Merge tag 'v4.1.41' into 4.1-2.0.x-imx

Linux 4.1.41

* tag 'v4.1.41': (473 commits)
  Linux 4.1.41
  mm/huge_memory.c: respect FOLL_FORCE/FOLL_COW for thp
  xc2028: Fix use-after-free bug properly
  iio: proximity: as3935: fix as3935_write
  ipx: call ipxitf_put() in ioctl error path
  sched/fair: Initialize throttle_count for new task-groups lazily
  sched/fair: Do not announce throttled next buddy in dequeue_task_fair()
  iio: dac: ad7303: fix channel description
  mwifiex: pcie: fix cmd_buf use-after-free in remove/reset
  rtlwifi: rtl8821ae: setup 8812ae RFE according to device type
  ARM: tegra: paz00: Mark panel regulator as enabled on boot
  fs/xattr.c: zero out memory copied to userspace in getxattr
  vfio/type1: Remove locked page accounting workqueue
  crypto: algif_aead - Require setkey before accept(2)
  staging: gdm724x: gdm_mux: fix use-after-free on module unload
  drm/ttm: fix use-after-free races in vm fault handling
  f2fs: sanity check segment count
  ipv6: reorder ip6_route_dev_notifier after ipv6_dev_notf
  ipv6: initialize route null entry in addrconf_init()
  rtnetlink: NUL-terminate IFLA_PHYS_PORT_NAME string
  ...

Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>

32 files changed, 385 insertions, 137 deletions

diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index de59b4892bfb..5c651324e976 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -321,6 +321,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
 		name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
 			struct iattr iattr;
+			struct posix_acl *old_acl = acl;
 
 			retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
 			if (retval)
@@ -331,6 +332,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
 				 * by the mode bits. So don't
 				 * update ACL.
 				 */
+				posix_acl_release(old_acl);
 				value = NULL;
 				size = 0;
 			}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 300566ea9b74..73c24c8e341c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -77,12 +77,11 @@ void invalidate_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
-		return;
-
-	invalidate_bh_lrus();
-	lru_add_drain_all();	/* make sure all lru add caches are flushed */
-	invalidate_mapping_pages(mapping, 0, -1);
+	if (mapping->nrpages) {
+		invalidate_bh_lrus();
+		lru_add_drain_all();	/* make sure all lru add caches are flushed */
+		invalidate_mapping_pages(mapping, 0, -1);
+	}
 	/* 99% of the time, we don't need to flush the cleancache on the bdev.
 	 * But, for the strange corners, lets be cautious
 	 */
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index cd7ffad4041d..61e3be7d1620 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -369,6 +369,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 
 	if (update_xattr) {
 		int err = 0;
+
 		if (xattr && (flags & XATTR_CREATE))
 			err = -EEXIST;
 		else if (!xattr && (flags & XATTR_REPLACE))
@@ -376,12 +377,14 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		if (err) {
 			kfree(name);
 			kfree(val);
+			kfree(*newxattr);
 			return err;
 		}
 		if (update_xattr < 0) {
 			if (xattr)
 				__remove_xattr(ci, xattr);
 			kfree(name);
+			kfree(*newxattr);
 			return 0;
 		}
 	}
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 02b071bf3732..a0b3e7d1be48 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -83,6 +83,9 @@ convert_sfm_char(const __u16 src_char, char *target)
 	case SFM_COLON:
 		*target = ':';
 		break;
+	case SFM_DOUBLEQUOTE:
+		*target = '"';
+		break;
 	case SFM_ASTERISK:
 		*target = '*';
 		break;
@@ -418,6 +421,9 @@ static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
 	case ':':
 		dest_char = cpu_to_le16(SFM_COLON);
 		break;
+	case '"':
+		dest_char = cpu_to_le16(SFM_DOUBLEQUOTE);
+		break;
 	case '*':
 		dest_char = cpu_to_le16(SFM_ASTERISK);
 		break;
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index 479bc0a941f3..07ade707fa60 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -57,6 +57,7 @@
  * not conflict (although almost does) with the mapping above.
  */
 
