aboutsummaryrefslogtreecommitdiffstats
path: root/scripts/kernel-doc
diff options
context:
space:
mode:
Diffstat (limited to 'scripts/kernel-doc')
-rwxr-xr-xscripts/kernel-doc41
1 files changed, 32 insertions, 9 deletions
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 1f5835115cad..1d1401807e95 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -5,6 +5,7 @@ use strict;
5## Copyright (c) 1998 Michael Zucchi, All Rights Reserved ## 5## Copyright (c) 1998 Michael Zucchi, All Rights Reserved ##
6## Copyright (C) 2000, 1 Tim Waugh <twaugh@redhat.com> ## 6## Copyright (C) 2000, 1 Tim Waugh <twaugh@redhat.com> ##
7## Copyright (C) 2001 Simon Huggins ## 7## Copyright (C) 2001 Simon Huggins ##
8## Copyright (C) 2005-2007 Randy Dunlap ##
8## ## 9## ##
9## #define enhancements by Armin Kuster <akuster@mvista.com> ## 10## #define enhancements by Armin Kuster <akuster@mvista.com> ##
10## Copyright (c) 2000 MontaVista Software, Inc. ## 11## Copyright (c) 2000 MontaVista Software, Inc. ##
@@ -161,7 +162,7 @@ my $type_constant = '\%([-_\w]+)';
161my $type_func = '(\w+)\(\)'; 162my $type_func = '(\w+)\(\)';
162my $type_param = '\@(\w+)'; 163my $type_param = '\@(\w+)';
163my $type_struct = '\&((struct\s*)*[_\w]+)'; 164my $type_struct = '\&((struct\s*)*[_\w]+)';
164my $type_struct_xml = '\\\amp;((struct\s*)*[_\w]+)'; 165my $type_struct_xml = '\\&amp;((struct\s*)*[_\w]+)';
165my $type_env = '(\$\w+)'; 166my $type_env = '(\$\w+)';
166 167
167# Output conversion substitutions. 168# Output conversion substitutions.
@@ -173,7 +174,9 @@ my %highlights_html = ( $type_constant, "<i>\$1</i>",
173 $type_struct_xml, "<i>\$1</i>", 174 $type_struct_xml, "<i>\$1</i>",
174 $type_env, "<b><i>\$1</i></b>", 175 $type_env, "<b><i>\$1</i></b>",
175 $type_param, "<tt><b>\$1</b></tt>" ); 176 $type_param, "<tt><b>\$1</b></tt>" );
176my $blankline_html = "<p>"; 177my $local_lt = "\\\\\\\\lt:";
178my $local_gt = "\\\\\\\\gt:";
179my $blankline_html = $local_lt . "p" . $local_gt; # was "<p>"
177 180
178# XML, docbook format 181# XML, docbook format
179my %highlights_xml = ( "([^=])\\\"([^\\\"<]+)\\\"", "\$1<quote>\$2</quote>", 182my %highlights_xml = ( "([^=])\\\"([^\\\"<]+)\\\"", "\$1<quote>\$2</quote>",
@@ -391,17 +394,19 @@ sub output_highlight {
391# confess "output_highlight got called with no args?\n"; 394# confess "output_highlight got called with no args?\n";
392# } 395# }
393 396
397 if ($output_mode eq "html") {
398 $contents = local_unescape($contents);
399 # convert data read & converted thru xml_escape() into &xyz; format:
400 $contents =~ s/\\\\\\/&/g;
401 }
394# print STDERR "contents b4:$contents\n"; 402# print STDERR "contents b4:$contents\n";
395 eval $dohighlight; 403 eval $dohighlight;
396 die $@ if $@; 404 die $@ if $@;
397 if ($output_mode eq "html") {
398 $contents =~ s/\\\\//;
399 }
400# print STDERR "contents af:$contents\n"; 405# print STDERR "contents af:$contents\n";
401 406
402 foreach $line (split "\n", $contents) { 407 foreach $line (split "\n", $contents) {
403 if ($line eq ""){ 408 if ($line eq ""){
404 print $lineprefix, $blankline; 409 print $lineprefix, local_unescape($blankline);
405 } else { 410 } else {
406 $line =~ s/\\\\\\/\&/g; 411 $line =~ s/\\\\\\/\&/g;
407 if ($output_mode eq "man" && substr($line, 0, 1) eq ".") { 412 if ($output_mode eq "man" && substr($line, 0, 1) eq ".") {
@@ -1752,7 +1757,13 @@ sub process_state3_type($$) {
1752 } 1757 }
1753} 1758}
1754 1759
1755# replace <, >, and & 1760# xml_escape: replace <, >, and & in the text stream;
1761#
1762# however, formatting controls that are generated internally/locally in the
1763# kernel-doc script are not escaped here; instead, they begin life like
1764# $blankline_html (4 of '\' followed by a mnemonic + ':'), then these strings
1765# are converted to their mnemonic-expected output, without the 4 * '\' & ':',
1766# just before actual output; (this is done by local_unescape())
1756sub xml_escape($) { 1767sub xml_escape($) {
1757 my $text = shift; 1768 my $text = shift;
1758 if (($output_mode eq "text") || ($output_mode eq "man")) { 1769 if (($output_mode eq "text") || ($output_mode eq "man")) {
@@ -1764,6 +1775,18 @@ sub xml_escape($) {
1764 return $text; 1775 return $text;
1765} 1776}
1766 1777
1778# convert local escape strings to html
1779# local escape strings look like: '\\\\menmonic:' (that's 4 backslashes)
1780sub local_unescape($) {
1781 my $text = shift;
1782 if (($output_mode eq "text") || ($output_mode eq "man")) {
1783 return $text;
1784 }
1785 $text =~ s/\\\\\\\\lt:/</g;
1786 $text =~ s/\\\\\\\\gt:/>/g;
1787 return $text;
1788}
1789
1767sub process_file($) { 1790sub process_file($) {
1768 my $file; 1791 my $file;
1769 my $identifier; 1792 my $identifier;
@@ -1903,7 +1926,7 @@ sub process_file($) {
1903 } elsif ($state == 4) { 1926 } elsif ($state == 4) {
1904 # Documentation block 1927 # Documentation block
1905 if (/$doc_block/) { 1928 if (/$doc_block/) {
1906 dump_section($section, $contents); 1929 dump_section($section, xml_escape($contents));
1907 output_intro({'sectionlist' => \@sectionlist, 1930 output_intro({'sectionlist' => \@sectionlist,
1908 'sections' => \%sections }); 1931 'sections' => \%sections });
1909 $contents = ""; 1932 $contents = "";
@@ -1923,7 +1946,7 @@ sub process_file($) {
1923 } 1946 }
1924 elsif (/$doc_end/) 1947 elsif (/$doc_end/)
1925 { 1948 {
1926 dump_section($section, $contents); 1949 dump_section($section, xml_escape($contents));
1927 output_intro({'sectionlist' => \@sectionlist, 1950 output_intro({'sectionlist' => \@sectionlist,
1928 'sections' => \%sections }); 1951 'sections' => \%sections });
1929 $contents = ""; 1952 $contents = "";
href='#n1085'>1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462
/*
 * POSIX message queues filesystem for Linux.
 *
 * Copyright (C) 2003,2004  Krzysztof Benedyczak    (golbi@mat.uni.torun.pl)
 *                          Michal Wronski          (michal.wronski@gmail.com)
 *
 * Spinlocks:               Mohamed Abbas           (abbas.mohamed@intel.com)
 * Lockless receive & send, fd based notify:
 *			    Manfred Spraul	    (manfred@colorfullife.com)
 *
 * Audit:                   George Wilson           (ltcgcw@us.ibm.com)
 *
 * This file is released under the GPL.
 */

