Merge tag 'nfs-for-3.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

   - stable fix for a bug in nfs3_list_one_acl()
   - speed up NFS path walks by supporting LOOKUP_RCU
   - more read/write code cleanups
   - pNFS fixes for layout return on close
   - fixes for the RCU handling in the rpcsec_gss code
   - more NFS/RDMA fixes"

* tag 'nfs-for-3.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (79 commits)
  nfs: reject changes to resvport and sharecache during remount
  NFS: Avoid infinite loop when RELEASE_LOCKOWNER getting expired error
  SUNRPC: remove all refcounting of groupinfo from rpcauth_lookupcred
  NFS: fix two problems in lookup_revalidate in RCU-walk
  NFS: allow lockless access to access_cache
  NFS: teach nfs_lookup_verify_inode to handle LOOKUP_RCU
  NFS: teach nfs_neg_need_reval to understand LOOKUP_RCU
  NFS: support RCU_WALK in nfs_permission()
  sunrpc/auth: allow lockless (rcu) lookup of credential cache.
  NFS: prepare for RCU-walk support but pushing tests later in code.
  NFS: nfs4_lookup_revalidate: only evaluate parent if it will be used.
  NFS: add checks for returned value of try_module_get()
  nfs: clear_request_commit while holding i_lock
  pnfs: add pnfs_put_lseg_async
  pnfs: find swapped pages on pnfs commit lists too
  nfs: fix comment and add warn_on for PG_INODE_REF
  nfs: check wait_on_bit_lock err in page_group_lock
  sunrpc: remove "ec" argument from encrypt_v2 operation
  sunrpc: clean up sparse endianness warnings in gss_krb5_wrap.c
  sunrpc: clean up sparse endianness warnings in gss_krb5_seal.c
  ...

fs/nfs/blocklayout/blocklayout.c

@@ -210,8 +210,7 @@ static void bl_end_io_read(struct bio *bio, int err)
 			SetPageUptodate(bvec->bv_page);
 
 	if (err) {
-		struct nfs_pgio_data *rdata = par->data;
-		struct nfs_pgio_header *header = rdata->header;
+		struct nfs_pgio_header *header = par->data;
 
 		if (!header->pnfs_error)
 			header->pnfs_error = -EIO;
@@ -224,43 +223,44 @@ static void bl_end_io_read(struct bio *bio, int err)
 static void bl_read_cleanup(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_pgio_data *rdata;
+	struct nfs_pgio_header *hdr;
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	rdata = container_of(task, struct nfs_pgio_data, task);
-	pnfs_ld_read_done(rdata);
+	hdr = container_of(task, struct nfs_pgio_header, task);
+	pnfs_ld_read_done(hdr);
 }
 
 static void
 bl_end_par_io_read(void *data, int unused)
 {
-	struct nfs_pgio_data *rdata = data;
+	struct nfs_pgio_header *hdr = data;
 
-	rdata->task.tk_status = rdata->header->pnfs_error;
-	INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
-	schedule_work(&rdata->task.u.tk_work);
+	hdr->task.tk_status = hdr->pnfs_error;
+	INIT_WORK(&hdr->task.u.tk_work, bl_read_cleanup);
+	schedule_work(&hdr->task.u.tk_work);
 }
 
 static enum pnfs_try_status
-bl_read_pagelist(struct nfs_pgio_data *rdata)
+bl_read_pagelist(struct nfs_pgio_header *hdr)
 {
-	struct nfs_pgio_header *header = rdata->header;
+	struct nfs_pgio_header *header = hdr;
 	int i, hole;
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
 	sector_t isect, extent_length = 0;
 	struct parallel_io *par;
-	loff_t f_offset = rdata->args.offset;
-	size_t bytes_left = rdata->args.count;
+	loff_t f_offset = hdr->args.offset;
+	size_t bytes_left = hdr->args.count;
 	unsigned int pg_offset, pg_len;
-	struct page **pages = rdata->args.pages;
-	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
+	struct page **pages = hdr->args.pages;
+	int pg_index = hdr->args.pgbase >> PAGE_CACHE_SHIFT;
 	const bool is_dio = (header->dreq != NULL);
 
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
-	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
+		hdr->page_array.npages, f_offset,
+		(unsigned int)hdr->args.count);
 
