Merge branch 'nfs-for-3.2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

* 'nfs-for-3.2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (25 commits)
  nfs: set vs_hidden on nfs4_callback_version4 (try #2)
  pnfs-obj: Support for RAID5 read-4-write interface.
  pnfs-obj: move to ore 03: Remove old raid engine
  pnfs-obj: move to ore 02: move to ORE
  pnfs-obj: move to ore 01: ore_layout & ore_components
  pnfs-obj: Rename objlayout_io_state => objlayout_io_res
  pnfs-obj: Get rid of objlayout_{alloc,free}_io_state
  pnfs-obj: Return PNFS_NOT_ATTEMPTED in case of read/write_pagelist
  pnfs-obj: Remove redundant EOF from objlayout_io_state
  nfs: Remove unused variable from write.c
  nfs: Fix unused variable warning from file.c
  NFS: Remove no-op less-than-zero checks on unsigned variables.
  NFS: Clean up nfs4_xdr_dec_secinfo()
  NFS: Fix documenting comment for nfs_create_request()
  NFS4: fix cb_recallany decode error
  nfs4: serialize layoutcommit
  SUNRPC: remove rpcbind clients destruction on module cleanup
  SUNRPC: remove rpcbind clients creation during service registering
  NFSd: call svc rpcbind cleanup explicitly
  SUNRPC: cleanup service destruction
  ...

fs/exofs/Kconfig

@@ -5,7 +5,7 @@
 # selected by any of the users.
 config ORE
 	tristate
-	depends on EXOFS_FS
+	depends on EXOFS_FS || PNFS_OBJLAYOUT
 	select ASYNC_XOR
 	default SCSI_OSD_ULD
 

fs/nfs/callback_xdr.c

@@ -488,17 +488,18 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp,
 				      struct xdr_stream *xdr,
 				      struct cb_recallanyargs *args)
 {
-	__be32 *p;
+	uint32_t bitmap[2];
+	__be32 *p, status;
 
 	args->craa_addr = svc_addr(rqstp);
 	p = read_buf(xdr, 4);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_BADXDR);
 	args->craa_objs_to_keep = ntohl(*p++);
-	p = read_buf(xdr, 4);
-	if (unlikely(p == NULL))
-		return htonl(NFS4ERR_BADXDR);
-	args->craa_type_mask = ntohl(*p);
+	status = decode_bitmap(xdr, bitmap);
+	if (unlikely(status))
+		return status;
+	args->craa_type_mask = bitmap[0];
 
 	return 0;
 }
@@ -986,4 +987,5 @@ struct svc_version nfs4_callback_version4 = {
 	.vs_proc = nfs4_callback_procedures1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
+	.vs_hidden = 1,
 };

fs/nfs/file.c

@@ -137,11 +137,9 @@ nfs_file_open(struct inode *inode, struct file *filp)
 static int
 nfs_file_release(struct inode *inode, struct file *filp)
 {
-	struct dentry *dentry = filp->f_path.dentry;
-
 	dprintk("NFS: release(%s/%s)\n",
-			dentry->d_parent->d_name.name,
-			dentry->d_name.name);
+			filp->f_path.dentry->d_parent->d_name.name,
+			filp->f_path.dentry->d_name.name);
 
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
 	return nfs_release(inode, filp);
@@ -228,14 +226,13 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	struct dentry * dentry = iocb->ki_filp->f_path.dentry;
 	struct inode * inode = dentry->d_inode;
 	ssize_t result;
-	size_t count = iov_length(iov, nr_segs);
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
 		return nfs_file_direct_read(iocb, iov, nr_segs, pos);
 
 	dprintk("NFS: read(%s/%s, %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
-		(unsigned long) count, (unsigned long) pos);
+		(unsigned long) iov_length(iov, nr_segs), (unsigned long) pos);
 
 	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
 	if (!result) {

fs/nfs/nfs4filelayout.c

@@ -449,9 +449,8 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 
 	fl->dsaddr = dsaddr;
 
