Merge branch 'merge'

Conflicts:

	arch/powerpc/sysdev/fsl_soc.c

36 files changed, 283 insertions, 228 deletions

diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 55e8ee1900a5..3263084eef9e 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -42,7 +42,7 @@ config BINFMT_ELF_FDPIC
 
 config BINFMT_FLAT
 	bool "Kernel support for flat binaries"
-	depends on !MMU
+	depends on !MMU && (!FRV || BROKEN)
 	help
 	  Support uClinux FLAT format binaries.
 
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index a78d5b236bb1..587ef5123cd8 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -8,7 +8,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  *
- * Authors: David Woodhouse <dwmw2@cambridge.redhat.com>
+ * Authors: David Woodhouse <dwmw2@infradead.org>
  *          David Howells <dhowells@redhat.com>
  *
  */
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 08db82e1343a..bb47217f6a18 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -8,7 +8,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  *
- * Authors: David Woodhouse <dwmw2@cambridge.redhat.com>
+ * Authors: David Woodhouse <dwmw2@infradead.org>
  *          David Howells <dhowells@redhat.com>
  *
  */
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 4b572b801d8d..7e3faeef6818 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -10,7 +10,7 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  *
  * Authors: David Howells <dhowells@redhat.com>
- *          David Woodhouse <dwmw2@redhat.com>
+ *          David Woodhouse <dwmw2@infradead.org>
  *
  */
 
diff --git a/fs/aio.c b/fs/aio.c
index b5253e77eb2f..0fb3117ddd93 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -591,10 +591,6 @@ static void use_mm(struct mm_struct *mm)
 	atomic_inc(&mm->mm_count);
 	tsk->mm = mm;
 	tsk->active_mm = mm;
-	/*
-	 * Note that on UML this *requires* PF_BORROWED_MM to be set, otherwise
-	 * it won't work. Update it accordingly if you change it here
-	 */
 	switch_mm(active_mm, mm, tsk);
 	task_unlock(tsk);
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index ddd35d873391..d051a32e6270 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -390,7 +390,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 	}
 
 	/* expand the stack mapping to use up the entire allocation granule */
-	fullsize = ksize((char *) current->mm->start_brk);
+	fullsize = kobjsize((char *) current->mm->start_brk);
 	if (!IS_ERR_VALUE(do_mremap(current->mm->start_brk, stack_size,
 				    fullsize, 0, 0)))
 		stack_size = fullsize;
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 3b40d45a3a16..2cb1acda3a82 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -548,7 +548,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 			PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0);
 		/* Remap to use all availabe slack region space */
 		if (realdatastart && (realdatastart < (unsigned long)-4096)) {
-			reallen = ksize((void *)realdatastart);
+			reallen = kobjsize((void *)realdatastart);
 			if (reallen > len) {
 				realdatastart = do_mremap(realdatastart, len,
 					reallen, MREMAP_FIXED, realdatastart);
@@ -600,7 +600,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 			PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
 		/* Remap to use all availabe slack region space */
 		if (textpos && (textpos < (unsigned long) -4096)) {
-			reallen = ksize((void *)textpos);
+			reallen = kobjsize((void *)textpos);
 			if (reallen > len) {
 				textpos = do_mremap(textpos, len, reallen,
 					MREMAP_FIXED, textpos);
@@ -683,7 +683,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 		 */
 		current->mm->start_brk = datapos + data_len + bss_len;
 		current->mm->brk = (current->mm->start_brk + 3) & ~3;
-		current->mm->context.end_brk = memp + ksize((void *) memp) - stack_len;
+		current->mm->context.end_brk = memp + kobjsize((void *) memp) - stack_len;
 	}
 
 	if (flags & FLAT_FLAG_KTRACE)
@@ -790,7 +790,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 
 	/* zero the BSS,  BRK and stack areas */
 	memset((void*)(datapos + data_len), 0, bss_len + 
-			(memp + ksize((void *) memp) - stack_len -	/* end brk */
+			(memp + kobjsize((void *) memp) - stack_len -	/* end brk */
 			libinfo->lib_list[id].start_brk) +		/* start brk */
 			stack_len);
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7d822fae7765..470c10ceb0fb 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -12,6 +12,7 @@
 #include <linux/kmod.h>
 #include <linux/major.h>
 #include <linux/smp_lock.h>
+#include <linux/device_cgroup.h>
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
 #include <linux/module.h>
@@ -928,9 +929,14 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 {
 	struct module *owner = NULL;
 	struct gendisk *disk;
-	int ret = -ENXIO;
+	int ret;
 	int part;
 
+	ret = devcgroup_inode_permission(bdev->bd_inode, file->f_mode);
+	if (ret != 0)
+		return ret;
+
+	ret = -ENXIO;
 	file->f_mapping = bdev->bd_inode->i_mapping;
 	lock_kernel();
 	disk = get_gendisk(bdev->bd_dev, &part);
diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index cb52cbbe45ff..f58e41d3ba48 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -186,6 +186,11 @@ asn1_length_decode(struct asn1_ctx *ctx, unsigned int *def, unsigned int *len)
 			}
 		}
 	}
+
+	/* don't trust len bigger than ctx buffer */
+	if (*len > ctx->end - ctx->pointer)
+		return 0;
+
 	return 1;
 }
 
@@ -203,6 +208,10 @@ asn1_header_decode(struct asn1_ctx *ctx,
 	if (!asn1_length_decode(ctx, &def, &len))
 		return 0;
 