-	par = alloc_parallel(rdata);
+	par = alloc_parallel(hdr);
 	if (!par)
 		goto use_mds;
 	par->pnfs_callback = bl_end_par_io_read;
@@ -268,7 +268,7 @@ bl_read_pagelist(struct nfs_pgio_data *rdata)
 
 	isect = (sector_t) (f_offset >> SECTOR_SHIFT);
 	/* Code assumes extents are page-aligned */
-	for (i = pg_index; i < rdata->pages.npages; i++) {
+	for (i = pg_index; i < hdr->page_array.npages; i++) {
 		if (!extent_length) {
 			/* We've used up the previous extent */
 			bl_put_extent(be);
@@ -317,7 +317,8 @@ bl_read_pagelist(struct nfs_pgio_data *rdata)
 			struct pnfs_block_extent *be_read;
 
 			be_read = (hole && cow_read) ? cow_read : be;
-			bio = do_add_page_to_bio(bio, rdata->pages.npages - i,
+			bio = do_add_page_to_bio(bio,
+						 hdr->page_array.npages - i,
 						 READ,
 						 isect, pages[i], be_read,
 						 bl_end_io_read, par,
@@ -332,10 +333,10 @@ bl_read_pagelist(struct nfs_pgio_data *rdata)
 		extent_length -= PAGE_CACHE_SECTORS;
 	}
 	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
-		rdata->res.eof = 1;
-		rdata->res.count = header->inode->i_size - rdata->args.offset;
+		hdr->res.eof = 1;
+		hdr->res.count = header->inode->i_size - hdr->args.offset;
 	} else {
-		rdata->res.count = (isect << SECTOR_SHIFT) - rdata->args.offset;
+		hdr->res.count = (isect << SECTOR_SHIFT) - hdr->args.offset;
 	}
 out:
 	bl_put_extent(be);
@@ -390,8 +391,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	}
 
 	if (unlikely(err)) {
-		struct nfs_pgio_data *data = par->data;
-		struct nfs_pgio_header *header = data->header;
+		struct nfs_pgio_header *header = par->data;
 
 		if (!header->pnfs_error)
 			header->pnfs_error = -EIO;
@@ -405,8 +405,7 @@ static void bl_end_io_write(struct bio *bio, int err)
 {
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct nfs_pgio_data *data = par->data;
-	struct nfs_pgio_header *header = data->header;
+	struct nfs_pgio_header *header = par->data;
 
 	if (!uptodate) {
 		if (!header->pnfs_error)
@@ -423,32 +422,32 @@ static void bl_end_io_write(struct bio *bio, int err)
 static void bl_write_cleanup(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_pgio_data *wdata;
+	struct nfs_pgio_header *hdr;
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	wdata = container_of(task, struct nfs_pgio_data, task);
-	if (likely(!wdata->header->pnfs_error)) {
+	hdr = container_of(task, struct nfs_pgio_header, task);
+	if (likely(!hdr->pnfs_error)) {
 		/* Marks for LAYOUTCOMMIT */
-		mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
-				     wdata->args.offset, wdata->args.count);
+		mark_extents_written(BLK_LSEG2EXT(hdr->lseg),
+				     hdr->args.offset, hdr->args.count);
 	}
-	pnfs_ld_write_done(wdata);
+	pnfs_ld_write_done(hdr);
 }
 
 /* Called when last of bios associated with a bl_write_pagelist call finishes */
 static void bl_end_par_io_write(void *data, int num_se)
 {
-	struct nfs_pgio_data *wdata = data;
+	struct nfs_pgio_header *hdr = data;
 
-	if (unlikely(wdata->header->pnfs_error)) {
-		bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
+	if (unlikely(hdr->pnfs_error)) {
+		bl_free_short_extents(&BLK_LSEG2EXT(hdr->lseg)->bl_inval,
 					num_se);
 	}
 
-	wdata->task.tk_status = wdata->header->pnfs_error;
-	wdata->verf.committed = NFS_FILE_SYNC;
-	INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
-	schedule_work(&wdata->task.u.tk_work);
+	hdr->task.tk_status = hdr->pnfs_error;
+	hdr->verf.committed = NFS_FILE_SYNC;
+	INIT_WORK(&hdr->task.u.tk_work, bl_write_cleanup);
+	schedule_work(&hdr->task.u.tk_work);
 }
 