#include <linux/capability.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/mqueue.h>
#include <linux/msg.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/netlink.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/signal.h>
#include <linux/mutex.h>
#include <linux/nsproxy.h>
#include <linux/pid.h>
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>

#include <net/sock.h>
#include "util.h"

#define MQUEUE_MAGIC	0x19800202
#define DIRENT_SIZE	20
#define FILENT_SIZE	80

#define SEND		0
#define RECV		1

#define STATE_NONE	0
#define STATE_PENDING	1
#define STATE_READY	2

struct posix_msg_tree_node {
	struct rb_node		rb_node;
	struct list_head	msg_list;
	int			priority;
};

struct ext_wait_queue {		/* queue of sleeping tasks */
	struct task_struct *task;
	struct list_head list;
	struct msg_msg *msg;	/* ptr of loaded message */
	int state;		/* one of STATE_* values */
};

struct mqueue_inode_info {
	spinlock_t lock;
	struct inode vfs_inode;
	wait_queue_head_t wait_q;

	struct rb_root msg_tree;
	struct posix_msg_tree_node *node_cache;
	struct mq_attr attr;

	struct sigevent notify;
	struct pid *notify_owner;
	struct user_namespace *notify_user_ns;
	struct user_struct *user;	/* user who created, for accounting */
	struct sock *notify_sock;
	struct sk_buff *notify_cookie;

