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

* 'linux-next' of git://git.infradead.org/~dedekind/ubifs-2.6: (29 commits)
  UBIFS: xattr bugfixes
  UBIFS: remove unneeded check
  UBIFS: few commentary fixes
  UBIFS: fix budgeting request alignment in xattr code
  UBIFS: improve arguments checking in debugging messages
  UBIFS: always set i_generation to 0
  UBIFS: correct spelling of "thrice".
  UBIFS: support splice_write
  UBIFS: minor tweaks in commit
  UBIFS: reserve more space for index
  UBIFS: print pid in dump function
  UBIFS: align inode data to eight
  UBIFS: improve budgeting checks
  UBIFS: correct orphan deletion order
  UBIFS: fix typos in comments
  UBIFS: do not union creat_sqnum and del_cmtno
  UBIFS: optimize deletions
  UBIFS: increment commit number earlier
  UBIFS: remove another unneeded function parameter
  UBIFS: remove unneeded function parameter
  ...

Documentation/filesystems/ubifs.txt

@@ -57,7 +57,7 @@ Similarly to JFFS2, UBIFS supports on-the-flight compression which makes
 it possible to fit quite a lot of data to the flash.
 
 Similarly to JFFS2, UBIFS is tolerant of unclean reboots and power-cuts.
-It does not need stuff like ckfs.ext2. UBIFS automatically replays its
+It does not need stuff like fsck.ext2. UBIFS automatically replays its
 journal and recovers from crashes, ensuring that the on-flash data
 structures are consistent.
 

fs/ubifs/budget.c

@@ -263,8 +263,8 @@ int ubifs_calc_min_idx_lebs(struct ubifs_info *c)
 
 	idx_size = c->old_idx_sz + c->budg_idx_growth + c->budg_uncommitted_idx;
 
-	/* And make sure we have twice the index size of space reserved */
-	idx_size <<= 1;
+	/* And make sure we have thrice the index size of space reserved */
+	idx_size = idx_size + (idx_size << 1);
 
 	/*
 	 * We do not maintain 'old_idx_size' as 'old_idx_lebs'/'old_idx_bytes'
@@ -388,11 +388,11 @@ static int can_use_rp(struct ubifs_info *c)
  * This function makes sure UBIFS has enough free eraseblocks for index growth
  * and data.
  *
- * When budgeting index space, UBIFS reserves twice as more LEBs as the index
+ * When budgeting index space, UBIFS reserves thrice as many LEBs as the index
  * would take if it was consolidated and written to the flash. This guarantees
  * that the "in-the-gaps" commit method always succeeds and UBIFS will always
  * be able to commit dirty index. So this function basically adds amount of
- * budgeted index space to the size of the current index, multiplies this by 2,
+ * budgeted index space to the size of the current index, multiplies this by 3,
  * and makes sure this does not exceed the amount of free eraseblocks.
  *
  * Notes about @c->min_idx_lebs and @c->lst.idx_lebs variables:
@@ -543,8 +543,16 @@ int ubifs_budget_space(struct ubifs_info *c, struct ubifs_budget_req *req)
 	int err, idx_growth, data_growth, dd_growth;
 	struct retries_info ri;
 
+	ubifs_assert(req->new_page <= 1);
+	ubifs_assert(req->dirtied_page <= 1);
+	ubifs_assert(req->new_dent <= 1);
+	ubifs_assert(req->mod_dent <= 1);
+	ubifs_assert(req->new_ino <= 1);
+	ubifs_assert(req->new_ino_d <= UBIFS_MAX_INO_DATA);
 	ubifs_assert(req->dirtied_ino <= 4);
 	ubifs_assert(req->dirtied_ino_d <= UBIFS_MAX_INO_DATA * 4);
+	ubifs_assert(!(req->new_ino_d & 7));
+	ubifs_assert(!(req->dirtied_ino_d & 7));
 
 	data_growth = calc_data_growth(c, req);
 	dd_growth = calc_dd_growth(c, req);
@@ -618,8 +626,16 @@ int ubifs_budget_space(struct ubifs_info *c, struct ubifs_budget_req *req)
  */
 void ubifs_release_budget(struct ubifs_info *c, struct ubifs_budget_req *req)
 {
+	ubifs_assert(req->new_page <= 1);
+	ubifs_assert(req->dirtied_page <= 1);
+	ubifs_assert(req->new_dent <= 1);
+	ubifs_assert(req->mod_dent <= 1);
+	ubifs_assert(req->new_ino <= 1);
+	ubifs_assert(req->new_ino_d <= UBIFS_MAX_INO_DATA);
 	ubifs_assert(req->dirtied_ino <= 4);
 	ubifs_assert(req->dirtied_ino_d <= UBIFS_MAX_INO_DATA * 4);
+	ubifs_assert(!(req->new_ino_d & 7));
+	ubifs_assert(!(req->dirtied_ino_d & 7));
 	if (!req->recalculate) {
 		ubifs_assert(req->idx_growth >= 0);
 		ubifs_assert(req->data_growth >= 0);
@@ -647,7 +663,11 @@ void ubifs_release_budget(struct ubifs_info *c, struct ubifs_budget_req *req)
 
 	ubifs_assert(c->budg_idx_growth >= 0);
 	ubifs_assert(c->budg_data_growth >= 0);
+	ubifs_assert(c->budg_dd_growth >= 0);
 	ubifs_assert(c->min_idx_lebs < c->main_lebs);
+	ubifs_assert(!(c->budg_idx_growth & 7));
+	ubifs_assert(!(c->budg_data_growth & 7));
+	ubifs_assert(!(c->budg_dd_growth & 7));
 	spin_unlock(&c->space_lock);
 }
 
@@ -686,9 +706,10 @@ void ubifs_convert_page_budget(struct ubifs_info *c)
 void ubifs_release_dirty_inode_budget(struct ubifs_info *c,
 				      struct ubifs_inode *ui)
 {
-	struct ubifs_budget_req req = {.dd_growth = c->inode_budget,
-				       .dirtied_ino_d = ui->data_len};
+	struct ubifs_budget_req req;
 
+	memset(&req, 0, sizeof(struct ubifs_budget_req));
+	req.dd_growth = c->inode_budget + ALIGN(ui->data_len, 8);
 	ubifs_release_budget(c, &req);
 }
 

fs/ubifs/commit.c

@@ -74,6 +74,7 @@ static int do_commit(struct ubifs_info *c)
 			goto out_up;
 	}
 
