35 files changed, 428 insertions, 203 deletions

diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index c25256a5c5b0..c57d9ce5ff7e 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -171,6 +171,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 #ifdef ELF_FDPIC_PLAT_INIT
         unsigned long dynaddr;
 #endif
+#ifndef CONFIG_MMU
+        unsigned long stack_prot;
+#endif
         struct file *interpreter = NULL; /* to shut gcc up */
         char *interpreter_name = NULL;
         int executable_stack;
@@ -316,6 +319,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
          * defunct, deceased, etc. after this point we have to exit via
          * error_kill */
         set_personality(PER_LINUX_FDPIC);
+        if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
+                current->personality |= READ_IMPLIES_EXEC;
         set_binfmt(&elf_fdpic_format);
 
         current->mm->start_code = 0;
@@ -377,9 +382,13 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
         if (stack_size < PAGE_SIZE * 2)
                 stack_size = PAGE_SIZE * 2;
 
+        stack_prot = PROT_READ | PROT_WRITE;
+        if (executable_stack == EXSTACK_ENABLE_X ||
+            (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC))
+                stack_prot |= PROT_EXEC;
+
         down_write(&current->mm->mmap_sem);
-        current->mm->start_brk = do_mmap(NULL, 0, stack_size,
-                                         PROT_READ | PROT_WRITE | PROT_EXEC,
+        current->mm->start_brk = do_mmap(NULL, 0, stack_size, stack_prot,
                                          MAP_PRIVATE | MAP_ANONYMOUS |
                                          MAP_UNINITIALIZED | MAP_GROWSDOWN,
                                          0);
@@ -1798,11 +1807,11 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
         ELF_CORE_WRITE_EXTRA_DATA;
 #endif
 
-        if (file->f_pos != offset) {
+        if (cprm->file->f_pos != offset) {
                 /* Sanity check */
                 printk(KERN_WARNING
                        "elf_core_dump: file->f_pos (%lld) != offset (%lld)\n",
-                       file->f_pos, offset);
+                       cprm->file->f_pos, offset);
         }
 
 end_coredump:
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 094ea65afc85..7b2600b380d7 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -5,7 +5,9 @@ have duplicated data). Fix oops in cifs_lookup. Workaround problem
 mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session.
 Disable use of server inode numbers when server only
 partially supports them (e.g. for one server querying inode numbers on
-FindFirst fails but QPathInfo queries works).
+FindFirst fails but QPathInfo queries works). Fix oops with dfs in 
+cifs_put_smb_ses. Fix mmap to work on directio mounts (needed
+for OpenOffice when on forcedirectio mount e.g.)
 
 Version 1.60
 -------------
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 29f1da761bbf..8c6a03627176 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -758,7 +758,7 @@ const struct file_operations cifs_file_ops = {
 };
 
 const struct file_operations cifs_file_direct_ops = {
-        /* no mmap, no aio, no readv -
+        /* no aio, no readv -
            BB reevaluate whether they can be done with directio, no cache */
         .read = cifs_user_read,
         .write = cifs_user_write,
@@ -767,6 +767,7 @@ const struct file_operations cifs_file_direct_ops = {
         .lock = cifs_lock,
         .fsync = cifs_fsync,
         .flush = cifs_flush,
+        .mmap = cifs_file_mmap,
         .splice_read = generic_file_splice_read,
 #ifdef CONFIG_CIFS_POSIX
         .unlocked_ioctl  = cifs_ioctl,
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 63ea83ff687f..3bbcaa716b3c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2287,12 +2287,12 @@ int
 cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
                 char *mount_data_global, const char *devname)
 {
-        int rc = 0;
+        int rc;
         int xid;
         struct smb_vol *volume_info;
-        struct cifsSesInfo *pSesInfo = NULL;
-        struct cifsTconInfo *tcon = NULL;
-        struct TCP_Server_Info *srvTcp = NULL;
+        struct cifsSesInfo *pSesInfo;
+        struct cifsTconInfo *tcon;
+        struct TCP_Server_Info *srvTcp;
         char   *full_path;
         char *mount_data = mount_data_global;
 #ifdef CONFIG_CIFS_DFS_UPCALL
@@ -2301,6 +2301,10 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
         int referral_walks_count = 0;
 try_mount_again:
 #endif
+        rc = 0;
+        tcon = NULL;
+        pSesInfo = NULL;
+        srvTcp = NULL;
         full_path = NULL;
 
         xid = GetXid();
@@ -2597,6 +2601,7 @@ remote_path_check:
 
                         cleanup_volume_info(&volume_info);
                         referral_walks_count++;
+                        FreeXid(xid);
                         goto try_mount_again;
                 }
 #else /* No DFS support, return error on mount */
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 698a8636d39c..2afbcebeda71 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -738,13 +738,28 @@ static int exofs_write_begin_export(struct file *file,
                                         fsdata);
 }
 
+static int exofs_write_end(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned copied,
+                        struct page *page, void *fsdata)
+{
+        struct inode *inode = mapping->host;
+        /* According to comment in simple_write_end i_mutex is held */
+        loff_t i_size = inode->i_size;
+        int ret;
+
+        ret = simple_write_end(file, mapping,pos, len, copied, page, fsdata);
+        if (i_size != inode->i_size)
+                mark_inode_dirty(inode);
+        return ret;
+}
+
 const struct address_space_operations exofs_aops = {
         .readpage       = exofs_readpage,
         .readpages      = exofs_readpages,
         .writepage      = exofs_writepage,
         .writepages     = exofs_writepages,
         .write_begin    = exofs_write_begin_export,
-        .write_end      = simple_write_end,
+        .write_end      = exofs_write_end,
 };
 
 /******************************************************************************
diff --git a/fs/exofs/pnfs.h b/fs/exofs/pnfs.h
index 423033addd1f..c52e9888b8ab 100644
--- a/fs/exofs/pnfs.h
+++ b/fs/exofs/pnfs.h
@@ -15,13 +15,7 @@
 #ifndef __EXOFS_PNFS_H__
 #define __EXOFS_PNFS_H__
 
