Merge branch 'sched/urgent' into sched/core

Merge reason: Merge dependent fix, update to latest -rc.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

119 files changed, 2152 insertions, 1641 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 18f74ec..9d03d1e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1001,44 +1001,6 @@ done:
 }
 
 /**
- * v9fs_vfs_readlink - read a symlink's location
- * @dentry: dentry for symlink
- * @buffer: buffer to load symlink location into
- * @buflen: length of buffer
- *
- */
-
-static int v9fs_vfs_readlink(struct dentry *dentry, char __user * buffer,
-			     int buflen)
-{
-	int retval;
-	int ret;
-	char *link = __getname();
-
-	if (unlikely(!link))
-		return -ENOMEM;
-
-	if (buflen > PATH_MAX)
-		buflen = PATH_MAX;
-
-	P9_DPRINTK(P9_DEBUG_VFS, " dentry: %s (%p)\n", dentry->d_name.name,
-									dentry);
-
-	retval = v9fs_readlink(dentry, link, buflen);
-
-	if (retval > 0) {
-		if ((ret = copy_to_user(buffer, link, retval)) != 0) {
-			P9_DPRINTK(P9_DEBUG_ERROR,
-					"problem copying to user: %d\n", ret);
-			retval = ret;
-		}
-	}
-
-	__putname(link);
-	return retval;
-}
-
-/**
  * v9fs_vfs_follow_link - follow a symlink path
  * @dentry: dentry for symlink
  * @nd: nameidata
@@ -1230,7 +1192,6 @@ static const struct inode_operations v9fs_dir_inode_operations_ext = {
 	.rmdir = v9fs_vfs_rmdir,
 	.mknod = v9fs_vfs_mknod,
 	.rename = v9fs_vfs_rename,
-	.readlink = v9fs_vfs_readlink,
 	.getattr = v9fs_vfs_getattr,
 	.setattr = v9fs_vfs_setattr,
 };
@@ -1253,7 +1214,7 @@ static const struct inode_operations v9fs_file_inode_operations = {
 };
 
 static const struct inode_operations v9fs_symlink_inode_operations = {
-	.readlink = v9fs_vfs_readlink,
+	.readlink = generic_readlink,
 	.follow_link = v9fs_vfs_follow_link,
 	.put_link = v9fs_vfs_put_link,
 	.getattr = v9fs_vfs_getattr,
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 14a8644..69357c0 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -188,7 +188,8 @@ static void v9fs_kill_super(struct super_block *s)
 
 	P9_DPRINTK(P9_DEBUG_VFS, " %p\n", s);
 
-	v9fs_dentry_release(s->s_root);	/* clunk root */
+	if (s->s_root)
+		v9fs_dentry_release(s->s_root);	/* clunk root */
 
 	kill_anon_super(s);
 
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index e511dc6..0e40caa 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -106,8 +106,8 @@ struct affs_sb_info {
 	u32 s_last_bmap;
 	struct buffer_head *s_bmap_bh;
 	char *s_prefix;			/* Prefix for volumes and assigns. */
-	int s_prefix_len;		/* Length of prefix. */
 	char s_volume[32];		/* Volume prefix for absolute symlinks. */
+	spinlock_t symlink_lock;	/* protects the previous two */
 };
 
 #define SF_INTL		0x0001		/* International filesystem. */
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 960d336..d70bbba 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -341,10 +341,13 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	p  = (char *)AFFS_HEAD(bh)->table;
 	lc = '/';
 	if (*symname == '/') {
+		struct affs_sb_info *sbi = AFFS_SB(sb);
 		while (*symname == '/')
 			symname++;
-		while (AFFS_SB(sb)->s_volume[i])	/* Cannot overflow */
-			*p++ = AFFS_SB(sb)->s_volume[i++];
+		spin_lock(&sbi->symlink_lock);
+		while (sbi->s_volume[i])	/* Cannot overflow */
+			*p++ = sbi->s_volume[i++];
+		spin_unlock(&sbi->symlink_lock);
 	}
 	while (i < maxlen && (c = *symname++)) {
 		if (c == '.' && lc == '/' && *symname == '.' && symname[1] == '/') {
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 104fdcb..d41e967 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -203,7 +203,7 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 		switch (token) {
 		case Opt_bs:
 			if (match_int(&args[0], &n))
-				return -EINVAL;
+				return 0;
 			if (n != 512 && n != 1024 && n != 2048
 			    && n != 4096) {
 				printk ("AFFS: Invalid blocksize (512, 1024, 2048, 4096 allowed)\n");
@@ -213,7 +213,7 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 			break;
 		case Opt_mode:
 			if (match_octal(&args[0], &option))
-				return 1;
+				return 0;
 			*mode = option & 0777;
 			*mount_opts |= SF_SETMODE;
 			break;
@@ -221,8 +221,6 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 			*mount_opts |= SF_MUFS;
 			break;
 		case Opt_prefix:
-			/* Free any previous prefix */
-			kfree(*prefix);
 			*prefix = match_strdup(&args[0]);
 			if (!*prefix)
 				return 0;
@@ -233,21 +231,21 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 			break;
 		case Opt_reserved:
 			if (match_int(&args[0], reserved))
-				return 1;
+				return 0;
 			break;
 		case Opt_root:
 			if (match_int(&args[0], root))
-				return 1;
+				return 0;
 			break;
 		case Opt_setgid:
 			if (match_int(&args[0], &option))
-				return 1;
+				return 0;
 			*gid = option;
 			*mount_opts |= SF_SETGID;
 			break;
 		case Opt_setuid:
 			if (match_int(&args[0], &option))
-				return -EINVAL;
+				return 0;
 			*uid = option;
 			*mount_opts |= SF_SETUID;
 			break;
@@ -311,11 +309,14 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	sb->s_fs_info = sbi;
 	mutex_init(&sbi->s_bmlock);
+	spin_lock_init(&sbi->symlink_lock);
 
 	if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block,
 				&blocksize,&sbi->s_prefix,
 				sbi->s_volume, &mount_flags)) {
 		printk(KERN_ERR "AFFS: Error parsing options\n");
+		kfree(sbi->s_prefix);
+		kfree(sbi);
 		return -EINVAL;
 	}
 	/* N.B. after this point s_prefix must be released */
@@ -516,14 +517,18 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	unsigned long		 mount_flags;
 	int			 res = 0;
 	char			*new_opts = kstrdup(data, GFP_KERNEL);
+	char			 volume[32];
+	char			*prefix = NULL;
 
 	pr_debug("AFFS: remount(flags=0x%x,opts=\"%s\")\n",*flags,data);
 
 	*flags |= MS_NODIRATIME;
 
+	memcpy(volume, sbi->s_volume, 32);
 	if (!parse_options(data, &uid, &gid, &mode, &reserved, &root_block,
-			   &blocksize, &sbi->s_prefix, sbi->s_volume,
+			   &blocksize, &prefix, volume,
 			   &mount_flags)) {
+		kfree(prefix);
 		kfree(new_opts);
 		return -EINVAL;
 	}
@@ -534,6 +539,14 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	sbi->s_mode  = mode;
 	sbi->s_uid   = uid;
 	sbi->s_gid   = gid;
+	/* protect against readers */
+	spin_lock(&sbi->symlink_lock);
+	if (prefix) {
+		kfree(sbi->s_prefix);
+		sbi->s_prefix = prefix;
+	}
+	memcpy(sbi->s_volume, volume, 32);
+	spin_unlock(&sbi->symlink_lock);
 
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		unlock_kernel();
diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c
index 4178253..ee00f08 100644
--- a/fs/affs/symlink.c
+++ b/fs/affs/symlink.c
@@ -20,7 +20,6 @@ static int affs_symlink_readpage(struct file *file, struct page *page)
 	int			 i, j;
 	char			 c;
 	char			 lc;
-	char			*pf;
 
 	pr_debug("AFFS: follow_link(ino=%lu)\n",inode->i_ino);
 
@@ -32,11 +31,15 @@ static int affs_symlink_readpage(struct file *file, struct page *page)
 	j  = 0;
 	lf = (struct slink_front *)bh->b_data;
 	lc = 0;
-	pf = AFFS_SB(inode->i_sb)->s_prefix ? AFFS_SB(inode->i_sb)->s_prefix : "/";
 
 	if (strchr(lf->symname,':')) {	/* Handle assign or volume name */
+		struct affs_sb_info *sbi = AFFS_SB(inode->i_sb);
+		char *pf;
+		spin_lock(&sbi->symlink_lock);
+		pf = sbi->s_prefix ? sbi->s_prefix : "/";
 		while (i < 1023 && (c = pf[i]))
 			link[i++] = c;
+		spin_unlock(&sbi->symlink_lock);
 		while (i < 1023 && lf->symname[j] != ':')
 			link[i++] = lf->symname[j++];
 		if (i < 1023)
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 6f60336..8f3d9fd 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -353,35 +353,35 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 	struct inode *inode;
 	unsigned i, imap_len;
 	struct bfs_sb_info *info;
-	long ret = -EINVAL;
+	int ret = -EINVAL;
 	unsigned long i_sblock, i_eblock, i_eoff, s_size;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
+	mutex_init(&info->bfs_lock);
 	s->s_fs_info = info;
 
 	sb_set_blocksize(s, BFS_BSIZE);
 
-	bh = sb_bread(s, 0);
-	if(!bh)
+	info->si_sbh = sb_bread(s, 0);
+	if (!info->si_sbh)
 		goto out;
-	bfs_sb = (struct bfs_super_block *)bh->b_data;
+	bfs_sb = (struct bfs_super_block *)info->si_sbh->b_data;
 	if (le32_to_cpu(bfs_sb->s_magic) != BFS_MAGIC) {
 		if (!silent)
 			printf("No BFS filesystem on %s (magic=%08x)\n", 
 				s->s_id,  le32_to_cpu(bfs_sb->s_magic));
-		goto out;
+		goto out1;
 	}
 	if (BFS_UNCLEAN(bfs_sb, s) && !silent)
 		printf("%s is unclean, continuing\n", s->s_id);
 
 	s->s_magic = BFS_MAGIC;
-	info->si_sbh = bh;
 
 	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end)) {
 		printf("Superblock is corrupted\n");
-		goto out;
+		goto out1;
 	}
 
 	info->si_lasti = (le32_to_cpu(bfs_sb->s_start) - BFS_BSIZE) /
@@ -390,7 +390,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 	imap_len = (info->si_lasti / 8) + 1;
 	info->si_imap = kzalloc(imap_len, GFP_KERNEL);
 	if (!info->si_imap)
-		goto out;
+		goto out1;
 	for (i = 0; i < BFS_ROOT_INO; i++)
 		set_bit(i, info->si_imap);
 
@@ -398,15 +398,13 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 	inode = bfs_iget(s, BFS_ROOT_INO);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
-		kfree(info->si_imap);
-		goto out;
+		goto out2;
 	}
 	s->s_root = d_alloc_root(inode);
 	if (!s->s_root) {
 		iput(inode);
 		ret = -ENOMEM;
-		kfree(info->si_imap);
-		goto out;
+		goto out2;
 	}
 
 	info->si_blocks = (le32_to_cpu(bfs_sb->s_end) + 1) >> BFS_BSIZE_BITS;
@@ -419,10 +417,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 	bh = sb_bread(s, info->si_blocks - 1);
 	if (!bh) {
 		printf("Last block not available: %lu\n", info->si_blocks - 1);
-		iput(inode);
 		ret = -EIO;
-		kfree(info->si_imap);
-		goto out;
+		goto out3;
 	}
 	brelse(bh);
 
@@ -459,11 +455,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 			printf("Inode 0x%08x corrupted\n", i);
 
 			brelse(bh);
-			s->s_root = NULL;
-			kfree(info->si_imap);
-			kfree(info);
-			s->s_fs_info = NULL;
-			return -EIO;
+			ret = -EIO;
+			goto out3;
 		}
 
 		if (!di->i_ino) {
@@ -483,11 +476,17 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 		s->s_dirt = 1;
 	} 
 	dump_imap("read_super", s);
-	mutex_init(&info->bfs_lock);
 	return 0;
 
+out3:
+	dput(s->s_root);
+	s->s_root = NULL;
+out2:
+	kfree(info->si_imap);
+out1:
+	brelse(info->si_sbh);
 out:
-	brelse(bh);
+	mutex_destroy(&info->bfs_lock);
 	kfree(info);
 	s->s_fs_info = NULL;
 	return ret;
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 346b694..fdd3970 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -264,6 +264,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 #else
 	set_personality(PER_LINUX);
 #endif
+	setup_new_exec(bprm);
 
 	current->mm->end_code = ex.a_text +
 		(current->mm->start_code = N_TXTADDR(ex));
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index edd90c4..fd5b2ea 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -662,27 +662,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
 				goto out_free_interp;
 
-			/*
-			 * The early SET_PERSONALITY here is so that the lookup
-			 * for the interpreter happens in the namespace of the 
-			 * to-be-execed image.  SET_PERSONALITY can select an
-			 * alternate root.
-			 *
-			 * However, SET_PERSONALITY is NOT allowed to switch
-			 * this task into the new images's memory mapping
-			 * policy - that is, TASK_SIZE must still evaluate to
-			 * that which is appropriate to the execing application.
-			 * This is because exit_mmap() needs to have TASK_SIZE
-			 * evaluate to the size of the old image.
-			 *
-			 * So if (say) a 64-bit application is execing a 32-bit
-			 * application it is the architecture's responsibility
-			 * to defer changing the value of TASK_SIZE until the
-			 * switch really is going to happen - do this in
-			 * flush_thread().	- akpm
-			 */
-			SET_PERSONALITY(loc->elf_ex);
-
 			interpreter = open_exec(elf_interpreter);
 			retval = PTR_ERR(interpreter);
 			if (IS_ERR(interpreter))
@@ -730,9 +709,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		/* Verify the interpreter has a valid arch */
 		if (!elf_check_arch(&loc->interp_elf_ex))
 			goto out_free_dentry;
-	} else {
-		/* Executables without an interpreter also need a personality  */
-		SET_PERSONALITY(loc->elf_ex);
 	}
 
 	/* Flush all traces of the currently running executable */
@@ -752,7 +728,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
 	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
 		current->flags |= PF_RANDOMIZE;
-	arch_pick_mmap_layout(current->mm);
+
+	setup_new_exec(bprm);
 
 	/* Do this so that we can load the interpreter, if need be.  We will
 	   change some of these later */
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index c25256a..18d7729 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 +319,11 @@ 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;
+
+	setup_new_exec(bprm);
+
 	set_binfmt(&elf_fdpic_format);
 
 	current->mm->start_code = 0;
@@ -377,9 +385,13 @@ 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 +1810,11 @@ 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/binfmt_flat.c b/fs/binfmt_flat.c
index d4a00ea..42c6b4a 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -519,6 +519,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 
 		/* OK, This is the point of no return */
 		set_personality(PER_LINUX_32BIT);
+		setup_new_exec(bprm);
 	}
 
 	/*
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index 2a9b533..cc8560f 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -227,6 +227,7 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	/* OK, This is the point of no return */
 	current->flags &= ~PF_FORKNOEXEC;
 	current->personality = PER_HPUX;
+	setup_new_exec(bprm);
 
 	/* Set the task size for HP-UX processes such that
 	 * the gateway page is outside the address space.
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 49a34e7..a16f29e 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -61,7 +61,7 @@ static inline unsigned int vecs_to_idx(unsigned int nr)
 
 static inline int use_bip_pool(unsigned int idx)
 {
-	if (idx == BIOVEC_NR_POOLS)
+	if (idx == BIOVEC_MAX_IDX)
 		return 1;
 
 	return 0;
@@ -95,6 +95,7 @@ struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
 
 	/* Use mempool if lower order alloc failed or max vecs were requested */
 	if (bip == NULL) {
+		idx = BIOVEC_MAX_IDX;  /* so we free the payload properly later */
 		bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
 
 		if (unlikely(bip == NULL)) {
diff --git a/fs/bio.c b/fs/bio.c
index 76e6713a..88094af 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -78,7 +78,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
 
 	i = 0;
 	while (i < bio_slab_nr) {
-		struct bio_slab *bslab = &bio_slabs[i];
+		bslab = &bio_slabs[i];
 
 		if (!bslab->slab && entry == -1)
 			entry = i;
@@ -542,13 +542,18 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 
 		if (page == prev->bv_page &&
 		    offset == prev->bv_offset + prev->bv_len) {
+			unsigned int prev_bv_len = prev->bv_len;
 			prev->bv_len += len;
 
 			if (q->merge_bvec_fn) {
 				struct bvec_merge_data bvm = {
+					/* prev_bvec is already charged in
+					   bi_size, discharge it in order to
+					   simulate merging updated prev_bvec
+					   as new bvec. */
 					.bi_bdev = bio->bi_bdev,
 					.bi_sector = bio->bi_sector,
-					.bi_size = bio->bi_size,
+					.bi_size = bio->bi_size - prev_bv_len,
 					.bi_rw = bio->bi_rw,
 				};
 
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 2e9e699..6df6d6e 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -112,12 +112,14 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		mode = inode->i_mode;
-		ret = posix_acl_equiv_mode(acl, &mode);
-		if (ret < 0)
-			return ret;
-		ret = 0;
-		inode->i_mode = mode;
 		name = POSIX_ACL_XATTR_ACCESS;
+		if (acl) {
+			ret = posix_acl_equiv_mode(acl, &mode);
+			if (ret < 0)
+				return ret;
+			inode->i_mode = mode;
+		}
+		ret = 0;
 		break;
 	case ACL_TYPE_DEFAULT:
 		if (!S_ISDIR(inode->i_mode))
@@ -242,6 +244,7 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans,
 						    ACL_TYPE_ACCESS);
 			}
 		}
+		posix_acl_release(clone);
 	}
 failed:
 	posix_acl_release(acl);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9f806dd..2aa8ec6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1161,6 +1161,7 @@ struct btrfs_root {
 #define BTRFS_MOUNT_SSD_SPREAD		(1 << 8)
 #define BTRFS_MOUNT_NOSSD		(1 << 9)
 #define BTRFS_MOUNT_DISCARD		(1 << 10)
+#define BTRFS_MOUNT_FORCE_COMPRESS      (1 << 11)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 009e3bd..2b59201 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1982,7 +1982,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		ret = btrfs_recover_relocation(tree_root);
-		BUG_ON(ret);
+		if (ret < 0) {
+			printk(KERN_WARNING
+			       "btrfs: failed to recover relocation\n");
+			err = -EINVAL;
+			goto fail_trans_kthread;
+		}
 	}
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
@@ -1993,6 +1998,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (!fs_info->fs_root)
 		goto fail_trans_kthread;
 
+	if (!(sb->s_flags & MS_RDONLY)) {
+		down_read(&fs_info->cleanup_work_sem);
+		btrfs_orphan_cleanup(fs_info->fs_root);
+		up_read(&fs_info->cleanup_work_sem);
+	}
+
 	return tree_root;
 
 fail_trans_kthread:
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 56e5013..559f724 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -83,6 +83,17 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
 	return (cache->flags & bits) == bits;
 }
 
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+{
+	atomic_inc(&cache->count);
+}
+
+void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
+{
+	if (atomic_dec_and_test(&cache->count))
+		kfree(cache);
+}
+
 /*
  * this adds the block group to the fs_info rb tree for the block group
  * cache
@@ -156,7 +167,7 @@ block_group_cache_tree_search(struct btrfs_fs_info *info, u64 bytenr,
 		}
 	}
 	if (ret)
-		atomic_inc(&ret->count);
+		btrfs_get_block_group(ret);
 	spin_unlock(&info->block_group_cache_lock);
 
 	return ret;
@@ -407,6 +418,8 @@ err:
 
 	put_caching_control(caching_ctl);
 	atomic_dec(&block_group->space_info->caching_threads);
+	btrfs_put_block_group(block_group);
+
 	return 0;
 }
 
@@ -447,6 +460,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache)
 	up_write(&fs_info->extent_commit_sem);
 
 	atomic_inc(&cache->space_info->caching_threads);
+	btrfs_get_block_group(cache);
 
 	tsk = kthread_run(caching_kthread, cache, "btrfs-cache-%llu\n",
 			  cache->key.objectid);
@@ -486,12 +500,6 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
 	return cache;
 }
 
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
-{
-	if (atomic_dec_and_test(&cache->count))
-		kfree(cache);
-}
-
 static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
 						  u64 flags)
 {
@@ -2582,7 +2590,7 @@ next_block_group(struct btrfs_root *root,
 	if (node) {
 		cache = rb_entry(node, struct btrfs_block_group_cache,
 				 cache_node);
-		atomic_inc(&cache->count);
+		btrfs_get_block_group(cache);
 	} else
 		cache = NULL;
 	spin_unlock(&root->fs_info->block_group_cache_lock);
@@ -4227,7 +4235,7 @@ search:
 		u64 offset;
 		int cached;
 
-		atomic_inc(&block_group->count);
+		btrfs_get_block_group(block_group);
 		search_start = block_group->key.objectid;
 
 have_block_group:
@@ -4315,7 +4323,7 @@ have_block_group:
 
 				btrfs_put_block_group(block_group);
 				block_group = last_ptr->block_group;
-				atomic_inc(&block_group->count);
+				btrfs_get_block_group(block_group);
 				spin_unlock(&last_ptr->lock);
 				spin_unlock(&last_ptr->refill_lock);
 
@@ -5394,10 +5402,6 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
 	int ret;
 
 	while (level >= 0) {
-		if (path->slots[level] >=
-		    btrfs_header_nritems(path->nodes[level]))
-			break;
-
 		ret = walk_down_proc(trans, root, path, wc, lookup_info);
 		if (ret > 0)
 			break;
@@ -5405,6 +5409,10 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
 		if (level == 0)
 			break;
 
+		if (path->slots[level] >=
+		    btrfs_header_nritems(path->nodes[level]))
+			break;
+
 		ret = do_walk_down(trans, root, path, wc, &lookup_info);
 		if (ret > 0) {
 			path->slots[level]++;
@@ -7395,9 +7403,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 			wait_block_group_cache_done(block_group);
 
 		btrfs_remove_free_space_cache(block_group);
-
-		WARN_ON(atomic_read(&block_group->count) != 1);
-		kfree(block_group);
+		btrfs_put_block_group(block_group);
 
 		spin_lock(&info->block_group_cache_lock);
 	}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 96577e8..b177ed3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3165,10 +3165,9 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 		spin_unlock(&tree->buffer_lock);
 		goto free_eb;
 	}
-	spin_unlock(&tree->buffer_lock);
-
 	/* add one reference for the tree */
 	atomic_inc(&eb->refs);
+	spin_unlock(&tree->buffer_lock);
 	return eb;
 
 free_eb:
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 46bea0f..428fcac 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -155,20 +155,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
 	return NULL;
 }
 
