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

* 'linux-next' of git://git.infradead.org/ubifs-2.6: (25 commits)
  UBIFS: fix ubifs_compress commentary
  UBIFS: amend printk
  UBIFS: do not read unnecessary bytes when unpacking bits
  UBIFS: check buffer length when scanning for LPT nodes
  UBIFS: correct condition to eliminate unecessary assignment
  UBIFS: add more debugging messages for LPT
  UBIFS: fix bulk-read handling uptodate pages
  UBIFS: improve garbage collection
  UBIFS: allow for sync_fs when read-only
  UBIFS: commit on sync_fs
  UBIFS: correct comment for commit_on_unmount
  UBIFS: update dbg_dump_inode
  UBIFS: fix commentary
  UBIFS: fix races in bit-fields
  UBIFS: ensure data read beyond i_size is zeroed out correctly
  UBIFS: correct key comparison
  UBIFS: use bit-fields when possible
  UBIFS: check data CRC when in error state
  UBIFS: improve znode splitting rules
  UBIFS: add no_chk_data_crc mount option
  ...

Documentation/filesystems/ubifs.txt

@@ -86,6 +86,15 @@ norm_unmount (*)	commit on unmount; the journal is committed
 fast_unmount		do not commit on unmount; this option makes
 			unmount faster, but the next mount slower
 			because of the need to replay the journal.
+bulk_read		read more in one go to take advantage of flash
+			media that read faster sequentially
+no_bulk_read (*)	do not bulk-read
+no_chk_data_crc		skip checking of CRCs on data nodes in order to
+			improve read performance. Use this option only
+			if the flash media is highly reliable. The effect
+			of this option is that corruption of the contents
+			of a file can go unnoticed.
+chk_data_crc (*)	do not skip checking CRCs on data nodes
 
 
 Quick usage instructions

fs/ubifs/budget.c

@@ -414,19 +414,21 @@ static int do_budget_space(struct ubifs_info *c)
 	 *    @c->lst.empty_lebs + @c->freeable_cnt + @c->idx_gc_cnt -
 	 *    @c->lst.taken_empty_lebs
 	 *
-	 * @empty_lebs are available because they are empty. @freeable_cnt are
-	 * available because they contain only free and dirty space and the
-	 * index allocation always occurs after wbufs are synch'ed.
-	 * @idx_gc_cnt are available because they are index LEBs that have been
-	 * garbage collected (including trivial GC) and are awaiting the commit
-	 * before they can be unmapped - note that the in-the-gaps method will
-	 * grab these if it needs them. @taken_empty_lebs are empty_lebs that
-	 * have already been allocated for some purpose (also includes those
-	 * LEBs on the @idx_gc list).
+	 * @c->lst.empty_lebs are available because they are empty.
+	 * @c->freeable_cnt are available because they contain only free and
+	 * dirty space, @c->idx_gc_cnt are available because they are index
+	 * LEBs that have been garbage collected and are awaiting the commit
+	 * before they can be used. And the in-the-gaps method will grab these
+	 * if it needs them. @c->lst.taken_empty_lebs are empty LEBs that have
+	 * already been allocated for some purpose.
 	 *
-	 * Note, @taken_empty_lebs may temporarily be higher by one because of
-	 * the way we serialize LEB allocations and budgeting. See a comment in
-	 * 'ubifs_find_free_space()'.
+	 * Note, @c->idx_gc_cnt is included to both @c->lst.empty_lebs (because
+	 * these LEBs are empty) and to @c->lst.taken_empty_lebs (because they
+	 * are taken until after the commit).
+	 *
+	 * Note, @c->lst.taken_empty_lebs may temporarily be higher by one
+	 * because of the way we serialize LEB allocations and budgeting. See a
+	 * comment in 'ubifs_find_free_space()'.
 	 */
 	lebs = c->lst.empty_lebs + c->freeable_cnt + c->idx_gc_cnt -
 	       c->lst.taken_empty_lebs;

fs/ubifs/compress.c

@@ -91,8 +91,6 @@ struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
  *
  * Note, if the input buffer was not compressed, it is copied to the output
  * buffer and %UBIFS_COMPR_NONE is returned in @compr_type.
- *
- * This functions returns %0 on success or a negative error code on failure.
  */
 void ubifs_compress(const void *in_buf, int in_len, void *out_buf, int *out_len,
 		    int *compr_type)

fs/ubifs/debug.c

@@ -222,30 +222,38 @@ void dbg_dump_inode(const struct ubifs_info *c, const struct inode *inode)
 {
 	const struct ubifs_inode *ui = ubifs_inode(inode);
 
-	printk(KERN_DEBUG "inode      %lu\n", inode->i_ino);
-	printk(KERN_DEBUG "size       %llu\n",
+	printk(KERN_DEBUG "Dump in-memory inode:");
+	printk(KERN_DEBUG "\tinode          %lu\n", inode->i_ino);
+	printk(KERN_DEBUG "\tsize           %llu\n",
 	       (unsigned long long)i_size_read(inode));
-	printk(KERN_DEBUG "nlink      %u\n", inode->i_nlink);
-	printk(KERN_DEBUG "uid        %u\n", (unsigned int)inode->i_uid);
-	printk(KERN_DEBUG "gid        %u\n", (unsigned int)inode->i_gid);
-	printk(KERN_DEBUG "atime      %u.%u\n",
+	printk(KERN_DEBUG "\tnlink          %u\n", inode->i_nlink);
+	printk(KERN_DEBUG "\tuid            %u\n", (unsigned int)inode->i_uid);
+	printk(KERN_DEBUG "\tgid            %u\n", (unsigned int)inode->i_gid);
+	printk(KERN_DEBUG "\tatime          %u.%u\n",
 	       (unsigned int)inode->i_atime.tv_sec,
 	       (unsigned int)inode->i_atime.tv_nsec);
-	printk(KERN_DEBUG "mtime      %u.%u\n",
+	printk(KERN_DEBUG "\tmtime          %u.%u\n",
 	       (unsigned int)inode->i_mtime.tv_sec,
 	       (unsigned int)inode->i_mtime.tv_nsec);
-	printk(KERN_DEBUG "ctime       %u.%u\n",
+	printk(KERN_DEBUG "\tctime          %u.%u\n",
 	       (unsigned int)inode->i_ctime.tv_sec,
 	       (unsigned int)inode->i_ctime.tv_nsec);
-	printk(KERN_DEBUG "creat_sqnum %llu\n", ui->creat_sqnum);
-	printk(KERN_DEBUG "xattr_size  %u\n", ui->xattr_size);
-	printk(KERN_DEBUG "xattr_cnt   %u\n", ui->xattr_cnt);
-	printk(KERN_DEBUG "xattr_names %u\n", ui->xattr_names);
-	printk(KERN_DEBUG "dirty       %u\n", ui->dirty);
-	printk(KERN_DEBUG "xattr       %u\n", ui->xattr);
-	printk(KERN_DEBUG "flags       %d\n", ui->flags);
-	printk(KERN_DEBUG "compr_type  %d\n", ui->compr_type);
-	printk(KERN_DEBUG "data_len    %d\n", ui->data_len);
+	printk(KERN_DEBUG "\tcreat_sqnum    %llu\n", ui->creat_sqnum);
+	printk(KERN_DEBUG "\txattr_size     %u\n", ui->xattr_size);
+	printk(KERN_DEBUG "\txattr_cnt      %u\n", ui->xattr_cnt);
+	printk(KERN_DEBUG "\txattr_names    %u\n", ui->xattr_names);
+	printk(KERN_DEBUG "\tdirty          %u\n", ui->dirty);
+	printk(KERN_DEBUG "\txattr          %u\n", ui->xattr);
+	printk(KERN_DEBUG "\tbulk_read      %u\n", ui->xattr);
+	printk(KERN_DEBUG "\tsynced_i_size  %llu\n",
+	       (unsigned long long)ui->synced_i_size);
+	printk(KERN_DEBUG "\tui_size        %llu\n",
+	       (unsigned long long)ui->ui_size);
+	printk(KERN_DEBUG "\tflags          %d\n", ui->flags);
+	printk(KERN_DEBUG "\tcompr_type     %d\n", ui->compr_type);
+	printk(KERN_DEBUG "\tlast_page_read %lu\n", ui->last_page_read);
+	printk(KERN_DEBUG "\tread_in_a_row  %lu\n", ui->read_in_a_row);
+	printk(KERN_DEBUG "\tdata_len       %d\n", ui->data_len);
 }
 
 void dbg_dump_node(const struct ubifs_info *c, const void *node)
@@ -647,6 +655,43 @@ void dbg_dump_lprops(struct ubifs_info *c)
 	}
 }
 
+void dbg_dump_lpt_info(struct ubifs_info *c)
+{
+	int i;
+
+	spin_lock(&dbg_lock);
+	printk(KERN_DEBUG "\tlpt_sz:        %lld\n", c->lpt_sz);
+	printk(KERN_DEBUG "\tpnode_sz:      %d\n", c->pnode_sz);
+	printk(KERN_DEBUG "\tnnode_sz:      %d\n", c->nnode_sz);
+	printk(KERN_DEBUG "\tltab_sz:       %d\n", c->ltab_sz);
+	printk(KERN_DEBUG "\tlsave_sz:      %d\n", c->lsave_sz);
+	printk(KERN_DEBUG "\tbig_lpt:       %d\n", c->big_lpt);
+	printk(KERN_DEBUG "\tlpt_hght:      %d\n", c->lpt_hght);
+	printk(KERN_DEBUG "\tpnode_cnt:     %d\n", c->pnode_cnt);
+	printk(KERN_DEBUG "\tnnode_cnt:     %d\n", c->nnode_cnt);
+	printk(KERN_DEBUG "\tdirty_pn_cnt:  %d\n", c->dirty_pn_cnt);
+	printk(KERN_DEBUG "\tdirty_nn_cnt:  %d\n", c->dirty_nn_cnt);
+	printk(KERN_DEBUG "\tlsave_cnt:     %d\n", c->lsave_cnt);
+	printk(KERN_DEBUG "\tspace_bits:    %d\n", c->space_bits);
+	printk(KERN_DEBUG "\tlpt_lnum_bits: %d\n", c->lpt_lnum_bits);
+	printk(KERN_DEBUG "\tlpt_offs_bits: %d\n", c->lpt_offs_bits);
+	printk(KERN_DEBUG "\tlpt_spc_bits:  %d\n", c->lpt_spc_bits);
+	printk(KERN_DEBUG "\tpcnt_bits:     %d\n", c->pcnt_bits);
+	printk(KERN_DEBUG "\tlnum_bits:     %d\n", c->lnum_bits);
+	printk(KERN_DEBUG "\tLPT root is at %d:%d\n", c->lpt_lnum, c->lpt_offs);
+	printk(KERN_DEBUG "\tLPT head is at %d:%d\n",
+	       c->nhead_lnum, c->nhead_offs);
+	printk(KERN_DEBUG "\tLPT ltab is at %d:%d\n", c->ltab_lnum, c->ltab_offs);
+	if (c->big_lpt)
+		printk(KERN_DEBUG "\tLPT lsave is at %d:%d\n",
+		       c->lsave_lnum, c->lsave_offs);
+	for (i = 0; i < c->lpt_lebs; i++)
+		printk(KERN_DEBUG "\tLPT LEB %d free %d dirty %d tgc %d "
+		       "cmt %d\n", i + c->lpt_first, c->ltab[i].free,
+		       c->ltab[i].dirty, c->ltab[i].tgc, c->ltab[i].cmt);
+	spin_unlock(&dbg_lock);
+}
+
 void dbg_dump_leb(const struct ubifs_info *c, int lnum)
 {
 	struct ubifs_scan_leb *sleb;

