Merge branch 'linus' into core/softirqtip-core-softirq-2008-06-16_09.24_Mon

53 files changed, 645 insertions, 426 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/CHANGES b/fs/cifs/CHANGES
index 28e3d5c5fcac..1f3465201fdf 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -2,6 +2,11 @@ Version 1.53
 ------------
 DFS support added (Microsoft Distributed File System client support needed
 for referrals which enable a hierarchical name space among servers).
+Disable temporary caching of mode bits to servers which do not support
+storing of mode (e.g. Windows servers, when client mounts without cifsacl
+mount option) and add new "dynperm" mount option to enable temporary caching
+of mode (enable old behavior).  Fix hang on mount caused when server crashes
+tcp session during negotiate protocol.
 
 Version 1.52
 ------------
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/cifsfs.c b/fs/cifs/cifsfs.c
index 5df93fd6303f..86b4d5f405ae 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -97,9 +97,6 @@ cifs_read_super(struct super_block *sb, void *data,
 {
 	struct inode *inode;
 	struct cifs_sb_info *cifs_sb;
-#ifdef CONFIG_CIFS_DFS_UPCALL
-	int len;
-#endif
 	int rc = 0;
 
 	/* BB should we make this contingent on mount parm? */
@@ -117,15 +114,17 @@ cifs_read_super(struct super_block *sb, void *data,
 	 * complex operation (mount), and in case of fail
 	 * just exit instead of doing mount and attempting
 	 * undo it if this copy fails?*/
-	len = strlen(data);
-	cifs_sb->mountdata = kzalloc(len + 1, GFP_KERNEL);
-	if (cifs_sb->mountdata == NULL) {
-		kfree(sb->s_fs_info);
-		sb->s_fs_info = NULL;
-		return -ENOMEM;
+	if (data) {
+		int len = strlen(data);
+		cifs_sb->mountdata = kzalloc(len + 1, GFP_KERNEL);
+		if (cifs_sb->mountdata == NULL) {
+			kfree(sb->s_fs_info);
+			sb->s_fs_info = NULL;
+			return -ENOMEM;
+		}
+		strncpy(cifs_sb->mountdata, data, len + 1);
+		cifs_sb->mountdata[len] = '\0';
 	}
-	strncpy(cifs_sb->mountdata, data, len + 1);
-	cifs_sb->mountdata[len] = '\0';
 #endif
 
 	rc = cifs_mount(sb, cifs_sb, data, devname);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 08914053242b..9cfcf326ead3 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -333,7 +333,6 @@ struct cifsFileInfo {
 	bool messageMode:1;	/* for pipes: message vs byte mode */
 	atomic_t wrtPending;   /* handle in use - defer close */
 	struct semaphore fh_sem; /* prevents reopen race after dead ses*/
-	char *search_resume_name; /* BB removeme BB */
 	struct cifs_search_info srch_inf;
 };
 
@@ -626,7 +625,7 @@ GLOBAL_EXTERN atomic_t tcpSesAllocCount;
 GLOBAL_EXTERN atomic_t tcpSesReconnectCount;
 GLOBAL_EXTERN atomic_t tconInfoReconnectCount;
 
-/* Various Debug counters to remove someday (BB) */
+/* Various Debug counters */
 GLOBAL_EXTERN atomic_t bufAllocCount;    /* current number allocated  */
 #ifdef CONFIG_CIFS_STATS2
 GLOBAL_EXTERN atomic_t totBufAllocCount; /* total allocated over all time */
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 65d58b4e6a61..0f327c224da3 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -79,6 +79,19 @@
 #define TRANS2_GET_DFS_REFERRAL       0x10
 #define TRANS2_REPORT_DFS_INCOSISTENCY 0x11
 
+/* SMB Transact (Named Pipe) subcommand codes */
+#define TRANS_SET_NMPIPE_STATE      0x0001
+#define TRANS_RAW_READ_NMPIPE       0x0011
+#define TRANS_QUERY_NMPIPE_STATE    0x0021
+#define TRANS_QUERY_NMPIPE_INFO     0x0022
+#define TRANS_PEEK_NMPIPE           0x0023
+#define TRANS_TRANSACT_NMPIPE       0x0026
+#define TRANS_RAW_WRITE_NMPIPE      0x0031
+#define TRANS_READ_NMPIPE           0x0036
+#define TRANS_WRITE_NMPIPE          0x0037
+#define TRANS_WAIT_NMPIPE           0x0053
+#define TRANS_CALL_NMPIPE           0x0054
+
 /* NT Transact subcommand codes */
 #define NT_TRANSACT_CREATE            0x01
 #define NT_TRANSACT_IOCTL             0x02
@@ -328,12 +341,13 @@
 #define CREATE_COMPLETE_IF_OPLK 0x00000100	/* should be zero */
 #define CREATE_NO_EA_KNOWLEDGE  0x00000200
 #define CREATE_EIGHT_DOT_THREE  0x00000400	/* doc says this is obsolete
-						 open for recovery flag - should
-						 be zero */
+						 "open for recovery" flag - should
+						 be zero in any case */
+#define CREATE_OPEN_FOR_RECOVERY 0x00000400
 #define CREATE_RANDOM_ACCESS	0x00000800
 #define CREATE_DELETE_ON_CLOSE	0x00001000
 #define CREATE_OPEN_BY_ID       0x00002000
-#define CREATE_OPEN_BACKUP_INTN 0x00004000
+#define CREATE_OPEN_BACKUP_INTENT 0x00004000
 #define CREATE_NO_COMPRESSION   0x00008000
 #define CREATE_RESERVE_OPFILTER 0x00100000	/* should be zero */
 #define OPEN_REPARSE_POINT	0x00200000
@@ -722,7 +736,6 @@ typedef struct smb_com_tconx_rsp_ext {
 #define SMB_CSC_CACHE_AUTO_REINT   0x0004
 #define SMB_CSC_CACHE_VDO          0x0008
 #define SMB_CSC_NO_CACHING         0x000C
-
 #define SMB_UNIQUE_FILE_NAME    0x0010
 #define SMB_EXTENDED_SIGNATURES 0x0020
 