 /* FIXME STUB - mark intersection of layout and page as bad, so is not
@@ -673,18 +672,17 @@ bl_find_get_zeroing_page(struct inode *inode, pgoff_t index,
 }
 
 static enum pnfs_try_status
-bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
+bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 {
-	struct nfs_pgio_header *header = wdata->header;
 	int i, ret, npg_zero, pg_index, last = 0;
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
 	sector_t isect, last_isect = 0, extent_length = 0;
 	struct parallel_io *par = NULL;
-	loff_t offset = wdata->args.offset;
-	size_t count = wdata->args.count;
+	loff_t offset = header->args.offset;
+	size_t count = header->args.count;
 	unsigned int pg_offset, pg_len, saved_len;
-	struct page **pages = wdata->args.pages;
+	struct page **pages = header->args.pages;
 	struct page *page;
 	pgoff_t index;
 	u64 temp;
@@ -699,11 +697,11 @@ bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
 		dprintk("pnfsblock nonblock aligned DIO writes. Resend MDS\n");
 		goto out_mds;
 	}
-	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
+	/* At this point, header->page_aray is a (sequential) list of nfs_pages.
 	 * We want to write each, and if there is an error set pnfs_error
 	 * to have it redone using nfs.
 	 */
-	par = alloc_parallel(wdata);
+	par = alloc_parallel(header);
 	if (!par)
 		goto out_mds;
 	par->pnfs_callback = bl_end_par_io_write;
@@ -790,8 +788,8 @@ bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
 	bio = bl_submit_bio(WRITE, bio);
 
 	/* Middle pages */
-	pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
-	for (i = pg_index; i < wdata->pages.npages; i++) {
+	pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+	for (i = pg_index; i < header->page_array.npages; i++) {
 		if (!extent_length) {
 			/* We've used up the previous extent */
 			bl_put_extent(be);
@@ -862,7 +860,8 @@ bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
 		}
 
 
-		bio = do_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
+		bio = do_add_page_to_bio(bio, header->page_array.npages - i,
+					 WRITE,
 					 isect, pages[i], be,
 					 bl_end_io_write, par,
 					 pg_offset, pg_len);
@@ -890,7 +889,7 @@ bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
 	}
 
 write_done:
-	wdata->res.count = wdata->args.count;
+	header->res.count = header->args.count;
 out:
 	bl_put_extent(be);
 	bl_put_extent(cow_read);
@@ -1063,7 +1062,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
+	pages = kcalloc(max_pages, sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
 		kfree(dev);
 		return ERR_PTR(-ENOMEM);

fs/nfs/callback.c

@@ -428,6 +428,18 @@ check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
 	if (p == NULL)
 		return 0;
 
+	/*
+	 * Did we get the acceptor from userland during the SETCLIENID
+	 * negotiation?
+	 */
+	if (clp->cl_acceptor)
+		return !strcmp(p, clp->cl_acceptor);
+
+	/*
+	 * Otherwise try to verify it using the cl_hostname. Note that this
+	 * doesn't work if a non-canonical hostname was used in the devname.
+	 */
+
 	/* Expect a GSS_C_NT_HOSTBASED_NAME like "nfs@serverhostname" */
 
 	if (memcmp(p, "nfs@", 4) != 0)

fs/nfs/client.c

@@ -110,8 +110,8 @@ struct nfs_subversion *get_nfs_version(unsigned int version)
 		mutex_unlock(&nfs_version_mutex);
 	}
 
-	if (!IS_ERR(nfs))
-		try_module_get(nfs->owner);
+	if (!IS_ERR(nfs) && !try_module_get(nfs->owner))
+		return ERR_PTR(-EAGAIN);
 	return nfs;
 }
 
@@ -158,7 +158,8 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 		goto error_0;
 
 	clp->cl_nfs_mod = cl_init->nfs_mod;
-	try_module_get(clp->cl_nfs_mod->owner);
+	if (!try_module_get(clp->cl_nfs_mod->owner))
+		goto error_dealloc;
 
 	clp->rpc_ops = clp->cl_nfs_mod->rpc_ops;
 
