Creation of Cybook 2416 (actually Gen4) repository

fs/proc/Makefile

@@ -0,0 +1,17 @@
+#
+# 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_misc.o
+
+proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
+proc-$(CONFIG_PROC_KCORE)	+= kcore.o
+proc-$(CONFIG_PROC_VMCORE)	+= vmcore.o
+proc-$(CONFIG_PROC_DEVICETREE)	+= proc_devtree.o
+proc-$(CONFIG_PRINTK)	+= kmsg.o

fs/proc/array.c

@@ -0,0 +1,523 @@
+/*
+ *  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.Cox@linux.org>
+ *
+ * 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/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/times.h>
+#include <linux/cpuset.h>
+#include <linux/rcupdate.h>
+#include <linux/delayacct.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include "internal.h"
+
+/* Gcc optimizes away "strlen(x)" for constant x */
+#define ADDBUF(buffer, string) \
+do { memcpy(buffer, string, strlen(string)); \
+     buffer += strlen(string); } while (0)
+
+static inline char * task_name(struct task_struct *p, char * buf)
+{
+	int i;
+	char * name;
+	char tcomm[sizeof(p->comm)];
+
+	get_task_comm(tcomm, p);
+
+	ADDBUF(buf, "Name:\t");
+	name = tcomm;
+	i = sizeof(tcomm);
+	do {
+		unsigned char c = *name;
+		name++;
+		i--;
+		*buf = c;
+		if (!c)
+			break;
+		if (c == '\\') {
+			buf[1] = c;
+			buf += 2;
+			continue;
+		}
+		if (c == '\n') {
+			buf[0] = '\\';
+			buf[1] = 'n';
+			buf += 2;
+			continue;
+		}
+		buf++;
+	} while (i);
+	*buf = '\n';
+	return buf+1;
+}
+
+/*
+ * 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_RUNNING |
+					    TASK_INTERRUPTIBLE |
+					    TASK_UNINTERRUPTIBLE |
+					    TASK_STOPPED |
+					    TASK_TRACED)) |
+			(tsk->exit_state & (EXIT_ZOMBIE |
+					    EXIT_DEAD));
+	const char **p = &task_state_array[0];
+
+	while (state) {
+		p++;
+		state >>= 1;
+	}
+	return *p;
+}
+
+static inline char * task_state(struct task_struct *p, char *buffer)
+{
+	struct group_info *group_info;
+	int g;
+	struct fdtable *fdt = NULL;
+
+	rcu_read_lock();
+	buffer += sprintf(buffer,
+		"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),
+	       	p->tgid, p->pid,
+	       	pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0,
+		pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0,
+		p->uid, p->euid, p->suid, p->fsuid,
+		p->gid, p->egid, p->sgid, p->fsgid);
+
+	task_lock(p);
+	if (p->files)
+		fdt = files_fdtable(p->files);
+	buffer += sprintf(buffer,
+		"FDSize:\t%d\n"
+		"Groups:\t",
+		fdt ? fdt->max_fds : 0);
+	rcu_read_unlock();
+
+	group_info = p->group_info;
+	get_group_info(group_info);
+	task_unlock(p);
+
+	for (g = 0; g < min(group_info->ngroups,NGROUPS_SMALL); g++)
+		buffer += sprintf(buffer, "%d ", GROUP_AT(group_info,g));
+	put_group_info(group_info);
+
+	buffer += sprintf(buffer, "\n");
+	return buffer;
+}
+
+static char * render_sigset_t(const char *header, sigset_t *set, char *buffer)
+{
+	int i, len;
+
+	len = strlen(header);
+	memcpy(buffer, header, len);
+	buffer += len;
+
+	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;
+		*buffer++ = (x < 10 ? '0' : 'a' - 10) + x;
+	} while (i >= 4);
+
+	*buffer++ = '\n';
+	*buffer = 0;
+	return buffer;
+}
+
+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 char * task_sig(struct task_struct *p, char *buffer)
+{
+	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);
+
+	rcu_read_lock();
+	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(&p->user->sigpending);
+		qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
+		unlock_task_sighand(p, &flags);
+	}
+	rcu_read_unlock();
+
+	buffer += sprintf(buffer, "Threads:\t%d\n", num_threads);
+	buffer += sprintf(buffer, "SigQ:\t%lu/%lu\n", qsize, qlim);
+
+	/* render them all */
+	buffer = render_sigset_t("SigPnd:\t", &pending, buffer);
+	buffer = render_sigset_t("ShdPnd:\t", &shpending, buffer);
+	buffer = render_sigset_t("SigBlk:\t", &blocked, buffer);
+	buffer = render_sigset_t("SigIgn:\t", &ignored, buffer);
+	buffer = render_sigset_t("SigCgt:\t", &caught, buffer);
+
+	return buffer;
+}
+
+static inline char *task_cap(struct task_struct *p, char *buffer)
+{
+    return buffer + sprintf(buffer, "CapInh:\t%016x\n"
+			    "CapPrm:\t%016x\n"
+			    "CapEff:\t%016x\n",
+			    cap_t(p->cap_inheritable),
+			    cap_t(p->cap_permitted),
+			    cap_t(p->cap_effective));
+}
+
+int proc_pid_status(struct task_struct *task, char * buffer)
+{
+	char * orig = buffer;
+	struct mm_struct *mm = get_task_mm(task);
+
+	buffer = task_name(task, buffer);
+	buffer = task_state(task, buffer);
+ 
+	if (mm) {
+		buffer = task_mem(mm, buffer);
+		mmput(mm);
+	}
+	buffer = task_sig(task, buffer);
+	buffer = task_cap(task, buffer);
+	buffer = cpuset_task_status_allowed(task, buffer);
+#if defined(CONFIG_S390)
+	buffer = task_show_regs(task, buffer);
+#endif
+	return buffer - orig;
+}
+
+static clock_t task_utime(struct task_struct *p)
+{
+	clock_t utime = cputime_to_clock_t(p->utime),
+		total = utime + cputime_to_clock_t(p->stime);
+	u64 temp;
+
+	/*
+	 * Use CFS's precise accounting:
+	 */
+	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+
+	if (total) {
+		temp *= utime;
+		do_div(temp, total);
+	}
+	utime = (clock_t)temp;
+
+	return utime;
+}
+
+static clock_t task_stime(struct task_struct *p)
+{
+	clock_t stime = cputime_to_clock_t(p->stime);
+
+	/*
+	 * Use CFS's precise accounting. (we subtract utime from
+	 * the total, to make sure the total observed by userspace
+	 * grows monotonically - apps rely on that):
+	 */
+	stime = nsec_to_clock_t(p->se.sum_exec_runtime) - task_utime(p);
+
+	return stime;
+}
+
+
+static int do_task_stat(struct task_struct *task, char * buffer, 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;
+	int res;
+ 	pid_t ppid = 0, pgid = -1, sid = -1;
+	int num_threads = 0;
+	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;
+	clock_t utime, stime;
+	unsigned long rsslim = 0;
+	char tcomm[sizeof(task->comm)];
+	unsigned long flags;
+
+	state = *get_task_state(task);
+	vsize = eip = esp = 0;
+	mm = get_task_mm(task);
+	if (mm) {
+		vsize = task_vsize(mm);
+		eip = KSTK_EIP(task);
+		esp = KSTK_ESP(task);
+	}
+
+	get_task_comm(tcomm, task);
+
+	sigemptyset(&sigign);
+	sigemptyset(&sigcatch);
+	cutime = cstime = cputime_zero;
+	utime = stime = 0;
+
+	rcu_read_lock();
+	if (lock_task_sighand(task, &flags)) {
+		struct signal_struct *sig = task->signal;
+
+		if (sig->tty) {
+			tty_pgrp = pid_nr(sig->tty->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;
+		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;
+				utime += task_utime(t);
+				stime += task_stime(t);
+				t = next_thread(t);
+			} while (t != task);
+
+			min_flt += sig->min_flt;
+			maj_flt += sig->maj_flt;
+			utime += cputime_to_clock_t(sig->utime);
+			stime += cputime_to_clock_t(sig->stime);
+		}
+
+		sid = signal_session(sig);
+		pgid = process_group(task);
+		ppid = rcu_dereference(task->real_parent)->tgid;
+
+		unlock_task_sighand(task, &flags);
+	}
+	rcu_read_unlock();
+
+	if (!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);
+	}
+
+	/* 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->start_time.tv_sec * NSEC_PER_SEC
+				+ task->start_time.tv_nsec;
+	/* convert nsec -> ticks */
+	start_time = nsec_to_clock_t(start_time);
+
+	res = sprintf(buffer,"%d (%s) %c %d %d %d %d %d %lu %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 %lu %lu %llu\n",
+		task->pid,
+		tcomm,
+		state,
+		ppid,
+		pgid,
+		sid,
+		tty_nr,
+		tty_pgrp,
+		task->flags,
+		min_flt,
+		cmin_flt,
+		maj_flt,
+		cmaj_flt,
+		utime,
+		stime,
+		cputime_to_clock_t(cutime),
+		cputime_to_clock_t(cstime),
+		priority,
+		nice,
+		num_threads,
+		start_time,
+		vsize,
+		mm ? get_mm_rss(mm) : 0,
+	        rsslim,
+		mm ? mm->start_code : 0,
+		mm ? mm->end_code : 0,
+		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));
+	if(mm)
+		mmput(mm);
+	return res;
+}
+
+int proc_tid_stat(struct task_struct *task, char * buffer)
+{
+	return do_task_stat(task, buffer, 0);
+}
+
+int proc_tgid_stat(struct task_struct *task, char * buffer)
+{
+	return do_task_stat(task, buffer, 1);
+}
+
+int proc_pid_statm(struct task_struct *task, char *buffer)
+{
+	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);
+	}
+
+	return sprintf(buffer,"%d %d %d %d %d %d %d\n",
+		       size, resident, shared, text, lib, data, 0);
+}

