Merge with /pub/scm/linux/kernel/git/torvalds/linux-2.6.git

10 files changed, 467 insertions, 189 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index e54be705835..ed78d24ee42 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -783,28 +783,6 @@ config SYSFS
 
 	Designers of embedded systems may wish to say N here to conserve space.
 
-config DEVPTS_FS_XATTR
-	bool "/dev/pts Extended Attributes"
-	depends on UNIX98_PTYS
-	help
-	  Extended attributes are name:value pairs associated with inodes by
-	  the kernel or by users (see the attr(5) manual page, or visit
-	  <http://acl.bestbits.at/> for details).
-
-	  If unsure, say N.
-
-config DEVPTS_FS_SECURITY
-	bool "/dev/pts Security Labels"
-	depends on DEVPTS_FS_XATTR
-	help
-	  Security labels support alternative access control models
-	  implemented by security modules like SELinux.  This option
-	  enables an extended attribute handler for file security
-	  labels in the /dev/pts filesystem.
-
-	  If you are not using a security module that requires using
-	  extended attributes for file security labels, say N.
-
 config TMPFS
 	bool "Virtual memory file system support (former shm fs)"
 	help
@@ -817,27 +795,6 @@ config TMPFS
 
 	  See <file:Documentation/filesystems/tmpfs.txt> for details.
 
-config TMPFS_XATTR
-	bool "tmpfs Extended Attributes"
-	depends on TMPFS
-	help
-	  Extended attributes are name:value pairs associated with inodes by
-	  the kernel or by users (see the attr(5) manual page, or visit
-	  <http://acl.bestbits.at/> for details).
-
-	  If unsure, say N.
-
-config TMPFS_SECURITY
-	bool "tmpfs Security Labels"
-	depends on TMPFS_XATTR
-	help
-	  Security labels support alternative access control models
-	  implemented by security modules like SELinux.  This option
-	  enables an extended attribute handler for file security
-	  labels in the tmpfs filesystem.
-	  If you are not using a security module that requires using
-	  extended attributes for file security labels, say N.
-
 config HUGETLBFS
 	bool "HugeTLB file system support"
 	depends X86 || IA64 || PPC64 || SPARC64 || SUPERH || X86_64 || BROKEN
diff --git a/fs/aio.c b/fs/aio.c
index 06d7d4390fe..4f641abac3c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -567,6 +567,10 @@ static void use_mm(struct mm_struct *mm)
 	atomic_inc(&mm->mm_count);
 	tsk->mm = mm;
 	tsk->active_mm = mm;
+	/*
+	 * Note that on UML this *requires* PF_BORROWED_MM to be set, otherwise
+	 * it won't work. Update it accordingly if you change it here
+	 */
 	activate_mm(active_mm, mm);
 	task_unlock(tsk);
 
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index c8998dc6688..7974efa107b 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -520,7 +520,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 		DBG_FLT("BINFMT_FLAT: ROM mapping of file (we hope)\n");
 
 		down_write(&current->mm->mmap_sem);
-		textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, MAP_SHARED, 0);
+		textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, MAP_PRIVATE, 0);
 		up_write(&current->mm->mmap_sem);
 		if (!textpos  || textpos >= (unsigned long) -4096) {
 			if (!textpos)
diff --git a/fs/devpts/Makefile b/fs/devpts/Makefile
index 5800df2e50c..236696efcba 100644
--- a/fs/devpts/Makefile
+++ b/fs/devpts/Makefile
@@ -5,4 +5,3 @@
 obj-$(CONFIG_UNIX98_PTYS)		+= devpts.o
 
 devpts-$(CONFIG_UNIX98_PTYS)		:= inode.o
-devpts-$(CONFIG_DEVPTS_FS_SECURITY)	+= xattr_security.o
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 1571c8d6c23..f2be44d4491 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -18,28 +18,9 @@
 #include <linux/mount.h>
 #include <linux/tty.h>
 #include <linux/devpts_fs.h>
-#include <linux/xattr.h>
 
