add idl4k kernel firmware version 1.13.0.105

kernel/fs/proc/Kconfig

@@ -0,0 +1,69 @@
+config PROC_FS
+	bool "/proc file system support" if EMBEDDED
+	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
+
+config PROC_VMCORE
+        bool "/proc/vmcore support (EXPERIMENTAL)"
+        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 EMBEDDED
+	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 EMBEDDED
+ 	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.

kernel/fs/proc/Makefile

@@ -0,0 +1,28 @@
+#
+# Makefile for the Linux proc filesystem routines.
+#
+
+obj-$(CONFIG_PROC_FS) += proc.o
+
+proc-y			:= nommu.o task_nommu.o
+proc-$(CONFIG_MMU)	:= mmu.o task_mmu.o
+
+proc-y       += inode.o root.o base.o generic.o array.o \
+		proc_tty.o
+proc-y	+= cmdline.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-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
+proc-$(CONFIG_NET)		+= proc_net.o
+proc-$(CONFIG_PROC_KCORE)	+= kcore.o
+proc-$(CONFIG_PROC_VMCORE)	+= vmcore.o
+proc-$(CONFIG_PROC_DEVICETREE)	+= proc_devtree.o
+proc-$(CONFIG_PRINTK)	+= kmsg.o
+proc-$(CONFIG_PROC_PAGE_MONITOR)	+= page.o

kernel/fs/proc/array.c

@@ -0,0 +1,530 @@
+/*
+ *  linux/fs/proc/array.c
+ *
+ *  Copyright (C) 1992  by Linus Torvalds
+ *  based on ideas by Darren Senn
+ *
+ * Fixes:
+ * Michael. K. Johnson: stat,statm extensions.
+ *                      <johnsonm@stolaf.edu>
+ *
+ * Pauline Middelink :  Made cmdline,envline only break at '\0's, to
+ *                      make sure SET_PROCTITLE works. Also removed
+ *                      bad '!' which forced address recalculation for
+ *                      EVERY character on the current page.
+ *                      <middelin@polyware.iaf.nl>
+ *
+ * Danny ter Haar    :	added cpuinfo
+ *			<dth@cistron.nl>
+ *
+ * Alessandro Rubini :  profile extension.
+ *                      <rubini@ipvvis.unipv.it>
+ *
+ * Jeff Tranter      :  added BogoMips field to cpuinfo
+ *                      <Jeff_Tranter@Mitel.COM>
+ *
+ * Bruno Haible      :  remove 4K limit for the maps file
+ *			<haible@ma2s2.mathematik.uni-karlsruhe.de>
+ *
+ * Yves Arrouye      :  remove removal of trailing spaces in get_array.
+ *			<Yves.Arrouye@marin.fdn.fr>
+ *
+ * Jerome Forissier  :  added per-CPU time information to /proc/stat
+ *                      and /proc/<pid>/cpu extension
+ *                      <forissier@isia.cma.fr>
+ *			- Incorporation and non-SMP safe operation
+ *			of forissier patch in 2.1.78 by
+ *			Hans Marcus <crowbar@concepts.nl>
+ *
+ * aeb@cwi.nl        :  /proc/partitions
+ *
+ *
+ * Alan Cox	     :  security fixes.
+ *			<alan@lxorguk.ukuu.org.uk>
+ *
+ * Al Viro           :  safe handling of mm_struct
+ *
+ * Gerhard Wichert   :  added BIGMEM support
+ * Siemens AG           <Gerhard.Wichert@pdb.siemens.de>
+ *
+ * Al Viro & Jeff Garzik :  moved most of the thing into base.c and
+ *			 :  proc_misc.c. The rest may eventually go into
+ *			 :  base.c too.
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/tty.h>
+#include <linux/string.h>
+#include <linux/mman.h>
+#include <linux/proc_fs.h>
+#include <linux/ioport.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/signal.h>
+#include <linux/highmem.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/times.h>
+#include <linux/cpuset.h>
+#include <linux/rcupdate.h>
+#include <linux/delayacct.h>
+#include <linux/seq_file.h>
+#include <linux/pid_namespace.h>
+#include <linux/ptrace.h>
+#include <linux/tracehook.h>
+
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include "internal.h"
+
+static inline void task_name(struct seq_file *m, struct task_struct *p)
+{
+	int i;
+	char *buf, *end;
+	char *name;
+	char tcomm[sizeof(p->comm)];
+
+	get_task_comm(tcomm, p);
+
+	seq_printf(m, "Name:\t");
+	end = m->buf + m->size;
+	buf = m->buf + m->count;
+	name = tcomm;
+	i = sizeof(tcomm);
+	while (i && (buf < end)) {
+		unsigned char c = *name;
+		name++;
+		i--;
+		*buf = c;
+		if (!c)
+			break;
+		if (c == '\\') {
+			buf++;
+			if (buf < end)
+				*buf++ = c;
+			continue;
+		}
+		if (c == '\n') {
+			*buf++ = '\\';
+			if (buf < end)
+				*buf++ = 'n';
+			continue;
+		}
+		buf++;
+	}
+	m->count = buf - m->buf;
+	seq_printf(m, "\n");
+}
+
+/*
+ * The task state array is a strange "bitmap" of
+ * reasons to sleep. Thus "running" is zero, and
+ * you can test for combinations of others with
+ * simple bit tests.
+ */
+static const char *task_state_array[] = {
+	"R (running)",		/*  0 */
+	"S (sleeping)",		/*  1 */
+	"D (disk sleep)",	/*  2 */
+	"T (stopped)",		/*  4 */
+	"T (tracing stop)",	/*  8 */
+	"Z (zombie)",		/* 16 */
+	"X (dead)"		/* 32 */
+};
+
+static inline const char *get_task_state(struct task_struct *tsk)
+{
+	unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state;
+	const char **p = &task_state_array[0];
+
+	while (state) {
+		p++;
+		state >>= 1;
+	}
+	return *p;
+}
+
+static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *p)
+{
+	struct group_info *group_info;
+	int g;
+	struct fdtable *fdt = NULL;
+	const struct cred *cred;
+	pid_t ppid, tpid;
+
+	rcu_read_lock();
+	ppid = pid_alive(p) ?
+		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
+	tpid = 0;
+	if (pid_alive(p)) {
+		struct task_struct *tracer = tracehook_tracer_task(p);
+		if (tracer)
+			tpid = task_pid_nr_ns(tracer, ns);
+	}
+	cred = get_task_cred(p);
+	seq_printf(m,
+		"State:\t%s\n"
+		"Tgid:\t%d\n"
+		"Pid:\t%d\n"
+		"PPid:\t%d\n"
+		"TracerPid:\t%d\n"
+		"Uid:\t%d\t%d\t%d\t%d\n"
+		"Gid:\t%d\t%d\t%d\t%d\n",
+		get_task_state(p),
+		task_tgid_nr_ns(p, ns),
+		pid_nr_ns(pid, ns),
+		ppid, tpid,
+		cred->uid, cred->euid, cred->suid, cred->fsuid,
+		cred->gid, cred->egid, cred->sgid, cred->fsgid);
+
+	task_lock(p);
+	if (p->files)
+		fdt = files_fdtable(p->files);
+	seq_printf(m,
+		"FDSize:\t%d\n"
+		"Groups:\t",
+		fdt ? fdt->max_fds : 0);
+	rcu_read_unlock();
+
+	group_info = cred->group_info;
+	task_unlock(p);
+
+	for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
+		seq_printf(m, "%d ", GROUP_AT(group_info, g));
+	put_cred(cred);
+
+	seq_printf(m, "\n");
+}
+
+static void render_sigset_t(struct seq_file *m, const char *header,
+				sigset_t *set)
+{
+	int i;
+
+	seq_printf(m, "%s", header);
+
+	i = _NSIG;
+	do {
+		int x = 0;
+
+		i -= 4;
+		if (sigismember(set, i+1)) x |= 1;
+		if (sigismember(set, i+2)) x |= 2;
+		if (sigismember(set, i+3)) x |= 4;
+		if (sigismember(set, i+4)) x |= 8;
+		seq_printf(m, "%x", x);
+	} while (i >= 4);
+
+	seq_printf(m, "\n");
+}
+
+static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
+				    sigset_t *catch)
+{
+	struct k_sigaction *k;
+	int i;
+
+	k = p->sighand->action;
+	for (i = 1; i <= _NSIG; ++i, ++k) {
+		if (k->sa.sa_handler == SIG_IGN)
+			sigaddset(ign, i);
+		else if (k->sa.sa_handler != SIG_DFL)
+			sigaddset(catch, i);
+	}
+}
+
+static inline void task_sig(struct seq_file *m, struct task_struct *p)
+{
+	unsigned long flags;
+	sigset_t pending, shpending, blocked, ignored, caught;
+	int num_threads = 0;
+	unsigned long qsize = 0;
+	unsigned long qlim = 0;
+
+	sigemptyset(&pending);
+	sigemptyset(&shpending);
+	sigemptyset(&blocked);
+	sigemptyset(&ignored);
+	sigemptyset(&caught);
+
+	if (lock_task_sighand(p, &flags)) {
+		pending = p->pending.signal;
+		shpending = p->signal->shared_pending.signal;
+		blocked = p->blocked;
+		collect_sigign_sigcatch(p, &ignored, &caught);
+		num_threads = atomic_read(&p->signal->count);
+		qsize = atomic_read(&__task_cred(p)->user->sigpending);
+		qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
+		unlock_task_sighand(p, &flags);
+	}
+
+	seq_printf(m, "Threads:\t%d\n", num_threads);
+	seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
+
+	/* render them all */
+	render_sigset_t(m, "SigPnd:\t", &pending);
+	render_sigset_t(m, "ShdPnd:\t", &shpending);
+	render_sigset_t(m, "SigBlk:\t", &blocked);
+	render_sigset_t(m, "SigIgn:\t", &ignored);
+	render_sigset_t(m, "SigCgt:\t", &caught);
+}
+
+static void render_cap_t(struct seq_file *m, const char *header,
+			kernel_cap_t *a)
+{
+	unsigned __capi;
+
+	seq_printf(m, "%s", header);
+	CAP_FOR_EACH_U32(__capi) {
+		seq_printf(m, "%08x",
+			   a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
+	}
+	seq_printf(m, "\n");
+}
+
+static inline void task_cap(struct seq_file *m, struct task_struct *p)
+{
+	const struct cred *cred;
+	kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset;
+
+	rcu_read_lock();
+	cred = __task_cred(p);
+	cap_inheritable	= cred->cap_inheritable;
+	cap_permitted	= cred->cap_permitted;
+	cap_effective	= cred->cap_effective;
+	cap_bset	= cred->cap_bset;
+	rcu_read_unlock();
+
+	render_cap_t(m, "CapInh:\t", &cap_inheritable);
+	render_cap_t(m, "CapPrm:\t", &cap_permitted);
+	render_cap_t(m, "CapEff:\t", &cap_effective);
+	render_cap_t(m, "CapBnd:\t", &cap_bset);
+}
+
+static inline void task_context_switch_counts(struct seq_file *m,
+						struct task_struct *p)
+{
+	seq_printf(m,	"voluntary_ctxt_switches:\t%lu\n"
+			"nonvoluntary_ctxt_switches:\t%lu\n",
+			p->nvcsw,
+			p->nivcsw);
+}
+
+int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm = get_task_mm(task);
+
+	task_name(m, task);
+	task_state(m, ns, pid, task);
+
+	if (mm) {
+		task_mem(m, mm);
+		mmput(mm);
+	}
+	task_sig(m, task);
+	task_cap(m, task);
+	cpuset_task_status_allowed(m, task);
+	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;
+	long priority, nice;
+	int tty_pgrp = -1, tty_nr = 0;
+	sigset_t sigign, sigcatch;
+	char state;
+	pid_t ppid = 0, pgid = -1, sid = -1;
+	int num_threads = 0;
+	int permitted;
+	struct mm_struct *mm;
+	unsigned long long start_time;
+	unsigned long cmin_flt = 0, cmaj_flt = 0;
+	unsigned long  min_flt = 0,  maj_flt = 0;
+	cputime_t cutime, cstime, utime, stime;
+	cputime_t cgtime, gtime;
+	unsigned long rsslim = 0;
+	char tcomm[sizeof(task->comm)];
+	unsigned long flags;
+
+	state = *get_task_state(task);
+	vsize = eip = esp = 0;
+	permitted = ptrace_may_access(task, PTRACE_MODE_READ);
+	mm = get_task_mm(task);
+	if (mm) {
+		vsize = task_vsize(mm);
+		if (permitted) {
+			eip = KSTK_EIP(task);
+			esp = KSTK_ESP(task);
+		}
+	}
+
+	get_task_comm(tcomm, task);
+
+	sigemptyset(&sigign);
+	sigemptyset(&sigcatch);
+	cutime = cstime = utime = stime = cputime_zero;
+	cgtime = gtime = cputime_zero;
+
+	if (lock_task_sighand(task, &flags)) {
+		struct signal_struct *sig = task->signal;
+
+		if (sig->tty) {
+			struct pid *pgrp = tty_get_pgrp(sig->tty);
+			tty_pgrp = pid_nr_ns(pgrp, ns);
+			put_pid(pgrp);
+			tty_nr = new_encode_dev(tty_devnum(sig->tty));
+		}
+
+		num_threads = atomic_read(&sig->count);
+		collect_sigign_sigcatch(task, &sigign, &sigcatch);
+
+		cmin_flt = sig->cmin_flt;
+		cmaj_flt = sig->cmaj_flt;
+		cutime = sig->cutime;
+		cstime = sig->cstime;
+		cgtime = sig->cgtime;
+		rsslim = sig->rlim[RLIMIT_RSS].rlim_cur;
+
+		/* add up live thread stats at the group level */
+		if (whole) {
+			struct task_struct *t = task;
+			do {
+				min_flt += t->min_flt;
+				maj_flt += t->maj_flt;
+				gtime = cputime_add(gtime, task_gtime(t));
+				t = next_thread(t);
+			} while (t != task);
+
+			min_flt += sig->min_flt;
+			maj_flt += sig->maj_flt;
+			thread_group_times(task, &utime, &stime);
+			gtime = cputime_add(gtime, sig->gtime);
+		}
+
+		sid = task_session_nr_ns(task, ns);
+		ppid = task_tgid_nr_ns(task->real_parent, ns);
+		pgid = task_pgrp_nr_ns(task, ns);
+
+		unlock_task_sighand(task, &flags);
+	}
+
+	if (permitted && (!whole || num_threads < 2))
+		wchan = get_wchan(task);
+	if (!whole) {
+		min_flt = task->min_flt;
+		maj_flt = task->maj_flt;
+		utime = task_utime(task);
+		stime = task_stime(task);
+		gtime = task_gtime(task);
+	}
+
+	/* scale priority and nice values from timeslices to -20..20 */
+	/* to make it look like a "normal" Unix priority/nice value  */
+	priority = task_prio(task);
+	nice = task_nice(task);
+
+	/* Temporary variable needed for gcc-2.96 */
+	/* convert timespec -> nsec*/
+	start_time =
+		(unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC
+				+ task->real_start_time.tv_nsec;
+	/* convert nsec -> ticks */
+	start_time = nsec_to_clock_t(start_time);
+
+	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
+%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
+%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
+		pid_nr_ns(pid, ns),
+		tcomm,
+		state,
+		ppid,
+		pgid,
+		sid,
+		tty_nr,
+		tty_pgrp,
+		task->flags,
+		min_flt,
+		cmin_flt,
+		maj_flt,
+		cmaj_flt,
+		cputime_to_clock_t(utime),
+		cputime_to_clock_t(stime),
+		cputime_to_clock_t(cutime),
+		cputime_to_clock_t(cstime),
+		priority,
+		nice,
+		num_threads,
+		start_time,
+		vsize,
+		mm ? get_mm_rss(mm) : 0,
+		rsslim,
+		mm ? (permitted ? mm->start_code : 1) : 0,
+		mm ? (permitted ? mm->end_code : 1) : 0,
+		(permitted && mm) ? mm->start_stack : 0,
+		esp,
+		eip,
+		/* The signal information here is obsolete.
+		 * It must be decimal for Linux 2.0 compatibility.
+		 * Use /proc/#/status for real-time signals.
+		 */
+		task->pending.signal.sig[0] & 0x7fffffffUL,
+		task->blocked.sig[0] & 0x7fffffffUL,
+		sigign      .sig[0] & 0x7fffffffUL,
+		sigcatch    .sig[0] & 0x7fffffffUL,
+		wchan,
+		0UL,
+		0UL,
+		task->exit_signal,
+		task_cpu(task),
+		task->rt_priority,
+		task->policy,
+		(unsigned long long)delayacct_blkio_ticks(task),
+		cputime_to_clock_t(gtime),
+		cputime_to_clock_t(cgtime));
+	if (mm)
+		mmput(mm);
+	return 0;
+}
+
+int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	return do_task_stat(m, ns, pid, task, 0);
+}
+
+int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	return do_task_stat(m, ns, pid, task, 1);
+}
+
+int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0;
+	struct mm_struct *mm = get_task_mm(task);
+
+	if (mm) {
+		size = task_statm(mm, &shared, &text, &data, &resident);
+		mmput(mm);
+	}
+	seq_printf(m, "%d %d %d %d %d %d %d\n",
+			size, resident, shared, text, lib, data, 0);
+
+	return 0;
+}