+	/* primitive shall be definite, indefinite shall be constructed */
+	if (*con == ASN1_PRI && !def)
+		return 0;
+
 	if (def)
 		*eoc = ctx->pointer + len;
 	else
@@ -389,6 +398,11 @@ asn1_oid_decode(struct asn1_ctx *ctx,
 	unsigned long *optr;
 
 	size = eoc - ctx->pointer + 1;
+
+	/* first subid actually encodes first two subids */
+	if (size < 2 || size > ULONG_MAX/sizeof(unsigned long))
+		return 0;
+
 	*oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC);
 	if (*oid == NULL)
 		return 0;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 9b8b4cfdf993..fb655b4593c6 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -3927,9 +3927,9 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
 	}
 
 	ref = (struct dfs_referral_level_3 *) &(pSMBr->referrals);
-	if (ref->VersionNumber != 3) {
+	if (ref->VersionNumber != cpu_to_le16(3)) {
 		cERROR(1, ("Referrals of V%d version are not supported,"
-			"should be V3", ref->VersionNumber));
+			"should be V3", le16_to_cpu(ref->VersionNumber)));
 		rc = -EINVAL;
 		goto parse_DFS_referrals_exit;
 	}
@@ -3977,7 +3977,7 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
 		if (rc)
 			goto parse_DFS_referrals_exit;
 
-		ref += ref->Size;
+		ref += le16_to_cpu(ref->Size);
 	}
 
 parse_DFS_referrals_exit:
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index cd62d75b2cc0..e2832bc7869a 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1906,9 +1906,9 @@ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
 			goto out;
 		}
 	}
-	mutex_unlock(&key_tfm_list_mutex);
 	(*tfm) = key_tfm->key_tfm;
 	(*tfm_mutex) = &key_tfm->key_tfm_mutex;
 out:
+	mutex_unlock(&key_tfm_list_mutex);
 	return rc;
 }
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 951ee33a022d..c15c25745e05 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -660,8 +660,6 @@ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
 int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
 				      struct ecryptfs_auth_tok **auth_tok,
 				      char *sig);
-int ecryptfs_write_zeros(struct file *file, pgoff_t index, int start,
-			 int num_zeros);
 int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
 			 loff_t offset, size_t size);
 int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index ebf55150be56..75c2ea9fee35 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -157,20 +157,6 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
-		if (start_offset_in_page) {
-			/* Read in the page from the lower
-			 * into the eCryptfs inode page cache,
-			 * decrypting */
-			rc = ecryptfs_decrypt_page(ecryptfs_page);
-			if (rc) {
-				printk(KERN_ERR "%s: Error decrypting "
-				       "page; rc = [%d]\n",
-				       __func__, rc);
-				ClearPageUptodate(ecryptfs_page);
-				page_cache_release(ecryptfs_page);
-				goto out;
-			}
-		}
 		ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0);
 
 		/*
@@ -349,14 +335,6 @@ int ecryptfs_read(char *data, loff_t offset, size_t size,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
-		rc = ecryptfs_decrypt_page(ecryptfs_page);
-		if (rc) {
-			printk(KERN_ERR "%s: Error decrypting "
-			       "page; rc = [%d]\n", __func__, rc);
-			ClearPageUptodate(ecryptfs_page);
-			page_cache_release(ecryptfs_page);
-			goto out;
-		}
 		ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0);
 		memcpy((data + data_offset),
 		       ((char *)ecryptfs_page_virt + start_offset_in_page),
diff --git a/fs/exec.c b/fs/exec.c
index 3c2ba7ce11d4..9448f1b50b4a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -860,6 +860,7 @@ static int de_thread(struct task_struct *tsk)
 
 no_thread_group:
 	exit_itimers(sig);
+	flush_itimer_signals();
 	if (leader)
 		release_task(leader);
 
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 28cfd0b40527..77278e947e94 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -580,7 +580,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	}
 
 	blk = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + EXT3_SB(sb)->s_gdb_count;
-	data = (__le32 *)dind->b_data + EXT3_SB(sb)->s_gdb_count;
+	data = (__le32 *)dind->b_data + (EXT3_SB(sb)->s_gdb_count %
+					 EXT3_ADDR_PER_BLOCK(sb));
 	end = (__le32 *)dind->b_data + EXT3_ADDR_PER_BLOCK(sb);
 
 	/* Get each reserved primary GDT block and verify it holds backups */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index fb77e0962132..43e99513334a 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -488,7 +488,12 @@ static struct fuse_conn *new_conn(struct super_block *sb)
 		err = bdi_init(&fc->bdi);
 		if (err)
 			goto error_kfree;
-		err = bdi_register_dev(&fc->bdi, fc->dev);
+		if (sb->s_bdev) {
+			err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
+					   MAJOR(fc->dev), MINOR(fc->dev));
+		} else {
+			err = bdi_register_dev(&fc->bdi, fc->dev);
+		}
 		if (err)
 			goto error_bdi_destroy;
 		/*
diff --git a/fs/libfs.c b/fs/libfs.c
index b004dfadd891..892d41cb3382 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -528,6 +528,23 @@ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
 	return count;
 }
 
+ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
+				const void *from, size_t available)
+{
+	loff_t pos = *ppos;
+
+	if (pos < 0)
+		return -EINVAL;
+	if (pos >= available)
+		return 0;
+	if (count > available - pos)
+		count = available - pos;
+	memcpy(to, from + pos, count);
+	*ppos = pos + count;
+
+	return count;
+}
+
 /*
  * Transaction based IO.
  * The file expects a single write which triggers the transaction, and then
@@ -800,6 +817,7 @@ EXPORT_SYMBOL(simple_statfs);
 EXPORT_SYMBOL(simple_sync_file);
 EXPORT_SYMBOL(simple_unlink);
 EXPORT_SYMBOL(simple_read_from_buffer);
+EXPORT_SYMBOL(memory_read_from_buffer);
 EXPORT_SYMBOL(simple_transaction_get);
 EXPORT_SYMBOL(simple_transaction_read);
 EXPORT_SYMBOL(simple_transaction_release);
diff --git a/fs/ntfs/upcase.c b/fs/ntfs/upcase.c
index 9101807dc81a..e2f72ca98037 100644
--- a/fs/ntfs/upcase.c
+++ b/fs/ntfs/upcase.c
@@ -77,11 +77,10 @@ ntfschar *generate_default_upcase(void)
 		uc[i] = cpu_to_le16(i);
 	for (r = 0; uc_run_table[r][0]; r++)
 		for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
-			uc[i] = cpu_to_le16(le16_to_cpu(uc[i]) +
-					uc_run_table[r][2]);
+			le16_add_cpu(&uc[i], uc_run_table[r][2]);
 	for (r = 0; uc_dup_table[r][0]; r++)
 		for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
-			uc[i + 1] = cpu_to_le16(le16_to_cpu(uc[i + 1]) - 1);
+			le16_add_cpu(&uc[i + 1], -1);
 	for (r = 0; uc_word_table[r][0]; r++)
 		uc[uc_word_table[r][0]] = cpu_to_le16(uc_word_table[r][1]);
 	return uc;
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 1e44ad14881a..a27d61581bd6 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -142,53 +142,43 @@ static void o2net_idle_timer(unsigned long data);
 static void o2net_sc_postpone_idle(struct o2net_sock_container *sc);
 static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc);
 
-static void o2net_init_nst(struct o2net_send_tracking *nst, u32 msgtype,
-			   u32 msgkey, struct task_struct *task, u8 node)
-{
 #ifdef CONFIG_DEBUG_FS
+void o2net_init_nst(struct o2net_send_tracking *nst, u32 msgtype,
+		    u32 msgkey, struct task_struct *task, u8 node)
+{
 	INIT_LIST_HEAD(&nst->st_net_debug_item);
 	nst->st_task = task;
 	nst->st_msg_type = msgtype;
 	nst->st_msg_key = msgkey;
 	nst->st_node = node;
-#endif
 }
 
-static void o2net_set_nst_sock_time(struct o2net_send_tracking *nst)
+void o2net_set_nst_sock_time(struct o2net_send_tracking *nst)
 {
-#ifdef CONFIG_DEBUG_FS
 	do_gettimeofday(&nst->st_sock_time);
-#endif
 }
 
-static void o2net_set_nst_send_time(struct o2net_send_tracking *nst)
+void o2net_set_nst_send_time(struct o2net_send_tracking *nst)
 {
-#ifdef CONFIG_DEBUG_FS
 	do_gettimeofday(&nst->st_send_time);
-#endif
 }
 
-static void o2net_set_nst_status_time(struct o2net_send_tracking *nst)
+void o2net_set_nst_status_time(struct o2net_send_tracking *nst)
 {
-#ifdef CONFIG_DEBUG_FS
 	do_gettimeofday(&nst->st_status_time);
-#endif
 }
 
-static void o2net_set_nst_sock_container(struct o2net_send_tracking *nst,
+void o2net_set_nst_sock_container(struct o2net_send_tracking *nst,
 					 struct o2net_sock_container *sc)
 {
-#ifdef CONFIG_DEBUG_FS
 	nst->st_sc = sc;
-#endif
 }
 
-static void o2net_set_nst_msg_id(struct o2net_send_tracking *nst, u32 msg_id)
+void o2net_set_nst_msg_id(struct o2net_send_tracking *nst, u32 msg_id)
 {
-#ifdef CONFIG_DEBUG_FS
 	nst->st_id = msg_id;
-#endif
 }
+#endif /* CONFIG_DEBUG_FS */
 
 static inline int o2net_reconnect_delay(void)
 {
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index a705d5d19036..fd6179eb26d4 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -128,23 +128,23 @@ void o2net_debug_del_nst(struct o2net_send_tracking *nst);
 void o2net_debug_add_sc(struct o2net_sock_container *sc);
 void o2net_debug_del_sc(struct o2net_sock_container *sc);
 #else
-static int o2net_debugfs_init(void)
+static inline int o2net_debugfs_init(void)
 {
 	return 0;
 }
-static void o2net_debugfs_exit(void)
+static inline void o2net_debugfs_exit(void)
 {
 }
-static void o2net_debug_add_nst(struct o2net_send_tracking *nst)
+static inline void o2net_debug_add_nst(struct o2net_send_tracking *nst)
 {
 }
-static void o2net_debug_del_nst(struct o2net_send_tracking *nst)
+static inline void o2net_debug_del_nst(struct o2net_send_tracking *nst)
 {
 }
-static void o2net_debug_add_sc(struct o2net_sock_container *sc)
+static inline void o2net_debug_add_sc(struct o2net_sock_container *sc)
 {
 }
-static void o2net_debug_del_sc(struct o2net_sock_container *sc)
+static inline void o2net_debug_del_sc(struct o2net_sock_container *sc)
 {
 }
 #endif	/* CONFIG_DEBUG_FS */
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index 8d58cfe410b1..18307ff81b77 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -224,10 +224,42 @@ struct o2net_send_tracking {
 	struct timeval			st_send_time;
 	struct timeval			st_status_time;
 };
+
+void o2net_init_nst(struct o2net_send_tracking *nst, u32 msgtype,
+		    u32 msgkey, struct task_struct *task, u8 node);
+void o2net_set_nst_sock_time(struct o2net_send_tracking *nst);
+void o2net_set_nst_send_time(struct o2net_send_tracking *nst);
+void o2net_set_nst_status_time(struct o2net_send_tracking *nst);
+void o2net_set_nst_sock_container(struct o2net_send_tracking *nst,
+				  struct o2net_sock_container *sc);
+void o2net_set_nst_msg_id(struct o2net_send_tracking *nst, u32 msg_id);
+
 #else
 struct o2net_send_tracking {
 	u32	dummy;
 };
+
+static inline void o2net_init_nst(struct o2net_send_tracking *nst, u32 msgtype,
+				  u32 msgkey, struct task_struct *task, u8 node)
+{
+}
+static inline void o2net_set_nst_sock_time(struct o2net_send_tracking *nst)
+{
+}
+static inline void o2net_set_nst_send_time(struct o2net_send_tracking *nst)
+{
+}
+static inline void o2net_set_nst_status_time(struct o2net_send_tracking *nst)
+{
+}
+static inline void o2net_set_nst_sock_container(struct o2net_send_tracking *nst,
+						struct o2net_sock_container *sc)
+{
+}
+static inline void o2net_set_nst_msg_id(struct o2net_send_tracking *nst,
+					u32 msg_id)
+{
+}
 #endif	/* CONFIG_DEBUG_FS */
 