+	c->cmt_no += 1;
 	err = ubifs_gc_start_commit(c);
 	if (err)
 		goto out_up;
@@ -115,7 +116,7 @@ static int do_commit(struct ubifs_info *c)
 		goto out;
 
 	mutex_lock(&c->mst_mutex);
-	c->mst_node->cmt_no      = cpu_to_le64(++c->cmt_no);
+	c->mst_node->cmt_no      = cpu_to_le64(c->cmt_no);
 	c->mst_node->log_lnum    = cpu_to_le32(new_ltail_lnum);
 	c->mst_node->root_lnum   = cpu_to_le32(zroot.lnum);
 	c->mst_node->root_offs   = cpu_to_le32(zroot.offs);

fs/ubifs/debug.c

@@ -568,8 +568,8 @@ void dbg_dump_budget_req(const struct ubifs_budget_req *req)
 void dbg_dump_lstats(const struct ubifs_lp_stats *lst)
 {
 	spin_lock(&dbg_lock);
-	printk(KERN_DEBUG "Lprops statistics: empty_lebs %d, idx_lebs  %d\n",
-	       lst->empty_lebs, lst->idx_lebs);
+	printk(KERN_DEBUG "(pid %d) Lprops statistics: empty_lebs %d, "
+	       "idx_lebs  %d\n", current->pid, lst->empty_lebs, lst->idx_lebs);
 	printk(KERN_DEBUG "\ttaken_empty_lebs %d, total_free %lld, "
 	       "total_dirty %lld\n", lst->taken_empty_lebs, lst->total_free,
 	       lst->total_dirty);
@@ -587,8 +587,8 @@ void dbg_dump_budg(struct ubifs_info *c)
 	struct ubifs_gced_idx_leb *idx_gc;
 
 	spin_lock(&dbg_lock);
-	printk(KERN_DEBUG "Budgeting info: budg_data_growth %lld, "
-	       "budg_dd_growth %lld, budg_idx_growth %lld\n",
+	printk(KERN_DEBUG "(pid %d) Budgeting info: budg_data_growth %lld, "
+	       "budg_dd_growth %lld, budg_idx_growth %lld\n", current->pid,
 	       c->budg_data_growth, c->budg_dd_growth, c->budg_idx_growth);
 	printk(KERN_DEBUG "\tdata budget sum %lld, total budget sum %lld, "
 	       "freeable_cnt %d\n", c->budg_data_growth + c->budg_dd_growth,
@@ -634,7 +634,7 @@ void dbg_dump_lprops(struct ubifs_info *c)
 	struct ubifs_lprops lp;
 	struct ubifs_lp_stats lst;
 
-	printk(KERN_DEBUG "Dumping LEB properties\n");
+	printk(KERN_DEBUG "(pid %d) Dumping LEB properties\n", current->pid);
 	ubifs_get_lp_stats(c, &lst);
 	dbg_dump_lstats(&lst);
 
@@ -655,7 +655,7 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum)
 	if (dbg_failure_mode)
 		return;
 
-	printk(KERN_DEBUG "Dumping LEB %d\n", lnum);
+	printk(KERN_DEBUG "(pid %d) Dumping LEB %d\n", current->pid, lnum);
 
 	sleb = ubifs_scan(c, lnum, 0, c->dbg_buf);
 	if (IS_ERR(sleb)) {
@@ -720,8 +720,8 @@ void dbg_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat)
 {
 	int i;
 
-	printk(KERN_DEBUG "Dumping heap cat %d (%d elements)\n",
-	       cat, heap->cnt);
+	printk(KERN_DEBUG "(pid %d) Dumping heap cat %d (%d elements)\n",
+	       current->pid, cat, heap->cnt);
 	for (i = 0; i < heap->cnt; i++) {
 		struct ubifs_lprops *lprops = heap->arr[i];
 
@@ -736,7 +736,7 @@ void dbg_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode,
 {
 	int i;
 
-	printk(KERN_DEBUG "Dumping pnode:\n");
+	printk(KERN_DEBUG "(pid %d) Dumping pnode:\n", current->pid);
 	printk(KERN_DEBUG "\taddress %zx parent %zx cnext %zx\n",
 	       (size_t)pnode, (size_t)parent, (size_t)pnode->cnext);
 	printk(KERN_DEBUG "\tflags %lu iip %d level %d num %d\n",
@@ -755,7 +755,7 @@ void dbg_dump_tnc(struct ubifs_info *c)
 	int level;
 
 	printk(KERN_DEBUG "\n");
-	printk(KERN_DEBUG "Dumping the TNC tree\n");
+	printk(KERN_DEBUG "(pid %d) Dumping the TNC tree\n", current->pid);
 	znode = ubifs_tnc_levelorder_next(c->zroot.znode, NULL);
 	level = znode->level;
 	printk(KERN_DEBUG "== Level %d ==\n", level);
@@ -2208,16 +2208,17 @@ int dbg_leb_read(struct ubi_volume_desc *desc, int lnum, char *buf, int offset,
 int dbg_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf,
 		  int offset, int len, int dtype)
 {
-	int err;
+	int err, failing;
 
 	if (in_failure_mode(desc))
 		return -EIO;
-	if (do_fail(desc, lnum, 1))
+	failing = do_fail(desc, lnum, 1);
+	if (failing)
 		cut_data(buf, len);
 	err = ubi_leb_write(desc, lnum, buf, offset, len, dtype);
 	if (err)
 		return err;
-	if (in_failure_mode(desc))
+	if (failing)
 		return -EIO;
 	return 0;
 }

fs/ubifs/debug.h

@@ -73,7 +73,7 @@ const char *dbg_key_str1(const struct ubifs_info *c,
 			 const union ubifs_key *key);
 
 /*
- * DBGKEY macros require dbg_lock to be held, which it is in the dbg message
+ * DBGKEY macros require @dbg_lock to be held, which it is in the dbg message
  * macros.
  */
 #define DBGKEY(key) dbg_key_str0(c, (key))
@@ -239,34 +239,23 @@ typedef int (*dbg_leaf_callback)(struct ubifs_info *c,
 				 struct ubifs_zbranch *zbr, void *priv);
 typedef int (*dbg_znode_callback)(struct ubifs_info *c,
 				  struct ubifs_znode *znode, void *priv);
-
 int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb,
 		   dbg_znode_callback znode_cb, void *priv);
 
 /* Checking functions */
 
 int dbg_check_lprops(struct ubifs_info *c);
-
 int dbg_old_index_check_init(struct ubifs_info *c, struct ubifs_zbranch *zroot);
 int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot);
-
 int dbg_check_cats(struct ubifs_info *c);
-
 int dbg_check_ltab(struct ubifs_info *c);
-
 int dbg_check_synced_i_size(struct inode *inode);
-
 int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir);
-
 int dbg_check_tnc(struct ubifs_info *c, int extra);
-
 int dbg_check_idx_size(struct ubifs_info *c, long long idx_size);
-
 int dbg_check_filesystem(struct ubifs_info *c);
-
 void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat,
 		    int add_pos);
-
 int dbg_check_lprops(struct ubifs_info *c);
 int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode,
 			int row, int col);
@@ -329,26 +318,44 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum,
 #else /* !CONFIG_UBIFS_FS_DEBUG */
 
