Merge tag 'nfs-for-5.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS Client Updates from Anna Schumaker:
 "New Features:
   - Support for eager writes, and the write=eager and write=wait mount
     options

- Other Bugfixes and Cleanups:
   - Fix typos in some comments
   - Fix up fall-through warnings for Clang
   - Cleanups to the NFS readpage codepath
   - Remove FMR support in rpcrdma_convert_iovs()
   - Various other cleanups to xprtrdma
   - Fix xprtrdma pad optimization for servers that don't support
     RFC 8797
   - Improvements to rpcrdma tracepoints
   - Fix up nfs4_bitmask_adjust()
   - Optimize sparse writes past the end of files"

* tag 'nfs-for-5.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (27 commits)
  NFS: Support the '-owrite=' option in /proc/self/mounts and mountinfo
  NFS: Set the stable writes flag when initialising the super block
  NFS: Add mount options supporting eager writes
  NFS: Add support for eager writes
  NFS: 'flags' field should be unsigned in struct nfs_server
  NFS: Don't set NFS_INO_INVALID_XATTR if there is no xattr cache
  NFS: Always clear an invalid mapping when attempting a buffered write
  NFS: Optimise sparse writes past the end of file
  NFS: Fix documenting comment for nfs_revalidate_file_size()
  NFSv4: Fixes for nfs4_bitmask_adjust()
  xprtrdma: Clean up rpcrdma_prepare_readch()
  rpcrdma: Capture bytes received in Receive completion tracepoints
  xprtrdma: Pad optimization, revisited
  rpcrdma: Fix comments about reverse-direction operation
  xprtrdma: Refactor invocations of offset_in_page()
  xprtrdma: Simplify rpcrdma_convert_kvec() and frwr_map()
  xprtrdma: Remove FMR support in rpcrdma_convert_iovs()
  NFS: Add nfs_pageio_complete_read() and remove nfs_readpage_async()
  NFS: Call readpage_async_filler() from nfs_readpage_async()
  NFS: Refactor nfs_readpage() and nfs_readpage_async() to use nfs_readdesc
  ...

fs/nfs/file.c

@@ -89,7 +89,7 @@ nfs_file_release(struct inode *inode, struct file *filp)
 EXPORT_SYMBOL_GPL(nfs_file_release);
 
 /**
- * nfs_revalidate_size - Revalidate the file size
+ * nfs_revalidate_file_size - Revalidate the file size
  * @inode: pointer to inode struct
  * @filp: pointer to struct file
  *
@@ -606,8 +606,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	unsigned long written = 0;
+	unsigned int mntflags = NFS_SERVER(inode)->flags;
-	ssize_t result;
+	ssize_t result, written;
 	errseq_t since;
 	int error;
 
@@ -626,13 +626,13 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	/*
 	 * O_APPEND implies that we must revalidate the file length.
 	 */
-	if (iocb->ki_flags & IOCB_APPEND) {
+	if (iocb->ki_flags & IOCB_APPEND || iocb->ki_pos > i_size_read(inode)) {
 		result = nfs_revalidate_file_size(inode, file);
 		if (result)
 			goto out;
 	}
-	if (iocb->ki_pos > i_size_read(inode))
+
-		nfs_revalidate_mapping(inode, file->f_mapping);
+	nfs_clear_invalid_mapping(file->f_mapping);
 
 	since = filemap_sample_wb_err(file->f_mapping);
 	nfs_start_io_write(inode);
@@ -648,6 +648,21 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 
 	written = result;
 	iocb->ki_pos += written;
+
+	if (mntflags & NFS_MOUNT_WRITE_EAGER) {
+		result = filemap_fdatawrite_range(file->f_mapping,
+						  iocb->ki_pos - written,
+						  iocb->ki_pos - 1);
+		if (result < 0)
+			goto out;
+	}
+	if (mntflags & NFS_MOUNT_WRITE_WAIT) {
+		result = filemap_fdatawait_range(file->f_mapping,
+						 iocb->ki_pos - written,
+						 iocb->ki_pos - 1);
+		if (result < 0)
+			goto out;
+	}
 	result = generic_write_sync(iocb, written);
 	if (result < 0)
 		goto out;

fs/nfs/fs_context.c

@@ -82,6 +82,7 @@ enum nfs_param {
 	Opt_v,
 	Opt_vers,
 	Opt_wsize,
+	Opt_write,
 };
 
 enum {
@@ -113,6 +114,19 @@ static const struct constant_table nfs_param_enums_lookupcache[] = {
 	{}
 };
 
+enum {
+	Opt_write_lazy,
+	Opt_write_eager,
+	Opt_write_wait,
+};
+
+static const struct constant_table nfs_param_enums_write[] = {
+	{ "lazy",		Opt_write_lazy },
+	{ "eager",		Opt_write_eager },
+	{ "wait",		Opt_write_wait },
+	{}
+};
+
 static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_flag_no("ac",		Opt_ac),
 	fsparam_u32   ("acdirmax",	Opt_acdirmax),
@@ -171,6 +185,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_flag  ("v4.1",		Opt_v),
 	fsparam_flag  ("v4.2",		Opt_v),
 	fsparam_string("vers",		Opt_vers),
+	fsparam_enum  ("write",		Opt_write, nfs_param_enums_write),
 	fsparam_u32   ("wsize",		Opt_wsize),
 	{}
 };
@@ -770,6 +785,24 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 			goto out_invalid_value;
 		}
 		break;
+	case Opt_write:
+		switch (result.uint_32) {
+		case Opt_write_lazy:
+			ctx->flags &=
+				~(NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT);
+			break;
+		case Opt_write_eager:
+			ctx->flags |= NFS_MOUNT_WRITE_EAGER;
+			ctx->flags &= ~NFS_MOUNT_WRITE_WAIT;
+			break;
+		case Opt_write_wait:
+			ctx->flags |=
+				NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT;
+			break;
+		default:
+			goto out_invalid_value;
+		}
+		break;
 
