Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

A set of overlapping changes in macvlan and the rocker
driver, nothing serious.

Signed-off-by: David S. Miller <davem@davemloft.net>

16 files changed, 95 insertions, 57 deletions

diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 734cbf8d9676..dd9f1bebb5a3 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -344,7 +344,7 @@ 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/block_dev.c b/fs/block_dev.c
index 519599dddd36..0a7404ef9335 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -263,7 +263,10 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		kfree(vecs);
 
 	if (unlikely(bio.bi_error))
-		return bio.bi_error;
+		ret = bio.bi_error;
+
+	bio_uninit(&bio);
+
 	return ret;
 }
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0fd081bd2a2f..fcef70602b27 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3271,7 +3271,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
 	if (!is_sync_kiocb(iocb))
 		ctx->iocb = iocb;
 
-	if (to->type & ITER_IOVEC)
+	if (to->type == ITER_IOVEC)
 		ctx->should_dirty = true;
 
 	rc = setup_aio_ctx_iter(ctx, to, READ);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index b08531977daa..3b147dc6af63 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -810,7 +810,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
 
 	if (!pages) {
 		pages = vmalloc(max_pages * sizeof(struct page *));
-		if (!bv) {
+		if (!pages) {
 			kvfree(bv);
 			return -ENOMEM;
 		}
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 27bc360c7ffd..a723df3e0197 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 c58691834eb2..7e48561abd29 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -982,7 +982,7 @@ 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;
 	}
 
@@ -992,7 +992,7 @@ 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;
@@ -1809,7 +1809,8 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 
 	sg = init_sg(rqst, sign);
 	if (!sg) {
-		cifs_dbg(VFS, "%s: Failed to init sg %d", __func__, rc);
+		cifs_dbg(VFS, "%s: Failed to init sg", __func__);
+		rc = -ENOMEM;
 		goto free_req;
 	}
 
@@ -1817,6 +1818,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 	iv = kzalloc(iv_len, GFP_KERNEL);
 	if (!iv) {
 		cifs_dbg(VFS, "%s: Failed to alloc IV", __func__);
+		rc = -ENOMEM;
 		goto free_sg;
 	}
 	iv[0] = 3;
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 3cb5c9e2d4e7..de50e749ff05 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -188,8 +188,6 @@ static int cifs_creation_time_get(struct dentry *dentry, struct inode *inode,
 	pcreatetime = (__u64 *)value;
 	*pcreatetime = CIFS_I(inode)->createtime;
 	return sizeof(__u64);
-
-	return rc;
 }
 
 
diff --git a/fs/dax.c b/fs/dax.c
index 2a6889b3585f..9187f3b07f3e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -859,6 +859,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 			if (ret < 0)
 				goto out;
 		}
+		start_index = indices[pvec.nr - 1] + 1;
 	}
 out:
 	put_dax(dax_dev);
diff --git a/fs/exec.c b/fs/exec.c
index 72934df68471..904199086490 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -220,8 +220,26 @@ 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;
+		unsigned long ptr_size;
 		struct rlimit *rlim;
 
+		/*
+		 * 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);
 
 		/*
@@ -239,13 +257,15 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 		 *    to work from.
 		 */
 		rlim = current->signal->rlim;
-		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
-			put_page(page);
-			return NULL;
-		}
+		if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4)
+			goto fail;
 	}
 
 	return page;
+
+fail:
+	put_page(page);
+	return NULL;
 }
 
 static void put_arg_page(struct page *page)
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index c14758e08d73..390ac9c39c59 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -753,7 +753,6 @@ static void nfs4_callback_free_slot(struct nfs4_session *session,
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
 	nfs4_free_slot(tbl, slot);
-	nfs4_slot_tbl_drain_complete(tbl);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 32ccd7754f8a..2ac00bf4ecf1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1946,29 +1946,6 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(nfs_link);
 