+#define SFM_DOUBLEQUOTE ((__u16) 0xF020)
 #define SFM_ASTERISK    ((__u16) 0xF021)
 #define SFM_QUESTION    ((__u16) 0xF025)
 #define SFM_COLON       ((__u16) 0xF022)
@@ -64,8 +65,8 @@
 #define SFM_LESSTHAN    ((__u16) 0xF023)
 #define SFM_PIPE        ((__u16) 0xF027)
 #define SFM_SLASH       ((__u16) 0xF026)
-#define SFM_PERIOD	((__u16) 0xF028)
-#define SFM_SPACE	((__u16) 0xF029)
+#define SFM_SPACE	((__u16) 0xF028)
+#define SFM_PERIOD	((__u16) 0xF029)
 
 /*
  * Mapping mechanism to use when one of the seven reserved characters is
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 9d0e4fef8ee1..335f4ec51ecf 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -891,7 +891,6 @@ struct cifs_tcon {
 	bool need_reconnect:1; /* connection reset, tid now invalid */
 #ifdef CONFIG_CIFS_SMB2
 	bool print:1;		/* set if connection to printer share */
-	bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
 	__le32 capabilities;
 	__u32 share_flags;
 	__u32 maximal_access;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index f1a5067d5494..b3f401bb281a 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -716,6 +716,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
+	if (server->capabilities & CAP_UNICODE)
+		smb->hdr.Flags2 |= SMBFLG2_UNICODE;
+
 	/* set up echo request */
 	smb->hdr.Tid = 0xffff;
 	smb->hdr.WordCount = 1;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3f50cee79df9..fcf986aa2abe 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2535,7 +2535,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		wdata->credits = credits;
 
 		if (!wdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(wdata->cfile, false))
+		    !(rc = cifs_reopen_file(wdata->cfile, false)))
 			rc = server->ops->async_writev(wdata,
 					cifs_uncached_writedata_release);
 		if (rc) {
@@ -2948,7 +2948,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->credits = credits;
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 error:
 		if (rc) {
@@ -3534,7 +3534,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		}
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 		if (rc) {
 			add_credits_and_wake_if(server, rdata->credits, 0);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index fc537c29044e..87b87e091e8e 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile)
 	return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
 }
 
+static bool
+cifs_can_echo(struct TCP_Server_Info *server)
+{
+	if (server->tcpStatus == CifsGood)
+		return true;
+
+	return false;
+}
+
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = {
 	.get_dfs_refer = CIFSGetDFSRefer,
 	.qfs_tcon = cifs_qfs_tcon,
 	.is_path_accessible = cifs_is_path_accessible,
+	.can_echo = cifs_can_echo,
 	.query_path_info = cifs_query_path_info,
 	.query_file_info = cifs_query_file_info,
 	.get_srv_inum = cifs_get_srv_inum,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index e3cf4a5fb35a..f8ae041d60fe 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -491,8 +491,12 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 	}
 
 	if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
-		cifs_dbg(VFS, "invalid size of protocol negotiate response\n");
-		return -EIO;
+		cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
+			 rsplen);
+
+		/* relax check since Mac returns max bufsize allowed on ioctl */
+		if (rsplen > CIFSMaxBufSize)
+			return -EIO;
 	}
 
 	/* check validate negotiate info response matches what we got earlier */
@@ -854,9 +858,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	else
 		return -EIO;
 
-	if (tcon && tcon->bad_network_name)
-		return -ENOENT;
-
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -868,6 +869,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		return -EINVAL;
 	}
 