-	if (fl->first_stripe_index < 0 ||
-	    fl->first_stripe_index >= dsaddr->stripe_count) {
-		dprintk("%s Bad first_stripe_index %d\n",
+	if (fl->first_stripe_index >= dsaddr->stripe_count) {
+		dprintk("%s Bad first_stripe_index %u\n",
 				__func__, fl->first_stripe_index);
 		goto out_put;
 	}
@@ -552,7 +551,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 
 	/* Note that a zero value for num_fh is legal for STRIPE_SPARSE.
 	 * Futher checking is done in filelayout_check_layout */
-	if (fl->num_fh < 0 || fl->num_fh >
+	if (fl->num_fh >
 	    max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT))
 		goto out_err;
 

fs/nfs/nfs4proc.c

@@ -5950,6 +5950,7 @@ static void nfs4_layoutcommit_release(void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
 	struct pnfs_layout_segment *lseg, *tmp;
+	unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
 
 	pnfs_cleanup_layoutcommit(data);
 	/* Matched by references in pnfs_set_layoutcommit */
@@ -5959,6 +5960,11 @@ static void nfs4_layoutcommit_release(void *calldata)
 				       &lseg->pls_flags))
 			put_lseg(lseg);
 	}
+
+	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+	smp_mb__after_clear_bit();
+	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+
 	put_rpccred(data->cred);
 	kfree(data);
 }

fs/nfs/nfs4xdr.c

@@ -6602,8 +6602,6 @@ static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp,
 	if (status)
 		goto out;
 	status = decode_secinfo(xdr, res);
-	if (status)
-		goto out;
 out:
 	return status;
 }

fs/nfs/objlayout/objlayout.c

@@ -156,77 +156,39 @@ last_byte_offset(u64 start, u64 len)
 	return end > start ? end - 1 : NFS4_MAX_UINT64;
 }
 
-static struct objlayout_io_state *
-objlayout_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type,
-			struct page **pages,
-			unsigned pgbase,
-			loff_t offset,
-			size_t count,
-			struct pnfs_layout_segment *lseg,
-			void *rpcdata,
-			gfp_t gfp_flags)
+void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
+			   struct page ***p_pages, unsigned *p_pgbase,
+			   u64 offset, unsigned long count)
 {
-	struct objlayout_io_state *state;
 	u64 lseg_end_offset;
 
-	dprintk("%s: allocating io_state\n", __func__);
-	if (objio_alloc_io_state(lseg, &state, gfp_flags))
-		return NULL;
-
 	BUG_ON(offset < lseg->pls_range.offset);
 	lseg_end_offset = end_offset(lseg->pls_range.offset,
 				     lseg->pls_range.length);
 	BUG_ON(offset >= lseg_end_offset);
-	if (offset + count > lseg_end_offset) {
-		count = lseg->pls_range.length -
-				(offset - lseg->pls_range.offset);
-		dprintk("%s: truncated count %Zd\n", __func__, count);
-	}
+	WARN_ON(offset + count > lseg_end_offset);
 
-	if (pgbase > PAGE_SIZE) {
-		pages += pgbase >> PAGE_SHIFT;
-		pgbase &= ~PAGE_MASK;
+	if (*p_pgbase > PAGE_SIZE) {
+		dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase);
+		*p_pages += *p_pgbase >> PAGE_SHIFT;
+		*p_pgbase &= ~PAGE_MASK;
 	}
-
-	INIT_LIST_HEAD(&state->err_list);
-	state->lseg = lseg;
-	state->rpcdata = rpcdata;
-	state->pages = pages;
-	state->pgbase = pgbase;
-	state->nr_pages = (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	state->offset = offset;
-	state->count = count;
-	state->sync = 0;
-
-	return state;
-}
-
-static void
-objlayout_free_io_state(struct objlayout_io_state *state)
-{
-	dprintk("%s: freeing io_state\n", __func__);
-	if (unlikely(!state))
-		return;
-
-	objio_free_io_state(state);
 }
 