kernel/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;
+}
+module_init(proc_cmdline_init);

kernel/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;
+}
+module_init(proc_cpuinfo_init);

kernel/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_printf(f, "Character devices:\n");
+		chrdev_show(f, i);
+	}
+#ifdef CONFIG_BLOCK
+	else {
+		i -= CHRDEV_MAJOR_HASH_SIZE;
+		if (i == 0)
+			seq_printf(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;
+}
+module_init(proc_devices_init);

kernel/fs/proc/generic.c

@@ -0,0 +1,850 @@
+/*
+ * 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/module.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/idr.h>
+#include <linux/namei.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+DEFINE_SPINLOCK(proc_subdir_lock);
+
+static int proc_match(int len, const char *name, struct proc_dir_entry *de)
+{
+	if (de->namelen != len)
+		return 0;
+	return !memcmp(name, de->name, len);
+}
+
+/* buffer size is one page but our output routines use some slack for overruns */
+#define PROC_BLOCK_SIZE	(PAGE_SIZE - 1024)
+
+static ssize_t
+__proc_file_read(struct file *file, char __user *buf, size_t nbytes,
+	       loff_t *ppos)
+{
+	struct inode * inode = file->f_path.dentry->d_inode;
+	char 	*page;
+	ssize_t	retval=0;
+	int	eof=0;
+	ssize_t	n, count;
+	char	*start;
+	struct proc_dir_entry * dp;
+	unsigned long long pos;
+
+	/*
+	 * Gaah, please just use "seq_file" instead. The legacy /proc
+	 * interfaces cut loff_t down to off_t for reads, and ignore
+	 * the offset entirely for writes..
+	 */
+	pos = *ppos;
+	if (pos > MAX_NON_LFS)
+		return 0;
+	if (nbytes > MAX_NON_LFS - pos)
+		nbytes = MAX_NON_LFS - pos;
+
+	dp = PDE(inode);
+	if (!(page = (char*) __get_free_page(GFP_TEMPORARY)))
+		return -ENOMEM;
+
+	while ((nbytes > 0) && !eof) {
+		count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
+
+		start = NULL;
+		if (dp->read_proc) {
+			/*
+			 * How to be a proc read function
+			 * ------------------------------
+			 * Prototype:
+			 *    int f(char *buffer, char **start, off_t offset,
+			 *          int count, int *peof, void *dat)
+			 *
+			 * Assume that the buffer is "count" bytes in size.
+			 *
+			 * If you know you have supplied all the data you
+			 * have, set *peof.
+			 *
+			 * You have three ways to return data:
+			 * 0) Leave *start = NULL.  (This is the default.)
+			 *    Put the data of the requested offset at that
+			 *    offset within the buffer.  Return the number (n)
+			 *    of bytes there are from the beginning of the
+			 *    buffer up to the last byte of data.  If the
+			 *    number of supplied bytes (= n - offset) is 
+			 *    greater than zero and you didn't signal eof
+			 *    and the reader is prepared to take more data
+			 *    you will be called again with the requested
+			 *    offset advanced by the number of bytes 
+			 *    absorbed.  This interface is useful for files
+			 *    no larger than the buffer.
+			 * 1) Set *start = an unsigned long value less than
+			 *    the buffer address but greater than zero.
+			 *    Put the data of the requested offset at the
+			 *    beginning of the buffer.  Return the number of
+			 *    bytes of data placed there.  If this number is
+			 *    greater than zero and you didn't signal eof
+			 *    and the reader is prepared to take more data
+			 *    you will be called again with the requested
+			 *    offset advanced by *start.  This interface is
+			 *    useful when you have a large file consisting
+			 *    of a series of blocks which you want to count
+			 *    and return as wholes.
+			 *    (Hack by Paul.Russell@rustcorp.com.au)
+			 * 2) Set *start = an address within the buffer.
+			 *    Put the data of the requested offset at *start.
+			 *    Return the number of bytes of data placed there.
+			 *    If this number is greater than zero and you
+			 *    didn't signal eof and the reader is prepared to
+			 *    take more data you will be called again with the
+			 *    requested offset advanced by the number of bytes
+			 *    absorbed.
+			 */
+			n = dp->read_proc(page, &start, *ppos,
+					  count, &eof, dp->data);
+		} else
+			break;
+
+		if (n == 0)   /* end of file */
+			break;
+		if (n < 0) {  /* error */
+			if (retval == 0)
+				retval = n;
+			break;
+		}
+
+		if (start == NULL) {
+			if (n > PAGE_SIZE) {
+				printk(KERN_ERR
+				       "proc_file_read: Apparent buffer overflow!\n");
+				n = PAGE_SIZE;
+			}
+			n -= *ppos;
+			if (n <= 0)
+				break;
+			if (n > count)
+				n = count;
+			start = page + *ppos;
+		} else if (start < page) {
+			if (n > PAGE_SIZE) {
+				printk(KERN_ERR
+				       "proc_file_read: Apparent buffer overflow!\n");
+				n = PAGE_SIZE;
+			}
+			if (n > count) {
+				/*
+				 * Don't reduce n because doing so might
+				 * cut off part of a data block.
+				 */
+				printk(KERN_WARNING
+				       "proc_file_read: Read count exceeded\n");
+			}
+		} else /* start >= page */ {
+			unsigned long startoff = (unsigned long)(start - page);
+			if (n > (PAGE_SIZE - startoff)) {
+				printk(KERN_ERR
+				       "proc_file_read: Apparent buffer overflow!\n");
+				n = PAGE_SIZE - startoff;
+			}
+			if (n > count)
+				n = count;
+		}
+		
+ 		n -= copy_to_user(buf, start < page ? page : start, n);
+		if (n == 0) {
+			if (retval == 0)
+				retval = -EFAULT;
+			break;
+		}
+
+		*ppos += start < page ? (unsigned long)start : n;
+		nbytes -= n;
+		buf += n;
+		retval += n;
+	}
+	free_page((unsigned long) page);
+	return retval;
+}
+
+static ssize_t
+proc_file_read(struct file *file, char __user *buf, size_t nbytes,
+	       loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	ssize_t rv = -EIO;
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	spin_unlock(&pde->pde_unload_lock);
+
+	rv = __proc_file_read(file, buf, nbytes, ppos);
+
+	pde_users_dec(pde);
+	return rv;
+}
+
+static ssize_t
+proc_file_write(struct file *file, const char __user *buffer,
+		size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	ssize_t rv = -EIO;
+
+	if (pde->write_proc) {
+		spin_lock(&pde->pde_unload_lock);
+		if (!pde->proc_fops) {
+			spin_unlock(&pde->pde_unload_lock);
+			return rv;
+		}
+		pde->pde_users++;
+		spin_unlock(&pde->pde_unload_lock);
+
+		/* FIXME: does this routine need ppos?  probably... */
+		rv = pde->write_proc(file, buffer, count, pde->data);
+		pde_users_dec(pde);
+	}
+	return rv;
+}
+
+
+static loff_t
+proc_file_lseek(struct file *file, loff_t offset, int orig)
+{
+	loff_t retval = -EINVAL;
+	switch (orig) {
+	case 1:
+		offset += file->f_pos;
+	/* fallthrough */
+	case 0:
+		if (offset < 0 || offset > MAX_NON_LFS)
+			break;
+		file->f_pos = retval = offset;
+	}
+	return retval;
+}
+
+static const struct file_operations proc_file_operations = {
+	.llseek		= proc_file_lseek,
+	.read		= proc_file_read,
+	.write		= proc_file_write,
+};
+
+static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = dentry->d_inode;
+	struct proc_dir_entry *de = PDE(inode);
+	int error;
+
+	error = inode_change_ok(inode, iattr);
+	if (error)
+		goto out;
+
+	error = inode_setattr(inode, iattr);
+	if (error)
+		goto out;
+	
+	de->uid = inode->i_uid;
+	de->gid = inode->i_gid;
+	de->mode = inode->i_mode;
+out:
+	return error;
+}
+
+static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	struct proc_dir_entry *de = PROC_I(inode)->pde;
+	if (de && de->nlink)
+		inode->i_nlink = 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;
+	int			len;
+	int 			rtn = 0;
+
+	de = *ret;
+	if (!de)
+		de = &proc_root;
+
+	spin_lock(&proc_subdir_lock);
+	while (1) {
+		next = strchr(cp, '/');
+		if (!next)
+			break;
+
+		len = next - cp;
+		for (de = de->subdir; de ; de = de->next) {
+			if (proc_match(len, cp, de))
+				break;
+		}
+		if (!de) {
+			rtn = -ENOENT;
+			goto out;
+		}
+		cp += len + 1;
+	}
+	*residual = cp;
+	*ret = de;
+out:
+	spin_unlock(&proc_subdir_lock);
+	return rtn;
+}
+
+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.
+ *
+ * Current inode allocations in the proc-fs (hex-numbers):
+ *
+ * 00000000		reserved
+ * 00000001-00000fff	static entries	(goners)
+ *      001		root-ino
+ *
+ * 00001000-00001fff	unused
+ * 0001xxxx-7fffxxxx	pid-dir entries for pid 1-7fff
+ * 80000000-efffffff	unused
+ * f0000000-ffffffff	dynamic entries
+ *
+ * Goal:
+ *	Once we split the thing into several virtual filesystems,
+ *	we will get rid of magical ranges (and this comment, BTW).
+ */
+static unsigned int get_inode_number(void)
+{
+	unsigned int i;
+	int error;
+
+retry:
+	if (ida_pre_get(&proc_inum_ida, GFP_KERNEL) == 0)
+		return 0;
+
+	spin_lock(&proc_inum_lock);
+	error = ida_get_new(&proc_inum_ida, &i);
+	spin_unlock(&proc_inum_lock);
+	if (error == -EAGAIN)
+		goto retry;
+	else if (error)
+		return 0;
+
+	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
+		spin_lock(&proc_inum_lock);
+		ida_remove(&proc_inum_ida, i);
+		spin_unlock(&proc_inum_lock);
+		return 0;
+	}
+	return PROC_DYNAMIC_FIRST + i;
+}
+
+static void release_inode_number(unsigned int inum)
+{
+	spin_lock(&proc_inum_lock);
+	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
+	spin_unlock(&proc_inum_lock);
+}
+
+static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	nd_set_link(nd, PDE(dentry->d_inode)->data);
+	return NULL;
+}
+
+static const struct inode_operations proc_link_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= proc_follow_link,
+};
+
+/*
+ * As some entries in /proc are volatile, we want to 
+ * get rid of unused dentries.  This could be made 
+ * smarter: we could keep a "volatile" flag in the 
+ * inode to indicate which ones to keep.
+ */
+static int proc_delete_dentry(struct dentry * dentry)
+{
+	return 1;
+}
+
+static const struct dentry_operations proc_dentry_operations =
+{
+	.d_delete	= proc_delete_dentry,
+};
+
+/*
+ * 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 = NULL;
+	int error = -ENOENT;
+
+	spin_lock(&proc_subdir_lock);
+	for (de = de->subdir; de ; de = de->next) {
+		if (de->namelen != dentry->d_name.len)
+			continue;
+		if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
+			unsigned int ino;
+
+			ino = de->low_ino;
+			de_get(de);
+			spin_unlock(&proc_subdir_lock);
+			error = -EINVAL;
+			inode = proc_get_inode(dir->i_sb, ino, de);
+			goto out_unlock;
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+out_unlock:
+
+	if (inode) {
+		dentry->d_op = &proc_dentry_operations;
+		d_add(dentry, inode);
+		return NULL;
+	}
+	if (de)
+		de_put(de);
+	return ERR_PTR(error);
+}
+
+struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
+		struct nameidata *nd)
+{
+	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 *filp, void *dirent,
+		filldir_t filldir)
+{
+	unsigned int ino;
+	int i;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	int ret = 0;
+
+	ino = inode->i_ino;
+	i = filp->f_pos;
+	switch (i) {
+		case 0:
+			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
+				goto out;
+			i++;
+			filp->f_pos++;
+			/* fall through */
+		case 1:
+			if (filldir(dirent, "..", 2, i,
+				    parent_ino(filp->f_path.dentry),
+				    DT_DIR) < 0)
+				goto out;
+			i++;
+			filp->f_pos++;
+			/* fall through */
+		default:
+			spin_lock(&proc_subdir_lock);
+			de = de->subdir;
+			i -= 2;
+			for (;;) {
+				if (!de) {
+					ret = 1;
+					spin_unlock(&proc_subdir_lock);
+					goto out;
+				}
+				if (!i)
+					break;
+				de = de->next;
+				i--;
+			}
+
+			do {
+				struct proc_dir_entry *next;
+
+				/* filldir passes info to user space */
+				de_get(de);
+				spin_unlock(&proc_subdir_lock);
+				if (filldir(dirent, de->name, de->namelen, filp->f_pos,
+					    de->low_ino, de->mode >> 12) < 0) {
+					de_put(de);
+					goto out;
+				}
+				spin_lock(&proc_subdir_lock);
+				filp->f_pos++;
+				next = de->next;
+				de_put(de);
+				de = next;
+			} while (de);
+			spin_unlock(&proc_subdir_lock);
+	}
+	ret = 1;
+out:
+	return ret;	
+}
+
+int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+
+	return proc_readdir_de(PDE(inode), filp, dirent, filldir);
+}
+
+/*
+ * 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,
+	.readdir		= 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)
+{
+	unsigned int i;
+	struct proc_dir_entry *tmp;
+	
+	i = get_inode_number();
+	if (i == 0)
+		return -EAGAIN;
+	dp->low_ino = i;
+
+	if (S_ISDIR(dp->mode)) {
+		if (dp->proc_iops == NULL) {
+			dp->proc_fops = &proc_dir_operations;
+			dp->proc_iops = &proc_dir_inode_operations;
+		}
+		dir->nlink++;
+	} else if (S_ISLNK(dp->mode)) {
+		if (dp->proc_iops == NULL)
+			dp->proc_iops = &proc_link_inode_operations;
+	} else if (S_ISREG(dp->mode)) {
+		if (dp->proc_fops == NULL)
+			dp->proc_fops = &proc_file_operations;
+		if (dp->proc_iops == NULL)
+			dp->proc_iops = &proc_file_inode_operations;
+	}
+
+	spin_lock(&proc_subdir_lock);
+
+	for (tmp = dir->subdir; tmp; tmp = tmp->next)
+		if (strcmp(tmp->name, dp->name) == 0) {
+			WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n",
+				dir->name, dp->name);
+			break;
+		}
+
+	dp->next = dir->subdir;
+	dp->parent = dir;
+	dir->subdir = dp;
+	spin_unlock(&proc_subdir_lock);
+
+	return 0;
+}
+
+static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
+					  const char *name,
+					  mode_t mode,
+					  nlink_t nlink)
+{
+	struct proc_dir_entry *ent = NULL;
+	const char *fn = name;
+	int len;
+
+	/* make sure name is valid */
+	if (!name || !strlen(name)) goto out;
+
+	if (xlate_proc_name(name, parent, &fn) != 0)
+		goto out;
+
+	/* At this point there must not be any '/' characters beyond *fn */
+	if (strchr(fn, '/'))
+		goto out;
+
+	len = strlen(fn);
+
+	ent = kmalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
+	if (!ent) goto out;
+
+	memset(ent, 0, sizeof(struct proc_dir_entry));
+	memcpy(((char *) ent) + sizeof(struct proc_dir_entry), fn, len + 1);
+	ent->name = ((char *) ent) + sizeof(*ent);
+	ent->namelen = len;
+	ent->mode = mode;
+	ent->nlink = nlink;
+	atomic_set(&ent->count, 1);
+	ent->pde_users = 0;
+	spin_lock_init(&ent->pde_unload_lock);
+	ent->pde_unload_completion = NULL;
+	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);
+			if (proc_register(parent, ent) < 0) {
+				kfree(ent->data);
+				kfree(ent);
+				ent = NULL;
+			}
+		} else {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
+struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
+		struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *ent;
+
+	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
+	if (ent) {
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
+struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
+		struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *ent;
+
+	ent = __proc_create(&parent, name, S_IFDIR | S_IRUGO | S_IXUGO, 2);
+	if (ent) {
+		ent->data = net;
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+EXPORT_SYMBOL_GPL(proc_net_mkdir);
+
+struct proc_dir_entry *proc_mkdir(const char *name,
+		struct proc_dir_entry *parent)
+{
+	return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
+}
+
+struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
+					 struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *ent;
+	nlink_t nlink;
+
+	if (S_ISDIR(mode)) {
+		if ((mode & S_IALLUGO) == 0)
+			mode |= S_IRUGO | S_IXUGO;
+		nlink = 2;
+	} else {
+		if ((mode & S_IFMT) == 0)
+			mode |= S_IFREG;
+		if ((mode & S_IALLUGO) == 0)
+			mode |= S_IRUGO;
+		nlink = 1;
+	}
+
+	ent = __proc_create(&parent, name, mode, nlink);
+	if (ent) {
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
+struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
+					struct proc_dir_entry *parent,
+					const struct file_operations *proc_fops,
+					void *data)
+{
+	struct proc_dir_entry *pde;
+	nlink_t nlink;
+
+	if (S_ISDIR(mode)) {
+		if ((mode & S_IALLUGO) == 0)
+			mode |= S_IRUGO | S_IXUGO;
+		nlink = 2;
+	} else {
+		if ((mode & S_IFMT) == 0)
+			mode |= S_IFREG;
+		if ((mode & S_IALLUGO) == 0)
+			mode |= S_IRUGO;
+		nlink = 1;
+	}
+
+	pde = __proc_create(&parent, name, mode, nlink);
+	if (!pde)
+		goto out;
+	pde->proc_fops = proc_fops;
+	pde->data = data;
+	if (proc_register(parent, pde) < 0)
+		goto out_free;
+	return pde;
+out_free:
+	kfree(pde);
+out:
+	return NULL;
+}
+
+void free_proc_entry(struct proc_dir_entry *de)
+{
+	unsigned int ino = de->low_ino;
+
+	if (ino < PROC_DYNAMIC_FIRST)
+		return;
+
+	release_inode_number(ino);
+
+	if (S_ISLNK(de->mode))
+		kfree(de->data);
+	kfree(de);
+}
+
+/*
+ * 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 **p;
+	struct proc_dir_entry *de = NULL;
+	const char *fn = name;
+	int len;
+
+	if (xlate_proc_name(name, &parent, &fn) != 0)
+		return;
+	len = strlen(fn);
+
+	spin_lock(&proc_subdir_lock);
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (proc_match(len, fn, *p)) {
+			de = *p;
+			*p = de->next;
+			de->next = NULL;
+			break;
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+	if (!de)
+		return;
+
+	spin_lock(&de->pde_unload_lock);
+	/*
+	 * Stop accepting new callers into module. If you're
+	 * dynamically allocating ->proc_fops, save a pointer somewhere.
+	 */
+	de->proc_fops = NULL;
+	/* Wait until all existing callers into module are done. */
+	if (de->pde_users > 0) {
+		DECLARE_COMPLETION_ONSTACK(c);
+
+		if (!de->pde_unload_completion)
+			de->pde_unload_completion = &c;
+
+		spin_unlock(&de->pde_unload_lock);
+
+		wait_for_completion(de->pde_unload_completion);
+
+		goto continue_removing;
+	}
+	spin_unlock(&de->pde_unload_lock);
+
+continue_removing:
+	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);
+		list_del(&pdeo->lh);
+		spin_unlock(&de->pde_unload_lock);
+		pdeo->release(pdeo->inode, pdeo->file);
+		kfree(pdeo);
+		spin_lock(&de->pde_unload_lock);
+	}
+	spin_unlock(&de->pde_unload_lock);
+
+	if (S_ISDIR(de->mode))
+		parent->nlink--;
+	de->nlink = 0;
+	WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
+			"'%s/%s', leaking at least '%s'\n", __func__,
+			de->parent->name, de->name, de->subdir->name);
+	if (atomic_dec_and_test(&de->count))
+		free_proc_entry(de);
+}