-static void
-nfs_complete_rename(struct rpc_task *task, struct nfs_renamedata *data)
-{
-	struct dentry *old_dentry = data->old_dentry;
-	struct dentry *new_dentry = data->new_dentry;
-	struct inode *old_inode = d_inode(old_dentry);
-	struct inode *new_inode = d_inode(new_dentry);
-
-	nfs_mark_for_revalidate(old_inode);
-
-	switch (task->tk_status) {
-	case 0:
-		if (new_inode != NULL)
-			nfs_drop_nlink(new_inode);
-		d_move(old_dentry, new_dentry);
-		nfs_set_verifier(new_dentry,
-					nfs_save_change_attribute(data->new_dir));
-		break;
-	case -ENOENT:
-		nfs_dentry_handle_enoent(old_dentry);
-	}
-}
-
 /*
  * RENAME
  * FIXME: Some nfsds, like the Linux user space nfsd, may generate a
@@ -1999,7 +1976,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
 	struct inode *old_inode = d_inode(old_dentry);
 	struct inode *new_inode = d_inode(new_dentry);
-	struct dentry *dentry = NULL;
+	struct dentry *dentry = NULL, *rehash = NULL;
 	struct rpc_task *task;
 	int error = -EBUSY;
 
@@ -2022,8 +1999,10 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 * To prevent any new references to the target during the
 		 * rename, we unhash the dentry in advance.
 		 */
-		if (!d_unhashed(new_dentry))
+		if (!d_unhashed(new_dentry)) {
 			d_drop(new_dentry);
+			rehash = new_dentry;
+		}
 
 		if (d_count(new_dentry) > 2) {
 			int err;
@@ -2040,6 +2019,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				goto out;
 
 			new_dentry = dentry;
+			rehash = NULL;
 			new_inode = NULL;
 		}
 	}
@@ -2048,8 +2028,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (new_inode != NULL)
 		NFS_PROTO(new_inode)->return_delegation(new_inode);
 
-	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
-					nfs_complete_rename);
+	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL);
 	if (IS_ERR(task)) {
 		error = PTR_ERR(task);
 		goto out;
@@ -2059,9 +2038,27 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (error == 0)
 		error = task->tk_status;
 	rpc_put_task(task);
+	nfs_mark_for_revalidate(old_inode);
 out:
+	if (rehash)
+		d_rehash(rehash);
 	trace_nfs_rename_exit(old_dir, old_dentry,
 			new_dir, new_dentry, error);
+	if (!error) {
+		if (new_inode != NULL)
+			nfs_drop_nlink(new_inode);
+		/*
+		 * The d_move() should be here instead of in an async RPC completion
+		 * handler because we need the proper locks to move the dentry.  If
+		 * we're interrupted by a signal, the async RPC completion handler
+		 * should mark the directories for revalidation.
+		 */
+		d_move(old_dentry, new_dentry);
+		nfs_set_verifier(new_dentry,
+					nfs_save_change_attribute(new_dir));
+	} else if (error == -ENOENT)
+		nfs_dentry_handle_enoent(old_dentry);
+
 	/* new dentry created? */
 	if (dentry)
 		dput(dentry);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c08c46a3b8cd..dbfa18900e25 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2589,7 +2589,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata,
 
 	/* Except MODE, it seems harmless of setting twice. */
 	if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE &&
-		attrset[1] & FATTR4_WORD1_MODE)
+		(attrset[1] & FATTR4_WORD1_MODE ||
+		 attrset[2] & FATTR4_WORD2_MODE_UMASK))
 		sattr->ia_valid &= ~ATTR_MODE;
 
 	if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL)
@@ -8416,6 +8417,7 @@ static void nfs4_layoutget_release(void *calldata)
 	size_t max_pages = max_response_pages(server);
 
