Merge remote-tracking branch 'linux-stable/linux-3.0.y' into p-android-omap-3.0-dev-espresso

Conflicts: Makefile arch/arm/include/asm/hardware/cache-l2x0.h arch/arm/kernel/smp.c arch/arm/mach-omap2/board-4430sdp.c arch/arm/mach-omap2/board-omap4panda.c arch/arm/mach-omap2/opp.c arch/ia64/include/asm/futex.h drivers/bluetooth/ath3k.c drivers/bluetooth/btusb.c drivers/firmware/efivars.c drivers/gpu/drm/i915/intel_lvds.c drivers/gpu/drm/radeon/radeon_atombios.c drivers/gpu/drm/radeon/radeon_irq_kms.c drivers/hwmon/fam15h_power.c drivers/mfd/twl6030-irq.c drivers/mmc/core/sdio.c drivers/net/tun.c drivers/net/usb/ipheth.c drivers/net/usb/usbnet.c drivers/usb/core/hub.c drivers/usb/host/xhci-mem.c drivers/usb/host/xhci.h drivers/usb/musb/omap2430.c drivers/usb/serial/ftdi_sio.c drivers/usb/serial/ftdi_sio_ids.h drivers/usb/serial/option.c drivers/usb/serial/qcserial.c drivers/usb/serial/ti_usb_3410_5052.c drivers/usb/serial/ti_usb_3410_5052.h drivers/video/omap2/dss/hdmi.c fs/splice.c include/asm-generic/pgtable.h include/net/sch_generic.h kernel/cgroup.c kernel/futex.c kernel/time/timekeeping.c net/ipv4/route.c net/ipv4/syncookies.c net/ipv4/tcp_ipv4.c net/wireless/util.c security/commoncap.c sound/soc/soc-dapm.c
author: Ziyan <jaraidaniel@gmail.com> 2015-10-24 18:19:09 +0200
committer: Ziyan <jaraidaniel@gmail.com> 2015-10-25 16:24:52 +0100
commit: 101878938737bd16a5f7fb932b51041f7dbbb733 (patch)
tree: 235732d29c6741f22f2020218b2fad41c40b57b8 /fs
parent: 540bea4ab32149f8bc71fe34b73340c8d9abc053 (diff)
parent: 5dba9ddd98cbc7ad319d687887981a0ea0062c75 (diff)
download: kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.zip
kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.tar.gz
kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.tar.bz2
151 files changed, 1371 insertions, 774 deletions
diff --git a/fs/aio.c b/fs/aio.c
index b4a88cc..278ed7d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1395,6 +1395,10 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
 	if (ret < 0)
 		goto out;
 
+	ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret);
+	if (ret < 0)
+		goto out;
+
 	kiocb->ki_nr_segs = kiocb->ki_nbytes;
 	kiocb->ki_cur_seg = 0;
 	/* ki_nbytes/left now reflect bytes instead of segs */
@@ -1406,11 +1410,17 @@ out:
 	return ret;
 }
 
-static ssize_t aio_setup_single_vector(struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb)
 {
+	int bytes;
+
+	bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left);
+	if (bytes < 0)
+		return bytes;
+
 	kiocb->ki_iovec = &kiocb->ki_inline_vec;
 	kiocb->ki_iovec->iov_base = kiocb->ki_buf;
-	kiocb->ki_iovec->iov_len = kiocb->ki_left;
+	kiocb->ki_iovec->iov_len = bytes;
 	kiocb->ki_nr_segs = 1;
 	kiocb->ki_cur_seg = 0;
 	return 0;
@@ -1435,10 +1445,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf,
 			kiocb->ki_left)))
 			break;
-		ret = security_file_permission(file, MAY_READ);
-		if (unlikely(ret))
-			break;
-		ret = aio_setup_single_vector(kiocb);
+		ret = aio_setup_single_vector(READ, file, kiocb);
 		if (ret)
 			break;
 		ret = -EINVAL;
@@ -1453,10 +1460,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf,
 			kiocb->ki_left)))
 			break;
-		ret = security_file_permission(file, MAY_WRITE);
-		if (unlikely(ret))
-			break;
-		ret = aio_setup_single_vector(kiocb);
+		ret = aio_setup_single_vector(WRITE, file, kiocb);
 		if (ret)
 			break;
 		ret = -EINVAL;
@@ -1467,9 +1471,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		ret = -EBADF;
 		if (unlikely(!(file->f_mode & FMODE_READ)))
 			break;
-		ret = security_file_permission(file, MAY_READ);
-		if (unlikely(ret))
-			break;
 		ret = aio_setup_vectored_rw(READ, kiocb, compat);
 		if (ret)
 			break;
@@ -1481,9 +1482,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 		ret = -EBADF;
 		if (unlikely(!(file->f_mode & FMODE_WRITE)))
 			break;
-		ret = security_file_permission(file, MAY_WRITE);
-		if (unlikely(ret))
-			break;
 		ret = aio_setup_vectored_rw(WRITE, kiocb, compat);
 		if (ret)
 			break;
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 450f529..2c69d12 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -61,15 +61,6 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 		/* This is an autofs submount, we can't expire it */
 		if (autofs_type_indirect(sbi->type))
 			goto done;
-
-		/*
-		 * Otherwise it's an offset mount and we need to check
-		 * if we can umount its mount, if there is one.
-		 */
-		if (!d_mountpoint(path.dentry)) {
-			status = 0;
-			goto done;
-		}
 	}
 
 	/* Update the expiry counter if fs is busy */
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index f55ae23..790fa63 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -392,10 +392,12 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 		ino->flags |= AUTOFS_INF_PENDING;
 		spin_unlock(&sbi->fs_lock);
 		status = autofs4_mount_wait(dentry);
-		if (status)
-			return ERR_PTR(status);
 		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_PENDING;
+		if (status) {
+			spin_unlock(&sbi->fs_lock);
+			return ERR_PTR(status);
+		}
 	}
 done:
 	if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 618493e..7e8299f 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1669,30 +1669,19 @@ static int elf_note_info_init(struct elf_note_info *info)
 		return 0;
 	info->psinfo = kmalloc(sizeof(*info->psinfo), GFP_KERNEL);
 	if (!info->psinfo)
-		goto notes_free;
+		return 0;
 	info->prstatus = kmalloc(sizeof(*info->prstatus), GFP_KERNEL);
 	if (!info->prstatus)
-		goto psinfo_free;
+		return 0;
 	info->fpu = kmalloc(sizeof(*info->fpu), GFP_KERNEL);
 	if (!info->fpu)
-		goto prstatus_free;
+		return 0;
 #ifdef ELF_CORE_COPY_XFPREGS
 	info->xfpu = kmalloc(sizeof(*info->xfpu), GFP_KERNEL);
 	if (!info->xfpu)
-		goto fpu_free;
+		return 0;
 #endif
 	return 1;
-#ifdef ELF_CORE_COPY_XFPREGS
- fpu_free:
-	kfree(info->fpu);
-#endif
- prstatus_free:
-	kfree(info->prstatus);
- psinfo_free:
-	kfree(info->psinfo);
- notes_free:
-	kfree(info->notes);
-	return 0;
 }
 
 static int fill_note_info(struct elfhdr *elf, int phdrs,
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index b8e8b0a..4a1b984 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -42,7 +42,6 @@ static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
 			return -ENOEXEC;
 	}
 
-	bprm->recursion_depth++; /* Well, the bang-shell is implicit... */
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 1befe2e..b2497d4 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -116,10 +116,6 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (!enabled)
 		goto _ret;
 
-	retval = -ENOEXEC;
-	if (bprm->recursion_depth > BINPRM_MAX_RECURSION)
-		goto _ret;
-
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
@@ -176,7 +172,10 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		goto _error;
 	bprm->argc ++;
 
-	bprm->interp = iname;	/* for binfmt_script */
+	/* Update interp in case binfmt_script needs it. */
+	retval = bprm_change_interp(iname, bprm);
+	if (retval < 0)
+		goto _error;
 
 	interp_file = open_exec (iname);
 	retval = PTR_ERR (interp_file);
@@ -197,8 +196,6 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (retval < 0)
 		goto _error;
 
-	bprm->recursion_depth++;
-
 	retval = search_binary_handler (bprm, regs);
 	if (retval < 0)
 		goto _error;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 396a988..211ede0 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -22,15 +22,13 @@ static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
 	char interp[BINPRM_BUF_SIZE];
 	int retval;
 
-	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!') ||
-	    (bprm->recursion_depth > BINPRM_MAX_RECURSION))
+	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
 		return -ENOEXEC;
 	/*
 	 * This section does the #! interpretation.
 	 * Sorta complicated, but hopefully it will work.  -TYT
 	 */
 
-	bprm->recursion_depth++;
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
@@ -82,7 +80,9 @@ static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
 	retval = copy_strings_kernel(1, &i_name, bprm);
 	if (retval) return retval; 
 	bprm->argc++;
-	bprm->interp = interp;
+	retval = bprm_change_interp(interp, bprm);
+	if (retval < 0)
+		return retval;
 
 	/*
 	 * OK, now restart the process with the interpreter's dentry.
diff --git a/fs/bio.c b/fs/bio.c
index 9bfade8..5a48044 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -786,12 +786,22 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 int bio_uncopy_user(struct bio *bio)
 {
 	struct bio_map_data *bmd = bio->bi_private;
-	int ret = 0;
+	struct bio_vec *bvec;
+	int ret = 0, i;
 
-	if (!bio_flagged(bio, BIO_NULL_MAPPED))
-		ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
-				     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
-				     0, bmd->is_our_pages);
+	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+		/*
+		 * if we're in a workqueue, the request is orphaned, so
+		 * don't copy into a random user address space, just free.
+		 */
+		if (current->mm)
+			ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
+					     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+					     0, bmd->is_our_pages);
+		else if (bmd->is_our_pages)
+			__bio_for_each_segment(bvec, bio, i, 0)
+				__free_page(bvec->bv_page);
+	}
 	bio_free_map_data(bmd);
 	bio_put(bio);
 	return ret;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 74fc5ed..b5eb8c1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -55,16 +55,24 @@ EXPORT_SYMBOL(I_BDEV);
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
+	bool wakeup_bdi = false;
+
 	spin_lock(&inode_wb_list_lock);
 	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY)
+	if (inode->i_state & I_DIRTY) {
+		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
+			wakeup_bdi = true;
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	}
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_wb_list_lock);
+
+	if (wakeup_bdi)
+		bdi_wakeup_thread_delayed(dst);
 }
 
-static sector_t max_block(struct block_device *bdev)
+sector_t blkdev_max_block(struct block_device *bdev)
 {
 	sector_t retval = ~((sector_t)0);
 	loff_t sz = i_size_read(bdev->bd_inode);
@@ -135,7 +143,7 @@ static int
 blkdev_get_block(struct inode *inode, sector_t iblock,
 		struct buffer_head *bh, int create)
 {
-	if (iblock >= max_block(I_BDEV(inode))) {
+	if (iblock >= blkdev_max_block(I_BDEV(inode))) {
 		if (create)
 			return -EIO;
 
@@ -157,7 +165,7 @@ static int
 blkdev_get_blocks(struct inode *inode, sector_t iblock,
 		struct buffer_head *bh, int create)
 {
-	sector_t end_block = max_block(I_BDEV(inode));
+	sector_t end_block = blkdev_max_block(I_BDEV(inode));
 	unsigned long max_blocks = bh->b_size >> inode->i_blkbits;
 
 	if ((iblock + max_blocks) > end_block) {
@@ -576,6 +584,7 @@ struct block_device *bdgrab(struct block_device *bdev)
 	ihold(bdev->bd_inode);
 	return bdev;
 }
+EXPORT_SYMBOL(bdgrab);
 
 long nr_blockdev_pages(void)
 {
@@ -1052,7 +1061,9 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 {
 	unsigned bsize = bdev_logical_block_size(bdev);
 
-	bdev->bd_inode->i_size = size;
+	mutex_lock(&bdev->bd_inode->i_mutex);
+	i_size_write(bdev->bd_inode, size);
+	mutex_unlock(&bdev->bd_inode->i_mutex);
 	while (bsize < PAGE_CACHE_SIZE) {
 		if (size & bsize)
 			break;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 7ec1409..8006a28 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -212,10 +212,17 @@ static noinline int run_ordered_completions(struct btrfs_workers *workers,
 
 		work->ordered_func(work);
 
-		/* now take the lock again and call the freeing code */
+		/* now take the lock again and drop our item from the list */
 		spin_lock(&workers->order_lock);
 		list_del(&work->order_list);
+		spin_unlock(&workers->order_lock);
+
+		/*
+		 * we don't want to call the ordered free functions
+		 * with the lock held though
+		 */
 		work->ordered_free(work);
+		spin_lock(&workers->order_lock);
 	}
 
 	spin_unlock(&workers->order_lock);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1ac8db5d..57106a9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -801,7 +801,8 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 
 #ifdef CONFIG_MIGRATION
 static int btree_migratepage(struct address_space *mapping,
-			struct page *newpage, struct page *page)
+			struct page *newpage, struct page *page,
+			enum migrate_mode mode)
 {
 	/*
 	 * we can't safely write a btree page from here,
@@ -816,7 +817,7 @@ static int btree_migratepage(struct address_space *mapping,
 	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, mode);
 }
 #endif
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7e20a65..01220b7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3786,7 +3786,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	spin_lock(&block_rsv->lock);
 	spin_lock(&sinfo->lock);
 
-	block_rsv->size = num_bytes;
+	block_rsv->size = min_t(u64, num_bytes, 512 * 1024 * 1024);
 
 	num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
 		    sinfo->bytes_reserved + sinfo->bytes_readonly +
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a3c4751..a205027 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1539,7 +1539,11 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 		item_off = btrfs_item_ptr_offset(leaf, i);
 		item_len = btrfs_item_size_nr(leaf, i);
 
-		if (item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
+		btrfs_item_key_to_cpu(leaf, key, i);
+		if (!key_in_sk(key, sk))
+			continue;
+
+		if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
 			item_len = 0;
 
 		if (sizeof(sh) + item_len + *sk_offset >
@@ -1548,10 +1552,6 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 			goto overflow;
 		}
 
-		btrfs_item_key_to_cpu(leaf, key, i);
-		if (!key_in_sk(key, sk))
-			continue;
-
 		sh.objectid = key->objectid;
 		sh.offset = key->offset;
 		sh.type = key->type;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 5e0a3dc..2ab5837 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -670,6 +670,7 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
 	int cowonly;
 	int ret;
 	int err = 0;
+	bool need_check = true;
 
 	path1 = btrfs_alloc_path();
 	path2 = btrfs_alloc_path();
@@ -892,6 +893,7 @@ again:
 			cur->bytenr);
 
 		lower = cur;
+		need_check = true;
 		for (; level < BTRFS_MAX_LEVEL; level++) {
 			if (!path2->nodes[level]) {
 				BUG_ON(btrfs_root_bytenr(&root->root_item) !=
@@ -935,14 +937,12 @@ again:
 
 				/*
 				 * add the block to pending list if we
-				 * need check its backrefs. only block
-				 * at 'cur->level + 1' is added to the
-				 * tail of pending list. this guarantees
-				 * we check backrefs from lower level
-				 * blocks to upper level blocks.
+				 * need check its backrefs, we only do this once
+				 * while walking up a tree as we will catch
+				 * anything else later on.
 				 */
-				if (!upper->checked &&
-				    level == cur->level + 1) {
+				if (!upper->checked && need_check) {
+					need_check = false;
 					list_add_tail(&edge->list[UPPER],
 						      &list);
 				} else
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7fa128d..88dec16 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -315,6 +315,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 	unsigned long src_ptr;
 	unsigned long dst_ptr;
 	int overwrite_root = 0;
+	bool inode_item = key->type == BTRFS_INODE_ITEM_KEY;
 
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 		overwrite_root = 1;
@@ -324,6 +325,9 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 
 	/* look for the key in the destination tree */
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+
 	if (ret == 0) {
 		char *src_copy;
 		char *dst_copy;
@@ -365,6 +369,30 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 			return 0;
 		}
 
+		/*
+		 * We need to load the old nbytes into the inode so when we
+		 * replay the extents we've logged we get the right nbytes.
+		 */
+		if (inode_item) {
+			struct btrfs_inode_item *item;
+			u64 nbytes;
+
+			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+					      struct btrfs_inode_item);
+			nbytes = btrfs_inode_nbytes(path->nodes[0], item);
+			item = btrfs_item_ptr(eb, slot,
+					      struct btrfs_inode_item);
+			btrfs_set_inode_nbytes(eb, item, nbytes);
+		}
+	} else if (inode_item) {
+		struct btrfs_inode_item *item;
+
+		/*
+		 * New inode, set nbytes to 0 so that the nbytes comes out
+		 * properly when we replay the extents.
+		 */
+		item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
+		btrfs_set_inode_nbytes(eb, item, 0);
 	}
 insert:
 	btrfs_release_path(path);
@@ -487,7 +515,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	u64 extent_end;
 	u64 alloc_hint;
 	u64 start = key->offset;
-	u64 saved_nbytes;
+	u64 nbytes = 0;
 	struct btrfs_file_extent_item *item;
 	struct inode *inode = NULL;
 	unsigned long size;
@@ -497,10 +525,19 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	found_type = btrfs_file_extent_type(eb, item);
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
-	    found_type == BTRFS_FILE_EXTENT_PREALLOC)
-		extent_end = start + btrfs_file_extent_num_bytes(eb, item);
-	else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
+	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+		nbytes = btrfs_file_extent_num_bytes(eb, item);
+		extent_end = start + nbytes;
+
+		/*
+		 * We don't add to the inodes nbytes if we are prealloc or a
+		 * hole.
+		 */
+		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
+			nbytes = 0;
+	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size = btrfs_file_extent_inline_len(eb, item);
+		nbytes = btrfs_file_extent_ram_bytes(eb, item);
 		extent_end = (start + size + mask) & ~mask;
 	} else {
 		ret = 0;
@@ -549,7 +586,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	saved_nbytes = inode_get_bytes(inode);
 	/* drop any overlapping extents */
 	ret = btrfs_drop_extents(trans, inode, start, extent_end,
 				 &alloc_hint, 1);
@@ -637,7 +673,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		BUG_ON(ret);
 	}
 
-	inode_set_bytes(inode, saved_nbytes);
+	inode_add_bytes(inode, nbytes);
 	btrfs_update_inode(trans, root, inode);
 out:
 	if (inode)
@@ -691,6 +727,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 	kfree(name);
 
 	iput(inode);
+
+	btrfs_run_delayed_items(trans, root);
 	return ret;
 }
 
@@ -896,6 +934,7 @@ again:
 				ret = btrfs_unlink_inode(trans, root, dir,
 							 inode, victim_name,
 							 victim_name_len);
+				btrfs_run_delayed_items(trans, root);
 			}
 			kfree(victim_name);
 			ptr = (unsigned long)(victim_ref + 1) + victim_name_len;
@@ -1476,6 +1515,9 @@ again:
 			ret = btrfs_unlink_inode(trans, root, dir, inode,
 						 name, name_len);
 			BUG_ON(ret);
+
+			btrfs_run_delayed_items(trans, root);
+
 			kfree(name);
 			iput(inode);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 43baaf0..7745ad5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -512,6 +512,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		new_device->writeable = 0;
 		new_device->in_fs_metadata = 0;
 		new_device->can_discard = 0;
+		spin_lock_init(&new_device->io_lock);
 		list_replace_rcu(&device->dev_list, &new_device->dev_list);
 
 		call_rcu(&device->rcu, free_device);
@@ -545,6 +546,12 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		__btrfs_close_devices(fs_devices);
 		free_fs_devices(fs_devices);
 	}
+	/*
+	 * Wait for rcu kworkers under __btrfs_close_devices
+	 * to finish all blkdev_puts so device is really
+	 * free when umount is done.
+	 */
+	rcu_barrier();
 	return ret;
 }
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 1a80b04..166028b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -961,13 +961,14 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
 /*
  * Initialise the state of a blockdev page's buffers.
  */ 
-static void
+static sector_t
 init_page_buffers(struct page *page, struct block_device *bdev,
 			sector_t block, int size)
 {
 	struct buffer_head *head = page_buffers(page);
 	struct buffer_head *bh = head;
 	int uptodate = PageUptodate(page);
+	sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode));
 
 	do {
 		if (!buffer_mapped(bh)) {
@@ -976,38 +977,47 @@ init_page_buffers(struct page *page, struct block_device *bdev,
 			bh->b_blocknr = block;
 			if (uptodate)
 				set_buffer_uptodate(bh);
-			set_buffer_mapped(bh);
+			if (block < end_block)
+				set_buffer_mapped(bh);
 		}
 		block++;
 		bh = bh->b_this_page;
 	} while (bh != head);
+
+	/*
+	 * Caller needs to validate requested block against end of device.
+	 */
+	return end_block;
 }
 
 /*
  * Create the page-cache page that contains the requested block.
  *
- * This is user purely for blockdev mappings.
+ * This is used purely for blockdev mappings.
  */
-static struct page *
+static int
 grow_dev_page(struct block_device *bdev, sector_t block,
-		pgoff_t index, int size)
+		pgoff_t index, int size, int sizebits)
 {
 	struct inode *inode = bdev->bd_inode;
 	struct page *page;
 	struct buffer_head *bh;
+	sector_t end_block;
+	int ret = 0;		/* Will call free_more_memory() */
 
 	page = find_or_create_page(inode->i_mapping, index,
 		(mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
 	if (!page)
-		return NULL;
+		return ret;
 
 	BUG_ON(!PageLocked(page));
 
 	if (page_has_buffers(page)) {
 		bh = page_buffers(page);
 		if (bh->b_size == size) {
-			init_page_buffers(page, bdev, block, size);
-			return page;
+			end_block = init_page_buffers(page, bdev,
+						index << sizebits, size);
+			goto done;
 		}
 		if (!try_to_free_buffers(page))
 			goto failed;
@@ -1027,15 +1037,15 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	 */
 	spin_lock(&inode->i_mapping->private_lock);
 	link_dev_buffers(page, bh);
-	init_page_buffers(page, bdev, block, size);
+	end_block = init_page_buffers(page, bdev, index << sizebits, size);
 	spin_unlock(&inode->i_mapping->private_lock);
-	return page;
+done:
+	ret = (block < end_block) ? 1 : -ENXIO;
 
 failed:
-	BUG();
 	unlock_page(page);
 	page_cache_release(page);
-	return NULL;
+	return ret;
 }
 
 /*
@@ -1045,7 +1055,6 @@ failed:
 static int
 grow_buffers(struct block_device *bdev, sector_t block, int size)
 {
-	struct page *page;
 	pgoff_t index;
 	int sizebits;
 