-/*
- * look for an offset in the tree, and if it can't be found, return
- * the first offset we can find smaller than 'offset'.
- */
-static inline struct rb_node *tree_search(struct rb_root *root, u64 offset)
-{
-	struct rb_node *prev;
-	struct rb_node *ret;
-	ret = __tree_search(root, offset, &prev, NULL);
-	if (!ret)
-		return prev;
-	return ret;
-}
-
 /* check to see if two extent_map structs are adjacent and safe to merge */
 static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index feaa13b..9d08096 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -506,7 +506,8 @@ next_slot:
 }
 
 static int extent_mergeable(struct extent_buffer *leaf, int slot,
-			    u64 objectid, u64 bytenr, u64 *start, u64 *end)
+			    u64 objectid, u64 bytenr, u64 orig_offset,
+			    u64 *start, u64 *end)
 {
 	struct btrfs_file_extent_item *fi;
 	struct btrfs_key key;
@@ -522,6 +523,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
 	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 	if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG ||
 	    btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr ||
+	    btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset ||
 	    btrfs_file_extent_compression(leaf, fi) ||
 	    btrfs_file_extent_encryption(leaf, fi) ||
 	    btrfs_file_extent_other_encoding(leaf, fi))
@@ -561,6 +563,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	u64 split;
 	int del_nr = 0;
 	int del_slot = 0;
+	int recow;
 	int ret;
 
 	btrfs_drop_extent_cache(inode, start, end - 1, 0);
@@ -568,6 +571,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 again:
+	recow = 0;
 	split = start;
 	key.objectid = inode->i_ino;
 	key.type = BTRFS_EXTENT_DATA_KEY;
@@ -591,12 +595,60 @@ again:
 	bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
 	num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
 	orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
+	memcpy(&new_key, &key, sizeof(new_key));
+
+	if (start == key.offset && end < extent_end) {
+		other_start = 0;
+		other_end = start;
+		if (extent_mergeable(leaf, path->slots[0] - 1,
+				     inode->i_ino, bytenr, orig_offset,
+				     &other_start, &other_end)) {
+			new_key.offset = end;
+			btrfs_set_item_key_safe(trans, root, path, &new_key);
+			fi = btrfs_item_ptr(leaf, path->slots[0],
+					    struct btrfs_file_extent_item);
+			btrfs_set_file_extent_num_bytes(leaf, fi,
+							extent_end - end);
+			btrfs_set_file_extent_offset(leaf, fi,
+						     end - orig_offset);
+			fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
+					    struct btrfs_file_extent_item);
+			btrfs_set_file_extent_num_bytes(leaf, fi,
+							end - other_start);
+			btrfs_mark_buffer_dirty(leaf);
+			goto out;
+		}
+	}
+
+	if (start > key.offset && end == extent_end) {
+		other_start = end;
+		other_end = 0;
+		if (extent_mergeable(leaf, path->slots[0] + 1,
+				     inode->i_ino, bytenr, orig_offset,
+				     &other_start, &other_end)) {
+			fi = btrfs_item_ptr(leaf, path->slots[0],
+					    struct btrfs_file_extent_item);
+			btrfs_set_file_extent_num_bytes(leaf, fi,
+							start - key.offset);
+			path->slots[0]++;
+			new_key.offset = start;
+			btrfs_set_item_key_safe(trans, root, path, &new_key);
+
+			fi = btrfs_item_ptr(leaf, path->slots[0],
+					    struct btrfs_file_extent_item);
+			btrfs_set_file_extent_num_bytes(leaf, fi,
+							other_end - start);
+			btrfs_set_file_extent_offset(leaf, fi,
+						     start - orig_offset);
+			btrfs_mark_buffer_dirty(leaf);
+			goto out;
+		}
+	}
 
 	while (start > key.offset || end < extent_end) {
 		if (key.offset == start)
 			split = end;
 
-		memcpy(&new_key, &key, sizeof(new_key));
 		new_key.offset = split;
 		ret = btrfs_duplicate_item(trans, root, path, &new_key);
 		if (ret == -EAGAIN) {
@@ -631,15 +683,18 @@ again:
 			path->slots[0]--;
 			extent_end = end;
 		}
+		recow = 1;
 	}
 
-	fi = btrfs_item_ptr(leaf, path->slots[0],
-			    struct btrfs_file_extent_item);
-
 	other_start = end;
 	other_end = 0;
-	if (extent_mergeable(leaf, path->slots[0] + 1, inode->i_ino,
-			     bytenr, &other_start, &other_end)) {
+	if (extent_mergeable(leaf, path->slots[0] + 1,
+			     inode->i_ino, bytenr, orig_offset,
+			     &other_start, &other_end)) {
+		if (recow) {
+			btrfs_release_path(root, path);
+			goto again;
+		}
 		extent_end = other_end;
 		del_slot = path->slots[0] + 1;
 		del_nr++;
@@ -650,8 +705,13 @@ again:
 	}
 	other_start = 0;
 	other_end = start;
-	if (extent_mergeable(leaf, path->slots[0] - 1, inode->i_ino,
-			     bytenr, &other_start, &other_end)) {
+	if (extent_mergeable(leaf, path->slots[0] - 1,
+			     inode->i_ino, bytenr, orig_offset,
+			     &other_start, &other_end)) {
+		if (recow) {
+			btrfs_release_path(root, path);
+			goto again;
+		}
 		key.offset = other_start;
 		del_slot = path->slots[0];
 		del_nr++;
@@ -660,22 +720,22 @@ again:
 					inode->i_ino, orig_offset);
 		BUG_ON(ret);
 	}
+	fi = btrfs_item_ptr(leaf, path->slots[0],
+			   struct btrfs_file_extent_item);
 	if (del_nr == 0) {
 		btrfs_set_file_extent_type(leaf, fi,
 					   BTRFS_FILE_EXTENT_REG);
 		btrfs_mark_buffer_dirty(leaf);
-		goto out;
-	}
-
-	fi = btrfs_item_ptr(leaf, del_slot - 1,
-			    struct btrfs_file_extent_item);
-	btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG);
-	btrfs_set_file_extent_num_bytes(leaf, fi,
-					extent_end - key.offset);
-	btrfs_mark_buffer_dirty(leaf);
+	} else {
+		btrfs_set_file_extent_type(leaf, fi,
+					   BTRFS_FILE_EXTENT_REG);
+		btrfs_set_file_extent_num_bytes(leaf, fi,
+						extent_end - key.offset);
+		btrfs_mark_buffer_dirty(leaf);
 
-	ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
-	BUG_ON(ret);
+		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
+		BUG_ON(ret);
+	}
 out:
 	btrfs_free_path(path);
 	return 0;
@@ -1073,7 +1133,7 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
 	}
 	mutex_lock(&dentry->d_inode->i_mutex);
 out:
-	return ret > 0 ? EIO : ret;
+	return ret > 0 ? -EIO : ret;
 }
 
 static const struct vm_operations_struct btrfs_file_vm_ops = {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5440bab..4deb280 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -483,7 +483,8 @@ again:
 		nr_pages_ret = 0;
 
 		/* flag the file so we don't compress in the future */
-		BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
+		if (!btrfs_test_opt(root, FORCE_COMPRESS))
+			BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
 	}
 	if (will_compress) {
 		*num_added += 1;
@@ -1680,24 +1681,6 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
  * before we start the transaction.  It limits the amount of btree
  * reads required while inside the transaction.
  */
-static noinline void reada_csum(struct btrfs_root *root,
-				struct btrfs_path *path,
-				struct btrfs_ordered_extent *ordered_extent)
-{
-	struct btrfs_ordered_sum *sum;
-	u64 bytenr;
-
-	sum = list_entry(ordered_extent->list.next, struct btrfs_ordered_sum,
-			 list);
-	bytenr = sum->sums[0].bytenr;
-
-	/*
-	 * we don't care about the results, the point of this search is
-	 * just to get the btree leaves into ram
-	 */
-	btrfs_lookup_csum(NULL, root->fs_info->csum_root, path, bytenr, 0);
-}
-
 /* as ordered data IO finishes, this gets called so we can finish
  * an ordered extent if the range of bytes in the file it covers are
  * fully written.
@@ -1708,7 +1691,6 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	struct btrfs_path *path;
 	int compressed = 0;
 	int ret;
 
@@ -1716,32 +1698,9 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	if (!ret)
 		return 0;
 
-	/*
-	 * before we join the transaction, try to do some of our IO.
-	 * This will limit the amount of IO that we have to do with
-	 * the transaction running.  We're unlikely to need to do any
-	 * IO if the file extents are new, the disk_i_size checks
-	 * covers the most common case.
-	 */
-	if (start < BTRFS_I(inode)->disk_i_size) {
-		path = btrfs_alloc_path();
-		if (path) {
-			ret = btrfs_lookup_file_extent(NULL, root, path,
-						       inode->i_ino,
-						       start, 0);
-			ordered_extent = btrfs_lookup_ordered_extent(inode,
-								     start);
-			if (!list_empty(&ordered_extent->list)) {
-				btrfs_release_path(root, path);
-				reada_csum(root, path, ordered_extent);
-			}
-			btrfs_free_path(path);
-		}
-	}
-
-	if (!ordered_extent)
-		ordered_extent = btrfs_lookup_ordered_extent(inode, start);
+	ordered_extent = btrfs_lookup_ordered_extent(inode, start);
 	BUG_ON(!ordered_extent);
+
 	if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
 		BUG_ON(!list_empty(&ordered_extent->list));
 		ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
@@ -3995,7 +3954,11 @@ skip:
 
 	/* Reached end of directory/root. Bump pos past the last item. */
 	if (key_type == BTRFS_DIR_INDEX_KEY)
-		filp->f_pos = INT_LIMIT(off_t);
+		/*
+		 * 32-bit glibc will use getdents64, but then strtol -
+		 * so the last number we can serve is this.
+		 */
+		filp->f_pos = 0x7fffffff;
 	else
 		filp->f_pos++;
 nopos:
@@ -5789,7 +5752,7 @@ out_fail:
 }
 
 static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
-			       u64 alloc_hint, int mode)
+			u64 alloc_hint, int mode, loff_t actual_len)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -5798,6 +5761,7 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
 	u64 cur_offset = start;
 	u64 num_bytes = end - start;
 	int ret = 0;
+	u64 i_size;
 
 	while (num_bytes > 0) {
 		alloc_size = min(num_bytes, root->fs_info->max_extent);
@@ -5835,9 +5799,15 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
 		inode->i_ctime = CURRENT_TIME;
 		BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-		    cur_offset > inode->i_size) {
-			i_size_write(inode, cur_offset);
-			btrfs_ordered_update_i_size(inode, cur_offset, NULL);
+			(actual_len > inode->i_size) &&
+			(cur_offset > inode->i_size)) {
+
+			if (cur_offset > actual_len)
+				i_size  = actual_len;
+			else
+				i_size = cur_offset;
+			i_size_write(inode, i_size);
+			btrfs_ordered_update_i_size(inode, i_size, NULL);
 		}
 
 		ret = btrfs_update_inode(trans, root, inode);
@@ -5930,7 +5900,7 @@ static long btrfs_fallocate(struct inode *inode, int mode,
 		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
 			ret = prealloc_file_range(inode,
 						  cur_offset, last_byte,
-						  alloc_hint, mode);
+						alloc_hint, mode, offset+len);
 			if (ret < 0) {
 				free_extent_map(em);
 				break;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b10a49d..5c2a9e7 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -626,6 +626,8 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 
 	if (ordered)
 		offset = entry_end(ordered);
+	else
+		offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize);
 
 	mutex_lock(&tree->mutex);
 	disk_i_size = BTRFS_I(inode)->disk_i_size;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a972868..ab7ab53 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3281,8 +3281,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 		return -ENOMEM;
 
 	path = btrfs_alloc_path();
-	if (!path)
+	if (!path) {
+		kfree(cluster);
 		return -ENOMEM;
+	}
 
 	rc->extents_found = 0;
 	rc->extents_skipped = 0;
@@ -3762,7 +3764,8 @@ out:
 				       BTRFS_DATA_RELOC_TREE_OBJECTID);
 		if (IS_ERR(fs_root))
 			err = PTR_ERR(fs_root);
-		btrfs_orphan_cleanup(fs_root);
+		else
+			btrfs_orphan_cleanup(fs_root);
 	}
 	return err;
 }
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3f9b457..8a1ea6e 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -66,7 +66,8 @@ enum {
 	Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow,
 	Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier,
 	Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl,
-	Opt_compress, Opt_notreelog, Opt_ratio, Opt_flushoncommit,
+	Opt_compress, Opt_compress_force, Opt_notreelog, Opt_ratio,
+	Opt_flushoncommit,
 	Opt_discard, Opt_err,
 };
 
@@ -82,6 +83,7 @@ static match_table_t tokens = {
 	{Opt_alloc_start, "alloc_start=%s"},
 	{Opt_thread_pool, "thread_pool=%d"},
 	{Opt_compress, "compress"},
+	{Opt_compress_force, "compress-force"},
 	{Opt_ssd, "ssd"},
 	{Opt_ssd_spread, "ssd_spread"},
 	{Opt_nossd, "nossd"},
@@ -173,6 +175,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			printk(KERN_INFO "btrfs: use compression\n");
 			btrfs_set_opt(info->mount_opt, COMPRESS);
 			break;
+		case Opt_compress_force:
+			printk(KERN_INFO "btrfs: forcing compression\n");
+			btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
+			btrfs_set_opt(info->mount_opt, COMPRESS);
+			break;
 		case Opt_ssd:
 			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
 			btrfs_set_opt(info->mount_opt, SSD);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 198cff2..41ecbb2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1135,7 +1135,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		root->fs_info->avail_metadata_alloc_bits;
 
 	if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) &&
-	    root->fs_info->fs_devices->rw_devices <= 4) {
+	    root->fs_info->fs_devices->num_devices <= 4) {
 		printk(KERN_ERR "btrfs: unable to go below four devices "
 		       "on raid10\n");
 		ret = -EINVAL;
@@ -1143,7 +1143,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	}
 
 	if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) &&
-	    root->fs_info->fs_devices->rw_devices <= 2) {
+	    root->fs_info->fs_devices->num_devices <= 2) {
 		printk(KERN_ERR "btrfs: unable to go below two "
 		       "devices on raid1\n");
 		ret = -EINVAL;
@@ -1434,8 +1434,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		return -EINVAL;
 
 	bdev = open_bdev_exclusive(device_path, 0, root->fs_info->bdev_holder);
-	if (!bdev)
-		return -EIO;
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
 	if (root->fs_info->fs_devices->seeding) {
 		seeding_dev = 1;
@@ -2538,6 +2538,11 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	if (!em)
 		return 1;
 
+	if (btrfs_test_opt(root, DEGRADED)) {
+		free_extent_map(em);
+		return 0;
+	}
+
 	map = (struct map_lookup *)em->bdev;
 	for (i = 0; i < map->num_stripes; i++) {
 		if (!map->stripes[i].dev->writeable) {
@@ -2649,8 +2654,10 @@ again:
 	em = lookup_extent_mapping(em_tree, logical, *length);
 	read_unlock(&em_tree->lock);
 
-	if (!em && unplug_page)
+	if (!em && unplug_page) {
+		kfree(multi);
 		return 0;
+	}
 
 	if (!em) {
 		printk(KERN_CRIT "unable to find logical %llu len %llu\n",
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 094ea65..7b2600b 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/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index fea9e89..b44ce0a 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -269,7 +269,7 @@ static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
 	int err;
 
 	mntget(newmnt);
-	err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags, mntlist);
+	err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags | MNT_SHRINKABLE, mntlist);
 	switch (err) {
 	case 0:
 		path_put(&nd->path);
@@ -371,7 +371,6 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 	if (IS_ERR(mnt))
 		goto out_err;
 
-	nd->path.mnt->mnt_flags |= MNT_SHRINKABLE;
 	rc = add_mount_helper(mnt, nd, &cifs_dfs_automount_list);
 
 out:
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 29f1da7..8c6a036 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 63ea83f..3bbcaa7 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/compat_ioctl.c b/fs/compat_ioctl.c
index 332dd00..c5c45de 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1005,6 +1005,9 @@ COMPATIBLE_IOCTL(SCSI_IOCTL_SEND_COMMAND)
 COMPATIBLE_IOCTL(SCSI_IOCTL_PROBE_HOST)
 COMPATIBLE_IOCTL(SCSI_IOCTL_GET_PCI)
 #endif
+/* Big V (don't complain on serial console) */
+IGNORE_IOCTL(VT_OPENQRY)
+IGNORE_IOCTL(VT_GETMODE)
 /* Little p (/dev/rtc, /dev/envctrl, etc.) */
 COMPATIBLE_IOCTL(RTC_AIE_ON)
 COMPATIBLE_IOCTL(RTC_AIE_OFF)
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index c8afa6b..32a5f46 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -121,8 +121,10 @@ static int get_target(const char *symname, struct path *path,
 				ret = -ENOENT;
 				path_put(path);
 			}
-		} else
+		} else {
 			ret = -EPERM;
+			path_put(path);
+		}
 	}
 
 	return ret;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index b486169..274ac86 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -160,15 +160,8 @@ static int debugfs_create_by_name(const char *name, mode_t mode,
 	 * block. A pointer to that is in the struct vfsmount that we
 	 * have around.
 	 */
-	if (!parent) {
-		if (debugfs_mount && debugfs_mount->mnt_sb) {
-			parent = debugfs_mount->mnt_sb->s_root;
-		}
-	}
-	if (!parent) {
-		pr_debug("debugfs: Ah! can not find a parent!\n");
-		return -EFAULT;
-	}
+	if (!parent)
+		parent = debugfs_mount->mnt_sb->s_root;
 
 	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index fbb6e5e..7cb0a59 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1748,7 +1748,7 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
 			    char *cipher_name, size_t *key_size)
 {
 	char dummy_key[ECRYPTFS_MAX_KEY_BYTES];
-	char *full_alg_name;
+	char *full_alg_name = NULL;
 	int rc;
 
 	*key_tfm = NULL;
@@ -1763,7 +1763,6 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
 	if (rc)
 		goto out;
 	*key_tfm = crypto_alloc_blkcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
-	kfree(full_alg_name);
 	if (IS_ERR(*key_tfm)) {
 		rc = PTR_ERR(*key_tfm);
 		printk(KERN_ERR "Unable to allocate crypto cipher with name "
@@ -1786,6 +1785,7 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
 		goto out;
 	}
 out:
+	kfree(full_alg_name);
 	return rc;
 }
 
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 9e94405..678172b 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -158,7 +158,7 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	struct dentry *ecryptfs_dentry = file->f_path.dentry;
 	/* Private value of ecryptfs_dentry allocated in
 	 * ecryptfs_lookup() */
-	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
+	struct dentry *lower_dentry;
 	struct ecryptfs_file_info *file_info;
 
 	mount_crypt_stat = &ecryptfs_superblock_to_private(
@@ -191,13 +191,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 				      | ECRYPTFS_ENCRYPTED);
 	}
 	mutex_unlock(&crypt_stat->cs_mutex);
-	if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_RDONLY)
-	    && !(file->f_flags & O_RDONLY)) {
-		rc = -EPERM;
-		printk(KERN_WARNING "%s: Lower persistent file is RO; eCryptfs "
-		       "file must hence be opened RO\n", __func__);
-		goto out;
-	}
 	if (!ecryptfs_inode_to_private(inode)->lower_file) {
 		rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
 		if (rc) {
@@ -208,6 +201,13 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 			goto out;
 		}
 	}
+	if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_RDONLY)
+	    && !(file->f_flags & O_RDONLY)) {
+		rc = -EPERM;
+		printk(KERN_WARNING "%s: Lower persistent file is RO; eCryptfs "
+		       "file must hence be opened RO\n", __func__);
+		goto out;
+	}
 	ecryptfs_set_file_lower(
 		file, ecryptfs_inode_to_private(inode)->lower_file);
 	if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
@@ -299,7 +299,6 @@ static int ecryptfs_ioctl(struct inode *inode, struct file *file,
 const struct file_operations ecryptfs_dir_fops = {
 	.readdir = ecryptfs_readdir,
 	.ioctl = ecryptfs_ioctl,
-	.mmap = generic_file_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 429ca0b..4a430ab 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -282,7 +282,8 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
 		goto out;
 	}
 	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-				ecryptfs_dir_inode->i_sb, 1);
+				ecryptfs_dir_inode->i_sb,
+				ECRYPTFS_INTERPOSE_FLAG_D_ADD);
 	if (rc) {
 		printk(KERN_ERR "%s: Error interposing; rc = [%d]\n",
 		       __func__, rc);
@@ -463,9 +464,6 @@ out_lock:
 	unlock_dir(lower_dir_dentry);
 	dput(lower_new_dentry);
 	dput(lower_old_dentry);
-	d_drop(lower_old_dentry);
-	d_drop(new_dentry);
-	d_drop(old_dentry);
 	return rc;
 }
 