 #define DEVPTS_SUPER_MAGIC 0x1cd1
 
-extern struct xattr_handler devpts_xattr_security_handler;
-
-static struct xattr_handler *devpts_xattr_handlers[] = {
-#ifdef CONFIG_DEVPTS_FS_SECURITY
-	&devpts_xattr_security_handler,
-#endif
-	NULL
-};
-
-static struct inode_operations devpts_file_inode_operations = {
-#ifdef CONFIG_DEVPTS_FS_XATTR
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
-#endif
-};
-
 static struct vfsmount *devpts_mnt;
 static struct dentry *devpts_root;
 
@@ -102,7 +83,6 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
 	s->s_blocksize_bits = 10;
 	s->s_magic = DEVPTS_SUPER_MAGIC;
 	s->s_op = &devpts_sops;
-	s->s_xattr = devpts_xattr_handlers;
 	s->s_time_gran = 1;
 
 	inode = new_inode(s);
@@ -175,7 +155,6 @@ int devpts_pty_new(struct tty_struct *tty)
 	inode->i_gid = config.setgid ? config.gid : current->fsgid;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	init_special_inode(inode, S_IFCHR|config.mode, device);
-	inode->i_op = &devpts_file_inode_operations;
 	inode->u.generic_ip = tty;
 
 	dentry = get_node(number);
diff --git a/fs/devpts/xattr_security.c b/fs/devpts/xattr_security.c
deleted file mode 100644
index 864cb5c79ba..00000000000
--- a/fs/devpts/xattr_security.c
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Security xattr support for devpts.
- *
- * Author: Stephen Smalley <sds@epoch.ncsc.mil>
- * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/security.h>
-#include <linux/xattr.h>
-
-static size_t
-devpts_xattr_security_list(struct inode *inode, char *list, size_t list_len,
-			   const char *name, size_t name_len)
-{
-	return security_inode_listsecurity(inode, list, list_len);
-}
-
-static int
-devpts_xattr_security_get(struct inode *inode, const char *name,
-			  void *buffer, size_t size)
-{
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-	return security_inode_getsecurity(inode, name, buffer, size);
-}
-
-static int
-devpts_xattr_security_set(struct inode *inode, const char *name,
-			  const void *value, size_t size, int flags)
-{
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-	return security_inode_setsecurity(inode, name, value, size, flags);
-}
-
-struct xattr_handler devpts_xattr_security_handler = {
-	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= devpts_xattr_security_list,
-	.get	= devpts_xattr_security_get,
-	.set	= devpts_xattr_security_set,
-};
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 57ed50fe7f8..954cf893d50 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -93,7 +93,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
-	tfm = crypto_alloc_tfm("md5", 0);
+	tfm = crypto_alloc_tfm("md5", CRYPTO_TFM_REQ_MAY_SLEEP);
 	if (tfm == NULL)
 		goto out;
 	cksum.len = crypto_tfm_alg_digestsize(tfm);
@@ -114,8 +114,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 	kfree(cksum.data);
 	status = nfs_ok;
 out:
-	if (tfm)
-		crypto_free_tfm(tfm);
+	crypto_free_tfm(tfm);
 	return status;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 491f2d9f89a..520978e49e9 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -11,6 +11,40 @@
  *  go into icache. We cache the reference to task_struct upon lookup too.
  *  Eventually it should become a filesystem in its own. We don't use the
  *  rest of procfs anymore.
+ *
+ *
+ *  Changelog:
+ *  17-Jan-2005
+ *  Allan Bezerra
+ *  Bruna Moreira <bruna.moreira@indt.org.br>
+ *  Edjard Mota <edjard.mota@indt.org.br>
+ *  Ilias Biris <ilias.biris@indt.org.br>
+ *  Mauricio Lin <mauricio.lin@indt.org.br>
+ *
+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *
+ *  A new process specific entry (smaps) included in /proc. It shows the
+ *  size of rss for each memory area. The maps entry lacks information
+ *  about physical memory size (rss) for each mapped file, i.e.,
+ *  rss information for executables and library files.
+ *  This additional information is useful for any tools that need to know
+ *  about physical memory consumption for a process specific library.
+ *
+ *  Changelog:
+ *  21-Feb-2005
+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *  Pud inclusion in the page table walking.
+ *
+ *  ChangeLog:
+ *  10-Mar-2005
+ *  10LE Instituto Nokia de Tecnologia - INdT:
+ *  A better way to walks through the page table as suggested by Hugh Dickins.
+ *
+ *  Simo Piiroinen <simo.piiroinen@nokia.com>:
+ *  Smaps information related to shared, private, clean and dirty pages.
+ *
+ *  Paul Mundt <paul.mundt@nokia.com>:
+ *  Overall revision about smaps.
  */
 