fs/ubifs/debug.h

@@ -224,6 +224,7 @@ void dbg_dump_lstats(const struct ubifs_lp_stats *lst);
 void dbg_dump_budg(struct ubifs_info *c);
 void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp);
 void dbg_dump_lprops(struct ubifs_info *c);
+void dbg_dump_lpt_info(struct ubifs_info *c);
 void dbg_dump_leb(const struct ubifs_info *c, int lnum);
 void dbg_dump_znode(const struct ubifs_info *c,
 		    const struct ubifs_znode *znode);
@@ -249,6 +250,8 @@ 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_chk_lpt_free_spc(struct ubifs_info *c);
+int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len);
 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);
@@ -367,6 +370,7 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum,
 #define dbg_dump_budg(c)                      ({})
 #define dbg_dump_lprop(c, lp)                 ({})
 #define dbg_dump_lprops(c)                    ({})
+#define dbg_dump_lpt_info(c)                  ({})
 #define dbg_dump_leb(c, lnum)                 ({})
 #define dbg_dump_znode(c, znode)              ({})
 #define dbg_dump_heap(c, heap, cat)           ({})
@@ -379,6 +383,8 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum,
 #define dbg_check_old_index(c, zroot)              0
 #define dbg_check_cats(c)                          0
 #define dbg_check_ltab(c)                          0
+#define dbg_chk_lpt_free_spc(c)                    0
+#define dbg_chk_lpt_sz(c, action, len)             0
 #define dbg_check_synced_i_size(inode)             0
 #define dbg_check_dir_size(c, dir)                 0
 #define dbg_check_tnc(c, x)                        0

fs/ubifs/file.c

@@ -147,6 +147,12 @@ static int do_readpage(struct page *page)
 				err = ret;
 				if (err != -ENOENT)
 					break;
+			} else if (block + 1 == beyond) {
+				int dlen = le32_to_cpu(dn->size);
+				int ilen = i_size & (UBIFS_BLOCK_SIZE - 1);
+
+				if (ilen && ilen < dlen)
+					memset(addr + ilen, 0, dlen - ilen);
 			}
 		}
 		if (++i >= UBIFS_BLOCKS_PER_PAGE)
@@ -577,8 +583,262 @@ out:
 	return copied;
 }
 
+/**
+ * populate_page - copy data nodes into a page for bulk-read.
+ * @c: UBIFS file-system description object
+ * @page: page
+ * @bu: bulk-read information
+ * @n: next zbranch slot
+ *
+ * This function returns %0 on success and a negative error code on failure.
+ */
+static int populate_page(struct ubifs_info *c, struct page *page,
+			 struct bu_info *bu, int *n)
+{
+	int i = 0, nn = *n, offs = bu->zbranch[0].offs, hole = 0, read = 0;
+	struct inode *inode = page->mapping->host;
+	loff_t i_size = i_size_read(inode);
+	unsigned int page_block;
+	void *addr, *zaddr;
+	pgoff_t end_index;
+
+	dbg_gen("ino %lu, pg %lu, i_size %lld, flags %#lx",
+		inode->i_ino, page->index, i_size, page->flags);
+
+	addr = zaddr = kmap(page);
+
+	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+	if (!i_size || page->index > end_index) {
+		hole = 1;
+		memset(addr, 0, PAGE_CACHE_SIZE);
+		goto out_hole;
+	}
+
+	page_block = page->index << UBIFS_BLOCKS_PER_PAGE_SHIFT;
+	while (1) {
+		int err, len, out_len, dlen;
+
+		if (nn >= bu->cnt) {
+			hole = 1;
+			memset(addr, 0, UBIFS_BLOCK_SIZE);
+		} else if (key_block(c, &bu->zbranch[nn].key) == page_block) {
+			struct ubifs_data_node *dn;
+
+			dn = bu->buf + (bu->zbranch[nn].offs - offs);
+
+			ubifs_assert(dn->ch.sqnum >
+				     ubifs_inode(inode)->creat_sqnum);
+
+			len = le32_to_cpu(dn->size);
+			if (len <= 0 || len > UBIFS_BLOCK_SIZE)
+				goto out_err;
+
+			dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ;
+			out_len = UBIFS_BLOCK_SIZE;
+			err = ubifs_decompress(&dn->data, dlen, addr, &out_len,
+					       le16_to_cpu(dn->compr_type));
+			if (err || len != out_len)
+				goto out_err;
+
+			if (len < UBIFS_BLOCK_SIZE)
+				memset(addr + len, 0, UBIFS_BLOCK_SIZE - len);
+
+			nn += 1;
+			read = (i << UBIFS_BLOCK_SHIFT) + len;
+		} else if (key_block(c, &bu->zbranch[nn].key) < page_block) {
+			nn += 1;
+			continue;
+		} else {
+			hole = 1;
+			memset(addr, 0, UBIFS_BLOCK_SIZE);
+		}
+		if (++i >= UBIFS_BLOCKS_PER_PAGE)
+			break;
+		addr += UBIFS_BLOCK_SIZE;
+		page_block += 1;
+	}
+
+	if (end_index == page->index) {
+		int len = i_size & (PAGE_CACHE_SIZE - 1);
+
+		if (len && len < read)
+			memset(zaddr + len, 0, read - len);
+	}
+
+out_hole:
+	if (hole) {
+		SetPageChecked(page);
+		dbg_gen("hole");
+	}
+
+	SetPageUptodate(page);
+	ClearPageError(page);
+	flush_dcache_page(page);
+	kunmap(page);
+	*n = nn;
+	return 0;
+
+out_err:
+	ClearPageUptodate(page);
+	SetPageError(page);
+	flush_dcache_page(page);
+	kunmap(page);
+	ubifs_err("bad data node (block %u, inode %lu)",
+		  page_block, inode->i_ino);
+	return -EINVAL;
+}
+
+/**
+ * ubifs_do_bulk_read - do bulk-read.
+ * @c: UBIFS file-system description object
+ * @page1: first page
+ *
+ * This function returns %1 if the bulk-read is done, otherwise %0 is returned.
+ */
+static int ubifs_do_bulk_read(struct ubifs_info *c, struct page *page1)
+{
+	pgoff_t offset = page1->index, end_index;
+	struct address_space *mapping = page1->mapping;
+	struct inode *inode = mapping->host;
+	struct ubifs_inode *ui = ubifs_inode(inode);
+	struct bu_info *bu;
+	int err, page_idx, page_cnt, ret = 0, n = 0;
+	loff_t isize;
+
+	bu = kmalloc(sizeof(struct bu_info), GFP_NOFS);
+	if (!bu)
+		return 0;
+
+	bu->buf_len = c->bulk_read_buf_size;
+	bu->buf = kmalloc(bu->buf_len, GFP_NOFS);
+	if (!bu->buf)
+		goto out_free;
+
+	data_key_init(c, &bu->key, inode->i_ino,
+		      offset << UBIFS_BLOCKS_PER_PAGE_SHIFT);
+
+	err = ubifs_tnc_get_bu_keys(c, bu);
+	if (err)
+		goto out_warn;
+
+	if (bu->eof) {
+		/* Turn off bulk-read at the end of the file */
+		ui->read_in_a_row = 1;
+		ui->bulk_read = 0;
+	}
+
+	page_cnt = bu->blk_cnt >> UBIFS_BLOCKS_PER_PAGE_SHIFT;
+	if (!page_cnt) {
+		/*
+		 * This happens when there are multiple blocks per page and the
+		 * blocks for the first page we are looking for, are not
+		 * together. If all the pages were like this, bulk-read would
+		 * reduce performance, so we turn it off for a while.
+		 */
+		ui->read_in_a_row = 0;
+		ui->bulk_read = 0;
+		goto out_free;
+	}
+
+	if (bu->cnt) {
+		err = ubifs_tnc_bulk_read(c, bu);
+		if (err)
+			goto out_warn;
+	}
+
+	err = populate_page(c, page1, bu, &n);
+	if (err)
+		goto out_warn;
+
+	unlock_page(page1);
+	ret = 1;
+
+	isize = i_size_read(inode);
+	if (isize == 0)
+		goto out_free;
+	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+
+	for (page_idx = 1; page_idx < page_cnt; page_idx++) {
+		pgoff_t page_offset = offset + page_idx;
+		struct page *page;
+
+		if (page_offset > end_index)
+			break;
+		page = find_or_create_page(mapping, page_offset,
+					   GFP_NOFS | __GFP_COLD);
+		if (!page)
+			break;
+		if (!PageUptodate(page))
+			err = populate_page(c, page, bu, &n);
+		unlock_page(page);
+		page_cache_release(page);
+		if (err)
+			break;
+	}
+
+	ui->last_page_read = offset + page_idx - 1;
+
+out_free:
+	kfree(bu->buf);
+	kfree(bu);
+	return ret;
+
+out_warn:
+	ubifs_warn("ignoring error %d and skipping bulk-read", err);
+	goto out_free;
+}
+
+/**
+ * ubifs_bulk_read - determine whether to bulk-read and, if so, do it.
+ * @page: page from which to start bulk-read.
+ *
+ * Some flash media are capable of reading sequentially at faster rates. UBIFS
+ * bulk-read facility is designed to take advantage of that, by reading in one
+ * go consecutive data nodes that are also located consecutively in the same
+ * LEB. This function returns %1 if a bulk-read is done and %0 otherwise.
+ */
+static int ubifs_bulk_read(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct ubifs_info *c = inode->i_sb->s_fs_info;
+	struct ubifs_inode *ui = ubifs_inode(inode);
+	pgoff_t index = page->index, last_page_read = ui->last_page_read;
+	int ret = 0;
+
+	ui->last_page_read = index;
+
+	if (!c->bulk_read)
+		return 0;
+	/*
+	 * Bulk-read is protected by ui_mutex, but it is an optimization, so
+	 * don't bother if we cannot lock the mutex.
+	 */
+	if (!mutex_trylock(&ui->ui_mutex))
+		return 0;
+	if (index != last_page_read + 1) {
+		/* Turn off bulk-read if we stop reading sequentially */
+		ui->read_in_a_row = 1;
+		if (ui->bulk_read)
+			ui->bulk_read = 0;
+		goto out_unlock;
+	}
+	if (!ui->bulk_read) {
+		ui->read_in_a_row += 1;
+		if (ui->read_in_a_row < 3)
+			goto out_unlock;
+		/* Three reads in a row, so switch on bulk-read */
+		ui->bulk_read = 1;
+	}
+	ret = ubifs_do_bulk_read(c, page);
+out_unlock:
+	mutex_unlock(&ui->ui_mutex);
+	return ret;
+}
+
 static int ubifs_readpage(struct file *file, struct page *page)
 {
+	if (ubifs_bulk_read(page))
+		return 0;
 	do_readpage(page);
 	unlock_page(page);
 	return 0;

fs/ubifs/find.c

@@ -901,11 +901,11 @@ static int get_idx_gc_leb(struct ubifs_info *c)
 	 * it is needed now for this commit.
 	 */
 	lp = ubifs_lpt_lookup_dirty(c, lnum);
-	if (unlikely(IS_ERR(lp)))
+	if (IS_ERR(lp))
 		return PTR_ERR(lp);
 	lp = ubifs_change_lp(c, lp, LPROPS_NC, LPROPS_NC,
 			     lp->flags | LPROPS_INDEX, -1);
-	if (unlikely(IS_ERR(lp)))
+	if (IS_ERR(lp))
 		return PTR_ERR(lp);
 	dbg_find("LEB %d, dirty %d and free %d flags %#x",
 		 lp->lnum, lp->dirty, lp->free, lp->flags);

fs/ubifs/gc.c

@@ -95,6 +95,48 @@ static int switch_gc_head(struct ubifs_info *c)
 	return err;
 }
 