@@ -614,6 +612,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *lower_new_dentry;
 	struct dentry *lower_old_dir_dentry;
 	struct dentry *lower_new_dir_dentry;
+	struct dentry *trap = NULL;
 
 	lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
 	lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
@@ -621,7 +620,17 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	dget(lower_new_dentry);
 	lower_old_dir_dentry = dget_parent(lower_old_dentry);
 	lower_new_dir_dentry = dget_parent(lower_new_dentry);
-	lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+	trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+	/* source should not be ancestor of target */
+	if (trap == lower_old_dentry) {
+		rc = -EINVAL;
+		goto out_lock;
+	}
+	/* target should not be ancestor of source */
+	if (trap == lower_new_dentry) {
+		rc = -ENOTEMPTY;
+		goto out_lock;
+	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
 			lower_new_dir_dentry->d_inode, lower_new_dentry);
 	if (rc)
@@ -715,31 +724,31 @@ static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 	/* Released in ecryptfs_put_link(); only release here on error */
 	buf = kmalloc(len, GFP_KERNEL);
 	if (!buf) {
-		rc = -ENOMEM;
+		buf = ERR_PTR(-ENOMEM);
 		goto out;
 	}
 	old_fs = get_fs();
 	set_fs(get_ds());
 	rc = dentry->d_inode->i_op->readlink(dentry, (char __user *)buf, len);
 	set_fs(old_fs);
-	if (rc < 0)
-		goto out_free;
-	else
+	if (rc < 0) {
+		kfree(buf);
+		buf = ERR_PTR(rc);
+	} else
 		buf[rc] = '\0';
-	rc = 0;
-	nd_set_link(nd, buf);
-	goto out;
-out_free:
-	kfree(buf);
 out:
-	return ERR_PTR(rc);
+	nd_set_link(nd, buf);
+	return NULL;
 }
 
 static void
 ecryptfs_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr)
 {
-	/* Free the char* */
-	kfree(nd_get_link(nd));
+	char *buf = nd_get_link(nd);
+	if (!IS_ERR(buf)) {
+		/* Free the char* */
+		kfree(buf);
+	}
 }
 
 /**
@@ -772,18 +781,23 @@ upper_size_to_lower_size(struct ecryptfs_crypt_stat *crypt_stat,
 }
 
 /**
- * ecryptfs_truncate
+ * truncate_upper
  * @dentry: The ecryptfs layer dentry
- * @new_length: The length to expand the file to
+ * @ia: Address of the ecryptfs inode's attributes
+ * @lower_ia: Address of the lower inode's attributes
  *
  * Function to handle truncations modifying the size of the file. Note
  * that the file sizes are interpolated. When expanding, we are simply
- * writing strings of 0's out. When truncating, we need to modify the
- * underlying file size according to the page index interpolations.
+ * writing strings of 0's out. When truncating, we truncate the upper
+ * inode and update the lower_ia according to the page index
+ * interpolations. If ATTR_SIZE is set in lower_ia->ia_valid upon return,
+ * the caller must use lower_ia in a call to notify_change() to perform
+ * the truncation of the lower inode.
  *
  * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
+static int truncate_upper(struct dentry *dentry, struct iattr *ia,
+			  struct iattr *lower_ia)
 {
 	int rc = 0;
 	struct inode *inode = dentry->d_inode;
@@ -794,8 +808,10 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 	loff_t lower_size_before_truncate;
 	loff_t lower_size_after_truncate;
 
-	if (unlikely((new_length == i_size)))
+	if (unlikely((ia->ia_size == i_size))) {
+		lower_ia->ia_valid &= ~ATTR_SIZE;
 		goto out;
+	}
 	crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
 	/* Set up a fake ecryptfs file, this is used to interface with
 	 * the file in the underlying filesystem so that the
@@ -815,28 +831,30 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 		&fake_ecryptfs_file,
 		ecryptfs_inode_to_private(dentry->d_inode)->lower_file);
 	/* Switch on growing or shrinking file */
-	if (new_length > i_size) {
+	if (ia->ia_size > i_size) {
 		char zero[] = { 0x00 };
 
+		lower_ia->ia_valid &= ~ATTR_SIZE;
 		/* Write a single 0 at the last position of the file;
 		 * this triggers code that will fill in 0's throughout
 		 * the intermediate portion of the previous end of the
 		 * file and the new and of the file */
 		rc = ecryptfs_write(&fake_ecryptfs_file, zero,
-				    (new_length - 1), 1);
-	} else { /* new_length < i_size_read(inode) */
-		/* We're chopping off all the pages down do the page
-		 * in which new_length is located. Fill in the end of
-		 * that page from (new_length & ~PAGE_CACHE_MASK) to
+				    (ia->ia_size - 1), 1);
+	} else { /* ia->ia_size < i_size_read(inode) */
+		/* We're chopping off all the pages down to the page
+		 * in which ia->ia_size is located. Fill in the end of
+		 * that page from (ia->ia_size & ~PAGE_CACHE_MASK) to
 		 * PAGE_CACHE_SIZE with zeros. */
 		size_t num_zeros = (PAGE_CACHE_SIZE
-				    - (new_length & ~PAGE_CACHE_MASK));
+				    - (ia->ia_size & ~PAGE_CACHE_MASK));
 
 		if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
-			rc = vmtruncate(inode, new_length);
+			rc = vmtruncate(inode, ia->ia_size);
 			if (rc)
 				goto out_free;
-			rc = vmtruncate(lower_dentry->d_inode, new_length);
+			lower_ia->ia_size = ia->ia_size;
+			lower_ia->ia_valid |= ATTR_SIZE;
 			goto out_free;
 		}
 		if (num_zeros) {
@@ -848,7 +866,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 				goto out_free;
 			}
 			rc = ecryptfs_write(&fake_ecryptfs_file, zeros_virt,
-					    new_length, num_zeros);
+					    ia->ia_size, num_zeros);
 			kfree(zeros_virt);
 			if (rc) {
 				printk(KERN_ERR "Error attempting to zero out "
@@ -857,7 +875,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 				goto out_free;
 			}
 		}
-		vmtruncate(inode, new_length);
+		vmtruncate(inode, ia->ia_size);
 		rc = ecryptfs_write_inode_size_to_metadata(inode);
 		if (rc) {
 			printk(KERN_ERR	"Problem with "
@@ -870,10 +888,12 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 		lower_size_before_truncate =
 		    upper_size_to_lower_size(crypt_stat, i_size);
 		lower_size_after_truncate =
-		    upper_size_to_lower_size(crypt_stat, new_length);
-		if (lower_size_after_truncate < lower_size_before_truncate)
-			vmtruncate(lower_dentry->d_inode,
-				   lower_size_after_truncate);
+		    upper_size_to_lower_size(crypt_stat, ia->ia_size);
+		if (lower_size_after_truncate < lower_size_before_truncate) {
+			lower_ia->ia_size = lower_size_after_truncate;
+			lower_ia->ia_valid |= ATTR_SIZE;
+		} else
+			lower_ia->ia_valid &= ~ATTR_SIZE;
 	}
 out_free:
 	if (ecryptfs_file_to_private(&fake_ecryptfs_file))
@@ -883,6 +903,33 @@ out:
 	return rc;
 }
 
+/**
+ * ecryptfs_truncate
+ * @dentry: The ecryptfs layer dentry
+ * @new_length: The length to expand the file to
+ *
+ * Simple function that handles the truncation of an eCryptfs inode and
+ * its corresponding lower inode.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
+{
+	struct iattr ia = { .ia_valid = ATTR_SIZE, .ia_size = new_length };
+	struct iattr lower_ia = { .ia_valid = 0 };
+	int rc;
+
+	rc = truncate_upper(dentry, &ia, &lower_ia);
+	if (!rc && lower_ia.ia_valid & ATTR_SIZE) {
+		struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
+
+		mutex_lock(&lower_dentry->d_inode->i_mutex);
+		rc = notify_change(lower_dentry, &lower_ia);
+		mutex_unlock(&lower_dentry->d_inode->i_mutex);
+	}
+	return rc;
+}
+
 static int
 ecryptfs_permission(struct inode *inode, int mask)
 {
@@ -905,6 +952,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 {
 	int rc = 0;
 	struct dentry *lower_dentry;
+	struct iattr lower_ia;
 	struct inode *inode;
 	struct inode *lower_inode;
 	struct ecryptfs_crypt_stat *crypt_stat;
@@ -943,15 +991,11 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 		}
 	}
 	mutex_unlock(&crypt_stat->cs_mutex);
+	memcpy(&lower_ia, ia, sizeof(lower_ia));
+	if (ia->ia_valid & ATTR_FILE)
+		lower_ia.ia_file = ecryptfs_file_to_lower(ia->ia_file);
 	if (ia->ia_valid & ATTR_SIZE) {
-		ecryptfs_printk(KERN_DEBUG,
-				"ia->ia_valid = [0x%x] ATTR_SIZE" " = [0x%x]\n",
-				ia->ia_valid, ATTR_SIZE);
-		rc = ecryptfs_truncate(dentry, ia->ia_size);
-		/* ecryptfs_truncate handles resizing of the lower file */
-		ia->ia_valid &= ~ATTR_SIZE;
-		ecryptfs_printk(KERN_DEBUG, "ia->ia_valid = [%x]\n",
-				ia->ia_valid);
+		rc = truncate_upper(dentry, ia, &lower_ia);
 		if (rc < 0)
 			goto out;
 	}
@@ -960,17 +1004,32 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 	 * mode change is for clearing setuid/setgid bits. Allow lower fs
 	 * to interpret this in its own way.
 	 */
-	if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
-		ia->ia_valid &= ~ATTR_MODE;
+	if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
+		lower_ia.ia_valid &= ~ATTR_MODE;
 
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
-	rc = notify_change(lower_dentry, ia);
+	rc = notify_change(lower_dentry, &lower_ia);
 	mutex_unlock(&lower_dentry->d_inode->i_mutex);
 out:
 	fsstack_copy_attr_all(inode, lower_inode);
 	return rc;
 }
 
+int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		     struct kstat *stat)
+{
+	struct kstat lower_stat;
+	int rc;
+
+	rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry),
+			 ecryptfs_dentry_to_lower(dentry), &lower_stat);
+	if (!rc) {
+		generic_fillattr(dentry->d_inode, stat);
+		stat->blocks = lower_stat.blocks;
+	}
+	return rc;
+}
+
 int
 ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		  size_t size, int flags)
@@ -1100,6 +1159,7 @@ const struct inode_operations ecryptfs_dir_iops = {
 const struct inode_operations ecryptfs_main_iops = {
 	.permission = ecryptfs_permission,
 	.setattr = ecryptfs_setattr,
+	.getattr = ecryptfs_getattr,
 	.setxattr = ecryptfs_setxattr,
 	.getxattr = ecryptfs_getxattr,
 	.listxattr = ecryptfs_listxattr,
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 567bc4b..ea2f921 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -585,8 +585,8 @@ out:
  *                        with as much information as it can before needing
  *                        the lower filesystem.
  * ecryptfs_read_super(): this accesses the lower filesystem and uses
- *                        ecryptfs_interpolate to perform most of the linking
- * ecryptfs_interpolate(): links the lower filesystem into ecryptfs
+ *                        ecryptfs_interpose to perform most of the linking
+ * ecryptfs_interpose(): links the lower filesystem into ecryptfs (inode.c)
  */
 static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags,
 			const char *dev_name, void *raw_data,
diff --git a/fs/eventfd.c b/fs/eventfd.c
index d26402f..7758cc3 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -135,26 +135,71 @@ static unsigned int eventfd_poll(struct file *file, poll_table *wait)
 	return events;
 }
 
-static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
-			    loff_t *ppos)
+static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+{
+	*cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
+	ctx->count -= *cnt;
+}
+
+/**
+ * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
+ * @ctx: [in] Pointer to eventfd context.
+ * @wait: [in] Wait queue to be removed.
+ * @cnt: [out] Pointer to the 64bit conter value.
+ *
+ * Returns zero if successful, or the following error codes:
+ *
+ * -EAGAIN      : The operation would have blocked.
+ *
+ * This is used to atomically remove a wait queue entry from the eventfd wait
+ * queue head, and read/reset the counter value.
+ */
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
+				  __u64 *cnt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	eventfd_ctx_do_read(ctx, cnt);
+	__remove_wait_queue(&ctx->wqh, wait);
+	if (*cnt != 0 && waitqueue_active(&ctx->wqh))
+		wake_up_locked_poll(&ctx->wqh, POLLOUT);
+	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+
+	return *cnt != 0 ? 0 : -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
+
+/**
+ * eventfd_ctx_read - Reads the eventfd counter or wait if it is zero.
+ * @ctx: [in] Pointer to eventfd context.
+ * @no_wait: [in] Different from zero if the operation should not block.
+ * @cnt: [out] Pointer to the 64bit conter value.
+ *
+ * Returns zero if successful, or the following error codes:
+ *
+ * -EAGAIN      : The operation would have blocked but @no_wait was nonzero.
+ * -ERESTARTSYS : A signal interrupted the wait operation.
+ *
+ * If @no_wait is zero, the function might sleep until the eventfd internal
+ * counter becomes greater than zero.
+ */
+ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt)
 {
-	struct eventfd_ctx *ctx = file->private_data;
 	ssize_t res;
-	__u64 ucnt = 0;
 	DECLARE_WAITQUEUE(wait, current);
 
-	if (count < sizeof(ucnt))
-		return -EINVAL;
 	spin_lock_irq(&ctx->wqh.lock);
+	*cnt = 0;
 	res = -EAGAIN;
 	if (ctx->count > 0)
-		res = sizeof(ucnt);
-	else if (!(file->f_flags & O_NONBLOCK)) {
+		res = 0;
+	else if (!no_wait) {
 		__add_wait_queue(&ctx->wqh, &wait);
-		for (res = 0;;) {
+		for (;;) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (ctx->count > 0) {
-				res = sizeof(ucnt);
+				res = 0;
 				break;
 			}
 			if (signal_pending(current)) {
@@ -168,18 +213,32 @@ static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
 		__remove_wait_queue(&ctx->wqh, &wait);
 		__set_current_state(TASK_RUNNING);
 	}
-	if (likely(res > 0)) {
-		ucnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
-		ctx->count -= ucnt;
+	if (likely(res == 0)) {
+		eventfd_ctx_do_read(ctx, cnt);
 		if (waitqueue_active(&ctx->wqh))
 			wake_up_locked_poll(&ctx->wqh, POLLOUT);
 	}
 	spin_unlock_irq(&ctx->wqh.lock);
-	if (res > 0 && put_user(ucnt, (__u64 __user *) buf))
-		return -EFAULT;
 
 	return res;
 }
+EXPORT_SYMBOL_GPL(eventfd_ctx_read);
+
+static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	ssize_t res;
+	__u64 cnt;
+
+	if (count < sizeof(cnt))
+		return -EINVAL;
+	res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt);
+	if (res < 0)
+		return res;
+
+	return put_user(cnt, (__u64 __user *) buf) ? -EFAULT : sizeof(cnt);
+}
 
 static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
 			     loff_t *ppos)
diff --git a/fs/exec.c b/fs/exec.c
index 632b02e..0790a107 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -941,9 +941,7 @@ void set_task_comm(struct task_struct *tsk, char *buf)
 
 int flush_old_exec(struct linux_binprm * bprm)
 {
-	char * name;
-	int i, ch, retval;
-	char tcomm[sizeof(current->comm)];
+	int retval;
 
 	/*
 	 * Make sure we have a private signal table and that
@@ -964,6 +962,25 @@ int flush_old_exec(struct linux_binprm * bprm)
 
 	bprm->mm = NULL;		/* We're using it now */
 
+	current->flags &= ~PF_RANDOMIZE;
+	flush_thread();
+	current->personality &= ~bprm->per_clear;
+
+	return 0;
+
+out:
+	return retval;
+}
+EXPORT_SYMBOL(flush_old_exec);
+
+void setup_new_exec(struct linux_binprm * bprm)
+{
+	int i, ch;
+	char * name;
+	char tcomm[sizeof(current->comm)];
+
+	arch_pick_mmap_layout(current->mm);
+
 	/* This is the point of no return */
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
@@ -985,9 +1002,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 	tcomm[i] = '\0';
 	set_task_comm(current, tcomm);
 
-	current->flags &= ~PF_RANDOMIZE;
-	flush_thread();
-
 	/* Set the new mm task size. We have to do that late because it may
 	 * depend on TIF_32BIT which is only updated in flush_thread() on
 	 * some architectures like powerpc
@@ -1003,8 +1017,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 		set_dumpable(current->mm, suid_dumpable);
 	}
 
-	current->personality &= ~bprm->per_clear;
-
 	/*
 	 * Flush performance counters when crossing a
 	 * security domain:
@@ -1019,14 +1031,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 			
 	flush_signal_handlers(current, 0);
 	flush_old_files(current->files);
-
-	return 0;
-
-out:
-	return retval;
 }
-
-EXPORT_SYMBOL(flush_old_exec);
+EXPORT_SYMBOL(setup_new_exec);
 
 /*
  * Prepare credentials and lock ->cred_guard_mutex.
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 698a863..2afbceb 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 423033a..c52e988 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 9acf7e8..9ed1bb1 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 4df8621..a60ab9a 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 56f9271..874d169 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -361,14 +361,11 @@ struct ext4_new_group_data {
 	   so set the magic i_delalloc_reserve_flag after taking the 
 	   inode allocation semaphore for */
 #define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
-	/* Call ext4_da_update_reserve_space() after successfully 
-	   allocating the blocks */
-#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE	0x0008
 	/* caller is from the direct IO path, request to creation of an
 	unitialized extents if not allocated, split the uninitialized
 	extent if blocks has been preallocated already*/
-#define EXT4_GET_BLOCKS_DIO			0x0010
-#define EXT4_GET_BLOCKS_CONVERT			0x0020
+#define EXT4_GET_BLOCKS_DIO			0x0008
+#define EXT4_GET_BLOCKS_CONVERT			0x0010
 #define EXT4_GET_BLOCKS_DIO_CREATE_EXT		(EXT4_GET_BLOCKS_DIO|\
 					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
 	/* Convert extent to initialized after direct IO complete */
@@ -699,6 +696,8 @@ 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;
@@ -1441,6 +1440,8 @@ extern int ext4_block_truncate_page(handle_t *handle,
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int flush_aio_dio_completed_IO(struct inode *inode);
+extern void ext4_da_update_reserve_space(struct inode *inode,
+					int used, int quota_claim);
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 2ca6864..bdb6ce7 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 3a7928f..765a482 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 +3121,30 @@ 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);
+		allocated = max_blocks;
+	}
+
+	/*
+	 * If we have done fallocate with the offset that is already
+	 * delayed allocated, we would have block reservation
+	 * and quota reservation done in the delayed write path.
+	 * But fallocate would have already updated quota and block
+	 * count for this offset. So cancel these reservation
+	 */
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ext4_da_update_reserve_space(inode, allocated, 0);
+
 map_out:
 	set_buffer_mapped(bh_result);
 out1:
@@ -3190,7 +3237,13 @@ 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;
@@ -3327,9 +3380,18 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	/* previous routine could use block we allocated */
 	newblock = ext_pblock(&newex);
 	allocated = ext4_ext_get_actual_len(&newex);
+	if (allocated > max_blocks)
+		allocated = max_blocks;
 	set_buffer_new(bh_result);
 
 	/*
+	 * Update reserved blocks/metadata blocks after successful
+	 * block allocation which had been deferred till now.
+	 */
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ext4_da_update_reserve_space(inode, allocated, 1);
+
+	/*
 	 * Cache the extent and update transaction to commit on fdatasync only
 	 * when it is _not_ an uninitialized extent.
 	 */
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 0b22497..98bd140 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 ab80796..e119524 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1009,86 +1009,114 @@ 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);
 }
 
-static void ext4_da_update_reserve_space(struct inode *inode, int used)
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
+void ext4_da_update_reserve_space(struct inode *inode,
+					int used, int quota_claim)
 {
 	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, allocated_meta_blocks = 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;
+	allocated_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
-	 */
-	if (mdb_free)
-		vfs_dq_release_reservation_block(inode, mdb_free);
+	/* Update quota subsystem */
+	if (quota_claim) {
+		vfs_dq_claim_block(inode, used);
+		if (mdb_free)
+			vfs_dq_release_reservation_block(inode, mdb_free);
+	} else {
+		/*
+		 * We did fallocate with an offset that is already delayed
+		 * allocated. So on delayed allocated writeback we should
+		 * not update the quota for allocated blocks. But then
+		 * converting an fallocate region to initialized region would
+		 * have caused a metadata allocation. So claim quota for
+		 * that
+		 */
+		if (allocated_meta_blocks)
+			vfs_dq_claim_block(inode, allocated_meta_blocks);
+		vfs_dq_release_reservation_block(inode, mdb_free + used);
+	}
 
 	/*
 	 * If we have done all the pending block allocations and if
 	 * 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);
 }
 
@@ -1280,18 +1308,20 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 			 */
 			EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
 		}
-	}
 
+		/*
+		 * Update reserved blocks/metadata blocks after successful
+		 * block allocation which had been deferred till now. We don't
+		 * support fallocate for non extent files. So we can update
+		 * reserve space here.
+		 */
+		if ((retval > 0) &&
+			(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
+			ext4_da_update_reserve_space(inode, retval, 1);
+	}
 	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 		EXT4_I(inode)->i_delalloc_reserved_flag = 0;
 
-	/*
-	 * Update reserved blocks/metadata blocks after successful
-	 * block allocation which had been deferred till now.
-	 */
-	if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE))
-		ext4_da_update_reserve_space(inode, retval);
-
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && buffer_mapped(bh)) {
 		int ret = check_block_validity(inode, "file system "
@@ -1797,11 +1827,15 @@ 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 +1843,31 @@ 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))
 		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)) {
 			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 +1875,46 @@ 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,
@@ -2192,10 +2219,10 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
 	 * variables are updated after the blocks have been allocated.
 	 */
 	new.b_state = 0;
-	get_blocks_flags = (EXT4_GET_BLOCKS_CREATE |
-			    EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+	get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
 	if (mpd->b_state & (1 << BH_Delay))
-		get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE;
+		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
 	blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
 			       &new, get_blocks_flags);
 	if (blks < 0) {
@@ -2493,7 +2520,7 @@ 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 +2994,7 @@ 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 +3019,18 @@ 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;
 }
 
@@ -3005,7 +3038,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       loff_t pos, unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
 {
-	int ret, retries = 0;
+	int ret, retries = 0, quota_retries = 0;
 	struct page *page;
 	pgoff_t index;
 	unsigned from, to;
@@ -3064,6 +3097,22 @@ retry:
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
+
+	if ((ret == -EDQUOT) &&
+	    EXT4_I(inode)->i_reserved_meta_blocks &&
+	    (quota_retries++ < 3)) {
+		/*
+		 * Since we often over-estimate the number of meta
+		 * data blocks required, we may sometimes get a
+		 * spurios out of quota error even though there would
+		 * be enough space once we write the data blocks and
+		 * find out how many meta data blocks were _really_
+		 * required.  So try forcing the inode write to see if
+		 * that helps.
+		 */
+		write_inode_now(inode, (quota_retries == 3));
+		goto retry;
+	}
 out:
 	return ret;
 }
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 0ca8110..436521c 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 6ed9aa9..735c20d 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 83218be..f3a2f7e 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/fcntl.c b/fs/fcntl.c
index 2cf93ec..5ef953e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -199,7 +199,9 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
                      int force)
 {
-	write_lock_irq(&filp->f_owner.lock);
+	unsigned long flags;
+
+	write_lock_irqsave(&filp->f_owner.lock, flags);
 	if (force || !filp->f_owner.pid) {
 		put_pid(filp->f_owner.pid);
 		filp->f_owner.pid = get_pid(pid);
@@ -211,7 +213,7 @@ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
 			filp->f_owner.euid = cred->euid;
 		}
 	}
-	write_unlock_irq(&filp->f_owner.lock);
+	write_unlock_irqrestore(&filp->f_owner.lock, flags);
 }
 
 int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
@@ -618,60 +620,90 @@ static DEFINE_RWLOCK(fasync_lock);
 static struct kmem_cache *fasync_cache __read_mostly;
 