kernel/fs/proc/inode.c

@@ -0,0 +1,514 @@
+/*
+ *  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/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/completion.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/limits.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+#include <linux/sysctl.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+struct proc_dir_entry *de_get(struct proc_dir_entry *de)
+{
+	atomic_inc(&de->count);
+	return de;
+}
+
+/*
+ * Decrements the use count and checks for deferred deletion.
+ */
+void de_put(struct proc_dir_entry *de)
+{
+	if (!atomic_read(&de->count)) {
+		printk("de_put: entry %s already free!\n", de->name);
+		return;
+	}
+
+	if (atomic_dec_and_test(&de->count))
+		free_proc_entry(de);
+}
+
+/*
+ * Decrement the use count of the proc_dir_entry.
+ */
+static void proc_delete_inode(struct inode *inode)
+{
+	struct proc_dir_entry *de;
+
+	truncate_inode_pages(&inode->i_data, 0);
+
+	/* Stop tracking associated processes */
+	put_pid(PROC_I(inode)->pid);
+
+	/* Let go of any associated proc directory entry */
+	de = PROC_I(inode)->pde;
+	if (de)
+		de_put(de);
+	if (PROC_I(inode)->sysctl)
+		sysctl_head_put(PROC_I(inode)->sysctl);
+	clear_inode(inode);
+}
+
+struct vfsmount *proc_mnt;
+
+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;
+	inode = &ei->vfs_inode;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	return inode;
+}
+
+static void proc_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
+}
+
+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 const struct super_operations proc_sops = {
+	.alloc_inode	= proc_alloc_inode,
+	.destroy_inode	= proc_destroy_inode,
+	.drop_inode	= generic_delete_inode,
+	.delete_inode	= proc_delete_inode,
+	.statfs		= simple_statfs,
+};
+
+static void __pde_users_dec(struct proc_dir_entry *pde)
+{
+	pde->pde_users--;
+	if (pde->pde_unload_completion && pde->pde_users == 0)
+		complete(pde->pde_unload_completion);
+}
+
+void pde_users_dec(struct proc_dir_entry *pde)
+{
+	spin_lock(&pde->pde_unload_lock);
+	__pde_users_dec(pde);
+	spin_unlock(&pde->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	loff_t rv = -EINVAL;
+	loff_t (*llseek)(struct file *, loff_t, int);
+
+	spin_lock(&pde->pde_unload_lock);
+	/*
+	 * remove_proc_entry() is going to delete PDE (as part of module
+	 * cleanup sequence). No new callers into module allowed.
+	 */
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	/*
+	 * Bump refcount so that remove_proc_entry will wail for ->llseek to
+	 * complete.
+	 */
+	pde->pde_users++;
+	/*
+	 * Save function pointer under lock, to protect against ->proc_fops
+	 * NULL'ifying right after ->pde_unload_lock is dropped.
+	 */
+	llseek = pde->proc_fops->llseek;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (!llseek)
+		llseek = default_llseek;
+	rv = llseek(file, offset, whence);
+
+	pde_users_dec(pde);
+	return rv;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	ssize_t rv = -EIO;
+	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	read = pde->proc_fops->read;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (read)
+		rv = read(file, buf, count, ppos);
+
+	pde_users_dec(pde);
+	return rv;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	ssize_t rv = -EIO;
+	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	write = pde->proc_fops->write;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (write)
+		rv = write(file, buf, count, ppos);
+
+	pde_users_dec(pde);
+	return rv;
+}
+
+static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	unsigned int rv = DEFAULT_POLLMASK;
+	unsigned int (*poll)(struct file *, struct poll_table_struct *);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	poll = pde->proc_fops->poll;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (poll)
+		rv = poll(file, pts);
+
+	pde_users_dec(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->f_path.dentry->d_inode);
+	long rv = -ENOTTY;
+	long (*unlocked_ioctl)(struct file *, unsigned int, unsigned long);
+	int (*ioctl)(struct inode *, struct file *, unsigned int, unsigned long);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	unlocked_ioctl = pde->proc_fops->unlocked_ioctl;
+	ioctl = pde->proc_fops->ioctl;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (unlocked_ioctl) {
+		rv = unlocked_ioctl(file, cmd, arg);
+		if (rv == -ENOIOCTLCMD)
+			rv = -EINVAL;
+	} else if (ioctl) {
+		lock_kernel();
+		rv = ioctl(file->f_path.dentry->d_inode, file, cmd, arg);
+		unlock_kernel();
+	}
+
+	pde_users_dec(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->f_path.dentry->d_inode);
+	long rv = -ENOTTY;
+	long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	compat_ioctl = pde->proc_fops->compat_ioctl;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (compat_ioctl)
+		rv = compat_ioctl(file, cmd, arg);
+
+	pde_users_dec(pde);
+	return rv;
+}
+#endif
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+	int rv = -EIO;
+	int (*mmap)(struct file *, struct vm_area_struct *);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	mmap = pde->proc_fops->mmap;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (mmap)
+		rv = mmap(file, vma);
+
+	pde_users_dec(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 = kmalloc(sizeof(struct pde_opener), GFP_KERNEL);
+	if (!pdeo)
+		return -ENOMEM;
+
+	spin_lock(&pde->pde_unload_lock);
+	if (!pde->proc_fops) {
+		spin_unlock(&pde->pde_unload_lock);
+		kfree(pdeo);
+		return -EINVAL;
+	}
+	pde->pde_users++;
+	open = pde->proc_fops->open;
+	release = pde->proc_fops->release;
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (open)
+		rv = open(inode, file);
+
+	spin_lock(&pde->pde_unload_lock);
+	if (rv == 0 && release) {
+		/* To know what to release. */
+		pdeo->inode = inode;
+		pdeo->file = file;
+		/* Strictly for "too late" ->release in proc_reg_release(). */
+		pdeo->release = release;
+		list_add(&pdeo->lh, &pde->pde_openers);
+	} else
+		kfree(pdeo);
+	__pde_users_dec(pde);
+	spin_unlock(&pde->pde_unload_lock);
+	return rv;
+}
+
+static struct pde_opener *find_pde_opener(struct proc_dir_entry *pde,
+					struct inode *inode, struct file *file)
+{
+	struct pde_opener *pdeo;
+
+	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+		if (pdeo->inode == inode && pdeo->file == file)
+			return pdeo;
+	}
+	return NULL;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	int rv = 0;
+	int (*release)(struct inode *, struct file *);
+	struct pde_opener *pdeo;
+
+	spin_lock(&pde->pde_unload_lock);
+	pdeo = find_pde_opener(pde, inode, file);
+	if (!pde->proc_fops) {
+		/*
+		 * Can't simply exit, __fput() will think that everything is OK,
+		 * and move on to freeing struct file. remove_proc_entry() will
+		 * find slacker in opener's list and will try to do non-trivial
+		 * things with struct file. Therefore, remove opener from list.
+		 *
+		 * But if opener is removed from list, who will ->release it?
+		 */
+		if (pdeo) {
+			list_del(&pdeo->lh);
+			spin_unlock(&pde->pde_unload_lock);
+			rv = pdeo->release(inode, file);
+			kfree(pdeo);
+		} else
+			spin_unlock(&pde->pde_unload_lock);
+		return rv;
+	}
+	pde->pde_users++;
+	release = pde->proc_fops->release;
+	if (pdeo) {
+		list_del(&pdeo->lh);
+		kfree(pdeo);
+	}
+	spin_unlock(&pde->pde_unload_lock);
+
+	if (release)
+		rv = release(inode, file);
+
+	pde_users_dec(pde);
+	return rv;
+}
+
+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,
+	.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,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+#endif
+
+struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
+				struct proc_dir_entry *de)
+{
+	struct inode * inode;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return NULL;
+	if (inode->i_state & I_NEW) {
+		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		PROC_I(inode)->fd = 0;
+		PROC_I(inode)->pde = de;
+
+		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)
+			inode->i_nlink = de->nlink;
+		if (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;
+			}
+		}
+		unlock_new_inode(inode);
+	} else
+	       de_put(de);
+	return inode;
+}			
+
+int proc_fill_super(struct super_block *s)
+{
+	struct inode * root_inode;
+
+	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;
+	
+	de_get(&proc_root);
+	root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
+	if (!root_inode)
+		goto out_no_root;
+	root_inode->i_uid = 0;
+	root_inode->i_gid = 0;
+	s->s_root = d_alloc_root(root_inode);
+	if (!s->s_root)
+		goto out_no_root;
+	return 0;
+
+out_no_root:
+	printk("proc_read_super: get root inode failed\n");
+	iput(root_inode);
+	de_put(&proc_root);
+	return -ENOMEM;
+}