+/**
+ * joinup - bring data nodes for an inode together.
+ * @c: UBIFS file-system description object
+ * @sleb: describes scanned LEB
+ * @inum: inode number
+ * @blk: block number
+ * @data: list to which to add data nodes
+ *
+ * This function looks at the first few nodes in the scanned LEB @sleb and adds
+ * them to @data if they are data nodes from @inum and have a larger block
+ * number than @blk. This function returns %0 on success and a negative error
+ * code on failure.
+ */
+static int joinup(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ino_t inum,
+		  unsigned int blk, struct list_head *data)
+{
+	int err, cnt = 6, lnum = sleb->lnum, offs;
+	struct ubifs_scan_node *snod, *tmp;
+	union ubifs_key *key;
+
+	list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) {
+		key = &snod->key;
+		if (key_inum(c, key) == inum &&
+		    key_type(c, key) == UBIFS_DATA_KEY &&
+		    key_block(c, key) > blk) {
+			offs = snod->offs;
+			err = ubifs_tnc_has_node(c, key, 0, lnum, offs, 0);
+			if (err < 0)
+				return err;
+			list_del(&snod->list);
+			if (err) {
+				list_add_tail(&snod->list, data);
+				blk = key_block(c, key);
+			} else
+				kfree(snod);
+			cnt = 6;
+		} else if (--cnt == 0)
+			break;
+	}
+	return 0;
+}
+
 /**
  * move_nodes - move nodes.
  * @c: UBIFS file-system description object
@@ -116,16 +158,21 @@ static int switch_gc_head(struct ubifs_info *c)
 static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
 {
 	struct ubifs_scan_node *snod, *tmp;
-	struct list_head large, medium, small;
+	struct list_head data, large, medium, small;
 	struct ubifs_wbuf *wbuf = &c->jheads[GCHD].wbuf;
 	int avail, err, min = INT_MAX;
+	unsigned int blk = 0;
+	ino_t inum = 0;
 
+	INIT_LIST_HEAD(&data);
 	INIT_LIST_HEAD(&large);
 	INIT_LIST_HEAD(&medium);
 	INIT_LIST_HEAD(&small);
 
-	list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) {
-		struct list_head *lst;
+	while (!list_empty(&sleb->nodes)) {
+		struct list_head *lst = sleb->nodes.next;
+
+		snod = list_entry(lst, struct ubifs_scan_node, list);
 
 		ubifs_assert(snod->type != UBIFS_IDX_NODE);
 		ubifs_assert(snod->type != UBIFS_REF_NODE);
@@ -136,7 +183,6 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
 		if (err < 0)
 			goto out;
 
-		lst = &snod->list;
 		list_del(lst);
 		if (!err) {
 			/* The node is obsolete, remove it from the list */
@@ -145,15 +191,30 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
 		}
 
 		/*
-		 * Sort the list of nodes so that large nodes go first, and
-		 * small nodes go last.
+		 * Sort the list of nodes so that data nodes go first, large
+		 * nodes go second, and small nodes go last.
 		 */
-		if (snod->len > MEDIUM_NODE_WM)
-			list_add(lst, &large);
+		if (key_type(c, &snod->key) == UBIFS_DATA_KEY) {
+			if (inum != key_inum(c, &snod->key)) {
+				if (inum) {
+					/*
+					 * Try to move data nodes from the same
+					 * inode together.
+					 */
+					err = joinup(c, sleb, inum, blk, &data);
+					if (err)
+						goto out;
+				}
+				inum = key_inum(c, &snod->key);
+				blk = key_block(c, &snod->key);
+			}
+			list_add_tail(lst, &data);
+		} else if (snod->len > MEDIUM_NODE_WM)
+			list_add_tail(lst, &large);
 		else if (snod->len > SMALL_NODE_WM)
-			list_add(lst, &medium);
+			list_add_tail(lst, &medium);
 		else
-			list_add(lst, &small);
+			list_add_tail(lst, &small);
 
 		/* And find the smallest node */
 		if (snod->len < min)
@@ -164,6 +225,7 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
 	 * Join the tree lists so that we'd have one roughly sorted list
 	 * ('large' will be the head of the joined list).
 	 */
+	list_splice(&data, &large);
 	list_splice(&medium, large.prev);
 	list_splice(&small, large.prev);
 
@@ -653,7 +715,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
 	 */
 	while (1) {
 		lp = ubifs_fast_find_freeable(c);
-		if (unlikely(IS_ERR(lp))) {
+		if (IS_ERR(lp)) {
 			err = PTR_ERR(lp);
 			goto out;
 		}
@@ -665,7 +727,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
 		if (err)
 			goto out;
 		lp = ubifs_change_lp(c, lp, c->leb_size, 0, lp->flags, 0);
-		if (unlikely(IS_ERR(lp))) {
+		if (IS_ERR(lp)) {
 			err = PTR_ERR(lp);
 			goto out;
 		}
@@ -680,7 +742,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
 	/* Record index freeable LEBs for unmapping after commit */
 	while (1) {
 		lp = ubifs_fast_find_frdi_idx(c);
-		if (unlikely(IS_ERR(lp))) {
+		if (IS_ERR(lp)) {
 			err = PTR_ERR(lp);
 			goto out;
 		}
@@ -696,7 +758,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
 		/* Don't release the LEB until after the next commit */
 		flags = (lp->flags | LPROPS_TAKEN) ^ LPROPS_INDEX;
 		lp = ubifs_change_lp(c, lp, c->leb_size, 0, flags, 1);
-		if (unlikely(IS_ERR(lp))) {
+		if (IS_ERR(lp)) {
 			err = PTR_ERR(lp);
 			kfree(idx_gc);
 			goto out;

fs/ubifs/io.c

@@ -62,6 +62,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
 {
 	if (!c->ro_media) {
 		c->ro_media = 1;
+		c->no_chk_data_crc = 0;
 		ubifs_warn("switched to read-only mode, error %d", err);
 		dbg_dump_stack();
 	}
@@ -74,6 +75,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
  * @lnum: logical eraseblock number
  * @offs: offset within the logical eraseblock
  * @quiet: print no messages
+ * @chk_crc: indicates whether to always check the CRC
  *
  * This function checks node magic number and CRC checksum. This function also
  * validates node length to prevent UBIFS from becoming crazy when an attacker
@@ -85,7 +87,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
  * or magic.
  */
 int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
-		     int offs, int quiet)
+		     int offs, int quiet, int chk_crc)
 {
 	int err = -EINVAL, type, node_len;
 	uint32_t crc, node_crc, magic;
@@ -121,6 +123,10 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
 		   node_len > c->ranges[type].max_len)
 		goto out_len;
 
+	if (!chk_crc && type == UBIFS_DATA_NODE && !c->always_chk_crc)
+		if (c->no_chk_data_crc)
+			return 0;
+
 	crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
 	node_crc = le32_to_cpu(ch->crc);
 	if (crc != node_crc) {
@@ -722,7 +728,7 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len,
 		goto out;
 	}
 
-	err = ubifs_check_node(c, buf, lnum, offs, 0);
+	err = ubifs_check_node(c, buf, lnum, offs, 0, 0);
 	if (err) {
 		ubifs_err("expected node type %d", type);
 		return err;
@@ -781,7 +787,7 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len,
 		goto out;
 	}
 
-	err = ubifs_check_node(c, buf, lnum, offs, 0);
+	err = ubifs_check_node(c, buf, lnum, offs, 0, 0);
 	if (err) {
 		ubifs_err("expected node type %d", type);
 		return err;

fs/ubifs/key.h

@@ -484,7 +484,7 @@ static inline void key_copy(const struct ubifs_info *c,
  * @key2: the second key to compare
  *
  * This function compares 2 keys and returns %-1 if @key1 is less than
- * @key2, 0 if the keys are equivalent and %1 if @key1 is greater than @key2.
+ * @key2, %0 if the keys are equivalent and %1 if @key1 is greater than @key2.
  */
 static inline int keys_cmp(const struct ubifs_info *c,
 			   const union ubifs_key *key1,
@@ -502,6 +502,26 @@ static inline int keys_cmp(const struct ubifs_info *c,
 	return 0;
 }
 
+/**
+ * keys_eq - determine if keys are equivalent.
+ * @c: UBIFS file-system description object
+ * @key1: the first key to compare
+ * @key2: the second key to compare
+ *
+ * This function compares 2 keys and returns %1 if @key1 is equal to @key2 and
+ * %0 if not.
+ */
+static inline int keys_eq(const struct ubifs_info *c,
+			  const union ubifs_key *key1,
+			  const union ubifs_key *key2)
+{
+	if (key1->u32[0] != key2->u32[0])
+		return 0;
+	if (key1->u32[1] != key2->u32[1])
+		return 0;
+	return 1;
+}
+
 /**
  * is_hash_key - is a key vulnerable to hash collisions.
  * @c: UBIFS file-system description object

fs/ubifs/lprops.c

@@ -125,6 +125,7 @@ static void adjust_lpt_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap,
 			}
 		}
 	}
+
 	/* Not greater than parent, so compare to children */
 	while (1) {
 		/* Compare to left child */
@@ -459,18 +460,6 @@ static void change_category(struct ubifs_info *c, struct ubifs_lprops *lprops)
 	}
 }
 
-/**
- * ubifs_get_lprops - get reference to LEB properties.
- * @c: the UBIFS file-system description object
- *
- * This function locks lprops. Lprops have to be unlocked by
- * 'ubifs_release_lprops()'.
- */
-void ubifs_get_lprops(struct ubifs_info *c)
-{
-	mutex_lock(&c->lp_mutex);
-}
-
 /**
  * calc_dark - calculate LEB dark space size.
  * @c: the UBIFS file-system description object
@@ -576,7 +565,6 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
 	ubifs_assert(!(lprops->free & 7) && !(lprops->dirty & 7));
 
 	spin_lock(&c->space_lock);
-
 	if ((lprops->flags & LPROPS_TAKEN) && lprops->free == c->leb_size)
 		c->lst.taken_empty_lebs -= 1;
 
@@ -637,30 +625,11 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
 		c->lst.taken_empty_lebs += 1;
 
 	change_category(c, lprops);
-
 	c->idx_gc_cnt += idx_gc_cnt;
-
 	spin_unlock(&c->space_lock);
-
 	return lprops;
 }
 