 		/*
 		 * Special options
@@ -1479,6 +1512,8 @@ static int nfs_init_fs_context(struct fs_context *fc)
 		ctx->selected_flavor	= RPC_AUTH_MAXFLAVOR;
 		ctx->minorversion	= 0;
 		ctx->need_mount		= true;
+
+		fc->s_iflags		|= SB_I_STABLE_WRITES;
 	}
 	fc->fs_private = ctx;
 	fc->ops = &nfs_fs_context_ops;

fs/nfs/fscache.c

@@ -390,10 +390,6 @@ static void nfs_readpage_from_fscache_complete(struct page *page,
 	if (!error) {
 		SetPageUptodate(page);
 		unlock_page(page);
-	} else {
-		error = nfs_readpage_async(context, page->mapping->host, page);
-		if (error)
-			unlock_page(page);
 	}
 }
 

fs/nfs/inode.c

@@ -195,6 +195,18 @@ bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
 }
 EXPORT_SYMBOL_GPL(nfs_check_cache_invalid);
 
+#ifdef CONFIG_NFS_V4_2
+static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi)
+{
+	return nfsi->xattr_cache != NULL;
+}
+#else
+static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi)
+{
+	return false;
+}
+#endif
+
 static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -209,6 +221,8 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 				| NFS_INO_INVALID_XATTR);
 	}
 
+	if (!nfs_has_xattr_cache(nfsi))
+		flags &= ~NFS_INO_INVALID_XATTR;
 	if (inode->i_mapping->nrpages == 0)
 		flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
 	nfsi->cache_validity |= flags;
@@ -1258,6 +1272,63 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 	return 0;
 }
 
+/**
+ * nfs_clear_invalid_mapping - Conditionally clear a mapping
+ * @mapping: pointer to mapping
+ *
+ * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping.
+ */
+int nfs_clear_invalid_mapping(struct address_space *mapping)
+{
+	struct inode *inode = mapping->host;
+	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long *bitlock = &nfsi->flags;
+	int ret = 0;
+
+	/*
+	 * We must clear NFS_INO_INVALID_DATA first to ensure that
+	 * invalidations that come in while we're shooting down the mappings
+	 * are respected. But, that leaves a race window where one revalidator
+	 * can clear the flag, and then another checks it before the mapping
+	 * gets invalidated. Fix that by serializing access to this part of
+	 * the function.
+	 *
+	 * At the same time, we need to allow other tasks to see whether we
+	 * might be in the middle of invalidating the pages, so we only set
+	 * the bit lock here if it looks like we're going to be doing that.
+	 */
+	for (;;) {
+		ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING,
+					 nfs_wait_bit_killable, TASK_KILLABLE);
+		if (ret)
+			goto out;
+		spin_lock(&inode->i_lock);
+		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+			break;
+		spin_unlock(&inode->i_lock);
+		goto out;
+	}
+
+	set_bit(NFS_INO_INVALIDATING, bitlock);
+	smp_wmb();
+	nfsi->cache_validity &=
+		~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER);
+	spin_unlock(&inode->i_lock);
+	trace_nfs_invalidate_mapping_enter(inode);
+	ret = nfs_invalidate_mapping(inode, mapping);
+	trace_nfs_invalidate_mapping_exit(inode, ret);
+
+	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+	smp_mb__after_atomic();
+	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
+out:
+	return ret;
+}
+
 bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 {
 	return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) ||
@@ -1290,65 +1361,19 @@ out:
  * @inode: pointer to host inode
  * @mapping: pointer to mapping
  */
-int nfs_revalidate_mapping(struct inode *inode,
+int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
-		struct address_space *mapping)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
-	unsigned long *bitlock = &nfsi->flags;
-	int ret = 0;
-
 	/* swapfiles are not supposed to be shared. */
 	if (IS_SWAPFILE(inode))
-		goto out;
+		return 0;
 
 	if (nfs_mapping_need_revalidate_inode(inode)) {
-		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+		int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		if (ret < 0)
-			goto out;
+			return ret;
 	}
 