+	/* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+	if (tcon)
+		tcon->tid = 0;
+
 	rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
 	if (rc) {
 		kfree(unc_path);
@@ -946,8 +951,6 @@ tcon_exit:
 tcon_error_exit:
 	if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
-		if (tcon)
-			tcon->bad_network_name = true;
 	}
 	goto tcon_exit;
 }
@@ -1314,8 +1317,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	 * than one credit. Windows typically sets this smaller, but for some
 	 * ioctls it may be useful to allow server to send more. No point
 	 * limiting what the server can send as long as fits in one credit
+	 * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE
+	 * (by default, note that it can be overridden to make max larger)
+	 * in responses (except for read responses which can be bigger.
+	 * We may want to bump this limit up
 	 */
-	req->MaxOutputResponse = cpu_to_le32(0xFF00); /* < 64K uses 1 credit */
+	req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize);
 
 	if (is_fsctl)
 		req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index d77d542c2ed5..2032cae5031f 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1155,10 +1155,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	set_buffer_uptodate(dir_block);
 	err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
 	if (err)
-		goto out;
+		return err;
 	set_buffer_verified(dir_block);
-out:
-	return err;
+	return ext4_mark_inode_dirty(handle, inode);
 }
 
 static int ext4_convert_inline_data_nolock(handle_t *handle,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5beca5c5413e..66e147b446c8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5316,6 +5316,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	file_update_time(vma->vm_file);
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_convert_inline_data(inode);
+	if (ret)
+		goto out_ret;
+
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index e6798ca34928..2524057fd880 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3095,6 +3095,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (ar->pright && start + size - 1 >= ar->lright)
 		size -= start + size - ar->lright;
 
+	/*
+	 * Trim allocation request for filesystems with artificially small
+	 * groups.
+	 */
+	if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb))
+		size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb);
+
 	end = start + size;
 
 	/* check we don't cross already preallocated blocks */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b2dd1b01f076..660183e9ab7c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -819,6 +819,79 @@ static loff_t max_file_size(unsigned bits)
 	return result;
 }
 
+static inline bool sanity_check_area_boundary(struct super_block *sb,
+					struct f2fs_super_block *raw_super)
+{
+	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
+	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
+	u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
+	u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr);
+	u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
+	u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
+	u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt);
+	u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit);
+	u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat);
+	u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa);
+	u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+	u32 segment_count = le32_to_cpu(raw_super->segment_count);
+	u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+
+	if (segment0_blkaddr != cp_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Mismatch start address, segment0(%u) cp_blkaddr(%u)",
+			segment0_blkaddr, cp_blkaddr);
+		return true;
+	}
+
+	if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) !=
+							sit_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong CP boundary, start(%u) end(%u) blocks(%u)",
+			cp_blkaddr, sit_blkaddr,
+			segment_count_ckpt << log_blocks_per_seg);
+		return true;
+	}
+
+	if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) !=
+							nat_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong SIT boundary, start(%u) end(%u) blocks(%u)",
+			sit_blkaddr, nat_blkaddr,
+			segment_count_sit << log_blocks_per_seg);
+		return true;
+	}
+
+	if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) !=
+							ssa_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong NAT boundary, start(%u) end(%u) blocks(%u)",
+			nat_blkaddr, ssa_blkaddr,
+			segment_count_nat << log_blocks_per_seg);
+		return true;
+	}
+
+	if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) !=
+							main_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong SSA boundary, start(%u) end(%u) blocks(%u)",
+			ssa_blkaddr, main_blkaddr,
+			segment_count_ssa << log_blocks_per_seg);
+		return true;
+	}
+
+	if (main_blkaddr + (segment_count_main << log_blocks_per_seg) !=
+		segment0_blkaddr + (segment_count << log_blocks_per_seg)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)",
+			main_blkaddr,
+			segment0_blkaddr + (segment_count << log_blocks_per_seg),
+			segment_count_main << log_blocks_per_seg);
+		return true;
+	}
+
+	return false;
+}
+
 static int sanity_check_raw_super(struct super_block *sb,
 			struct f2fs_super_block *raw_super)
 {
@@ -848,6 +921,14 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
+	/* check log blocks per segment */
+	if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid log blocks per segment (%u)\n",
+			le32_to_cpu(raw_super->log_blocks_per_seg));
+		return 1;
+	}
+
 	/* Currently, support 512/1024/2048/4096 bytes sector size */
 	if (le32_to_cpu(raw_super->log_sectorsize) >
 				F2FS_MAX_LOG_SECTOR_SIZE ||
@@ -866,6 +947,30 @@ static int sanity_check_raw_super(struct super_block *sb,
 			le32_to_cpu(raw_super->log_sectorsize));
 		return 1;
 	}
+
+	/* check reserved ino info */
+	if (le32_to_cpu(raw_super->node_ino) != 1 ||
+		le32_to_cpu(raw_super->meta_ino) != 2 ||
+		le32_to_cpu(raw_super->root_ino) != 3) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)",
+			le32_to_cpu(raw_super->node_ino),
+			le32_to_cpu(raw_super->meta_ino),
+			le32_to_cpu(raw_super->root_ino));
+		return 1;
+	}
+
+	if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment count (%u)",
+			le32_to_cpu(raw_super->segment_count));
+		return 1;
+	}
+
+	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
+	if (sanity_check_area_boundary(sb, raw_super))
+		return 1;
+
 	return 0;
 }
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index c06774658345..beaec0d7cca3 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1268,6 +1268,16 @@ out:
 	return 0;
 }
 
