Merge branch 'for-3.0' into for-3.1

10 files changed, 552 insertions, 109 deletions

diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index df434c5f28f..c1c72933592 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -20,6 +20,7 @@ proc-y	+= stat.o
 proc-y	+= uptime.o
 proc-y	+= version.o
 proc-y	+= softirqs.o
+proc-y	+= namespaces.o
 proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
 proc-$(CONFIG_NET)		+= proc_net.o
 proc-$(CONFIG_PROC_KCORE)	+= kcore.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 5e4f776b091..9b45ee84fbc 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -131,7 +131,7 @@ static inline void task_name(struct seq_file *m, struct task_struct *p)
  * you can test for combinations of others with
  * simple bit tests.
  */
-static const char *task_state_array[] = {
+static const char * const task_state_array[] = {
 	"R (running)",		/*   0 */
 	"S (sleeping)",		/*   1 */
 	"D (disk sleep)",	/*   2 */
@@ -147,7 +147,7 @@ static const char *task_state_array[] = {
 static inline const char *get_task_state(struct task_struct *tsk)
 {
 	unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state;
-	const char **p = &task_state_array[0];
+	const char * const *p = &task_state_array[0];
 
 	BUILD_BUG_ON(1 + ilog2(TASK_STATE_MAX) != ARRAY_SIZE(task_state_array));
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd6628d3ba4..14def991d9d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -83,6 +83,9 @@
 #include <linux/pid_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#ifdef CONFIG_HARDWALL
+#include <asm/hardwall.h>
+#endif
 #include "internal.h"
 
 /* NOTE:
@@ -600,7 +603,7 @@ static int proc_fd_access_allowed(struct inode *inode)
 	return allowed;
 }
 
-static int proc_setattr(struct dentry *dentry, struct iattr *attr)
+int proc_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int error;
 	struct inode *inode = dentry->d_inode;
@@ -894,20 +897,20 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 	if (!task)
 		goto out_no_task;
 
+	copied = -ENOMEM;
+	page = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!page)
+		goto out_task;
+
 	mm = check_mem_permission(task);
 	copied = PTR_ERR(mm);
 	if (IS_ERR(mm))
-		goto out_task;
+		goto out_free;
 
 	copied = -EIO;
 	if (file->private_data != (void *)((long)current->self_exec_id))
 		goto out_mm;
 
-	copied = -ENOMEM;
-	page = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!page)
-		goto out_mm;
-
 	copied = 0;
 	while (count > 0) {
 		int this_len, retval;
@@ -929,9 +932,11 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 		count -= retval;			
 	}
 	*ppos = dst;
-	free_page((unsigned long) page);
+
 out_mm:
 	mmput(mm);
+out_free:
+	free_page((unsigned long) page);
 out_task:
 	put_task_struct(task);
 out_no_task:
@@ -1059,7 +1064,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
 {
 	struct task_struct *task;
 	char buffer[PROC_NUMBUF];
-	long oom_adjust;
+	int oom_adjust;
 	unsigned long flags;
 	int err;
 
@@ -1071,7 +1076,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	err = strict_strtol(strstrip(buffer), 0, &oom_adjust);
+	err = kstrtoint(strstrip(buffer), 0, &oom_adjust);
 	if (err)
 		goto out;
 	if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
@@ -1168,7 +1173,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 	struct task_struct *task;
 	char buffer[PROC_NUMBUF];
 	unsigned long flags;
-	long oom_score_adj;
+	int oom_score_adj;
 	int err;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -1179,7 +1184,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	err = strict_strtol(strstrip(buffer), 0, &oom_score_adj);
+	err = kstrtoint(strstrip(buffer), 0, &oom_score_adj);
 	if (err)
 		goto out;
 	if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
@@ -1468,7 +1473,7 @@ sched_autogroup_write(struct file *file, const char __user *buf,
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct task_struct *p;
 	char buffer[PROC_NUMBUF];
-	long nice;
+	int nice;
 	int err;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -1477,9 +1482,9 @@ sched_autogroup_write(struct file *file, const char __user *buf,
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
 
