84 files changed, 1072 insertions, 816 deletions
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index fd01d90cada5..57997fa14e69 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -51,4 +51,4 @@ int v9fs_dir_release(struct inode *inode, struct file *filp);
 int v9fs_file_open(struct inode *inode, struct file *file);
 void v9fs_inode2stat(struct inode *inode, struct p9_stat *stat);
 void v9fs_dentry_release(struct dentry *);
-int v9fs_uflags2omode(int uflags);
+int v9fs_uflags2omode(int uflags, int extended);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 0d55affe37d4..52944d2249a4 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -59,7 +59,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
        P9_DPRINTK(P9_DEBUG_VFS, "inode: %p file: %p \n", inode, file);
        v9ses = v9fs_inode2v9ses(inode);
-        omode = v9fs_uflags2omode(file->f_flags);
+        omode = v9fs_uflags2omode(file->f_flags, v9fs_extended(v9ses));
        fid = file->private_data;
        if (!fid) {
                fid = v9fs_fid_clone(file->f_path.dentry);
@@ -75,6 +75,8 @@ int v9fs_file_open(struct inode *inode, struct file *file)
                        inode->i_size = 0;
                        inode->i_blocks = 0;
                }
+                if ((file->f_flags & O_APPEND) && (!v9fs_extended(v9ses)))
+                        generic_file_llseek(file, 0, SEEK_END);
        }
        file->private_data = fid;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 40fa807bd929..c95295c65045 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -132,10 +132,10 @@ static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode)
 /**
 * v9fs_uflags2omode- convert posix open flags to plan 9 mode bits
 * @uflags: flags to convert
- *
+ * @extended: if .u extensions are active
 */
-int v9fs_uflags2omode(int uflags)
+int v9fs_uflags2omode(int uflags, int extended)
 {
        int ret;
@@ -155,14 +155,16 @@ int v9fs_uflags2omode(int uflags)
                break;
        }
-        if (uflags & O_EXCL)
-                ret |= P9_OEXCL;
        if (uflags & O_TRUNC)
                ret |= P9_OTRUNC;
-        if (uflags & O_APPEND)
+        if (extended) {
-                ret |= P9_OAPPEND;
+                if (uflags & O_EXCL)
+                        ret |= P9_OEXCL;
+                if (uflags & O_APPEND)
+                        ret |= P9_OAPPEND;
+        }
        return ret;
 }
@@ -506,7 +508,7 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode,
                flags = O_RDWR;
        fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
-                                                v9fs_uflags2omode(flags));
+                                v9fs_uflags2omode(flags, v9fs_extended(v9ses)));
        if (IS_ERR(fid)) {
                err = PTR_ERR(fid);
                fid = NULL;
diff --git a/fs/Kconfig b/fs/Kconfig
index cf12c403b8c7..2694648cbd1b 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -830,7 +830,7 @@ config NTFS_FS
          from the project web site.
          For more information see <file:Documentation/filesystems/ntfs.txt>
-          and <http://linux-ntfs.sourceforge.net/>.
+          and <http://www.linux-ntfs.org/>.
          To compile this file system support as a module, choose M here: the
          module will be called ntfs.
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.c b/fs/binfmt_elf.c
index 0fa95b198e6e..d48ff5f370f4 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -16,7 +16,6 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
-#include <linux/a.out.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/binfmts.h>
@@ -548,7 +547,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
        struct {
                struct elfhdr elf_ex;
                struct elfhdr interp_elf_ex;
-                struct exec interp_ex;
        } *loc;
        loc = kmalloc(sizeof(*loc), GFP_KERNEL);
@@ -680,7 +678,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                        }
                        /* Get the exec headers */
-                        loc->interp_ex = *((struct exec *)bprm->buf);
                        loc->interp_elf_ex = *((struct elfhdr *)bprm->buf);
                        break;
                }
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..10d8a0aa871a 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 +929,22 @@ 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;
+        int perm = 0;
+        if (file->f_mode & FMODE_READ)
+                perm |= MAY_READ;
+        if (file->f_mode & FMODE_WRITE)
+                perm |= MAY_WRITE;
+        /*
+         * hooks: /n/, see "layering violations".
+         */
+        ret = devcgroup_inode_permission(bdev->bd_inode, perm);
+        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/buffer.c b/fs/buffer.c
index a073f3f4f013..0f51c0f7c266 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -821,7 +821,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
                                 * contents - it is a noop if I/O is still in
                                 * flight on potentially older contents.
                                 */
-                                ll_rw_block(SWRITE, 1, &bh);
+                                ll_rw_block(SWRITE_SYNC, 1, &bh);
                                brelse(bh);
                                spin_lock(lock);
                        }
@@ -2940,16 +2940,19 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
        for (i = 0; i < nr; i++) {
                struct buffer_head *bh = bhs[i];
-                if (rw == SWRITE)
+                if (rw == SWRITE || rw == SWRITE_SYNC)
                        lock_buffer(bh);
                else if (test_set_buffer_locked(bh))
                        continue;
-                if (rw == WRITE || rw == SWRITE) {
+                if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
                        if (test_clear_buffer_dirty(bh)) {
                                bh->b_end_io = end_buffer_write_sync;
                                get_bh(bh);
-                                submit_bh(WRITE, bh);
+                                if (rw == SWRITE_SYNC)
+                                        submit_bh(WRITE_SYNC, bh);
+                                else
+                                        submit_bh(WRITE, bh);
                                continue;
                        }
                } else {
@@ -2978,7 +2981,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
        if (test_clear_buffer_dirty(bh)) {
                get_bh(bh);
                bh->b_end_io = end_buffer_write_sync;
-                ret = submit_bh(WRITE, bh);
+                ret = submit_bh(WRITE_SYNC, bh);
                wait_on_buffer(bh);
                if (buffer_eopnotsupp(bh)) {
                        clear_buffer_eopnotsupp(bh);
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);
+        if (data) {
-        cifs_sb->mountdata = kzalloc(len + 1, GFP_KERNEL);
+                int len = strlen(data);
-        if (cifs_sb->mountdata == NULL) {
+                cifs_sb->mountdata = kzalloc(len + 1, GFP_KERNEL);
-                kfree(sb->s_fs_info);
+                if (cifs_sb->mountdata == NULL) {
-                sb->s_fs_info = NULL;
+                        kfree(sb->s_fs_info);
-                return -ENOMEM;
+                        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
+                                                 "open for recovery" flag - should
-                                                 be zero */
+                                                 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 */
+        /* get default inode mode */
-        if (atomic_read(&cifsInfo->inUse) == 0)
+        if (attr & ATTR_DIRECTORY)
-                /* new inode, can safely set these fields */
+                default_mode = cifs_sb->mnt_dir_mode;
-                inode->i_mode = cifs_sb->mnt_file_mode;
+        else
-        else /* since we set the inode type below we need to mask off
+                default_mode = cifs_sb->mnt_file_mode;
-             to avoid strange results if type changes and both
-             get orred in */
+        /* set permission bits */
-                inode->i_mode &= ~S_IFMT;
+        if (atomic_read(&cifsInfo->inUse) == 0 ||
-/*      if (attr & ATTR_REPARSE)  */
+            (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
-        /* We no longer handle these as symlinks because we could not
+                inode->i_mode = default_mode;
-           follow them due to the absolute path with drive letter */
+        else {
-        if (attr & ATTR_DIRECTORY) {
+                /* just reenable write bits if !ATTR_READONLY */
-        /* override default perms since we do not do byte range locking
+                if ((inode->i_mode & S_IWUGO) == 0 &&
-           on dirs */
+                    (attr & ATTR_READONLY) == 0)
-                inode->i_mode = cifs_sb->mnt_dir_mode;
+                        inode->i_mode |= (S_IWUGO & default_mode);
-                inode->i_mode |= S_IFDIR;
+                        inode->i_mode &= ~S_IFMT;
-        } else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) &&
+        }
-                   (cifsInfo->cifsAttrs & ATTR_SYSTEM) &&
+        /* clear write bits if ATTR_READONLY is set */
-                   /* No need to le64 convert size of zero */
+        if (attr & ATTR_READONLY)
-                   (pfindData->EndOfFile == 0)) {
+                inode->i_mode &= ~S_IWUGO;
-                inode->i_mode = cifs_sb->mnt_file_mode;
-                inode->i_mode |= S_IFIFO;
+        /* set inode type */
-/* BB Finish for SFU style symlinks and devices */
+        if ((attr & ATTR_SYSTEM) &&
-        } else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) &&
+            (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) {
-                   (cifsInfo->cifsAttrs & ATTR_SYSTEM)) {
+                /* no need to fix endianness on 0 */
-                if (decode_sfu_inode(inode, le64_to_cpu(pfindData->EndOfFile),
+                if (pfindData->EndOfFile == 0)
-                                     full_path, cifs_sb, xid))
+                        inode->i_mode |= S_IFIFO;
-                        cFYI(1, ("Unrecognized sfu inode type"));
+                else if (decode_sfu_inode(inode,