 #include <asm/uaccess.h>
@@ -65,8 +99,10 @@ enum pid_directory_inos {
 	PROC_TGID_STAT,
 	PROC_TGID_STATM,
 	PROC_TGID_MAPS,
+	PROC_TGID_NUMA_MAPS,
 	PROC_TGID_MOUNTS,
 	PROC_TGID_WCHAN,
+	PROC_TGID_SMAPS,
 #ifdef CONFIG_SCHEDSTATS
 	PROC_TGID_SCHEDSTAT,
 #endif
@@ -102,8 +138,10 @@ enum pid_directory_inos {
 	PROC_TID_STAT,
 	PROC_TID_STATM,
 	PROC_TID_MAPS,
+	PROC_TID_NUMA_MAPS,
 	PROC_TID_MOUNTS,
 	PROC_TID_WCHAN,
+	PROC_TID_SMAPS,
 #ifdef CONFIG_SCHEDSTATS
 	PROC_TID_SCHEDSTAT,
 #endif
@@ -144,6 +182,9 @@ static struct pid_entry tgid_base_stuff[] = {
 	E(PROC_TGID_STAT,      "stat",    S_IFREG|S_IRUGO),
 	E(PROC_TGID_STATM,     "statm",   S_IFREG|S_IRUGO),
 	E(PROC_TGID_MAPS,      "maps",    S_IFREG|S_IRUGO),
+#ifdef CONFIG_NUMA
+	E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO),
+#endif
 	E(PROC_TGID_MEM,       "mem",     S_IFREG|S_IRUSR|S_IWUSR),
 #ifdef CONFIG_SECCOMP
 	E(PROC_TGID_SECCOMP,   "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
@@ -152,6 +193,7 @@ static struct pid_entry tgid_base_stuff[] = {
 	E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
 	E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
 	E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
+	E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUGO),
 #ifdef CONFIG_SECURITY
 	E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -180,6 +222,9 @@ static struct pid_entry tid_base_stuff[] = {
 	E(PROC_TID_STAT,       "stat",    S_IFREG|S_IRUGO),
 	E(PROC_TID_STATM,      "statm",   S_IFREG|S_IRUGO),
 	E(PROC_TID_MAPS,       "maps",    S_IFREG|S_IRUGO),
+#ifdef CONFIG_NUMA
+	E(PROC_TID_NUMA_MAPS,  "numa_maps",    S_IFREG|S_IRUGO),
+#endif
 	E(PROC_TID_MEM,        "mem",     S_IFREG|S_IRUSR|S_IWUSR),
 #ifdef CONFIG_SECCOMP
 	E(PROC_TID_SECCOMP,    "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
@@ -188,6 +233,7 @@ static struct pid_entry tid_base_stuff[] = {
 	E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
 	E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
 	E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
+	E(PROC_TID_SMAPS,      "smaps",   S_IFREG|S_IRUGO),
 #ifdef CONFIG_SECURITY
 	E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -515,6 +561,46 @@ static struct file_operations proc_maps_operations = {
 	.release	= seq_release,
 };
 