 #define UBIFS_DBG(op)
-#define ubifs_assert(expr)                         ({})
-#define ubifs_assert_cmt_locked(c)
+
+/* Use "if (0)" to make compiler check arguments even if debugging is off */
+#define ubifs_assert(expr)  do {                                               \
+	if (0 && (expr))                                                       \
+		printk(KERN_CRIT "UBIFS assert failed in %s at %u (pid %d)\n", \
+		       __func__, __LINE__, current->pid);                      \
+} while (0)
+
+#define dbg_err(fmt, ...)   do {                                               \
+	if (0)                                                                 \
+		ubifs_err(fmt, ##__VA_ARGS__);                                 \
+} while (0)
+
+#define dbg_msg(fmt, ...) do {                                                 \
+	if (0)                                                                 \
+		printk(KERN_DEBUG "UBIFS DBG (pid %d): %s: " fmt "\n",         \
+		       current->pid, __func__, ##__VA_ARGS__);                 \
+} while (0)
+
 #define dbg_dump_stack()
-#define dbg_err(fmt, ...)                          ({})
-#define dbg_msg(fmt, ...)                          ({})
-#define dbg_key(c, key, fmt, ...)                  ({})
-
-#define dbg_gen(fmt, ...)                          ({})
-#define dbg_jnl(fmt, ...)                          ({})
-#define dbg_tnc(fmt, ...)                          ({})
-#define dbg_lp(fmt, ...)                           ({})
-#define dbg_find(fmt, ...)                         ({})
-#define dbg_mnt(fmt, ...)                          ({})
-#define dbg_io(fmt, ...)                           ({})
-#define dbg_cmt(fmt, ...)                          ({})
-#define dbg_budg(fmt, ...)                         ({})
-#define dbg_log(fmt, ...)                          ({})
-#define dbg_gc(fmt, ...)                           ({})
-#define dbg_scan(fmt, ...)                         ({})
-#define dbg_rcvry(fmt, ...)                        ({})
+#define ubifs_assert_cmt_locked(c)
+
+#define dbg_gen(fmt, ...)   dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_jnl(fmt, ...)   dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_tnc(fmt, ...)   dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_lp(fmt, ...)    dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_find(fmt, ...)  dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_mnt(fmt, ...)   dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_io(fmt, ...)    dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_cmt(fmt, ...)   dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_budg(fmt, ...)  dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_log(fmt, ...)   dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_gc(fmt, ...)    dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_scan(fmt, ...)  dbg_msg(fmt, ##__VA_ARGS__)
+#define dbg_rcvry(fmt, ...) dbg_msg(fmt, ##__VA_ARGS__)
+
+#define DBGKEY(key)  ((char *)(key))
+#define DBGKEY1(key) ((char *)(key))
 
 #define dbg_ntype(type)                       ""
 #define dbg_cstate(cmt_state)                 ""
@@ -368,32 +375,20 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum,
 #define dbg_dump_index(c)                     ({})
 
 #define dbg_walk_index(c, leaf_cb, znode_cb, priv) 0
-
 #define dbg_old_index_check_init(c, zroot)         0
 #define dbg_check_old_index(c, zroot)              0
-
 #define dbg_check_cats(c)                          0
-
 #define dbg_check_ltab(c)                          0
-
 #define dbg_check_synced_i_size(inode)             0
-
 #define dbg_check_dir_size(c, dir)                 0
-
 #define dbg_check_tnc(c, x)                        0
-
 #define dbg_check_idx_size(c, idx_size)            0
-
 #define dbg_check_filesystem(c)                    0
-
 #define dbg_check_heap(c, heap, cat, add_pos)      ({})
-
 #define dbg_check_lprops(c)                        0
 #define dbg_check_lpt_nodes(c, cnode, row, col)    0
-
 #define dbg_force_in_the_gaps_enabled              0
 #define dbg_force_in_the_gaps()                    0
-
 #define dbg_failure_mode                           0
 #define dbg_failure_mode_registration(c)           ({})
 #define dbg_failure_mode_deregistration(c)         ({})

fs/ubifs/dir.c

@@ -165,7 +165,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
 	}
 
 	inode->i_ino = ++c->highest_inum;
-	inode->i_generation = ++c->vfs_gen;
 	/*
 	 * The creation sequence number remains with this inode for its
 	 * lifetime. All nodes for this inode have a greater sequence number,
@@ -220,15 +219,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 
 	err = ubifs_tnc_lookup_nm(c, &key, dent, &dentry->d_name);
 	if (err) {
-		/*
-		 * Do not hash the direntry if parent 'i_nlink' is zero, because
-		 * this has side-effects - '->delete_inode()' call will not be
-		 * called for the parent orphan inode, because 'd_count' of its
-		 * direntry will stay 1 (it'll be negative direntry I guess)
-		 * and prevent 'iput_final()' until the dentry is destroyed due
-		 * to unmount or memory pressure.
-		 */
-		if (err == -ENOENT && dir->i_nlink != 0) {
+		if (err == -ENOENT) {
 			dbg_gen("not found");
 			goto done;
 		}
@@ -525,7 +516,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 	struct ubifs_inode *dir_ui = ubifs_inode(dir);
 	int err, sz_change = CALC_DENT_SIZE(dentry->d_name.len);
 	struct ubifs_budget_req req = { .new_dent = 1, .dirtied_ino = 2,
-					.dirtied_ino_d = ui->data_len };
+				.dirtied_ino_d = ALIGN(ui->data_len, 8) };
 
 	/*
 	 * Budget request settings: new direntry, changing the target inode,
@@ -727,8 +718,7 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	struct ubifs_inode *dir_ui = ubifs_inode(dir);
 	struct ubifs_info *c = dir->i_sb->s_fs_info;
 	int err, sz_change = CALC_DENT_SIZE(dentry->d_name.len);
-	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
-					.dirtied_ino_d = 1 };
+	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1 };
 
 	/*
 	 * Budget request settings: new inode, new direntry and changing parent
@@ -789,7 +779,8 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 	int sz_change = CALC_DENT_SIZE(dentry->d_name.len);
 	int err, devlen = 0;
 	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
-					.new_ino_d = devlen, .dirtied_ino = 1 };
+					.new_ino_d = ALIGN(devlen, 8),
+					.dirtied_ino = 1 };
 
 	/*
 	 * Budget request settings: new inode, new direntry and changing parent
@@ -863,7 +854,8 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry,
 	int err, len = strlen(symname);
 	int sz_change = CALC_DENT_SIZE(dentry->d_name.len);
 	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
-					.new_ino_d = len, .dirtied_ino = 1 };
+					.new_ino_d = ALIGN(len, 8),
+					.dirtied_ino = 1 };
 