	/* for tasks waiting for free space and messages, respectively */
	struct ext_wait_queue e_wait_q[2];

	unsigned long qsize; /* size of queue in memory (sum of all msgs) */
};

static const struct inode_operations mqueue_dir_inode_operations;
static const struct file_operations mqueue_file_operations;
static const struct super_operations mqueue_super_ops;
static void remove_notification(struct mqueue_inode_info *info);

static struct kmem_cache *mqueue_inode_cachep;

static struct ctl_table_header *mq_sysctl_table;

static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
{
	return container_of(inode, struct mqueue_inode_info, vfs_inode);
}

/*
 * This routine should be called with the mq_lock held.
 */
static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode)
{
	return get_ipc_ns(inode->i_sb->s_fs_info);
}

static struct ipc_namespace *get_ns_from_inode(struct inode *inode)
{
	struct ipc_namespace *ns;

	spin_lock(&mq_lock);
	ns = __get_ns_from_inode(inode);
	spin_unlock(&mq_lock);
	return ns;
}

/* Auxiliary functions to manipulate messages' list */
static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
{
	struct rb_node **p, *parent = NULL;
	struct posix_msg_tree_node *leaf;

	p = &info->msg_tree.rb_node;
	while (*p) {
		parent = *p;
		leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);

		if (likely(leaf->priority == msg->m_type))
			goto insert_msg;
		else if (msg->m_type < leaf->priority)
			p = &(*p)->rb_left;
		else
			p = &(*p)->rb_right;
	}
	if (info->node_cache) {
		leaf = info->node_cache;
		info->node_cache = NULL;
	} else {
		leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC);
		if (!leaf)
			return -ENOMEM;
		INIT_LIST_HEAD(&leaf->msg_list);
		info->qsize += sizeof(*leaf);
	}
	leaf->priority = msg->m_type;
	rb_link_node(&leaf->rb_node, parent, p);
	rb_insert_color(&leaf->rb_node, &info->msg_tree);
insert_msg:
	info->attr.mq_curmsgs++;
	info->qsize += msg->m_ts;
	list_add_tail(&msg->m_list, &leaf->msg_list);
	return 0;
}

static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
{
	struct rb_node **p, *parent = NULL;
	struct posix_msg_tree_node *leaf;
	struct msg_msg *msg;

try_again:
	p = &info->msg_tree.rb_node;
	while (*p) {
		parent = *p;
		/*
		 * During insert, low priorities go to the left and high to the
		 * right.  On receive, we want the highest priorities first, so
		 * walk all the way to the right.
		 */
		p = &(*p)->rb_right;
	}
	if (!parent) {
		if (info->attr.mq_curmsgs) {
			pr_warn_once("Inconsistency in POSIX message queue, "
				     "no tree element, but supposedly messages "
				     "should exist!\n");
			info->attr.mq_curmsgs = 0;
		}
		return NULL;
	}
	leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);
	if (unlikely(list_empty(&leaf->msg_list))) {
		pr_warn_once("Inconsistency in POSIX message queue, "
			     "empty leaf node but we haven't implemented "
			     "lazy leaf delete!\n");
		rb_erase(&leaf->rb_node, &info->msg_tree);
		if (info->node_cache) {
			info->qsize -= sizeof(*leaf);
			kfree(leaf);
		} else {
			info->node_cache = leaf;
		}
		goto try_again;
	} else {
		msg = list_first_entry(&leaf->msg_list,
				       struct msg_msg, m_list);
		list_del(&msg->m_list);
		if (list_empty(&leaf->msg_list)) {
			rb_erase(&leaf->rb_node, &info->msg_tree);
			if (info->node_cache) {
				info->qsize -= sizeof(*leaf);
				kfree(leaf);
			} else {
				info->node_cache = leaf;
			}
		}
	}
	info->attr.mq_curmsgs--;
	info->qsize -= msg->m_ts;
	return msg;
}