@@ -1069,14 +1078,9 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
 			bdevname(bdev, b));
 		return -EIO;
 	}
-	block = index << sizebits;
+
 	/* Create a page with the proper size buffers.. */
-	page = grow_dev_page(bdev, block, index, size);
-	if (!page)
-		return 0;
-	unlock_page(page);
-	page_cache_release(page);
-	return 1;
+	return grow_dev_page(bdev, block, index, size, sizebits);
 }
 
 static struct buffer_head *
@@ -1095,7 +1099,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
 	}
 
 	for (;;) {
-		struct buffer_head * bh;
+		struct buffer_head *bh;
 		int ret;
 
 		bh = __find_get_block(bdev, block, size);
@@ -1363,10 +1367,6 @@ EXPORT_SYMBOL(__find_get_block);
  * which corresponds to the passed block_device, block and size. The
  * returned buffer has its reference count incremented.
  *
- * __getblk() cannot fail - it just keeps trying.  If you pass it an
- * illegal block number, __getblk() will happily return a buffer_head
- * which represents the non-existent block.  Very weird.
- *
  * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
  * attempt is failing.  FIXME, perhaps?
  */
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index f67b687..a080779 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -84,7 +84,7 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
  * FIXME: we should try harder by querying the mds for the ino.
  */
 static struct dentry *__fh_to_dentry(struct super_block *sb,
-				     struct ceph_nfs_fh *fh)
+				     struct ceph_nfs_fh *fh, int fh_len)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -92,6 +92,9 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
+	if (fh_len < sizeof(*fh) / 4)
+		return ERR_PTR(-ESTALE);
+
 	dout("__fh_to_dentry %llx\n", fh->ino);
 	vino.ino = fh->ino;
 	vino.snap = CEPH_NOSNAP;
@@ -136,7 +139,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
  * convert connectable fh to dentry
  */
 static struct dentry *__cfh_to_dentry(struct super_block *sb,
-				      struct ceph_nfs_confh *cfh)
+				      struct ceph_nfs_confh *cfh, int fh_len)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -144,6 +147,9 @@ static struct dentry *__cfh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
+
 	dout("__cfh_to_dentry %llx (%llx/%x)\n",
 	     cfh->ino, cfh->parent_ino, cfh->parent_name_hash);
 
@@ -193,9 +199,11 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb, struct fid *fid,
 					int fh_len, int fh_type)
 {
 	if (fh_type == 1)
-		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw);
+		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw,
+								fh_len);
 	else
-		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw);
+		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw,
+								fh_len);
 }
 
 /*
@@ -216,6 +224,8 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 
 	if (fh_type == 1)
 		return ERR_PTR(-ESTALE);
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
 
 	pr_debug("fh_to_parent %llx/%d\n", cfh->parent_ino,
 		 cfh->parent_name_hash);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index f2f77fd..1775022 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -70,8 +70,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	/*
 	 * express utilization in terms of large blocks to avoid
 	 * overflow on 32-bit machines.
+	 *
+	 * NOTE: for the time being, we make bsize == frsize to humor
+	 * not-yet-ancient versions of glibc that are broken.
+	 * Someday, we will probably want to report a real block
+	 * size...  whatever that may mean for a network file system!
 	 */
 	buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
+	buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
 	buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
 	buf->f_bfree = (le64_to_cpu(st.kb) - le64_to_cpu(st.kb_used)) >>
 		(CEPH_BLOCK_SHIFT-10);
@@ -80,7 +86,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = le64_to_cpu(st.num_objects);
 	buf->f_ffree = -1;
 	buf->f_namelen = NAME_MAX;
-	buf->f_frsize = PAGE_CACHE_SIZE;
 
 	/* leave fsid little-endian, regardless of host endianness */
 	fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f5cabef..9091926 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -21,7 +21,7 @@
 
 /* large granularity for statfs utilization stats to facilitate
  * large volume sizes on 32-bit machines. */
-#define CEPH_BLOCK_SHIFT   20  /* 1 MB */
+#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
 #define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index cfd1ce3..1d36db1 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -614,53 +614,10 @@ decode_negTokenInit(unsigned char *security_blob, int length,
 		}
 	}
 
-	/* mechlistMIC */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		/* Check if we have reached the end of the blob, but with
-		   no mechListMic (e.g. NTLMSSP instead of KRB5) */
-		if (ctx.error == ASN1_ERR_DEC_EMPTY)
-			goto decode_negtoken_exit;
-		cFYI(1, "Error decoding last part negTokenInit exit3");
-		return 0;
-	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		/* tag = 3 indicating mechListMIC */
-		cFYI(1, "Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-
-	/* sequence */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit5");
-		return 0;
-	} else if ((cls != ASN1_UNI) || (con != ASN1_CON)
-		   || (tag != ASN1_SEQ)) {
-		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-	}
-
-	/* sequence of */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit 7");
-		return 0;
-	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		cFYI(1, "Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-
-	/* general string */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit9");
-		return 0;
-	} else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
-		   || (tag != ASN1_GENSTR)) {
-		cFYI(1, "Exit10 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-	cFYI(1, "Need to call asn1_octets_decode() function for %s",
-		ctx.pointer);	/* is this UTF-8 or ASCII? */
-decode_negtoken_exit:
+	/*
+	 * We currently ignore anything at the end of the SPNEGO blob after
+	 * the mechTypes have been parsed, since none of that info is
+	 * used at the moment.
+	 */
 	return 1;
 }
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 8d8f28c..993384e4 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/vfs.h>
 #include <linux/fs.h>
+#include <linux/inet.h>
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifsfs.h"
@@ -149,7 +150,8 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	 * assuming that we have 'unc=' and 'ip=' in
 	 * the original sb_mountdata
 	 */
-	md_len = strlen(sb_mountdata) + rc + strlen(ref->node_name) + 12;
+	md_len = strlen(sb_mountdata) + rc + strlen(ref->node_name) + 12 +
+			INET6_ADDRSTRLEN;
 	mountdata = kzalloc(md_len+1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		rc = -ENOMEM;
@@ -225,6 +227,8 @@ compose_mount_options_out:
 compose_mount_options_err:
 	kfree(mountdata);
 	mountdata = ERR_PTR(rc);
+	kfree(*devname);
+	*devname = NULL;
 	goto compose_mount_options_out;
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 53e7d72..bf6aa8c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -571,6 +571,11 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 			dentry = ERR_PTR(-ENOENT);
 			break;
 		}
+		if (!S_ISDIR(dir->i_mode)) {
+			dput(dentry);
+			dentry = ERR_PTR(-ENOTDIR);
+			break;
+		}
 
 		/* skip separators */
 		while (*s == sep)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 6255fa8..7cb9dd2 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -43,6 +43,7 @@
 
 #define CIFS_MIN_RCV_POOL 4
 
+#define MAX_REOPEN_ATT	5 /* these many maximum attempts to reopen a file */
 /*
  * default attribute cache timeout (jiffies)
  */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 07132c4..219933b 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -3473,13 +3473,12 @@ CIFSSMBSetCIFSACL(const int xid, struct cifs_tcon *tcon, __u16 fid,
 	int rc = 0;
 	int bytes_returned = 0;
 	SET_SEC_DESC_REQ *pSMB = NULL;
-	NTRANSACT_RSP *pSMBr = NULL;
+	void *pSMBr;
 
 setCifsAclRetry:
-	rc = smb_init(SMB_COM_NT_TRANSACT, 19, tcon, (void **) &pSMB,
-			(void **) &pSMBr);
+	rc = smb_init(SMB_COM_NT_TRANSACT, 19, tcon, (void **) &pSMB, &pSMBr);
 	if (rc)
-			return (rc);
+		return rc;
 
 	pSMB->MaxSetupCount = 0;
 	pSMB->Reserved = 0;
@@ -3507,9 +3506,8 @@ setCifsAclRetry:
 	pSMB->AclFlags = cpu_to_le32(CIFS_ACL_DACL);
 
 	if (pntsd && acllen) {
-		memcpy((char *) &pSMBr->hdr.Protocol + data_offset,
-			(char *) pntsd,
-			acllen);
+		memcpy((char *)pSMBr + offsetof(struct smb_hdr, Protocol) +
+				data_offset, pntsd, acllen);
 		inc_rfc1001_len(pSMB, byte_count + data_count);
 	} else
 		inc_rfc1001_len(pSMB, byte_count);
@@ -5291,7 +5289,8 @@ CIFSSMBSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
 	offset = param_offset + params;
 
-	data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
+	data_offset = (char *)pSMB +
+			offsetof(struct smb_hdr, Protocol) + offset;
 
 	count = sizeof(FILE_BASIC_INFO);
 	pSMB->MaxParameterCount = cpu_to_le16(2);
@@ -5560,7 +5559,7 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 		       u16 fid, u32 pid_of_opener)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
-	FILE_UNIX_BASIC_INFO *data_offset;
+	char *data_offset;
 	int rc = 0;
 	u16 params, param_offset, offset, byte_count, count;
 
@@ -5582,8 +5581,9 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
 	offset = param_offset + params;
 
-	data_offset = (FILE_UNIX_BASIC_INFO *)
-				((char *)(&pSMB->hdr.Protocol) + offset);
+	data_offset = (char *)pSMB +
+			offsetof(struct smb_hdr, Protocol) + offset;
+
 	count = sizeof(FILE_UNIX_BASIC_INFO);
 
 	pSMB->MaxParameterCount = cpu_to_le16(2);
@@ -5605,7 +5605,7 @@ CIFSSMBUnixSetFileInfo(const int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 
-	cifs_fill_unix_set_info(data_offset, args);
+	cifs_fill_unix_set_info((FILE_UNIX_BASIC_INFO *)data_offset, args);
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
 	if (rc)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index b775809..9e6ee47 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -158,6 +158,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		try_to_freeze();
 
 		/* we should try only the port we connected to before */
+		mutex_lock(&server->srv_mutex);
 		rc = generic_ip_connect(server);
 		if (rc) {
 			cFYI(1, "reconnect error %d", rc);
@@ -169,6 +170,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 				server->tcpStatus = CifsNeedNegotiate;
 			spin_unlock(&GlobalMid_Lock);
 		}
+		mutex_unlock(&server->srv_mutex);
 	} while (server->tcpStatus == CifsNeedReconnect);
 
 	return rc;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index a9b4a24..9040cb0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -973,10 +973,11 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
 					bool fsuid_only)
 {
-	struct cifsFileInfo *open_file;
+	struct cifsFileInfo *open_file, *inv_file = NULL;
 	struct cifs_sb_info *cifs_sb;
 	bool any_available = false;
 	int rc;
+	unsigned int refind = 0;
 
 	/* Having a null inode here (because mapping->host was set to zero by
 	the VFS or MM) should not happen but we had reports of on oops (due to
@@ -996,40 +997,25 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
 
 	spin_lock(&cifs_file_list_lock);
 refind_writable:
+	if (refind > MAX_REOPEN_ATT) {
+		spin_unlock(&cifs_file_list_lock);
+		return NULL;
+	}
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
 		if (!any_available && open_file->pid != current->tgid)
 			continue;
 		if (fsuid_only && open_file->uid != current_fsuid())
 			continue;
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
-			cifsFileInfo_get(open_file);
-
 			if (!open_file->invalidHandle) {
 				/* found a good writable file */
+				cifsFileInfo_get(open_file);
 				spin_unlock(&cifs_file_list_lock);
 				return open_file;
+			} else {
+				if (!inv_file)
+					inv_file = open_file;
 			}
-
-			spin_unlock(&cifs_file_list_lock);
-
-			/* Had to unlock since following call can block */
-			rc = cifs_reopen_file(open_file, false);
-			if (!rc)
-				return open_file;
-
-			/* if it fails, try another handle if possible */
-			cFYI(1, "wp failed on reopen file");
-			cifsFileInfo_put(open_file);
-
-			spin_lock(&cifs_file_list_lock);
-
-			/* else we simply continue to the next entry. Thus
-			   we do not loop on reopen errors.  If we
-			   can not reopen the file, for example if we
-			   reconnected to a server with another client
-			   racing to delete or lock the file we would not
-			   make progress if we restarted before the beginning
-			   of the loop here. */
 		}
 	}
 	/* couldn't find useable FH with same pid, try any available */
@@ -1037,7 +1023,30 @@ refind_writable:
 		any_available = true;
 		goto refind_writable;
 	}
+
+	if (inv_file) {
+		any_available = false;
+		cifsFileInfo_get(inv_file);
+	}
+
 	spin_unlock(&cifs_file_list_lock);
+
+	if (inv_file) {
+		rc = cifs_reopen_file(inv_file, false);
+		if (!rc)
+			return inv_file;
+		else {
+			spin_lock(&cifs_file_list_lock);
+			list_move_tail(&inv_file->flist,
+					&cifs_inode->openFileList);
+			spin_unlock(&cifs_file_list_lock);
+			cifsFileInfo_put(inv_file);
+			spin_lock(&cifs_file_list_lock);
+			++refind;
+			goto refind_writable;
+		}
+	}
+
 	return NULL;
 }
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 745e5cd..6f37228 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -173,7 +173,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 
 	if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
 		inode->i_flags |= S_AUTOMOUNT;
-	cifs_set_ops(inode);
+	if (inode->i_state & I_NEW)
+		cifs_set_ops(inode);
 }
 
 void
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 6751e74..c71032b 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -85,9 +85,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
 
 	dentry = d_lookup(parent, name);
 	if (dentry) {
-		/* FIXME: check for inode number changes? */
-		if (dentry->d_inode != NULL)
+		inode = dentry->d_inode;
+		/* update inode in place if i_ino didn't change */
+		if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) {
+			cifs_fattr_to_inode(inode, fattr);
 			return dentry;
+		}
 		d_drop(dentry);
 		dput(dentry);
 	}
diff --git a/fs/compat.c b/fs/compat.c
index 0ea0083..f77a963 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -576,6 +576,10 @@ ssize_t compat_rw_copy_check_uvector(int type,
 	}
 	*ret_pointer = iov;
 
+	ret = -EFAULT;
+	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+		goto out;
+
 	/*
 	 * Single unix specification:
 	 * We should -EINVAL if an element length is not >= 0 and fitting an
@@ -1106,17 +1110,12 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	if (!file->f_op)
 		goto out;
 
-	ret = -EFAULT;
-	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs,
+	ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
 					       UIO_FASTIOV, iovstack, &iov);
-	if (tot_len == 0) {
-		ret = 0;
+	if (ret <= 0)
 		goto out;
-	}
 
+	tot_len = ret;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
@@ -1177,11 +1176,14 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec,
 	struct file *file;
 	int fput_needed;
 	ssize_t ret;
+	loff_t pos;
 
 	file = fget_light(fd, &fput_needed);
 	if (!file)
 		return -EBADF;
-	ret = compat_readv(file, vec, vlen, &file->f_pos);
+	pos = file->f_pos;
+	ret = compat_readv(file, vec, vlen, &pos);
+	file->f_pos = pos;
 	fput_light(file, fput_needed);
 	return ret;
 }
@@ -1236,11 +1238,14 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec,
 	struct file *file;
 	int fput_needed;
 	ssize_t ret;
+	loff_t pos;
 
 	file = fget_light(fd, &fput_needed);
 	if (!file)
 		return -EBADF;
-	ret = compat_writev(file, vec, vlen, &file->f_pos);
+	pos = file->f_pos;
+	ret = compat_writev(file, vec, vlen, &pos);
+	file->f_pos = pos;
 	fput_light(file, fput_needed);
 	return ret;
 }
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 61abb63..3deb58d 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -208,6 +208,8 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd,
 
 	err  = get_user(palp, &up->palette);
 	err |= get_user(length, &up->length);
+	if (err)
+		return -EFAULT;
 
 	up_native = compat_alloc_user_space(sizeof(struct video_spu_palette));
 	err  = put_user(compat_ptr(palp), &up_native->palette);
diff --git a/fs/dcache.c b/fs/dcache.c
index 0b51cfc..ecc0742 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -290,7 +290,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
 	 * Inform try_to_ascend() that we are no longer attached to the
 	 * dentry tree
 	 */
-	dentry->d_flags |= DCACHE_DISCONNECTED;
+	dentry->d_flags |= DCACHE_DENTRY_KILLED;
 	if (parent)
 		spin_unlock(&parent->d_lock);
 	dentry_iput(dentry);
@@ -1015,7 +1015,7 @@ static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq
 	 * or deletion
 	 */
 	if (new != old->d_parent ||
-		 (old->d_flags & DCACHE_DISCONNECTED) ||
+		 (old->d_flags & DCACHE_DENTRY_KILLED) ||
 		 (!locked && read_seqretry(&rename_lock, seq))) {
 		spin_unlock(&new->d_lock);
 		new = NULL;
@@ -1101,6 +1101,8 @@ positive:
 	return 1;
 
 rename_retry:
+	if (locked)
+		goto again;
 	locked = 1;
 	write_seqlock(&rename_lock);
 	goto again;
@@ -1203,6 +1205,8 @@ out:
 rename_retry:
 	if (found)
 		return found;
+	if (locked)
+		goto again;
 	locked = 1;
 	write_seqlock(&rename_lock);
 	goto again;
@@ -1559,7 +1563,7 @@ static struct dentry * d_find_any_alias(struct inode *inode)
  */
 struct dentry *d_obtain_alias(struct inode *inode)
 {
-	static const struct qstr anonstring = { .name = "" };
+	static const struct qstr anonstring = { .name = "/", .len = 1 };
 	struct dentry *tmp;
 	struct dentry *res;
 
@@ -2990,6 +2994,8 @@ resume:
 	return;
 
 rename_retry:
+	if (locked)
+		goto again;
 	locked = 1;
 	write_seqlock(&rename_lock);
 	goto again;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index e7a7a2f..eac5b7c 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -380,8 +380,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
  */
 void debugfs_remove_recursive(struct dentry *dentry)
 {
-	struct dentry *child;
-	struct dentry *parent;
+	struct dentry *child, *next, *parent;
 
 	if (!dentry)
 		return;
@@ -391,61 +390,37 @@ void debugfs_remove_recursive(struct dentry *dentry)
 		return;
 
 	parent = dentry;
+ down:
 	mutex_lock(&parent->d_inode->i_mutex);
+	list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+		if (!debugfs_positive(child))
+			continue;
 
-	while (1) {
-		/*
-		 * When all dentries under "parent" has been removed,
-		 * walk up the tree until we reach our starting point.
-		 */
-		if (list_empty(&parent->d_subdirs)) {
-			mutex_unlock(&parent->d_inode->i_mutex);
-			if (parent == dentry)
-				break;
-			parent = parent->d_parent;
-			mutex_lock(&parent->d_inode->i_mutex);
-		}
-		child = list_entry(parent->d_subdirs.next, struct dentry,
-				d_u.d_child);
- next_sibling:
-
-		/*
-		 * If "child" isn't empty, walk down the tree and
-		 * remove all its descendants first.
-		 */
+		/* perhaps simple_empty(child) makes more sense */
 		if (!list_empty(&child->d_subdirs)) {
 			mutex_unlock(&parent->d_inode->i_mutex);
 			parent = child;
-			mutex_lock(&parent->d_inode->i_mutex);
-			continue;
-		}
-		__debugfs_remove(child, parent);
-		if (parent->d_subdirs.next == &child->d_u.d_child) {
-			/*
-			 * Try the next sibling.
-			 */
-			if (child->d_u.d_child.next != &parent->d_subdirs) {
-				child = list_entry(child->d_u.d_child.next,
-						   struct dentry,
-						   d_u.d_child);
-				goto next_sibling;
-			}
-
-			/*
-			 * Avoid infinite loop if we fail to remove
-			 * one dentry.
-			 */
-			mutex_unlock(&parent->d_inode->i_mutex);
-			break;
+			goto down;
 		}
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ up:
+		if (!__debugfs_remove(child, parent))
+			simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	}
 
-	parent = dentry->d_parent;
+	mutex_unlock(&parent->d_inode->i_mutex);
+	child = parent;
+	parent = parent->d_parent;
 	mutex_lock(&parent->d_inode->i_mutex);
-	__debugfs_remove(dentry, parent);
+
+	if (child != dentry) {
+		next = list_entry(child->d_u.d_child.next, struct dentry,
+					d_u.d_child);
+		goto up;
+	}
+
+	if (!__debugfs_remove(child, parent))
+		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	mutex_unlock(&parent->d_inode->i_mutex);
-	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
 EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
 
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 2717329..4a91a05 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -653,6 +653,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *lower_old_dir_dentry;
 	struct dentry *lower_new_dir_dentry;
 	struct dentry *trap = NULL;
+	struct inode *target_inode;
 
 	lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
 	lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
@@ -660,6 +661,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	dget(lower_new_dentry);
 	lower_old_dir_dentry = dget_parent(lower_old_dentry);
 	lower_new_dir_dentry = dget_parent(lower_new_dentry);
+	target_inode = new_dentry->d_inode;
 	trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
 	/* source should not be ancestor of target */
 	if (trap == lower_old_dentry) {
@@ -675,6 +677,9 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			lower_new_dir_dentry->d_inode, lower_new_dentry);
 	if (rc)
 		goto out_lock;
+	if (target_inode)
+		fsstack_copy_attr_all(target_inode,
+				      ecryptfs_inode_to_lower(target_inode));
 	fsstack_copy_attr_all(new_dir, lower_new_dir_dentry->d_inode);
 	if (new_dir != old_dir)
 		fsstack_copy_attr_all(old_dir, lower_old_dir_dentry->d_inode);
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index 69f994a..0dbe58a 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -149,7 +149,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	(*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred);
 	if (!IS_ERR(*lower_file))
 		goto out;
-	if (flags & O_RDONLY) {
+	if ((flags & O_ACCMODE) == O_RDONLY) {
 		rc = PTR_ERR((*lower_file));
 		goto out;
 	}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index b4a6bef..d1125e3 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -279,6 +279,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	char *fnek_src;
 	char *cipher_key_bytes_src;
 	char *fn_cipher_key_bytes_src;
+	u8 cipher_code;
 
 	*check_ruid = 0;
 