@@ -806,7 +819,7 @@ typedef struct smb_com_findclose_req {
 #define ICOUNT_MASK		0x00FF
 #define PIPE_READ_MODE		0x0100
 #define NAMED_PIPE_TYPE		0x0400
-#define PIPE_END_POINT		0x0800
+#define PIPE_END_POINT		0x4000
 #define BLOCKING_NAMED_PIPE	0x8000
 
 typedef struct smb_com_open_req {	/* also handles create */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 9b8b4cfdf993..4511b708f0f3 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1728,7 +1728,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 {
 	int rc = 0;
 	LOCK_REQ *pSMB = NULL;
-	LOCK_RSP *pSMBr = NULL;
+/*	LOCK_RSP *pSMBr = NULL; */ /* No response data other than rc to parse */
 	int bytes_returned;
 	int timeout = 0;
 	__u16 count;
@@ -1739,8 +1739,6 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 	if (rc)
 		return rc;
 
-	pSMBr = (LOCK_RSP *)pSMB; /* BB removeme BB */
-
 	if (lockType == LOCKING_ANDX_OPLOCK_RELEASE) {
 		timeout = CIFS_ASYNC_OP; /* no response expected */
 		pSMB->Timeout = 0;
@@ -1774,7 +1772,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 
 	if (waitFlag) {
 		rc = SendReceiveBlockingLock(xid, tcon, (struct smb_hdr *) pSMB,
-			(struct smb_hdr *) pSMBr, &bytes_returned);
+			(struct smb_hdr *) pSMB, &bytes_returned);
 		cifs_small_buf_release(pSMB);
 	} else {
 		rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *)pSMB,
@@ -3927,9 +3925,9 @@ 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 +3975,7 @@ 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/cifs/connect.c b/fs/cifs/connect.c
index 023434f72c15..e8fa46c7cff2 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -653,6 +653,7 @@ multi_t2_fnd:
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
+	wake_up_all(&server->response_q);
 
 	/* don't exit until kthread_stop is called */
 	set_current_state(TASK_UNINTERRUPTIBLE);
@@ -2120,6 +2121,10 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
 		}
 
+		if ((volume_info.cifs_acl) && (volume_info.dynperm))
+			cERROR(1, ("mount option dynperm ignored if cifsacl "
+				   "mount option supported"));
+
 		tcon =
 		    find_unc(sin_server.sin_addr.s_addr, volume_info.UNC,
 			     volume_info.username);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index f0b5b5f3dd2e..fb69c1fa85c9 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -260,7 +260,9 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
 						 buf, inode->i_sb, xid,
 						 &fileHandle);
 			if (newinode) {
-				newinode->i_mode = mode;
+				if (cifs_sb->mnt_cifs_flags &
+				    CIFS_MOUNT_DYNPERM)
+					newinode->i_mode = mode;
 				if ((oplock & CIFS_CREATE_ACTION) &&
 				    (cifs_sb->mnt_cifs_flags &
 				     CIFS_MOUNT_SET_UID)) {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 8636cec2642c..0aac824371a5 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -546,7 +546,6 @@ int cifs_close(struct inode *inode, struct file *file)
 			msleep(timeout);
 			timeout *= 8;
 		}
-		kfree(pSMBFile->search_resume_name);
 		kfree(file->private_data);
 		file->private_data = NULL;
 	} else
@@ -605,12 +604,6 @@ int cifs_closedir(struct inode *inode, struct file *file)
 			else
 				cifs_buf_release(ptmp);
 		}
-		ptmp = pCFileStruct->search_resume_name;
-		if (ptmp) {
-			cFYI(1, ("closedir free resume name"));
-			pCFileStruct->search_resume_name = NULL;
-			kfree(ptmp);
-		}
 		kfree(file->private_data);
 		file->private_data = NULL;
 	}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 129dbfe4dca7..722be543ceec 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -418,6 +418,7 @@ int cifs_get_inode_info(struct inode **pinode,
 	char *buf = NULL;
 	bool adjustTZ = false;
 	bool is_dfs_referral = false;
+	umode_t default_mode;
 
 	pTcon = cifs_sb->tcon;
 	cFYI(1, ("Getting info on %s", full_path));
@@ -530,47 +531,42 @@ int cifs_get_inode_info(struct inode **pinode,
 		inode->i_mtime.tv_sec += pTcon->ses->server->timeAdj;
 	}
 
