Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 1672 insertions, 305 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index c602b8d20f06..f9bd395b3473 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -462,59 +462,56 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	/* convert nsec -> ticks */
 	start_time = nsec_to_clock_t(start_time);
 
-	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
-%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
-%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld %lu %lu %lu\n",
-		pid_nr_ns(pid, ns),
-		tcomm,
-		state,
-		ppid,
-		pgid,
-		sid,
-		tty_nr,
-		tty_pgrp,
-		task->flags,
-		min_flt,
-		cmin_flt,
-		maj_flt,
-		cmaj_flt,
-		cputime_to_clock_t(utime),
-		cputime_to_clock_t(stime),
-		cputime_to_clock_t(cutime),
-		cputime_to_clock_t(cstime),
-		priority,
-		nice,
-		num_threads,
-		start_time,
-		vsize,
-		mm ? get_mm_rss(mm) : 0,
-		rsslim,
-		mm ? (permitted ? mm->start_code : 1) : 0,
-		mm ? (permitted ? mm->end_code : 1) : 0,
-		(permitted && mm) ? mm->start_stack : 0,
-		esp,
-		eip,
-		/* The signal information here is obsolete.
-		 * It must be decimal for Linux 2.0 compatibility.
-		 * Use /proc/#/status for real-time signals.
-		 */
-		task->pending.signal.sig[0] & 0x7fffffffUL,
-		task->blocked.sig[0] & 0x7fffffffUL,
-		sigign      .sig[0] & 0x7fffffffUL,
-		sigcatch    .sig[0] & 0x7fffffffUL,
-		wchan,
-		0UL,
-		0UL,
-		task->exit_signal,
-		task_cpu(task),
-		task->rt_priority,
-		task->policy,
-		(unsigned long long)delayacct_blkio_ticks(task),
-		cputime_to_clock_t(gtime),
-		cputime_to_clock_t(cgtime),
-		(mm && permitted) ? mm->start_data : 0,
-		(mm && permitted) ? mm->end_data : 0,
-		(mm && permitted) ? mm->start_brk : 0);
+	seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state);
+	seq_put_decimal_ll(m, ' ', ppid);
+	seq_put_decimal_ll(m, ' ', pgid);
+	seq_put_decimal_ll(m, ' ', sid);
+	seq_put_decimal_ll(m, ' ', tty_nr);
+	seq_put_decimal_ll(m, ' ', tty_pgrp);
+	seq_put_decimal_ull(m, ' ', task->flags);
+	seq_put_decimal_ull(m, ' ', min_flt);
+	seq_put_decimal_ull(m, ' ', cmin_flt);
+	seq_put_decimal_ull(m, ' ', maj_flt);
+	seq_put_decimal_ull(m, ' ', cmaj_flt);
+	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime));
+	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime));
+	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime));
+	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime));
+	seq_put_decimal_ll(m, ' ', priority);
+	seq_put_decimal_ll(m, ' ', nice);
+	seq_put_decimal_ll(m, ' ', num_threads);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ull(m, ' ', start_time);
+	seq_put_decimal_ull(m, ' ', vsize);
+	seq_put_decimal_ll(m, ' ', mm ? get_mm_rss(mm) : 0);
+	seq_put_decimal_ull(m, ' ', rsslim);
+	seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0);
+	seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0);
+	seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0);
+	seq_put_decimal_ull(m, ' ', esp);
+	seq_put_decimal_ull(m, ' ', eip);
+	/* The signal information here is obsolete.
+	 * It must be decimal for Linux 2.0 compatibility.
+	 * Use /proc/#/status for real-time signals.
+	 */
+	seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, ' ', wchan);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ll(m, ' ', task->exit_signal);
+	seq_put_decimal_ll(m, ' ', task_cpu(task));
+	seq_put_decimal_ull(m, ' ', task->rt_priority);
+	seq_put_decimal_ull(m, ' ', task->policy);
+	seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task));
+	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime));
+	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime));
+	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_data : 0);
+	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->end_data : 0);
+	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_brk : 0);
+	seq_putc(m, '\n');
 	if (mm)
 		mmput(mm);
 	return 0;
@@ -542,8 +539,20 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 		size = task_statm(mm, &shared, &text, &data, &resident);
 		mmput(mm);
 	}
-	seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
-			size, resident, shared, text, data);
+	/*
+	 * For quick read, open code by putting numbers directly
+	 * expected format is
+	 * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
+	 *               size, resident, shared, text, data);
+	 */
+	seq_put_decimal_ull(m, 0, size);
+	seq_put_decimal_ull(m, ' ', resident);
+	seq_put_decimal_ull(m, ' ', shared);
+	seq_put_decimal_ull(m, ' ', text);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_put_decimal_ull(m, ' ', data);
+	seq_put_decimal_ull(m, ' ', 0);
+	seq_putc(m, '\n');
 
 	return 0;
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index db6ab4b36a0b..1c8b280146d7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1310,8 +1310,7 @@ sched_autogroup_write(struct file *file, const char __user *buf,
 	if (!p)
 		return -ESRCH;
 
-	err = nice;
-	err = proc_sched_autogroup_set_nice(p, &err);
+	err = proc_sched_autogroup_set_nice(p, nice);
 	if (err)
 		count = err;
 
@@ -2990,9 +2989,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("cmdline",    S_IRUGO, proc_pid_cmdline),
 	ONE("stat",       S_IRUGO, proc_tgid_stat),
 	ONE("statm",      S_IRUGO, proc_pid_statm),
-	REG("maps",       S_IRUGO, proc_maps_operations),
+	REG("maps",       S_IRUGO, proc_pid_maps_operations),
 #ifdef CONFIG_NUMA
-	REG("numa_maps",  S_IRUGO, proc_numa_maps_operations),
+	REG("numa_maps",  S_IRUGO, proc_pid_numa_maps_operations),
 #endif
 	REG("mem",        S_IRUSR|S_IWUSR, proc_mem_operations),
 	LNK("cwd",        proc_cwd_link),
@@ -3003,7 +3002,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("mountstats", S_IRUSR, proc_mountstats_operations),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
-	REG("smaps",      S_IRUGO, proc_smaps_operations),
+	REG("smaps",      S_IRUGO, proc_pid_smaps_operations),
 	REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
@@ -3349,9 +3348,9 @@ static const struct pid_entry tid_base_stuff[] = {
 	INF("cmdline",   S_IRUGO, proc_pid_cmdline),
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
-	REG("maps",      S_IRUGO, proc_maps_operations),
+	REG("maps",      S_IRUGO, proc_tid_maps_operations),
 #ifdef CONFIG_NUMA
-	REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+	REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
 #endif
 	REG("mem",       S_IRUSR|S_IWUSR, proc_mem_operations),
 	LNK("cwd",       proc_cwd_link),
@@ -3361,7 +3360,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
-	REG("smaps",     S_IRUGO, proc_smaps_operations),
+	REG("smaps",     S_IRUGO, proc_tid_smaps_operations),
 	REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 84fd3235a590..205c92280838 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 #include <linux/mount.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -486,8 +485,6 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 
 int proc_fill_super(struct super_block *s)
 {
-	struct inode * root_inode;
-
 	s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
 	s->s_blocksize = 1024;
 	s->s_blocksize_bits = 10;
@@ -496,19 +493,11 @@ int proc_fill_super(struct super_block *s)
 	s->s_time_gran = 1;
 	
 	pde_get(&proc_root);
-	root_inode = proc_get_inode(s, &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;
+	s->s_root = d_make_root(proc_get_inode(s, &proc_root));
+	if (s->s_root)
+		return 0;
 
-out_no_root:
 	printk("proc_read_super: get root inode failed\n");
-	iput(root_inode);
 	pde_put(&proc_root);
 	return -ENOMEM;
 }
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 292577531ad1..5f79bb8b4c60 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -10,12 +10,15 @@
  */
 