@@ -420,6 +421,18 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	    && !fn_cipher_key_bytes_set)
 		mount_crypt_stat->global_default_fn_cipher_key_bytes =
 			mount_crypt_stat->global_default_cipher_key_size;
+
+	cipher_code = ecryptfs_code_for_cipher_string(
+		mount_crypt_stat->global_default_cipher_name,
+		mount_crypt_stat->global_default_cipher_key_size);
+	if (!cipher_code) {
+		ecryptfs_printk(KERN_ERR,
+				"eCryptfs doesn't support cipher: %s",
+				mount_crypt_stat->global_default_cipher_name);
+		rc = -EINVAL;
+		goto out;
+	}
+
 	mutex_lock(&key_tfm_list_mutex);
 	if (!ecryptfs_tfm_exists(mount_crypt_stat->global_default_cipher_name,
 				 NULL)) {
@@ -505,7 +518,6 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	s->s_flags = flags;
 	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
 	if (rc)
 		goto out1;
@@ -541,6 +553,15 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	}
 
 	ecryptfs_set_superblock_lower(s, path.dentry->d_sb);
+
+	/**
+	 * Set the POSIX ACL flag based on whether they're enabled in the lower
+	 * mount. Force a read-only eCryptfs mount if the lower mount is ro.
+	 * Allow a ro eCryptfs mount even when the lower mount is rw.
+	 */
+	s->s_flags = flags & ~MS_POSIXACL;
+	s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
 	s->s_magic = ECRYPTFS_SUPER_MAGIC;
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 0dc5a3d..de42310 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -49,7 +49,10 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt)
 	mutex_lock(&ecryptfs_daemon_hash_mux);
 	/* TODO: Just use file->private_data? */
 	rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns());
-	BUG_ON(rc || !daemon);
+	if (rc || !daemon) {
+		mutex_unlock(&ecryptfs_daemon_hash_mux);
+		return -EINVAL;
+	}
 	mutex_lock(&daemon->mux);
 	mutex_unlock(&ecryptfs_daemon_hash_mux);
 	if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
@@ -122,6 +125,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
 		goto out_unlock_daemon;
 	}
 	daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN;
+	file->private_data = daemon;
 	atomic_inc(&ecryptfs_num_miscdev_opens);
 out_unlock_daemon:
 	mutex_unlock(&daemon->mux);
@@ -152,9 +156,9 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&ecryptfs_daemon_hash_mux);
 	rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns());
-	BUG_ON(rc || !daemon);
+	if (rc || !daemon)
+		daemon = file->private_data;
 	mutex_lock(&daemon->mux);
-	BUG_ON(daemon->pid != task_pid(current));
 	BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN));
 	daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN;
 	atomic_dec(&ecryptfs_num_miscdev_opens);
@@ -191,31 +195,32 @@ int ecryptfs_send_miscdev(char *data, size_t data_size,
 			  struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
 			  u16 msg_flags, struct ecryptfs_daemon *daemon)
 {
-	int rc = 0;
+	struct ecryptfs_message *msg;
 
-	mutex_lock(&msg_ctx->mux);
-	msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size),
-			       GFP_KERNEL);
-	if (!msg_ctx->msg) {
-		rc = -ENOMEM;
+	msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL);
+	if (!msg) {
 		printk(KERN_ERR "%s: Out of memory whilst attempting "
 		       "to kmalloc(%zd, GFP_KERNEL)\n", __func__,
-		       (sizeof(*msg_ctx->msg) + data_size));
-		goto out_unlock;
+		       (sizeof(*msg) + data_size));
+		return -ENOMEM;
 	}
+
+	mutex_lock(&msg_ctx->mux);
+	msg_ctx->msg = msg;
 	msg_ctx->msg->index = msg_ctx->index;
 	msg_ctx->msg->data_len = data_size;
 	msg_ctx->type = msg_type;
 	memcpy(msg_ctx->msg->data, data, data_size);
 	msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size);
-	mutex_lock(&daemon->mux);
 	list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue);
+	mutex_unlock(&msg_ctx->mux);
+
+	mutex_lock(&daemon->mux);
 	daemon->num_queued_msg_ctx++;
 	wake_up_interruptible(&daemon->wait);
 	mutex_unlock(&daemon->mux);
-out_unlock:
-	mutex_unlock(&msg_ctx->mux);
-	return rc;
+
+	return 0;
 }
 
 /**
@@ -246,8 +251,16 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count,
 	mutex_lock(&ecryptfs_daemon_hash_mux);
 	/* TODO: Just use file->private_data? */
 	rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns());
-	BUG_ON(rc || !daemon);
+	if (rc || !daemon) {
+		mutex_unlock(&ecryptfs_daemon_hash_mux);
+		return -EINVAL;
+	}
 	mutex_lock(&daemon->mux);
+	if (task_pid(current) != daemon->pid) {
+		mutex_unlock(&daemon->mux);
+		mutex_unlock(&ecryptfs_daemon_hash_mux);
+		return -EPERM;
+	}
 	if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
 		rc = 0;
 		mutex_unlock(&ecryptfs_daemon_hash_mux);
@@ -284,9 +297,6 @@ check_list:
 		 * message from the queue; try again */
 		goto check_list;
 	}
-	BUG_ON(euid != daemon->euid);
-	BUG_ON(current_user_ns() != daemon->user_ns);
-	BUG_ON(task_pid(current) != daemon->pid);
 	msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue,
 				   struct ecryptfs_msg_ctx, daemon_out_list);
 	BUG_ON(!msg_ctx);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 35a852a..35a1a61 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1197,10 +1197,30 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
 	 * otherwise we might miss an event that happens between the
 	 * f_op->poll() call and the new event set registering.
 	 */
-	epi->event.events = event->events;
+	epi->event.events = event->events; /* need barrier below */
 	epi->event.data = event->data; /* protected by mtx */
 
 	/*
+	 * The following barrier has two effects:
+	 *
+	 * 1) Flush epi changes above to other CPUs.  This ensures
+	 *    we do not miss events from ep_poll_callback if an
+	 *    event occurs immediately after we call f_op->poll().
+	 *    We need this because we did not take ep->lock while
+	 *    changing epi above (but ep_poll_callback does take
+	 *    ep->lock).
+	 *
+	 * 2) We also need to ensure we do not miss _past_ events
+	 *    when calling f_op->poll().  This barrier also
+	 *    pairs with the barrier in wq_has_sleeper (see
+	 *    comments for wq_has_sleeper).
+	 *
+	 * This barrier will now guarantee ep_poll_callback or f_op->poll
+	 * (or both) will notice the readiness of an item.
+	 */
+	smp_mb();
+
+	/*
 	 * Get current event bits. We can safely use the file* here because
 	 * its usage count has been increased by the caller of this function.
 	 */
diff --git a/fs/exec.c b/fs/exec.c
index 044c13f..9ab31ca 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1149,13 +1149,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 		set_dumpable(current->mm, suid_dumpable);
 	}
 
-	/*
-	 * Flush performance counters when crossing a
-	 * security domain:
-	 */
-	if (!get_dumpable(current->mm))
-		perf_event_exit_task(current);
-
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
 
@@ -1192,9 +1185,24 @@ void free_bprm(struct linux_binprm *bprm)
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
+	/* If a binfmt changed the interp, free it. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
 	kfree(bprm);
 }
 
+int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+{
+	/* If a binfmt changed the interp, free it first. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
+	bprm->interp = kstrdup(interp, GFP_KERNEL);
+	if (!bprm->interp)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(bprm_change_interp);
+
 /*
  * install the new credentials for this executable
  */
@@ -1204,6 +1212,15 @@ void install_exec_creds(struct linux_binprm *bprm)
 
 	commit_creds(bprm->cred);
 	bprm->cred = NULL;
+
+	/*
+	 * Disable monitoring for regular users
+	 * when executing setuid binaries. Must
+	 * wait until new credentials are committed
+	 * by commit_creds() above
+	 */
+	if (get_dumpable(current->mm) != SUID_DUMP_USER)
+		perf_event_exit_task(current);
 	/*
 	 * cred_guard_mutex must be held at least to this point to prevent
 	 * ptrace_attach() from altering our determination of the task's
@@ -1354,6 +1371,10 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	int try,retval;
 	struct linux_binfmt *fmt;
 
+	/* This allows 4 levels of binfmt rewrites before failing hard. */
+	if (depth > 5)
+		return -ELOOP;
+
 	retval = security_bprm_check(bprm);
 	if (retval)
 		return retval;
@@ -1372,12 +1393,8 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			if (!try_module_get(fmt->module))
 				continue;
 			read_unlock(&binfmt_lock);
+			bprm->recursion_depth = depth + 1;
 			retval = fn(bprm, regs);
-			/*
-			 * Restore the depth counter to its starting value
-			 * in this call, so we don't have to rely on every
-			 * load_binary function to restore it on return.
-			 */
 			bprm->recursion_depth = depth;
 			if (retval >= 0) {
 				if (depth == 0)
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index bfc2dc4..0b3da7c 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -561,8 +561,12 @@ got:
 	if (IS_DIRSYNC(inode))
 		handle->h_sync = 1;
 	if (insert_inode_locked(inode) < 0) {
-		err = -EINVAL;
-		goto fail_drop;
+		/*
+		 * Likely a bitmap corruption causing inode to be allocated
+		 * twice.
+		 */
+		err = -EIO;
+		goto fail;
 	}
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index db9ba1a..0aedb27 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -3013,6 +3013,8 @@ static int ext3_do_update_inode(handle_t *handle,
 	struct ext3_inode_info *ei = EXT3_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	int err = 0, rc, block;
+	int need_datasync = 0;
+	__le32 disksize;
 
 again:
 	/* we can't allow multiple procs in here at once, its a bit racey */
@@ -3050,7 +3052,11 @@ again:
 		raw_inode->i_gid_high = 0;
 	}
 	raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
-	raw_inode->i_size = cpu_to_le32(ei->i_disksize);
+	disksize = cpu_to_le32(ei->i_disksize);
+	if (disksize != raw_inode->i_size) {
+		need_datasync = 1;
+		raw_inode->i_size = disksize;
+	}
 	raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
 	raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
 	raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
@@ -3066,8 +3072,11 @@ again:
 	if (!S_ISREG(inode->i_mode)) {
 		raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl);
 	} else {
-		raw_inode->i_size_high =
-			cpu_to_le32(ei->i_disksize >> 32);
+		disksize = cpu_to_le32(ei->i_disksize >> 32);
+		if (disksize != raw_inode->i_size_high) {
+			raw_inode->i_size_high = disksize;
+			need_datasync = 1;
+		}
 		if (ei->i_disksize > 0x7fffffffULL) {
 			struct super_block *sb = inode->i_sb;
 			if (!EXT3_HAS_RO_COMPAT_FEATURE(sb,
@@ -3120,6 +3129,8 @@ again:
 	ext3_clear_inode_state(inode, EXT3_STATE_NEW);
 
 	atomic_set(&ei->i_sync_tid, handle->h_transaction->t_tid);
+	if (need_datasync)
+		atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
 out_brelse:
 	brelse (bh);
 	ext3_std_error(inode->i_sb, err);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index e5a7111..8c9f82d 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -584,11 +584,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 		if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
 					(block<<EXT3_BLOCK_SIZE_BITS(dir->i_sb))
 						+((char *)de - bh->b_data))) {
-			/* On error, skip the f_pos to the next block. */
-			dir_file->f_pos = (dir_file->f_pos |
-					(dir->i_sb->s_blocksize - 1)) + 1;
-			brelse (bh);
-			return count;
+			/* silently ignore the rest of the block */
+			break;
 		}
 		ext3fs_dirhash(de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index aad153e..ba57a63 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -371,7 +371,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
 	return bdev;
 
 fail:
-	ext3_msg(sb, "error: failed to open journal device %s: %ld",
+	ext3_msg(sb, KERN_ERR, "error: failed to open journal device %s: %ld",
 		__bdevname(dev, b), PTR_ERR(bdev));
 
 	return NULL;
@@ -892,7 +892,7 @@ static ext3_fsblk_t get_sb_block(void **data, struct super_block *sb)
 	/*todo: use simple_strtoll with >32bit ext3 */
 	sb_block = simple_strtoul(options, &options, 0);
 	if (*options && *options != ',') {
-		ext3_msg(sb, "error: invalid sb specification: %s",
+		ext3_msg(sb, KERN_ERR, "error: invalid sb specification: %s",
 		       (char *) *data);
 		return 1;
 	}
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 9ed1bb1..5459168 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -82,4 +82,5 @@ config EXT4_DEBUG
 	  Enables run-time debugging support for the ext4 filesystem.
 
 	  If you select Y here, then you will be able to turn on debugging
-	  with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
+	  with a command such as:
+		echo 1 > /sys/module/ext4/parameters/mballoc_debug
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 21eacd7..4922087 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -450,8 +450,10 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
 
 retry:
 	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		error = PTR_ERR(handle);
+		goto release_and_out;
+	}
 	error = ext4_set_acl(handle, inode, type, acl);
 	ext4_journal_stop(handle);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 264f694..ebe95f5 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -514,7 +514,8 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 		if (bitmap_bh == NULL)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_BLOCKS_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
 			i, ext4_free_blks_count(sb, gdp), x);
 		bitmap_count += x;
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index fa3af81..012faaa 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -15,15 +15,13 @@
 
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
 {
 	unsigned int i, sum = 0;
 
-	if (!map)
-		return 0;
 	for (i = 0; i < numchars; i++)
-		sum += nibblemap[map->b_data[i] & 0xf] +
-			nibblemap[(map->b_data[i] >> 4) & 0xf];
+		sum += nibblemap[bitmap[i] & 0xf] +
+			nibblemap[(bitmap[i] >> 4) & 0xf];
 	return sum;
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1a34c1c..2041de7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -288,9 +288,9 @@ struct ext4_group_desc
  */
 
 struct flex_groups {
-	atomic_t free_inodes;
-	atomic_t free_blocks;
-	atomic_t used_dirs;
+	atomic64_t	free_blocks;
+	atomic_t	free_inodes;
+	atomic_t	used_dirs;
 };
 
 #define EXT4_BG_INODE_UNINIT	0x0001 /* Inode table/bitmap not in use */
@@ -1713,7 +1713,7 @@ struct mmpd_data {
 # define NORET_AND	noreturn,
 
 /* bitmap.c */
-extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
 
 /* balloc.c */
 extern unsigned int ext4_block_group(struct super_block *sb,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 611647b..d432d37 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2140,13 +2140,14 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
  * last index in the block only.
  */
 static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
-			struct ext4_ext_path *path)
+			struct ext4_ext_path *path, int depth)
 {
 	int err;
 	ext4_fsblk_t leaf;
 
 	/* free index block */
-	path--;
+	depth--;
+	path = path + depth;
 	leaf = ext4_idx_pblock(path->p_idx);
 	if (unlikely(path->p_hdr->eh_entries == 0)) {
 		EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
@@ -2162,6 +2163,19 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 	ext_debug("index is empty, remove it, free block %llu\n", leaf);
 	ext4_free_blocks(handle, inode, NULL, leaf, 1,
 			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+
+	while (--depth >= 0) {
+		if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr))
+			break;
+		path--;
+		err = ext4_ext_get_access(handle, inode, path);
+		if (err)
+			break;
+		path->p_idx->ei_block = (path+1)->p_idx->ei_block;
+		err = ext4_ext_dirty(handle, inode, path);
+		if (err)
+			break;
+	}
 	return err;
 }
 
@@ -2509,7 +2523,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	/* if this leaf is free, then we should
 	 * remove it from index block above */
 	if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
-		err = ext4_ext_rm_idx(handle, inode, path + depth);
+		err = ext4_ext_rm_idx(handle, inode, path, depth);
 
 out:
 	return err;
@@ -2639,7 +2653,7 @@ again:
 				/* index is empty, remove it;
 				 * handle must be already prepared by the
 				 * truncatei_leaf() */
-				err = ext4_ext_rm_idx(handle, inode, path + i);
+				err = ext4_ext_rm_idx(handle, inode, path, i);
 			}
 			/* root level has p_bh == NULL, brelse() eats this */
 			brelse(path[i].p_bh);
@@ -2887,6 +2901,7 @@ static int ext4_split_extent(handle_t *handle,
 	int err = 0;
 	int uninitialized;
 	int split_flag1, flags1;
+	int allocated = map->m_len;
 
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
@@ -2905,6 +2920,8 @@ static int ext4_split_extent(handle_t *handle,
 				map->m_lblk + map->m_len, split_flag1, flags1);
 		if (err)
 			goto out;
+	} else {
+		allocated = ee_len - (map->m_lblk - ee_block);
 	}
 
 	ext4_ext_drop_refs(path);
@@ -2927,7 +2944,7 @@ static int ext4_split_extent(handle_t *handle,
 
 	ext4_ext_show_leaf(inode, path);
 out:
-	return err ? err : map->m_len;
+	return err ? err : allocated;
 }
 
 #define EXT4_EXT_ZERO_LEN 7
@@ -3295,6 +3312,7 @@ out:
 					allocated - map->m_len);
 		allocated = map->m_len;
 	}
+	map->m_len = allocated;
 
 	/*
 	 * If we have done fallocate with the offset that is already
@@ -4137,7 +4155,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
 		error = ext4_get_inode_loc(inode, &iloc);
 		if (error)
 			return error;
-		physical = iloc.bh->b_blocknr << blockbits;
+		physical = (__u64)iloc.bh->b_blocknr << blockbits;
 		offset = EXT4_GOOD_OLD_INODE_SIZE +
 				EXT4_I(inode)->i_extra_isize;
 		physical += offset;
@@ -4145,7 +4163,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
 		flags |= FIEMAP_EXTENT_DATA_INLINE;
 		brelse(iloc.bh);
 	} else { /* external block */
-		physical = EXT4_I(inode)->i_file_acl << blockbits;
+		physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
 		length = inode->i_sb->s_blocksize;
 	}
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 21bb2f6..443ffb8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -22,6 +22,7 @@
 #include <linux/random.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/math64.h>
 #include <asm/byteorder.h>
 
 #include "ext4.h"
@@ -345,8 +346,8 @@ static int find_group_flex(struct super_block *sb, struct inode *parent,
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	int flex_size = ext4_flex_bg_size(sbi);
 	ext4_group_t best_flex = parent_fbg_group;
-	int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
-	int flexbg_free_blocks;
+	ext4_fsblk_t blocks_per_flex = sbi->s_blocks_per_group * flex_size;
+	ext4_fsblk_t flexbg_free_blocks;
 	int flex_freeb_ratio;
 	ext4_group_t n_fbg_groups;
 	ext4_group_t i;
@@ -355,8 +356,8 @@ static int find_group_flex(struct super_block *sb, struct inode *parent,
 		sbi->s_log_groups_per_flex;
 
 find_close_to_parent:
-	flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks);
-	flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+	flexbg_free_blocks = atomic64_read(&flex_group[best_flex].free_blocks);
+	flex_freeb_ratio = div64_u64(flexbg_free_blocks * 100, blocks_per_flex);
 	if (atomic_read(&flex_group[best_flex].free_inodes) &&
 	    flex_freeb_ratio > free_block_ratio)
 		goto found_flexbg;
@@ -370,8 +371,8 @@ find_close_to_parent:
 		if (i == parent_fbg_group || i == parent_fbg_group - 1)
 			continue;
 
-		flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks);
-		flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+		flexbg_free_blocks = atomic64_read(&flex_group[i].free_blocks);
+		flex_freeb_ratio = div64_u64(flexbg_free_blocks * 100, blocks_per_flex);
 
 		if (flex_freeb_ratio > free_block_ratio &&
 		    (atomic_read(&flex_group[i].free_inodes))) {
@@ -380,14 +381,14 @@ find_close_to_parent:
 		}
 
 		if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) ||
-		    ((atomic_read(&flex_group[i].free_blocks) >
-		      atomic_read(&flex_group[best_flex].free_blocks)) &&
+		    ((atomic64_read(&flex_group[i].free_blocks) >
+		      atomic64_read(&flex_group[best_flex].free_blocks)) &&
 		     atomic_read(&flex_group[i].free_inodes)))
 			best_flex = i;
 	}
 
 	if (!atomic_read(&flex_group[best_flex].free_inodes) ||
-	    !atomic_read(&flex_group[best_flex].free_blocks))
+	    !atomic64_read(&flex_group[best_flex].free_blocks))
 		return -1;
 
 found_flexbg:
@@ -406,8 +407,8 @@ out:
 }
 
 struct orlov_stats {
+	__u64 free_blocks;
 	__u32 free_inodes;
-	__u32 free_blocks;
 	__u32 used_dirs;
 };
 
@@ -424,7 +425,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 
 	if (flex_size > 1) {
 		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_blocks = atomic_read(&flex_group[g].free_blocks);
+		stats->free_blocks = atomic64_read(&flex_group[g].free_blocks);
 		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
 		return;
 	}
@@ -1021,8 +1022,12 @@ got:
 	if (IS_DIRSYNC(inode))
 		ext4_handle_sync(handle);
 	if (insert_inode_locked(inode) < 0) {
-		err = -EINVAL;
-		goto fail_drop;
+		/*
+		 * Likely a bitmap corruption causing inode to be allocated
+		 * twice.
+		 */
+		err = -EIO;
+		goto fail;
 	}
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
@@ -1189,7 +1194,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 		if (!bitmap_bh)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_INODES_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
 			(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
 		bitmap_count += x;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c1e6a72..5de8a27 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1134,6 +1134,15 @@ void ext4_da_update_reserve_space(struct inode *inode,
 		used = ei->i_reserved_data_blocks;
 	}
 
+	if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
+		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
+			 "with only %d reserved metadata blocks\n", __func__,
+			 inode->i_ino, ei->i_allocated_meta_blocks,
+			 ei->i_reserved_meta_blocks);
+		WARN_ON(1);
+		ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
+	}
+
 	/* Update per-inode reservations */
 	ei->i_reserved_data_blocks -= used;
 	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
@@ -2190,6 +2199,8 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
 
 	index = mpd->first_page;
 	end   = mpd->next_page - 1;
+
+	pagevec_init(&pvec, 0);
 	while (index <= end) {
 		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
 		if (nr_pages == 0)
@@ -5142,6 +5153,7 @@ static int ext4_do_update_inode(handle_t *handle,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	int err = 0, rc, block;
+	int need_datasync = 0;
 
 	/* For fields not not tracking in the in-memory inode,
 	 * initialise them to zero for new inodes. */
@@ -5190,7 +5202,10 @@ static int ext4_do_update_inode(handle_t *handle,
 		raw_inode->i_file_acl_high =
 			cpu_to_le16(ei->i_file_acl >> 32);
 	raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
-	ext4_isize_set(raw_inode, ei->i_disksize);
+	if (ei->i_disksize != ext4_isize(raw_inode)) {
+		ext4_isize_set(raw_inode, ei->i_disksize);
+		need_datasync = 1;
+	}
 	if (ei->i_disksize > 0x7fffffffULL) {
 		struct super_block *sb = inode->i_sb;
 		if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
@@ -5243,7 +5258,7 @@ static int ext4_do_update_inode(handle_t *handle,
 		err = rc;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
 
-	ext4_update_inode_fsync_trans(handle, inode, 0);
+	ext4_update_inode_fsync_trans(handle, inode, need_datasync);
 out_brelse:
 	brelse(bh);
 	ext4_std_error(inode->i_sb, err);
@@ -5466,7 +5481,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		 struct kstat *stat)
 {
 	struct inode *inode;
-	unsigned long delalloc_blocks;
+	unsigned long long delalloc_blocks;
 
 	inode = dentry->d_inode;
 	generic_fillattr(inode, stat);
@@ -5483,7 +5498,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	 */
 	delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
 