+                                le64_to_cpu(pfindData->EndOfFile),
-                cFYI(1, ("sfu mode 0%o", inode->i_mode));
+                                full_path, cifs_sb, xid))
+                        cFYI(1, ("unknown SFU file type\n"));
        } else {
-                inode->i_mode |= S_IFREG;
+                if (attr & ATTR_DIRECTORY)
-                /* treat dos attribute of read-only as read-only mode eg 555 */
+                        inode->i_mode |= S_IFDIR;
-                if (cifsInfo->cifsAttrs & ATTR_READONLY)
+                else
-                        inode->i_mode &= ~(S_IWUGO);
+                        inode->i_mode |= S_IFREG;
-                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? */
        }
        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;
+                                if (cifs_sb->mnt_cifs_flags &
-                                direntry->d_inode->i_mode |= S_IFDIR;
+                                     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;
+         * Without unix extensions we can't send ownership changes to the
-        }
+         * server, so silently ignore them. This is consistent with how
-        if (attrs->ia_valid & ATTR_GID) {
+         * local DOS/Windows filesystems behave (VFAT, NTFS, etc). With
-                cFYI(1, ("GID changed to %d", attrs->ia_gid));
+         * CIFSACL support + proper Windows to Unix idmapping, we may be
-                gid = attrs->ia_gid;
+         * 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
-#else
-                if ((mode & S_IWUGO) == 0) {
 #endif
-                        /* not writeable */
+                if (((mode & S_IWUGO) == 0) &&
-                        if ((cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
+                    (cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
-                                set_dosattr = true;
+                        set_dosattr = true;
-                                time_buf.Attributes =
+                        time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs |
-                                        cpu_to_le32(cifsInode->cifsAttrs |
+                                                          ATTR_READONLY);
-                                                    ATTR_READONLY);
+                        /* fix up mode if we're not using dynperm */
-                        }
+                        if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
-                } else if (cifsInode->cifsAttrs & ATTR_READONLY) {
+                                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->FileName, pnotify->Action));
-                                pnotify->Action));  /* BB removeme BB */
                        /*   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 {
+        if (attr & ATTR_DIRECTORY)
-                /* mask off the type bits since it gets set
+                default_mode = cifs_sb->mnt_dir_mode;
-                below and we do not want to get two type
+        else
-                bits set */
+                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) {
+        /* clear write bits if ATTR_READONLY is set */
-                *pobject_type = DT_DIR;
+        if (attr & ATTR_READONLY)
-                /* override default perms since we do not lock dirs */
+                tmp_inode->i_mode &= ~S_IWUGO;
-                if (atomic_read(&cifsInfo->inUse) == 0)
-                        tmp_inode->i_mode = cifs_sb->mnt_dir_mode;
+        /* set inode type */
-                tmp_inode->i_mode |= S_IFDIR;
+        if ((attr & ATTR_SYSTEM) &&
-        } else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) &&
+            (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) {
-                   (attr & ATTR_SYSTEM)) {
                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
+                         * trying to get the type can be slow, so just call
-                        (blk vs chr vs. symlink) later ie in lookup */
+                         * this a regular file for now, and mark for reval
-                        *pobject_type = DT_REG;
+                         */
                        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;
+                if (attr & ATTR_DIRECTORY) {
-                tmp_inode->i_mode |= S_IFREG;
+                        tmp_inode->i_mode |= S_IFDIR;
-                if (attr & ATTR_READONLY)
+                        *pobject_type = DT_DIR;
-                        tmp_inode->i_mode &= ~(S_IWUGO);
+                } else {
-                else if ((tmp_inode->i_mode & S_IWUGO) == 0)
+                        tmp_inode->i_mode |= S_IFREG;
-                        /* the ATTR_READONLY flag may have been changed on   */
+                        *pobject_type = DT_REG;
-                        /* 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? */
        /* 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/dcache.c b/fs/dcache.c
index 3ee588d5f585..6068c25b393c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -17,6 +17,7 @@
 #include <linux/syscalls.h>
 #include <linux/string.h>
 #include <linux/mm.h>
+#include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/slab.h>
@@ -106,9 +107,10 @@ static void dentry_lru_remove(struct dentry *dentry)
 /*
 * Release the dentry's inode, using the filesystem
 * d_iput() operation if defined.
- * Called with dcache_lock and per dentry lock held, drops both.
 */
 static void dentry_iput(struct dentry * dentry)
+        __releases(dentry->d_lock)
+        __releases(dcache_lock)
 {
        struct inode *inode = dentry->d_inode;
        if (inode) {
@@ -132,12 +134,13 @@ static void dentry_iput(struct dentry * dentry)
 * d_kill - kill dentry and return parent
 * @dentry: dentry to kill
 *
- * Called with dcache_lock and d_lock, releases both.  The dentry must
+ * The dentry must already be unhashed and removed from the LRU.
- * already be unhashed and removed from the LRU.
 *
 * If this is the root of the dentry tree, return NULL.
 */
 static struct dentry *d_kill(struct dentry *dentry)
+        __releases(dentry->d_lock)
+        __releases(dcache_lock)
 {
        struct dentry *parent;
@@ -383,11 +386,11 @@ restart:
 * Try to prune ancestors as well.  This is necessary to prevent
 * quadratic behavior of shrink_dcache_parent(), but is also expected
 * to be beneficial in reducing dentry cache fragmentation.
- *
- * Called with dcache_lock, drops it and then regains.
- * Called with dentry->d_lock held, drops it.
 */
 static void prune_one_dentry(struct dentry * dentry)
+        __releases(dentry->d_lock)
+        __releases(dcache_lock)
+        __acquires(dcache_lock)
 {
        __d_drop(dentry);
        dentry = d_kill(dentry);
@@ -1604,10 +1607,9 @@ static int d_isparent(struct dentry *p1, struct dentry *p2)
 *
 * Note: If ever the locking in lock_rename() changes, then please
 * remember to update this too...
- *
- * On return, dcache_lock will have been unlocked.
 */
 static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
+        __releases(dcache_lock)
 {
        struct mutex *m1 = NULL, *m2 = NULL;
        struct dentry *ret;
@@ -1743,11 +1745,9 @@ out_nolock:
 shouldnt_be_hashed:
        spin_unlock(&dcache_lock);
        BUG();
-        goto shouldnt_be_hashed;
 }
-static int prepend(char **buffer, int *buflen, const char *str,
+static int prepend(char **buffer, int *buflen, const char *str, int namelen)
-                          int namelen)
 {
        *buflen -= namelen;
        if (*buflen < 0)
@@ -1757,8 +1757,13 @@ static int prepend(char **buffer, int *buflen, const char *str,
        return 0;
 }
+static int prepend_name(char **buffer, int *buflen, struct qstr *name)
+{
+        return prepend(buffer, buflen, name->name, name->len);
+}
 /**
- * d_path - return the path of a dentry
+ * __d_path - return the path of a dentry
 * @path: the dentry/vfsmount to report
 * @root: root vfsmnt/dentry (may be modified by this function)
 * @buffer: buffer to return value in
@@ -1779,9 +1784,10 @@ char *__d_path(const struct path *path, struct path *root,
 {
        struct dentry *dentry = path->dentry;
        struct vfsmount *vfsmnt = path->mnt;
-        char * end = buffer+buflen;
+        char *end = buffer + buflen;
-        char * retval;
+        char *retval;
+        spin_lock(&vfsmount_lock);
        prepend(&end, &buflen, "\0", 1);
        if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
                (prepend(&end, &buflen, " (deleted)", 10) != 0))
@@ -1800,38 +1806,37 @@ char *__d_path(const struct path *path, struct path *root,
                        break;
                if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
                        /* Global root? */
-                        spin_lock(&vfsmount_lock);
                        if (vfsmnt->mnt_parent == vfsmnt) {
-                                spin_unlock(&vfsmount_lock);
                                goto global_root;
                        }
                        dentry = vfsmnt->mnt_mountpoint;
                        vfsmnt = vfsmnt->mnt_parent;
-                        spin_unlock(&vfsmount_lock);
                        continue;
                }
                parent = dentry->d_parent;
                prefetch(parent);
-                if ((prepend(&end, &buflen, dentry->d_name.name,
+                if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
-                                dentry->d_name.len) != 0) ||
                    (prepend(&end, &buflen, "/", 1) != 0))
                        goto Elong;
                retval = end;
                dentry = parent;
        }
+out:
+        spin_unlock(&vfsmount_lock);
        return retval;
 global_root:
        retval += 1;    /* hit the slash */
-        if (prepend(&retval, &buflen, dentry->d_name.name,
+        if (prepend_name(&retval, &buflen, &dentry->d_name) != 0)
-                    dentry->d_name.len) != 0)
                goto Elong;
        root->mnt = vfsmnt;
        root->dentry = dentry;
-        return retval;
+        goto out;
 Elong:
-        return ERR_PTR(-ENAMETOOLONG);
+        retval = ERR_PTR(-ENAMETOOLONG);
+        goto out;
 }
 /**
@@ -1845,9 +1850,9 @@ Elong:
 *
 * Returns the buffer or an error code if the path was too long.
 *
- * "buflen" should be positive. Caller holds the dcache_lock.
+ * "buflen" should be positive.