 #include <linux/proc_fs.h>
+struct  ctl_table_header;
 
 extern struct proc_dir_entry proc_root;
 #ifdef CONFIG_PROC_SYSCTL
 extern int proc_sys_init(void);
+extern void sysctl_head_put(struct ctl_table_header *head);
 #else
 static inline void proc_sys_init(void) { }
+static inline void sysctl_head_put(struct ctl_table_header *head) { }
 #endif
 #ifdef CONFIG_NET
 extern int proc_net_init(void);
@@ -53,9 +56,12 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
-extern const struct file_operations proc_maps_operations;
-extern const struct file_operations proc_numa_maps_operations;
-extern const struct file_operations proc_smaps_operations;
+extern const struct file_operations proc_pid_maps_operations;
+extern const struct file_operations proc_tid_maps_operations;
+extern const struct file_operations proc_pid_numa_maps_operations;
+extern const struct file_operations proc_tid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_tid_smaps_operations;
 extern const struct file_operations proc_clear_refs_operations;
 extern const struct file_operations proc_pagemap_operations;
 extern const struct file_operations proc_net_operations;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index d245cb23dd72..86c67eee439f 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -157,7 +157,8 @@ static int kcore_update_ram(void)
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /* calculate vmemmap's address from given system ram pfn and register it */
-int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
 {
 	unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT;
 	unsigned long nr_pages = ent->size >> PAGE_SHIFT;
@@ -189,7 +190,8 @@ int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
 
 }
 #else
-int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
 {
 	return 1;
 }
@@ -513,7 +515,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 
 				n = copy_to_user(buffer, (char *)start, tsz);
 				/*
-				 * We cannot distingush between fault on source
+				 * We cannot distinguish between fault on source
 				 * and fault on destination. When this happens
 				 * we clear too and hope it will trigger the
 				 * EFAULT again.
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 27da860115c6..0d9e23a39e49 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -53,7 +53,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
 	ei->ns_ops    = ns_ops;
 	ei->ns	      = ns;
 
-	dentry->d_op = &pid_dentry_operations;
+	d_set_d_op(dentry, &pid_dentry_operations);
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, NULL))
@@ -156,15 +156,15 @@ static struct dentry *proc_ns_dir_lookup(struct inode *dir,
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out;
 
-	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
-	for (entry = ns_entries; entry <= last; entry++) {
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
 		if (strlen((*entry)->name) != len)
 			continue;
 		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
 			break;
 	}
 	error = ERR_PTR(-ENOENT);
-	if (entry > last)
+	if (entry == last)
 		goto out;
 
 	error = proc_ns_instantiate(dir, dentry, task, *entry);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 6d8e6a9e93ab..7fcd0d60a968 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -115,6 +115,8 @@ u64 stable_page_flags(struct page *page)
 		u |= 1 << KPF_COMPOUND_TAIL;
 	if (PageHuge(page))
 		u |= 1 << KPF_HUGE;
+	else if (PageTransCompound(page))
+		u |= 1 << KPF_THP;
 
 	/*
 	 * Caveats on high order pages: page->_count will only be set
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index a6b62173d4c3..21d836f40292 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -6,7 +6,10 @@
 #include <linux/poll.h>
 #include <linux/proc_fs.h>
 #include <linux/security.h>
+#include <linux/sched.h>
 #include <linux/namei.h>
+#include <linux/mm.h>
+#include <linux/module.h>
 #include "internal.h"
 
 static const struct dentry_operations proc_sys_dentry_operations;
@@ -24,6 +27,371 @@ void proc_sys_poll_notify(struct ctl_table_poll *poll)
 	wake_up_interruptible(&poll->wait);
 }
 
+static struct ctl_table root_table[] = {
+	{
+		.procname = "",
+		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
+	},
+	{ }
+};
+static struct ctl_table_root sysctl_table_root = {
+	.default_set.dir.header = {
+		{{.count = 1,
+		  .nreg = 1,
+		  .ctl_table = root_table }},
+		.ctl_table_arg = root_table,
+		.root = &sysctl_table_root,
+		.set = &sysctl_table_root.default_set,
+	},
+};
+
+static DEFINE_SPINLOCK(sysctl_lock);
+
+static void drop_sysctl_table(struct ctl_table_header *header);
+static int sysctl_follow_link(struct ctl_table_header **phead,
+	struct ctl_table **pentry, struct nsproxy *namespaces);
+static int insert_links(struct ctl_table_header *head);
+static void put_links(struct ctl_table_header *header);
+
+static void sysctl_print_dir(struct ctl_dir *dir)
+{
+	if (dir->header.parent)
+		sysctl_print_dir(dir->header.parent);
+	printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
+}
+
+static int namecmp(const char *name1, int len1, const char *name2, int len2)
+{
+	int minlen;
+	int cmp;
+
+	minlen = len1;
+	if (minlen > len2)
+		minlen = len2;
+
+	cmp = memcmp(name1, name2, minlen);
+	if (cmp == 0)
+		cmp = len1 - len2;
+	return cmp;
+}
+
+/* Called under sysctl_lock */
+static struct ctl_table *find_entry(struct ctl_table_header **phead,
+	struct ctl_dir *dir, const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+	struct rb_node *node = dir->root.rb_node;
+
+	while (node)
+	{
+		struct ctl_node *ctl_node;
+		const char *procname;
+		int cmp;
+
+		ctl_node = rb_entry(node, struct ctl_node, node);
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+		procname = entry->procname;
+
+		cmp = namecmp(name, namelen, procname, strlen(procname));
+		if (cmp < 0)
+			node = node->rb_left;
+		else if (cmp > 0)
+			node = node->rb_right;
+		else {
+			*phead = head;
+			return entry;
+		}
+	}
+	return NULL;
+}
+
+static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+	struct rb_node *node = &head->node[entry - head->ctl_table].node;
+	struct rb_node **p = &head->parent->root.rb_node;
+	struct rb_node *parent = NULL;
+	const char *name = entry->procname;
+	int namelen = strlen(name);
+
+	while (*p) {
+		struct ctl_table_header *parent_head;
+		struct ctl_table *parent_entry;
+		struct ctl_node *parent_node;
+		const char *parent_name;
+		int cmp;
+
+		parent = *p;
+		parent_node = rb_entry(parent, struct ctl_node, node);
+		parent_head = parent_node->header;
+		parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
+		parent_name = parent_entry->procname;
+
+		cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else if (cmp > 0)
+			p = &(*p)->rb_right;
+		else {
+			printk(KERN_ERR "sysctl duplicate entry: ");
+			sysctl_print_dir(head->parent);
+			printk(KERN_CONT "/%s\n", entry->procname);
+			return -EEXIST;
+		}
+	}
+
+	rb_link_node(node, parent, p);
+	return 0;
+}
+
+static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+	struct rb_node *node = &head->node[entry - head->ctl_table].node;
+
+	rb_erase(node, &head->parent->root);
+}
+
+static void init_header(struct ctl_table_header *head,
+	struct ctl_table_root *root, struct ctl_table_set *set,
+	struct ctl_node *node, struct ctl_table *table)
+{
+	head->ctl_table = table;
+	head->ctl_table_arg = table;
+	head->used = 0;
+	head->count = 1;
+	head->nreg = 1;
+	head->unregistering = NULL;
+	head->root = root;
+	head->set = set;
+	head->parent = NULL;
+	head->node = node;
+	if (node) {
+		struct ctl_table *entry;
+		for (entry = table; entry->procname; entry++, node++) {
+			rb_init_node(&node->node);
+			node->header = head;
+		}
+	}
+}
+
+static void erase_header(struct ctl_table_header *head)
+{
+	struct ctl_table *entry;
+	for (entry = head->ctl_table; entry->procname; entry++)
+		erase_entry(head, entry);
+}
+
+static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
+{
+	struct ctl_table *entry;
+	int err;
+
+	dir->header.nreg++;
+	header->parent = dir;
+	err = insert_links(header);
+	if (err)
+		goto fail_links;
+	for (entry = header->ctl_table; entry->procname; entry++) {
+		err = insert_entry(header, entry);
+		if (err)
+			goto fail;
+	}
+	return 0;
+fail:
+	erase_header(header);
+	put_links(header);
+fail_links:
+	header->parent = NULL;
+	drop_sysctl_table(&dir->header);
+	return err;
+}
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+	if (unlikely(p->unregistering))
+		return 0;
+	p->used++;
+	return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+	if (!--p->used)
+		if (unlikely(p->unregistering))
+			complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+	/*
+	 * if p->used is 0, nobody will ever touch that entry again;
+	 * we'll eliminate all paths to it before dropping sysctl_lock
+	 */
+	if (unlikely(p->used)) {
+		struct completion wait;
+		init_completion(&wait);
+		p->unregistering = &wait;
+		spin_unlock(&sysctl_lock);
+		wait_for_completion(&wait);
+		spin_lock(&sysctl_lock);
+	} else {
+		/* anything non-NULL; we'll never dereference it */
+		p->unregistering = ERR_PTR(-EINVAL);
+	}
+	/*
+	 * do not remove from the list until nobody holds it; walking the
+	 * list in do_sysctl() relies on that.
+	 */
+	erase_header(p);
+}
+
+static void sysctl_head_get(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	head->count++;
+	spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	if (!--head->count)
+		kfree_rcu(head, rcu);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+	if (!head)
+		BUG();
+	spin_lock(&sysctl_lock);
+	if (!use_table(head))
+		head = ERR_PTR(-ENOENT);
+	spin_unlock(&sysctl_lock);
+	return head;
+}
+
+static void sysctl_head_finish(struct ctl_table_header *head)
+{
+	if (!head)
+		return;
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+	struct ctl_table_set *set = &root->default_set;
+	if (root->lookup)
+		set = root->lookup(root, namespaces);
+	return set;
+}
+
+static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
+				      struct ctl_dir *dir,
+				      const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+
+	spin_lock(&sysctl_lock);
+	entry = find_entry(&head, dir, name, namelen);
+	if (entry && use_table(head))
+		*phead = head;
+	else
+		entry = NULL;
+	spin_unlock(&sysctl_lock);
+	return entry;
+}
+
+static struct ctl_node *first_usable_entry(struct rb_node *node)
+{
+	struct ctl_node *ctl_node;
+
+	for (;node; node = rb_next(node)) {
+		ctl_node = rb_entry(node, struct ctl_node, node);
+		if (use_table(ctl_node->header))
+			return ctl_node;
+	}
+	return NULL;
+}
+
+static void first_entry(struct ctl_dir *dir,
+	struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+	struct ctl_table_header *head = NULL;
+	struct ctl_table *entry = NULL;
+	struct ctl_node *ctl_node;
+
+	spin_lock(&sysctl_lock);
+	ctl_node = first_usable_entry(rb_first(&dir->root));
+	spin_unlock(&sysctl_lock);
+	if (ctl_node) {
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+	}
+	*phead = head;
+	*pentry = entry;
+}
+
+static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+	struct ctl_table_header *head = *phead;
+	struct ctl_table *entry = *pentry;
+	struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
+
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+
+	ctl_node = first_usable_entry(rb_next(&ctl_node->node));
+	spin_unlock(&sysctl_lock);
+	head = NULL;
+	if (ctl_node) {
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+	}
+	*phead = head;
+	*pentry = entry;
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+}
+
+/*
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
+ * some sysctl variables are readonly even to root.
+ */
+
+static int test_perm(int mode, int op)
+{
+	if (!current_euid())
+		mode >>= 6;
+	else if (in_egroup_p(0))
+		mode >>= 3;
+	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
+		return 0;
+	return -EACCES;
+}
+
+static int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
+{
+	int mode;
+
+	if (root->permissions)
+		mode = root->permissions(root, current->nsproxy, table);
+	else
+		mode = table->mode;
+
+	return test_perm(mode, op);
+}
+
 static struct inode *proc_sys_make_inode(struct super_block *sb,
 		struct ctl_table_header *head, struct ctl_table *table)
 {
@@ -43,13 +411,12 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode->i_mode = table->mode;
-	if (!table->child) {
+	if (!S_ISDIR(table->mode)) {
 		inode->i_mode |= S_IFREG;
 		inode->i_op = &proc_sys_inode_operations;
 		inode->i_fop = &proc_sys_file_operations;
 	} else {
 		inode->i_mode |= S_IFDIR;
-		clear_nlink(inode);
 		inode->i_op = &proc_sys_dir_operations;
 		inode->i_fop = &proc_sys_dir_file_operations;
 	}
@@ -57,70 +424,42 @@ out:
 	return inode;
 }
 