fs/proc/generic.c

@@ -0,0 +1,745 @@
+/*
+ * 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/smp_lock.h>
+#include <linux/init.h>
+#include <linux/idr.h>
+#include <linux/namei.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+static ssize_t proc_file_read(struct file *file, char __user *buf,
+			      size_t nbytes, loff_t *ppos);
+static ssize_t proc_file_write(struct file *file, const char __user *buffer,
+			       size_t count, loff_t *ppos);
+static loff_t proc_file_lseek(struct file *, loff_t, int);
+
+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);
+}
+
+static const struct file_operations proc_file_operations = {
+	.llseek		= proc_file_lseek,
+	.read		= proc_file_read,
+	.write		= proc_file_write,
+};
+
+/* 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_KERNEL)))
+		return -ENOMEM;
+
+	while ((nbytes > 0) && !eof) {
+		count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
+
+		start = NULL;
+		if (dp->get_info) {
+			/* Handle old net routines */
+			n = dp->get_info(page, &start, *ppos, count);
+			if (n < count)
+				eof = 1;
+		} else 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_write(struct file *file, const char __user *buffer,
+		size_t count, loff_t *ppos)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct proc_dir_entry * dp;
+	
+	dp = PDE(inode);
+
+	if (!dp->write_proc)
+		return -EIO;
+
+	/* FIXME: does this routine need ppos?  probably... */
+	return dp->write_proc(file, buffer, count, dp->data);
+}
+
+
+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 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;
+
+	spin_lock(&proc_subdir_lock);
+	de = &proc_root;
+	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_IDR(proc_inum_idr);
+static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
+
+#define PROC_DYNAMIC_FIRST 0xF0000000UL
+
+/*
+ * Return an inode number between PROC_DYNAMIC_FIRST and
+ * 0xffffffff, or zero on failure.
+ */
+static unsigned int get_inode_number(void)
+{
+	int i, inum = 0;
+	int error;
+
+retry:
+	if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
+		return 0;
+
+	spin_lock(&proc_inum_lock);
+	error = idr_get_new(&proc_inum_idr, NULL, &i);
+	spin_unlock(&proc_inum_lock);
+	if (error == -EAGAIN)
+		goto retry;
+	else if (error)
+		return 0;
+
+	inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;
+
+	/* inum will never be more than 0xf0ffffff, so no check
+	 * for overflow.
+	 */
+
+	return inum;
+}
+
+static void release_inode_number(unsigned int inum)
+{
+	int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;
+
+	spin_lock(&proc_inum_lock);
+	idr_remove(&proc_inum_idr, id);
+	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 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(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+{
+	struct inode *inode = NULL;
+	struct proc_dir_entry * de;
+	int error = -ENOENT;
+
+	lock_kernel();
+	spin_lock(&proc_subdir_lock);
+	de = PDE(dir);
+	if (de) {
+		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 = de->low_ino;
+
+				spin_unlock(&proc_subdir_lock);
+				error = -EINVAL;
+				inode = proc_get_inode(dir->i_sb, ino, de);
+				spin_lock(&proc_subdir_lock);
+				break;
+			}
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+	unlock_kernel();
+
+	if (inode) {
+		dentry->d_op = &proc_dentry_operations;
+		d_add(dentry, inode);
+		return NULL;
+	}
+	return ERR_PTR(error);
+}
+
+/*
+ * 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(struct file * filp,
+	void * dirent, filldir_t filldir)
+{
+	struct proc_dir_entry * de;
+	unsigned int ino;
+	int i;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	int ret = 0;
+
+	lock_kernel();
+
+	ino = inode->i_ino;
+	de = PDE(inode);
+	if (!de) {
+		ret = -EINVAL;
+		goto out;
+	}
+	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 {
+				/* filldir passes info to user space */
+				spin_unlock(&proc_subdir_lock);
+				if (filldir(dirent, de->name, de->namelen, filp->f_pos,
+					    de->low_ino, de->mode >> 12) < 0)
+					goto out;
+				spin_lock(&proc_subdir_lock);
+				filp->f_pos++;
+				de = de->next;
+			} while (de);
+			spin_unlock(&proc_subdir_lock);
+	}
+	ret = 1;
+out:	unlock_kernel();
+	return ret;	
+}
+
+/*
+ * 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 = {
+	.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;
+	
+	i = get_inode_number();
+	if (i == 0)
+		return -EAGAIN;
+	dp->low_ino = i;
+
+	spin_lock(&proc_subdir_lock);
+	dp->next = dir->subdir;
+	dp->parent = dir;
+	dir->subdir = dp;
+	spin_unlock(&proc_subdir_lock);
+
+	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;
+	}
+	return 0;
+}
+
+/*
+ * Kill an inode that got unregistered..
+ */
+static void proc_kill_inodes(struct proc_dir_entry *de)
+{
+	struct list_head *p;
+	struct super_block *sb = proc_mnt->mnt_sb;
+
+	/*
+	 * Actually it's a partial revoke().
+	 */
+	file_list_lock();
+	list_for_each(p, &sb->s_files) {
+		struct file * filp = list_entry(p, struct file, f_u.fu_list);
+		struct dentry * dentry = filp->f_path.dentry;
+		struct inode * inode;
+		const struct file_operations *fops;
+
+		if (dentry->d_op != &proc_dentry_operations)
+			continue;
+		inode = dentry->d_inode;
+		if (PDE(inode) != de)
+			continue;
+		fops = filp->f_op;
+		filp->f_op = NULL;
+		fops_put(fops);
+	}
+	file_list_unlock();
+}
+
+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 (!(*parent) && 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;
+ 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) {
+		ent->proc_fops = &proc_dir_operations;
+		ent->proc_iops = &proc_dir_inode_operations;
+
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
+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 (S_ISDIR(mode)) {
+			ent->proc_fops = &proc_dir_operations;
+			ent->proc_iops = &proc_dir_inode_operations;
+		}
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
+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) && de->data)
+		kfree(de->data);
+	kfree(de);
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ * If it is in use, we set the 'deleted' flag.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry **p;
+	struct proc_dir_entry *de;
+	const char *fn = name;
+	int len;
+
+	if (!parent && xlate_proc_name(name, &parent, &fn) != 0)
+		goto out;
+	len = strlen(fn);
+
+	spin_lock(&proc_subdir_lock);
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (!proc_match(len, fn, *p))
+			continue;
+		de = *p;
+		*p = de->next;
+		de->next = NULL;
+		if (S_ISDIR(de->mode))
+			parent->nlink--;
+		proc_kill_inodes(de);
+		de->nlink = 0;
+		WARN_ON(de->subdir);
+		if (!atomic_read(&de->count))
+			free_proc_entry(de);
+		else {
+			de->deleted = 1;
+			printk("remove_proc_entry: %s/%s busy, count=%d\n",
+				parent->name, de->name, atomic_read(&de->count));
+		}
+		break;
+	}
+	spin_unlock(&proc_subdir_lock);
+out:
+	return;
+}

fs/proc/inode-alloc.txt

@@ -0,0 +1,14 @@
+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:
+	a) once we'll split the thing into several virtual filesystems we
+	will get rid of magical ranges (and this file, BTW).