-	stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+	stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
 	return 0;
 }
 
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 808c554..4cbe1c2 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -35,7 +35,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		handle_t *handle = NULL;
 		int err, migrate = 0;
 		struct ext4_iloc iloc;
-		unsigned int oldflags;
+		unsigned int oldflags, mask, i;
 		unsigned int jflag;
 
 		if (!inode_owner_or_capable(inode))
@@ -112,9 +112,14 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (err)
 			goto flags_err;
 
-		flags = flags & EXT4_FL_USER_MODIFIABLE;
-		flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE;
-		ei->i_flags = flags;
+		for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
+			if (!(mask & EXT4_FL_USER_MODIFIABLE))
+				continue;
+			if (mask & flags)
+				ext4_set_inode_flag(inode, i);
+			else
+				ext4_clear_inode_flag(inode, i);
+		}
 
 		ext4_set_inode_flags(inode);
 		inode->i_ctime = ext4_current_time(inode);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0f1be7f..cdb8414 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2026,7 +2026,11 @@ repeat:
 		group = ac->ac_g_ex.fe_group;
 
 		for (i = 0; i < ngroups; group++, i++) {
-			if (group == ngroups)
+			/*
+			 * Artificially restricted ngroups for non-extent
+			 * files makes group > ngroups possible on first loop.
+			 */
+			if (group >= ngroups)
 				group = 0;
 
 			/* This now checks without needing the buddy page */
@@ -2528,6 +2532,9 @@ int ext4_mb_release(struct super_block *sb)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
 
+	if (sbi->s_proc)
+		remove_proc_entry("mb_groups", sbi->s_proc);
+
 	if (sbi->s_group_info) {
 		for (i = 0; i < ngroups; i++) {
 			grinfo = ext4_get_group_info(sb, i);
@@ -2575,8 +2582,6 @@ int ext4_mb_release(struct super_block *sb)
 	}
 
 	free_percpu(sbi->s_locality_groups);
-	if (sbi->s_proc)
-		remove_proc_entry("mb_groups", sbi->s_proc);
 
 	return 0;
 }
@@ -2813,8 +2818,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,
 							  ac->ac_b_ex.fe_group);
-		atomic_sub(ac->ac_b_ex.fe_len,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic64_sub(ac->ac_b_ex.fe_len,
+			     &sbi->s_flex_groups[flex_group].free_blocks);
 	}
 
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -4110,7 +4115,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 		/* The max size of hash table is PREALLOC_TB_SIZE */
 		order = PREALLOC_TB_SIZE - 1;
 	/* Add the prealloc space to lg */
-	rcu_read_lock();
+	spin_lock(&lg->lg_prealloc_lock);
 	list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order],
 						pa_inode_list) {
 		spin_lock(&tmp_pa->pa_lock);
@@ -4134,12 +4139,12 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 	if (!added)
 		list_add_tail_rcu(&pa->pa_inode_list,
 					&lg->lg_prealloc_list[order]);
-	rcu_read_unlock();
+	spin_unlock(&lg->lg_prealloc_lock);
 
 	/* Now trim the list to be not more than 8 elements */
 	if (lg_prealloc_count > 8) {
 		ext4_mb_discard_lg_preallocations(sb, lg,
-						order, lg_prealloc_count);
+						  order, lg_prealloc_count);
 		return;
 	}
 	return ;
@@ -4583,6 +4588,7 @@ do_more:
 		 */
 		new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
 		if (!new_entry) {
+			ext4_mb_unload_buddy(&e4b);
 			err = -ENOMEM;
 			goto error_return;
 		}
@@ -4612,7 +4618,7 @@ do_more:
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic64_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
@@ -4743,8 +4749,8 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(blocks_freed,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic64_add(blocks_freed,
+			     &sbi->s_flex_groups[flex_group].free_blocks);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index f57455a..72f9732 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -1209,7 +1209,12 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
-
+	/* TODO: This is non obvious task to swap blocks for inodes with full
+	   jornaling enabled */
+	if (ext4_should_journal_data(orig_inode) ||
+	    ext4_should_journal_data(donor_inode)) {
+		return -EINVAL;
+	}
 	/* Protect orig and donor inodes against a truncate */
 	ret1 = mext_inode_double_lock(orig_inode, donor_inode);
 	if (ret1 < 0)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 3d36d5a..595d087 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -585,11 +585,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
 				(block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
 					 + ((char *)de - bh->b_data))) {
-			/* On error, skip the f_pos to the next block. */
-			dir_file->f_pos = (dir_file->f_pos |
-					(dir->i_sb->s_blocksize - 1)) + 1;
-			brelse(bh);
-			return count;
+			/* silently ignore the rest of the block */
+			break;
 		}
 		ext4fs_dirhash(de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
@@ -1799,9 +1796,7 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
-#ifdef CONFIG_EXT4_FS_XATTR
 		inode->i_op = &ext4_special_inode_operations;
-#endif
 		err = ext4_add_nondir(handle, dentry, inode);
 	}
 	ext4_journal_stop(handle);
@@ -2064,7 +2059,8 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	int err = 0;
 
 	/* ext4_handle_valid() assumes a valid handle_t pointer */
-	if (handle && !ext4_handle_valid(handle))
+	if (handle && !ext4_handle_valid(handle) &&
+	    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS))
 		return 0;
 
 	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 80bbc9c..d2661aa 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -499,6 +499,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	return err;
 
 exit_inode:
+	kfree(n_group_desc);
 	/* ext4_handle_release_buffer(handle, iloc.bh); */
 	brelse(iloc.bh);
 exit_dindj:
@@ -928,8 +929,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	    sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
 		flex_group = ext4_flex_group(sbi, input->group);
-		atomic_add(input->free_blocks_count,
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic64_add(input->free_blocks_count,
+			     &sbi->s_flex_groups[flex_group].free_blocks);
 		atomic_add(EXT4_INODES_PER_GROUP(sb),
 			   &sbi->s_flex_groups[flex_group].free_inodes);
 	}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 63fe3ca..e05cd34 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -860,6 +860,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_reserved_meta_blocks = 0;
 	ei->i_allocated_meta_blocks = 0;
 	ei->i_da_metadata_calc_len = 0;
+	ei->i_da_metadata_calc_last_lblock = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
@@ -1991,8 +1992,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		flex_group = ext4_flex_group(sbi, i);
 		atomic_add(ext4_free_inodes_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].free_inodes);
-		atomic_add(ext4_free_blks_count(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic64_add(ext4_free_blks_count(sb, gdp),
+			     &sbi->s_flex_groups[flex_group].free_blocks);
 		atomic_add(ext4_used_dirs_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].used_dirs);
 	}
@@ -2203,7 +2204,9 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 				__func__, inode->i_ino, inode->i_size);
 			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
 				  inode->i_ino, inode->i_size);
+			mutex_lock(&inode->i_mutex);
 			ext4_truncate(inode);
+			mutex_unlock(&inode->i_mutex);
 			nr_truncates++;
 		} else {
 			ext4_msg(sb, KERN_DEBUG,
@@ -3619,7 +3622,8 @@ no_journal:
 		goto failed_mount4;
 	}
 
-	ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY);
+	if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
+		sb->s_flags |= MS_RDONLY;
 
 	/* determine the minimum size of new large inodes, if present */
 	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
@@ -3677,22 +3681,19 @@ no_journal:
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
 			 err);
-		goto failed_mount4;
+		goto failed_mount5;
 	}
 
 	err = ext4_register_li_request(sb, first_not_zeroed);
 	if (err)
-		goto failed_mount4;
+		goto failed_mount6;
 
 	sbi->s_kobj.kset = ext4_kset;
 	init_completion(&sbi->s_kobj_unregister);
 	err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
 				   "%s", sb->s_id);
-	if (err) {
-		ext4_mb_release(sb);
-		ext4_ext_release(sb);
-		goto failed_mount4;
-	};
+	if (err)
+		goto failed_mount7;
 
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
@@ -3726,13 +3727,19 @@ cantfind_ext4:
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
+failed_mount7:
+	ext4_unregister_li_request(sb);
+failed_mount6:
+	ext4_ext_release(sb);
+failed_mount5:
+	ext4_mb_release(sb);
+	ext4_release_system_zone(sb);
 failed_mount4:
 	iput(root);
 	sb->s_root = NULL;
 	ext4_msg(sb, KERN_ERR, "mount failed");
 	destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
 failed_mount_wq:
-	ext4_release_system_zone(sb);
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
@@ -4436,7 +4443,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	ext4_setup_system_zone(sb);
-	if (sbi->s_journal == NULL)
+	if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
 		ext4_commit_super(sb, 1);
 
 #ifdef CONFIG_QUOTA
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 19fe4e3..8f797ae 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -487,18 +487,19 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
+		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
+		if (ce)
+			mb_cache_entry_release(ce);
+		unlock_buffer(bh);
 		error = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 		dquot_free_block(inode, 1);
 		ea_bdebug(bh, "refcount now=%d; releasing",
 			  le32_to_cpu(BHDR(bh)->h_refcount));
-		if (ce)
-			mb_cache_entry_release(ce);
 	}
-	unlock_buffer(bh);
 out:
 	ext4_std_error(inode->i_sb, error);
 	return;
@@ -1270,6 +1271,8 @@ retry:
 				    s_min_extra_isize) {
 					tried_min_extra_isize++;
 					new_extra_isize = s_min_extra_isize;
+					kfree(is); is = NULL;
+					kfree(bs); bs = NULL;
 					goto retry;
 				}
 				error = -1;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 9836839..9fc6975 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1236,6 +1236,19 @@ static int fat_read_root(struct inode *inode)
 	return 0;
 }
 
+static unsigned long calc_fat_clusters(struct super_block *sb)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+
+	/* Divide first to avoid overflow */
+	if (sbi->fat_bits != 12) {
+		unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits;
+		return ent_per_sec * sbi->fat_length;
+	}
+
+	return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
+}
+
 /*
  * Read the super block of an MS-DOS FS.
  */
@@ -1442,7 +1455,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12;
 
 	/* check that FAT table does not overflow */
-	fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
+	fat_clusters = calc_fat_clusters(sb);
 	total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT);
 	if (total_clusters > MAX_FAT(sb)) {
 		if (!silent)
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 20b4ea5..6ee3c36 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -514,7 +514,8 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
 	int charlen;
 
 	if (utf8) {
-		*outlen = utf8s_to_utf16s(name, len, (wchar_t *)outname);
+		*outlen = utf8s_to_utf16s(name, len, UTF16_HOST_ENDIAN,
+				(wchar_t *) outname, FAT_LFN_LEN + 2);
 		if (*outlen < 0)
 			return *outlen;
 		else if (*outlen > FAT_LFN_LEN)
diff --git a/fs/fifo.c b/fs/fifo.c
index b1a524d..cf6f434 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -14,7 +14,7 @@
 #include <linux/sched.h>
 #include <linux/pipe_fs_i.h>
 
-static void wait_for_partner(struct inode* inode, unsigned int *cnt)
+static int wait_for_partner(struct inode* inode, unsigned int *cnt)
 {
 	int cur = *cnt;	
 
@@ -23,6 +23,7 @@ static void wait_for_partner(struct inode* inode, unsigned int *cnt)
 		if (signal_pending(current))
 			break;
 	}
+	return cur == *cnt ? -ERESTARTSYS : 0;
 }
 
 static void wake_up_partner(struct inode* inode)
@@ -67,8 +68,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 				 * seen a writer */
 				filp->f_version = pipe->w_counter;
 			} else {
-				wait_for_partner(inode, &pipe->w_counter);
-				if(signal_pending(current))
+				if (wait_for_partner(inode, &pipe->w_counter))
 					goto err_rd;
 			}
 		}
@@ -90,8 +90,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 			wake_up_partner(inode);
 
 		if (!pipe->readers) {
-			wait_for_partner(inode, &pipe->r_counter);
-			if (signal_pending(current))
+			if (wait_for_partner(inode, &pipe->r_counter))
 				goto err_wr;
 		}
 		break;
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190..73c0bd7 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -276,5 +276,5 @@ const struct file_operations fscache_stats_fops = {
 	.open		= fscache_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release        = single_release,
 };
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c858b5c..947b822 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1528,6 +1528,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 		req->pages[req->num_pages] = page;
 		req->num_pages++;
 
+		offset = 0;
 		num -= this_num;
 		total_len += this_num;
 		index++;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d5016071..607a973 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -858,6 +858,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
 		if (stat) {
 			generic_fillattr(inode, stat);
 			stat->mode = fi->orig_i_mode;
+			stat->ino = fi->orig_ino;
 		}
 	}
 
@@ -1438,6 +1439,8 @@ static int fuse_setxattr(struct dentry *entry, const char *name,
 		fc->no_setxattr = 1;
 		err = -EOPNOTSUPP;
 	}
+	if (!err)
+		fuse_invalidate_attr(inode);
 	return err;
 }
 
@@ -1567,6 +1570,8 @@ static int fuse_removexattr(struct dentry *entry, const char *name)
 		fc->no_removexattr = 1;
 		err = -EOPNOTSUPP;
 	}
+	if (!err)
+		fuse_invalidate_attr(inode);
 	return err;
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 82a6646..2e1c10fe 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1298,7 +1298,6 @@ static int fuse_writepage_locked(struct page *page)
 
 	inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
-	end_page_writeback(page);
 
 	spin_lock(&fc->lock);
 	list_add(&req->writepages_entry, &fi->writepages);
@@ -1306,6 +1305,8 @@ static int fuse_writepage_locked(struct page *page)
 	fuse_flush_writepages(inode);
 	spin_unlock(&fc->lock);
 
+	end_page_writeback(page);
+
 	return 0;
 
 err_free:
@@ -1710,7 +1711,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count)
 	size_t n;
 	u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT;
 
-	for (n = 0; n < count; n++) {
+	for (n = 0; n < count; n++, iov++) {
 		if (iov->iov_len > (size_t) max)
 			return -ENOMEM;
 		max -= iov->iov_len;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index b788bec..f621550 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -82,6 +82,9 @@ struct fuse_inode {
 	    preserve the original mode */
 	mode_t orig_i_mode;
 
+	/** 64 bit inode number */
+	u64 orig_ino;
+
 	/** Version of last attribute change */
 	u64 attr_version;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 38f84cd..69a1e0f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -91,6 +91,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	fi->nlookup = 0;
 	fi->attr_version = 0;
 	fi->writectr = 0;
+	fi->orig_ino = 0;
 	INIT_LIST_HEAD(&fi->write_files);
 	INIT_LIST_HEAD(&fi->queued_writes);
 	INIT_LIST_HEAD(&fi->writepages);
@@ -140,6 +141,18 @@ static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
 	return 0;
 }
 
+/*
+ * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
+ * so that it will fit.
+ */
+static ino_t fuse_squash_ino(u64 ino64)
+{
+	ino_t ino = (ino_t) ino64;
+	if (sizeof(ino_t) < sizeof(u64))
+		ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8;
+	return ino;
+}
+
 void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 				   u64 attr_valid)
 {
@@ -149,7 +162,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	fi->attr_version = ++fc->attr_version;
 	fi->i_time = attr_valid;
 
-	inode->i_ino     = attr->ino;
+	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
 	inode->i_nlink   = attr->nlink;
 	inode->i_uid     = attr->uid;
@@ -175,6 +188,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	fi->orig_i_mode = inode->i_mode;
 	if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
 		inode->i_mode &= ~S_ISVTX;
+
+	fi->orig_ino = attr->ino;
 }
 
 void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index fe9945f..5235d6e 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -167,6 +167,8 @@ static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
 	case GFS2_SMALL_FH_SIZE:
 	case GFS2_LARGE_FH_SIZE:
 	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_SMALL_FH_SIZE)
+			return NULL;
 		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
 		this.no_formal_ino |= be32_to_cpu(fh[1]);
 		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
@@ -186,6 +188,8 @@ static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
 	switch (fh_type) {
 	case GFS2_LARGE_FH_SIZE:
 	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_LARGE_FH_SIZE)
+			return NULL;
 		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
 		parent.no_formal_ino |= be32_to_cpu(fh[5]);
 		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 05bbb12..c133253 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -139,16 +139,14 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	struct gfs2_meta_header *mh;
 	struct gfs2_trans *tr;
 
-	lock_buffer(bd->bd_bh);
-	gfs2_log_lock(sdp);
 	if (!list_empty(&bd->bd_list_tr))
-		goto out;
+		return;
 	tr = current->journal_info;
 	tr->tr_touched = 1;
 	tr->tr_num_buf++;
 	list_add(&bd->bd_list_tr, &tr->tr_list_buf);
 	if (!list_empty(&le->le_list))
-		goto out;
+		return;
 	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
 	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
 	gfs2_meta_check(sdp, bd->bd_bh);
@@ -159,9 +157,6 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	sdp->sd_log_num_buf++;
 	list_add(&le->le_list, &sdp->sd_log_le_buf);
 	tr->tr_num_buf_new++;
-out:
-	gfs2_log_unlock(sdp);
-	unlock_buffer(bd->bd_bh);
 }
 
 static void buf_lo_before_commit(struct gfs2_sbd *sdp)
@@ -528,11 +523,9 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	struct address_space *mapping = bd->bd_bh->b_page->mapping;
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 
-	lock_buffer(bd->bd_bh);
-	gfs2_log_lock(sdp);
 	if (tr) {
 		if (!list_empty(&bd->bd_list_tr))
-			goto out;
+			return;
 		tr->tr_touched = 1;
 		if (gfs2_is_jdata(ip)) {
 			tr->tr_num_buf++;
@@ -540,7 +533,7 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 		}
 	}
 	if (!list_empty(&le->le_list))
-		goto out;
+		return;
 
 	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
 	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
@@ -552,9 +545,6 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	} else {
 		list_add_tail(&le->le_list, &sdp->sd_log_le_ordered);
 	}
-out:
-	gfs2_log_unlock(sdp);
-	unlock_buffer(bd->bd_bh);
 }
 
 static void gfs2_check_magic(struct buffer_head *bh)
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 9ec73a8..e6453c3 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -145,14 +145,22 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct gfs2_bufdata *bd;
 
+	lock_buffer(bh);
+	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd)
 		gfs2_assert(sdp, bd->bd_gl == gl);
 	else {
+		gfs2_log_unlock(sdp);
+		unlock_buffer(bh);
 		gfs2_attach_bufdata(gl, bh, meta);
 		bd = bh->b_private;
+		lock_buffer(bh);
+		gfs2_log_lock(sdp);
 	}
 	lops_add(sdp, &bd->bd_le);
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bh);
 }
 
 void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index b1991a2..9d8c087 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -499,7 +499,7 @@ void hfsplus_file_truncate(struct inode *inode)
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
-		u32 size = inode->i_size;
+		loff_t size = inode->i_size;
 		int res;
 
 		res = pagecache_write_begin(NULL, mapping, size, 0,
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 7b8112d..aac1563 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -56,7 +56,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct bio *bio;
 	int ret = 0;
-	unsigned int io_size;
+	u64 io_size;
 	loff_t start;
 	int offset;
 
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index a790821..ea3d1ca 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -17,7 +17,8 @@ unsigned int *hpfs_map_bitmap(struct super_block *s, unsigned bmp_block,
 			 struct quad_buffer_head *qbh, char *id)
 {
 	secno sec;
-	if (hpfs_sb(s)->sb_chk) if (bmp_block * 16384 > hpfs_sb(s)->sb_fs_size) {
+	unsigned n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14;
+	if (hpfs_sb(s)->sb_chk) if (bmp_block >= n_bands) {
 		hpfs_error(s, "hpfs_map_bitmap called with bad parameter: %08x at %s", bmp_block, id);
 		return NULL;
 	}
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 98580a3..f760c15 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -553,7 +553,13 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
 	sbi->sb_cp_table = NULL;
 	sbi->sb_c_bitmap = -1;
 	sbi->sb_max_fwd_alloc = 0xffffff;
-	
+
+	if (sbi->sb_fs_size >= 0x80000000) {
+		hpfs_error(s, "invalid size in superblock: %08x",
+			(unsigned)sbi->sb_fs_size);
+		goto bail4;
+	}
+
 	/* Load bitmap directory */
 	if (!(sbi->sb_bmp_dir = hpfs_load_bitmap_directory(s, le32_to_cpu(superblock->bitmaps))))
 		goto bail4;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8b0c875..6327a06 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -568,7 +568,8 @@ static int hugetlbfs_set_page_dirty(struct page *page)
 }
 
 static int hugetlbfs_migrate_page(struct address_space *mapping,
-				struct page *newpage, struct page *page)
+				struct page *newpage, struct page *page,
+				enum migrate_mode mode)
 {
 	int rc;
 
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index dd4687f..fd88add 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -135,6 +135,7 @@ isofs_export_encode_fh(struct dentry *dentry,
 	len = 3;
 	fh32[0] = ei->i_iget5_block;
  	fh16[2] = (__u16)ei->i_iget5_offset;  /* fh16 [sic] */
+	fh16[3] = 0;  /* avoid leaking uninitialized data */
 	fh32[2] = inode->i_generation;
 	if (connectable && !S_ISDIR(inode->i_mode)) {
 		struct inode *parent;
@@ -179,7 +180,7 @@ static struct dentry *isofs_fh_to_parent(struct super_block *sb,
 {
 	struct isofs_fid *ifid = (struct isofs_fid *)fid;
 
-	if (fh_type != 2)
+	if (fh_len < 2 || fh_type != 2)
 		return NULL;
 
 	return isofs_export_iget(sb,
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index b3cc858..26f6364 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -119,8 +119,8 @@ static void destroy_inodecache(void)
 
 static int isofs_remount(struct super_block *sb, int *flags, char *data)
 {
-	/* we probably want a lot more here */
-	*flags |= MS_RDONLY;
+	if (!(*flags & MS_RDONLY))
+		return -EROFS;
 	return 0;
 }
 
@@ -769,15 +769,6 @@ root_found:
 	 */
 	s->s_maxbytes = 0x80000000000LL;
 
-	/*
-	 * The CDROM is read-only, has no nodes (devices) on it, and since
-	 * all of the files appear to be owned by root, we really do not want
-	 * to allow suid.  (suid or devices will not show up unless we have
-	 * Rock Ridge extensions)
-	 */
-
-	s->s_flags |= MS_RDONLY /* | MS_NODEV | MS_NOSUID */;
-
 	/* Set this for reference. Its not currently used except on write
 	   which we don't have .. */
 
@@ -1528,6 +1519,9 @@ struct inode *isofs_iget(struct super_block *sb,
 static struct dentry *isofs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
+	/* We don't support read-write mounts */
+	if (!(flags & MS_RDONLY))
+		return ERR_PTR(-EACCES);
 	return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super);
 }
 