-#if defined(CONFIG_PNFS)
-
-
-/* FIXME: move this file to: linux/exportfs/pnfs_osd_xdr.h */
-#include "../nfs/objlayout/pnfs_osd_xdr.h"
-
-#else /* defined(CONFIG_PNFS) */
+#if ! defined(__PNFS_OSD_XDR_H__)
 
 enum pnfs_iomode {
         IOMODE_READ = 1,
@@ -46,6 +40,6 @@ struct pnfs_osd_data_map {
         u32     odm_raid_algorithm;
 };
 
-#endif /* else defined(CONFIG_PNFS) */
+#endif /* ! defined(__PNFS_OSD_XDR_H__) */
 
 #endif /* __EXOFS_PNFS_H__ */
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 9acf7e808139..9ed1bb1f319f 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -28,6 +28,7 @@ config EXT4_FS
 
 config EXT4_USE_FOR_EXT23
         bool "Use ext4 for ext2/ext3 file systems"
+        depends on EXT4_FS
         depends on EXT3_FS=n || EXT2_FS=n
         default y
         help
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 4df8621ec31c..a60ab9aad57d 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
-#include <linux/version.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
 #include "ext4.h"
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 56f9271ee8cc..af7b62699ea9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -699,6 +699,8 @@ struct ext4_inode_info {
         unsigned int i_reserved_meta_blocks;
         unsigned int i_allocated_meta_blocks;
         unsigned short i_delalloc_reserved_flag;
+        sector_t i_da_metadata_calc_last_lblock;
+        int i_da_metadata_calc_len;
 
         /* on-disk additional length */
         __u16 i_extra_isize;
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 2ca686454e87..bdb6ce7e2eb4 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -225,7 +225,8 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
         ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
 }
 
-extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
+extern int ext4_ext_calc_metadata_amount(struct inode *inode,
+                                         sector_t lblocks);
 extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
 extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
 extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3a7928f825e4..7d7b74e94687 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -296,29 +296,44 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
  * to allocate @blocks
  * Worse case is one block per extent
  */
-int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
+int ext4_ext_calc_metadata_amount(struct inode *inode, sector_t lblock)
 {
-        int lcap, icap, rcap, leafs, idxs, num;
-        int newextents = blocks;
-
-        rcap = ext4_ext_space_root_idx(inode, 0);
-        lcap = ext4_ext_space_block(inode, 0);
-        icap = ext4_ext_space_block_idx(inode, 0);
+        struct ext4_inode_info *ei = EXT4_I(inode);
+        int idxs, num = 0;
 
-        /* number of new leaf blocks needed */
-        num = leafs = (newextents + lcap - 1) / lcap;
+        idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+                / sizeof(struct ext4_extent_idx));
 
         /*
-         * Worse case, we need separate index block(s)
-         * to link all new leaf blocks
+         * If the new delayed allocation block is contiguous with the
+         * previous da block, it can share index blocks with the
+         * previous block, so we only need to allocate a new index
+         * block every idxs leaf blocks.  At ldxs**2 blocks, we need
+         * an additional index block, and at ldxs**3 blocks, yet
+         * another index blocks.
          */
-        idxs = (leafs + icap - 1) / icap;
-        do {
-                num += idxs;
-                idxs = (idxs + icap - 1) / icap;
-        } while (idxs > rcap);
+        if (ei->i_da_metadata_calc_len &&
+            ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+                if ((ei->i_da_metadata_calc_len % idxs) == 0)
+                        num++;
+                if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
+                        num++;
+                if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
+                        num++;
+                        ei->i_da_metadata_calc_len = 0;
+                } else
+                        ei->i_da_metadata_calc_len++;
+                ei->i_da_metadata_calc_last_lblock++;
+                return num;
+        }
 
-        return num;
+        /*
+         * In the worst case we need a new set of index blocks at
+         * every level of the inode's extent tree.
+         */
+        ei->i_da_metadata_calc_len = 1;
+        ei->i_da_metadata_calc_last_lblock = lblock;
+        return ext_depth(inode) + 1;
 }
 
 static int
@@ -3023,6 +3038,14 @@ out:
         return err;
 }
 
+static void unmap_underlying_metadata_blocks(struct block_device *bdev,
+                        sector_t block, int count)
+{
+        int i;
+        for (i = 0; i < count; i++)
+                unmap_underlying_metadata(bdev, block + i);
+}
+
 static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
                         ext4_lblk_t iblock, unsigned int max_blocks,
@@ -3098,6 +3121,18 @@ out:
         } else
                 allocated = ret;
         set_buffer_new(bh_result);
+        /*
+         * if we allocated more blocks than requested
+         * we need to make sure we unmap the extra block
+         * allocated. The actual needed block will get
+         * unmapped later when we find the buffer_head marked
+         * new.
+         */
+        if (allocated > max_blocks) {
+                unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
+                                        newblock + max_blocks,
+                                        allocated - max_blocks);
+        }
 map_out:
         set_buffer_mapped(bh_result);
 out1:
@@ -3190,7 +3225,13 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
          * this situation is possible, though, _during_ tree modification;
          * this is why assert can't be put in ext4_ext_find_extent()
          */
-        BUG_ON(path[depth].p_ext == NULL && depth != 0);
+        if (path[depth].p_ext == NULL && depth != 0) {
+                ext4_error(inode->i_sb, __func__, "bad extent address "
+                           "inode: %lu, iblock: %d, depth: %d",
+                           inode->i_ino, iblock, depth);
+                err = -EIO;
+                goto out2;
+        }
         eh = path[depth].p_hdr;
 
         ex = path[depth].p_ext;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 0b22497d92e1..98bd140aad01 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -88,9 +88,21 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
                 return ext4_force_commit(inode->i_sb);
 
         commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
-        if (jbd2_log_start_commit(journal, commit_tid))
+        if (jbd2_log_start_commit(journal, commit_tid)) {
+                /*
+                 * When the journal is on a different device than the
+                 * fs data disk, we need to issue the barrier in
+                 * writeback mode.  (In ordered mode, the jbd2 layer
+                 * will take care of issuing the barrier.  In
+                 * data=journal, all of the data blocks are written to
+                 * the journal device.)
+                 */
+                if (ext4_should_writeback_data(inode) &&
+                    (journal->j_fs_dev != journal->j_dev) &&
+                    (journal->j_flags & JBD2_BARRIER))
+                        blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
                 jbd2_log_wait_commit(journal, commit_tid);
-        else if (journal->j_flags & JBD2_BARRIER)
+        } else if (journal->j_flags & JBD2_BARRIER)
                 blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
         return ret;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ab807963a614..c818972c8302 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1009,77 +1009,88 @@ qsize_t *ext4_get_reserved_space(struct inode *inode)
         return &EXT4_I(inode)->i_reserved_quota;
 }
 #endif
+
 /*
  * Calculate the number of metadata blocks need to reserve
- * to allocate @blocks for non extent file based file
+ * to allocate a new block at @lblocks for non extent file based file
  */
-static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_indirect_calc_metadata_amount(struct inode *inode,
+                                              sector_t lblock)
 {
-        int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
-        int ind_blks, dind_blks, tind_blks;
-
-        /* number of new indirect blocks needed */
-        ind_blks = (blocks + icap - 1) / icap;
+        struct ext4_inode_info *ei = EXT4_I(inode);
+        int dind_mask = EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1;
+        int blk_bits;
 
-        dind_blks = (ind_blks + icap - 1) / icap;
+        if (lblock < EXT4_NDIR_BLOCKS)
+                return 0;
 
-        tind_blks = 1;
+        lblock -= EXT4_NDIR_BLOCKS;
 
-        return ind_blks + dind_blks + tind_blks;
+        if (ei->i_da_metadata_calc_len &&
+            (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
+                ei->i_da_metadata_calc_len++;
+                return 0;
+        }
+        ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
+        ei->i_da_metadata_calc_len = 1;
+        blk_bits = roundup_pow_of_two(lblock + 1);
+        return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
 }
 
 /*
  * Calculate the number of metadata blocks need to reserve
- * to allocate given number of blocks
+ * to allocate a block located at @lblock
  */
-static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
 {
-        if (!blocks)
-                return 0;
-
         if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
-                return ext4_ext_calc_metadata_amount(inode, blocks);
+                return ext4_ext_calc_metadata_amount(inode, lblock);
 
-        return ext4_indirect_calc_metadata_amount(inode, blocks);
+        return ext4_indirect_calc_metadata_amount(inode, lblock);
 }
 
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
 static void ext4_da_update_reserve_space(struct inode *inode, int used)
 {
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-        int total, mdb, mdb_free, mdb_claim = 0;
-
-        spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-        /* recalculate the number of metablocks still need to be reserved */
-        total = EXT4_I(inode)->i_reserved_data_blocks - used;
-        mdb = ext4_calc_metadata_amount(inode, total);
-
-        /* figure out how many metablocks to release */
-        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-        mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
-        if (mdb_free) {
-                /* Account for allocated meta_blocks */
-                mdb_claim = EXT4_I(inode)->i_allocated_meta_blocks;
-                BUG_ON(mdb_free < mdb_claim);
-                mdb_free -= mdb_claim;
-
-                /* update fs dirty blocks counter */
+        struct ext4_inode_info *ei = EXT4_I(inode);
+        int mdb_free = 0;
+
+        spin_lock(&ei->i_block_reservation_lock);
+        if (unlikely(used > ei->i_reserved_data_blocks)) {
+                ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+                         "with only %d reserved data blocks\n",
+                         __func__, inode->i_ino, used,
+                         ei->i_reserved_data_blocks);
+                WARN_ON(1);
+                used = ei->i_reserved_data_blocks;
+        }
+
+        /* Update per-inode reservations */
+        ei->i_reserved_data_blocks -= used;
+        used += ei->i_allocated_meta_blocks;
+        ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
+        ei->i_allocated_meta_blocks = 0;
+        percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
+
+        if (ei->i_reserved_data_blocks == 0) {
+                /*
+                 * We can release all of the reserved metadata blocks
+                 * only when we have written all of the delayed
+                 * allocation blocks.
+                 */
+                mdb_free = ei->i_reserved_meta_blocks;
+                ei->i_reserved_meta_blocks = 0;
+                ei->i_da_metadata_calc_len = 0;
                 percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
-                EXT4_I(inode)->i_allocated_meta_blocks = 0;
-                EXT4_I(inode)->i_reserved_meta_blocks = mdb;
         }
-
-        /* update per-inode reservations */
-        BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
-        EXT4_I(inode)->i_reserved_data_blocks -= used;
-        percpu_counter_sub(&sbi->s_dirtyblocks_counter, used + mdb_claim);
         spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-        vfs_dq_claim_block(inode, used + mdb_claim);
-
-        /*
-         * free those over-booking quota for metadata blocks
-         */
+        /* Update quota subsystem */
+        vfs_dq_claim_block(inode, used);
         if (mdb_free)
                 vfs_dq_release_reservation_block(inode, mdb_free);
 
@@ -1088,7 +1099,8 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
          * there aren't any writers on the inode, we can discard the
          * inode's preallocations.
          */
-        if (!total && (atomic_read(&inode->i_writecount) == 0))
+        if ((ei->i_reserved_data_blocks == 0) &&
+            (atomic_read(&inode->i_writecount) == 0))
                 ext4_discard_preallocations(inode);
 }
 
@@ -1797,11 +1809,15 @@ static int ext4_journalled_write_end(struct file *file,
         return ret ? ret : copied;
 }
 
-static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
+/*
+ * Reserve a single block located at lblock
+ */
+static int ext4_da_reserve_space(struct inode *inode, sector_t lblock)
 {
         int retries = 0;
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-        unsigned long md_needed, mdblocks, total = 0;
+        struct ext4_inode_info *ei = EXT4_I(inode);
+        unsigned long md_needed, md_reserved;
 
         /*
          * recalculate the amount of metadata blocks to reserve
@@ -1809,35 +1825,43 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
          * worse case is one extent per block
          */
 repeat:
-        spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-        total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
-        mdblocks = ext4_calc_metadata_amount(inode, total);
-        BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks);
-
-        md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
-        total = md_needed + nrblocks;
-        spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+        spin_lock(&ei->i_block_reservation_lock);
+        md_reserved = ei->i_reserved_meta_blocks;
+        md_needed = ext4_calc_metadata_amount(inode, lblock);
+        spin_unlock(&ei->i_block_reservation_lock);
 