 */
-char *d_path(struct path *path, char *buf, int buflen)
+char *d_path(const struct path *path, char *buf, int buflen)
 {
        char *res;
        struct path root;
@@ -1915,16 +1920,11 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen)
        retval = end-1;
        *retval = '/';
-        for (;;) {
+        while (!IS_ROOT(dentry)) {
-                struct dentry *parent;
+                struct dentry *parent = dentry->d_parent;
-                if (IS_ROOT(dentry))
-                        break;
-                parent = dentry->d_parent;
                prefetch(parent);
+                if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
-                if ((prepend(&end, &buflen, dentry->d_name.name,
-                                dentry->d_name.len) != 0) ||
                    (prepend(&end, &buflen, "/", 1) != 0))
                        goto Elong;
@@ -1975,7 +1975,7 @@ asmlinkage long sys_getcwd(char __user *buf, unsigned long size)
        error = -ENOENT;
        /* Has the current directory has been unlinked? */
        spin_lock(&dcache_lock);
-        if (pwd.dentry->d_parent == pwd.dentry || !d_unhashed(pwd.dentry)) {
+        if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) {
                unsigned long len;
                struct path tmp = root;
                char * cwd;
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/miscdev.c b/fs/ecryptfs/miscdev.c
index 50c994a249a5..09a4522f65e6 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -575,13 +575,11 @@ int ecryptfs_init_ecryptfs_miscdev(void)
        int rc;
        atomic_set(&ecryptfs_num_miscdev_opens, 0);
-        mutex_lock(&ecryptfs_daemon_hash_mux);
        rc = misc_register(&ecryptfs_miscdev);
        if (rc)
                printk(KERN_ERR "%s: Failed to register miscellaneous device "
                       "for communications with userspace daemons; rc = [%d]\n",
                       __func__, rc);
-        mutex_unlock(&ecryptfs_daemon_hash_mux);
        return rc;
 }
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..da94a6f05df3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -26,7 +26,6 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/mman.h>
-#include <linux/a.out.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/smp_lock.h>
@@ -61,6 +60,11 @@
 #include <linux/kmod.h>
 #endif
+#ifdef __alpha__
+/* for /sbin/loader handling in search_binary_handler() */
+#include <linux/a.out.h>
+#endif
 int core_uses_pid;
 char core_pattern[CORENAME_MAX_SIZE] = "core";
 int suid_dumpable = 0;
@@ -860,6 +864,7 @@ static int de_thread(struct task_struct *tsk)
 no_thread_group:
        exit_itimers(sig);
+        flush_itimer_signals();
        if (leader)
                release_task(leader);
@@ -1154,7 +1159,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 {
        int try,retval;
        struct linux_binfmt *fmt;
-#if defined(__alpha__) && defined(CONFIG_ARCH_SUPPORTS_AOUT)
+#ifdef __alpha__
        /* handle /sbin/loader.. */
        {
            struct exec * eh = (struct exec *) bprm->buf;
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/ext3/super.c b/fs/ext3/super.c
index fe3119a71ada..2845425077e8 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2875,8 +2875,10 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type,
                blk++;
        }
 out:
-        if (len == towrite)
+        if (len == towrite) {
+                mutex_unlock(&inode->i_mutex);
                return err;
+        }
        if (inode->i_size < off+len-towrite) {
                i_size_write(inode, off+len-towrite);
                EXT3_I(inode)->i_disksize = inode->i_size;
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 */
+                if (EXT4_HAS_INCOMPAT_FEATURE(sb,
-                ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data);
+                                              EXT4_FEATURE_INCOMPAT_FLEX_BG))
-                ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data);
+                        flex_bg = 1;
-                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);
+                /* 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 - ext4_group_used_meta_blocks(sb, block_group);
-        return free_blocks - sbi->s_itb_per_group - 2;
 }
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..9ff7b1c04239 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 */
@@ -854,7 +855,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         */
        /* Update group descriptor block for new group */
-        gdp = (struct ext4_group_desc *)primary->b_data + gdb_off;
+        gdp = (struct ext4_group_desc *)((char *)primary->b_data +
+                                         gdb_off * EXT4_DESC_SIZE(sb));
        ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
        ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 09d9359c8055..02bf24343979 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;
@@ -3305,8 +3337,10 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
                blk++;
        }
 out:
-        if (len == towrite)
+        if (len == towrite) {
+                mutex_unlock(&inode->i_mutex);
                return err;
+        }
        if (inode->i_size < off+len-towrite) {
                i_size_write(inode, off+len-towrite);
                EXT4_I(inode)->i_disksize = inode->i_size;
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,
+static int fat_sanitize_mode(const struct msdos_sb_info *sbi,
-                          mode_t mode)
+                             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 ((perm & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO)))
-        if ((req & (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)
+         * We don't return -EPERM here. Yes, strange, but this is too
-                goto out;
+         * 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))
+        error = inode_setattr(inode, attr);
-                mask = sbi->options.fs_dmask;
-        else
-                mask = sbi->options.fs_fmask;
-        inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask);
 out:
        unlock_kernel();
        return error;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index fb77e0962132..3141690558c8 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;
                /*
@@ -586,7 +591,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
                fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
                fc->minor = arg->minor;
                fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
-                fc->max_write = min_t(unsigned, 4096, fc->max_write);
+                fc->max_write = max_t(unsigned, 4096, fc->max_write);
                fc->conn_init = 1;
        }
        fuse_put_request(fc, req);
@@ -662,7 +667,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
        fc->flags = d.flags;
        fc->user_id = d.user_id;
        fc->group_id = d.group_id;
-        fc->max_read = min_t(unsigned, 4096, d.max_read);
+        fc->max_read = max_t(unsigned, 4096, d.max_read);
        /* Used by get_root_inode() */
        sb->s_fs_info = fc;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index c19184f2e70e..bec76b1c2bb0 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -246,15 +246,11 @@ static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
 }
-static inline unsigned int zero_metapath_length(const struct metapath *mp,
+static inline unsigned int metapath_branch_start(const struct metapath *mp)
-                                                unsigned height)
 {
-        unsigned int i;
+        if (mp->mp_list[0] == 0)
-        for (i = 0; i < height - 1; i++) {
+                return 2;
-                if (mp->mp_list[i] != 0)
+        return 1;
-                        return i;
-        }
-        return height;
 }
 /**
@@ -436,7 +432,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
        struct gfs2_sbd *sdp = GFS2_SB(inode);
        struct buffer_head *dibh = mp->mp_bh[0];
        u64 bn, dblock = 0;
-        unsigned n, i, blks, alloced = 0, iblks = 0, zmpl = 0;
+        unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
        unsigned dblks = 0;
        unsigned ptrs_per_blk;
        const unsigned end_of_metadata = height - 1;
@@ -471,9 +467,8 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
                        /* Building up tree height */
                        state = ALLOC_GROW_HEIGHT;
                        iblks = height - ip->i_height;
-                        zmpl = zero_metapath_length(mp, height);
+                        branch_start = metapath_branch_start(mp);
-                        iblks -= zmpl;
+                        iblks += (height - branch_start);
-                        iblks += height;
                }
        }
@@ -509,13 +504,13 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
                                        sizeof(struct gfs2_meta_header));
                                *ptr = zero_bn;
                                state = ALLOC_GROW_DEPTH;
-                                for(i = zmpl; i < height; i++) {
+                                for(i = branch_start; i < height; i++) {
                                        if (mp->mp_bh[i] == NULL)
                                                break;
                                        brelse(mp->mp_bh[i]);
                                        mp->mp_bh[i] = NULL;
                                }
-                                i = zmpl;
+                                i = branch_start;
                        }
                        if (n == 0)
                                break;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 6387523a3153..3401628d742b 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -195,7 +195,7 @@ ulong_aligned:
           depending on architecture.  I've experimented with several ways
           of writing this section such as using an else before the goto
           but this one seems to be the fastest. */
-        while ((unsigned char *)plong < end - 1) {
+        while ((unsigned char *)plong < end - sizeof(unsigned long)) {
                prefetch(plong + 1);
                if (((*plong) & LBITMASK) != lskipval)
                        break;
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 "
+                                        journal->j_failed_commit =
-                                                "found to be corrupt.\n",
+                                                info->end_transaction;
-                                                next_commit_ID - 1);
                                        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
+                                                journal->j_failed_commit =
-                                                       "JBD: Transaction %u "
+                                                        next_commit_ID;
-                                                       "found to be corrupt.\n",
-                                                       next_commit_ID);
                                                brelse(bh);
                                                break;
                                        }
diff --git a/fs/libfs.c b/fs/libfs.c
index b004dfadd891..baeb71ee1cde 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -512,6 +512,20 @@ void simple_release_fs(struct vfsmount **mount, int *count)
        mntput(mnt);
 }
+/**
+ * simple_read_from_buffer - copy data from the buffer to user space
+ * @to: the user space buffer to read to
+ * @count: the maximum number of bytes to read
+ * @ppos: the current position in the buffer
+ * @from: the buffer to read from
+ * @available: the size of the buffer
+ *
+ * The simple_read_from_buffer() function reads up to @count bytes from the
+ * buffer @from at offset @ppos into the user space address starting at @to.
+ *
+ * On success, the number of bytes read is returned and the offset @ppos is
+ * advanced by this number, or negative value is returned on error.
+ **/
 ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
                                const void *from, size_t available)
 {
@@ -528,6 +542,37 @@ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
        return count;
 }
+/**
+ * memory_read_from_buffer - copy data from the buffer
+ * @to: the kernel space buffer to read to
+ * @count: the maximum number of bytes to read
+ * @ppos: the current position in the buffer
+ * @from: the buffer to read from
+ * @available: the size of the buffer
+ *
+ * The memory_read_from_buffer() function reads up to @count bytes from the
+ * buffer @from at offset @ppos into the kernel space address starting at @to.