-static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
-{
-	int len;
-	for ( ; p->procname; p++) {
-
-		if (!p->procname)
-			continue;
-
-		len = strlen(p->procname);
-		if (len != name->len)
-			continue;
-
-		if (memcmp(p->procname, name->name, len) != 0)
-			continue;
-
-		/* I have a match */
-		return p;
-	}
-	return NULL;
-}
-
 static struct ctl_table_header *grab_header(struct inode *inode)
 {
-	if (PROC_I(inode)->sysctl)
-		return sysctl_head_grab(PROC_I(inode)->sysctl);
-	else
-		return sysctl_head_next(NULL);
+	struct ctl_table_header *head = PROC_I(inode)->sysctl;
+	if (!head)
+		head = &sysctl_table_root.default_set.dir.header;
+	return sysctl_head_grab(head);
 }
 
 static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
 					struct nameidata *nd)
 {
 	struct ctl_table_header *head = grab_header(dir);
-	struct ctl_table *table = PROC_I(dir)->sysctl_entry;
 	struct ctl_table_header *h = NULL;
 	struct qstr *name = &dentry->d_name;
 	struct ctl_table *p;
 	struct inode *inode;
 	struct dentry *err = ERR_PTR(-ENOENT);
+	struct ctl_dir *ctl_dir;
+	int ret;
 
 	if (IS_ERR(head))
 		return ERR_CAST(head);
 
-	if (table && !table->child) {
-		WARN_ON(1);
-		goto out;
-	}
-
-	table = table ? table->child : head->ctl_table;
-
-	p = find_in_table(table, name);
-	if (!p) {
-		for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
-			if (h->attached_to != table)
-				continue;
-			p = find_in_table(h->attached_by, name);
-			if (p)
-				break;
-		}
-	}
+	ctl_dir = container_of(head, struct ctl_dir, header);
 
+	p = lookup_entry(&h, ctl_dir, name->name, name->len);
 	if (!p)
 		goto out;
 
+	if (S_ISLNK(p->mode)) {
+		ret = sysctl_follow_link(&h, &p, current->nsproxy);
+		err = ERR_PTR(ret);
+		if (ret)
+			goto out;
+	}
+
 	err = ERR_PTR(-ENOMEM);
 	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
 	if (h)
@@ -188,20 +527,32 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
 
 static int proc_sys_open(struct inode *inode, struct file *filp)
 {
+	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 
+	/* sysctl was unregistered */
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
 	if (table->poll)
 		filp->private_data = proc_sys_poll_event(table->poll);
 
+	sysctl_head_finish(head);
+
 	return 0;
 }
 
 static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
 {
 	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	unsigned long event = (unsigned long)filp->private_data;
 	unsigned int ret = DEFAULT_POLLMASK;
+	unsigned long event;
+
+	/* sysctl was unregistered */
+	if (IS_ERR(head))
+		return POLLERR | POLLHUP;
 
 	if (!table->proc_handler)
 		goto out;
@@ -209,6 +560,7 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
 	if (!table->poll)
 		goto out;
 
+	event = (unsigned long)filp->private_data;
 	poll_wait(filp, &table->poll->wait, wait);
 
 	if (event != atomic_read(&table->poll->event)) {
@@ -217,6 +569,8 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
 	}
 
 out:
+	sysctl_head_finish(head);
+
 	return ret;
 }
 
@@ -258,28 +612,45 @@ static int proc_sys_fill_cache(struct file *filp, void *dirent,
 	return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
 }
 