kernel/fs/proc/internal.h

@@ -0,0 +1,119 @@
+/* internal.h: 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>
+
+extern struct proc_dir_entry proc_root;
+#ifdef CONFIG_PROC_SYSCTL
+extern int proc_sys_init(void);
+#else
+static inline void proc_sys_init(void) { }
+#endif
+#ifdef CONFIG_NET
+extern int proc_net_init(void);
+#else
+static inline int proc_net_init(void) { return 0; }
+#endif
+
+struct vmalloc_info {
+	unsigned long	used;
+	unsigned long	largest_chunk;
+};
+
+extern struct mm_struct *mm_for_maps(struct task_struct *);
+
+#ifdef CONFIG_MMU
+#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
+extern void get_vmalloc_info(struct vmalloc_info *vmi);
+#else
+
+#define VMALLOC_TOTAL 0UL
+#define get_vmalloc_info(vmi)			\
+do {						\
+	(vmi)->used = 0;			\
+	(vmi)->largest_chunk = 0;		\
+} while(0)
+#endif
+
+extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
+extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
+extern int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
+extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
+extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
+
+extern const struct file_operations proc_maps_operations;
+extern const struct file_operations proc_numa_maps_operations;
+extern const struct file_operations proc_smaps_operations;
+extern const struct file_operations proc_clear_refs_operations;
+extern const struct file_operations proc_pagemap_operations;
+extern const struct file_operations proc_net_operations;
+extern const struct inode_operations proc_net_inode_operations;
+
+void free_proc_entry(struct proc_dir_entry *de);
+
+void proc_init_inodecache(void);
+
+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 proc_fd(struct inode *inode)
+{
+	return PROC_I(inode)->fd;
+}
+
+struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino,
+		struct dentry *dentry);
+int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
+		filldir_t filldir);
+
+struct pde_opener {
+	struct inode *inode;
+	struct file *file;
+	int (*release)(struct inode *, struct file *);
+	struct list_head lh;
+};
+void pde_users_dec(struct proc_dir_entry *pde);
+
+extern spinlock_t proc_subdir_lock;
+
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
+int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
+unsigned long task_vsize(struct mm_struct *);
+int task_statm(struct mm_struct *, int *, int *, int *, int *);
+void task_mem(struct seq_file *, struct mm_struct *);
+
+struct proc_dir_entry *de_get(struct proc_dir_entry *de);
+void de_put(struct proc_dir_entry *de);
+
+extern struct vfsmount *proc_mnt;
+int proc_fill_super(struct super_block *);
+struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *);
+
+/*
+ * These are generic /proc routines that use the internal
+ * "struct proc_dir_entry" tree to traverse the filesystem.
+ *
+ * The /proc root directory has extended versions to take care
+ * of the /proc/<pid> subdirectories.
+ */
+int proc_readdir(struct file *, void *, filldir_t);
+struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);

kernel/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;
+}
+module_init(proc_interrupts_init);

kernel/fs/proc/kcore.c

@@ -0,0 +1,633 @@
+/*
+ *	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/user.h>
+#include <linux/capability.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/init.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>
+
+#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 */
+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 = ALIGN(end, PAGE_SIZE);
+	/* 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
+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_HIGH_MEMORY) {
+		unsigned long node_end;
+		node_end  = NODE_DATA(nid)->node_start_pfn +
+			NODE_DATA(nid)->node_spanned_pages;
+		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");
+	strncpy(prpsinfo.pr_psargs, saved_command_line, ELF_PRARGSZ);
+
+	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 == NULL) {
+			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 distingush 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,
+};
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+/* 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;
+}
+#endif
+
+
+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, _stext, _end - _stext, 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)
+{
+	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) {
+		printk(KERN_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();
+	hotplug_memory_notifier(kcore_callback, 0);
+
+	return 0;
+}
+module_init(proc_kcore_init);

kernel/fs/proc/kmsg.c

@@ -0,0 +1,63 @@
+/*
+ *  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 <asm/uaccess.h>
+#include <asm/io.h>
+
+extern wait_queue_head_t log_wait;
+
+extern int do_syslog(int type, char __user *bug, int count);
+
+static int kmsg_open(struct inode * inode, struct file * file)
+{
+	return do_syslog(1,NULL,0);
+}
+
+static int kmsg_release(struct inode * inode, struct file * file)
+{
+	(void) do_syslog(0,NULL,0);
+	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(9, NULL, 0))
+		return -EAGAIN;
+	return do_syslog(2, buf, count);
+}
+
+static unsigned int kmsg_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &log_wait, wait);
+	if (do_syslog(9, NULL, 0))
+		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,
+};
+
+static int __init proc_kmsg_init(void)
+{
+	proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
+	return 0;
+}
+module_init(proc_kmsg_init);

kernel/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;
+}
+module_init(proc_loadavg_init);

kernel/fs/proc/meminfo.c

@@ -0,0 +1,181 @@
+#include <linux/fs.h>
+#include <linux/hugetlb.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.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 <asm/atomic.h>
+#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;
+	unsigned long allowed;
+	struct vmalloc_info vmi;
+	long cached;
+	unsigned long pages[NR_LRU_LISTS];
+	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);
+	allowed = ((totalram_pages - hugetlb_total_pages())
+		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+
+	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);
+
+	/*
+	 * Tagged format, for easy grepping and expansion.
+	 */
+	seq_printf(m,
+		"MemTotal:       %8lu kB\n"
+		"MemFree:        %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_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
+		,
+		K(i.totalram),
+		K(i.freeram),
+		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(global_page_state(NR_SHMEM)),
+		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_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(allowed),
+		K(committed),
+		(unsigned long)VMALLOC_TOTAL >> 10,
+		vmi.used >> 10,
+		vmi.largest_chunk >> 10
+#ifdef CONFIG_MEMORY_FAILURE
+		,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
+#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;
+}
+module_init(proc_meminfo_init);

kernel/fs/proc/mmu.c

@@ -0,0 +1,60 @@
+/* mmu.c: mmu 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/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+#include <asm/pgtable.h>
+#include "internal.h"
+
+void get_vmalloc_info(struct vmalloc_info *vmi)
+{
+	struct vm_struct *vma;
+	unsigned long free_area_size;
+	unsigned long prev_end;
+
+	vmi->used = 0;
+
+	if (!vmlist) {
+		vmi->largest_chunk = VMALLOC_TOTAL;
+	}
+	else {
+		vmi->largest_chunk = 0;
+
+		prev_end = VMALLOC_START;
+
+		read_lock(&vmlist_lock);
+
+		for (vma = vmlist; vma; vma = vma->next) {
+			unsigned long addr = (unsigned long) vma->addr;
+
+			/*
+			 * Some archs keep another range for modules in vmlist
+			 */
+			if (addr < VMALLOC_START)
+				continue;
+			if (addr >= VMALLOC_END)
+				break;
+
+			vmi->used += vma->size;
+
+			free_area_size = addr - prev_end;
+			if (vmi->largest_chunk < free_area_size)
+				vmi->largest_chunk = free_area_size;
+
+			prev_end = vma->size + addr;
+		}
+
+		if (VMALLOC_END - prev_end > vmi->largest_chunk)
+			vmi->largest_chunk = VMALLOC_END - prev_end;
+
+		read_unlock(&vmlist_lock);
+	}
+}

kernel/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/slab.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, len;
+
+	flags = region->vm_flags;
+	file = region->vm_file;
+
+	if (file) {
+		struct inode *inode = region->vm_file->f_path.dentry->d_inode;
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+	}
+
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+		   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, &len);
+
+	if (file) {
+		len = 25 + sizeof(void *) * 6 - len;
+		if (len < 1)
+			len = 1;
+		seq_printf(m, "%*c", len, ' ');
+		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;
+}
+
+module_init(proc_nommu_init);

kernel/fs/proc/page.c

@@ -0,0 +1,249 @@
+#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/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.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)
+			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.
+ */
+
+/* These macros are used to decouple internal flags from exported ones */
+
+#define KPF_LOCKED		0
+#define KPF_ERROR		1
+#define KPF_REFERENCED		2
+#define KPF_UPTODATE		3
+#define KPF_DIRTY		4
+#define KPF_LRU			5
+#define KPF_ACTIVE		6
+#define KPF_SLAB		7
+#define KPF_WRITEBACK		8
+#define KPF_RECLAIM		9
+#define KPF_BUDDY		10
+
+/* 11-20: new additions in 2.6.31 */
+#define KPF_MMAP		11
+#define KPF_ANON		12
+#define KPF_SWAPCACHE		13
+#define KPF_SWAPBACKED		14
+#define KPF_COMPOUND_HEAD	15
+#define KPF_COMPOUND_TAIL	16
+#define KPF_HUGE		17
+#define KPF_UNEVICTABLE		18
+#define KPF_HWPOISON		19
+#define KPF_NOPAGE		20
+
+#define KPF_KSM			21
+
+/* kernel hacking assistances
+ * WARNING: subject to change, never rely on them!
+ */
+#define KPF_RESERVED		32
+#define KPF_MLOCKED		33
+#define KPF_MAPPEDTODISK	34
+#define KPF_PRIVATE		35
+#define KPF_PRIVATE_2		36
+#define KPF_OWNER_PRIVATE	37
+#define KPF_ARCH		38
+#define KPF_UNCACHED		39
+
+static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
+{
+	return ((kflags >> kbit) & 1) << ubit;
+}
+
+static u64 get_uflags(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;
+
+	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
+
+	/*
+	 * Caveats on high order pages:
+	 * PG_buddy will only be set on the head page; SLUB/SLQB do the same
+	 * for PG_slab; SLOB won't set PG_slab at all on compound pages.
+	 */
+	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
+	u |= kpf_copy_bit(k, KPF_BUDDY,		PG_buddy);
+
+	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_IA64_UNCACHED_ALLOCATOR
+	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(get_uflags(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;
+}
+module_init(proc_page_init);