 	/*
 	 * Budget request settings: new inode, new direntry and changing parent
@@ -1012,7 +1004,7 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct ubifs_budget_req req = { .new_dent = 1, .mod_dent = 1,
 					.dirtied_ino = 3 };
 	struct ubifs_budget_req ino_req = { .dirtied_ino = 1,
-				.dirtied_ino_d = old_inode_ui->data_len };
+			.dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
 	struct timespec time;
 
 	/*

fs/ubifs/file.c

@@ -890,7 +890,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode,
 	loff_t new_size = attr->ia_size;
 	struct ubifs_inode *ui = ubifs_inode(inode);
 	struct ubifs_budget_req req = { .dirtied_ino = 1,
-					.dirtied_ino_d = ui->data_len };
+				.dirtied_ino_d = ALIGN(ui->data_len, 8) };
 
 	err = ubifs_budget_space(c, &req);
 	if (err)
@@ -941,7 +941,8 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr)
 	struct inode *inode = dentry->d_inode;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 
-	dbg_gen("ino %lu, ia_valid %#x", inode->i_ino, attr->ia_valid);
+	dbg_gen("ino %lu, mode %#x, ia_valid %#x",
+		inode->i_ino, inode->i_mode, attr->ia_valid);
 	err = inode_change_ok(inode, attr);
 	if (err)
 		return err;
@@ -1051,7 +1052,7 @@ static int update_mctime(struct ubifs_info *c, struct inode *inode)
 	if (mctime_update_needed(inode, &now)) {
 		int err, release;
 		struct ubifs_budget_req req = { .dirtied_ino = 1,
-						.dirtied_ino_d = ui->data_len };
+				.dirtied_ino_d = ALIGN(ui->data_len, 8) };
 
 		err = ubifs_budget_space(c, &req);
 		if (err)
@@ -1270,6 +1271,7 @@ struct file_operations ubifs_file_operations = {
 	.fsync          = ubifs_fsync,
 	.unlocked_ioctl = ubifs_ioctl,
 	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = ubifs_compat_ioctl,
 #endif

fs/ubifs/find.c

@@ -290,9 +290,14 @@ int ubifs_find_dirty_leb(struct ubifs_info *c, struct ubifs_lprops *ret_lp,
 		idx_lp = idx_heap->arr[0];
 		sum = idx_lp->free + idx_lp->dirty;
 		/*
-		 * Since we reserve twice as more space for the index than it
+		 * Since we reserve thrice as much space for the index than it
 		 * actually takes, it does not make sense to pick indexing LEBs
-		 * with less than half LEB of dirty space.
+		 * with less than, say, half LEB of dirty space. May be half is
+		 * not the optimal boundary - this should be tested and
+		 * checked. This boundary should determine how much we use
+		 * in-the-gaps to consolidate the index comparing to how much
+		 * we use garbage collector to consolidate it. The "half"
+		 * criteria just feels to be fine.
 		 */
 		if (sum < min_space || sum < c->half_leb_size)
 			idx_lp = NULL;

fs/ubifs/io.c

@@ -53,6 +53,20 @@
 #include <linux/crc32.h>
 #include "ubifs.h"
 
+/**
+ * ubifs_ro_mode - switch UBIFS to read read-only mode.
+ * @c: UBIFS file-system description object
+ * @err: error code which is the reason of switching to R/O mode
+ */
+void ubifs_ro_mode(struct ubifs_info *c, int err)
+{
+	if (!c->ro_media) {
+		c->ro_media = 1;
+		ubifs_warn("switched to read-only mode, error %d", err);
+		dbg_dump_stack();
+	}
+}
+
 /**
  * ubifs_check_node - check node.
  * @c: UBIFS file-system description object

fs/ubifs/journal.c

@@ -447,13 +447,11 @@ static int get_dent_type(int mode)
  * @ino: buffer in which to pack inode node
  * @inode: inode to pack
  * @last: indicates the last node of the group
- * @last_reference: non-zero if this is a deletion inode
  */
 static void pack_inode(struct ubifs_info *c, struct ubifs_ino_node *ino,
-		       const struct inode *inode, int last,
-		       int last_reference)
+		       const struct inode *inode, int last)
 {
-	int data_len = 0;
+	int data_len = 0, last_reference = !inode->i_nlink;
 	struct ubifs_inode *ui = ubifs_inode(inode);
 
 	ino->ch.node_type = UBIFS_INO_NODE;
@@ -596,9 +594,9 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	ubifs_prep_grp_node(c, dent, dlen, 0);
 
 	ino = (void *)dent + aligned_dlen;
-	pack_inode(c, ino, inode, 0, last_reference);
+	pack_inode(c, ino, inode, 0);
 	ino = (void *)ino + aligned_ilen;
-	pack_inode(c, ino, dir, 1, 0);
+	pack_inode(c, ino, dir, 1);
 
 	if (last_reference) {
 		err = ubifs_add_orphan(c, inode->i_ino);
@@ -606,6 +604,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 			release_head(c, BASEHD);
 			goto out_finish;
 		}
+		ui->del_cmtno = c->cmt_no;
 	}
 
 	err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync);
@@ -750,30 +749,25 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
  * ubifs_jnl_write_inode - flush inode to the journal.
  * @c: UBIFS file-system description object
  * @inode: inode to flush
- * @deletion: inode has been deleted
  *
  * This function writes inode @inode to the journal. If the inode is
  * synchronous, it also synchronizes the write-buffer. Returns zero in case of
  * success and a negative error code in case of failure.
  */
-int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode,
-			  int deletion)
+int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode)
 {
-	int err, len, lnum, offs, sync = 0;
+	int err, lnum, offs;
 	struct ubifs_ino_node *ino;
 	struct ubifs_inode *ui = ubifs_inode(inode);
+	int sync = 0, len = UBIFS_INO_NODE_SZ, last_reference = !inode->i_nlink;
 
-	dbg_jnl("ino %lu%s", inode->i_ino,
-		deletion ? " (last reference)" : "");
-	if (deletion)
-		ubifs_assert(inode->i_nlink == 0);
+	dbg_jnl("ino %lu, nlink %u", inode->i_ino, inode->i_nlink);
 
-	len = UBIFS_INO_NODE_SZ;
 	/*
 	 * If the inode is being deleted, do not write the attached data. No
 	 * need to synchronize the write-buffer either.
 	 */
-	if (!deletion) {
+	if (!last_reference) {
 		len += ui->data_len;
 		sync = IS_SYNC(inode);
 	}
@@ -786,7 +780,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode,
 	if (err)
 		goto out_free;
 
-	pack_inode(c, ino, inode, 1, deletion);
+	pack_inode(c, ino, inode, 1);
 	err = write_head(c, BASEHD, ino, len, &lnum, &offs, sync);
 	if (err)
 		goto out_release;
@@ -795,7 +789,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode,
 					  inode->i_ino);
 	release_head(c, BASEHD);
 