 /*
  * I/O done common code
  */
 static void
-objlayout_iodone(struct objlayout_io_state *state)
+objlayout_iodone(struct objlayout_io_res *oir)
 {
-	dprintk("%s: state %p status\n", __func__, state);
-
-	if (likely(state->status >= 0)) {
-		objlayout_free_io_state(state);
+	if (likely(oir->status >= 0)) {
+		objio_free_result(oir);
 	} else {
-		struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
+		struct objlayout *objlay = oir->objlay;
 
 		spin_lock(&objlay->lock);
 		objlay->delta_space_valid = OBJ_DSU_INVALID;
-		list_add(&objlay->err_list, &state->err_list);
+		list_add(&objlay->err_list, &oir->err_list);
 		spin_unlock(&objlay->lock);
 	}
 }
@@ -238,13 +200,13 @@ objlayout_iodone(struct objlayout_io_state *state)
  * the error for later reporting at layout-return.
  */
 void
-objlayout_io_set_result(struct objlayout_io_state *state, unsigned index,
+objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
 			struct pnfs_osd_objid *pooid, int osd_error,
 			u64 offset, u64 length, bool is_write)
 {
-	struct pnfs_osd_ioerr *ioerr = &state->ioerrs[index];
+	struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index];
 
-	BUG_ON(index >= state->num_comps);
+	BUG_ON(index >= oir->num_comps);
 	if (osd_error) {
 		ioerr->oer_component = *pooid;
 		ioerr->oer_comp_offset = offset;
@@ -285,21 +247,18 @@ static void _rpc_read_complete(struct work_struct *work)
 }
 
 void
-objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync)
+objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 {
-	int eof = state->eof;
-	struct nfs_read_data *rdata;
+	struct nfs_read_data *rdata = oir->rpcdata;
 
-	state->status = status;
-	dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof);
-	rdata = state->rpcdata;
-	rdata->task.tk_status = status;
-	if (status >= 0) {
+	oir->status = rdata->task.tk_status = status;
+	if (status >= 0)
 		rdata->res.count = status;
-		rdata->res.eof = eof;
-	}
-	objlayout_iodone(state);
-	/* must not use state after this point */
+	objlayout_iodone(oir);
+	/* must not use oir after this point */
+
+	dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__,
+		status, rdata->res.eof, sync);
 
 	if (sync)
 		pnfs_ld_read_done(rdata);
@@ -317,40 +276,36 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
 {
 	loff_t offset = rdata->args.offset;
 	size_t count = rdata->args.count;
-	struct objlayout_io_state *state;
-	ssize_t status = 0;
+	int err;
 	loff_t eof;
 
-	dprintk("%s: Begin inode %p offset %llu count %d\n",
-		__func__, rdata->inode, offset, (int)count);
-
 	eof = i_size_read(rdata->inode);
 	if (unlikely(offset + count > eof)) {
 		if (offset >= eof) {
-			status = 0;
+			err = 0;
 			rdata->res.count = 0;
 			rdata->res.eof = 1;
+			/*FIXME: do we need to call pnfs_ld_read_done() */
 			goto out;
 		}
 		count = eof - offset;
 	}
 
-	state = objlayout_alloc_io_state(NFS_I(rdata->inode)->layout,
-					 rdata->args.pages, rdata->args.pgbase,
-					 offset, count,
-					 rdata->lseg, rdata,
-					 GFP_KERNEL);
-	if (unlikely(!state)) {
-		status = -ENOMEM;
-		goto out;
-	}
+	rdata->res.eof = (offset + count) >= eof;
+	_fix_verify_io_params(rdata->lseg, &rdata->args.pages,
+			      &rdata->args.pgbase,
+			      rdata->args.offset, rdata->args.count);
 
-	state->eof = state->offset + state->count >= eof;
+	dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
+		__func__, rdata->inode->i_ino, offset, count, rdata->res.eof);
 
-	status = objio_read_pagelist(state);
+	err = objio_read_pagelist(rdata);
  out:
-	dprintk("%s: Return status %Zd\n", __func__, status);
-	rdata->pnfs_error = status;
+	if (unlikely(err)) {
+		rdata->pnfs_error = err;
+		dprintk("%s: Returned Error %d\n", __func__, err);
+		return PNFS_NOT_ATTEMPTED;
+	}
 	return PNFS_ATTEMPTED;
 }
 
