Merge tag 'v4.1.43' into 4.1-2.0.x-imx

Linux 4.1.43

* tag 'v4.1.43': (182 commits)
  Linux 4.1.43
  HID: core: prevent out-of-bound readings
  ipvs: SNAT packet replies only for NATed connections
  Revert "dmaengine: ep93xx: Don't drain the transfers in terminate_all()"
  staging: comedi: ni_mio_common: fix E series ni_ai_insn_read() data
  kvm: vmx: Do not disable intercepts for BNDCFGS
  tracing: Use SOFTIRQ_OFFSET for softirq dectection for more accurate results
  PM / QoS: return -EINVAL for bogus strings
  sched/topology: Optimize build_group_mask()
  sched/topology: Fix overlapping sched_group_mask
  crypto: caam - fix signals handling
  crypto: atmel - only treat EBUSY as transient if backlog
  crypto: talitos - Extend max key length for SHA384/512-HMAC and AEAD
  Add "shutdown" to "struct class".
  mnt: Make propagate_umount less slow for overlapping mount propagation trees
  mnt: In propgate_umount handle visiting mounts in any order
  mnt: In umount propagation reparent in a separate pass
  vt: fix unchecked __put_user() in tioclinux ioctls
  exec: Limit arg stack to at most 75% of _STK_LIM
  s390: reduce ELF_ET_DYN_BASE
  ...

20 files changed, 356 insertions, 102 deletions

diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ac7d921ed984..257425511d10 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -331,7 +331,7 @@ static int autofs_dev_ioctl_fail(struct file *fp,
 	int status;
 
 	token = (autofs_wqt_t) param->fail.token;
-	status = param->fail.status ? param->fail.status : -ENOENT;
+	status = param->fail.status < 0 ? param->fail.status : -ENOENT;
 	return autofs4_wait_release(sbi, token, status);
 }
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index cd46e4158830..90f20f8ce87e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -904,17 +904,60 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
 
 		vaddr = elf_ppnt->p_vaddr;
+		/*
+		 * If we are loading ET_EXEC or we have already performed
+		 * the ET_DYN load_addr calculations, proceed normally.
+		 */
 		if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
 			elf_flags |= MAP_FIXED;
 		} else if (loc->elf_ex.e_type == ET_DYN) {
-			/* Try and get dynamic programs out of the way of the
-			 * default mmap base, as well as whatever program they
-			 * might try to exec.  This is because the brk will
-			 * follow the loader, and is not movable.  */
-			load_bias = ELF_ET_DYN_BASE - vaddr;
-			if (current->flags & PF_RANDOMIZE)
-				load_bias += arch_mmap_rnd();
-			load_bias = ELF_PAGESTART(load_bias);
+			/*
+			 * This logic is run once for the first LOAD Program
+			 * Header for ET_DYN binaries to calculate the
+			 * randomization (load_bias) for all the LOAD
+			 * Program Headers, and to calculate the entire
+			 * size of the ELF mapping (total_size). (Note that
+			 * load_addr_set is set to true later once the
+			 * initial mapping is performed.)
+			 *
+			 * There are effectively two types of ET_DYN
+			 * binaries: programs (i.e. PIE: ET_DYN with INTERP)
+			 * and loaders (ET_DYN without INTERP, since they
+			 * _are_ the ELF interpreter). The loaders must
+			 * be loaded away from programs since the program
+			 * may otherwise collide with the loader (especially
+			 * for ET_EXEC which does not have a randomized
+			 * position). For example to handle invocations of
+			 * "./ld.so someprog" to test out a new version of
+			 * the loader, the subsequent program that the
+			 * loader loads must avoid the loader itself, so
+			 * they cannot share the same load range. Sufficient
+			 * room for the brk must be allocated with the
+			 * loader as well, since brk must be available with
+			 * the loader.
+			 *
+			 * Therefore, programs are loaded offset from
+			 * ELF_ET_DYN_BASE and loaders are loaded into the
+			 * independently randomized mmap region (0 load_bias
+			 * without MAP_FIXED).
+			 */
+			if (elf_interpreter) {
+				load_bias = ELF_ET_DYN_BASE;
+				if (current->flags & PF_RANDOMIZE)
+					load_bias += arch_mmap_rnd();
+				elf_flags |= MAP_FIXED;
+			} else
+				load_bias = 0;
+
+			/*
+			 * Since load_bias is used for all subsequent loading
+			 * calculations, we must lower it by the first vaddr
+			 * so that the remaining calculations based on the
+			 * ELF vaddrs will be correctly offset. The result
+			 * is then page aligned.
+			 */
+			load_bias = ELF_PAGESTART(load_bias - vaddr);
+
 			total_size = total_mapping_size(elf_phdata,
 							loc->elf_ex.e_phnum);
 			if (!total_size) {
@@ -2285,6 +2328,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 				goto end_coredump;
 		}
 	}
+	dump_truncate(cprm);
 
