *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+
+	pfn = src / KPMSIZE;
+	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+
+	while (count > 0) {
+		if (pfn_valid(pfn))
+			ppage = pfn_to_page(pfn);
+		else
+			ppage = NULL;
+
+		if (put_user(stable_page_flags(ppage), out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+static const struct file_operations proc_kpageflags_operations = {
+	.llseek = mem_lseek,
+	.read = kpageflags_read,
+};
+
+static int __init proc_page_init(void)
+{
+	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
+	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
+	return 0;
+}
+fs_initcall(proc_page_init);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
new file mode 100644
index 000000000..350984a19
--- /dev/null
+++ b/fs/proc/proc_net.c
@@ -0,0 +1,233 @@
+/*
+ *  linux/fs/proc/net.c
+ *
+ *  Copyright (C) 2007
+ *
+ *  Author: Eric Biederman <ebiederm@xmission.com>
+ *
+ *  proc net directory handling functions
+ */
+
+#include <asm/uaccess.h>
+
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/mount.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+
+static inline struct net *PDE_NET(struct proc_dir_entry *pde)
+{
+	return pde->parent->data;
+}
+
+static struct net *get_proc_net(const struct inode *inode)
+{
+	return maybe_get_net(PDE_NET(PDE(inode)));
+}
+
+int seq_open_net(struct inode *ino, struct file *f,
+		 const struct seq_operations *ops, int size)
+{
+	struct net *net;
+	struct seq_net_private *p;
+
+	BUG_ON(size < sizeof(*p));
+
+	net = get_proc_net(ino);
+	if (net == NULL)
+		return -ENXIO;
+
+	p = __seq_open_private(f, ops, size);
+	if (p == NULL) {
+		put_net(net);
+		return -ENOMEM;
+	}
+#ifdef CONFIG_NET_NS
+	p->net = net;
+#endif
+	return 0;
+}
+EXPORT_SYMBOL_GPL(seq_open_net);
+
+int single_open_net(struct inode *inode, struct file *file,
+		int (*show)(struct seq_file *, void *))
+{
+	int err;
+	struct net *net;
+
+	err = -ENXIO;
+	net = get_proc_net(inode);
+	if (net == NULL)
+		goto err_net;
+
+	err = single_open(file, show, net);
+	if (err < 0)
+		goto err_open;
+
+	return 0;
+
+err_open:
+	put_net(net);
+err_net:
+	return err;
+}
+EXPORT_SYMBOL_GPL(single_open_net);
+
+int seq_release_net(struct inode *ino, struct file *f)
+{
+	struct seq_file *seq;
+
+	seq = f->private_data;
+
+	put_net(seq_file_net(seq));
+	seq_release_private(ino, f);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(seq_release_net);
+
+int single_release_net(struct inode *ino, struct file *f)
+{
+	struct seq_file *seq = f->private_data;
+	put_net(seq->private);
+	return single_release(ino, f);
+}
+EXPORT_SYMBOL_GPL(single_release_net);
+
+static struct net *get_proc_task_net(struct inode *dir)
+{
+	struct task_struct *task;
+	struct nsproxy *ns;
+	struct net *net = NULL;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(dir), PIDTYPE_PID);
+	if (task != NULL) {
+		task_lock(task);
+		ns = task->nsproxy;
+		if (ns != NULL)
+			net = get_net(ns->net_ns);
+		task_unlock(task);
+	}
+	rcu_read_unlock();
+
+	return net;
+}
+
+static struct dentry *proc_tgid_net_lookup(struct inode *dir,
+		struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *de;
+	struct net *net;
+
+	de = ERR_PTR(-ENOENT);
+	net = get_proc_task_net(dir);
+	if (net != NULL) {
+		de = proc_lookup_de(net->proc_net, dir, dentry);
+		put_net(net);
+	}
+	return de;
+}
+
+static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	struct net *net;
+
+	net = get_proc_task_net(inode);
+
+	generic_fillattr(inode, stat);
+
+	if (net != NULL) {
+		stat->nlink = net->proc_net->nlink;
+		put_net(net);
+	}
+
+	return 0;
+}
+
+const struct inode_operations proc_net_inode_operations = {
+	.lookup		= proc_tgid_net_lookup,
+	.getattr	= proc_tgid_net_getattr,
+};
+
+static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx)
+{
+	int ret;
+	struct net *net;
+
+	ret = -EINVAL;
+	net = get_proc_task_net(file_inode(file));
+	if (net != NULL) {
+		ret = proc_readdir_de(net->proc_net, file, ctx);
+		put_net(net);
+	}
+	return ret;
+}
+
+const struct file_operations proc_net_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate	= proc_tgid_net_readdir,
+};
+
+static __net_init int proc_net_ns_init(struct net *net)
+{
+	struct proc_dir_entry *netd, *net_statd;
+	int err;
+
+	err = -ENOMEM;
+	netd = kzalloc(sizeof(*netd) + 4, GFP_KERNEL);
+	if (!netd)
+		goto out;
+
+	netd->subdir = RB_ROOT;
+	netd->data = net;
+	netd->nlink = 2;
+	netd->namelen = 3;
+	netd->parent = &proc_root;
+	memcpy(netd->name, "net", 4);
+
+	err = -EEXIST;
+	net_statd = proc_net_mkdir(net, "stat", netd);
+	if (!net_statd)
+		goto free_net;
+
+	net->proc_net = netd;
+	net->proc_net_stat = net_statd;
+	return 0;
+
+free_net:
+	kfree(netd);
+out:
+	return err;
+}
+
+static __net_exit void proc_net_ns_exit(struct net *net)
+{
+	remove_proc_entry("stat", net->proc_net);
+	kfree(net->proc_net);
+}
+
+static struct pernet_operations __net_initdata proc_net_ns_ops = {
+	.init = proc_net_ns_init,
+	.exit = proc_net_ns_exit,
+};
+
+int __init proc_net_init(void)
+{
+	proc_symlink("net", NULL, "self/net");
+
+	return register_pernet_subsys(&proc_net_ns_ops);
+}
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
new file mode 100644
index 000000000..fdda62e61
--- /dev/null
+++ b/fs/proc/proc_sysctl.c
@@ -0,0 +1,1619 @@
+/*
+ * /proc/sys support
+ */
+#include <linux/init.h>
+#include <linux/sysctl.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/printk.h>
+#include <linux/security.h>
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include "internal.h"
+
+static const struct dentry_operations proc_sys_dentry_operations;
+static const struct file_operations proc_sys_file_operations;
+static const struct inode_operations proc_sys_inode_operations;
+static const struct file_operations proc_sys_dir_file_operations;
+static const struct inode_operations proc_sys_dir_operations;
+
+/* Support for permanently empty directories */
+
+struct ctl_table sysctl_mount_point[] = {
+	{ }
+};
+
+static bool is_empty_dir(struct ctl_table_header *head)
+{
+	return head->ctl_table[0].child == sysctl_mount_point;
+}
+
+static void set_empty_dir(struct ctl_dir *dir)
+{
+	dir->header.ctl_table[0].child = sysctl_mount_point;
+}
+
+static void clear_empty_dir(struct ctl_dir *dir)
+
+{
+	dir->header.ctl_table[0].child = NULL;
+}
+
+void proc_sys_poll_notify(struct ctl_table_poll *poll)
+{
+	if (!poll)
+		return;
+
+	atomic_inc(&poll->event);
+	wake_up_interruptible(&poll->wait);
+}
+
+static struct ctl_table root_table[] = {
+	{
+		.procname = "",
+		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
+	},
+	{ }
+};
+static struct ctl_table_root sysctl_table_root = {
+	.default_set.dir.header = {
+		{{.count = 1,
+		  .nreg = 1,
+		  .ctl_table = root_table }},
+		.ctl_table_arg = root_table,
+		.root = &sysctl_table_root,
+		.set = &sysctl_table_root.default_set,
+	},
+};
+
+static DEFINE_SPINLOCK(sysctl_lock);
+
+static void drop_sysctl_table(struct ctl_table_header *header);
+static int sysctl_follow_link(struct ctl_table_header **phead,
+	struct ctl_table **pentry, struct nsproxy *namespaces);
+static int insert_links(struct ctl_table_header *head);
+static void put_links(struct ctl_table_header *header);
+
+static void sysctl_print_dir(struct ctl_dir *dir)
+{
+	if (dir->header.parent)
+		sysctl_print_dir(dir->header.parent);
+	pr_cont("%s/", dir->header.ctl_table[0].procname);
+}
+
+static int namecmp(const char *name1, int len1, const char *name2, int len2)
+{
+	int minlen;
+	int cmp;
+
+	minlen = len1;
+	if (minlen > len2)
+		minlen = len2;
+
+	cmp = memcmp(name1, name2, minlen);
+	if (cmp == 0)
+		cmp = len1 - len2;
+	return cmp;
+}
+
+/* Called under sysctl_lock */
+static struct ctl_table *find_entry(struct ctl_table_header **phead,
+	struct ctl_dir *dir, const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+	struct rb_node *node = dir->root.rb_node;
+
+	while (node)
+	{
+		struct ctl_node *ctl_node;
+		const char *procname;
+		int cmp;
+
+		ctl_node = rb_entry(node, struct ctl_node, node);
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+		procname = entry->procname;
+
+		cmp = namecmp(name, namelen, procname, strlen(procname));
+		if (cmp < 0)
+			node = node->rb_left;
+		else if (cmp > 0)
+			node = node->rb_right;
+		else {
+			*phead = head;
+			return entry;
+		}
+	}
+	return NULL;
+}
+
+static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+	struct rb_node *node = &head->node[entry - head->ctl_table].node;
+	struct rb_node **p = &head->parent->root.rb_node;
+	struct rb_node *parent = NULL;
+	const char *name = entry->procname;
+	int namelen = strlen(name);
+
+	while (*p) {
+		struct ctl_table_header *parent_head;
+		struct ctl_table *parent_entry;
+		struct ctl_node *parent_node;
+		const char *parent_name;
+		int cmp;
+
+		parent = *p;
+		parent_node = rb_entry(parent, struct ctl_node, node);
+		parent_head = parent_node->header;
+		parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
+		parent_name = parent_entry->procname;
+
+		cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else if (cmp > 0)
+			p = &(*p)->rb_right;
+		else {
+			pr_err("sysctl duplicate entry: ");
+			sysctl_print_dir(head->parent);
+			pr_cont("/%s\n", entry->procname);
+			return -EEXIST;
+		}
+	}
+
+	rb_link_node(node, parent, p);
+	rb_insert_color(node, &head->parent->root);
+	return 0;
+}
+
+static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+	struct rb_node *node = &head->node[entry - head->ctl_table].node;
+
+	rb_erase(node, &head->parent->root);
+}
+
+static void init_header(struct ctl_table_header *head,
+	struct ctl_table_root *root, struct ctl_table_set *set,
+	struct ctl_node *node, struct ctl_table *table)
+{
+	head->ctl_table = table;
+	head->ctl_table_arg = table;
+	head->used = 0;
+	head->count = 1;
+	head->nreg = 1;
+	head->unregistering = NULL;
+	head->root = root;
+	head->set = set;
+	head->parent = NULL;
+	head->node = node;
+	if (node) {
+		struct ctl_table *entry;
+		for (entry = table; entry->procname; entry++, node++)
+			node->header = head;
+	}
+}
+
+static void erase_header(struct ctl_table_header *head)
+{
+	struct ctl_table *entry;
+	for (entry = head->ctl_table; entry->procname; entry++)
+		erase_entry(head, entry);
+}
+
+static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
+{
+	struct ctl_table *entry;
+	int err;
+
+	/* Is this a permanently empty directory? */
+	if (is_empty_dir(&dir->header))
+		return -EROFS;
+
+	/* Am I creating a permanently empty directory? */
+	if (header->ctl_table == sysctl_mount_point) {
+		if (!RB_EMPTY_ROOT(&dir->root))
+			return -EINVAL;
+		set_empty_dir(dir);
+	}
+
+	dir->header.nreg++;
+	header->parent = dir;
+	err = insert_links(header);
+	if (err)
+		goto fail_links;
+	for (entry = header->ctl_table; entry->procname; entry++) {
+		err = insert_entry(header, entry);
+		if (err)
+			goto fail;
+	}
+	return 0;
+fail:
+	erase_header(header);
+	put_links(header);
+fail_links:
+	if (header->ctl_table == sysctl_mount_point)
+		clear_empty_dir(dir);
+	header->parent = NULL;
+	drop_sysctl_table(&dir->header);
+	return err;
+}
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+	if (unlikely(p->unregistering))
+		return 0;
+	p->used++;
+	return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+	if (!--p->used)
+		if (unlikely(p->unregistering))
+			complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+	/*
+	 * if p->used is 0, nobody will ever touch that entry again;
+	 * we'll eliminate all paths to it before dropping sysctl_lock
+	 */
+	if (unlikely(p->used)) {
+		struct completion wait;
+		init_completion(&wait);
+		p->unregistering = &wait;
+		spin_unlock(&sysctl_lock);
+		wait_for_completion(&wait);
+		spin_lock(&sysctl_lock);
+	} else {
+		/* anything non-NULL; we'll never dereference it */
+		p->unregistering = ERR_PTR(-EINVAL);
+	}
+	/*
+	 * do not remove from the list until nobody holds it; walking the
+	 * list in do_sysctl() relies on that.
+	 */
+	erase_header(p);
+}
+
+static void sysctl_head_get(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	head->count++;
+	spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	if (!--head->count)
+		kfree_rcu(head, rcu);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+	BUG_ON(!head);
+	spin_lock(&sysctl_lock);
+	if (!use_table(head))
+		head = ERR_PTR(-ENOENT);
+	spin_unlock(&sysctl_lock);
+	return head;
+}
+
+static void sysctl_head_finish(struct ctl_table_header *head)
+{
+	if (!head)
+		return;
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+	struct ctl_table_set *set = &root->default_set;
+	if (root->lookup)
+		set = root->lookup(root, namespaces);
+	return set;
+}
+
+static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
+				      struct ctl_dir *dir,
+				      const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+
+	spin_lock(&sysctl_lock);
+	entry = find_entry(&head, dir, name, namelen);
+	if (entry && use_table(head))
+		*phead = head;
+	else
+		entry = NULL;
+	spin_unlock(&sysctl_lock);
+	return entry;
+}
+
+static struct ctl_node *first_usable_entry(struct rb_node *node)
+{
+	struct ctl_node *ctl_node;
+
+	for (;node; node = rb_next(node)) {
+		ctl_node = rb_entry(node, struct ctl_node, node);
+		if (use_table(ctl_node->header))
+			return ctl_node;
+	}
+	return NULL;
+}
+
+static void first_entry(struct ctl_dir *dir,
+	struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+	struct ctl_table_header *head = NULL;
+	struct ctl_table *entry = NULL;
+	struct ctl_node *ctl_node;
+
+	spin_lock(&sysctl_lock);
+	ctl_node = first_usable_entry(rb_first(&dir->root));
+	spin_unlock(&sysctl_lock);
+	if (ctl_node) {
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+	}
+	*phead = head;
+	*pentry = entry;
+}
+
+static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+	struct ctl_table_header *head = *phead;
+	struct ctl_table *entry = *pentry;
+	struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
+
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+
+	ctl_node = first_usable_entry(rb_next(&ctl_node->node));
+	spin_unlock(&sysctl_lock);
+	head = NULL;
+	if (ctl_node) {
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+	}
+	*phead = head;
+	*pentry = entry;
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+}
+
+/*
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
+ * some sysctl variables are readonly even to root.
+ */
+
+static int test_perm(int mode, int op)
+{
+	if (uid_eq(current_euid(), GLOBAL_ROOT_UID))
+		mode >>= 6;
+	else if (in_egroup_p(GLOBAL_ROOT_GID))
+		mode >>= 3;
+	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
+		return 0;
+	return -EACCES;
+}
+
+static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, int op)
+{
+	struct ctl_table_root *root = head->root;
+	int mode;
+
+	if (root->permissions)
+		mode = root->permissions(head, table);
+	else
+		mode = table->mode;
+
+	return test_perm(mode, op);
+}
+
+static struct inode *proc_sys_make_inode(struct super_block *sb,
+		struct ctl_table_header *head, struct ctl_table *table)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = new_inode(sb);
+	if (!inode)
+		goto out;
+
+	inode->i_ino = get_next_ino();
+
+	sysctl_head_get(head);
+	ei = PROC_I(inode);
+	ei->sysctl = head;
+	ei->sysctl_entry = table;
+
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mode = table->mode;
+	if (!S_ISDIR(table->mode)) {
+		inode->i_mode |= S_IFREG;
+		inode->i_op = &proc_sys_inode_operations;
+		inode->i_fop = &proc_sys_file_operations;
+	} else {
+		inode->i_mode |= S_IFDIR;
+		inode->i_op = &proc_sys_dir_operations;
+		inode->i_fop = &proc_sys_dir_file_operations;
+		if (is_empty_dir(head))
+			make_empty_dir_inode(inode);
+	}
+out:
+	return inode;
+}
+
+static struct ctl_table_header *grab_header(struct inode *inode)
+{
+	struct ctl_table_header *head = PROC_I(inode)->sysctl;
+	if (!head)
+		head = &sysctl_table_root.default_set.dir.header;
+	return sysctl_head_grab(head);
+}
+
+static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
+					unsigned int flags)
+{
+	struct ctl_table_header *head = grab_header(dir);
+	struct ctl_table_header *h = NULL;
+	struct qstr *name = &dentry->d_name;
+	struct ctl_table *p;
+	struct inode *inode;
+	struct dentry *err = ERR_PTR(-ENOENT);
+	struct ctl_dir *ctl_dir;
+	int ret;
+
+	if (IS_ERR(head))
+		return ERR_CAST(head);
+
+	ctl_dir = container_of(head, struct ctl_dir, header);
+
+	p = lookup_entry(&h, ctl_dir, name->name, name->len);
+	if (!p)
+		goto out;
+
+	if (S_ISLNK(p->mode)) {
+		ret = sysctl_follow_link(&h, &p, current->nsproxy);
+		err = ERR_PTR(ret);
+		if (ret)
+			goto out;
+	}
+
+	err = ERR_PTR(-ENOMEM);
+	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
+	if (!inode)
+		goto out;
+
+	err = NULL;
+	d_set_d_op(dentry, &proc_sys_dentry_operations);
+	d_add(dentry, inode);
+
+out:
+	if (h)
+		sysctl_head_finish(h);
+	sysctl_head_finish(head);
+	return err;
+}
+
+static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
+		size_t count, loff_t *ppos, int write)
+{
+	struct inode *inode = file_inode(filp);
+	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	ssize_t error;
+	size_t res;
+
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	/*
+	 * At this point we know that the sysctl was not unregistered
+	 * and won't be until we finish.