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 72ffa97..dcd23f8 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -85,7 +85,12 @@ nope:
 static void release_data_buffer(struct buffer_head *bh)
 {
 	if (buffer_freed(bh)) {
+		WARN_ON_ONCE(buffer_dirty(bh));
 		clear_buffer_freed(bh);
+		clear_buffer_mapped(bh);
+		clear_buffer_new(bh);
+		clear_buffer_req(bh);
+		bh->b_bdev = NULL;
 		release_buffer_page(bh);
 	} else
 		put_bh(bh);
@@ -840,17 +845,35 @@ restart_loop:
 		 * there's no point in keeping a checkpoint record for
 		 * it. */
 
-		/* A buffer which has been freed while still being
-		 * journaled by a previous transaction may end up still
-		 * being dirty here, but we want to avoid writing back
-		 * that buffer in the future after the "add to orphan"
-		 * operation been committed,  That's not only a performance
-		 * gain, it also stops aliasing problems if the buffer is
-		 * left behind for writeback and gets reallocated for another
-		 * use in a different page. */
-		if (buffer_freed(bh) && !jh->b_next_transaction) {
-			clear_buffer_freed(bh);
-			clear_buffer_jbddirty(bh);
+		/*
+		 * A buffer which has been freed while still being journaled by
+		 * a previous transaction.
+		 */
+		if (buffer_freed(bh)) {
+			/*
+			 * If the running transaction is the one containing
+			 * "add to orphan" operation (b_next_transaction !=
+			 * NULL), we have to wait for that transaction to
+			 * commit before we can really get rid of the buffer.
+			 * So just clear b_modified to not confuse transaction
+			 * credit accounting and refile the buffer to
+			 * BJ_Forget of the running transaction. If the just
+			 * committed transaction contains "add to orphan"
+			 * operation, we can completely invalidate the buffer
+			 * now. We are rather throughout in that since the
+			 * buffer may be still accessible when blocksize <
+			 * pagesize and it is attached to the last partial
+			 * page.
+			 */
+			jh->b_modified = 0;
+			if (!jh->b_next_transaction) {
+				clear_buffer_freed(bh);
+				clear_buffer_jbddirty(bh);
+				clear_buffer_mapped(bh);
+				clear_buffer_new(bh);
+				clear_buffer_req(bh);
+				bh->b_bdev = NULL;
+			}
 		}
 
 		if (buffer_jbddirty(bh)) {
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index f7ee81a..d7ab092 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1837,15 +1837,16 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
  * We're outside-transaction here.  Either or both of j_running_transaction
  * and j_committing_transaction may be NULL.
  */
-static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
+static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
+				int partial_page)
 {
 	transaction_t *transaction;
 	struct journal_head *jh;
 	int may_free = 1;
-	int ret;
 
 	BUFFER_TRACE(bh, "entry");
 
+retry:
 	/*
 	 * It is safe to proceed here without the j_list_lock because the
 	 * buffers cannot be stolen by try_to_free_buffers as long as we are
@@ -1873,10 +1874,18 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 	 * clear the buffer dirty bit at latest at the moment when the
 	 * transaction marking the buffer as freed in the filesystem
 	 * structures is committed because from that moment on the
-	 * buffer can be reallocated and used by a different page.
+	 * block can be reallocated and used by a different page.
 	 * Since the block hasn't been freed yet but the inode has
 	 * already been added to orphan list, it is safe for us to add
 	 * the buffer to BJ_Forget list of the newest transaction.
+	 *
+	 * Also we have to clear buffer_mapped flag of a truncated buffer
+	 * because the buffer_head may be attached to the page straddling
+	 * i_size (can happen only when blocksize < pagesize) and thus the
+	 * buffer_head can be reused when the file is extended again. So we end
+	 * up keeping around invalidated buffers attached to transactions'
+	 * BJ_Forget list just to stop checkpointing code from cleaning up
+	 * the transaction this buffer was modified in.
 	 */
 	transaction = jh->b_transaction;
 	if (transaction == NULL) {
@@ -1903,13 +1912,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 			 * committed, the buffer won't be needed any
 			 * longer. */
 			JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
-			ret = __dispose_buffer(jh,
+			may_free = __dispose_buffer(jh,
 					journal->j_running_transaction);
-			journal_put_journal_head(jh);
-			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
-			spin_unlock(&journal->j_state_lock);
-			return ret;
+			goto zap_buffer;
 		} else {
 			/* There is no currently-running transaction. So the
 			 * orphan record which we wrote for this file must have
@@ -1917,13 +1922,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 			 * the committing transaction, if it exists. */
 			if (journal->j_committing_transaction) {
 				JBUFFER_TRACE(jh, "give to committing trans");
-				ret = __dispose_buffer(jh,
+				may_free = __dispose_buffer(jh,
 					journal->j_committing_transaction);
-				journal_put_journal_head(jh);
-				spin_unlock(&journal->j_list_lock);
-				jbd_unlock_bh_state(bh);
-				spin_unlock(&journal->j_state_lock);
-				return ret;
+				goto zap_buffer;
 			} else {
 				/* The orphan record's transaction has
 				 * committed.  We can cleanse this buffer */
@@ -1944,10 +1945,26 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 		}
 		/*
 		 * The buffer is committing, we simply cannot touch
-		 * it. So we just set j_next_transaction to the
-		 * running transaction (if there is one) and mark
-		 * buffer as freed so that commit code knows it should
-		 * clear dirty bits when it is done with the buffer.
+		 * it. If the page is straddling i_size we have to wait
+		 * for commit and try again.
+		 */
+		if (partial_page) {
+			tid_t tid = journal->j_committing_transaction->t_tid;
+
+			journal_put_journal_head(jh);
+			spin_unlock(&journal->j_list_lock);
+			jbd_unlock_bh_state(bh);
+			spin_unlock(&journal->j_state_lock);
+			unlock_buffer(bh);
+			log_wait_commit(journal, tid);
+			lock_buffer(bh);
+			goto retry;
+		}
+		/*
+		 * OK, buffer won't be reachable after truncate. We just set
+		 * j_next_transaction to the running transaction (if there is
+		 * one) and mark buffer as freed so that commit code knows it
+		 * should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
@@ -1970,6 +1987,14 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 	}
 
 zap_buffer:
+	/*
+	 * This is tricky. Although the buffer is truncated, it may be reused
+	 * if blocksize < pagesize and it is attached to the page straddling
+	 * EOF. Since the buffer might have been added to BJ_Forget list of the
+	 * running transaction, journal_get_write_access() won't clear
+	 * b_modified and credit accounting gets confused. So clear b_modified
+	 * here. */
+	jh->b_modified = 0;
 	journal_put_journal_head(jh);
 zap_buffer_no_jh:
 	spin_unlock(&journal->j_list_lock);
@@ -2018,7 +2043,8 @@ void journal_invalidatepage(journal_t *journal,
 		if (offset <= curr_off) {
 			/* This block is wholly outside the truncation point */
 			lock_buffer(bh);
-			may_free &= journal_unmap_buffer(journal, bh);
+			may_free &= journal_unmap_buffer(journal, bh,
+							 offset > 0);
 			unlock_buffer(bh);
 		}
 		curr_off = next_off;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 9baa39e..26e11db 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -178,7 +178,8 @@ repeat:
 		if (!new_transaction)
 			goto alloc_transaction;
 		write_lock(&journal->j_state_lock);
-		if (!journal->j_running_transaction) {
+		if (!journal->j_running_transaction &&
+		    !journal->j_barrier_count) {
 			jbd2_get_transaction(journal, new_transaction);
 			new_transaction = NULL;
 		}
@@ -468,10 +469,10 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
 		   &transaction->t_outstanding_credits);
 	if (atomic_dec_and_test(&transaction->t_updates))
 		wake_up(&journal->j_wait_updates);
+	tid = transaction->t_tid;
 	spin_unlock(&transaction->t_handle_lock);
 
 	jbd_debug(2, "restarting handle %p\n", handle);
-	tid = transaction->t_tid;
 	need_to_start = !tid_geq(journal->j_commit_request, tid);
 	read_unlock(&journal->j_state_lock);
 	if (need_to_start)
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 31dce61..4bbd521 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -225,8 +225,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 			return 0;
 
 		D1(printk(KERN_DEBUG "No progress from erasing blocks; doing GC anyway\n"));
-		spin_lock(&c->erase_completion_lock);
 		mutex_lock(&c->alloc_sem);
+		spin_lock(&c->erase_completion_lock);
 	}
 
 	/* First, work out which block we're garbage-collecting */
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 694aa5b..e304795 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -355,14 +355,16 @@ static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 			spin_unlock(&c->erase_completion_lock);
 
 			ret = jffs2_prealloc_raw_node_refs(c, jeb, 1);
-			if (ret)
-				return ret;
+
 			/* Just lock it again and continue. Nothing much can change because
 			   we hold c->alloc_sem anyway. In fact, it's not entirely clear why
 			   we hold c->erase_completion_lock in the majority of this function...
 			   but that's a question for another (more caffeine-rich) day. */
 			spin_lock(&c->erase_completion_lock);
 
+			if (ret)
+				return ret;
+
 			waste = jeb->free_size;
 			jffs2_link_node_ref(c, jeb,
 					    (jeb->offset + c->sector_size - waste) | REF_OBSOLETE,
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 1096559..09100b4 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -125,7 +125,7 @@ int jfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	int wait = wbc->sync_mode == WB_SYNC_ALL;
 
-	if (test_cflag(COMMIT_Nolink, inode))
+	if (inode->i_nlink == 0)
 		return 0;
 	/*
 	 * If COMMIT_DIRTY is not set, the inode isn't really dirty.
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 9197a1b..b6f17c0 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -3047,6 +3047,14 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 
 		dir_index = (u32) filp->f_pos;
 
+		/*
+		 * NFSv4 reserves cookies 1 and 2 for . and .. so we add
+		 * the value we return to the vfs is one greater than the
+		 * one we use internally.
+		 */
+		if (dir_index)
+			dir_index--;
+
 		if (dir_index > 1) {
 			struct dir_table_slot dirtab_slot;
 
@@ -3086,7 +3094,7 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 			if (p->header.flag & BT_INTERNAL) {
 				jfs_err("jfs_readdir: bad index table");
 				DT_PUTPAGE(mp);
-				filp->f_pos = -1;
+				filp->f_pos = DIREND;
 				return 0;
 			}
 		} else {
@@ -3094,7 +3102,7 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 				/*
 				 * self "."
 				 */
-				filp->f_pos = 0;
+				filp->f_pos = 1;
 				if (filldir(dirent, ".", 1, 0, ip->i_ino,
 					    DT_DIR))
 					return 0;
@@ -3102,7 +3110,7 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 			/*
 			 * parent ".."
 			 */
-			filp->f_pos = 1;
+			filp->f_pos = 2;
 			if (filldir(dirent, "..", 2, 1, PARENT(ip), DT_DIR))
 				return 0;
 
@@ -3123,24 +3131,25 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		/*
 		 * Legacy filesystem - OS/2 & Linux JFS < 0.3.6
 		 *
-		 * pn = index = 0:	First entry "."
-		 * pn = 0; index = 1:	Second entry ".."
+		 * pn = 0; index = 1:	First entry "."
+		 * pn = 0; index = 2:	Second entry ".."
 		 * pn > 0:		Real entries, pn=1 -> leftmost page
 		 * pn = index = -1:	No more entries
 		 */
 		dtpos = filp->f_pos;
-		if (dtpos == 0) {
+		if (dtpos < 2) {
 			/* build "." entry */
 
+			filp->f_pos = 1;
 			if (filldir(dirent, ".", 1, filp->f_pos, ip->i_ino,
 				    DT_DIR))
 				return 0;
-			dtoffset->index = 1;
+			dtoffset->index = 2;
 			filp->f_pos = dtpos;
 		}
 
 		if (dtoffset->pn == 0) {
-			if (dtoffset->index == 1) {
+			if (dtoffset->index == 2) {
 				/* build ".." entry */
 
 				if (filldir(dirent, "..", 2, filp->f_pos,
@@ -3233,6 +3242,12 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 					}
 					jfs_dirent->position = unique_pos++;
 				}
+				/*
+				 * We add 1 to the index because we may
+				 * use a value of 2 internally, and NFSv4
+				 * doesn't like that.
+				 */
+				jfs_dirent->position++;
 			} else {
 				jfs_dirent->position = dtpos;
 				len = min(d_namleft, DTLHDRDATALEN_LEGACY);
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 583636f..ee55e45 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1057,7 +1057,8 @@ static int lmLogSync(struct jfs_log * log, int hard_sync)
  */
 void jfs_syncpt(struct jfs_log *log, int hard_sync)
 {	LOG_LOCK(log);
-	lmLogSync(log, hard_sync);
+	if (!test_bit(log_QUIESCE, &log->flag))
+		lmLogSync(log, hard_sync);
 	LOG_UNLOCK(log);
 }
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 8d4ea83..de88922 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -141,6 +141,9 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
 			timeout);
 	if (ret < 0)
 		return -ERESTARTSYS;
+	/* Reset the lock status after a server reboot so we resend */
+	if (block->b_status == nlm_lck_denied_grace_period)
+		block->b_status = nlm_lck_blocked;
 	req->a_res.status = block->b_status;
 	return 0;
 }
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 36057ce..6e2a2d5 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -223,7 +223,7 @@ static void encode_nlm_stat(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	BUG_ON(be32_to_cpu(stat) > NLM_LCK_DENIED_GRACE_PERIOD);
+	WARN_ON_ONCE(be32_to_cpu(stat) > NLM_LCK_DENIED_GRACE_PERIOD);
 	p = xdr_reserve_space(xdr, 4);
 	*p = stat;
 }
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 6e31695..db7be3a 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -913,6 +913,7 @@ nlmsvc_retry_blocked(void)
 	unsigned long	timeout = MAX_SCHEDULE_TIMEOUT;
 	struct nlm_block *block;
 
+	spin_lock(&nlm_blocked_lock);
 	while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
 		block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
 
@@ -922,6 +923,7 @@ nlmsvc_retry_blocked(void)
 			timeout = block->b_when - jiffies;
 			break;
 		}
+		spin_unlock(&nlm_blocked_lock);
 
 		dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
 			block, block->b_when);
@@ -931,7 +933,9 @@ nlmsvc_retry_blocked(void)
 			retry_deferred_block(block);
 		} else
 			nlmsvc_grant_blocked(block);
+		spin_lock(&nlm_blocked_lock);
 	}
+	spin_unlock(&nlm_blocked_lock);
 
 	return timeout;
 }
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index d27aab1..d413af3 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -67,7 +67,8 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 	/* Obtain file pointer. Not used by FREE_ALL call. */
 	if (filp != NULL) {
-		if ((error = nlm_lookup_file(rqstp, &file, &lock->fh)) != 0)
+		error = cast_status(nlm_lookup_file(rqstp, &file, &lock->fh));
+		if (error != 0)
 			goto no_locks;
 		*filp = file;
 
diff --git a/fs/locks.c b/fs/locks.c
index b286539..35388d5 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -315,7 +315,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock,
 	return 0;
 }
 
-static int assign_type(struct file_lock *fl, int type)
+static int assign_type(struct file_lock *fl, long type)
 {
 	switch (type) {
 	case F_RDLCK:
@@ -452,7 +452,7 @@ static const struct lock_manager_operations lease_manager_ops = {
 /*
  * Initialize a lease, use the default lock manager operations
  */
-static int lease_init(struct file *filp, int type, struct file_lock *fl)
+static int lease_init(struct file *filp, long type, struct file_lock *fl)
  {
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
@@ -470,7 +470,7 @@ static int lease_init(struct file *filp, int type, struct file_lock *fl)
 }
 
 /* Allocate a file_lock initialised to this type of lease */
-static struct file_lock *lease_alloc(struct file *filp, int type)
+static struct file_lock *lease_alloc(struct file *filp, long type)
 {
 	struct file_lock *fl = locks_alloc_lock();
 	int error = -ENOMEM;
diff --git a/fs/namespace.c b/fs/namespace.c
index edc1c4a..b3d8f51 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1244,8 +1244,9 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
+		if (p->mnt_ns)
+			__mnt_make_shortterm(p);
 		p->mnt_ns = NULL;
-		__mnt_make_shortterm(p);
 		list_del_init(&p->mnt_child);
 		if (p->mnt_parent != p) {
 			p->mnt_parent->mnt_ghosts++;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index b3dc2b8..0cb731f 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -673,8 +673,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
  */
 static void nfs_destroy_server(struct nfs_server *server)
 {
-	if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) ||
-			!(server->flags & NFS_MOUNT_LOCAL_FCNTL))
+	if (server->nlm_host)
 		nlmclnt_done(server->nlm_host);
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 462a006..4033264 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1100,7 +1100,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct nfs_fattr *fattr = NULL;
 	int error;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (nd && (nd->flags & LOOKUP_RCU))
 		return -ECHILD;
 
 	parent = dget_parent(dentry);
@@ -1216,11 +1216,14 @@ static int nfs_dentry_delete(const struct dentry *dentry)
 
 }
 
+/* Ensure that we revalidate inode->i_nlink */
 static void nfs_drop_nlink(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	if (inode->i_nlink > 0)
-		drop_nlink(inode);
+	/* drop the inode if we're reasonably sure this is the last link */
+	if (inode->i_nlink == 1)
+		clear_nlink(inode);
+	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
 	spin_unlock(&inode->i_lock);
 }
 
@@ -1235,8 +1238,8 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
 
 	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
-		drop_nlink(inode);
 		nfs_complete_unlink(dentry, inode);
+		nfs_drop_nlink(inode);
 	}
 	iput(inode);
 }
@@ -1498,7 +1501,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct nfs_open_context *ctx;
 	int openflags, ret = 0;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (nd && (nd->flags & LOOKUP_RCU))
 		return -ECHILD;
 
 	inode = dentry->d_inode;
@@ -1788,10 +1791,8 @@ static int nfs_safe_remove(struct dentry *dentry)
 	if (inode != NULL) {
 		nfs_inode_return_delegation(inode);
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
-		/* The VFS may want to delete this inode */
 		if (error == 0)
 			nfs_drop_nlink(inode);
-		nfs_mark_for_revalidate(inode);
 	} else
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
 	if (error == -ENOENT)
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index a6e711a..ee02db5 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -213,7 +213,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 {
 	char buf1[NFS_DNS_HOSTNAME_MAXLEN+1];
 	struct nfs_dns_ent key, *item;
-	unsigned long ttl;
+	unsigned int ttl;
 	ssize_t len;
 	int ret = -EINVAL;
 
@@ -236,7 +236,8 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 	key.namelen = len;
 	memset(&key.h, 0, sizeof(key.h));
 
-	ttl = get_expiry(&buf);
+	if (get_uint(&buf, &ttl) < 0)
+		goto out;
 	if (ttl == 0)
 		goto out;
 	key.h.expiry_time = ttl + seconds_since_boot();
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index dd2f130..6c6e2c4 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -493,8 +493,11 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
-	/* Only do I/O if gfp is a superset of GFP_KERNEL */
-	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) {
+	/* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not
+	 * doing this memory reclaim for a fs-related allocation.
+	 */
+	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL &&
+	    !(current->flags & PF_FSTRANS)) {
 		int how = FLUSH_SYNC;
 
 		/* Don't let kswapd deadlock waiting for OOM RPC calls */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c48f9f6..873c6f2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -150,7 +150,7 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 	nfsi->attrtimeo_timestamp = jiffies;
 
-	memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
+	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
 	else
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2a55347..399a505 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -274,8 +274,9 @@ extern void nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
 
 /* namespace.c */
+#define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
-		      char *buffer, ssize_t buflen);
+		      char *buffer, ssize_t buflen, unsigned flags);
 extern struct vfsmount *nfs_d_automount(struct path *path);
 
 /* getroot.c */
@@ -315,7 +316,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
-		struct page *, struct page *);
+		struct page *, struct page *, enum migrate_mode);
 #else
 #define nfs_migrate_page NULL
 #endif
@@ -349,7 +350,7 @@ static inline char *nfs_devname(struct dentry *dentry,
 				char *buffer, ssize_t buflen)
 {
 	char *dummy;
-	return nfs_path(&dummy, dentry, buffer, buflen);
+	return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL);
 }
 
 /*
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d4c2d6b..3d93216 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -181,7 +181,7 @@ int nfs_mount(struct nfs_mount_request *info)
 	else
 		msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT];
 
-	status = rpc_call_sync(mnt_clnt, &msg, 0);
+	status = rpc_call_sync(mnt_clnt, &msg, RPC_TASK_SOFT|RPC_TASK_TIMEOUT);
 	rpc_shutdown_client(mnt_clnt);
 
 	if (status < 0)
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 1f063ba..d6122ef 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -37,6 +37,7 @@ static struct vfsmount *nfs_do_submount(struct dentry *dentry,
  * @dentry - pointer to dentry
  * @buffer - result buffer
  * @buflen - length of buffer
+ * @flags - options (see below)
  *
  * Helper function for constructing the server pathname
  * by arbitrary hashed dentry.
@@ -44,8 +45,14 @@ static struct vfsmount *nfs_do_submount(struct dentry *dentry,
  * This is mainly for use in figuring out the path on the
  * server side when automounting on top of an existing partition
  * and in generating /proc/mounts and friends.
+ *
+ * Supported flags:
+ * NFS_PATH_CANONICAL: ensure there is exactly one slash after
+ *		       the original device (export) name
+ *		       (if unset, the original name is returned verbatim)
  */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen)
+char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
+	       unsigned flags)
 {
 	char *end;
 	int namelen;
@@ -78,7 +85,7 @@ rename_retry:
 		rcu_read_unlock();
 		goto rename_retry;
 	}
-	if (*end != '/') {
+	if ((flags & NFS_PATH_CANONICAL) && *end != '/') {
 		if (--buflen < 0) {
 			spin_unlock(&dentry->d_lock);
 			rcu_read_unlock();
@@ -95,9 +102,11 @@ rename_retry:
 		return end;
 	}
 	namelen = strlen(base);
-	/* Strip off excess slashes in base string */
-	while (namelen > 0 && base[namelen - 1] == '/')
-		namelen--;
+	if (flags & NFS_PATH_CANONICAL) {
+		/* Strip off excess slashes in base string */
+		while (namelen > 0 && base[namelen - 1] == '/')
+			namelen--;
+	}
 	buflen -= namelen;
 	if (buflen < 0) {
 		spin_unlock(&dentry->d_lock);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 771741f..f0a6990 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -68,7 +68,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle,
 	nfs_fattr_init(info->fattr);
 	status = rpc_call_sync(client, &msg, 0);
 	dprintk("%s: reply fsinfo: %d\n", __func__, status);
-	if (!(info->fattr->valid & NFS_ATTR_FATTR)) {
+	if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) {
 		msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR];
 		msg.rpc_resp = info->fattr;
 		status = rpc_call_sync(client, &msg, 0);
@@ -633,7 +633,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 		  u64 cookie, struct page **pages, unsigned int count, int plus)
 {
 	struct inode		*dir = dentry->d_inode;
-	__be32			*verf = NFS_COOKIEVERF(dir);
+	__be32			*verf = NFS_I(dir)->cookieverf;
 	struct nfs3_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
 		.cookie		= cookie,
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index bb80c49..96f2b67 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -57,7 +57,8 @@ Elong:
 static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen)
 {
 	char *limit;
-	char *path = nfs_path(&limit, dentry, buffer, buflen);
+	char *path = nfs_path(&limit, dentry, buffer, buflen,
+			      NFS_PATH_CANONICAL);
 	if (!IS_ERR(path)) {
 		char *colon = strchr(path, ':');
 		if (colon && colon < limit)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3d67302..7204bcc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -94,6 +94,8 @@ static int nfs4_map_errors(int err)
 	case -NFS4ERR_BADOWNER:
 	case -NFS4ERR_BADNAME:
 		return -EINVAL;
+	case -NFS4ERR_SHARE_DENIED:
+		return -EACCES;
 	default:
 		dprintk("%s could not handle NFSv4 error %d\n",
 				__func__, -err);
@@ -298,8 +300,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
 			nfs4_schedule_session_recovery(clp->cl_session);
-			exception->retry = 1;
-			break;
+			goto wait_on_recovery;
 #endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
 			if (exception->timeout > HZ) {
@@ -1334,6 +1335,12 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 			case -ENOMEM:
 				err = 0;
 				goto out;
+			case -NFS4ERR_DELAY:
+			case -NFS4ERR_GRACE:
+				set_bit(NFS_DELEGATED_STATE, &state->flags);
+				ssleep(1);
+				err = -EAGAIN;
+				goto out;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
@@ -1771,6 +1778,7 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
 			nfs_setattr_update_inode(state->inode, sattr);
 		nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
 	}
+	nfs_revalidate_inode(server, state->inode);
 	nfs4_opendata_put(opendata);
 	nfs4_put_state_owner(sp);
 	*res = state;
@@ -3015,11 +3023,11 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name,
 			(unsigned long long)cookie);
-	nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
+	nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args);
 	res.pgbase = args.pgbase;
 	status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0);
 	if (status >= 0) {
-		memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
+		memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE);
 		status += args.pgbase;
 	}
 
