Merge branch 'reiserfs/kill-bkl' of...

Merge branch 'reiserfs/kill-bkl' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing

* 'reiserfs/kill-bkl' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing: (31 commits)
  kill-the-bkl/reiserfs: turn GFP_ATOMIC flag to GFP_NOFS in reiserfs_get_block()
  kill-the-bkl/reiserfs: drop the fs race watchdog from _get_block_create_0()
  kill-the-bkl/reiserfs: definitely drop the bkl from reiserfs_ioctl()
  kill-the-bkl/reiserfs: always lock the ioctl path
  kill-the-bkl/reiserfs: fix reiserfs lock to cpu_add_remove_lock dependency
  kill-the-bkl/reiserfs: Fix induced mm->mmap_sem to sysfs_mutex dependency
  kill-the-bkl/reiserfs: panic in case of lock imbalance
  kill-the-bkl/reiserfs: fix recursive reiserfs write lock in reiserfs_commit_write()
  kill-the-bkl/reiserfs: fix recursive reiserfs lock in reiserfs_mkdir()
  kill-the-bkl/reiserfs: fix "reiserfs lock" / "inode mutex" lock inversion dependency
  kill-the-bkl/reiserfs: move the concurrent tree accesses checks per superblock
  kill-the-bkl/reiserfs: acquire the inode mutex safely
  kill-the-bkl/reiserfs: unlock only when needed in search_by_key
  kill-the-bkl/reiserfs: use mutex_lock in reiserfs_mutex_lock_safe
  kill-the-bkl/reiserfs: factorize the locking in reiserfs_write_end()
  kill-the-bkl/reiserfs: reduce number of contentions in search_by_key()
  kill-the-bkl/reiserfs: don't hold the write recursively in reiserfs_lookup()
  kill-the-bkl/reiserfs: lock only once on reiserfs_get_block()
  kill-the-bkl/reiserfs: conditionaly release the write lock on fs_changed()
  kill-the-BKL/reiserfs: add reiserfs_cond_resched()
  ...

fs/reiserfs/Makefile

@@ -7,7 +7,7 @@ obj-$(CONFIG_REISERFS_FS) += reiserfs.o
 reiserfs-objs := bitmap.o do_balan.o namei.o inode.o file.o dir.o fix_node.o \
 		 super.o prints.o objectid.o lbalance.o ibalance.o stree.o \
 		 hashes.o tail_conversion.o journal.o resize.o \
-		 item_ops.o ioctl.o procfs.o xattr.o
+		 item_ops.o ioctl.o procfs.o xattr.o lock.o
 
 ifeq ($(CONFIG_REISERFS_FS_XATTR),y)
 reiserfs-objs += xattr_user.o xattr_trusted.o

fs/reiserfs/bitmap.c

@@ -1249,14 +1249,18 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb,
 	else if (bitmap == 0)
 		block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1;
 
+	reiserfs_write_unlock(sb);
 	bh = sb_bread(sb, block);
+	reiserfs_write_lock(sb);
 	if (bh == NULL)
 		reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) "
 		                 "reading failed", __func__, block);
 	else {
 		if (buffer_locked(bh)) {
 			PROC_INFO_INC(sb, scan_bitmap.wait);
+			reiserfs_write_unlock(sb);
 			__wait_on_buffer(bh);
+			reiserfs_write_lock(sb);
 		}
 		BUG_ON(!buffer_uptodate(bh));
 		BUG_ON(atomic_read(&bh->b_count) == 0);

fs/reiserfs/dir.c

@@ -20,7 +20,7 @@ const struct file_operations reiserfs_dir_operations = {
 	.read = generic_read_dir,
 	.readdir = reiserfs_readdir,
 	.fsync = reiserfs_dir_fsync,
-	.ioctl = reiserfs_ioctl,
+	.unlocked_ioctl = reiserfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = reiserfs_compat_ioctl,
 #endif
@@ -174,14 +174,22 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
 				// user space buffer is swapped out. At that time
 				// entry can move to somewhere else
 				memcpy(local_buf, d_name, d_reclen);
+
+				/*
+				 * Since filldir might sleep, we can release
+				 * the write lock here for other waiters
+				 */
+				reiserfs_write_unlock(inode->i_sb);
 				if (filldir
 				    (dirent, local_buf, d_reclen, d_off, d_ino,
 				     DT_UNKNOWN) < 0) {
+					reiserfs_write_lock(inode->i_sb);
 					if (local_buf != small_buf) {
 						kfree(local_buf);
 					}
 					goto end;
 				}
+				reiserfs_write_lock(inode->i_sb);
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}

fs/reiserfs/do_balan.c

@@ -21,14 +21,6 @@
 #include <linux/buffer_head.h>
 #include <linux/kernel.h>
 
-#ifdef CONFIG_REISERFS_CHECK
-
-struct tree_balance *cur_tb = NULL;	/* detects whether more than one
-					   copy of tb exists as a means
-					   of checking whether schedule
-					   is interrupting do_balance */
-#endif
-
 static inline void buffer_info_init_left(struct tree_balance *tb,
                                          struct buffer_info *bi)
 {
@@ -1840,11 +1832,12 @@ static int check_before_balancing(struct tree_balance *tb)
 {
 	int retval = 0;
 
-	if (cur_tb) {
+	if (REISERFS_SB(tb->tb_sb)->cur_tb) {
 		reiserfs_panic(tb->tb_sb, "vs-12335", "suspect that schedule "
 			       "occurred based on cur_tb not being null at "
 			       "this point in code. do_balance cannot properly "
-			       "handle schedule occurring while it runs.");
+			       "handle concurrent tree accesses on a same "
+			       "mount point.");
 	}
 
 	/* double check that buffers that we will modify are unlocked. (fix_nodes should already have
@@ -1986,7 +1979,7 @@ static inline void do_balance_starts(struct tree_balance *tb)
 	     "check");*/
 	RFALSE(check_before_balancing(tb), "PAP-12340: locked buffers in TB");
 #ifdef CONFIG_REISERFS_CHECK
-	cur_tb = tb;
+	REISERFS_SB(tb->tb_sb)->cur_tb = tb;
 #endif
 }
 
@@ -1996,7 +1989,7 @@ static inline void do_balance_completed(struct tree_balance *tb)
 #ifdef CONFIG_REISERFS_CHECK
 	check_leaf_level(tb);
 	check_internal_levels(tb);
-	cur_tb = NULL;
+	REISERFS_SB(tb->tb_sb)->cur_tb = NULL;
 #endif
 
 	/* reiserfs_free_block is no longer schedule safe.  So, we need to

fs/reiserfs/file.c

@@ -284,7 +284,7 @@ static ssize_t reiserfs_file_write(struct file *file,	/* the file we are going t
 const struct file_operations reiserfs_file_operations = {
 	.read = do_sync_read,
 	.write = reiserfs_file_write,
-	.ioctl = reiserfs_ioctl,
+	.unlocked_ioctl = reiserfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = reiserfs_compat_ioctl,
 #endif

fs/reiserfs/fix_node.c

@@ -563,9 +563,6 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 	return needed_nodes;
 }
 