 #endif /* O2CLUSTER_TCP_INTERNAL_H */
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index d34a62a3a625..8c686d22f9c7 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -60,25 +60,25 @@ void dlm_destroy_debugfs_root(void);
 
 #else
 
-static int dlm_debug_init(struct dlm_ctxt *dlm)
+static inline int dlm_debug_init(struct dlm_ctxt *dlm)
 {
 	return 0;
 }
-static void dlm_debug_shutdown(struct dlm_ctxt *dlm)
+static inline void dlm_debug_shutdown(struct dlm_ctxt *dlm)
 {
 }
-static int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
+static inline int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
 {
 	return 0;
 }
-static void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
+static inline void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
 {
 }
-static int dlm_create_debugfs_root(void)
+static inline int dlm_create_debugfs_root(void)
 {
 	return 0;
 }
-static void dlm_destroy_debugfs_root(void)
+static inline void dlm_destroy_debugfs_root(void)
 {
 }
 
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index b503772cd0ec..6b97d11f6bf8 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -61,7 +61,7 @@
  * negotiated by the client.  The client negotiates based on the maximum
  * version advertised in /sys/fs/ocfs2/max_locking_protocol.  The major
  * number from the "SETV" message must match
- * user_stack.sp_proto->lp_max_version.pv_major, and the minor number
+ * ocfs2_user_plugin.sp_proto->lp_max_version.pv_major, and the minor number
  * must be less than or equal to ...->lp_max_version.pv_minor.
  *
  * Once this information has been set, mounts will be allowed.  From this
@@ -153,7 +153,7 @@ union ocfs2_control_message {
 	struct ocfs2_control_message_down	u_down;
 };
 
-static struct ocfs2_stack_plugin user_stack;
+static struct ocfs2_stack_plugin ocfs2_user_plugin;
 
 static atomic_t ocfs2_control_opened;
 static int ocfs2_control_this_node = -1;
@@ -399,7 +399,7 @@ static int ocfs2_control_do_setversion_msg(struct file *file,
 	char *ptr = NULL;
 	struct ocfs2_control_private *p = file->private_data;
 	struct ocfs2_protocol_version *max =
-		&user_stack.sp_proto->lp_max_version;
+		&ocfs2_user_plugin.sp_proto->lp_max_version;
 
 	if (ocfs2_control_get_handshake_state(file) !=
 	    OCFS2_CONTROL_HANDSHAKE_PROTOCOL)
@@ -680,7 +680,7 @@ static void fsdlm_lock_ast_wrapper(void *astarg)
 	struct dlm_lksb *lksb = fsdlm_astarg_to_lksb(astarg);
 	int status = lksb->sb_status;
 
-	BUG_ON(user_stack.sp_proto == NULL);
+	BUG_ON(ocfs2_user_plugin.sp_proto == NULL);
 
 	/*
 	 * For now we're punting on the issue of other non-standard errors
@@ -693,16 +693,16 @@ static void fsdlm_lock_ast_wrapper(void *astarg)
 	 */
 
 	if (status == -DLM_EUNLOCK || status == -DLM_ECANCEL)
-		user_stack.sp_proto->lp_unlock_ast(astarg, 0);
+		ocfs2_user_plugin.sp_proto->lp_unlock_ast(astarg, 0);
 	else
-		user_stack.sp_proto->lp_lock_ast(astarg);
+		ocfs2_user_plugin.sp_proto->lp_lock_ast(astarg);
 }
 
 static void fsdlm_blocking_ast_wrapper(void *astarg, int level)
 {
-	BUG_ON(user_stack.sp_proto == NULL);
+	BUG_ON(ocfs2_user_plugin.sp_proto == NULL);
 
-	user_stack.sp_proto->lp_blocking_ast(astarg, level);
+	ocfs2_user_plugin.sp_proto->lp_blocking_ast(astarg, level);
 }
 
 static int user_dlm_lock(struct ocfs2_cluster_connection *conn,
@@ -838,7 +838,7 @@ static int user_cluster_this_node(unsigned int *this_node)
 	return 0;
 }
 
-static struct ocfs2_stack_operations user_stack_ops = {
+static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
 	.connect	= user_cluster_connect,
 	.disconnect	= user_cluster_disconnect,
 	.this_node	= user_cluster_this_node,
@@ -849,20 +849,20 @@ static struct ocfs2_stack_operations user_stack_ops = {
 	.dump_lksb	= user_dlm_dump_lksb,
 };
 
-static struct ocfs2_stack_plugin user_stack = {
+static struct ocfs2_stack_plugin ocfs2_user_plugin = {
 	.sp_name	= "user",
-	.sp_ops		= &user_stack_ops,
+	.sp_ops		= &ocfs2_user_plugin_ops,
 	.sp_owner	= THIS_MODULE,
 };
 