fs/proc/inode.c

@@ -0,0 +1,218 @@
+/*
+ *  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/file.h>
+#include <linux/limits.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+static inline struct proc_dir_entry * de_get(struct proc_dir_entry *de)
+{
+	if (de)
+		atomic_inc(&de->count);
+	return de;
+}
+
+/*
+ * Decrements the use count and checks for deferred deletion.
+ */
+static void de_put(struct proc_dir_entry *de)
+{
+	if (de) {	
+		lock_kernel();		
+		if (!atomic_read(&de->count)) {
+			printk("de_put: entry %s already free!\n", de->name);
+			unlock_kernel();
+			return;
+		}
+
+		if (atomic_dec_and_test(&de->count)) {
+			if (de->deleted) {
+				printk("de_put: deferred delete of %s\n",
+					de->name);
+				free_proc_entry(de);
+			}
+		}		
+		unlock_kernel();
+	}
+}
+
+/*
+ * 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) {
+		if (de->owner)
+			module_put(de->owner);
+		de_put(de);
+	}
+	clear_inode(inode);
+}
+
+struct vfsmount *proc_mnt;
+
+static void proc_read_inode(struct inode * inode)
+{
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+}
+
+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;
+	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 kmem_cache * cachep, unsigned long flags)
+{
+	struct proc_inode *ei = (struct proc_inode *) foo;
+
+	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+	    SLAB_CTOR_CONSTRUCTOR)
+		inode_init_once(&ei->vfs_inode);
+}
+ 
+int __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),
+					     init_once, NULL);
+	if (proc_inode_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+static int proc_remount(struct super_block *sb, int *flags, char *data)
+{
+	*flags |= MS_NODIRATIME;
+	return 0;
+}
+
+static const struct super_operations proc_sops = {
+	.alloc_inode	= proc_alloc_inode,
+	.destroy_inode	= proc_destroy_inode,
+	.read_inode	= proc_read_inode,
+	.drop_inode	= generic_delete_inode,
+	.delete_inode	= proc_delete_inode,
+	.statfs		= simple_statfs,
+	.remount_fs	= proc_remount,
+};
+
+struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
+				struct proc_dir_entry *de)
+{
+	struct inode * inode;
+
+	/*
+	 * Increment the use count so the dir entry can't disappear.
+	 */
+	de_get(de);
+
+	WARN_ON(de && de->deleted);
+
+	if (de != NULL && !try_module_get(de->owner))
+		goto out_mod;
+
+	inode = iget(sb, ino);
+	if (!inode)
+		goto out_ino;
+
+	PROC_I(inode)->fd = 0;
+	PROC_I(inode)->pde = de;
+	if (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)
+			inode->i_fop = de->proc_fops;
+	}
+
+	return inode;
+
+out_ino:
+	if (de != NULL)
+		module_put(de->owner);
+out_mod:
+	de_put(de);
+	return NULL;
+}			
+
+int proc_fill_super(struct super_block *s, void *data, int silent)
+{
+	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;
+	
+	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);
+	return -ENOMEM;
+}
+MODULE_LICENSE("GPL");

fs/proc/internal.h

@@ -0,0 +1,73 @@
+/* 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>
+
+#ifdef CONFIG_PROC_SYSCTL
+extern int proc_sys_init(void);
+#else
+static inline void proc_sys_init(void) { }
+#endif
+
+struct vmalloc_info {
+	unsigned long	used;
+	unsigned long	largest_chunk;
+};
+
+#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)
+
+extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
+#endif
+
+extern void create_seq_entry(char *name, mode_t mode, const struct file_operations *f);
+extern int proc_exe_link(struct inode *, struct dentry **, struct vfsmount **);
+extern int proc_tid_stat(struct task_struct *,  char *);
+extern int proc_tgid_stat(struct task_struct *, char *);
+extern int proc_pid_status(struct task_struct *, char *);
+extern int proc_pid_statm(struct task_struct *, char *);
+
+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_maps_operations;
+extern const struct file_operations proc_numa_maps_operations;
+extern const struct file_operations proc_smaps_operations;
+
+
+void free_proc_entry(struct proc_dir_entry *de);
+
+int 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;
+}

fs/proc/kcore.c

@@ -0,0 +1,402 @@
+/*
+ *	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/a.out.h>
+#include <linux/capability.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+
+#define CORE_STR "CORE"
+
+static int open_kcore(struct inode * inode, struct file * filp)
+{
+	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
+}
+
+static ssize_t read_kcore(struct file *, char __user *, size_t, loff_t *);
+
+const struct file_operations proc_kcore_operations = {
+	.read		= read_kcore,
+	.open		= open_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 struct kcore_list *kclist;
+static DEFINE_RWLOCK(kclist_lock);
+
+void
+kclist_add(struct kcore_list *new, void *addr, size_t size)
+{
+	new->addr = (unsigned long)addr;
+	new->size = size;
+
+	write_lock(&kclist_lock);
+	new->next = kclist;
+	kclist = new;
+	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;
+
+	for (m=kclist; m; m=m->next) {
+		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;
+}
+
+
+/*****************************************************************************/
+/*
+ * 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;
+#if defined(CONFIG_H8300)
+	elf->e_flags	= ELF_FLAGS;
+#else
+	elf->e_flags	= 0;
+#endif
+	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 */
+	for (m=kclist; m; m=m->next) {
+		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);
+	proc_root_kcore->size = 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);
+		for (m=kclist; m; m=m->next) {
+			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 ((start >= VMALLOC_START) && (start < VMALLOC_END)) {
+			char * elf_buf;
+			struct vm_struct *m;
+			unsigned long curstart = start;
+			unsigned long cursize = tsz;
+
+			elf_buf = kzalloc(tsz, GFP_KERNEL);
+			if (!elf_buf)
+				return -ENOMEM;
+
+			read_lock(&vmlist_lock);
+			for (m=vmlist; m && cursize; m=m->next) {
+				unsigned long vmstart;
+				unsigned long vmsize;
+				unsigned long msize = m->size - PAGE_SIZE;
+
+				if (((unsigned long)m->addr + msize) < 
+								curstart)
+					continue;
+				if ((unsigned long)m->addr > (curstart + 
+								cursize))
+					break;
+				vmstart = (curstart < (unsigned long)m->addr ? 
+					(unsigned long)m->addr : curstart);
+				if (((unsigned long)m->addr + msize) > 
+							(curstart + cursize))
+					vmsize = curstart + cursize - vmstart;
+				else
+					vmsize = (unsigned long)m->addr + 
+							msize - vmstart;
+				curstart = vmstart + vmsize;
+				cursize -= vmsize;
+				/* don't dump ioremap'd stuff! (TA) */
+				if (m->flags & VM_IOREMAP)
+					continue;
+				memcpy(elf_buf + (vmstart - start),
+					(char *)vmstart, vmsize);
+			}
+			read_unlock(&vmlist_lock);
+			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;
+}

fs/proc/kmsg.c

@@ -0,0 +1,55 @@
+/*
+ *  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/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;
+}
+
+
+const struct file_operations proc_kmsg_operations = {
+	.read		= kmsg_read,
+	.poll		= kmsg_poll,
+	.open		= kmsg_open,
+	.release	= kmsg_release,
+};

fs/proc/mmu.c

@@ -0,0 +1,77 @@
+/* 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/types.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"
+
+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);
+	}
+}

fs/proc/nommu.c

@@ -0,0 +1,144 @@
+/* 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 VMA to a sequenced file
+ */
+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;
+
+	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;
+	}
+
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08lx %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',
+		   vma->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.mnt, file->f_path.dentry, "");
+	}
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+/*
+ * display a list of all the VMAs the kernel knows about
+ * - nommu kernals have a single flat list
+ */
+static int nommu_vma_list_show(struct seq_file *m, void *v)
+{
+	struct vm_area_struct *vma;
+
+	vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb);
+	return nommu_vma_show(m, vma);
+}
+
+static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct rb_node *_rb;
+	loff_t pos = *_pos;
+	void *next = NULL;
+
+	down_read(&nommu_vma_sem);
+
+	for (_rb = rb_first(&nommu_vma_tree); _rb; _rb = rb_next(_rb)) {
+		if (pos == 0) {
+			next = _rb;
+			break;
+		}
+		pos--;
+	}
+
+	return next;
+}
+
+static void nommu_vma_list_stop(struct seq_file *m, void *v)
+{
+	up_read(&nommu_vma_sem);
+}
+
+static void *nommu_vma_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return rb_next((struct rb_node *) v);
+}
+
+static struct seq_operations proc_nommu_vma_list_seqop = {
+	.start	= nommu_vma_list_start,
+	.next	= nommu_vma_list_next,
+	.stop	= nommu_vma_list_stop,
+	.show	= nommu_vma_list_show
+};
+
+static int proc_nommu_vma_list_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &proc_nommu_vma_list_seqop);
+}
+
+static const struct file_operations proc_nommu_vma_list_operations = {
+	.open    = proc_nommu_vma_list_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+static int __init proc_nommu_init(void)
+{
+	create_seq_entry("maps", S_IRUGO, &proc_nommu_vma_list_operations);
+	return 0;
+}
+
+module_init(proc_nommu_init);