-#ifdef CONFIG_REISERFS_CHECK
-extern struct tree_balance *cur_tb;
-#endif
 
 /* Set parameters for balancing.
  * Performs write of results of analysis of balancing into structure tb,
@@ -1022,7 +1019,11 @@ static int get_far_parent(struct tree_balance *tb,
 	/* Check whether the common parent is locked. */
 
 	if (buffer_locked(*pcom_father)) {
+
+		/* Release the write lock while the buffer is busy */
+		reiserfs_write_unlock(tb->tb_sb);
 		__wait_on_buffer(*pcom_father);
+		reiserfs_write_lock(tb->tb_sb);
 		if (FILESYSTEM_CHANGED_TB(tb)) {
 			brelse(*pcom_father);
 			return REPEAT_SEARCH;
@@ -1927,7 +1928,9 @@ static int get_direct_parent(struct tree_balance *tb, int h)
 		return REPEAT_SEARCH;
 
 	if (buffer_locked(bh)) {
+		reiserfs_write_unlock(tb->tb_sb);
 		__wait_on_buffer(bh);
+		reiserfs_write_lock(tb->tb_sb);
 		if (FILESYSTEM_CHANGED_TB(tb))
 			return REPEAT_SEARCH;
 	}
@@ -1965,7 +1968,9 @@ static int get_neighbors(struct tree_balance *tb, int h)
 		     tb->FL[h]) ? tb->lkey[h] : B_NR_ITEMS(tb->
 								       FL[h]);
 		son_number = B_N_CHILD_NUM(tb->FL[h], child_position);
+		reiserfs_write_unlock(sb);
 		bh = sb_bread(sb, son_number);
+		reiserfs_write_lock(sb);
 		if (!bh)
 			return IO_ERROR;
 		if (FILESYSTEM_CHANGED_TB(tb)) {
@@ -2003,7 +2008,9 @@ static int get_neighbors(struct tree_balance *tb, int h)
 		child_position =
 		    (bh == tb->FR[h]) ? tb->rkey[h] + 1 : 0;
 		son_number = B_N_CHILD_NUM(tb->FR[h], child_position);
+		reiserfs_write_unlock(sb);
 		bh = sb_bread(sb, son_number);
+		reiserfs_write_lock(sb);
 		if (!bh)
 			return IO_ERROR;
 		if (FILESYSTEM_CHANGED_TB(tb)) {
@@ -2278,7 +2285,9 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb)
 				    REPEAT_SEARCH : CARRY_ON;
 			}
 #endif
+			reiserfs_write_unlock(tb->tb_sb);
 			__wait_on_buffer(locked);
+			reiserfs_write_lock(tb->tb_sb);
 			if (FILESYSTEM_CHANGED_TB(tb))
 				return REPEAT_SEARCH;
 		}
@@ -2349,12 +2358,14 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 
 	/* if it possible in indirect_to_direct conversion */
 	if (buffer_locked(tbS0)) {
+		reiserfs_write_unlock(tb->tb_sb);
 		__wait_on_buffer(tbS0);
+		reiserfs_write_lock(tb->tb_sb);
 		if (FILESYSTEM_CHANGED_TB(tb))
 			return REPEAT_SEARCH;
 	}
 #ifdef CONFIG_REISERFS_CHECK
-	if (cur_tb) {
+	if (REISERFS_SB(tb->tb_sb)->cur_tb) {
 		print_cur_tb("fix_nodes");
 		reiserfs_panic(tb->tb_sb, "PAP-8305",
 			       "there is pending do_balance");

fs/reiserfs/inode.c

@@ -251,7 +251,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	struct cpu_key key;
 	struct buffer_head *bh;
 	struct item_head *ih, tmp_ih;
-	int fs_gen;
 	b_blocknr_t blocknr;
 	char *p = NULL;
 	int chars;
@@ -265,7 +264,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 		     (loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
 		     3);
 
-      research:
 	result = search_for_position_by_key(inode->i_sb, &key, &path);
 	if (result != POSITION_FOUND) {
 		pathrelse(&path);
@@ -340,7 +338,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	}
 	// read file tail into part of page
 	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
-	fs_gen = get_generation(inode->i_sb);
 	copy_item_head(&tmp_ih, ih);
 
 	/* we only want to kmap if we are reading the tail into the page.
@@ -348,13 +345,9 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	 ** sure we need to.  But, this means the item might move if
 	 ** kmap schedules
 	 */
-	if (!p) {
+	if (!p)
 		p = (char *)kmap(bh_result->b_page);
-		if (fs_changed(fs_gen, inode->i_sb)
-		    && item_moved(&tmp_ih, &path)) {
-			goto research;
-		}
-	}
+
 	p += offset;
 	memset(p, 0, inode->i_sb->s_blocksize);
 	do {
@@ -489,10 +482,14 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 	   disappeared */
 	if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
 		int err;
-		lock_kernel();
+
+		reiserfs_write_lock(inode->i_sb);
+
 		err = reiserfs_commit_for_inode(inode);
 		REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
-		unlock_kernel();
+
+		reiserfs_write_unlock(inode->i_sb);
+
 		if (err < 0)
 			ret = err;
 	}
@@ -601,6 +598,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	__le32 *item;
 	int done;
 	int fs_gen;
+	int lock_depth;
 	struct reiserfs_transaction_handle *th = NULL;
 	/* space reserved in transaction batch:
 	   . 3 balancings in direct->indirect conversion
@@ -616,12 +614,11 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	loff_t new_offset =
 	    (((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1;
 
-	/* bad.... */
-	reiserfs_write_lock(inode->i_sb);
+	lock_depth = reiserfs_write_lock_once(inode->i_sb);
 	version = get_inode_item_key_version(inode);
 
 	if (!file_capable(inode, block)) {
-		reiserfs_write_unlock(inode->i_sb);
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 		return -EFBIG;
 	}
 
@@ -633,7 +630,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		/* find number of block-th logical block of the file */
 		ret = _get_block_create_0(inode, block, bh_result,
 					  create | GET_BLOCK_READ_DIRECT);
-		reiserfs_write_unlock(inode->i_sb);
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 		return ret;
 	}
 	/*
@@ -751,7 +748,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		if (!dangle && th)
 			retval = reiserfs_end_persistent_transaction(th);
 
-		reiserfs_write_unlock(inode->i_sb);
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 
 		/* the item was found, so new blocks were not added to the file
 		 ** there is no need to make sure the inode is updated with this
@@ -935,7 +932,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			if (blocks_needed == 1) {
 				un = &unf_single;
 			} else {
-				un = kzalloc(min(blocks_needed, max_to_insert) * UNFM_P_SIZE, GFP_ATOMIC);	// We need to avoid scheduling.
+				un = kzalloc(min(blocks_needed, max_to_insert) * UNFM_P_SIZE, GFP_NOFS);
 				if (!un) {
 					un = &unf_single;
 					blocks_needed = 1;
@@ -997,10 +994,16 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			if (retval)
 				goto failure;
 		}
-		/* inserting indirect pointers for a hole can take a
-		 ** long time.  reschedule if needed
+		/*
+		 * inserting indirect pointers for a hole can take a
+		 * long time.  reschedule if needed and also release the write
+		 * lock for others.
 		 */
-		cond_resched();
+		if (need_resched()) {
+			reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+			schedule();
+			lock_depth = reiserfs_write_lock_once(inode->i_sb);
+		}
 
 		retval = search_for_position_by_key(inode->i_sb, &key, &path);
 		if (retval == IO_ERROR) {
@@ -1035,7 +1038,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			retval = err;
 	}
 
-	reiserfs_write_unlock(inode->i_sb);
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 	reiserfs_check_path(&path);
 	return retval;
 }
@@ -2072,8 +2075,9 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 	int error;
 	struct buffer_head *bh = NULL;
 	int err2;
+	int lock_depth;
 