static struct inode *mqueue_get_inode(struct super_block *sb,
		struct ipc_namespace *ipc_ns, umode_t mode,
		struct mq_attr *attr)
{
	struct user_struct *u = current_user();
	struct inode *inode;
	int ret = -ENOMEM;

	inode = new_inode(sb);
	if (!inode)
		goto err;

	inode->i_ino = get_next_ino();
	inode->i_mode = mode;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_mtime = inode->i_ctime = inode->i_atime = CURRENT_TIME;

	if (S_ISREG(mode)) {
		struct mqueue_inode_info *info;
		unsigned long mq_bytes, mq_treesize;

		inode->i_fop = &mqueue_file_operations;
		inode->i_size = FILENT_SIZE;
		/* mqueue specific info */
		info = MQUEUE_I(inode);
		spin_lock_init(&info->lock);
		init_waitqueue_head(&info->wait_q);
		INIT_LIST_HEAD(&info->e_wait_q[0].list);
		INIT_LIST_HEAD(&info->e_wait_q[1].list);
		info->notify_owner = NULL;
		info->notify_user_ns = NULL;
		info->qsize = 0;
		info->user = NULL;	/* set when all is ok */
		info->msg_tree = RB_ROOT;
		info->node_cache = NULL;
		memset(&info->attr, 0, sizeof(info->attr));
		info->attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
					   ipc_ns->mq_msg_default);
		info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
					    ipc_ns->mq_msgsize_default);
		if (attr) {
			info->attr.mq_maxmsg = attr->mq_maxmsg;
			info->attr.mq_msgsize = attr->mq_msgsize;
		}
		/*
		 * We used to allocate a static array of pointers and account
		 * the size of that array as well as one msg_msg struct per
		 * possible message into the queue size. That's no longer
		 * accurate as the queue is now an rbtree and will grow and
		 * shrink depending on usage patterns.  We can, however, still
		 * account one msg_msg struct per message, but the nodes are
		 * allocated depending on priority usage, and most programs
		 * only use one, or a handful, of priorities.  However, since
		 * this is pinned memory, we need to assume worst case, so
		 * that means the min(mq_maxmsg, max_priorities) * struct
		 * posix_msg_tree_node.
		 */
		mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
			min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
			sizeof(struct posix_msg_tree_node);

		mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
					  info->attr.mq_msgsize);

		spin_lock(&mq_lock);
		if (u->mq_bytes + mq_bytes < u->mq_bytes ||
		    u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) {
			spin_unlock(&mq_lock);
			/* mqueue_evict_inode() releases info->messages */
			ret = -EMFILE;
			goto out_inode;
		}
		u->mq_bytes += mq_bytes;
		spin_unlock(&mq_lock);

		/* all is ok */
		info->user = get_uid(u);
	} else if (S_ISDIR(mode)) {
		inc_nlink(inode);
		/* Some things misbehave if size == 0 on a directory */
		inode->i_size = 2 * DIRENT_SIZE;
		inode->i_op = &mqueue_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;
	}

	return inode;
out_inode:
	iput(inode);
err:
	return ERR_PTR(ret);
}

static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode *inode;
	struct ipc_namespace *ns = data;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = MQUEUE_MAGIC;
	sb->s_op = &mqueue_super_ops;

	inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	sb->s_root = d_make_root(inode);
	if (!sb->s_root)
		return -ENOMEM;
	return 0;
}

static struct dentry *mqueue_mount(struct file_system_type *fs_type,
			 int flags, const char *dev_name,
			 void *data)
{
	if (!(flags & MS_KERNMOUNT)) {
		struct ipc_namespace *ns = current->nsproxy->ipc_ns;
		/* Don't allow mounting unless the caller has CAP_SYS_ADMIN
		 * over the ipc namespace.
		 */
		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
			return ERR_PTR(-EPERM);

		data = ns;
	}
	return mount_ns(fs_type, flags, data, mqueue_fill_super);
}

static void init_once(void *foo)
{
	struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;

	inode_init_once(&p->vfs_inode);
}

static struct inode *mqueue_alloc_inode(struct super_block *sb)
{
	struct mqueue_inode_info *ei;

	ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void mqueue_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
}

static void mqueue_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, mqueue_i_callback);
}

static void mqueue_evict_inode(struct inode *inode)
{
	struct mqueue_inode_info *info;
	struct user_struct *user;
	unsigned long mq_bytes, mq_treesize;
	struct ipc_namespace *ipc_ns;
	struct msg_msg *msg;

	clear_inode(inode);

	if (S_ISDIR(inode->i_mode))
		return;

	ipc_ns = get_ns_from_inode(inode);
	info = MQUEUE_I(inode);
	spin_lock(&info->lock);
	while ((msg = msg_get(info)) != NULL)
		free_msg(msg);
	kfree(info->node_cache);
	spin_unlock(&info->lock);

	/* Total amount of bytes accounted for the mqueue */
	mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
		min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
		sizeof(struct posix_msg_tree_node);

	mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
				  info->attr.mq_msgsize);

	user = info->user;
	if (user) {
		spin_lock(&mq_lock);
		user->mq_bytes -= mq_bytes;
		/*
		 * get_ns_from_inode() ensures that the
		 * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
		 * to which we now hold a reference, or it is NULL.
		 * We can't put it here under mq_lock, though.
		 */
		if (ipc_ns)
			ipc_ns->mq_queues_count--;
		spin_unlock(&mq_lock);
		free_uid(user);
	}
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
}

static int mqueue_create(struct inode *dir, struct dentry *dentry,
				umode_t mode, bool excl)
{
	struct inode *inode;
	struct mq_attr *attr = dentry->d_fsdata;
	int error;
	struct ipc_namespace *ipc_ns;

	spin_lock(&mq_lock);
	ipc_ns = __get_ns_from_inode(dir);
	if (!ipc_ns) {
		error = -EACCES;
		goto out_unlock;
	}

	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
	    !capable(CAP_SYS_RESOURCE)) {
		error = -ENOSPC;
		goto out_unlock;
	}
	ipc_ns->mq_queues_count++;
	spin_unlock(&mq_lock);

	inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
	if (IS_ERR(inode)) {
		error = PTR_ERR(inode);
		spin_lock(&mq_lock);
		ipc_ns->mq_queues_count--;
		goto out_unlock;
	}

	put_ipc_ns(ipc_ns);
	dir->i_size += DIRENT_SIZE;
	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;

	d_instantiate(dentry, inode);
	dget(dentry);
	return 0;
out_unlock:
	spin_unlock(&mq_lock);
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
	return error;
}

static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
	dir->i_size -= DIRENT_SIZE;
	drop_nlink(inode);
	dput(dentry);
	return 0;
}

/*
*	This is routine for system read from queue file.
*	To avoid mess with doing here some sort of mq_receive we allow
*	to read only queue size & notification info (the only values
*	that are interesting from user point of view and aren't accessible
*	through std routines)
*/
static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
				size_t count, loff_t *off)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
	char buffer[FILENT_SIZE];
	ssize_t ret;

	spin_lock(&info->lock);
	snprintf(buffer, sizeof(buffer),
			"QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n",
			info->qsize,
			info->notify_owner ? info->notify.sigev_notify : 0,
			(info->notify_owner &&
			 info->notify.sigev_notify == SIGEV_SIGNAL) ?
				info->notify.sigev_signo : 0,
			pid_vnr(info->notify_owner));
	spin_unlock(&info->lock);
	buffer[sizeof(buffer)-1] = '\0';

	ret = simple_read_from_buffer(u_data, count, off, buffer,
				strlen(buffer));
	if (ret <= 0)
		return ret;

	file_inode(filp)->i_atime = file_inode(filp)->i_ctime = CURRENT_TIME;
	return ret;
}

static int mqueue_flush_file(struct file *filp, fl_owner_t id)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));

	spin_lock(&info->lock);
	if (task_tgid(current) == info->notify_owner)
		remove_notification(info);

	spin_unlock(&info->lock);
	return 0;
}

static unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
	int retval = 0;

	poll_wait(filp, &info->wait_q, poll_tab);

	spin_lock(&info->lock);
	if (info->attr.mq_curmsgs)
		retval = POLLIN | POLLRDNORM;

	if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
		retval |= POLLOUT | POLLWRNORM;
	spin_unlock(&info->lock);

	return retval;
}

/* Adds current to info->e_wait_q[sr] before element with smaller prio */
static void wq_add(struct mqueue_inode_info *info, int sr,
			struct ext_wait_queue *ewp)
{
	struct ext_wait_queue *walk;

	ewp->task = current;

	list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
		if (walk->task->static_prio <= current->static_prio) {
			list_add_tail(&ewp->list, &walk->list);
			return;
		}
	}
	list_add_tail(&ewp->list, &info->e_wait_q[sr].list);
}