-	err = strict_strtol(strstrip(buffer), 0, &nice);
-	if (err)
-		return -EINVAL;
+	err = kstrtoint(strstrip(buffer), 0, &nice);
+	if (err < 0)
+		return err;
 
 	p = get_proc_task(inode);
 	if (!p)
@@ -1576,57 +1581,6 @@ static const struct file_operations proc_pid_set_comm_operations = {
 	.release	= single_release,
 };
 
-/*
- * We added or removed a vma mapping the executable. The vmas are only mapped
- * during exec and are not mapped with the mmap system call.
- * Callers must hold down_write() on the mm's mmap_sem for these
- */
-void added_exe_file_vma(struct mm_struct *mm)
-{
-	mm->num_exe_file_vmas++;
-}
-
-void removed_exe_file_vma(struct mm_struct *mm)
-{
-	mm->num_exe_file_vmas--;
-	if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
-		fput(mm->exe_file);
-		mm->exe_file = NULL;
-	}
-
-}
-
-void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
-{
-	if (new_exe_file)
-		get_file(new_exe_file);
-	if (mm->exe_file)
-		fput(mm->exe_file);
-	mm->exe_file = new_exe_file;
-	mm->num_exe_file_vmas = 0;
-}
-
-struct file *get_mm_exe_file(struct mm_struct *mm)
-{
-	struct file *exe_file;
-
-	/* We need mmap_sem to protect against races with removal of
-	 * VM_EXECUTABLE vmas */
-	down_read(&mm->mmap_sem);
-	exe_file = mm->exe_file;
-	if (exe_file)
-		get_file(exe_file);
-	up_read(&mm->mmap_sem);
-	return exe_file;
-}
-
-void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
-{
-	/* It's safe to write the exe_file pointer without exe_file_lock because
-	 * this is called during fork when the task is not yet in /proc */
-	newmm->exe_file = get_mm_exe_file(oldmm);
-}
-
 static int proc_exe_link(struct inode *inode, struct path *exe_path)
 {
 	struct task_struct *task;
@@ -1736,8 +1690,7 @@ static int task_dumpable(struct task_struct *task)
 	return 0;
 }
 
-
-static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
+struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
 {
 	struct inode * inode;
 	struct proc_inode *ei;
@@ -1779,7 +1732,7 @@ out_unlock:
 	return NULL;
 }
 
-static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
 	struct task_struct *task;
@@ -1820,7 +1773,7 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat
  * made this apply to all per process world readable and executable
  * directories.
  */
-static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
+int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode;
 	struct task_struct *task;
@@ -1862,7 +1815,7 @@ static int pid_delete_dentry(const struct dentry * dentry)
 	return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
 }
 
-static const struct dentry_operations pid_dentry_operations =
+const struct dentry_operations pid_dentry_operations =
 {
 	.d_revalidate	= pid_revalidate,
 	.d_delete	= pid_delete_dentry,
@@ -1870,9 +1823,6 @@ static const struct dentry_operations pid_dentry_operations =
 
 /* Lookups */
 
-typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
-				struct task_struct *, const void *);
-
 /*
  * Fill a directory entry.
  *
@@ -1885,8 +1835,8 @@ typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
  * reported by readdir in sync with the inode numbers reported
  * by stat.
  */
-static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
-	char *name, int len,
+int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+	const char *name, int len,
 	instantiate_t instantiate, struct task_struct *task, const void *ptr)
 {
 	struct dentry *child, *dir = filp->f_path.dentry;
@@ -2820,6 +2770,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	DIR("task",       S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
 	DIR("fd",         S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
 	DIR("fdinfo",     S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+	DIR("ns",	  S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
 #ifdef CONFIG_NET
 	DIR("net",        S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
 #endif
@@ -2894,6 +2845,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	INF("io",	S_IRUGO, proc_tgid_io_accounting),
 #endif
+#ifdef CONFIG_HARDWALL
+	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file * filp,
@@ -3124,11 +3078,16 @@ static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldi
 /* for the /proc/ directory itself, after non-process stuff has been done */
 int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
 {
-	unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
-	struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
+	unsigned int nr;
+	struct task_struct *reaper;
 	struct tgid_iter iter;
 	struct pid_namespace *ns;
 
+	if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET)
+		goto out_no_task;
+	nr = filp->f_pos - FIRST_PROCESS_ENTRY;
+
+	reaper = get_proc_task(filp->f_path.dentry->d_inode);
 	if (!reaper)
 		goto out_no_task;
 