kernel/fs/proc/proc_devtree.c

@@ -0,0 +1,233 @@
+/*
+ * proc_devtree.c - handles /proc/device-tree
+ *
+ * Copyright 1997 Paul Mackerras
+ */
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <asm/prom.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+#ifndef HAVE_ARCH_DEVTREE_FIXUPS
+static inline void set_node_proc_entry(struct device_node *np,
+				       struct proc_dir_entry *de)
+{
+}
+#endif
+
+static struct proc_dir_entry *proc_device_tree;
+
+/*
+ * Supply data on a read from /proc/device-tree/node/property.
+ */
+static int property_read_proc(char *page, char **start, off_t off,
+			      int count, int *eof, void *data)
+{
+	struct property *pp = data;
+	int n;
+
+	if (off >= pp->length) {
+		*eof = 1;
+		return 0;
+	}
+	n = pp->length - off;
+	if (n > count)
+		n = count;
+	else
+		*eof = 1;
+	memcpy(page, (char *)pp->value + off, n);
+	*start = page;
+	return n;
+}
+
+/*
+ * For a node with a name like "gc@10", we make symlinks called "gc"
+ * and "@10" to it.
+ */
+
+/*
+ * Add a property to a node
+ */
+static struct proc_dir_entry *
+__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp,
+		const char *name)
+{
+	struct proc_dir_entry *ent;
+
+	/*
+	 * Unfortunately proc_register puts each new entry
+	 * at the beginning of the list.  So we rearrange them.
+	 */
+	ent = create_proc_read_entry(name,
+				     strncmp(name, "security-", 9)
+				     ? S_IRUGO : S_IRUSR, de,
+				     property_read_proc, pp);
+	if (ent == NULL)
+		return NULL;
+
+	if (!strncmp(name, "security-", 9))
+		ent->size = 0; /* don't leak number of password chars */
+	else
+		ent->size = pp->length;
+
+	return ent;
+}
+
+
+void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop)
+{
+	__proc_device_tree_add_prop(pde, prop, prop->name);
+}
+
+void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
+				  struct property *prop)
+{
+	remove_proc_entry(prop->name, pde);
+}
+
+void proc_device_tree_update_prop(struct proc_dir_entry *pde,
+				  struct property *newprop,
+				  struct property *oldprop)
+{
+	struct proc_dir_entry *ent;
+
+	for (ent = pde->subdir; ent != NULL; ent = ent->next)
+		if (ent->data == oldprop)
+			break;
+	if (ent == NULL) {
+		printk(KERN_WARNING "device-tree: property \"%s\" "
+		       " does not exist\n", oldprop->name);
+	} else {
+		ent->data = newprop;
+		ent->size = newprop->length;
+	}
+}
+
+/*
+ * Various dodgy firmware might give us nodes and/or properties with
+ * conflicting names. That's generally ok, except for exporting via /proc,
+ * so munge names here to ensure they're unique.
+ */
+
+static int duplicate_name(struct proc_dir_entry *de, const char *name)
+{
+	struct proc_dir_entry *ent;
+	int found = 0;
+
+	spin_lock(&proc_subdir_lock);
+
+	for (ent = de->subdir; ent != NULL; ent = ent->next) {
+		if (strcmp(ent->name, name) == 0) {
+			found = 1;
+			break;
+		}
+	}
+
+	spin_unlock(&proc_subdir_lock);
+
+	return found;
+}
+
+static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de,
+		const char *name)
+{
+	char *fixed_name;
+	int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */
+	int i = 1, size;
+
+realloc:
+	fixed_name = kmalloc(fixup_len, GFP_KERNEL);
+	if (fixed_name == NULL) {
+		printk(KERN_ERR "device-tree: Out of memory trying to fixup "
+				"name \"%s\"\n", name);
+		return name;
+	}
+
+retry:
+	size = snprintf(fixed_name, fixup_len, "%s#%d", name, i);
+	size++; /* account for NULL */
+
+	if (size > fixup_len) {
+		/* We ran out of space, free and reallocate. */
+		kfree(fixed_name);
+		fixup_len = size;
+		goto realloc;
+	}
+
+	if (duplicate_name(de, fixed_name)) {
+		/* Multiple duplicates. Retry with a different offset. */
+		i++;
+		goto retry;
+	}
+
+	printk(KERN_WARNING "device-tree: Duplicate name in %s, "
+			"renamed to \"%s\"\n", np->full_name, fixed_name);
+
+	return fixed_name;
+}
+
+/*
+ * Process a node, adding entries for its children and its properties.
+ */
+void proc_device_tree_add_node(struct device_node *np,
+			       struct proc_dir_entry *de)
+{
+	struct property *pp;
+	struct proc_dir_entry *ent;
+	struct device_node *child;
+	const char *p;
+
+	set_node_proc_entry(np, de);
+	for (child = NULL; (child = of_get_next_child(np, child));) {
+		/* Use everything after the last slash, or the full name */
+		p = strrchr(child->full_name, '/');
+		if (!p)
+			p = child->full_name;
+		else
+			++p;
+
+		if (duplicate_name(de, p))
+			p = fixup_name(np, de, p);
+
+		ent = proc_mkdir(p, de);
+		if (ent == NULL)
+			break;
+		proc_device_tree_add_node(child, ent);
+	}
+	of_node_put(child);
+
+	for (pp = np->properties; pp != NULL; pp = pp->next) {
+		p = pp->name;
+
+		if (duplicate_name(de, p))
+			p = fixup_name(np, de, p);
+
+		ent = __proc_device_tree_add_prop(de, pp, p);
+		if (ent == NULL)
+			break;
+	}
+}
+
+/*
+ * Called on initialization to set up the /proc/device-tree subtree
+ */
+void __init proc_device_tree_init(void)
+{
+	struct device_node *root;
+
+	proc_device_tree = proc_mkdir("device-tree", NULL);
+	if (proc_device_tree == NULL)
+		return;
+	root = of_find_node_by_path("/");
+	if (root == NULL) {
+		printk(KERN_ERR "/proc/device-tree: can't find root\n");
+		return;
+	}
+	proc_device_tree_add_node(root, proc_device_tree);
+	of_node_put(root);
+}

kernel/fs/proc/proc_net.c

@@ -0,0 +1,240 @@
+/*
+ *  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/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 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) {
+		ns = task_nsproxy(task);
+		if (ns != NULL)
+			net = get_net(ns->net_ns);
+	}
+	rcu_read_unlock();
+
+	return net;
+}
+
+static struct dentry *proc_tgid_net_lookup(struct inode *dir,
+		struct dentry *dentry, struct nameidata *nd)
+{
+	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 = dentry->d_inode;
+	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 *filp, void *dirent,
+		filldir_t filldir)
+{
+	int ret;
+	struct net *net;
+
+	ret = -EINVAL;
+	net = get_proc_task_net(filp->f_path.dentry->d_inode);
+	if (net != NULL) {
+		ret = proc_readdir_de(net->proc_net, filp, dirent, filldir);
+		put_net(net);
+	}
+	return ret;
+}
+
+const struct file_operations proc_net_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.readdir	= proc_tgid_net_readdir,
+};
+
+
+struct proc_dir_entry *proc_net_fops_create(struct net *net,
+	const char *name, mode_t mode, const struct file_operations *fops)
+{
+	return proc_create(name, mode, net->proc_net, fops);
+}
+EXPORT_SYMBOL_GPL(proc_net_fops_create);
+
+void proc_net_remove(struct net *net, const char *name)
+{
+	remove_proc_entry(name, net->proc_net);
+}
+EXPORT_SYMBOL_GPL(proc_net_remove);
+
+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), GFP_KERNEL);
+	if (!netd)
+		goto out;
+
+	netd->data = net;
+	netd->nlink = 2;
+	netd->name = "net";
+	netd->namelen = 3;
+	netd->parent = &proc_root;
+
+	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);
+}

kernel/fs/proc/proc_sysctl.c

@@ -0,0 +1,414 @@
+/*
+ * /proc/sys support
+ */
+#include <linux/init.h>
+#include <linux/sysctl.h>
+#include <linux/proc_fs.h>
+#include <linux/security.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;
+
+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;
+
+	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_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
+	inode->i_mode = table->mode;
+	if (!table->child) {
+		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_nlink = 0;
+		inode->i_op = &proc_sys_dir_operations;
+		inode->i_fop = &proc_sys_dir_file_operations;
+	}
+out:
+	return inode;
+}
+
+static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
+{
+	int len;
+	for ( ; p->ctl_name || p->procname; p++) {
+
+		if (!p->procname)
+			continue;
+
+		len = strlen(p->procname);
+		if (len != name->len)
+			continue;
+
+		if (memcmp(p->procname, name->name, len) != 0)
+			continue;
+
+		/* I have a match */
+		return p;
+	}
+	return NULL;
+}
+
+static struct ctl_table_header *grab_header(struct inode *inode)
+{
+	if (PROC_I(inode)->sysctl)
+		return sysctl_head_grab(PROC_I(inode)->sysctl);
+	else
+		return sysctl_head_next(NULL);
+}
+
+static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
+					struct nameidata *nd)
+{
+	struct ctl_table_header *head = grab_header(dir);
+	struct ctl_table *table = PROC_I(dir)->sysctl_entry;
+	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);
+
+	if (IS_ERR(head))
+		return ERR_CAST(head);
+
+	if (table && !table->child) {
+		WARN_ON(1);
+		goto out;
+	}
+
+	table = table ? table->child : head->ctl_table;
+
+	p = find_in_table(table, name);
+	if (!p) {
+		for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
+			if (h->attached_to != table)
+				continue;
+			p = find_in_table(h->attached_by, name);
+			if (p)
+				break;
+		}
+	}
+
+	if (!p)
+		goto out;
+
+	err = ERR_PTR(-ENOMEM);
+	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
+	if (h)
+		sysctl_head_finish(h);
+
+	if (!inode)
+		goto out;
+
+	err = NULL;
+	dentry->d_op = &proc_sys_dentry_operations;
+	d_add(dentry, inode);
+
+out:
+	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 = filp->f_path.dentry->d_inode;
+	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->root, 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_fill_cache(struct file *filp, void *dirent,
+				filldir_t filldir,
+				struct ctl_table_header *head,
+				struct ctl_table *table)
+{
+	struct dentry *child, *dir = filp->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 -ENOMEM;
+			} else {
+				child->d_op = &proc_sys_dentry_operations;
+				d_add(child, inode);
+			}
+		} else {
+			return -ENOMEM;
+		}
+	}
+	inode = child->d_inode;
+	ino  = inode->i_ino;
+	type = inode->i_mode >> 12;
+	dput(child);
+	return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+}
+
+static int scan(struct ctl_table_header *head, ctl_table *table,
+		unsigned long *pos, struct file *file,
+		void *dirent, filldir_t filldir)
+{
+
+	for (; table->ctl_name || table->procname; table++, (*pos)++) {
+		int res;
+
+		/* Can't do anything without a proc name */
+		if (!table->procname)
+			continue;
+
+		if (*pos < file->f_pos)
+			continue;
+
+		res = proc_sys_fill_cache(file, dirent, filldir, head, table);
+		if (res)
+			return res;
+
+		file->f_pos = *pos + 1;
+	}
+	return 0;
+}
+
+static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	struct dentry *dentry = filp->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	struct ctl_table_header *h = NULL;
+	unsigned long pos;
+	int ret = -EINVAL;
+
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	if (table && !table->child) {
+		WARN_ON(1);
+		goto out;
+	}
+
+	table = table ? table->child : head->ctl_table;
+
+	ret = 0;
+	/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
+	if (filp->f_pos == 0) {
+		if (filldir(dirent, ".", 1, filp->f_pos,
+				inode->i_ino, DT_DIR) < 0)
+			goto out;
+		filp->f_pos++;
+	}
+	if (filp->f_pos == 1) {
+		if (filldir(dirent, "..", 2, filp->f_pos,
+				parent_ino(dentry), DT_DIR) < 0)
+			goto out;
+		filp->f_pos++;
+	}
+	pos = 2;
+
+	ret = scan(head, table, &pos, filp, dirent, filldir);
+	if (ret)
+		goto out;
+
+	for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
+		if (h->attached_to != table)
+			continue;
+		ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
+		if (ret) {
+			sysctl_head_finish(h);
+			break;
+		}
+	}
+	ret = 1;
+out:
+	sysctl_head_finish(head);
+	return ret;
+}
+
+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->root, table, mask);
+
+	sysctl_head_finish(head);
+	return error;
+}
+
+static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = dentry->d_inode;
+	int error;
+
+	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+		return -EPERM;
+
+	error = inode_change_ok(inode, attr);
+	if (!error)
+		error = inode_setattr(inode, attr);
+
+	return error;
+}
+
+static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	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 = {
+	.read		= proc_sys_read,
+	.write		= proc_sys_write,
+};
+
+static const struct file_operations proc_sys_dir_file_operations = {
+	.readdir	= 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, struct nameidata *nd)
+{
+	return !PROC_I(dentry->d_inode)->sysctl->unregistering;
+}
+
+static int proc_sys_delete(struct dentry *dentry)
+{
+	return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
+}
+
+static int proc_sys_compare(struct dentry *dir, struct qstr *qstr,
+			    struct qstr *name)
+{
+	struct dentry *dentry = container_of(qstr, struct dentry, d_name);
+	if (qstr->len != name->len)
+		return 1;
+	if (memcmp(qstr->name, name->name, name->len))
+		return 1;
+	return !sysctl_is_seen(PROC_I(dentry->d_inode)->sysctl);
+}
+
+static const struct dentry_operations proc_sys_dentry_operations = {
+	.d_revalidate	= proc_sys_revalidate,
+	.d_delete	= proc_sys_delete,
+	.d_compare	= proc_sys_compare,
+};
+
+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 0;
+}

kernel/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_ldisc, *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_printf(m, "system");
+		if (p->subtype == SYSTEM_TYPE_TTY)
+			seq_printf(m, ":/dev/tty");
+		else if (p->subtype == SYSTEM_TYPE_SYSCONS)
+			seq_printf(m, ":console");
+		else if (p->subtype == SYSTEM_TYPE_CONSOLE)
+			seq_printf(m, ":vtmaster");
+		break;
+	case TTY_DRIVER_TYPE_CONSOLE:
+		seq_printf(m, "console");
+		break;
+	case TTY_DRIVER_TYPE_SERIAL:
+		seq_printf(m, "serial");
+		break;
+	case TTY_DRIVER_TYPE_PTY:
+		if (p->subtype == PTY_TYPE_MASTER)
+			seq_printf(m, "pty:master");
+		else if (p->subtype == PTY_TYPE_SLAVE)
+			seq_printf(m, "pty:slave");
+		else
+			seq_printf(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_printf(m, "system:/dev/tty\n");
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/console", "console");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 1);
+		seq_printf(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_printf(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_printf(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_tty_ldisc = proc_mkdir("tty/ldisc", NULL);
+	/*
+	 * /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);
+}