fs/proc/proc_devtree.c

@@ -0,0 +1,232 @@
+/*
+ * proc_devtree.c - handles /proc/device-tree
+ *
+ * Copyright 1997 Paul Mackerras
+ */
+#include <linux/errno.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>
+
+#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, 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 == 0)
+			break;
+		proc_device_tree_add_node(child, ent);
+	}
+	of_node_put(child);
+
+	for (pp = np->properties; pp != 0; 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 == 0)
+			break;
+	}
+}
+
+/*
+ * Called on initialization to set up the /proc/device-tree subtree
+ */
+void proc_device_tree_init(void)
+{
+	struct device_node *root;
+	if ( !have_of )
+		return;
+	proc_device_tree = proc_mkdir("device-tree", NULL);
+	if (proc_device_tree == 0)
+		return;
+	root = of_find_node_by_path("/");
+	if (root == 0) {
+		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);
+}

fs/proc/proc_misc.c

@@ -0,0 +1,789 @@
+/*
+ *  linux/fs/proc/proc_misc.c
+ *
+ *  linux/fs/proc/array.c
+ *  Copyright (C) 1992  by Linus Torvalds
+ *  based on ideas by Darren Senn
+ *
+ *  This used to be the part of array.c. See the rest of history and credits
+ *  there. I took this into a separate file and switched the thing to generic
+ *  proc_file_inode_operations, leaving in array.c only per-process stuff.
+ *  Inumbers allocation made dynamic (via create_proc_entry()).  AV, May 1999.
+ *
+ * Changes:
+ * Fulton Green      :  Encapsulated position metric calculations.
+ *			<kernel@FultonGreen.com>
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/fs.h>
+#include <linux/tty.h>
+#include <linux/string.h>
+#include <linux/mman.h>
+#include <linux/proc_fs.h>
+#include <linux/ioport.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/signal.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/smp_lock.h>
+#include <linux/seq_file.h>
+#include <linux/times.h>
+#include <linux/profile.h>
+#include <linux/utsname.h>
+#include <linux/blkdev.h>
+#include <linux/hugetlb.h>
+#include <linux/jiffies.h>
+#include <linux/sysrq.h>
+#include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
+#include <linux/pid_namespace.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/io.h>
+#include <asm/tlb.h>
+#include <asm/div64.h>
+#include "internal.h"
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+/*
+ * Warning: stuff below (imported functions) assumes that its output will fit
+ * into one page. For some of those functions it may be wrong. Moreover, we
+ * have a way to deal with that gracefully. Right now I used straightforward
+ * wrappers, but this needs further analysis wrt potential overflows.
+ */
+extern int get_hardware_list(char *);
+extern int get_stram_list(char *);
+extern int get_filesystem_list(char *);
+extern int get_exec_domain_list(char *);
+extern int get_dma_list(char *);
+extern int get_locks_status (char *, char **, off_t, int);
+
+static int proc_calc_metrics(char *page, char **start, off_t off,
+				 int count, int *eof, int len)
+{
+	if (len <= off+count) *eof = 1;
+	*start = page + off;
+	len -= off;
+	if (len>count) len = count;
+	if (len<0) len = 0;
+	return len;
+}
+
+static int loadavg_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int a, b, c;
+	int len;
+
+	a = avenrun[0] + (FIXED_1/200);
+	b = avenrun[1] + (FIXED_1/200);
+	c = avenrun[2] + (FIXED_1/200);
+	len = sprintf(page,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
+		LOAD_INT(a), LOAD_FRAC(a),
+		LOAD_INT(b), LOAD_FRAC(b),
+		LOAD_INT(c), LOAD_FRAC(c),
+		nr_running(), nr_threads, current->nsproxy->pid_ns->last_pid);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+static int uptime_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	struct timespec uptime;
+	struct timespec idle;
+	int len;
+	cputime_t idletime = cputime_add(init_task.utime, init_task.stime);
+
+	do_posix_clock_monotonic_gettime(&uptime);
+	cputime_to_timespec(idletime, &idle);
+	len = sprintf(page,"%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 proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+static int meminfo_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	struct sysinfo i;
+	int len;
+	unsigned long committed;
+	unsigned long allowed;
+	struct vmalloc_info vmi;
+	long cached;
+
+/*
+ * display in kilobytes.
+ */
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+	si_meminfo(&i);
+	si_swapinfo(&i);
+	committed = atomic_read(&vm_committed_space);
+	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);
+
+	/*
+	 * Tagged format, for easy grepping and expansion.
+	 */
+	len = sprintf(page,
+		"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"
+#ifdef CONFIG_HIGHMEM
+		"HighTotal:    %8lu kB\n"
+		"HighFree:     %8lu kB\n"
+		"LowTotal:     %8lu kB\n"
+		"LowFree:      %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"
+		"Slab:         %8lu kB\n"
+		"SReclaimable: %8lu kB\n"
+		"SUnreclaim:   %8lu kB\n"
+		"PageTables:   %8lu kB\n"
+		"NFS_Unstable: %8lu kB\n"
+		"Bounce:       %8lu kB\n"
+		"CommitLimit:  %8lu kB\n"
+		"Committed_AS: %8lu kB\n"
+		"VmallocTotal: %8lu kB\n"
+		"VmallocUsed:  %8lu kB\n"
+		"VmallocChunk: %8lu kB\n",
+		K(i.totalram),
+		K(i.freeram),
+		K(i.bufferram),
+		K(cached),
+		K(total_swapcache_pages),
+		K(global_page_state(NR_ACTIVE)),
+		K(global_page_state(NR_INACTIVE)),
+#ifdef CONFIG_HIGHMEM
+		K(i.totalhigh),
+		K(i.freehigh),
+		K(i.totalram-i.totalhigh),
+		K(i.freeram-i.freehigh),
+#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_SLAB_RECLAIMABLE) +
+				global_page_state(NR_SLAB_UNRECLAIMABLE)),
+		K(global_page_state(NR_SLAB_RECLAIMABLE)),
+		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+		K(global_page_state(NR_PAGETABLE)),
+		K(global_page_state(NR_UNSTABLE_NFS)),
+		K(global_page_state(NR_BOUNCE)),
+		K(allowed),
+		K(committed),
+		(unsigned long)VMALLOC_TOTAL >> 10,
+		vmi.used >> 10,
+		vmi.largest_chunk >> 10
+		);
+
+		len += hugetlb_report_meminfo(page + len);
+
+	return proc_calc_metrics(page, start, off, count, eof, len);
+#undef K
+}
+
+extern struct seq_operations fragmentation_op;
+static int fragmentation_open(struct inode *inode, struct file *file)
+{
+	(void)inode;
+	return seq_open(file, &fragmentation_op);
+}
+
+static const struct file_operations fragmentation_file_operations = {
+	.open		= fragmentation_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+extern struct seq_operations zoneinfo_op;
+static int zoneinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &zoneinfo_op);
+}
+
+static const struct file_operations proc_zoneinfo_file_operations = {
+	.open		= zoneinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int version_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len;
+
+	len = snprintf(page, PAGE_SIZE, linux_proc_banner,
+		utsname()->sysname,
+		utsname()->release,
+		utsname()->version);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+
+//Qisda, Asaku Chen, 2009/08/17, uboot and kernel version {
+static int qisda_kernel_version_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len;
+
+	len = snprintf(page, PAGE_SIZE, qisda_kernel_proc_banner);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+
+static int qisda_uboot_version_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len;
+
+	len = snprintf(page, PAGE_SIZE, qisda_uboot_proc_banner);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+static int uboot_version_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len;
+
+	len = snprintf(page, PAGE_SIZE, uboot_proc_banner);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+//Qisda, Asaku Chen, 2009/08/17, uboot and kernel version }
+
+extern 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 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 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,
+};
+
+extern struct seq_operations vmstat_op;
+static int vmstat_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &vmstat_op);
+}
+static const struct file_operations proc_vmstat_file_operations = {
+	.open		= vmstat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+#ifdef CONFIG_PROC_HARDWARE
