Merge branch 'linux-next' of git://git.infradead.org/ubifs-2.6

* 'linux-next' of git://git.infradead.org/ubifs-2.6:
  UBIFS: start using hrtimers
  hrtimer: export ktime_add_safe
  UBIFS: do not forget to register BDI device
  UBIFS: allow sync option in rootflags
  UBIFS: remove dead code
  UBIFS: use anonymous device
  UBIFS: return proper error code if the compr is not present
  UBIFS: return error if link and unlink race
  UBIFS: reset no_space flag after inode deletion

6 files changed, 102 insertions, 72 deletions

diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index af19144..eaf6d89 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -91,7 +91,6 @@ static int shrink_liability(struct ubifs_info *c, int nr_to_write)
 	return nr_written;
 }
 
-
 /**
  * run_gc - run garbage collector.
  * @c: UBIFS file-system description object
@@ -628,7 +627,7 @@ void ubifs_convert_page_budget(struct ubifs_info *c)
  *
  * This function releases budget corresponding to a dirty inode. It is usually
  * called when after the inode has been written to the media and marked as
- * clean.
+ * clean. It also causes the "no space" flags to be cleared.
  */
 void ubifs_release_dirty_inode_budget(struct ubifs_info *c,
 				      struct ubifs_inode *ui)
@@ -636,6 +635,7 @@ void ubifs_release_dirty_inode_budget(struct ubifs_info *c,
 	struct ubifs_budget_req req;
 
 	memset(&req, 0, sizeof(struct ubifs_budget_req));
+	/* The "no space" flags will be cleared because dd_growth is > 0 */
 	req.dd_growth = c->inode_budget + ALIGN(ui->data_len, 8);
 	ubifs_release_budget(c, &req);
 }
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index f55d523..552fb01 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -528,6 +528,25 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 		inode->i_nlink, dir->i_ino);
 	ubifs_assert(mutex_is_locked(&dir->i_mutex));
 	ubifs_assert(mutex_is_locked(&inode->i_mutex));
+
+	/*
+	 * Return -ENOENT if we've raced with unlink and i_nlink is 0.  Doing
+	 * otherwise has the potential to corrupt the orphan inode list.
+	 *
+	 * Indeed, consider a scenario when 'vfs_link(dirA/fileA)' and
+	 * 'vfs_unlink(dirA/fileA, dirB/fileB)' race. 'vfs_link()' does not
+	 * lock 'dirA->i_mutex', so this is possible. Both of the functions
+	 * lock 'fileA->i_mutex' though. Suppose 'vfs_unlink()' wins, and takes
+	 * 'fileA->i_mutex' mutex first. Suppose 'fileA->i_nlink' is 1. In this
+	 * case 'ubifs_unlink()' will drop the last reference, and put 'inodeA'
+	 * to the list of orphans. After this, 'vfs_link()' will link
+	 * 'dirB/fileB' to 'inodeA'. This is a problem because, for example,
+	 * the subsequent 'vfs_unlink(dirB/fileB)' will add the same inode
+	 * to the list of orphans.
+	 */
+	 if (inode->i_nlink == 0)
+		 return -ENOENT;
+
 	err = dbg_check_synced_i_size(inode);
 	if (err)
 		return err;
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index e8e632a..bc58571 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -293,13 +293,14 @@ void ubifs_prep_grp_node(struct ubifs_info *c, void *node, int len, int last)
  *
  * This function is called when the write-buffer timer expires.
  */
-static void wbuf_timer_callback_nolock(unsigned long data)
+static enum hrtimer_restart wbuf_timer_callback_nolock(struct hrtimer *timer)
 {
-	struct ubifs_wbuf *wbuf = (struct ubifs_wbuf *)data;
+	struct ubifs_wbuf *wbuf = container_of(timer, struct ubifs_wbuf, timer);
 
 	wbuf->need_sync = 1;
 	wbuf->c->need_wbuf_sync = 1;
 	ubifs_wake_up_bgt(wbuf->c);
+	return HRTIMER_NORESTART;
 }
 
 /**
@@ -308,13 +309,12 @@ static void wbuf_timer_callback_nolock(unsigned long data)
  */
 static void new_wbuf_timer_nolock(struct ubifs_wbuf *wbuf)
 {
-	ubifs_assert(!timer_pending(&wbuf->timer));
+	ubifs_assert(!hrtimer_active(&wbuf->timer));
 