         /*
          * Make quota reservation here to prevent quota overflow
          * later. Real quota accounting is done at pages writeout
          * time.
          */
-        if (vfs_dq_reserve_block(inode, total))
+        if (vfs_dq_reserve_block(inode, md_needed + 1)) {
+                /* 
+                 * We tend to badly over-estimate the amount of
+                 * metadata blocks which are needed, so if we have
+                 * reserved any metadata blocks, try to force out the
+                 * inode and see if we have any better luck.
+                 */
+                if (md_reserved && retries++ <= 3)
+                        goto retry;
                 return -EDQUOT;
+        }
 
-        if (ext4_claim_free_blocks(sbi, total)) {
-                vfs_dq_release_reservation_block(inode, total);
+        if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
+                vfs_dq_release_reservation_block(inode, md_needed + 1);
                 if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+                retry:
+                        if (md_reserved)
+                                write_inode_now(inode, (retries == 3));
                         yield();
                         goto repeat;
                 }
                 return -ENOSPC;
         }
-        spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-        EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
-        EXT4_I(inode)->i_reserved_meta_blocks += md_needed;
-        spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+        spin_lock(&ei->i_block_reservation_lock);
+        ei->i_reserved_data_blocks++;
+        ei->i_reserved_meta_blocks += md_needed;
+        spin_unlock(&ei->i_block_reservation_lock);
 
         return 0;       /* success */
 }
@@ -1845,49 +1869,46 @@ repeat:
 static void ext4_da_release_space(struct inode *inode, int to_free)
 {
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-        int total, mdb, mdb_free, release;
+        struct ext4_inode_info *ei = EXT4_I(inode);
 
         if (!to_free)
                 return;         /* Nothing to release, exit */
 
         spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 
-        if (!EXT4_I(inode)->i_reserved_data_blocks) {
+        if (unlikely(to_free > ei->i_reserved_data_blocks)) {
                 /*
-                 * if there is no reserved blocks, but we try to free some
-                 * then the counter is messed up somewhere.
-                 * but since this function is called from invalidate
-                 * page, it's harmless to return without any action
+                 * if there aren't enough reserved blocks, then the
+                 * counter is messed up somewhere.  Since this
+                 * function is called from invalidate page, it's
+                 * harmless to return without any action.
                  */
-                printk(KERN_INFO "ext4 delalloc try to release %d reserved "
-                            "blocks for inode %lu, but there is no reserved "
-                            "data blocks\n", to_free, inode->i_ino);
-                spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-                return;
+                ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+                         "ino %lu, to_free %d with only %d reserved "
+                         "data blocks\n", inode->i_ino, to_free,
+                         ei->i_reserved_data_blocks);
+                WARN_ON(1);
+                to_free = ei->i_reserved_data_blocks;
         }
+        ei->i_reserved_data_blocks -= to_free;
 
-        /* recalculate the number of metablocks still need to be reserved */
-        total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
-        mdb = ext4_calc_metadata_amount(inode, total);
-
-        /* figure out how many metablocks to release */
-        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-        mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
-        release = to_free + mdb_free;
-
-        /* update fs dirty blocks counter for truncate case */
-        percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
+        if (ei->i_reserved_data_blocks == 0) {
+                /*
+                 * We can release all of the reserved metadata blocks
+                 * only when we have written all of the delayed
+                 * allocation blocks.
+                 */
+                to_free += ei->i_reserved_meta_blocks;
+                ei->i_reserved_meta_blocks = 0;
+                ei->i_da_metadata_calc_len = 0;
+        }
 
-        /* update per-inode reservations */
-        BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
-        EXT4_I(inode)->i_reserved_data_blocks -= to_free;
+        /* update fs dirty blocks counter */
+        percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
 
-        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-        EXT4_I(inode)->i_reserved_meta_blocks = mdb;
         spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-        vfs_dq_release_reservation_block(inode, release);
+        vfs_dq_release_reservation_block(inode, to_free);
 }
 
 static void ext4_da_page_release_reservation(struct page *page,
@@ -2493,7 +2514,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
                  * XXX: __block_prepare_write() unmaps passed block,
                  * is it OK?
                  */
-                ret = ext4_da_reserve_space(inode, 1);
+                ret = ext4_da_reserve_space(inode, iblock);
                 if (ret)
                         /* not enough space to reserve */
                         return ret;
@@ -2967,8 +2988,7 @@ retry:
 out_writepages:
         if (!no_nrwrite_index_update)
                 wbc->no_nrwrite_index_update = 0;
-        if (wbc->nr_to_write > nr_to_writebump)
-                wbc->nr_to_write -= nr_to_writebump;
+        wbc->nr_to_write -= nr_to_writebump;
         wbc->range_start = range_start;
         trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
         return ret;
@@ -2993,11 +3013,18 @@ static int ext4_nonda_switch(struct super_block *sb)
         if (2 * free_blocks < 3 * dirty_blocks ||
                 free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
                 /*
-                 * free block count is less that 150% of dirty blocks
-                 * or free blocks is less that watermark
+                 * free block count is less than 150% of dirty blocks
+                 * or free blocks is less than watermark
                  */
                 return 1;
         }
+        /*
+         * Even if we don't switch but are nearing capacity,
+         * start pushing delalloc when 1/2 of free blocks are dirty.
+         */
+        if (free_blocks < 2 * dirty_blocks)
+                writeback_inodes_sb_if_idle(sb);
+
         return 0;
 }
 