+static int hardware_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len = get_hardware_list(page);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+#endif
+
+#ifdef CONFIG_STRAM_PROC
+static int stram_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len = get_stram_list(page);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+#endif
+
+#ifdef CONFIG_BLOCK
+extern struct seq_operations partitions_op;
+static int partitions_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &partitions_op);
+}
+static const struct file_operations proc_partitions_operations = {
+	.open		= partitions_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+extern struct seq_operations diskstats_op;
+static int diskstats_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &diskstats_op);
+}
+static const struct file_operations proc_diskstats_operations = {
+	.open		= diskstats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
+#ifdef CONFIG_MODULES
+extern struct seq_operations modules_op;
+static int modules_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &modules_op);
+}
+static const struct file_operations proc_modules_operations = {
+	.open		= modules_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
+#ifdef CONFIG_SLAB
+extern struct seq_operations slabinfo_op;
+extern ssize_t slabinfo_write(struct file *, const char __user *, size_t, loff_t *);
+static int slabinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slabinfo_op);
+}
+static const struct file_operations proc_slabinfo_operations = {
+	.open		= slabinfo_open,
+	.read		= seq_read,
+	.write		= slabinfo_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+extern struct seq_operations slabstats_op;
+static int slabstats_open(struct inode *inode, struct file *file)
+{
+	unsigned long *n = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	int ret = -ENOMEM;
+	if (n) {
+		ret = seq_open(file, &slabstats_op);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			*n = PAGE_SIZE / (2 * sizeof(unsigned long));
+			m->private = n;
+			n = NULL;
+		}
+		kfree(n);
+	}
+	return ret;
+}
+
+static int slabstats_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+	kfree(m->private);
+	return seq_release(inode, file);
+}
+
+static const struct file_operations proc_slabstats_operations = {
+	.open		= slabstats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= slabstats_release,
+};
+#endif
+#endif
+
+static int show_stat(struct seq_file *p, void *v)
+{
+	int i;
+	unsigned long jif;
+	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
+	u64 sum = 0;
+
+	user = nice = system = idle = iowait =
+		irq = softirq = steal = cputime64_zero;
+	jif = - wall_to_monotonic.tv_sec;
+	if (wall_to_monotonic.tv_nsec)
+		--jif;
+
+	for_each_possible_cpu(i) {
+		int j;
+
+		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);
+		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);
+		for (j = 0 ; j < NR_IRQS ; j++)
+			sum += kstat_cpu(i).irqs[j];
+	}
+
+	seq_printf(p, "cpu  %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));
+	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;
+		iowait = kstat_cpu(i).cpustat.iowait;
+		irq = kstat_cpu(i).cpustat.irq;
+		softirq = kstat_cpu(i).cpustat.softirq;
+		steal = kstat_cpu(i).cpustat.steal;
+		seq_printf(p, "cpu%d %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));
+	}
+	seq_printf(p, "intr %llu", (unsigned long long)sum);
+
+#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) && !defined(CONFIG_IA64)
+	for (i = 0; i < NR_IRQS; i++)
+		seq_printf(p, " %u", kstat_irqs(i));
+#endif
+
+	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());
+
+	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,
+};
+
+/*
+ * /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 */
+}
+
+
+extern int show_interrupts(struct seq_file *f, void *v); /* In arch code */
+static 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 filesystems_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len = get_filesystem_list(page);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+static int cmdline_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len;
+
+	len = sprintf(page, "%s\n", saved_command_line);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+static int locks_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len = get_locks_status(page, start, off, count);
+
+	if (len < count)
+		*eof = 1;
+	return len;
+}
+
+static int execdomains_read_proc(char *page, char **start, off_t off,
+				 int count, int *eof, void *data)
+{
+	int len = get_exec_domain_list(page);
+	return proc_calc_metrics(page, start, off, count, eof, len);
+}
+
+#ifdef CONFIG_MAGIC_SYSRQ
+/*
+ * writing 'C' to /proc/sysrq-trigger is like sysrq-C
+ */
+static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	if (count) {
+		char c;
+
+		if (get_user(c, buf))
+			return -EFAULT;
+		__handle_sysrq(c, NULL, 0);
+	}
+	return count;
+}
+
+static const struct file_operations proc_sysrq_trigger_operations = {
+	.write		= write_sysrq_trigger,
+};
+#endif
+
+struct proc_dir_entry *proc_root_kcore;
+
+void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)
+{
+	struct proc_dir_entry *entry;
+	entry = create_proc_entry(name, mode, NULL);
+	if (entry)
+		entry->proc_fops = f;
+}
+
+void __init proc_misc_init(void)
+{
+	static struct {
+		char *name;
+		int (*read_proc)(char*,char**,off_t,int,int*,void*);
+	} *p, simple_ones[] = {
+		{"loadavg",     loadavg_read_proc},
+		{"uptime",	uptime_read_proc},
+		{"meminfo",	meminfo_read_proc},
+		{"version",	version_read_proc},
+#ifdef CONFIG_PROC_HARDWARE
+		{"hardware",	hardware_read_proc},
+#endif
+#ifdef CONFIG_STRAM_PROC
+		{"stram",	stram_read_proc},
+#endif
+		{"filesystems",	filesystems_read_proc},
+		{"cmdline",	cmdline_read_proc},
+		{"locks",	locks_read_proc},
+		{"execdomains",	execdomains_read_proc},
+
+		//Qisda, Asaku Chen, 2009/08/17, uboot and kernel version {
+		{"odm_kernel_version", qisda_kernel_version_read_proc},
+		{"odm_uboot_version", qisda_uboot_version_read_proc},
+		{"uboot_version", uboot_version_read_proc},
+		//Qisda, Asaku Chen, 2009/08/17, uboot and kernel version }
+
+		{NULL,}
+	};
+	for (p = simple_ones; p->name; p++)
+		create_proc_read_entry(p->name, 0, NULL, p->read_proc, NULL);
+
+	proc_symlink("mounts", NULL, "self/mounts");
+
+	/* And now for trickier ones */
+#ifdef CONFIG_PRINTK
+	{
+		struct proc_dir_entry *entry;
+		entry = create_proc_entry("kmsg", S_IRUSR, &proc_root);
+		if (entry)
+			entry->proc_fops = &proc_kmsg_operations;
+	}
+#endif
+	create_seq_entry("devices", 0, &proc_devinfo_operations);
+	create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations);
+#ifdef CONFIG_BLOCK
+	create_seq_entry("partitions", 0, &proc_partitions_operations);
+#endif
+	create_seq_entry("stat", 0, &proc_stat_operations);
+	create_seq_entry("interrupts", 0, &proc_interrupts_operations);
+#ifdef CONFIG_SLAB
+	create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations);
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+	create_seq_entry("slab_allocators", 0 ,&proc_slabstats_operations);
+#endif
+#endif
+	create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations);
+	create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations);
+	create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations);
+#ifdef CONFIG_BLOCK
+	create_seq_entry("diskstats", 0, &proc_diskstats_operations);
+#endif
+#ifdef CONFIG_MODULES
+	create_seq_entry("modules", 0, &proc_modules_operations);
+#endif
+#ifdef CONFIG_SCHEDSTATS
+	create_seq_entry("schedstat", 0, &proc_schedstat_operations);
+#endif
+#ifdef CONFIG_PROC_KCORE
+	proc_root_kcore = create_proc_entry("kcore", S_IRUSR, NULL);
+	if (proc_root_kcore) {
+		proc_root_kcore->proc_fops = &proc_kcore_operations;
+		proc_root_kcore->size =
+				(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
+	}
+#endif
+#ifdef CONFIG_PROC_VMCORE
+	proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
+	if (proc_vmcore)
+		proc_vmcore->proc_fops = &proc_vmcore_operations;
+#endif
+#ifdef CONFIG_MAGIC_SYSRQ
+	{
+		struct proc_dir_entry *entry;
+		entry = create_proc_entry("sysrq-trigger", S_IWUSR, NULL);
+		if (entry)
+			entry->proc_fops = &proc_sysrq_trigger_operations;
+	}
+#endif
+}