+ *
+ * On success, the number of bytes read is returned and the offset @ppos is
+ * advanced by this number, or negative value is returned on error.
+ **/
+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 +845,7 @@ 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/locks.c b/fs/locks.c
index 11dbf08651b7..dce8c747371c 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -561,9 +561,6 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
        /* insert into file's list */
        fl->fl_next = *pos;
        *pos = fl;
-        if (fl->fl_ops && fl->fl_ops->fl_insert)
-                fl->fl_ops->fl_insert(fl);
 }
 /*
@@ -586,9 +583,6 @@ static void locks_delete_lock(struct file_lock **thisfl_p)
                fl->fl_fasync = NULL;
        }
-        if (fl->fl_ops && fl->fl_ops->fl_remove)
-                fl->fl_ops->fl_remove(fl);
        if (fl->fl_nspid) {
                put_pid(fl->fl_nspid);
                fl->fl_nspid = NULL;
diff --git a/fs/namei.c b/fs/namei.c
index c7e43536c49a..01e67dddcc3d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -581,15 +581,13 @@ static __always_inline int link_path_walk(const char *name, struct nameidata *nd
        int result;
        /* make sure the stuff we saved doesn't go away */
-        dget(save.dentry);
+        path_get(&save);
-        mntget(save.mnt);
        result = __link_path_walk(name, nd);
        if (result == -ESTALE) {
                /* nd->path had been dropped */
                nd->path = save;
-                dget(nd->path.dentry);
+                path_get(&nd->path);
-                mntget(nd->path.mnt);
                nd->flags |= LOOKUP_REVAL;
                result = __link_path_walk(name, nd);
        }
@@ -1216,8 +1214,9 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
        nd->flags = flags;
        nd->depth = 0;
-        nd->path.mnt = mntget(mnt);
+        nd->path.dentry = dentry;
-        nd->path.dentry = dget(dentry);
+        nd->path.mnt = mnt;
+        path_get(&nd->path);
        retval = path_walk(name, nd);
        if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
@@ -2857,16 +2856,17 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
        struct nameidata nd;
        void *cookie;
+        int res;
        nd.depth = 0;
        cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
-        if (!IS_ERR(cookie)) {
+        if (IS_ERR(cookie))
-                int res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+                return PTR_ERR(cookie);
-                if (dentry->d_inode->i_op->put_link)
-                        dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+        res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
-                cookie = ERR_PTR(res);
+        if (dentry->d_inode->i_op->put_link)
-        }
+                dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
-        return PTR_ERR(cookie);
+        return res;
 }
 int vfs_follow_link(struct nameidata *nd, const char *link)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 58d43daec084..982a2064fe4c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -204,7 +204,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
         * Note: assumes we have exclusive access to this mapping either
         *       through inode->i_mutex or some other mechanism.
         */
-        if (page->index == 0 && invalidate_inode_pages2_range(inode->i_mapping, PAGE_CACHE_SIZE, -1) < 0) {
+        if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
                /* Should never happen */
                nfs_zap_mapping(inode, inode->i_mapping);
        }
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 49c7cd0502cc..779d2eb649c5 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -130,10 +130,11 @@ static int xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p,
                                struct mnt_fhstatus *res)
 {
        struct nfs_fh *fh = res->fh;
+        unsigned size;
        if ((res->status = ntohl(*p++)) == 0) {
-                int size = ntohl(*p++);
+                size = ntohl(*p++);
-                if (size <= NFS3_FHSIZE) {
+                if (size <= NFS3_FHSIZE && size != 0) {
                        fh->size = size;
                        memcpy(fh->data, p, size);
                } else
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2a4a024a4e7b..614efeed5437 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1216,8 +1216,6 @@ static int nfs_validate_mount_data(void *options,
 {
        struct nfs_mount_data *data = (struct nfs_mount_data *)options;
-        memset(args, 0, sizeof(*args));
        if (data == NULL)
                goto out_no_data;
@@ -1251,13 +1249,13 @@ static int nfs_validate_mount_data(void *options,
        case 5:
                memset(data->context, 0, sizeof(data->context));
        case 6:
-                if (data->flags & NFS_MOUNT_VER3)
+                if (data->flags & NFS_MOUNT_VER3) {
+                        if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
+                                goto out_invalid_fh;
                        mntfh->size = data->root.size;
-                else
+                } else
                        mntfh->size = NFS2_FHSIZE;
-                if (mntfh->size > sizeof(mntfh->data))
-                        goto out_invalid_fh;
                memcpy(mntfh->data, data->root.data, mntfh->size);
                if (mntfh->size < sizeof(mntfh->data))
@@ -1585,24 +1583,29 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 {
        struct nfs_server *server = NULL;
        struct super_block *s;
-        struct nfs_fh mntfh;
+        struct nfs_parsed_mount_data *data;
-        struct nfs_parsed_mount_data data;
+        struct nfs_fh *mntfh;
        struct dentry *mntroot;
        int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
        struct nfs_sb_mountdata sb_mntdata = {
                .mntflags = flags,
        };
-        int error;
+        int error = -ENOMEM;
+        data = kzalloc(sizeof(*data), GFP_KERNEL);
+        mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL);
+        if (data == NULL || mntfh == NULL)
+                goto out_free_fh;
-        security_init_mnt_opts(&data.lsm_opts);
+        security_init_mnt_opts(&data->lsm_opts);
        /* Validate the mount data */
-        error = nfs_validate_mount_data(raw_data, &data, &mntfh, dev_name);
+        error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name);
        if (error < 0)
                goto out;
        /* Get a volume representation */
-        server = nfs_create_server(&data, &mntfh);
+        server = nfs_create_server(data, mntfh);
        if (IS_ERR(server)) {
                error = PTR_ERR(server);
                goto out;
@@ -1630,16 +1633,16 @@ static int nfs_get_sb(struct file_system_type *fs_type,
        if (!s->s_root) {
                /* initial superblock/root creation */
-                nfs_fill_super(s, &data);
+                nfs_fill_super(s, data);
        }
-        mntroot = nfs_get_root(s, &mntfh);
+        mntroot = nfs_get_root(s, mntfh);
        if (IS_ERR(mntroot)) {
                error = PTR_ERR(mntroot);
                goto error_splat_super;
        }
-        error = security_sb_set_mnt_opts(s, &data.lsm_opts);
+        error = security_sb_set_mnt_opts(s, &data->lsm_opts);
        if (error)
                goto error_splat_root;
@@ -1649,9 +1652,12 @@ static int nfs_get_sb(struct file_system_type *fs_type,
        error = 0;
 out:
-        kfree(data.nfs_server.hostname);
+        kfree(data->nfs_server.hostname);
-        kfree(data.mount_server.hostname);
+        kfree(data->mount_server.hostname);
-        security_free_mnt_opts(&data.lsm_opts);
+        security_free_mnt_opts(&data->lsm_opts);
+out_free_fh:
+        kfree(mntfh);
+        kfree(data);
        return error;
 out_err_nosb:
@@ -1800,8 +1806,6 @@ static int nfs4_validate_mount_data(void *options,
        struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
        char *c;
-        memset(args, 0, sizeof(*args));
        if (data == NULL)
                goto out_no_data;
@@ -1959,26 +1963,31 @@ out_no_client_address:
 static int nfs4_get_sb(struct file_system_type *fs_type,
        int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
 {
-        struct nfs_parsed_mount_data data;
+        struct nfs_parsed_mount_data *data;
        struct super_block *s;
        struct nfs_server *server;
-        struct nfs_fh mntfh;
+        struct nfs_fh *mntfh;
        struct dentry *mntroot;
        int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
        struct nfs_sb_mountdata sb_mntdata = {
                .mntflags = flags,
        };
-        int error;
+        int error = -ENOMEM;
-        security_init_mnt_opts(&data.lsm_opts);
+        data = kzalloc(sizeof(*data), GFP_KERNEL);
+        mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL);
+        if (data == NULL || mntfh == NULL)
+                goto out_free_fh;
+        security_init_mnt_opts(&data->lsm_opts);
        /* Validate the mount data */
-        error = nfs4_validate_mount_data(raw_data, &data, dev_name);
+        error = nfs4_validate_mount_data(raw_data, data, dev_name);
        if (error < 0)
                goto out;
        /* Get a volume representation */
-        server = nfs4_create_server(&data, &mntfh);
+        server = nfs4_create_server(data, mntfh);
        if (IS_ERR(server)) {
                error = PTR_ERR(server);
                goto out;
@@ -2009,13 +2018,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
                nfs4_fill_super(s);
        }
-        mntroot = nfs4_get_root(s, &mntfh);
+        mntroot = nfs4_get_root(s, mntfh);
        if (IS_ERR(mntroot)) {
                error = PTR_ERR(mntroot);
                goto error_splat_super;
        }
-        error = security_sb_set_mnt_opts(s, &data.lsm_opts);
+        error = security_sb_set_mnt_opts(s, &data->lsm_opts);
        if (error)
                goto error_splat_root;