 
-static int __init user_stack_init(void)
+static int __init ocfs2_user_plugin_init(void)
 {
 	int rc;
 
 	rc = ocfs2_control_init();
 	if (!rc) {
-		rc = ocfs2_stack_glue_register(&user_stack);
+		rc = ocfs2_stack_glue_register(&ocfs2_user_plugin);
 		if (rc)
 			ocfs2_control_exit();
 	}
@@ -870,14 +870,14 @@ static int __init user_stack_init(void)
 	return rc;
 }
 
-static void __exit user_stack_exit(void)
+static void __exit ocfs2_user_plugin_exit(void)
 {
-	ocfs2_stack_glue_unregister(&user_stack);
+	ocfs2_stack_glue_unregister(&ocfs2_user_plugin);
 	ocfs2_control_exit();
 }
 
 MODULE_AUTHOR("Oracle");
 MODULE_DESCRIPTION("ocfs2 driver for userspace cluster stacks");
 MODULE_LICENSE("GPL");
-module_init(user_stack_init);
-module_exit(user_stack_exit);
+module_init(ocfs2_user_plugin_init);
+module_exit(ocfs2_user_plugin_exit);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 9e3b8c33c24b..797d775e0354 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -288,7 +288,7 @@ static void render_cap_t(struct seq_file *m, const char *header,
 	seq_printf(m, "%s", header);
 	CAP_FOR_EACH_U32(__capi) {
 		seq_printf(m, "%08x",
-			   a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]);
+			   a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
 	}
 	seq_printf(m, "\n");
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c447e0743a3c..3b455371e7ff 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -127,6 +127,25 @@ struct pid_entry {
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = &proc_##OTYPE } )
 
+/*
+ * Count the number of hardlinks for the pid_entry table, excluding the .
+ * and .. links.
+ */
+static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
+	unsigned int n)
+{
+	unsigned int i;
+	unsigned int count;
+
+	count = 0;
+	for (i = 0; i < n; ++i) {
+		if (S_ISDIR(entries[i].mode))
+			++count;
+	}
+
+	return count;
+}
+
 int maps_protect;
 EXPORT_SYMBOL(maps_protect);
 
@@ -2585,10 +2604,9 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
 	inode->i_op = &proc_tgid_base_inode_operations;
 	inode->i_fop = &proc_tgid_base_operations;
 	inode->i_flags|=S_IMMUTABLE;
-	inode->i_nlink = 5;
-#ifdef CONFIG_SECURITY
-	inode->i_nlink += 1;
-#endif
+
+	inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
+		ARRAY_SIZE(tgid_base_stuff));
 
 	dentry->d_op = &pid_dentry_operations;
 
@@ -2816,10 +2834,9 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
 	inode->i_op = &proc_tid_base_inode_operations;
 	inode->i_fop = &proc_tid_base_operations;
 	inode->i_flags|=S_IMMUTABLE;
-	inode->i_nlink = 4;
-#ifdef CONFIG_SECURITY
-	inode->i_nlink += 1;
-#endif
+
+	inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
+		ARRAY_SIZE(tid_base_stuff));
 
 	dentry->d_op = &pid_dentry_operations;
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6f4e8dc97da1..b08d10017911 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -425,7 +425,8 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 			}
 		}
 		unlock_new_inode(inode);
-	}
+	} else
+	       module_put(de->owner);
 	return inode;
 
 out_ino:
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 74a323d2b850..7e277f2ad466 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -139,7 +139,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	si_meminfo(&i);
 	si_swapinfo(&i);
-	committed = atomic_read(&vm_committed_space);
+	committed = atomic_long_read(&vm_committed_space);
 	allowed = ((totalram_pages - hugetlb_total_pages())
 		* sysctl_overcommit_ratio / 100) + total_swap_pages;
 
@@ -716,7 +716,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 	pfn = src / KPMSIZE;
 	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
 	if (src & KPMMASK || count & KPMMASK)
-		return -EIO;
+		return -EINVAL;
 
 	while (count > 0) {
 		ppage = NULL;
@@ -726,7 +726,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 		if (!ppage)
 			pcount = 0;
 		else
-			pcount = atomic_read(&ppage->_count);
+			pcount = page_mapcount(ppage);
 
 		if (put_user(pcount, out++)) {
 			ret = -EFAULT;
@@ -782,7 +782,7 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
 	pfn = src / KPMSIZE;
 	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
 	if (src & KPMMASK || count & KPMMASK)
-		return -EIO;
+		return -EINVAL;
 
 	while (count > 0) {
 		ppage = NULL;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 88717c0f941b..17403629e330 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -496,7 +496,7 @@ const struct file_operations proc_clear_refs_operations = {
 };
 
 struct pagemapread {
-	char __user *out, *end;
+	u64 __user *out, *end;
 };
 
 #define PM_ENTRY_BYTES      sizeof(u64)
@@ -519,21 +519,11 @@ struct pagemapread {
 static int add_to_pagemap(unsigned long addr, u64 pfn,
 			  struct pagemapread *pm)
 {
-	/*
-	 * Make sure there's room in the buffer for an
-	 * entire entry.  Otherwise, only copy part of
-	 * the pfn.
-	 */
-	if (pm->out + PM_ENTRY_BYTES >= pm->end) {
-		if (copy_to_user(pm->out, &pfn, pm->end - pm->out))
-			return -EFAULT;
-		pm->out = pm->end;
-		return PM_END_OF_BUFFER;
-	}
-
 	if (put_user(pfn, pm->out))
 		return -EFAULT;
-	pm->out += PM_ENTRY_BYTES;
+	pm->out++;
+	if (pm->out >= pm->end)
+		return PM_END_OF_BUFFER;
 	return 0;
 }
 
@@ -634,7 +624,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 
 	ret = -EINVAL;
 	/* file position must be aligned */
-	if (*ppos % PM_ENTRY_BYTES)
+	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
 		goto out_task;
 
 	ret = 0;
@@ -664,8 +654,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		goto out_pages;
 	}
 