@@ -3438,19 +3446,6 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
  */
 #define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
 
-static void buf_to_pages(const void *buf, size_t buflen,
-		struct page **pages, unsigned int *pgbase)
-{
-	const void *p = buf;
-
-	*pgbase = offset_in_page(buf);
-	p -= *pgbase;
-	while (p < buf + buflen) {
-		*(pages++) = virt_to_page(p);
-		p += PAGE_CACHE_SIZE;
-	}
-}
-
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
 {
@@ -3547,9 +3542,19 @@ out:
 	nfs4_set_cached_acl(inode, acl);
 }
 
+/*
+ * The getxattr API returns the required buffer length when called with a
+ * NULL buf. The NFSv4 acl tool then calls getxattr again after allocating
+ * the required buf.  On a NULL buf, we send a page of data to the server
+ * guessing that the ACL request can be serviced by a page. If so, we cache
+ * up to the page of ACL data, and the 2nd call to getxattr is serviced by
+ * the cache. If not so, we throw away the page, and cache the required
+ * length. The next getxattr call will then produce another round trip to
+ * the server, this time with the input buf of the required size.
+ */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES];
+	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -3564,41 +3569,61 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	struct page *localpage = NULL;
-	int ret;
-
-	if (buflen < PAGE_SIZE) {
-		/* As long as we're doing a round trip to the server anyway,
-		 * let's be prepared for a page of acl data. */
-		localpage = alloc_page(GFP_KERNEL);
-		resp_buf = page_address(localpage);
-		if (localpage == NULL)
-			return -ENOMEM;
-		args.acl_pages[0] = localpage;
-		args.acl_pgbase = 0;
-		args.acl_len = PAGE_SIZE;
-	} else {
-		resp_buf = buf;
-		buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase);
+	int ret = -ENOMEM, npages, i;
+	size_t acl_len = 0;
+
+	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	/* As long as we're doing a round trip to the server anyway,
+	 * let's be prepared for a page of acl data. */
+	if (npages == 0)
+		npages = 1;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto out_free;
 	}
-	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0);
+	if (npages > 1) {
+		/* for decoding across pages */
+		res.acl_scratch = alloc_page(GFP_KERNEL);
+		if (!res.acl_scratch)
+			goto out_free;
+	}
+	args.acl_len = npages * PAGE_SIZE;
+	args.acl_pgbase = 0;
+	/* Let decode_getfacl know not to fail if the ACL data is larger than
+	 * the page we send as a guess */
+	if (buf == NULL)
+		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
+	resp_buf = page_address(pages[0]);
+
+	dprintk("%s  buf %p buflen %ld npages %d args.acl_len %ld\n",
+		__func__, buf, buflen, npages, args.acl_len);
+	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
+			     &msg, &args.seq_args, &res.seq_res, 0);
 	if (ret)
 		goto out_free;
-	if (res.acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, res.acl_len);
+
+	acl_len = res.acl_len - res.acl_data_offset;
+	if (acl_len > args.acl_len)
+		nfs4_write_cached_acl(inode, NULL, acl_len);
 	else
-		nfs4_write_cached_acl(inode, resp_buf, res.acl_len);
+		nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset,
+				      acl_len);
 	if (buf) {
 		ret = -ERANGE;
-		if (res.acl_len > buflen)
+		if (acl_len > buflen)
 			goto out_free;
-		if (localpage)
-			memcpy(buf, resp_buf, res.acl_len);
+		_copy_from_pages(buf, pages, res.acl_data_offset,
+				res.acl_len);
 	}
-	ret = res.acl_len;
+	ret = acl_len;
 out_free:
-	if (localpage)
-		__free_page(localpage);
+	for (i = 0; i < npages; i++)
+		if (pages[i])
+			__free_page(pages[i]);
+	if (res.acl_scratch)
+		__free_page(res.acl_scratch);
 	return ret;
 }
 
@@ -3629,6 +3654,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
+		/* -ENOENT is returned if there is no ACL or if there is an ACL
+		 * but no cached acl data, just the acl length */
 		return ret;
 	return nfs4_get_acl_uncached(inode, buf, buflen);
 }
@@ -4113,6 +4140,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 				nfs_restart_rpc(task,
 						 calldata->server->nfs_client);
 	}
+	nfs_release_seqid(calldata->arg.seqid);
 }
 
 static void nfs4_locku_prepare(struct rpc_task *task, void *data)
@@ -5763,12 +5791,8 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		return;
 	}
 	spin_lock(&lo->plh_inode->i_lock);
-	if (task->tk_status == 0) {
-		if (lrp->res.lrs_present) {
-			pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
-		} else
-			BUG_ON(!list_empty(&lo->plh_segs));
-	}
+	if (task->tk_status == 0 && lrp->res.lrs_present)
+		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
 	dprintk("<-- %s\n", __func__);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index fc97fd5..4204e96 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2374,11 +2374,12 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + nfs4_fattr_bitmap_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz + 1;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
 		args->acl_pages, args->acl_pgbase, args->acl_len);
+
 	encode_nops(&hdr);
 }
 
@@ -4714,17 +4715,18 @@ decode_restorefh(struct xdr_stream *xdr)
 }
 
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
-		size_t *acl_len)
+			 struct nfs_getaclres *res)
 {
-	__be32 *savep;
+	__be32 *savep, *bm_p;
 	uint32_t attrlen,
 		 bitmap[2] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
-	*acl_len = 0;
+	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
 		goto out;
+	bm_p = xdr->p;
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
@@ -4736,18 +4738,30 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		size_t hdrlen;
 		u32 recvd;
 
+		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
+		 * are stored with the acl data to handle the problem of
+		 * variable length bitmaps.*/
+		xdr->p = bm_p;
+		res->acl_data_offset = be32_to_cpup(bm_p) + 2;
+		res->acl_data_offset <<= 2;
+
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
 		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
+		attrlen += res->acl_data_offset;
 		recvd = req->rq_rcv_buf.len - hdrlen;
 		if (attrlen > recvd) {
-			dprintk("NFS: server cheating in getattr"
-					" acl reply: attrlen %u > recvd %u\n",
+			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
+				/* getxattr interface called with a NULL buf */
+				res->acl_len = attrlen;
+				goto out;
+			}
+			dprintk("NFS: acl reply: attrlen %u > recvd %u\n",
 					attrlen, recvd);
 			return -EINVAL;
 		}
 		xdr_read_pages(xdr, attrlen);
-		*acl_len = attrlen;
+		res->acl_len = attrlen;
 	} else
 		status = -EOPNOTSUPP;
 
@@ -5673,6 +5687,10 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	struct compound_hdr hdr;
 	int status;
 
+	if (res->acl_scratch != NULL) {
+		void *p = page_address(res->acl_scratch);
+		xdr_set_scratch_buffer(xdr, p, PAGE_SIZE);
+	}
 	status = decode_compound_hdr(xdr, &hdr);
 	if (status)
 		goto out;
@@ -5682,7 +5700,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(xdr, rqstp, &res->acl_len);
+	status = decode_getacl(xdr, rqstp, res);
 
 out:
 	return status;
@@ -5745,7 +5763,8 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
-	if (decode_getfh(xdr, &res->fh) != 0)
+	status = decode_getfh(xdr, &res->fh);
+	if (status)
 		goto out;
 	if (decode_getfattr(xdr, res->f_attr, res->server,
 				!RPC_IS_ASYNC(rqstp->rq_task)) != 0)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 8e7b61d..a5b2419 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -763,7 +763,7 @@ static int nfs_show_devname(struct seq_file *m, struct vfsmount *mnt)
 	int err = 0;
 	if (!page)
 		return -ENOMEM;
-	devname = nfs_path(&dummy, mnt->mnt_root, page, PAGE_SIZE);
+	devname = nfs_path(&dummy, mnt->mnt_root, page, PAGE_SIZE, 0);
 	if (IS_ERR(devname))
 		err = PTR_ERR(devname);
 	else
@@ -1052,7 +1052,7 @@ static int nfs_get_option_str(substring_t args[], char **option)
 {
 	kfree(*option);
 	*option = match_strdup(args);
-	return !option;
+	return !*option;
 }
 
 static int nfs_get_option_ul(substring_t args[], unsigned long *option)
@@ -1815,6 +1815,7 @@ static int nfs_validate_mount_data(void *options,
 
 		memcpy(sap, &data->addr, sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
+		args->nfs_server.port = ntohs(data->addr.sin_port);
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
@@ -2528,6 +2529,7 @@ static int nfs4_validate_mount_data(void *options,
 			return -EFAULT;
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
+		args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port);
 
 		if (data->auth_flavourlen) {
 			if (data->auth_flavourlen > 1)
@@ -3096,4 +3098,6 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
 	return res;
 }
 
+MODULE_ALIAS("nfs4");
+
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f2f80c0..58bb999 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1662,7 +1662,7 @@ out_error:
 
 #ifdef CONFIG_MIGRATION
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
-		struct page *page)
+		struct page *page, enum migrate_mode mode)
 {
 	/*
 	 * If PagePrivate is set, then the page is currently associated with
@@ -1677,7 +1677,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, mode);
 }
 #endif
 
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 4b470f6..d7c4f02 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -403,7 +403,7 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc)
 	int migrated, i, err;
 
 	/* listsize */
-	err = get_int(mesg, &fsloc->locations_count);
+	err = get_uint(mesg, &fsloc->locations_count);
 	if (err)
 		return err;
 	if (fsloc->locations_count > MAX_FS_LOCATIONS)
@@ -461,7 +461,7 @@ static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
 		return -EINVAL;
 
 	for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) {
-		err = get_int(mesg, &f->pseudoflavor);
+		err = get_uint(mesg, &f->pseudoflavor);
 		if (err)
 			return err;
 		/*
@@ -470,7 +470,7 @@ static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
 		 * problem at export time instead of when a client fails
 		 * to authenticate.
 		 */
-		err = get_int(mesg, &f->flags);
+		err = get_uint(mesg, &f->flags);
 		if (err)
 			return err;
 		/* Only some flags are allowed to differ between flavors: */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 92f7eb7..4ec38df 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -189,13 +189,7 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 {
 	if (atomic_dec_and_test(&fp->fi_access[oflag])) {
 		nfs4_file_put_fd(fp, oflag);
-		/*
-		 * It's also safe to get rid of the RDWR open *if*
-		 * we no longer have need of the other kind of access
-		 * or if we already have the other kind of open:
-		 */
-		if (fp->fi_fds[1-oflag]
-			|| atomic_read(&fp->fi_access[1 - oflag]) == 0)
+		if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
 			nfs4_file_put_fd(fp, O_RDWR);
 	}
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 6c74097..45f53ae 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -159,8 +159,8 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
 	 */
 	memcpy(p, argp->p, avail);
 	/* step to next page */
-	argp->p = page_address(argp->pagelist[0]);
 	argp->pagelist++;
+	argp->p = page_address(argp->pagelist[0]);
 	if (argp->pagelen < PAGE_SIZE) {
 		argp->end = argp->p + (argp->pagelen>>2);
 		argp->pagelen = 0;
@@ -262,7 +262,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		iattr->ia_valid |= ATTR_SIZE;
 	}
 	if (bmval[0] & FATTR4_WORD0_ACL) {
-		int nace;
+		u32 nace;
 		struct nfs4_ace *ace;
 
 		READ_BUF(4); len += 4;
@@ -342,10 +342,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ32(dummy32);
-			if (dummy32)
-				return nfserr_inval;
-			READ32(iattr->ia_atime.tv_sec);
+			READ64(iattr->ia_atime.tv_sec);
 			READ32(iattr->ia_atime.tv_nsec);
 			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
@@ -368,10 +365,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ32(dummy32);
-			if (dummy32)
-				return nfserr_inval;
-			READ32(iattr->ia_mtime.tv_sec);
+			READ64(iattr->ia_mtime.tv_sec);
 			READ32(iattr->ia_mtime.tv_nsec);
 			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
@@ -2010,7 +2004,7 @@ out_acl:
 	if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) {
 		if ((buflen -= 4) < 0)
 			goto out_resource;
-		WRITE32(1);
+		WRITE32(0);
 	}
 	if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) {
 		if ((buflen -= 4) < 0)
@@ -2148,8 +2142,7 @@ out_acl:
 	if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.atime.tv_sec);
+		WRITE64((s64)stat.atime.tv_sec);
 		WRITE32(stat.atime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
@@ -2162,15 +2155,13 @@ out_acl:
 	if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.ctime.tv_sec);
+		WRITE64((s64)stat.ctime.tv_sec);
 		WRITE32(stat.ctime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.mtime.tv_sec);
+		WRITE64((s64)stat.mtime.tv_sec);
 		WRITE32(stat.mtime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
@@ -2682,11 +2673,16 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	len = maxcount;
 	v = 0;
 	while (len > 0) {
-		pn = resp->rqstp->rq_resused++;
+		pn = resp->rqstp->rq_resused;
+		if (!resp->rqstp->rq_respages[pn]) { /* ran out of pages */
+			maxcount -= len;
+			break;
+		}
 		resp->rqstp->rq_vec[v].iov_base =
 			page_address(resp->rqstp->rq_respages[pn]);
 		resp->rqstp->rq_vec[v].iov_len =
 			len < PAGE_SIZE ? len : PAGE_SIZE;
+		resp->rqstp->rq_resused++;
 		v++;
 		len -= PAGE_SIZE;
 	}
@@ -2734,6 +2730,8 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
 		return nfserr;
 	if (resp->xbuf->page_len)
 		return nfserr_resource;
+	if (!resp->rqstp->rq_respages[resp->rqstp->rq_resused])
+		return nfserr_resource;
 
 	page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
 
@@ -2783,6 +2781,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 		return nfserr;
 	if (resp->xbuf->page_len)
 		return nfserr_resource;
+	if (!resp->rqstp->rq_respages[resp->rqstp->rq_resused])
+		return nfserr_resource;
 
 	RESERVE_SPACE(8);  /* verifier */
 	savep = p;
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 08a07a2..57ceaf3 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -191,6 +191,8 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs)
 	while (!list_empty(head)) {
 		ii = list_first_entry(head, struct nilfs_inode_info, i_dirty);
 		list_del_init(&ii->i_dirty);
+		truncate_inode_pages(&ii->vfs_inode.i_data, 0);
+		nilfs_btnode_cache_clear(&ii->i_btnode_cache);
 		iput(&ii->vfs_inode);
 	}
 }
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index b9b45fc..373cd7b 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -195,13 +195,32 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 
 static int nilfs_set_page_dirty(struct page *page)
 {
-	int ret = __set_page_dirty_buffers(page);
+	int ret = __set_page_dirty_nobuffers(page);
 
-	if (ret) {
+	if (page_has_buffers(page)) {
 		struct inode *inode = page->mapping->host;
-		unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
+		unsigned nr_dirty = 0;
+		struct buffer_head *bh, *head;
 
-		nilfs_set_file_dirty(inode, nr_dirty);
+		/*
+		 * This page is locked by callers, and no other thread
+		 * concurrently marks its buffers dirty since they are
+		 * only dirtied through routines in fs/buffer.c in
+		 * which call sites of mark_buffer_dirty are protected
+		 * by page lock.
+		 */
+		bh = head = page_buffers(page);
+		do {
+			/* Do not mark hole blocks dirty */
+			if (buffer_dirty(bh) || !buffer_mapped(bh))
+				continue;
+
+			set_buffer_dirty(bh);
+			nr_dirty++;
+		} while (bh = bh->b_this_page, bh != head);
+
+		if (nr_dirty)
+			nilfs_set_file_dirty(inode, nr_dirty);
 	}
 	return ret;
 }
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 3e65427..cee648e 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -182,7 +182,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
 	if (copy_from_user(&cpmode, argp, sizeof(cpmode)))
 		goto out;
 
-	down_read(&inode->i_sb->s_umount);
+	mutex_lock(&nilfs->ns_snapshot_mount_mutex);
 
 	nilfs_transaction_begin(inode->i_sb, &ti, 0);
 	ret = nilfs_cpfile_change_cpmode(
@@ -192,7 +192,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
 	else
 		nilfs_transaction_commit(inode->i_sb); /* never fails */
 
-	up_read(&inode->i_sb->s_umount);
+	mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
 out:
 	mnt_drop_write(filp->f_path.mnt);
 	return ret;
@@ -661,8 +661,11 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
 	if (ret < 0)
 		printk(KERN_ERR "NILFS: GC failed during preparation: "
 			"cannot read source blocks: err=%d\n", ret);
-	else
+	else {
+		if (nilfs_sb_need_update(nilfs))
+			set_nilfs_discontinued(nilfs);
 		ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
+	}
 
 	nilfs_remove_all_gcinodes(nilfs);
 	clear_nilfs_gc_running(nilfs);
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 850a7c0..07a666a 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -345,8 +345,7 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
 
 	if (err == -EOPNOTSUPP) {
 		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		bio_put(bio);
-		/* to be detected by submit_seg_bio() */
+		/* to be detected by nilfs_segbuf_submit_bio() */
 	}
 
 	if (!uptodate)
@@ -377,12 +376,12 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
 	bio->bi_private = segbuf;
 	bio_get(bio);
 	submit_bio(mode, bio);
+	segbuf->sb_nbio++;
 	if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
 		bio_put(bio);
 		err = -EOPNOTSUPP;
 		goto failed;
 	}
-	segbuf->sb_nbio++;
 	bio_put(bio);
 
 	wi->bio = NULL;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index bb24ab6..6f24e67 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2309,6 +2309,8 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head)
 		if (!test_bit(NILFS_I_UPDATED, &ii->i_state))
 			continue;
 		list_del_init(&ii->i_dirty);
+		truncate_inode_pages(&ii->vfs_inode.i_data, 0);
+		nilfs_btnode_cache_clear(&ii->i_btnode_cache);
 		iput(&ii->vfs_inode);
 	}
 }
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 8351c44..97bfbdd 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -951,6 +951,8 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 	struct nilfs_root *root;
 	int ret;
 
+	mutex_lock(&nilfs->ns_snapshot_mount_mutex);
+
 	down_read(&nilfs->ns_segctor_sem);
 	ret = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile, cno);
 	up_read(&nilfs->ns_segctor_sem);
@@ -975,6 +977,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 	ret = nilfs_get_root_dentry(s, root, root_dentry);
 	nilfs_put_root(root);
  out:
+	mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
 	return ret;
 }
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 35a8970..1c98f53 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -76,6 +76,7 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 	nilfs->ns_bdev = bdev;
 	atomic_set(&nilfs->ns_ndirtyblks, 0);
 	init_rwsem(&nilfs->ns_sem);
+	mutex_init(&nilfs->ns_snapshot_mount_mutex);
 	INIT_LIST_HEAD(&nilfs->ns_dirty_files);
 	INIT_LIST_HEAD(&nilfs->ns_gc_inodes);
 	spin_lock_init(&nilfs->ns_inode_lock);
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 9992b11..de7435f 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -47,6 +47,7 @@ enum {
  * @ns_flags: flags
  * @ns_bdev: block device
  * @ns_sem: semaphore for shared states
+ * @ns_snapshot_mount_mutex: mutex to protect snapshot mounts
  * @ns_sbh: buffer heads of on-disk super blocks
  * @ns_sbp: pointers to super block data
  * @ns_sbwtime: previous write time of super block
@@ -99,6 +100,7 @@ struct the_nilfs {
 
 	struct block_device    *ns_bdev;
 	struct rw_semaphore	ns_sem;
+	struct mutex		ns_snapshot_mount_mutex;
 
 	/*
 	 * used for
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c
index 44a88a9..0eb059e 100644
--- a/fs/nls/nls_base.c
+++ b/fs/nls/nls_base.c
@@ -114,34 +114,57 @@ int utf32_to_utf8(unicode_t u, u8 *s, int maxlen)
 }
 EXPORT_SYMBOL(utf32_to_utf8);
 