-	/*
+	return nfs_clear_invalid_mapping(mapping);
-	 * We must clear NFS_INO_INVALID_DATA first to ensure that
-	 * invalidations that come in while we're shooting down the mappings
-	 * are respected. But, that leaves a race window where one revalidator
-	 * can clear the flag, and then another checks it before the mapping
-	 * gets invalidated. Fix that by serializing access to this part of
-	 * the function.
-	 *
-	 * At the same time, we need to allow other tasks to see whether we
-	 * might be in the middle of invalidating the pages, so we only set
-	 * the bit lock here if it looks like we're going to be doing that.
-	 */
-	for (;;) {
-		ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING,
-					 nfs_wait_bit_killable, TASK_KILLABLE);
-		if (ret)
-			goto out;
-		spin_lock(&inode->i_lock);
-		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
-			spin_unlock(&inode->i_lock);
-			continue;
-		}
-		if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
-			break;
-		spin_unlock(&inode->i_lock);
-		goto out;
-	}
-
-	set_bit(NFS_INO_INVALIDATING, bitlock);
-	smp_wmb();
-	nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA|
-			NFS_INO_DATA_INVAL_DEFER);
-	spin_unlock(&inode->i_lock);
-	trace_nfs_invalidate_mapping_enter(inode);
-	ret = nfs_invalidate_mapping(inode, mapping);
-	trace_nfs_invalidate_mapping_exit(inode, ret);
-
-	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
-	smp_mb__after_atomic();
-	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
-out:
-	return ret;
 }
 
 static bool nfs_file_has_writers(struct nfs_inode *nfsi)

fs/nfs/nfs3acl.c

@@ -111,6 +111,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
 			fallthrough;
 		case -ENOTSUPP:
 			status = -EOPNOTSUPP;
+			goto getout;
 		default:
 			goto getout;
 	}

fs/nfs/nfs4client.c

@@ -609,6 +609,7 @@ found:
 			 * changed. Schedule recovery!
 			 */
 			nfs4_schedule_path_down_recovery(pos);
+			goto out;
 		default:
 			goto out;
 		}

fs/nfs/nfs4proc.c

@@ -71,10 +71,6 @@
 
 #include "nfs4trace.h"
 
-#ifdef CONFIG_NFS_V4_2
-#include "nfs42.h"
-#endif /* CONFIG_NFS_V4_2 */
-
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 #define NFS4_BITMASK_SZ		3
@@ -2231,6 +2227,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 		default:
 			printk(KERN_ERR "NFS: %s: unhandled error "
 					"%d.\n", __func__, err);
+			fallthrough;
 		case 0:
 		case -ENOENT:
 		case -EAGAIN:
@@ -5438,15 +5435,16 @@ static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
 
 	if (cache_validity & NFS_INO_INVALID_ATIME)
 		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
-	if (cache_validity & NFS_INO_INVALID_ACCESS)
+	if (cache_validity & NFS_INO_INVALID_OTHER)
-		bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
+		bitmask[1] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
-				FATTR4_WORD1_OWNER_GROUP;
+				FATTR4_WORD1_OWNER_GROUP |
-	if (cache_validity & NFS_INO_INVALID_ACL)
+				FATTR4_WORD1_NUMLINKS;
-		bitmask[0] |= FATTR4_WORD0_ACL;
+	if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL)
-	if (cache_validity & NFS_INO_INVALID_LABEL)
 		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
-	if (cache_validity & NFS_INO_INVALID_CTIME)
+	if (cache_validity & NFS_INO_INVALID_CHANGE)
 		bitmask[0] |= FATTR4_WORD0_CHANGE;
+	if (cache_validity & NFS_INO_INVALID_CTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_METADATA;
 	if (cache_validity & NFS_INO_INVALID_MTIME)
 		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
 	if (cache_validity & NFS_INO_INVALID_SIZE)
@@ -9708,6 +9706,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 	case -NFS4ERR_BADLAYOUT:     /* no layout */
 	case -NFS4ERR_GRACE:	    /* loca_recalim always false */
 		task->tk_status = 0;
+		break;
 	case 0:
 		break;
 	default:

fs/nfs/nfs4state.c

@@ -1125,6 +1125,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 					" sequence-id error on an"
 					" unconfirmed sequence %p!\n",
 					seqid->sequence);
+			return;
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_BAD_STATEID:

fs/nfs/pnfs.c

@@ -2875,6 +2875,7 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc,
 	switch (trypnfs) {
 	case PNFS_NOT_ATTEMPTED:
 		pnfs_write_through_mds(desc, hdr);
+		break;
 	case PNFS_ATTEMPTED:
 		break;
 	case PNFS_TRY_AGAIN:
@@ -3019,6 +3020,7 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
 	switch (trypnfs) {
 	case PNFS_NOT_ATTEMPTED:
 		pnfs_read_through_mds(desc, hdr);
+		break;
 	case PNFS_ATTEMPTED:
 		break;
 	case PNFS_TRY_AGAIN:

fs/nfs/read.c

@@ -74,6 +74,24 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
+static void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio,
+				     struct inode *inode)
+{
+	struct nfs_pgio_mirror *pgm;
+	unsigned long npages;
+
+	nfs_pageio_complete(pgio);
+
+	/* It doesn't make sense to do mirrored reads! */
+	WARN_ON_ONCE(pgio->pg_mirror_count != 1);
+
+	pgm = &pgio->pg_mirrors[0];
+	NFS_I(inode)->read_io += pgm->pg_bytes_written;
+	npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
+}
+
+
 void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
@@ -114,41 +132,10 @@ static void nfs_readpage_release(struct nfs_page *req, int error)
 	nfs_release_request(req);
 }
 