@@ -371,26 +326,20 @@ static void _rpc_write_complete(struct work_struct *work)
 }
 
 void
-objlayout_write_done(struct objlayout_io_state *state, ssize_t status,
-		     bool sync)
+objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 {
-	struct nfs_write_data *wdata;
+	struct nfs_write_data *wdata = oir->rpcdata;
 
-	dprintk("%s: Begin\n", __func__);
-	wdata = state->rpcdata;
-	state->status = status;
-	wdata->task.tk_status = status;
+	oir->status = wdata->task.tk_status = status;
 	if (status >= 0) {
 		wdata->res.count = status;
-		wdata->verf.committed = state->committed;
-		dprintk("%s: Return status %d committed %d\n",
-			__func__, wdata->task.tk_status,
-			wdata->verf.committed);
-	} else
-		dprintk("%s: Return status %d\n",
-			__func__, wdata->task.tk_status);
-	objlayout_iodone(state);
-	/* must not use state after this point */
+		wdata->verf.committed = oir->committed;
+	}
+	objlayout_iodone(oir);
+	/* must not use oir after this point */
+
+	dprintk("%s: Return status %zd committed %d sync=%d\n", __func__,
+		status, wdata->verf.committed, sync);
 
 	if (sync)
 		pnfs_ld_write_done(wdata);
@@ -407,30 +356,18 @@ enum pnfs_try_status
 objlayout_write_pagelist(struct nfs_write_data *wdata,
 			 int how)
 {
-	struct objlayout_io_state *state;
-	ssize_t status;
-
-	dprintk("%s: Begin inode %p offset %llu count %u\n",
-		__func__, wdata->inode, wdata->args.offset, wdata->args.count);
-
-	state = objlayout_alloc_io_state(NFS_I(wdata->inode)->layout,
-					 wdata->args.pages,
-					 wdata->args.pgbase,
-					 wdata->args.offset,
-					 wdata->args.count,
-					 wdata->lseg, wdata,
-					 GFP_NOFS);
-	if (unlikely(!state)) {
-		status = -ENOMEM;
-		goto out;
-	}
+	int err;
 
-	state->sync = how & FLUSH_SYNC;
+	_fix_verify_io_params(wdata->lseg, &wdata->args.pages,
+			      &wdata->args.pgbase,
+			      wdata->args.offset, wdata->args.count);
 
-	status = objio_write_pagelist(state, how & FLUSH_STABLE);
- out:
-	dprintk("%s: Return status %Zd\n", __func__, status);
-	wdata->pnfs_error = status;
+	err = objio_write_pagelist(wdata, how);
+	if (unlikely(err)) {
+		wdata->pnfs_error = err;
+		dprintk("%s: Returned Error %d\n", __func__, err);
+		return PNFS_NOT_ATTEMPTED;
+	}
 	return PNFS_ATTEMPTED;
 }
 
@@ -537,14 +474,14 @@ merge_ioerr(struct pnfs_osd_ioerr *dest_err,
 static void
 encode_accumulated_error(struct objlayout *objlay, __be32 *p)
 {
-	struct objlayout_io_state *state, *tmp;
+	struct objlayout_io_res *oir, *tmp;
 	struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
 
-	list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+	list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
 		unsigned i;
 
-		for (i = 0; i < state->num_comps; i++) {
-			struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+		for (i = 0; i < oir->num_comps; i++) {
+			struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
 
 			if (!ioerr->oer_errno)
 				continue;
@@ -563,8 +500,8 @@ encode_accumulated_error(struct objlayout *objlay, __be32 *p)
 
 			merge_ioerr(&accumulated_err, ioerr);
 		}
-		list_del(&state->err_list);
-		objlayout_free_io_state(state);
+		list_del(&oir->err_list);
+		objio_free_result(oir);
 	}
 
 	pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
@@ -576,7 +513,7 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
 			      const struct nfs4_layoutreturn_args *args)
 {
 	struct objlayout *objlay = OBJLAYOUT(pnfslay);
-	struct objlayout_io_state *state, *tmp;
+	struct objlayout_io_res *oir, *tmp;
 	__be32 *start;
 
 	dprintk("%s: Begin\n", __func__);
@@ -585,13 +522,13 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
 
 	spin_lock(&objlay->lock);
 