+static void fat_dummy_inode_init(struct inode *inode)
+{
+	/* Initialize this dummy inode to work as no-op. */
+	MSDOS_I(inode)->mmu_private = 0;
+	MSDOS_I(inode)->i_start = 0;
+	MSDOS_I(inode)->i_logstart = 0;
+	MSDOS_I(inode)->i_attrs = 0;
+	MSDOS_I(inode)->i_pos = 0;
+}
+
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1712,12 +1722,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	MSDOS_I(fat_inode)->i_pos = 0;
+	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
+	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 487527b42d94..e4aab588d822 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -755,7 +755,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index,
 	int error;
 
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (!error)
+	if (!IS_ERR_VALUE(error))
 		error = get_leaf(dip, leaf_no, bh_out);
 
 	return error;
@@ -971,7 +971,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	index = name->hash >> (32 - dip->i_depth);
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (error)
+	if (IS_ERR_VALUE(error))
 		return error;
 
 	/*  Get the old leaf block  */
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 2abbb2babcae..deff03371626 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1778,7 +1778,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 
 	__blist_del_buffer(list, jh);
 	jh->b_jlist = BJ_None;
-	if (test_clear_buffer_jbddirty(bh))
+	if (transaction && is_journal_aborted(transaction->t_journal))
+		clear_buffer_jbddirty(bh);
+	else if (test_clear_buffer_jbddirty(bh))
 		mark_buffer_dirty(bh);	/* Expose it to the VM */
 }
 
diff --git a/fs/mount.h b/fs/mount.h
index 2152c16ddf74..32cabd55a787 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -88,7 +88,6 @@ static inline int is_mounted(struct vfsmount *mnt)
 }
 
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
-extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index c46921daca22..df20ee946f7c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -630,28 +630,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 }
 
 /*
- * find the last mount at @dentry on vfsmount @mnt.
- * mount_lock must be held.
- */
-struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
-{
-	struct mount *p, *res = NULL;
-	p = __lookup_mnt(mnt, dentry);
-	if (!p)
-		goto out;
-	if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-		res = p;
-	hlist_for_each_entry_continue(p, mnt_hash) {
-		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-			break;
-		if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-			res = p;
-	}
-out:
-	return res;
-}
-
-/*
  * lookup_mnt - Return the first child mount mounted at path
  *
  * "First" means first mounted chronologically.  If you create the
@@ -871,6 +849,13 @@ void mnt_set_mountpoint(struct mount *mnt,
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
+static void __attach_mnt(struct mount *mnt, struct mount *parent)
+{
+	hlist_add_head_rcu(&mnt->mnt_hash,
+			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
+	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -879,28 +864,45 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	__attach_mnt(mnt, parent);
 }
 