fs/proc/proc_sysctl.c

@@ -0,0 +1,479 @@
+/*
+ * /proc/sys support
+ */
+
+#include <linux/sysctl.h>
+#include <linux/proc_fs.h>
+#include <linux/security.h>
+#include "internal.h"
+
+static struct dentry_operations proc_sys_dentry_operations;
+static const struct file_operations proc_sys_file_operations;
+static struct inode_operations proc_sys_inode_operations;
+
+static void proc_sys_refresh_inode(struct inode *inode, struct ctl_table *table)
+{
+	/* Refresh the cached information bits in the inode */
+	if (table) {
+		inode->i_uid = 0;
+		inode->i_gid = 0;
+		inode->i_mode = table->mode;
+		if (table->proc_handler) {
+			inode->i_mode |= S_IFREG;
+			inode->i_nlink = 1;
+		} else {
+			inode->i_mode |= S_IFDIR;
+			inode->i_nlink = 0;	/* It is too hard to figure out */
+		}
+	}
+}
+
+static struct inode *proc_sys_make_inode(struct inode *dir, struct ctl_table *table)
+{
+	struct inode *inode;
+	struct proc_inode *dir_ei, *ei;
+	int depth;
+
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		goto out;
+
+	/* A directory is always one deeper than it's parent */
+	dir_ei = PROC_I(dir);
+	depth = dir_ei->fd + 1;
+
+	ei = PROC_I(inode);
+	ei->fd = depth;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_op = &proc_sys_inode_operations;
+	inode->i_fop = &proc_sys_file_operations;
+	inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
+	proc_sys_refresh_inode(inode, table);
+out:
+	return inode;
+}
+
+static struct dentry *proc_sys_ancestor(struct dentry *dentry, int depth)
+{
+	for (;;) {
+		struct proc_inode *ei;
+
+		ei = PROC_I(dentry->d_inode);
+		if (ei->fd == depth)
+			break; /* found */
+
+		dentry = dentry->d_parent;
+	}
+	return dentry;
+}
+
+static struct ctl_table *proc_sys_lookup_table_one(struct ctl_table *table,
+							struct qstr *name)
+{
+	int len;
+	for ( ; table->ctl_name || table->procname; table++) {
+
+		if (!table->procname)
+			continue;
+
+		len = strlen(table->procname);
+		if (len != name->len)
+			continue;
+
+		if (memcmp(table->procname, name->name, len) != 0)
+			continue;
+
+		/* I have a match */
+		return table;
+	}
+	return NULL;
+}
+
+static struct ctl_table *proc_sys_lookup_table(struct dentry *dentry,
+						struct ctl_table *table)
+{
+	struct dentry *ancestor;
+	struct proc_inode *ei;
+	int depth, i;
+
+	ei = PROC_I(dentry->d_inode);
+	depth = ei->fd;
+
+	if (depth == 0)
+		return table;
+
+	for (i = 1; table && (i <= depth); i++) {
+		ancestor = proc_sys_ancestor(dentry, i);
+		table = proc_sys_lookup_table_one(table, &ancestor->d_name);
+		if (table)
+			table = table->child;
+	}
+	return table;
+
+}
+static struct ctl_table *proc_sys_lookup_entry(struct dentry *dparent,
+						struct qstr *name,
+						struct ctl_table *table)
+{
+	table = proc_sys_lookup_table(dparent, table);
+	if (table)
+		table = proc_sys_lookup_table_one(table, name);
+	return table;
+}
+
+static struct ctl_table *do_proc_sys_lookup(struct dentry *parent,
+						struct qstr *name,
+						struct ctl_table_header **ptr)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *table = NULL;
+
+	for (head = sysctl_head_next(NULL); head;
+			head = sysctl_head_next(head)) {
+		table = proc_sys_lookup_entry(parent, name, head->ctl_table);
+		if (table)
+			break;
+	}
+	*ptr = head;
+	return table;
+}
+
+static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
+					struct nameidata *nd)
+{
+	struct ctl_table_header *head;
+	struct inode *inode;
+	struct dentry *err;
+	struct ctl_table *table;
+
+	err = ERR_PTR(-ENOENT);
+	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+	if (!table)
+		goto out;
+
+	err = ERR_PTR(-ENOMEM);
+	inode = proc_sys_make_inode(dir, table);
+	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_read(struct file *filp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct dentry *dentry = filp->f_dentry;
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	ssize_t error, res;
+
+	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+	/* Has the sysctl entry disappeared on us? */
+	error = -ENOENT;
+	if (!table)
+		goto out;
+
+	/* Has the sysctl entry been replaced by a directory? */
+	error = -EISDIR;
+	if (!table->proc_handler)
+		goto out;
+
+	/*
+	 * At this point we know that the sysctl was not unregistered
+	 * and won't be until we finish.
+	 */
+	error = -EPERM;
+	if (sysctl_perm(table, MAY_READ))
+		goto out;
+
+	/* careful: calling conventions are nasty here */
+	res = count;
+	error = table->proc_handler(table, 0, filp, buf, &res, ppos);
+	if (!error)
+		error = res;
+out:
+	sysctl_head_finish(head);
+
+	return error;
+}
+
+static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct dentry *dentry = filp->f_dentry;
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	ssize_t error, res;
+
+	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+	/* Has the sysctl entry disappeared on us? */
+	error = -ENOENT;
+	if (!table)
+		goto out;
+
+	/* Has the sysctl entry been replaced by a directory? */
+	error = -EISDIR;
+	if (!table->proc_handler)
+		goto out;
+
+	/*
+	 * At this point we know that the sysctl was not unregistered
+	 * and won't be until we finish.
+	 */
+	error = -EPERM;
+	if (sysctl_perm(table, MAY_WRITE))
+		goto out;
+
+	/* careful: calling conventions are nasty here */
+	res = count;
+	error = table->proc_handler(table, 1, filp, (char __user *)buf,
+				    &res, ppos);
+	if (!error)
+		error = res;
+out:
+	sysctl_head_finish(head);
+
+	return error;
+}
+
+
+static int proc_sys_fill_cache(struct file *filp, void *dirent,
+				filldir_t filldir, struct ctl_table *table)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *child_table = NULL;
+	struct dentry *child, *dir = filp->f_path.dentry;
+	struct inode *inode;
+	struct qstr qname;
+	ino_t ino = 0;
+	unsigned type = DT_UNKNOWN;
+	int ret;
+
+	qname.name = table->procname;
+	qname.len  = strlen(table->procname);
+	qname.hash = full_name_hash(qname.name, qname.len);
+
+	/* Suppress duplicates.
+	 * Only fill a directory entry if it is the value that
+	 * an ordinary lookup of that name returns.  Hide all
+	 * others.
+	 *
+	 * If we ever cache this translation in the dcache
+	 * I should do a dcache lookup first.  But for now
+	 * it is just simpler not to.
+	 */
+	ret = 0;
+	child_table = do_proc_sys_lookup(dir, &qname, &head);
+	sysctl_head_finish(head);
+	if (child_table != table)
+		return 0;
+
+	child = d_lookup(dir, &qname);
+	if (!child) {
+		struct dentry *new;
+		new = d_alloc(dir, &qname);
+		if (new) {
+			inode = proc_sys_make_inode(dir->d_inode, table);
+			if (!inode)
+				child = ERR_PTR(-ENOMEM);
+			else {
+				new->d_op = &proc_sys_dentry_operations;
+				d_add(new, inode);
+			}
+			if (child)
+				dput(new);
+			else
+				child = new;
+		}
+	}
+	if (!child || IS_ERR(child) || !child->d_inode)
+		goto end_instantiate;
+	inode = child->d_inode;
+	if (inode) {
+		ino  = inode->i_ino;
+		type = inode->i_mode >> 12;
+	}
+	dput(child);
+end_instantiate:
+	if (!ino)
+		ino= find_inode_number(dir, &qname);
+	if (!ino)
+		ino = 1;
+	return filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+}
+
+static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	struct dentry *dentry = filp->f_dentry;
+	struct inode *inode = dentry->d_inode;
+	struct ctl_table_header *head = NULL;
+	struct ctl_table *table;
+	unsigned long pos;
+	int ret;
+
+	ret = -ENOTDIR;
+	if (!S_ISDIR(inode->i_mode))
+		goto out;
+
+	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;
+
+	/* - Find each instance of the directory
+	 * - Read all entries in each instance
+	 * - Before returning an entry to user space lookup the entry
+	 *   by name and if I find a different entry don't return
+	 *   this one because it means it is a buried dup.
+	 * For sysctl this should only happen for directory entries.
+	 */
+	for (head = sysctl_head_next(NULL); head; head = sysctl_head_next(head)) {
+		table = proc_sys_lookup_table(dentry, head->ctl_table);
+
+		if (!table)
+			continue;
+
+		for (; table->ctl_name || table->procname; table++, pos++) {
+			/* Can't do anything without a proc name */
+			if (!table->procname)
+				continue;
+
+			if (pos < filp->f_pos)
+				continue;
+
+			if (proc_sys_fill_cache(filp, dirent, filldir, table) < 0)
+				goto out;
+			filp->f_pos = pos + 1;
+		}
+	}
+	ret = 1;
+out:
+	sysctl_head_finish(head);
+	return ret;
+}
+
+static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+	/*
+	 * sysctl entries that are not writeable,
+	 * are _NOT_ writeable, capabilities or not.
+	 */
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	struct dentry *dentry;
+	int mode;
+	int depth;
+	int error;
+
+	head = NULL;
+	depth = PROC_I(inode)->fd;
+
+	/* First check the cached permissions, in case we don't have
+	 * enough information to lookup the sysctl table entry.
+	 */
+	error = -EACCES;
+	mode = inode->i_mode;
+
+	if (current->euid == 0)
+		mode >>= 6;
+	else if (in_group_p(0))
+		mode >>= 3;
+
+	if ((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask)
+		error = 0;
+
+	/* If we can't get a sysctl table entry the permission
+	 * checks on the cached mode will have to be enough.
+	 */
+	if (!nd || !depth)
+		goto out;
+
+	dentry = nd->dentry;
+	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+
+	/* If the entry does not exist deny permission */
+	error = -EACCES;
+	if (!table)
+		goto out;
+
+	/* Use the permissions on the sysctl table entry */
+	error = sysctl_perm(table, mask);
+out:
+	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 = security_inode_setattr(dentry, attr);
+		if (!error)
+			error = inode_setattr(inode, attr);
+	}
+
+	return error;
+}
+
+/* I'm lazy and don't distinguish between files and directories,
+ * until access time.
+ */
+static const struct file_operations proc_sys_file_operations = {
+	.read		= proc_sys_read,
+	.write		= proc_sys_write,
+	.readdir	= proc_sys_readdir,
+};
+
+static struct inode_operations proc_sys_inode_operations = {
+	.lookup		= proc_sys_lookup,
+	.permission	= proc_sys_permission,
+	.setattr	= proc_sys_setattr,
+};
+
+static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+	proc_sys_refresh_inode(dentry->d_inode, table);
+	sysctl_head_finish(head);
+	return !!table;
+}
+
+static struct dentry_operations proc_sys_dentry_operations = {
+	.d_revalidate	= proc_sys_revalidate,
+};
+
+static struct proc_dir_entry *proc_sys_root;
+
+int proc_sys_init(void)
+{
+	proc_sys_root = proc_mkdir("sys", NULL);
+	proc_sys_root->proc_iops = &proc_sys_inode_operations;
+	proc_sys_root->proc_fops = &proc_sys_file_operations;
+	proc_sys_root->nlink = 0;
+	return 0;
+}