-	list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+	list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
 		__be32 *last_xdr = NULL, *p;
 		unsigned i;
 		int res = 0;
 
-		for (i = 0; i < state->num_comps; i++) {
-			struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+		for (i = 0; i < oir->num_comps; i++) {
+			struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
 
 			if (!ioerr->oer_errno)
 				continue;
@@ -615,7 +552,7 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
 			}
 
 			last_xdr = p;
-			pnfs_osd_xdr_encode_ioerr(p, &state->ioerrs[i]);
+			pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]);
 		}
 
 		/* TODO: use xdr_write_pages */
@@ -631,8 +568,8 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
 			encode_accumulated_error(objlay, last_xdr);
 			goto loop_done;
 		}
-		list_del(&state->err_list);
-		objlayout_free_io_state(state);
+		list_del(&oir->err_list);
+		objio_free_result(oir);
 	}
 loop_done:
 	spin_unlock(&objlay->lock);

fs/nfs/objlayout/objlayout.h

@@ -74,19 +74,11 @@ OBJLAYOUT(struct pnfs_layout_hdr *lo)
  * per-I/O operation state
  * embedded in objects provider io_state data structure
  */
-struct objlayout_io_state {
-	struct pnfs_layout_segment *lseg;
-
-	struct page **pages;
-	unsigned pgbase;
-	unsigned nr_pages;
-	unsigned long count;
-	loff_t offset;
-	bool sync;
+struct objlayout_io_res {
+	struct objlayout *objlay;
 
 	void *rpcdata;
 	int status;             /* res */
-	int eof;                /* res */
 	int committed;          /* res */
 
 	/* Error reporting (layout_return) */
@@ -100,6 +92,18 @@ struct objlayout_io_state {
 	struct pnfs_osd_ioerr *ioerrs;
 };
 
+static inline
+void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
+			struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
+			struct pnfs_layout_hdr *pnfs_layout_type)
+{
+	oir->objlay = OBJLAYOUT(pnfs_layout_type);
+	oir->rpcdata = rpcdata;
+	INIT_LIST_HEAD(&oir->err_list);
+	oir->num_comps = num_comps;
+	oir->ioerrs = ioerrs;
+}
+
 /*
  * Raid engine I/O API
  */
@@ -110,28 +114,24 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	gfp_t gfp_flags);
 extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
 
-extern int objio_alloc_io_state(
-	struct pnfs_layout_segment *lseg,
-	struct objlayout_io_state **outp,
-	gfp_t gfp_flags);
-extern void objio_free_io_state(struct objlayout_io_state *state);
+/* objio_free_result will free these @oir structs recieved from
+ * objlayout_{read,write}_done
+ */
+extern void objio_free_result(struct objlayout_io_res *oir);
 
-extern ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state);
-extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state,
-				    bool stable);
+extern int objio_read_pagelist(struct nfs_read_data *rdata);
+extern int objio_write_pagelist(struct nfs_write_data *wdata, int how);
 
 /*
  * callback API
  */
-extern void objlayout_io_set_result(struct objlayout_io_state *state,
+extern void objlayout_io_set_result(struct objlayout_io_res *oir,
 			unsigned index, struct pnfs_osd_objid *pooid,
 			int osd_error, u64 offset, u64 length, bool is_write);
 
 static inline void
-objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
+objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
 {
-	struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
-
 	/* If one of the I/Os errored out and the delta_space_used was
 	 * invalid we render the complete report as invalid. Protocol mandate
 	 * the DSU be accurate or not reported.
@@ -144,9 +144,9 @@ objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
 	spin_unlock(&objlay->lock);
 }
 