+static int proc_sys_link_fill_cache(struct file *filp, void *dirent,
+				    filldir_t filldir,
+				    struct ctl_table_header *head,
+				    struct ctl_table *table)
+{
+	int err, ret = 0;
+	head = sysctl_head_grab(head);
+
+	if (S_ISLNK(table->mode)) {
+		/* It is not an error if we can not follow the link ignore it */
+		err = sysctl_follow_link(&head, &table, current->nsproxy);
+		if (err)
+			goto out;
+	}
+
+	ret = proc_sys_fill_cache(filp, dirent, filldir, head, table);
+out:
+	sysctl_head_finish(head);
+	return ret;
+}
+
 static int scan(struct ctl_table_header *head, ctl_table *table,
 		unsigned long *pos, struct file *file,
 		void *dirent, filldir_t filldir)
 {
+	int res;
 
-	for (; table->procname; table++, (*pos)++) {
-		int res;
-
-		/* Can't do anything without a proc name */
-		if (!table->procname)
-			continue;
-
-		if (*pos < file->f_pos)
-			continue;
+	if ((*pos)++ < file->f_pos)
+		return 0;
 
+	if (unlikely(S_ISLNK(table->mode)))
+		res = proc_sys_link_fill_cache(file, dirent, filldir, head, table);
+	else
 		res = proc_sys_fill_cache(file, dirent, filldir, head, table);
-		if (res)
-			return res;
 
-		file->f_pos = *pos + 1;
-	}
-	return 0;
+	if (res == 0)
+		file->f_pos = *pos;
+
+	return res;
 }
 
 static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
@@ -287,20 +658,16 @@ static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	struct ctl_table_header *head = grab_header(inode);
-	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 	struct ctl_table_header *h = NULL;
+	struct ctl_table *entry;
+	struct ctl_dir *ctl_dir;
 	unsigned long pos;
 	int ret = -EINVAL;
 
 	if (IS_ERR(head))
 		return PTR_ERR(head);
 
-	if (table && !table->child) {
-		WARN_ON(1);
-		goto out;
-	}
-
-	table = table ? table->child : head->ctl_table;
+	ctl_dir = container_of(head, struct ctl_dir, header);
 
 	ret = 0;
 	/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
@@ -318,14 +685,8 @@ static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	}
 	pos = 2;
 
-	ret = scan(head, table, &pos, filp, dirent, filldir);
-	if (ret)
-		goto out;
-
-	for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
-		if (h->attached_to != table)
-			continue;
-		ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
+	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
+		ret = scan(h, entry, &pos, filp, dirent, filldir);
 		if (ret) {
 			sysctl_head_finish(h);
 			break;
@@ -445,6 +806,21 @@ static int proc_sys_delete(const struct dentry *dentry)
 	return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
 }
 
+static int sysctl_is_seen(struct ctl_table_header *p)
+{
+	struct ctl_table_set *set = p->set;
+	int res;
+	spin_lock(&sysctl_lock);
+	if (p->unregistering)
+		res = 0;
+	else if (!set->is_seen)
+		res = 1;
+	else
+		res = set->is_seen(set);
+	spin_unlock(&sysctl_lock);
+	return res;
+}
+
 static int proc_sys_compare(const struct dentry *parent,
 		const struct inode *pinode,
 		const struct dentry *dentry, const struct inode *inode,
@@ -470,6 +846,753 @@ static const struct dentry_operations proc_sys_dentry_operations = {
 	.d_compare	= proc_sys_compare,
 };
 