+#ifdef CONFIG_NUMA
+extern struct seq_operations proc_pid_numa_maps_op;
+static int numa_maps_open(struct inode *inode, struct file *file)
+{
+	struct task_struct *task = proc_task(inode);
+	int ret = seq_open(file, &proc_pid_numa_maps_op);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = task;
+	}
+	return ret;
+}
+
+static struct file_operations proc_numa_maps_operations = {
+	.open		= numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
+extern struct seq_operations proc_pid_smaps_op;
+static int smaps_open(struct inode *inode, struct file *file)
+{
+	struct task_struct *task = proc_task(inode);
+	int ret = seq_open(file, &proc_pid_smaps_op);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = task;
+	}
+	return ret;
+}
+
+static struct file_operations proc_smaps_operations = {
+	.open		= smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 extern struct seq_operations mounts_op;
 static int mounts_open(struct inode *inode, struct file *file)
 {
@@ -1524,6 +1610,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 		case PROC_TGID_MAPS:
 			inode->i_fop = &proc_maps_operations;
 			break;
+#ifdef CONFIG_NUMA
+		case PROC_TID_NUMA_MAPS:
+		case PROC_TGID_NUMA_MAPS:
+			inode->i_fop = &proc_numa_maps_operations;
+			break;
+#endif
 		case PROC_TID_MEM:
 		case PROC_TGID_MEM:
 			inode->i_op = &proc_mem_inode_operations;
@@ -1539,6 +1631,10 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 		case PROC_TGID_MOUNTS:
 			inode->i_fop = &proc_mounts_operations;
 			break;
+		case PROC_TID_SMAPS:
+		case PROC_TGID_SMAPS:
+			inode->i_fop = &proc_smaps_operations;
+			break;
 #ifdef CONFIG_SECURITY
 		case PROC_TID_ATTR:
 			inode->i_nlink = 2;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 28b4a0253a9..c7ef3e48e35 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2,8 +2,13 @@
 #include <linux/hugetlb.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/mempolicy.h>
+
 #include <asm/elf.h>
 #include <asm/uaccess.h>
+#include <asm/tlbflush.h>
 #include "internal.h"
 
 char *task_mem(struct mm_struct *mm, char *buffer)
@@ -87,49 +92,58 @@ static void pad_len_spaces(struct seq_file *m, int len)
 	seq_printf(m, "%*c", len, ' ');
 }
 
-static int show_map(struct seq_file *m, void *v)
+struct mem_size_stats
+{
+	unsigned long resident;
+	unsigned long shared_clean;
+	unsigned long shared_dirty;
+	unsigned long private_clean;
+	unsigned long private_dirty;
+};
+
+static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
 {
 	struct task_struct *task = m->private;
-	struct vm_area_struct *map = v;
-	struct mm_struct *mm = map->vm_mm;
-	struct file *file = map->vm_file;
-	int flags = map->vm_flags;
+	struct vm_area_struct *vma = v;
+	struct mm_struct *mm = vma->vm_mm;
+	struct file *file = vma->vm_file;
+	int flags = vma->vm_flags;
 	unsigned long ino = 0;
 	dev_t dev = 0;
 	int len;
 
 	if (file) {
-		struct inode *inode = map->vm_file->f_dentry->d_inode;
+		struct inode *inode = vma->vm_file->f_dentry->d_inode;
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 	}
 
 	seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n",
-			map->vm_start,
-			map->vm_end,
+			vma->vm_start,
+			vma->vm_end,
 			flags & VM_READ ? 'r' : '-',
 			flags & VM_WRITE ? 'w' : '-',
 			flags & VM_EXEC ? 'x' : '-',
 			flags & VM_MAYSHARE ? 's' : 'p',
-			map->vm_pgoff << PAGE_SHIFT,
+			vma->vm_pgoff << PAGE_SHIFT,
 			MAJOR(dev), MINOR(dev), ino, &len);
 