-	if (!wbuf->timeout)
+	if (!ktime_to_ns(wbuf->softlimit))
 		return;
-
-	wbuf->timer.expires = jiffies + wbuf->timeout;
-	add_timer(&wbuf->timer);
+	hrtimer_start_range_ns(&wbuf->timer, wbuf->softlimit, wbuf->delta,
+			       HRTIMER_MODE_REL);
 }
 
 /**
@@ -329,7 +329,7 @@ static void cancel_wbuf_timer_nolock(struct ubifs_wbuf *wbuf)
 	 * should be canceled.
 	 */
 	wbuf->need_sync = 0;
-	del_timer(&wbuf->timer);
+	hrtimer_cancel(&wbuf->timer);
 }
 
 /**
@@ -825,6 +825,7 @@ out:
 int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf)
 {
 	size_t size;
+	ktime_t hardlimit;
 
 	wbuf->buf = kmalloc(c->min_io_size, GFP_KERNEL);
 	if (!wbuf->buf)
@@ -845,14 +846,21 @@ int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf)
 	wbuf->sync_callback = NULL;
 	mutex_init(&wbuf->io_mutex);
 	spin_lock_init(&wbuf->lock);
-
 	wbuf->c = c;
-	init_timer(&wbuf->timer);
-	wbuf->timer.function = wbuf_timer_callback_nolock;
-	wbuf->timer.data = (unsigned long)wbuf;
-	wbuf->timeout = DEFAULT_WBUF_TIMEOUT;
 	wbuf->next_ino = 0;
 
+	hrtimer_init(&wbuf->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	wbuf->timer.function = wbuf_timer_callback_nolock;
+	/*
+	 * Make write-buffer soft limit to be 20% of the hard limit. The
+	 * write-buffer timer is allowed to expire any time between the soft
+	 * and hard limits.
+	 */
+	hardlimit = ktime_set(DEFAULT_WBUF_TIMEOUT_SECS, 0);
+	wbuf->delta = (DEFAULT_WBUF_TIMEOUT_SECS * NSEC_PER_SEC) * 2 / 10;
+	wbuf->softlimit = ktime_sub_ns(hardlimit, wbuf->delta);
+	hrtimer_set_expires_range_ns(&wbuf->timer,  wbuf->softlimit,
+				     wbuf->delta);
 	return 0;
 }
 
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 1066297..8056052 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -343,33 +343,15 @@ int ubifs_write_rcvrd_mst_node(struct ubifs_info *c)
  *
  * This function returns %1 if @offs was in the last write to the LEB whose data
  * is in @buf, otherwise %0 is returned.  The determination is made by checking
- * for subsequent empty space starting from the next min_io_size boundary (or a
- * bit less than the common header size if min_io_size is one).
+ * for subsequent empty space starting from the next @c->min_io_size boundary.
  */
 static int is_last_write(const struct ubifs_info *c, void *buf, int offs)
 {
-	int empty_offs;
-	int check_len;
+	int empty_offs, check_len;
 	uint8_t *p;
 
-	if (c->min_io_size == 1) {
-		check_len = c->leb_size - offs;
-		p = buf + check_len;
-		for (; check_len > 0; check_len--)
-			if (*--p != 0xff)
-				break;
-		/*
-		 * 'check_len' is the size of the corruption which cannot be
-		 * more than the size of 1 node if it was caused by an unclean
-		 * unmount.
-		 */
-		if (check_len > UBIFS_MAX_NODE_SZ)
-			return 0;
-		return 1;
-	}
-
 	/*
-	 * Round up to the next c->min_io_size boundary i.e. 'offs' is in the
+	 * Round up to the next @c->min_io_size boundary i.e. @offs is in the
 	 * last wbuf written. After that should be empty space.
 	 */
 	empty_offs = ALIGN(offs + 1, c->min_io_size);
@@ -392,7 +374,7 @@ static int is_last_write(const struct ubifs_info *c, void *buf, int offs)
  *
  * This function pads up to the next min_io_size boundary (if there is one) and
  * sets empty space to all 0xff. @buf, @offs and @len are updated to the next
- * min_io_size boundary (if there is one).
+ * @c->min_io_size boundary.
  */
 static void clean_buf(const struct ubifs_info *c, void **buf, int lnum,
 		      int *offs, int *len)
@@ -402,11 +384,6 @@ static void clean_buf(const struct ubifs_info *c, void **buf, int lnum,
 	lnum = lnum;
 	dbg_rcvry("cleaning corruption at %d:%d", lnum, *offs);
 