@@ -3163,6 +3122,7 @@ out_no_task:
 static const struct pid_entry tid_base_stuff[] = {
 	DIR("fd",        S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
 	DIR("fdinfo",    S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+	DIR("ns",	 S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
 	REG("environ",   S_IRUSR, proc_environ_operations),
 	INF("auxv",      S_IRUSR, proc_pid_auxv),
 	ONE("status",    S_IRUGO, proc_pid_status),
@@ -3227,6 +3187,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	INF("io",	S_IRUGO, proc_tid_io_accounting),
 #endif
+#ifdef CONFIG_HARDWALL
+	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file * filp,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index f1281339b6f..f1637f17c37 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -674,6 +674,7 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
 	}
 	return ent;
 }
+EXPORT_SYMBOL(proc_mkdir_mode);
 
 struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 		struct proc_dir_entry *parent)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d15aa1b1cc8..74b48cfa1bb 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -28,6 +28,7 @@ static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
+	const struct proc_ns_operations *ns_ops;
 
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
@@ -44,6 +45,10 @@ static void proc_evict_inode(struct inode *inode)
 		rcu_assign_pointer(PROC_I(inode)->sysctl, NULL);
 		sysctl_head_put(head);
 	}
+	/* Release any associated namespace */
+	ns_ops = PROC_I(inode)->ns_ops;
+	if (ns_ops && ns_ops->put)
+		ns_ops->put(PROC_I(inode)->ns);
 }
 
 static struct kmem_cache * proc_inode_cachep;
@@ -62,6 +67,8 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 	ei->pde = NULL;
 	ei->sysctl = NULL;
 	ei->sysctl_entry = NULL;
+	ei->ns = NULL;
+	ei->ns_ops = NULL;
 	inode = &ei->vfs_inode;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	return inode;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c03e8d3a3a5..7838e5cfec1 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -61,6 +61,14 @@ extern const struct file_operations proc_pagemap_operations;
 extern const struct file_operations proc_net_operations;
 extern const struct inode_operations proc_net_inode_operations;
 
+struct proc_maps_private {
+	struct pid *pid;
+	struct task_struct *task;
+#ifdef CONFIG_MMU
+	struct vm_area_struct *tail_vma;
+#endif
+};
+
 void proc_init_inodecache(void);
 