@@ -2025,10 +2034,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
        error = 0;
 out:
-        kfree(data.client_address);
+        kfree(data->client_address);
-        kfree(data.nfs_server.export_path);
+        kfree(data->nfs_server.export_path);
-        kfree(data.nfs_server.hostname);
+        kfree(data->nfs_server.hostname);
-        security_free_mnt_opts(&data.lsm_opts);
+        security_free_mnt_opts(&data->lsm_opts);
+out_free_fh:
+        kfree(mntfh);
+        kfree(data);
        return error;
 out_free:
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 6d8ace3e3259..f333848fd3be 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -739,12 +739,13 @@ int nfs_updatepage(struct file *file, struct page *page,
        }
        status = nfs_writepage_setup(ctx, page, offset, count);
-        __set_page_dirty_nobuffers(page);
+        if (status < 0)
+                nfs_set_pageerror(page);
+        else
+                __set_page_dirty_nobuffers(page);
        dprintk("NFS:      nfs_updatepage returns %d (isize %Ld)\n",
                        status, (long long)i_size_read(inode));
-        if (status < 0)
-                nfs_set_pageerror(page);
        return status;
 }
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]) +
+                        le16_add_cpu(&uc[i], uc_run_table[r][2]);
-                                        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/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index cf9401e8cd0b..cfdb08b484ed 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -21,7 +21,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/sysctl.h>
 #include <linux/configfs.h>
 #include "tcp.h"
@@ -36,65 +35,6 @@
 * cluster references throughout where nodes are looked up */
 struct o2nm_cluster *o2nm_single_cluster = NULL;
-#define OCFS2_MAX_HB_CTL_PATH 256
-static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
-static ctl_table ocfs2_nm_table[] = {
-        {
-                .ctl_name       = 1,
-                .procname       = "hb_ctl_path",
-                .data           = ocfs2_hb_ctl_path,
-                .maxlen         = OCFS2_MAX_HB_CTL_PATH,
-                .mode           = 0644,
-                .proc_handler   = &proc_dostring,
-                .strategy       = &sysctl_string,
-        },
-        { .ctl_name = 0 }
-};
-static ctl_table ocfs2_mod_table[] = {
-        {
-                .ctl_name       = FS_OCFS2_NM,
-                .procname       = "nm",
-                .data           = NULL,
-                .maxlen         = 0,
-                .mode           = 0555,
-                .child          = ocfs2_nm_table
-        },
-        { .ctl_name = 0}
-};
-static ctl_table ocfs2_kern_table[] = {
-        {
-                .ctl_name       = FS_OCFS2,
-                .procname       = "ocfs2",
-                .data           = NULL,
-                .maxlen         = 0,
-                .mode           = 0555,
-                .child          = ocfs2_mod_table
-        },
-        { .ctl_name = 0}
-};
-static ctl_table ocfs2_root_table[] = {
-        {
-                .ctl_name       = CTL_FS,
-                .procname       = "fs",
-                .data           = NULL,
-                .maxlen         = 0,
-                .mode           = 0555,
-                .child          = ocfs2_kern_table
-        },
-        { .ctl_name = 0 }
-};
-static struct ctl_table_header *ocfs2_table_header = NULL;
-const char *o2nm_get_hb_ctl_path(void)
-{
-        return ocfs2_hb_ctl_path;
-}
-EXPORT_SYMBOL_GPL(o2nm_get_hb_ctl_path);
 struct o2nm_node *o2nm_get_node_by_num(u8 node_num)
 {
@@ -941,9 +881,6 @@ void o2nm_undepend_this_node(void)
 static void __exit exit_o2nm(void)
 {
-        if (ocfs2_table_header)
-                unregister_sysctl_table(ocfs2_table_header);
        /* XXX sync with hb callbacks and shut down hb? */
        o2net_unregister_hb_callbacks();
        configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys);
@@ -964,16 +901,9 @@ static int __init init_o2nm(void)
        if (ret)
                goto out;
-        ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
-        if (!ocfs2_table_header) {
-                printk(KERN_ERR "nodemanager: unable to register sysctl\n");
-                ret = -ENOMEM; /* or something. */
-                goto out_o2net;
-        }
        ret = o2net_register_hb_callbacks();
        if (ret)
-                goto out_sysctl;
+                goto out_o2net;
        config_group_init(&o2nm_cluster_group.cs_subsys.su_group);
        mutex_init(&o2nm_cluster_group.cs_subsys.su_mutex);
@@ -990,8 +920,6 @@ static int __init init_o2nm(void)
        configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys);
 out_callbacks:
        o2net_unregister_hb_callbacks();
-out_sysctl:
-        unregister_sysctl_table(ocfs2_table_header);
 out_o2net:
        o2net_exit();
 out:
diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h
index 7c860361b8dd..c992ea0da4ad 100644
--- a/fs/ocfs2/cluster/nodemanager.h
+++ b/fs/ocfs2/cluster/nodemanager.h
@@ -33,10 +33,6 @@
 #include <linux/configfs.h>
 #include <linux/rbtree.h>
-#define FS_OCFS2_NM             1
-const char *o2nm_get_hb_ctl_path(void);
 struct o2nm_node {
        spinlock_t              nd_lock;
        struct config_item      nd_item;
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/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index efc015c6128a..44f87caf3683 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -606,7 +606,9 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
        res->last_used = 0;
+        spin_lock(&dlm->spinlock);
        list_add_tail(&res->tracking, &dlm->tracking_list);
+        spin_unlock(&dlm->spinlock);
        memset(res->lvb, 0, DLM_LVB_LEN);
        memset(res->refmap, 0, sizeof(res->refmap));
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index bbd1667aa7d3..fcd120f1493a 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -317,8 +317,7 @@ out:
        return rc;
 }
-static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn,
+static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn)
-                                   int hangup_pending)
 {
        struct dlm_ctxt *dlm = conn->cc_lockspace;
        struct o2dlm_private *priv = conn->cc_private;
@@ -333,43 +332,6 @@ static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn,
        return 0;
 }
-static void o2hb_stop(const char *group)
-{
-        int ret;
-        char *argv[5], *envp[3];
-        argv[0] = (char *)o2nm_get_hb_ctl_path();
-        argv[1] = "-K";
-        argv[2] = "-u";
-        argv[3] = (char *)group;
-        argv[4] = NULL;
-        mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]);
-        /* minimal command environment taken from cpu_run_sbin_hotplug */
-        envp[0] = "HOME=/";
-        envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
-        envp[2] = NULL;
-        ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
-        if (ret < 0)
-                mlog_errno(ret);
-}
-/*
- * Hangup is a hack for tools compatibility.  Older ocfs2-tools software
- * expects the filesystem to call "ocfs2_hb_ctl" during unmount.  This
- * happens regardless of whether the DLM got started, so we can't do it
- * in ocfs2_cluster_disconnect().  We bring the o2hb_stop() function into
- * the glue and provide a "hangup" API for super.c to call.
- *
- * Other stacks will eventually provide a NULL ->hangup() pointer.
- */
-static void o2cb_cluster_hangup(const char *group, int grouplen)
-{
-        o2hb_stop(group);
-}
 static int o2cb_cluster_this_node(unsigned int *node)
 {
        int node_num;
@@ -388,7 +350,6 @@ static int o2cb_cluster_this_node(unsigned int *node)
 static struct ocfs2_stack_operations o2cb_stack_ops = {
        .connect        = o2cb_cluster_connect,
        .disconnect     = o2cb_cluster_disconnect,
-        .hangup         = o2cb_cluster_hangup,
        .this_node      = o2cb_cluster_this_node,
        .dlm_lock       = o2cb_dlm_lock,
        .dlm_unlock     = o2cb_dlm_unlock,
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index b503772cd0ec..c021280dd462 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,
@@ -816,8 +816,7 @@ out:
        return rc;
 }
-static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn,
+static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn)
-                                   int hangup_pending)
 {
        dlm_release_lockspace(conn->cc_lockspace, 2);
        conn->cc_lockspace = NULL;
@@ -838,7 +837,7 @@ 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 +848,20 @@ 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 +869,14 @@ 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_init(ocfs2_user_plugin_init);
-module_exit(user_stack_exit);
+module_exit(ocfs2_user_plugin_exit);
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 119f60cea9cc..10e149ae5e3a 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
+#include <linux/sysctl.h>
 #include "ocfs2_fs.h"
@@ -33,11 +34,13 @@
 #define OCFS2_STACK_PLUGIN_O2CB         "o2cb"
 #define OCFS2_STACK_PLUGIN_USER         "user"
+#define OCFS2_MAX_HB_CTL_PATH           256
 static struct ocfs2_locking_protocol *lproto;
 static DEFINE_SPINLOCK(ocfs2_stack_lock);
 static LIST_HEAD(ocfs2_stack_list);
 static char cluster_stack_name[OCFS2_STACK_LABEL_LEN + 1];
+static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
 /*
 * The stack currently in use.  If not null, active_stack->sp_count > 0,
@@ -349,7 +352,7 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn,
        BUG_ON(conn == NULL);
-        ret = active_stack->sp_ops->disconnect(conn, hangup_pending);
+        ret = active_stack->sp_ops->disconnect(conn);
        /* XXX Should we free it anyway? */
        if (!ret) {
@@ -362,13 +365,48 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn,
 }
 EXPORT_SYMBOL_GPL(ocfs2_cluster_disconnect);
+/*
+ * Leave the group for this filesystem.  This is executed by a userspace
+ * program (stored in ocfs2_hb_ctl_path).