+	 */
+	error = -EPERM;
+	if (sysctl_perm(head, table, write ? MAY_WRITE : MAY_READ))
+		goto out;
+
+	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
+	error = -EINVAL;
+	if (!table->proc_handler)
+		goto out;
+
+	/* careful: calling conventions are nasty here */
+	res = count;
+	error = table->proc_handler(table, write, buf, &res, ppos);
+	if (!error)
+		error = res;
+out:
+	sysctl_head_finish(head);
+
+	return error;
+}
+
+static ssize_t proc_sys_read(struct file *filp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+}
+
+static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
+}
+
+static int proc_sys_open(struct inode *inode, struct file *filp)
+{
+	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+	/* sysctl was unregistered */
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	if (table->poll)
+		filp->private_data = proc_sys_poll_event(table->poll);
+
+	sysctl_head_finish(head);
+
+	return 0;
+}
+
+static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
+{
+	struct inode *inode = file_inode(filp);
+	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	unsigned int ret = DEFAULT_POLLMASK;
+	unsigned long event;
+
+	/* sysctl was unregistered */
+	if (IS_ERR(head))
+		return POLLERR | POLLHUP;
+
+	if (!table->proc_handler)
+		goto out;
+
+	if (!table->poll)
+		goto out;
+
+	event = (unsigned long)filp->private_data;
+	poll_wait(filp, &table->poll->wait, wait);
+
+	if (event != atomic_read(&table->poll->event)) {
+		filp->private_data = proc_sys_poll_event(table->poll);
+		ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI;
+	}
+
+out:
+	sysctl_head_finish(head);
+
+	return ret;
+}
+
+static bool proc_sys_fill_cache(struct file *file,
+				struct dir_context *ctx,
+				struct ctl_table_header *head,
+				struct ctl_table *table)
+{
+	struct dentry *child, *dir = file->f_path.dentry;
+	struct inode *inode;
+	struct qstr qname;
+	ino_t ino = 0;
+	unsigned type = DT_UNKNOWN;
+
+	qname.name = table->procname;
+	qname.len  = strlen(table->procname);
+	qname.hash = full_name_hash(qname.name, qname.len);
+
+	child = d_lookup(dir, &qname);
+	if (!child) {
+		child = d_alloc(dir, &qname);
+		if (child) {
+			inode = proc_sys_make_inode(dir->d_sb, head, table);
+			if (!inode) {
+				dput(child);
+				return false;
+			} else {
+				d_set_d_op(child, &proc_sys_dentry_operations);
+				d_add(child, inode);
+			}
+		} else {
+			return false;
+		}
+	}
+	inode = d_inode(child);
+	ino  = inode->i_ino;
+	type = inode->i_mode >> 12;
+	dput(child);
+	return dir_emit(ctx, qname.name, qname.len, ino, type);
+}
+
+static bool proc_sys_link_fill_cache(struct file *file,
+				    struct dir_context *ctx,
+				    struct ctl_table_header *head,
+				    struct ctl_table *table)
+{
+	bool ret = true;
+	head = sysctl_head_grab(head);
+
+	if (S_ISLNK(table->mode)) {
+		/* It is not an error if we can not follow the link ignore it */
+		int err = sysctl_follow_link(&head, &table, current->nsproxy);
+		if (err)
+			goto out;
+	}
+
+	ret = proc_sys_fill_cache(file, ctx, head, table);
+out:
+	sysctl_head_finish(head);
+	return ret;
+}
+
+static int scan(struct ctl_table_header *head, struct ctl_table *table,
+		unsigned long *pos, struct file *file,
+		struct dir_context *ctx)
+{
+	bool res;
+
+	if ((*pos)++ < ctx->pos)
+		return true;
+
+	if (unlikely(S_ISLNK(table->mode)))
+		res = proc_sys_link_fill_cache(file, ctx, head, table);
+	else
+		res = proc_sys_fill_cache(file, ctx, head, table);
+
+	if (res)
+		ctx->pos = *pos;
+
+	return res;
+}
+
+static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct ctl_table_header *head = grab_header(file_inode(file));
+	struct ctl_table_header *h = NULL;
+	struct ctl_table *entry;
+	struct ctl_dir *ctl_dir;
+	unsigned long pos;
+
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	ctl_dir = container_of(head, struct ctl_dir, header);
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	pos = 2;
+
+	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
+		if (!scan(h, entry, &pos, file, ctx)) {
+			sysctl_head_finish(h);
+			break;
+		}
+	}
+	sysctl_head_finish(head);
+	return 0;
+}
+
+static int proc_sys_permission(struct inode *inode, int mask)
+{
+	/*
+	 * sysctl entries that are not writeable,
+	 * are _NOT_ writeable, capabilities or not.
+	 */
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	int error;
+
+	/* Executable files are not allowed under /proc/sys/ */
+	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
+		return -EACCES;
+
+	head = grab_header(inode);
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	table = PROC_I(inode)->sysctl_entry;
+	if (!table) /* global root - r-xr-xr-x */
+		error = mask & MAY_WRITE ? -EACCES : 0;
+	else /* Use the permissions on the sysctl table entry */
+		error = sysctl_perm(head, table, mask & ~MAY_NOT_BLOCK);
+
+	sysctl_head_finish(head);
+	return error;
+}
+
+static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = d_inode(dentry);
+	int error;
+
+	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+		return -EPERM;
+
+	error = inode_change_ok(inode, attr);
+	if (error)
+		return error;
+
+	setattr_copy(inode, attr);
+	mark_inode_dirty(inode);
+	return 0;
+}
+
+static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	generic_fillattr(inode, stat);
+	if (table)
+		stat->mode = (stat->mode & S_IFMT) | table->mode;
+
+	sysctl_head_finish(head);
+	return 0;
+}
+
+static const struct file_operations proc_sys_file_operations = {
+	.open		= proc_sys_open,
+	.poll		= proc_sys_poll,
+	.read		= proc_sys_read,
+	.write		= proc_sys_write,
+	.llseek		= default_llseek,
+};
+
+static const struct file_operations proc_sys_dir_file_operations = {
+	.read		= generic_read_dir,
+	.iterate	= proc_sys_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+static const struct inode_operations proc_sys_inode_operations = {
+	.permission	= proc_sys_permission,
+	.setattr	= proc_sys_setattr,
+	.getattr	= proc_sys_getattr,
+};
+
+static const struct inode_operations proc_sys_dir_operations = {
+	.lookup		= proc_sys_lookup,
+	.permission	= proc_sys_permission,
+	.setattr	= proc_sys_setattr,
+	.getattr	= proc_sys_getattr,
+};
+
+static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+	return !PROC_I(d_inode(dentry))->sysctl->unregistering;
+}
+
+static int proc_sys_delete(const struct dentry *dentry)
+{
+	return !!PROC_I(d_inode(dentry))->sysctl->unregistering;
+}
+
+static int sysctl_is_seen(struct ctl_table_header *p)
+{
+	struct ctl_table_set *set = p->set;
+	int res;
+	spin_lock(&sysctl_lock);
+	if (p->unregistering)
+		res = 0;
+	else if (!set->is_seen)
+		res = 1;
+	else
+		res = set->is_seen(set);
+	spin_unlock(&sysctl_lock);
+	return res;
+}
+
+static int proc_sys_compare(const struct dentry *parent, const struct dentry *dentry,
+		unsigned int len, const char *str, const struct qstr *name)
+{
+	struct ctl_table_header *head;
+	struct inode *inode;
+
+	/* Although proc doesn't have negative dentries, rcu-walk means
+	 * that inode here can be NULL */
+	/* AV: can it, indeed? */
+	inode = d_inode_rcu(dentry);
+	if (!inode)
+		return 1;
+	if (name->len != len)
+		return 1;
+	if (memcmp(name->name, str, len))
+		return 1;
+	head = rcu_dereference(PROC_I(inode)->sysctl);
+	return !head || !sysctl_is_seen(head);
+}
+
+static const struct dentry_operations proc_sys_dentry_operations = {
+	.d_revalidate	= proc_sys_revalidate,
+	.d_delete	= proc_sys_delete,
+	.d_compare	= proc_sys_compare,
+};
+
+static struct ctl_dir *find_subdir(struct ctl_dir *dir,
+				   const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+
+	entry = find_entry(&head, dir, name, namelen);
+	if (!entry)
+		return ERR_PTR(-ENOENT);
+	if (!S_ISDIR(entry->mode))
+		return ERR_PTR(-ENOTDIR);
+	return container_of(head, struct ctl_dir, header);
+}
+
+static struct ctl_dir *new_dir(struct ctl_table_set *set,
+			       const char *name, int namelen)
+{
+	struct ctl_table *table;
+	struct ctl_dir *new;
+	struct ctl_node *node;
+	char *new_name;
+
+	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
+		      sizeof(struct ctl_table)*2 +  namelen + 1,
+		      GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	node = (struct ctl_node *)(new + 1);
+	table = (struct ctl_table *)(node + 1);
+	new_name = (char *)(table + 2);
+	memcpy(new_name, name, namelen);
+	new_name[namelen] = '\0';
+	table[0].procname = new_name;
+	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
+	init_header(&new->header, set->dir.header.root, set, node, table);
+
+	return new;
+}
+
+/**
+ * get_subdir - find or create a subdir with the specified name.
+ * @dir:  Directory to create the subdirectory in
+ * @name: The name of the subdirectory to find or create
+ * @namelen: The length of name
+ *
+ * Takes a directory with an elevated reference count so we know that
+ * if we drop the lock the directory will not go away.  Upon success
+ * the reference is moved from @dir to the returned subdirectory.
+ * Upon error an error code is returned and the reference on @dir is
+ * simply dropped.
+ */
+static struct ctl_dir *get_subdir(struct ctl_dir *dir,
+				  const char *name, int namelen)
+{
+	struct ctl_table_set *set = dir->header.set;
+	struct ctl_dir *subdir, *new = NULL;
+	int err;
+
+	spin_lock(&sysctl_lock);
+	subdir = find_subdir(dir, name, namelen);
+	if (!IS_ERR(subdir))
+		goto found;
+	if (PTR_ERR(subdir) != -ENOENT)
+		goto failed;
+
+	spin_unlock(&sysctl_lock);
+	new = new_dir(set, name, namelen);
+	spin_lock(&sysctl_lock);
+	subdir = ERR_PTR(-ENOMEM);
+	if (!new)
+		goto failed;
+
+	/* Was the subdir added while we dropped the lock? */
+	subdir = find_subdir(dir, name, namelen);
+	if (!IS_ERR(subdir))
+		goto found;
+	if (PTR_ERR(subdir) != -ENOENT)
+		goto failed;
+
+	/* Nope.  Use the our freshly made directory entry. */
+	err = insert_header(dir, &new->header);
+	subdir = ERR_PTR(err);
+	if (err)
+		goto failed;
+	subdir = new;
+found:
+	subdir->header.nreg++;
+failed:
+	if (unlikely(IS_ERR(subdir))) {
+		pr_err("sysctl could not get directory: ");
+		sysctl_print_dir(dir);
+		pr_cont("/%*.*s %ld\n",
+			namelen, namelen, name, PTR_ERR(subdir));
+	}
+	drop_sysctl_table(&dir->header);
+	if (new)
+		drop_sysctl_table(&new->header);
+	spin_unlock(&sysctl_lock);
+	return subdir;
+}
+
+static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
+{
+	struct ctl_dir *parent;
+	const char *procname;
+	if (!dir->header.parent)
+		return &set->dir;
+	parent = xlate_dir(set, dir->header.parent);
+	if (IS_ERR(parent))
+		return parent;
+	procname = dir->header.ctl_table[0].procname;
+	return find_subdir(parent, procname, strlen(procname));
+}
+
+static int sysctl_follow_link(struct ctl_table_header **phead,
+	struct ctl_table **pentry, struct nsproxy *namespaces)
+{
+	struct ctl_table_header *head;
+	struct ctl_table_root *root;
+	struct ctl_table_set *set;
+	struct ctl_table *entry;
+	struct ctl_dir *dir;
+	int ret;
+
+	ret = 0;
+	spin_lock(&sysctl_lock);
+	root = (*pentry)->data;
+	set = lookup_header_set(root, namespaces);
+	dir = xlate_dir(set, (*phead)->parent);
+	if (IS_ERR(dir))
+		ret = PTR_ERR(dir);
+	else {
+		const char *procname = (*pentry)->procname;
+		head = NULL;
+		entry = find_entry(&head, dir, procname, strlen(procname));
+		ret = -ENOENT;
+		if (entry && use_table(head)) {
+			unuse_table(*phead);
+			*phead = head;
+			*pentry = entry;
+			ret = 0;
+		}
+	}
+
+	spin_unlock(&sysctl_lock);
+	return ret;
+}
+
+static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_err("sysctl table check failed: %s/%s %pV\n",
+	       path, table->procname, &vaf);
+
+	va_end(args);
+	return -EINVAL;
+}
+
+static int sysctl_check_table(const char *path, struct ctl_table *table)
+{
+	int err = 0;
+	for (; table->procname; table++) {
+		if (table->child)
+			err = sysctl_err(path, table, "Not a file");
+
+		if ((table->proc_handler == proc_dostring) ||
+		    (table->proc_handler == proc_dointvec) ||
+		    (table->proc_handler == proc_dointvec_minmax) ||
+		    (table->proc_handler == proc_dointvec_jiffies) ||
+		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
+		    (table->proc_handler == proc_dointvec_ms_jiffies) ||
+		    (table->proc_handler == proc_doulongvec_minmax) ||
+		    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
+			if (!table->data)
+				err = sysctl_err(path, table, "No data");
+			if (!table->maxlen)
+				err = sysctl_err(path, table, "No maxlen");
+		}
+		if (!table->proc_handler)
+			err = sysctl_err(path, table, "No proc_handler");
+
+		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
+			err = sysctl_err(path, table, "bogus .mode 0%o",
+				table->mode);
+	}
+	return err;
+}
+
+static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table,
+	struct ctl_table_root *link_root)
+{
+	struct ctl_table *link_table, *entry, *link;
+	struct ctl_table_header *links;
+	struct ctl_node *node;
+	char *link_name;
+	int nr_entries, name_bytes;
+
+	name_bytes = 0;
+	nr_entries = 0;
+	for (entry = table; entry->procname; entry++) {
+		nr_entries++;
+		name_bytes += strlen(entry->procname) + 1;
+	}
+
+	links = kzalloc(sizeof(struct ctl_table_header) +
+			sizeof(struct ctl_node)*nr_entries +
+			sizeof(struct ctl_table)*(nr_entries + 1) +
+			name_bytes,
+			GFP_KERNEL);
+
+	if (!links)
+		return NULL;
+
+	node = (struct ctl_node *)(links + 1);
+	link_table = (struct ctl_table *)(node + nr_entries);
+	link_name = (char *)&link_table[nr_entries + 1];
+
+	for (link = link_table, entry = table; entry->procname; link++, entry++) {
+		int len = strlen(entry->procname) + 1;
+		memcpy(link_name, entry->procname, len);
+		link->procname = link_name;
+		link->mode = S_IFLNK|S_IRWXUGO;
+		link->data = link_root;
+		link_name += len;
+	}
+	init_header(links, dir->header.root, dir->header.set, node, link_table);
+	links->nreg = nr_entries;
+
+	return links;
+}
+
+static bool get_links(struct ctl_dir *dir,
+	struct ctl_table *table, struct ctl_table_root *link_root)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry, *link;
+
+	/* Are there links available for every entry in table? */
+	for (entry = table; entry->procname; entry++) {
+		const char *procname = entry->procname;
+		link = find_entry(&head, dir, procname, strlen(procname));
+		if (!link)
+			return false;
+		if (S_ISDIR(link->mode) && S_ISDIR(entry->mode))
+			continue;
+		if (S_ISLNK(link->mode) && (link->data == link_root))
+			continue;
+		return false;
+	}
+
+	/* The checks passed.  Increase the registration count on the links */
+	for (entry = table; entry->procname; entry++) {
+		const char *procname = entry->procname;
+		link = find_entry(&head, dir, procname, strlen(procname));
+		head->nreg++;
+	}
+	return true;
+}
+
+static int insert_links(struct ctl_table_header *head)
+{
+	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+	struct ctl_dir *core_parent = NULL;
+	struct ctl_table_header *links;
+	int err;
+
+	if (head->set == root_set)
+		return 0;
+
+	core_parent = xlate_dir(root_set, head->parent);
+	if (IS_ERR(core_parent))
+		return 0;
+
+	if (get_links(core_parent, head->ctl_table, head->root))
+		return 0;
+
+	core_parent->header.nreg++;
+	spin_unlock(&sysctl_lock);
+
+	links = new_links(core_parent, head->ctl_table, head->root);
+
+	spin_lock(&sysctl_lock);
+	err = -ENOMEM;
+	if (!links)
+		goto out;
+
+	err = 0;
+	if (get_links(core_parent, head->ctl_table, head->root)) {
+		kfree(links);
+		goto out;
+	}
+
+	err = insert_header(core_parent, links);
+	if (err)
+		kfree(links);
+out:
+	drop_sysctl_table(&core_parent->header);
+	return err;
+}
+
+/**
+ * __register_sysctl_table - register a leaf sysctl table
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * The members of the &struct ctl_table structure are used as follows:
+ *
+ * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
+ *            enter a sysctl file
+ *
+ * data - a pointer to data for use by proc_handler
+ *
+ * maxlen - the maximum size in bytes of the data
+ *
+ * mode - the file permissions for the /proc/sys file
+ *
+ * child - must be %NULL.
+ *
+ * proc_handler - the text handler routine (described below)
+ *
+ * extra1, extra2 - extra pointers usable by the proc handler routines
+ *
+ * Leaf nodes in the sysctl tree will be represented by a single file
+ * under /proc; non-leaf nodes will be represented by directories.
+ *
+ * There must be a proc_handler routine for any terminal nodes.
+ * Several default handlers are available to cover common cases -
+ *
+ * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
+ * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
+ * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
+ *
+ * It is the handler's job to read the input buffer from user memory
+ * and process it. The handler should return 0 on success.
+ *
+ * This routine returns %NULL on a failure to register, and a pointer
+ * to the table header on success.