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 0ca811061bc7..436521cae456 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -17,7 +17,6 @@
 #include <linux/proc_fs.h>
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
-#include <linux/version.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
 #include "ext4_jbd2.h"
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6ed9aa91f27d..735c20d5fd56 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -702,6 +702,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
         ei->i_reserved_data_blocks = 0;
         ei->i_reserved_meta_blocks = 0;
         ei->i_allocated_meta_blocks = 0;
+        ei->i_da_metadata_calc_len = 0;
         ei->i_delalloc_reserved_flag = 0;
         spin_lock_init(&(ei->i_block_reservation_lock));
 #ifdef CONFIG_QUOTA
@@ -2174,9 +2175,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
         struct super_block *sb = sbi->s_buddy_cache->i_sb;
 
         return snprintf(buf, PAGE_SIZE, "%llu\n",
-                        sbi->s_kbytes_written + 
+                        (unsigned long long)(sbi->s_kbytes_written +
                         ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
-                          EXT4_SB(sb)->s_sectors_written_start) >> 1));
+                          EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
 static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
@@ -4005,6 +4006,7 @@ static inline void unregister_as_ext2(void)
 {
         unregister_filesystem(&ext2_fs_type);
 }
+MODULE_ALIAS("ext2");
 #else
 static inline void register_as_ext2(void) { }
 static inline void unregister_as_ext2(void) { }
@@ -4031,6 +4033,7 @@ static inline void unregister_as_ext3(void)
 {
         unregister_filesystem(&ext3_fs_type);
 }
+MODULE_ALIAS("ext3");
 #else
 static inline void register_as_ext3(void) { }
 static inline void unregister_as_ext3(void) { }
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 83218bebbc7c..f3a2f7ed45aa 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1332,6 +1332,8 @@ retry:
                         goto cleanup;
                 kfree(b_entry_name);
                 kfree(buffer);
+                b_entry_name = NULL;
+                buffer = NULL;
                 brelse(is->iloc.bh);
                 kfree(is);
                 kfree(bs);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 49bc1b8e8f19..1a7c42c64ff4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -242,6 +242,7 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
 /**
  * bdi_start_writeback - start writeback
  * @bdi: the backing device to write from
+ * @sb: write inodes from this super_block
  * @nr_pages: the number of pages to write
  *
  * Description:
@@ -1187,6 +1188,23 @@ void writeback_inodes_sb(struct super_block *sb)
 EXPORT_SYMBOL(writeback_inodes_sb);
 
 /**
+ * writeback_inodes_sb_if_idle  -       start writeback if none underway
+ * @sb: the superblock
+ *
+ * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int writeback_inodes_sb_if_idle(struct super_block *sb)
+{
+        if (!writeback_in_progress(sb->s_bdi)) {
+                writeback_inodes_sb(sb);
+                return 1;
+        } else
+                return 0;
+}
+EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
+
+/**
  * sync_inodes_sb       -       sync sb inode pages
  * @sb: the superblock
  *
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index ca0f5eb62b20..886849370950 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -22,6 +22,7 @@
 #include <linux/jbd2.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 #include <trace/events/jbd2.h>
 
 /*
@@ -515,6 +516,20 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
         journal->j_tail_sequence = first_tid;
         journal->j_tail = blocknr;
         spin_unlock(&journal->j_state_lock);
+
+        /*
+         * If there is an external journal, we need to make sure that
+         * any data blocks that were recently written out --- perhaps
+         * by jbd2_log_do_checkpoint() --- are flushed out before we
+         * drop the transactions from the external journal.  It's
+         * unlikely this will be necessary, especially with a
+         * appropriately sized journal, but we need this to guarantee
+         * correctness.  Fortunately jbd2_cleanup_journal_tail()
+         * doesn't get called all that often.
+         */
+        if ((journal->j_fs_dev != journal->j_dev) &&
+            (journal->j_flags & JBD2_BARRIER))
+                blkdev_issue_flush(journal->j_fs_dev, NULL);
         if (!(journal->j_flags & JBD2_ABORT))
                 jbd2_journal_update_superblock(journal, 1);
         return 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6a10238d2c63..1bc74b6f26d2 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -259,6 +259,7 @@ static int journal_submit_data_buffers(journal_t *journal,
                         ret = err;
                 spin_lock(&journal->j_list_lock);
                 J_ASSERT(jinode->i_transaction == commit_transaction);
+                commit_transaction->t_flushed_data_blocks = 1;
                 jinode->i_flags &= ~JI_COMMIT_RUNNING;
                 wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
         }
@@ -708,8 +709,17 @@ start_journal_io:
                 }
         }
 
-        /* Done it all: now write the commit record asynchronously. */
+        /* 
+         * If the journal is not located on the file system device,
+         * then we must flush the file system device before we issue
+         * the commit record
+         */
+        if (commit_transaction->t_flushed_data_blocks &&
+            (journal->j_fs_dev != journal->j_dev) &&
+            (journal->j_flags & JBD2_BARRIER))
+                blkdev_issue_flush(journal->j_fs_dev, NULL);
 
+        /* Done it all: now write the commit record asynchronously. */
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
                                       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
                 err = journal_submit_commit_record(journal, commit_transaction,
@@ -720,13 +730,6 @@ start_journal_io:
                         blkdev_issue_flush(journal->j_dev, NULL);
         }
 
-        /*
-         * This is the right place to wait for data buffers both for ASYNC
-         * and !ASYNC commit. If commit is ASYNC, we need to wait only after
-         * the commit block went to disk (which happens above). If commit is
-         * SYNC, we need to wait for data buffers before we start writing
-         * commit block, which happens below in such setting.
-         */
         err = journal_finish_inode_data_buffers(journal, commit_transaction);
         if (err) {
                 printk(KERN_WARNING
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 17af879e6e9e..ac0d027595d0 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -814,7 +814,7 @@ static journal_t * journal_init_common (void)
         journal_t *journal;
         int err;
 
-        journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
+        journal = kzalloc(sizeof(*journal), GFP_KERNEL);
         if (!journal)
                 goto fail;
 
diff --git a/fs/namei.c b/fs/namei.c
index 68921d9b5302..b55440baf7ab 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -232,6 +232,7 @@ int generic_permission(struct inode *inode, int mask,
         /*
          * Searching includes executable on directories, else just read.
          */
+        mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
         if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
                 if (capable(CAP_DAC_READ_SEARCH))
                         return 0;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7c2e337d05af..c194793b642b 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -780,12 +780,9 @@ static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
         int (*fsync) (struct file *, struct dentry *, int);
         int err;
 
-        err = filemap_fdatawrite(inode->i_mapping);
+        err = filemap_write_and_wait(inode->i_mapping);
         if (err == 0 && fop && (fsync = fop->fsync))
                 err = fsync(filp, dp, 0);
-        if (err == 0)
-                err = filemap_fdatawait(inode->i_mapping);
-
         return err;
 }
 