-	/* set default mode. will override for dirs below */
-	if (atomic_read(&cifsInfo->inUse) == 0)
-		/* new inode, can safely set these fields */
-		inode->i_mode = cifs_sb->mnt_file_mode;
-	else /* since we set the inode type below we need to mask off
-	     to avoid strange results if type changes and both
-	     get orred in */
-		inode->i_mode &= ~S_IFMT;
-/*	if (attr & ATTR_REPARSE)  */
-	/* We no longer handle these as symlinks because we could not
-	   follow them due to the absolute path with drive letter */
-	if (attr & ATTR_DIRECTORY) {
-	/* override default perms since we do not do byte range locking
-	   on dirs */
-		inode->i_mode = cifs_sb->mnt_dir_mode;
-		inode->i_mode |= S_IFDIR;
-	} else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) &&
-		   (cifsInfo->cifsAttrs & ATTR_SYSTEM) &&
-		   /* No need to le64 convert size of zero */
-		   (pfindData->EndOfFile == 0)) {
-		inode->i_mode = cifs_sb->mnt_file_mode;
-		inode->i_mode |= S_IFIFO;
-/* BB Finish for SFU style symlinks and devices */
-	} else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) &&
-		   (cifsInfo->cifsAttrs & ATTR_SYSTEM)) {
-		if (decode_sfu_inode(inode, le64_to_cpu(pfindData->EndOfFile),
-				     full_path, cifs_sb, xid))
-			cFYI(1, ("Unrecognized sfu inode type"));
-
-		cFYI(1, ("sfu mode 0%o", inode->i_mode));
+	/* get default inode mode */
+	if (attr & ATTR_DIRECTORY)
+		default_mode = cifs_sb->mnt_dir_mode;
+	else
+		default_mode = cifs_sb->mnt_file_mode;
+
+	/* set permission bits */
+	if (atomic_read(&cifsInfo->inUse) == 0 ||
+	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
+		inode->i_mode = default_mode;
+	else {
+		/* just reenable write bits if !ATTR_READONLY */
+		if ((inode->i_mode & S_IWUGO) == 0 &&
+		    (attr & ATTR_READONLY) == 0)
+			inode->i_mode |= (S_IWUGO & default_mode);
+			inode->i_mode &= ~S_IFMT;
+	}
+	/* clear write bits if ATTR_READONLY is set */
+	if (attr & ATTR_READONLY)
+		inode->i_mode &= ~S_IWUGO;
+
+	/* set inode type */
+	if ((attr & ATTR_SYSTEM) &&
+	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) {
+		/* no need to fix endianness on 0 */
+		if (pfindData->EndOfFile == 0)
+			inode->i_mode |= S_IFIFO;
+		else if (decode_sfu_inode(inode,
+				le64_to_cpu(pfindData->EndOfFile),
+				full_path, cifs_sb, xid))
+			cFYI(1, ("unknown SFU file type\n"));
 	} else {
-		inode->i_mode |= S_IFREG;
-		/* treat dos attribute of read-only as read-only mode eg 555 */
-		if (cifsInfo->cifsAttrs & ATTR_READONLY)
-			inode->i_mode &= ~(S_IWUGO);
-		else if ((inode->i_mode & S_IWUGO) == 0)
-			/* the ATTR_READONLY flag may have been	*/
-			/* changed on server -- set any w bits	*/
-			/* allowed by mnt_file_mode		*/
-			inode->i_mode |= (S_IWUGO & cifs_sb->mnt_file_mode);
-	/* BB add code to validate if device or weird share or device type? */
+		if (attr & ATTR_DIRECTORY)
+			inode->i_mode |= S_IFDIR;
+		else
+			inode->i_mode |= S_IFREG;
 	}
 