+ */
+static void ocfs2_leave_group(const char *group)
+{
+        int ret;
+        char *argv[5], *envp[3];
+        argv[0] = ocfs2_hb_ctl_path;
+        argv[1] = "-K";
+        argv[2] = "-u";
+        argv[3] = (char *)group;
+        argv[4] = NULL;
+        /* minimal command environment taken from cpu_run_sbin_hotplug */
+        envp[0] = "HOME=/";
+        envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+        envp[2] = NULL;
+        ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+        if (ret < 0) {
+                printk(KERN_ERR
+                       "ocfs2: Error %d running user helper "
+                       "\"%s %s %s %s\"\n",
+                       ret, argv[0], argv[1], argv[2], argv[3]);
+        }
+}
+/*
+ * Hangup is a required post-umount.  ocfs2-tools software expects the
+ * filesystem to call "ocfs2_hb_ctl" during unmount.  This happens
+ * regardless of whether the DLM got started, so we can't do it
+ * in ocfs2_cluster_disconnect().  The ocfs2_leave_group() function does
+ * the actual work.
+ */
 void ocfs2_cluster_hangup(const char *group, int grouplen)
 {
        BUG_ON(group == NULL);
        BUG_ON(group[grouplen] != '\0');
-        if (active_stack->sp_ops->hangup)
+        ocfs2_leave_group(group);
-                active_stack->sp_ops->hangup(group, grouplen);
        /* cluster_disconnect() was called with hangup_pending==1 */
        ocfs2_stack_driver_put();
@@ -548,10 +586,83 @@ error:
        return ret;
 }
+/*
+ * Sysctl bits
+ *
+ * The sysctl lives at /proc/sys/fs/ocfs2/nm/hb_ctl_path.  The 'nm' doesn't
+ * make as much sense in a multiple cluster stack world, but it's safer
+ * and easier to preserve the name.
+ */
+#define FS_OCFS2_NM             1
+static ctl_table ocfs2_nm_table[] = {
+        {
+                .ctl_name       = 1,
+                .procname       = "hb_ctl_path",
+                .data           = ocfs2_hb_ctl_path,
+                .maxlen         = OCFS2_MAX_HB_CTL_PATH,
+                .mode           = 0644,
+                .proc_handler   = &proc_dostring,
+                .strategy       = &sysctl_string,
+        },
+        { .ctl_name = 0 }
+};
+static ctl_table ocfs2_mod_table[] = {
+        {
+                .ctl_name       = FS_OCFS2_NM,
+                .procname       = "nm",
+                .data           = NULL,
+                .maxlen         = 0,
+                .mode           = 0555,
+                .child          = ocfs2_nm_table
+        },
+        { .ctl_name = 0}
+};
+static ctl_table ocfs2_kern_table[] = {
+        {
+                .ctl_name       = FS_OCFS2,
+                .procname       = "ocfs2",
+                .data           = NULL,
+                .maxlen         = 0,
+                .mode           = 0555,
+                .child          = ocfs2_mod_table
+        },
+        { .ctl_name = 0}
+};
+static ctl_table ocfs2_root_table[] = {
+        {
+                .ctl_name       = CTL_FS,
+                .procname       = "fs",
+                .data           = NULL,
+                .maxlen         = 0,
+                .mode           = 0555,
+                .child          = ocfs2_kern_table
+        },
+        { .ctl_name = 0 }
+};
+static struct ctl_table_header *ocfs2_table_header = NULL;
+/*
+ * Initialization
+ */
 static int __init ocfs2_stack_glue_init(void)
 {
        strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB);
+        ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
+        if (!ocfs2_table_header) {
+                printk(KERN_ERR
+                       "ocfs2 stack glue: unable to register sysctl\n");
+                return -ENOMEM; /* or something. */
+        }
        return ocfs2_sysfs_init();
 }
@@ -559,6 +670,8 @@ static void __exit ocfs2_stack_glue_exit(void)
 {
        lproto = NULL;
        ocfs2_sysfs_exit();
+        if (ocfs2_table_header)
+                unregister_sysctl_table(ocfs2_table_header);
 }
 MODULE_AUTHOR("Oracle");
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 005e4f170e0f..db56281dd1be 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -134,22 +134,10 @@ struct ocfs2_stack_operations {
         * be freed.  Thus, a stack must not return from ->disconnect()
         * until it will no longer reference the conn pointer.
         *
-         * If hangup_pending is zero, ocfs2_cluster_disconnect() will also
+         * Once this call returns, the stack glue will be dropping this
-         * be dropping the reference on the module.
+         * connection's reference on the module.
         */
-        int (*disconnect)(struct ocfs2_cluster_connection *conn,
+        int (*disconnect)(struct ocfs2_cluster_connection *conn);
-                          int hangup_pending);
-        /*
-         * ocfs2_cluster_hangup() exists for compatibility with older
-         * ocfs2 tools.  Only the classic stack really needs it.  As such
-         * ->hangup() is not required of all stacks.  See the comment by
-         * ocfs2_cluster_hangup() for more details.
-         *
-         * Note that ocfs2_cluster_hangup() can only be called if
-         * hangup_pending was passed to ocfs2_cluster_disconnect().
-         */
-        void (*hangup)(const char *group, int grouplen);
        /*
         * ->this_node() returns the cluster's unique identifier for the
@@ -258,4 +246,5 @@ void ocfs2_stack_glue_set_locking_protocol(struct ocfs2_locking_protocol *proto)
 /* Used by stack plugins */
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 #endif  /* STACKGLUE_H */
diff --git a/fs/open.c b/fs/open.c
index a1450086e92f..a99ad09c3197 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -16,6 +16,7 @@
 #include <linux/namei.h>
 #include <linux/backing-dev.h>
 #include <linux/capability.h>
+#include <linux/securebits.h>
 #include <linux/security.h>
 #include <linux/mount.h>
 #include <linux/vfs.h>
@@ -425,7 +426,7 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 {
        struct nameidata nd;
        int old_fsuid, old_fsgid;
-        kernel_cap_t old_cap;
+        kernel_cap_t uninitialized_var(old_cap);  /* !SECURE_NO_SETUID_FIXUP */
        int res;
        if (mode & ~S_IRWXO)    /* where's F_OK, X_OK, W_OK, R_OK? */
@@ -433,23 +434,27 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
        old_fsuid = current->fsuid;
        old_fsgid = current->fsgid;
-        old_cap = current->cap_effective;
        current->fsuid = current->uid;
        current->fsgid = current->gid;
-        /*
+        if (!issecure(SECURE_NO_SETUID_FIXUP)) {
-         * Clear the capabilities if we switch to a non-root user
+                /*
-         *
+                 * Clear the capabilities if we switch to a non-root user
-         * FIXME: There is a race here against sys_capset.  The
+                 */
-         * capabilities can change yet we will restore the old
+#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
-         * value below.  We should hold task_capabilities_lock,
+                /*
-         * but we cannot because user_path_walk can sleep.
+                 * FIXME: There is a race here against sys_capset.  The
-         */
+                 * capabilities can change yet we will restore the old
-        if (current->uid)
+                 * value below.  We should hold task_capabilities_lock,
-                cap_clear(current->cap_effective);
+                 * but we cannot because user_path_walk can sleep.