 /*
- * fasync_helper() is used by almost all character device drivers
- * to set up the fasync queue. It returns negative on error, 0 if it did
- * no changes and positive if it added/deleted the entry.
+ * Remove a fasync entry. If successfully removed, return
+ * positive and clear the FASYNC flag. If no entry exists,
+ * do nothing and return 0.
+ *
+ * NOTE! It is very important that the FASYNC flag always
+ * match the state "is the filp on a fasync list".
+ *
+ * We always take the 'filp->f_lock', in since fasync_lock
+ * needs to be irq-safe.
  */
-int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
+static int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 {
 	struct fasync_struct *fa, **fp;
-	struct fasync_struct *new = NULL;
 	int result = 0;
 
-	if (on) {
-		new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
-		if (!new)
-			return -ENOMEM;
+	spin_lock(&filp->f_lock);
+	write_lock_irq(&fasync_lock);
+	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
+		if (fa->fa_file != filp)
+			continue;
+		*fp = fa->fa_next;
+		kmem_cache_free(fasync_cache, fa);
+		filp->f_flags &= ~FASYNC;
+		result = 1;
+		break;
 	}
+	write_unlock_irq(&fasync_lock);
+	spin_unlock(&filp->f_lock);
+	return result;
+}
+
+/*
+ * Add a fasync entry. Return negative on error, positive if
+ * added, and zero if did nothing but change an existing one.
+ *
+ * NOTE! It is very important that the FASYNC flag always
+ * match the state "is the filp on a fasync list".
+ */
+static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp)
+{
+	struct fasync_struct *new, *fa, **fp;
+	int result = 0;
+
+	new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
 
-	/*
-	 * We need to take f_lock first since it's not an IRQ-safe
-	 * lock.
-	 */
 	spin_lock(&filp->f_lock);
 	write_lock_irq(&fasync_lock);
 	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
-		if (fa->fa_file == filp) {
-			if(on) {
-				fa->fa_fd = fd;
-				kmem_cache_free(fasync_cache, new);
-			} else {
-				*fp = fa->fa_next;
-				kmem_cache_free(fasync_cache, fa);
-				result = 1;
-			}
-			goto out;
-		}
+		if (fa->fa_file != filp)
+			continue;
+		fa->fa_fd = fd;
+		kmem_cache_free(fasync_cache, new);
+		goto out;
 	}
 
-	if (on) {
-		new->magic = FASYNC_MAGIC;
-		new->fa_file = filp;
-		new->fa_fd = fd;
-		new->fa_next = *fapp;
-		*fapp = new;
-		result = 1;
-	}
+	new->magic = FASYNC_MAGIC;
+	new->fa_file = filp;
+	new->fa_fd = fd;
+	new->fa_next = *fapp;
+	*fapp = new;
+	result = 1;
+	filp->f_flags |= FASYNC;
+
 out:
-	if (on)
-		filp->f_flags |= FASYNC;
-	else
-		filp->f_flags &= ~FASYNC;
 	write_unlock_irq(&fasync_lock);
 	spin_unlock(&filp->f_lock);
 	return result;
 }
 
+/*
+ * fasync_helper() is used by almost all character device drivers
+ * to set up the fasync queue, and for regular files by the file
+ * lease code. It returns negative on error, 0 if it did no changes
+ * and positive if it added/deleted the entry.
+ */
+int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
+{
+	if (!on)
+		return fasync_remove_entry(filp, fapp);
+	return fasync_add_entry(fd, filp, fapp);
+}
+
 EXPORT_SYMBOL(fasync_helper);
 
 void __kill_fasync(struct fasync_struct *fa, int sig, int band)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 49bc1b8..1a7c42c 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/fuse/file.c b/fs/fuse/file.c
index c18913a..a9f5e13 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -828,6 +828,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		if (!page)
 			break;
 
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_page(page);
+
 		pagefault_disable();
 		tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
 		pagefault_enable();
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4eb308a..a6abbae8 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -569,6 +569,40 @@ static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
 	return ret;
 }
 
+/**
+ * gfs2_file_aio_write - Perform a write to a file
+ * @iocb: The io context
+ * @iov: The data to write
+ * @nr_segs: Number of @iov segments
+ * @pos: The file position
+ *
+ * We have to do a lock/unlock here to refresh the inode size for
+ * O_APPEND writes, otherwise we can land up writing at the wrong
+ * offset. There is still a race, but provided the app is using its
+ * own file locking, this will make O_APPEND work as expected.
+ *
+ */
+
+static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+				   unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+
+	if (file->f_flags & O_APPEND) {
+		struct dentry *dentry = file->f_dentry;
+		struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+		struct gfs2_holder gh;
+		int ret;
+
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+		if (ret)
+			return ret;
+		gfs2_glock_dq_uninit(&gh);
+	}
+
+	return generic_file_aio_write(iocb, iov, nr_segs, pos);
+}
+
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
 
 /**
@@ -711,7 +745,7 @@ const struct file_operations gfs2_file_fops = {
 	.read		= do_sync_read,
 	.aio_read	= generic_file_aio_read,
 	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.aio_write	= gfs2_file_aio_write,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
@@ -741,7 +775,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.read		= do_sync_read,
 	.aio_read	= generic_file_aio_read,
 	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.aio_write	= gfs2_file_aio_write,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index f455a03..f426633 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -769,6 +769,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	if (!gl)
 		return -ENOMEM;
 
+	atomic_inc(&sdp->sd_glock_disposal);
 	gl->gl_flags = 0;
 	gl->gl_name = name;
 	atomic_set(&gl->gl_ref, 1);
@@ -1538,6 +1539,9 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
 		up_write(&gfs2_umount_flush_sem);
 		msleep(10);
 	}
+	flush_workqueue(glock_workqueue);
+	wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
+	gfs2_dump_lockstate(sdp);
 }
 
 void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 13f0bd2..c0262fa 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -123,7 +123,7 @@ struct lm_lockops {
 	int (*lm_mount) (struct gfs2_sbd *sdp, const char *fsname);
  	void (*lm_unmount) (struct gfs2_sbd *sdp);
 	void (*lm_withdraw) (struct gfs2_sbd *sdp);
-	void (*lm_put_lock) (struct kmem_cache *cachep, void *gl);
+	void (*lm_put_lock) (struct kmem_cache *cachep, struct gfs2_glock *gl);
 	unsigned int (*lm_lock) (struct gfs2_glock *gl,
 				 unsigned int req_state, unsigned int flags);
 	void (*lm_cancel) (struct gfs2_glock *gl);
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 4792200..bc0ad15 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -544,6 +544,8 @@ struct gfs2_sbd {
 	struct gfs2_holder sd_live_gh;
 	struct gfs2_glock *sd_rename_gl;
 	struct gfs2_glock *sd_trans_gl;
+	wait_queue_head_t sd_glock_wait;
+	atomic_t sd_glock_disposal;
 
 	/* Inode Stuff */
 
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 46df988..0e5e0e7 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -21,6 +21,7 @@ static void gdlm_ast(void *arg)
 {
 	struct gfs2_glock *gl = arg;
 	unsigned ret = gl->gl_state;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
 
 	BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED);
 
@@ -30,6 +31,8 @@ static void gdlm_ast(void *arg)
 	switch (gl->gl_lksb.sb_status) {
 	case -DLM_EUNLOCK: /* Unlocked, so glock can be freed */
 		kmem_cache_free(gfs2_glock_cachep, gl);
+		if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+			wake_up(&sdp->sd_glock_wait);
 		return;
 	case -DLM_ECANCEL: /* Cancel while getting lock */
 		ret |= LM_OUT_CANCELED;
@@ -164,14 +167,16 @@ static unsigned int gdlm_lock(struct gfs2_glock *gl,
 	return LM_OUT_ASYNC;
 }
 
-static void gdlm_put_lock(struct kmem_cache *cachep, void *ptr)
+static void gdlm_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
 {
-	struct gfs2_glock *gl = ptr;
-	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 	int error;
 
 	if (gl->gl_lksb.sb_lkid == 0) {
 		kmem_cache_free(cachep, gl);
+		if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+			wake_up(&sdp->sd_glock_wait);
 		return;
 	}
 
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index cb8d7a9..6f68a5f 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -121,7 +121,7 @@ struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp)
 	if (aspace) {
 		mapping_set_gfp_mask(aspace->i_mapping, GFP_NOFS);
 		aspace->i_mapping->a_ops = &aspace_aops;
-		aspace->i_size = ~0ULL;
+		aspace->i_size = MAX_LFS_FILESIZE;
 		ip = GFS2_I(aspace);
 		clear_bit(GIF_USER, &ip->i_flags);
 		insert_inode_hash(aspace);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index edfee24..8a102f7 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -82,6 +82,8 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	gfs2_tune_init(&sdp->sd_tune);
 
+	init_waitqueue_head(&sdp->sd_glock_wait);
+	atomic_set(&sdp->sd_glock_disposal, 0);
 	spin_lock_init(&sdp->sd_statfs_spin);
 
 	spin_lock_init(&sdp->sd_rindex_spin);
@@ -983,9 +985,17 @@ static const match_table_t nolock_tokens = {
 	{ Opt_err, NULL },
 };
 
+static void nolock_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	kmem_cache_free(cachep, gl);
+	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+		wake_up(&sdp->sd_glock_wait);
+}
+
 static const struct lm_lockops nolock_ops = {
 	.lm_proto_name = "lock_nolock",
-	.lm_put_lock = kmem_cache_free,
+	.lm_put_lock = nolock_put_lock,
 	.lm_tokens = &nolock_tokens,
 };
 
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 247436c..84350e1 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -748,7 +748,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
-	int alloc_required;
+	int alloc_required = 0;
 	unsigned int x;
 	int error;
 
@@ -867,7 +867,9 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			goto out_gunlock;
 	}
 
-	alloc_required = error = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
+	if (nip == NULL)
+		alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
+	error = alloc_required;
 	if (error < 0)
 		goto out_gunlock;
 	error = 0;
@@ -1086,7 +1088,8 @@ static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
 		error = vfs_follow_link(nd, buf);
 		if (buf != array)
 			kfree(buf);
-	}
+	} else
+		path_put(&nd->path);
 
 	return ERR_PTR(error);
 }
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 0608f49..503b842 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -591,11 +591,7 @@ static int gfs2_ri_update(struct gfs2_inode *ip)
 	u64 rgrp_count = ip->i_disksize;
 	int error;
 
-	if (do_div(rgrp_count, sizeof(struct gfs2_rindex))) {
-		gfs2_consist_inode(ip);
-		return -EIO;
-	}
-
+	do_div(rgrp_count, sizeof(struct gfs2_rindex));
 	clear_rgrpdi(sdp);
 
 	file_ra_state_init(&ra_state, inode->i_mapping);
@@ -915,7 +911,7 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
 struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
 {
 	BUG_ON(ip->i_alloc != NULL);
-	ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_KERNEL);
+	ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_NOFS);
 	return ip->i_alloc;
 }
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index c282ad4..b9dd3da 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -21,6 +21,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/time.h>
+#include <linux/wait.h>
 
 #include "gfs2.h"
 #include "incore.h"
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 8a04108..c2ebdf2c 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1296,6 +1296,7 @@ fail:
 
 int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 {
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_ea_location el;
 	struct buffer_head *dibh;
 	int error;
@@ -1305,16 +1306,17 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 		return error;
 
 	if (GFS2_EA_IS_STUFFED(el.el_ea)) {
-		error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + RES_EATTR, 0);
-		if (error)
-			return error;
-
-		gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1);
-		memcpy(GFS2_EA2DATA(el.el_ea), data,
-		       GFS2_EA_DATA_LEN(el.el_ea));
-	} else
+		error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0);
+		if (error == 0) {
+			gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1);
+			memcpy(GFS2_EA2DATA(el.el_ea), data,
+			       GFS2_EA_DATA_LEN(el.el_ea));
+		}
+	} else {
 		error = ea_acl_chmod_unstuffed(ip, el.el_ea, data);
+	}
 
+	brelse(el.el_bh);
 	if (error)
 		return error;
 
@@ -1327,8 +1329,7 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 		brelse(dibh);
 	}
 
-	gfs2_trans_end(GFS2_SB(&ip->i_inode));
-
+	gfs2_trans_end(sdp);
 	return error;
 }
 
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index a5089a6..7239efc 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -646,22 +646,27 @@ static const struct super_operations hppfs_sbops = {
 static int hppfs_readlink(struct dentry *dentry, char __user *buffer,
 			  int buflen)
 {
-	struct dentry *proc_dentry;
-
-	proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
+	struct dentry *proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
 	return proc_dentry->d_inode->i_op->readlink(proc_dentry, buffer,
 						    buflen);
 }
 
 static void *hppfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
-	struct dentry *proc_dentry;
-
-	proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
+	struct dentry *proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
 
 	return proc_dentry->d_inode->i_op->follow_link(proc_dentry, nd);
 }
 
+static void hppfs_put_link(struct dentry *dentry, struct nameidata *nd,
+			   void *cookie)
+{
+	struct dentry *proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
+
+	if (proc_dentry->d_inode->i_op->put_link)
+		proc_dentry->d_inode->i_op->put_link(proc_dentry, nd, cookie);
+}
+
 static const struct inode_operations hppfs_dir_iops = {
 	.lookup		= hppfs_lookup,
 };
@@ -669,6 +674,7 @@ static const struct inode_operations hppfs_dir_iops = {
 static const struct inode_operations hppfs_link_iops = {
 	.readlink	= hppfs_readlink,
 	.follow_link	= hppfs_follow_link,
+	.put_link	= hppfs_put_link,
 };
 
 static struct inode *get_inode(struct super_block *sb, struct dentry *dentry)
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index ca0f5eb..8868493 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 6a10238..1bc74b6 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 17af879..ac0d027 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 68921d9..94a5e60 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;
@@ -560,6 +561,7 @@ static __always_inline int __do_follow_link(struct path *path, struct nameidata
 		dget(dentry);
 	}
 	mntget(path->mnt);
+	nd->last_type = LAST_BIND;
 	cookie = dentry->d_inode->i_op->follow_link(dentry, nd);
 	error = PTR_ERR(cookie);
 	if (!IS_ERR(cookie)) {
@@ -1602,11 +1604,12 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	struct file *filp;
 	struct nameidata nd;
 	int error;
-	struct path path, save;
+	struct path path;
 	struct dentry *dir;
 	int count = 0;
 	int will_truncate;
 	int flag = open_to_namei_flags(open_flag);
+	int force_reval = 0;
 
 	/*
 	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
@@ -1618,7 +1621,7 @@ struct file *do_filp_open(int dfd, const char *pathname,
 		open_flag |= O_DSYNC;
 
 	if (!acc_mode)
-		acc_mode = MAY_OPEN | ACC_MODE(flag);
+		acc_mode = MAY_OPEN | ACC_MODE(open_flag);
 
 	/* O_TRUNC implies we need access checks for write permissions */
 	if (flag & O_TRUNC)
@@ -1658,9 +1661,12 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	/*
 	 * Create - we need to know the parent.
 	 */
+reval:
 	error = path_init(dfd, pathname, LOOKUP_PARENT, &nd);
 	if (error)
 		return ERR_PTR(error);
+	if (force_reval)
+		nd.flags |= LOOKUP_REVAL;
 	error = path_walk(pathname, &nd);
 	if (error) {
 		if (nd.root.mnt)
@@ -1852,17 +1858,7 @@ do_link:
 	error = security_inode_follow_link(path.dentry, &nd);
 	if (error)
 		goto exit_dput;
-	save = nd.path;
-	path_get(&save);
 	error = __do_follow_link(&path, &nd);
-	if (error == -ESTALE) {
-		/* nd.path had been dropped */
-		nd.path = save;
-		path_get(&nd.path);
-		nd.flags |= LOOKUP_REVAL;
-		error = __do_follow_link(&path, &nd);
-	}
-	path_put(&save);
 	path_put(&path);
 	if (error) {
 		/* Does someone understand code flow here? Or it is only
@@ -1872,6 +1868,10 @@ do_link:
 		release_open_intent(&nd);
 		if (nd.root.mnt)
 			path_put(&nd.root);
+		if (error == -ESTALE && !force_reval) {
+			force_reval = 1;
+			goto reval;
+		}
 		return ERR_PTR(error);
 	}
 	nd.flags &= ~LOOKUP_PARENT;
diff --git a/fs/namespace.c b/fs/namespace.c
index 7d70d63..c768f73 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -965,10 +965,12 @@ EXPORT_SYMBOL(may_umount_tree);
 int may_umount(struct vfsmount *mnt)
 {
 	int ret = 1;
+	down_read(&namespace_sem);
 	spin_lock(&vfsmount_lock);
 	if (propagate_mount_busy(mnt, 2))
 		ret = 0;
 	spin_unlock(&vfsmount_lock);
+	up_read(&namespace_sem);
 	return ret;
 }
 
@@ -1352,12 +1354,12 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	if (err)
 		goto out_cleanup_ids;
 
+	spin_lock(&vfsmount_lock);
+
 	if (IS_MNT_SHARED(dest_mnt)) {
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
 	}
-
-	spin_lock(&vfsmount_lock);
 	if (parent_path) {
 		detach_mnt(source_mnt, parent_path);
 		attach_mnt(source_mnt, path);
@@ -1534,8 +1536,12 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 		err = change_mount_flags(path->mnt, flags);
 	else
 		err = do_remount_sb(sb, flags, data, 0);
-	if (!err)
+	if (!err) {
+		spin_lock(&vfsmount_lock);
+		mnt_flags |= path->mnt->mnt_flags & MNT_PNODE_MASK;
 		path->mnt->mnt_flags = mnt_flags;
+		spin_unlock(&vfsmount_lock);
+	}
 	up_write(&sb->s_umount);
 	if (!err) {
 		security_sb_post_remount(path->mnt, flags, data);
@@ -1665,6 +1671,8 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 {
 	int err;
 
+	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD);
+
 	down_write(&namespace_sem);
 	/* Something was mounted here while we slept */
 	while (d_mountpoint(path->dentry) &&
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2c5ace4..3c7f03b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1615,6 +1615,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				goto out;
 
 			new_dentry = dentry;
+			rehash = NULL;
 			new_inode = NULL;
 		}
 	}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 6b89132..63f2071 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -486,6 +486,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 {
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
+	if (gfp & __GFP_WAIT)
+		nfs_wb_page(page->mapping->host, page);
 	/* If PagePrivate() is set, then the page is not freeable */
 	if (PagePrivate(page))
 		return 0;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index faa0918..f141bde 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1261,8 +1261,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
 		if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
+			umode_t newmode = inode->i_mode & S_IFMT;
+			newmode |= fattr->mode & S_IALLUGO;
+			inode->i_mode = newmode;
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
-			inode->i_mode = fattr->mode;
 		}
 	} else if (server->caps & NFS_CAP_MODE)
 		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 865265b..0c6fda3 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -146,6 +146,7 @@ enum {
 	NFS_O_RDWR_STATE,		/* OPEN stateid has read/write state */
 	NFS_STATE_RECLAIM_REBOOT,	/* OPEN stateid server rebooted */
 	NFS_STATE_RECLAIM_NOGRACE,	/* OPEN stateid needs to recover state */
+	NFS_STATE_POSIX_LOCKS,		/* Posix locks are supported */
 };
 
 struct nfs4_state {
@@ -277,6 +278,7 @@ extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs4_schedule_state_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
+extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 198d51d..375f0fa 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -249,19 +249,15 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 			if (state == NULL)
 				break;
 			nfs4_state_mark_reclaim_nograce(clp, state);
-		case -NFS4ERR_STALE_CLIENTID:
+			goto do_state_recovery;
 		case -NFS4ERR_STALE_STATEID:
-		case -NFS4ERR_EXPIRED:
-			nfs4_schedule_state_recovery(clp);
-			ret = nfs4_wait_clnt_recover(clp);
-			if (ret == 0)
-				exception->retry = 1;
-#if !defined(CONFIG_NFS_V4_1)
-			break;
-#else /* !defined(CONFIG_NFS_V4_1) */
-			if (!nfs4_has_session(server->nfs_client))
+			if (state == NULL)
 				break;
-			/* FALLTHROUGH */
+			nfs4_state_mark_reclaim_reboot(clp, state);
+		case -NFS4ERR_STALE_CLIENTID:
+		case -NFS4ERR_EXPIRED:
+			goto do_state_recovery;
+#if defined(CONFIG_NFS_V4_1)
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
 		case -NFS4ERR_BAD_HIGH_SLOT:
@@ -274,7 +270,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 			nfs4_schedule_state_recovery(clp);
 			exception->retry = 1;
 			break;
-#endif /* !defined(CONFIG_NFS_V4_1) */
+#endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
 			if (exception->timeout > HZ) {
 				/* We have retried a decent amount, time to
@@ -293,6 +289,12 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 	}
 	/* We failed to handle the error */
 	return nfs4_map_errors(ret);
+do_state_recovery:
+	nfs4_schedule_state_recovery(clp);
+	ret = nfs4_wait_clnt_recover(clp);
+	if (ret == 0)
+		exception->retry = 1;
+	return ret;
 }
 