-	if (c->min_io_size == 1) {
-		memset(*buf, 0xff, c->leb_size - *offs);
-		return;
-	}
-
 	ubifs_assert(!(*offs & 7));
 	empty_offs = ALIGN(*offs, c->min_io_size);
 	pad_len = empty_offs - *offs;
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 3260b73..79fad43 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -361,6 +361,11 @@ static void ubifs_delete_inode(struct inode *inode)
 out:
 	if (ui->dirty)
 		ubifs_release_dirty_inode_budget(c, ui);
+	else {
+		/* We've deleted something - clean the "no space" flags */
+		c->nospace = c->nospace_rp = 0;
+		smp_wmb();
+	}
 	clear_inode(inode);
 }
 
@@ -792,7 +797,7 @@ static int alloc_wbufs(struct ubifs_info *c)
 	 * does not need to be synchronized by timer.
 	 */
 	c->jheads[GCHD].wbuf.dtype = UBI_LONGTERM;
-	c->jheads[GCHD].wbuf.timeout = 0;
+	c->jheads[GCHD].wbuf.softlimit = ktime_set(0, 0);
 
 	return 0;
 }
@@ -933,6 +938,27 @@ static const match_table_t tokens = {
 };
 
 /**
+ * parse_standard_option - parse a standard mount option.
+ * @option: the option to parse
+ *
+ * Normally, standard mount options like "sync" are passed to file-systems as
+ * flags. However, when a "rootflags=" kernel boot parameter is used, they may
+ * be present in the options string. This function tries to deal with this
+ * situation and parse standard options. Returns 0 if the option was not
+ * recognized, and the corresponding integer flag if it was.
+ *
+ * UBIFS is only interested in the "sync" option, so do not check for anything
+ * else.
+ */
+static int parse_standard_option(const char *option)
+{
+	ubifs_msg("parse %s", option);
+	if (!strcmp(option, "sync"))
+		return MS_SYNCHRONOUS;
+	return 0;
+}
+
+/**
  * ubifs_parse_options - parse mount parameters.
  * @c: UBIFS file-system description object
  * @options: parameters to parse
@@ -1008,9 +1034,19 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options,
 			break;
 		}
 		default:
-			ubifs_err("unrecognized mount option \"%s\" "
-				  "or missing value", p);
-			return -EINVAL;
+		{
+			unsigned long flag;
+			struct super_block *sb = c->vfs_sb;
+
+			flag = parse_standard_option(p);
+			if (!flag) {
+				ubifs_err("unrecognized mount option \"%s\" "
+					  "or missing value", p);
+				return -EINVAL;
+			}
+			sb->s_flags |= flag;
+			break;
+		}
 		}
 	}
 
@@ -1180,6 +1216,7 @@ static int mount_ubifs(struct ubifs_info *c)
 	if (!ubifs_compr_present(c->default_compr)) {
 		ubifs_err("'compressor \"%s\" is not compiled in",
 			  ubifs_compr_name(c->default_compr));
+		err = -ENOTSUPP;
 		goto out_free;
 	}
 
@@ -1656,7 +1693,7 @@ static void ubifs_remount_ro(struct ubifs_info *c)
 
 	for (i = 0; i < c->jhead_cnt; i++) {
 		ubifs_wbuf_sync(&c->jheads[i].wbuf);
-		del_timer_sync(&c->jheads[i].wbuf.timer);
+		hrtimer_cancel(&c->jheads[i].wbuf.timer);
 	}
 
 	c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
@@ -1719,7 +1756,7 @@ static void ubifs_put_super(struct super_block *sb)
 		if (c->jheads)
 			for (i = 0; i < c->jhead_cnt; i++) {
 				ubifs_wbuf_sync(&c->jheads[i].wbuf);
-				del_timer_sync(&c->jheads[i].wbuf.timer);
+				hrtimer_cancel(&c->jheads[i].wbuf.timer);
 			}
 