 static inline struct pid *proc_pid(struct inode *inode)
@@ -119,3 +127,21 @@ struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
  */
 int proc_readdir(struct file *, void *, filldir_t);
 struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
+
+
+
+/* Lookups */
+typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
+				struct task_struct *, const void *);
+int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+	const char *name, int len,
+	instantiate_t instantiate, struct task_struct *task, const void *ptr);
+int pid_revalidate(struct dentry *dentry, struct nameidata *nd);
+struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task);
+extern const struct dentry_operations pid_dentry_operations;
+int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
+int proc_setattr(struct dentry *dentry, struct iattr *attr);
+
+extern const struct inode_operations proc_ns_dir_inode_operations;
+extern const struct file_operations proc_ns_dir_operations;
+
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
new file mode 100644
index 00000000000..781dec5bd68
--- /dev/null
+++ b/fs/proc/namespaces.c
@@ -0,0 +1,198 @@
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/fs_struct.h>
+#include <linux/mount.h>
+#include <linux/path.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/mnt_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+};
+
+static const struct file_operations ns_file_operations = {
+	.llseek		= no_llseek,
+};
+
+static struct dentry *proc_ns_instantiate(struct inode *dir,
+	struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct dentry *error = ERR_PTR(-ENOENT);
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	inode->i_mode = S_IFREG|S_IRUSR;
+	inode->i_fop  = &ns_file_operations;
+	ei->ns_ops    = ns_ops;
+	ei->ns	      = ns_ops->get(task);
+	if (!ei->ns)
+		goto out_iput;
+
+	dentry->d_op = &pid_dentry_operations;
+	d_add(dentry, inode);
+	/* Close the race of the process dying before we return the dentry */
+	if (pid_revalidate(dentry, NULL))
+		error = NULL;
+out:
+	return error;
+out_iput:
+	iput(inode);
+	goto out;
+}
+
+static int proc_ns_fill_cache(struct file *filp, void *dirent,
+	filldir_t filldir, struct task_struct *task,
+	const struct proc_ns_operations *ops)
+{
+	return proc_fill_cache(filp, dirent, filldir,
+				ops->name, strlen(ops->name),
+				proc_ns_instantiate, task, ops);
+}
+
+static int proc_ns_dir_readdir(struct file *filp, void *dirent,
+				filldir_t filldir)
+{
+	int i;
+	struct dentry *dentry = filp->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+	struct task_struct *task = get_proc_task(inode);
+	const struct proc_ns_operations **entry, **last;
+	ino_t ino;
+	int ret;
+
+	ret = -ENOENT;
+	if (!task)
+		goto out_no_task;
+
+	ret = -EPERM;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out;
+
+	ret = 0;
+	i = filp->f_pos;
+	switch (i) {
+	case 0:
+		ino = inode->i_ino;
+		if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
+			goto out;
+		i++;
+		filp->f_pos++;
+		/* fall through */
+	case 1:
+		ino = parent_ino(dentry);
+		if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
+			goto out;
+		i++;
+		filp->f_pos++;
+		/* fall through */
+	default:
+		i -= 2;
+		if (i >= ARRAY_SIZE(ns_entries)) {
+			ret = 1;
+			goto out;
+		}
+		entry = ns_entries + i;
+		last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+		while (entry <= last) {
+			if (proc_ns_fill_cache(filp, dirent, filldir,
+						task, *entry) < 0)
+				goto out;
+			filp->f_pos++;
+			entry++;
+		}
+	}
+
+	ret = 1;
+out:
+	put_task_struct(task);
+out_no_task:
+	return ret;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_ns_dir_readdir,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *error;
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations **entry, **last;
+	unsigned int len = dentry->d_name.len;
+
+	error = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+
+	error = ERR_PTR(-EPERM);
+	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++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	error = ERR_PTR(-ENOENT);
+	if (entry > last)
+		goto out;
+
+	error = proc_ns_instantiate(dir, dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return error;
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_setattr,
+};
+
+struct file *proc_ns_fget(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
+
+	if (file->f_op != &ns_file_operations)
+		goto out_invalid;
+
+	return file;
+
+out_invalid:
+	fput(file);
+	return ERR_PTR(-EINVAL);
+}
+
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 1cffa2b8a2f..9758b654a1b 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -138,9 +138,9 @@ static int stat_open(struct inode *inode, struct file *file)
 	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;
+	/* don't ask for more than the kmalloc() max size */
+	if (size > KMALLOC_MAX_SIZE)
+		size = KMALLOC_MAX_SIZE;
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 2e7addfd980..25b6a887adb 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -211,10 +211,10 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
-	int flags = vma->vm_flags;
+	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
-	unsigned long start;
+	unsigned long start, end;
 	dev_t dev = 0;
 	int len;
 
@@ -227,13 +227,15 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 
 	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
-	if (vma->vm_flags & VM_GROWSDOWN)
-		if (!vma_stack_continue(vma->vm_prev, vma->vm_start))
-			start += PAGE_SIZE;
+	if (stack_guard_page_start(vma, start))
+		start += PAGE_SIZE;
+	end = vma->vm_end;
+	if (stack_guard_page_end(vma, end))
+		end -= PAGE_SIZE;
 
 	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
 			start,
-			vma->vm_end,
+			end,
 			flags & VM_READ ? 'r' : '-',
 			flags & VM_WRITE ? 'w' : '-',
 			flags & VM_EXEC ? 'x' : '-',
@@ -534,15 +536,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	char buffer[PROC_NUMBUF];
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	long type;
+	int type;
+	int rv;
 
 	memset(buffer, 0, sizeof(buffer));
 	if (count > sizeof(buffer) - 1)
 		count = sizeof(buffer) - 1;
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
-	if (strict_strtol(strstrip(buffer), 10, &type))
-		return -EINVAL;
+	rv = kstrtoint(strstrip(buffer), 10, &type);
+	if (rv < 0)
+		return rv;
 	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
 		return -EINVAL;
 	task = get_proc_task(file->f_path.dentry->d_inode);
@@ -767,18 +771,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!task)
 		goto out;
 