-	reiserfs_write_lock(inode->i_sb);
+	lock_depth = reiserfs_write_lock_once(inode->i_sb);
 
 	if (inode->i_size > 0) {
 		error = grab_tail_page(inode, &page, &bh);
@@ -2142,14 +2146,17 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 		page_cache_release(page);
 	}
 
-	reiserfs_write_unlock(inode->i_sb);
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+
 	return 0;
       out:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
 	}
-	reiserfs_write_unlock(inode->i_sb);
+
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+
 	return error;
 }
 
@@ -2608,7 +2615,10 @@ int reiserfs_prepare_write(struct file *f, struct page *page,
 	int ret;
 	int old_ref = 0;
 
+	reiserfs_write_unlock(inode->i_sb);
 	reiserfs_wait_on_write_block(inode->i_sb);
+	reiserfs_write_lock(inode->i_sb);
+
 	fix_tail_page_for_writing(page);
 	if (reiserfs_transaction_running(inode->i_sb)) {
 		struct reiserfs_transaction_handle *th;
@@ -2664,6 +2674,8 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 	int update_sd = 0;
 	struct reiserfs_transaction_handle *th;
 	unsigned start;
+	int lock_depth = 0;
+	bool locked = false;
 
 	if ((unsigned long)fsdata & AOP_FLAG_CONT_EXPAND)
 		pos ++;
@@ -2690,9 +2702,11 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 	 ** to do the i_size updates here.
 	 */
 	pos += copied;
+
 	if (pos > inode->i_size) {
 		struct reiserfs_transaction_handle myth;
-		reiserfs_write_lock(inode->i_sb);
+		lock_depth = reiserfs_write_lock_once(inode->i_sb);
+		locked = true;
 		/* If the file have grown beyond the border where it
 		   can have a tail, unmark it as needing a tail
 		   packing */
@@ -2703,10 +2717,9 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 			REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
 
 		ret = journal_begin(&myth, inode->i_sb, 1);
-		if (ret) {
-			reiserfs_write_unlock(inode->i_sb);
+		if (ret)
 			goto journal_error;
-		}
+
 		reiserfs_update_inode_transaction(inode);
 		inode->i_size = pos;
 		/*
@@ -2718,34 +2731,36 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 		reiserfs_update_sd(&myth, inode);
 		update_sd = 1;
 		ret = journal_end(&myth, inode->i_sb, 1);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto journal_error;
 	}
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
+		if (!locked) {
+			lock_depth = reiserfs_write_lock_once(inode->i_sb);
+			locked = true;
+		}
 		if (!update_sd)
 			mark_inode_dirty(inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto out;
 	}
 
       out:
+	if (locked)
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 	unlock_page(page);
 	page_cache_release(page);
 	return ret == 0 ? copied : ret;
 
       journal_error:
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+	locked = false;
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
 		if (!update_sd)
 			reiserfs_update_sd(th, inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 	}
-
 	goto out;
 }
 
@@ -2758,7 +2773,10 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 	int update_sd = 0;
 	struct reiserfs_transaction_handle *th = NULL;
 
+	reiserfs_write_unlock(inode->i_sb);
 	reiserfs_wait_on_write_block(inode->i_sb);
+	reiserfs_write_lock(inode->i_sb);
+
 	if (reiserfs_transaction_running(inode->i_sb)) {
 		th = current->journal_info;
 	}
@@ -2770,7 +2788,6 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 	 */
 	if (pos > inode->i_size) {
 		struct reiserfs_transaction_handle myth;
-		reiserfs_write_lock(inode->i_sb);
 		/* If the file have grown beyond the border where it
 		   can have a tail, unmark it as needing a tail
 		   packing */
@@ -2781,10 +2798,9 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 			REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
 
 		ret = journal_begin(&myth, inode->i_sb, 1);
-		if (ret) {
-			reiserfs_write_unlock(inode->i_sb);
+		if (ret)
 			goto journal_error;
-		}
+
 		reiserfs_update_inode_transaction(inode);
 		inode->i_size = pos;
 		/*
@@ -2796,16 +2812,13 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 		reiserfs_update_sd(&myth, inode);
 		update_sd = 1;
 		ret = journal_end(&myth, inode->i_sb, 1);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto journal_error;
 	}
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
 		if (!update_sd)
 			mark_inode_dirty(inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto out;
 	}
@@ -2815,11 +2828,9 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 
       journal_error:
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
 		if (!update_sd)
 			reiserfs_update_sd(th, inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 	}
 
 	return ret;

fs/reiserfs/ioctl.c

@@ -13,44 +13,52 @@
 #include <linux/compat.h>
 
 /*
-** reiserfs_ioctl - handler for ioctl for inode
-** supported commands:
-**  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
-**                           and prevent packing file (argument arg has to be non-zero)
-**  2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
-**  3) That's all for a while ...
-*/
-int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
-		   unsigned long arg)
+ * reiserfs_ioctl - handler for ioctl for inode
+ * supported commands:
+ *  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
+ *                           and prevent packing file (argument arg has to be non-zero)
+ *  2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
+ *  3) That's all for a while ...
+ */
+long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = filp->f_path.dentry->d_inode;
 	unsigned int flags;
 	int err = 0;
 
+	reiserfs_write_lock(inode->i_sb);
+
 	switch (cmd) {
 	case REISERFS_IOC_UNPACK:
 		if (S_ISREG(inode->i_mode)) {
 			if (arg)
-				return reiserfs_unpack(inode, filp);
-			else
-				return 0;
+				err = reiserfs_unpack(inode, filp);
 		} else
-			return -ENOTTY;
-		/* following two cases are taken from fs/ext2/ioctl.c by Remy
-		   Card (card@masi.ibp.fr) */
+			err = -ENOTTY;
+		break;
+		/*
+		 * following two cases are taken from fs/ext2/ioctl.c by Remy
+		 * Card (card@masi.ibp.fr)
+		 */
 	case REISERFS_IOC_GETFLAGS:
-		if (!reiserfs_attrs(inode->i_sb))
-			return -ENOTTY;
+		if (!reiserfs_attrs(inode->i_sb)) {
+			err = -ENOTTY;
+			break;
+		}
 
 		flags = REISERFS_I(inode)->i_attrs;
 		i_attrs_to_sd_attrs(inode, (__u16 *) & flags);
-		return put_user(flags, (int __user *)arg);
+		err = put_user(flags, (int __user *)arg);
+		break;
 	case REISERFS_IOC_SETFLAGS:{
-			if (!reiserfs_attrs(inode->i_sb))
-				return -ENOTTY;
+			if (!reiserfs_attrs(inode->i_sb)) {
+				err = -ENOTTY;
+				break;
+			}
 
 			err = mnt_want_write(filp->f_path.mnt);
 			if (err)
-				return err;
+				break;
 
 			if (!is_owner_or_cap(inode)) {
 				err = -EPERM;
@@ -90,16 +98,18 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 			mark_inode_dirty(inode);
 setflags_out:
 			mnt_drop_write(filp->f_path.mnt);
-			return err;
+			break;
 		}
 	case REISERFS_IOC_GETVERSION:
-		return put_user(inode->i_generation, (int __user *)arg);
+		err = put_user(inode->i_generation, (int __user *)arg);
+		break;
 	case REISERFS_IOC_SETVERSION:
 		if (!is_owner_or_cap(inode))
-			return -EPERM;
+			err = -EPERM;
+			break;
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
-			return err;
+			break;
 		if (get_user(inode->i_generation, (int __user *)arg)) {
 			err = -EFAULT;
 			goto setversion_out;
@@ -108,19 +118,20 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 		mark_inode_dirty(inode);
 setversion_out:
 		mnt_drop_write(filp->f_path.mnt);
-		return err;
+		break;
 	default:
-		return -ENOTTY;
+		err = -ENOTTY;
 	}
+
+	reiserfs_write_unlock(inode->i_sb);
+
+	return err;
 }
 