+ */
+struct ctl_table_header *__register_sysctl_table(
+	struct ctl_table_set *set,
+	const char *path, struct ctl_table *table)
+{
+	struct ctl_table_root *root = set->dir.header.root;
+	struct ctl_table_header *header;
+	const char *name, *nextname;
+	struct ctl_dir *dir;
+	struct ctl_table *entry;
+	struct ctl_node *node;
+	int nr_entries = 0;
+
+	for (entry = table; entry->procname; entry++)
+		nr_entries++;
+
+	header = kzalloc(sizeof(struct ctl_table_header) +
+			 sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
+	if (!header)
+		return NULL;
+
+	node = (struct ctl_node *)(header + 1);
+	init_header(header, root, set, node, table);
+	if (sysctl_check_table(path, table))
+		goto fail;
+
+	spin_lock(&sysctl_lock);
+	dir = &set->dir;
+	/* Reference moved down the diretory tree get_subdir */
+	dir->header.nreg++;
+	spin_unlock(&sysctl_lock);
+
+	/* Find the directory for the ctl_table */
+	for (name = path; name; name = nextname) {
+		int namelen;
+		nextname = strchr(name, '/');
+		if (nextname) {
+			namelen = nextname - name;
+			nextname++;
+		} else {
+			namelen = strlen(name);
+		}
+		if (namelen == 0)
+			continue;
+
+		dir = get_subdir(dir, name, namelen);
+		if (IS_ERR(dir))
+			goto fail;
+	}
+
+	spin_lock(&sysctl_lock);
+	if (insert_header(dir, header))
+		goto fail_put_dir_locked;
+
+	drop_sysctl_table(&dir->header);
+	spin_unlock(&sysctl_lock);
+
+	return header;
+
+fail_put_dir_locked:
+	drop_sysctl_table(&dir->header);
+	spin_unlock(&sysctl_lock);
+fail:
+	kfree(header);
+	dump_stack();
+	return NULL;
+}
+
+/**
+ * register_sysctl - register a sysctl table
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the table structure
+ *
+ * Register a sysctl table. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table)
+{
+	return __register_sysctl_table(&sysctl_table_root.default_set,
+					path, table);
+}
+EXPORT_SYMBOL(register_sysctl);
+
+static char *append_path(const char *path, char *pos, const char *name)
+{
+	int namelen;
+	namelen = strlen(name);
+	if (((pos - path) + namelen + 2) >= PATH_MAX)
+		return NULL;
+	memcpy(pos, name, namelen);
+	pos[namelen] = '/';
+	pos[namelen + 1] = '\0';
+	pos += namelen + 1;
+	return pos;
+}
+
+static int count_subheaders(struct ctl_table *table)
+{
+	int has_files = 0;
+	int nr_subheaders = 0;
+	struct ctl_table *entry;
+
+	/* special case: no directory and empty directory */
+	if (!table || !table->procname)
+		return 1;
+
+	for (entry = table; entry->procname; entry++) {
+		if (entry->child)
+			nr_subheaders += count_subheaders(entry->child);
+		else
+			has_files = 1;
+	}
+	return nr_subheaders + has_files;
+}
+
+static int register_leaf_sysctl_tables(const char *path, char *pos,
+	struct ctl_table_header ***subheader, struct ctl_table_set *set,
+	struct ctl_table *table)
+{
+	struct ctl_table *ctl_table_arg = NULL;
+	struct ctl_table *entry, *files;
+	int nr_files = 0;
+	int nr_dirs = 0;
+	int err = -ENOMEM;
+
+	for (entry = table; entry->procname; entry++) {
+		if (entry->child)
+			nr_dirs++;
+		else
+			nr_files++;
+	}
+
+	files = table;
+	/* If there are mixed files and directories we need a new table */
+	if (nr_dirs && nr_files) {
+		struct ctl_table *new;
+		files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1),
+				GFP_KERNEL);
+		if (!files)
+			goto out;
+
+		ctl_table_arg = files;
+		for (new = files, entry = table; entry->procname; entry++) {
+			if (entry->child)
+				continue;
+			*new = *entry;
+			new++;
+		}
+	}
+
+	/* Register everything except a directory full of subdirectories */
+	if (nr_files || !nr_dirs) {
+		struct ctl_table_header *header;
+		header = __register_sysctl_table(set, path, files);
+		if (!header) {
+			kfree(ctl_table_arg);
+			goto out;
+		}
+
+		/* Remember if we need to free the file table */
+		header->ctl_table_arg = ctl_table_arg;
+		**subheader = header;
+		(*subheader)++;
+	}
+
+	/* Recurse into the subdirectories. */
+	for (entry = table; entry->procname; entry++) {
+		char *child_pos;
+
+		if (!entry->child)
+			continue;
+
+		err = -ENAMETOOLONG;
+		child_pos = append_path(path, pos, entry->procname);
+		if (!child_pos)
+			goto out;
+
+		err = register_leaf_sysctl_tables(path, child_pos, subheader,
+						  set, entry->child);
+		pos[0] = '\0';
+		if (err)
+			goto out;
+	}
+	err = 0;
+out:
+	/* On failure our caller will unregister all registered subheaders */
+	return err;
+}
+
+/**
+ * __register_sysctl_paths - register a sysctl table hierarchy
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *__register_sysctl_paths(
+	struct ctl_table_set *set,
+	const struct ctl_path *path, struct ctl_table *table)
+{
+	struct ctl_table *ctl_table_arg = table;
+	int nr_subheaders = count_subheaders(table);
+	struct ctl_table_header *header = NULL, **subheaders, **subheader;
+	const struct ctl_path *component;
+	char *new_path, *pos;
+
+	pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!new_path)
+		return NULL;
+
+	pos[0] = '\0';
+	for (component = path; component->procname; component++) {
+		pos = append_path(new_path, pos, component->procname);
+		if (!pos)
+			goto out;
+	}
+	while (table->procname && table->child && !table[1].procname) {
+		pos = append_path(new_path, pos, table->procname);
+		if (!pos)
+			goto out;
+		table = table->child;
+	}
+	if (nr_subheaders == 1) {
+		header = __register_sysctl_table(set, new_path, table);
+		if (header)
+			header->ctl_table_arg = ctl_table_arg;
+	} else {
+		header = kzalloc(sizeof(*header) +
+				 sizeof(*subheaders)*nr_subheaders, GFP_KERNEL);
+		if (!header)
+			goto out;
+
+		subheaders = (struct ctl_table_header **) (header + 1);
+		subheader = subheaders;
+		header->ctl_table_arg = ctl_table_arg;
+
+		if (register_leaf_sysctl_tables(new_path, pos, &subheader,
+						set, table))
+			goto err_register_leaves;
+	}
+
+out:
+	kfree(new_path);
+	return header;
+
+err_register_leaves:
+	while (subheader > subheaders) {
+		struct ctl_table_header *subh = *(--subheader);
+		struct ctl_table *table = subh->ctl_table_arg;
+		unregister_sysctl_table(subh);
+		kfree(table);
+	}
+	kfree(header);
+	header = NULL;
+	goto out;
+}
+
+/**
+ * register_sysctl_table_path - register a sysctl table hierarchy
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+						struct ctl_table *table)
+{
+	return __register_sysctl_paths(&sysctl_table_root.default_set,
+					path, table);
+}
+EXPORT_SYMBOL(register_sysctl_paths);
+
+/**
+ * register_sysctl_table - register a sysctl table hierarchy
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
+{
+	static const struct ctl_path null_path[] = { {} };
+
+	return register_sysctl_paths(null_path, table);
+}
+EXPORT_SYMBOL(register_sysctl_table);
+
+static void put_links(struct ctl_table_header *header)
+{
+	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+	struct ctl_table_root *root = header->root;
+	struct ctl_dir *parent = header->parent;
+	struct ctl_dir *core_parent;
+	struct ctl_table *entry;
+
+	if (header->set == root_set)
+		return;
+
+	core_parent = xlate_dir(root_set, parent);
+	if (IS_ERR(core_parent))
+		return;
+
+	for (entry = header->ctl_table; entry->procname; entry++) {
+		struct ctl_table_header *link_head;
+		struct ctl_table *link;
+		const char *name = entry->procname;
+
+		link = find_entry(&link_head, core_parent, name, strlen(name));
+		if (link &&
+		    ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) ||
+		     (S_ISLNK(link->mode) && (link->data == root)))) {
+			drop_sysctl_table(link_head);
+		}
+		else {
+			pr_err("sysctl link missing during unregister: ");
+			sysctl_print_dir(parent);
+			pr_cont("/%s\n", name);
+		}
+	}
+}
+
+static void drop_sysctl_table(struct ctl_table_header *header)
+{
+	struct ctl_dir *parent = header->parent;
+
+	if (--header->nreg)
+		return;
+
+	put_links(header);
+	start_unregistering(header);
+	if (!--header->count)
+		kfree_rcu(header, rcu);
+
+	if (parent)
+		drop_sysctl_table(&parent->header);
+}
+
+/**
+ * unregister_sysctl_table - unregister a sysctl table hierarchy
+ * @header: the header returned from register_sysctl_table
+ *
+ * Unregisters the sysctl table and all children. proc entries may not
+ * actually be removed until they are no longer used by anyone.
+ */
+void unregister_sysctl_table(struct ctl_table_header * header)
+{
+	int nr_subheaders;
+	might_sleep();
+
+	if (header == NULL)
+		return;
+
+	nr_subheaders = count_subheaders(header->ctl_table_arg);
+	if (unlikely(nr_subheaders > 1)) {
+		struct ctl_table_header **subheaders;
+		int i;
+
+		subheaders = (struct ctl_table_header **)(header + 1);
+		for (i = nr_subheaders -1; i >= 0; i--) {
+			struct ctl_table_header *subh = subheaders[i];
+			struct ctl_table *table = subh->ctl_table_arg;
+			unregister_sysctl_table(subh);
+			kfree(table);
+		}
+		kfree(header);
+		return;
+	}
+
+	spin_lock(&sysctl_lock);
+	drop_sysctl_table(header);
+	spin_unlock(&sysctl_lock);
+}
+EXPORT_SYMBOL(unregister_sysctl_table);
+
+void setup_sysctl_set(struct ctl_table_set *set,
+	struct ctl_table_root *root,
+	int (*is_seen)(struct ctl_table_set *))
+{
+	memset(set, 0, sizeof(*set));
+	set->is_seen = is_seen;
+	init_header(&set->dir.header, root, set, NULL, root_table);
+}
+
+void retire_sysctl_set(struct ctl_table_set *set)
+{
+	WARN_ON(!RB_EMPTY_ROOT(&set->dir.root));
+}
+
+int __init proc_sys_init(void)
+{
+	struct proc_dir_entry *proc_sys_root;
+
+	proc_sys_root = proc_mkdir("sys", NULL);
+	proc_sys_root->proc_iops = &proc_sys_dir_operations;
+	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
+	proc_sys_root->nlink = 0;
+
+	return sysctl_init();
+}
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
new file mode 100644
index 000000000..15f327bed
--- /dev/null
+++ b/fs/proc/proc_tty.c
@@ -0,0 +1,189 @@
+/*
+ * proc_tty.c -- handles /proc/tty
+ *
+ * Copyright 1997, Theodore Ts'o
+ */
+
+#include <asm/uaccess.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/tty.h>
+#include <linux/seq_file.h>
+#include <linux/bitops.h>
+
+/*
+ * The /proc/tty directory inodes...
+ */
+static struct proc_dir_entry *proc_tty_driver;
+
+/*
+ * This is the handler for /proc/tty/drivers
+ */
+static void show_tty_range(struct seq_file *m, struct tty_driver *p,
+	dev_t from, int num)
+{
+	seq_printf(m, "%-20s ", p->driver_name ? p->driver_name : "unknown");
+	seq_printf(m, "/dev/%-8s ", p->name);
+	if (p->num > 1) {
+		seq_printf(m, "%3d %d-%d ", MAJOR(from), MINOR(from),
+			MINOR(from) + num - 1);
+	} else {
+		seq_printf(m, "%3d %7d ", MAJOR(from), MINOR(from));
+	}
+	switch (p->type) {
+	case TTY_DRIVER_TYPE_SYSTEM:
+		seq_puts(m, "system");
+		if (p->subtype == SYSTEM_TYPE_TTY)
+			seq_puts(m, ":/dev/tty");
+		else if (p->subtype == SYSTEM_TYPE_SYSCONS)
+			seq_puts(m, ":console");
+		else if (p->subtype == SYSTEM_TYPE_CONSOLE)
+			seq_puts(m, ":vtmaster");
+		break;
+	case TTY_DRIVER_TYPE_CONSOLE:
+		seq_puts(m, "console");
+		break;
+	case TTY_DRIVER_TYPE_SERIAL:
+		seq_puts(m, "serial");
+		break;
+	case TTY_DRIVER_TYPE_PTY:
+		if (p->subtype == PTY_TYPE_MASTER)
+			seq_puts(m, "pty:master");
+		else if (p->subtype == PTY_TYPE_SLAVE)
+			seq_puts(m, "pty:slave");
+		else
+			seq_puts(m, "pty");
+		break;
+	default:
+		seq_printf(m, "type:%d.%d", p->type, p->subtype);
+	}
+	seq_putc(m, '\n');
+}
+
+static int show_tty_driver(struct seq_file *m, void *v)
+{
+	struct tty_driver *p = list_entry(v, struct tty_driver, tty_drivers);
+	dev_t from = MKDEV(p->major, p->minor_start);
+	dev_t to = from + p->num;
+
+	if (&p->tty_drivers == tty_drivers.next) {
+		/* pseudo-drivers first */
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/tty", "tty");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 0);
+		seq_puts(m, "system:/dev/tty\n");
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/console", "console");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 1);
+		seq_puts(m, "system:console\n");
+#ifdef CONFIG_UNIX98_PTYS
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/ptmx", "ptmx");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 2);
+		seq_puts(m, "system\n");
+#endif
+#ifdef CONFIG_VT
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/vc/0", "vc/0");
+		seq_printf(m, "%3d %7d ", TTY_MAJOR, 0);
+		seq_puts(m, "system:vtmaster\n");
+#endif
+	}
+
+	while (MAJOR(from) < MAJOR(to)) {
+		dev_t next = MKDEV(MAJOR(from)+1, 0);
+		show_tty_range(m, p, from, next - from);
+		from = next;
+	}
+	if (from != to)
+		show_tty_range(m, p, from, to - from);
+	return 0;
+}
+
+/* iterator */
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&tty_mutex);
+	return seq_list_start(&tty_drivers, *pos);
+}
+
+static void *t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &tty_drivers, pos);
+}
+
+static void t_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&tty_mutex);
+}
+
+static const struct seq_operations tty_drivers_op = {
+	.start	= t_start,
+	.next	= t_next,
+	.stop	= t_stop,
+	.show	= show_tty_driver
+};
+
+static int tty_drivers_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &tty_drivers_op);
+}
+
+static const struct file_operations proc_tty_drivers_operations = {
+	.open		= tty_drivers_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * This function is called by tty_register_driver() to handle
+ * registering the driver's /proc handler into /proc/tty/driver/<foo>
+ */
+void proc_tty_register_driver(struct tty_driver *driver)
+{
+	struct proc_dir_entry *ent;
+		
+	if (!driver->driver_name || driver->proc_entry ||
+	    !driver->ops->proc_fops)
+		return;
+
+	ent = proc_create_data(driver->driver_name, 0, proc_tty_driver,
+			       driver->ops->proc_fops, driver);
+	driver->proc_entry = ent;
+}
+
+/*
+ * This function is called by tty_unregister_driver()
+ */
+void proc_tty_unregister_driver(struct tty_driver *driver)
+{
+	struct proc_dir_entry *ent;
+
+	ent = driver->proc_entry;
+	if (!ent)
+		return;
+		
+	remove_proc_entry(driver->driver_name, proc_tty_driver);
+	
+	driver->proc_entry = NULL;
+}
+
+/*
+ * Called by proc_root_init() to initialize the /proc/tty subtree
+ */
+void __init proc_tty_init(void)
+{
+	if (!proc_mkdir("tty", NULL))
+		return;
+	proc_mkdir("tty/ldisc", NULL);	/* Preserved: it's userspace visible */
+	/*
+	 * /proc/tty/driver/serial reveals the exact character counts for
+	 * serial links which is just too easy to abuse for inferring
+	 * password lengths and inter-keystroke timings during password
+	 * entry.
+	 */
+	proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL);
+	proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops);
+	proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations);
+}
diff --git a/fs/proc/root.c b/fs/proc/root.c
new file mode 100644
index 000000000..68feb0f70
--- /dev/null
+++ b/fs/proc/root.c
@@ -0,0 +1,270 @@
+/*
+ *  linux/fs/proc/root.c
+ *
+ *  Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ *  proc root directory handling functions
+ */
+
+#include <asm/uaccess.h>
+
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/user_namespace.h>
+#include <linux/mount.h>
+#include <linux/pid_namespace.h>
+#include <linux/parser.h>
+
+#include "internal.h"
+
+static int proc_test_super(struct super_block *sb, void *data)
+{
+	return sb->s_fs_info == data;
+}
+
+static int proc_set_super(struct super_block *sb, void *data)
+{
+	int err = set_anon_super(sb, NULL);
+	if (!err) {
+		struct pid_namespace *ns = (struct pid_namespace *)data;
+		sb->s_fs_info = get_pid_ns(ns);
+	}
+	return err;
+}
+
+enum {
+	Opt_gid, Opt_hidepid, Opt_err,
+};
+
+static const match_table_t tokens = {
+	{Opt_hidepid, "hidepid=%u"},
+	{Opt_gid, "gid=%u"},
+	{Opt_err, NULL},
+};
+
+static int proc_parse_options(char *options, struct pid_namespace *pid)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+
+	if (!options)
+		return 1;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		if (!*p)
+			continue;
+
+		args[0].to = args[0].from = NULL;
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_gid:
+			if (match_int(&args[0], &option))
+				return 0;
+			pid->pid_gid = make_kgid(current_user_ns(), option);
+			break;
+		case Opt_hidepid:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0 || option > 2) {
+				pr_err("proc: hidepid value must be between 0 and 2.\n");
+				return 0;
+			}
+			pid->hide_pid = option;
+			break;
+		default:
+			pr_err("proc: unrecognized mount option \"%s\" "
+			       "or missing value\n", p);
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
+int proc_remount(struct super_block *sb, int *flags, char *data)
+{
+	struct pid_namespace *pid = sb->s_fs_info;
+
+	sync_filesystem(sb);
+	return !proc_parse_options(data, pid);
+}
+
+static struct dentry *proc_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
+{
+	int err;
+	struct super_block *sb;
+	struct pid_namespace *ns;
+	char *options;
+
+	if (flags & MS_KERNMOUNT) {
+		ns = (struct pid_namespace *)data;
+		options = NULL;
+	} else {
+		ns = task_active_pid_ns(current);
+		options = data;
+
+		/* Does the mounter have privilege over the pid namespace? */
+		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+			return ERR_PTR(-EPERM);
+	}
+
+	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
+	if (IS_ERR(sb))
+		return ERR_CAST(sb);
+
+	if (!proc_parse_options(options, ns)) {
+		deactivate_locked_super(sb);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!sb->s_root) {
+		err = proc_fill_super(sb);
+		if (err) {
+			deactivate_locked_super(sb);
+			return ERR_PTR(err);
+		}
+
+		sb->s_flags |= MS_ACTIVE;
+	}
+
+	return dget(sb->s_root);
+}
+
+static void proc_kill_sb(struct super_block *sb)
+{
+	struct pid_namespace *ns;
+
+	ns = (struct pid_namespace *)sb->s_fs_info;
+	if (ns->proc_self)
+		dput(ns->proc_self);
+	if (ns->proc_thread_self)
+		dput(ns->proc_thread_self);
+	kill_anon_super(sb);
+	put_pid_ns(ns);
+}
+
+static struct file_system_type proc_fs_type = {
+	.name		= "proc",
+	.mount		= proc_mount,
+	.kill_sb	= proc_kill_sb,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
+};
+
+void __init proc_root_init(void)
+{
+	int err;
+
+	proc_init_inodecache();
+	err = register_filesystem(&proc_fs_type);
+	if (err)
+		return;
+
+	proc_self_init();
+	proc_thread_self_init();
+	proc_symlink("mounts", NULL, "self/mounts");
+
+	proc_net_init();
+
+#ifdef CONFIG_SYSVIPC
+	proc_mkdir("sysvipc", NULL);
+#endif
+	proc_mkdir("fs", NULL);
+	proc_mkdir("driver", NULL);
+	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
+#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
+	/* just give it a mountpoint */
+	proc_create_mount_point("openprom");
+#endif
+	proc_tty_init();
+	proc_mkdir("bus", NULL);
+	proc_sys_init();
+}
+
+static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
+)
+{
+	generic_fillattr(d_inode(dentry), stat);
+	stat->nlink = proc_root.nlink + nr_processes();
+	return 0;
+}
+
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
+{
+	if (!proc_pid_lookup(dir, dentry, flags))
+		return NULL;
+	
+	return proc_lookup(dir, dentry, flags);
+}
+
+static int proc_root_readdir(struct file *file, struct dir_context *ctx)
+{
+	if (ctx->pos < FIRST_PROCESS_ENTRY) {
+		int error = proc_readdir(file, ctx);
+		if (unlikely(error <= 0))
+			return error;
+		ctx->pos = FIRST_PROCESS_ENTRY;
+	}
+
+	return proc_pid_readdir(file, ctx);
+}
+
+/*
+ * The root /proc directory is special, as it has the
+ * <pid> directories. Thus we don't use the generic
+ * directory handling functions for that..