-/**
- * ubifs_release_lprops - release lprops lock.
- * @c: the UBIFS file-system description object
- *
- * This function has to be called after each 'ubifs_get_lprops()' call to
- * unlock lprops.
- */
-void ubifs_release_lprops(struct ubifs_info *c)
-{
-	ubifs_assert(mutex_is_locked(&c->lp_mutex));
-	ubifs_assert(c->lst.empty_lebs >= 0 &&
-		     c->lst.empty_lebs <= c->main_lebs);
-
-	mutex_unlock(&c->lp_mutex);
-}
-
 /**
  * ubifs_get_lp_stats - get lprops statistics.
  * @c: UBIFS file-system description object
@@ -1262,7 +1231,6 @@ static int scan_check_cb(struct ubifs_info *c,
 	}
 
 	ubifs_scan_destroy(sleb);
-
 	return LPT_SCAN_CONTINUE;
 
 out_print:

fs/ubifs/lpt.c

@@ -109,7 +109,8 @@ static void do_calc_lpt_geom(struct ubifs_info *c)
 	c->lpt_sz = (long long)c->pnode_cnt * c->pnode_sz;
 	c->lpt_sz += (long long)c->nnode_cnt * c->nnode_sz;
 	c->lpt_sz += c->ltab_sz;
-	c->lpt_sz += c->lsave_sz;
+	if (c->big_lpt)
+		c->lpt_sz += c->lsave_sz;
 
 	/* Add wastage */
 	sz = c->lpt_sz;
@@ -287,25 +288,56 @@ uint32_t ubifs_unpack_bits(uint8_t **addr, int *pos, int nrbits)
 	const int k = 32 - nrbits;
 	uint8_t *p = *addr;
 	int b = *pos;
-	uint32_t val;
+	uint32_t uninitialized_var(val);
+	const int bytes = (nrbits + b + 7) >> 3;
 
 	ubifs_assert(nrbits > 0);
 	ubifs_assert(nrbits <= 32);
 	ubifs_assert(*pos >= 0);
 	ubifs_assert(*pos < 8);
 	if (b) {
-		val = p[1] | ((uint32_t)p[2] << 8) | ((uint32_t)p[3] << 16) |
-		      ((uint32_t)p[4] << 24);
+		switch (bytes) {
+		case 2:
+			val = p[1];
+			break;
+		case 3:
+			val = p[1] | ((uint32_t)p[2] << 8);
+			break;
+		case 4:
+			val = p[1] | ((uint32_t)p[2] << 8) |
+				     ((uint32_t)p[3] << 16);
+			break;
+		case 5:
+			val = p[1] | ((uint32_t)p[2] << 8) |
+				     ((uint32_t)p[3] << 16) |
+				     ((uint32_t)p[4] << 24);
+		}
 		val <<= (8 - b);
 		val |= *p >> b;
 		nrbits += b;
-	} else
-		val = p[0] | ((uint32_t)p[1] << 8) | ((uint32_t)p[2] << 16) |
-		      ((uint32_t)p[3] << 24);
+	} else {
+		switch (bytes) {
+		case 1:
+			val = p[0];
+			break;
+		case 2:
+			val = p[0] | ((uint32_t)p[1] << 8);
+			break;
+		case 3:
+			val = p[0] | ((uint32_t)p[1] << 8) |
+				     ((uint32_t)p[2] << 16);
+			break;
+		case 4:
+			val = p[0] | ((uint32_t)p[1] << 8) |
+				     ((uint32_t)p[2] << 16) |
+				     ((uint32_t)p[3] << 24);
+			break;
+		}
+	}
 	val <<= k;
 	val >>= k;
 	b = nrbits & 7;
-	p += nrbits / 8;
+	p += nrbits >> 3;
 	*addr = p;
 	*pos = b;
 	ubifs_assert((val >> nrbits) == 0 || nrbits - b == 32);

fs/ubifs/lpt_commit.c

@@ -177,8 +177,6 @@ static int alloc_lpt_leb(struct ubifs_info *c, int *lnum)
 			return 0;
 		}
 	}
-	dbg_err("last LEB %d", *lnum);
-	dump_stack();
 	return -ENOSPC;
 }
 
@@ -193,6 +191,9 @@ static int layout_cnodes(struct ubifs_info *c)
 	int lnum, offs, len, alen, done_lsave, done_ltab, err;
 	struct ubifs_cnode *cnode;
 
+	err = dbg_chk_lpt_sz(c, 0, 0);
+	if (err)
+		return err;
 	cnode = c->lpt_cnext;
 	if (!cnode)
 		return 0;
@@ -206,6 +207,7 @@ static int layout_cnodes(struct ubifs_info *c)
 		c->lsave_lnum = lnum;
 		c->lsave_offs = offs;
 		offs += c->lsave_sz;
+		dbg_chk_lpt_sz(c, 1, c->lsave_sz);
 	}
 
 	if (offs + c->ltab_sz <= c->leb_size) {
@@ -213,6 +215,7 @@ static int layout_cnodes(struct ubifs_info *c)
 		c->ltab_lnum = lnum;
 		c->ltab_offs = offs;
 		offs += c->ltab_sz;
+		dbg_chk_lpt_sz(c, 1, c->ltab_sz);
 	}
 
 	do {
@@ -226,9 +229,10 @@ static int layout_cnodes(struct ubifs_info *c)
 		while (offs + len > c->leb_size) {
 			alen = ALIGN(offs, c->min_io_size);
 			upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+			dbg_chk_lpt_sz(c, 2, alen - offs);
 			err = alloc_lpt_leb(c, &lnum);
 			if (err)
-				return err;
+				goto no_space;
 			offs = 0;
 			ubifs_assert(lnum >= c->lpt_first &&
 				     lnum <= c->lpt_last);
@@ -238,6 +242,7 @@ static int layout_cnodes(struct ubifs_info *c)
 				c->lsave_lnum = lnum;
 				c->lsave_offs = offs;
 				offs += c->lsave_sz;
+				dbg_chk_lpt_sz(c, 1, c->lsave_sz);
 				continue;
 			}
 			if (!done_ltab) {
@@ -245,6 +250,7 @@ static int layout_cnodes(struct ubifs_info *c)
 				c->ltab_lnum = lnum;
 				c->ltab_offs = offs;
 				offs += c->ltab_sz;
+				dbg_chk_lpt_sz(c, 1, c->ltab_sz);
 				continue;
 			}
 			break;
@@ -257,6 +263,7 @@ static int layout_cnodes(struct ubifs_info *c)
 			c->lpt_offs = offs;
 		}
 		offs += len;
+		dbg_chk_lpt_sz(c, 1, len);
 		cnode = cnode->cnext;
 	} while (cnode && cnode != c->lpt_cnext);
 
@@ -265,9 +272,10 @@ static int layout_cnodes(struct ubifs_info *c)
 		if (offs + c->lsave_sz > c->leb_size) {
 			alen = ALIGN(offs, c->min_io_size);
 			upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+			dbg_chk_lpt_sz(c, 2, alen - offs);
 			err = alloc_lpt_leb(c, &lnum);
 			if (err)
-				return err;
+				goto no_space;
 			offs = 0;
 			ubifs_assert(lnum >= c->lpt_first &&
 				     lnum <= c->lpt_last);
@@ -276,6 +284,7 @@ static int layout_cnodes(struct ubifs_info *c)
 		c->lsave_lnum = lnum;
 		c->lsave_offs = offs;
 		offs += c->lsave_sz;
+		dbg_chk_lpt_sz(c, 1, c->lsave_sz);
 	}
 
 	/* Make sure to place LPT's own lprops table */
@@ -283,9 +292,10 @@ static int layout_cnodes(struct ubifs_info *c)
 		if (offs + c->ltab_sz > c->leb_size) {
 			alen = ALIGN(offs, c->min_io_size);
 			upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+			dbg_chk_lpt_sz(c, 2, alen - offs);
 			err = alloc_lpt_leb(c, &lnum);
 			if (err)
-				return err;
+				goto no_space;
 			offs = 0;
 			ubifs_assert(lnum >= c->lpt_first &&
 				     lnum <= c->lpt_last);
@@ -294,11 +304,23 @@ static int layout_cnodes(struct ubifs_info *c)
 		c->ltab_lnum = lnum;
 		c->ltab_offs = offs;
 		offs += c->ltab_sz;
+		dbg_chk_lpt_sz(c, 1, c->ltab_sz);
 	}
 
 	alen = ALIGN(offs, c->min_io_size);
 	upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+	dbg_chk_lpt_sz(c, 4, alen - offs);
+	err = dbg_chk_lpt_sz(c, 3, alen);
+	if (err)
+		return err;
 	return 0;
+
+no_space:
+	ubifs_err("LPT out of space");
+	dbg_err("LPT out of space at LEB %d:%d needing %d, done_ltab %d, "
+		"done_lsave %d", lnum, offs, len, done_ltab, done_lsave);
+	dbg_dump_lpt_info(c);
+	return err;
 }
 
 /**
@@ -333,8 +355,6 @@ static int realloc_lpt_leb(struct ubifs_info *c, int *lnum)
 			*lnum = i + c->lpt_first;
 			return 0;
 		}
-	dbg_err("last LEB %d", *lnum);
-	dump_stack();
 	return -ENOSPC;
 }
 
@@ -369,12 +389,14 @@ static int write_cnodes(struct ubifs_info *c)
 		done_lsave = 1;
 		ubifs_pack_lsave(c, buf + offs, c->lsave);
 		offs += c->lsave_sz;
+		dbg_chk_lpt_sz(c, 1, c->lsave_sz);
 	}
 
 	if (offs + c->ltab_sz <= c->leb_size) {
 		done_ltab = 1;
 		ubifs_pack_ltab(c, buf + offs, c->ltab_cmt);
 		offs += c->ltab_sz;
+		dbg_chk_lpt_sz(c, 1, c->ltab_sz);
 	}
 
 	/* Loop for each cnode */
@@ -392,10 +414,12 @@ static int write_cnodes(struct ubifs_info *c)
 						       alen, UBI_SHORTTERM);
 				if (err)
 					return err;
+				dbg_chk_lpt_sz(c, 4, alen - wlen);
 			}
+			dbg_chk_lpt_sz(c, 2, 0);
 			err = realloc_lpt_leb(c, &lnum);
 			if (err)
-				return err;
+				goto no_space;
 			offs = 0;
 			from = 0;
 			ubifs_assert(lnum >= c->lpt_first &&
@@ -408,12 +432,14 @@ static int write_cnodes(struct ubifs_info *c)
 				done_lsave = 1;
 				ubifs_pack_lsave(c, buf + offs, c->lsave);
 				offs += c->lsave_sz;
+				dbg_chk_lpt_sz(c, 1, c->lsave_sz);
 				continue;
 			}
 			if (!done_ltab) {
 				done_ltab = 1;
 				ubifs_pack_ltab(c, buf + offs, c->ltab_cmt);
 				offs += c->ltab_sz;
+				dbg_chk_lpt_sz(c, 1, c->ltab_sz);
 				continue;
 			}
 			break;
@@ -435,6 +461,7 @@ static int write_cnodes(struct ubifs_info *c)
 		clear_bit(COW_ZNODE, &cnode->flags);
 		smp_mb__after_clear_bit();
 		offs += len;
+		dbg_chk_lpt_sz(c, 1, len);
 		cnode = cnode->cnext;
 	} while (cnode && cnode != c->lpt_cnext);
 
@@ -448,9 +475,10 @@ static int write_cnodes(struct ubifs_info *c)
 					      UBI_SHORTTERM);
 			if (err)
 				return err;
+			dbg_chk_lpt_sz(c, 2, alen - wlen);
 			err = realloc_lpt_leb(c, &lnum);
 			if (err)
-				return err;
+				goto no_space;
 			offs = 0;
 			ubifs_assert(lnum >= c->lpt_first &&
 				     lnum <= c->lpt_last);
@@ -461,6 +489,7 @@ static int write_cnodes(struct ubifs_info *c)
 		done_lsave = 1;
 		ubifs_pack_lsave(c, buf + offs, c->lsave);
 		offs += c->lsave_sz;
+		dbg_chk_lpt_sz(c, 1, c->lsave_sz);
 	}
 