-static void attach_shadowed(struct mount *mnt,
-			struct mount *parent,
-			struct mount *shadows)
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
-	if (shadows) {
-		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-		list_add(&mnt->mnt_child, &shadows->mnt_child);
-	} else {
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-	}
+	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
+	struct mount *old_parent = mnt->mnt_parent;
+
+	list_del_init(&mnt->mnt_child);
+	hlist_del_init(&mnt->mnt_mp_list);
+	hlist_del_init_rcu(&mnt->mnt_hash);
+
+	attach_mnt(mnt, parent, mp);
+
+	put_mountpoint(old_mp);
+
+	/*
+	 * Safely avoid even the suggestion this code might sleep or
+	 * lock the mount hash by taking advantage of the knowledge that
+	 * mnt_change_mountpoint will not release the final reference
+	 * to a mountpoint.
+	 *
+	 * During mounting, the mount passed in as the parent mount will
+	 * continue to use the old mountpoint and during unmounting, the
+	 * old mountpoint will continue to exist until namespace_unlock,
+	 * which happens well after mnt_change_mountpoint.
+	 */
+	spin_lock(&old_mountpoint->d_lock);
+	old_mountpoint->d_lockref.count--;
+	spin_unlock(&old_mountpoint->d_lock);
+
+	mnt_add_count(old_parent, -1);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt, struct mount *shadows)
+static void commit_tree(struct mount *mnt)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -918,7 +920,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 	n->mounts += n->pending_mounts;
 	n->pending_mounts = 0;
 
-	attach_shadowed(mnt, parent, shadows);
+	__attach_mnt(mnt, parent);
 	touch_mnt_namespace(n);
 }
 
@@ -1718,7 +1720,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
-			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1740,14 +1741,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			mnt_set_mountpoint(parent, p->mnt_mp, q);
-			if (!list_empty(&parent->mnt_mounts)) {
-				t = list_last_entry(&parent->mnt_mounts,
-					struct mount, mnt_child);
-				if (t->mnt_mp != p->mnt_mp)
-					t = NULL;
-			}
-			attach_shadowed(q, parent, t);
+			attach_mnt(q, parent, p->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -1948,10 +1942,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 {
 	HLIST_HEAD(tree_list);
 	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct mountpoint *smp;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Preallocate a mountpoint in case the new mounts need
+	 * to be tucked under other mounts.
+	 */
+	smp = get_mountpoint(source_mnt->mnt.mnt_root);
+	if (IS_ERR(smp))
+		return PTR_ERR(smp);
+
 	/* Is there space to add these mounts to the mount namespace? */
 	if (!parent_path) {
 		err = count_mounts(ns, source_mnt);
@@ -1978,16 +1980,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt, NULL);
+		commit_tree(source_mnt);
 	}
 
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt_last(&child->mnt_parent->mnt,
-				      child->mnt_mountpoint);
-		commit_tree(child, q);
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
+		commit_tree(child);
 	}
+	put_mountpoint(smp);
 	unlock_mount_hash();
 
 	return 0;
@@ -2002,6 +2007,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	ns->pending_mounts = 0;
+
+	read_seqlock_excl(&mount_lock);
+	put_mountpoint(smp);
+	read_sequnlock_excl(&mount_lock);
+
 	return err;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 319ba6814899..5d8c7e978c33 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2321,6 +2321,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	ret = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto out;
+	ctx->state = state;
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 
@@ -2343,7 +2344,6 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	if (ret != 0)
 		goto out;
 
-	ctx->state = state;
 	if (d_inode(dentry) == state->inode) {
 		nfs_inode_attach_open_context(ctx);
 		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -4556,7 +4556,7 @@ out:
  */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
+	struct page *pages[NFS4ACL_MAXPAGES + 1] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -4570,13 +4570,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1;
 	int ret = -ENOMEM, i;
 
-	/* 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;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0aea97841d30..5069561f8e1e 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2470,7 +2470,7 @@ 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 + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index e4b2b4322553..ea2138726365 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -358,6 +358,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 {
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
+	struct kvec *head = rqstp->rq_arg.head;
 