 #ifdef CONFIG_COMPAT
 long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
-	int ret;
-
 	/* These are just misnamed, they actually get/put from/to user an int */
 	switch (cmd) {
 	case REISERFS_IOC32_UNPACK:
@@ -141,10 +152,8 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 	default:
 		return -ENOIOCTLCMD;
 	}
-	lock_kernel();
-	ret = reiserfs_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
-	unlock_kernel();
-	return ret;
+
+	return reiserfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
 }
 #endif
 

fs/reiserfs/journal.c

@@ -429,21 +429,6 @@ static void clear_prepared_bits(struct buffer_head *bh)
 	clear_buffer_journal_restore_dirty(bh);
 }
 
-/* utility function to force a BUG if it is called without the big
-** kernel lock held.  caller is the string printed just before calling BUG()
-*/
-void reiserfs_check_lock_depth(struct super_block *sb, char *caller)
-{
-#ifdef CONFIG_SMP
-	if (current->lock_depth < 0) {
-		reiserfs_panic(sb, "journal-1", "%s called without kernel "
-			       "lock held", caller);
-	}
-#else
-	;
-#endif
-}
-
 /* return a cnode with same dev, block number and size in table, or null if not found */
 static inline struct reiserfs_journal_cnode *get_journal_hash_dev(struct
 								  super_block
@@ -556,7 +541,8 @@ static inline void insert_journal_hash(struct reiserfs_journal_cnode **table,
 static inline void lock_journal(struct super_block *sb)
 {
 	PROC_INFO_INC(sb, journal.lock_journal);
-	mutex_lock(&SB_JOURNAL(sb)->j_mutex);
+
+	reiserfs_mutex_lock_safe(&SB_JOURNAL(sb)->j_mutex, sb);
 }
 
 /* unlock the current transaction */
@@ -708,7 +694,9 @@ static void check_barrier_completion(struct super_block *s,
 		disable_barrier(s);
 		set_buffer_uptodate(bh);
 		set_buffer_dirty(bh);
+		reiserfs_write_unlock(s);
 		sync_dirty_buffer(bh);
+		reiserfs_write_lock(s);
 	}
 }
 
@@ -996,8 +984,13 @@ static int reiserfs_async_progress_wait(struct super_block *s)
 {
 	DEFINE_WAIT(wait);
 	struct reiserfs_journal *j = SB_JOURNAL(s);
-	if (atomic_read(&j->j_async_throttle))
+
+	if (atomic_read(&j->j_async_throttle)) {
+		reiserfs_write_unlock(s);
 		congestion_wait(BLK_RW_ASYNC, HZ / 10);
+		reiserfs_write_lock(s);
+	}
+
 	return 0;
 }
 
@@ -1043,7 +1036,8 @@ static int flush_commit_list(struct super_block *s,
 	}
 
 	/* make sure nobody is trying to flush this one at the same time */
-	mutex_lock(&jl->j_commit_mutex);
+	reiserfs_mutex_lock_safe(&jl->j_commit_mutex, s);
+
 	if (!journal_list_still_alive(s, trans_id)) {
 		mutex_unlock(&jl->j_commit_mutex);
 		goto put_jl;
@@ -1061,12 +1055,17 @@ static int flush_commit_list(struct super_block *s,
 
 	if (!list_empty(&jl->j_bh_list)) {
 		int ret;
-		unlock_kernel();
+
+		/*
+		 * We might sleep in numerous places inside
+		 * write_ordered_buffers. Relax the write lock.
+		 */
+		reiserfs_write_unlock(s);
 		ret = write_ordered_buffers(&journal->j_dirty_buffers_lock,
 					    journal, jl, &jl->j_bh_list);
 		if (ret < 0 && retval == 0)
 			retval = ret;
-		lock_kernel();
+		reiserfs_write_lock(s);
 	}
 	BUG_ON(!list_empty(&jl->j_bh_list));
 	/*
@@ -1085,8 +1084,11 @@ static int flush_commit_list(struct super_block *s,
 		    SB_ONDISK_JOURNAL_SIZE(s);
 		tbh = journal_find_get_block(s, bn);
 		if (tbh) {
-			if (buffer_dirty(tbh))
-			    ll_rw_block(WRITE, 1, &tbh) ;
+			if (buffer_dirty(tbh)) {
+		            reiserfs_write_unlock(s);
+			    ll_rw_block(WRITE, 1, &tbh);
+			    reiserfs_write_lock(s);
+			}
 			put_bh(tbh) ;
 		}
 	}
@@ -1114,12 +1116,19 @@ static int flush_commit_list(struct super_block *s,
 		bn = SB_ONDISK_JOURNAL_1st_BLOCK(s) +
 		    (jl->j_start + i) % SB_ONDISK_JOURNAL_SIZE(s);
 		tbh = journal_find_get_block(s, bn);
+
+		reiserfs_write_unlock(s);
 		wait_on_buffer(tbh);
+		reiserfs_write_lock(s);
 		// since we're using ll_rw_blk above, it might have skipped over
 		// a locked buffer.  Double check here
 		//
-		if (buffer_dirty(tbh))	/* redundant, sync_dirty_buffer() checks */
+		/* redundant, sync_dirty_buffer() checks */
+		if (buffer_dirty(tbh)) {
+			reiserfs_write_unlock(s);
 			sync_dirty_buffer(tbh);
+			reiserfs_write_lock(s);
+		}
 		if (unlikely(!buffer_uptodate(tbh))) {
 #ifdef CONFIG_REISERFS_CHECK
 			reiserfs_warning(s, "journal-601",
@@ -1143,10 +1152,15 @@ static int flush_commit_list(struct super_block *s,
 			if (buffer_dirty(jl->j_commit_bh))
 				BUG();
 			mark_buffer_dirty(jl->j_commit_bh) ;
+			reiserfs_write_unlock(s);
 			sync_dirty_buffer(jl->j_commit_bh) ;
+			reiserfs_write_lock(s);
 		}
-	} else
+	} else {
+		reiserfs_write_unlock(s);
 		wait_on_buffer(jl->j_commit_bh);
+		reiserfs_write_lock(s);
+	}
 
 	check_barrier_completion(s, jl->j_commit_bh);
 
@@ -1286,7 +1300,9 @@ static int _update_journal_header_block(struct super_block *sb,
 
 	if (trans_id >= journal->j_last_flush_trans_id) {
 		if (buffer_locked((journal->j_header_bh))) {
+			reiserfs_write_unlock(sb);
 			wait_on_buffer((journal->j_header_bh));
+			reiserfs_write_lock(sb);
 			if (unlikely(!buffer_uptodate(journal->j_header_bh))) {
 #ifdef CONFIG_REISERFS_CHECK
 				reiserfs_warning(sb, "journal-699",
@@ -1312,12 +1328,16 @@ static int _update_journal_header_block(struct super_block *sb,
 				disable_barrier(sb);
 				goto sync;
 			}
+			reiserfs_write_unlock(sb);
 			wait_on_buffer(journal->j_header_bh);
+			reiserfs_write_lock(sb);
 			check_barrier_completion(sb, journal->j_header_bh);
 		} else {
 		      sync:
 			set_buffer_dirty(journal->j_header_bh);
+			reiserfs_write_unlock(sb);
 			sync_dirty_buffer(journal->j_header_bh);
+			reiserfs_write_lock(sb);
 		}
 		if (!buffer_uptodate(journal->j_header_bh)) {
 			reiserfs_warning(sb, "journal-837",
@@ -1409,7 +1429,7 @@ static int flush_journal_list(struct super_block *s,
 