 
@@ -1658,6 +1660,8 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
 	status = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto err_opendata_put;
+	if ((opendata->o_res.rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) != 0)
+		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 	nfs4_opendata_put(opendata);
 	nfs4_put_state_owner(sp);
 	*res = state;
@@ -3422,15 +3426,14 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			if (state == NULL)
 				break;
 			nfs4_state_mark_reclaim_nograce(clp, state);
-		case -NFS4ERR_STALE_CLIENTID:
+			goto do_state_recovery;
 		case -NFS4ERR_STALE_STATEID:
+			if (state == NULL)
+				break;
+			nfs4_state_mark_reclaim_reboot(clp, state);
+		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
-			rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
-			nfs4_schedule_state_recovery(clp);
-			if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
-				rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
-			task->tk_status = 0;
-			return -EAGAIN;
+			goto do_state_recovery;
 #if defined(CONFIG_NFS_V4_1)
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -3458,6 +3461,13 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 	}
 	task->tk_status = nfs4_map_errors(task->tk_status);
 	return 0;
+do_state_recovery:
+	rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
+	nfs4_schedule_state_recovery(clp);
+	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
+		rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
+	task->tk_status = 0;
+	return -EAGAIN;
 }
 
 static int
@@ -4088,6 +4098,28 @@ static const struct rpc_call_ops nfs4_recover_lock_ops = {
 	.rpc_release = nfs4_lock_release,
 };
 
+static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error)
+{
+	struct nfs_client *clp = server->nfs_client;
+	struct nfs4_state *state = lsp->ls_state;
+
+	switch (error) {
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_EXPIRED:
+		if (new_lock_owner != 0 ||
+		   (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+			nfs4_state_mark_reclaim_nograce(clp, state);
+		lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+		break;
+	case -NFS4ERR_STALE_STATEID:
+		if (new_lock_owner != 0 ||
+		    (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+			nfs4_state_mark_reclaim_reboot(clp, state);
+		lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+	};
+}
+
 static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int recovery_type)
 {
 	struct nfs4_lockdata *data;
@@ -4126,6 +4158,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 	ret = nfs4_wait_for_completion_rpc_task(task);
 	if (ret == 0) {
 		ret = data->rpc_status;
+		if (ret)
+			nfs4_handle_setlk_error(data->server, data->lsp,
+					data->arg.new_lock_owner, ret);
 	} else
 		data->cancelled = 1;
 	rpc_put_task(task);
@@ -4181,8 +4216,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
 	unsigned char fl_flags = request->fl_flags;
-	int status;
+	int status = -ENOLCK;
 
+	if ((fl_flags & FL_POSIX) &&
+			!test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
+		goto out;
 	/* Is this a delegated open? */
 	status = nfs4_set_lock_state(state, request);
 	if (status != 0)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6d263ed..c1e2733 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -901,7 +901,7 @@ void nfs4_schedule_state_recovery(struct nfs_client *clp)
 	nfs4_schedule_state_manager(clp);
 }
 
-static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
+int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
 {
 
 	set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index e297593..a12c45b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -176,6 +176,12 @@ void nfs_release_request(struct nfs_page *req)
 	kref_put(&req->wb_kref, nfs_free_request);
 }
 
+static int nfs_wait_bit_uninterruptible(void *word)
+{
+	io_schedule();
+	return 0;
+}
+
 /**
  * nfs_wait_on_request - Wait for a request to complete.
  * @req: request to wait upon.
@@ -186,14 +192,9 @@ void nfs_release_request(struct nfs_page *req)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
-	int ret = 0;
-
-	if (!test_bit(PG_BUSY, &req->wb_flags))
-		goto out;
-	ret = out_of_line_wait_on_bit(&req->wb_flags, PG_BUSY,
-			nfs_wait_bit_killable, TASK_KILLABLE);
-out:
-	return ret;
+	return wait_on_bit(&req->wb_flags, PG_BUSY,
+			nfs_wait_bit_uninterruptible,
+			TASK_UNINTERRUPTIBLE);
 }
 
 /**
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ce907ef..f1afee4 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -243,6 +243,7 @@ static int  nfs_show_stats(struct seq_file *, struct vfsmount *);
 static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *);
 static int nfs_xdev_get_sb(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
+static void nfs_put_super(struct super_block *);
 static void nfs_kill_super(struct super_block *);
 static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
@@ -266,6 +267,7 @@ static const struct super_operations nfs_sops = {
 	.alloc_inode	= nfs_alloc_inode,
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs_write_inode,
+	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.clear_inode	= nfs_clear_inode,
 	.umount_begin	= nfs_umount_begin,
@@ -335,6 +337,7 @@ static const struct super_operations nfs4_sops = {
 	.alloc_inode	= nfs_alloc_inode,
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs_write_inode,
+	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.clear_inode	= nfs4_clear_inode,
 	.umount_begin	= nfs_umount_begin,
@@ -2258,6 +2261,17 @@ error_splat_super:
 }
 
 /*
+ * Ensure that we unregister the bdi before kill_anon_super
+ * releases the device name
+ */
+static void nfs_put_super(struct super_block *s)
+{
+	struct nfs_server *server = NFS_SB(s);
+
+	bdi_unregister(&server->backing_dev_info);
+}
+
+/*
  * Destroy an NFS2/3 superblock
  */
 static void nfs_kill_super(struct super_block *s)
@@ -2265,7 +2279,6 @@ static void nfs_kill_super(struct super_block *s)
 	struct nfs_server *server = NFS_SB(s);
 
 	kill_anon_super(s);
-	bdi_unregister(&server->backing_dev_info);
 	nfs_fscache_release_super_cookie(s);
 	nfs_free_server(server);
 }
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 70e1fbb..ad4d2e7 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -15,8 +15,10 @@
 
 #include "callback.h"
 
+#ifdef CONFIG_NFS_V4
 static const int nfs_set_port_min = 0;
 static const int nfs_set_port_max = 65535;
+#endif
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index d171696..7b54b8b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1233,7 +1233,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-void nfs_commitdata_release(void *data)
+static void nfs_commitdata_release(void *data)
 {
 	struct nfs_write_data *wdata = data;
 
@@ -1541,6 +1541,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 			break;
 		}
 		ret = nfs_wait_on_request(req);
+		nfs_release_request(req);
 		if (ret < 0)
 			goto out;
 	}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7c2e337..c194793 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 f4a14ea..effdbdb 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 d5ad54e..1873781 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 d369ac7..236753d 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 f6af760..d6b2b83 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/nilfs2/segment.c b/fs/nilfs2/segment.c
index 17584c5..105b508 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2829,7 +2829,7 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 		|| sci->sc_seq_request != sci->sc_seq_done);
 	spin_unlock(&sci->sc_state_lock);
 
-	if (flag || nilfs_segctor_confirm(sci))
+	if (flag || !nilfs_segctor_confirm(sci))
 		nilfs_segctor_write_out(sci);
 
 	WARN_ON(!list_empty(&sci->sc_copied_buffers));
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index c9ee67b..1afb0a1 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -121,7 +121,7 @@ static int idr_callback(int id, void *p, void *data)
 	if (warned)
 		return 0;
 
-	warned = false;
+	warned = true;
 	entry = p;
 	ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
 
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 8271cf0..a94e8bd 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -552,7 +552,7 @@ retry:
 
 	spin_lock(&group->inotify_data.idr_lock);
 	ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
-				group->inotify_data.last_wd,
+				group->inotify_data.last_wd+1,
 				&tmp_ientry->wd);
 	spin_unlock(&group->inotify_data.idr_lock);
 	if (ret) {
@@ -632,7 +632,7 @@ static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsign
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
-	group->inotify_data.last_wd = 1;
+	group->inotify_data.last_wd = 0;
 	group->inotify_data.user = user;
 	group->inotify_data.fa = NULL;
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3d30a1c..06ccf6a 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/proc/array.c b/fs/proc/array.c
index f560325..13b5d07 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -327,94 +327,6 @@ static inline void task_context_switch_counts(struct seq_file *m,
 			p->nivcsw);
 }
 
-#ifdef CONFIG_MMU
-
-struct stack_stats {
-	struct vm_area_struct *vma;
-	unsigned long	startpage;
-	unsigned long	usage;
-};
-
-static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr,
-				unsigned long end, struct mm_walk *walk)
-{
-	struct stack_stats *ss = walk->private;
-	struct vm_area_struct *vma = ss->vma;
-	pte_t *pte, ptent;
-	spinlock_t *ptl;
-	int ret = 0;
-
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE) {
-		ptent = *pte;
-
-#ifdef CONFIG_STACK_GROWSUP
-		if (pte_present(ptent) || is_swap_pte(ptent))
-			ss->usage = addr - ss->startpage + PAGE_SIZE;
-#else
-		if (pte_present(ptent) || is_swap_pte(ptent)) {
-			ss->usage = ss->startpage - addr + PAGE_SIZE;
-			pte++;
-			ret = 1;
-			break;
-		}
-#endif
-	}
-	pte_unmap_unlock(pte - 1, ptl);
-	cond_resched();
-	return ret;
-}
-
-static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma,
-				struct task_struct *task)
-{
-	struct stack_stats ss;
-	struct mm_walk stack_walk = {
-		.pmd_entry = stack_usage_pte_range,
-		.mm = vma->vm_mm,
-		.private = &ss,
-	};
-
-	if (!vma->vm_mm || is_vm_hugetlb_page(vma))
-		return 0;
-
-	ss.vma = vma;
-	ss.startpage = task->stack_start & PAGE_MASK;
-	ss.usage = 0;
-
-#ifdef CONFIG_STACK_GROWSUP
-	walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end,
-		&stack_walk);
-#else
-	walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE,
-		&stack_walk);
-#endif
-	return ss.usage;
-}
-
-static inline void task_show_stack_usage(struct seq_file *m,
-						struct task_struct *task)
-{
-	struct vm_area_struct	*vma;
-	struct mm_struct	*mm = get_task_mm(task);
-
-	if (mm) {
-		down_read(&mm->mmap_sem);
-		vma = find_vma(mm, task->stack_start);
-		if (vma)
-			seq_printf(m, "Stack usage:\t%lu kB\n",
-				get_stack_usage_in_bytes(vma, task) >> 10);
-
-		up_read(&mm->mmap_sem);
-		mmput(mm);
-	}
-}
-#else
-static void task_show_stack_usage(struct seq_file *m, struct task_struct *task)
-{
-}
-#endif		/* CONFIG_MMU */
-
 static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 {
 	seq_printf(m, "Cpus_allowed:\t");
@@ -445,7 +357,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 	task_show_regs(m, task);
 #endif
 	task_context_switch_counts(m, task);
-	task_show_stack_usage(m, task);
 	return 0;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 18d5cc6..e42bbd8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1419,7 +1419,6 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
 		goto out;
 
 	error = PROC_I(inode)->op.proc_get_link(inode, &nd->path);
-	nd->last_type = LAST_BIND;
 out:
 	return ERR_PTR(error);
 }
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 47c03f4..f277c4a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -361,12 +361,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (!pte_present(ptent))
 			continue;
 
-		mss->resident += PAGE_SIZE;
-
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
 
+		mss->resident += PAGE_SIZE;
 		/* Accumulate the size in pages that have been accessed. */
 		if (pte_young(ptent) || PageReferenced(page))
 			mss->referenced += PAGE_SIZE;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index dea86ab..3fc62b0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1377,6 +1377,9 @@ static void inode_sub_rsv_space(struct inode *inode, qsize_t number)
 static qsize_t inode_get_rsv_space(struct inode *inode)
 {
 	qsize_t ret;
+
+	if (!inode->i_sb->dq_op->get_reserved_space)
+		return 0;
 	spin_lock(&inode->i_lock);
 	ret = *inode_reserved_space(inode);
 	spin_unlock(&inode->i_lock);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 2efc571..1739a4a 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -123,30 +123,6 @@ add_error:
 
 /*****************************************************************************/
 /*
- * check that file shrinkage doesn't leave any VMAs dangling in midair
- */
-static int ramfs_nommu_check_mappings(struct inode *inode,
-				      size_t newsize, size_t size)
-{
-	struct vm_area_struct *vma;
-	struct prio_tree_iter iter;
-
-	/* search for VMAs that fall within the dead zone */
-	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
-			      newsize >> PAGE_SHIFT,
-			      (size + PAGE_SIZE - 1) >> PAGE_SHIFT
-			      ) {
-		/* found one - only interested if it's shared out of the page
-		 * cache */
-		if (vma->vm_flags & VM_SHARED)
-			return -ETXTBSY; /* not quite true, but near enough */
-	}
-
-	return 0;
-}
-
-/*****************************************************************************/
-/*
  *
  */
 static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size)
@@ -164,7 +140,7 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size)
 
 	/* check that a decrease in size doesn't cut off any shared mappings */
 	if (newsize < size) {
-		ret = ramfs_nommu_check_mappings(inode, newsize, size);
+		ret = nommu_shrink_inode_mappings(inode, size, newsize);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index 6854957..65c8727 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 290ae38..9087b10 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,
@@ -3061,13 +3062,14 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
 int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
-	int error;
 	unsigned int ia_valid;
+	int depth;
+	int error;
 
 	/* must be turned off for recursive notify_change calls */
 	ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
 
-	reiserfs_write_lock(inode->i_sb);
+	depth = reiserfs_write_lock_once(inode->i_sb);
 	if (attr->ia_valid & ATTR_SIZE) {
 		/* version 2 items will be caught by the s_maxbytes check
 		 ** done for us in vmtruncate
@@ -3148,8 +3150,17 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 				    journal_end(&th, inode->i_sb, jbegin_count);
 			}
 		}
-		if (!error)
+		if (!error) {
+			/*
+			 * Relax the lock here, as it might truncate the
+			 * inode pages and wait for inode pages locks.
+			 * To release such page lock, the owner needs the
+			 * reiserfs lock
+			 */
+			reiserfs_write_unlock_once(inode->i_sb, depth);
 			error = inode_setattr(inode, attr);
+			depth = reiserfs_write_lock_once(inode->i_sb);
+		}
 	}
 
 	if (!error && reiserfs_posixacl(inode->i_sb)) {
@@ -3158,7 +3169,8 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
       out:
-	reiserfs_write_unlock(inode->i_sb);
+	reiserfs_write_unlock_once(inode->i_sb, depth);
+
 	return error;
 }
 
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index ace7745..f53505d 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -104,9 +104,10 @@ setflags_out:
 		err = put_user(inode->i_generation, (int __user *)arg);
 		break;
 	case REISERFS_IOC_SETVERSION:
-		if (!is_owner_or_cap(inode))
+		if (!is_owner_or_cap(inode)) {
 			err = -EPERM;
 			break;
+		}
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
 			break;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 2f8a7e7..ba98546 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 */
@@ -2903,7 +2913,9 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	journal->j_mount_id = 10;
 	journal->j_state = 0;
 	atomic_set(&(journal->j_jlock), 0);
+	reiserfs_write_unlock(sb);
 	journal->j_cnode_free_list = allocate_cnodes(num_cnodes);
+	reiserfs_write_lock(sb);
 	journal->j_cnode_free_orig = journal->j_cnode_free_list;
 	journal->j_cnode_free = journal->j_cnode_free_list ? num_cnodes : 0;
 	journal->j_cnode_used = 0;
diff --git a/fs/reiserfs/lock.c b/fs/reiserfs/lock.c
index ee2cfc0..b87aa2c 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 e296ff7..9d4dcf0 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 8c7033a..81f09fa 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);
@@ -443,7 +452,9 @@ static int lookup_and_delete_xattr(struct inode *inode, const char *name)
 	}
 
 	if (dentry->d_inode) {
+		reiserfs_write_lock(inode->i_sb);
 		err = xattr_unlink(xadir->d_inode, dentry);
+		reiserfs_write_unlock(inode->i_sb);
 		update_ctime(inode);
 	}
 
@@ -477,15 +488,24 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 	if (get_inode_sd_version(inode) == STAT_DATA_V1)
 		return -EOPNOTSUPP;
 
-	if (!buffer)
-		return lookup_and_delete_xattr(inode, name);
+	reiserfs_write_unlock(inode->i_sb);
+
+	if (!buffer) {
+		err = lookup_and_delete_xattr(inode, name);
+		reiserfs_write_lock(inode->i_sb);
+		return err;
+	}
 
 	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);
 
+	reiserfs_write_lock(inode->i_sb);
+
 	xahash = xattr_hash(buffer, buffer_size);
 	while (buffer_pos < buffer_size || buffer_pos == 0) {
 		size_t chunk;
@@ -540,8 +560,12 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 			.ia_size = buffer_size,
 			.ia_valid = ATTR_SIZE | ATTR_CTIME,
 		};
+
+		reiserfs_write_unlock(inode->i_sb);
 		mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
 		down_write(&dentry->d_inode->i_alloc_sem);
+		reiserfs_write_lock(inode->i_sb);
+
 		err = reiserfs_setattr(dentry, &newattrs);
 		up_write(&dentry->d_inode->i_alloc_sem);
 		mutex_unlock(&dentry->d_inode->i_mutex);
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index cc32e6a..dd20a78 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -455,7 +455,9 @@ int reiserfs_acl_chmod(struct inode *inode)
 		return 0;
 	}
 
+	reiserfs_write_unlock(inode->i_sb);
 	acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
+	reiserfs_write_lock(inode->i_sb);
 	if (!acl)
 		return 0;
 	if (IS_ERR(acl))
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index c117fa8..42d2135 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -544,6 +544,7 @@ error:
 error_rsb_inval:
 	ret = -EINVAL;
 error_rsb:
+	kfree(rsb);
 	return ret;
 }
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index f05f230..699f371 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 ca52e7b..cdd9377 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.
  */
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 618c270..e5a3d8e 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -54,6 +54,7 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/list_sort.h>
 #include "ubifs.h"
 
 /*
@@ -108,101 +109,6 @@ static int switch_gc_head(struct ubifs_info *c)
 }
 
 /**
- * list_sort - sort a list.
- * @priv: private data, passed to @cmp
- * @head: the list to sort
- * @cmp: the elements comparison function
- *
- * This function has been implemented by Mark J Roberts <mjr@znex.org>. It
- * implements "merge sort" which has O(nlog(n)) complexity. The list is sorted
- * in ascending order.
- *
- * The comparison function @cmp is supposed to return a negative value if @a is
- * than @b, and a positive value if @a is greater than @b. If @a and @b are
- * equivalent, then it does not matter what this function returns.
- */
-static void list_sort(void *priv, struct list_head *head,
-		      int (*cmp)(void *priv, struct list_head *a,
-				 struct list_head *b))
-{
-	struct list_head *p, *q, *e, *list, *tail, *oldhead;
-	int insize, nmerges, psize, qsize, i;
-
-	if (list_empty(head))
-		return;
-
-	list = head->next;
-	list_del(head);
-	insize = 1;
-	for (;;) {
-		p = oldhead = list;
-		list = tail = NULL;
-		nmerges = 0;
-
-		while (p) {
-			nmerges++;
-			q = p;
-			psize = 0;
-			for (i = 0; i < insize; i++) {
-				psize++;
-				q = q->next == oldhead ? NULL : q->next;
-				if (!q)
-					break;
-			}
-
-			qsize = insize;
-			while (psize > 0 || (qsize > 0 && q)) {
-				if (!psize) {
-					e = q;
-					q = q->next;
-					qsize--;
-					if (q == oldhead)
-						q = NULL;
-				} else if (!qsize || !q) {
-					e = p;
-					p = p->next;
-					psize--;
-					if (p == oldhead)
-						p = NULL;
-				} else if (cmp(priv, p, q) <= 0) {
-					e = p;
-					p = p->next;
-					psize--;
-					if (p == oldhead)
-						p = NULL;
-				} else {
-					e = q;
-					q = q->next;
-					qsize--;
-					if (q == oldhead)
-						q = NULL;
-				}
-				if (tail)
-					tail->next = e;
-				else
-					list = e;
-				e->prev = tail;
-				tail = e;
-			}
-			p = q;
-		}
-
-		tail->next = list;
-		list->prev = tail;
-
-		if (nmerges <= 1)
-			break;
-
-		insize *= 2;
-	}
-
-	head->next = list;
-	head->prev = list->prev;
-	list->prev->next = head;
-	list->prev = head;
-}
-
-/**
  * data_nodes_cmp - compare 2 data nodes.
  * @priv: UBIFS file-system description object
  * @a: first data node
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 2512125..883ca5a 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -251,8 +251,9 @@ xfs_set_mode(struct inode *inode, mode_t mode)
 	if (mode != inode->i_mode) {
 		struct iattr iattr;
 
-		iattr.ia_valid = ATTR_MODE;
+		iattr.ia_valid = ATTR_MODE | ATTR_CTIME;
 		iattr.ia_mode = mode;
+		iattr.ia_ctime = current_fs_time(inode->i_sb);
 
 		error = -xfs_setattr(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
 	}
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 09783cc..77414db 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -954,16 +954,14 @@ xfs_fs_destroy_inode(
 	ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
 
 	/*
-	 * If we have nothing to flush with this inode then complete the
-	 * teardown now, otherwise delay the flush operation.
+	 * We always use background reclaim here because even if the
+	 * inode is clean, it still may be under IO and hence we have
+	 * to take the flush lock. The background reclaim path handles
+	 * this more efficiently than we can here, so simply let background
+	 * reclaim tear down all inodes.
 	 */
-	if (!xfs_inode_clean(ip)) {
-		xfs_inode_set_reclaim_tag(ip);
-		return;
-	}
-
 out_reclaim:
-	xfs_ireclaim(ip);
+	xfs_inode_set_reclaim_tag(ip);
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 6fed97a..1f5e4bb 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -65,7 +65,6 @@ xfs_inode_ag_lookup(
 	 * as the tree is sparse and a gang lookup walks to find
 	 * the number of objects requested.
 	 */
-	read_lock(&pag->pag_ici_lock);
 	if (tag == XFS_ICI_NO_TAG) {
 		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
 				(void **)&ip, *first_index, 1);
@@ -74,7 +73,7 @@ xfs_inode_ag_lookup(
 				(void **)&ip, *first_index, 1, tag);
 	}
 	if (!nr_found)
-		goto unlock;
+		return NULL;
 
 	/*
 	 * Update the index for the next lookup. Catch overflows
@@ -84,13 +83,8 @@ xfs_inode_ag_lookup(
 	 */
 	*first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
 	if (*first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
-		goto unlock;
-
+		return NULL;
 	return ip;
-
-unlock:
-	read_unlock(&pag->pag_ici_lock);
-	return NULL;
 }
 