+static struct ctl_dir *find_subdir(struct ctl_dir *dir,
+				   const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+
+	entry = find_entry(&head, dir, name, namelen);
+	if (!entry)
+		return ERR_PTR(-ENOENT);
+	if (!S_ISDIR(entry->mode))
+		return ERR_PTR(-ENOTDIR);
+	return container_of(head, struct ctl_dir, header);
+}
+
+static struct ctl_dir *new_dir(struct ctl_table_set *set,
+			       const char *name, int namelen)
+{
+	struct ctl_table *table;
+	struct ctl_dir *new;
+	struct ctl_node *node;
+	char *new_name;
+
+	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
+		      sizeof(struct ctl_table)*2 +  namelen + 1,
+		      GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	node = (struct ctl_node *)(new + 1);
+	table = (struct ctl_table *)(node + 1);
+	new_name = (char *)(table + 2);
+	memcpy(new_name, name, namelen);
+	new_name[namelen] = '\0';
+	table[0].procname = new_name;
+	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
+	init_header(&new->header, set->dir.header.root, set, node, table);
+
+	return new;
+}
+
+/**
+ * get_subdir - find or create a subdir with the specified name.
+ * @dir:  Directory to create the subdirectory in
+ * @name: The name of the subdirectory to find or create
+ * @namelen: The length of name
+ *
+ * Takes a directory with an elevated reference count so we know that
+ * if we drop the lock the directory will not go away.  Upon success
+ * the reference is moved from @dir to the returned subdirectory.
+ * Upon error an error code is returned and the reference on @dir is
+ * simply dropped.
+ */
+static struct ctl_dir *get_subdir(struct ctl_dir *dir,
+				  const char *name, int namelen)
+{
+	struct ctl_table_set *set = dir->header.set;
+	struct ctl_dir *subdir, *new = NULL;
+	int err;
+
+	spin_lock(&sysctl_lock);
+	subdir = find_subdir(dir, name, namelen);
+	if (!IS_ERR(subdir))
+		goto found;
+	if (PTR_ERR(subdir) != -ENOENT)
+		goto failed;
+
+	spin_unlock(&sysctl_lock);
+	new = new_dir(set, name, namelen);
+	spin_lock(&sysctl_lock);
+	subdir = ERR_PTR(-ENOMEM);
+	if (!new)
+		goto failed;
+
+	/* Was the subdir added while we dropped the lock? */
+	subdir = find_subdir(dir, name, namelen);
+	if (!IS_ERR(subdir))
+		goto found;
+	if (PTR_ERR(subdir) != -ENOENT)
+		goto failed;
+
+	/* Nope.  Use the our freshly made directory entry. */
+	err = insert_header(dir, &new->header);
+	subdir = ERR_PTR(err);
+	if (err)
+		goto failed;
+	subdir = new;
+found:
+	subdir->header.nreg++;
+failed:
+	if (unlikely(IS_ERR(subdir))) {
+		printk(KERN_ERR "sysctl could not get directory: ");
+		sysctl_print_dir(dir);
+		printk(KERN_CONT "/%*.*s %ld\n",
+			namelen, namelen, name, PTR_ERR(subdir));
+	}
+	drop_sysctl_table(&dir->header);
+	if (new)
+		drop_sysctl_table(&new->header);
+	spin_unlock(&sysctl_lock);
+	return subdir;
+}
+
+static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
+{
+	struct ctl_dir *parent;
+	const char *procname;
+	if (!dir->header.parent)
+		return &set->dir;
+	parent = xlate_dir(set, dir->header.parent);
+	if (IS_ERR(parent))
+		return parent;
+	procname = dir->header.ctl_table[0].procname;
+	return find_subdir(parent, procname, strlen(procname));
+}
+
+static int sysctl_follow_link(struct ctl_table_header **phead,
+	struct ctl_table **pentry, struct nsproxy *namespaces)
+{
+	struct ctl_table_header *head;
+	struct ctl_table_root *root;
+	struct ctl_table_set *set;
+	struct ctl_table *entry;
+	struct ctl_dir *dir;
+	int ret;
+
+	ret = 0;
+	spin_lock(&sysctl_lock);
+	root = (*pentry)->data;
+	set = lookup_header_set(root, namespaces);
+	dir = xlate_dir(set, (*phead)->parent);
+	if (IS_ERR(dir))
+		ret = PTR_ERR(dir);
+	else {
+		const char *procname = (*pentry)->procname;
+		head = NULL;
+		entry = find_entry(&head, dir, procname, strlen(procname));
+		ret = -ENOENT;
+		if (entry && use_table(head)) {
+			unuse_table(*phead);
+			*phead = head;
+			*pentry = entry;
+			ret = 0;
+		}
+	}
+
+	spin_unlock(&sysctl_lock);
+	return ret;
+}
+
+static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n",
+		path, table->procname, &vaf);
+
+	va_end(args);
+	return -EINVAL;
+}
+
+static int sysctl_check_table(const char *path, struct ctl_table *table)
+{
+	int err = 0;
+	for (; table->procname; table++) {
+		if (table->child)
+			err = sysctl_err(path, table, "Not a file");
+
+		if ((table->proc_handler == proc_dostring) ||
+		    (table->proc_handler == proc_dointvec) ||
+		    (table->proc_handler == proc_dointvec_minmax) ||
+		    (table->proc_handler == proc_dointvec_jiffies) ||
+		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
+		    (table->proc_handler == proc_dointvec_ms_jiffies) ||
+		    (table->proc_handler == proc_doulongvec_minmax) ||
+		    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
+			if (!table->data)
+				err = sysctl_err(path, table, "No data");
+			if (!table->maxlen)
+				err = sysctl_err(path, table, "No maxlen");
+		}
+		if (!table->proc_handler)
+			err = sysctl_err(path, table, "No proc_handler");
+
+		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
+			err = sysctl_err(path, table, "bogus .mode 0%o",
+				table->mode);
+	}
+	return err;
+}
+
+static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table,
+	struct ctl_table_root *link_root)
+{
+	struct ctl_table *link_table, *entry, *link;
+	struct ctl_table_header *links;
+	struct ctl_node *node;
+	char *link_name;
+	int nr_entries, name_bytes;
+
+	name_bytes = 0;
+	nr_entries = 0;
+	for (entry = table; entry->procname; entry++) {
+		nr_entries++;
+		name_bytes += strlen(entry->procname) + 1;
+	}
+
+	links = kzalloc(sizeof(struct ctl_table_header) +
+			sizeof(struct ctl_node)*nr_entries +
+			sizeof(struct ctl_table)*(nr_entries + 1) +
+			name_bytes,
+			GFP_KERNEL);
+
+	if (!links)
+		return NULL;
+
+	node = (struct ctl_node *)(links + 1);
+	link_table = (struct ctl_table *)(node + nr_entries);
+	link_name = (char *)&link_table[nr_entries + 1];
+
+	for (link = link_table, entry = table; entry->procname; link++, entry++) {
+		int len = strlen(entry->procname) + 1;
+		memcpy(link_name, entry->procname, len);
+		link->procname = link_name;
+		link->mode = S_IFLNK|S_IRWXUGO;
+		link->data = link_root;
+		link_name += len;
+	}
+	init_header(links, dir->header.root, dir->header.set, node, link_table);
+	links->nreg = nr_entries;
+
+	return links;
+}
+
+static bool get_links(struct ctl_dir *dir,
+	struct ctl_table *table, struct ctl_table_root *link_root)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry, *link;
+
+	/* Are there links available for every entry in table? */
+	for (entry = table; entry->procname; entry++) {
+		const char *procname = entry->procname;
+		link = find_entry(&head, dir, procname, strlen(procname));
+		if (!link)
+			return false;
+		if (S_ISDIR(link->mode) && S_ISDIR(entry->mode))
+			continue;
+		if (S_ISLNK(link->mode) && (link->data == link_root))
+			continue;
+		return false;
+	}
+
+	/* The checks passed.  Increase the registration count on the links */
+	for (entry = table; entry->procname; entry++) {
+		const char *procname = entry->procname;
+		link = find_entry(&head, dir, procname, strlen(procname));
+		head->nreg++;
+	}
+	return true;
+}
+
+static int insert_links(struct ctl_table_header *head)
+{
+	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+	struct ctl_dir *core_parent = NULL;
+	struct ctl_table_header *links;
+	int err;
+
+	if (head->set == root_set)
+		return 0;
+
+	core_parent = xlate_dir(root_set, head->parent);
+	if (IS_ERR(core_parent))
+		return 0;
+
+	if (get_links(core_parent, head->ctl_table, head->root))
+		return 0;
+
+	core_parent->header.nreg++;
+	spin_unlock(&sysctl_lock);
+
+	links = new_links(core_parent, head->ctl_table, head->root);
+
+	spin_lock(&sysctl_lock);
+	err = -ENOMEM;
+	if (!links)
+		goto out;
+
+	err = 0;
+	if (get_links(core_parent, head->ctl_table, head->root)) {
+		kfree(links);
+		goto out;
+	}
+
+	err = insert_header(core_parent, links);
+	if (err)
+		kfree(links);
+out:
+	drop_sysctl_table(&core_parent->header);
+	return err;
+}
+
+/**
+ * __register_sysctl_table - register a leaf sysctl table
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * The members of the &struct ctl_table structure are used as follows:
+ *
+ * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
+ *            enter a sysctl file
+ *
+ * data - a pointer to data for use by proc_handler
+ *
+ * maxlen - the maximum size in bytes of the data
+ *
+ * mode - the file permissions for the /proc/sys file
+ *
+ * child - must be %NULL.
+ *
+ * proc_handler - the text handler routine (described below)
+ *
+ * extra1, extra2 - extra pointers usable by the proc handler routines
+ *
+ * Leaf nodes in the sysctl tree will be represented by a single file
+ * under /proc; non-leaf nodes will be represented by directories.
+ *
+ * There must be a proc_handler routine for any terminal nodes.
+ * Several default handlers are available to cover common cases -
+ *
+ * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
+ * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
+ * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
+ *
+ * It is the handler's job to read the input buffer from user memory
+ * and process it. The handler should return 0 on success.
+ *
+ * This routine returns %NULL on a failure to register, and a pointer
+ * to the table header on success.
+ */
+struct ctl_table_header *__register_sysctl_table(
+	struct ctl_table_set *set,
+	const char *path, struct ctl_table *table)
+{
+	struct ctl_table_root *root = set->dir.header.root;
+	struct ctl_table_header *header;