kernel/fs/proc/root.c

@@ -0,0 +1,228 @@
+/*
+ *  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/mount.h>
+#include <linux/pid_namespace.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)
+{
+	struct pid_namespace *ns;
+
+	ns = (struct pid_namespace *)data;
+	sb->s_fs_info = get_pid_ns(ns);
+	return set_anon_super(sb, NULL);
+}
+
+static int proc_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	int err;
+	struct super_block *sb;
+	struct pid_namespace *ns;
+	struct proc_inode *ei;
+
+	if (proc_mnt) {
+		/* Seed the root directory with a pid so it doesn't need
+		 * to be special in base.c.  I would do this earlier but
+		 * the only task alive when /proc is mounted the first time
+		 * is the init_task and it doesn't have any pids.
+		 */
+		ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
+		if (!ei->pid)
+			ei->pid = find_get_pid(1);
+	}
+
+	if (flags & MS_KERNMOUNT)
+		ns = (struct pid_namespace *)data;
+	else
+		ns = current->nsproxy->pid_ns;
+
+	sb = sget(fs_type, proc_test_super, proc_set_super, ns);
+	if (IS_ERR(sb))
+		return PTR_ERR(sb);
+
+	if (!sb->s_root) {
+		sb->s_flags = flags;
+		err = proc_fill_super(sb);
+		if (err) {
+			deactivate_locked_super(sb);
+			return err;
+		}
+
+		ei = PROC_I(sb->s_root->d_inode);
+		if (!ei->pid) {
+			rcu_read_lock();
+			ei->pid = get_pid(find_pid_ns(1, ns));
+			rcu_read_unlock();
+		}
+
+		sb->s_flags |= MS_ACTIVE;
+		ns->proc_mnt = mnt;
+	}
+
+	simple_set_mnt(mnt, sb);
+	return 0;
+}
+
+static void proc_kill_sb(struct super_block *sb)
+{
+	struct pid_namespace *ns;
+
+	ns = (struct pid_namespace *)sb->s_fs_info;
+	kill_anon_super(sb);
+	put_pid_ns(ns);
+}
+
+static struct file_system_type proc_fs_type = {
+	.name		= "proc",
+	.get_sb		= proc_get_sb,
+	.kill_sb	= proc_kill_sb,
+};
+
+void __init proc_root_init(void)
+{
+	int err;
+
+	proc_init_inodecache();
+	err = register_filesystem(&proc_fs_type);
+	if (err)
+		return;
+	proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
+	err = PTR_ERR(proc_mnt);
+	if (IS_ERR(proc_mnt)) {
+		unregister_filesystem(&proc_fs_type);
+		return;
+	}
+
+	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_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
+#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
+	/* just give it a mountpoint */
+	proc_mkdir("openprom", NULL);
+#endif
+	proc_tty_init();
+#ifdef CONFIG_PROC_DEVICETREE
+	proc_device_tree_init();
+#endif
+	proc_mkdir("bus", NULL);
+	proc_sys_init();
+}
+
+static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
+)
+{
+	generic_fillattr(dentry->d_inode, stat);
+	stat->nlink = proc_root.nlink + nr_processes();
+	return 0;
+}
+
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+{
+	if (!proc_lookup(dir, dentry, nd)) {
+		return NULL;
+	}
+	
+	return proc_pid_lookup(dir, dentry, nd);
+}
+
+static int proc_root_readdir(struct file * filp,
+	void * dirent, filldir_t filldir)
+{
+	unsigned int nr = filp->f_pos;
+	int ret;
+
+	if (nr < FIRST_PROCESS_ENTRY) {
+		int error = proc_readdir(filp, dirent, filldir);
+		if (error <= 0)
+			return error;
+		filp->f_pos = FIRST_PROCESS_ENTRY;
+	}
+
+	ret = proc_pid_readdir(filp, dirent, filldir);
+	return ret;
+}
+
+/*
+ * 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,
+	.readdir	 = proc_root_readdir,
+};
+
+/*
+ * 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, 
+	.name		= "/proc",
+	.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,
+};
+
+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);
+
+	return 0;
+}
+
+void pid_ns_release_proc(struct pid_namespace *ns)
+{
+	mntput(ns->proc_mnt);
+}
+
+EXPORT_SYMBOL(proc_symlink);
+EXPORT_SYMBOL(proc_mkdir);
+EXPORT_SYMBOL(create_proc_entry);
+EXPORT_SYMBOL(proc_create_data);
+EXPORT_SYMBOL(remove_proc_entry);

kernel/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_printf(p, "                ");
+	for_each_possible_cpu(i)
+		seq_printf(p, "CPU%-8d", i);
+	seq_printf(p, "\n");
+
+	for (i = 0; i < NR_SOFTIRQS; i++) {
+		seq_printf(p, "%8s:", softirq_to_name[i]);
+		for_each_possible_cpu(j)
+			seq_printf(p, " %10u", kstat_softirqs_cpu(i, j));
+		seq_printf(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;
+}
+module_init(proc_softirqs_init);

kernel/fs/proc/stat.c

@@ -0,0 +1,172 @@
+#include <linux/cpumask.h>
+#include <linux/fs.h>
+#include <linux/gfp.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 <asm/cputime.h>
+
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+#ifndef arch_irq_stat
+#define arch_irq_stat() 0
+#endif
+#ifndef arch_idle_time
+#define arch_idle_time(cpu) 0
+#endif
+
+static int show_stat(struct seq_file *p, void *v)
+{
+	int i, j;
+	unsigned long jif;
+	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
+	cputime64_t guest;
+	u64 sum = 0;
+	u64 sum_softirq = 0;
+	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
+	struct timespec boottime;
+	unsigned int per_irq_sum;
+
+	user = nice = system = idle = iowait =
+		irq = softirq = steal = cputime64_zero;
+	guest = cputime64_zero;
+	getboottime(&boottime);
+	jif = boottime.tv_sec;
+
+	for_each_possible_cpu(i) {
+		user = cputime64_add(user, kstat_cpu(i).cpustat.user);
+		nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
+		system = cputime64_add(system, kstat_cpu(i).cpustat.system);
+		idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle);
+		idle = cputime64_add(idle, arch_idle_time(i));
+		iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait);
+		irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
+		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
+		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
+		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
+		for_each_irq_nr(j) {
+			sum += kstat_irqs_cpu(j, 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_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+		(unsigned long long)cputime64_to_clock_t(user),
+		(unsigned long long)cputime64_to_clock_t(nice),
+		(unsigned long long)cputime64_to_clock_t(system),
+		(unsigned long long)cputime64_to_clock_t(idle),
+		(unsigned long long)cputime64_to_clock_t(iowait),
+		(unsigned long long)cputime64_to_clock_t(irq),
+		(unsigned long long)cputime64_to_clock_t(softirq),
+		(unsigned long long)cputime64_to_clock_t(steal),
+		(unsigned long long)cputime64_to_clock_t(guest));
+	for_each_online_cpu(i) {
+
+		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
+		user = kstat_cpu(i).cpustat.user;
+		nice = kstat_cpu(i).cpustat.nice;
+		system = kstat_cpu(i).cpustat.system;
+		idle = kstat_cpu(i).cpustat.idle;
+		idle = cputime64_add(idle, arch_idle_time(i));
+		iowait = kstat_cpu(i).cpustat.iowait;
+		irq = kstat_cpu(i).cpustat.irq;
+		softirq = kstat_cpu(i).cpustat.softirq;
+		steal = kstat_cpu(i).cpustat.steal;
+		guest = kstat_cpu(i).cpustat.guest;
+		seq_printf(p,
+			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+			i,
+			(unsigned long long)cputime64_to_clock_t(user),
+			(unsigned long long)cputime64_to_clock_t(nice),
+			(unsigned long long)cputime64_to_clock_t(system),
+			(unsigned long long)cputime64_to_clock_t(idle),
+			(unsigned long long)cputime64_to_clock_t(iowait),
+			(unsigned long long)cputime64_to_clock_t(irq),
+			(unsigned long long)cputime64_to_clock_t(softirq),
+			(unsigned long long)cputime64_to_clock_t(steal),
+			(unsigned long long)cputime64_to_clock_t(guest));
+	}
+	seq_printf(p, "intr %llu", (unsigned long long)sum);
+
+	/* sum again ? it could be updated? */
+	for_each_irq_nr(j) {
+		per_irq_sum = 0;
+		for_each_possible_cpu(i)
+			per_irq_sum += kstat_irqs_cpu(j, i);
+
+		seq_printf(p, " %u", per_irq_sum);
+	}
+
+	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_printf(p, " %u", per_softirq_sums[i]);
+	seq_printf(p, "\n");
+
+	return 0;
+}
+
+static int stat_open(struct inode *inode, struct file *file)
+{
+	unsigned size = 4096 * (1 + num_possible_cpus() / 32);
+	char *buf;
+	struct seq_file *m;
+	int res;
+
+	/* don't ask for more than the kmalloc() max size, currently 128 KB */
+	if (size > 128 * 1024)
+		size = 128 * 1024;
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	res = single_open(file, show_stat, NULL);
+	if (!res) {
+		m = file->private_data;
+		m->buf = buf;
+		m->size = size;
+	} else
+		kfree(buf);
+	return res;
+}
+
+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;
+}
+module_init(proc_stat_init);