 STATIC int
@@ -100,7 +94,8 @@ xfs_inode_ag_walk(
 	int			(*execute)(struct xfs_inode *ip,
 					   struct xfs_perag *pag, int flags),
 	int			flags,
-	int			tag)
+	int			tag,
+	int			exclusive)
 {
 	struct xfs_perag	*pag = &mp->m_perag[ag];
 	uint32_t		first_index;
@@ -114,10 +109,20 @@ restart:
 		int		error = 0;
 		xfs_inode_t	*ip;
 
+		if (exclusive)
+			write_lock(&pag->pag_ici_lock);
+		else
+			read_lock(&pag->pag_ici_lock);
 		ip = xfs_inode_ag_lookup(mp, pag, &first_index, tag);
-		if (!ip)
+		if (!ip) {
+			if (exclusive)
+				write_unlock(&pag->pag_ici_lock);
+			else
+				read_unlock(&pag->pag_ici_lock);
 			break;
+		}
 
+		/* execute releases pag->pag_ici_lock */
 		error = execute(ip, pag, flags);
 		if (error == EAGAIN) {
 			skipped++;
@@ -125,9 +130,8 @@ restart:
 		}
 		if (error)
 			last_error = error;
-		/*
-		 * bail out if the filesystem is corrupted.
-		 */
+
+		/* bail out if the filesystem is corrupted.  */
 		if (error == EFSCORRUPTED)
 			break;
 
@@ -148,7 +152,8 @@ xfs_inode_ag_iterator(
 	int			(*execute)(struct xfs_inode *ip,
 					   struct xfs_perag *pag, int flags),
 	int			flags,
-	int			tag)
+	int			tag,
+	int			exclusive)
 {
 	int			error = 0;
 	int			last_error = 0;
@@ -157,7 +162,8 @@ xfs_inode_ag_iterator(
 	for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
 		if (!mp->m_perag[ag].pag_ici_init)
 			continue;
-		error = xfs_inode_ag_walk(mp, ag, execute, flags, tag);
+		error = xfs_inode_ag_walk(mp, ag, execute, flags, tag,
+						exclusive);
 		if (error) {
 			last_error = error;
 			if (error == EFSCORRUPTED)
@@ -174,30 +180,31 @@ xfs_sync_inode_valid(
 	struct xfs_perag	*pag)
 {
 	struct inode		*inode = VFS_I(ip);
+	int			error = EFSCORRUPTED;
 
 	/* nothing to sync during shutdown */
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-		read_unlock(&pag->pag_ici_lock);
-		return EFSCORRUPTED;
-	}
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		goto out_unlock;
 
-	/*
-	 * If we can't get a reference on the inode, it must be in reclaim.
-	 * Leave it for the reclaim code to flush. Also avoid inodes that
-	 * haven't been fully initialised.
-	 */
-	if (!igrab(inode)) {
-		read_unlock(&pag->pag_ici_lock);
-		return ENOENT;
-	}
-	read_unlock(&pag->pag_ici_lock);
+	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
+	error = ENOENT;
+	if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+		goto out_unlock;
 
-	if (is_bad_inode(inode) || xfs_iflags_test(ip, XFS_INEW)) {
+	/* If we can't grab the inode, it must on it's way to reclaim. */
+	if (!igrab(inode))
+		goto out_unlock;
+
+	if (is_bad_inode(inode)) {
 		IRELE(ip);
-		return ENOENT;
+		goto out_unlock;
 	}
 
-	return 0;
+	/* inode is valid */
+	error = 0;
+out_unlock:
+	read_unlock(&pag->pag_ici_lock);
+	return error;
 }
 
 STATIC int
@@ -282,7 +289,7 @@ xfs_sync_data(
 	ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);
 
 	error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags,
-				      XFS_ICI_NO_TAG);
+				      XFS_ICI_NO_TAG, 0);
 	if (error)
 		return XFS_ERROR(error);
 
@@ -304,7 +311,7 @@ xfs_sync_attr(
 	ASSERT((flags & ~SYNC_WAIT) == 0);
 
 	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags,
-				     XFS_ICI_NO_TAG);
+				     XFS_ICI_NO_TAG, 0);
 }
 
 STATIC int
@@ -664,60 +671,6 @@ xfs_syncd_stop(
 	kthread_stop(mp->m_sync_task);
 }
 
-STATIC int
-xfs_reclaim_inode(
-	xfs_inode_t	*ip,
-	int		sync_mode)
-{
-	xfs_perag_t	*pag = xfs_get_perag(ip->i_mount, ip->i_ino);
-
-	/* The hash lock here protects a thread in xfs_iget_core from
-	 * racing with us on linking the inode back with a vnode.
-	 * Once we have the XFS_IRECLAIM flag set it will not touch
-	 * us.
-	 */
-	write_lock(&pag->pag_ici_lock);
-	spin_lock(&ip->i_flags_lock);
-	if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
-	    !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
-		spin_unlock(&ip->i_flags_lock);
-		write_unlock(&pag->pag_ici_lock);
-		return -EAGAIN;
-	}
-	__xfs_iflags_set(ip, XFS_IRECLAIM);
-	spin_unlock(&ip->i_flags_lock);
-	write_unlock(&pag->pag_ici_lock);
-	xfs_put_perag(ip->i_mount, pag);
-
-	/*
-	 * If the inode is still dirty, then flush it out.  If the inode
-	 * is not in the AIL, then it will be OK to flush it delwri as
-	 * long as xfs_iflush() does not keep any references to the inode.
-	 * We leave that decision up to xfs_iflush() since it has the
-	 * knowledge of whether it's OK to simply do a delwri flush of
-	 * the inode or whether we need to wait until the inode is
-	 * pulled from the AIL.
-	 * We get the flush lock regardless, though, just to make sure
-	 * we don't free it while it is being flushed.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_iflock(ip);
-
-	/*
-	 * In the case of a forced shutdown we rely on xfs_iflush() to
-	 * wait for the inode to be unpinned before returning an error.
-	 */
-	if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
-		/* synchronize with xfs_iflush_done */
-		xfs_iflock(ip);
-		xfs_ifunlock(ip);
-	}
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	xfs_ireclaim(ip);
-	return 0;
-}
-
 void
 __xfs_inode_set_reclaim_tag(
 	struct xfs_perag	*pag,
@@ -760,19 +713,55 @@ __xfs_inode_clear_reclaim_tag(
 }
 
 STATIC int
-xfs_reclaim_inode_now(
+xfs_reclaim_inode(
 	struct xfs_inode	*ip,
 	struct xfs_perag	*pag,
-	int			flags)
+	int			sync_mode)
 {
-	/* ignore if already under reclaim */
-	if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
-		read_unlock(&pag->pag_ici_lock);
+	/*
+	 * The radix tree lock here protects a thread in xfs_iget from racing
+	 * with us starting reclaim on the inode.  Once we have the
+	 * XFS_IRECLAIM flag set it will not touch us.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+	if (__xfs_iflags_test(ip, XFS_IRECLAIM)) {
+		/* ignore as it is already under reclaim */
+		spin_unlock(&ip->i_flags_lock);
+		write_unlock(&pag->pag_ici_lock);
 		return 0;
 	}
-	read_unlock(&pag->pag_ici_lock);
+	__xfs_iflags_set(ip, XFS_IRECLAIM);
+	spin_unlock(&ip->i_flags_lock);
+	write_unlock(&pag->pag_ici_lock);
 
-	return xfs_reclaim_inode(ip, flags);
+	/*
+	 * If the inode is still dirty, then flush it out.  If the inode
+	 * is not in the AIL, then it will be OK to flush it delwri as
+	 * long as xfs_iflush() does not keep any references to the inode.
+	 * We leave that decision up to xfs_iflush() since it has the
+	 * knowledge of whether it's OK to simply do a delwri flush of
+	 * the inode or whether we need to wait until the inode is
+	 * pulled from the AIL.
+	 * We get the flush lock regardless, though, just to make sure
+	 * we don't free it while it is being flushed.
+	 */
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_iflock(ip);
+
+	/*
+	 * In the case of a forced shutdown we rely on xfs_iflush() to
+	 * wait for the inode to be unpinned before returning an error.
+	 */
+	if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
+		/* synchronize with xfs_iflush_done */
+		xfs_iflock(ip);
+		xfs_ifunlock(ip);
+	}
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_ireclaim(ip);
+	return 0;
 }
 
 int
@@ -780,6 +769,6 @@ xfs_reclaim_inodes(
 	xfs_mount_t	*mp,
 	int		mode)
 {
-	return xfs_inode_ag_iterator(mp, xfs_reclaim_inode_now, mode,
-					XFS_ICI_RECLAIM_TAG);
+	return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode,
+					XFS_ICI_RECLAIM_TAG, 1);
 }
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index a500b4d..ea932b4 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -54,6 +54,6 @@ void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
 int xfs_sync_inode_valid(struct xfs_inode *ip, struct xfs_perag *pag);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
-	int flags, int tag);
+	int flags, int tag, int write_lock);
 
 #endif
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index c40834b..c22a608 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -33,51 +33,55 @@ struct xfs_dquot;
 struct xlog_ticket;
 struct log;
 
+DECLARE_EVENT_CLASS(xfs_attr_list_class,
+	TP_PROTO(struct xfs_attr_list_context *ctx),
+	TP_ARGS(ctx),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(u32, hashval)
+		__field(u32, blkno)
+		__field(u32, offset)
+		__field(void *, alist)
+		__field(int, bufsize)
+		__field(int, count)
+		__field(int, firstu)
+		__field(int, dupcnt)
+		__field(int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ctx->dp)->i_sb->s_dev;
+		__entry->ino = ctx->dp->i_ino;
+		__entry->hashval = ctx->cursor->hashval;
+		__entry->blkno = ctx->cursor->blkno;
+		__entry->offset = ctx->cursor->offset;
+		__entry->alist = ctx->alist;
+		__entry->bufsize = ctx->bufsize;
+		__entry->count = ctx->count;
+		__entry->firstu = ctx->firstu;
+		__entry->flags = ctx->flags;
+	),
+	TP_printk("dev %d:%d ino 0x%llx cursor h/b/o 0x%x/0x%x/%u dupcnt %u "
+		  "alist 0x%p size %u count %u firstu %u flags %d %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		   __entry->ino,
+		   __entry->hashval,
+		   __entry->blkno,
+		   __entry->offset,
+		   __entry->dupcnt,
+		   __entry->alist,
+		   __entry->bufsize,
+		   __entry->count,
+		   __entry->firstu,
+		   __entry->flags,
+		   __print_flags(__entry->flags, "|", XFS_ATTR_FLAGS)
+	)
+)
+
 #define DEFINE_ATTR_LIST_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_attr_list_class, name, \
 	TP_PROTO(struct xfs_attr_list_context *ctx), \
-	TP_ARGS(ctx), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(u32, hashval) \
-		__field(u32, blkno) \
-		__field(u32, offset) \
-		__field(void *, alist) \
-		__field(int, bufsize) \
-		__field(int, count) \
-		__field(int, firstu) \
-		__field(int, dupcnt) \
-		__field(int, flags) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ctx->dp)->i_sb->s_dev; \
-		__entry->ino = ctx->dp->i_ino; \
-		__entry->hashval = ctx->cursor->hashval; \
-		__entry->blkno = ctx->cursor->blkno; \
-		__entry->offset = ctx->cursor->offset; \
-		__entry->alist = ctx->alist; \
-		__entry->bufsize = ctx->bufsize; \
-		__entry->count = ctx->count; \
-		__entry->firstu = ctx->firstu; \
-		__entry->flags = ctx->flags; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx cursor h/b/o 0x%x/0x%x/%u dupcnt %u " \
-		  "alist 0x%p size %u count %u firstu %u flags %d %s", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		   __entry->ino, \
-		   __entry->hashval, \
-		   __entry->blkno, \
-		   __entry->offset, \
-		   __entry->dupcnt, \
-		   __entry->alist, \
-		   __entry->bufsize, \
-		   __entry->count, \
-		   __entry->firstu, \
-		   __entry->flags, \
-		   __print_flags(__entry->flags, "|", XFS_ATTR_FLAGS) \
-	) \
-)
+	TP_ARGS(ctx))
 DEFINE_ATTR_LIST_EVENT(xfs_attr_list_sf);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_list_sf_all);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_list_leaf);
@@ -178,91 +182,99 @@ TRACE_EVENT(xfs_iext_insert,
 		  (char *)__entry->caller_ip)
 );
 
+DECLARE_EVENT_CLASS(xfs_bmap_class,
+	TP_PROTO(struct xfs_inode *ip, xfs_extnum_t idx, int state,
+		 unsigned long caller_ip),
+	TP_ARGS(ip, idx, state, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_extnum_t, idx)
+		__field(xfs_fileoff_t, startoff)
+		__field(xfs_fsblock_t, startblock)
+		__field(xfs_filblks_t, blockcount)
+		__field(xfs_exntst_t, state)
+		__field(int, bmap_state)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		struct xfs_ifork	*ifp = (state & BMAP_ATTRFORK) ?
+						ip->i_afp : &ip->i_df;
+		struct xfs_bmbt_irec	r;
+
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &r);
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->idx = idx;
+		__entry->startoff = r.br_startoff;
+		__entry->startblock = r.br_startblock;
+		__entry->blockcount = r.br_blockcount;
+		__entry->state = r.br_state;
+		__entry->bmap_state = state;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d ino 0x%llx state %s idx %ld "
+		  "offset %lld block %s count %lld flag %d caller %pf",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
+		  (long)__entry->idx,
+		  __entry->startoff,
+		  xfs_fmtfsblock(__entry->startblock),
+		  __entry->blockcount,
+		  __entry->state,
+		  (char *)__entry->caller_ip)
+)
+
 #define DEFINE_BMAP_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_bmap_class, name, \
 	TP_PROTO(struct xfs_inode *ip, xfs_extnum_t idx, int state, \
 		 unsigned long caller_ip), \
-	TP_ARGS(ip, idx, state, caller_ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(xfs_extnum_t, idx) \
-		__field(xfs_fileoff_t, startoff) \
-		__field(xfs_fsblock_t, startblock) \
-		__field(xfs_filblks_t, blockcount) \
-		__field(xfs_exntst_t, state) \
-		__field(int, bmap_state) \
-		__field(unsigned long, caller_ip) \
-	), \
-	TP_fast_assign( \
-		struct xfs_ifork	*ifp = (state & BMAP_ATTRFORK) ? \
-						ip->i_afp : &ip->i_df; \
-		struct xfs_bmbt_irec	r; \
-	\
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &r); \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->idx = idx; \
-		__entry->startoff = r.br_startoff; \
-		__entry->startblock = r.br_startblock; \
-		__entry->blockcount = r.br_blockcount; \
-		__entry->state = r.br_state; \
-		__entry->bmap_state = state; \
-		__entry->caller_ip = caller_ip; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx state %s idx %ld " \
-		  "offset %lld block %s count %lld flag %d caller %pf", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), \
-		  (long)__entry->idx, \
-		  __entry->startoff, \
-		  xfs_fmtfsblock(__entry->startblock), \
-		  __entry->blockcount, \
-		  __entry->state, \
-		  (char *)__entry->caller_ip) \
-)
-
+	TP_ARGS(ip, idx, state, caller_ip))
 DEFINE_BMAP_EVENT(xfs_iext_remove);
 DEFINE_BMAP_EVENT(xfs_bmap_pre_update);
 DEFINE_BMAP_EVENT(xfs_bmap_post_update);
 DEFINE_BMAP_EVENT(xfs_extlist);
 
-#define DEFINE_BUF_EVENT(tname) \
-TRACE_EVENT(tname, \
-	TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip), \
-	TP_ARGS(bp, caller_ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_daddr_t, bno) \
-		__field(size_t, buffer_length) \
-		__field(int, hold) \
-		__field(int, pincount) \
-		__field(unsigned, lockval) \
-		__field(unsigned, flags) \
-		__field(unsigned long, caller_ip) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = bp->b_target->bt_dev; \
-		__entry->bno = bp->b_bn; \
-		__entry->buffer_length = bp->b_buffer_length; \
-		__entry->hold = atomic_read(&bp->b_hold); \
-		__entry->pincount = atomic_read(&bp->b_pin_count); \
-		__entry->lockval = xfs_buf_lock_value(bp); \
-		__entry->flags = bp->b_flags; \
-		__entry->caller_ip = caller_ip; \
-	), \
-	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " \
-		  "lock %d flags %s caller %pf", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  (unsigned long long)__entry->bno, \
-		  __entry->buffer_length, \
-		  __entry->hold, \
-		  __entry->pincount, \
-		  __entry->lockval, \
-		  __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), \
-		  (void *)__entry->caller_ip) \
+DECLARE_EVENT_CLASS(xfs_buf_class,
+	TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip),
+	TP_ARGS(bp, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_daddr_t, bno)
+		__field(size_t, buffer_length)
+		__field(int, hold)
+		__field(int, pincount)
+		__field(unsigned, lockval)
+		__field(unsigned, flags)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = bp->b_target->bt_dev;
+		__entry->bno = bp->b_bn;
+		__entry->buffer_length = bp->b_buffer_length;
+		__entry->hold = atomic_read(&bp->b_hold);
+		__entry->pincount = atomic_read(&bp->b_pin_count);
+		__entry->lockval = xfs_buf_lock_value(bp);
+		__entry->flags = bp->b_flags;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+		  "lock %d flags %s caller %pf",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->bno,
+		  __entry->buffer_length,
+		  __entry->hold,
+		  __entry->pincount,
+		  __entry->lockval,
+		  __print_flags(__entry->flags, "|", XFS_BUF_FLAGS),
+		  (void *)__entry->caller_ip)
 )
+
+#define DEFINE_BUF_EVENT(name) \
+DEFINE_EVENT(xfs_buf_class, name, \
+	TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip), \
+	TP_ARGS(bp, caller_ip))
 DEFINE_BUF_EVENT(xfs_buf_init);
 DEFINE_BUF_EVENT(xfs_buf_free);
 DEFINE_BUF_EVENT(xfs_buf_hold);
@@ -299,41 +311,45 @@ DEFINE_BUF_EVENT(xfs_reset_dqcounts);
 DEFINE_BUF_EVENT(xfs_inode_item_push);
 
 /* pass flags explicitly */
-#define DEFINE_BUF_FLAGS_EVENT(tname) \
-TRACE_EVENT(tname, \
-	TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip), \
-	TP_ARGS(bp, flags, caller_ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_daddr_t, bno) \
-		__field(size_t, buffer_length) \
-		__field(int, hold) \
-		__field(int, pincount) \
-		__field(unsigned, lockval) \
-		__field(unsigned, flags) \
-		__field(unsigned long, caller_ip) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = bp->b_target->bt_dev; \
-		__entry->bno = bp->b_bn; \
-		__entry->buffer_length = bp->b_buffer_length; \
-		__entry->flags = flags; \
-		__entry->hold = atomic_read(&bp->b_hold); \
-		__entry->pincount = atomic_read(&bp->b_pin_count); \
-		__entry->lockval = xfs_buf_lock_value(bp); \
-		__entry->caller_ip = caller_ip; \
-	), \
-	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " \
-		  "lock %d flags %s caller %pf", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  (unsigned long long)__entry->bno, \
-		  __entry->buffer_length, \
-		  __entry->hold, \
-		  __entry->pincount, \
-		  __entry->lockval, \
-		  __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), \
-		  (void *)__entry->caller_ip) \
+DECLARE_EVENT_CLASS(xfs_buf_flags_class,
+	TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip),
+	TP_ARGS(bp, flags, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_daddr_t, bno)
+		__field(size_t, buffer_length)
+		__field(int, hold)
+		__field(int, pincount)
+		__field(unsigned, lockval)
+		__field(unsigned, flags)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = bp->b_target->bt_dev;
+		__entry->bno = bp->b_bn;
+		__entry->buffer_length = bp->b_buffer_length;
+		__entry->flags = flags;
+		__entry->hold = atomic_read(&bp->b_hold);
+		__entry->pincount = atomic_read(&bp->b_pin_count);
+		__entry->lockval = xfs_buf_lock_value(bp);
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+		  "lock %d flags %s caller %pf",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->bno,
+		  __entry->buffer_length,
+		  __entry->hold,
+		  __entry->pincount,
+		  __entry->lockval,
+		  __print_flags(__entry->flags, "|", XFS_BUF_FLAGS),
+		  (void *)__entry->caller_ip)
 )
+
+#define DEFINE_BUF_FLAGS_EVENT(name) \
+DEFINE_EVENT(xfs_buf_flags_class, name, \
+	TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip), \
+	TP_ARGS(bp, flags, caller_ip))
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_find);
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_get);
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_read);
@@ -376,55 +392,58 @@ TRACE_EVENT(xfs_buf_ioerror,
 		  (void *)__entry->caller_ip)
 );
 