 	/* if flushall == 0, the lock is already held */
 	if (flushall) {
-		mutex_lock(&journal->j_flush_mutex);
+		reiserfs_mutex_lock_safe(&journal->j_flush_mutex, s);
 	} else if (mutex_trylock(&journal->j_flush_mutex)) {
 		BUG();
 	}
@@ -1553,7 +1573,11 @@ static int flush_journal_list(struct super_block *s,
 					reiserfs_panic(s, "journal-1011",
 						       "cn->bh is NULL");
 				}
+
+				reiserfs_write_unlock(s);
 				wait_on_buffer(cn->bh);
+				reiserfs_write_lock(s);
+
 				if (!cn->bh) {
 					reiserfs_panic(s, "journal-1012",
 						       "cn->bh is NULL");
@@ -1769,7 +1793,7 @@ static int kupdate_transactions(struct super_block *s,
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
 	chunk.nr = 0;
 
-	mutex_lock(&journal->j_flush_mutex);
+	reiserfs_mutex_lock_safe(&journal->j_flush_mutex, s);
 	if (!journal_list_still_alive(s, orig_trans_id)) {
 		goto done;
 	}
@@ -1973,11 +1997,19 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	reiserfs_mounted_fs_count--;
 	/* wait for all commits to finish */
 	cancel_delayed_work(&SB_JOURNAL(sb)->j_work);
+
+	/*
+	 * We must release the write lock here because
+	 * the workqueue job (flush_async_commit) needs this lock
+	 */
+	reiserfs_write_unlock(sb);
 	flush_workqueue(commit_wq);
+
 	if (!reiserfs_mounted_fs_count) {
 		destroy_workqueue(commit_wq);
 		commit_wq = NULL;
 	}
+	reiserfs_write_lock(sb);
 
 	free_journal_ram(sb);
 
@@ -2243,7 +2275,11 @@ static int journal_read_transaction(struct super_block *sb,
 	/* read in the log blocks, memcpy to the corresponding real block */
 	ll_rw_block(READ, get_desc_trans_len(desc), log_blocks);
 	for (i = 0; i < get_desc_trans_len(desc); i++) {
+
+		reiserfs_write_unlock(sb);
 		wait_on_buffer(log_blocks[i]);
+		reiserfs_write_lock(sb);
+
 		if (!buffer_uptodate(log_blocks[i])) {
 			reiserfs_warning(sb, "journal-1212",
 					 "REPLAY FAILURE fsck required! "
@@ -2765,11 +2801,27 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 		goto free_and_return;
 	}
 
+	/*
+	 * We need to unlock here to avoid creating the following
+	 * dependency:
+	 * reiserfs_lock -> sysfs_mutex
+	 * Because the reiserfs mmap path creates the following dependency:
+	 * mm->mmap -> reiserfs_lock, hence we have
+	 * mm->mmap -> reiserfs_lock ->sysfs_mutex
+	 * This would ends up in a circular dependency with sysfs readdir path
+	 * which does sysfs_mutex -> mm->mmap_sem
+	 * This is fine because the reiserfs lock is useless in mount path,
+	 * at least until we call journal_begin. We keep it for paranoid
+	 * reasons.
+	 */
+	reiserfs_write_unlock(sb);
 	if (journal_init_dev(sb, journal, j_dev_name) != 0) {
+		reiserfs_write_lock(sb);
 		reiserfs_warning(sb, "sh-462",
 				 "unable to initialize jornal device");
 		goto free_and_return;
 	}
+	reiserfs_write_lock(sb);
 
 	rs = SB_DISK_SUPER_BLOCK(sb);
 
@@ -2881,8 +2933,11 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	}
 
 	reiserfs_mounted_fs_count++;
-	if (reiserfs_mounted_fs_count <= 1)
+	if (reiserfs_mounted_fs_count <= 1) {
+		reiserfs_write_unlock(sb);
 		commit_wq = create_workqueue("reiserfs");
+		reiserfs_write_lock(sb);
+	}
 
 	INIT_DELAYED_WORK(&journal->j_work, flush_async_commits);
 	journal->j_work_sb = sb;
@@ -2964,8 +3019,11 @@ static void queue_log_writer(struct super_block *s)
 	init_waitqueue_entry(&wait, current);
 	add_wait_queue(&journal->j_join_wait, &wait);
 	set_current_state(TASK_UNINTERRUPTIBLE);
-	if (test_bit(J_WRITERS_QUEUED, &journal->j_state))
+	if (test_bit(J_WRITERS_QUEUED, &journal->j_state)) {
+		reiserfs_write_unlock(s);
 		schedule();
+		reiserfs_write_lock(s);
+	}
 	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&journal->j_join_wait, &wait);
 }
@@ -2982,7 +3040,9 @@ static void let_transaction_grow(struct super_block *sb, unsigned int trans_id)
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 	unsigned long bcount = journal->j_bcount;
 	while (1) {
+		reiserfs_write_unlock(sb);
 		schedule_timeout_uninterruptible(1);
+		reiserfs_write_lock(sb);
 		journal->j_current_jl->j_state |= LIST_COMMIT_PENDING;
 		while ((atomic_read(&journal->j_wcount) > 0 ||
 			atomic_read(&journal->j_jlock)) &&
@@ -3033,7 +3093,9 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 
 	if (test_bit(J_WRITERS_BLOCKED, &journal->j_state)) {
 		unlock_journal(sb);
+		reiserfs_write_unlock(sb);
 		reiserfs_wait_on_write_block(sb);
+		reiserfs_write_lock(sb);
 		PROC_INFO_INC(sb, journal.journal_relock_writers);
 		goto relock;
 	}
@@ -3506,14 +3568,14 @@ static void flush_async_commits(struct work_struct *work)
 	struct reiserfs_journal_list *jl;
 	struct list_head *entry;
 
-	lock_kernel();
+	reiserfs_write_lock(sb);
 	if (!list_empty(&journal->j_journal_list)) {
 		/* last entry is the youngest, commit it and you get everything */
 		entry = journal->j_journal_list.prev;
 		jl = JOURNAL_LIST_ENTRY(entry);
 		flush_commit_list(sb, jl, 1);
 	}
-	unlock_kernel();
+	reiserfs_write_unlock(sb);
 }
 
 /*
@@ -4041,7 +4103,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	 * the new transaction is fully setup, and we've already flushed the
 	 * ordered bh list
 	 */
-	mutex_lock(&jl->j_commit_mutex);
+	reiserfs_mutex_lock_safe(&jl->j_commit_mutex, sb);
 
 	/* save the transaction id in case we need to commit it later */
 	commit_trans_id = jl->j_trans_id;
@@ -4156,7 +4218,9 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 		next = cn->next;
 		free_cnode(sb, cn);
 		cn = next;
+		reiserfs_write_unlock(sb);
 		cond_resched();
+		reiserfs_write_lock(sb);
 	}
 