 	/* Make sure to place LPT's own lprops table */
@@ -473,9 +502,10 @@ static int write_cnodes(struct ubifs_info *c)
 					      UBI_SHORTTERM);
 			if (err)
 				return err;
+			dbg_chk_lpt_sz(c, 2, alen - wlen);
 			err = realloc_lpt_leb(c, &lnum);
 			if (err)
-				return err;
+				goto no_space;
 			offs = 0;
 			ubifs_assert(lnum >= c->lpt_first &&
 				     lnum <= c->lpt_last);
@@ -486,6 +516,7 @@ static int write_cnodes(struct ubifs_info *c)
 		done_ltab = 1;
 		ubifs_pack_ltab(c, buf + offs, c->ltab_cmt);
 		offs += c->ltab_sz;
+		dbg_chk_lpt_sz(c, 1, c->ltab_sz);
 	}
 
 	/* Write remaining data in buffer */
@@ -495,6 +526,12 @@ static int write_cnodes(struct ubifs_info *c)
 	err = ubifs_leb_write(c, lnum, buf + from, from, alen, UBI_SHORTTERM);
 	if (err)
 		return err;
+
+	dbg_chk_lpt_sz(c, 4, alen - wlen);
+	err = dbg_chk_lpt_sz(c, 3, ALIGN(offs, c->min_io_size));
+	if (err)
+		return err;
+
 	c->nhead_lnum = lnum;
 	c->nhead_offs = ALIGN(offs, c->min_io_size);
 
@@ -503,7 +540,15 @@ static int write_cnodes(struct ubifs_info *c)
 	dbg_lp("LPT ltab is at %d:%d", c->ltab_lnum, c->ltab_offs);
 	if (c->big_lpt)
 		dbg_lp("LPT lsave is at %d:%d", c->lsave_lnum, c->lsave_offs);
+
 	return 0;
+
+no_space:
+	ubifs_err("LPT out of space mismatch");
+	dbg_err("LPT out of space mismatch at LEB %d:%d needing %d, done_ltab "
+	        "%d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave);
+	dbg_dump_lpt_info(c);
+	return err;
 }
 
 /**
@@ -1044,6 +1089,8 @@ static int is_a_node(struct ubifs_info *c, uint8_t *buf, int len)
 	int pos = 0, node_type, node_len;
 	uint16_t crc, calc_crc;
 
+	if (len < UBIFS_LPT_CRC_BYTES + (UBIFS_LPT_TYPE_BITS + 7) / 8)
+		return 0;
 	node_type = ubifs_unpack_bits(&addr, &pos, UBIFS_LPT_TYPE_BITS);
 	if (node_type == UBIFS_LPT_NOT_A_NODE)
 		return 0;
@@ -1156,6 +1203,9 @@ int ubifs_lpt_start_commit(struct ubifs_info *c)
 	dbg_lp("");
 
 	mutex_lock(&c->lp_mutex);
+	err = dbg_chk_lpt_free_spc(c);
+	if (err)
+		goto out;
 	err = dbg_check_ltab(c);
 	if (err)
 		goto out;
@@ -1645,4 +1695,121 @@ int dbg_check_ltab(struct ubifs_info *c)
 	return 0;
 }
 
+/**
+ * dbg_chk_lpt_free_spc - check LPT free space is enough to write entire LPT.
+ * @c: the UBIFS file-system description object
+ *
+ * This function returns %0 on success and a negative error code on failure.
+ */
+int dbg_chk_lpt_free_spc(struct ubifs_info *c)
+{
+	long long free = 0;
+	int i;
+
+	for (i = 0; i < c->lpt_lebs; i++) {
+		if (c->ltab[i].tgc || c->ltab[i].cmt)
+			continue;
+		if (i + c->lpt_first == c->nhead_lnum)
+			free += c->leb_size - c->nhead_offs;
+		else if (c->ltab[i].free == c->leb_size)
+			free += c->leb_size;
+	}
+	if (free < c->lpt_sz) {
+		dbg_err("LPT space error: free %lld lpt_sz %lld",
+			free, c->lpt_sz);
+		dbg_dump_lpt_info(c);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * dbg_chk_lpt_sz - check LPT does not write more than LPT size.
+ * @c: the UBIFS file-system description object
+ * @action: action
+ * @len: length written
+ *
+ * This function returns %0 on success and a negative error code on failure.
+ */
+int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len)
+{
+	long long chk_lpt_sz, lpt_sz;
+	int err = 0;
+
+	switch (action) {
+	case 0:
+		c->chk_lpt_sz = 0;
+		c->chk_lpt_sz2 = 0;
+		c->chk_lpt_lebs = 0;
+		c->chk_lpt_wastage = 0;
+		if (c->dirty_pn_cnt > c->pnode_cnt) {
+			dbg_err("dirty pnodes %d exceed max %d",
+				c->dirty_pn_cnt, c->pnode_cnt);
+			err = -EINVAL;
+		}
+		if (c->dirty_nn_cnt > c->nnode_cnt) {
+			dbg_err("dirty nnodes %d exceed max %d",
+				c->dirty_nn_cnt, c->nnode_cnt);
+			err = -EINVAL;
+		}
+		return err;
+	case 1:
+		c->chk_lpt_sz += len;
+		return 0;
+	case 2:
+		c->chk_lpt_sz += len;
+		c->chk_lpt_wastage += len;
+		c->chk_lpt_lebs += 1;
+		return 0;
+	case 3:
+		chk_lpt_sz = c->leb_size;
+		chk_lpt_sz *= c->chk_lpt_lebs;
+		chk_lpt_sz += len - c->nhead_offs;
+		if (c->chk_lpt_sz != chk_lpt_sz) {
+			dbg_err("LPT wrote %lld but space used was %lld",
+				c->chk_lpt_sz, chk_lpt_sz);
+			err = -EINVAL;
+		}
+		if (c->chk_lpt_sz > c->lpt_sz) {
+			dbg_err("LPT wrote %lld but lpt_sz is %lld",
+				c->chk_lpt_sz, c->lpt_sz);
+			err = -EINVAL;
+		}
+		if (c->chk_lpt_sz2 && c->chk_lpt_sz != c->chk_lpt_sz2) {
+			dbg_err("LPT layout size %lld but wrote %lld",
+				c->chk_lpt_sz, c->chk_lpt_sz2);
+			err = -EINVAL;
+		}
+		if (c->chk_lpt_sz2 && c->new_nhead_offs != len) {
+			dbg_err("LPT new nhead offs: expected %d was %d",
+				c->new_nhead_offs, len);
+			err = -EINVAL;
+		}
+		lpt_sz = (long long)c->pnode_cnt * c->pnode_sz;
+		lpt_sz += (long long)c->nnode_cnt * c->nnode_sz;
+		lpt_sz += c->ltab_sz;
+		if (c->big_lpt)
+			lpt_sz += c->lsave_sz;
+		if (c->chk_lpt_sz - c->chk_lpt_wastage > lpt_sz) {
+			dbg_err("LPT chk_lpt_sz %lld + waste %lld exceeds %lld",
+				c->chk_lpt_sz, c->chk_lpt_wastage, lpt_sz);
+			err = -EINVAL;
+		}
+		if (err)
+			dbg_dump_lpt_info(c);
+		c->chk_lpt_sz2 = c->chk_lpt_sz;
+		c->chk_lpt_sz = 0;
+		c->chk_lpt_wastage = 0;
+		c->chk_lpt_lebs = 0;
+		c->new_nhead_offs = len;
+		return err;
+	case 4:
+		c->chk_lpt_sz += len;
+		c->chk_lpt_wastage += len;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 #endif /* CONFIG_UBIFS_FS_DEBUG */

fs/ubifs/misc.h

@@ -310,4 +310,31 @@ static inline int ubifs_tnc_lookup(struct ubifs_info *c,
 	return ubifs_tnc_locate(c, key, node, NULL, NULL);
 }
 
+/**
+ * ubifs_get_lprops - get reference to LEB properties.
+ * @c: the UBIFS file-system description object
+ *
+ * This function locks lprops. Lprops have to be unlocked by
+ * 'ubifs_release_lprops()'.
+ */
+static inline void ubifs_get_lprops(struct ubifs_info *c)
+{
+	mutex_lock(&c->lp_mutex);
+}
+
+/**
+ * ubifs_release_lprops - release lprops lock.
+ * @c: the UBIFS file-system description object
+ *
+ * This function has to be called after each 'ubifs_get_lprops()' call to
+ * unlock lprops.
+ */
+static inline void ubifs_release_lprops(struct ubifs_info *c)
+{
+	ubifs_assert(mutex_is_locked(&c->lp_mutex));
+	ubifs_assert(c->lst.empty_lebs >= 0 &&
+		     c->lst.empty_lebs <= c->main_lebs);
+	mutex_unlock(&c->lp_mutex);
+}
+
 #endif /* __UBIFS_MISC_H__ */

fs/ubifs/scan.c

@@ -87,7 +87,7 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum,
 
 	dbg_scan("scanning %s", dbg_ntype(ch->node_type));
 
-	if (ubifs_check_node(c, buf, lnum, offs, quiet))
+	if (ubifs_check_node(c, buf, lnum, offs, quiet, 1))
 		return SCANNED_A_CORRUPT_NODE;
 
 	if (ch->node_type == UBIFS_PAD_NODE) {

fs/ubifs/super.c

@@ -401,6 +401,16 @@ static int ubifs_show_options(struct seq_file *s, struct vfsmount *mnt)
 	else if (c->mount_opts.unmount_mode == 1)
 		seq_printf(s, ",norm_unmount");
 
+	if (c->mount_opts.bulk_read == 2)
+		seq_printf(s, ",bulk_read");
+	else if (c->mount_opts.bulk_read == 1)
+		seq_printf(s, ",no_bulk_read");
+
+	if (c->mount_opts.chk_data_crc == 2)
+		seq_printf(s, ",chk_data_crc");
+	else if (c->mount_opts.chk_data_crc == 1)
+		seq_printf(s, ",no_chk_data_crc");
+
 	return 0;
 }
 
@@ -408,13 +418,26 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
 {
 	struct ubifs_info *c = sb->s_fs_info;
 	int i, ret = 0, err;
+	long long bud_bytes;
 
-	if (c->jheads)
+	if (c->jheads) {
 		for (i = 0; i < c->jhead_cnt; i++) {
 			err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
 			if (err && !ret)
 				ret = err;
 		}
+
+		/* Commit the journal unless it has too little data */
+		spin_lock(&c->buds_lock);
+		bud_bytes = c->bud_bytes;
+		spin_unlock(&c->buds_lock);
+		if (bud_bytes > c->leb_size) {
+			err = ubifs_run_commit(c);
+			if (err)
+				return err;
+		}
+	}
+
 	/*
 	 * We ought to call sync for c->ubi but it does not have one. If it had
 	 * it would in turn call mtd->sync, however mtd operations are
@@ -538,6 +561,18 @@ static int init_constants_early(struct ubifs_info *c)
 	 * calculations when reporting free space.
 	 */
 	c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ;
+	/* Buffer size for bulk-reads */
+	c->bulk_read_buf_size = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
+	if (c->bulk_read_buf_size > c->leb_size)
+		c->bulk_read_buf_size = c->leb_size;
+	if (c->bulk_read_buf_size > 128 * 1024) {
+		/* Check if we can kmalloc more than 128KiB */
+		void *try = kmalloc(c->bulk_read_buf_size, GFP_KERNEL);
+
+		kfree(try);
+		if (!try)
+			c->bulk_read_buf_size = 128 * 1024;
+	}
 	return 0;
 }
 