+	const char *name, *nextname;
+	struct ctl_dir *dir;
+	struct ctl_table *entry;
+	struct ctl_node *node;
+	int nr_entries = 0;
+
+	for (entry = table; entry->procname; entry++)
+		nr_entries++;
+
+	header = kzalloc(sizeof(struct ctl_table_header) +
+			 sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
+	if (!header)
+		return NULL;
+
+	node = (struct ctl_node *)(header + 1);
+	init_header(header, root, set, node, table);
+	if (sysctl_check_table(path, table))
+		goto fail;
+
+	spin_lock(&sysctl_lock);
+	dir = &set->dir;
+	/* Reference moved down the diretory tree get_subdir */
+	dir->header.nreg++;
+	spin_unlock(&sysctl_lock);
+
+	/* Find the directory for the ctl_table */
+	for (name = path; name; name = nextname) {
+		int namelen;
+		nextname = strchr(name, '/');
+		if (nextname) {
+			namelen = nextname - name;
+			nextname++;
+		} else {
+			namelen = strlen(name);
+		}
+		if (namelen == 0)
+			continue;
+
+		dir = get_subdir(dir, name, namelen);
+		if (IS_ERR(dir))
+			goto fail;
+	}
+
+	spin_lock(&sysctl_lock);
+	if (insert_header(dir, header))
+		goto fail_put_dir_locked;
+
+	drop_sysctl_table(&dir->header);
+	spin_unlock(&sysctl_lock);
+
+	return header;
+
+fail_put_dir_locked:
+	drop_sysctl_table(&dir->header);
+	spin_unlock(&sysctl_lock);
+fail:
+	kfree(header);
+	dump_stack();
+	return NULL;
+}
+
+/**
+ * register_sysctl - register a sysctl table
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the table structure
+ *
+ * Register a sysctl table. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table)
+{
+	return __register_sysctl_table(&sysctl_table_root.default_set,
+					path, table);
+}
+EXPORT_SYMBOL(register_sysctl);
+
+static char *append_path(const char *path, char *pos, const char *name)
+{
+	int namelen;
+	namelen = strlen(name);
+	if (((pos - path) + namelen + 2) >= PATH_MAX)
+		return NULL;
+	memcpy(pos, name, namelen);
+	pos[namelen] = '/';
+	pos[namelen + 1] = '\0';
+	pos += namelen + 1;
+	return pos;
+}
+
+static int count_subheaders(struct ctl_table *table)
+{
+	int has_files = 0;
+	int nr_subheaders = 0;
+	struct ctl_table *entry;
+
+	/* special case: no directory and empty directory */
+	if (!table || !table->procname)
+		return 1;
+
+	for (entry = table; entry->procname; entry++) {
+		if (entry->child)
+			nr_subheaders += count_subheaders(entry->child);
+		else
+			has_files = 1;
+	}
+	return nr_subheaders + has_files;
+}
+
+static int register_leaf_sysctl_tables(const char *path, char *pos,
+	struct ctl_table_header ***subheader, struct ctl_table_set *set,
+	struct ctl_table *table)
+{
+	struct ctl_table *ctl_table_arg = NULL;
+	struct ctl_table *entry, *files;
+	int nr_files = 0;
+	int nr_dirs = 0;
+	int err = -ENOMEM;
+
+	for (entry = table; entry->procname; entry++) {
+		if (entry->child)
+			nr_dirs++;
+		else
+			nr_files++;
+	}
+
+	files = table;
+	/* If there are mixed files and directories we need a new table */
+	if (nr_dirs && nr_files) {
+		struct ctl_table *new;
+		files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1),
+				GFP_KERNEL);
+		if (!files)
+			goto out;
+
+		ctl_table_arg = files;
+		for (new = files, entry = table; entry->procname; entry++) {
+			if (entry->child)
+				continue;
+			*new = *entry;
+			new++;
+		}
+	}
+
+	/* Register everything except a directory full of subdirectories */
+	if (nr_files || !nr_dirs) {
+		struct ctl_table_header *header;
+		header = __register_sysctl_table(set, path, files);
+		if (!header) {
+			kfree(ctl_table_arg);
+			goto out;
+		}
+
+		/* Remember if we need to free the file table */
+		header->ctl_table_arg = ctl_table_arg;
+		**subheader = header;
+		(*subheader)++;
+	}
+
+	/* Recurse into the subdirectories. */
+	for (entry = table; entry->procname; entry++) {
+		char *child_pos;
+
+		if (!entry->child)
+			continue;
+
+		err = -ENAMETOOLONG;
+		child_pos = append_path(path, pos, entry->procname);
+		if (!child_pos)
+			goto out;
+
+		err = register_leaf_sysctl_tables(path, child_pos, subheader,
+						  set, entry->child);
+		pos[0] = '\0';
+		if (err)
+			goto out;
+	}
+	err = 0;
+out:
+	/* On failure our caller will unregister all registered subheaders */
+	return err;
+}
+
+/**
+ * __register_sysctl_paths - register a sysctl table hierarchy
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *__register_sysctl_paths(
+	struct ctl_table_set *set,
+	const struct ctl_path *path, struct ctl_table *table)
+{
+	struct ctl_table *ctl_table_arg = table;
+	int nr_subheaders = count_subheaders(table);
+	struct ctl_table_header *header = NULL, **subheaders, **subheader;
+	const struct ctl_path *component;
+	char *new_path, *pos;
+
+	pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!new_path)
+		return NULL;
+
+	pos[0] = '\0';
+	for (component = path; component->procname; component++) {
+		pos = append_path(new_path, pos, component->procname);
+		if (!pos)
+			goto out;
+	}
+	while (table->procname && table->child && !table[1].procname) {
+		pos = append_path(new_path, pos, table->procname);
+		if (!pos)
+			goto out;
+		table = table->child;
+	}
+	if (nr_subheaders == 1) {
+		header = __register_sysctl_table(set, new_path, table);
+		if (header)
+			header->ctl_table_arg = ctl_table_arg;
+	} else {
+		header = kzalloc(sizeof(*header) +
+				 sizeof(*subheaders)*nr_subheaders, GFP_KERNEL);
+		if (!header)
+			goto out;
+
+		subheaders = (struct ctl_table_header **) (header + 1);
+		subheader = subheaders;
+		header->ctl_table_arg = ctl_table_arg;
+
+		if (register_leaf_sysctl_tables(new_path, pos, &subheader,
+						set, table))
+			goto err_register_leaves;
+	}
+
+out:
+	kfree(new_path);
+	return header;
+
+err_register_leaves:
+	while (subheader > subheaders) {
+		struct ctl_table_header *subh = *(--subheader);
+		struct ctl_table *table = subh->ctl_table_arg;
+		unregister_sysctl_table(subh);
+		kfree(table);
+	}
+	kfree(header);
+	header = NULL;
+	goto out;
+}
+
+/**
+ * register_sysctl_table_path - register a sysctl table hierarchy
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+						struct ctl_table *table)
+{
+	return __register_sysctl_paths(&sysctl_table_root.default_set,
+					path, table);
+}
+EXPORT_SYMBOL(register_sysctl_paths);
+
+/**
+ * register_sysctl_table - register a sysctl table hierarchy
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
+{
+	static const struct ctl_path null_path[] = { {} };
+
+	return register_sysctl_paths(null_path, table);
+}
+EXPORT_SYMBOL(register_sysctl_table);
+
+static void put_links(struct ctl_table_header *header)
+{
+	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+	struct ctl_table_root *root = header->root;
+	struct ctl_dir *parent = header->parent;
+	struct ctl_dir *core_parent;
+	struct ctl_table *entry;
+
+	if (header->set == root_set)
+		return;
+
+	core_parent = xlate_dir(root_set, parent);
+	if (IS_ERR(core_parent))
+		return;
+
+	for (entry = header->ctl_table; entry->procname; entry++) {
+		struct ctl_table_header *link_head;
+		struct ctl_table *link;
+		const char *name = entry->procname;
+
+		link = find_entry(&link_head, core_parent, name, strlen(name));
+		if (link &&
+		    ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) ||
+		     (S_ISLNK(link->mode) && (link->data == root)))) {
+			drop_sysctl_table(link_head);
+		}
+		else {
+			printk(KERN_ERR "sysctl link missing during unregister: ");
+			sysctl_print_dir(parent);
+			printk(KERN_CONT "/%s\n", name);
+		}
+	}
+}
+
+static void drop_sysctl_table(struct ctl_table_header *header)
+{
+	struct ctl_dir *parent = header->parent;
+
+	if (--header->nreg)
+		return;
+
+	put_links(header);
+	start_unregistering(header);
+	if (!--header->count)
+		kfree_rcu(header, rcu);
+
+	if (parent)
+		drop_sysctl_table(&parent->header);
+}
+
+/**
+ * unregister_sysctl_table - unregister a sysctl table hierarchy
+ * @header: the header returned from register_sysctl_table
+ *
+ * Unregisters the sysctl table and all children. proc entries may not
+ * actually be removed until they are no longer used by anyone.
+ */
+void unregister_sysctl_table(struct ctl_table_header * header)
+{
+	int nr_subheaders;
+	might_sleep();
+
+	if (header == NULL)
+		return;
+
+	nr_subheaders = count_subheaders(header->ctl_table_arg);
+	if (unlikely(nr_subheaders > 1)) {
+		struct ctl_table_header **subheaders;
+		int i;
+
+		subheaders = (struct ctl_table_header **)(header + 1);
+		for (i = nr_subheaders -1; i >= 0; i--) {
+			struct ctl_table_header *subh = subheaders[i];
+			struct ctl_table *table = subh->ctl_table_arg;
+			unregister_sysctl_table(subh);
+			kfree(table);
+		}
+		kfree(header);
+		return;
+	}
+
+	spin_lock(&sysctl_lock);
+	drop_sysctl_table(header);
+	spin_unlock(&sysctl_lock);
+}
+EXPORT_SYMBOL(unregister_sysctl_table);
+
+void setup_sysctl_set(struct ctl_table_set *set,
+	struct ctl_table_root *root,
+	int (*is_seen)(struct ctl_table_set *))
+{
+	memset(set, 0, sizeof(*set));
+	set->is_seen = is_seen;
+	init_header(&set->dir.header, root, set, NULL, root_table);
+}
+
+void retire_sysctl_set(struct ctl_table_set *set)
+{
+	WARN_ON(!RB_EMPTY_ROOT(&set->dir.root));
+}
+
 int __init proc_sys_init(void)
 {
 	struct proc_dir_entry *proc_sys_root;
@@ -478,5 +1601,6 @@ int __init proc_sys_init(void)
 	proc_sys_root->proc_iops = &proc_sys_dir_operations;
 	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
 	proc_sys_root->nlink = 0;
-	return 0;
+
+	return sysctl_init();
 }
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 46a15d8a29ca..eed44bfc85db 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -115,12 +115,13 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
 