/*
 * Puts current task to sleep. Caller must hold queue lock. After return
 * lock isn't held.
 * sr: SEND or RECV
 */
static int wq_sleep(struct mqueue_inode_info *info, int sr,
		    ktime_t *timeout, struct ext_wait_queue *ewp)
{
	int retval;
	signed long time;

	wq_add(info, sr, ewp);

	for (;;) {
		set_current_state(TASK_INTERRUPTIBLE);

		spin_unlock(&info->lock);
		time = schedule_hrtimeout_range_clock(timeout, 0,
			HRTIMER_MODE_ABS, CLOCK_REALTIME);

		while (ewp->state == STATE_PENDING)
			cpu_relax();

		if (ewp->state == STATE_READY) {
			retval = 0;
			goto out;
		}
		spin_lock(&info->lock);
		if (ewp->state == STATE_READY) {
			retval = 0;
			goto out_unlock;
		}
		if (signal_pending(current)) {
			retval = -ERESTARTSYS;
			break;
		}
		if (time == 0) {
			retval = -ETIMEDOUT;
			break;
		}
	}
	list_del(&ewp->list);
out_unlock:
	spin_unlock(&info->lock);
out:
	return retval;
}

/*
 * Returns waiting task that should be serviced first or NULL if none exists
 */
static struct ext_wait_queue *wq_get_first_waiter(
		struct mqueue_inode_info *info, int sr)
{
	struct list_head *ptr;

	ptr = info->e_wait_q[sr].list.prev;
	if (ptr == &info->e_wait_q[sr].list)
		return NULL;
	return list_entry(ptr, struct ext_wait_queue, list);
}


static inline void set_cookie(struct sk_buff *skb, char code)
{
	((char *)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
}

/*
 * The next function is only to split too long sys_mq_timedsend
 */
static void __do_notify(struct mqueue_inode_info *info)
{
	/* notification
	 * invoked when there is registered process and there isn't process
	 * waiting synchronously for message AND state of queue changed from
	 * empty to not empty. Here we are sure that no one is waiting
	 * synchronously. */
	if (info->notify_owner &&
	    info->attr.mq_curmsgs == 1) {
		struct siginfo sig_i;
		switch (info->notify.sigev_notify) {
		case SIGEV_NONE:
			break;
		case SIGEV_SIGNAL:
			/* sends signal */

			sig_i.si_signo = info->notify.sigev_signo;
			sig_i.si_errno = 0;
			sig_i.si_code = SI_MESGQ;
			sig_i.si_value = info->notify.sigev_value;
			/* map current pid/uid into info->owner's namespaces */
			rcu_read_lock();
			sig_i.si_pid = task_tgid_nr_ns(current,
						ns_of_pid(info->notify_owner));
			sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
			rcu_read_unlock();

			kill_pid_info(info->notify.sigev_signo,
				      &sig_i, info->notify_owner);
			break;
		case SIGEV_THREAD:
			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
			netlink_sendskb(info->notify_sock, info->notify_cookie);
			break;
		}
		/* after notification unregisters process */
		put_pid(info->notify_owner);
		put_user_ns(info->notify_user_ns);
		info->notify_owner = NULL;
		info->notify_user_ns = NULL;
	}
	wake_up(&info->wait_q);
}

static int prepare_timeout(const struct timespec __user *u_abs_timeout,
			   ktime_t *expires, struct timespec *ts)
{
	if (copy_from_user(ts, u_abs_timeout, sizeof(struct timespec)))
		return -EFAULT;
	if (!timespec_valid(ts))
		return -EINVAL;