 	p = decode_fh(p, &args->fh);
 	if (!p)
@@ -367,6 +368,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	args->count = ntohl(*p++);
 	args->stable = ntohl(*p++);
 	len = args->len = ntohl(*p++);
+	if ((void *)p > head->iov_base + head->iov_len)
+		return 0;
 	/*
 	 * The count must equal the amount of data passed.
 	 */
@@ -377,9 +380,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 	/*
 	 * Round the length of the data which was specified up to
 	 * the next multiple of XDR units and then compare that
@@ -396,7 +398,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		len = args->len = max_blocksize;
 	}
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
@@ -471,6 +473,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 	/* first copy and check from the first page */
 	old = (char*)p;
 	vec = &rqstp->rq_arg.head[0];
+	if ((void *)old > vec->iov_base + vec->iov_len)
+		return 0;
 	avail = vec->iov_len - (old - (char*)vec->iov_base);
 	while (len && avail && *old) {
 		*new++ = *old++;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index d8297542f8b3..16fcfdd6011c 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4021,8 +4021,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 		struct nfsd4_getdeviceinfo *gdev)
 {
 	struct xdr_stream *xdr = &resp->xdr;
-	const struct nfsd4_layout_ops *ops =
-		nfsd4_layout_ops[gdev->gd_layout_type];
+	const struct nfsd4_layout_ops *ops;
 	u32 starting_len = xdr->buf->len, needed_len;
 	__be32 *p;
 
@@ -4039,6 +4038,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 	/* If maxcount is 0 then just update notifications */
 	if (gdev->gd_maxcount != 0) {
+		ops = nfsd4_layout_ops[gdev->gd_layout_type];
 		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
 		if (nfserr) {
 			/*
@@ -4091,8 +4091,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
 		struct nfsd4_layoutget *lgp)
 {
 	struct xdr_stream *xdr = &resp->xdr;
-	const struct nfsd4_layout_ops *ops =
-		nfsd4_layout_ops[lgp->lg_layout_type];
+	const struct nfsd4_layout_ops *ops;
 	__be32 *p;
 
 	dprintk("%s: err %d\n", __func__, nfserr);
@@ -4115,6 +4114,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
 	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
 	*p++ = cpu_to_be32(lgp->lg_layout_type);
 
+	ops = nfsd4_layout_ops[lgp->lg_layout_type];
 	nfserr = ops->encode_layoutget(xdr, lgp);
 out:
 	kfree(lgp->lg_content);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9277cc91c21b..c493427e9d69 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -647,6 +647,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
 	return nfserr;
 }
 
+/*
+ * A write procedure can have a large argument, and a read procedure can
+ * have a large reply, but no NFSv2 or NFSv3 procedure has argument and
+ * reply that can both be larger than a page.  The xdr code has taken
+ * advantage of this assumption to be a sloppy about bounds checking in
+ * some cases.  Pending a rewrite of the NFSv2/v3 xdr code to fix that
+ * problem, we enforce these assumptions here:
+ */
+static bool nfs_request_too_big(struct svc_rqst *rqstp,
+				struct svc_procedure *proc)
+{
+	/*
+	 * The ACL code has more careful bounds-checking and is not
+	 * susceptible to this problem:
+	 */
+	if (rqstp->rq_prog != NFS_PROGRAM)
+		return false;
+	/*
+	 * Ditto NFSv4 (which can in theory have argument and reply both
+	 * more than a page):
+	 */
+	if (rqstp->rq_vers >= 4)
+		return false;
+	/* The reply will be small, we're OK: */
+	if (proc->pc_xdrressize > 0 &&
+	    proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE))
+		return false;
+
+	return rqstp->rq_arg.len > PAGE_SIZE;
+}
+
 int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
@@ -659,6 +690,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 				rqstp->rq_vers, rqstp->rq_proc);
 	proc = rqstp->rq_procinfo;
 
+	if (nfs_request_too_big(rqstp, proc)) {
+		dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
+		*statp = rpc_garbage_args;
+		return 1;
+	}
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
 	 * (necessary in the NFSv4.0 compound case)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 79d964aa8079..bf913201a6ad 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd_writeargs *args)
 {
 	unsigned int len, hdr, dlen;
+	struct kvec *head = rqstp->rq_arg.head;
 	int v;
 
 	p = decode_fh(p, &args->fh);
@@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	if (hdr > head->iov_len)
+		return 0;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 
 	/*
 	 * Round the length of the data which was specified up to
@@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		return 0;
 