+	if (!proc_parse_options(options, ns)) {
+		deactivate_locked_super(sb);
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (!sb->s_root) {
 		sb->s_flags = flags;
-		if (!proc_parse_options(options, ns)) {
-			deactivate_locked_super(sb);
-			return ERR_PTR(-EINVAL);
-		}
 		err = proc_fill_super(sb);
 		if (err) {
 			deactivate_locked_super(sb);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 121f77cfef76..6a0c62d6e442 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -89,18 +89,19 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	sum += arch_irq_stat();
 
-	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu "
-		"%llu\n",
-		(unsigned long long)cputime64_to_clock_t(user),
-		(unsigned long long)cputime64_to_clock_t(nice),
-		(unsigned long long)cputime64_to_clock_t(system),
-		(unsigned long long)cputime64_to_clock_t(idle),
-		(unsigned long long)cputime64_to_clock_t(iowait),
-		(unsigned long long)cputime64_to_clock_t(irq),
-		(unsigned long long)cputime64_to_clock_t(softirq),
-		(unsigned long long)cputime64_to_clock_t(steal),
-		(unsigned long long)cputime64_to_clock_t(guest),
-		(unsigned long long)cputime64_to_clock_t(guest_nice));
+	seq_puts(p, "cpu ");
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+	seq_putc(p, '\n');
+
 	for_each_online_cpu(i) {
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
 		user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
@@ -113,26 +114,24 @@ static int show_stat(struct seq_file *p, void *v)
 		steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
 		guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
 		guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
-		seq_printf(p,
-			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
-			"%llu\n",
-			i,
-			(unsigned long long)cputime64_to_clock_t(user),
-			(unsigned long long)cputime64_to_clock_t(nice),
-			(unsigned long long)cputime64_to_clock_t(system),
-			(unsigned long long)cputime64_to_clock_t(idle),
-			(unsigned long long)cputime64_to_clock_t(iowait),
-			(unsigned long long)cputime64_to_clock_t(irq),
-			(unsigned long long)cputime64_to_clock_t(softirq),
-			(unsigned long long)cputime64_to_clock_t(steal),
-			(unsigned long long)cputime64_to_clock_t(guest),
-			(unsigned long long)cputime64_to_clock_t(guest_nice));
+		seq_printf(p, "cpu%d", i);
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+		seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+		seq_putc(p, '\n');
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
 	/* sum again ? it could be updated? */
 	for_each_irq_nr(j)
-		seq_printf(p, " %u", kstat_irqs(j));
+		seq_put_decimal_ull(p, ' ', kstat_irqs(j));
 
 	seq_printf(p,
 		"\nctxt %llu\n"
@@ -149,7 +148,7 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
 
 	for (i = 0; i < NR_SOFTIRQS; i++)
-		seq_printf(p, " %u", per_softirq_sums[i]);
+		seq_put_decimal_ull(p, ' ', per_softirq_sums[i]);
 	seq_putc(p, '\n');
 
 	return 0;
@@ -157,11 +156,14 @@ static int show_stat(struct seq_file *p, void *v)
 
 static int stat_open(struct inode *inode, struct file *file)
 {
-	unsigned size = 4096 * (1 + num_possible_cpus() / 32);
+	unsigned size = 1024 + 128 * num_possible_cpus();
 	char *buf;
 	struct seq_file *m;
 	int res;
 
+	/* minimum size to display an interrupt count : 2 bytes */
+	size += 2 * nr_irqs;
+
 	/* don't ask for more than the kmalloc() max size */
 	if (size > KMALLOC_MAX_SIZE)
 		size = KMALLOC_MAX_SIZE;
@@ -173,7 +175,7 @@ static int stat_open(struct inode *inode, struct file *file)
 	if (!res) {
 		m = file->private_data;
 		m->buf = buf;
-		m->size = size;
+		m->size = ksize(buf);
 	} else
 		kfree(buf);
 	return res;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7dcd2a250495..2b9a7607cbd5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -209,16 +209,20 @@ static int do_maps_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
 	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
 	unsigned long start, end;
 	dev_t dev = 0;
 	int len;
+	const char *name = NULL;
 
 	if (file) {
 		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
@@ -252,36 +256,57 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	if (file) {
 		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "\n");
-	} else {
-		const char *name = arch_vma_name(vma);
-		if (!name) {
-			if (mm) {
-				if (vma->vm_start <= mm->brk &&
-						vma->vm_end >= mm->start_brk) {
-					name = "[heap]";
-				} else if (vma->vm_start <= mm->start_stack &&
-					   vma->vm_end >= mm->start_stack) {
-					name = "[stack]";
-				}
+		goto done;
+	}
+
+	name = arch_vma_name(vma);
+	if (!name) {
+		pid_t tid;
+
+		if (!mm) {
+			name = "[vdso]";
+			goto done;
+		}
+
+		if (vma->vm_start <= mm->brk &&
+		    vma->vm_end >= mm->start_brk) {
+			name = "[heap]";
+			goto done;
+		}
+
+		tid = vm_is_stack(task, vma, is_pid);
+
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack)) {
+				name = "[stack]";
 			} else {
-				name = "[vdso]";
+				/* Thread stack in /proc/PID/maps */
+				pad_len_spaces(m, len);
+				seq_printf(m, "[stack:%d]", tid);
 			}
 		}
-		if (name) {
-			pad_len_spaces(m, len);
-			seq_puts(m, name);
-		}
+	}
+
+done:
+	if (name) {
+		pad_len_spaces(m, len);
+		seq_puts(m, name);
 	}
 	seq_putc(m, '\n');
 }
 
-static int show_map(struct seq_file *m, void *v)
+static int show_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task->mm))
@@ -289,20 +314,49 @@ static int show_map(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_maps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_maps_op);
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -394,21 +448,15 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	spin_lock(&walk->mm->page_table_lock);
-	if (pmd_trans_huge(*pmd)) {
-		if (pmd_trans_splitting(*pmd)) {
-			spin_unlock(&walk->mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma, pmd);
-		} else {
-			smaps_pte_entry(*(pte_t *)pmd, addr,
-					HPAGE_PMD_SIZE, walk);
-			spin_unlock(&walk->mm->page_table_lock);
-			mss->anonymous_thp += HPAGE_PMD_SIZE;
-			return 0;
-		}
-	} else {
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
 		spin_unlock(&walk->mm->page_table_lock);
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+		return 0;
 	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	/*
 	 * The mmap_sem held all the way back in m_start() is what
 	 * keeps khugepaged out of here and from collapsing things
@@ -422,7 +470,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return 0;
 }
 
-static int show_smap(struct seq_file *m, void *v)
+static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
@@ -440,7 +488,7 @@ static int show_smap(struct seq_file *m, void *v)
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	seq_printf(m,
 		   "Size:           %8lu kB\n"
@@ -479,20 +527,49 @@ static int show_smap(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_smaps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_smap
+	.show	= show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_smap
 };
 
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_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,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+	.open		= pid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -507,6 +584,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -598,11 +677,18 @@ const struct file_operations proc_clear_refs_operations = {
 	.llseek		= noop_llseek,
 };
 
+typedef struct {
+	u64 pme;
+} pagemap_entry_t;
+
 struct pagemapread {
 	int pos, len;
-	u64 *buffer;
+	pagemap_entry_t *buffer;
 };
 
+#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
+#define PAGEMAP_WALK_MASK	(PMD_MASK)
+
 #define PM_ENTRY_BYTES      sizeof(u64)
 #define PM_STATUS_BITS      3
 #define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
@@ -620,10 +706,15 @@ struct pagemapread {
 #define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
 #define PM_END_OF_BUFFER    1
 