-	pm.out = buf;
-	pm.end = buf + count;
+	pm.out = (u64 *)buf;
+	pm.end = (u64 *)(buf + count);
 
 	if (!ptrace_may_attach(task)) {
 		ret = -EIO;
@@ -690,9 +680,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		if (ret == PM_END_OF_BUFFER)
 			ret = 0;
 		/* don't need mmap_sem for these, but this looks cleaner */
-		*ppos += pm.out - buf;
+		*ppos += (char *)pm.out - buf;
 		if (!ret)
-			ret = pm.out - buf;
+			ret = (char *)pm.out - buf;
 	}
 
 out_pages:
diff --git a/fs/splice.c b/fs/splice.c
index 78150038b584..aa5f6f60b305 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -58,8 +58,8 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
 		 */
 		wait_on_page_writeback(page);
 
-		if (PagePrivate(page))
-			try_to_release_page(page, GFP_KERNEL);
+		if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+			goto out_unlock;
 
 		/*
 		 * If we succeeded in removing the mapping, set LRU flag
@@ -75,6 +75,7 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
 	 * Raced with truncate or failed to remove page from current
 	 * address space, unlock and return failure.
 	 */
+out_unlock:
 	unlock_page(page);
 	return 1;
 }
@@ -983,7 +984,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 
 	while (len) {
 		size_t read_len;
-		loff_t pos = sd->pos;
+		loff_t pos = sd->pos, prev_pos = pos;
 
 		ret = do_splice_to(in, &pos, pipe, len, flags);
 		if (unlikely(ret <= 0))
@@ -998,15 +999,19 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 		 * could get stuck data in the internal pipe:
 		 */
 		ret = actor(pipe, sd);
-		if (unlikely(ret <= 0))
+		if (unlikely(ret <= 0)) {
+			sd->pos = prev_pos;
 			goto out_release;
+		}
 
 		bytes += ret;
 		len -= ret;
 		sd->pos = pos;
 
-		if (ret < read_len)
+		if (ret < read_len) {
+			sd->pos = prev_pos + ret;
 			goto out_release;
+		}
 	}
 
 done:
@@ -1072,7 +1077,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 
 	ret = splice_direct_to_actor(in, &sd, direct_splice_actor);
 	if (ret > 0)
-		*ppos += ret;
+		*ppos = sd.pos;
 
 	return ret;
 }
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 5105015a75ad..98e0e86093b4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -387,6 +387,8 @@ _xfs_buf_lookup_pages(
 		if (unlikely(page == NULL)) {
 			if (flags & XBF_READ_AHEAD) {
 				bp->b_page_count = i;
+				for (i = 0; i < bp->b_page_count; i++)
+					unlock_page(bp->b_pages[i]);
 				return -ENOMEM;
 			}
 
@@ -416,17 +418,24 @@ _xfs_buf_lookup_pages(
 		ASSERT(!PagePrivate(page));
 		if (!PageUptodate(page)) {
 			page_count--;
-			if (blocksize < PAGE_CACHE_SIZE && !PagePrivate(page)) {
+			if (blocksize >= PAGE_CACHE_SIZE) {
+				if (flags & XBF_READ)
+					bp->b_flags |= _XBF_PAGE_LOCKED;
+			} else if (!PagePrivate(page)) {
 				if (test_page_region(page, offset, nbytes))
 					page_count++;
 			}
 		}
 
-		unlock_page(page);
 		bp->b_pages[i] = page;
 		offset = 0;
 	}
 
+	if (!(bp->b_flags & _XBF_PAGE_LOCKED)) {
+		for (i = 0; i < bp->b_page_count; i++)
+			unlock_page(bp->b_pages[i]);
+	}
+
 	if (page_count == bp->b_page_count)
 		bp->b_flags |= XBF_DONE;
 
@@ -746,6 +755,7 @@ xfs_buf_associate_memory(
 	bp->b_count_desired = len;
 	bp->b_buffer_length = buflen;
 	bp->b_flags |= XBF_MAPPED;
+	bp->b_flags &= ~_XBF_PAGE_LOCKED;
 
 	return 0;
 }
@@ -1093,8 +1103,10 @@ _xfs_buf_ioend(
 	xfs_buf_t		*bp,
 	int			schedule)
 {
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
+		bp->b_flags &= ~_XBF_PAGE_LOCKED;
 		xfs_buf_ioend(bp, schedule);
+	}
 }
 
 STATIC void
@@ -1125,6 +1137,9 @@ xfs_buf_bio_end_io(
 
 		if (--bvec >= bio->bi_io_vec)
 			prefetchw(&bvec->bv_page->flags);
+
+		if (bp->b_flags & _XBF_PAGE_LOCKED)
+			unlock_page(page);
 	} while (bvec >= bio->bi_io_vec);
 
 	_xfs_buf_ioend(bp, 1);
@@ -1163,7 +1178,8 @@ _xfs_buf_ioapply(
 	 * filesystem block size is not smaller than the page size.
 	 */
 	if ((bp->b_buffer_length < PAGE_CACHE_SIZE) &&
-	    (bp->b_flags & XBF_READ) &&
+	    ((bp->b_flags & (XBF_READ|_XBF_PAGE_LOCKED)) ==
+	      (XBF_READ|_XBF_PAGE_LOCKED)) &&
 	    (blocksize >= PAGE_CACHE_SIZE)) {
 		bio = bio_alloc(GFP_NOIO, 1);
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 841d7883528d..f948ec7ba9a4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -66,6 +66,25 @@ typedef enum {
 	_XBF_PAGES = (1 << 18),	    /* backed by refcounted pages	   */
 	_XBF_RUN_QUEUES = (1 << 19),/* run block device task queue	   */
 	_XBF_DELWRI_Q = (1 << 21),   /* buffer on delwri queue		   */
+
+	/*
+	 * Special flag for supporting metadata blocks smaller than a FSB.
+	 *
+	 * In this case we can have multiple xfs_buf_t on a single page and
+	 * need to lock out concurrent xfs_buf_t readers as they only
+	 * serialise access to the buffer.
+	 *
+	 * If the FSB size >= PAGE_CACHE_SIZE case, we have no serialisation
+	 * between reads of the page. Hence we can have one thread read the
+	 * page and modify it, but then race with another thread that thinks
+	 * the page is not up-to-date and hence reads it again.
+	 *
+	 * The result is that the first modifcation to the page is lost.
+	 * This sort of AGF/AGI reading race can happen when unlinking inodes
+	 * that require truncation and results in the AGI unlinked list
+	 * modifications being lost.
+	 */
+	_XBF_PAGE_LOCKED = (1 << 22),
 } xfs_buf_flags_t;
 