+ */
+static const struct file_operations proc_root_operations = {
+	.read		 = generic_read_dir,
+	.iterate	 = proc_root_readdir,
+	.llseek		= default_llseek,
+};
+
+/*
+ * proc root can do almost nothing..
+ */
+static const struct inode_operations proc_root_inode_operations = {
+	.lookup		= proc_root_lookup,
+	.getattr	= proc_root_getattr,
+};
+
+/*
+ * This is the root "inode" in the /proc tree..
+ */
+struct proc_dir_entry proc_root = {
+	.low_ino	= PROC_ROOT_INO, 
+	.namelen	= 5, 
+	.mode		= S_IFDIR | S_IRUGO | S_IXUGO, 
+	.nlink		= 2, 
+	.count		= ATOMIC_INIT(1),
+	.proc_iops	= &proc_root_inode_operations, 
+	.proc_fops	= &proc_root_operations,
+	.parent		= &proc_root,
+	.subdir		= RB_ROOT,
+	.name		= "/proc",
+};
+
+int pid_ns_prepare_proc(struct pid_namespace *ns)
+{
+	struct vfsmount *mnt;
+
+	mnt = kern_mount_data(&proc_fs_type, ns);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	ns->proc_mnt = mnt;
+	return 0;
+}
+
+void pid_ns_release_proc(struct pid_namespace *ns)
+{
+	kern_unmount(ns->proc_mnt);
+}
diff --git a/fs/proc/self.c b/fs/proc/self.c
new file mode 100644
index 000000000..6195b4a7c
--- /dev/null
+++ b/fs/proc/self.c
@@ -0,0 +1,84 @@
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/self:
+ */
+static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
+			      int buflen)
+{
+	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	char tmp[PROC_NUMBUF];
+	if (!tgid)
+		return -ENOENT;
+	sprintf(tmp, "%d", tgid);
+	return readlink_copy(buffer, buflen, tmp);
+}
+
+static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	char *name = ERR_PTR(-ENOENT);
+	if (tgid) {
+		/* 11 for max length of signed int in decimal + NULL term */
+		name = kmalloc(12, GFP_KERNEL);
+		if (!name)
+			name = ERR_PTR(-ENOMEM);
+		else
+			sprintf(name, "%d", tgid);
+	}
+	nd_set_link(nd, name);
+	return NULL;
+}
+
+static const struct inode_operations proc_self_inode_operations = {
+	.readlink	= proc_self_readlink,
+	.follow_link	= proc_self_follow_link,
+	.put_link	= kfree_put_link,
+};
+
+static unsigned self_inum;
+
+int proc_setup_self(struct super_block *s)
+{
+	struct inode *root_inode = d_inode(s->s_root);
+	struct pid_namespace *ns = s->s_fs_info;
+	struct dentry *self;
+	
+	mutex_lock(&root_inode->i_mutex);
+	self = d_alloc_name(s->s_root, "self");
+	if (self) {
+		struct inode *inode = new_inode_pseudo(s);
+		if (inode) {
+			inode->i_ino = self_inum;
+			inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+			inode->i_mode = S_IFLNK | S_IRWXUGO;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+			inode->i_op = &proc_self_inode_operations;
+			d_add(self, inode);
+		} else {
+			dput(self);
+			self = ERR_PTR(-ENOMEM);
+		}
+	} else {
+		self = ERR_PTR(-ENOMEM);
+	}
+	mutex_unlock(&root_inode->i_mutex);
+	if (IS_ERR(self)) {
+		pr_err("proc_fill_super: can't allocate /proc/self\n");
+		return PTR_ERR(self);
+	}
+	ns->proc_self = self;
+	return 0;
+}
+
+void __init proc_self_init(void)
+{
+	proc_alloc_inum(&self_inum);
+}
diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c
new file mode 100644
index 000000000..ad8a77f94
--- /dev/null
+++ b/fs/proc/softirqs.c
@@ -0,0 +1,44 @@
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+/*
+ * /proc/softirqs  ... display the number of softirqs
+ */
+static int show_softirqs(struct seq_file *p, void *v)
+{
+	int i, j;
+
+	seq_puts(p, "                    ");
+	for_each_possible_cpu(i)
+		seq_printf(p, "CPU%-8d", i);
+	seq_putc(p, '\n');
+
+	for (i = 0; i < NR_SOFTIRQS; i++) {
+		seq_printf(p, "%12s:", softirq_to_name[i]);
+		for_each_possible_cpu(j)
+			seq_printf(p, " %10u", kstat_softirqs_cpu(i, j));
+		seq_putc(p, '\n');
+	}
+	return 0;
+}
+
+static int softirqs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_softirqs, NULL);
+}
+
+static const struct file_operations proc_softirqs_operations = {
+	.open		= softirqs_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_softirqs_init(void)
+{
+	proc_create("softirqs", 0, NULL, &proc_softirqs_operations);
+	return 0;
+}
+fs_initcall(proc_softirqs_init);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
new file mode 100644
index 000000000..510413eb2
--- /dev/null
+++ b/fs/proc/stat.c
@@ -0,0 +1,206 @@
+#include <linux/cpumask.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/irqnr.h>
+#include <linux/cputime.h>
+#include <linux/tick.h>
+
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+#ifndef arch_irq_stat
+#define arch_irq_stat() 0
+#endif
+
+#ifdef arch_idle_time
+
+static cputime64_t get_idle_time(int cpu)
+{
+	cputime64_t idle;
+
+	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
+	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
+		idle += arch_idle_time(cpu);
+	return idle;
+}
+
+static cputime64_t get_iowait_time(int cpu)
+{
+	cputime64_t iowait;
+
+	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
+	if (cpu_online(cpu) && nr_iowait_cpu(cpu))
+		iowait += arch_idle_time(cpu);
+	return iowait;
+}
+
+#else
+
+static u64 get_idle_time(int cpu)
+{
+	u64 idle, idle_time = -1ULL;
+
+	if (cpu_online(cpu))
+		idle_time = get_cpu_idle_time_us(cpu, NULL);
+
+	if (idle_time == -1ULL)
+		/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
+		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
+	else
+		idle = usecs_to_cputime64(idle_time);
+
+	return idle;
+}
+
+static u64 get_iowait_time(int cpu)
+{
+	u64 iowait, iowait_time = -1ULL;
+
+	if (cpu_online(cpu))
+		iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+
+	if (iowait_time == -1ULL)
+		/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
+		iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
+	else
+		iowait = usecs_to_cputime64(iowait_time);
+
+	return iowait;
+}
+
+#endif
+
+static int show_stat(struct seq_file *p, void *v)
+{
+	int i, j;
+	unsigned long jif;
+	u64 user, nice, system, idle, iowait, irq, softirq, steal;
+	u64 guest, guest_nice;
+	u64 sum = 0;
+	u64 sum_softirq = 0;
+	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
+	struct timespec boottime;
+
+	user = nice = system = idle = iowait =
+		irq = softirq = steal = 0;
+	guest = guest_nice = 0;
+	getboottime(&boottime);
+	jif = boottime.tv_sec;
+
+	for_each_possible_cpu(i) {
+		user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
+		nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];
+		system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
+		idle += get_idle_time(i);
+		iowait += get_iowait_time(i);
+		irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
+		softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
+		steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
+		guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
+		guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
+		sum += kstat_cpu_irqs_sum(i);
+		sum += arch_irq_stat_cpu(i);
+
+		for (j = 0; j < NR_SOFTIRQS; j++) {
+			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
+
+			per_softirq_sums[j] += softirq_stat;
+			sum_softirq += softirq_stat;
+		}
+	}
+	sum += arch_irq_stat();
+
+	seq_puts(p, "cpu ");
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+	seq_putc(p, '\n');
+
+	for_each_online_cpu(i) {
+		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
+		user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
+		nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];
+		system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
+		idle = get_idle_time(i);
+		iowait = get_iowait_time(i);
+		irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
+		softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
+		steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
+		guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
+		guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
+		seq_printf(p, "cpu%d", i);
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+		seq_putc(p, '\n');
+	}
+	seq_printf(p, "intr %llu", (unsigned long long)sum);
+
+	/* sum again ? it could be updated? */
+	for_each_irq_nr(j)
+		seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j));
+
+	seq_printf(p,
+		"\nctxt %llu\n"
+		"btime %lu\n"
+		"processes %lu\n"
+		"procs_running %lu\n"
+		"procs_blocked %lu\n",
+		nr_context_switches(),
+		(unsigned long)jif,
+		total_forks,
+		nr_running(),
+		nr_iowait());
+
+	seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
+
+	for (i = 0; i < NR_SOFTIRQS; i++)
+		seq_put_decimal_ull(p, ' ', per_softirq_sums[i]);
+	seq_putc(p, '\n');
+
+	return 0;
+}
+
+static int stat_open(struct inode *inode, struct file *file)
+{
+	size_t size = 1024 + 128 * num_online_cpus();
+
+	/* minimum size to display an interrupt count : 2 bytes */
+	size += 2 * nr_irqs;
+	return single_open_size(file, show_stat, NULL, size);
+}
+
+static const struct file_operations proc_stat_operations = {
+	.open		= stat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_stat_init(void)
+{
+	proc_create("stat", 0, NULL, &proc_stat_operations);
+	return 0;
+}
+fs_initcall(proc_stat_init);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
new file mode 100644
index 000000000..9afa35d04
--- /dev/null
+++ b/fs/proc/task_mmu.c
@@ -0,0 +1,1628 @@
+#include <linux/mm.h>
+#include <linux/vmacache.h>
+#include <linux/hugetlb.h>
+#include <linux/huge_mm.h>
+#include <linux/mount.h>
+#include <linux/seq_file.h>
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+#include <linux/mempolicy.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/elf.h>
+#include <asm/uaccess.h>
+#include <asm/tlbflush.h>
+#include "internal.h"
+
+void task_mem(struct seq_file *m, struct mm_struct *mm)
+{
+	unsigned long data, text, lib, swap, ptes, pmds;
+	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
+
+	/*
+	 * Note: to minimize their overhead, mm maintains hiwater_vm and
+	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
+	 * collector of these hiwater stats must therefore get total_vm
+	 * and rss too, which will usually be the higher.  Barriers? not
+	 * worth the effort, such snapshots can always be inconsistent.
+	 */
+	hiwater_vm = total_vm = mm->total_vm;
+	if (hiwater_vm < mm->hiwater_vm)
+		hiwater_vm = mm->hiwater_vm;
+	hiwater_rss = total_rss = get_mm_rss(mm);
+	if (hiwater_rss < mm->hiwater_rss)
+		hiwater_rss = mm->hiwater_rss;
+
+	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
+	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
+	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
+	swap = get_mm_counter(mm, MM_SWAPENTS);
+	ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes);
+	pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);
+	seq_printf(m,
+		"VmPeak:\t%8lu kB\n"
+		"VmSize:\t%8lu kB\n"
+		"VmLck:\t%8lu kB\n"
+		"VmPin:\t%8lu kB\n"
+		"VmHWM:\t%8lu kB\n"
+		"VmRSS:\t%8lu kB\n"
+		"VmData:\t%8lu kB\n"
+		"VmStk:\t%8lu kB\n"
+		"VmExe:\t%8lu kB\n"
+		"VmLib:\t%8lu kB\n"
+		"VmPTE:\t%8lu kB\n"
+		"VmPMD:\t%8lu kB\n"
+		"VmSwap:\t%8lu kB\n",
+		hiwater_vm << (PAGE_SHIFT-10),
+		total_vm << (PAGE_SHIFT-10),
+		mm->locked_vm << (PAGE_SHIFT-10),
+		mm->pinned_vm << (PAGE_SHIFT-10),
+		hiwater_rss << (PAGE_SHIFT-10),
+		total_rss << (PAGE_SHIFT-10),
+		data << (PAGE_SHIFT-10),
+		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
+		ptes >> 10,
+		pmds >> 10,
+		swap << (PAGE_SHIFT-10));
+}
+
+unsigned long task_vsize(struct mm_struct *mm)
+{
+	return PAGE_SIZE * mm->total_vm;
+}
+
+unsigned long task_statm(struct mm_struct *mm,
+			 unsigned long *shared, unsigned long *text,
+			 unsigned long *data, unsigned long *resident)
+{
+	*shared = get_mm_counter(mm, MM_FILEPAGES);
+	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
+								>> PAGE_SHIFT;
+	*data = mm->total_vm - mm->shared_vm;
+	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+	return mm->total_vm;
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * Save get_task_policy() for show_numa_map().
+ */
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+	struct task_struct *task = priv->task;
+
+	task_lock(task);
+	priv->task_mempolicy = get_task_policy(task);
+	mpol_get(priv->task_mempolicy);
+	task_unlock(task);
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+	mpol_put(priv->task_mempolicy);
+}
+#else
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+#endif
+
+static void vma_stop(struct proc_maps_private *priv)
+{
+	struct mm_struct *mm = priv->mm;
+
+	release_task_mempolicy(priv);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+}
+
+static struct vm_area_struct *
+m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma)
+{
+	if (vma == priv->tail_vma)
+		return NULL;
+	return vma->vm_next ?: priv->tail_vma;
+}
+
+static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma)
+{
+	if (m->count < m->size)	/* vma is copied successfully */
+		m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL;
+}
+
+static void *m_start(struct seq_file *m, loff_t *ppos)
+{
+	struct proc_maps_private *priv = m->private;
+	unsigned long last_addr = m->version;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	unsigned int pos = *ppos;
+
+	/* See m_cache_vma(). Zero at the start or after lseek. */
+	if (last_addr == -1UL)
+		return NULL;
+
+	priv->task = get_proc_task(priv->inode);
+	if (!priv->task)
+		return ERR_PTR(-ESRCH);
+
+	mm = priv->mm;
+	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+		return NULL;
+
+	down_read(&mm->mmap_sem);
+	hold_task_mempolicy(priv);
+	priv->tail_vma = get_gate_vma(mm);
+
+	if (last_addr) {
+		vma = find_vma(mm, last_addr);
+		if (vma && (vma = m_next_vma(priv, vma)))
+			return vma;
+	}
+
+	m->version = 0;
+	if (pos < mm->map_count) {
+		for (vma = mm->mmap; pos; pos--) {
+			m->version = vma->vm_start;
+			vma = vma->vm_next;
+		}
+		return vma;
+	}
+
+	/* we do not bother to update m->version in this case */
+	if (pos == mm->map_count && priv->tail_vma)
+		return priv->tail_vma;
+
+	vma_stop(priv);
+	return NULL;
+}
+
+static void *m_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *next;
+
+	(*pos)++;
+	next = m_next_vma(priv, v);
+	if (!next)
+		vma_stop(priv);
+	return next;
+}
+
+static void m_stop(struct seq_file *m, void *v)
+{
+	struct proc_maps_private *priv = m->private;
+
+	if (!IS_ERR_OR_NULL(v))
+		vma_stop(priv);
+	if (priv->task) {
+		put_task_struct(priv->task);
+		priv->task = NULL;
+	}
+}
+
+static int proc_maps_open(struct inode *inode, struct file *file,
+			const struct seq_operations *ops, int psize)
+{
+	struct proc_maps_private *priv = __seq_open_private(file, ops, psize);
+
+	if (!priv)
+		return -ENOMEM;
+
+	priv->inode = inode;
+	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR(priv->mm)) {
+		int err = PTR_ERR(priv->mm);
+
+		seq_release_private(inode, file);
+		return err;
+	}
+
+	return 0;
+}
+
+static int proc_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct proc_maps_private *priv = seq->private;
+
+	if (priv->mm)
+		mmdrop(priv->mm);
+
+	return seq_release_private(inode, file);
+}
+
+static int do_maps_open(struct inode *inode, struct file *file,
+			const struct seq_operations *ops)
+{
+	return proc_maps_open(inode, file, ops,
+				sizeof(struct proc_maps_private));
+}
+
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct file *file = vma->vm_file;
+	struct proc_maps_private *priv = m->private;
+	vm_flags_t flags = vma->vm_flags;
+	unsigned long ino = 0;
+	unsigned long long pgoff = 0;
+	unsigned long start, end;
+	dev_t dev = 0;
+	const char *name = NULL;
+
+	if (file) {
+		struct inode *inode;
+
+		file = vma_pr_or_file(vma);
+		inode = file_inode(file);
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
+	}
+
+	/* We don't show the stack guard page in /proc/maps */
+	start = vma->vm_start;
+	if (stack_guard_page_start(vma, start))
+		start += PAGE_SIZE;
+	end = vma->vm_end;
+	if (stack_guard_page_end(vma, end))
+		end -= PAGE_SIZE;
+
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+			start,
+			end,
+			flags & VM_READ ? 'r' : '-',
+			flags & VM_WRITE ? 'w' : '-',
+			flags & VM_EXEC ? 'x' : '-',
+			flags & VM_MAYSHARE ? 's' : 'p',
+			pgoff,
+			MAJOR(dev), MINOR(dev), ino);
+
+	/*
+	 * Print the dentry name for named mappings, and a
+	 * special [heap] marker for the heap:
+	 */
+	if (file) {
+		seq_pad(m, ' ');
+		seq_path(m, &file->f_path, "\n");
+		goto done;
+	}
+
+	if (vma->vm_ops && vma->vm_ops->name) {
+		name = vma->vm_ops->name(vma);
+		if (name)
+			goto done;
+	}
+
+	name = arch_vma_name(vma);
+	if (!name) {
+		pid_t tid;
+
+		if (!mm) {
+			name = "[vdso]";
+			goto done;
+		}
+
+		if (vma->vm_start <= mm->brk &&
+		    vma->vm_end >= mm->start_brk) {
+			name = "[heap]";
+			goto done;
+		}
+
+		tid = pid_of_stack(priv, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack)) {
+				name = "[stack]";
+			} else {
+				/* Thread stack in /proc/PID/maps */
+				seq_pad(m, ' ');
+				seq_printf(m, "[stack:%d]", tid);
+			}
+		}
+	}
+
+done:
+	if (name) {
+		seq_pad(m, ' ');
+		seq_puts(m, name);
+	}
+	seq_putc(m, '\n');
+}
+
+static int show_map(struct seq_file *m, void *v, int is_pid)
+{
+	show_map_vma(m, v, is_pid);
+	m_cache_vma(m, v);
+	return 0;
+}
+
+static int show_pid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 0);
+}
+
+static const struct seq_operations proc_pid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_maps_op);
+}
+
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
+/*
+ * Proportional Set Size(PSS): my share of RSS.