-int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
+struct nfs_readdesc {
-		       struct page *page)
-{
-	struct nfs_page	*new;
-	unsigned int len;
 	struct nfs_pageio_descriptor pgio;
-	struct nfs_pgio_mirror *pgm;
+	struct nfs_open_context *ctx;
-
+};
-	len = nfs_page_length(page);
-	if (len == 0)
-		return nfs_return_empty_page(page);
-	new = nfs_create_request(ctx, page, 0, len);
-	if (IS_ERR(new)) {
-		unlock_page(page);
-		return PTR_ERR(new);
-	}
-	if (len < PAGE_SIZE)
-		zero_user_segment(page, len, PAGE_SIZE);
-
-	nfs_pageio_init_read(&pgio, inode, false,
-			     &nfs_async_read_completion_ops);
-	if (!nfs_pageio_add_request(&pgio, new)) {
-		nfs_list_remove_request(new);
-		nfs_readpage_release(new, pgio.pg_error);
-	}
-	nfs_pageio_complete(&pgio);
-
-	/* It doesn't make sense to do mirrored reads! */
-	WARN_ON_ONCE(pgio.pg_mirror_count != 1);
-
-	pgm = &pgio.pg_mirrors[0];
-	NFS_I(inode)->read_io += pgm->pg_bytes_written;
-
-	return pgio.pg_error < 0 ? pgio.pg_error : 0;
-}
 
 static void nfs_page_group_set_uptodate(struct nfs_page *req)
 {
@@ -171,8 +158,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
 
 		if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
 			/* note: regions of the page not covered by a
-			 * request are zeroed in nfs_readpage_async /
+			 * request are zeroed in readpage_async_filler */
-			 * readpage_async_filler */
 			if (bytes > hdr->good_bytes) {
 				/* nothing in this request was good, so zero
 				 * the full extent of the request */
@@ -304,78 +290,10 @@ static void nfs_readpage_result(struct rpc_task *task,
 		nfs_readpage_retry(task, hdr);
 }
 
-/*
- * Read a page over NFS.
- * We read the page synchronously in the following case:
- *  -	The error flag is set for this page. This happens only when a
- *	previous async read operation failed.
- */
-int nfs_readpage(struct file *file, struct page *page)
-{
-	struct nfs_open_context *ctx;
-	struct inode *inode = page_file_mapping(page)->host;
-	int		error;
-
-	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
-		page, PAGE_SIZE, page_index(page));
-	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
-	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
-
-	/*
-	 * Try to flush any pending writes to the file..
-	 *
-	 * NOTE! Because we own the page lock, there cannot
-	 * be any new pending writes generated at this point
-	 * for this page (other pages can be written to).
-	 */
-	error = nfs_wb_page(inode, page);
-	if (error)
-		goto out_unlock;
-	if (PageUptodate(page))
-		goto out_unlock;
-
-	error = -ESTALE;
-	if (NFS_STALE(inode))
-		goto out_unlock;
-
-	if (file == NULL) {
-		error = -EBADF;
-		ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
-		if (ctx == NULL)
-			goto out_unlock;
-	} else
-		ctx = get_nfs_open_context(nfs_file_open_context(file));
-
-	if (!IS_SYNC(inode)) {
-		error = nfs_readpage_from_fscache(ctx, inode, page);
-		if (error == 0)
-			goto out;
-	}
-
-	xchg(&ctx->error, 0);
-	error = nfs_readpage_async(ctx, inode, page);
-	if (!error) {
-		error = wait_on_page_locked_killable(page);
-		if (!PageUptodate(page) && !error)
-			error = xchg(&ctx->error, 0);
-	}
-out:
-	put_nfs_open_context(ctx);
-	return error;
-out_unlock:
-	unlock_page(page);
-	return error;
-}
-
-struct nfs_readdesc {
-	struct nfs_pageio_descriptor *pgio;
-	struct nfs_open_context *ctx;
-};
-
 static int
 readpage_async_filler(void *data, struct page *page)
 {
-	struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
+	struct nfs_readdesc *desc = data;
 	struct nfs_page *new;
 	unsigned int len;
 	int error;
@@ -390,9 +308,9 @@ readpage_async_filler(void *data, struct page *page)
 
 	if (len < PAGE_SIZE)
 		zero_user_segment(page, len, PAGE_SIZE);
-	if (!nfs_pageio_add_request(desc->pgio, new)) {
+	if (!nfs_pageio_add_request(&desc->pgio, new)) {
 		nfs_list_remove_request(new);
-		error = desc->pgio->pg_error;
+		error = desc->pgio.pg_error;
 		nfs_readpage_release(new, error);
 		goto out;
 	}
@@ -404,17 +322,82 @@ out:
 	return error;
 }
 