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
diff --git a/fs/pnode.c b/fs/pnode.c
index 234a9ac49958..b394ca5307ec 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -324,6 +324,21 @@ out:
 	return ret;
 }
 
+static struct mount *find_topper(struct mount *mnt)
+{
+	/* If there is exactly one mount covering mnt completely return it. */
+	struct mount *child;
+
+	if (!list_is_singular(&mnt->mnt_mounts))
+		return NULL;
+
+	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
+	if (child->mnt_mountpoint != mnt->mnt.mnt_root)
+		return NULL;
+
+	return child;
+}
+
 /*
  * return true if the refcount is greater than count
  */
@@ -344,9 +359,8 @@ static inline int do_refcount_check(struct mount *mnt, int count)
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
-	struct mount *m, *child;
+	struct mount *m, *child, *topper;
 	struct mount *parent = mnt->mnt_parent;
-	int ret = 0;
 
 	if (mnt == parent)
 		return do_refcount_check(mnt, refcnt);
@@ -361,12 +375,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 
 	for (m = propagation_next(parent, parent); m;
 	     		m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-		if (child && list_empty(&child->mnt_mounts) &&
-		    (ret = do_refcount_check(child, 1)))
-			break;
+		int count = 1;
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
+		if (!child)
+			continue;
+
+		/* Is there exactly one mount on the child that covers
+		 * it completely whose reference should be ignored?
+		 */
+		topper = find_topper(child);
+		if (topper)
+			count += 1;
+		else if (!list_empty(&child->mnt_mounts))
+			continue;
+
+		if (do_refcount_check(child, count))
+			return 1;
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -383,7 +409,7 @@ void propagate_mount_unlock(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
 		if (child)
 			child->mnt.mnt_flags &= ~MNT_LOCKED;
 	}
@@ -401,9 +427,11 @@ static void mark_umount_candidates(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt_last(&m->mnt,
+		struct mount *child = __lookup_mnt(&m->mnt,
 						mnt->mnt_mountpoint);
-		if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) {
+		if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
+			continue;
+		if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
 			SET_MNT_MARK(child);
 		}
 	}
@@ -422,8 +450,8 @@ static void __propagate_umount(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-
-		struct mount *child = __lookup_mnt_last(&m->mnt,
+		struct mount *topper;
+		struct mount *child = __lookup_mnt(&m->mnt,
 						mnt->mnt_mountpoint);
 		/*
 		 * umount the child only if the child has no children
@@ -432,6 +460,15 @@ static void __propagate_umount(struct mount *mnt)
 		if (!child || !IS_MNT_MARKED(child))
 			continue;
 		CLEAR_MNT_MARK(child);
+
+		/* If there is exactly one mount covering all of child
+		 * replace child with that mount.
+		 */
+		topper = find_topper(child);
+		if (topper)
+			mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
+					      topper);
+
 		if (list_empty(&child->mnt_mounts)) {
 			list_del_init(&child->mnt_child);
 			child->mnt.mnt_flags |= MNT_UMOUNT;
diff --git a/fs/pnode.h b/fs/pnode.h
index 550f5a8b4fcf..dc87e65becd2 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root);
 unsigned int mnt_get_count(struct mount *mnt);
 void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 			struct mount *);
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
+			   struct mount *mnt);
 struct mount *copy_tree(struct mount *, struct dentry *, int);
 bool is_path_reachable(struct mount *, struct dentry *,
 			 const struct path *root);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index d99099fe62d4..709586995b46 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -469,6 +469,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
 		ent->data = NULL;
 		ent->proc_fops = NULL;
 		ent->proc_iops = NULL;
+		parent->nlink++;
 		if (proc_register(parent, ent) < 0) {
 			kfree(ent);
 			parent->nlink--;
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 167f80e8f08d..5bccdf684765 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	struct kobject *kobj = of->kn->parent->priv;
-	size_t len;
+	ssize_t len;
 