 typedef enum {
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 65e78c13d4ae..5f60363b9343 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -184,19 +184,24 @@ xfs_file_release(
 	return -xfs_release(XFS_I(inode));
 }
 
+/*
+ * We ignore the datasync flag here because a datasync is effectively
+ * identical to an fsync. That is, datasync implies that we need to write
+ * only the metadata needed to be able to access the data that is written
+ * if we crash after the call completes. Hence if we are writing beyond
+ * EOF we have to log the inode size change as well, which makes it a
+ * full fsync. If we don't write beyond EOF, the inode core will be
+ * clean in memory and so we don't need to log the inode, just like
+ * fsync.
+ */
 STATIC int
 xfs_file_fsync(
 	struct file	*filp,
 	struct dentry	*dentry,
 	int		datasync)
 {
-	int		flags = FSYNC_WAIT;
-
-	if (datasync)
-		flags |= FSYNC_DATA;
 	xfs_iflags_clear(XFS_I(dentry->d_inode), XFS_ITRUNCATED);
-	return -xfs_fsync(XFS_I(dentry->d_inode), flags,
-			(xfs_off_t)0, (xfs_off_t)-1);
+	return -xfs_fsync(XFS_I(dentry->d_inode));
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index 9d73cb5c0fc7..25eb2a9e8d9b 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -230,14 +230,6 @@ static inline void vn_atime_to_time_t(bhv_vnode_t *vp, time_t *tt)
 #define ATTR_NOSIZETOK	0x400	/* Don't get the SIZE token */
 
 /*
- * Flags to vop_fsync/reclaim.
- */
-#define FSYNC_NOWAIT	0	/* asynchronous flush */
-#define FSYNC_WAIT	0x1	/* synchronous fsync or forced reclaim */
-#define FSYNC_INVAL	0x2	/* flush and invalidate cached data */
-#define FSYNC_DATA	0x4	/* synchronous fsync of data only */
-
-/*
  * Tracking vnode activity.
  */
 #if defined(XFS_INODE_TRACE)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index cf0bb9c1d621..e569bf5d6cf0 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2974,6 +2974,7 @@ xfs_iflush_cluster(
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_perag_t		*pag = xfs_get_perag(mp, ip->i_ino);
 	unsigned long		first_index, mask;
+	unsigned long		inodes_per_cluster;
 	int			ilist_size;
 	xfs_inode_t		**ilist;
 	xfs_inode_t		*iq;
@@ -2985,8 +2986,9 @@ xfs_iflush_cluster(
 	ASSERT(pag->pagi_inodeok);
 	ASSERT(pag->pag_ici_init);
 
-	ilist_size = XFS_INODE_CLUSTER_SIZE(mp) * sizeof(xfs_inode_t *);
-	ilist = kmem_alloc(ilist_size, KM_MAYFAIL);
+	inodes_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog;
+	ilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
+	ilist = kmem_alloc(ilist_size, KM_MAYFAIL|KM_NOFS);
 	if (!ilist)
 		return 0;
 
@@ -2995,8 +2997,7 @@ xfs_iflush_cluster(
 	read_lock(&pag->pag_ici_lock);
 	/* really need a gang lookup range call here */
 	nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
-					first_index,
-					XFS_INODE_CLUSTER_SIZE(mp));
+					first_index, inodes_per_cluster);
 	if (nr_found == 0)
 		goto out_free;
 
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 70702a60b4bb..e475e3717eb3 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -856,18 +856,14 @@ xfs_readlink(
 /*
  * xfs_fsync
  *
- * This is called to sync the inode and its data out to disk.
- * We need to hold the I/O lock while flushing the data, and
- * the inode lock while flushing the inode.  The inode lock CANNOT
- * be held while flushing the data, so acquire after we're done
- * with that.
+ * This is called to sync the inode and its data out to disk.  We need to hold
+ * the I/O lock while flushing the data, and the inode lock while flushing the
+ * inode.  The inode lock CANNOT be held while flushing the data, so acquire
+ * after we're done with that.
  */
 int
 xfs_fsync(
-	xfs_inode_t	*ip,
-	int		flag,
-	xfs_off_t	start,
-	xfs_off_t	stop)
+	xfs_inode_t	*ip)
 {
 	xfs_trans_t	*tp;
 	int		error;
@@ -875,103 +871,79 @@ xfs_fsync(
 
 	xfs_itrace_entry(ip);
 
-	ASSERT(start >= 0 && stop >= -1);
-
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return XFS_ERROR(EIO);
 
-	if (flag & FSYNC_DATA)
-		filemap_fdatawait(vn_to_inode(XFS_ITOV(ip))->i_mapping);
+	/* capture size updates in I/O completion before writing the inode. */
+	error = filemap_fdatawait(vn_to_inode(XFS_ITOV(ip))->i_mapping);
+	if (error)
+		return XFS_ERROR(error);
 