+ *
+ * PSS of a process is the count of pages it has in memory, where each
+ * page is divided by the number of processes sharing it.  So if a
+ * process has 1000 pages all to itself, and 1000 shared with one other
+ * process, its PSS will be 1500.
+ *
+ * To keep (accumulated) division errors low, we adopt a 64bit
+ * fixed-point pss counter to minimize division errors. So (pss >>
+ * PSS_SHIFT) would be the real byte count.
+ *
+ * A shift of 12 before division means (assuming 4K page size):
+ * 	- 1M 3-user-pages add up to 8KB errors;
+ * 	- supports mapcount up to 2^24, or 16M;
+ * 	- supports PSS up to 2^52 bytes, or 4PB.
+ */
+#define PSS_SHIFT 12
+
+#ifdef CONFIG_PROC_PAGE_MONITOR
+struct mem_size_stats {
+	unsigned long resident;
+	unsigned long shared_clean;
+	unsigned long shared_dirty;
+	unsigned long private_clean;
+	unsigned long private_dirty;
+	unsigned long referenced;
+	unsigned long anonymous;
+	unsigned long anonymous_thp;
+	unsigned long swap;
+	u64 pss;
+};
+
+static void smaps_account(struct mem_size_stats *mss, struct page *page,
+		unsigned long size, bool young, bool dirty)
+{
+	int mapcount;
+
+	if (PageAnon(page))
+		mss->anonymous += size;
+
+	mss->resident += size;
+	/* Accumulate the size in pages that have been accessed. */
+	if (young || PageReferenced(page))
+		mss->referenced += size;
+	mapcount = page_mapcount(page);
+	if (mapcount >= 2) {
+		u64 pss_delta;
+
+		if (dirty || PageDirty(page))
+			mss->shared_dirty += size;
+		else
+			mss->shared_clean += size;
+		pss_delta = (u64)size << PSS_SHIFT;
+		do_div(pss_delta, mapcount);
+		mss->pss += pss_delta;
+	} else {
+		if (dirty || PageDirty(page))
+			mss->private_dirty += size;
+		else
+			mss->private_clean += size;
+		mss->pss += (u64)size << PSS_SHIFT;
+	}
+}
+
+static void smaps_pte_entry(pte_t *pte, unsigned long addr,
+		struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	struct page *page = NULL;
+
+	if (pte_present(*pte)) {
+		page = vm_normal_page(vma, addr, *pte);
+	} else if (is_swap_pte(*pte)) {
+		swp_entry_t swpent = pte_to_swp_entry(*pte);
+
+		if (!non_swap_entry(swpent))
+			mss->swap += PAGE_SIZE;
+		else if (is_migration_entry(swpent))
+			page = migration_entry_to_page(swpent);
+	}
+
+	if (!page)
+		return;
+	smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+		struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	struct page *page;
+
+	/* FOLL_DUMP will return -EFAULT on huge zero page */
+	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+	if (IS_ERR_OR_NULL(page))
+		return;
+	mss->anonymous_thp += HPAGE_PMD_SIZE;
+	smaps_account(mss, page, HPAGE_PMD_SIZE,
+			pmd_young(*pmd), pmd_dirty(*pmd));
+}
+#else
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+		struct mm_walk *walk)
+{
+}
+#endif
+
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			   struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		smaps_pmd_entry(pmd, addr, walk);
+		spin_unlock(ptl);
+		return 0;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+	/*
+	 * The mmap_sem held all the way back in m_start() is what
+	 * keeps khugepaged out of here and from collapsing things
+	 * in here.
+	 */
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE)
+		smaps_pte_entry(pte, addr, walk);
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+	return 0;
+}
+
+static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
+{
+	/*
+	 * Don't forget to update Documentation/ on changes.
+	 */
+	static const char mnemonics[BITS_PER_LONG][2] = {
+		/*
+		 * In case if we meet a flag we don't know about.
+		 */
+		[0 ... (BITS_PER_LONG-1)] = "??",
+
+		[ilog2(VM_READ)]	= "rd",
+		[ilog2(VM_WRITE)]	= "wr",
+		[ilog2(VM_EXEC)]	= "ex",
+		[ilog2(VM_SHARED)]	= "sh",
+		[ilog2(VM_MAYREAD)]	= "mr",
+		[ilog2(VM_MAYWRITE)]	= "mw",
+		[ilog2(VM_MAYEXEC)]	= "me",
+		[ilog2(VM_MAYSHARE)]	= "ms",
+		[ilog2(VM_GROWSDOWN)]	= "gd",
+		[ilog2(VM_PFNMAP)]	= "pf",
+		[ilog2(VM_DENYWRITE)]	= "dw",
+#ifdef CONFIG_X86_INTEL_MPX
+		[ilog2(VM_MPX)]		= "mp",
+#endif
+		[ilog2(VM_LOCKED)]	= "lo",
+		[ilog2(VM_IO)]		= "io",
+		[ilog2(VM_SEQ_READ)]	= "sr",
+		[ilog2(VM_RAND_READ)]	= "rr",
+		[ilog2(VM_DONTCOPY)]	= "dc",
+		[ilog2(VM_DONTEXPAND)]	= "de",
+		[ilog2(VM_ACCOUNT)]	= "ac",
+		[ilog2(VM_NORESERVE)]	= "nr",
+		[ilog2(VM_HUGETLB)]	= "ht",
+		[ilog2(VM_ARCH_1)]	= "ar",
+		[ilog2(VM_DONTDUMP)]	= "dd",
+#ifdef CONFIG_MEM_SOFT_DIRTY
+		[ilog2(VM_SOFTDIRTY)]	= "sd",
+#endif
+		[ilog2(VM_MIXEDMAP)]	= "mm",
+		[ilog2(VM_HUGEPAGE)]	= "hg",
+		[ilog2(VM_NOHUGEPAGE)]	= "nh",
+		[ilog2(VM_MERGEABLE)]	= "mg",
+	};
+	size_t i;
+
+	seq_puts(m, "VmFlags: ");
+	for (i = 0; i < BITS_PER_LONG; i++) {
+		if (vma->vm_flags & (1UL << i)) {
+			seq_printf(m, "%c%c ",
+				   mnemonics[i][0], mnemonics[i][1]);
+		}
+	}
+	seq_putc(m, '\n');
+}
+
+static int show_smap(struct seq_file *m, void *v, int is_pid)
+{
+	struct vm_area_struct *vma = v;
+	struct mem_size_stats mss;
+	struct mm_walk smaps_walk = {
+		.pmd_entry = smaps_pte_range,
+		.mm = vma->vm_mm,
+		.private = &mss,
+	};
+
+	memset(&mss, 0, sizeof mss);
+	/* mmap_sem is held in m_start */
+	walk_page_vma(vma, &smaps_walk);
+
+	show_map_vma(m, vma, is_pid);
+
+	seq_printf(m,
+		   "Size:           %8lu kB\n"
+		   "Rss:            %8lu kB\n"
+		   "Pss:            %8lu kB\n"
+		   "Shared_Clean:   %8lu kB\n"
+		   "Shared_Dirty:   %8lu kB\n"
+		   "Private_Clean:  %8lu kB\n"
+		   "Private_Dirty:  %8lu kB\n"
+		   "Referenced:     %8lu kB\n"
+		   "Anonymous:      %8lu kB\n"
+		   "AnonHugePages:  %8lu kB\n"
+		   "Swap:           %8lu kB\n"
+		   "KernelPageSize: %8lu kB\n"
+		   "MMUPageSize:    %8lu kB\n"
+		   "Locked:         %8lu kB\n",
+		   (vma->vm_end - vma->vm_start) >> 10,
+		   mss.resident >> 10,
+		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
+		   mss.shared_clean  >> 10,
+		   mss.shared_dirty  >> 10,
+		   mss.private_clean >> 10,
+		   mss.private_dirty >> 10,
+		   mss.referenced >> 10,
+		   mss.anonymous >> 10,
+		   mss.anonymous_thp >> 10,
+		   mss.swap >> 10,
+		   vma_kernel_pagesize(vma) >> 10,
+		   vma_mmu_pagesize(vma) >> 10,
+		   (vma->vm_flags & VM_LOCKED) ?
+			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
+
+	show_smap_vma_flags(m, vma);
+	m_cache_vma(m, vma);
+	return 0;
+}
+
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 0);
+}
+
+static const struct seq_operations proc_pid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_smap
+};
+
+static int pid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_smaps_op);
+}
+
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+	.open		= pid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+	.open		= tid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
+/*
+ * We do not want to have constant page-shift bits sitting in
+ * pagemap entries and are about to reuse them some time soon.
+ *
+ * Here's the "migration strategy":
+ * 1. when the system boots these bits remain what they are,
+ *    but a warning about future change is printed in log;
+ * 2. once anyone clears soft-dirty bits via clear_refs file,
+ *    these flag is set to denote, that user is aware of the
+ *    new API and those page-shift bits change their meaning.
+ *    The respective warning is printed in dmesg;
+ * 3. In a couple of releases we will remove all the mentions
+ *    of page-shift in pagemap entries.
+ */
+
+static bool soft_dirty_cleared __read_mostly;
+
+enum clear_refs_types {
+	CLEAR_REFS_ALL = 1,
+	CLEAR_REFS_ANON,
+	CLEAR_REFS_MAPPED,
+	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_MM_HIWATER_RSS,
+	CLEAR_REFS_LAST,
+};
+
+struct clear_refs_private {
+	enum clear_refs_types type;
+};
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+	/*
+	 * The soft-dirty tracker uses #PF-s to catch writes
+	 * to pages, so write-protect the pte as well. See the
+	 * Documentation/vm/soft-dirty.txt for full description
+	 * of how soft-dirty works.
+	 */
+	pte_t ptent = *pte;
+
+	if (pte_present(ptent)) {
+		ptent = pte_wrprotect(ptent);
+		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+	} else if (is_swap_pte(ptent)) {
+		ptent = pte_swp_clear_soft_dirty(ptent);
+	}
+
+	set_pte_at(vma->vm_mm, addr, pte, ptent);
+}
+
+static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+
+	pmd = pmd_wrprotect(pmd);
+	pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
+
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		vma->vm_flags &= ~VM_SOFTDIRTY;
+
+	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+}
+
+#else
+
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+}
+
+static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+}
+#endif
+
+static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty_pmd(vma, addr, pmd);
+			goto out;
+		}
+
+		page = pmd_page(*pmd);
+
+		/* Clear accessed and referenced bits. */
+		pmdp_test_and_clear_young(vma, addr, pmd);
+		ClearPageReferenced(page);
+out:
+		spin_unlock(ptl);
+		return 0;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty(vma, addr, pte);
+			continue;
+		}
+
+		if (!pte_present(ptent))
+			continue;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		/* Clear accessed and referenced bits. */
+		ptep_test_and_clear_young(vma, addr, pte);
+		ClearPageReferenced(page);
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+	return 0;
+}
+
+static int clear_refs_test_walk(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+
+	if (vma->vm_flags & VM_PFNMAP)
+		return 1;
+
+	/*
+	 * Writing 1 to /proc/pid/clear_refs affects all pages.
+	 * Writing 2 to /proc/pid/clear_refs only affects anonymous pages.
+	 * Writing 3 to /proc/pid/clear_refs only affects file mapped pages.
+	 * Writing 4 to /proc/pid/clear_refs affects all pages.
+	 */
+	if (cp->type == CLEAR_REFS_ANON && vma->vm_file)
+		return 1;
+	if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file)
+		return 1;
+	return 0;
+}
+
+static ssize_t clear_refs_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF];
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	enum clear_refs_types type;
+	int itype;
+	int rv;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+	rv = kstrtoint(strstrip(buffer), 10, &itype);
+	if (rv < 0)
+		return rv;
+	type = (enum clear_refs_types)itype;
+	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
+		return -EINVAL;
+
+	if (type == CLEAR_REFS_SOFT_DIRTY) {
+		soft_dirty_cleared = true;
+		pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
+			     " See the linux/Documentation/vm/pagemap.txt for "
+			     "details.\n");
+	}
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+	mm = get_task_mm(task);
+	if (mm) {
+		struct clear_refs_private cp = {
+			.type = type,
+		};
+		struct mm_walk clear_refs_walk = {
+			.pmd_entry = clear_refs_pte_range,
+			.test_walk = clear_refs_test_walk,
+			.mm = mm,
+			.private = &cp,
+		};
+
+		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+			/*
+			 * Writing 5 to /proc/pid/clear_refs resets the peak
+			 * resident set size to this mm's current rss value.
+			 */
+			down_write(&mm->mmap_sem);
+			reset_mm_hiwater_rss(mm);
+			up_write(&mm->mmap_sem);
+			goto out_mm;
+		}
+
+		down_read(&mm->mmap_sem);
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
+			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+				if (!(vma->vm_flags & VM_SOFTDIRTY))
+					continue;
+				up_read(&mm->mmap_sem);
+				down_write(&mm->mmap_sem);
+				for (vma = mm->mmap; vma; vma = vma->vm_next) {
+					vma->vm_flags &= ~VM_SOFTDIRTY;
+					vma_set_page_prot(vma);
+				}
+				downgrade_write(&mm->mmap_sem);
+				break;
+			}
+			mmu_notifier_invalidate_range_start(mm, 0, -1);
+		}
+		walk_page_range(0, ~0UL, &clear_refs_walk);
+		if (type == CLEAR_REFS_SOFT_DIRTY)
+			mmu_notifier_invalidate_range_end(mm, 0, -1);
+		flush_tlb_mm(mm);
+		up_read(&mm->mmap_sem);
+out_mm:
+		mmput(mm);
+	}
+	put_task_struct(task);
+
+	return count;
+}
+
+const struct file_operations proc_clear_refs_operations = {
+	.write		= clear_refs_write,
+	.llseek		= noop_llseek,
+};
+
+typedef struct {
+	u64 pme;
+} pagemap_entry_t;
+
+struct pagemapread {
+	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
+	pagemap_entry_t *buffer;
+	bool v2;
+};
+
+#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
+#define PAGEMAP_WALK_MASK	(PMD_MASK)
+
+#define PM_ENTRY_BYTES      sizeof(pagemap_entry_t)
+#define PM_STATUS_BITS      3
+#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
+#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
+#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
+#define PM_PSHIFT_BITS      6
+#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
+#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
+#define __PM_PSHIFT(x)      (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
+#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+/* in "new" pagemap pshift bits are occupied with more status bits */
+#define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
+
+#define __PM_SOFT_DIRTY      (1LL)
+#define PM_PRESENT          PM_STATUS(4LL)
+#define PM_SWAP             PM_STATUS(2LL)
+#define PM_FILE             PM_STATUS(1LL)
+#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
+#define PM_END_OF_BUFFER    1
+
+static inline pagemap_entry_t make_pme(u64 val)
+{
+	return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
+			  struct pagemapread *pm)
+{
+	pm->buffer[pm->pos++] = *pme;
+	if (pm->pos >= pm->len)
+		return PM_END_OF_BUFFER;
+	return 0;
+}
+
+static int pagemap_pte_hole(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct pagemapread *pm = walk->private;
+	unsigned long addr = start;
+	int err = 0;
+
+	while (addr < end) {
+		struct vm_area_struct *vma = find_vma(walk->mm, addr);
+		pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+		/* End of address space hole, which we mark as non-present. */
+		unsigned long hole_end;
+
+		if (vma)
+			hole_end = min(end, vma->vm_start);
+		else
+			hole_end = end;
+
+		for (; addr < hole_end; addr += PAGE_SIZE) {
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				goto out;
+		}
+
+		if (!vma)
+			break;
+
+		/* Addresses in the VMA. */
+		if (vma->vm_flags & VM_SOFTDIRTY)
+			pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				goto out;
+		}
+	}
+out:
+	return err;
+}
+
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+	u64 frame, flags;
+	struct page *page = NULL;
+	int flags2 = 0;
+
+	if (pte_present(pte)) {
+		frame = pte_pfn(pte);
+		flags = PM_PRESENT;
+		page = vm_normal_page(vma, addr, pte);
+		if (pte_soft_dirty(pte))
+			flags2 |= __PM_SOFT_DIRTY;
+	} else if (is_swap_pte(pte)) {
+		swp_entry_t entry;
+		if (pte_swp_soft_dirty(pte))
+			flags2 |= __PM_SOFT_DIRTY;
+		entry = pte_to_swp_entry(pte);
+		frame = swp_type(entry) |
+			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+		flags = PM_SWAP;
+		if (is_migration_entry(entry))
+			page = migration_entry_to_page(entry);
+	} else {
+		if (vma->vm_flags & VM_SOFTDIRTY)
+			flags2 |= __PM_SOFT_DIRTY;
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
+		return;
+	}
+
+	if (page && !PageAnon(page))
+		flags |= PM_FILE;
+	if ((vma->vm_flags & VM_SOFTDIRTY))
+		flags2 |= __PM_SOFT_DIRTY;
+
+	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
+{
+	/*
+	 * Currently pmd for thp is always present because thp can not be
+	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+	 * This if-check is just to prepare for future implementation.