 	spin_lock(&inode->i_lock);
@@ -1019,8 +1015,11 @@ mkdir_get_info:
 						CIFS_MOUNT_MAP_SPECIAL_CHR);
 			}
 			if (direntry->d_inode) {
-				direntry->d_inode->i_mode = mode;
-				direntry->d_inode->i_mode |= S_IFDIR;
+				if (cifs_sb->mnt_cifs_flags &
+				     CIFS_MOUNT_DYNPERM)
+					direntry->d_inode->i_mode =
+						(mode | S_IFDIR);
+
 				if (cifs_sb->mnt_cifs_flags &
 				     CIFS_MOUNT_SET_UID) {
 					direntry->d_inode->i_uid =
@@ -1547,13 +1546,26 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 		} else
 			goto cifs_setattr_exit;
 	}
-	if (attrs->ia_valid & ATTR_UID) {
-		cFYI(1, ("UID changed to %d", attrs->ia_uid));
-		uid = attrs->ia_uid;
-	}
-	if (attrs->ia_valid & ATTR_GID) {
-		cFYI(1, ("GID changed to %d", attrs->ia_gid));
-		gid = attrs->ia_gid;
+
+	/*
+	 * Without unix extensions we can't send ownership changes to the
+	 * server, so silently ignore them. This is consistent with how
+	 * local DOS/Windows filesystems behave (VFAT, NTFS, etc). With
+	 * CIFSACL support + proper Windows to Unix idmapping, we may be
+	 * able to support this in the future.
+	 */
+	if (!pTcon->unix_ext &&
+	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
+		attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
+	} else {
+		if (attrs->ia_valid & ATTR_UID) {
+			cFYI(1, ("UID changed to %d", attrs->ia_uid));
+			uid = attrs->ia_uid;
+		}
+		if (attrs->ia_valid & ATTR_GID) {
+			cFYI(1, ("GID changed to %d", attrs->ia_gid));
+			gid = attrs->ia_gid;
+		}
 	}
 
 	time_buf.Attributes = 0;
@@ -1563,7 +1575,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 		attrs->ia_valid &= ~ATTR_MODE;
 
 	if (attrs->ia_valid & ATTR_MODE) {
-		cFYI(1, ("Mode changed to 0x%x", attrs->ia_mode));
+		cFYI(1, ("Mode changed to 0%o", attrs->ia_mode));
 		mode = attrs->ia_mode;
 	}
 
@@ -1578,18 +1590,18 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 #ifdef CONFIG_CIFS_EXPERIMENTAL
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
 			rc = mode_to_acl(inode, full_path, mode);
-		else if ((mode & S_IWUGO) == 0) {
-#else
-		if ((mode & S_IWUGO) == 0) {
+		else
 #endif
-			/* not writeable */
-			if ((cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
-				set_dosattr = true;
-				time_buf.Attributes =
-					cpu_to_le32(cifsInode->cifsAttrs |
-						    ATTR_READONLY);
-			}
-		} else if (cifsInode->cifsAttrs & ATTR_READONLY) {
+		if (((mode & S_IWUGO) == 0) &&
+		    (cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
+			set_dosattr = true;
+			time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs |
+							  ATTR_READONLY);
+			/* fix up mode if we're not using dynperm */
+			if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
+				attrs->ia_mode = inode->i_mode & ~S_IWUGO;
+		} else if ((mode & S_IWUGO) &&
+			   (cifsInode->cifsAttrs & ATTR_READONLY)) {
 			/* If file is readonly on server, we would
 			not be able to write to it - so if any write
 			bit is enabled for user or group or other we
@@ -1600,6 +1612,20 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 			/* Windows ignores set to zero */
 			if (time_buf.Attributes == 0)
 				time_buf.Attributes |= cpu_to_le32(ATTR_NORMAL);
+
+			/* reset local inode permissions to normal */
+			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
+				attrs->ia_mode &= ~(S_IALLUGO);
+				if (S_ISDIR(inode->i_mode))
+					attrs->ia_mode |=
+						cifs_sb->mnt_dir_mode;
+				else
+					attrs->ia_mode |=
+						cifs_sb->mnt_file_mode;
+			}
+		} else if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
+			/* ignore mode change - ATTR_READONLY hasn't changed */
+			attrs->ia_valid &= ~ATTR_MODE;
 		}
 	}
 
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 1d69b8014e0b..4b17f8fe3157 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -519,8 +519,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 			pnotify = (struct file_notify_information *)
 				((char *)&pSMBr->hdr.Protocol + data_offset);
 			cFYI(1, ("dnotify on %s Action: 0x%x",
-				 pnotify->FileName,
-				pnotify->Action));  /* BB removeme BB */
+				 pnotify->FileName, pnotify->Action));
 			/*   cifs_dump_mem("Rcvd notify Data: ",buf,
 				sizeof(struct smb_hdr)+60); */
 			return true;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 713c25110197..83f306954883 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -132,6 +132,7 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type,
 	__u32 attr;
 	__u64 allocation_size;
 	__u64 end_of_file;
+	umode_t default_mode;
 
 	/* save mtime and size */
 	local_mtime = tmp_inode->i_mtime;
@@ -187,48 +188,54 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type,
 	if (atomic_read(&cifsInfo->inUse) == 0) {
 		tmp_inode->i_uid = cifs_sb->mnt_uid;
 		tmp_inode->i_gid = cifs_sb->mnt_gid;
-		/* set default mode. will override for dirs below */
-		tmp_inode->i_mode = cifs_sb->mnt_file_mode;
-	} else {
-		/* mask off the type bits since it gets set
-		below and we do not want to get two type
-		bits set */
+	}
+
+	if (attr & ATTR_DIRECTORY)
+		default_mode = cifs_sb->mnt_dir_mode;
+	else
+		default_mode = cifs_sb->mnt_file_mode;
+
+	/* set initial permissions */
+	if ((atomic_read(&cifsInfo->inUse) == 0) ||
+	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
+		tmp_inode->i_mode = default_mode;
+	else {
+		/* just reenable write bits if !ATTR_READONLY */
+		if ((tmp_inode->i_mode & S_IWUGO) == 0 &&
+		    (attr & ATTR_READONLY) == 0)
+			tmp_inode->i_mode |= (S_IWUGO & default_mode);
+
 		tmp_inode->i_mode &= ~S_IFMT;
 	}
 