-static int add_to_pagemap(unsigned long addr, u64 pfn,
+static inline pagemap_entry_t make_pme(u64 val)
+{
+	return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
 			  struct pagemapread *pm)
 {
-	pm->buffer[pm->pos++] = pfn;
+	pm->buffer[pm->pos++] = *pme;
 	if (pm->pos >= pm->len)
 		return PM_END_OF_BUFFER;
 	return 0;
@@ -635,8 +726,10 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			break;
 	}
@@ -649,17 +742,35 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
-static u64 pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte)
 {
-	u64 pme = 0;
 	if (is_swap_pte(pte))
-		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+		*pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP);
 	else if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte))
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+					pmd_t pmd, int offset)
+{
+	/*
+	 * Currently pmd for thp is always present because thp can not be
+	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+	 * This if-check is just to prepare for future implementation.
+	 */
+	if (pmd_present(pmd))
+		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
 }
+#else
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+						pmd_t pmd, int offset)
+{
+}
+#endif
 
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
@@ -668,13 +779,28 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
-
-	split_huge_page_pmd(walk->mm, pmd);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		for (; addr != end; addr += PAGE_SIZE) {
+			unsigned long offset;
+
+			offset = (addr & ~PAGEMAP_WALK_MASK) >>
+					PAGE_SHIFT;
+			thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				break;
+		}
+		spin_unlock(&walk->mm->page_table_lock);
+		return err;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	for (; addr != end; addr += PAGE_SIZE) {
-		u64 pfn = PM_NOT_PRESENT;
 
 		/* check to see if we've left 'vma' behind
 		 * and need a new, higher one */
@@ -686,11 +812,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pfn = pte_to_pagemap_entry(*pte);
+			pte_to_pagemap_entry(&pme, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
-		err = add_to_pagemap(addr, pfn, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -701,13 +827,12 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+					pte_t pte, int offset)
 {
-	u64 pme = 0;
 	if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte) + offset)
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -717,12 +842,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 {
 	struct pagemapread *pm = walk->private;
 	int err = 0;
-	u64 pfn;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		pfn = huge_pte_to_pagemap_entry(*pte, offset);
-		err = add_to_pagemap(addr, pfn, pm);
+		huge_pte_to_pagemap_entry(&pme, *pte, offset);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -757,8 +882,6 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * determine which areas of memory are actually mapped and llseek to
  * skip over unmapped regions.
  */
-#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
-#define PAGEMAP_WALK_MASK	(PMD_MASK)
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
@@ -941,26 +1064,21 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *pte;
 
 	md = walk->private;
-	spin_lock(&walk->mm->page_table_lock);
-	if (pmd_trans_huge(*pmd)) {
-		if (pmd_trans_splitting(*pmd)) {
-			spin_unlock(&walk->mm->page_table_lock);
-			wait_split_huge_page(md->vma->anon_vma, pmd);
-		} else {
-			pte_t huge_pte = *(pte_t *)pmd;
-			struct page *page;
-
-			page = can_gather_numa_stats(huge_pte, md->vma, addr);
-			if (page)
-				gather_stats(page, md, pte_dirty(huge_pte),
-						HPAGE_PMD_SIZE/PAGE_SIZE);
-			spin_unlock(&walk->mm->page_table_lock);
-			return 0;
-		}
-	} else {
+
+	if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+		pte_t huge_pte = *(pte_t *)pmd;
+		struct page *page;
+
+		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		if (page)
+			gather_stats(page, md, pte_dirty(huge_pte),
+				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(&walk->mm->page_table_lock);
+		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -1002,7 +1120,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 /*
  * Display pages allocated per node and memory policy via /proc.
  */
-static int show_numa_map(struct seq_file *m, void *v)
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct numa_maps_private *numa_priv = m->private;
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
@@ -1039,9 +1157,19 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_path(m, &file->f_path, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_printf(m, " heap");
-	} else if (vma->vm_start <= mm->start_stack &&
-			vma->vm_end >= mm->start_stack) {
-		seq_printf(m, " stack");
+	} else {
+		pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, " stack");
+			else
+				seq_printf(m, " stack:%d", tid);
+		}
 	}
 
 	if (is_vm_hugetlb_page(vma))
@@ -1084,21 +1212,39 @@ out:
 	return 0;
 }
 
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_numa_maps_op = {
-        .start  = m_start,
-        .next   = m_next,
-        .stop   = m_stop,
-        .show   = show_numa_map,
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_pid_numa_map,
 };
 
-static int numa_maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_tid_numa_map,
+};
+
+static int numa_maps_open(struct inode *inode, struct file *file,
+			  const struct seq_operations *ops)
 {
 	struct numa_maps_private *priv;
 	int ret = -ENOMEM;
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (priv) {
 		priv->proc_maps.pid = proc_pid(inode);
-		ret = seq_open(file, &proc_pid_numa_maps_op);
+		ret = seq_open(file, ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = priv;
@@ -1109,8 +1255,25 @@ static int numa_maps_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-const struct file_operations proc_numa_maps_operations = {
-	.open		= numa_maps_open,
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+	.open		= pid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+	.open		= tid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 980de547c070..74fe164d1b23 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -134,9 +134,11 @@ static void pad_len_spaces(struct seq_file *m, int len)
 /*
  * display a single VMA to a sequenced file
  */
-static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
+			  int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct proc_maps_private *priv = m->private;
 	unsigned long ino = 0;
 	struct file *file;
 	dev_t dev = 0;
@@ -168,10 +170,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "");
 	} else if (mm) {
-		if (vma->vm_start <= mm->start_stack &&
-			vma->vm_end >= mm->start_stack) {
+		pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+
+		if (tid != 0) {
 			pad_len_spaces(m, len);
-			seq_puts(m, "[stack]");
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, "[stack]");
+			else
+				seq_printf(m, "[stack:%d]", tid);
 		}
 	}
 
@@ -182,11 +193,22 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 /*
  * display mapping lines for a particular process's /proc/pid/maps
  */
-static int show_map(struct seq_file *m, void *_p)
+static int show_map(struct seq_file *m, void *_p, int is_pid)
 {
 	struct rb_node *p = _p;
 
-	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
+	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb),
+			      is_pid);
+}
+
+static int show_pid_map(struct seq_file *m, void *_p)
+{
+	return show_map(m, _p, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *_p)
+{
+	return show_map(m, _p, 0);
 }
 
 static void *m_start(struct seq_file *m, loff_t *pos)
@@ -240,10 +262,18 @@ static const struct seq_operations proc_pid_maps_ops = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_ops = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static int maps_open(struct inode *inode, struct file *file,
+		     const struct seq_operations *ops)
 {
 	struct proc_maps_private *priv;
 	int ret = -ENOMEM;
@@ -251,7 +281,7 @@ static int maps_open(struct inode *inode, struct file *file)
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (priv) {
 		priv->pid = proc_pid(inode);
-		ret = seq_open(file, &proc_pid_maps_ops);
+		ret = seq_open(file, ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = priv;
@@ -262,8 +292,25 @@ static int maps_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_pid_maps_ops);
+}
+
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_tid_maps_ops);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index b0f450a2bb7c..0d5071d29985 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -700,3 +700,26 @@ static int __init vmcore_init(void)
 	return 0;
 }
 module_init(vmcore_init)
+
+/* Cleanup function for vmcore module. */
+void vmcore_cleanup(void)
+{
+	struct list_head *pos, *next;
+
+	if (proc_vmcore) {
+		remove_proc_entry(proc_vmcore->name, proc_vmcore->parent);
+		proc_vmcore = NULL;
+	}
+
+	/* clear the vmcore list. */
+	list_for_each_safe(pos, next, &vmcore_list) {
+		struct vmcore *m;
+
+		m = list_entry(pos, struct vmcore, list);
+		list_del(&m->list);
+		kfree(m);
+	}
+	kfree(elfcorebuf);
+	elfcorebuf = NULL;
+}
+EXPORT_SYMBOL_GPL(vmcore_cleanup);