kernel/fs/proc/task_mmu.c

@@ -0,0 +1,803 @@
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/mount.h>
+#include <linux/seq_file.h>
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/pagemap.h>
+#include <linux/mempolicy.h>
+#include <linux/swap.h>
+#include <linux/swapops.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;
+	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;
+	seq_printf(m,
+		"VmPeak:\t%8lu kB\n"
+		"VmSize:\t%8lu kB\n"
+		"VmLck:\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",
+		hiwater_vm << (PAGE_SHIFT-10),
+		(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
+		mm->locked_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,
+		(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
+}
+
+unsigned long task_vsize(struct mm_struct *mm)
+{
+	return PAGE_SIZE * mm->total_vm;
+}
+
+int task_statm(struct mm_struct *mm, int *shared, int *text,
+	       int *data, int *resident)
+{
+	*shared = get_mm_counter(mm, file_rss);
+	*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, anon_rss);
+	return mm->total_vm;
+}
+
+static void pad_len_spaces(struct seq_file *m, int len)
+{
+	len = 25 + sizeof(void*) * 6 - len;
+	if (len < 1)
+		len = 1;
+	seq_printf(m, "%*c", len, ' ');
+}
+
+static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
+{
+	if (vma && vma != priv->tail_vma) {
+		struct mm_struct *mm = vma->vm_mm;
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+}
+
+static void *m_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_maps_private *priv = m->private;
+	unsigned long last_addr = m->version;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma, *tail_vma = NULL;
+	loff_t l = *pos;
+
+	/* Clear the per syscall fields in priv */
+	priv->task = NULL;
+	priv->tail_vma = NULL;
+
+	/*
+	 * We remember last_addr rather than next_addr to hit with
+	 * mmap_cache most of the time. We have zero last_addr at
+	 * the beginning and also after lseek. We will have -1 last_addr
+	 * after the end of the vmas.
+	 */
+
+	if (last_addr == -1UL)
+		return NULL;
+
+	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+	if (!priv->task)
+		return NULL;
+
+	mm = mm_for_maps(priv->task);
+	if (!mm)
+		return NULL;
+	down_read(&mm->mmap_sem);
+
+	tail_vma = get_gate_vma(priv->task);
+	priv->tail_vma = tail_vma;
+
+	/* Start with last addr hint */
+	vma = find_vma(mm, last_addr);
+	if (last_addr && vma) {
+		vma = vma->vm_next;
+		goto out;
+	}
+
+	/*
+	 * Check the vma index is within the range and do
+	 * sequential scan until m_index.
+	 */
+	vma = NULL;
+	if ((unsigned long)l < mm->map_count) {
+		vma = mm->mmap;
+		while (l-- && vma)
+			vma = vma->vm_next;
+		goto out;
+	}
+
+	if (l != mm->map_count)
+		tail_vma = NULL; /* After gate vma */
+
+out:
+	if (vma)
+		return vma;
+
+	/* End of vmas has been reached */
+	m->version = (tail_vma != NULL)? 0: -1UL;
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+	return tail_vma;
+}
+
+static void *m_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma = v;
+	struct vm_area_struct *tail_vma = priv->tail_vma;
+
+	(*pos)++;
+	if (vma && (vma != tail_vma) && vma->vm_next)
+		return vma->vm_next;
+	vma_stop(priv, vma);
+	return (vma != tail_vma)? tail_vma: NULL;
+}
+
+static void m_stop(struct seq_file *m, void *v)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma = v;
+
+	vma_stop(priv, vma);
+	if (priv->task)
+		put_task_struct(priv->task);
+}
+
+static int do_maps_open(struct inode *inode, struct file *file,
+			const struct seq_operations *ops)
+{
+	struct proc_maps_private *priv;
+	int ret = -ENOMEM;
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (priv) {
+		priv->pid = proc_pid(inode);
+		ret = seq_open(file, ops);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = priv;
+		} else {
+			kfree(priv);
+		}
+	}
+	return ret;
+}
+
+static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct file *file = vma->vm_file;
+	int flags = vma->vm_flags;
+	unsigned long ino = 0;
+	unsigned long long pgoff = 0;
+	unsigned long start;
+	dev_t dev = 0;
+	int len;
+
+	if (file) {
+		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+		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 (vma->vm_flags & VM_GROWSDOWN)
+		if (!vma_stack_continue(vma->vm_prev, vma->vm_start))
+			start += PAGE_SIZE;
+
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+			start,
+			vma->vm_end,
+			flags & VM_READ ? 'r' : '-',
+			flags & VM_WRITE ? 'w' : '-',
+			flags & VM_EXEC ? 'x' : '-',
+			flags & VM_MAYSHARE ? 's' : 'p',
+			pgoff,
+			MAJOR(dev), MINOR(dev), ino, &len);
+
+	/*
+	 * Print the dentry name for named mappings, and a
+	 * special [heap] marker for the heap:
+	 */
+	if (file) {
+		pad_len_spaces(m, len);
+		seq_path(m, &file->f_path, "\n");
+	} else {
+		const char *name = arch_vma_name(vma);
+		if (!name) {
+			if (mm) {
+				if (vma->vm_start <= mm->brk &&
+						vma->vm_end >= mm->start_brk) {
+					name = "[heap]";
+				} else if (vma->vm_start <= mm->start_stack &&
+					   vma->vm_end >= mm->start_stack) {
+					name = "[stack]";
+				}
+			} else {
+				name = "[vdso]";
+			}
+		}
+		if (name) {
+			pad_len_spaces(m, len);
+			seq_puts(m, name);
+		}
+	}
+	seq_putc(m, '\n');
+}
+
+static int show_map(struct seq_file *m, void *v)
+{
+	struct vm_area_struct *vma = v;
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
+
+	show_map_vma(m, vma);
+
+	if (m->count < m->size)  /* vma is copied successfully */
+		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+	return 0;
+}
+
+static const struct seq_operations proc_pid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_map
+};
+
+static int maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_maps_op);
+}
+
+const struct file_operations proc_maps_operations = {
+	.open		= maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+/*
+ * 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 {
+	struct vm_area_struct *vma;
+	unsigned long resident;
+	unsigned long shared_clean;
+	unsigned long shared_dirty;
+	unsigned long private_clean;
+	unsigned long private_dirty;
+	unsigned long referenced;
+	unsigned long swap;
+	u64 pss;
+};
+
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			   struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = mss->vma;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+	int mapcount;
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+
+		if (is_swap_pte(ptent)) {
+			mss->swap += PAGE_SIZE;
+			continue;
+		}
+
+		if (!pte_present(ptent))
+			continue;
+
+		mss->resident += PAGE_SIZE;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		/* Accumulate the size in pages that have been accessed. */
+		if (pte_young(ptent) || PageReferenced(page))
+			mss->referenced += PAGE_SIZE;
+		mapcount = page_mapcount(page);
+		if (mapcount >= 2) {
+			if (pte_dirty(ptent))
+				mss->shared_dirty += PAGE_SIZE;
+			else
+				mss->shared_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+		} else {
+			if (pte_dirty(ptent))
+				mss->private_dirty += PAGE_SIZE;
+			else
+				mss->private_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_SHIFT);
+		}
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+	return 0;
+}
+
+static int show_smap(struct seq_file *m, void *v)
+{
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
+	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);
+	mss.vma = vma;
+	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
+		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
+
+	show_map_vma(m, vma);
+
+	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"
+		   "Swap:           %8lu kB\n"
+		   "KernelPageSize: %8lu kB\n"
+		   "MMUPageSize:    %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.swap >> 10,
+		   vma_kernel_pagesize(vma) >> 10,
+		   vma_mmu_pagesize(vma) >> 10);
+
+	if (m->count < m->size)  /* vma is copied successfully */
+		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+	return 0;
+}
+
+static const struct seq_operations proc_pid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_smap
+};
+
+static int smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_smaps_op);
+}
+
+const struct file_operations proc_smaps_operations = {
+	.open		= smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->private;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+		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;
+}
+
+#define CLEAR_REFS_ALL 1
+#define CLEAR_REFS_ANON 2
+#define CLEAR_REFS_MAPPED 3
+
+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;
+	long type;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+	if (strict_strtol(strstrip(buffer), 10, &type))
+		return -EINVAL;
+	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+		return -EINVAL;
+	task = get_proc_task(file->f_path.dentry->d_inode);
+	if (!task)
+		return -ESRCH;
+	mm = get_task_mm(task);
+	if (mm) {
+		struct mm_walk clear_refs_walk = {
+			.pmd_entry = clear_refs_pte_range,
+			.mm = mm,
+		};
+		down_read(&mm->mmap_sem);
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			clear_refs_walk.private = vma;
+			if (is_vm_hugetlb_page(vma))
+				continue;
+			/*
+			 * 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.
+			 */
+			if (type == CLEAR_REFS_ANON && vma->vm_file)
+				continue;
+			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
+				continue;
+			walk_page_range(vma->vm_start, vma->vm_end,
+					&clear_refs_walk);
+		}
+		flush_tlb_mm(mm);
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+	put_task_struct(task);
+
+	return count;
+}
+
+const struct file_operations proc_clear_refs_operations = {
+	.write		= clear_refs_write,
+};
+
+struct pagemapread {
+	u64 __user *out, *end;
+};
+
+#define PM_ENTRY_BYTES      sizeof(u64)
+#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)
+
+#define PM_PRESENT          PM_STATUS(4LL)
+#define PM_SWAP             PM_STATUS(2LL)
+#define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
+#define PM_END_OF_BUFFER    1
+
+static int add_to_pagemap(unsigned long addr, u64 pfn,
+			  struct pagemapread *pm)
+{
+	if (put_user(pfn, pm->out))
+		return -EFAULT;
+	pm->out++;
+	if (pm->out >= pm->end)
+		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;
+	int err = 0;
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static u64 swap_pte_to_pagemap_entry(pte_t pte)
+{
+	swp_entry_t e = pte_to_swp_entry(pte);
+	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
+}
+
+static u64 pte_to_pagemap_entry(pte_t pte)
+{
+	u64 pme = 0;
+	if (is_swap_pte(pte))
+		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+	else if (pte_present(pte))
+		pme = PM_PFRAME(pte_pfn(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+	return pme;
+}
+
+static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			     struct mm_walk *walk)
+{
+	struct vm_area_struct *vma;
+	struct pagemapread *pm = walk->private;
+	pte_t *pte;
+	int err = 0;
+
+	/* find the first VMA at or above 'addr' */
+	vma = find_vma(walk->mm, addr);
+	for (; addr != end; addr += PAGE_SIZE) {
+		u64 pfn = PM_NOT_PRESENT;
+
+		/* check to see if we've left 'vma' behind
+		 * and need a new, higher one */
+		if (vma && (addr >= vma->vm_end))
+			vma = find_vma(walk->mm, addr);
+
+		/* check that 'vma' actually covers this address,
+		 * and that it isn't a huge page vma */
+		if (vma && (vma->vm_start <= addr) &&
+		    !is_vm_hugetlb_page(vma)) {
+			pte = pte_offset_map(pmd, addr);
+			pfn = pte_to_pagemap_entry(*pte);
+			/* unmap before userspace copy */
+			pte_unmap(pte);
+		}
+		err = add_to_pagemap(addr, pfn, pm);
+		if (err)
+			return err;
+	}
+
+	cond_resched();
+
+	return err;
+}
+
+/*
+ * /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 0-55  page frame number (PFN) if present
+ * Bits 0-4   swap type if swapped
+ * Bits 5-55  swap offset if swapped
+ * Bits 55-60 page shift (page size = 1<<page shift)
+ * Bit  61    reserved for future use
+ * 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->f_path.dentry->d_inode);
+	struct page **pages, *page;
+	unsigned long uaddr, uend;
+	struct mm_struct *mm;
+	struct pagemapread pm;
+	int pagecount;
+	int ret = -ESRCH;
+	struct mm_walk pagemap_walk = {};
+	unsigned long src;
+	unsigned long svpfn;
+	unsigned long start_vaddr;
+	unsigned long end_vaddr;
+
+	if (!task)
+		goto out;
+
+	ret = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out_task;
+
+	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;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_task;
+
+
+	uaddr = (unsigned long)buf & PAGE_MASK;
+	uend = (unsigned long)(buf + count);
+	pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
+	ret = 0;
+	if (pagecount == 0)
+		goto out_mm;
+	pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
+	ret = -ENOMEM;
+	if (!pages)
+		goto out_mm;
+
+	down_read(&current->mm->mmap_sem);
+	ret = get_user_pages(current, current->mm, uaddr, pagecount,
+			     1, 0, pages, NULL);
+	up_read(&current->mm->mmap_sem);
+
+	if (ret < 0)
+		goto out_free;
+
+	if (ret != pagecount) {
+		pagecount = ret;
+		ret = -EFAULT;
+		goto out_pages;
+	}
+
+	pm.out = (u64 __user *)buf;
+	pm.end = (u64 __user *)(buf + count);
+
+	pagemap_walk.pmd_entry = pagemap_pte_range;
+	pagemap_walk.pte_hole = pagemap_pte_hole;
+	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 = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk);
+	if (ret == PM_END_OF_BUFFER)
+		ret = 0;
+	/* don't need mmap_sem for these, but this looks cleaner */
+	*ppos += (char __user *)pm.out - buf;
+	if (!ret)
+		ret = (char __user *)pm.out - buf;
+
+out_pages:
+	for (; pagecount; pagecount--) {
+		page = pages[pagecount-1];
+		if (!PageReserved(page))
+			SetPageDirty(page);
+		page_cache_release(page);
+	}
+out_free:
+	kfree(pages);
+out_mm:
+	mmput(mm);
+out_task:
+	put_task_struct(task);
+out:
+	return ret;
+}
+
+const struct file_operations proc_pagemap_operations = {
+	.llseek		= mem_lseek, /* borrow this */
+	.read		= pagemap_read,
+};
+#endif /* CONFIG_PROC_PAGE_MONITOR */
+
+#ifdef CONFIG_NUMA
+extern int show_numa_map(struct seq_file *m, void *v);
+
+static const struct seq_operations proc_pid_numa_maps_op = {
+        .start  = m_start,
+        .next   = m_next,
+        .stop   = m_stop,
+        .show   = show_numa_map,
+};
+
+static int numa_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+const struct file_operations proc_numa_maps_operations = {
+	.open		= numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+#endif

kernel/fs/proc/task_nommu.c

@@ -0,0 +1,253 @@
+
+#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/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;
+}
+
+int task_statm(struct mm_struct *mm, int *shared, int *text,
+	       int *data, int *resident)
+{
+	struct vm_area_struct *vma;
+	struct vm_region *region;
+	struct rb_node *p;
+	int 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;
+		}
+	}
+
+	size += (*text = mm->end_code - mm->start_code);
+	size += (*data = mm->start_stack - mm->start_data);
+	up_read(&mm->mmap_sem);
+	*resident = size;
+	return size;
+}
+
+/*
+ * display a single VMA to a sequenced file
+ */
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+{
+	unsigned long ino = 0;
+	struct file *file;
+	dev_t dev = 0;
+	int flags, len;
+	unsigned long long pgoff = 0;
+
+	flags = vma->vm_flags;
+	file = vma->vm_file;
+
+	if (file) {
+		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+		pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+	}
+
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+		   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, &len);
+
+	if (file) {
+		len = 25 + sizeof(void *) * 6 - len;
+		if (len < 1)
+			len = 1;
+		seq_printf(m, "%*c", len, ' ');
+		seq_path(m, &file->f_path, "");
+	}
+
+	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)
+{
+	struct rb_node *p = _p;
+
+	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
+}
+
+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_pid_task(priv->pid, PIDTYPE_PID);
+	if (!priv->task)
+		return NULL;
+
+	mm = mm_for_maps(priv->task);
+	if (!mm) {
+		put_task_struct(priv->task);
+		priv->task = NULL;
+		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;
+	return NULL;
+}
+
+static void m_stop(struct seq_file *m, void *_vml)
+{
+	struct proc_maps_private *priv = m->private;
+
+	if (priv->task) {
+		struct mm_struct *mm = priv->task->mm;
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+		put_task_struct(priv->task);
+	}
+}
+
+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_map
+};
+
+static int maps_open(struct inode *inode, struct file *file)
+{
+	struct proc_maps_private *priv;
+	int ret = -ENOMEM;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (priv) {
+		priv->pid = proc_pid(inode);
+		ret = seq_open(file, &proc_pid_maps_ops);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = priv;
+		} else {
+			kfree(priv);
+		}
+	}
+	return ret;
+}
+
+const struct file_operations proc_maps_operations = {
+	.open		= maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+

kernel/fs/proc/uptime.c

@@ -0,0 +1,48 @@
+#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 <asm/cputime.h>
+
+static int uptime_proc_show(struct seq_file *m, void *v)
+{
+	struct timespec uptime;
+	struct timespec idle;
+	int i;
+	cputime_t idletime = cputime_zero;
+
+	for_each_possible_cpu(i)
+		idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle);
+
+	do_posix_clock_monotonic_gettime(&uptime);
+	monotonic_to_bootbased(&uptime);
+	cputime_to_timespec(idletime, &idle);
+	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;
+}
+module_init(proc_uptime_init);

kernel/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;
+}
+module_init(proc_version_init);