-int nfs_readpages(struct file *filp, struct address_space *mapping,
+/*
+ * Read a page over NFS.
+ * We read the page synchronously in the following case:
+ *  -	The error flag is set for this page. This happens only when a
+ *	previous async read operation failed.
+ */
+int nfs_readpage(struct file *file, struct page *page)
+{
+	struct nfs_readdesc desc;
+	struct inode *inode = page_file_mapping(page)->host;
+	int ret;
+
+	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
+		page, PAGE_SIZE, page_index(page));
+	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
+
+	/*
+	 * Try to flush any pending writes to the file..
+	 *
+	 * NOTE! Because we own the page lock, there cannot
+	 * be any new pending writes generated at this point
+	 * for this page (other pages can be written to).
+	 */
+	ret = nfs_wb_page(inode, page);
+	if (ret)
+		goto out_unlock;
+	if (PageUptodate(page))
+		goto out_unlock;
+
+	ret = -ESTALE;
+	if (NFS_STALE(inode))
+		goto out_unlock;
+
+	if (file == NULL) {
+		ret = -EBADF;
+		desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
+		if (desc.ctx == NULL)
+			goto out_unlock;
+	} else
+		desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
+
+	if (!IS_SYNC(inode)) {
+		ret = nfs_readpage_from_fscache(desc.ctx, inode, page);
+		if (ret == 0)
+			goto out;
+	}
+
+	xchg(&desc.ctx->error, 0);
+	nfs_pageio_init_read(&desc.pgio, inode, false,
+			     &nfs_async_read_completion_ops);
+
+	ret = readpage_async_filler(&desc, page);
+
+	if (!ret)
+		nfs_pageio_complete_read(&desc.pgio, inode);
+
+	ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0;
+	if (!ret) {
+		ret = wait_on_page_locked_killable(page);
+		if (!PageUptodate(page) && !ret)
+			ret = xchg(&desc.ctx->error, 0);
+	}
+out:
+	put_nfs_open_context(desc.ctx);
+	return ret;
+out_unlock:
+	unlock_page(page);
+	return ret;
+}
+
+int nfs_readpages(struct file *file, struct address_space *mapping,
 		struct list_head *pages, unsigned nr_pages)
 {
-	struct nfs_pageio_descriptor pgio;
+	struct nfs_readdesc desc;
-	struct nfs_pgio_mirror *pgm;
-	struct nfs_readdesc desc = {
-		.pgio = &pgio,
-	};
 	struct inode *inode = mapping->host;
-	unsigned long npages;
+	int ret;
-	int ret = -ESTALE;
 
 	dprintk("NFS: nfs_readpages (%s/%Lu %d)\n",
 			inode->i_sb->s_id,
@@ -422,15 +405,17 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			nr_pages);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
 
+	ret = -ESTALE;
 	if (NFS_STALE(inode))
 		goto out;
 
-	if (filp == NULL) {
+	if (file == NULL) {
+		ret = -EBADF;
 		desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
 		if (desc.ctx == NULL)
-			return -EBADF;
+			goto out;
 	} else
-		desc.ctx = get_nfs_open_context(nfs_file_open_context(filp));
+		desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
 
 	/* attempt to read as many of the pages as possible from the cache
 	 * - this returns -ENOBUFS immediately if the cookie is negative
@@ -440,20 +425,13 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	nfs_pageio_init_read(&pgio, inode, false,
+	nfs_pageio_init_read(&desc.pgio, inode, false,
 			     &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
-	nfs_pageio_complete(&pgio);
 
-	/* It doesn't make sense to do mirrored reads! */
+	nfs_pageio_complete_read(&desc.pgio, inode);
-	WARN_ON_ONCE(pgio.pg_mirror_count != 1);
 
-	pgm = &pgio.pg_mirrors[0];
-	NFS_I(inode)->read_io += pgm->pg_bytes_written;
-	npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >>
-		 PAGE_SHIFT;
-	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 read_complete:
 	put_nfs_open_context(desc.ctx);
 out:

fs/nfs/super.c

@@ -523,6 +523,13 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		seq_puts(m, ",local_lock=flock");
 	else
 		seq_puts(m, ",local_lock=posix");
+
+	if (nfss->flags & NFS_MOUNT_WRITE_EAGER) {
+		if (nfss->flags & NFS_MOUNT_WRITE_WAIT)
+			seq_puts(m, ",write=wait");
+		else
+			seq_puts(m, ",write=eager");
+	}
 }
 
 /*

fs/nfs/write.c

@@ -712,16 +712,23 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
 	struct nfs_pageio_descriptor pgio;
-	struct nfs_io_completion *ioc;
+	struct nfs_io_completion *ioc = NULL;
+	unsigned int mntflags = NFS_SERVER(inode)->flags;
+	int priority = 0;
 	int err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
-	ioc = nfs_io_completion_alloc(GFP_KERNEL);
+	if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate ||
-	if (ioc)
+	    wbc->for_background || wbc->for_sync || wbc->for_reclaim) {
-		nfs_io_completion_init(ioc, nfs_io_completion_commit, inode);
+		ioc = nfs_io_completion_alloc(GFP_KERNEL);
+		if (ioc)
+			nfs_io_completion_init(ioc, nfs_io_completion_commit,
+					       inode);
+		priority = wb_priority(wbc);
+	}
 
-	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
+	nfs_pageio_init_write(&pgio, inode, priority, false,
 				&nfs_async_write_completion_ops);
 	pgio.pg_io_completion = ioc;
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
@@ -1278,19 +1285,21 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode)
  * the PageUptodate() flag. In this case, we will need to turn off
  * write optimisations that depend on the page contents being correct.
  */
-static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
+static bool nfs_write_pageuptodate(struct page *page, struct inode *inode,
+				   unsigned int pagelen)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
-	if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+	if (nfsi->cache_validity &
+	    (NFS_INO_REVAL_PAGECACHE | NFS_INO_INVALID_SIZE))
 		return false;
 	smp_rmb();
-	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
+	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags) && pagelen != 0)
 		return false;
 out:
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA && pagelen != 0)
 		return false;
 	return PageUptodate(page) != 0;
 }
@@ -1310,7 +1319,8 @@ is_whole_file_wrlock(struct file_lock *fl)
  * If the file is opened for synchronous writes then we can just skip the rest
  * of the checks.
  */
-static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
+static int nfs_can_extend_write(struct file *file, struct page *page,
+				struct inode *inode, unsigned int pagelen)
 {
 	int ret;
 	struct file_lock_context *flctx = inode->i_flctx;
@@ -1318,7 +1328,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
 