-int utf8s_to_utf16s(const u8 *s, int len, wchar_t *pwcs)
+static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian)
+{
+	switch (endian) {
+	default:
+		*s = (wchar_t) c;
+		break;
+	case UTF16_LITTLE_ENDIAN:
+		*s = __cpu_to_le16(c);
+		break;
+	case UTF16_BIG_ENDIAN:
+		*s = __cpu_to_be16(c);
+		break;
+	}
+}
+
+int utf8s_to_utf16s(const u8 *s, int len, enum utf16_endian endian,
+		wchar_t *pwcs, int maxlen)
 {
 	u16 *op;
 	int size;
 	unicode_t u;
 
 	op = pwcs;
-	while (*s && len > 0) {
+	while (len > 0 && maxlen > 0 && *s) {
 		if (*s & 0x80) {
 			size = utf8_to_utf32(s, len, &u);
 			if (size < 0)
 				return -EINVAL;
+			s += size;
+			len -= size;
 
 			if (u >= PLANE_SIZE) {
+				if (maxlen < 2)
+					break;
 				u -= PLANE_SIZE;
-				*op++ = (wchar_t) (SURROGATE_PAIR |
-						((u >> 10) & SURROGATE_BITS));
-				*op++ = (wchar_t) (SURROGATE_PAIR |
+				put_utf16(op++, SURROGATE_PAIR |
+						((u >> 10) & SURROGATE_BITS),
+						endian);
+				put_utf16(op++, SURROGATE_PAIR |
 						SURROGATE_LOW |
-						(u & SURROGATE_BITS));
+						(u & SURROGATE_BITS),
+						endian);
+				maxlen -= 2;
 			} else {
-				*op++ = (wchar_t) u;
+				put_utf16(op++, u, endian);
+				maxlen--;
 			}
-			s += size;
-			len -= size;
 		} else {
-			*op++ = *s++;
+			put_utf16(op++, *s++, endian);
 			len--;
+			maxlen--;
 		}
 	}
 	return op - pwcs;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index f35794b..0c2f912 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -18,9 +18,16 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new)
 	    old->tgid == new->tgid) {
 		switch (old->data_type) {
 		case (FSNOTIFY_EVENT_PATH):
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+			/* dont merge two permission events */
+			if ((old->mask & FAN_ALL_PERM_EVENTS) &&
+			    (new->mask & FAN_ALL_PERM_EVENTS))
+				return false;
+#endif
 			if ((old->path.mnt == new->path.mnt) &&
 			    (old->path.dentry == new->path.dentry))
 				return true;
+			break;
 		case (FSNOTIFY_EVENT_NONE):
 			return true;
 		default:
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9fde1c0..9860f6b 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -118,6 +118,7 @@ static int fill_event_metadata(struct fsnotify_group *group,
 	metadata->event_len = FAN_EVENT_METADATA_LEN;
 	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata->vers = FANOTIFY_METADATA_VERSION;
+	metadata->reserved = 0;
 	metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
 	metadata->pid = pid_vnr(event->tgid);
 	if (unlikely(event->mask & FAN_Q_OVERFLOW))
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 8445fbc..6f292dd 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -579,8 +579,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 
 	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
-	if (unlikely(!(mask & IN_ALL_EVENTS)))
-		return -EINVAL;
 
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
 	if (!fsn_mark)
@@ -632,8 +630,6 @@ static int inotify_new_watch(struct fsnotify_group *group,
 
 	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
-	if (unlikely(!(mask & IN_ALL_EVENTS)))
-		return -EINVAL;
 
 	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
 	if (unlikely(!tmp_i_mark))
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 7642d7c..ab4046f 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2539,6 +2539,7 @@ int ocfs2_super_lock(struct ocfs2_super *osb,
 	 * everything is up to the caller :) */
 	status = ocfs2_should_refresh_lock_res(lockres);
 	if (status < 0) {
+		ocfs2_cluster_unlock(osb, lockres, level);
 		mlog_errno(status);
 		goto bail;
 	}
@@ -2547,8 +2548,10 @@ int ocfs2_super_lock(struct ocfs2_super *osb,
 
 		ocfs2_complete_lock_res_refresh(lockres, status);
 
-		if (status < 0)
+		if (status < 0) {
+			ocfs2_cluster_unlock(osb, lockres, level);
 			mlog_errno(status);
+		}
 		ocfs2_track_lock_refresh(lockres);
 	}
 bail:
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 23457b4..774a032 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -782,7 +782,6 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	cpos = map_start >> osb->s_clustersize_bits;
 	mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
 					       map_start + map_len);
-	mapping_end -= cpos;
 	is_last = 0;
 	while (cpos < mapping_end && !is_last) {
 		u32 fe_flags;
@@ -791,7 +790,7 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 						 &hole_size, &rec, &is_last);
 		if (ret) {
 			mlog_errno(ret);
-			goto out;
+			goto out_unlock;
 		}
 
 		if (rec.e_blkno == 0ULL) {
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f169da4..b7e74b5 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -642,7 +642,7 @@ ocfs2_block_group_alloc_discontig(handle_t *handle,
 	 * cluster groups will be staying in cache for the duration of
 	 * this operation.
 	 */
-	ac->ac_allow_chain_relink = 0;
+	ac->ac_disable_chain_relink = 1;
 
 	/* Claim the first region */
 	status = ocfs2_block_group_claim_bits(osb, handle, ac, min_bits,
@@ -1823,7 +1823,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	 * Do this *after* figuring out how many bits we're taking out
 	 * of our target group.
 	 */
-	if (ac->ac_allow_chain_relink &&
+	if (!ac->ac_disable_chain_relink &&
 	    (prev_group_bh) &&
 	    (ocfs2_block_group_reasonably_empty(bg, res->sr_bits))) {
 		status = ocfs2_relink_block_group(handle, alloc_inode,
@@ -1928,7 +1928,6 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 
 	victim = ocfs2_find_victim_chain(cl);
 	ac->ac_chain = victim;
-	ac->ac_allow_chain_relink = 1;
 
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
@@ -1947,7 +1946,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	 * searching each chain in order. Don't allow chain relinking
 	 * because we only calculate enough journal credits for one
 	 * relink per alloc. */
-	ac->ac_allow_chain_relink = 0;
+	ac->ac_disable_chain_relink = 1;
 	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
 		if (i == victim)
 			continue;
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b8afabf..a36d0aa 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -49,7 +49,7 @@ struct ocfs2_alloc_context {
 
 	/* these are used by the chain search */
 	u16    ac_chain;
-	int    ac_allow_chain_relink;
+	int    ac_disable_chain_relink;
 	group_search_t *ac_group_search;
 
 	u64    ac_last_group;
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 81ecf9c..61a84cf 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -6497,6 +6497,16 @@ static int ocfs2_reflink_xattr_inline(struct ocfs2_xattr_reflink *args)
 	}
 
 	new_oi = OCFS2_I(args->new_inode);
+	/*
+	 * Adjust extent record count to reserve space for extended attribute.
+	 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+	 */
+	if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+	    !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
+		struct ocfs2_extent_list *el = &new_di->id2.i_list;
+		le16_add_cpu(&el->l_count, -(inline_size /
+					sizeof(struct ocfs2_extent_rec)));
+	}
 	spin_lock(&new_oi->ip_lock);
 	new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
 	new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);
diff --git a/fs/open.c b/fs/open.c
index b52cf01..bf00a86 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -396,10 +396,10 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
 	struct file *file;
 	struct inode *inode;
-	int error;
+	int error, fput_needed;
 
 	error = -EBADF;
-	file = fget(fd);
+	file = fget_raw_light(fd, &fput_needed);
 	if (!file)
 		goto out;
 
@@ -413,7 +413,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 	if (!error)
 		set_fs_pwd(current->fs, &file->f_path);
 out_putf:
-	fput(file);
+	fput_light(file, fput_needed);
 out:
 	return error;
 }
@@ -900,9 +900,10 @@ static inline int build_open_flags(int flags, int mode, struct open_flags *op)
 	int lookup_flags = 0;
 	int acc_mode;
 
-	if (!(flags & O_CREAT))
-		mode = 0;
-	op->mode = mode;
+	if (flags & O_CREAT)
+		op->mode = (mode & S_IALLUGO) | S_IFREG;
+	else
+		op->mode = 0;
 
 	/* Must never be set by userspace */
 	flags &= ~FMODE_NONOTIFY;
diff --git a/fs/pipe.c b/fs/pipe.c
index 0499a96..342aa86 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -859,6 +859,9 @@ pipe_rdwr_open(struct inode *inode, struct file *filp)
 {
 	int ret = -ENOENT;
 
+	if (!(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
+		return -EINVAL;
+
 	mutex_lock(&inode->i_mutex);
 
 	if (inode->i_pipe) {
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index fbb0b47..d5378d0 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -110,6 +110,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 
 		/* prevent the page from being discarded on memory pressure */
 		SetPageDirty(page);
+		SetPageUptodate(page);
 
 		unlock_page(page);
 		put_page(page);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 4fd5bb3..ebe8db4 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1568,8 +1568,10 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 			reiserfs_warning(sb, "reiserfs-13077",
 				"nfsd/reiserfs, fhtype=%d, len=%d - odd",
 				fh_type, fh_len);
-		fh_type = 5;
+		fh_type = fh_len;
 	}
+	if (fh_len < 2)
+		return NULL;
 
 	return reiserfs_get_dentry(sb, fid->raw[0], fid->raw[1],
 		(fh_type == 3 || fh_type >= 5) ? fid->raw[2] : 0);
@@ -1578,6 +1580,8 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid,
 		int fh_len, int fh_type)
 {
+	if (fh_type > fh_len)
+		fh_type = fh_len;
 	if (fh_type < 4)
 		return NULL;
 
@@ -1779,8 +1783,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 
 	BUG_ON(!th->t_trans_id);
 
-	dquot_initialize(inode);
+	reiserfs_write_unlock(inode->i_sb);
 	err = dquot_alloc_inode(inode);
+	reiserfs_write_lock(inode->i_sb);
 	if (err)
 		goto out_end_trans;
 	if (!dir->i_nlink) {
@@ -1976,8 +1981,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 
       out_end_trans:
 	journal_end(th, th->t_super, th->t_blocks_allocated);
+	reiserfs_write_unlock(inode->i_sb);
 	/* Drop can be outside and it needs more credits so it's better to have it outside */
 	dquot_drop(inode);
+	reiserfs_write_lock(inode->i_sb);
 	inode->i_flags |= S_NOQUOTA;
 	make_bad_inode(inode);
 
@@ -3101,10 +3108,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	/* must be turned off for recursive notify_change calls */
 	ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
 
-	depth = reiserfs_write_lock_once(inode->i_sb);
 	if (is_quota_modification(inode, attr))
 		dquot_initialize(inode);
-
+	depth = reiserfs_write_lock_once(inode->i_sb);
 	if (attr->ia_valid & ATTR_SIZE) {
 		/* version 2 items will be caught by the s_maxbytes check
 		 ** done for us in vmtruncate
@@ -3165,7 +3171,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 		error = journal_begin(&th, inode->i_sb, jbegin_count);
 		if (error)
 			goto out;
+		reiserfs_write_unlock_once(inode->i_sb, depth);
 		error = dquot_transfer(inode, attr);
+		depth = reiserfs_write_lock_once(inode->i_sb);
 		if (error) {
 			journal_end(&th, inode->i_sb, jbegin_count);
 			goto out;
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 313d39d..3ae9926 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -1968,7 +1968,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
 		       key2type(&(key->on_disk_key)));
 #endif
 
+	reiserfs_write_unlock(inode->i_sb);
 	retval = dquot_alloc_space_nodirty(inode, pasted_size);
+	reiserfs_write_lock(inode->i_sb);
 	if (retval) {
 		pathrelse(search_path);
 		return retval;
@@ -2061,9 +2063,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 			       "reiserquota insert_item(): allocating %u id=%u type=%c",
 			       quota_bytes, inode->i_uid, head2type(ih));
 #endif
+		reiserfs_write_unlock(inode->i_sb);
 		/* We can't dirty inode here. It would be immediately written but
 		 * appropriate stat item isn't inserted yet... */
 		retval = dquot_alloc_space_nodirty(inode, quota_bytes);
+		reiserfs_write_lock(inode->i_sb);
 		if (retval) {
 			pathrelse(path);
 			return retval;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index f19dfbf..7527623 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -254,7 +254,9 @@ static int finish_unfinished(struct super_block *s)
 			retval = remove_save_link_only(s, &save_link_key, 0);
 			continue;
 		}
+		reiserfs_write_unlock(s);
 		dquot_initialize(inode);
+		reiserfs_write_lock(s);
 
 		if (truncate && S_ISDIR(inode->i_mode)) {
 			/* We got a truncate request for a dir which is impossible.
@@ -1207,7 +1209,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 				kfree(qf_names[i]);
 #endif
 		err = -EINVAL;
-		goto out_err;
+		goto out_unlock;
 	}
 #ifdef CONFIG_QUOTA
 	handle_quota_files(s, qf_names, &qfmt);
@@ -1250,7 +1252,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	if (blocks) {
 		err = reiserfs_resize(s, blocks);
 		if (err != 0)
-			goto out_err;
+			goto out_unlock;
 	}
 
 	if (*mount_flags & MS_RDONLY) {
@@ -1260,9 +1262,15 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 			/* it is read-only already */
 			goto out_ok;
 
+		/*
+		 * Drop write lock. Quota will retake it when needed and lock
+		 * ordering requires calling dquot_suspend() without it.
+		 */
+		reiserfs_write_unlock(s);
 		err = dquot_suspend(s, -1);
 		if (err < 0)
 			goto out_err;
+		reiserfs_write_lock(s);
 
 		/* try to remount file system with read-only permissions */
 		if (sb_umount_state(rs) == REISERFS_VALID_FS
@@ -1272,7 +1280,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 
 		err = journal_begin(&th, s, 10);
 		if (err)
-			goto out_err;
+			goto out_unlock;
 
 		/* Mounting a rw partition read-only. */
 		reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
@@ -1287,7 +1295,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 
 		if (reiserfs_is_journal_aborted(journal)) {
 			err = journal->j_errno;
-			goto out_err;
+			goto out_unlock;
 		}
 
 		handle_data_mode(s, mount_options);
@@ -1296,7 +1304,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 		s->s_flags &= ~MS_RDONLY;	/* now it is safe to call journal_begin */
 		err = journal_begin(&th, s, 10);
 		if (err)
-			goto out_err;
+			goto out_unlock;
 
 		/* Mount a partition which is read-only, read-write */
 		reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
@@ -1313,11 +1321,17 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	SB_JOURNAL(s)->j_must_wait = 1;
 	err = journal_end(&th, s, 10);
 	if (err)
-		goto out_err;
+		goto out_unlock;
 	s->s_dirt = 0;
 
 	if (!(*mount_flags & MS_RDONLY)) {
+		/*
+		 * Drop write lock. Quota will retake it when needed and lock
+		 * ordering requires calling dquot_resume() without it.
+		 */
+		reiserfs_write_unlock(s);
 		dquot_resume(s, -1);
+		reiserfs_write_lock(s);
 		finish_unfinished(s);
 		reiserfs_xattr_init(s, *mount_flags);
 	}
@@ -1327,9 +1341,10 @@ out_ok:
 	reiserfs_write_unlock(s);
 	return 0;
 
+out_unlock:
+	reiserfs_write_unlock(s);
 out_err:
 	kfree(new_opts);
-	reiserfs_write_unlock(s);
 	return err;
 }
 
@@ -1952,13 +1967,15 @@ static int reiserfs_write_dquot(struct dquot *dquot)
 			  REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
 	if (ret)
 		goto out;
+	reiserfs_write_unlock(dquot->dq_sb);
 	ret = dquot_commit(dquot);
+	reiserfs_write_lock(dquot->dq_sb);
 	err =
 	    journal_end(&th, dquot->dq_sb,
 			REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
 	if (!ret && err)
 		ret = err;
-      out:
+out:
 	reiserfs_write_unlock(dquot->dq_sb);
 	return ret;
 }
@@ -1974,13 +1991,15 @@ static int reiserfs_acquire_dquot(struct dquot *dquot)
 			  REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
 	if (ret)
 		goto out;
+	reiserfs_write_unlock(dquot->dq_sb);
 	ret = dquot_acquire(dquot);
+	reiserfs_write_lock(dquot->dq_sb);
 	err =
 	    journal_end(&th, dquot->dq_sb,
 			REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
 	if (!ret && err)
 		ret = err;
-      out:
+out:
 	reiserfs_write_unlock(dquot->dq_sb);
 	return ret;
 }
@@ -1994,19 +2013,21 @@ static int reiserfs_release_dquot(struct dquot *dquot)
 	ret =
 	    journal_begin(&th, dquot->dq_sb,
 			  REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+	reiserfs_write_unlock(dquot->dq_sb);
 	if (ret) {
 		/* Release dquot anyway to avoid endless cycle in dqput() */
 		dquot_release(dquot);
 		goto out;
 	}
 	ret = dquot_release(dquot);
+	reiserfs_write_lock(dquot->dq_sb);
 	err =
 	    journal_end(&th, dquot->dq_sb,
 			REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
 	if (!ret && err)
 		ret = err;
-      out:
 	reiserfs_write_unlock(dquot->dq_sb);
+out:
 	return ret;
 }
 
@@ -2031,11 +2052,13 @@ static int reiserfs_write_info(struct super_block *sb, int type)
 	ret = journal_begin(&th, sb, 2);
 	if (ret)
 		goto out;
+	reiserfs_write_unlock(sb);
 	ret = dquot_commit_info(sb, type);
+	reiserfs_write_lock(sb);
 	err = journal_end(&th, sb, 2);
 	if (!ret && err)
 		ret = err;
-      out:
+out:
 	reiserfs_write_unlock(sb);
 	return ret;
 }
@@ -2059,8 +2082,11 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 	struct inode *inode;
 	struct reiserfs_transaction_handle th;
 
-	if (!(REISERFS_SB(sb)->s_mount_opt & (1 << REISERFS_QUOTA)))
-		return -EINVAL;
+	reiserfs_write_lock(sb);
+	if (!(REISERFS_SB(sb)->s_mount_opt & (1 << REISERFS_QUOTA))) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	/* Quotafile not on the same filesystem? */
 	if (path->mnt->mnt_sb != sb) {
@@ -2102,8 +2128,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 		if (err)
 			goto out;
 	}
-	err = dquot_quota_on(sb, type, format_id, path);
+	reiserfs_write_unlock(sb);
+	return dquot_quota_on(sb, type, format_id, path);
 out:
+	reiserfs_write_unlock(sb);
 	return err;
 }
 
@@ -2177,7 +2205,9 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 		tocopy = sb->s_blocksize - offset < towrite ?
 		    sb->s_blocksize - offset : towrite;
 		tmp_bh.b_state = 0;
+		reiserfs_write_lock(sb);
 		err = reiserfs_get_block(inode, blk, &tmp_bh, GET_BLOCK_CREATE);
+		reiserfs_write_unlock(sb);
 		if (err)
 			goto out;
 		if (offset || tocopy != sb->s_blocksize)
@@ -2193,10 +2223,12 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 		flush_dcache_page(bh->b_page);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
+		reiserfs_write_lock(sb);
 		reiserfs_prepare_for_journal(sb, bh, 1);
 		journal_mark_dirty(current->journal_info, sb, bh);
 		if (!journal_quota)
 			reiserfs_add_ordered_list(inode, bh);
+		reiserfs_write_unlock(sb);
 		brelse(bh);
 		offset = 0;
 		towrite -= tocopy;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index d780896..6e3ca4e 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -187,8 +187,8 @@ fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
 	if (dbuf->count == ARRAY_SIZE(dbuf->dentries))
 		return -ENOSPC;
 
-	if (name[0] == '.' && (name[1] == '\0' ||
-			       (name[1] == '.' && name[2] == '\0')))
+	if (name[0] == '.' && (namelen < 2 ||
+			       (namelen == 2 && name[1] == '.')))
 		return 0;
 
 	dentry = lookup_one_len(name, dbuf->xadir, namelen);
diff --git a/fs/splice.c b/fs/splice.c
index 9d89008..16d0cb4 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -274,13 +274,16 @@ static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
  * Check if we need to grow the arrays holding pages and partial page
  * descriptions.
  */
-int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
 {
-	if (pipe->buffers <= PIPE_DEF_BUFFERS)
+	unsigned int buffers = ACCESS_ONCE(pipe->buffers);
+
+	spd->nr_pages_max = buffers;
+	if (buffers <= PIPE_DEF_BUFFERS)
 		return 0;
 
-	spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
-	spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL);
+	spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL);
+	spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL);
 
 	if (spd->pages && spd->partial)
 		return 0;
@@ -290,10 +293,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
 	return -ENOMEM;
 }
 
-void splice_shrink_spd(struct pipe_inode_info *pipe,
-		       struct splice_pipe_desc *spd)
+void splice_shrink_spd(struct splice_pipe_desc *spd)
 {
-	if (pipe->buffers <= PIPE_DEF_BUFFERS)
+	if (spd->nr_pages_max <= PIPE_DEF_BUFFERS)
 		return;
 
 	kfree(spd->pages);
@@ -316,6 +318,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -327,7 +330,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	loff = *ppos & ~PAGE_CACHE_MASK;
 	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	nr_pages = min(req_pages, pipe->buffers);
+	nr_pages = min(req_pages, spd.nr_pages_max);
 
 	/*
 	 * Lookup the (hopefully) full range of pages we need.
@@ -498,7 +501,7 @@ fill_it:
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return error;
 }
 
@@ -599,6 +602,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &default_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -609,8 +613,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 
 	res = -ENOMEM;
 	vec = __vec;
-	if (pipe->buffers > PIPE_DEF_BUFFERS) {
-		vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+	if (spd.nr_pages_max > PIPE_DEF_BUFFERS) {
+		vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL);
 		if (!vec)
 			goto shrink_ret;
 	}
@@ -618,7 +622,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	offset = *ppos & ~PAGE_CACHE_MASK;
 	nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-	for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
+	for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) {
 		struct page *page;
 
 		page = alloc_page(GFP_USER);
@@ -666,7 +670,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 shrink_ret:
 	if (vec != __vec)
 		kfree(vec);
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return res;
 
 err:
@@ -693,8 +697,10 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 		return -EINVAL;
 
 	more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
-	if (sd->len < sd->total_len)
+
+	if (sd->len < sd->total_len && pipe->nrbufs > 1)
 		more |= MSG_SENDPAGE_NOTLAST;
+
 	return file->f_op->sendpage(file, buf->page, buf->offset,
 				    sd->len, &pos, more);
 }
@@ -1616,6 +1622,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &user_page_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1631,13 +1638,13 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
 
 	spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages,
 					    spd.partial, flags & SPLICE_F_GIFT,
-					    pipe->buffers);
+					    spd.nr_pages_max);
 	if (spd.nr_pages <= 0)
 		ret = spd.nr_pages;
 	else
 		ret = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return ret;
 }
 