 	dprintk("--> %s\n", __func__);
+	nfs4_sequence_free_slot(&lgp->res.seq_res);
 	nfs4_free_pages(lgp->args.layout.pages, max_pages);
 	pnfs_put_layout_hdr(NFS_I(inode)->layout);
 	put_nfs_open_context(lgp->args.ctx);
@@ -8490,7 +8492,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
 	/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
 	if (status == 0 && lgp->res.layoutp->len)
 		lseg = pnfs_layout_process(lgp);
-	nfs4_sequence_free_slot(&lgp->res.seq_res);
 	rpc_put_task(task);
 	dprintk("<-- %s status=%d\n", __func__, status);
 	if (status)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index b34de036501b..cbf82b0d4467 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2134,6 +2134,8 @@ again:
 	put_rpccred(cred);
 	switch (status) {
 	case 0:
+	case -EINTR:
+	case -ERESTARTSYS:
 		break;
 	case -ETIMEDOUT:
 		if (clnt->cl_softrtry)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 3b7c937a36b5..4689940a953c 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2591,6 +2591,10 @@ void ocfs2_inode_unlock_tracker(struct inode *inode,
 	struct ocfs2_lock_res *lockres;
 
 	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	/* had_lock means that the currect process already takes the cluster
+	 * lock previously. If had_lock is 1, we have nothing to do here, and
+	 * it will get unlocked where we got the lock.
+	 */
 	if (!had_lock) {
 		ocfs2_remove_holder(lockres, oh);
 		ocfs2_inode_unlock(inode, ex);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 3c5384d9b3a5..f70c3778d600 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1328,20 +1328,21 @@ static int ocfs2_xattr_get(struct inode *inode,
 			   void *buffer,
 			   size_t buffer_size)
 {
-	int ret;
+	int ret, had_lock;
 	struct buffer_head *di_bh = NULL;
+	struct ocfs2_lock_holder oh;
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 0);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh);
+	if (had_lock < 0) {
+		mlog_errno(had_lock);
+		return had_lock;
 	}
 	down_read(&OCFS2_I(inode)->ip_xattr_sem);
 	ret = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
 				     name, buffer, buffer_size);
 	up_read(&OCFS2_I(inode)->ip_xattr_sem);
 
-	ocfs2_inode_unlock(inode, 0);
+	ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
 
 	brelse(di_bh);
 
@@ -3537,11 +3538,12 @@ int ocfs2_xattr_set(struct inode *inode,
 {
 	struct buffer_head *di_bh = NULL;
 	struct ocfs2_dinode *di;
-	int ret, credits, ref_meta = 0, ref_credits = 0;
+	int ret, credits, had_lock, ref_meta = 0, ref_credits = 0;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, NULL, };
 	struct ocfs2_refcount_tree *ref_tree = NULL;
+	struct ocfs2_lock_holder oh;
 
 	struct ocfs2_xattr_info xi = {
 		.xi_name_index = name_index,
@@ -3572,8 +3574,9 @@ int ocfs2_xattr_set(struct inode *inode,
 		return -ENOMEM;
 	}
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (ret < 0) {
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 1, &oh);
+	if (had_lock < 0) {
+		ret = had_lock;
 		mlog_errno(ret);
 		goto cleanup_nolock;
 	}
@@ -3670,7 +3673,7 @@ cleanup:
 		if (ret)
 			mlog_errno(ret);
 	}
-	ocfs2_inode_unlock(inode, 1);
+	ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 cleanup_nolock:
 	brelse(di_bh);
 	brelse(xbs.xattr_bh);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 09af0f7cd55e..3b91faacc1ba 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1316,9 +1316,12 @@ xfs_vm_bmap(
 	 * The swap code (ab-)uses ->bmap to get a block mapping and then
 	 * bypasseѕ the file system for actual I/O.  We really can't allow
 	 * that on reflinks inodes, so we have to skip out here.  And yes,
-	 * 0 is the magic code for a bmap error..
+	 * 0 is the magic code for a bmap error.
+	 *
+	 * Since we don't pass back blockdev info, we can't return bmap
+	 * information for rt files either.
 	 */
-	if (xfs_is_reflink_inode(ip))
+	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip))
 		return 0;
 
 	filemap_write_and_wait(mapping);