 	if (file->f_flags & O_DSYNC)
 		return 0;
-	if (!nfs_write_pageuptodate(page, inode))
+	if (!nfs_write_pageuptodate(page, inode, pagelen))
 		return 0;
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return 1;
@@ -1356,6 +1366,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct address_space *mapping = page_file_mapping(page);
 	struct inode	*inode = mapping->host;
+	unsigned int	pagelen = nfs_page_length(page);
 	int		status = 0;
 
 	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -1366,8 +1377,8 @@ int nfs_updatepage(struct file *file, struct page *page,
 	if (!count)
 		goto out;
 
-	if (nfs_can_extend_write(file, page, inode)) {
+	if (nfs_can_extend_write(file, page, inode, pagelen)) {
-		count = max(count + offset, nfs_page_length(page));
+		count = max(count + offset, pagelen);
 		offset = 0;
 	}
 

include/linux/nfs_fs.h

@@ -388,6 +388,7 @@ extern int nfs_open(struct inode *, struct file *);
 extern int nfs_attribute_cache_expired(struct inode *inode);
 extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
+extern int nfs_clear_invalid_mapping(struct address_space *mapping);
 extern bool nfs_mapping_need_revalidate_inode(struct inode *inode);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
 extern int nfs_revalidate_mapping_rcu(struct inode *inode);
@@ -571,8 +572,6 @@ nfs_have_writebacks(struct inode *inode)
 extern int  nfs_readpage(struct file *, struct page *);
 extern int  nfs_readpages(struct file *, struct address_space *,
 		struct list_head *, unsigned);
-extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
-			       struct page *);
 
 /*
  * inline functions

include/linux/nfs_fs_sb.h

@@ -142,7 +142,7 @@ struct nfs_server {
 	struct nlm_host		*nlm_host;	/* NLM client handle */
 	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
 	atomic_long_t		writeback;	/* number of writeback pages */
-	int			flags;		/* various flags */
+	unsigned int		flags;		/* various flags */
 
 /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */
 #define NFS_MOUNT_LOOKUP_CACHE_NONEG	0x10000
@@ -153,6 +153,8 @@ struct nfs_server {
 #define NFS_MOUNT_LOCAL_FCNTL		0x200000
 #define NFS_MOUNT_SOFTERR		0x400000
 #define NFS_MOUNT_SOFTREVAL		0x800000
+#define NFS_MOUNT_WRITE_EAGER		0x01000000
+#define NFS_MOUNT_WRITE_WAIT		0x02000000
 
 	unsigned int		caps;		/* server capabilities */
 	unsigned int		rsize;		/* read size */

include/trace/events/rpcrdma.h

@@ -60,6 +60,51 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class,
 				),					\
 				TP_ARGS(wc, cid))
 
+DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class,
+	TP_PROTO(
+		const struct ib_wc *wc,
+		const struct rpc_rdma_cid *cid
+	),
+
+	TP_ARGS(wc, cid),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(u32, received)
+		__field(unsigned long, status)
+		__field(unsigned int, vendor_err)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->status = wc->status;
+		if (wc->status) {
+			__entry->received = 0;
+			__entry->vendor_err = wc->vendor_err;
+		} else {
+			__entry->received = wc->byte_len;
+			__entry->vendor_err = 0;
+		}
+	),
+
+	TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x) received=%u",
+		__entry->cq_id, __entry->completion_id,
+		rdma_show_wc_status(__entry->status),
+		__entry->status, __entry->vendor_err,
+		__entry->received
+	)
+);
+
+#define DEFINE_RECEIVE_COMPLETION_EVENT(name)				\
+		DEFINE_EVENT(rpcrdma_receive_completion_class, name,	\
+				TP_PROTO(				\
+					const struct ib_wc *wc,		\
+					const struct rpc_rdma_cid *cid	\
+				),					\
+				TP_ARGS(wc, cid))
+
 DECLARE_EVENT_CLASS(xprtrdma_reply_class,
 	TP_PROTO(
 		const struct rpcrdma_rep *rep
@@ -838,7 +883,8 @@ TRACE_EVENT(xprtrdma_post_linv_err,
  ** Completion events
  **/
 
-DEFINE_COMPLETION_EVENT(xprtrdma_wc_receive);
+DEFINE_RECEIVE_COMPLETION_EVENT(xprtrdma_wc_receive);
+
 DEFINE_COMPLETION_EVENT(xprtrdma_wc_send);
 DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg);
 DEFINE_COMPLETION_EVENT(xprtrdma_wc_li);
@@ -1790,7 +1836,7 @@ TRACE_EVENT(svcrdma_post_recv,
 	)
 );
 
-DEFINE_COMPLETION_EVENT(svcrdma_wc_receive);
+DEFINE_RECEIVE_COMPLETION_EVENT(svcrdma_wc_receive);
 