@@ -840,17 +875,29 @@ static int check_volume_empty(struct ubifs_info *c)
  *
  * Opt_fast_unmount: do not run a journal commit before un-mounting
  * Opt_norm_unmount: run a journal commit before un-mounting
+ * Opt_bulk_read: enable bulk-reads
+ * Opt_no_bulk_read: disable bulk-reads
+ * Opt_chk_data_crc: check CRCs when reading data nodes
+ * Opt_no_chk_data_crc: do not check CRCs when reading data nodes
  * Opt_err: just end of array marker
  */
 enum {
 	Opt_fast_unmount,
 	Opt_norm_unmount,
+	Opt_bulk_read,
+	Opt_no_bulk_read,
+	Opt_chk_data_crc,
+	Opt_no_chk_data_crc,
 	Opt_err,
 };
 
 static const match_table_t tokens = {
 	{Opt_fast_unmount, "fast_unmount"},
 	{Opt_norm_unmount, "norm_unmount"},
+	{Opt_bulk_read, "bulk_read"},
+	{Opt_no_bulk_read, "no_bulk_read"},
+	{Opt_chk_data_crc, "chk_data_crc"},
+	{Opt_no_chk_data_crc, "no_chk_data_crc"},
 	{Opt_err, NULL},
 };
 
@@ -888,6 +935,22 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options,
 			c->mount_opts.unmount_mode = 1;
 			c->fast_unmount = 0;
 			break;
+		case Opt_bulk_read:
+			c->mount_opts.bulk_read = 2;
+			c->bulk_read = 1;
+			break;
+		case Opt_no_bulk_read:
+			c->mount_opts.bulk_read = 1;
+			c->bulk_read = 0;
+			break;
+		case Opt_chk_data_crc:
+			c->mount_opts.chk_data_crc = 2;
+			c->no_chk_data_crc = 0;
+			break;
+		case Opt_no_chk_data_crc:
+			c->mount_opts.chk_data_crc = 1;
+			c->no_chk_data_crc = 1;
+			break;
 		default:
 			ubifs_err("unrecognized mount option \"%s\" "
 				  "or missing value", p);
@@ -996,6 +1059,8 @@ static int mount_ubifs(struct ubifs_info *c)
 			goto out_free;
 	}
 
+	c->always_chk_crc = 1;
+
 	err = ubifs_read_superblock(c);
 	if (err)
 		goto out_free;
@@ -1032,8 +1097,6 @@ static int mount_ubifs(struct ubifs_info *c)
 
 		/* Create background thread */
 		c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name);
-		if (!c->bgt)
-			c->bgt = ERR_PTR(-EINVAL);
 		if (IS_ERR(c->bgt)) {
 			err = PTR_ERR(c->bgt);
 			c->bgt = NULL;
@@ -1139,24 +1202,28 @@ static int mount_ubifs(struct ubifs_info *c)
 	if (err)
 		goto out_infos;
 
+	c->always_chk_crc = 0;
+
 	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;
-	ubifs_msg("file system size: %lld bytes (%lld KiB, %lld MiB, %d LEBs)",
-		  x, x >> 10, x >> 20, c->main_lebs);
+	ubifs_msg("file system size:   %lld bytes (%lld KiB, %lld MiB, %d "
+		  "LEBs)", x, x >> 10, x >> 20, c->main_lebs);
 	x = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes;
-	ubifs_msg("journal size: %lld bytes (%lld KiB, %lld MiB, %d LEBs)",
-		  x, x >> 10, x >> 20, c->log_lebs + c->max_bud_cnt);
-	ubifs_msg("default compressor: %s", ubifs_compr_name(c->default_compr));
-	ubifs_msg("media format %d, latest format %d",
+	ubifs_msg("journal size:       %lld bytes (%lld KiB, %lld MiB, %d "
+		  "LEBs)", x, x >> 10, x >> 20, c->log_lebs + c->max_bud_cnt);
+	ubifs_msg("media format:       %d (latest is %d)",
 		  c->fmt_version, UBIFS_FORMAT_VERSION);
+	ubifs_msg("default compressor: %s", ubifs_compr_name(c->default_compr));
+	ubifs_msg("reserved for root:  %llu bytes (%llu KiB)",
+		c->report_rp_size, c->report_rp_size >> 10);
 
 	dbg_msg("compiled on:         " __DATE__ " at " __TIME__);
 	dbg_msg("min. I/O unit size:  %d bytes", c->min_io_size);
 	dbg_msg("LEB size:            %d bytes (%d KiB)",
-		c->leb_size, c->leb_size / 1024);
+		c->leb_size, c->leb_size >> 10);
 	dbg_msg("data journal heads:  %d",
 		c->jhead_cnt - NONDATA_JHEADS_CNT);
 	dbg_msg("UUID:                %02X%02X%02X%02X-%02X%02X"
@@ -1282,6 +1349,7 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 
 	mutex_lock(&c->umount_mutex);
 	c->remounting_rw = 1;
+	c->always_chk_crc = 1;
 
 	/* Check for enough free space */
 	if (ubifs_calc_available(c, c->min_idx_lebs) <= 0) {
@@ -1345,20 +1413,20 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 
 	/* Create background thread */
 	c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name);
-	if (!c->bgt)
-		c->bgt = ERR_PTR(-EINVAL);
 	if (IS_ERR(c->bgt)) {
 		err = PTR_ERR(c->bgt);
 		c->bgt = NULL;
 		ubifs_err("cannot spawn \"%s\", error %d",
 			  c->bgt_name, err);
-		return err;
+		goto out;
 	}
 	wake_up_process(c->bgt);
 
 	c->orph_buf = vmalloc(c->leb_size);
-	if (!c->orph_buf)
-		return -ENOMEM;
+	if (!c->orph_buf) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	/* Check for enough log space */
 	lnum = c->lhead_lnum + 1;
@@ -1385,6 +1453,7 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 	dbg_gen("re-mounted read-write");
 	c->vfs_sb->s_flags &= ~MS_RDONLY;
 	c->remounting_rw = 0;
+	c->always_chk_crc = 0;
 	mutex_unlock(&c->umount_mutex);
 	return 0;
 
@@ -1400,6 +1469,7 @@ out:
 	c->ileb_buf = NULL;
 	ubifs_lpt_free(c, 1);
 	c->remounting_rw = 0;
+	c->always_chk_crc = 0;
 	mutex_unlock(&c->umount_mutex);
 	return err;
 }
@@ -1408,12 +1478,9 @@ out:
  * commit_on_unmount - commit the journal when un-mounting.
  * @c: UBIFS file-system description object
  *
- * This function is called during un-mounting and it commits the journal unless
- * the "fast unmount" mode is enabled. It also avoids committing the journal if
- * it contains too few data.
- *
- * Sometimes recovery requires the journal to be committed at least once, and
- * this function takes care about this.
+ * This function is called during un-mounting and re-mounting, and it commits
+ * the journal unless the "fast unmount" mode is enabled. It also avoids
+ * committing the journal if it contains too few data.
  */
 static void commit_on_unmount(struct ubifs_info *c)
 {

fs/ubifs/tnc.c

@@ -284,7 +284,7 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c,
 	}
 
 	zn = copy_znode(c, znode);
-	if (unlikely(IS_ERR(zn)))
+	if (IS_ERR(zn))
 		return zn;
 
 	if (zbr->len) {
@@ -470,6 +470,10 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type,
 	if (node_len != len)
 		return 0;
 
+	if (type == UBIFS_DATA_NODE && !c->always_chk_crc)
+		if (c->no_chk_data_crc)
+			return 0;
+
 	crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
 	node_crc = le32_to_cpu(ch->crc);
 	if (crc != node_crc)
@@ -1128,7 +1132,7 @@ static struct ubifs_znode *dirty_cow_bottom_up(struct ubifs_info *c,
 			ubifs_assert(znode == c->zroot.znode);
 			znode = dirty_cow_znode(c, &c->zroot);
 		}
-		if (unlikely(IS_ERR(znode)) || !p)
+		if (IS_ERR(znode) || !p)
 			break;
 		ubifs_assert(path[p - 1] >= 0);
 		ubifs_assert(path[p - 1] < znode->child_cnt);
@@ -1491,6 +1495,289 @@ out:
 	return err;
 }
 