-extern void objlayout_read_done(struct objlayout_io_state *state,
+extern void objlayout_read_done(struct objlayout_io_res *oir,
 				ssize_t status, bool sync);
-extern void objlayout_write_done(struct objlayout_io_state *state,
+extern void objlayout_write_done(struct objlayout_io_res *oir,
 				 ssize_t status, bool sync);
 
 extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,

fs/nfs/pagelist.c

@@ -41,7 +41,7 @@ nfs_page_free(struct nfs_page *p)
 
 /**
  * nfs_create_request - Create an NFS read/write request.
- * @file: file descriptor to use
+ * @ctx: open context to use
  * @inode: inode to which the request is attached
  * @page: page to write
  * @offset: starting offset within the page for the write

fs/nfs/pnfs.c

@@ -1443,17 +1443,31 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	/* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
 	data = kzalloc(sizeof(*data), GFP_NOFS);
 	if (!data) {
-		mark_inode_dirty_sync(inode);
 		status = -ENOMEM;
 		goto out;
 	}
 
+	if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+		goto out_free;
+
+	if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
+		if (!sync) {
+			status = -EAGAIN;
+			goto out_free;
+		}
+		status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
+					nfs_wait_bit_killable, TASK_KILLABLE);
+		if (status)
+			goto out_free;
+	}
+
 	INIT_LIST_HEAD(&data->lseg_list);
 	spin_lock(&inode->i_lock);
 	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
+		clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags);
 		spin_unlock(&inode->i_lock);
-		kfree(data);
-		goto out;
+		wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
+		goto out_free;
 	}
 
 	pnfs_list_write_lseg(inode, &data->lseg_list);
@@ -1475,6 +1489,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 
 	status = nfs4_proc_layoutcommit(data, sync);
 out:
+	if (status)
+		mark_inode_dirty_sync(inode);
 	dprintk("<-- %s status %d\n", __func__, status);
 	return status;
+out_free:
+	kfree(data);
+	goto out;
 }

fs/nfs/write.c

@@ -1243,7 +1243,6 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	struct nfs_writeargs	*argp = &data->args;
 	struct nfs_writeres	*resp = &data->res;
-	struct nfs_server	*server = NFS_SERVER(data->inode);
 	int status;
 
 	dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
@@ -1277,7 +1276,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		if (time_before(complain, jiffies)) {
 			dprintk("NFS:       faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
-				server->nfs_client->cl_hostname,
+				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
 				resp->verf->committed, argp->stable);
 			complain = jiffies + 300 * HZ;
 		}

fs/nfsd/nfssvc.c

@@ -256,6 +256,8 @@ static void nfsd_last_thread(struct svc_serv *serv)
 	nfsd_serv = NULL;
 	nfsd_shutdown();
 
+	svc_rpcb_cleanup(serv);
+
 	printk(KERN_WARNING "nfsd: last server has exited, flushing export "
 			    "cache\n");
 	nfsd_export_flush();

include/linux/nfs_fs.h

@@ -229,6 +229,7 @@ struct nfs_inode {
 #define NFS_INO_COMMIT		(7)		/* inode is committing unstable writes */
 #define NFS_INO_PNFS_COMMIT	(8)		/* use pnfs code for commit */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
+#define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {

include/linux/sunrpc/clnt.h

@@ -136,6 +136,8 @@ void		rpc_shutdown_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
 void		rpc_task_release_client(struct rpc_task *);
 