+	 */
+	if (pmd_present(pmd))
+		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
+	else
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
+}
+#else
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
+{
+}
+#endif
+
+static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			     struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+	struct pagemapread *pm = walk->private;
+	spinlock_t *ptl;
+	pte_t *pte, *orig_pte;
+	int err = 0;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		int pmd_flags2;
+
+		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
+			pmd_flags2 = __PM_SOFT_DIRTY;
+		else
+			pmd_flags2 = 0;
+
+		for (; addr != end; addr += PAGE_SIZE) {
+			unsigned long offset;
+			pagemap_entry_t pme;
+
+			offset = (addr & ~PAGEMAP_WALK_MASK) >>
+					PAGE_SHIFT;
+			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				break;
+		}
+		spin_unlock(ptl);
+		return err;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	/*
+	 * We can assume that @vma always points to a valid one and @end never
+	 * goes beyond vma->vm_end.
+	 */
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	for (; addr < end; pte++, addr += PAGE_SIZE) {
+		pagemap_entry_t pme;
+
+		pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+		err = add_to_pagemap(addr, &pme, pm);
+		if (err)
+			break;
+	}
+	pte_unmap_unlock(orig_pte, ptl);
+
+	cond_resched();
+
+	return err;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+					pte_t pte, int offset, int flags2)
+{
+	if (pte_present(pte))
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)	|
+				PM_STATUS2(pm->v2, flags2)		|
+				PM_PRESENT);
+	else
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2)			|
+				PM_STATUS2(pm->v2, flags2));
+}
+
+/* This function walks within one hugetlb entry in the single call */
+static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
+				 unsigned long addr, unsigned long end,
+				 struct mm_walk *walk)
+{
+	struct pagemapread *pm = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	int err = 0;
+	int flags2;
+	pagemap_entry_t pme;
+
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		flags2 = __PM_SOFT_DIRTY;
+	else
+		flags2 = 0;
+
+	for (; addr != end; addr += PAGE_SIZE) {
+		int offset = (addr & ~hmask) >> PAGE_SHIFT;
+		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
+		err = add_to_pagemap(addr, &pme, pm);
+		if (err)
+			return err;
+	}
+
+	cond_resched();
+
+	return err;
+}
+#endif /* HUGETLB_PAGE */
+
+/*
+ * /proc/pid/pagemap - an array mapping virtual pages to pfns
+ *
+ * For each page in the address space, this file contains one 64-bit entry
+ * consisting of the following:
+ *
+ * Bits 0-54  page frame number (PFN) if present
+ * Bits 0-4   swap type if swapped
+ * Bits 5-54  swap offset if swapped
+ * Bits 55-60 page shift (page size = 1<<page shift)
+ * Bit  61    page is file-page or shared-anon
+ * Bit  62    page swapped
+ * Bit  63    page present
+ *
+ * If the page is not present but in swap, then the PFN contains an
+ * encoding of the swap file number and the page's offset into the
+ * swap. Unmapped pages return a null PFN. This allows determining
+ * precisely which pages are mapped (or in swap) and comparing mapped
+ * pages between processes.
+ *
+ * Efficient users of this interface will use /proc/pid/maps to
+ * determine which areas of memory are actually mapped and llseek to
+ * skip over unmapped regions.
+ */
+static ssize_t pagemap_read(struct file *file, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	struct mm_struct *mm;
+	struct pagemapread pm;
+	int ret = -ESRCH;
+	struct mm_walk pagemap_walk = {};
+	unsigned long src;
+	unsigned long svpfn;
+	unsigned long start_vaddr;
+	unsigned long end_vaddr;
+	int copied = 0;
+
+	if (!task)
+		goto out;
+
+	ret = -EINVAL;
+	/* file position must be aligned */
+	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
+		goto out_task;
+
+	ret = 0;
+	if (!count)
+		goto out_task;
+
+	pm.v2 = soft_dirty_cleared;
+	pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+	pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
+	ret = -ENOMEM;
+	if (!pm.buffer)
+		goto out_task;
+
+	mm = mm_access(task, PTRACE_MODE_READ);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
+		goto out_free;
+
+	pagemap_walk.pmd_entry = pagemap_pte_range;
+	pagemap_walk.pte_hole = pagemap_pte_hole;
+#ifdef CONFIG_HUGETLB_PAGE
+	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
+#endif
+	pagemap_walk.mm = mm;
+	pagemap_walk.private = &pm;
+
+	src = *ppos;
+	svpfn = src / PM_ENTRY_BYTES;
+	start_vaddr = svpfn << PAGE_SHIFT;
+	end_vaddr = TASK_SIZE_OF(task);
+
+	/* watch out for wraparound */
+	if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
+		start_vaddr = end_vaddr;
+
+	/*
+	 * The odds are that this will stop walking way
+	 * before end_vaddr, because the length of the
+	 * user buffer is tracked in "pm", and the walk
+	 * will stop when we hit the end of the buffer.
+	 */
+	ret = 0;
+	while (count && (start_vaddr < end_vaddr)) {
+		int len;
+		unsigned long end;
+
+		pm.pos = 0;
+		end = (start_vaddr + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK;
+		/* overflow ? */
+		if (end < start_vaddr || end > end_vaddr)
+			end = end_vaddr;
+		down_read(&mm->mmap_sem);
+		ret = walk_page_range(start_vaddr, end, &pagemap_walk);
+		up_read(&mm->mmap_sem);
+		start_vaddr = end;
+
+		len = min(count, PM_ENTRY_BYTES * pm.pos);
+		if (copy_to_user(buf, pm.buffer, len)) {
+			ret = -EFAULT;
+			goto out_mm;
+		}
+		copied += len;
+		buf += len;
+		count -= len;
+	}
+	*ppos += copied;
+	if (!ret || ret == PM_END_OF_BUFFER)
+		ret = copied;
+
+out_mm:
+	mmput(mm);
+out_free:
+	kfree(pm.buffer);
+out_task:
+	put_task_struct(task);
+out:
+	return ret;
+}
+
+static int pagemap_open(struct inode *inode, struct file *file)
+{
+	/* do not disclose physical addresses: attack vector */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
+			"to stop being page-shift some time soon. See the "
+			"linux/Documentation/vm/pagemap.txt for details.\n");
+	return 0;
+}
+
+const struct file_operations proc_pagemap_operations = {
+	.llseek		= mem_lseek, /* borrow this */
+	.read		= pagemap_read,
+	.open		= pagemap_open,
+};
+#endif /* CONFIG_PROC_PAGE_MONITOR */
+
+#ifdef CONFIG_NUMA
+
+struct numa_maps {
+	unsigned long pages;
+	unsigned long anon;
+	unsigned long active;
+	unsigned long writeback;
+	unsigned long mapcount_max;
+	unsigned long dirty;
+	unsigned long swapcache;
+	unsigned long node[MAX_NUMNODES];
+};
+
+struct numa_maps_private {
+	struct proc_maps_private proc_maps;
+	struct numa_maps md;
+};
+
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
+			unsigned long nr_pages)
+{
+	int count = page_mapcount(page);
+
+	md->pages += nr_pages;
+	if (pte_dirty || PageDirty(page))
+		md->dirty += nr_pages;
+
+	if (PageSwapCache(page))
+		md->swapcache += nr_pages;
+
+	if (PageActive(page) || PageUnevictable(page))
+		md->active += nr_pages;
+
+	if (PageWriteback(page))
+		md->writeback += nr_pages;
+
+	if (PageAnon(page))
+		md->anon += nr_pages;
+
+	if (count > md->mapcount_max)
+		md->mapcount_max = count;
+
+	md->node[page_to_nid(page)] += nr_pages;
+}
+
+static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
+		unsigned long addr)
+{
+	struct page *page;
+	int nid;
+
+	if (!pte_present(pte))
+		return NULL;
+
+	page = vm_normal_page(vma, addr, pte);
+	if (!page)
+		return NULL;
+
+	if (PageReserved(page))
+		return NULL;
+
+	nid = page_to_nid(page);
+	if (!node_isset(nid, node_states[N_MEMORY]))
+		return NULL;
+
+	return page;
+}
+
+static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
+		unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	spinlock_t *ptl;
+	pte_t *orig_pte;
+	pte_t *pte;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		pte_t huge_pte = *(pte_t *)pmd;
+		struct page *page;
+
+		page = can_gather_numa_stats(huge_pte, vma, addr);
+		if (page)
+			gather_stats(page, md, pte_dirty(huge_pte),
+				     HPAGE_PMD_SIZE/PAGE_SIZE);
+		spin_unlock(ptl);
+		return 0;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	do {
+		struct page *page = can_gather_numa_stats(*pte, vma, addr);
+		if (!page)
+			continue;
+		gather_stats(page, md, pte_dirty(*pte), 1);
+
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(orig_pte, ptl);
+	return 0;
+}
+#ifdef CONFIG_HUGETLB_PAGE
+static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md;
+	struct page *page;
+
+	if (!pte_present(*pte))
+		return 0;
+
+	page = pte_page(*pte);
+	if (!page)
+		return 0;
+
+	md = walk->private;
+	gather_stats(page, md, pte_dirty(*pte), 1);
+	return 0;
+}
+
+#else
+static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
+{
+	struct numa_maps_private *numa_priv = m->private;
+	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+	struct vm_area_struct *vma = v;
+	struct numa_maps *md = &numa_priv->md;
+	struct file *file = vma_pr_or_file(vma);
+	struct mm_struct *mm = vma->vm_mm;
+	struct mm_walk walk = {
+		.hugetlb_entry = gather_hugetlb_stats,
+		.pmd_entry = gather_pte_stats,
+		.private = md,
+		.mm = mm,
+	};
+	struct mempolicy *pol;
+	char buffer[64];
+	int nid;
+
+	if (!mm)
+		return 0;
+
+	/* Ensure we start with an empty set of numa_maps statistics. */
+	memset(md, 0, sizeof(*md));
+
+	pol = __get_vma_policy(vma, vma->vm_start);
+	if (pol) {
+		mpol_to_str(buffer, sizeof(buffer), pol);
+		mpol_cond_put(pol);
+	} else {
+		mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy);
+	}
+
+	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
+
+	if (file) {
+		seq_puts(m, " file=");
+		seq_path(m, &file->f_path, "\n\t= ");
+	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
+		seq_puts(m, " heap");
+	} else {
+		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_puts(m, " stack");
+			else
+				seq_printf(m, " stack:%d", tid);
+		}
+	}
+
+	if (is_vm_hugetlb_page(vma))
+		seq_puts(m, " huge");
+
+	/* mmap_sem is held by m_start */
+	walk_page_vma(vma, &walk);
+
+	if (!md->pages)
+		goto out;
+
+	if (md->anon)
+		seq_printf(m, " anon=%lu", md->anon);
+
+	if (md->dirty)
+		seq_printf(m, " dirty=%lu", md->dirty);
+
+	if (md->pages != md->anon && md->pages != md->dirty)
+		seq_printf(m, " mapped=%lu", md->pages);
+
+	if (md->mapcount_max > 1)
+		seq_printf(m, " mapmax=%lu", md->mapcount_max);
+
+	if (md->swapcache)
+		seq_printf(m, " swapcache=%lu", md->swapcache);
+
+	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
+		seq_printf(m, " active=%lu", md->active);
+
+	if (md->writeback)
+		seq_printf(m, " writeback=%lu", md->writeback);
+
+	for_each_node_state(nid, N_MEMORY)
+		if (md->node[nid])
+			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
+
+	seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10);
+out:
+	seq_putc(m, '\n');
+	m_cache_vma(m, vma);
+	return 0;
+}
+
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 0);
+}
+
+static const struct seq_operations proc_pid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_pid_numa_map,
+};
+
+static const struct seq_operations proc_tid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_tid_numa_map,
+};
+
+static int numa_maps_open(struct inode *inode, struct file *file,
+			  const struct seq_operations *ops)
+{
+	return proc_maps_open(inode, file, ops,
+				sizeof(struct numa_maps_private));
+}
+
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+	.open		= pid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+	.open		= tid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+#endif /* CONFIG_NUMA */
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
new file mode 100644
index 000000000..174020784
--- /dev/null
+++ b/fs/proc/task_nommu.c
@@ -0,0 +1,348 @@
+
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/fs_struct.h>
+#include <linux/mount.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * Logic: we've got two memory sums for each process, "shared", and
+ * "non-shared". Shared memory may get counted more than once, for
+ * each process that owns it. Non-shared memory is counted
+ * accurately.
+ */
+void task_mem(struct seq_file *m, struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	struct vm_region *region;
+	struct rb_node *p;
+	unsigned long bytes = 0, sbytes = 0, slack = 0, size;
+        
+	down_read(&mm->mmap_sem);
+	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
+		vma = rb_entry(p, struct vm_area_struct, vm_rb);
+
+		bytes += kobjsize(vma);
+
+		region = vma->vm_region;
+		if (region) {
+			size = kobjsize(region);
+			size += region->vm_end - region->vm_start;
+		} else {
+			size = vma->vm_end - vma->vm_start;
+		}
+
+		if (atomic_read(&mm->mm_count) > 1 ||
+		    vma->vm_flags & VM_MAYSHARE) {
+			sbytes += size;
+		} else {
+			bytes += size;
+			if (region)
+				slack = region->vm_end - vma->vm_end;
+		}
+	}
+
+	if (atomic_read(&mm->mm_count) > 1)
+		sbytes += kobjsize(mm);
+	else
+		bytes += kobjsize(mm);
+	
+	if (current->fs && current->fs->users > 1)
+		sbytes += kobjsize(current->fs);
+	else
+		bytes += kobjsize(current->fs);
+
+	if (current->files && atomic_read(&current->files->count) > 1)
+		sbytes += kobjsize(current->files);
+	else
+		bytes += kobjsize(current->files);
+
+	if (current->sighand && atomic_read(&current->sighand->count) > 1)
+		sbytes += kobjsize(current->sighand);
+	else
+		bytes += kobjsize(current->sighand);
+
+	bytes += kobjsize(current); /* includes kernel stack */
+
+	seq_printf(m,
+		"Mem:\t%8lu bytes\n"
+		"Slack:\t%8lu bytes\n"
+		"Shared:\t%8lu bytes\n",
+		bytes, slack, sbytes);
+
+	up_read(&mm->mmap_sem);
+}
+
+unsigned long task_vsize(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *p;
+	unsigned long vsize = 0;
+
+	down_read(&mm->mmap_sem);
+	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
+		vma = rb_entry(p, struct vm_area_struct, vm_rb);
+		vsize += vma->vm_end - vma->vm_start;
+	}
+	up_read(&mm->mmap_sem);
+	return vsize;
+}
+
+unsigned long task_statm(struct mm_struct *mm,
+			 unsigned long *shared, unsigned long *text,
+			 unsigned long *data, unsigned long *resident)
+{
+	struct vm_area_struct *vma;
+	struct vm_region *region;
+	struct rb_node *p;
+	unsigned long size = kobjsize(mm);
+
+	down_read(&mm->mmap_sem);
+	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
+		vma = rb_entry(p, struct vm_area_struct, vm_rb);
+		size += kobjsize(vma);
+		region = vma->vm_region;
+		if (region) {
+			size += kobjsize(region);
+			size += region->vm_end - region->vm_start;
+		}
+	}
+
+	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
+		>> PAGE_SHIFT;
+	*data = (PAGE_ALIGN(mm->start_stack) - (mm->start_data & PAGE_MASK))
+		>> PAGE_SHIFT;
+	up_read(&mm->mmap_sem);
+	size >>= PAGE_SHIFT;
+	size += *text + *data;
+	*resident = size;
+	return size;
+}
+
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/*
+ * display a single VMA to a sequenced file
+ */
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
+			  int is_pid)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct proc_maps_private *priv = m->private;
+	unsigned long ino = 0;
+	struct file *file;
+	dev_t dev = 0;
+	int flags;
+	unsigned long long pgoff = 0;
+
+	flags = vma->vm_flags;
+	file = vma->vm_file;
+
+	if (file) {
+		struct inode *inode;
+
+		file = vma_pr_or_file(vma);
+		inode = file_inode(file);
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+		pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+	}
+
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+		   vma->vm_start,
+		   vma->vm_end,
+		   flags & VM_READ ? 'r' : '-',
+		   flags & VM_WRITE ? 'w' : '-',
+		   flags & VM_EXEC ? 'x' : '-',
+		   flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
+		   pgoff,
+		   MAJOR(dev), MINOR(dev), ino);
+
+	if (file) {
+		seq_pad(m, ' ');
+		seq_path(m, &file->f_path, "");
+	} else if (mm) {
+		pid_t tid = pid_of_stack(priv, vma, is_pid);
+
+		if (tid != 0) {
+			seq_pad(m, ' ');
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, "[stack]");
+			else
+				seq_printf(m, "[stack:%d]", tid);
+		}
+	}
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+/*
+ * display mapping lines for a particular process's /proc/pid/maps
+ */
+static int show_map(struct seq_file *m, void *_p, int is_pid)
+{
+	struct rb_node *p = _p;
+
+	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb),
+			      is_pid);
+}
+
+static int show_pid_map(struct seq_file *m, void *_p)
+{
+	return show_map(m, _p, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *_p)
+{
+	return show_map(m, _p, 0);
+}
+
+static void *m_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct mm_struct *mm;
+	struct rb_node *p;
+	loff_t n = *pos;
+
+	/* pin the task and mm whilst we play with them */
+	priv->task = get_proc_task(priv->inode);
+	if (!priv->task)
+		return ERR_PTR(-ESRCH);
+
+	mm = priv->mm;
+	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+		return NULL;
+
+	down_read(&mm->mmap_sem);
+	/* start from the Nth VMA */
+	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
+		if (n-- == 0)
+			return p;
+
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+	return NULL;
+}
+
+static void m_stop(struct seq_file *m, void *_vml)
+{
+	struct proc_maps_private *priv = m->private;
+
+	if (!IS_ERR_OR_NULL(_vml)) {
+		up_read(&priv->mm->mmap_sem);
+		mmput(priv->mm);
+	}
+	if (priv->task) {
+		put_task_struct(priv->task);
+		priv->task = NULL;
+	}
+}
+
+static void *m_next(struct seq_file *m, void *_p, loff_t *pos)
+{
+	struct rb_node *p = _p;
+
+	(*pos)++;
+	return p ? rb_next(p) : NULL;
+}
+
+static const struct seq_operations proc_pid_maps_ops = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_ops = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
+};
+
+static int maps_open(struct inode *inode, struct file *file,
+		     const struct seq_operations *ops)
+{
+	struct proc_maps_private *priv;
+
+	priv = __seq_open_private(file, ops, sizeof(*priv));
+	if (!priv)
+		return -ENOMEM;
+
+	priv->inode = inode;
+	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR(priv->mm)) {
+		int err = PTR_ERR(priv->mm);
+
+		seq_release_private(inode, file);
+		return err;
+	}
+
+	return 0;
+}
+
+
+static int map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct proc_maps_private *priv = seq->private;
+
+	if (priv->mm)
+		mmdrop(priv->mm);
+
+	return seq_release_private(inode, file);
+}
+
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_pid_maps_ops);
+}
+
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_tid_maps_ops);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= map_release,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= map_release,
+};
+
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
new file mode 100644
index 000000000..a8371993b
--- /dev/null
+++ b/fs/proc/thread_self.c
@@ -0,0 +1,85 @@
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/thread_self:
+ */
+static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
+			      int buflen)
+{
+	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	pid_t pid = task_pid_nr_ns(current, ns);
+	char tmp[PROC_NUMBUF + 6 + PROC_NUMBUF];
+	if (!pid)
+		return -ENOENT;
+	sprintf(tmp, "%d/task/%d", tgid, pid);
+	return readlink_copy(buffer, buflen, tmp);
+}
+
+static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	pid_t pid = task_pid_nr_ns(current, ns);
+	char *name = ERR_PTR(-ENOENT);
+	if (pid) {
+		name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+		if (!name)
+			name = ERR_PTR(-ENOMEM);
+		else
+			sprintf(name, "%d/task/%d", tgid, pid);
+	}
+	nd_set_link(nd, name);
+	return NULL;
+}
+
+static const struct inode_operations proc_thread_self_inode_operations = {
+	.readlink	= proc_thread_self_readlink,
+	.follow_link	= proc_thread_self_follow_link,
+	.put_link	= kfree_put_link,
+};
+
+static unsigned thread_self_inum;
+
+int proc_setup_thread_self(struct super_block *s)
+{
+	struct inode *root_inode = d_inode(s->s_root);
+	struct pid_namespace *ns = s->s_fs_info;
+	struct dentry *thread_self;
+
+	mutex_lock(&root_inode->i_mutex);
+	thread_self = d_alloc_name(s->s_root, "thread-self");
+	if (thread_self) {
+		struct inode *inode = new_inode_pseudo(s);
+		if (inode) {
+			inode->i_ino = thread_self_inum;
+			inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+			inode->i_mode = S_IFLNK | S_IRWXUGO;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+			inode->i_op = &proc_thread_self_inode_operations;
+			d_add(thread_self, inode);
+		} else {
+			dput(thread_self);
+			thread_self = ERR_PTR(-ENOMEM);
+		}
+	} else {
+		thread_self = ERR_PTR(-ENOMEM);
+	}
+	mutex_unlock(&root_inode->i_mutex);
+	if (IS_ERR(thread_self)) {
+		pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
+		return PTR_ERR(thread_self);
+	}
+	ns->proc_thread_self = thread_self;
+	return 0;
+}
+
+void __init proc_thread_self_init(void)
+{
+	proc_alloc_inum(&thread_self_inum);
+}
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
new file mode 100644
index 000000000..33de567c2
--- /dev/null
+++ b/fs/proc/uptime.c
@@ -0,0 +1,52 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/time.h>
+#include <linux/kernel_stat.h>
+#include <linux/cputime.h>
+
+static int uptime_proc_show(struct seq_file *m, void *v)
+{
+	struct timespec uptime;
+	struct timespec idle;
+	u64 idletime;
+	u64 nsec;
+	u32 rem;
+	int i;
+
+	idletime = 0;
+	for_each_possible_cpu(i)
+		idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+
+	get_monotonic_boottime(&uptime);
+	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
+	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+	idle.tv_nsec = rem;
+	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
+			(unsigned long) uptime.tv_sec,
+			(uptime.tv_nsec / (NSEC_PER_SEC / 100)),
+			(unsigned long) idle.tv_sec,
+			(idle.tv_nsec / (NSEC_PER_SEC / 100)));
+	return 0;
+}
+
+static int uptime_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, uptime_proc_show, NULL);
+}
+
+static const struct file_operations uptime_proc_fops = {
+	.open		= uptime_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_uptime_init(void)
+{
+	proc_create("uptime", 0, NULL, &uptime_proc_fops);
+	return 0;
+}
+fs_initcall(proc_uptime_init);
diff --git a/fs/proc/version.c b/fs/proc/version.c
new file mode 100644
index 000000000..d2154eb6d
--- /dev/null
+++ b/fs/proc/version.c
@@ -0,0 +1,34 @@
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/utsname.h>
+
+static int version_proc_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, linux_proc_banner,
+		utsname()->sysname,
+		utsname()->release,
+		utsname()->version);
+	return 0;
+}
+
+static int version_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, version_proc_show, NULL);
+}
+
+static const struct file_operations version_proc_fops = {
+	.open		= version_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_version_init(void)
+{
+	proc_create("version", 0, NULL, &version_proc_fops);
+	return 0;
+}
+fs_initcall(proc_version_init);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
new file mode 100644
index 000000000..4e61388ec
--- /dev/null
+++ b/fs/proc/vmcore.c
@@ -0,0 +1,1194 @@
+/*
+ *	fs/proc/vmcore.c Interface for accessing the crash
+ * 				 dump from the system's previous life.