 TRACE_EVENT(svcrdma_rq_post_err,
 	TP_PROTO(

net/sunrpc/rpc_pipe.c

@@ -478,6 +478,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode)
 		inode->i_fop = &simple_dir_operations;
 		inode->i_op = &simple_dir_inode_operations;
 		inc_nlink(inode);
+		break;
 	default:
 		break;
 	}

net/sunrpc/xprtrdma/backchannel.c

@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2015-2020, Oracle and/or its affiliates.
  *
- * Support for backward direction RPCs on RPC/RDMA.
+ * Support for reverse-direction RPCs on RPC/RDMA.
  */
 
 #include <linux/sunrpc/xprt.h>
@@ -208,7 +208,7 @@ create_req:
 }
 
 /**
- * rpcrdma_bc_receive_call - Handle a backward direction call
+ * rpcrdma_bc_receive_call - Handle a reverse-direction Call
  * @r_xprt: transport receiving the call
  * @rep: receive buffer containing the call
  *

net/sunrpc/xprtrdma/frwr_ops.c

@@ -306,20 +306,14 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	if (nsegs > ep->re_max_fr_depth)
 		nsegs = ep->re_max_fr_depth;
 	for (i = 0; i < nsegs;) {
-		if (seg->mr_page)
+		sg_set_page(&mr->mr_sg[i], seg->mr_page,
-			sg_set_page(&mr->mr_sg[i],
+			    seg->mr_len, seg->mr_offset);
-				    seg->mr_page,
-				    seg->mr_len,
-				    offset_in_page(seg->mr_offset));
-		else
-			sg_set_buf(&mr->mr_sg[i], seg->mr_offset,
-				   seg->mr_len);
 
 		++seg;
 		++i;
 		if (ep->re_mrtype == IB_MR_TYPE_SG_GAPS)
 			continue;
-		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+		if ((i < nsegs && seg->mr_offset) ||
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}

net/sunrpc/xprtrdma/rpc_rdma.c

@@ -204,9 +204,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf)
 	return 0;
 }
 
-/* Split @vec on page boundaries into SGEs. FMR registers pages, not
+/* Convert @vec to a single SGL element.
- * a byte range. Other modes coalesce these SGEs into a single MR
- * when they can.
  *
  * Returns pointer to next available SGE, and bumps the total number
  * of SGEs consumed.
@@ -215,22 +213,11 @@ static struct rpcrdma_mr_seg *
 rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
 		     unsigned int *n)
 {
-	u32 remaining, page_offset;
+	seg->mr_page = virt_to_page(vec->iov_base);
-	char *base;
+	seg->mr_offset = offset_in_page(vec->iov_base);
-
+	seg->mr_len = vec->iov_len;
-	base = vec->iov_base;
+	++seg;
-	page_offset = offset_in_page(base);
+	++(*n);
-	remaining = vec->iov_len;
-	while (remaining) {
-		seg->mr_page = NULL;
-		seg->mr_offset = base;
-		seg->mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining);
-		remaining -= seg->mr_len;
-		base += seg->mr_len;
-		++seg;
-		++(*n);
-		page_offset = 0;
-	}
 	return seg;
 }
 
@@ -259,7 +246,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 	page_base = offset_in_page(xdrbuf->page_base);
 	while (len) {
 		seg->mr_page = *ppages;
-		seg->mr_offset = (char *)page_base;
+		seg->mr_offset = page_base;
 		seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len);
 		len -= seg->mr_len;
 		++ppages;
@@ -268,10 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 		page_base = 0;
 	}
 
-	/* When encoding a Read chunk, the tail iovec contains an
+	if (type == rpcrdma_readch)
-	 * XDR pad and may be omitted.
-	 */
-	if (type == rpcrdma_readch && r_xprt->rx_ep->re_implicit_roundup)
 		goto out;
 
 	/* When encoding a Write chunk, some servers need to see an
@@ -283,7 +267,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 		goto out;
 
 	if (xdrbuf->tail[0].iov_len)
-		seg = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n);
+		rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n);
 
 out:
 	if (unlikely(n > RPCRDMA_MAX_SEGS))
@@ -644,9 +628,8 @@ out_mapping_err:
 	return false;
 }
 
-/* The tail iovec may include an XDR pad for the page list,
+/* The tail iovec might not reside in the same page as the
- * as well as additional content, and may not reside in the
+ * head iovec.
- * same page as the head iovec.
  */
 static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req,
 				     struct xdr_buf *xdr,
@@ -764,27 +747,19 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt,
 				   struct rpcrdma_req *req,
 				   struct xdr_buf *xdr)
 {
+	struct kvec *tail = &xdr->tail[0];
+
 	if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len))
 		return false;
 
-	/* If there is a Read chunk, the page list is being handled
+	/* If there is a Read chunk, the page list is handled
 	 * via explicit RDMA, and thus is skipped here.
 	 */
 