 	/*
 	 * Print the dentry name for named mappings, and a
 	 * special [heap] marker for the heap:
 	 */
-	if (map->vm_file) {
+	if (file) {
 		pad_len_spaces(m, len);
-		seq_path(m, file->f_vfsmnt, file->f_dentry, "");
+		seq_path(m, file->f_vfsmnt, file->f_dentry, "\n");
 	} else {
 		if (mm) {
-			if (map->vm_start <= mm->start_brk &&
-						map->vm_end >= mm->brk) {
+			if (vma->vm_start <= mm->start_brk &&
+						vma->vm_end >= mm->brk) {
 				pad_len_spaces(m, len);
 				seq_puts(m, "[heap]");
 			} else {
-				if (map->vm_start <= mm->start_stack &&
-					map->vm_end >= mm->start_stack) {
+				if (vma->vm_start <= mm->start_stack &&
+					vma->vm_end >= mm->start_stack) {
 
 					pad_len_spaces(m, len);
 					seq_puts(m, "[stack]");
@@ -141,24 +155,146 @@ static int show_map(struct seq_file *m, void *v)
 		}
 	}
 	seq_putc(m, '\n');
-	if (m->count < m->size)  /* map is copied successfully */
-		m->version = (map != get_gate_vma(task))? map->vm_start: 0;
+
+	if (mss)
+		seq_printf(m,
+			   "Size:          %8lu kB\n"
+			   "Rss:           %8lu kB\n"
+			   "Shared_Clean:  %8lu kB\n"
+			   "Shared_Dirty:  %8lu kB\n"
+			   "Private_Clean: %8lu kB\n"
+			   "Private_Dirty: %8lu kB\n",
+			   (vma->vm_end - vma->vm_start) >> 10,
+			   mss->resident >> 10,
+			   mss->shared_clean  >> 10,
+			   mss->shared_dirty  >> 10,
+			   mss->private_clean >> 10,
+			   mss->private_dirty >> 10);
+
+	if (m->count < m->size)  /* vma is copied successfully */
+		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
 	return 0;
 }
 
+static int show_map(struct seq_file *m, void *v)
+{
+	return show_map_internal(m, v, 0);
+}
+
+static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pte_t *pte, ptent;
+	unsigned long pfn;
+	struct page *page;
+
+	pte = pte_offset_map(pmd, addr);
+	do {
+		ptent = *pte;
+		if (pte_none(ptent) || !pte_present(ptent))
+			continue;
+
+		mss->resident += PAGE_SIZE;
+		pfn = pte_pfn(ptent);
+		if (!pfn_valid(pfn))
+			continue;
+
+		page = pfn_to_page(pfn);
+		if (page_count(page) >= 2) {
+			if (pte_dirty(ptent))
+				mss->shared_dirty += PAGE_SIZE;
+			else
+				mss->shared_clean += PAGE_SIZE;
+		} else {
+			if (pte_dirty(ptent))
+				mss->private_dirty += PAGE_SIZE;
+			else
+				mss->private_clean += PAGE_SIZE;
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap(pte - 1);
+	cond_resched_lock(&vma->vm_mm->page_table_lock);
+}
+
+static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none_or_clear_bad(pmd))
+			continue;
+		smaps_pte_range(vma, pmd, addr, next, mss);
+	} while (pmd++, addr = next, addr != end);
+}
+
+static inline void smaps_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		smaps_pmd_range(vma, pud, addr, next, mss);
+	} while (pud++, addr = next, addr != end);
+}
+
+static inline void smaps_pgd_range(struct vm_area_struct *vma,
+				unsigned long addr, unsigned long end,
+				struct mem_size_stats *mss)
+{
+	pgd_t *pgd;
+	unsigned long next;
+
+	pgd = pgd_offset(vma->vm_mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		smaps_pud_range(vma, pgd, addr, next, mss);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static int show_smap(struct seq_file *m, void *v)
+{
+	struct vm_area_struct *vma = v;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mem_size_stats mss;
+
+	memset(&mss, 0, sizeof mss);
+
+	if (mm) {
+		spin_lock(&mm->page_table_lock);
+		smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
+		spin_unlock(&mm->page_table_lock);
+	}
+
+	return show_map_internal(m, v, &mss);
+}
+
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct task_struct *task = m->private;
 	unsigned long last_addr = m->version;
 	struct mm_struct *mm;
-	struct vm_area_struct *map, *tail_map;
+	struct vm_area_struct *vma, *tail_vma;
 	loff_t l = *pos;
 