-	if (attr & ATTR_DIRECTORY) {
-		*pobject_type = DT_DIR;
-		/* override default perms since we do not lock dirs */
-		if (atomic_read(&cifsInfo->inUse) == 0)
-			tmp_inode->i_mode = cifs_sb->mnt_dir_mode;
-		tmp_inode->i_mode |= S_IFDIR;
-	} else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) &&
-		   (attr & ATTR_SYSTEM)) {
+	/* clear write bits if ATTR_READONLY is set */
+	if (attr & ATTR_READONLY)
+		tmp_inode->i_mode &= ~S_IWUGO;
+
+	/* set inode type */
+	if ((attr & ATTR_SYSTEM) &&
+	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) {
 		if (end_of_file == 0)  {
-			*pobject_type = DT_FIFO;
 			tmp_inode->i_mode |= S_IFIFO;
+			*pobject_type = DT_FIFO;
 		} else {
-			/* rather than get the type here, we mark the
-			inode as needing revalidate and get the real type
-			(blk vs chr vs. symlink) later ie in lookup */
-			*pobject_type = DT_REG;
+			/*
+			 * trying to get the type can be slow, so just call
+			 * this a regular file for now, and mark for reval
+			 */
 			tmp_inode->i_mode |= S_IFREG;
+			*pobject_type = DT_REG;
 			cifsInfo->time = 0;
 		}
-/* we no longer mark these because we could not follow them */
-/*        } else if (attr & ATTR_REPARSE) {
-		*pobject_type = DT_LNK;
-		tmp_inode->i_mode |= S_IFLNK; */
 	} else {
-		*pobject_type = DT_REG;
-		tmp_inode->i_mode |= S_IFREG;
-		if (attr & ATTR_READONLY)
-			tmp_inode->i_mode &= ~(S_IWUGO);
-		else if ((tmp_inode->i_mode & S_IWUGO) == 0)
-			/* the ATTR_READONLY flag may have been changed on   */
-			/* server -- set any w bits allowed by mnt_file_mode */
-			tmp_inode->i_mode |= (S_IWUGO & cifs_sb->mnt_file_mode);
-	} /* could add code here - to validate if device or weird share type? */
+		if (attr & ATTR_DIRECTORY) {
+			tmp_inode->i_mode |= S_IFDIR;
+			*pobject_type = DT_DIR;
+		} else {
+			tmp_inode->i_mode |= S_IFREG;
+			*pobject_type = DT_REG;
+		}
+	}
 
 	/* can not fill in nlink here as in qpathinfo version and Unx search */
 	if (atomic_read(&cifsInfo->inUse) == 0)
@@ -675,8 +682,6 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon,
 			cifsFile->invalidHandle = true;
 			CIFSFindClose(xid, pTcon, cifsFile->netfid);
 		}
-		kfree(cifsFile->search_resume_name);
-		cifsFile->search_resume_name = NULL;
 		if (cifsFile->srch_inf.ntwrk_buf_start) {
 			cFYI(1, ("freeing SMB ff cache buf on search rewind"));
 			if (cifsFile->srch_inf.smallBuf)
@@ -1043,9 +1048,7 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
 		} /* else {
 			cifsFile->invalidHandle = true;
 			CIFSFindClose(xid, pTcon, cifsFile->netfid);
-		}
-		kfree(cifsFile->search_resume_name);
-		cifsFile->search_resume_name = NULL; */
+		} */
 
 		rc = find_cifs_entry(xid, pTcon, file,
 				&current_entry, &num_to_fill);
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/ext4/balloc.c b/fs/ext4/balloc.c
index 30494c5da843..9cc80b9cc8d8 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -43,6 +43,46 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 
 }
 
+static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
+			ext4_group_t block_group)
+{
+	ext4_group_t actual_group;
+	ext4_get_group_no_and_offset(sb, block, &actual_group, 0);
+	if (actual_group == block_group)
+		return 1;
+	return 0;
+}
+
+static int ext4_group_used_meta_blocks(struct super_block *sb,
+				ext4_group_t block_group)
+{
+	ext4_fsblk_t tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	/* block bitmap, inode bitmap, and inode table blocks */
+	int used_blocks = sbi->s_itb_per_group + 2;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		struct ext4_group_desc *gdp;
+		struct buffer_head *bh;
+
+		gdp = ext4_get_group_desc(sb, block_group, &bh);
+		if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
+					block_group))
+			used_blocks--;
+
+		if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
+					block_group))
+			used_blocks--;
+
+		tmp = ext4_inode_table(sb, gdp);
+		for (; tmp < ext4_inode_table(sb, gdp) +
+				sbi->s_itb_per_group; tmp++) {
+			if (!ext4_block_in_group(sb, tmp, block_group))
+				used_blocks -= 1;
+		}
+	}
+	return used_blocks;
+}
 /* Initializes an uninitialized block bitmap if given, and returns the
  * number of blocks free in the group. */
 unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
@@ -105,20 +145,34 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	free_blocks = group_blocks - bit_max;
 