+ * 	Heavily borrowed from fs/proc/kcore.c
+ *	Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
+ *	Copyright (C) IBM Corporation, 2004. All rights reserved
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/kcore.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+#include <linux/printk.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/crash_dump.h>
+#include <linux/list.h>
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include "internal.h"
+
+/* List representing chunks of contiguous memory areas and their offsets in
+ * vmcore file.
+ */
+static LIST_HEAD(vmcore_list);
+
+/* Stores the pointer to the buffer containing kernel elf core headers. */
+static char *elfcorebuf;
+static size_t elfcorebuf_sz;
+static size_t elfcorebuf_sz_orig;
+
+static char *elfnotes_buf;
+static size_t elfnotes_sz;
+
+/* Total size of vmcore file. */
+static u64 vmcore_size;
+
+static struct proc_dir_entry *proc_vmcore;
+
+/*
+ * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
+ * The called function has to take care of module refcounting.
+ */
+static int (*oldmem_pfn_is_ram)(unsigned long pfn);
+
+int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
+{
+	if (oldmem_pfn_is_ram)
+		return -EBUSY;
+	oldmem_pfn_is_ram = fn;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);
+
+void unregister_oldmem_pfn_is_ram(void)
+{
+	oldmem_pfn_is_ram = NULL;
+	wmb();
+}
+EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);
+
+static int pfn_is_ram(unsigned long pfn)
+{
+	int (*fn)(unsigned long pfn);
+	/* pfn is ram unless fn() checks pagetype */
+	int ret = 1;
+
+	/*
+	 * Ask hypervisor if the pfn is really ram.
+	 * A ballooned page contains no data and reading from such a page
+	 * will cause high load in the hypervisor.
+	 */
+	fn = oldmem_pfn_is_ram;
+	if (fn)
+		ret = fn(pfn);
+
+	return ret;
+}
+
+/* Reads a page from the oldmem device from given offset. */
+static ssize_t read_from_oldmem(char *buf, size_t count,
+				u64 *ppos, int userbuf)
+{
+	unsigned long pfn, offset;
+	size_t nr_bytes;
+	ssize_t read = 0, tmp;
+
+	if (!count)
+		return 0;
+
+	offset = (unsigned long)(*ppos % PAGE_SIZE);
+	pfn = (unsigned long)(*ppos / PAGE_SIZE);
+
+	do {
+		if (count > (PAGE_SIZE - offset))
+			nr_bytes = PAGE_SIZE - offset;
+		else
+			nr_bytes = count;
+
+		/* If pfn is not ram, return zeros for sparse dump files */
+		if (pfn_is_ram(pfn) == 0)
+			memset(buf, 0, nr_bytes);
+		else {
+			tmp = copy_oldmem_page(pfn, buf, nr_bytes,
+						offset, userbuf);
+			if (tmp < 0)
+				return tmp;
+		}
+		*ppos += nr_bytes;
+		count -= nr_bytes;
+		buf += nr_bytes;
+		read += nr_bytes;
+		++pfn;
+		offset = 0;
+	} while (count);
+
+	return read;
+}
+
+/*
+ * Architectures may override this function to allocate ELF header in 2nd kernel
+ */
+int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
+{
+	return 0;
+}
+
+/*
+ * Architectures may override this function to free header
+ */
+void __weak elfcorehdr_free(unsigned long long addr)
+{}
+
+/*
+ * Architectures may override this function to read from ELF header
+ */
+ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+	return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to read from notes sections
+ */
+ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+	return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to map oldmem
+ */
+int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+				  unsigned long from, unsigned long pfn,
+				  unsigned long size, pgprot_t prot)
+{
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Copy to either kernel or user space
+ */
+static int copy_to(void *target, void *src, size_t size, int userbuf)
+{
+	if (userbuf) {
+		if (copy_to_user((char __user *) target, src, size))
+			return -EFAULT;
+	} else {
+		memcpy(target, src, size);
+	}
+	return 0;
+}
+
+/* Read from the ELF header and then the crash dump. On error, negative value is
+ * returned otherwise number of bytes read are returned.
+ */
+static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
+			     int userbuf)
+{
+	ssize_t acc = 0, tmp;
+	size_t tsz;
+	u64 start;
+	struct vmcore *m = NULL;
+
+	if (buflen == 0 || *fpos >= vmcore_size)
+		return 0;
+
+	/* trim buflen to not go beyond EOF */
+	if (buflen > vmcore_size - *fpos)
+		buflen = vmcore_size - *fpos;
+
+	/* Read ELF core header */
+	if (*fpos < elfcorebuf_sz) {
+		tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
+		if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
+			return -EFAULT;
+		buflen -= tsz;
+		*fpos += tsz;
+		buffer += tsz;
+		acc += tsz;
+
+		/* leave now if filled buffer already */
+		if (buflen == 0)
+			return acc;
+	}
+
+	/* Read Elf note segment */
+	if (*fpos < elfcorebuf_sz + elfnotes_sz) {
+		void *kaddr;
+
+		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
+		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
+		if (copy_to(buffer, kaddr, tsz, userbuf))
+			return -EFAULT;
+		buflen -= tsz;
+		*fpos += tsz;
+		buffer += tsz;
+		acc += tsz;
+
+		/* leave now if filled buffer already */
+		if (buflen == 0)
+			return acc;
+	}
+
+	list_for_each_entry(m, &vmcore_list, list) {
+		if (*fpos < m->offset + m->size) {
+			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
+			start = m->paddr + *fpos - m->offset;
+			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
+			if (tmp < 0)
+				return tmp;
+			buflen -= tsz;
+			*fpos += tsz;
+			buffer += tsz;
+			acc += tsz;
+
+			/* leave now if filled buffer already */
+			if (buflen == 0)
+				return acc;
+		}
+	}
+
+	return acc;
+}
+
+static ssize_t read_vmcore(struct file *file, char __user *buffer,
+			   size_t buflen, loff_t *fpos)
+{
+	return __read_vmcore((__force char *) buffer, buflen, fpos, 1);
+}
+
+/*
+ * The vmcore fault handler uses the page cache and fills data using the
+ * standard __vmcore_read() function.
+ *
+ * On s390 the fault handler is used for memory regions that can't be mapped
+ * directly with remap_pfn_range().
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+#ifdef CONFIG_S390
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	pgoff_t index = vmf->pgoff;
+	struct page *page;
+	loff_t offset;
+	char *buf;
+	int rc;
+
+	page = find_or_create_page(mapping, index, GFP_KERNEL);
+	if (!page)
+		return VM_FAULT_OOM;
+	if (!PageUptodate(page)) {
+		offset = (loff_t) index << PAGE_CACHE_SHIFT;
+		buf = __va((page_to_pfn(page) << PAGE_SHIFT));
+		rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
+		if (rc < 0) {
+			unlock_page(page);
+			page_cache_release(page);
+			return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+		}
+		SetPageUptodate(page);
+	}
+	unlock_page(page);
+	vmf->page = page;
+	return 0;
+#else
+	return VM_FAULT_SIGBUS;
+#endif
+}
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+	.fault = mmap_vmcore_fault,
+};
+
+/**
+ * alloc_elfnotes_buf - allocate buffer for ELF note segment in
+ *                      vmalloc memory
+ *
+ * @notes_sz: size of buffer
+ *
+ * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
+ * the buffer to user-space by means of remap_vmalloc_range().
+ *
+ * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
+ * disabled and there's no need to allow users to mmap the buffer.
+ */
+static inline char *alloc_elfnotes_buf(size_t notes_sz)
+{
+#ifdef CONFIG_MMU
+	return vmalloc_user(notes_sz);
+#else
+	return vzalloc(notes_sz);
+#endif
+}
+
+/*
+ * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is
+ * essential for mmap_vmcore() in order to map physically
+ * non-contiguous objects (ELF header, ELF note segment and memory
+ * regions in the 1st kernel pointed to by PT_LOAD entries) into
+ * virtually contiguous user-space in ELF layout.
+ */
+#ifdef CONFIG_MMU
+/*
+ * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages
+ * reported as not being ram with the zero page.
+ *
+ * @vma: vm_area_struct describing requested mapping
+ * @from: start remapping from
+ * @pfn: page frame number to start remapping to
+ * @size: remapping size
+ * @prot: protection bits
+ *
+ * Returns zero on success, -EAGAIN on failure.
+ */
+static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
+				    unsigned long from, unsigned long pfn,
+				    unsigned long size, pgprot_t prot)
+{
+	unsigned long map_size;
+	unsigned long pos_start, pos_end, pos;
+	unsigned long zeropage_pfn = my_zero_pfn(0);
+	size_t len = 0;
+
+	pos_start = pfn;
+	pos_end = pfn + (size >> PAGE_SHIFT);
+
+	for (pos = pos_start; pos < pos_end; ++pos) {
+		if (!pfn_is_ram(pos)) {
+			/*
+			 * We hit a page which is not ram. Remap the continuous
+			 * region between pos_start and pos-1 and replace
+			 * the non-ram page at pos with the zero page.
+			 */
+			if (pos > pos_start) {
+				/* Remap continuous region */
+				map_size = (pos - pos_start) << PAGE_SHIFT;
+				if (remap_oldmem_pfn_range(vma, from + len,
+							   pos_start, map_size,
+							   prot))
+					goto fail;
+				len += map_size;
+			}
+			/* Remap the zero page */
+			if (remap_oldmem_pfn_range(vma, from + len,
+						   zeropage_pfn,
+						   PAGE_SIZE, prot))
+				goto fail;
+			len += PAGE_SIZE;
+			pos_start = pos + 1;
+		}
+	}
+	if (pos > pos_start) {
+		/* Remap the rest */
+		map_size = (pos - pos_start) << PAGE_SHIFT;
+		if (remap_oldmem_pfn_range(vma, from + len, pos_start,
+					   map_size, prot))
+			goto fail;
+	}
+	return 0;
+fail:
+	do_munmap(vma->vm_mm, from, len);
+	return -EAGAIN;
+}
+
+static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
+			    unsigned long from, unsigned long pfn,
+			    unsigned long size, pgprot_t prot)
+{
+	/*
+	 * Check if oldmem_pfn_is_ram was registered to avoid
+	 * looping over all pages without a reason.
+	 */
+	if (oldmem_pfn_is_ram)
+		return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+	else
+		return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+}
+
+static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+	u64 start, end, len, tsz;
+	struct vmcore *m;
+
+	start = (u64)vma->vm_pgoff << PAGE_SHIFT;
+	end = start + size;
+
+	if (size > vmcore_size || end > vmcore_size)
+		return -EINVAL;
+
+	if (vma->vm_flags & (VM_WRITE | VM_EXEC))
+		return -EPERM;
+
+	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
+	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_ops = &vmcore_mmap_ops;
+
+	len = 0;
+
+	if (start < elfcorebuf_sz) {
+		u64 pfn;
+
+		tsz = min(elfcorebuf_sz - (size_t)start, size);
+		pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT;
+		if (remap_pfn_range(vma, vma->vm_start, pfn, tsz,
+				    vma->vm_page_prot))
+			return -EAGAIN;
+		size -= tsz;
+		start += tsz;
+		len += tsz;
+
+		if (size == 0)
+			return 0;
+	}
+
+	if (start < elfcorebuf_sz + elfnotes_sz) {
+		void *kaddr;
+
+		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
+		kaddr = elfnotes_buf + start - elfcorebuf_sz;
+		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
+						kaddr, tsz))
+			goto fail;
+		size -= tsz;
+		start += tsz;
+		len += tsz;
+
+		if (size == 0)
+			return 0;
+	}
+
+	list_for_each_entry(m, &vmcore_list, list) {
+		if (start < m->offset + m->size) {
+			u64 paddr = 0;
+
+			tsz = min_t(size_t, m->offset + m->size - start, size);
+			paddr = m->paddr + start - m->offset;
+			if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
+						    paddr >> PAGE_SHIFT, tsz,
+						    vma->vm_page_prot))
+				goto fail;
+			size -= tsz;
+			start += tsz;
+			len += tsz;
+
+			if (size == 0)
+				return 0;
+		}
+	}
+
+	return 0;
+fail:
+	do_munmap(vma->vm_mm, vma->vm_start, len);
+	return -EAGAIN;
+}
+#else
+static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+{
+	return -ENOSYS;
+}
+#endif
+
+static const struct file_operations proc_vmcore_operations = {
+	.read		= read_vmcore,
+	.llseek		= default_llseek,
+	.mmap		= mmap_vmcore,
+};
+
+static struct vmcore* __init get_new_element(void)
+{
+	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
+}
+
+static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
+				  struct list_head *vc_list)
+{
+	u64 size;
+	struct vmcore *m;
+
+	size = elfsz + elfnotesegsz;
+	list_for_each_entry(m, vc_list, list) {
+		size += m->size;
+	}
+	return size;
+}
+
+/**
+ * update_note_header_size_elf64 - update p_memsz member of each PT_NOTE entry
+ *
+ * @ehdr_ptr: ELF header
+ *
+ * This function updates p_memsz member of each PT_NOTE entry in the
+ * program header table pointed to by @ehdr_ptr to real size of ELF
+ * note segment.