-	mm = mm_for_maps(task);
-	ret = PTR_ERR(mm);
-	if (!mm || IS_ERR(mm))
-		goto out_task;
-
 	ret = -EINVAL;
 	/* file position must be aligned */
 	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
 		goto out_task;
 
 	ret = 0;
-
 	if (!count)
 		goto out_task;
 
@@ -786,7 +784,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;
 	if (!pm.buffer)
-		goto out_mm;
+		goto out_task;
+
+	mm = mm_for_maps(task);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
+		goto out_free;
 
 	pagemap_walk.pmd_entry = pagemap_pte_range;
 	pagemap_walk.pte_hole = pagemap_pte_hole;
@@ -829,7 +832,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		len = min(count, PM_ENTRY_BYTES * pm.pos);
 		if (copy_to_user(buf, pm.buffer, len)) {
 			ret = -EFAULT;
-			goto out_free;
+			goto out_mm;
 		}
 		copied += len;
 		buf += len;
@@ -839,10 +842,10 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!ret || ret == PM_END_OF_BUFFER)
 		ret = copied;
 
-out_free:
-	kfree(pm.buffer);
 out_mm:
 	mmput(mm);
+out_free:
+	kfree(pm.buffer);
 out_task:
 	put_task_struct(task);
 out:
@@ -856,7 +859,192 @@ const struct file_operations proc_pagemap_operations = {
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
 #ifdef CONFIG_NUMA
-extern int show_numa_map(struct seq_file *m, void *v);
+
+struct numa_maps {
+	struct vm_area_struct *vma;
+	unsigned long pages;
+	unsigned long anon;
+	unsigned long active;
+	unsigned long writeback;
+	unsigned long mapcount_max;
+	unsigned long dirty;
+	unsigned long swapcache;
+	unsigned long node[MAX_NUMNODES];
+};
+
+struct numa_maps_private {
+	struct proc_maps_private proc_maps;
+	struct numa_maps md;
+};
+
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty)
+{
+	int count = page_mapcount(page);
+
+	md->pages++;
+	if (pte_dirty || PageDirty(page))
+		md->dirty++;
+
+	if (PageSwapCache(page))
+		md->swapcache++;
+
+	if (PageActive(page) || PageUnevictable(page))
+		md->active++;
+
+	if (PageWriteback(page))
+		md->writeback++;
+
+	if (PageAnon(page))
+		md->anon++;
+
+	if (count > md->mapcount_max)
+		md->mapcount_max = count;
+
+	md->node[page_to_nid(page)]++;
+}
+
+static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
+		unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md;
+	spinlock_t *ptl;
+	pte_t *orig_pte;
+	pte_t *pte;
+
+	md = walk->private;
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	do {
+		struct page *page;
+		int nid;
+
+		if (!pte_present(*pte))
+			continue;
+
+		page = vm_normal_page(md->vma, addr, *pte);
+		if (!page)
+			continue;
+
+		if (PageReserved(page))
+			continue;
+
+		nid = page_to_nid(page);
+		if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+			continue;
+
+		gather_stats(page, md, pte_dirty(*pte));
+
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(orig_pte, ptl);
+	return 0;
+}
+#ifdef CONFIG_HUGETLB_PAGE
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md;
+	struct page *page;
+
+	if (pte_none(*pte))
+		return 0;
+
+	page = pte_page(*pte);
+	if (!page)
+		return 0;
+
+	md = walk->private;
+	gather_stats(page, md, pte_dirty(*pte));
+	return 0;
+}
+
+#else
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
+static int show_numa_map(struct seq_file *m, void *v)
+{
+	struct numa_maps_private *numa_priv = m->private;
+	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+	struct vm_area_struct *vma = v;
+	struct numa_maps *md = &numa_priv->md;
+	struct file *file = vma->vm_file;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mm_walk walk = {};
+	struct mempolicy *pol;
+	int n;
+	char buffer[50];
+
+	if (!mm)
+		return 0;
+
+	/* Ensure we start with an empty set of numa_maps statistics. */
+	memset(md, 0, sizeof(*md));
+
+	md->vma = vma;
+
+	walk.hugetlb_entry = gather_hugetbl_stats;
+	walk.pmd_entry = gather_pte_stats;
+	walk.private = md;
+	walk.mm = mm;
+
+	pol = get_vma_policy(proc_priv->task, vma, vma->vm_start);
+	mpol_to_str(buffer, sizeof(buffer), pol, 0);
+	mpol_cond_put(pol);
+
+	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
+
+	if (file) {
+		seq_printf(m, " file=");
+		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");
+	}
+
+	walk_page_range(vma->vm_start, vma->vm_end, &walk);
+
+	if (!md->pages)
+		goto out;
+
+	if (md->anon)
+		seq_printf(m, " anon=%lu", md->anon);
+
+	if (md->dirty)
+		seq_printf(m, " dirty=%lu", md->dirty);
+
+	if (md->pages != md->anon && md->pages != md->dirty)
+		seq_printf(m, " mapped=%lu", md->pages);
+
+	if (md->mapcount_max > 1)
+		seq_printf(m, " mapmax=%lu", md->mapcount_max);
+
+	if (md->swapcache)
+		seq_printf(m, " swapcache=%lu", md->swapcache);
+
+	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
+		seq_printf(m, " active=%lu", md->active);
+
+	if (md->writeback)
+		seq_printf(m, " writeback=%lu", md->writeback);
+
+	for_each_node_state(n, N_HIGH_MEMORY)
+		if (md->node[n])
+			seq_printf(m, " N%d=%lu", n, md->node[n]);
+out:
+	seq_putc(m, '\n');
+
+	if (m->count < m->size)
+		m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+	return 0;
+}
 