 	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 04997ac958c4..db6115486166 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4358,8 +4358,19 @@ search_again:
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size)
+			if (item_end < new_size) {
+				/*
+				 * With NO_HOLES mode, for the following mapping
+				 *
+				 * [0-4k][hole][8k-12k]
+				 *
+				 * if truncating isize down to 6k, it ends up
+				 * isize being 8k.
+				 */
+				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+					last_size = new_size;
 				break;
+			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 7d7bd466520b..cb3406815330 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -401,6 +401,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		}
 	} while (server->tcpStatus == CifsNeedReconnect);
 
+	if (server->tcpStatus == CifsNeedNegotiate)
+		mod_delayed_work(cifsiod_wq, &server->echo, 0);
+
 	return rc;
 }
 
@@ -410,18 +413,27 @@ cifs_echo_request(struct work_struct *work)
 	int rc;
 	struct TCP_Server_Info *server = container_of(work,
 					struct TCP_Server_Info, echo.work);
+	unsigned long echo_interval;
+
+	/*
+	 * If we need to renegotiate, set echo interval to zero to
+	 * immediately call echo service where we can renegotiate.
+	 */
+	if (server->tcpStatus == CifsNeedNegotiate)
+		echo_interval = 0;
+	else
+		echo_interval = SMB_ECHO_INTERVAL;
 
 	/*
-	 * We cannot send an echo if it is disabled or until the
-	 * NEGOTIATE_PROTOCOL request is done, which is indicated by
-	 * server->ops->need_neg() == true. Also, no need to ping if
-	 * we got a response recently.
+	 * We cannot send an echo if it is disabled.
+	 * Also, no need to ping if we got a response recently.
 	 */
 
 	if (server->tcpStatus == CifsNeedReconnect ||
-	    server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
+	    server->tcpStatus == CifsExiting ||
+	    server->tcpStatus == CifsNew ||
 	    (server->ops->can_echo && !server->ops->can_echo(server)) ||
-	    time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
+	    time_before(jiffies, server->lstrp + echo_interval - HZ))
 		goto requeue_echo;
 
 	rc = server->ops->echo ? server->ops->echo(server) : -ENOSYS;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 87b87e091e8e..efd72e1fae74 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -849,8 +849,13 @@ cifs_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 		     struct cifs_fid *fid, __u16 search_flags,
 		     struct cifs_search_info *srch_inf)
 {
-	return CIFSFindFirst(xid, tcon, path, cifs_sb,
-			     &fid->netfid, search_flags, srch_inf, true);
+	int rc;
+
+	rc = CIFSFindFirst(xid, tcon, path, cifs_sb,
+			   &fid->netfid, search_flags, srch_inf, true);
+	if (rc)
+		cifs_dbg(FYI, "find first failed=%d\n", rc);
+	return rc;
 }
 
 static int
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 57aeae6116d6..16212dab81d5 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -843,7 +843,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
 	kfree(utf16_path);
 	if (rc) {
-		cifs_dbg(VFS, "open dir failed\n");
+		cifs_dbg(FYI, "open dir failed rc=%d\n", rc);
 		return rc;
 	}
 