 	/* we are done  with both the c_bh and d_bh, but
@@ -4203,10 +4267,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	 * is lost.
 	 */
 	if (!list_empty(&jl->j_tail_bh_list)) {
-		unlock_kernel();
+		reiserfs_write_unlock(sb);
 		write_ordered_buffers(&journal->j_dirty_buffers_lock,
 				      journal, jl, &jl->j_tail_bh_list);
-		lock_kernel();
+		reiserfs_write_lock(sb);
 	}
 	BUG_ON(!list_empty(&jl->j_tail_bh_list));
 	mutex_unlock(&jl->j_commit_mutex);

fs/reiserfs/lock.c

+#include <linux/reiserfs_fs.h>
+#include <linux/mutex.h>
+
+/*
+ * The previous reiserfs locking scheme was heavily based on
+ * the tricky properties of the Bkl:
+ *
+ * - it was acquired recursively by a same task
+ * - the performances relied on the release-while-schedule() property
+ *
+ * Now that we replace it by a mutex, we still want to keep the same
+ * recursive property to avoid big changes in the code structure.
+ * We use our own lock_owner here because the owner field on a mutex
+ * is only available in SMP or mutex debugging, also we only need this field
+ * for this mutex, no need for a system wide mutex facility.
+ *
+ * Also this lock is often released before a call that could block because
+ * reiserfs performances were partialy based on the release while schedule()
+ * property of the Bkl.
+ */
+void reiserfs_write_lock(struct super_block *s)
+{
+	struct reiserfs_sb_info *sb_i = REISERFS_SB(s);
+
+	if (sb_i->lock_owner != current) {
+		mutex_lock(&sb_i->lock);
+		sb_i->lock_owner = current;
+	}
+
+	/* No need to protect it, only the current task touches it */
+	sb_i->lock_depth++;
+}
+
+void reiserfs_write_unlock(struct super_block *s)
+{
+	struct reiserfs_sb_info *sb_i = REISERFS_SB(s);
+
+	/*
+	 * Are we unlocking without even holding the lock?
+	 * Such a situation must raise a BUG() if we don't want
+	 * to corrupt the data.
+	 */
+	BUG_ON(sb_i->lock_owner != current);
+
+	if (--sb_i->lock_depth == -1) {
+		sb_i->lock_owner = NULL;
+		mutex_unlock(&sb_i->lock);
+	}
+}
+
+/*
+ * If we already own the lock, just exit and don't increase the depth.
+ * Useful when we don't want to lock more than once.
+ *
+ * We always return the lock_depth we had before calling
+ * this function.
+ */
+int reiserfs_write_lock_once(struct super_block *s)
+{
+	struct reiserfs_sb_info *sb_i = REISERFS_SB(s);
+
+	if (sb_i->lock_owner != current) {
+		mutex_lock(&sb_i->lock);
+		sb_i->lock_owner = current;
+		return sb_i->lock_depth++;
+	}
+
+	return sb_i->lock_depth;
+}
+
+void reiserfs_write_unlock_once(struct super_block *s, int lock_depth)
+{
+	if (lock_depth == -1)
+		reiserfs_write_unlock(s);
+}
+
+/*
+ * Utility function to force a BUG if it is called without the superblock
+ * write lock held.  caller is the string printed just before calling BUG()
+ */
+void reiserfs_check_lock_depth(struct super_block *sb, char *caller)
+{
+	struct reiserfs_sb_info *sb_i = REISERFS_SB(sb);
+
+	if (sb_i->lock_depth < 0)
+		reiserfs_panic(sb, "%s called without kernel lock held %d",
+			       caller);
+}

fs/reiserfs/namei.c

@@ -324,6 +324,7 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 				      struct nameidata *nd)
 {
 	int retval;
+	int lock_depth;
 	struct inode *inode = NULL;
 	struct reiserfs_dir_entry de;
 	INITIALIZE_PATH(path_to_entry);
@@ -331,7 +332,13 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 	if (REISERFS_MAX_NAME(dir->i_sb->s_blocksize) < dentry->d_name.len)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	reiserfs_write_lock(dir->i_sb);
+	/*
+	 * Might be called with or without the write lock, must be careful
+	 * to not recursively hold it in case we want to release the lock
+	 * before rescheduling.
+	 */
+	lock_depth = reiserfs_write_lock_once(dir->i_sb);
+
 	de.de_gen_number_bit_string = NULL;
 	retval =
 	    reiserfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len,
@@ -341,7 +348,7 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 		inode = reiserfs_iget(dir->i_sb,
 				      (struct cpu_key *)&(de.de_dir_id));
 		if (!inode || IS_ERR(inode)) {
-			reiserfs_write_unlock(dir->i_sb);
+			reiserfs_write_unlock_once(dir->i_sb, lock_depth);
 			return ERR_PTR(-EACCES);
 		}
 
@@ -350,7 +357,7 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 		if (IS_PRIVATE(dir))
 			inode->i_flags |= S_PRIVATE;
 	}
-	reiserfs_write_unlock(dir->i_sb);
+	reiserfs_write_unlock_once(dir->i_sb, lock_depth);
 	if (retval == IO_ERROR) {
 		return ERR_PTR(-EIO);
 	}
@@ -725,6 +732,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	struct inode *inode;
 	struct reiserfs_transaction_handle th;
 	struct reiserfs_security_handle security;
+	int lock_depth;
 	/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 +
@@ -748,7 +756,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 		return retval;
 	}
 	jbegin_count += retval;
-	reiserfs_write_lock(dir->i_sb);
+	lock_depth = reiserfs_write_lock_once(dir->i_sb);
 
 	retval = journal_begin(&th, dir->i_sb, jbegin_count);
 	if (retval) {
@@ -798,8 +806,8 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
 	retval = journal_end(&th, dir->i_sb, jbegin_count);
-      out_failed:
-	reiserfs_write_unlock(dir->i_sb);
+out_failed:
+	reiserfs_write_unlock_once(dir->i_sb, lock_depth);
 	return retval;
 }
 

fs/reiserfs/prints.c

@@ -349,10 +349,6 @@ void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...)
 
    .  */
 
-#ifdef CONFIG_REISERFS_CHECK
-extern struct tree_balance *cur_tb;
-#endif
-
 void __reiserfs_panic(struct super_block *sb, const char *id,
 		      const char *function, const char *fmt, ...)
 {

fs/reiserfs/resize.c

@@ -141,7 +141,9 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 
 			set_buffer_uptodate(bh);
 			mark_buffer_dirty(bh);
+			reiserfs_write_unlock(s);
 			sync_dirty_buffer(bh);
+			reiserfs_write_lock(s);
 			// update bitmap_info stuff
 			bitmap[i].free_count = sb_blocksize(sb) * 8 - 1;
 			brelse(bh);

fs/reiserfs/stree.c

@@ -222,9 +222,6 @@ static inline int bin_search(const void *key,	/* Key to search for. */
 	return ITEM_NOT_FOUND;
 }
 
-#ifdef CONFIG_REISERFS_CHECK
-extern struct tree_balance *cur_tb;
-#endif
 
 /* Minimal possible key. It is never in the tree. */
 const struct reiserfs_key MIN_KEY = { 0, 0, {{0, 0},} };
@@ -519,25 +516,48 @@ static int is_tree_node(struct buffer_head *bh, int level)
 