kernel/fs/proc/vmcore.c

@@ -0,0 +1,653 @@
+/*
+ *	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/proc_fs.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/crash_dump.h>
+#include <linux/list.h>
+#include <asm/uaccess.h>
+#include <asm/io.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;
+
+/* Total size of vmcore file. */
+static u64 vmcore_size;
+
+static struct proc_dir_entry *proc_vmcore = NULL;
+
+/* 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;
+
+		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;
+}
+
+/* Maps vmcore file offset to respective physical address in memroy. */
+static u64 map_offset_to_paddr(loff_t offset, struct list_head *vc_list,
+					struct vmcore **m_ptr)
+{
+	struct vmcore *m;
+	u64 paddr;
+
+	list_for_each_entry(m, vc_list, list) {
+		u64 start, end;
+		start = m->offset;
+		end = m->offset + m->size - 1;
+		if (offset >= start && offset <= end) {
+			paddr = m->paddr + offset - start;
+			*m_ptr = m;
+			return paddr;
+		}
+	}
+	*m_ptr = NULL;
+	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(struct file *file, char __user *buffer,
+				size_t buflen, loff_t *fpos)
+{
+	ssize_t acc = 0, tmp;
+	size_t tsz;
+	u64 start, nr_bytes;
+	struct vmcore *curr_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 = elfcorebuf_sz - *fpos;
+		if (buflen < tsz)
+			tsz = buflen;
+		if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
+			return -EFAULT;
+		buflen -= tsz;
+		*fpos += tsz;
+		buffer += tsz;
+		acc += tsz;
+
+		/* leave now if filled buffer already */
+		if (buflen == 0)
+			return acc;
+	}
+
+	start = map_offset_to_paddr(*fpos, &vmcore_list, &curr_m);
+	if (!curr_m)
+        	return -EINVAL;
+	if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
+		tsz = buflen;
+
+	/* Calculate left bytes in current memory segment. */
+	nr_bytes = (curr_m->size - (start - curr_m->paddr));
+	if (tsz > nr_bytes)
+		tsz = nr_bytes;
+
+	while (buflen) {
+		tmp = read_from_oldmem(buffer, tsz, &start, 1);
+		if (tmp < 0)
+			return tmp;
+		buflen -= tsz;
+		*fpos += tsz;
+		buffer += tsz;
+		acc += tsz;
+		if (start >= (curr_m->paddr + curr_m->size)) {
+			if (curr_m->list.next == &vmcore_list)
+				return acc;	/*EOF*/
+			curr_m = list_entry(curr_m->list.next,
+						struct vmcore, list);
+			start = curr_m->paddr;
+		}
+		if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
+			tsz = buflen;
+		/* Calculate left bytes in current memory segment. */
+		nr_bytes = (curr_m->size - (start - curr_m->paddr));
+		if (tsz > nr_bytes)
+			tsz = nr_bytes;
+	}
+	return acc;
+}
+
+static const struct file_operations proc_vmcore_operations = {
+	.read		= read_vmcore,
+};
+
+static struct vmcore* __init get_new_element(void)
+{
+	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
+}
+
+static u64 __init get_vmcore_size_elf64(char *elfptr)
+{
+	int i;
+	u64 size;
+	Elf64_Ehdr *ehdr_ptr;
+	Elf64_Phdr *phdr_ptr;
+
+	ehdr_ptr = (Elf64_Ehdr *)elfptr;
+	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr));
+	size = sizeof(Elf64_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr));
+	for (i = 0; i < ehdr_ptr->e_phnum; i++) {
+		size += phdr_ptr->p_memsz;
+		phdr_ptr++;
+	}
+	return size;
+}
+
+static u64 __init get_vmcore_size_elf32(char *elfptr)
+{
+	int i;
+	u64 size;
+	Elf32_Ehdr *ehdr_ptr;
+	Elf32_Phdr *phdr_ptr;
+
+	ehdr_ptr = (Elf32_Ehdr *)elfptr;
+	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr));
+	size = sizeof(Elf32_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr));
+	for (i = 0; i < ehdr_ptr->e_phnum; i++) {
+		size += phdr_ptr->p_memsz;
+		phdr_ptr++;
+	}
+	return size;
+}
+
+/* Merges all the PT_NOTE headers into one. */
+static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
+						struct list_head *vc_list)
+{
+	int i, nr_ptnote=0, rc=0;
+	char *tmp;
+	Elf64_Ehdr *ehdr_ptr;
+	Elf64_Phdr phdr, *phdr_ptr;
+	Elf64_Nhdr *nhdr_ptr;
+	u64 phdr_sz = 0, note_off;
+
+	ehdr_ptr = (Elf64_Ehdr *)elfptr;
+	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr));
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		int j;
+		void *notes_section;
+		struct vmcore *new;
+		u64 offset, max_sz, sz, real_sz = 0;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		nr_ptnote++;
+		max_sz = phdr_ptr->p_memsz;
+		offset = phdr_ptr->p_offset;
+		notes_section = kmalloc(max_sz, GFP_KERNEL);
+		if (!notes_section)
+			return -ENOMEM;
+		rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+		if (rc < 0) {
+			kfree(notes_section);
+			return rc;
+		}
+		nhdr_ptr = notes_section;
+		for (j = 0; j < max_sz; j += sz) {
+			if (nhdr_ptr->n_namesz == 0)
+				break;
+			sz = sizeof(Elf64_Nhdr) +
+				((nhdr_ptr->n_namesz + 3) & ~3) +
+				((nhdr_ptr->n_descsz + 3) & ~3);
+			real_sz += sz;
+			nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
+		}
+
+		/* Add this contiguous chunk of notes section to vmcore list.*/
+		new = get_new_element();
+		if (!new) {
+			kfree(notes_section);
+			return -ENOMEM;
+		}
+		new->paddr = phdr_ptr->p_offset;
+		new->size = real_sz;
+		list_add_tail(&new->list, vc_list);
+		phdr_sz += real_sz;
+		kfree(notes_section);
+	}
+
+	/* 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  = note_off;
+	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)));
+
+	/* Modify e_phnum to reflect merged headers. */
+	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
+
+	return 0;
+}
+
+/* Merges all the PT_NOTE headers into one. */
+static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
+						struct list_head *vc_list)
+{
+	int i, nr_ptnote=0, rc=0;
+	char *tmp;
+	Elf32_Ehdr *ehdr_ptr;
+	Elf32_Phdr phdr, *phdr_ptr;
+	Elf32_Nhdr *nhdr_ptr;
+	u64 phdr_sz = 0, note_off;
+
+	ehdr_ptr = (Elf32_Ehdr *)elfptr;
+	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr));
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		int j;
+		void *notes_section;
+		struct vmcore *new;
+		u64 offset, max_sz, sz, real_sz = 0;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		nr_ptnote++;
+		max_sz = phdr_ptr->p_memsz;
+		offset = phdr_ptr->p_offset;
+		notes_section = kmalloc(max_sz, GFP_KERNEL);
+		if (!notes_section)
+			return -ENOMEM;
+		rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+		if (rc < 0) {
+			kfree(notes_section);
+			return rc;
+		}
+		nhdr_ptr = notes_section;
+		for (j = 0; j < max_sz; j += sz) {
+			if (nhdr_ptr->n_namesz == 0)
+				break;
+			sz = sizeof(Elf32_Nhdr) +
+				((nhdr_ptr->n_namesz + 3) & ~3) +
+				((nhdr_ptr->n_descsz + 3) & ~3);
+			real_sz += sz;
+			nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
+		}
+
+		/* Add this contiguous chunk of notes section to vmcore list.*/
+		new = get_new_element();
+		if (!new) {
+			kfree(notes_section);
+			return -ENOMEM;
+		}
+		new->paddr = phdr_ptr->p_offset;
+		new->size = real_sz;
+		list_add_tail(&new->list, vc_list);
+		phdr_sz += real_sz;
+		kfree(notes_section);
+	}
+
+	/* 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  = note_off;
+	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)));
+
+	/* 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,
+						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 */
+
+	/* First program header is PT_NOTE header. */
+	vmcore_off = sizeof(Elf64_Ehdr) +
+			(ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr) +
+			phdr_ptr->p_memsz; /* Note sections */
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		if (phdr_ptr->p_type != PT_LOAD)
+			continue;
+
+		/* Add this contiguous chunk of memory to vmcore list.*/
+		new = get_new_element();
+		if (!new)
+			return -ENOMEM;
+		new->paddr = phdr_ptr->p_offset;
+		new->size = phdr_ptr->p_memsz;
+		list_add_tail(&new->list, vc_list);
+
+		/* Update the program header offset. */
+		phdr_ptr->p_offset = vmcore_off;
+		vmcore_off = vmcore_off + phdr_ptr->p_memsz;
+	}
+	return 0;
+}
+
+static int __init process_ptload_program_headers_elf32(char *elfptr,
+						size_t elfsz,
+						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 */
+
+	/* First program header is PT_NOTE header. */
+	vmcore_off = sizeof(Elf32_Ehdr) +
+			(ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr) +
+			phdr_ptr->p_memsz; /* Note sections */
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		if (phdr_ptr->p_type != PT_LOAD)
+			continue;
+
+		/* Add this contiguous chunk of memory to vmcore list.*/
+		new = get_new_element();
+		if (!new)
+			return -ENOMEM;
+		new->paddr = phdr_ptr->p_offset;
+		new->size = phdr_ptr->p_memsz;
+		list_add_tail(&new->list, vc_list);
+
+		/* Update the program header offset */
+		phdr_ptr->p_offset = vmcore_off;
+		vmcore_off = vmcore_off + phdr_ptr->p_memsz;
+	}
+	return 0;
+}
+
+/* Sets offset fields of vmcore elements. */
+static void __init set_vmcore_list_offsets_elf64(char *elfptr,
+						struct list_head *vc_list)
+{
+	loff_t vmcore_off;
+	Elf64_Ehdr *ehdr_ptr;
+	struct vmcore *m;
+
+	ehdr_ptr = (Elf64_Ehdr *)elfptr;
+
+	/* Skip Elf header and program headers. */
+	vmcore_off = sizeof(Elf64_Ehdr) +
+			(ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr);
+
+	list_for_each_entry(m, vc_list, list) {
+		m->offset = vmcore_off;
+		vmcore_off += m->size;
+	}
+}
+
+/* Sets offset fields of vmcore elements. */
+static void __init set_vmcore_list_offsets_elf32(char *elfptr,
+						struct list_head *vc_list)
+{
+	loff_t vmcore_off;
+	Elf32_Ehdr *ehdr_ptr;
+	struct vmcore *m;
+
+	ehdr_ptr = (Elf32_Ehdr *)elfptr;
+
+	/* Skip Elf header and program headers. */
+	vmcore_off = sizeof(Elf32_Ehdr) +
+			(ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr);
+
+	list_for_each_entry(m, vc_list, list) {
+		m->offset = vmcore_off;
+		vmcore_off += m->size;
+	}
+}
+
+static int __init parse_crash_elf64_headers(void)
+{
+	int rc=0;
+	Elf64_Ehdr ehdr;
+	u64 addr;
+
+	addr = elfcorehdr_addr;
+
+	/* Read Elf header */
+	rc = read_from_oldmem((char*)&ehdr, sizeof(Elf64_Ehdr), &addr, 0);
+	if (rc < 0)
+		return rc;
+
+	/* Do some basic Verification. */
+	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
+		(ehdr.e_type != ET_CORE) ||
+		!vmcore_elf_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) {
+		printk(KERN_WARNING "Warning: Core image elf header is not"
+					"sane\n");
+		return -EINVAL;
+	}
+
+	/* Read in all elf headers. */
+	elfcorebuf_sz = sizeof(Elf64_Ehdr) + ehdr.e_phnum * sizeof(Elf64_Phdr);
+	elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL);
+	if (!elfcorebuf)
+		return -ENOMEM;
+	addr = elfcorehdr_addr;
+	rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0);
+	if (rc < 0) {
+		kfree(elfcorebuf);
+		return rc;
+	}
+
+	/* Merge all PT_NOTE headers into one. */
+	rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, &vmcore_list);
+	if (rc) {
+		kfree(elfcorebuf);
+		return rc;
+	}
+	rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz,
+							&vmcore_list);
+	if (rc) {
+		kfree(elfcorebuf);
+		return rc;
+	}
+	set_vmcore_list_offsets_elf64(elfcorebuf, &vmcore_list);
+	return 0;
+}
+
+static int __init parse_crash_elf32_headers(void)
+{
+	int rc=0;
+	Elf32_Ehdr ehdr;
+	u64 addr;
+
+	addr = elfcorehdr_addr;
+
+	/* Read Elf header */
+	rc = read_from_oldmem((char*)&ehdr, sizeof(Elf32_Ehdr), &addr, 0);
+	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) {
+		printk(KERN_WARNING "Warning: Core image elf header is not"
+					"sane\n");
+		return -EINVAL;
+	}
+
+	/* Read in all elf headers. */
+	elfcorebuf_sz = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr);
+	elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL);
+	if (!elfcorebuf)
+		return -ENOMEM;
+	addr = elfcorehdr_addr;
+	rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0);
+	if (rc < 0) {
+		kfree(elfcorebuf);
+		return rc;
+	}
+
+	/* Merge all PT_NOTE headers into one. */
+	rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, &vmcore_list);
+	if (rc) {
+		kfree(elfcorebuf);
+		return rc;
+	}
+	rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz,
+								&vmcore_list);
+	if (rc) {
+		kfree(elfcorebuf);
+		return rc;
+	}
+	set_vmcore_list_offsets_elf32(elfcorebuf, &vmcore_list);
+	return 0;
+}
+
+static int __init parse_crash_elf_headers(void)
+{
+	unsigned char e_ident[EI_NIDENT];
+	u64 addr;
+	int rc=0;
+
+	addr = elfcorehdr_addr;
+	rc = read_from_oldmem(e_ident, EI_NIDENT, &addr, 0);
+	if (rc < 0)
+		return rc;
+	if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
+		printk(KERN_WARNING "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;
+
+		/* Determine vmcore size. */
+		vmcore_size = get_vmcore_size_elf64(elfcorebuf);
+	} else if (e_ident[EI_CLASS] == ELFCLASS32) {
+		rc = parse_crash_elf32_headers();
+		if (rc)
+			return rc;
+
+		/* Determine vmcore size. */
+		vmcore_size = get_vmcore_size_elf32(elfcorebuf);
+	} else {
+		printk(KERN_WARNING "Warning: Core image elf header is not"
+					" sane\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Init function for vmcore module. */
+static int __init vmcore_init(void)
+{
+	int rc = 0;
+
+	/* If elfcorehdr= has been passed in cmdline, then capture the dump.*/
+	if (!(is_vmcore_usable()))
+		return rc;
+	rc = parse_crash_elf_headers();
+	if (rc) {
+		printk(KERN_WARNING "Kdump: vmcore not initialized\n");
+		return rc;
+	}
+
+	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
+	if (proc_vmcore)
+		proc_vmcore->size = vmcore_size;
+	return 0;
+}
+module_init(vmcore_init)