-	if (deletion) {
+	if (last_reference) {
 		err = ubifs_tnc_remove_ino(c, inode->i_ino);
 		if (err)
 			goto out_ro;
@@ -827,6 +821,65 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode,
 	return err;
 }
 
+/**
+ * ubifs_jnl_delete_inode - delete an inode.
+ * @c: UBIFS file-system description object
+ * @inode: inode to delete
+ *
+ * This function deletes inode @inode which includes removing it from orphans,
+ * deleting it from TNC and, in some cases, writing a deletion inode to the
+ * journal.
+ *
+ * When regular file inodes are unlinked or a directory inode is removed, the
+ * 'ubifs_jnl_update()' function writes a corresponding deletion inode and
+ * direntry to the media, and adds the inode to orphans. After this, when the
+ * last reference to this inode has been dropped, this function is called. In
+ * general, it has to write one more deletion inode to the media, because if
+ * a commit happened between 'ubifs_jnl_update()' and
+ * 'ubifs_jnl_delete_inode()', the deletion inode is not in the journal
+ * anymore, and in fact it might not be on the flash anymore, because it might
+ * have been garbage-collected already. And for optimization reasons UBIFS does
+ * not read the orphan area if it has been unmounted cleanly, so it would have
+ * no indication in the journal that there is a deleted inode which has to be
+ * removed from TNC.
+ *
+ * However, if there was no commit between 'ubifs_jnl_update()' and
+ * 'ubifs_jnl_delete_inode()', then there is no need to write the deletion
+ * inode to the media for the second time. And this is quite a typical case.
+ *
+ * This function returns zero in case of success and a negative error code in
+ * case of failure.
+ */
+int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode)
+{
+	int err;
+	struct ubifs_inode *ui = ubifs_inode(inode);
+
+	ubifs_assert(inode->i_nlink == 0);
+
+	if (ui->del_cmtno != c->cmt_no)
+		/* A commit happened for sure */
+		return ubifs_jnl_write_inode(c, inode);
+
+	down_read(&c->commit_sem);
+	/*
+	 * Check commit number again, because the first test has been done
+	 * without @c->commit_sem, so a commit might have happened.
+	 */
+	if (ui->del_cmtno != c->cmt_no) {
+		up_read(&c->commit_sem);
+		return ubifs_jnl_write_inode(c, inode);
+	}
+
+	err = ubifs_tnc_remove_ino(c, inode->i_ino);
+	if (err)
+		ubifs_ro_mode(c, err);
+	else
+		ubifs_delete_orphan(c, inode->i_ino);
+	up_read(&c->commit_sem);
+	return err;
+}
+
 /**
  * ubifs_jnl_rename - rename a directory entry.
  * @c: UBIFS file-system description object
@@ -917,16 +970,16 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 
 	p = (void *)dent2 + aligned_dlen2;
 	if (new_inode) {
-		pack_inode(c, p, new_inode, 0, last_reference);
+		pack_inode(c, p, new_inode, 0);
 		p += ALIGN(ilen, 8);
 	}
 
 	if (!move)
-		pack_inode(c, p, old_dir, 1, 0);
+		pack_inode(c, p, old_dir, 1);
 	else {
-		pack_inode(c, p, old_dir, 0, 0);
+		pack_inode(c, p, old_dir, 0);
 		p += ALIGN(plen, 8);
-		pack_inode(c, p, new_dir, 1, 0);
+		pack_inode(c, p, new_dir, 1);
 	}
 
 	if (last_reference) {
@@ -935,6 +988,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 			release_head(c, BASEHD);
 			goto out_finish;
 		}
+		new_ui->del_cmtno = c->cmt_no;
 	}
 
 	err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync);
@@ -1131,7 +1185,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode,
 	if (err)
 		goto out_free;
 
-	pack_inode(c, ino, inode, 0, 0);
+	pack_inode(c, ino, inode, 0);
 	ubifs_prep_grp_node(c, trun, UBIFS_TRUN_NODE_SZ, dlen ? 0 : 1);
 	if (dlen)
 		ubifs_prep_grp_node(c, dn, dlen, 1);
@@ -1251,9 +1305,9 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host,
 	ubifs_prep_grp_node(c, xent, xlen, 0);
 
 	ino = (void *)xent + aligned_xlen;
-	pack_inode(c, ino, inode, 0, 1);
+	pack_inode(c, ino, inode, 0);
 	ino = (void *)ino + UBIFS_INO_NODE_SZ;
-	pack_inode(c, ino, host, 1, 0);
+	pack_inode(c, ino, host, 1);
 
 	err = write_head(c, BASEHD, xent, len, &lnum, &xent_offs, sync);
 	if (!sync && !err)
@@ -1320,7 +1374,7 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode,
 			   const struct inode *host)
 {
 	int err, len1, len2, aligned_len, aligned_len1, lnum, offs;
-	struct ubifs_inode *host_ui = ubifs_inode(inode);
+	struct ubifs_inode *host_ui = ubifs_inode(host);
 	struct ubifs_ino_node *ino;
 	union ubifs_key key;
 	int sync = IS_DIRSYNC(host);
@@ -1344,8 +1398,8 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode,
 	if (err)
 		goto out_free;
 
-	pack_inode(c, ino, host, 0, 0);
-	pack_inode(c, (void *)ino + aligned_len1, inode, 1, 0);
+	pack_inode(c, ino, host, 0);
+	pack_inode(c, (void *)ino + aligned_len1, inode, 1);
 
 	err = write_head(c, BASEHD, ino, aligned_len, &lnum, &offs, 0);
 	if (!sync && !err) {

fs/ubifs/log.c

@@ -317,6 +317,8 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs)
 	return 0;
 
 out_unlock:
+	if (err != -EAGAIN)
+		ubifs_ro_mode(c, err);
 	mutex_unlock(&c->log_mutex);
 	kfree(ref);
 	kfree(bud);
@@ -410,7 +412,7 @@ int ubifs_log_start_commit(struct ubifs_info *c, int *ltail_lnum)
 		return -ENOMEM;
 
 	cs->ch.node_type = UBIFS_CS_NODE;
-	cs->cmt_no = cpu_to_le64(c->cmt_no + 1);
+	cs->cmt_no = cpu_to_le64(c->cmt_no);
 	ubifs_prepare_node(c, cs, UBIFS_CS_NODE_SZ, 0);
 
 	/*

fs/ubifs/misc.h

@@ -79,20 +79,6 @@ static inline struct ubifs_inode *ubifs_inode(const struct inode *inode)
 	return container_of(inode, struct ubifs_inode, vfs_inode);
 }
 