+ */
+static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
+{
+	int i, rc=0;
+	Elf64_Phdr *phdr_ptr;
+	Elf64_Nhdr *nhdr_ptr;
+
+	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		void *notes_section;
+		u64 offset, max_sz, sz, real_sz = 0;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		max_sz = phdr_ptr->p_memsz;
+		offset = phdr_ptr->p_offset;
+		notes_section = kmalloc(max_sz, GFP_KERNEL);
+		if (!notes_section)
+			return -ENOMEM;
+		rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
+		if (rc < 0) {
+			kfree(notes_section);
+			return rc;
+		}
+		nhdr_ptr = notes_section;
+		while (nhdr_ptr->n_namesz != 0) {
+			sz = sizeof(Elf64_Nhdr) +
+				(((u64)nhdr_ptr->n_namesz + 3) & ~3) +
+				(((u64)nhdr_ptr->n_descsz + 3) & ~3);
+			if ((real_sz + sz) > max_sz) {
+				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+				break;
+			}
+			real_sz += sz;
+			nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
+		}
+		kfree(notes_section);
+		phdr_ptr->p_memsz = real_sz;
+		if (real_sz == 0) {
+			pr_warn("Warning: Zero PT_NOTE entries found\n");
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * get_note_number_and_size_elf64 - get the number of PT_NOTE program
+ * headers and sum of real size of their ELF note segment headers and
+ * data.
+ *
+ * @ehdr_ptr: ELF header
+ * @nr_ptnote: buffer for the number of PT_NOTE program headers
+ * @sz_ptnote: buffer for size of unique PT_NOTE program header
+ *
+ * This function is used to merge multiple PT_NOTE program headers
+ * into a unique single one. The resulting unique entry will have
+ * @sz_ptnote in its phdr->p_mem.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf64
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init get_note_number_and_size_elf64(const Elf64_Ehdr *ehdr_ptr,
+						 int *nr_ptnote, u64 *sz_ptnote)
+{
+	int i;
+	Elf64_Phdr *phdr_ptr;
+
+	*nr_ptnote = *sz_ptnote = 0;
+
+	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		*nr_ptnote += 1;
+		*sz_ptnote += phdr_ptr->p_memsz;
+	}
+
+	return 0;
+}
+
+/**
+ * copy_notes_elf64 - copy ELF note segments in a given buffer
+ *
+ * @ehdr_ptr: ELF header
+ * @notes_buf: buffer into which ELF note segments are copied
+ *
+ * This function is used to copy ELF note segment in the 1st kernel
+ * into the buffer @notes_buf in the 2nd kernel. It is assumed that
+ * size of the buffer @notes_buf is equal to or larger than sum of the
+ * real ELF note segment headers and data.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf64
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf)
+{
+	int i, rc=0;
+	Elf64_Phdr *phdr_ptr;
+
+	phdr_ptr = (Elf64_Phdr*)(ehdr_ptr + 1);
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 offset;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		offset = phdr_ptr->p_offset;
+		rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+					   &offset);
+		if (rc < 0)
+			return rc;
+		notes_buf += phdr_ptr->p_memsz;
+	}
+
+	return 0;
+}
+
+/* Merges all the PT_NOTE headers into one. */
+static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
+					   char **notes_buf, size_t *notes_sz)
+{
+	int i, nr_ptnote=0, rc=0;
+	char *tmp;
+	Elf64_Ehdr *ehdr_ptr;
+	Elf64_Phdr phdr;
+	u64 phdr_sz = 0, note_off;
+
+	ehdr_ptr = (Elf64_Ehdr *)elfptr;
+
+	rc = update_note_header_size_elf64(ehdr_ptr);
+	if (rc < 0)
+		return rc;
+
+	rc = get_note_number_and_size_elf64(ehdr_ptr, &nr_ptnote, &phdr_sz);
+	if (rc < 0)
+		return rc;
+
+	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
+	*notes_buf = alloc_elfnotes_buf(*notes_sz);
+	if (!*notes_buf)
+		return -ENOMEM;
+
+	rc = copy_notes_elf64(ehdr_ptr, *notes_buf);
+	if (rc < 0)
+		return rc;
+
+	/* Prepare merged PT_NOTE program header. */
+	phdr.p_type    = PT_NOTE;
+	phdr.p_flags   = 0;
+	note_off = sizeof(Elf64_Ehdr) +
+			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr);
+	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
+	phdr.p_vaddr   = phdr.p_paddr = 0;
+	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
+	phdr.p_align   = 0;
+
+	/* Add merged PT_NOTE program header*/
+	tmp = elfptr + sizeof(Elf64_Ehdr);
+	memcpy(tmp, &phdr, sizeof(phdr));
+	tmp += sizeof(phdr);
+
+	/* Remove unwanted PT_NOTE program headers. */
+	i = (nr_ptnote - 1) * sizeof(Elf64_Phdr);
+	*elfsz = *elfsz - i;
+	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr)));
+	memset(elfptr + *elfsz, 0, i);
+	*elfsz = roundup(*elfsz, PAGE_SIZE);
+
+	/* Modify e_phnum to reflect merged headers. */
+	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
+
+	return 0;
+}
+
+/**
+ * update_note_header_size_elf32 - update p_memsz member of each PT_NOTE entry
+ *
+ * @ehdr_ptr: ELF header
+ *
+ * This function updates p_memsz member of each PT_NOTE entry in the
+ * program header table pointed to by @ehdr_ptr to real size of ELF
+ * note segment.
+ */
+static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
+{
+	int i, rc=0;
+	Elf32_Phdr *phdr_ptr;
+	Elf32_Nhdr *nhdr_ptr;
+
+	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		void *notes_section;
+		u64 offset, max_sz, sz, real_sz = 0;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		max_sz = phdr_ptr->p_memsz;
+		offset = phdr_ptr->p_offset;
+		notes_section = kmalloc(max_sz, GFP_KERNEL);
+		if (!notes_section)
+			return -ENOMEM;
+		rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
+		if (rc < 0) {
+			kfree(notes_section);
+			return rc;
+		}
+		nhdr_ptr = notes_section;
+		while (nhdr_ptr->n_namesz != 0) {
+			sz = sizeof(Elf32_Nhdr) +
+				(((u64)nhdr_ptr->n_namesz + 3) & ~3) +
+				(((u64)nhdr_ptr->n_descsz + 3) & ~3);
+			if ((real_sz + sz) > max_sz) {
+				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+				break;
+			}
+			real_sz += sz;
+			nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
+		}
+		kfree(notes_section);
+		phdr_ptr->p_memsz = real_sz;
+		if (real_sz == 0) {
+			pr_warn("Warning: Zero PT_NOTE entries found\n");
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * get_note_number_and_size_elf32 - get the number of PT_NOTE program
+ * headers and sum of real size of their ELF note segment headers and
+ * data.
+ *
+ * @ehdr_ptr: ELF header
+ * @nr_ptnote: buffer for the number of PT_NOTE program headers
+ * @sz_ptnote: buffer for size of unique PT_NOTE program header
+ *
+ * This function is used to merge multiple PT_NOTE program headers
+ * into a unique single one. The resulting unique entry will have
+ * @sz_ptnote in its phdr->p_mem.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf32
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init get_note_number_and_size_elf32(const Elf32_Ehdr *ehdr_ptr,
+						 int *nr_ptnote, u64 *sz_ptnote)
+{
+	int i;
+	Elf32_Phdr *phdr_ptr;
+
+	*nr_ptnote = *sz_ptnote = 0;
+
+	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		*nr_ptnote += 1;
+		*sz_ptnote += phdr_ptr->p_memsz;
+	}
+
+	return 0;
+}
+
+/**
+ * copy_notes_elf32 - copy ELF note segments in a given buffer
+ *
+ * @ehdr_ptr: ELF header
+ * @notes_buf: buffer into which ELF note segments are copied
+ *
+ * This function is used to copy ELF note segment in the 1st kernel
+ * into the buffer @notes_buf in the 2nd kernel. It is assumed that
+ * size of the buffer @notes_buf is equal to or larger than sum of the
+ * real ELF note segment headers and data.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf32
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf)
+{
+	int i, rc=0;
+	Elf32_Phdr *phdr_ptr;
+
+	phdr_ptr = (Elf32_Phdr*)(ehdr_ptr + 1);
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 offset;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		offset = phdr_ptr->p_offset;
+		rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+					   &offset);
+		if (rc < 0)
+			return rc;
+		notes_buf += phdr_ptr->p_memsz;
+	}
+
+	return 0;
+}
+
+/* Merges all the PT_NOTE headers into one. */
+static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
+					   char **notes_buf, size_t *notes_sz)
+{
+	int i, nr_ptnote=0, rc=0;
+	char *tmp;
+	Elf32_Ehdr *ehdr_ptr;
+	Elf32_Phdr phdr;
+	u64 phdr_sz = 0, note_off;
+
+	ehdr_ptr = (Elf32_Ehdr *)elfptr;
+
+	rc = update_note_header_size_elf32(ehdr_ptr);
+	if (rc < 0)
+		return rc;
+
+	rc = get_note_number_and_size_elf32(ehdr_ptr, &nr_ptnote, &phdr_sz);
+	if (rc < 0)
+		return rc;
+
+	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
+	*notes_buf = alloc_elfnotes_buf(*notes_sz);
+	if (!*notes_buf)
+		return -ENOMEM;
+
+	rc = copy_notes_elf32(ehdr_ptr, *notes_buf);
+	if (rc < 0)
+		return rc;
+
+	/* Prepare merged PT_NOTE program header. */
+	phdr.p_type    = PT_NOTE;
+	phdr.p_flags   = 0;
+	note_off = sizeof(Elf32_Ehdr) +
+			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr);
+	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
+	phdr.p_vaddr   = phdr.p_paddr = 0;
+	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
+	phdr.p_align   = 0;
+
+	/* Add merged PT_NOTE program header*/
+	tmp = elfptr + sizeof(Elf32_Ehdr);
+	memcpy(tmp, &phdr, sizeof(phdr));
+	tmp += sizeof(phdr);
+
+	/* Remove unwanted PT_NOTE program headers. */
+	i = (nr_ptnote - 1) * sizeof(Elf32_Phdr);
+	*elfsz = *elfsz - i;
+	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr)));
+	memset(elfptr + *elfsz, 0, i);
+	*elfsz = roundup(*elfsz, PAGE_SIZE);
+
+	/* Modify e_phnum to reflect merged headers. */
+	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
+
+	return 0;
+}
+
+/* Add memory chunks represented by program headers to vmcore list. Also update
+ * the new offset fields of exported program headers. */
+static int __init process_ptload_program_headers_elf64(char *elfptr,
+						size_t elfsz,
+						size_t elfnotes_sz,
+						struct list_head *vc_list)
+{
+	int i;
+	Elf64_Ehdr *ehdr_ptr;
+	Elf64_Phdr *phdr_ptr;
+	loff_t vmcore_off;
+	struct vmcore *new;
+
+	ehdr_ptr = (Elf64_Ehdr *)elfptr;
+	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
+
+	/* Skip Elf header, program headers and Elf note segment. */
+	vmcore_off = elfsz + elfnotes_sz;
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 paddr, start, end, size;
+
+		if (phdr_ptr->p_type != PT_LOAD)
+			continue;
+
+		paddr = phdr_ptr->p_offset;
+		start = rounddown(paddr, PAGE_SIZE);
+		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
+		size = end - start;
+
+		/* Add this contiguous chunk of memory to vmcore list.*/
+		new = get_new_element();
+		if (!new)
+			return -ENOMEM;
+		new->paddr = start;
+		new->size = size;
+		list_add_tail(&new->list, vc_list);
+
+		/* Update the program header offset. */
+		phdr_ptr->p_offset = vmcore_off + (paddr - start);
+		vmcore_off = vmcore_off + size;
+	}
+	return 0;
+}
+
+static int __init process_ptload_program_headers_elf32(char *elfptr,
+						size_t elfsz,
+						size_t elfnotes_sz,
+						struct list_head *vc_list)
+{
+	int i;
+	Elf32_Ehdr *ehdr_ptr;
+	Elf32_Phdr *phdr_ptr;
+	loff_t vmcore_off;
+	struct vmcore *new;
+
+	ehdr_ptr = (Elf32_Ehdr *)elfptr;
+	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */
+
+	/* Skip Elf header, program headers and Elf note segment. */
+	vmcore_off = elfsz + elfnotes_sz;
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 paddr, start, end, size;
+
+		if (phdr_ptr->p_type != PT_LOAD)
+			continue;
+
+		paddr = phdr_ptr->p_offset;
+		start = rounddown(paddr, PAGE_SIZE);
+		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
+		size = end - start;
+
+		/* Add this contiguous chunk of memory to vmcore list.*/
+		new = get_new_element();
+		if (!new)
+			return -ENOMEM;
+		new->paddr = start;
+		new->size = size;
+		list_add_tail(&new->list, vc_list);
+
+		/* Update the program header offset */
+		phdr_ptr->p_offset = vmcore_off + (paddr - start);
+		vmcore_off = vmcore_off + size;
+	}
+	return 0;
+}
+
+/* Sets offset fields of vmcore elements. */
+static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
+					   struct list_head *vc_list)
+{
+	loff_t vmcore_off;
+	struct vmcore *m;
+
+	/* Skip Elf header, program headers and Elf note segment. */
+	vmcore_off = elfsz + elfnotes_sz;
+
+	list_for_each_entry(m, vc_list, list) {
+		m->offset = vmcore_off;
+		vmcore_off += m->size;
+	}
+}
+
+static void free_elfcorebuf(void)
+{
+	free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
+	elfcorebuf = NULL;
+	vfree(elfnotes_buf);
+	elfnotes_buf = NULL;
+}
+
+static int __init parse_crash_elf64_headers(void)
+{
+	int rc=0;
+	Elf64_Ehdr ehdr;
+	u64 addr;
+
+	addr = elfcorehdr_addr;
+
+	/* Read Elf header */
+	rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr);
+	if (rc < 0)
+		return rc;
+
+	/* Do some basic Verification. */
+	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
+		(ehdr.e_type != ET_CORE) ||
+		!vmcore_elf64_check_arch(&ehdr) ||
+		ehdr.e_ident[EI_CLASS] != ELFCLASS64 ||
+		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
+		ehdr.e_version != EV_CURRENT ||
+		ehdr.e_ehsize != sizeof(Elf64_Ehdr) ||
+		ehdr.e_phentsize != sizeof(Elf64_Phdr) ||
+		ehdr.e_phnum == 0) {
+		pr_warn("Warning: Core image elf header is not sane\n");
+		return -EINVAL;
+	}
+
+	/* Read in all elf headers. */
+	elfcorebuf_sz_orig = sizeof(Elf64_Ehdr) +
+				ehdr.e_phnum * sizeof(Elf64_Phdr);
+	elfcorebuf_sz = elfcorebuf_sz_orig;
+	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					      get_order(elfcorebuf_sz_orig));
+	if (!elfcorebuf)
+		return -ENOMEM;
+	addr = elfcorehdr_addr;
+	rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
+	if (rc < 0)
+		goto fail;
+
+	/* Merge all PT_NOTE headers into one. */
+	rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz,
+				      &elfnotes_buf, &elfnotes_sz);
+	if (rc)
+		goto fail;
+	rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz,
+						  elfnotes_sz, &vmcore_list);
+	if (rc)
+		goto fail;
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+	return 0;
+fail:
+	free_elfcorebuf();
+	return rc;
+}
+
+static int __init parse_crash_elf32_headers(void)
+{
+	int rc=0;
+	Elf32_Ehdr ehdr;
+	u64 addr;
+
+	addr = elfcorehdr_addr;
+
+	/* Read Elf header */
+	rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr);
+	if (rc < 0)
+		return rc;
+
+	/* Do some basic Verification. */
+	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
+		(ehdr.e_type != ET_CORE) ||
+		!elf_check_arch(&ehdr) ||
+		ehdr.e_ident[EI_CLASS] != ELFCLASS32||
+		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
+		ehdr.e_version != EV_CURRENT ||
+		ehdr.e_ehsize != sizeof(Elf32_Ehdr) ||
+		ehdr.e_phentsize != sizeof(Elf32_Phdr) ||
+		ehdr.e_phnum == 0) {
+		pr_warn("Warning: Core image elf header is not sane\n");
+		return -EINVAL;
+	}
+
+	/* Read in all elf headers. */
+	elfcorebuf_sz_orig = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr);
+	elfcorebuf_sz = elfcorebuf_sz_orig;
+	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					      get_order(elfcorebuf_sz_orig));
+	if (!elfcorebuf)
+		return -ENOMEM;
+	addr = elfcorehdr_addr;
+	rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
+	if (rc < 0)
+		goto fail;
+
+	/* Merge all PT_NOTE headers into one. */
+	rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz,
+				      &elfnotes_buf, &elfnotes_sz);
+	if (rc)
+		goto fail;
+	rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz,
+						  elfnotes_sz, &vmcore_list);
+	if (rc)
+		goto fail;
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+	return 0;
+fail:
+	free_elfcorebuf();
+	return rc;
+}
+
+static int __init parse_crash_elf_headers(void)
+{
+	unsigned char e_ident[EI_NIDENT];
+	u64 addr;
+	int rc=0;
+
+	addr = elfcorehdr_addr;
+	rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr);
+	if (rc < 0)
+		return rc;
+	if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
+		pr_warn("Warning: Core image elf header not found\n");
+		return -EINVAL;
+	}
+
+	if (e_ident[EI_CLASS] == ELFCLASS64) {
+		rc = parse_crash_elf64_headers();
+		if (rc)
+			return rc;
+	} else if (e_ident[EI_CLASS] == ELFCLASS32) {
+		rc = parse_crash_elf32_headers();
+		if (rc)
+			return rc;
+	} else {
+		pr_warn("Warning: Core image elf header is not sane\n");
+		return -EINVAL;
+	}
+
+	/* Determine vmcore size. */
+	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+				      &vmcore_list);
+
+	return 0;
+}
+
+/* Init function for vmcore module. */
+static int __init vmcore_init(void)
+{
+	int rc = 0;
+
+	/* Allow architectures to allocate ELF header in 2nd kernel */
+	rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size);
+	if (rc)
+		return rc;
+	/*
+	 * If elfcorehdr= has been passed in cmdline or created in 2nd kernel,
+	 * then capture the dump.
+	 */
+	if (!(is_vmcore_usable()))
+		return rc;
+	rc = parse_crash_elf_headers();
+	if (rc) {
+		pr_warn("Kdump: vmcore not initialized\n");
+		return rc;
+	}
+	elfcorehdr_free(elfcorehdr_addr);
+	elfcorehdr_addr = ELFCORE_ADDR_ERR;
+
+	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
+	if (proc_vmcore)
+		proc_vmcore->size = vmcore_size;
+	return 0;
+}
+fs_initcall(vmcore_init);
+
+/* Cleanup function for vmcore module. */
+void vmcore_cleanup(void)
+{
+	struct list_head *pos, *next;
+
+	if (proc_vmcore) {
+		proc_remove(proc_vmcore);
+		proc_vmcore = NULL;
+	}
+
+	/* clear the vmcore list. */
+	list_for_each_safe(pos, next, &vmcore_list) {
+		struct vmcore *m;
+
+		m = list_entry(pos, struct vmcore, list);
+		list_del(&m->list);
+		kfree(m);
+	}
+	free_elfcorebuf();
+}