 		/*
@@ -1911,6 +1948,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&c->orph_list);
 	INIT_LIST_HEAD(&c->orph_new);
 
+	c->vfs_sb = sb;
 	c->highest_inum = UBIFS_FIRST_INO;
 	c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM;
 
@@ -1945,13 +1983,10 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto out_bdi;
 
-	c->vfs_sb = sb;
-
 	sb->s_fs_info = c;
 	sb->s_magic = UBIFS_SUPER_MAGIC;
 	sb->s_blocksize = UBIFS_BLOCK_SIZE;
 	sb->s_blocksize_bits = UBIFS_BLOCK_SHIFT;
-	sb->s_dev = c->vi.cdev;
 	sb->s_maxbytes = c->max_inode_sz = key_max_inode_size(c);
 	if (c->max_inode_sz > MAX_LFS_FILESIZE)
 		sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE;
@@ -1996,16 +2031,9 @@ out_free:
 static int sb_test(struct super_block *sb, void *data)
 {
 	dev_t *dev = data;
+	struct ubifs_info *c = sb->s_fs_info;
 
-	return sb->s_dev == *dev;
-}
-
-static int sb_set(struct super_block *sb, void *data)
-{
-	dev_t *dev = data;
-
-	sb->s_dev = *dev;
-	return 0;
+	return c->vi.cdev == *dev;
 }
 
 static int ubifs_get_sb(struct file_system_type *fs_type, int flags,
@@ -2033,7 +2061,7 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags,
 
 	dbg_gen("opened ubi%d_%d", vi.ubi_num, vi.vol_id);
 
-	sb = sget(fs_type, &sb_test, &sb_set, &vi.cdev);
+	sb = sget(fs_type, &sb_test, &set_anon_super, &vi.cdev);
 	if (IS_ERR(sb)) {
 		err = PTR_ERR(sb);
 		goto out_close;
@@ -2073,16 +2101,11 @@ out_close:
 	return err;
 }
 
-static void ubifs_kill_sb(struct super_block *sb)
-{
-	generic_shutdown_super(sb);
-}
-
 static struct file_system_type ubifs_fs_type = {
 	.name    = "ubifs",
 	.owner   = THIS_MODULE,
 	.get_sb  = ubifs_get_sb,
-	.kill_sb = ubifs_kill_sb
+	.kill_sb = kill_anon_super,
 };
 
 /*
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 0a8341e..1bf01d8 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -95,8 +95,8 @@
  */
 #define BGT_NAME_PATTERN "ubifs_bgt%d_%d"
 
-/* Default write-buffer synchronization timeout (5 secs) */
-#define DEFAULT_WBUF_TIMEOUT (5 * HZ)
+/* Default write-buffer synchronization timeout in seconds */
+#define DEFAULT_WBUF_TIMEOUT_SECS 5
 
 /* Maximum possible inode number (only 32-bit inodes are supported now) */
 #define MAX_INUM 0xFFFFFFFF
@@ -650,8 +650,10 @@ typedef int (*ubifs_lpt_scan_callback)(struct ubifs_info *c,
  * @io_mutex: serializes write-buffer I/O
  * @lock: serializes @buf, @lnum, @offs, @avail, @used, @next_ino and @inodes
  *        fields
+ * @softlimit: soft write-buffer timeout interval
+ * @delta: hard and soft timeouts delta (the timer expire inteval is @softlimit
+ *         and @softlimit + @delta)
  * @timer: write-buffer timer
- * @timeout: timer expire interval in jiffies
  * @need_sync: it is set if its timer expired and needs sync
  * @next_ino: points to the next position of the following inode number
  * @inodes: stores the inode numbers of the nodes which are in wbuf
@@ -678,8 +680,9 @@ struct ubifs_wbuf {
 	int (*sync_callback)(struct ubifs_info *c, int lnum, int free, int pad);
 	struct mutex io_mutex;
 	spinlock_t lock;
-	struct timer_list timer;
-	int timeout;
+	ktime_t softlimit;
+	unsigned long long delta;
+	struct hrtimer timer;
 	int need_sync;
 	int next_ino;
 	ino_t *inodes;