-/**
- * ubifs_ro_mode - switch UBIFS to read read-only mode.
- * @c: UBIFS file-system description object
- * @err: error code which is the reason of switching to R/O mode
- */
-static inline void ubifs_ro_mode(struct ubifs_info *c, int err)
-{
-	if (!c->ro_media) {
-		c->ro_media = 1;
-		ubifs_warn("switched to read-only mode, error %d", err);
-		dbg_dump_stack();
-	}
-}
-
 /**
  * ubifs_compr_present - check if compressor was compiled in.
  * @compr_type: compressor type to check
@@ -322,7 +308,7 @@ static inline long long ubifs_reported_space(const struct ubifs_info *c,
 {
 	int divisor, factor;
 
-	divisor = UBIFS_MAX_DATA_NODE_SZ + (c->max_idx_node_sz << 1);
+	divisor = UBIFS_MAX_DATA_NODE_SZ + (c->max_idx_node_sz * 3);
 	factor = UBIFS_MAX_DATA_NODE_SZ - UBIFS_DATA_NODE_SZ;
 	do_div(free, divisor);
 

fs/ubifs/orphan.c

@@ -310,10 +310,10 @@ static int write_orph_node(struct ubifs_info *c, int atomic)
 	c->cmt_orphans -= cnt;
 	spin_unlock(&c->orphan_lock);
 	if (c->cmt_orphans)
-		orph->cmt_no = cpu_to_le64(c->cmt_no + 1);
+		orph->cmt_no = cpu_to_le64(c->cmt_no);
 	else
 		/* Mark the last node of the commit */
-		orph->cmt_no = cpu_to_le64((c->cmt_no + 1) | (1ULL << 63));
+		orph->cmt_no = cpu_to_le64((c->cmt_no) | (1ULL << 63));
 	ubifs_assert(c->ohead_offs + len <= c->leb_size);
 	ubifs_assert(c->ohead_lnum >= c->orph_first);
 	ubifs_assert(c->ohead_lnum <= c->orph_last);

fs/ubifs/super.c

@@ -30,7 +30,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
-#include <linux/random.h>
 #include <linux/kthread.h>
 #include <linux/parser.h>
 #include <linux/seq_file.h>
@@ -149,7 +148,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
 	if (err)
 		goto out_invalid;
 
-	/* Disable readahead */
+	/* Disable read-ahead */
 	inode->i_mapping->backing_dev_info = &c->bdi;
 
 	switch (inode->i_mode & S_IFMT) {
@@ -278,7 +277,7 @@ static void ubifs_destroy_inode(struct inode *inode)
  */
 static int ubifs_write_inode(struct inode *inode, int wait)
 {
-	int err;
+	int err = 0;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 	struct ubifs_inode *ui = ubifs_inode(inode);
 
@@ -299,10 +298,18 @@ static int ubifs_write_inode(struct inode *inode, int wait)
 		return 0;
 	}
 
-	dbg_gen("inode %lu", inode->i_ino);
-	err = ubifs_jnl_write_inode(c, inode, 0);
+	/*
+	 * As an optimization, do not write orphan inodes to the media just
+	 * because this is not needed.
+	 */
+	dbg_gen("inode %lu, mode %#x, nlink %u",
+		inode->i_ino, (int)inode->i_mode, inode->i_nlink);
+	if (inode->i_nlink) {
+		err = ubifs_jnl_write_inode(c, inode);
 		if (err)
-		ubifs_err("can't write inode %lu, error %d", inode->i_ino, err);
+			ubifs_err("can't write inode %lu, error %d",
+				  inode->i_ino, err);
+	}
 
 	ui->dirty = 0;
 	mutex_unlock(&ui->ui_mutex);
@@ -314,8 +321,9 @@ static void ubifs_delete_inode(struct inode *inode)
 {
 	int err;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
+	struct ubifs_inode *ui = ubifs_inode(inode);
 
-	if (ubifs_inode(inode)->xattr)
+	if (ui->xattr)
 		/*
 		 * Extended attribute inode deletions are fully handled in
 		 * 'ubifs_removexattr()'. These inodes are special and have
@@ -323,7 +331,7 @@ static void ubifs_delete_inode(struct inode *inode)
 		 */
 		goto out;
 
-	dbg_gen("inode %lu", inode->i_ino);
+	dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
 	ubifs_assert(!atomic_read(&inode->i_count));
 	ubifs_assert(inode->i_nlink == 0);
 
@@ -331,15 +339,19 @@ static void ubifs_delete_inode(struct inode *inode)
 	if (is_bad_inode(inode))
 		goto out;
 
-	ubifs_inode(inode)->ui_size = inode->i_size = 0;
-	err = ubifs_jnl_write_inode(c, inode, 1);
+	ui->ui_size = inode->i_size = 0;
+	err = ubifs_jnl_delete_inode(c, inode);
 	if (err)
 		/*
 		 * Worst case we have a lost orphan inode wasting space, so a
-		 * simple error message is ok here.
+		 * simple error message is OK here.
 		 */
-		ubifs_err("can't write inode %lu, error %d", inode->i_ino, err);
+		ubifs_err("can't delete inode %lu, error %d",
+			  inode->i_ino, err);
+
 out:
+	if (ui->dirty)
+		ubifs_release_dirty_inode_budget(c, ui);
 	clear_inode(inode);
 }
 
@@ -1122,8 +1134,8 @@ static int mount_ubifs(struct ubifs_info *c)
 	if (err)
 		goto out_infos;
 
-	ubifs_msg("mounted UBI device %d, volume %d", c->vi.ubi_num,
-		  c->vi.vol_id);
+	ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"",
+		  c->vi.ubi_num, c->vi.vol_id, c->vi.name);
 	if (mounted_read_only)
 		ubifs_msg("mounted read-only");
 	x = (long long)c->main_lebs * c->leb_size;
@@ -1469,6 +1481,7 @@ static void ubifs_put_super(struct super_block *sb)
 	 */
 	ubifs_assert(atomic_long_read(&c->dirty_pg_cnt) == 0);
 	ubifs_assert(c->budg_idx_growth == 0);
+	ubifs_assert(c->budg_dd_growth == 0);
 	ubifs_assert(c->budg_data_growth == 0);
 