-        else
+                 */
-                current->cap_effective = current->cap_permitted;
+#endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */
+                if (current->uid)
+                        old_cap = cap_set_effective(__cap_empty_set);
+                else
+                        old_cap = cap_set_effective(current->cap_permitted);
+        }
        res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
        if (res)
@@ -478,7 +483,9 @@ out_path_release:
 out:
        current->fsuid = old_fsuid;
        current->fsgid = old_fsgid;
-        current->cap_effective = old_cap;
+        if (!issecure(SECURE_NO_SETUID_FIXUP))
+                cap_set_effective(old_cap);
        return res;
 }
diff --git a/fs/pipe.c b/fs/pipe.c
index ec228bc9f882..700f4e0d9572 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1003,8 +1003,7 @@ struct file *create_write_pipe(void)
 void free_write_pipe(struct file *f)
 {
        free_pipe_info(f->f_dentry->d_inode);
-        dput(f->f_path.dentry);
+        path_put(&f->f_path);
-        mntput(f->f_path.mnt);
        put_filp(f);
 }
@@ -1015,8 +1014,8 @@ struct file *create_read_pipe(struct file *wrf)
                return ERR_PTR(-ENFILE);
        /* Grab pipe from the writer */
-        f->f_path.mnt = mntget(wrf->f_path.mnt);
+        f->f_path = wrf->f_path;
-        f->f_path.dentry = dget(wrf->f_path.dentry);
+        path_get(&wrf->f_path);
        f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
        f->f_pos = 0;
@@ -1068,8 +1067,7 @@ int do_pipe(int *fd)
 err_fdr:
        put_unused_fd(fdr);
 err_read_pipe:
-        dput(fr->f_dentry);
+        path_put(&fr->f_path);
-        mntput(fr->f_vfsmnt);
        put_filp(fr);
 err_write_pipe:
        free_write_pipe(fw);
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 = 2 + pid_entry_count_dirs(tgid_base_stuff,
-        inode->i_nlink += 1;
+                ARRAY_SIZE(tgid_base_stuff));
-#endif
        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 = 2 + pid_entry_count_dirs(tid_base_stuff,
-        inode->i_nlink += 1;
+                ARRAY_SIZE(tid_base_stuff));
-#endif
        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..c492449f3b45 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,
+                walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
-                                &smaps_walk, &mss);
        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) {
+                struct mm_walk clear_refs_walk = {
+                        .pmd_entry = clear_refs_pte_range,
+                        .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,
+                                walk_page_range(vma->vm_start, vma->vm_end,
-                                                &clear_refs_walk, vma);
+                                                &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))
+                /* check to see if we've left 'vma' behind
-                        pfn = PM_PFRAME(swap_pte_to_pagemap_entry(*pte))
+                 * and need a new, higher one */
-                                | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+                if (vma && (addr >= vma->vm_end))
-                else if (pte_present(*pte))
+                        vma = find_vma(walk->mm, addr);
-                        pfn = PM_PFRAME(pte_pfn(*pte))
-                                | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+                /* check that 'vma' actually covers this address,
-                /* unmap so we're not in atomic when we copy to userspace */
+                 * and that it isn't a huge page vma */
-                pte_unmap(pte);
+                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;
@@ -585,11 +602,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
        return err;
 }
-static struct mm_walk pagemap_walk = {
-        .pmd_entry = pagemap_pte_range,
-        .pte_hole = pagemap_pte_hole
-};
 /*
 * /proc/pid/pagemap - an array mapping virtual pages to pfns
 *
@@ -624,6 +636,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
        struct pagemapread pm;
        int pagecount;
        int ret = -ESRCH;
+        struct mm_walk pagemap_walk;
+        unsigned long src;
+        unsigned long svpfn;
+        unsigned long start_vaddr;
+        unsigned long end_vaddr;
        if (!task)
                goto out;
@@ -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;
@@ -642,11 +659,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
        if (!mm)
                goto out_task;
-        ret = -ENOMEM;
        uaddr = (unsigned long)buf & PAGE_MASK;
        uend = (unsigned long)(buf + count);
        pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
-        pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL);
+        ret = 0;
+        if (pagecount == 0)
+                goto out_mm;
+        pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
+        ret = -ENOMEM;
        if (!pages)
                goto out_mm;
@@ -664,36 +685,36 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
                goto out_pages;
        }
-        pm.out = buf;
+        pm.out = (u64 *)buf;
-        pm.end = buf + count;
+        pm.end = (u64 *)(buf + count);
-        if (!ptrace_may_attach(task)) {
+        pagemap_walk.pmd_entry = pagemap_pte_range;
-                ret = -EIO;
+        pagemap_walk.pte_hole = pagemap_pte_hole;
-        } else {
+        pagemap_walk.mm = mm;
-                unsigned long src = *ppos;
+        pagemap_walk.private = &pm;
-                unsigned long svpfn = src / PM_ENTRY_BYTES;
-                unsigned long start_vaddr = svpfn << PAGE_SHIFT;
+        src = *ppos;
-                unsigned long end_vaddr = TASK_SIZE_OF(task);
+        svpfn = src / PM_ENTRY_BYTES;
+        start_vaddr = svpfn << PAGE_SHIFT;
-                /* watch out for wraparound */
+        end_vaddr = TASK_SIZE_OF(task);
-                if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
-                        start_vaddr = end_vaddr;
+        /* watch out for wraparound */
+        if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
-                /*
+                start_vaddr = end_vaddr;
-                 * The odds are that this will stop walking way
-                 * before end_vaddr, because the length of the
+        /*
-                 * user buffer is tracked in "pm", and the walk
+         * The odds are that this will stop walking way
-                 * will stop when we hit the end of the buffer.
+         * before end_vaddr, because the length of the
-                 */
+         * user buffer is tracked in "pm", and the walk
-                ret = walk_page_range(mm, start_vaddr, end_vaddr,
+         * will stop when we hit the end of the buffer.
-                                        &pagemap_walk, &pm);
+         */
-                if (ret == PM_END_OF_BUFFER)
+        ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk);
-                        ret = 0;
+        if (ret == PM_END_OF_BUFFER)
-                /* don't need mmap_sem for these, but this looks cleaner */
+                ret = 0;
-                *ppos += pm.out - buf;
+        /* don't need mmap_sem for these, but this looks cleaner */
-                if (!ret)
+        *ppos += (char *)pm.out - buf;
-                        ret = pm.out - buf;
+        if (!ret)
-        }
+                ret = (char *)pm.out - buf;
 out_pages:
        for (; pagecount; pagecount--) {
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 57917932212e..192269698a8a 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -45,6 +45,8 @@ void reiserfs_delete_inode(struct inode *inode)
                        goto out;
                reiserfs_update_inode_transaction(inode);
+                reiserfs_discard_prealloc(&th, inode);
                err = reiserfs_delete_object(&th, inode);
                /* Do quota update inside a transaction for journaled quotas. We must do that
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index ed424d708e69..1d40f2bd1970 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -2165,8 +2165,10 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
                blk++;
        }
 out:
-        if (len == towrite)
+        if (len == towrite) {
+                mutex_unlock(&inode->i_mutex);
                return err;
+        }
        if (inode->i_size < off + len - towrite)
                i_size_write(inode, off + len - towrite);
        inode->i_version++;
diff --git a/fs/select.c b/fs/select.c
index 8dda969614a9..da0e88201c3a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -249,7 +249,6 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
                                                retval++;
                                        }
                                }
-                                cond_resched();
                        }
                        if (res_in)
                                *rinp = res_in;
@@ -257,6 +256,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
                                *routp = res_out;
                        if (res_ex)
                                *rexp = res_ex;
+                        cond_resched();
                }
                wait = NULL;
                if (retval || !*timeout || signal_pending(current))
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))
+                if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
-                        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/udf/super.c b/fs/udf/super.c
index 7a5f69be6ac2..44cc702f96cc 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -682,38 +682,26 @@ static int udf_vrs(struct super_block *sb, int silent)
 /*
 * Check whether there is an anchor block in the given block
 */
-static int udf_check_anchor_block(struct super_block *sb, sector_t block,
+static int udf_check_anchor_block(struct super_block *sb, sector_t block)
-                                        bool varconv)
 {
-        struct buffer_head *bh = NULL;
+        struct buffer_head *bh;
-        tag *t;
        uint16_t ident;
-        uint32_t location;
-        if (varconv) {
+        if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
-                if (udf_fixed_to_variable(block) >=
+            udf_fixed_to_variable(block) >=
-                    sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
+            sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
-                        return 0;
+                return 0;
-                bh = sb_bread(sb, udf_fixed_to_variable(block));
-        }
-        else
-                bh = sb_bread(sb, block);
+        bh = udf_read_tagged(sb, block, block, &ident);
        if (!bh)
                return 0;
-        t = (tag *)bh->b_data;
-        ident = le16_to_cpu(t->tagIdent);
-        location = le32_to_cpu(t->tagLocation);
        brelse(bh);
-        if (ident != TAG_IDENT_AVDP)
-                return 0;
+        return ident == TAG_IDENT_AVDP;
-        return location == block;
 }
 /* Search for an anchor volume descriptor pointer */
-static sector_t udf_scan_anchors(struct super_block *sb, bool varconv,
+static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock)
-                                        sector_t lastblock)
 {
        sector_t last[6];
        int i;
@@ -739,7 +727,7 @@ static sector_t udf_scan_anchors(struct super_block *sb, bool varconv,
                                sb->s_blocksize_bits)
                        continue;
-                if (udf_check_anchor_block(sb, last[i], varconv)) {
+                if (udf_check_anchor_block(sb, last[i])) {
                        sbi->s_anchor[0] = last[i];
                        sbi->s_anchor[1] = last[i] - 256;
                        return last[i];
@@ -748,17 +736,17 @@ static sector_t udf_scan_anchors(struct super_block *sb, bool varconv,
                if (last[i] < 256)
                        continue;
-                if (udf_check_anchor_block(sb, last[i] - 256, varconv)) {
+                if (udf_check_anchor_block(sb, last[i] - 256)) {
                        sbi->s_anchor[1] = last[i] - 256;
                        return last[i];
                }
        }
-        if (udf_check_anchor_block(sb, sbi->s_session + 256, varconv)) {
+        if (udf_check_anchor_block(sb, sbi->s_session + 256)) {
                sbi->s_anchor[0] = sbi->s_session + 256;
                return last[0];
        }
-        if (udf_check_anchor_block(sb, sbi->s_session + 512, varconv)) {
+        if (udf_check_anchor_block(sb, sbi->s_session + 512)) {
                sbi->s_anchor[0] = sbi->s_session + 512;
                return last[0];
        }
@@ -780,23 +768,24 @@ static void udf_find_anchor(struct super_block *sb)
        int i;
        struct udf_sb_info *sbi = UDF_SB(sb);
-        lastblock = udf_scan_anchors(sb, 0, sbi->s_last_block);
+        lastblock = udf_scan_anchors(sb, sbi->s_last_block);
        if (lastblock)
                goto check_anchor;
        /* No anchor found? Try VARCONV conversion of block numbers */
+        UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
        /* Firstly, we try to not convert number of the last block */
-        lastblock = udf_scan_anchors(sb, 1,
+        lastblock = udf_scan_anchors(sb,
                                udf_variable_to_fixed(sbi->s_last_block));
-        if (lastblock) {
+        if (lastblock)
-                UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
                goto check_anchor;
-        }
        /* Secondly, we try with converted number of the last block */
-        lastblock = udf_scan_anchors(sb, 1, sbi->s_last_block);
+        lastblock = udf_scan_anchors(sb, sbi->s_last_block);
-        if (lastblock)
+        if (!lastblock) {
-                UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
+                /* VARCONV didn't help. Clear it. */
+                UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV);
+        }
 check_anchor:
        /*
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 8fa9c2d70911..8ec865de5f13 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -16,7 +16,7 @@
 #define UDF_PREALLOCATE
 #define UDF_DEFAULT_PREALLOC_BLOCKS     8
-#define UDFFS_DEBUG
+#undef UDFFS_DEBUG
 #ifdef UDFFS_DEBUG
 #define udf_debug(f, a...) \
diff --git a/fs/utimes.c b/fs/utimes.c
index af059d5cb485..b6b664e7145e 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -40,14 +40,9 @@ asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times)
 #endif
-static bool nsec_special(long nsec)
-{
-        return nsec == UTIME_OMIT || nsec == UTIME_NOW;
-}
 static bool nsec_valid(long nsec)
 {
-        if (nsec_special(nsec))
+        if (nsec == UTIME_OMIT || nsec == UTIME_NOW)
                return true;
        return nsec >= 0 && nsec <= 999999999;
@@ -102,7 +97,11 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
        if (error)
                goto dput_and_out;
-        /* Don't worry, the checks are done in inode_change_ok() */
+        if (times && times[0].tv_nsec == UTIME_NOW &&
+                     times[1].tv_nsec == UTIME_NOW)
+                times = NULL;
+        /* In most cases, the checks are done in inode_change_ok() */
        newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
        if (times) {
                error = -EPERM;
@@ -124,28 +123,34 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
                        newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
                        newattrs.ia_valid |= ATTR_MTIME_SET;
                }
-        }
-        /*
+                /*
-         * If times is NULL or both times are either UTIME_OMIT or
+                 * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT
-         * UTIME_NOW, then need to check permissions, because
+                 * cases, we need to make an extra check that is not done by
-         * inode_change_ok() won't do it.