@@ -853,7 +853,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_query_directory(xid, tcon, fid->persistent_fid,
 				  fid->volatile_fid, 0, srch_inf);
 	if (rc) {
-		cifs_dbg(VFS, "query directory failed\n");
+		cifs_dbg(FYI, "query directory failed rc=%d\n", rc);
 		SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
 	}
 	return rc;
diff --git a/fs/coredump.c b/fs/coredump.c
index 26d05e3bc6db..e07cbb629f1c 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -803,3 +803,21 @@ int dump_align(struct coredump_params *cprm, int align)
 	return mod ? dump_skip(cprm, align - mod) : 1;
 }
 EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+	struct file *file = cprm->file;
+	loff_t offset;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		offset = file->f_op->llseek(file, 0, SEEK_CUR);
+		if (i_size_read(file->f_mapping->host) < offset)
+			do_truncate(file->f_path.dentry, offset, 0, file);
+	}
+}
+EXPORT_SYMBOL(dump_truncate);
diff --git a/fs/dcache.c b/fs/dcache.c
index 11d466bbfb0b..5ca8f0b2b897 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1128,11 +1128,12 @@ void shrink_dcache_sb(struct super_block *sb)
 		LIST_HEAD(dispose);
 
 		freed = list_lru_walk(&sb->s_dentry_lru,
-			dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+			dentry_lru_isolate_shrink, &dispose, 1024);
 
 		this_cpu_sub(nr_dentry_unused, freed);
 		shrink_dentry_list(&dispose);
-	} while (freed > 0);
+		cond_resched();
+	} while (list_lru_count(&sb->s_dentry_lru) > 0);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
diff --git a/fs/exec.c b/fs/exec.c
index 04c9cab4d4d3..3ba35c21726e 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -199,7 +199,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 
 	if (write) {
 		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
-		struct rlimit *rlim;
+		unsigned long ptr_size, limit;
+
+		/*
+		 * Since the stack will hold pointers to the strings, we
+		 * must account for them as well.
+		 *
+		 * The size calculation is the entire vma while each arg page is
+		 * built, so each time we get here it's calculating how far it
+		 * is currently (rather than each call being just the newly
+		 * added size from the arg page).  As a result, we need to
+		 * always add the entire size of the pointers, so that on the
+		 * last call to get_arg_page() we'll actually have the entire
+		 * correct size.
+		 */
+		ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+		if (ptr_size > ULONG_MAX - size)
+			goto fail;
+		size += ptr_size;
 
 		acct_arg_size(bprm, size / PAGE_SIZE);
 
@@ -211,20 +228,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return page;
 
 		/*
-		 * Limit to 1/4-th the stack size for the argv+env strings.
+		 * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
+		 * (whichever is smaller) for the argv+env strings.
 		 * This ensures that:
 		 *  - the remaining binfmt code will not run out of stack space,
 		 *  - the program will have a reasonable amount of stack left
 		 *    to work from.
 		 */
-		rlim = current->signal->rlim;
-		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
-			put_page(page);
-			return NULL;
-		}
+		limit = _STK_LIM / 4 * 3;
+		limit = min(limit, rlimit(RLIMIT_STACK) / 4);
+		if (size > limit)
+			goto fail;
 	}
 
 	return page;
+
+fail:
+	put_page(page);
+	return NULL;
 }
 
 static void put_arg_page(struct page *page)
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ee85cd4e136a..62376451bbce 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,16 +740,10 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
-		O_RDONLY	| O_WRONLY	| O_RDWR	|
-		O_CREAT		| O_EXCL	| O_NOCTTY	|
-		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
-		__O_SYNC	| O_DSYNC	| FASYNC	|
-		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
-		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
-		__FMODE_NONOTIFY
-		));
+	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+		HWEIGHT32(
+			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
+			__FMODE_EXEC | __FMODE_NONOTIFY));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
 		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
diff --git a/fs/mount.h b/fs/mount.h
index 32cabd55a787..bae2b0943019 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -57,6 +57,7 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct hlist_head mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
diff --git a/fs/namespace.c b/fs/namespace.c
index df20ee946f7c..58b281ad30d5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -237,6 +237,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
+		INIT_LIST_HEAD(&mnt->mnt_umounting);
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index aadb4af4a0fe..b6d97dfa9cb6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2446,6 +2446,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
 }
 EXPORT_SYMBOL_GPL(nfs_may_open);
 