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index f4a14ea2ed9c..effdbdbe6c11 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -417,8 +417,8 @@ __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *bmap,
 
         key = page_index(bh->b_page) << (PAGE_CACHE_SHIFT -
                                          bmap->b_inode->i_blkbits);
-        for (pbh = page_buffers(bh->b_page); pbh != bh;
-             pbh = pbh->b_this_page, key++);
+        for (pbh = page_buffers(bh->b_page); pbh != bh; pbh = pbh->b_this_page)
+                key++;
 
         return key;
 }
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index d5ad54e204a5..18737818db63 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -328,19 +328,24 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
                         tnicps += nicps;
                         nilfs_mdt_mark_buffer_dirty(cp_bh);
                         nilfs_mdt_mark_dirty(cpfile);
-                        if (!nilfs_cpfile_is_in_first(cpfile, cno) &&
-                            (count = nilfs_cpfile_block_sub_valid_checkpoints(
-                                    cpfile, cp_bh, kaddr, nicps)) == 0) {
-                                /* make hole */
-                                kunmap_atomic(kaddr, KM_USER0);
-                                brelse(cp_bh);
-                                ret = nilfs_cpfile_delete_checkpoint_block(
-                                        cpfile, cno);
-                                if (ret == 0)
-                                        continue;
-                                printk(KERN_ERR "%s: cannot delete block\n",
-                                       __func__);
-                                break;
+                        if (!nilfs_cpfile_is_in_first(cpfile, cno)) {
+                                count =
+                                  nilfs_cpfile_block_sub_valid_checkpoints(
+                                                cpfile, cp_bh, kaddr, nicps);
+                                if (count == 0) {
+                                        /* make hole */
+                                        kunmap_atomic(kaddr, KM_USER0);
+                                        brelse(cp_bh);
+                                        ret =
+                                          nilfs_cpfile_delete_checkpoint_block(
+                                                                   cpfile, cno);
+                                        if (ret == 0)
+                                                continue;
+                                        printk(KERN_ERR
+                                               "%s: cannot delete block\n",
+                                               __func__);
+                                        break;
+                                }
                         }
                 }
 
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index d369ac718277..236753df5cdf 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -51,11 +51,11 @@ static int nilfs_direct_lookup(const struct nilfs_bmap *bmap,
         struct nilfs_direct *direct;
         __u64 ptr;
 
-        direct = (struct nilfs_direct *)bmap;
-        if ((key > NILFS_DIRECT_KEY_MAX) ||
-            (level != 1) ||     /* XXX: use macro for level 1 */
-            ((ptr = nilfs_direct_get_ptr(direct, key)) ==
-             NILFS_BMAP_INVALID_PTR))
+        direct = (struct nilfs_direct *)bmap;  /* XXX: use macro for level 1 */
+        if (key > NILFS_DIRECT_KEY_MAX || level != 1)
+                return -ENOENT;
+        ptr = nilfs_direct_get_ptr(direct, key);
+        if (ptr == NILFS_BMAP_INVALID_PTR)
                 return -ENOENT;
 
         if (ptrp != NULL)
@@ -73,9 +73,10 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *bmap,
         sector_t blocknr;
         int ret, cnt;
 
-        if (key > NILFS_DIRECT_KEY_MAX ||
-            (ptr = nilfs_direct_get_ptr(direct, key)) ==
-            NILFS_BMAP_INVALID_PTR)
+        if (key > NILFS_DIRECT_KEY_MAX)
+                return -ENOENT;
+        ptr = nilfs_direct_get_ptr(direct, key);
+        if (ptr == NILFS_BMAP_INVALID_PTR)
                 return -ENOENT;
 
         if (NILFS_BMAP_USE_VBN(bmap)) {
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index f6af76042d80..d6b2b83de363 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -480,7 +480,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
                                       unsigned int cmd, void __user *argp)
 {
         struct nilfs_argv argv[5];
-        const static size_t argsz[5] = {
+        static const size_t argsz[5] = {
                 sizeof(struct nilfs_vdesc),
                 sizeof(struct nilfs_period),
                 sizeof(__u64),
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3d30a1c974a8..06ccf6a86d35 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1772,7 +1772,8 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
                                          loff_t *ppos,
                                          size_t count,
                                          int appending,
-                                         int *direct_io)
+                                         int *direct_io,
+                                         int *has_refcount)
 {
         int ret = 0, meta_level = 0;
         struct inode *inode = dentry->d_inode;
@@ -1833,6 +1834,8 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
                                                                saved_pos,
                                                                count,
                                                                &meta_level);
+                        if (has_refcount)
+                                *has_refcount = 1;
                 }
 
                 if (ret < 0) {
@@ -1856,6 +1859,10 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
                         break;
                 }
 
+                if (has_refcount && *has_refcount == 1) {
+                        *direct_io = 0;
+                        break;
+                }
                 /*
                  * Allowing concurrent direct writes means
                  * i_size changes wouldn't be synchronized, so
@@ -1899,7 +1906,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
                                     loff_t pos)
 {
         int ret, direct_io, appending, rw_level, have_alloc_sem  = 0;
-        int can_do_direct;
+        int can_do_direct, has_refcount = 0;
         ssize_t written = 0;
         size_t ocount;          /* original count */
         size_t count;           /* after file limit checks */
@@ -1942,7 +1949,7 @@ relock:
         can_do_direct = direct_io;
         ret = ocfs2_prepare_inode_for_write(file->f_path.dentry, ppos,
                                             iocb->ki_left, appending,
-                                            &can_do_direct);
+                                            &can_do_direct, &has_refcount);
         if (ret < 0) {
                 mlog_errno(ret);
                 goto out;
@@ -2006,14 +2013,16 @@ out_dio:
         /* buffered aio wouldn't have proper lock coverage today */
         BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT));
 
