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
  ...

20 files changed, 1178 insertions, 167 deletions

diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index 73db464cd08..1a4973e1066 100644
--- a/fs/ubifs/budget.c
+++ b/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;
diff --git a/fs/ubifs/compress.c b/fs/ubifs/compress.c
index 5bb51dac3c1..a0ada596b17 100644
--- a/fs/ubifs/compress.c
+++ b/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)
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index d7f7645779f..7186400750e 100644
--- a/fs/ubifs/debug.c
+++ b/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;
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 50315fc5718..33d6b95071e 100644
--- a/fs/ubifs/debug.h
+++ b/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
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 3d698e2022b..51cf511d44d 100644
--- a/fs/ubifs/file.c
+++ b/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;
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 47814cde240..717d79c97c5 100644
--- a/fs/ubifs/find.c
+++ b/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);
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 02aba36fe3d..0bef6501d58 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -96,6 +96,48 @@ static int switch_gc_head(struct ubifs_info *c)
 }
 
 /**
+ * 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
  * @sleb: describes nodes to move
@@ -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;
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 054363f2b20..01682713af6 100644
--- a/fs/ubifs/io.c
+++ b/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;
diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h
index 8f747600754..9ee65086f62 100644
--- a/fs/ubifs/key.h
+++ b/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,
@@ -503,6 +503,26 @@ static inline int keys_cmp(const struct ubifs_info *c,
 }
 
 /**
+ * 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
  * @key: key
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 2ba93da71b6..f27176e9b70 100644
--- a/fs/ubifs/lprops.c
+++ b/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 */
@@ -460,18 +461,6 @@ 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
  * @spc: amount of free and dirty space in the LEB
@@ -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;
 
@@ -637,31 +625,12 @@ 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
  * @st: return statistics
@@ -1262,7 +1231,6 @@ static int scan_check_cb(struct ubifs_info *c,
 	}
 
 	ubifs_scan_destroy(sleb);
-
 	return LPT_SCAN_CONTINUE;
 
 out_print:
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index 9ff2463177e..db8bd0e518b 100644
--- a/fs/ubifs/lpt.c
+++ b/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) {