 	/*
@@ -1657,7 +1670,6 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&c->orph_new);
 
 	c->highest_inum = UBIFS_FIRST_INO;
-	get_random_bytes(&c->vfs_gen, sizeof(int));
 	c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM;
 
 	ubi_get_volume_info(ubi, &c->vi);
@@ -1671,10 +1683,10 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/*
-	 * UBIFS provids 'backing_dev_info' in order to disable readahead. For
+	 * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
 	 * UBIFS, I/O is not deferred, it is done immediately in readpage,
 	 * which means the user would have to wait not just for their own I/O
-	 * but the readahead I/O as well i.e. completely pointless.
+	 * but the read-ahead I/O as well i.e. completely pointless.
 	 *
 	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
 	 */

fs/ubifs/tnc_commit.c

@@ -372,12 +372,15 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
 		written = layout_leb_in_gaps(c, p);
 		if (written < 0) {
 			err = written;
-			if (err == -ENOSPC) {
+			if (err != -ENOSPC) {
+				kfree(c->gap_lebs);
+				c->gap_lebs = NULL;
+				return err;
+			}
 			if (!dbg_force_in_the_gaps_enabled) {
 				/*
-					 * Do not print scary warnings if the
-					 * debugging option which forces
-					 * in-the-gaps is enabled.
+				 * Do not print scary warnings if the debugging
+				 * option which forces in-the-gaps is enabled.
 				 */
 				ubifs_err("out of space");
 				spin_lock(&c->space_lock);
@@ -389,10 +392,6 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
 			err = 0;
 			break;
 		}
-			kfree(c->gap_lebs);
-			c->gap_lebs = NULL;
-			return err;
-		}
 		p++;
 		cnt -= written;
 		leb_needed_cnt = get_leb_cnt(c, cnt);

fs/ubifs/ubifs-media.h

@@ -228,10 +228,10 @@ enum {
 /* Minimum number of orphan area logical eraseblocks */
 #define UBIFS_MIN_ORPH_LEBS 1
 /*
- * Minimum number of main area logical eraseblocks (buds, 2 for the index, 1
+ * Minimum number of main area logical eraseblocks (buds, 3 for the index, 1
  * for GC, 1 for deletions, and at least 1 for committed data).
  */
-#define UBIFS_MIN_MAIN_LEBS (UBIFS_MIN_BUD_LEBS + 5)
+#define UBIFS_MIN_MAIN_LEBS (UBIFS_MIN_BUD_LEBS + 6)
 
 /* Minimum number of logical eraseblocks */
 #define UBIFS_MIN_LEB_CNT (UBIFS_SB_LEBS + UBIFS_MST_LEBS + \

fs/ubifs/ubifs.h

@@ -20,8 +20,6 @@
  *          Adrian Hunter
  */
 
-/* Implementation version 0.7 */
-
 #ifndef __UBIFS_H__
 #define __UBIFS_H__
 
@@ -322,6 +320,8 @@ struct ubifs_gced_idx_leb {
  * struct ubifs_inode - UBIFS in-memory inode description.
  * @vfs_inode: VFS inode description object
  * @creat_sqnum: sequence number at time of creation
+ * @del_cmtno: commit number corresponding to the time the inode was deleted,
+ *             protected by @c->commit_sem;
  * @xattr_size: summarized size of all extended attributes in bytes
  * @xattr_cnt: count of extended attributes this inode has
  * @xattr_names: sum of lengths of all extended attribute names belonging to
@@ -373,6 +373,7 @@ struct ubifs_gced_idx_leb {
 struct ubifs_inode {
 	struct inode vfs_inode;
 	unsigned long long creat_sqnum;
+	unsigned long long del_cmtno;
 	unsigned int xattr_size;
 	unsigned int xattr_cnt;
 	unsigned int xattr_names;
@@ -779,7 +780,7 @@ struct ubifs_compressor {
 /**
  * struct ubifs_budget_req - budget requirements of an operation.
  *
- * @fast: non-zero if the budgeting should try to aquire budget quickly and
+ * @fast: non-zero if the budgeting should try to acquire budget quickly and
  *        should not try to call write-back
  * @recalculate: non-zero if @idx_growth, @data_growth, and @dd_growth fields
  *               have to be re-calculated
@@ -805,21 +806,31 @@ struct ubifs_compressor {
  * An inode may contain 4KiB of data at max., thus the widths of @new_ino_d
  * is 13 bits, and @dirtied_ino_d - 15, because up to 4 inodes may be made
  * dirty by the re-name operation.
+ *
+ * Note, UBIFS aligns node lengths to 8-bytes boundary, so the requester has to
+ * make sure the amount of inode data which contribute to @new_ino_d and
+ * @dirtied_ino_d fields are aligned.
  */
 struct ubifs_budget_req {
 	unsigned int fast:1;
 	unsigned int recalculate:1;
+#ifndef UBIFS_DEBUG
 	unsigned int new_page:1;
 	unsigned int dirtied_page:1;
 	unsigned int new_dent:1;
 	unsigned int mod_dent:1;
 	unsigned int new_ino:1;
 	unsigned int new_ino_d:13;
-#ifndef UBIFS_DEBUG
 	unsigned int dirtied_ino:4;
 	unsigned int dirtied_ino_d:15;
 #else
 	/* Not bit-fields to check for overflows */
+	unsigned int new_page;
+	unsigned int dirtied_page;
+	unsigned int new_dent;
+	unsigned int mod_dent;
+	unsigned int new_ino;
+	unsigned int new_ino_d;
 	unsigned int dirtied_ino;
 	unsigned int dirtied_ino_d;
 #endif
@@ -860,13 +871,13 @@ struct ubifs_mount_opts {
  * struct ubifs_info - UBIFS file-system description data structure
  * (per-superblock).
  * @vfs_sb: VFS @struct super_block object
- * @bdi: backing device info object to make VFS happy and disable readahead
+ * @bdi: backing device info object to make VFS happy and disable read-ahead
  *
  * @highest_inum: highest used inode number
- * @vfs_gen: VFS inode generation counter
  * @max_sqnum: current global sequence number
- * @cmt_no: commit number (last successfully completed commit)
- * @cnt_lock: protects @highest_inum, @vfs_gen, and @max_sqnum counters
+ * @cmt_no: commit number of the last successfully completed commit, protected
+ *          by @commit_sem
+ * @cnt_lock: protects @highest_inum and @max_sqnum counters
  * @fmt_version: UBIFS on-flash format version
  * @uuid: UUID from super block
  *
@@ -1103,7 +1114,6 @@ struct ubifs_info {
 	struct backing_dev_info bdi;
 
 	ino_t highest_inum;
-	unsigned int vfs_gen;
 	unsigned long long max_sqnum;
 	unsigned long long cmt_no;
 	spinlock_t cnt_lock;
@@ -1346,6 +1356,7 @@ extern struct backing_dev_info ubifs_backing_dev_info;
 extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
 
 /* io.c */
+void ubifs_ro_mode(struct ubifs_info *c, int err);
 int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len);
 int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs,
 			   int dtype);
@@ -1399,8 +1410,8 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 		     int deletion, int xent);
 int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
 			 const union ubifs_key *key, const void *buf, int len);
-int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode,
-			  int last_reference);
+int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode);
+int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode);
 int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		     const struct dentry *old_dentry,
 		     const struct inode *new_dir,

fs/ubifs/xattr.c

@@ -61,7 +61,7 @@
 
 /*
  * Limit the number of extended attributes per inode so that the total size
- * (xattr_size) is guaranteeded to fit in an 'unsigned int'.
+ * (@xattr_size) is guaranteeded to fit in an 'unsigned int'.
  */
 #define MAX_XATTRS_PER_INODE 65535
 