 	if (bh) {
-		ext4_fsblk_t start;
+		ext4_fsblk_t start, tmp;
+		int flex_bg = 0;
 
 		for (bit = 0; bit < bit_max; bit++)
 			ext4_set_bit(bit, bh->b_data);
 
 		start = ext4_group_first_block_no(sb, block_group);
 
-		/* Set bits for block and inode bitmaps, and inode table */
-		ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data);
-		ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data);
-		for (bit = (ext4_inode_table(sb, gdp) - start),
-		     bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++)
-			ext4_set_bit(bit, bh->b_data);
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+					      EXT4_FEATURE_INCOMPAT_FLEX_BG))
+			flex_bg = 1;
 
+		/* Set bits for block and inode bitmaps, and inode table */
+		tmp = ext4_block_bitmap(sb, gdp);
+		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+			ext4_set_bit(tmp - start, bh->b_data);
+
+		tmp = ext4_inode_bitmap(sb, gdp);
+		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+			ext4_set_bit(tmp - start, bh->b_data);
+
+		tmp = ext4_inode_table(sb, gdp);
+		for (; tmp < ext4_inode_table(sb, gdp) +
+				sbi->s_itb_per_group; tmp++) {
+			if (!flex_bg ||
+				ext4_block_in_group(sb, tmp, block_group))
+				ext4_set_bit(tmp - start, bh->b_data);
+		}
 		/*
 		 * Also if the number of blocks within the group is
 		 * less than the blocksize * 8 ( which is the size
@@ -126,8 +180,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 */
 		mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
 	}
-
-	return free_blocks - sbi->s_itb_per_group - 2;
+	return free_blocks - ext4_group_used_meta_blocks(sb, block_group);
 }
 
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 873ad9b3418c..c9900aade150 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2745,8 +2745,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	sbi = EXT4_SB(sb);
 	es = sbi->s_es;
 
-	ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group,
-			gdp->bg_free_blocks_count);
 
 	err = -EIO;
 	bitmap_bh = read_block_bitmap(sb, ac->ac_b_ex.fe_group);
@@ -2762,6 +2760,9 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (!gdp)
 		goto out_err;
 
+	ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group,
+			gdp->bg_free_blocks_count);
+
 	err = ext4_journal_get_write_access(handle, gdp_bh);
 	if (err)
 		goto out_err;
@@ -3094,8 +3095,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
 static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
 				struct ext4_prealloc_space *pa)
 {
-	unsigned len = ac->ac_o_ex.fe_len;
-
+	unsigned int len = ac->ac_o_ex.fe_len;
 	ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart,
 					&ac->ac_b_ex.fe_group,
 					&ac->ac_b_ex.fe_start);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 9f086a6a472b..9ecb92f68543 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -563,7 +563,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	}
 
 	blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
-	data = (__le32 *)dind->b_data + EXT4_SB(sb)->s_gdb_count;
+	data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
+					 EXT4_ADDR_PER_BLOCK(sb));
 	end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
 
 	/* Get each reserved primary GDT block and verify it holds backups */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 09d9359c8055..cb96f127c366 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -671,6 +671,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	unsigned long def_mount_opts;
 	struct super_block *sb = vfs->mnt_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	journal_t *journal = sbi->s_journal;
 	struct ext4_super_block *es = sbi->s_es;
 
 	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
@@ -729,8 +730,15 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_printf(seq, ",commit=%u",
 			   (unsigned) (sbi->s_commit_interval / HZ));
 	}
-	if (test_opt(sb, BARRIER))
-		seq_puts(seq, ",barrier=1");
+	/*
+	 * We're changing the default of barrier mount option, so
+	 * let's always display its mount state so it's clear what its
+	 * status is.
+	 */
+	seq_puts(seq, ",barrier=");
+	seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
+	if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
+		seq_puts(seq, ",journal_async_commit");
 	if (test_opt(sb, NOBH))
 		seq_puts(seq, ",nobh");
 	if (!test_opt(sb, EXTENTS))
@@ -1907,6 +1915,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
 
 	set_opt(sbi->s_mount_opt, RESERVATION);
+	set_opt(sbi->s_mount_opt, BARRIER);
 