-#define DEFINE_BUF_ITEM_EVENT(tname) \
-TRACE_EVENT(tname, \
-	TP_PROTO(struct xfs_buf_log_item *bip), \
-	TP_ARGS(bip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_daddr_t, buf_bno) \
-		__field(size_t, buf_len) \
-		__field(int, buf_hold) \
-		__field(int, buf_pincount) \
-		__field(int, buf_lockval) \
-		__field(unsigned, buf_flags) \
-		__field(unsigned, bli_recur) \
-		__field(int, bli_refcount) \
-		__field(unsigned, bli_flags) \
-		__field(void *, li_desc) \
-		__field(unsigned, li_flags) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = bip->bli_buf->b_target->bt_dev; \
-		__entry->bli_flags = bip->bli_flags; \
-		__entry->bli_recur = bip->bli_recur; \
-		__entry->bli_refcount = atomic_read(&bip->bli_refcount); \
-		__entry->buf_bno = bip->bli_buf->b_bn; \
-		__entry->buf_len = bip->bli_buf->b_buffer_length; \
-		__entry->buf_flags = bip->bli_buf->b_flags; \
-		__entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); \
-		__entry->buf_pincount = \
-			atomic_read(&bip->bli_buf->b_pin_count); \
-		__entry->buf_lockval = xfs_buf_lock_value(bip->bli_buf); \
-		__entry->li_desc = bip->bli_item.li_desc; \
-		__entry->li_flags = bip->bli_item.li_flags; \
-	), \
-	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " \
-		  "lock %d flags %s recur %d refcount %d bliflags %s " \
-		  "lidesc 0x%p liflags %s", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  (unsigned long long)__entry->buf_bno, \
-		  __entry->buf_len, \
-		  __entry->buf_hold, \
-		  __entry->buf_pincount, \
-		  __entry->buf_lockval, \
-		  __print_flags(__entry->buf_flags, "|", XFS_BUF_FLAGS), \
-		  __entry->bli_recur, \
-		  __entry->bli_refcount, \
-		  __print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS), \
-		  __entry->li_desc, \
-		  __print_flags(__entry->li_flags, "|", XFS_LI_FLAGS)) \
+DECLARE_EVENT_CLASS(xfs_buf_item_class,
+	TP_PROTO(struct xfs_buf_log_item *bip),
+	TP_ARGS(bip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_daddr_t, buf_bno)
+		__field(size_t, buf_len)
+		__field(int, buf_hold)
+		__field(int, buf_pincount)
+		__field(int, buf_lockval)
+		__field(unsigned, buf_flags)
+		__field(unsigned, bli_recur)
+		__field(int, bli_refcount)
+		__field(unsigned, bli_flags)
+		__field(void *, li_desc)
+		__field(unsigned, li_flags)
+	),
+	TP_fast_assign(
+		__entry->dev = bip->bli_buf->b_target->bt_dev;
+		__entry->bli_flags = bip->bli_flags;
+		__entry->bli_recur = bip->bli_recur;
+		__entry->bli_refcount = atomic_read(&bip->bli_refcount);
+		__entry->buf_bno = bip->bli_buf->b_bn;
+		__entry->buf_len = bip->bli_buf->b_buffer_length;
+		__entry->buf_flags = bip->bli_buf->b_flags;
+		__entry->buf_hold = atomic_read(&bip->bli_buf->b_hold);
+		__entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count);
+		__entry->buf_lockval = xfs_buf_lock_value(bip->bli_buf);
+		__entry->li_desc = bip->bli_item.li_desc;
+		__entry->li_flags = bip->bli_item.li_flags;
+	),
+	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+		  "lock %d flags %s recur %d refcount %d bliflags %s "
+		  "lidesc 0x%p liflags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->buf_bno,
+		  __entry->buf_len,
+		  __entry->buf_hold,
+		  __entry->buf_pincount,
+		  __entry->buf_lockval,
+		  __print_flags(__entry->buf_flags, "|", XFS_BUF_FLAGS),
+		  __entry->bli_recur,
+		  __entry->bli_refcount,
+		  __print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS),
+		  __entry->li_desc,
+		  __print_flags(__entry->li_flags, "|", XFS_LI_FLAGS))
 )
+
+#define DEFINE_BUF_ITEM_EVENT(name) \
+DEFINE_EVENT(xfs_buf_item_class, name, \
+	TP_PROTO(struct xfs_buf_log_item *bip), \
+	TP_ARGS(bip))
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format);
@@ -450,78 +469,90 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
 
+DECLARE_EVENT_CLASS(xfs_lock_class,
+	TP_PROTO(struct xfs_inode *ip, unsigned lock_flags,
+		 unsigned long caller_ip),
+	TP_ARGS(ip,  lock_flags, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, lock_flags)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->lock_flags = lock_flags;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d ino 0x%llx flags %s caller %pf",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_flags(__entry->lock_flags, "|", XFS_LOCK_FLAGS),
+		  (void *)__entry->caller_ip)
+)
+
 #define DEFINE_LOCK_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_lock_class, name, \
 	TP_PROTO(struct xfs_inode *ip, unsigned lock_flags, \
 		 unsigned long caller_ip), \
-	TP_ARGS(ip,  lock_flags, caller_ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(int, lock_flags) \
-		__field(unsigned long, caller_ip) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->lock_flags = lock_flags; \
-		__entry->caller_ip = caller_ip; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx flags %s caller %pf", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __print_flags(__entry->lock_flags, "|", XFS_LOCK_FLAGS), \
-		  (void *)__entry->caller_ip) \
-)
-
+	TP_ARGS(ip,  lock_flags, caller_ip))
 DEFINE_LOCK_EVENT(xfs_ilock);
 DEFINE_LOCK_EVENT(xfs_ilock_nowait);
 DEFINE_LOCK_EVENT(xfs_ilock_demote);
 DEFINE_LOCK_EVENT(xfs_iunlock);
 
+DECLARE_EVENT_CLASS(xfs_iget_class,
+	TP_PROTO(struct xfs_inode *ip),
+	TP_ARGS(ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+	),
+	TP_printk("dev %d:%d ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino)
+)
+
 #define DEFINE_IGET_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_iget_class, name, \
 	TP_PROTO(struct xfs_inode *ip), \
-	TP_ARGS(ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino) \
-)
+	TP_ARGS(ip))
 DEFINE_IGET_EVENT(xfs_iget_skip);
 DEFINE_IGET_EVENT(xfs_iget_reclaim);
 DEFINE_IGET_EVENT(xfs_iget_found);
 DEFINE_IGET_EVENT(xfs_iget_alloc);
 
+DECLARE_EVENT_CLASS(xfs_inode_class,
+	TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),
+	TP_ARGS(ip, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, count)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->count = atomic_read(&VFS_I(ip)->i_count);
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d ino 0x%llx count %d caller %pf",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->count,
+		  (char *)__entry->caller_ip)
+)
+
 #define DEFINE_INODE_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_inode_class, name, \
 	TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), \
-	TP_ARGS(ip, caller_ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(int, count) \
-		__field(unsigned long, caller_ip) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->count = atomic_read(&VFS_I(ip)->i_count); \
-		__entry->caller_ip = caller_ip; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx count %d caller %pf", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->count, \
-		  (char *)__entry->caller_ip) \
-)
+	TP_ARGS(ip, caller_ip))
 DEFINE_INODE_EVENT(xfs_ihold);
 DEFINE_INODE_EVENT(xfs_irele);
 /* the old xfs_itrace_entry tracer - to be replaced by s.th. in the VFS */
@@ -529,55 +560,59 @@ DEFINE_INODE_EVENT(xfs_inode);
 #define xfs_itrace_entry(ip)    \
 	trace_xfs_inode(ip, _THIS_IP_)
 
-#define DEFINE_DQUOT_EVENT(tname) \
-TRACE_EVENT(tname, \
-	TP_PROTO(struct xfs_dquot *dqp), \
-	TP_ARGS(dqp), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(__be32, id) \
-		__field(unsigned, flags) \
-		__field(unsigned, nrefs) \
-		__field(unsigned long long, res_bcount) \
-		__field(unsigned long long, bcount) \
-		__field(unsigned long long, icount) \
-		__field(unsigned long long, blk_hardlimit) \
-		__field(unsigned long long, blk_softlimit) \
-		__field(unsigned long long, ino_hardlimit) \
-		__field(unsigned long long, ino_softlimit) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = dqp->q_mount->m_super->s_dev; \
-		__entry->id = dqp->q_core.d_id; \
-		__entry->flags = dqp->dq_flags; \
-		__entry->nrefs = dqp->q_nrefs; \
-		__entry->res_bcount = dqp->q_res_bcount; \
-		__entry->bcount = be64_to_cpu(dqp->q_core.d_bcount); \
-		__entry->icount = be64_to_cpu(dqp->q_core.d_icount); \
-		__entry->blk_hardlimit = \
-			be64_to_cpu(dqp->q_core.d_blk_hardlimit); \
-		__entry->blk_softlimit = \
-			be64_to_cpu(dqp->q_core.d_blk_softlimit); \
-		__entry->ino_hardlimit = \
-			be64_to_cpu(dqp->q_core.d_ino_hardlimit); \
-		__entry->ino_softlimit = \
-			be64_to_cpu(dqp->q_core.d_ino_softlimit); \
+DECLARE_EVENT_CLASS(xfs_dquot_class,
+	TP_PROTO(struct xfs_dquot *dqp),
+	TP_ARGS(dqp),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(__be32, id)
+		__field(unsigned, flags)
+		__field(unsigned, nrefs)
+		__field(unsigned long long, res_bcount)
+		__field(unsigned long long, bcount)
+		__field(unsigned long long, icount)
+		__field(unsigned long long, blk_hardlimit)
+		__field(unsigned long long, blk_softlimit)
+		__field(unsigned long long, ino_hardlimit)
+		__field(unsigned long long, ino_softlimit)
 	), \
-	TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx " \
-		  "bcnt 0x%llx [hard 0x%llx | soft 0x%llx] " \
-		  "icnt 0x%llx [hard 0x%llx | soft 0x%llx]", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  be32_to_cpu(__entry->id), \
-		  __print_flags(__entry->flags, "|", XFS_DQ_FLAGS), \
-		  __entry->nrefs, \
-		  __entry->res_bcount, \
-		  __entry->bcount, \
-		  __entry->blk_hardlimit, \
-		  __entry->blk_softlimit, \
-		  __entry->icount, \
-		  __entry->ino_hardlimit, \
-		  __entry->ino_softlimit) \
+	TP_fast_assign(
+		__entry->dev = dqp->q_mount->m_super->s_dev;
+		__entry->id = dqp->q_core.d_id;
+		__entry->flags = dqp->dq_flags;
+		__entry->nrefs = dqp->q_nrefs;
+		__entry->res_bcount = dqp->q_res_bcount;
+		__entry->bcount = be64_to_cpu(dqp->q_core.d_bcount);
+		__entry->icount = be64_to_cpu(dqp->q_core.d_icount);
+		__entry->blk_hardlimit =
+			be64_to_cpu(dqp->q_core.d_blk_hardlimit);
+		__entry->blk_softlimit =
+			be64_to_cpu(dqp->q_core.d_blk_softlimit);
+		__entry->ino_hardlimit =
+			be64_to_cpu(dqp->q_core.d_ino_hardlimit);
+		__entry->ino_softlimit =
+			be64_to_cpu(dqp->q_core.d_ino_softlimit);
+	),
+	TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx "
+		  "bcnt 0x%llx [hard 0x%llx | soft 0x%llx] "
+		  "icnt 0x%llx [hard 0x%llx | soft 0x%llx]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  be32_to_cpu(__entry->id),
+		  __print_flags(__entry->flags, "|", XFS_DQ_FLAGS),
+		  __entry->nrefs,
+		  __entry->res_bcount,
+		  __entry->bcount,
+		  __entry->blk_hardlimit,
+		  __entry->blk_softlimit,
+		  __entry->icount,
+		  __entry->ino_hardlimit,
+		  __entry->ino_softlimit)
 )
+
+#define DEFINE_DQUOT_EVENT(name) \
+DEFINE_EVENT(xfs_dquot_class, name, \
+	TP_PROTO(struct xfs_dquot *dqp), \
+	TP_ARGS(dqp))
 DEFINE_DQUOT_EVENT(xfs_dqadjust);
 DEFINE_DQUOT_EVENT(xfs_dqshake_dirty);
 DEFINE_DQUOT_EVENT(xfs_dqshake_unlink);
@@ -610,72 +645,75 @@ DEFINE_DQUOT_EVENT(xfs_dqflush_done);
 DEFINE_IGET_EVENT(xfs_dquot_dqalloc);
 DEFINE_IGET_EVENT(xfs_dquot_dqdetach);
 
+DECLARE_EVENT_CLASS(xfs_loggrant_class,
+	TP_PROTO(struct log *log, struct xlog_ticket *tic),
+	TP_ARGS(log, tic),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned, trans_type)
+		__field(char, ocnt)
+		__field(char, cnt)
+		__field(int, curr_res)
+		__field(int, unit_res)
+		__field(unsigned int, flags)
+		__field(void *, reserve_headq)
+		__field(void *, write_headq)
+		__field(int, grant_reserve_cycle)
+		__field(int, grant_reserve_bytes)
+		__field(int, grant_write_cycle)
+		__field(int, grant_write_bytes)
+		__field(int, curr_cycle)
+		__field(int, curr_block)
+		__field(xfs_lsn_t, tail_lsn)
+	),
+	TP_fast_assign(
+		__entry->dev = log->l_mp->m_super->s_dev;
+		__entry->trans_type = tic->t_trans_type;
+		__entry->ocnt = tic->t_ocnt;
+		__entry->cnt = tic->t_cnt;
+		__entry->curr_res = tic->t_curr_res;
+		__entry->unit_res = tic->t_unit_res;
+		__entry->flags = tic->t_flags;
+		__entry->reserve_headq = log->l_reserve_headq;
+		__entry->write_headq = log->l_write_headq;
+		__entry->grant_reserve_cycle = log->l_grant_reserve_cycle;
+		__entry->grant_reserve_bytes = log->l_grant_reserve_bytes;
+		__entry->grant_write_cycle = log->l_grant_write_cycle;
+		__entry->grant_write_bytes = log->l_grant_write_bytes;
+		__entry->curr_cycle = log->l_curr_cycle;
+		__entry->curr_block = log->l_curr_block;
+		__entry->tail_lsn = log->l_tail_lsn;
+	),
+	TP_printk("dev %d:%d type %s t_ocnt %u t_cnt %u t_curr_res %u "
+		  "t_unit_res %u t_flags %s reserve_headq 0x%p "
+		  "write_headq 0x%p grant_reserve_cycle %d "
+		  "grant_reserve_bytes %d grant_write_cycle %d "
+		  "grant_write_bytes %d curr_cycle %d curr_block %d "
+		  "tail_cycle %d tail_block %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->trans_type, XFS_TRANS_TYPES),
+		  __entry->ocnt,
+		  __entry->cnt,
+		  __entry->curr_res,
+		  __entry->unit_res,
+		  __print_flags(__entry->flags, "|", XLOG_TIC_FLAGS),
+		  __entry->reserve_headq,
+		  __entry->write_headq,
+		  __entry->grant_reserve_cycle,
+		  __entry->grant_reserve_bytes,
+		  __entry->grant_write_cycle,
+		  __entry->grant_write_bytes,
+		  __entry->curr_cycle,
+		  __entry->curr_block,
+		  CYCLE_LSN(__entry->tail_lsn),
+		  BLOCK_LSN(__entry->tail_lsn)
+	)
+)
 
-#define DEFINE_LOGGRANT_EVENT(tname) \
-TRACE_EVENT(tname, \
+#define DEFINE_LOGGRANT_EVENT(name) \
+DEFINE_EVENT(xfs_loggrant_class, name, \
 	TP_PROTO(struct log *log, struct xlog_ticket *tic), \
-	TP_ARGS(log, tic), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(unsigned, trans_type) \
-		__field(char, ocnt) \
-		__field(char, cnt) \
-		__field(int, curr_res) \
-		__field(int, unit_res) \
-		__field(unsigned int, flags) \
-		__field(void *, reserve_headq) \
-		__field(void *, write_headq) \
-		__field(int, grant_reserve_cycle) \
-		__field(int, grant_reserve_bytes) \
-		__field(int, grant_write_cycle) \
-		__field(int, grant_write_bytes) \
-		__field(int, curr_cycle) \
-		__field(int, curr_block) \
-		__field(xfs_lsn_t, tail_lsn) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = log->l_mp->m_super->s_dev; \
-		__entry->trans_type = tic->t_trans_type; \
-		__entry->ocnt = tic->t_ocnt; \
-		__entry->cnt = tic->t_cnt; \
-		__entry->curr_res = tic->t_curr_res; \
-		__entry->unit_res = tic->t_unit_res; \
-		__entry->flags = tic->t_flags; \
-		__entry->reserve_headq = log->l_reserve_headq; \
-		__entry->write_headq = log->l_write_headq; \
-		__entry->grant_reserve_cycle = log->l_grant_reserve_cycle; \
-		__entry->grant_reserve_bytes = log->l_grant_reserve_bytes; \
-		__entry->grant_write_cycle = log->l_grant_write_cycle; \
-		__entry->grant_write_bytes = log->l_grant_write_bytes; \
-		__entry->curr_cycle = log->l_curr_cycle; \
-		__entry->curr_block = log->l_curr_block; \
-		__entry->tail_lsn = log->l_tail_lsn; \
-	), \
-	TP_printk("dev %d:%d type %s t_ocnt %u t_cnt %u t_curr_res %u " \
-		  "t_unit_res %u t_flags %s reserve_headq 0x%p " \
-		  "write_headq 0x%p grant_reserve_cycle %d " \
-		  "grant_reserve_bytes %d grant_write_cycle %d " \
-		  "grant_write_bytes %d curr_cycle %d curr_block %d " \
-		  "tail_cycle %d tail_block %d", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __print_symbolic(__entry->trans_type, XFS_TRANS_TYPES), \
-		  __entry->ocnt, \
-		  __entry->cnt, \
-		  __entry->curr_res, \
-		  __entry->unit_res, \
-		  __print_flags(__entry->flags, "|", XLOG_TIC_FLAGS), \
-		  __entry->reserve_headq, \
-		  __entry->write_headq, \
-		  __entry->grant_reserve_cycle, \
-		  __entry->grant_reserve_bytes, \
-		  __entry->grant_write_cycle, \
-		  __entry->grant_write_bytes, \
-		  __entry->curr_cycle, \
-		  __entry->curr_block, \
-		  CYCLE_LSN(__entry->tail_lsn), \
-		  BLOCK_LSN(__entry->tail_lsn) \
-	) \
-)
+	TP_ARGS(log, tic))
 DEFINE_LOGGRANT_EVENT(xfs_log_done_nonperm);
 DEFINE_LOGGRANT_EVENT(xfs_log_done_perm);
 DEFINE_LOGGRANT_EVENT(xfs_log_reserve);
@@ -815,7 +853,7 @@ TRACE_EVENT(name, \
 	), \
 	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
 		  "offset 0x%llx count %zd flags %s " \
-		  "startoff 0x%llx startblock 0x%llx blockcount 0x%llx", \
+		  "startoff 0x%llx startblock %s blockcount 0x%llx", \
 		  MAJOR(__entry->dev), MINOR(__entry->dev), \
 		  __entry->ino, \
 		  __entry->size, \
@@ -824,7 +862,7 @@ TRACE_EVENT(name, \
 		  __entry->count, \
 		  __print_flags(__entry->flags, "|", BMAPI_FLAGS), \
 		  __entry->startoff, \
-		  __entry->startblock, \
+		  xfs_fmtfsblock(__entry->startblock), \
 		  __entry->blockcount) \
 )
 DEFINE_IOMAP_EVENT(xfs_iomap_enter);
@@ -897,28 +935,32 @@ TRACE_EVENT(xfs_itruncate_start,
 		  __entry->toss_finish)
 );
 
+DECLARE_EVENT_CLASS(xfs_itrunc_class,
+	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
+	TP_ARGS(ip, new_size),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_fsize_t, size)
+		__field(xfs_fsize_t, new_size)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->size = ip->i_d.di_size;
+		__entry->new_size = new_size;
+	),
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->new_size)
+)
+
 #define DEFINE_ITRUNC_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_itrunc_class, name, \
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), \
-	TP_ARGS(ip, new_size), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(xfs_fsize_t, size) \
-		__field(xfs_fsize_t, new_size) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->size = ip->i_d.di_size; \
-		__entry->new_size = new_size; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->size, \
-		  __entry->new_size) \
-)
+	TP_ARGS(ip, new_size))
 DEFINE_ITRUNC_EVENT(xfs_itruncate_finish_start);
 DEFINE_ITRUNC_EVENT(xfs_itruncate_finish_end);
 
@@ -1037,28 +1079,28 @@ TRACE_EVENT(xfs_alloc_unbusy,
 
 TRACE_EVENT(xfs_alloc_busysearch,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
-		 xfs_extlen_t len, int found),
-	TP_ARGS(mp, agno, agbno, len, found),
+		 xfs_extlen_t len, xfs_lsn_t lsn),
+	TP_ARGS(mp, agno, agbno, len, lsn),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_agblock_t, agbno)
 		__field(xfs_extlen_t, len)
-		__field(int, found)
+		__field(xfs_lsn_t, lsn)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
-		__entry->found = found;
+		__entry->lsn = lsn;
 	),
-	TP_printk("dev %d:%d agno %u agbno %u len %u %s",
+	TP_printk("dev %d:%d agno %u agbno %u len %u force lsn 0x%llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->agbno,
 		  __entry->len,
-		  __print_symbolic(__entry->found, XFS_BUSY_STATES))
+		  __entry->lsn)
 );
 
 TRACE_EVENT(xfs_agf,
@@ -1152,77 +1194,80 @@ TRACE_EVENT(xfs_free_extent,
 
 );
 