@@ -103,14 +103,14 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
 	struct inode *inode;
 	struct ubifs_inode *ui, *host_ui = ubifs_inode(host);
 	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
-					.new_ino_d = size, .dirtied_ino = 1,
-					.dirtied_ino_d = host_ui->data_len};
+				.new_ino_d = ALIGN(size, 8), .dirtied_ino = 1,
+				.dirtied_ino_d = ALIGN(host_ui->data_len, 8) };
 
 	if (host_ui->xattr_cnt >= MAX_XATTRS_PER_INODE)
 		return -ENOSPC;
 	/*
 	 * Linux limits the maximum size of the extended attribute names list
-	 * to %XATTR_LIST_MAX. This means we should not allow creating more*
+	 * to %XATTR_LIST_MAX. This means we should not allow creating more
 	 * extended attributes if the name list becomes larger. This limitation
 	 * is artificial for UBIFS, though.
 	 */
@@ -128,7 +128,6 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
 		goto out_budg;
 	}
 
-	mutex_lock(&host_ui->ui_mutex);
 	/* Re-define all operations to be "nothing" */
 	inode->i_mapping->a_ops = &none_address_operations;
 	inode->i_op = &none_inode_operations;
@@ -141,23 +140,19 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
 	ui->data = kmalloc(size, GFP_NOFS);
 	if (!ui->data) {
 		err = -ENOMEM;
-		goto out_unlock;
+		goto out_free;
 	}
-
 	memcpy(ui->data, value, size);
+	inode->i_size = ui->ui_size = size;
+	ui->data_len = size;
+
+	mutex_lock(&host_ui->ui_mutex);
 	host->i_ctime = ubifs_current_time(host);
 	host_ui->xattr_cnt += 1;
 	host_ui->xattr_size += CALC_DENT_SIZE(nm->len);
 	host_ui->xattr_size += CALC_XATTR_BYTES(size);
 	host_ui->xattr_names += nm->len;
 
-	/*
-	 * We do not use i_size_write() because nobody can race with us as we
-	 * are holding host @host->i_mutex - every xattr operation for this
-	 * inode is serialized by it.
-	 */
-	inode->i_size = ui->ui_size = size;
-	ui->data_len = size;
 	err = ubifs_jnl_update(c, host, nm, inode, 0, 1);
 	if (err)
 		goto out_cancel;
@@ -172,8 +167,8 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
 	host_ui->xattr_cnt -= 1;
 	host_ui->xattr_size -= CALC_DENT_SIZE(nm->len);
 	host_ui->xattr_size -= CALC_XATTR_BYTES(size);
-out_unlock:
 	mutex_unlock(&host_ui->ui_mutex);
+out_free:
 	make_bad_inode(inode);
 	iput(inode);
 out_budg:
@@ -200,29 +195,28 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 	struct ubifs_inode *host_ui = ubifs_inode(host);
 	struct ubifs_inode *ui = ubifs_inode(inode);
 	struct ubifs_budget_req req = { .dirtied_ino = 2,
-				.dirtied_ino_d = size + host_ui->data_len };
+		.dirtied_ino_d = ALIGN(size, 8) + ALIGN(host_ui->data_len, 8) };
 
 	ubifs_assert(ui->data_len == inode->i_size);
 	err = ubifs_budget_space(c, &req);
 	if (err)
 		return err;
 
-	mutex_lock(&host_ui->ui_mutex);
-	host->i_ctime = ubifs_current_time(host);
-	host_ui->xattr_size -= CALC_XATTR_BYTES(ui->data_len);
-	host_ui->xattr_size += CALC_XATTR_BYTES(size);
-
 	kfree(ui->data);
 	ui->data = kmalloc(size, GFP_NOFS);
 	if (!ui->data) {
 		err = -ENOMEM;
-		goto out_unlock;
+		goto out_free;
 	}
-
 	memcpy(ui->data, value, size);
 	inode->i_size = ui->ui_size = size;
 	ui->data_len = size;
 
+	mutex_lock(&host_ui->ui_mutex);
+	host->i_ctime = ubifs_current_time(host);
+	host_ui->xattr_size -= CALC_XATTR_BYTES(ui->data_len);
+	host_ui->xattr_size += CALC_XATTR_BYTES(size);
+
 	/*
 	 * It is important to write the host inode after the xattr inode
 	 * because if the host inode gets synchronized (via 'fsync()'), then
@@ -240,9 +234,9 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 out_cancel:
 	host_ui->xattr_size -= CALC_XATTR_BYTES(size);
 	host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len);
-	make_bad_inode(inode);
-out_unlock:
 	mutex_unlock(&host_ui->ui_mutex);
+	make_bad_inode(inode);
+out_free:
 	ubifs_release_budget(c, &req);
 	return err;
 }
@@ -312,6 +306,7 @@ int ubifs_setxattr(struct dentry *dentry, const char *name,
 
 	dbg_gen("xattr '%s', host ino %lu ('%.*s'), size %zd", name,
 		host->i_ino, dentry->d_name.len, dentry->d_name.name, size);
+	ubifs_assert(mutex_is_locked(&host->i_mutex));
 
 	if (size > UBIFS_MAX_INO_DATA)
 		return -ERANGE;
@@ -384,7 +379,6 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
 	if (!xent)
 		return -ENOMEM;
 
-	mutex_lock(&host->i_mutex);
 	xent_key_init(c, &key, host->i_ino, &nm);
 	err = ubifs_tnc_lookup_nm(c, &key, xent, &nm);
 	if (err) {
@@ -419,7 +413,6 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
 out_iput:
 	iput(inode);
 out_unlock:
-	mutex_unlock(&host->i_mutex);
 	kfree(xent);
 	return err;
 }
@@ -449,8 +442,6 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		return -ERANGE;
 
 	lowest_xent_key(c, &key, host->i_ino);
-
-	mutex_lock(&host->i_mutex);
 	while (1) {
 		int type;
 
@@ -479,7 +470,6 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		pxent = xent;
 		key_read(c, &xent->key, &key);
 	}
-	mutex_unlock(&host->i_mutex);
 
 	kfree(pxent);
 	if (err != -ENOENT) {
@@ -497,8 +487,8 @@ static int remove_xattr(struct ubifs_info *c, struct inode *host,
 	int err;
 	struct ubifs_inode *host_ui = ubifs_inode(host);
 	struct ubifs_inode *ui = ubifs_inode(inode);
-	struct ubifs_budget_req req = { .dirtied_ino = 1, .mod_dent = 1,
-					.dirtied_ino_d = host_ui->data_len };
+	struct ubifs_budget_req req = { .dirtied_ino = 2, .mod_dent = 1,
+				.dirtied_ino_d = ALIGN(host_ui->data_len, 8) };
 
 	ubifs_assert(ui->data_len == inode->i_size);