 static const struct seq_operations proc_pid_numa_maps_op = {
         .start  = m_start,
@@ -867,7 +1055,20 @@ static const struct seq_operations proc_pid_numa_maps_op = {
 
 static int numa_maps_open(struct inode *inode, struct file *file)
 {
-	return do_maps_open(inode, file, &proc_pid_numa_maps_op);
+	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);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = priv;
+		} else {
+			kfree(priv);
+		}
+	}
+	return ret;
 }
 
 const struct file_operations proc_numa_maps_operations = {
@@ -876,4 +1077,4 @@ const struct file_operations proc_numa_maps_operations = {
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
-#endif
+#endif /* CONFIG_NUMA */
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 74802bc5ded..cd99bf55765 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -35,6 +35,46 @@ static u64 vmcore_size;
 
 static struct proc_dir_entry *proc_vmcore = NULL;
 
+/*
+ * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
+ * The called function has to take care of module refcounting.
+ */
+static int (*oldmem_pfn_is_ram)(unsigned long pfn);
+
+int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
+{
+	if (oldmem_pfn_is_ram)
+		return -EBUSY;
+	oldmem_pfn_is_ram = fn;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);
+
+void unregister_oldmem_pfn_is_ram(void)
+{
+	oldmem_pfn_is_ram = NULL;
+	wmb();
+}
+EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);
+
+static int pfn_is_ram(unsigned long pfn)
+{
+	int (*fn)(unsigned long pfn);
+	/* pfn is ram unless fn() checks pagetype */
+	int ret = 1;
+
+	/*
+	 * Ask hypervisor if the pfn is really ram.
+	 * A ballooned page contains no data and reading from such a page
+	 * will cause high load in the hypervisor.
+	 */
+	fn = oldmem_pfn_is_ram;
+	if (fn)
+		ret = fn(pfn);
+
+	return ret;
+}
+
 /* Reads a page from the oldmem device from given offset. */
 static ssize_t read_from_oldmem(char *buf, size_t count,
 				u64 *ppos, int userbuf)
@@ -55,9 +95,15 @@ static ssize_t read_from_oldmem(char *buf, size_t count,
 		else
 			nr_bytes = count;
 
-		tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf);
-		if (tmp < 0)
-			return tmp;
+		/* If pfn is not ram, return zeros for sparse dump files */
+		if (pfn_is_ram(pfn) == 0)
+			memset(buf, 0, nr_bytes);
+		else {
+			tmp = copy_oldmem_page(pfn, buf, nr_bytes,
+						offset, userbuf);
+			if (tmp < 0)
+				return tmp;
+		}
 		*ppos += nr_bytes;
 		count -= nr_bytes;
 		buf += nr_bytes;