-#define DEFINE_ALLOC_EVENT(name) \
-TRACE_EVENT(name, \
-	TP_PROTO(struct xfs_alloc_arg *args), \
-	TP_ARGS(args), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_agnumber_t, agno) \
-		__field(xfs_agblock_t, agbno) \
-		__field(xfs_extlen_t, minlen) \
-		__field(xfs_extlen_t, maxlen) \
-		__field(xfs_extlen_t, mod) \
-		__field(xfs_extlen_t, prod) \
-		__field(xfs_extlen_t, minleft) \
-		__field(xfs_extlen_t, total) \
-		__field(xfs_extlen_t, alignment) \
-		__field(xfs_extlen_t, minalignslop) \
-		__field(xfs_extlen_t, len) \
-		__field(short, type) \
-		__field(short, otype) \
-		__field(char, wasdel) \
-		__field(char, wasfromfl) \
-		__field(char, isfl) \
-		__field(char, userdata) \
-		__field(xfs_fsblock_t, firstblock) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = args->mp->m_super->s_dev; \
-		__entry->agno = args->agno; \
-		__entry->agbno = args->agbno; \
-		__entry->minlen = args->minlen; \
-		__entry->maxlen = args->maxlen; \
-		__entry->mod = args->mod; \
-		__entry->prod = args->prod; \
-		__entry->minleft = args->minleft; \
-		__entry->total = args->total; \
-		__entry->alignment = args->alignment; \
-		__entry->minalignslop = args->minalignslop; \
-		__entry->len = args->len; \
-		__entry->type = args->type; \
-		__entry->otype = args->otype; \
-		__entry->wasdel = args->wasdel; \
-		__entry->wasfromfl = args->wasfromfl; \
-		__entry->isfl = args->isfl; \
-		__entry->userdata = args->userdata; \
-		__entry->firstblock = args->firstblock; \
-	), \
-	TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u " \
-		  "prod %u minleft %u total %u alignment %u minalignslop %u " \
-		  "len %u type %s otype %s wasdel %d wasfromfl %d isfl %d " \
-		  "userdata %d firstblock 0x%llx", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->agno, \
-		  __entry->agbno, \
-		  __entry->minlen, \
-		  __entry->maxlen, \
-		  __entry->mod, \
-		  __entry->prod, \
-		  __entry->minleft, \
-		  __entry->total, \
-		  __entry->alignment, \
-		  __entry->minalignslop, \
-		  __entry->len, \
-		  __print_symbolic(__entry->type, XFS_ALLOC_TYPES), \
-		  __print_symbolic(__entry->otype, XFS_ALLOC_TYPES), \
-		  __entry->wasdel, \
-		  __entry->wasfromfl, \
-		  __entry->isfl, \
-		  __entry->userdata, \
-		  __entry->firstblock) \
+DECLARE_EVENT_CLASS(xfs_alloc_class,
+	TP_PROTO(struct xfs_alloc_arg *args),
+	TP_ARGS(args),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, minlen)
+		__field(xfs_extlen_t, maxlen)
+		__field(xfs_extlen_t, mod)
+		__field(xfs_extlen_t, prod)
+		__field(xfs_extlen_t, minleft)
+		__field(xfs_extlen_t, total)
+		__field(xfs_extlen_t, alignment)
+		__field(xfs_extlen_t, minalignslop)
+		__field(xfs_extlen_t, len)
+		__field(short, type)
+		__field(short, otype)
+		__field(char, wasdel)
+		__field(char, wasfromfl)
+		__field(char, isfl)
+		__field(char, userdata)
+		__field(xfs_fsblock_t, firstblock)
+	),
+	TP_fast_assign(
+		__entry->dev = args->mp->m_super->s_dev;
+		__entry->agno = args->agno;
+		__entry->agbno = args->agbno;
+		__entry->minlen = args->minlen;
+		__entry->maxlen = args->maxlen;
+		__entry->mod = args->mod;
+		__entry->prod = args->prod;
+		__entry->minleft = args->minleft;
+		__entry->total = args->total;
+		__entry->alignment = args->alignment;
+		__entry->minalignslop = args->minalignslop;
+		__entry->len = args->len;
+		__entry->type = args->type;
+		__entry->otype = args->otype;
+		__entry->wasdel = args->wasdel;
+		__entry->wasfromfl = args->wasfromfl;
+		__entry->isfl = args->isfl;
+		__entry->userdata = args->userdata;
+		__entry->firstblock = args->firstblock;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u "
+		  "prod %u minleft %u total %u alignment %u minalignslop %u "
+		  "len %u type %s otype %s wasdel %d wasfromfl %d isfl %d "
+		  "userdata %d firstblock 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->minlen,
+		  __entry->maxlen,
+		  __entry->mod,
+		  __entry->prod,
+		  __entry->minleft,
+		  __entry->total,
+		  __entry->alignment,
+		  __entry->minalignslop,
+		  __entry->len,
+		  __print_symbolic(__entry->type, XFS_ALLOC_TYPES),
+		  __print_symbolic(__entry->otype, XFS_ALLOC_TYPES),
+		  __entry->wasdel,
+		  __entry->wasfromfl,
+		  __entry->isfl,
+		  __entry->userdata,
+		  __entry->firstblock)
 )
 
+#define DEFINE_ALLOC_EVENT(name) \
+DEFINE_EVENT(xfs_alloc_class, name, \
+	TP_PROTO(struct xfs_alloc_arg *args), \
+	TP_ARGS(args))
 DEFINE_ALLOC_EVENT(xfs_alloc_exact_done);
 DEFINE_ALLOC_EVENT(xfs_alloc_exact_error);
 DEFINE_ALLOC_EVENT(xfs_alloc_near_nominleft);
@@ -1245,92 +1290,100 @@ DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_allfailed);
 
-#define DEFINE_DIR2_TRACE(tname) \
-TRACE_EVENT(tname, \
+DECLARE_EVENT_CLASS(xfs_dir2_class,
+	TP_PROTO(struct xfs_da_args *args),
+	TP_ARGS(args),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__dynamic_array(char, name, args->namelen)
+		__field(int, namelen)
+		__field(xfs_dahash_t, hashval)
+		__field(xfs_ino_t, inumber)
+		__field(int, op_flags)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(args->dp)->i_sb->s_dev;
+		__entry->ino = args->dp->i_ino;
+		if (args->namelen)
+			memcpy(__get_str(name), args->name, args->namelen);
+		__entry->namelen = args->namelen;
+		__entry->hashval = args->hashval;
+		__entry->inumber = args->inumber;
+		__entry->op_flags = args->op_flags;
+	),
+	TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d hashval 0x%x "
+		  "inumber 0x%llx op_flags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->namelen,
+		  __entry->namelen ? __get_str(name) : NULL,
+		  __entry->namelen,
+		  __entry->hashval,
+		  __entry->inumber,
+		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS))
+)
+
+#define DEFINE_DIR2_EVENT(name) \
+DEFINE_EVENT(xfs_dir2_class, name, \
 	TP_PROTO(struct xfs_da_args *args), \
-	TP_ARGS(args), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__dynamic_array(char, name, args->namelen) \
-		__field(int, namelen) \
-		__field(xfs_dahash_t, hashval) \
-		__field(xfs_ino_t, inumber) \
-		__field(int, op_flags) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(args->dp)->i_sb->s_dev; \
-		__entry->ino = args->dp->i_ino; \
-		if (args->namelen) \
-			memcpy(__get_str(name), args->name, args->namelen); \
-		__entry->namelen = args->namelen; \
-		__entry->hashval = args->hashval; \
-		__entry->inumber = args->inumber; \
-		__entry->op_flags = args->op_flags; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d hashval 0x%x " \
-		  "inumber 0x%llx op_flags %s", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->namelen, \
-		  __entry->namelen ? __get_str(name) : NULL, \
-		  __entry->namelen, \
-		  __entry->hashval, \
-		  __entry->inumber, \
-		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS)) \
+	TP_ARGS(args))
+DEFINE_DIR2_EVENT(xfs_dir2_sf_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_create);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_toino4);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_toino8);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_to_block);
+DEFINE_DIR2_EVENT(xfs_dir2_block_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_block_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_block_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_block_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_block_to_sf);
+DEFINE_DIR2_EVENT(xfs_dir2_block_to_leaf);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_to_block);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_to_node);
+DEFINE_DIR2_EVENT(xfs_dir2_node_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_node_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_node_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_node_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_node_to_leaf);
+
+DECLARE_EVENT_CLASS(xfs_dir2_space_class,
+	TP_PROTO(struct xfs_da_args *args, int idx),
+	TP_ARGS(args, idx),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, op_flags)
+		__field(int, idx)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(args->dp)->i_sb->s_dev;
+		__entry->ino = args->dp->i_ino;
+		__entry->op_flags = args->op_flags;
+		__entry->idx = idx;
+	),
+	TP_printk("dev %d:%d ino 0x%llx op_flags %s index %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS),
+		  __entry->idx)
 )
-DEFINE_DIR2_TRACE(xfs_dir2_sf_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_create);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_toino4);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_toino8);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_to_block);
-DEFINE_DIR2_TRACE(xfs_dir2_block_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_block_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_block_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_block_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_block_to_sf);
-DEFINE_DIR2_TRACE(xfs_dir2_block_to_leaf);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_to_block);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_to_node);
-DEFINE_DIR2_TRACE(xfs_dir2_node_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_node_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_node_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_node_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_node_to_leaf);
 
-#define DEFINE_DIR2_SPACE_TRACE(tname) \
-TRACE_EVENT(tname, \
+#define DEFINE_DIR2_SPACE_EVENT(name) \
+DEFINE_EVENT(xfs_dir2_space_class, name, \
 	TP_PROTO(struct xfs_da_args *args, int idx), \
-	TP_ARGS(args, idx), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(int, op_flags) \
-		__field(int, idx) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(args->dp)->i_sb->s_dev; \
-		__entry->ino = args->dp->i_ino; \
-		__entry->op_flags = args->op_flags; \
-		__entry->idx = idx; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx op_flags %s index %d", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS), \
-		  __entry->idx) \
-)
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_leafn_add);
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_leafn_remove);
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_grow_inode);
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_shrink_inode);
+	TP_ARGS(args, idx))
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_leafn_add);
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_leafn_remove);
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_grow_inode);
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_shrink_inode);
 
 TRACE_EVENT(xfs_dir2_leafn_moveents,
 	TP_PROTO(struct xfs_da_args *args, int src_idx, int dst_idx, int count),
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 71af76f..873e07e 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -891,7 +891,7 @@ xfs_qm_dqrele_all_inodes(
 	uint		 flags)
 {
 	ASSERT(mp->m_quotainfo);
-	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, XFS_ICI_NO_TAG);
+	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, XFS_ICI_NO_TAG, 0);
 }
 
 /*------------------------------------------------------------------------*/
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index a1c65fc..275b1f4 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2563,43 +2563,41 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
 	xfs_mount_t		*mp;
 	xfs_perag_busy_t	*bsy;
 	xfs_agblock_t		uend, bend;
-	xfs_lsn_t		lsn;
+	xfs_lsn_t		lsn = 0;
 	int			cnt;
 
 	mp = tp->t_mountp;
 
 	spin_lock(&mp->m_perag[agno].pagb_lock);
-	cnt = mp->m_perag[agno].pagb_count;
 
 	uend = bno + len - 1;
 
-	/* search pagb_list for this slot, skipping open slots */
-	for (bsy = mp->m_perag[agno].pagb_list; cnt; bsy++) {
+	/*
+	 * search pagb_list for this slot, skipping open slots. We have to
+	 * search the entire array as there may be multiple overlaps and
+	 * we have to get the most recent LSN for the log force to push out
+	 * all the transactions that span the range.
+	 */
+	for (cnt = 0; cnt < mp->m_perag[agno].pagb_count; cnt++) {
+		bsy = &mp->m_perag[agno].pagb_list[cnt];
+		if (!bsy->busy_tp)
+			continue;
 
-		/*
-		 * (start1,length1) within (start2, length2)
-		 */
-		if (bsy->busy_tp != NULL) {
-			bend = bsy->busy_start + bsy->busy_length - 1;
-			if ((bno > bend) || (uend < bsy->busy_start)) {
-				cnt--;
-			} else {
-				break;
-			}
-		}
-	}
+		bend = bsy->busy_start + bsy->busy_length - 1;
+		if (bno > bend || uend < bsy->busy_start)
+			continue;
 
-	trace_xfs_alloc_busysearch(mp, agno, bno, len, !!cnt);
+		/* (start1,length1) within (start2, length2) */
+		if (XFS_LSN_CMP(bsy->busy_tp->t_commit_lsn, lsn) > 0)
+			lsn = bsy->busy_tp->t_commit_lsn;
+	}
+	spin_unlock(&mp->m_perag[agno].pagb_lock);
+	trace_xfs_alloc_busysearch(tp->t_mountp, agno, bno, len, lsn);
 
 	/*
 	 * If a block was found, force the log through the LSN of the
 	 * transaction that freed the block
 	 */
-	if (cnt) {
-		lsn = bsy->busy_tp->t_commit_lsn;
-		spin_unlock(&mp->m_perag[agno].pagb_lock);
+	if (lsn)
 		xfs_log_force(mp, lsn, XFS_LOG_FORCE|XFS_LOG_SYNC);
-	} else {
-		spin_unlock(&mp->m_perag[agno].pagb_lock);
-	}
 }
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index d1483a4..84ca1cf 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -114,10 +114,82 @@ xfs_swapext(
 	return error;
 }
 
+/*
+ * We need to check that the format of the data fork in the temporary inode is
+ * valid for the target inode before doing the swap. This is not a problem with
+ * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
+ * data fork depending on the space the attribute fork is taking so we can get
+ * invalid formats on the target inode.
+ *
+ * E.g. target has space for 7 extents in extent format, temp inode only has
+ * space for 6.  If we defragment down to 7 extents, then the tmp format is a
+ * btree, but when swapped it needs to be in extent format. Hence we can't just
+ * blindly swap data forks on attr2 filesystems.
+ *
+ * Note that we check the swap in both directions so that we don't end up with
+ * a corrupt temporary inode, either.
+ *
+ * Note that fixing the way xfs_fsr sets up the attribute fork in the source
+ * inode will prevent this situation from occurring, so all we do here is
+ * reject and log the attempt. basically we are putting the responsibility on
+ * userspace to get this right.
+ */
+static int
+xfs_swap_extents_check_format(
+	xfs_inode_t	*ip,	/* target inode */
+	xfs_inode_t	*tip)	/* tmp inode */
+{
+
+	/* Should never get a local format */
+	if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
+	    tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
+		return EINVAL;
+
+	/*
+	 * if the target inode has less extents that then temporary inode then
+	 * why did userspace call us?
+	 */
+	if (ip->i_d.di_nextents < tip->i_d.di_nextents)
+		return EINVAL;
+
+	/*
+	 * if the target inode is in extent form and the temp inode is in btree
+	 * form then we will end up with the target inode in the wrong format
+	 * as we already know there are less extents in the temp inode.
+	 */
+	if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
+		return EINVAL;
+
+	/* Check temp in extent form to max in target */
+	if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+	    XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > ip->i_df.if_ext_max)
+		return EINVAL;
+
+	/* Check target in extent form to max in temp */
+	if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+	    XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > tip->i_df.if_ext_max)
+		return EINVAL;
+
+	/* Check root block of temp in btree form to max in target */
+	if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+	    XFS_IFORK_BOFF(ip) &&
+	    tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip))
+		return EINVAL;
+
+	/* Check root block of target in btree form to max in temp */
+	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+	    XFS_IFORK_BOFF(tip) &&
+	    ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip))
+		return EINVAL;
+
+	return 0;
+}
+
 int
 xfs_swap_extents(
-	xfs_inode_t	*ip,
-	xfs_inode_t	*tip,
+	xfs_inode_t	*ip,	/* target inode */
+	xfs_inode_t	*tip,	/* tmp inode */
 	xfs_swapext_t	*sxp)
 {
 	xfs_mount_t	*mp;
@@ -161,13 +233,6 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
-	/* Should never get a local format */
-	if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
-	    tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
-		error = XFS_ERROR(EINVAL);
-		goto out_unlock;
-	}
-
 	if (VN_CACHED(VFS_I(tip)) != 0) {
 		error = xfs_flushinval_pages(tip, 0, -1,
 				FI_REMAPF_LOCKED);
@@ -189,13 +254,12 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
-	/*
-	 * If the target has extended attributes, the tmp file
-	 * must also in order to ensure the correct data fork
-	 * format.
-	 */
-	if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) {
-		error = XFS_ERROR(EINVAL);
+	/* check inode formats now that data is flushed */
+	error = xfs_swap_extents_check_format(ip, tip);
+	if (error) {
+		xfs_fs_cmn_err(CE_NOTE, mp,
+		    "%s: inode 0x%llx format is incompatible for exchanging.",
+				__FILE__, ip->i_ino);
 		goto out_unlock;
 	}
 
@@ -276,6 +340,16 @@ xfs_swap_extents(
 	*tifp = *tempifp;	/* struct copy */
 
 	/*
+	 * Fix the in-memory data fork values that are dependent on the fork
+	 * offset in the inode. We can't assume they remain the same as attr2
+	 * has dynamic fork offsets.
+	 */
+	ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) /
+					(uint)sizeof(xfs_bmbt_rec_t);
+	tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) /
+					(uint)sizeof(xfs_bmbt_rec_t);
+
+	/*
 	 * Fix the on-disk inode values
 	 */
 	tmp = (__uint64_t)ip->i_d.di_nblocks;
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index fa402a6..155e798 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -73,7 +73,6 @@ xfs_inode_alloc(
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(completion_done(&ip->i_flush));
-	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
 
 	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ce278b3..ef77fd8 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2841,8 +2841,8 @@ xfs_iflush(
 	mp = ip->i_mount;
 
 	/*
-	 * If the inode isn't dirty, then just release the inode
-	 * flush lock and do nothing.
+	 * If the inode isn't dirty, then just release the inode flush lock and
+	 * do nothing.
 	 */
 	if (xfs_inode_clean(ip)) {
 		xfs_ifunlock(ip);
@@ -2868,6 +2868,19 @@ xfs_iflush(
 	xfs_iunpin_wait(ip);
 
 	/*
+	 * For stale inodes we cannot rely on the backing buffer remaining
+	 * stale in cache for the remaining life of the stale inode and so
+	 * xfs_itobp() below may give us a buffer that no longer contains
+	 * inodes below. We have to check this after ensuring the inode is
+	 * unpinned so that it is safe to reclaim the stale inode after the
+	 * flush call.
+	 */
+	if (xfs_iflags_test(ip, XFS_ISTALE)) {
+		xfs_ifunlock(ip);
+		return 0;
+	}
+
+	/*
 	 * This may have been unpinned because the filesystem is shutting
 	 * down forcibly. If that's the case we must not write this inode
 	 * to disk, because the log record didn't make it to disk!
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 9e15a11..6be05f7 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1517,6 +1517,8 @@ xfs_rtfree_range(
 	 */
 	error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1,
 		&postblock);
+	if (error)
+		return error;
 	/*
 	 * If there are blocks not being freed at the front of the
 	 * old extent, add summary data for them to be allocated.
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 6558ffd..6f26875 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -70,7 +70,6 @@ xfs_setattr(
 	uint			commit_flags=0;
 	uid_t			uid=0, iuid=0;
 	gid_t			gid=0, igid=0;
-	int			timeflags = 0;
 	struct xfs_dquot	*udqp, *gdqp, *olddquot1, *olddquot2;
 	int			need_iolock = 1;
 
@@ -135,16 +134,13 @@ xfs_setattr(
 	if (flags & XFS_ATTR_NOLOCK)
 		need_iolock = 0;
 	if (!(mask & ATTR_SIZE)) {
-		if ((mask != (ATTR_CTIME|ATTR_ATIME|ATTR_MTIME)) ||
-		    (mp->m_flags & XFS_MOUNT_WSYNC)) {
-			tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
-			commit_flags = 0;
-			if ((code = xfs_trans_reserve(tp, 0,
-						     XFS_ICHANGE_LOG_RES(mp), 0,
-						     0, 0))) {
-				lock_flags = 0;
-				goto error_return;
-			}
+		tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+		commit_flags = 0;
+		code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp),
+					 0, 0, 0);
+		if (code) {
+			lock_flags = 0;
+			goto error_return;
 		}
 	} else {
 		if (DM_EVENT_ENABLED(ip, DM_EVENT_TRUNCATE) &&
@@ -295,15 +291,23 @@ xfs_setattr(
 		 * or we are explicitly asked to change it. This handles
 		 * the semantic difference between truncate() and ftruncate()
 		 * as implemented in the VFS.
+		 *
+		 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME
+		 * is a special case where we need to update the times despite
+		 * not having these flags set.  For all other operations the
+		 * VFS set these flags explicitly if it wants a timestamp
+		 * update.
 		 */
-		if (iattr->ia_size != ip->i_size || (mask & ATTR_CTIME))
-			timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+		if (iattr->ia_size != ip->i_size &&
+		    (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+			iattr->ia_ctime = iattr->ia_mtime =
+				current_fs_time(inode->i_sb);
+			mask |= ATTR_CTIME | ATTR_MTIME;
+		}
 
 		if (iattr->ia_size > ip->i_size) {
 			ip->i_d.di_size = iattr->ia_size;
 			ip->i_size = iattr->ia_size;
-			if (!(flags & XFS_ATTR_DMI))
-				xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		} else if (iattr->ia_size <= ip->i_size ||
 			   (iattr->ia_size == 0 && ip->i_d.di_nextents)) {
@@ -374,9 +378,6 @@ xfs_setattr(
 			ip->i_d.di_gid = gid;
 			inode->i_gid = gid;
 		}
-
-		xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
-		timeflags |= XFS_ICHGTIME_CHG;
 	}
 
 	/*
@@ -393,51 +394,37 @@ xfs_setattr(
 
 		inode->i_mode &= S_IFMT;
 		inode->i_mode |= mode & ~S_IFMT;
-
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		timeflags |= XFS_ICHGTIME_CHG;
 	}
 
 	/*
 	 * Change file access or modified times.
 	 */
-	if (mask & (ATTR_ATIME|ATTR_MTIME)) {
-		if (mask & ATTR_ATIME) {
-			inode->i_atime = iattr->ia_atime;
-			ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
-			ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
-			ip->i_update_core = 1;
-		}
-		if (mask & ATTR_MTIME) {
-			inode->i_mtime = iattr->ia_mtime;
-			ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
-			ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
-			timeflags &= ~XFS_ICHGTIME_MOD;
-			timeflags |= XFS_ICHGTIME_CHG;
-		}
-		if (tp && (mask & (ATTR_MTIME_SET|ATTR_ATIME_SET)))
-			xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
+	if (mask & ATTR_ATIME) {
+		inode->i_atime = iattr->ia_atime;
+		ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
+		ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
+		ip->i_update_core = 1;
 	}
-
-	/*
-	 * Change file inode change time only if ATTR_CTIME set
-	 * AND we have been called by a DMI function.
-	 */
-
-	if ((flags & XFS_ATTR_DMI) && (mask & ATTR_CTIME)) {
+	if (mask & ATTR_CTIME) {
 		inode->i_ctime = iattr->ia_ctime;
 		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
 		ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
 		ip->i_update_core = 1;
-		timeflags &= ~XFS_ICHGTIME_CHG;
+	}
+	if (mask & ATTR_MTIME) {
+		inode->i_mtime = iattr->ia_mtime;
+		ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
+		ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
+		ip->i_update_core = 1;
 	}
 
 	/*
-	 * Send out timestamp changes that need to be set to the
-	 * current time.  Not done when called by a DMI function.
+	 * And finally, log the inode core if any attribute in it
+	 * has been changed.
 	 */
-	if (timeflags && !(flags & XFS_ATTR_DMI))
-		xfs_ichgtime(ip, timeflags);
+	if (mask & (ATTR_UID|ATTR_GID|ATTR_MODE|
+		    ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	XFS_STATS_INC(xs_ig_attrchg);
 
@@ -452,12 +439,10 @@ xfs_setattr(
 	 * mix so this probably isn't worth the trouble to optimize.
 	 */
 	code = 0;
-	if (tp) {
-		if (mp->m_flags & XFS_MOUNT_WSYNC)
-			xfs_trans_set_sync(tp);
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_trans_set_sync(tp);
 
-		code = xfs_trans_commit(tp, commit_flags);
-	}
+	code = xfs_trans_commit(tp, commit_flags);
 
 	xfs_iunlock(ip, lock_flags);