	*expires = timespec_to_ktime(*ts);
	return 0;
}

static void remove_notification(struct mqueue_inode_info *info)
{
	if (info->notify_owner != NULL &&
	    info->notify.sigev_notify == SIGEV_THREAD) {
		set_cookie(info->notify_cookie, NOTIFY_REMOVED);
		netlink_sendskb(info->notify_sock, info->notify_cookie);
	}
	put_pid(info->notify_owner);
	put_user_ns(info->notify_user_ns);
	info->notify_owner = NULL;
	info->notify_user_ns = NULL;
}

static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
{
	int mq_treesize;
	unsigned long total_size;

	if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0)
		return -EINVAL;
	if (capable(CAP_SYS_RESOURCE)) {
		if (attr->mq_maxmsg > HARD_MSGMAX ||
		    attr->mq_msgsize > HARD_MSGSIZEMAX)
			return -EINVAL;
	} else {
		if (attr->mq_maxmsg > ipc_ns->mq_msg_max ||
				attr->mq_msgsize > ipc_ns->mq_msgsize_max)
			return -EINVAL;
	}
	/* check for overflow */
	if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg)
		return -EOVERFLOW;
	mq_treesize = attr->mq_maxmsg * sizeof(struct msg_msg) +
		min_t(unsigned int, attr->mq_maxmsg, MQ_PRIO_MAX) *
		sizeof(struct posix_msg_tree_node);
	total_size = attr->mq_maxmsg * attr->mq_msgsize;
	if (total_size + mq_treesize < total_size)
		return -EOVERFLOW;
	return 0;
}

/*
 * Invoked when creating a new queue via sys_mq_open
 */
static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir,
			struct path *path, int oflag, umode_t mode,
			struct mq_attr *attr)
{
	const struct cred *cred = current_cred();
	int ret;

	if (attr) {
		ret = mq_attr_ok(ipc_ns, attr);
		if (ret)
			return ERR_PTR(ret);
		/* store for use during create */
		path->dentry->d_fsdata = attr;
	} else {
		struct mq_attr def_attr;

		def_attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
					 ipc_ns->mq_msg_default);
		def_attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
					  ipc_ns->mq_msgsize_default);
		ret = mq_attr_ok(ipc_ns, &def_attr);
		if (ret)
			return ERR_PTR(ret);
	}

	mode &= ~current_umask();
	ret = vfs_create(dir, path->dentry, mode, true);
	path->dentry->d_fsdata = NULL;
	if (ret)
		return ERR_PTR(ret);
	return dentry_open(path, oflag, cred);
}

/* Opens existing queue */
static struct file *do_open(struct path *path, int oflag)
{
	static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
						  MAY_READ | MAY_WRITE };
	int acc;
	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
		return ERR_PTR(-EINVAL);
	acc = oflag2acc[oflag & O_ACCMODE];
	if (inode_permission(path->dentry->d_inode, acc))
		return ERR_PTR(-EACCES);
	return dentry_open(path, oflag, current_cred());
}

SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
		struct mq_attr __user *, u_attr)
{
	struct path path;
	struct file *filp;
	struct filename *name;
	struct mq_attr attr;
	int fd, error;
	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
	struct vfsmount *mnt = ipc_ns->mq_mnt;
	struct dentry *root = mnt->mnt_root;
	int ro;

	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
		return -EFAULT;

	audit_mq_open(oflag, mode, u_attr ? &attr : NULL);

	if (IS_ERR(name = getname(u_name)))
		return PTR_ERR(name);

	fd = get_unused_fd_flags(O_CLOEXEC);
	if (fd < 0)
		goto out_putname;

	ro = mnt_want_write(mnt);	/* we'll drop it in any case */
	error = 0;
	mutex_lock(&root->d_inode->i_mutex);
	path.dentry = lookup_one_len(name->name, root, strlen(name->name));
	if (IS_ERR(path.dentry)) {
		error = PTR_ERR(path.dentry);
		goto out_putfd;
	}
	path.mnt = mntget(mnt);

	if (oflag & O_CREAT) {
		if (path.dentry->d_inode) {	/* entry already exists */
			audit_inode(name, path.dentry, 0);
			if (oflag & O_EXCL) {
				error = -EEXIST;
				goto out;
			}
			filp = do_open(&path, oflag);
		} else {
			if (ro) {
				error = ro;
				goto out;
			}
			audit_inode_parent_hidden(name, root);
			filp = do_create(ipc_ns, root->d_inode,
						&path, oflag, mode,
						u_attr ? &attr : NULL);
		}
	} else {
		if (!path.dentry->d_inode) {
			error = -ENOENT;
			goto out;
		}
		audit_inode(name, path.dentry, 0);
		filp = do_open(&path, oflag);
	}

	if (!IS_ERR(filp))
		fd_install(fd, filp);
	else
		error = PTR_ERR(filp);
out:
	path_put(&path);
out_putfd:
	if (error) {