 	/*
 	 * turn on extents feature by default in ext4 filesystem
@@ -2189,6 +2198,29 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
 		if (ext4_load_journal(sb, es, journal_devnum))
 			goto failed_mount3;
+		if (!(sb->s_flags & MS_RDONLY) &&
+		    EXT4_SB(sb)->s_journal->j_failed_commit) {
+			printk(KERN_CRIT "EXT4-fs error (device %s): "
+			       "ext4_fill_super: Journal transaction "
+			       "%u is corrupt\n", sb->s_id, 
+			       EXT4_SB(sb)->s_journal->j_failed_commit);
+			if (test_opt (sb, ERRORS_RO)) {
+				printk (KERN_CRIT
+					"Mounting filesystem read-only\n");
+				sb->s_flags |= MS_RDONLY;
+				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+			}
+			if (test_opt(sb, ERRORS_PANIC)) {
+				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+				ext4_commit_super(sb, es, 1);
+				printk(KERN_CRIT
+				       "EXT4-fs (device %s): mount failed\n",
+				      sb->s_id);
+				goto failed_mount4;
+			}
+		}
 	} else if (journal_inum) {
 		if (ext4_create_journal(sb, es, journal_inum))
 			goto failed_mount3;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 27cc1164ec36..771326b8047e 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -257,26 +257,34 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 }
 EXPORT_SYMBOL_GPL(fat_getattr);
 
-static int fat_check_mode(const struct msdos_sb_info *sbi, struct inode *inode,
-			  mode_t mode)
+static int fat_sanitize_mode(const struct msdos_sb_info *sbi,
+			     struct inode *inode, umode_t *mode_ptr)
 {
-	mode_t mask, req = mode & ~S_IFMT;
+	mode_t mask, perm;
 
-	if (S_ISREG(mode))
+	/*
+	 * Note, the basic check is already done by a caller of
+	 * (attr->ia_mode & ~MSDOS_VALID_MODE)
+	 */
+
+	if (S_ISREG(inode->i_mode))
 		mask = sbi->options.fs_fmask;
 	else
 		mask = sbi->options.fs_dmask;
 
+	perm = *mode_ptr & ~(S_IFMT | mask);
+
 	/*
 	 * Of the r and x bits, all (subject to umask) must be present. Of the
 	 * w bits, either all (subject to umask) or none must be present.
 	 */
-	req &= ~mask;
-	if ((req & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO)))
+	if ((perm & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO)))
 		return -EPERM;
-	if ((req & S_IWUGO) && ((req & S_IWUGO) != (S_IWUGO & ~mask)))
+	if ((perm & S_IWUGO) && ((perm & S_IWUGO) != (S_IWUGO & ~mask)))
 		return -EPERM;
 
+	*mode_ptr &= S_IFMT | perm;
+
 	return 0;
 }
 
@@ -299,7 +307,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
 	struct inode *inode = dentry->d_inode;
-	int mask, error = 0;
+	int error = 0;
 	unsigned int ia_valid;
 
 	lock_kernel();
@@ -332,12 +340,13 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 			error = 0;
 		goto out;
 	}
+
 	if (((attr->ia_valid & ATTR_UID) &&
 	     (attr->ia_uid != sbi->options.fs_uid)) ||
 	    ((attr->ia_valid & ATTR_GID) &&
 	     (attr->ia_gid != sbi->options.fs_gid)) ||
 	    ((attr->ia_valid & ATTR_MODE) &&
-	     fat_check_mode(sbi, inode, attr->ia_mode) < 0))
+	     (attr->ia_mode & ~MSDOS_VALID_MODE)))
 		error = -EPERM;
 
 	if (error) {
@@ -346,15 +355,16 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 		goto out;
 	}
 
-	error = inode_setattr(inode, attr);
-	if (error)
-		goto out;
+	/*
+	 * We don't return -EPERM here. Yes, strange, but this is too
+	 * old behavior.
+	 */
+	if (attr->ia_valid & ATTR_MODE) {
+		if (fat_sanitize_mode(sbi, inode, &attr->ia_mode) < 0)
+			attr->ia_valid &= ~ATTR_MODE;
+	}
 
-	if (S_ISDIR(inode->i_mode))
-		mask = sbi->options.fs_dmask;
-	else
-		mask = sbi->options.fs_fmask;
-	inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask);
+	error = inode_setattr(inode, attr);
 out:
 	unlock_kernel();
 	return error;
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/jbd2/commit.c b/fs/jbd2/commit.c
index 4d99685fdce4..a2ed72f7ceee 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -168,6 +168,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		spin_unlock(&journal->j_state_lock);
 
 		/* And try again, without the barrier */
+		lock_buffer(bh);
 		set_buffer_uptodate(bh);
 		set_buffer_dirty(bh);
 		ret = submit_bh(WRITE, bh);
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 5d0405a9e7ca..058f50f65b76 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -344,6 +344,7 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh,
 			*crc32_sum = crc32_be(*crc32_sum, (void *)obh->b_data,
 				     obh->b_size);
 		}
+		put_bh(obh);
 	}
 	return 0;
 }
@@ -610,9 +611,8 @@ static int do_one_pass(journal_t *journal,
 				chksum_err = chksum_seen = 0;
 
 				if (info->end_transaction) {
-					printk(KERN_ERR "JBD: Transaction %u "
-						"found to be corrupt.\n",
-						next_commit_ID - 1);
+					journal->j_failed_commit =
+						info->end_transaction;
 					brelse(bh);
 					break;
 				}
@@ -643,10 +643,8 @@ static int do_one_pass(journal_t *journal,
 
 					if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
 					   JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)){
-						printk(KERN_ERR
-						       "JBD: Transaction %u "
-						       "found to be corrupt.\n",
-						       next_commit_ID);
+						journal->j_failed_commit =
+							next_commit_ID;
 						brelse(bh);
 						break;
 					}
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..ab8ccc9d14ff 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -315,9 +315,9 @@ struct mem_size_stats {
 };
 