+static int nfs_execute_ok(struct inode *inode, int mask)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		ret = nfs_revalidate_inode_rcu(server, inode);
+	else
+		ret = nfs_revalidate_inode(server, inode);
+	if (ret == 0 && !execute_ok(inode))
+		ret = -EACCES;
+	return ret;
+}
+
 int nfs_permission(struct inode *inode, int mask)
 {
 	struct rpc_cred *cred;
@@ -2463,6 +2477,9 @@ int nfs_permission(struct inode *inode, int mask)
 		case S_IFLNK:
 			goto out;
 		case S_IFREG:
+			if ((mask & MAY_OPEN) &&
+			   nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN))
+				return 0;
 			break;
 		case S_IFDIR:
 			/*
@@ -2495,8 +2512,8 @@ force_lookup:
 			res = PTR_ERR(cred);
 	}
 out:
-	if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
-		res = -EACCES;
+	if (!res && (mask & MAY_EXEC))
+		res = nfs_execute_ok(inode, mask);
 
 	dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
 		inode->i_sb->s_id, inode->i_ino, mask, res);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5d8c7e978c33..f06af7248be7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2068,8 +2068,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
 		return 0;
 
-	/* even though OPEN succeeded, access is denied. Close the file */
-	nfs4_close_state(state, fmode);
 	return -EACCES;
 }
 
diff --git a/fs/open.c b/fs/open.c
index ff80b2542989..d0169e52d7fe 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -881,6 +881,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 	int lookup_flags = 0;
 	int acc_mode;
 
+	/*
+	 * Clear out all open flags we don't know about so that we don't report
+	 * them in fcntl(F_GETFD) or similar interfaces.
+	 */
+	flags &= VALID_OPEN_FLAGS;
+
 	if (flags & (O_CREAT | __O_TMPFILE))
 		op->mode = (mode & S_IALLUGO) | S_IFREG;
 	else
diff --git a/fs/pnode.c b/fs/pnode.c
index b394ca5307ec..d15c63e97ef1 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p)
 	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
 }
 
+static inline struct mount *last_slave(struct mount *p)
+{
+	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+}
+
 static inline struct mount *next_slave(struct mount *p)
 {
 	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
@@ -164,6 +169,19 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
+static struct mount *skip_propagation_subtree(struct mount *m,
+						struct mount *origin)
+{
+	/*
+	 * Advance m such that propagation_next will not return
+	 * the slaves of m.
+	 */
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+		m = last_slave(m);
+
+	return m;
+}
+
 static struct mount *next_group(struct mount *m, struct mount *origin)
 {
 	while (1) {
@@ -415,65 +433,104 @@ void propagate_mount_unlock(struct mount *mnt)
 	}
 }
 
-/*
- * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
- */
-static void mark_umount_candidates(struct mount *mnt)
+static void umount_one(struct mount *mnt, struct list_head *to_umount)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-
-	BUG_ON(parent == mnt);
-
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt(&m->mnt,
-						mnt->mnt_mountpoint);
-		if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
-			continue;
-		if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
-			SET_MNT_MARK(child);
-		}
-	}
+	CLEAR_MNT_MARK(mnt);
+	mnt->mnt.mnt_flags |= MNT_UMOUNT;
+	list_del_init(&mnt->mnt_child);
+	list_del_init(&mnt->mnt_umounting);
+	list_move_tail(&mnt->mnt_list, to_umount);
 }
 
 /*
  * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
  * parent propagates to.
  */
-static void __propagate_umount(struct mount *mnt)
+static bool __propagate_umount(struct mount *mnt,
+			       struct list_head *to_umount,
+			       struct list_head *to_restore)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
+	bool progress = false;
+	struct mount *child;
 
-	BUG_ON(parent == mnt);
+	/*
+	 * The state of the parent won't change if this mount is
+	 * already unmounted or marked as without children.
+	 */
+	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
+		goto out;
 