 	/*
 	 * We remember last_addr rather than next_addr to hit with
 	 * mmap_cache most of the time. We have zero last_addr at
-	 * the begining and also after lseek. We will have -1 last_addr
-	 * after the end of the maps.
+	 * the beginning and also after lseek. We will have -1 last_addr
+	 * after the end of the vmas.
 	 */
 
 	if (last_addr == -1UL)
@@ -168,47 +304,47 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	if (!mm)
 		return NULL;
 
-	tail_map = get_gate_vma(task);
+	tail_vma = get_gate_vma(task);
 	down_read(&mm->mmap_sem);
 
 	/* Start with last addr hint */
-	if (last_addr && (map = find_vma(mm, last_addr))) {
-		map = map->vm_next;
+	if (last_addr && (vma = find_vma(mm, last_addr))) {
+		vma = vma->vm_next;
 		goto out;
 	}
 
 	/*
-	 * Check the map index is within the range and do
+	 * Check the vma index is within the range and do
 	 * sequential scan until m_index.
 	 */
-	map = NULL;
+	vma = NULL;
 	if ((unsigned long)l < mm->map_count) {
-		map = mm->mmap;
-		while (l-- && map)
-			map = map->vm_next;
+		vma = mm->mmap;
+		while (l-- && vma)
+			vma = vma->vm_next;
 		goto out;
 	}
 
 	if (l != mm->map_count)
-		tail_map = NULL; /* After gate map */
+		tail_vma = NULL; /* After gate vma */
 
 out:
-	if (map)
-		return map;
+	if (vma)
+		return vma;
 
-	/* End of maps has reached */
-	m->version = (tail_map != NULL)? 0: -1UL;
+	/* End of vmas has been reached */
+	m->version = (tail_vma != NULL)? 0: -1UL;
 	up_read(&mm->mmap_sem);
 	mmput(mm);
-	return tail_map;
+	return tail_vma;
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
 	struct task_struct *task = m->private;
-	struct vm_area_struct *map = v;
-	if (map && map != get_gate_vma(task)) {
-		struct mm_struct *mm = map->vm_mm;
+	struct vm_area_struct *vma = v;
+	if (vma && vma != get_gate_vma(task)) {
+		struct mm_struct *mm = vma->vm_mm;
 		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
@@ -217,14 +353,14 @@ static void m_stop(struct seq_file *m, void *v)
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct task_struct *task = m->private;
-	struct vm_area_struct *map = v;
-	struct vm_area_struct *tail_map = get_gate_vma(task);
+	struct vm_area_struct *vma = v;
+	struct vm_area_struct *tail_vma = get_gate_vma(task);
 
 	(*pos)++;
-	if (map && (map != tail_map) && map->vm_next)
-		return map->vm_next;
+	if (vma && (vma != tail_vma) && vma->vm_next)
+		return vma->vm_next;
 	m_stop(m, v);
-	return (map != tail_map)? tail_map: NULL;
+	return (vma != tail_vma)? tail_vma: NULL;
 }
 