 #define SEARCH_BY_KEY_READA 16
 
-/* The function is NOT SCHEDULE-SAFE! */
-static void search_by_key_reada(struct super_block *s,
+/*
+ * The function is NOT SCHEDULE-SAFE!
+ * It might unlock the write lock if we needed to wait for a block
+ * to be read. Note that in this case it won't recover the lock to avoid
+ * high contention resulting from too much lock requests, especially
+ * the caller (search_by_key) will perform other schedule-unsafe
+ * operations just after calling this function.
+ *
+ * @return true if we have unlocked
+ */
+static bool search_by_key_reada(struct super_block *s,
 				struct buffer_head **bh,
 				b_blocknr_t *b, int num)
 {
 	int i, j;
+	bool unlocked = false;
 
 	for (i = 0; i < num; i++) {
 		bh[i] = sb_getblk(s, b[i]);
 	}
+	/*
+	 * We are going to read some blocks on which we
+	 * have a reference. It's safe, though we might be
+	 * reading blocks concurrently changed if we release
+	 * the lock. But it's still fine because we check later
+	 * if the tree changed
+	 */
 	for (j = 0; j < i; j++) {
 		/*
 		 * note, this needs attention if we are getting rid of the BKL
 		 * you have to make sure the prepared bit isn't set on this buffer
 		 */
-		if (!buffer_uptodate(bh[j]))
+		if (!buffer_uptodate(bh[j])) {
+			if (!unlocked) {
+				reiserfs_write_unlock(s);
+				unlocked = true;
+			}
 			ll_rw_block(READA, 1, bh + j);
+		}
 		brelse(bh[j]);
 	}
+	return unlocked;
 }
 
 /**************************************************************************
@@ -625,11 +645,26 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 		   have a pointer to it. */
 		if ((bh = last_element->pe_buffer =
 		     sb_getblk(sb, block_number))) {
+			bool unlocked = false;
+
 			if (!buffer_uptodate(bh) && reada_count > 1)
-				search_by_key_reada(sb, reada_bh,
+				/* may unlock the write lock */
+				unlocked = search_by_key_reada(sb, reada_bh,
 						    reada_blocks, reada_count);
+			/*
+			 * If we haven't already unlocked the write lock,
+			 * then we need to do that here before reading
+			 * the current block
+			 */
+			if (!buffer_uptodate(bh) && !unlocked) {
+				reiserfs_write_unlock(sb);
+				unlocked = true;
+			}
 			ll_rw_block(READ, 1, &bh);
 			wait_on_buffer(bh);
+
+			if (unlocked)
+				reiserfs_write_lock(sb);
 			if (!buffer_uptodate(bh))
 				goto io_error;
 		} else {
@@ -673,7 +708,7 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 		       !key_in_buffer(search_path, key, sb),
 		       "PAP-5130: key is not in the buffer");
 #ifdef CONFIG_REISERFS_CHECK
-		if (cur_tb) {
+		if (REISERFS_SB(sb)->cur_tb) {
 			print_cur_tb("5140");
 			reiserfs_panic(sb, "PAP-5140",
 				       "schedule occurred in do_balance!");
@@ -1024,7 +1059,9 @@ static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, st
 			reiserfs_free_block(th, inode, block, 1);
 		    }
 
+		    reiserfs_write_unlock(sb);
 		    cond_resched();
+		    reiserfs_write_lock(sb);
 
 		    if (item_moved (&s_ih, path))  {
 			need_re_search = 1;

fs/reiserfs/super.c

@@ -465,7 +465,7 @@ static void reiserfs_put_super(struct super_block *s)
 	struct reiserfs_transaction_handle th;
 	th.t_trans_id = 0;
 
-	lock_kernel();
+	reiserfs_write_lock(s);
 
 	if (s->s_dirt)
 		reiserfs_write_super(s);
@@ -499,10 +499,10 @@ static void reiserfs_put_super(struct super_block *s)
 
 	reiserfs_proc_info_done(s);
 
+	reiserfs_write_unlock(s);
+	mutex_destroy(&REISERFS_SB(s)->lock);
 	kfree(s->s_fs_info);
 	s->s_fs_info = NULL;
-
-	unlock_kernel();
 }
 
 static struct kmem_cache *reiserfs_inode_cachep;
@@ -554,25 +554,28 @@ static void reiserfs_dirty_inode(struct inode *inode)
 	struct reiserfs_transaction_handle th;
 
 	int err = 0;
+	int lock_depth;
+
 	if (inode->i_sb->s_flags & MS_RDONLY) {
 		reiserfs_warning(inode->i_sb, "clm-6006",
 				 "writing inode %lu on readonly FS",
 				 inode->i_ino);
 		return;
 	}
-	reiserfs_write_lock(inode->i_sb);
+	lock_depth = reiserfs_write_lock_once(inode->i_sb);
 
 	/* this is really only used for atime updates, so they don't have
 	 ** to be included in O_SYNC or fsync
 	 */
 	err = journal_begin(&th, inode->i_sb, 1);
-	if (err) {
-		reiserfs_write_unlock(inode->i_sb);
-		return;
-	}
+	if (err)
+		goto out;
+
 	reiserfs_update_sd(&th, inode);
 	journal_end(&th, inode->i_sb, 1);
-	reiserfs_write_unlock(inode->i_sb);
+
+out:
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 }
 
 #ifdef CONFIG_QUOTA
@@ -1168,11 +1171,14 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	unsigned int qfmt = 0;
 #ifdef CONFIG_QUOTA
 	int i;
+#endif
+
+	reiserfs_write_lock(s);
 
+#ifdef CONFIG_QUOTA
 	memcpy(qf_names, REISERFS_SB(s)->s_qf_names, sizeof(qf_names));
 #endif
 
-	lock_kernel();
 	rs = SB_DISK_SUPER_BLOCK(s);
 
 	if (!reiserfs_parse_options
@@ -1295,12 +1301,12 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 
 out_ok:
 	replace_mount_options(s, new_opts);
-	unlock_kernel();
+	reiserfs_write_unlock(s);
 	return 0;
 
 out_err:
 	kfree(new_opts);
-	unlock_kernel();
+	reiserfs_write_unlock(s);
 	return err;
 }
 
@@ -1404,7 +1410,9 @@ static int read_super_block(struct super_block *s, int offset)
 static int reread_meta_blocks(struct super_block *s)
 {
 	ll_rw_block(READ, 1, &(SB_BUFFER_WITH_SB(s)));
+	reiserfs_write_unlock(s);
 	wait_on_buffer(SB_BUFFER_WITH_SB(s));
+	reiserfs_write_lock(s);
 	if (!buffer_uptodate(SB_BUFFER_WITH_SB(s))) {
 		reiserfs_warning(s, "reiserfs-2504", "error reading the super");
 		return 1;
@@ -1613,7 +1621,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL);
 	if (!sbi) {
 		errval = -ENOMEM;
-		goto error;
+		goto error_alloc;
 	}
 	s->s_fs_info = sbi;
 	/* Set default values for options: non-aggressive tails, RO on errors */
@@ -1627,6 +1635,20 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	/* setup default block allocator options */
 	reiserfs_init_alloc_options(s);
 