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
-		struct mount *topper;
-		struct mount *child = __lookup_mnt(&m->mnt,
-						mnt->mnt_mountpoint);
-		/*
-		 * umount the child only if the child has no children
-		 * and the child is marked safe to unmount.
-		 */
-		if (!child || !IS_MNT_MARKED(child))
+	/* Verify topper is the only grandchild that has not been
+	 * speculatively unmounted.
+	 */
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
 			continue;
-		CLEAR_MNT_MARK(child);
+		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
+			continue;
+		/* Found a mounted child */
+		goto children;
+	}
 
-		/* 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);
+	/* Mark mounts that can be unmounted if not locked */
+	SET_MNT_MARK(mnt);
+	progress = true;
+
+	/* If a mount is without children and not locked umount it. */
+	if (!IS_MNT_LOCKED(mnt)) {
+		umount_one(mnt, to_umount);
+	} else {
+children:
+		list_move_tail(&mnt->mnt_umounting, to_restore);
+	}
+out:
+	return progress;
+}
+
+static void umount_list(struct list_head *to_umount,
+			struct list_head *to_restore)
+{
+	struct mount *mnt, *child, *tmp;
+	list_for_each_entry(mnt, to_umount, mnt_list) {
+		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
+			/* topper? */
+			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
+				list_move_tail(&child->mnt_umounting, to_restore);
+			else
+				umount_one(child, to_umount);
+		}
+	}
+}
 
-		if (list_empty(&child->mnt_mounts)) {
-			list_del_init(&child->mnt_child);
-			child->mnt.mnt_flags |= MNT_UMOUNT;
-			list_move_tail(&child->mnt_list, &mnt->mnt_list);
+static void restore_mounts(struct list_head *to_restore)
+{
+	/* Restore mounts to a clean working state */
+	while (!list_empty(to_restore)) {
+		struct mount *mnt, *parent;
+		struct mountpoint *mp;
+
+		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
+		CLEAR_MNT_MARK(mnt);
+		list_del_init(&mnt->mnt_umounting);
+
+		/* Should this mount be reparented? */
+		mp = mnt->mnt_mp;
+		parent = mnt->mnt_parent;
+		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+			mp = parent->mnt_mp;
+			parent = parent->mnt_parent;
 		}
+		if (parent != mnt->mnt_parent)
+			mnt_change_mountpoint(parent, mp, mnt);
+	}
+}
+
+static void cleanup_umount_visitations(struct list_head *visited)
+{
+	while (!list_empty(visited)) {
+		struct mount *mnt =
+			list_first_entry(visited, struct mount, mnt_umounting);
+		list_del_init(&mnt->mnt_umounting);
 	}
 }
 
@@ -487,11 +544,68 @@ static void __propagate_umount(struct mount *mnt)
 int propagate_umount(struct list_head *list)
 {
 	struct mount *mnt;
+	LIST_HEAD(to_restore);
+	LIST_HEAD(to_umount);
+	LIST_HEAD(visited);
+
+	/* Find candidates for unmounting */
+	list_for_each_entry_reverse(mnt, list, mnt_list) {
+		struct mount *parent = mnt->mnt_parent;
+		struct mount *m;
+
+		/*
+		 * If this mount has already been visited it is known that it's
+		 * entire peer group and all of their slaves in the propagation
+		 * tree for the mountpoint has already been visited and there is
+		 * no need to visit them again.
+		 */
+		if (!list_empty(&mnt->mnt_umounting))
+			continue;
+
+		list_add_tail(&mnt->mnt_umounting, &visited);
+		for (m = propagation_next(parent, parent); m;
+		     m = propagation_next(m, parent)) {
+			struct mount *child = __lookup_mnt(&m->mnt,
+							   mnt->mnt_mountpoint);
+			if (!child)
+				continue;
+
+			if (!list_empty(&child->mnt_umounting)) {
+				/*
+				 * If the child has already been visited it is
+				 * know that it's entire peer group and all of
+				 * their slaves in the propgation tree for the
+				 * mountpoint has already been visited and there
+				 * is no need to visit this subtree again.
+				 */
+				m = skip_propagation_subtree(m, parent);
+				continue;
+			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
+				/*
+				 * We have come accross an partially unmounted
+				 * mount in list that has not been visited yet.
+				 * Remember it has been visited and continue
+				 * about our merry way.
+				 */
+				list_add_tail(&child->mnt_umounting, &visited);
+				continue;
+			}
+
+			/* Check the child and parents while progress is made */
+			while (__propagate_umount(child,
+						  &to_umount, &to_restore)) {
+				/* Is the parent a umount candidate? */
+				child = child->mnt_parent;
+				if (list_empty(&child->mnt_umounting))
+					break;
+			}
+		}
+	}
 