 struct seq_operations proc_pid_maps_op = {
@@ -233,3 +369,140 @@ struct seq_operations proc_pid_maps_op = {
 	.stop	= m_stop,
 	.show	= show_map
 };
+
+struct seq_operations proc_pid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_smap
+};
+
+#ifdef CONFIG_NUMA
+
+struct numa_maps {
+	unsigned long pages;
+	unsigned long anon;
+	unsigned long mapped;
+	unsigned long mapcount_max;
+	unsigned long node[MAX_NUMNODES];
+};
+
+/*
+ * Calculate numa node maps for a vma
+ */
+static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
+{
+	struct page *page;
+	unsigned long vaddr;
+	struct mm_struct *mm = vma->vm_mm;
+	int i;
+	struct numa_maps *md = kmalloc(sizeof(struct numa_maps), GFP_KERNEL);
+
+	if (!md)
+		return NULL;
+	md->pages = 0;
+	md->anon = 0;
+	md->mapped = 0;
+	md->mapcount_max = 0;
+	for_each_node(i)
+		md->node[i] =0;
+
+	spin_lock(&mm->page_table_lock);
+ 	for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
+		page = follow_page(mm, vaddr, 0);
+		if (page) {
+			int count = page_mapcount(page);
+
+			if (count)
+				md->mapped++;
+			if (count > md->mapcount_max)
+				md->mapcount_max = count;
+			md->pages++;
+			if (PageAnon(page))
+				md->anon++;
+			md->node[page_to_nid(page)]++;
+		}
+	}
+	spin_unlock(&mm->page_table_lock);
+	return md;
+}
+
+static int show_numa_map(struct seq_file *m, void *v)
+{
+	struct task_struct *task = m->private;
+	struct vm_area_struct *vma = v;
+	struct mempolicy *pol;
+	struct numa_maps *md;
+	struct zone **z;
+	int n;
+	int first;
+
+	if (!vma->vm_mm)
+		return 0;
+
+	md = get_numa_maps(vma);
+	if (!md)
+		return 0;
+
+	seq_printf(m, "%08lx", vma->vm_start);
+	pol = get_vma_policy(task, vma, vma->vm_start);
+	/* Print policy */
+	switch (pol->policy) {
+	case MPOL_PREFERRED:
+		seq_printf(m, " prefer=%d", pol->v.preferred_node);
+		break;
+	case MPOL_BIND:
+		seq_printf(m, " bind={");
+		first = 1;
+		for (z = pol->v.zonelist->zones; *z; z++) {
+
+			if (!first)
+				seq_putc(m, ',');
+			else
+				first = 0;
+			seq_printf(m, "%d/%s", (*z)->zone_pgdat->node_id,
+					(*z)->name);
+		}
+		seq_putc(m, '}');
+		break;
+	case MPOL_INTERLEAVE:
+		seq_printf(m, " interleave={");
+		first = 1;
+		for_each_node(n) {
+			if (test_bit(n, pol->v.nodes)) {
+				if (!first)
+					seq_putc(m,',');
+				else
+					first = 0;
+				seq_printf(m, "%d",n);
+			}
+		}
+		seq_putc(m, '}');
+		break;
+	default:
+		seq_printf(m," default");
+		break;
+	}
+	seq_printf(m, " MaxRef=%lu Pages=%lu Mapped=%lu",
+			md->mapcount_max, md->pages, md->mapped);
+	if (md->anon)
+		seq_printf(m," Anon=%lu",md->anon);
+
+	for_each_online_node(n) {
+		if (md->node[n])
+			seq_printf(m, " N%d=%lu", n, md->node[n]);
+	}
+	seq_putc(m, '\n');
+	kfree(md);
+	if (m->count < m->size)  /* vma is copied successfully */
+		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+	return 0;
+}
+
+struct seq_operations proc_pid_numa_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_numa_map
+};
+#endif
diff --git a/fs/xattr.c b/fs/xattr.c
index 6acd5c63da9..dc8bc7624f2 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -51,20 +51,29 @@ setxattr(struct dentry *d, char __user *name, void __user *value,
 		}
 	}
 