fs/proc/proc_tty.c

@@ -0,0 +1,242 @@
+/*
+ * proc_tty.c -- handles /proc/tty
+ *
+ * Copyright 1997, Theodore Ts'o
+ */
+
+#include <asm/uaccess.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>
+
+static int tty_ldiscs_read_proc(char *page, char **start, off_t off,
+				int count, int *eof, void *data);
+
+/*
+ * 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 = v;
+	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)
+{
+	struct list_head *p;
+	loff_t l = *pos;
+	list_for_each(p, &tty_drivers)
+		if (!l--)
+			return list_entry(p, struct tty_driver, tty_drivers);
+	return NULL;
+}
+
+static void *t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct list_head *p = ((struct tty_driver *)v)->tty_drivers.next;
+	(*pos)++;
+	return p==&tty_drivers ? NULL :
+			list_entry(p, struct tty_driver, tty_drivers);
+}
+
+static void t_stop(struct seq_file *m, void *v)
+{
+}
+
+static 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 is the handler for /proc/tty/ldiscs
+ */
+static int tty_ldiscs_read_proc(char *page, char **start, off_t off,
+				int count, int *eof, void *data)
+{
+	int	i;
+	int	len = 0;
+	off_t	begin = 0;
+	struct tty_ldisc *ld;
+	
+	for (i=0; i < NR_LDISCS; i++) {
+		ld = tty_ldisc_get(i);
+		if (ld == NULL)
+			continue;
+		len += sprintf(page+len, "%-10s %2d\n",
+			       ld->name ? ld->name : "???", i);
+		tty_ldisc_put(i);
+		if (len+begin > off+count)
+			break;
+		if (len+begin < off) {
+			begin += len;
+			len = 0;
+		}
+	}
+	if (i >= NR_LDISCS)
+		*eof = 1;
+	if (off >= len+begin)
+		return 0;
+	*start = page + (off-begin);
+	return ((count < begin+len-off) ? count : begin+len-off);
+}
+
+/*
+ * 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->read_proc && !driver->write_proc) ||
+	    !driver->driver_name ||
+	    driver->proc_entry)
+		return;
+
+	ent = create_proc_entry(driver->driver_name, 0, proc_tty_driver);
+	if (!ent)
+		return;
+	ent->read_proc = driver->read_proc;
+	ent->write_proc = driver->write_proc;
+	ent->owner = driver->owner;
+	ent->data = 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)
+{
+	struct proc_dir_entry *entry;
+	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);
+
+	create_proc_read_entry("tty/ldiscs", 0, NULL, tty_ldiscs_read_proc, NULL);
+	entry = create_proc_entry("tty/drivers", 0, NULL);
+	if (entry)
+		entry->proc_fops = &proc_tty_drivers_operations;
+}

fs/proc/root.c

@@ -0,0 +1,165 @@
+/*
+ *  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/smp_lock.h>
+#include <linux/mount.h>
+
+#include "internal.h"
+
+struct proc_dir_entry *proc_net, *proc_net_stat, *proc_bus, *proc_root_fs, *proc_root_driver;
+
+static int proc_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	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.
+		 */
+		struct proc_inode *ei;
+		ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
+		if (!ei->pid)
+			ei->pid = find_get_pid(1);
+	}
+	return get_sb_single(fs_type, flags, data, proc_fill_super, mnt);
+}
+
+static struct file_system_type proc_fs_type = {
+	.name		= "proc",
+	.get_sb		= proc_get_sb,
+	.kill_sb	= kill_anon_super,
+};
+
+void __init proc_root_init(void)
+{
+	int err = proc_init_inodecache();
+	if (err)
+		return;
+	err = register_filesystem(&proc_fs_type);
+	if (err)
+		return;
+	proc_mnt = kern_mount(&proc_fs_type);
+	err = PTR_ERR(proc_mnt);
+	if (IS_ERR(proc_mnt)) {
+		unregister_filesystem(&proc_fs_type);
+		return;
+	}
+	proc_misc_init();
+	proc_net = proc_mkdir("net", NULL);
+	proc_net_stat = proc_mkdir("net/stat", NULL);
+
+#ifdef CONFIG_SYSVIPC
+	proc_mkdir("sysvipc", NULL);
+#endif
+	proc_root_fs = proc_mkdir("fs", NULL);
+	proc_root_driver = 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_bus = 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;
+
+	lock_kernel();
+
+	if (nr < FIRST_PROCESS_ENTRY) {
+		int error = proc_readdir(filp, dirent, filldir);
+		if (error <= 0) {
+			unlock_kernel();
+			return error;
+		}
+		filp->f_pos = FIRST_PROCESS_ENTRY;
+	}
+	unlock_kernel();
+
+	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, 
+	.proc_iops	= &proc_root_inode_operations, 
+	.proc_fops	= &proc_root_operations,
+	.parent		= &proc_root,
+};
+
+EXPORT_SYMBOL(proc_symlink);
+EXPORT_SYMBOL(proc_mkdir);
+EXPORT_SYMBOL(create_proc_entry);
+EXPORT_SYMBOL(remove_proc_entry);
+EXPORT_SYMBOL(proc_root);
+EXPORT_SYMBOL(proc_root_fs);
+EXPORT_SYMBOL(proc_net);
+EXPORT_SYMBOL(proc_net_stat);
+EXPORT_SYMBOL(proc_bus);
+EXPORT_SYMBOL(proc_root_driver);