+                 * inode_change_ok().
-         */
+                 */
-        if (!times || (nsec_special(times[0].tv_nsec) &&
+                if (((times[0].tv_nsec == UTIME_NOW &&
-                       nsec_special(times[1].tv_nsec))) {
+                            times[1].tv_nsec == UTIME_OMIT)
+                     ||
+                     (times[0].tv_nsec == UTIME_OMIT &&
+                            times[1].tv_nsec == UTIME_NOW))
+                    && !is_owner_or_cap(inode))
+                        goto mnt_drop_write_and_out;
+        } else {
+                /*
+                 * If times is NULL (or both times are UTIME_NOW),
+                 * then we need to check permissions, because
+                 * inode_change_ok() won't do it.
+                 */
                error = -EACCES;
                if (IS_IMMUTABLE(inode))
                        goto mnt_drop_write_and_out;
                if (!is_owner_or_cap(inode)) {
-                        if (f) {
+                        error = permission(inode, MAY_WRITE, NULL);
-                                if (!(f->f_mode & FMODE_WRITE))
+                        if (error)
-                                        goto mnt_drop_write_and_out;
+                                goto mnt_drop_write_and_out;
-                        } else {
-                                error = vfs_permission(&nd, MAY_WRITE);
-                                if (error)
-                                        goto mnt_drop_write_and_out;
-                        }
                }
        }
        mutex_lock(&inode->i_mutex);
@@ -169,14 +174,6 @@ asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __
        if (utimes) {
                if (copy_from_user(&tstimes, utimes, sizeof(tstimes)))
                        return -EFAULT;
-                if ((tstimes[0].tv_nsec == UTIME_OMIT ||
-                     tstimes[0].tv_nsec == UTIME_NOW) &&
-                    tstimes[0].tv_sec != 0)
-                        return -EINVAL;
-                if ((tstimes[1].tv_nsec == UTIME_OMIT ||
-                     tstimes[1].tv_nsec == UTIME_NOW) &&
-                    tstimes[1].tv_sec != 0)
-                        return -EINVAL;
                /* Nothing to do, we must not even check the path.  */
                if (tstimes[0].tv_nsec == UTIME_OMIT &&
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,
+        return -xfs_fsync(XFS_I(dentry->d_inode));
-                        (xfs_off_t)0, (xfs_off_t)-1);
 }
 /*
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 *);
+        inodes_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog;
-        ilist = kmem_alloc(ilist_size, KM_MAYFAIL);
+        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,
+                                        first_index, inodes_per_cluster);
-                                        XFS_INODE_CLUSTER_SIZE(mp));
        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.
+ * This is called to sync the inode and its data out to disk.  We need to hold
- * We need to hold the I/O lock while flushing the data, and
+ * the I/O lock while flushing the data, and the inode lock while flushing the
- * the inode lock while flushing the inode.  The inode lock CANNOT
+ * inode.  The inode lock CANNOT be held while flushing the data, so acquire
- * be held while flushing the data, so acquire after we're done
+ * after we're done with that.
- * with that.
 */
 int
 xfs_fsync(
-        xfs_inode_t     *ip,
+        xfs_inode_t     *ip)
-        int             flag,
-        xfs_off_t       start,
-        xfs_off_t       stop)
 {
        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)
+        /* capture size updates in I/O completion before writing the inode. */
-                filemap_fdatawait(vn_to_inode(XFS_ITOV(ip))->i_mapping);
+        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
+         * We always need to make sure that the required inode state is safe on
-         * is safe on disk.  The vnode might be clean but because
+         * disk.  The vnode might be clean but we still might need to force the
-         * of committed transactions that haven't hit the disk yet.
+         * log because of committed transactions that haven't hit the disk yet.
-         * Likewise, there could be unflushed non-transactional
+         * Likewise, there could be unflushed non-transactional changes to the
-         * changes to the inode core that have to go to disk.
+         * 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
+         * This code relies on the assumption that if the update_* fields
-         * any transaction that changes an inode logs the core
+         * of the inode are clear and the inode is unpinned then it is clean
-         * because it has to change some field in the inode core
+         * and no action is required.
-         * (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.)
         */
        xfs_ilock(ip, XFS_ILOCK_SHARED);
-        /* If we are flushing data then we care about update_size
+        if (!(ip->i_update_size || ip->i_update_core)) {
-         * being set, otherwise we care about update_core
-         */
-        if ((flag & FSYNC_DATA) ?
-                        (ip->i_update_size == 0) :
-                        (ip->i_update_core == 0)) {
                /*
-                 * Timestamps/size haven't changed since last inode
+                 * Timestamps/size haven't changed since last inode flush or
-                 * flush or inode transaction commit.  That means
+                 * inode transaction commit.  That means either nothing got
-                 * either nothing got written or a transaction
+                 * written or a transaction committed which caught the updates.
-                 * committed which caught the updates.  If the
+                 * If the latter happened and the transaction hasn't hit the
-                 * latter happened and the transaction hasn't
+                 * disk yet, the inode will be still be pinned.  If it is,
-                 * hit the disk yet, the inode will be still
+                 * force the log.
-                 * 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,
+                        error = _xfs_log_force(ip->i_mount, (xfs_lsn_t)0,
-                                      XFS_LOG_FORCE |
+                                      XFS_LOG_FORCE | XFS_LOG_SYNC,
-                                      ((flag & FSYNC_WAIT)
-                                       ? XFS_LOG_SYNC : 0),
                                      &log_flushed);
                } else {
                        /*
-                         * If the inode is not pinned and nothing
+                         * If the inode is not pinned and nothing has changed
-                         * has changed we don't need to flush the
+                         * we don't need to flush the cache.
-                         * cache.
                         */
                        changed = 0;
                }
-                error = 0;
        } else  {
                /*
-                 * Kick off a transaction to log the inode
+                 * Kick off a transaction to log the inode core to get the
-                 * core to get the updates.  Make it
+                 * updates.  The sync transaction will also force the log.
-                 * sync if FSYNC_WAIT is passed in (which
-                 * is done by everybody but specfs).  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,
+                error = xfs_trans_reserve(tp, 0,
-                                XFS_FSYNC_TS_LOG_RES(ip->i_mount),
+                                XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
-                                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
+                 * Note - it's possible that we might have pushed ourselves out
-                 * ourselves out of the way during trans_reserve
+                 * of the way during trans_reserve which would flush the inode.
-                 * which would flush the inode.  But there's no
+                 * But there's no guarantee that the inode buffer has actually
-                 * guarantee that the inode buffer has actually
+                 * gone out yet (it's delwri).  Plus the buffer could be pinned
-                 * gone out yet (it's delwri).  Plus the buffer
+                 * anyway if it's part of an inode in another recent
-                 * could be pinned anyway if it's part of an
+                 * transaction.  So we play it safe and fire off the
-                 * inode in another recent transaction.  So we
+                 * transaction anyway.
-                 * 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,
+int xfs_fsync(struct xfs_inode *ip);
-                xfs_off_t stop);
 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,