+	down(&d->d_inode->i_sem);
+	error = security_inode_setxattr(d, kname, kvalue, size, flags);
+	if (error)
+		goto out;
 	error = -EOPNOTSUPP;
 	if (d->d_inode->i_op && d->d_inode->i_op->setxattr) {
-		down(&d->d_inode->i_sem);
-		error = security_inode_setxattr(d, kname, kvalue, size, flags);
-		if (error)
-			goto out;
-		error = d->d_inode->i_op->setxattr(d, kname, kvalue, size, flags);
+		error = d->d_inode->i_op->setxattr(d, kname, kvalue,
+						   size, flags);
 		if (!error) {
 			fsnotify_xattr(d);
-			security_inode_post_setxattr(d, kname, kvalue, size, flags);
+			security_inode_post_setxattr(d, kname, kvalue,
+						     size, flags);
 		}
-out:
-		up(&d->d_inode->i_sem);
+	} else if (!strncmp(kname, XATTR_SECURITY_PREFIX,
+			    sizeof XATTR_SECURITY_PREFIX - 1)) {
+		const char *suffix = kname + sizeof XATTR_SECURITY_PREFIX - 1;
+		error = security_inode_setsecurity(d->d_inode, suffix, kvalue,
+						   size, flags);
+		if (!error)
+			fsnotify_xattr(d);
 	}
+out:
+	up(&d->d_inode->i_sem);
 	if (kvalue)
 		kfree(kvalue);
 	return error;
@@ -139,20 +148,25 @@ getxattr(struct dentry *d, char __user *name, void __user *value, size_t size)
 			return -ENOMEM;
 	}
 
+	error = security_inode_getxattr(d, kname);
+	if (error)
+		goto out;
 	error = -EOPNOTSUPP;
-	if (d->d_inode->i_op && d->d_inode->i_op->getxattr) {
-		error = security_inode_getxattr(d, kname);
-		if (error)
-			goto out;
+	if (d->d_inode->i_op && d->d_inode->i_op->getxattr)
 		error = d->d_inode->i_op->getxattr(d, kname, kvalue, size);
-		if (error > 0) {
-			if (size && copy_to_user(value, kvalue, error))
-				error = -EFAULT;
-		} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
-			/* The file system tried to returned a value bigger
-			   than XATTR_SIZE_MAX bytes. Not possible. */
-			error = -E2BIG;
-		}
+	else if (!strncmp(kname, XATTR_SECURITY_PREFIX,
+			  sizeof XATTR_SECURITY_PREFIX - 1)) {
+		const char *suffix = kname + sizeof XATTR_SECURITY_PREFIX - 1;
+		error = security_inode_getsecurity(d->d_inode, suffix, kvalue,
+						   size);
+	}
+	if (error > 0) {
+		if (size && copy_to_user(value, kvalue, error))
+			error = -EFAULT;
+	} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
+		/* The file system tried to returned a value bigger
+		   than XATTR_SIZE_MAX bytes. Not possible. */
+		error = -E2BIG;
 	}
 out:
 	if (kvalue)
@@ -221,20 +235,24 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 			return -ENOMEM;
 	}
 
+	error = security_inode_listxattr(d);
+	if (error)
+		goto out;
 	error = -EOPNOTSUPP;
 	if (d->d_inode->i_op && d->d_inode->i_op->listxattr) {
-		error = security_inode_listxattr(d);
-		if (error)
-			goto out;
 		error = d->d_inode->i_op->listxattr(d, klist, size);
-		if (error > 0) {
-			if (size && copy_to_user(list, klist, error))
-				error = -EFAULT;
-		} else if (error == -ERANGE && size >= XATTR_LIST_MAX) {
-			/* The file system tried to returned a list bigger
-			   than XATTR_LIST_MAX bytes. Not possible. */
-			error = -E2BIG;
-		}
+	} else {
+		error = security_inode_listsecurity(d->d_inode, klist, size);
+		if (size && error >= size)
+			error = -ERANGE;
+	}
+	if (error > 0) {
+		if (size && copy_to_user(list, klist, error))
+			error = -EFAULT;
+	} else if (error == -ERANGE && size >= XATTR_LIST_MAX) {
+		/* The file system tried to returned a list bigger
+		   than XATTR_LIST_MAX bytes. Not possible. */
+		error = -E2BIG;
 	}
 out:
 	if (klist)