+/**
+ * ubifs_tnc_get_bu_keys - lookup keys for bulk-read.
+ * @c: UBIFS file-system description object
+ * @bu: bulk-read parameters and results
+ *
+ * Lookup consecutive data node keys for the same inode that reside
+ * consecutively in the same LEB.
+ */
+int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu)
+{
+	int n, err = 0, lnum = -1, uninitialized_var(offs);
+	int uninitialized_var(len);
+	unsigned int block = key_block(c, &bu->key);
+	struct ubifs_znode *znode;
+
+	bu->cnt = 0;
+	bu->blk_cnt = 0;
+	bu->eof = 0;
+
+	mutex_lock(&c->tnc_mutex);
+	/* Find first key */
+	err = ubifs_lookup_level0(c, &bu->key, &znode, &n);
+	if (err < 0)
+		goto out;
+	if (err) {
+		/* Key found */
+		len = znode->zbranch[n].len;
+		/* The buffer must be big enough for at least 1 node */
+		if (len > bu->buf_len) {
+			err = -EINVAL;
+			goto out;
+		}
+		/* Add this key */
+		bu->zbranch[bu->cnt++] = znode->zbranch[n];
+		bu->blk_cnt += 1;
+		lnum = znode->zbranch[n].lnum;
+		offs = ALIGN(znode->zbranch[n].offs + len, 8);
+	}
+	while (1) {
+		struct ubifs_zbranch *zbr;
+		union ubifs_key *key;
+		unsigned int next_block;
+
+		/* Find next key */
+		err = tnc_next(c, &znode, &n);
+		if (err)
+			goto out;
+		zbr = &znode->zbranch[n];
+		key = &zbr->key;
+		/* See if there is another data key for this file */
+		if (key_inum(c, key) != key_inum(c, &bu->key) ||
+		    key_type(c, key) != UBIFS_DATA_KEY) {
+			err = -ENOENT;
+			goto out;
+		}
+		if (lnum < 0) {
+			/* First key found */
+			lnum = zbr->lnum;
+			offs = ALIGN(zbr->offs + zbr->len, 8);
+			len = zbr->len;
+			if (len > bu->buf_len) {
+				err = -EINVAL;
+				goto out;
+			}
+		} else {
+			/*
+			 * The data nodes must be in consecutive positions in
+			 * the same LEB.
+			 */
+			if (zbr->lnum != lnum || zbr->offs != offs)
+				goto out;
+			offs += ALIGN(zbr->len, 8);
+			len = ALIGN(len, 8) + zbr->len;
+			/* Must not exceed buffer length */
+			if (len > bu->buf_len)
+				goto out;
+		}
+		/* Allow for holes */
+		next_block = key_block(c, key);
+		bu->blk_cnt += (next_block - block - 1);
+		if (bu->blk_cnt >= UBIFS_MAX_BULK_READ)
+			goto out;
+		block = next_block;
+		/* Add this key */
+		bu->zbranch[bu->cnt++] = *zbr;
+		bu->blk_cnt += 1;
+		/* See if we have room for more */
+		if (bu->cnt >= UBIFS_MAX_BULK_READ)
+			goto out;
+		if (bu->blk_cnt >= UBIFS_MAX_BULK_READ)
+			goto out;
+	}
+out:
+	if (err == -ENOENT) {
+		bu->eof = 1;
+		err = 0;
+	}
+	bu->gc_seq = c->gc_seq;
+	mutex_unlock(&c->tnc_mutex);
+	if (err)
+		return err;
+	/*
+	 * An enormous hole could cause bulk-read to encompass too many
+	 * page cache pages, so limit the number here.
+	 */
+	if (bu->blk_cnt > UBIFS_MAX_BULK_READ)
+		bu->blk_cnt = UBIFS_MAX_BULK_READ;
+	/*
+	 * Ensure that bulk-read covers a whole number of page cache
+	 * pages.
+	 */
+	if (UBIFS_BLOCKS_PER_PAGE == 1 ||
+	    !(bu->blk_cnt & (UBIFS_BLOCKS_PER_PAGE - 1)))
+		return 0;
+	if (bu->eof) {
+		/* At the end of file we can round up */
+		bu->blk_cnt += UBIFS_BLOCKS_PER_PAGE - 1;
+		return 0;
+	}
+	/* Exclude data nodes that do not make up a whole page cache page */
+	block = key_block(c, &bu->key) + bu->blk_cnt;
+	block &= ~(UBIFS_BLOCKS_PER_PAGE - 1);
+	while (bu->cnt) {
+		if (key_block(c, &bu->zbranch[bu->cnt - 1].key) < block)
+			break;
+		bu->cnt -= 1;
+	}
+	return 0;
+}
+
+/**
+ * read_wbuf - bulk-read from a LEB with a wbuf.
+ * @wbuf: wbuf that may overlap the read
+ * @buf: buffer into which to read
+ * @len: read length
+ * @lnum: LEB number from which to read
+ * @offs: offset from which to read
+ *
+ * This functions returns %0 on success or a negative error code on failure.
+ */
+static int read_wbuf(struct ubifs_wbuf *wbuf, void *buf, int len, int lnum,
+		     int offs)
+{
+	const struct ubifs_info *c = wbuf->c;
+	int rlen, overlap;
+
+	dbg_io("LEB %d:%d, length %d", lnum, offs, len);
+	ubifs_assert(wbuf && lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
+	ubifs_assert(!(offs & 7) && offs < c->leb_size);
+	ubifs_assert(offs + len <= c->leb_size);
+
+	spin_lock(&wbuf->lock);
+	overlap = (lnum == wbuf->lnum && offs + len > wbuf->offs);
+	if (!overlap) {
+		/* We may safely unlock the write-buffer and read the data */
+		spin_unlock(&wbuf->lock);
+		return ubi_read(c->ubi, lnum, buf, offs, len);
+	}
+
+	/* Don't read under wbuf */
+	rlen = wbuf->offs - offs;
+	if (rlen < 0)
+		rlen = 0;
+
+	/* Copy the rest from the write-buffer */
+	memcpy(buf + rlen, wbuf->buf + offs + rlen - wbuf->offs, len - rlen);
+	spin_unlock(&wbuf->lock);
+
+	if (rlen > 0)
+		/* Read everything that goes before write-buffer */
+		return ubi_read(c->ubi, lnum, buf, offs, rlen);
+
+	return 0;
+}
+
+/**
+ * validate_data_node - validate data nodes for bulk-read.
+ * @c: UBIFS file-system description object
+ * @buf: buffer containing data node to validate
+ * @zbr: zbranch of data node to validate
+ *
+ * This functions returns %0 on success or a negative error code on failure.
+ */
+static int validate_data_node(struct ubifs_info *c, void *buf,
+			      struct ubifs_zbranch *zbr)
+{
+	union ubifs_key key1;
+	struct ubifs_ch *ch = buf;
+	int err, len;
+
+	if (ch->node_type != UBIFS_DATA_NODE) {
+		ubifs_err("bad node type (%d but expected %d)",
+			  ch->node_type, UBIFS_DATA_NODE);
+		goto out_err;
+	}
+
+	err = ubifs_check_node(c, buf, zbr->lnum, zbr->offs, 0, 0);
+	if (err) {
+		ubifs_err("expected node type %d", UBIFS_DATA_NODE);
+		goto out;
+	}
+
+	len = le32_to_cpu(ch->len);
+	if (len != zbr->len) {
+		ubifs_err("bad node length %d, expected %d", len, zbr->len);
+		goto out_err;
+	}
+
+	/* Make sure the key of the read node is correct */
+	key_read(c, buf + UBIFS_KEY_OFFSET, &key1);
+	if (!keys_eq(c, &zbr->key, &key1)) {
+		ubifs_err("bad key in node at LEB %d:%d",
+			  zbr->lnum, zbr->offs);
+		dbg_tnc("looked for key %s found node's key %s",
+			DBGKEY(&zbr->key), DBGKEY1(&key1));
+		goto out_err;
+	}
+
+	return 0;
+
+out_err:
+	err = -EINVAL;
+out:
+	ubifs_err("bad node at LEB %d:%d", zbr->lnum, zbr->offs);
+	dbg_dump_node(c, buf);
+	dbg_dump_stack();
+	return err;
+}
+
+/**
+ * ubifs_tnc_bulk_read - read a number of data nodes in one go.
+ * @c: UBIFS file-system description object
+ * @bu: bulk-read parameters and results
+ *
+ * This functions reads and validates the data nodes that were identified by the
+ * 'ubifs_tnc_get_bu_keys()' function. This functions returns %0 on success,
+ * -EAGAIN to indicate a race with GC, or another negative error code on
+ * failure.
+ */
+int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu)
+{
+	int lnum = bu->zbranch[0].lnum, offs = bu->zbranch[0].offs, len, err, i;
+	struct ubifs_wbuf *wbuf;
+	void *buf;
+
+	len = bu->zbranch[bu->cnt - 1].offs;
+	len += bu->zbranch[bu->cnt - 1].len - offs;
+	if (len > bu->buf_len) {
+		ubifs_err("buffer too small %d vs %d", bu->buf_len, len);
+		return -EINVAL;
+	}
+
+	/* Do the read */
+	wbuf = ubifs_get_wbuf(c, lnum);
+	if (wbuf)
+		err = read_wbuf(wbuf, bu->buf, len, lnum, offs);
+	else
+		err = ubi_read(c->ubi, lnum, bu->buf, offs, len);
+
+	/* Check for a race with GC */
+	if (maybe_leb_gced(c, lnum, bu->gc_seq))
+		return -EAGAIN;
+
+	if (err && err != -EBADMSG) {
+		ubifs_err("failed to read from LEB %d:%d, error %d",
+			  lnum, offs, err);
+		dbg_dump_stack();
+		dbg_tnc("key %s", DBGKEY(&bu->key));
+		return err;
+	}
+
+	/* Validate the nodes read */
+	buf = bu->buf;
+	for (i = 0; i < bu->cnt; i++) {
+		err = validate_data_node(c, buf, &bu->zbranch[i]);
+		if (err)
+			return err;
+		buf = buf + ALIGN(bu->zbranch[i].len, 8);
+	}
+
+	return 0;
+}
+
 /**
  * do_lookup_nm- look up a "hashed" node.
  * @c: UBIFS file-system description object
@@ -1675,7 +1962,7 @@ static int tnc_insert(struct ubifs_info *c, struct ubifs_znode *znode,
 {
 	struct ubifs_znode *zn, *zi, *zp;
 	int i, keep, move, appending = 0;
-	union ubifs_key *key = &zbr->key;
+	union ubifs_key *key = &zbr->key, *key1;
 
 	ubifs_assert(n >= 0 && n <= c->fanout);
 
@@ -1716,20 +2003,33 @@ again:
 	zn->level = znode->level;
 
 	/* Decide where to split */
-	if (znode->level == 0 && n == c->fanout &&
-	    key_type(c, key) == UBIFS_DATA_KEY) {
-		union ubifs_key *key1;
-
-		/*
-		 * If this is an inode which is being appended - do not split
-		 * it because no other zbranches can be inserted between
-		 * zbranches of consecutive data nodes anyway.
-		 */
-		key1 = &znode->zbranch[n - 1].key;
-		if (key_inum(c, key1) == key_inum(c, key) &&
-		    key_type(c, key1) == UBIFS_DATA_KEY &&
-		    key_block(c, key1) == key_block(c, key) - 1)
-			appending = 1;
+	if (znode->level == 0 && key_type(c, key) == UBIFS_DATA_KEY) {
+		/* Try not to split consecutive data keys */
+		if (n == c->fanout) {
+			key1 = &znode->zbranch[n - 1].key;
+			if (key_inum(c, key1) == key_inum(c, key) &&
+			    key_type(c, key1) == UBIFS_DATA_KEY)
+				appending = 1;
+		} else
+			goto check_split;
+	} else if (appending && n != c->fanout) {
+		/* Try not to split consecutive data keys */
+		appending = 0;
+check_split:
+		if (n >= (c->fanout + 1) / 2) {
+			key1 = &znode->zbranch[0].key;
+			if (key_inum(c, key1) == key_inum(c, key) &&
+			    key_type(c, key1) == UBIFS_DATA_KEY) {
+				key1 = &znode->zbranch[n].key;
+				if (key_inum(c, key1) != key_inum(c, key) ||
+				    key_type(c, key1) != UBIFS_DATA_KEY) {
+					keep = n;
+					move = c->fanout - keep;
+					zi = znode;
+					goto do_split;
+				}
+			}
+		}
 	}
 
 	if (appending) {
@@ -1759,6 +2059,8 @@ again:
 			zbr->znode->parent = zn;
 	}
 
+do_split:
+
 	__set_bit(DIRTY_ZNODE, &zn->flags);
 	atomic_long_inc(&c->dirty_zn_cnt);
 
@@ -1785,14 +2087,11 @@ again:
 
 	/* Insert new znode (produced by spitting) into the parent */
 	if (zp) {
-		i = n;
+		if (n == 0 && zi == znode && znode->iip == 0)
+			correct_parent_keys(c, znode);
+
 		/* Locate insertion point */
 		n = znode->iip + 1;
-		if (appending && n != c->fanout)
-			appending = 0;
-
-		if (i == 0 && zi == znode && znode->iip == 0)
-			correct_parent_keys(c, znode);
 
 		/* Tail recursion */
 		zbr->key = zn->zbranch[0].key;

fs/ubifs/tnc_misc.c

@@ -480,8 +480,8 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 	}
 
 	/* Make sure the key of the read node is correct */
-	key_read(c, key, &key1);
-	if (memcmp(node + UBIFS_KEY_OFFSET, &key1, c->key_len)) {
+	key_read(c, node + UBIFS_KEY_OFFSET, &key1);
+	if (!keys_eq(c, key, &key1)) {
 		ubifs_err("bad key in node at LEB %d:%d",
 			  zbr->lnum, zbr->offs);
 		dbg_tnc("looked for key %s found node's key %s",

fs/ubifs/ubifs-media.h

@@ -75,7 +75,6 @@
  */
 #define UBIFS_BLOCK_SIZE  4096
 #define UBIFS_BLOCK_SHIFT 12
-#define UBIFS_BLOCK_MASK  0x00000FFF
 