-	list_for_each_entry_reverse(mnt, list, mnt_list)
-		mark_umount_candidates(mnt);
+	umount_list(&to_umount, &to_restore);
+	restore_mounts(&to_restore);
+	cleanup_umount_visitations(&visited);
+	list_splice_tail(&to_umount, list);
 
-	list_for_each_entry(mnt, list, mnt_list)
-		__propagate_umount(mnt);
 	return 0;
 }
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index dd4824589470..234331227c0c 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -112,6 +112,7 @@ typedef struct attrlist_cursor_kern {
  *========================================================================*/
 
 
+/* Return 0 on success, or -errno; other state communicated via *context */
 typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, int,
 			      unsigned char *, int, int, unsigned char *);
 
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 8f7e09d0d0f0..36db8b21969f 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -108,16 +108,14 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 					   (int)sfe->namelen,
 					   (int)sfe->valuelen,
 					   &sfe->nameval[sfe->namelen]);
-
+			if (error)
+				return error;
 			/*
 			 * Either search callback finished early or
 			 * didn't fit it all in the buffer after all.
 			 */
 			if (context->seen_enough)
 				break;
-
-			if (error)
-				return error;
 			sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
 		}
 		trace_xfs_attr_list_sf_all(context);
@@ -581,7 +579,7 @@ xfs_attr_put_listent(
 		trace_xfs_attr_list_full(context);
 		alist->al_more = 1;
 		context->seen_enough = 1;
-		return 1;
+		return 0;
 	}
 
 	aep = (attrlist_ent_t *)&context->alist[context->firstu];
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index e69a0899bc05..3b7985991823 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -402,6 +402,7 @@ xfs_attrlist_by_handle(
 {
 	int			error = -ENOMEM;
 	attrlist_cursor_kern_t	*cursor;
+	struct xfs_fsop_attrlist_handlereq __user	*p = arg;
 	xfs_fsop_attrlist_handlereq_t al_hreq;
 	struct dentry		*dentry;
 	char			*kbuf;
@@ -434,6 +435,11 @@ xfs_attrlist_by_handle(
 	if (error)
 		goto out_kfree;
 
+	if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) {
+		error = -EFAULT;
+		goto out_kfree;
+	}
+
 	if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
 		error = -EFAULT;
 
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index c036815183cb..ead53c933de6 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -151,7 +151,8 @@ xfs_xattr_put_listent(
 	arraytop = context->count + prefix_len + namelen + 1;
 	if (arraytop > context->firstu) {
 		context->count = -1;	/* insufficient space */
-		return 1;
+		context->seen_enough = 1;
+		return 0;
 	}
 	offset = (char *)context->alist + context->count;
 	strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
@@ -193,12 +194,15 @@ list_one_attr(const char *name, const size_t len, void *data,
 }
 
 ssize_t
-xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
+xfs_vn_listxattr(
+	struct dentry	*dentry,
+	char		*data,
+	size_t		size)
 {
 	struct xfs_attr_list_context context;
 	struct attrlist_cursor_kern cursor = { 0 };
-	struct inode		*inode = d_inode(dentry);
-	int			error;
+	struct inode	*inode = d_inode(dentry);
+	int		error;
 
 	/*
 	 * First read the regular on-disk attributes.
@@ -216,7 +220,9 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
 	else
 		context.put_listent = xfs_xattr_put_listent_sizes;
 
-	xfs_attr_list_int(&context);
+	error = xfs_attr_list_int(&context);
+	if (error)
+		return error;
 	if (context.count < 0)
 		return -ERANGE;