 	/*
 	 * If buf != of->prealloc_buf, we don't know how
@@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 	if (WARN_ON_ONCE(buf != of->prealloc_buf))
 		return 0;
 	len = ops->show(kobj, of->kn->priv, buf);
+	if (len < 0)
+		return len;
 	if (pos) {
 		if (len <= pos)
 			return 0;
 		len -= pos;
 		memmove(buf, buf + pos, len);
 	}
-	return min(count, len);
+	return min_t(ssize_t, count, len);
 }
 
 /* kernfs write callback for regular sysfs files */
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b94fa6c3c6eb..16356867adf0 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -40,6 +40,7 @@ struct timerfd_ctx {
 	short unsigned settime_flags;	/* to show in fdinfo */
 	struct rcu_head rcu;
 	struct list_head clist;
+	spinlock_t cancel_lock;
 	bool might_cancel;
 };
 
@@ -112,7 +113,7 @@ void timerfd_clock_was_set(void)
 	rcu_read_unlock();
 }
 
-static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
 {
 	if (ctx->might_cancel) {
 		ctx->might_cancel = false;
@@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
 	}
 }
 
+static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+{
+	spin_lock(&ctx->cancel_lock);
+	__timerfd_remove_cancel(ctx);
+	spin_unlock(&ctx->cancel_lock);
+}
+
 static bool timerfd_canceled(struct timerfd_ctx *ctx)
 {
 	if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX)
@@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx)
 
 static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 {
+	spin_lock(&ctx->cancel_lock);
 	if ((ctx->clockid == CLOCK_REALTIME ||
 	     ctx->clockid == CLOCK_REALTIME_ALARM) &&
 	    (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
@@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 			list_add_rcu(&ctx->clist, &cancel_list);
 			spin_unlock(&cancel_lock);
 		}
-	} else if (ctx->might_cancel) {
-		timerfd_remove_cancel(ctx);
+	} else {
+		__timerfd_remove_cancel(ctx);
 	}
+	spin_unlock(&ctx->cancel_lock);
 }
 
 static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
@@ -395,6 +405,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 		return -ENOMEM;
 
 	init_waitqueue_head(&ctx->wqh);
+	spin_lock_init(&ctx->cancel_lock);
 	ctx->clockid = clockid;
 
 	if (isalarm(ctx))
diff --git a/fs/xattr.c b/fs/xattr.c
index 4ef698549e31..81d4695a6115 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -442,7 +442,7 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 			size = XATTR_SIZE_MAX;
 		kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!kvalue) {
-			vvalue = vmalloc(size);
+			vvalue = vzalloc(size);
 			if (!vvalue)
 				return -ENOMEM;
 			kvalue = vvalue;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 550f8c4733ee..28cf809a855c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1170,7 +1170,7 @@ xfs_find_get_desired_pgoff(
 		unsigned	nr_pages;
 		unsigned int	i;
 
-		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  want);
 		/*
@@ -1197,17 +1197,6 @@ xfs_find_get_desired_pgoff(
 			break;
 		}
 
-		/*
-		 * At lease we found one page.  If this is the first time we
-		 * step into the loop, and if the first page index offset is
-		 * greater than the given search offset, a hole was found.
-		 */
-		if (type == HOLE_OFF && lastoff == startoff &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = true;
-			break;
-		}
-
 		for (i = 0; i < nr_pages; i++) {
 			struct page	*page = pvec.pages[i];
 			loff_t		b_offset;
@@ -1219,18 +1208,18 @@ xfs_find_get_desired_pgoff(
 			 * file mapping. However, page->index will not change
 			 * because we have a reference on the page.
 			 *
-			 * Searching done if the page index is out of range.
-			 * If the current offset is not reaches the end of
-			 * the specified search range, there should be a hole
-			 * between them.
+			 * If current page offset is beyond where we've ended,
+			 * we've found a hole.
 			 */
-			if (page->index > end) {
-				if (type == HOLE_OFF && lastoff < endoff) {
-					*offset = lastoff;
-					found = true;
-				}
+			if (type == HOLE_OFF && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
+				found = true;
+				*offset = lastoff;
 				goto out;
 			}
+			/* Searching done if the page index is out of range. */
+			if (page->index > end)
+				goto out;
 
 			lock_page(page);
 			/*