-	/* Do not include the tail if it is only an XDR pad */
+	if (tail->iov_len) {
-	if (xdr->tail[0].iov_len > 3) {
+		if (!rpcrdma_prepare_tail_iov(req, xdr,
-		unsigned int page_base, len;
+					      offset_in_page(tail->iov_base),
-
+					      tail->iov_len))
-		/* If the content in the page list is an odd length,
-		 * xdr_write_pages() adds a pad at the beginning of
-		 * the tail iovec. Force the tail's non-pad content to
-		 * land at the next XDR position in the Send message.
-		 */
-		page_base = offset_in_page(xdr->tail[0].iov_base);
-		len = xdr->tail[0].iov_len;
-		page_base += len & 3;
-		len -= len & 3;
-		if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len))
 			return false;
 		kref_get(&req->rl_kref);
 	}
@@ -1164,14 +1139,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 	 */
 	p = xdr_inline_decode(xdr, 3 * sizeof(*p));
 	if (unlikely(!p))
-		goto out_short;
+		return true;
 
 	rpcrdma_bc_receive_call(r_xprt, rep);
 	return true;
-
-out_short:
-	pr_warn("RPC/RDMA short backward direction call\n");
-	return true;
 }
 #else	/* CONFIG_SUNRPC_BACKCHANNEL */
 {

net/sunrpc/xprtrdma/svc_rdma_backchannel.c

@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2015-2018 Oracle.  All rights reserved.
  *
- * Support for backward direction RPCs on RPC/RDMA (server-side).
+ * Support for reverse-direction RPCs on RPC/RDMA (server-side).
  */
 
 #include <linux/sunrpc/svc_rdma.h>
@@ -59,7 +59,7 @@ out_unlock:
 	spin_unlock(&xprt->queue_lock);
 }
 
-/* Send a backwards direction RPC call.
+/* Send a reverse-direction RPC Call.
  *
  * Caller holds the connection's mutex and has already marshaled
  * the RPC/RDMA request.

net/sunrpc/xprtrdma/xprt_rdma.h

@@ -98,9 +98,9 @@ struct rpcrdma_ep {
 	atomic_t		re_completion_ids;
 };
 
-/* Pre-allocate extra Work Requests for handling backward receives
+/* Pre-allocate extra Work Requests for handling reverse-direction
- * and sends. This is a fixed value because the Work Queues are
+ * Receives and Sends. This is a fixed value because the Work Queues
- * allocated when the forward channel is set up, long before the
+ * are allocated when the forward channel is set up, long before the
  * backchannel is provisioned. This value is two times
  * NFS4_DEF_CB_SLOT_TABLE_SIZE.
  */
@@ -283,10 +283,11 @@ enum {
 				  RPCRDMA_MAX_IOV_SEGS,
 };
 
-struct rpcrdma_mr_seg {		/* chunk descriptors */
+/* Arguments for DMA mapping and registration */
-	u32		mr_len;		/* length of chunk or segment */
+struct rpcrdma_mr_seg {
-	struct page	*mr_page;	/* owning page, if any */
+	u32		mr_len;		/* length of segment */
-	char		*mr_offset;	/* kva if no page, else offset */
+	struct page	*mr_page;	/* underlying struct page */
+	u64		mr_offset;	/* IN: page offset, OUT: iova */
 };
 
 /* The Send SGE array is provisioned to send a maximum size

net/sunrpc/xprtsock.c

@@ -829,7 +829,7 @@ xs_stream_record_marker(struct xdr_buf *xdr)
  *   EAGAIN:	The socket was blocked, please call again later to
  *		complete the request
  * ENOTCONN:	Caller needs to invoke connect logic then call again
- *    other:	Some other error occured, the request was not sent
+ *    other:	Some other error occurred, the request was not sent
  */
 static int xs_local_send_request(struct rpc_rqst *req)
 {
@@ -1665,7 +1665,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
 	 * This ensures that we can continue to establish TCP
 	 * connections even when all local ephemeral ports are already
 	 * a part of some TCP connection.  This makes no difference
-	 * for UDP sockets, but also doens't harm them.
+	 * for UDP sockets, but also doesn't harm them.
 	 *
 	 * If we're asking for any reserved port (i.e. port == 0 &&
 	 * transport->xprt.resvport == 1) xs_get_srcport above will
@@ -1875,6 +1875,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 		xprt->stat.connect_time += (long)jiffies -
 					   xprt->stat.connect_start;
 		xprt_set_connected(xprt);
+		break;
 	case -ENOBUFS:
 		break;
 	case -ENOENT:
@@ -2276,10 +2277,8 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -EHOSTUNREACH:
 	case -EADDRINUSE:
 	case -ENOBUFS:
-		/*
+		/* xs_tcp_force_close() wakes tasks with a fixed error code.
-		 * xs_tcp_force_close() wakes tasks with -EIO.
+		 * We need to wake them first to ensure the correct error code.
-		 * We need to wake them first to ensure the
-		 * correct error code.
 		 */
 		xprt_wake_pending_tasks(xprt, status);
 		xs_tcp_force_close(xprt);
@@ -2380,7 +2379,7 @@ static void xs_error_handle(struct work_struct *work)
 }
 
 /**
- * xs_local_print_stats - display AF_LOCAL socket-specifc stats
+ * xs_local_print_stats - display AF_LOCAL socket-specific stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
  *
@@ -2409,7 +2408,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 }
 
 /**
- * xs_udp_print_stats - display UDP socket-specifc stats
+ * xs_udp_print_stats - display UDP socket-specific stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
  *
@@ -2433,7 +2432,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 }
 
 /**
- * xs_tcp_print_stats - display TCP socket-specifc stats
+ * xs_tcp_print_stats - display TCP socket-specific stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
  *