fs/proc/task_mmu.c

@@ -0,0 +1,477 @@
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/mount.h>
+#include <linux/seq_file.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/mempolicy.h>
+
+#include <asm/elf.h>
+#include <asm/uaccess.h>
+#include <asm/tlbflush.h>
+#include "internal.h"
+
+char *task_mem(struct mm_struct *mm, char *buffer)
+{
+	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;
+	buffer += sprintf(buffer,
+		"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);
+	return buffer;
+}
+
+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;
+}
+
+int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+{
+	struct vm_area_struct * vma;
+	int result = -ENOENT;
+	struct task_struct *task = get_proc_task(inode);
+	struct mm_struct * mm = NULL;
+
+	if (task) {
+		mm = get_task_mm(task);
+		put_task_struct(task);
+	}
+	if (!mm)
+		goto out;
+	down_read(&mm->mmap_sem);
+
+	vma = mm->mmap;
+	while (vma) {
+		if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file)
+			break;
+		vma = vma->vm_next;
+	}
+
+	if (vma) {
+		*mnt = mntget(vma->vm_file->f_path.mnt);
+		*dentry = dget(vma->vm_file->f_path.dentry);
+		result = 0;
+	}
+
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+out:
+	return result;
+}
+
+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, ' ');
+}
+
+struct mem_size_stats
+{
+	unsigned long resident;
+	unsigned long shared_clean;
+	unsigned long shared_dirty;
+	unsigned long private_clean;
+	unsigned long private_dirty;
+};
+
+static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
+{
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
+	struct vm_area_struct *vma = v;
+	struct mm_struct *mm = vma->vm_mm;
+	struct file *file = vma->vm_file;
+	int flags = vma->vm_flags;
+	unsigned long ino = 0;
+	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;
+	}
+
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %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 ? 's' : 'p',
+			vma->vm_pgoff << PAGE_SHIFT,
+			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.mnt, file->f_path.dentry, "\n");
+	} else {
+		const char *name = arch_vma_name(vma);
+		if (!name) {
+			if (mm) {
+				if (vma->vm_start <= mm->start_brk &&
+						vma->vm_end >= mm->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');
+
+	if (mss)
+		seq_printf(m,
+			   "Size:          %8lu kB\n"
+			   "Rss:           %8lu kB\n"
+			   "Shared_Clean:  %8lu kB\n"
+			   "Shared_Dirty:  %8lu kB\n"
+			   "Private_Clean: %8lu kB\n"
+			   "Private_Dirty: %8lu kB\n",
+			   (vma->vm_end - vma->vm_start) >> 10,
+			   mss->resident >> 10,
+			   mss->shared_clean  >> 10,
+			   mss->shared_dirty  >> 10,
+			   mss->private_clean >> 10,
+			   mss->private_dirty >> 10);
+
+	if (m->count < m->size)  /* vma is copied successfully */
+		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+	return 0;
+}
+
+static int show_map(struct seq_file *m, void *v)
+{
+	return show_map_internal(m, v, NULL);
+}
+
+static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	do {
+		ptent = *pte;
+		if (!pte_present(ptent))
+			continue;
+
+		mss->resident += PAGE_SIZE;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		if (page_mapcount(page) >= 2) {
+			if (pte_dirty(ptent))
+				mss->shared_dirty += PAGE_SIZE;
+			else
+				mss->shared_clean += PAGE_SIZE;
+		} else {
+			if (pte_dirty(ptent))
+				mss->private_dirty += PAGE_SIZE;
+			else
+				mss->private_clean += PAGE_SIZE;
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+}
+
+static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none_or_clear_bad(pmd))
+			continue;
+		smaps_pte_range(vma, pmd, addr, next, mss);
+	} while (pmd++, addr = next, addr != end);
+}
+
+static inline void smaps_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		smaps_pmd_range(vma, pud, addr, next, mss);
+	} while (pud++, addr = next, addr != end);
+}
+
+static inline void smaps_pgd_range(struct vm_area_struct *vma,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pgd_t *pgd;
+	unsigned long next;
+
+	pgd = pgd_offset(vma->vm_mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		smaps_pud_range(vma, pgd, addr, next, mss);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static int show_smap(struct seq_file *m, void *v)
+{
+	struct vm_area_struct *vma = v;
+	struct mem_size_stats mss;
+
+	memset(&mss, 0, sizeof mss);
+	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
+		smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
+	return show_map_internal(m, v, &mss);
+}
+
+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 = get_task_mm(priv->task);
+	if (!mm)
+		return NULL;
+
+	priv->tail_vma = tail_vma = get_gate_vma(priv->task);
+	down_read(&mm->mmap_sem);
+
+	/* Start with last addr hint */
+	if (last_addr && (vma = find_vma(mm, last_addr))) {
+		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 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_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 struct seq_operations proc_pid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_map
+};
+
+static struct seq_operations proc_pid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_smap
+};
+
+static int do_maps_open(struct inode *inode, struct file *file,
+			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 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,
+};
+
+#ifdef CONFIG_NUMA
+extern int show_numa_map(struct seq_file *m, void *v);
+
+static 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
+
+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,
+};

fs/proc/task_nommu.c

@@ -0,0 +1,229 @@
+
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/mount.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 then once, for
+ * each process that owns it. Non-shared memory is counted
+ * accurately.
+ */
+char *task_mem(struct mm_struct *mm, char *buffer)
+{
+	struct vm_list_struct *vml;
+	unsigned long bytes = 0, sbytes = 0, slack = 0;
+        
+	down_read(&mm->mmap_sem);
+	for (vml = mm->context.vmlist; vml; vml = vml->next) {
+		if (!vml->vma)
+			continue;
+
+		bytes += kobjsize(vml);
+		if (atomic_read(&mm->mm_count) > 1 ||
+		    atomic_read(&vml->vma->vm_usage) > 1
+		    ) {
+			sbytes += kobjsize((void *) vml->vma->vm_start);
+			sbytes += kobjsize(vml->vma);
+		} else {
+			bytes += kobjsize((void *) vml->vma->vm_start);
+			bytes += kobjsize(vml->vma);
+			slack += kobjsize((void *) vml->vma->vm_start) -
+				(vml->vma->vm_end - vml->vma->vm_start);
+		}
+	}
+
+	if (atomic_read(&mm->mm_count) > 1)
+		sbytes += kobjsize(mm);
+	else
+		bytes += kobjsize(mm);
+	
+	if (current->fs && atomic_read(&current->fs->count) > 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 */
+
+	buffer += sprintf(buffer,
+		"Mem:\t%8lu bytes\n"
+		"Slack:\t%8lu bytes\n"
+		"Shared:\t%8lu bytes\n",
+		bytes, slack, sbytes);
+
+	up_read(&mm->mmap_sem);
+	return buffer;
+}
+
+unsigned long task_vsize(struct mm_struct *mm)
+{
+	struct vm_list_struct *tbp;
+	unsigned long vsize = 0;
+
+	down_read(&mm->mmap_sem);
+	for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) {
+		if (tbp->vma)
+			vsize += kobjsize((void *) tbp->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_list_struct *tbp;
+	int size = kobjsize(mm);
+
+	down_read(&mm->mmap_sem);
+	for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) {
+		size += kobjsize(tbp);
+		if (tbp->vma) {
+			size += kobjsize(tbp->vma);
+			size += kobjsize((void *) tbp->vma->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;
+}
+
+int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+{
+	struct vm_list_struct *vml;
+	struct vm_area_struct *vma;
+	struct task_struct *task = get_proc_task(inode);
+	struct mm_struct *mm = get_task_mm(task);
+	int result = -ENOENT;
+
+	if (!mm)
+		goto out;
+	down_read(&mm->mmap_sem);
+
+	vml = mm->context.vmlist;
+	vma = NULL;
+	while (vml) {
+		if ((vml->vma->vm_flags & VM_EXECUTABLE) && vml->vma->vm_file) {
+			vma = vml->vma;
+			break;
+		}
+		vml = vml->next;
+	}
+
+	if (vma) {
+		*mnt = mntget(vma->vm_file->f_path.mnt);
+		*dentry = dget(vma->vm_file->f_path.dentry);
+		result = 0;
+	}
+
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+out:
+	return result;
+}
+
+/*
+ * display mapping lines for a particular process's /proc/pid/maps
+ */
+static int show_map(struct seq_file *m, void *_vml)
+{
+	struct vm_list_struct *vml = _vml;
+	return nommu_vma_show(m, vml->vma);
+}
+
+static void *m_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_list_struct *vml;
+	struct mm_struct *mm;
+	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 = get_task_mm(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 (vml = mm->context.vmlist; vml; vml = vml->next)
+		if (n-- == 0)
+			return vml;
+	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 *_vml, loff_t *pos)
+{
+	struct vm_list_struct *vml = _vml;
+
+	(*pos)++;
+	return vml ? vml->next : NULL;
+}
+
+static 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,
+};
+

fs/proc/vmcore.c

@@ -0,0 +1,670 @@
+/*
+ *	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/a.out.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;
+
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
+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);
+	if (pfn > saved_max_pfn)
+		return -EINVAL;
+
+	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 int open_vmcore(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+const struct file_operations proc_vmcore_operations = {
+	.read		= read_vmcore,
+	.open		= open_vmcore,
+};
+
+static struct vmcore* __init get_new_element(void)
+{
+	struct vmcore *p;
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (p)
+		memset(p, 0, sizeof(*p));
+	return p;
+}
+
+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) ||
+		!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 (!(elfcorehdr_addr < ELFCORE_ADDR_MAX))
+		return rc;
+	rc = parse_crash_elf_headers();
+	if (rc) {
+		printk(KERN_WARNING "Kdump: vmcore not initialized\n");
+		return rc;
+	}
+
+	/* Initialize /proc/vmcore size if proc is already up. */
+	if (proc_vmcore)
+		proc_vmcore->size = vmcore_size;
+	return 0;
+}
+module_init(vmcore_init)