 /* UBIFS padding byte pattern (must not be first or last byte of node magic) */
 #define UBIFS_PADDING_BYTE 0xCE

fs/ubifs/ubifs.h

@@ -142,6 +142,9 @@
 /* Maximum expected tree height for use by bottom_up_buf */
 #define BOTTOM_UP_HEIGHT 64
 
+/* Maximum number of data nodes to bulk-read */
+#define UBIFS_MAX_BULK_READ 32
+
 /*
  * Lockdep classes for UBIFS inode @ui_mutex.
  */
@@ -328,9 +331,10 @@ struct ubifs_gced_idx_leb {
  *               this inode
  * @dirty: non-zero if the inode is dirty
  * @xattr: non-zero if this is an extended attribute inode
+ * @bulk_read: non-zero if bulk-read should be used
  * @ui_mutex: serializes inode write-back with the rest of VFS operations,
- *            serializes "clean <-> dirty" state changes, protects @dirty,
- *            @ui_size, and @xattr_size
+ *            serializes "clean <-> dirty" state changes, serializes bulk-read,
+ *            protects @dirty, @bulk_read, @ui_size, and @xattr_size
  * @ui_lock: protects @synced_i_size
  * @synced_i_size: synchronized size of inode, i.e. the value of inode size
  *                 currently stored on the flash; used only for regular file
@@ -338,6 +342,8 @@ struct ubifs_gced_idx_leb {
  * @ui_size: inode size used by UBIFS when writing to flash
  * @flags: inode flags (@UBIFS_COMPR_FL, etc)
  * @compr_type: default compression type used for this inode
+ * @last_page_read: page number of last page read (for bulk read)
+ * @read_in_a_row: number of consecutive pages read in a row (for bulk read)
  * @data_len: length of the data attached to the inode
  * @data: inode's data
  *
@@ -379,12 +385,15 @@ struct ubifs_inode {
 	unsigned int xattr_names;
 	unsigned int dirty:1;
 	unsigned int xattr:1;
+	unsigned int bulk_read:1;
 	struct mutex ui_mutex;
 	spinlock_t ui_lock;
 	loff_t synced_i_size;
 	loff_t ui_size;
 	int flags;
 	int compr_type;
+	pgoff_t last_page_read;
+	pgoff_t read_in_a_row;
 	int data_len;
 	void *data;
 };
@@ -698,8 +707,8 @@ struct ubifs_jhead {
  * struct ubifs_zbranch - key/coordinate/length branch stored in znodes.
  * @key: key
  * @znode: znode address in memory
- * @lnum: LEB number of the indexing node
- * @offs: offset of the indexing node within @lnum
+ * @lnum: LEB number of the target node (indexing node or data node)
+ * @offs: target node offset within @lnum
  * @len: target node length
  */
 struct ubifs_zbranch {
@@ -743,6 +752,28 @@ struct ubifs_znode {
 	struct ubifs_zbranch zbranch[];
 };
 
+/**
+ * struct bu_info - bulk-read information
+ * @key: first data node key
+ * @zbranch: zbranches of data nodes to bulk read
+ * @buf: buffer to read into
+ * @buf_len: buffer length
+ * @gc_seq: GC sequence number to detect races with GC
+ * @cnt: number of data nodes for bulk read
+ * @blk_cnt: number of data blocks including holes
+ * @oef: end of file reached
+ */
+struct bu_info {
+	union ubifs_key key;
+	struct ubifs_zbranch zbranch[UBIFS_MAX_BULK_READ];
+	void *buf;
+	int buf_len;
+	int gc_seq;
+	int cnt;
+	int blk_cnt;
+	int eof;
+};
+
 /**
  * struct ubifs_node_range - node length range description data structure.
  * @len: fixed node length
@@ -862,9 +893,13 @@ struct ubifs_orphan {
 /**
  * struct ubifs_mount_opts - UBIFS-specific mount options information.
  * @unmount_mode: selected unmount mode (%0 default, %1 normal, %2 fast)
+ * @bulk_read: enable bulk-reads
+ * @chk_data_crc: check CRCs when reading data nodes
  */
 struct ubifs_mount_opts {
 	unsigned int unmount_mode:2;
+	unsigned int bulk_read:2;
+	unsigned int chk_data_crc:2;
 };
 
 /**
@@ -905,13 +940,12 @@ struct ubifs_mount_opts {
  * @cmt_state: commit state
  * @cs_lock: commit state lock
  * @cmt_wq: wait queue to sleep on if the log is full and a commit is running
+ *
  * @fast_unmount: do not run journal commit before un-mounting
  * @big_lpt: flag that LPT is too big to write whole during commit
- * @check_lpt_free: flag that indicates LPT GC may be needed
- * @nospace: non-zero if the file-system does not have flash space (used as
- *           optimization)
- * @nospace_rp: the same as @nospace, but additionally means that even reserved
- *              pool is full
+ * @no_chk_data_crc: do not check CRCs when reading data nodes (except during
+ *                   recovery)
+ * @bulk_read: enable bulk-reads
  *
  * @tnc_mutex: protects the Tree Node Cache (TNC), @zroot, @cnext, @enext, and
  *             @calc_idx_sz
@@ -935,6 +969,7 @@ struct ubifs_mount_opts {
  * @mst_node: master node
  * @mst_offs: offset of valid master node
  * @mst_mutex: protects the master node area, @mst_node, and @mst_offs
+ * @bulk_read_buf_size: buffer size for bulk-reads
  *
  * @log_lebs: number of logical eraseblocks in the log
  * @log_bytes: log size in bytes
@@ -977,12 +1012,17 @@ struct ubifs_mount_opts {
  *                        but which still have to be taken into account because
  *                        the index has not been committed so far
  * @space_lock: protects @budg_idx_growth, @budg_data_growth, @budg_dd_growth,
- *              @budg_uncommited_idx, @min_idx_lebs, @old_idx_sz, and @lst;
+ *              @budg_uncommited_idx, @min_idx_lebs, @old_idx_sz, @lst,
+ *              @nospace, and @nospace_rp;
  * @min_idx_lebs: minimum number of LEBs required for the index
  * @old_idx_sz: size of index on flash
  * @calc_idx_sz: temporary variable which is used to calculate new index size
  *               (contains accurate new index size at end of TNC commit start)
  * @lst: lprops statistics
+ * @nospace: non-zero if the file-system does not have flash space (used as
+ *           optimization)
+ * @nospace_rp: the same as @nospace, but additionally means that even reserved
+ *              pool is full
  *
  * @page_budget: budget for a page
  * @inode_budget: budget for an inode
@@ -1061,6 +1101,7 @@ struct ubifs_mount_opts {
  * @lpt_drty_flgs: dirty flags for LPT special nodes e.g. ltab
  * @dirty_nn_cnt: number of dirty nnodes
  * @dirty_pn_cnt: number of dirty pnodes
+ * @check_lpt_free: flag that indicates LPT GC may be needed
  * @lpt_sz: LPT size
  * @lpt_nod_buf: buffer for an on-flash nnode or pnode
  * @lpt_buf: buffer of LEB size used by LPT
@@ -1102,6 +1143,7 @@ struct ubifs_mount_opts {
  * @rcvrd_mst_node: recovered master node to write when mounting ro to rw
  * @size_tree: inode size information for recovery
  * @remounting_rw: set while remounting from ro to rw (sb flags have MS_RDONLY)
+ * @always_chk_crc: always check CRCs (while mounting and remounting rw)
  * @mount_opts: UBIFS-specific mount options
  *
  * @dbg_buf: a buffer of LEB size used for debugging purposes
@@ -1146,11 +1188,11 @@ struct ubifs_info {
 	int cmt_state;
 	spinlock_t cs_lock;
 	wait_queue_head_t cmt_wq;
+
 	unsigned int fast_unmount:1;
 	unsigned int big_lpt:1;
-	unsigned int check_lpt_free:1;
-	unsigned int nospace:1;
-	unsigned int nospace_rp:1;
+	unsigned int no_chk_data_crc:1;
+	unsigned int bulk_read:1;
 
 	struct mutex tnc_mutex;
 	struct ubifs_zbranch zroot;
@@ -1175,6 +1217,7 @@ struct ubifs_info {
 	struct ubifs_mst_node *mst_node;
 	int mst_offs;
 	struct mutex mst_mutex;
+	int bulk_read_buf_size;
 
 	int log_lebs;
 	long long log_bytes;
@@ -1218,6 +1261,8 @@ struct ubifs_info {
 	unsigned long long old_idx_sz;
 	unsigned long long calc_idx_sz;
 	struct ubifs_lp_stats lst;
+	unsigned int nospace:1;
+	unsigned int nospace_rp:1;
 
 	int page_budget;
 	int inode_budget;
@@ -1294,6 +1339,7 @@ struct ubifs_info {
 	int lpt_drty_flgs;
 	int dirty_nn_cnt;
 	int dirty_pn_cnt;
+	int check_lpt_free;
 	long long lpt_sz;
 	void *lpt_nod_buf;
 	void *lpt_buf;
@@ -1335,6 +1381,7 @@ struct ubifs_info {
 	struct ubifs_mst_node *rcvrd_mst_node;
 	struct rb_root size_tree;
 	int remounting_rw;
+	int always_chk_crc;
 	struct ubifs_mount_opts mount_opts;
 
 #ifdef CONFIG_UBIFS_FS_DEBUG
@@ -1347,6 +1394,12 @@ struct ubifs_info {
 	unsigned long fail_timeout;
 	unsigned int fail_cnt;
 	unsigned int fail_cnt_max;
+	long long chk_lpt_sz;
+	long long chk_lpt_sz2;
+	long long chk_lpt_wastage;
+	int chk_lpt_lebs;
+	int new_nhead_lnum;
+	int new_nhead_offs;
 #endif
 };
 
@@ -1377,7 +1430,7 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len,
 int ubifs_write_node(struct ubifs_info *c, void *node, int len, int lnum,
 		     int offs, int dtype);
 int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
-		     int offs, int quiet);
+		     int offs, int quiet, int chk_crc);
 void ubifs_prepare_node(struct ubifs_info *c, void *buf, int len, int pad);
 void ubifs_prep_grp_node(struct ubifs_info *c, void *node, int len, int last);
 int ubifs_io_init(struct ubifs_info *c);
@@ -1490,6 +1543,8 @@ void destroy_old_idx(struct ubifs_info *c);
 int is_idx_node_in_tnc(struct ubifs_info *c, union ubifs_key *key, int level,
 		       int lnum, int offs);
 int insert_old_idx_znode(struct ubifs_info *c, struct ubifs_znode *znode);
+int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu);
+int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu);
 
 /* tnc_misc.c */
 struct ubifs_znode *ubifs_tnc_levelorder_next(struct ubifs_znode *zr,
@@ -1586,12 +1641,10 @@ int ubifs_lpt_post_commit(struct ubifs_info *c);
 void ubifs_lpt_free(struct ubifs_info *c, int wr_only);
 
 /* lprops.c */
-void ubifs_get_lprops(struct ubifs_info *c);
 const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
 					   const struct ubifs_lprops *lp,
 					   int free, int dirty, int flags,
 					   int idx_gc_cnt);
-void ubifs_release_lprops(struct ubifs_info *c);
 void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *stats);
 void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
 		      int cat);

fs/ubifs/xattr.c

@@ -446,7 +446,7 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		int type;
 
 		xent = ubifs_tnc_next_ent(c, &key, &nm);
-		if (unlikely(IS_ERR(xent))) {
+		if (IS_ERR(xent)) {
 			err = PTR_ERR(xent);
 			break;
 		}