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 7438850..b5a8636 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -290,7 +290,7 @@ handle_fragments:
 
 check_directory_table:
 	/* Sanity check directory_table */
-	if (msblk->directory_table >= next_table) {
+	if (msblk->directory_table > next_table) {
 		err = -EINVAL;
 		goto failed_mount;
 	}
diff --git a/fs/stat.c b/fs/stat.c
index 02a6061..aec24ec 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -57,7 +57,7 @@ EXPORT_SYMBOL(vfs_getattr);
 
 int vfs_fstat(unsigned int fd, struct kstat *stat)
 {
-	struct file *f = fget(fd);
+	struct file *f = fget_raw(fd);
 	int error = -EBADF;
 
 	if (f) {
diff --git a/fs/statfs.c b/fs/statfs.c
index 9cf04a1..a133c3e 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -86,7 +86,7 @@ int user_statfs(const char __user *pathname, struct kstatfs *st)
 
 int fd_statfs(int fd, struct kstatfs *st)
 {
-	struct file *file = fget(fd);
+	struct file *file = fget_raw(fd);
 	int error = -EBADF;
 	if (file) {
 		error = vfs_statfs(&file->f_path, st);
diff --git a/fs/super.c b/fs/super.c
index ab3d672..a448af5 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -222,19 +222,19 @@ EXPORT_SYMBOL(deactivate_super);
  *	and want to turn it into a full-blown active reference.  grab_super()
  *	is called with sb_lock held and drops it.  Returns 1 in case of
  *	success, 0 if we had failed (superblock contents was already dead or
- *	dying when grab_super() had been called).
+ *	dying when grab_super() had been called).  Note that this is only
+ *	called for superblocks not in rundown mode (== ones still on ->fs_supers
+ *	of their type), so increment of ->s_count is OK here.
  */
 static int grab_super(struct super_block *s) __releases(sb_lock)
 {
-	if (atomic_inc_not_zero(&s->s_active)) {
-		spin_unlock(&sb_lock);
-		return 1;
-	}
-	/* it's going away */
 	s->s_count++;
 	spin_unlock(&sb_lock);
-	/* wait for it to die */
 	down_write(&s->s_umount);
+	if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) {
+		put_super(s);
+		return 1;
+	}
 	up_write(&s->s_umount);
 	put_super(s);
 	return 0;
@@ -335,11 +335,6 @@ retry:
 				destroy_super(s);
 				s = NULL;
 			}
-			down_write(&old->s_umount);
-			if (unlikely(!(old->s_flags & MS_BORN))) {
-				deactivate_locked_super(old);
-				goto retry;
-			}
 			return old;
 		}
 	}
@@ -512,10 +507,10 @@ restart:
 		if (list_empty(&sb->s_instances))
 			continue;
 		if (sb->s_bdev == bdev) {
-			if (grab_super(sb)) /* drops sb_lock */
-				return sb;
-			else
+			if (!grab_super(sb))
 				goto restart;
+			up_write(&sb->s_umount);
+			return sb;
 		}
 	}
 	spin_unlock(&sb_lock);
@@ -1009,6 +1004,8 @@ int freeze_super(struct super_block *sb)
 			printk(KERN_ERR
 				"VFS:Filesystem freeze failed\n");
 			sb->s_frozen = SB_UNFROZEN;
+			smp_wmb();
+			wake_up(&sb->s_wait_unfrozen);
 			deactivate_locked_super(sb);
 			return ret;
 		}
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index ea9120a..3ab78b8 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -404,20 +404,18 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 /**
  *	sysfs_pathname - return full path to sysfs dirent
  *	@sd: sysfs_dirent whose path we want
- *	@path: caller allocated buffer
+ *	@path: caller allocated buffer of size PATH_MAX
  *
  *	Gives the name "/" to the sysfs_root entry; any path returned
  *	is relative to wherever sysfs is mounted.
- *
- *	XXX: does no error checking on @path size
  */
 static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
 {
 	if (sd->s_parent) {
 		sysfs_pathname(sd->s_parent, path);
-		strcat(path, "/");
+		strlcat(path, "/", PATH_MAX);
 	}
-	strcat(path, sd->s_name);
+	strlcat(path, sd->s_name, PATH_MAX);
 	return path;
 }
 
@@ -450,9 +448,11 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 		char *path = kzalloc(PATH_MAX, GFP_KERNEL);
 		WARN(1, KERN_WARNING
 		     "sysfs: cannot create duplicate filename '%s'\n",
-		     (path == NULL) ? sd->s_name :
-		     strcat(strcat(sysfs_pathname(acxt->parent_sd, path), "/"),
-		            sd->s_name));
+		     (path == NULL) ? sd->s_name
+				    : (sysfs_pathname(acxt->parent_sd, path),
+				       strlcat(path, "/", PATH_MAX),
+				       strlcat(path, sd->s_name, PATH_MAX),
+				       path));
 		kfree(path);
 	}
 
@@ -917,6 +917,8 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		ino = parent_sd->s_ino;
 		if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
+		else
+			return 0;
 	}
 	if (filp->f_pos == 1) {
 		if (parent_sd->s_parent)
@@ -925,6 +927,8 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 			ino = parent_sd->s_ino;
 		if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
+		else
+			return 0;
 	}
 	mutex_lock(&sysfs_mutex);
 	for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
@@ -955,7 +959,6 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	return 0;
 }
 
-
 const struct file_operations sysfs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= sysfs_readdir,
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index ef5abd3..936a038 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -355,31 +355,50 @@ static unsigned int vfs_dent_type(uint8_t type)
 static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 {
 	int err, over = 0;
+	loff_t pos = file->f_pos;
 	struct qstr nm;
 	union ubifs_key key;
 	struct ubifs_dent_node *dent;
 	struct inode *dir = file->f_path.dentry->d_inode;
 	struct ubifs_info *c = dir->i_sb->s_fs_info;
 
-	dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, file->f_pos);
+	dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, pos);
 
-	if (file->f_pos > UBIFS_S_KEY_HASH_MASK || file->f_pos == 2)
+	if (pos > UBIFS_S_KEY_HASH_MASK || pos == 2)
 		/*
 		 * The directory was seek'ed to a senseless position or there
 		 * are no more entries.
 		 */
 		return 0;
 
+	if (file->f_version == 0) {
+		/*
+		 * The file was seek'ed, which means that @file->private_data
+		 * is now invalid. This may also be just the first
+		 * 'ubifs_readdir()' invocation, in which case
+		 * @file->private_data is NULL, and the below code is
+		 * basically a no-op.
+		 */
+		kfree(file->private_data);
+		file->private_data = NULL;
+	}
+
+	/*
+	 * 'generic_file_llseek()' unconditionally sets @file->f_version to
+	 * zero, and we use this for detecting whether the file was seek'ed.
+	 */
+	file->f_version = 1;
+
 	/* File positions 0 and 1 correspond to "." and ".." */
-	if (file->f_pos == 0) {
+	if (pos == 0) {
 		ubifs_assert(!file->private_data);
 		over = filldir(dirent, ".", 1, 0, dir->i_ino, DT_DIR);
 		if (over)
 			return 0;
-		file->f_pos = 1;
+		file->f_pos = pos = 1;
 	}
 
-	if (file->f_pos == 1) {
+	if (pos == 1) {
 		ubifs_assert(!file->private_data);
 		over = filldir(dirent, "..", 2, 1,
 			       parent_ino(file->f_path.dentry), DT_DIR);
@@ -395,7 +414,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 			goto out;
 		}
 
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 	}
 
@@ -403,17 +422,16 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 	if (!dent) {
 		/*
 		 * The directory was seek'ed to and is now readdir'ed.
-		 * Find the entry corresponding to @file->f_pos or the
-		 * closest one.
+		 * Find the entry corresponding to @pos or the closest one.
 		 */
-		dent_key_init_hash(c, &key, dir->i_ino, file->f_pos);
+		dent_key_init_hash(c, &key, dir->i_ino, pos);
 		nm.name = NULL;
 		dent = ubifs_tnc_next_ent(c, &key, &nm);
 		if (IS_ERR(dent)) {
 			err = PTR_ERR(dent);
 			goto out;
 		}
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 	}
 
@@ -425,7 +443,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 			     ubifs_inode(dir)->creat_sqnum);
 
 		nm.len = le16_to_cpu(dent->nlen);
-		over = filldir(dirent, dent->name, nm.len, file->f_pos,
+		over = filldir(dirent, dent->name, nm.len, pos,
 			       le64_to_cpu(dent->inum),
 			       vfs_dent_type(dent->type));
 		if (over)
@@ -441,9 +459,17 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 		}
 
 		kfree(file->private_data);
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 		cond_resched();
+
+		if (file->f_version == 0)
+			/*
+			 * The file was seek'ed meanwhile, lets return and start
+			 * reading direntries from the new position on the next
+			 * invocation.
+			 */
+			return 0;
 	}
 
 out:
@@ -454,15 +480,13 @@ out:
 
 	kfree(file->private_data);
 	file->private_data = NULL;
+	/* 2 is a special value indicating that there are no more direntries */
 	file->f_pos = 2;
 	return 0;
 }
 
-/* If a directory is seeked, we have to free saved readdir() state */
 static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int origin)
 {
-	kfree(file->private_data);
-	file->private_data = NULL;
 	return generic_file_llseek(file, offset, origin);
 }
 
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 2559d17..5dc48ca 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c)
 	if (!lprops) {
 		lprops = ubifs_fast_find_freeable(c);
 		if (!lprops) {
-			ubifs_assert(c->freeable_cnt == 0);
-			if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+			/*
+			 * The first condition means the following: go scan the
+			 * LPT if there are uncategorized lprops, which means
+			 * there may be freeable LEBs there (UBIFS does not
+			 * store the information about freeable LEBs in the
+			 * master node).
+			 */
+			if (c->in_a_category_cnt != c->main_lebs ||
+			    c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+				ubifs_assert(c->freeable_cnt == 0);
 				lprops = scan_for_leb_for_idx(c);
 				if (IS_ERR(lprops)) {
 					err = PTR_ERR(lprops);
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 667884f..ae6f74a 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
 	default:
 		ubifs_assert(0);
 	}
+
 	lprops->flags &= ~LPROPS_CAT_MASK;
 	lprops->flags |= cat;
+	c->in_a_category_cnt += 1;
+	ubifs_assert(c->in_a_category_cnt <= c->main_lebs);
 }
 
 /**
@@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c,
 	default:
 		ubifs_assert(0);
 	}
+
+	c->in_a_category_cnt -= 1;
+	ubifs_assert(c->in_a_category_cnt >= 0);
 }
 
 /**
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index c606f01..1250016 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -715,8 +715,12 @@ static int fixup_free_space(struct ubifs_info *c)
 		lnum = ubifs_next_log_lnum(c, lnum);
 	}
 
-	/* Fixup the current log head */
-	err = fixup_leb(c, c->lhead_lnum, c->lhead_offs);
+	/*
+	 * Fixup the log head which contains the only a CS node at the
+	 * beginning.
+	 */
+	err = fixup_leb(c, c->lhead_lnum,
+			ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size));
 	if (err)
 		goto out;
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 529be05..db04976 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1583,6 +1583,12 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 	c->remounting_rw = 1;
 	c->ro_mount = 0;
 
+	if (c->space_fixup) {
+		err = ubifs_fixup_free_space(c);
+		if (err)
+			return err;
+	}
+
 	err = check_free_space(c);
 	if (err)
 		goto out;
@@ -1699,12 +1705,6 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 		err = dbg_check_space_info(c);
 	}
 
-	if (c->space_fixup) {
-		err = ubifs_fixup_free_space(c);
-		if (err)
-			goto out;
-	}
-
 	mutex_unlock(&c->umount_mutex);
 	return err;
 
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index f79983d..62d50a9 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1187,6 +1187,8 @@ struct ubifs_debug_info;
  * @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size)
  * @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size)
  * @freeable_cnt: number of freeable LEBs in @freeable_list
+ * @in_a_category_cnt: count of lprops which are in a certain category, which
+ *                     basically meants that they were loaded from the flash
  *
  * @ltab_lnum: LEB number of LPT's own lprops table
  * @ltab_offs: offset of LPT's own lprops table
@@ -1416,6 +1418,7 @@ struct ubifs_info {
 	struct list_head freeable_list;
 	struct list_head frdi_idx_list;
 	int freeable_cnt;
+	int in_a_category_cnt;
 
 	int ltab_lnum;
 	int ltab_offs;
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 3438b00..8eb9628 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -39,20 +39,24 @@
 #include "udf_i.h"
 #include "udf_sb.h"
 
-static int udf_adinicb_readpage(struct file *file, struct page *page)
+static void __udf_adinicb_readpage(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	char *kaddr;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
-	BUG_ON(!PageLocked(page));
-
 	kaddr = kmap(page);
-	memset(kaddr, 0, PAGE_CACHE_SIZE);
 	memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, inode->i_size);
+	memset(kaddr + inode->i_size, 0, PAGE_CACHE_SIZE - inode->i_size);
 	flush_dcache_page(page);
 	SetPageUptodate(page);
 	kunmap(page);
+}
+
+static int udf_adinicb_readpage(struct file *file, struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+	__udf_adinicb_readpage(page);
 	unlock_page(page);
 
 	return 0;
@@ -77,6 +81,25 @@ static int udf_adinicb_writepage(struct page *page,
 	return 0;
 }
 
+static int udf_adinicb_write_begin(struct file *file,
+			struct address_space *mapping, loff_t pos,
+			unsigned len, unsigned flags, struct page **pagep,
+			void **fsdata)
+{
+	struct page *page;
+
+	if (WARN_ON_ONCE(pos >= PAGE_CACHE_SIZE))
+		return -EIO;
+	page = grab_cache_page_write_begin(mapping, 0, flags);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
+
+	if (!PageUptodate(page) && len != PAGE_CACHE_SIZE)
+		__udf_adinicb_readpage(page);
+	return 0;
+}
+
 static int udf_adinicb_write_end(struct file *file,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
@@ -98,8 +121,8 @@ static int udf_adinicb_write_end(struct file *file,
 const struct address_space_operations udf_adinicb_aops = {
 	.readpage	= udf_adinicb_readpage,
 	.writepage	= udf_adinicb_writepage,
-	.write_begin = simple_write_begin,
-	.write_end = udf_adinicb_write_end,
+	.write_begin	= udf_adinicb_write_begin,
+	.write_end	= udf_adinicb_write_end,
 };
 
 static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 262050f..957c974 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -575,6 +575,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 	struct udf_inode_info *iinfo = UDF_I(inode);
 	int goal = 0, pgoal = iinfo->i_location.logicalBlockNum;
 	int lastblock = 0;
+	bool isBeyondEOF;
 
 	prev_epos.offset = udf_file_entry_alloc_offset(inode);
 	prev_epos.block = iinfo->i_location;
@@ -653,7 +654,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 	/* Are we beyond EOF? */
 	if (etype == -1) {
 		int ret;
-
+		isBeyondEOF = 1;
 		if (count) {
 			if (c)
 				laarr[0] = laarr[1];
@@ -696,6 +697,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 		endnum = c + 1;
 		lastblock = 1;
 	} else {
+		isBeyondEOF = 0;
 		endnum = startnum = ((count > 2) ? 2 : count);
 
 		/* if the current extent is in position 0,
@@ -738,10 +740,13 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 				goal, err);
 		if (!newblocknum) {
 			brelse(prev_epos.bh);
+			brelse(cur_epos.bh);
+			brelse(next_epos.bh);
 			*err = -ENOSPC;
 			return NULL;
 		}
-		iinfo->i_lenExtents += inode->i_sb->s_blocksize;
+		if (isBeyondEOF)
+			iinfo->i_lenExtents += inode->i_sb->s_blocksize;
 	}
 
 	/* if the extent the requsted block is located in contains multiple
@@ -768,6 +773,8 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 	udf_update_extents(inode, laarr, startnum, endnum, &prev_epos);
 
 	brelse(prev_epos.bh);
+	brelse(cur_epos.bh);
+	brelse(next_epos.bh);
 
 	newblock = udf_get_pblock(inode->i_sb, newblocknum,
 				iinfo->i_location.partitionReferenceNum, 0);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index f1dce84..d8c1bb5 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1297,6 +1297,7 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp,
 	*lenp = 3;
 	fid->udf.block = location.logicalBlockNum;
 	fid->udf.partref = location.partitionReferenceNum;
+	fid->udf.parent_partref = 0;
 	fid->udf.generation = inode->i_generation;
 
 	if (connectable && !S_ISDIR(inode->i_mode)) {
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 7f0e18a..b0c7b53 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -56,6 +56,7 @@
 #include <linux/seq_file.h>
 #include <linux/bitmap.h>
 #include <linux/crc-itu-t.h>
+#include <linux/log2.h>
 #include <asm/byteorder.h>
 
 #include "udf_sb.h"
@@ -1244,16 +1245,65 @@ out_bh:
 	return ret;
 }
 
+static int udf_load_sparable_map(struct super_block *sb,
+				 struct udf_part_map *map,
+				 struct sparablePartitionMap *spm)
+{
+	uint32_t loc;
+	uint16_t ident;
+	struct sparingTable *st;
+	struct udf_sparing_data *sdata = &map->s_type_specific.s_sparing;
+	int i;
+	struct buffer_head *bh;
+
+	map->s_partition_type = UDF_SPARABLE_MAP15;
+	sdata->s_packet_len = le16_to_cpu(spm->packetLength);
+	if (!is_power_of_2(sdata->s_packet_len)) {
+		udf_error(sb, __func__, "error loading logical volume descriptor: "
+			"Invalid packet length %u\n",
+			(unsigned)sdata->s_packet_len);
+		return -EIO;
+	}
+	if (spm->numSparingTables > 4) {
+		udf_error(sb, __func__, "error loading logical volume descriptor: "
+			"Too many sparing tables (%d)\n",
+			(int)spm->numSparingTables);
+		return -EIO;
+	}
+
+	for (i = 0; i < spm->numSparingTables; i++) {
+		loc = le32_to_cpu(spm->locSparingTable[i]);
+		bh = udf_read_tagged(sb, loc, loc, &ident);
+		if (!bh)
+			continue;
+
+		st = (struct sparingTable *)bh->b_data;
+		if (ident != 0 ||
+		    strncmp(st->sparingIdent.ident, UDF_ID_SPARING,
+			    strlen(UDF_ID_SPARING)) ||
+		    sizeof(*st) + le16_to_cpu(st->reallocationTableLen) >
+							sb->s_blocksize) {
+			brelse(bh);
+			continue;
+		}
+
+		sdata->s_spar_map[i] = bh;
+	}
+	map->s_partition_func = udf_get_pblock_spar15;
+	return 0;
+}
+
 static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 			       struct kernel_lb_addr *fileset)
 {
 	struct logicalVolDesc *lvd;
-	int i, j, offset;
+	int i, offset;
 	uint8_t type;
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct genericPartitionMap *gpm;
 	uint16_t ident;
 	struct buffer_head *bh;
+	unsigned int table_len;
 	int ret = 0;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
@@ -1261,15 +1311,21 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 		return 1;
 	BUG_ON(ident != TAG_IDENT_LVD);
 	lvd = (struct logicalVolDesc *)bh->b_data;
-
-	i = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps));
-	if (i != 0) {
-		ret = i;
+	table_len = le32_to_cpu(lvd->mapTableLength);
+	if (sizeof(*lvd) + table_len > sb->s_blocksize) {
+		udf_error(sb, __func__, "error loading logical volume descriptor: "
+			"Partition table too long (%u > %lu)\n", table_len,
+			sb->s_blocksize - sizeof(*lvd));
+		ret = 1;
 		goto out_bh;
 	}
 
+	ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps));
+	if (ret)
+		goto out_bh;
+
 	for (i = 0, offset = 0;
-	     i < sbi->s_partitions && offset < le32_to_cpu(lvd->mapTableLength);
+	     i < sbi->s_partitions && offset < table_len;
 	     i++, offset += gpm->partitionMapLength) {
 		struct udf_part_map *map = &sbi->s_partmaps[i];
 		gpm = (struct genericPartitionMap *)
@@ -1304,38 +1360,11 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 			} else if (!strncmp(upm2->partIdent.ident,
 						UDF_ID_SPARABLE,
 						strlen(UDF_ID_SPARABLE))) {
-				uint32_t loc;
-				struct sparingTable *st;
-				struct sparablePartitionMap *spm =
-					(struct sparablePartitionMap *)gpm;
-
-				map->s_partition_type = UDF_SPARABLE_MAP15;
-				map->s_type_specific.s_sparing.s_packet_len =
-						le16_to_cpu(spm->packetLength);
-				for (j = 0; j < spm->numSparingTables; j++) {
-					struct buffer_head *bh2;
-
-					loc = le32_to_cpu(
-						spm->locSparingTable[j]);
-					bh2 = udf_read_tagged(sb, loc, loc,
-							     &ident);
-					map->s_type_specific.s_sparing.
-							s_spar_map[j] = bh2;
-
-					if (bh2 == NULL)
-						continue;
-
-					st = (struct sparingTable *)bh2->b_data;
-					if (ident != 0 || strncmp(
-						st->sparingIdent.ident,
-						UDF_ID_SPARING,
-						strlen(UDF_ID_SPARING))) {
-						brelse(bh2);
-						map->s_type_specific.s_sparing.
-							s_spar_map[j] = NULL;
-					}
+				if (udf_load_sparable_map(sb, map,
+				    (struct sparablePartitionMap *)gpm) < 0) {
+					ret = 1;
+					goto out_bh;
 				}
-				map->s_partition_func = udf_get_pblock_spar15;
 			} else if (!strncmp(upm2->partIdent.ident,
 						UDF_ID_METADATA,
 						strlen(UDF_ID_METADATA))) {
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 4858c19..54706dc 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -79,7 +79,7 @@ struct udf_virtual_data {
 struct udf_bitmap {
 	__u32			s_extLength;
 	__u32			s_extPosition;
-	__u16			s_nr_groups;
+	int			s_nr_groups;
 	struct buffer_head 	**s_block_bitmap;
 };
 
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index fed3f3c..844b22b 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -195,6 +195,9 @@ xfs_fs_fh_to_parent(struct super_block *sb, struct fid *fid,
 	struct xfs_fid64	*fid64 = (struct xfs_fid64 *)fid;
 	struct inode		*inode = NULL;
 
+	if (fh_len < xfs_fileid_length(fileid_type))
+		return NULL;
+
 	switch (fileid_type) {
 	case FILEID_INO32_GEN_PARENT:
 		inode = xfs_nfs_get_inode(sb, fid->i32.parent_ino,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b75fd67..6a5a1af 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3512,7 +3512,7 @@ xlog_do_recovery_pass(
 				 *   - order is important.
 				 */
 				error = xlog_bread_offset(log, 0,
-						bblks - split_bblks, hbp,
+						bblks - split_bblks, dbp,
 						offset + BBTOB(split_bblks));
 				if (error)
 					goto bread_err2;
author	Ziyan <jaraidaniel@gmail.com>	2015-10-24 18:19:09 +0200
committer	Ziyan <jaraidaniel@gmail.com>	2015-10-25 16:24:52 +0100
commit	101878938737bd16a5f7fb932b51041f7dbbb733 (patch)
tree	235732d29c6741f22f2020218b2fad41c40b57b8 /fs
parent	540bea4ab32149f8bc71fe34b73340c8d9abc053 (diff)
parent	5dba9ddd98cbc7ad319d687887981a0ea0062c75 (diff)
download	kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.zip kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.tar.gz kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.tar.bz2