 	/*
-	 * We always need to make sure that the required inode state
-	 * is safe on disk.  The vnode might be clean but because
-	 * of committed transactions that haven't hit the disk yet.
-	 * Likewise, there could be unflushed non-transactional
-	 * changes to the inode core that have to go to disk.
+	 * We always need to make sure that the required inode state is safe on
+	 * disk.  The vnode might be clean but we still might need to force the
+	 * log because of committed transactions that haven't hit the disk yet.
+	 * Likewise, there could be unflushed non-transactional changes to the
+	 * inode core that have to go to disk and this requires us to issue
+	 * a synchronous transaction to capture these changes correctly.
 	 *
-	 * The following code depends on one assumption:  that
-	 * any transaction that changes an inode logs the core
-	 * because it has to change some field in the inode core
-	 * (typically nextents or nblocks).  That assumption
-	 * implies that any transactions against an inode will
-	 * catch any non-transactional updates.  If inode-altering
-	 * transactions exist that violate this assumption, the
-	 * code breaks.  Right now, it figures that if the involved
-	 * update_* field is clear and the inode is unpinned, the
-	 * inode is clean.  Either it's been flushed or it's been
-	 * committed and the commit has hit the disk unpinning the inode.
-	 * (Note that xfs_inode_item_format() called at commit clears
-	 * the update_* fields.)
+	 * This code relies on the assumption that if the update_* fields
+	 * of the inode are clear and the inode is unpinned then it is clean
+	 * and no action is required.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 
-	/* If we are flushing data then we care about update_size
-	 * being set, otherwise we care about update_core
-	 */
-	if ((flag & FSYNC_DATA) ?
-			(ip->i_update_size == 0) :
-			(ip->i_update_core == 0)) {
+	if (!(ip->i_update_size || ip->i_update_core)) {
 		/*
-		 * Timestamps/size haven't changed since last inode
-		 * flush or inode transaction commit.  That means
-		 * either nothing got written or a transaction
-		 * committed which caught the updates.	If the
-		 * latter happened and the transaction hasn't
-		 * hit the disk yet, the inode will be still
-		 * be pinned.  If it is, force the log.
+		 * Timestamps/size haven't changed since last inode flush or
+		 * inode transaction commit.  That means either nothing got
+		 * written or a transaction committed which caught the updates.
+		 * If the latter happened and the transaction hasn't hit the
+		 * disk yet, the inode will be still be pinned.  If it is,
+		 * force the log.
 		 */
 
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 		if (xfs_ipincount(ip)) {
-			_xfs_log_force(ip->i_mount, (xfs_lsn_t)0,
-				      XFS_LOG_FORCE |
-				      ((flag & FSYNC_WAIT)
-				       ? XFS_LOG_SYNC : 0),
+			error = _xfs_log_force(ip->i_mount, (xfs_lsn_t)0,
+				      XFS_LOG_FORCE | XFS_LOG_SYNC,
 				      &log_flushed);
 		} else {
 			/*
-			 * If the inode is not pinned and nothing
-			 * has changed we don't need to flush the
-			 * cache.
+			 * If the inode is not pinned and nothing has changed
+			 * we don't need to flush the cache.
 			 */
 			changed = 0;
 		}
-		error = 0;
 	} else	{
 		/*
-		 * Kick off a transaction to log the inode
-		 * core to get the updates.  Make it
-		 * sync if FSYNC_WAIT is passed in (which
-		 * is done by everybody but specfs).  The
-		 * sync transaction will also force the log.
+		 * Kick off a transaction to log the inode core to get the
+		 * updates.  The sync transaction will also force the log.
 		 */
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
-		if ((error = xfs_trans_reserve(tp, 0,
-				XFS_FSYNC_TS_LOG_RES(ip->i_mount),
-				0, 0, 0)))  {
+		error = xfs_trans_reserve(tp, 0,
+				XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
+		if (error) {
 			xfs_trans_cancel(tp, 0);
 			return error;
 		}
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 
 		/*
-		 * Note - it's possible that we might have pushed
-		 * ourselves out of the way during trans_reserve
-		 * which would flush the inode.	 But there's no
-		 * guarantee that the inode buffer has actually
-		 * gone out yet (it's delwri).	Plus the buffer
-		 * could be pinned anyway if it's part of an
-		 * inode in another recent transaction.	 So we
-		 * play it safe and fire off the transaction anyway.
+		 * Note - it's possible that we might have pushed ourselves out
+		 * of the way during trans_reserve which would flush the inode.
+		 * But there's no guarantee that the inode buffer has actually
+		 * gone out yet (it's delwri).	Plus the buffer could be pinned
+		 * anyway if it's part of an inode in another recent
+		 * transaction.	 So we play it safe and fire off the
+		 * transaction anyway.
 		 */
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 		xfs_trans_ihold(tp, ip);
 		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		if (flag & FSYNC_WAIT)
-			xfs_trans_set_sync(tp);
+		xfs_trans_set_sync(tp);
 		error = _xfs_trans_commit(tp, 0, &log_flushed);
 
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
index 8abe8f186e20..57335ba4ce53 100644
--- a/fs/xfs/xfs_vnodeops.h
+++ b/fs/xfs/xfs_vnodeops.h
@@ -18,8 +18,7 @@ int xfs_open(struct xfs_inode *ip);
 int xfs_setattr(struct xfs_inode *ip, struct bhv_vattr *vap, int flags,
 		struct cred *credp);
 int xfs_readlink(struct xfs_inode *ip, char *link);
-int xfs_fsync(struct xfs_inode *ip, int flag, xfs_off_t start,
-		xfs_off_t stop);
+int xfs_fsync(struct xfs_inode *ip);
 int xfs_release(struct xfs_inode *ip);
 int xfs_inactive(struct xfs_inode *ip);
 int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,