+int		rpcb_create_local(void);
+void		rpcb_put_local(void);
 int		rpcb_register(u32, u32, int, unsigned short);
 int		rpcb_v4_register(const u32 program, const u32 version,
 				 const struct sockaddr *address,

include/linux/sunrpc/svc.h

@@ -413,6 +413,7 @@ struct svc_procedure {
 /*
  * Function prototypes.
  */
+void svc_rpcb_cleanup(struct svc_serv *serv);
 struct svc_serv *svc_create(struct svc_program *, unsigned int,
 			    void (*shutdown)(struct svc_serv *));
 struct svc_rqst *svc_prepare_thread(struct svc_serv *serv,

net/sunrpc/auth_unix.c

@@ -129,6 +129,9 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags)
 	for (i = 0; i < groups ; i++)
 		if (cred->uc_gids[i] != GROUP_AT(acred->group_info, i))
 			return 0;
+	if (groups < NFS_NGROUPS &&
+	    cred->uc_gids[groups] != NOGROUP)
+		return 0;
 	return 1;
 }
 

net/sunrpc/rpcb_clnt.c

@@ -114,6 +114,9 @@ static struct rpc_program	rpcb_program;
 static struct rpc_clnt *	rpcb_local_clnt;
 static struct rpc_clnt *	rpcb_local_clnt4;
 
+DEFINE_SPINLOCK(rpcb_clnt_lock);
+unsigned int			rpcb_users;
+
 struct rpcbind_args {
 	struct rpc_xprt *	r_xprt;
 
@@ -161,6 +164,56 @@ static void rpcb_map_release(void *data)
 	kfree(map);
 }
 
+static int rpcb_get_local(void)
+{
+	int cnt;
+
+	spin_lock(&rpcb_clnt_lock);
+	if (rpcb_users)
+		rpcb_users++;
+	cnt = rpcb_users;
+	spin_unlock(&rpcb_clnt_lock);
+
+	return cnt;
+}
+
+void rpcb_put_local(void)
+{
+	struct rpc_clnt *clnt = rpcb_local_clnt;
+	struct rpc_clnt *clnt4 = rpcb_local_clnt4;
+	int shutdown;
+
+	spin_lock(&rpcb_clnt_lock);
+	if (--rpcb_users == 0) {
+		rpcb_local_clnt = NULL;
+		rpcb_local_clnt4 = NULL;
+	}
+	shutdown = !rpcb_users;
+	spin_unlock(&rpcb_clnt_lock);
+
+	if (shutdown) {
+		/*
+		 * cleanup_rpcb_clnt - remove xprtsock's sysctls, unregister
+		 */
+		if (clnt4)
+			rpc_shutdown_client(clnt4);
+		if (clnt)
+			rpc_shutdown_client(clnt);
+	}
+}
+
+static void rpcb_set_local(struct rpc_clnt *clnt, struct rpc_clnt *clnt4)
+{
+	/* Protected by rpcb_create_local_mutex */
+	rpcb_local_clnt = clnt;
+	rpcb_local_clnt4 = clnt4;
+	smp_wmb(); 
+	rpcb_users = 1;
+	dprintk("RPC:       created new rpcb local clients (rpcb_local_clnt: "
+			"%p, rpcb_local_clnt4: %p)\n", rpcb_local_clnt,
+			rpcb_local_clnt4);
+}
+
 /*
  * Returns zero on success, otherwise a negative errno value
  * is returned.
@@ -205,9 +258,7 @@ static int rpcb_create_local_unix(void)
 		clnt4 = NULL;
 	}
 
-	/* Protected by rpcb_create_local_mutex */
-	rpcb_local_clnt = clnt;
-	rpcb_local_clnt4 = clnt4;
+	rpcb_set_local(clnt, clnt4);
 
 out:
 	return result;
@@ -259,9 +310,7 @@ static int rpcb_create_local_net(void)
 		clnt4 = NULL;
 	}
 
-	/* Protected by rpcb_create_local_mutex */
-	rpcb_local_clnt = clnt;
-	rpcb_local_clnt4 = clnt4;
+	rpcb_set_local(clnt, clnt4);
 
 out:
 	return result;
@@ -271,16 +320,16 @@ static int rpcb_create_local_net(void)
  * Returns zero on success, otherwise a negative errno value
  * is returned.
  */
-static int rpcb_create_local(void)
+int rpcb_create_local(void)
 {
 	static DEFINE_MUTEX(rpcb_create_local_mutex);
 	int result = 0;
 