-        if ((file->f_flags & O_DSYNC && !direct_io) || IS_SYNC(inode)) {
+        if ((file->f_flags & O_DSYNC && !direct_io) || IS_SYNC(inode) ||
+            (file->f_flags & O_DIRECT && has_refcount)) {
                 ret = filemap_fdatawrite_range(file->f_mapping, pos,
                                                pos + count - 1);
                 if (ret < 0)
                         written = ret;
 
                 if (!ret && (old_size != i_size_read(inode) ||
-                    old_clusters != OCFS2_I(inode)->ip_clusters)) {
+                    old_clusters != OCFS2_I(inode)->ip_clusters ||
+                    has_refcount)) {
                         ret = jbd2_journal_force_commit(osb->journal->j_journal);
                         if (ret < 0)
                                 written = ret;
@@ -2062,7 +2071,7 @@ static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
         int ret;
 
         ret = ocfs2_prepare_inode_for_write(out->f_path.dentry, &sd->pos,
-                                            sd->total_len, 0, NULL);
+                                            sd->total_len, 0, NULL, NULL);
         if (ret < 0) {
                 mlog_errno(ret);
                 return ret;
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index 685495707181..65c872761177 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -1277,7 +1277,10 @@ int reiserfs_init_bitmap_cache(struct super_block *sb)
         struct reiserfs_bitmap_info *bitmap;
         unsigned int bmap_nr = reiserfs_bmap_count(sb);
 
+        /* Avoid lock recursion in fault case */
+        reiserfs_write_unlock(sb);
         bitmap = vmalloc(sizeof(*bitmap) * bmap_nr);
+        reiserfs_write_lock(sb);
         if (bitmap == NULL)
                 return -ENOMEM;
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 290ae38fca8a..1150ebb2536f 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -31,11 +31,12 @@ void reiserfs_delete_inode(struct inode *inode)
             JOURNAL_PER_BALANCE_CNT * 2 +
             2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
         struct reiserfs_transaction_handle th;
+        int depth;
         int err;
 
         truncate_inode_pages(&inode->i_data, 0);
 
-        reiserfs_write_lock(inode->i_sb);
+        depth = reiserfs_write_lock_once(inode->i_sb);
 
         /* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */
         if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) {  /* also handles bad_inode case */
@@ -74,7 +75,7 @@ void reiserfs_delete_inode(struct inode *inode)
       out:
         clear_inode(inode);     /* note this must go after the journal_end to prevent deadlock */
         inode->i_blocks = 0;
-        reiserfs_write_unlock(inode->i_sb);
+        reiserfs_write_unlock_once(inode->i_sb, depth);
 }
 
 static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 2f8a7e7b8dab..83ac4d3b3cb0 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2009,10 +2009,11 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
                 destroy_workqueue(commit_wq);
                 commit_wq = NULL;
         }
-        reiserfs_write_lock(sb);
 
         free_journal_ram(sb);
 
+        reiserfs_write_lock(sb);
+
         return 0;
 }
 
@@ -2758,11 +2759,18 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
         struct reiserfs_journal *journal;
         struct reiserfs_journal_list *jl;
         char b[BDEVNAME_SIZE];
+        int ret;
 
+        /*
+         * Unlock here to avoid various RECLAIM-FS-ON <-> IN-RECLAIM-FS
+         * dependency inversion warnings.
+         */
+        reiserfs_write_unlock(sb);
         journal = SB_JOURNAL(sb) = vmalloc(sizeof(struct reiserfs_journal));
         if (!journal) {
                 reiserfs_warning(sb, "journal-1256",
                                  "unable to get memory for journal structure");
+                reiserfs_write_lock(sb);
                 return 1;
         }
         memset(journal, 0, sizeof(struct reiserfs_journal));
@@ -2771,10 +2779,12 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
         INIT_LIST_HEAD(&journal->j_working_list);
         INIT_LIST_HEAD(&journal->j_journal_list);
         journal->j_persistent_trans = 0;
-        if (reiserfs_allocate_list_bitmaps(sb,
-                                           journal->j_list_bitmap,
-                                           reiserfs_bmap_count(sb)))
+        ret = reiserfs_allocate_list_bitmaps(sb, journal->j_list_bitmap,
+                                           reiserfs_bmap_count(sb));
+        reiserfs_write_lock(sb);
+        if (ret)
                 goto free_and_return;
+
         allocate_bitmap_nodes(sb);
 
         /* reserved for journal area support */
diff --git a/fs/reiserfs/lock.c b/fs/reiserfs/lock.c
index ee2cfc0fd8a7..b87aa2c1afc1 100644
--- a/fs/reiserfs/lock.c
+++ b/fs/reiserfs/lock.c
@@ -86,3 +86,12 @@ void reiserfs_check_lock_depth(struct super_block *sb, char *caller)
                 reiserfs_panic(sb, "%s called without kernel lock held %d",
                                caller);
 }
+
+#ifdef CONFIG_REISERFS_CHECK
+void reiserfs_lock_check_recursive(struct super_block *sb)
+{
+        struct reiserfs_sb_info *sb_i = REISERFS_SB(sb);
+
+        WARN_ONCE((sb_i->lock_depth > 0), "Unwanted recursive reiserfs lock!\n");
+}
+#endif
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index e296ff72a6cc..9d4dcf0b07cb 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -921,6 +921,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
         struct reiserfs_transaction_handle th;
         int jbegin_count;
         unsigned long savelink;
+        int depth;
 
         inode = dentry->d_inode;
 
@@ -932,7 +933,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
             JOURNAL_PER_BALANCE_CNT * 2 + 2 +
             4 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
 
-        reiserfs_write_lock(dir->i_sb);
+        depth = reiserfs_write_lock_once(dir->i_sb);
         retval = journal_begin(&th, dir->i_sb, jbegin_count);
         if (retval)
                 goto out_unlink;
@@ -993,7 +994,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
 
         retval = journal_end(&th, dir->i_sb, jbegin_count);
         reiserfs_check_path(&path);
-        reiserfs_write_unlock(dir->i_sb);
+        reiserfs_write_unlock_once(dir->i_sb, depth);
         return retval;
 
       end_unlink:
@@ -1003,7 +1004,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
         if (err)
                 retval = err;
       out_unlink:
-        reiserfs_write_unlock(dir->i_sb);
+        reiserfs_write_unlock_once(dir->i_sb, depth);
         return retval;
 }
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 8c7033a8b67e..c3b004ee627b 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -83,7 +83,8 @@ static int xattr_unlink(struct inode *dir, struct dentry *dentry)
         BUG_ON(!mutex_is_locked(&dir->i_mutex));
         vfs_dq_init(dir);
 