+	mutex_init(&REISERFS_SB(s)->lock);
+	REISERFS_SB(s)->lock_depth = -1;
+
+	/*
+	 * This function is called with the bkl, which also was the old
+	 * locking used here.
+	 * do_journal_begin() will soon check if we hold the lock (ie: was the
+	 * bkl). This is likely because do_journal_begin() has several another
+	 * callers because at this time, it doesn't seem to be necessary to
+	 * protect against anything.
+	 * Anyway, let's be conservative and lock for now.
+	 */
+	reiserfs_write_lock(s);
+
 	jdev_name = NULL;
 	if (reiserfs_parse_options
 	    (s, (char *)data, &(sbi->s_mount_opt), &blocks, &jdev_name,
@@ -1852,9 +1874,13 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	init_waitqueue_head(&(sbi->s_wait));
 	spin_lock_init(&sbi->bitmap_lock);
 
+	reiserfs_write_unlock(s);
+
 	return (0);
 
 error:
+	reiserfs_write_unlock(s);
+error_alloc:
 	if (jinit_done) {	/* kill the commit thread, free journal ram */
 		journal_release_error(NULL, s);
 	}

fs/reiserfs/xattr.c

@@ -975,7 +975,7 @@ int reiserfs_lookup_privroot(struct super_block *s)
 	int err = 0;
 
 	/* If we don't have the privroot located yet - go find it */
-	mutex_lock(&s->s_root->d_inode->i_mutex);
+	reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s);
 	dentry = lookup_one_len(PRIVROOT_NAME, s->s_root,
 				strlen(PRIVROOT_NAME));
 	if (!IS_ERR(dentry)) {
@@ -1004,14 +1004,14 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 		goto error;
 
 	if (!privroot->d_inode && !(mount_flags & MS_RDONLY)) {
-		mutex_lock(&s->s_root->d_inode->i_mutex);
+		reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s);
 		err = create_privroot(REISERFS_SB(s)->priv_root);
 		mutex_unlock(&s->s_root->d_inode->i_mutex);
 	}
 
 	if (privroot->d_inode) {
 		s->s_xattr = reiserfs_xattr_handlers;
-		mutex_lock(&privroot->d_inode->i_mutex);
+		reiserfs_mutex_lock_safe(&privroot->d_inode->i_mutex, s);
 		if (!REISERFS_SB(s)->xattr_root) {
 			struct dentry *dentry;
 			dentry = lookup_one_len(XAROOT_NAME, privroot,

include/linux/reiserfs_fs.h

@@ -52,11 +52,63 @@
 #define REISERFS_IOC32_GETVERSION	FS_IOC32_GETVERSION
 #define REISERFS_IOC32_SETVERSION	FS_IOC32_SETVERSION
 
-/* Locking primitives */
-/* Right now we are still falling back to (un)lock_kernel, but eventually that
-   would evolve into real per-fs locks */
-#define reiserfs_write_lock( sb ) lock_kernel()
-#define reiserfs_write_unlock( sb ) unlock_kernel()
+/*
+ * Locking primitives. The write lock is a per superblock
+ * special mutex that has properties close to the Big Kernel Lock
+ * which was used in the previous locking scheme.
+ */
+void reiserfs_write_lock(struct super_block *s);
+void reiserfs_write_unlock(struct super_block *s);
+int reiserfs_write_lock_once(struct super_block *s);
+void reiserfs_write_unlock_once(struct super_block *s, int lock_depth);
+
+/*
+ * Several mutexes depend on the write lock.
+ * However sometimes we want to relax the write lock while we hold
+ * these mutexes, according to the release/reacquire on schedule()
+ * properties of the Bkl that were used.
+ * Reiserfs performances and locking were based on this scheme.
+ * Now that the write lock is a mutex and not the bkl anymore, doing so
+ * may result in a deadlock:
+ *
+ * A acquire write_lock
+ * A acquire j_commit_mutex
+ * A release write_lock and wait for something
+ * B acquire write_lock
+ * B can't acquire j_commit_mutex and sleep
+ * A can't acquire write lock anymore
+ * deadlock
+ *
+ * What we do here is avoiding such deadlock by playing the same game
+ * than the Bkl: if we can't acquire a mutex that depends on the write lock,
+ * we release the write lock, wait a bit and then retry.
+ *
+ * The mutexes concerned by this hack are:
+ * - The commit mutex of a journal list
+ * - The flush mutex
+ * - The journal lock
+ * - The inode mutex
+ */
+static inline void reiserfs_mutex_lock_safe(struct mutex *m,
+			       struct super_block *s)
+{
+	reiserfs_write_unlock(s);
+	mutex_lock(m);
+	reiserfs_write_lock(s);
+}
+
+/*
+ * When we schedule, we usually want to also release the write lock,
+ * according to the previous bkl based locking scheme of reiserfs.
+ */
+static inline void reiserfs_cond_resched(struct super_block *s)
+{
+	if (need_resched()) {
+		reiserfs_write_unlock(s);
+		schedule();
+		reiserfs_write_lock(s);
+	}
+}
 
 struct fid;
 
@@ -1329,7 +1381,11 @@ static inline loff_t max_reiserfs_offset(struct inode *inode)
 #define get_generation(s) atomic_read (&fs_generation(s))
 #define FILESYSTEM_CHANGED_TB(tb)  (get_generation((tb)->tb_sb) != (tb)->fs_gen)
 #define __fs_changed(gen,s) (gen != get_generation (s))
-#define fs_changed(gen,s) ({cond_resched(); __fs_changed(gen, s);})
+#define fs_changed(gen,s)		\
+({					\
+	reiserfs_cond_resched(s);	\
+	__fs_changed(gen, s);		\
+})
 
 /***************************************************************************/
 /*                  FIXATE NODES                                           */
@@ -2258,8 +2314,7 @@ __u32 r5_hash(const signed char *msg, int len);
 #define SPARE_SPACE 500
 
 /* prototypes from ioctl.c */
-int reiserfs_ioctl(struct inode *inode, struct file *filp,
-		   unsigned int cmd, unsigned long arg);
+long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 long reiserfs_compat_ioctl(struct file *filp,
 		   unsigned int cmd, unsigned long arg);
 int reiserfs_unpack(struct inode *inode, struct file *filp);

include/linux/reiserfs_fs_sb.h

@@ -7,6 +7,8 @@
 #ifdef __KERNEL__
 #include <linux/workqueue.h>
 #include <linux/rwsem.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
 #endif
 
 typedef enum {
@@ -355,6 +357,13 @@ struct reiserfs_sb_info {
 	struct reiserfs_journal *s_journal;	/* pointer to journal information */
 	unsigned short s_mount_state;	/* reiserfs state (valid, invalid) */
 
+	/* Serialize writers access, replace the old bkl */
+	struct mutex lock;
+	/* Owner of the lock (can be recursive) */
+	struct task_struct *lock_owner;
+	/* Depth of the lock, start from -1 like the bkl */
+	int lock_depth;
+
 	/* Comment? -Hans */
 	void (*end_io_handler) (struct buffer_head *, int);
 	hashf_t s_hash_function;	/* pointer to function which is used
@@ -408,6 +417,17 @@ struct reiserfs_sb_info {
 	char *s_qf_names[MAXQUOTAS];
 	int s_jquota_fmt;
 #endif
+#ifdef CONFIG_REISERFS_CHECK
+
+	struct tree_balance *cur_tb;	/*
+					 * Detects whether more than one
+					 * copy of tb exists per superblock
+					 * as a means of checking whether
+					 * do_balance is executing concurrently
+					 * against another tree reader/writer
+					 * on a same mount point.
+					 */
+#endif
 };
 
 /* Definitions of reiserfs on-disk properties: */