-	if (rpcb_local_clnt)
+	if (rpcb_get_local())
 		return result;
 
 	mutex_lock(&rpcb_create_local_mutex);
-	if (rpcb_local_clnt)
+	if (rpcb_get_local())
 		goto out;
 
 	if (rpcb_create_local_unix() != 0)
@@ -382,11 +431,6 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port)
 	struct rpc_message msg = {
 		.rpc_argp	= &map,
 	};
-	int error;
-
-	error = rpcb_create_local();
-	if (error)
-		return error;
 
 	dprintk("RPC:       %sregistering (%u, %u, %d, %u) with local "
 			"rpcbind\n", (port ? "" : "un"),
@@ -522,11 +566,7 @@ int rpcb_v4_register(const u32 program, const u32 version,
 	struct rpc_message msg = {
 		.rpc_argp	= &map,
 	};
-	int error;
 
-	error = rpcb_create_local();
-	if (error)
-		return error;
 	if (rpcb_local_clnt4 == NULL)
 		return -EPROTONOSUPPORT;
 
@@ -1060,15 +1100,3 @@ static struct rpc_program rpcb_program = {
 	.version	= rpcb_version,
 	.stats		= &rpcb_stats,
 };
-
-/**
- * cleanup_rpcb_clnt - remove xprtsock's sysctls, unregister
- *
- */
-void cleanup_rpcb_clnt(void)
-{
-	if (rpcb_local_clnt4)
-		rpc_shutdown_client(rpcb_local_clnt4);
-	if (rpcb_local_clnt)
-		rpc_shutdown_client(rpcb_local_clnt);
-}

net/sunrpc/sunrpc_syms.c

@@ -61,8 +61,6 @@ static struct pernet_operations sunrpc_net_ops = {
 
 extern struct cache_detail unix_gid_cache;
 
-extern void cleanup_rpcb_clnt(void);
-
 static int __init
 init_sunrpc(void)
 {
@@ -102,7 +100,6 @@ init_sunrpc(void)
 static void __exit
 cleanup_sunrpc(void)
 {
-	cleanup_rpcb_clnt();
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
 	svc_cleanup_xprt_sock();

net/sunrpc/svc.c

@@ -366,6 +366,42 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu)
 	return &serv->sv_pools[pidx % serv->sv_nrpools];
 }
 
+static int svc_rpcb_setup(struct svc_serv *serv)
+{
+	int err;
+
+	err = rpcb_create_local();
+	if (err)
+		return err;
+
+	/* Remove any stale portmap registrations */
+	svc_unregister(serv);
+	return 0;
+}
+
+void svc_rpcb_cleanup(struct svc_serv *serv)
+{
+	svc_unregister(serv);
+	rpcb_put_local();
+}
+EXPORT_SYMBOL_GPL(svc_rpcb_cleanup);
+
+static int svc_uses_rpcbind(struct svc_serv *serv)
+{
+	struct svc_program	*progp;
+	unsigned int		i;
+
+	for (progp = serv->sv_program; progp; progp = progp->pg_next) {
+		for (i = 0; i < progp->pg_nvers; i++) {
+			if (progp->pg_vers[i] == NULL)
+				continue;
+			if (progp->pg_vers[i]->vs_hidden == 0)
+				return 1;
+		}
+	}
+
+	return 0;
+}
 
 /*
  * Create an RPC service
@@ -431,8 +467,15 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		spin_lock_init(&pool->sp_lock);
 	}
 
-	/* Remove any stale portmap registrations */
-	svc_unregister(serv);
+	if (svc_uses_rpcbind(serv)) {
+	       	if (svc_rpcb_setup(serv) < 0) {
+			kfree(serv->sv_pools);
+			kfree(serv);
+			return NULL;
+		}
+		if (!serv->sv_shutdown)
+			serv->sv_shutdown = svc_rpcb_cleanup;
+	}
 
 	return serv;
 }
@@ -500,7 +543,6 @@ svc_destroy(struct svc_serv *serv)
 	if (svc_serv_is_pooled(serv))
 		svc_pool_map_put();
 
-	svc_unregister(serv);
 	kfree(serv->sv_pools);
 	kfree(serv);
 }