-        mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+        reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex,
+                                        I_MUTEX_CHILD, dir->i_sb);
         error = dir->i_op->unlink(dir, dentry);
         mutex_unlock(&dentry->d_inode->i_mutex);
 
@@ -98,7 +99,8 @@ static int xattr_rmdir(struct inode *dir, struct dentry *dentry)
         BUG_ON(!mutex_is_locked(&dir->i_mutex));
         vfs_dq_init(dir);
 
-        mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+        reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex,
+                                        I_MUTEX_CHILD, dir->i_sb);
         dentry_unhash(dentry);
         error = dir->i_op->rmdir(dir, dentry);
         if (!error)
@@ -235,16 +237,22 @@ static int reiserfs_for_each_xattr(struct inode *inode,
         if (IS_PRIVATE(inode) || get_inode_sd_version(inode) == STAT_DATA_V1)
                 return 0;
 
+        reiserfs_write_unlock(inode->i_sb);
         dir = open_xa_dir(inode, XATTR_REPLACE);
         if (IS_ERR(dir)) {
                 err = PTR_ERR(dir);
+                reiserfs_write_lock(inode->i_sb);
                 goto out;
         } else if (!dir->d_inode) {
                 err = 0;
+                reiserfs_write_lock(inode->i_sb);
                 goto out_dir;
         }
 
         mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_XATTR);
+
+        reiserfs_write_lock(inode->i_sb);
+
         buf.xadir = dir;
         err = reiserfs_readdir_dentry(dir, &buf, fill_with_dentries, &pos);
         while ((err == 0 || err == -ENOSPC) && buf.count) {
@@ -283,8 +291,9 @@ static int reiserfs_for_each_xattr(struct inode *inode,
                 err = journal_begin(&th, inode->i_sb, blocks);
                 if (!err) {
                         int jerror;
-                        mutex_lock_nested(&dir->d_parent->d_inode->i_mutex,
-                                          I_MUTEX_XATTR);
+                        reiserfs_mutex_lock_nested_safe(
+                                          &dir->d_parent->d_inode->i_mutex,
+                                          I_MUTEX_XATTR, inode->i_sb);
                         err = action(dir, data);
                         jerror = journal_end(&th, inode->i_sb, blocks);
                         mutex_unlock(&dir->d_parent->d_inode->i_mutex);
@@ -480,11 +489,16 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
         if (!buffer)
                 return lookup_and_delete_xattr(inode, name);
 
+        reiserfs_write_unlock(inode->i_sb);
         dentry = xattr_lookup(inode, name, flags);
-        if (IS_ERR(dentry))
+        if (IS_ERR(dentry)) {
+                reiserfs_write_lock(inode->i_sb);
                 return PTR_ERR(dentry);
+        }
 
-        down_write(&REISERFS_I(inode)->i_xattr_sem);
+        down_read(&REISERFS_I(inode)->i_xattr_sem);
+
+        reiserfs_write_lock(inode->i_sb);
 
         xahash = xattr_hash(buffer, buffer_size);
         while (buffer_pos < buffer_size || buffer_pos == 0) {
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index f05f2303a8b8..699f371b9f12 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -106,8 +106,10 @@ static struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
                         return NULL;
 
                 t = atomic_cmpxchg(&sd->s_active, v, v + 1);
-                if (likely(t == v))
+                if (likely(t == v)) {
+                        rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
                         return sd;
+                }
                 if (t < 0)
                         return NULL;
 
@@ -130,6 +132,7 @@ static void sysfs_put_active(struct sysfs_dirent *sd)
         if (unlikely(!sd))
                 return;
 
+        rwsem_release(&sd->dep_map, 1, _RET_IP_);
         v = atomic_dec_return(&sd->s_active);
         if (likely(v != SD_DEACTIVATED_BIAS))
                 return;
@@ -194,15 +197,21 @@ static void sysfs_deactivate(struct sysfs_dirent *sd)
         BUG_ON(sd->s_sibling || !(sd->s_flags & SYSFS_FLAG_REMOVED));
         sd->s_sibling = (void *)&wait;
 
+        rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_);
         /* atomic_add_return() is a mb(), put_active() will always see
          * the updated sd->s_sibling.
          */
         v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active);
 
-        if (v != SD_DEACTIVATED_BIAS)
+        if (v != SD_DEACTIVATED_BIAS) {
+                lock_contended(&sd->dep_map, _RET_IP_);
                 wait_for_completion(&wait);
+        }
 
         sd->s_sibling = NULL;
+
+        lock_acquired(&sd->dep_map, _RET_IP_);
+        rwsem_release(&sd->dep_map, 1, _RET_IP_);
 }
 
 static int sysfs_alloc_ino(ino_t *pino)
@@ -345,6 +354,7 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
 
         atomic_set(&sd->s_count, 1);
         atomic_set(&sd->s_active, 0);
+        sysfs_dirent_init_lockdep(sd);
 
         sd->s_name = name;
         sd->s_mode = mode;
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index ca52e7b9d8f8..cdd9377a6e06 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -8,6 +8,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/lockdep.h>
 #include <linux/fs.h>
 
 struct sysfs_open_dirent;
@@ -50,6 +51,9 @@ struct sysfs_inode_attrs {
 struct sysfs_dirent {
         atomic_t                s_count;
         atomic_t                s_active;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        struct lockdep_map      dep_map;
+#endif
         struct sysfs_dirent     *s_parent;
         struct sysfs_dirent     *s_sibling;
         const char              *s_name;
@@ -84,6 +88,17 @@ static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
         return sd->s_flags & SYSFS_TYPE_MASK;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#define sysfs_dirent_init_lockdep(sd)                           \
+do {                                                            \
+        static struct lock_class_key __key;                     \
+                                                                \
+        lockdep_init_map(&sd->dep_map, "s_active", &__key, 0);  \
+} while(0)
+#else
+#define sysfs_dirent_init_lockdep(sd) do {} while(0)
+#endif
+
 /*
  * Context structure to be used while adding/removing nodes.
  */