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			   void *private)
+			   struct mm_walk *walk)
 {
-	struct mem_size_stats *mss = private;
+	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = mss->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
@@ -365,19 +365,21 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return 0;
 }
 
-static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range };
-
 static int show_smap(struct seq_file *m, void *v)
 {
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	int ret;
+	struct mm_walk smaps_walk = {
+		.pmd_entry = smaps_pte_range,
+		.mm = vma->vm_mm,
+		.private = &mss,
+	};
 
 	memset(&mss, 0, sizeof mss);
 	mss.vma = vma;
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
-		walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
-				&smaps_walk, &mss);
+		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
 	ret = show_map(m, v);
 	if (ret)
@@ -426,9 +428,9 @@ const struct file_operations proc_smaps_operations = {
 };
 
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
-				unsigned long end, void *private)
+				unsigned long end, struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = private;
+	struct vm_area_struct *vma = walk->private;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
@@ -452,8 +454,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
-static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };
-
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -476,11 +476,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		return -ESRCH;
 	mm = get_task_mm(task);
 	if (mm) {
+		static struct mm_walk clear_refs_walk;
+		memset(&clear_refs_walk, 0, sizeof(clear_refs_walk));
+		clear_refs_walk.pmd_entry = clear_refs_pte_range;
+		clear_refs_walk.mm = mm;
 		down_read(&mm->mmap_sem);
-		for (vma = mm->mmap; vma; vma = vma->vm_next)
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			clear_refs_walk.private = vma;
 			if (!is_vm_hugetlb_page(vma))
-				walk_page_range(mm, vma->vm_start, vma->vm_end,
-						&clear_refs_walk, vma);
+				walk_page_range(vma->vm_start, vma->vm_end,
+						&clear_refs_walk);
+		}
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
 		mmput(mm);
@@ -496,7 +502,7 @@ const struct file_operations proc_clear_refs_operations = {
 };
 
 struct pagemapread {
-	char __user *out, *end;
+	u64 __user *out, *end;
 };
 
 #define PM_ENTRY_BYTES      sizeof(u64)
@@ -519,28 +525,18 @@ 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;
 }
 
 static int pagemap_pte_hole(unsigned long start, unsigned long end,
-				void *private)
+				struct mm_walk *walk)
 {
-	struct pagemapread *pm = private;
+	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
@@ -557,24 +553,45 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
+static unsigned long pte_to_pagemap_entry(pte_t pte)
+{
+	unsigned long pme = 0;
+	if (is_swap_pte(pte))
+		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+	else if (pte_present(pte))
+		pme = PM_PFRAME(pte_pfn(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+	return pme;
+}
+
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			     void *private)
+			     struct mm_walk *walk)
 {
-	struct pagemapread *pm = private;
+	struct vm_area_struct *vma;
+	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
 
+	/* find the first VMA at or above 'addr' */
+	vma = find_vma(walk->mm, addr);
 	for (; addr != end; addr += PAGE_SIZE) {
 		u64 pfn = PM_NOT_PRESENT;
-		pte = pte_offset_map(pmd, addr);
-		if (is_swap_pte(*pte))
-			pfn = PM_PFRAME(swap_pte_to_pagemap_entry(*pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
-		else if (pte_present(*pte))
-			pfn = PM_PFRAME(pte_pfn(*pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-		/* unmap so we're not in atomic when we copy to userspace */
-		pte_unmap(pte);
+
+		/* check to see if we've left 'vma' behind
+		 * and need a new, higher one */
+		if (vma && (addr >= vma->vm_end))
+			vma = find_vma(walk->mm, addr);
+
+		/* check that 'vma' actually covers this address,
+		 * and that it isn't a huge page vma */
+		if (vma && (vma->vm_start <= addr) &&
+		    !is_vm_hugetlb_page(vma)) {
+			pte = pte_offset_map(pmd, addr);
+			pfn = pte_to_pagemap_entry(*pte);
+			/* unmap before userspace copy */
+			pte_unmap(pte);
+		}
 		err = add_to_pagemap(addr, pfn, pm);
 		if (err)
 			return err;
@@ -634,7 +651,7 @@ 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 +681,8 @@ 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;
@@ -685,14 +702,14 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		 * user buffer is tracked in "pm", and the walk
 		 * will stop when we hit the end of the buffer.
 		 */
-		ret = walk_page_range(mm, start_vaddr, end_vaddr,
-					&pagemap_walk, &pm);
+		ret = walk_page_range(start_vaddr, end_vaddr,
+					&pagemap_walk);
 		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,