@@ -190,6 +191,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 
 error_cleanup:
 	put_nfs_version(clp->cl_nfs_mod);
+error_dealloc:
 	kfree(clp);
 error_0:
 	return ERR_PTR(err);
@@ -252,6 +254,7 @@ void nfs_free_client(struct nfs_client *clp)
 	put_net(clp->cl_net);
 	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp->cl_hostname);
+	kfree(clp->cl_acceptor);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
@@ -482,8 +485,13 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 	struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
 	const struct nfs_rpc_ops *rpc_ops = cl_init->nfs_mod->rpc_ops;
 
+	if (cl_init->hostname == NULL) {
+		WARN_ON(1);
+		return NULL;
+	}
+
 	dprintk("--> nfs_get_client(%s,v%u)\n",
-		cl_init->hostname ?: "", rpc_ops->version);
+		cl_init->hostname, rpc_ops->version);
 
 	/* see if the client already exists */
 	do {
@@ -510,7 +518,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 	} while (!IS_ERR(new));
 
 	dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
-		cl_init->hostname ?: "", PTR_ERR(new));
+		cl_init->hostname, PTR_ERR(new));
 	return new;
 }
 EXPORT_SYMBOL_GPL(nfs_get_client);

fs/nfs/delegation.c

@@ -41,14 +41,8 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
 	set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags);
 }
 
-/**
- * nfs_have_delegation - check if inode has a delegation
- * @inode: inode to check
- * @flags: delegation types to check for
- *
- * Returns one if inode has the indicated delegation, otherwise zero.
- */
-int nfs4_have_delegation(struct inode *inode, fmode_t flags)
+static int
+nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
 {
 	struct nfs_delegation *delegation;
 	int ret = 0;
@@ -58,12 +52,34 @@ int nfs4_have_delegation(struct inode *inode, fmode_t flags)
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
 	if (delegation != NULL && (delegation->type & flags) == flags &&
 	    !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
-		nfs_mark_delegation_referenced(delegation);
+		if (mark)
+			nfs_mark_delegation_referenced(delegation);
 		ret = 1;
 	}
 	rcu_read_unlock();
 	return ret;
 }
+/**
+ * nfs_have_delegation - check if inode has a delegation, mark it
+ * NFS_DELEGATION_REFERENCED if there is one.
+ * @inode: inode to check
+ * @flags: delegation types to check for
+ *
+ * Returns one if inode has the indicated delegation, otherwise zero.
+ */
+int nfs4_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return nfs4_do_check_delegation(inode, flags, true);
+}
+
+/*
+ * nfs4_check_delegation - check if inode has a delegation, do not mark
+ * NFS_DELEGATION_REFERENCED if it has one.
+ */
+int nfs4_check_delegation(struct inode *inode, fmode_t flags)
+{
+	return nfs4_do_check_delegation(inode, flags, false);
+}
 
 static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
 {

fs/nfs/delegation.h

@@ -59,6 +59,7 @@ bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs4_have_delegation(struct inode *inode, fmode_t flags);
+int nfs4_check_delegation(struct inode *inode, fmode_t flags);
 
 #endif
 

fs/nfs/direct.c

@@ -148,8 +148,8 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
-				      hdr->data->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
+				      hdr->ds_idx);
 	WARN_ON_ONCE(verfp->committed >= 0);
 	memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
 	WARN_ON_ONCE(verfp->committed < 0);
@@ -169,8 +169,8 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
-					 hdr->data->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
+					 hdr->ds_idx);
 	if (verfp->committed < 0) {
 		nfs_direct_set_hdr_verf(dreq, hdr);
 		return 0;
@@ -715,7 +715,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;
 	struct nfs_commit_info cinfo;
-	int bit = -1;
+	bool request_commit = false;
 	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
@@ -729,27 +729,20 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		dreq->flags = 0;
 		dreq->error = hdr->error;
 	}
-	if (dreq->error != 0)
-		bit = NFS_IOHDR_ERROR;
-	else {
+	if (dreq->error == 0) {
 		dreq->count += hdr->good_bytes;
-		if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) {
-			dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
-			bit = NFS_IOHDR_NEED_RESCHED;
-		} else if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
+		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
-				bit = NFS_IOHDR_NEED_RESCHED;
+				request_commit = true;
 			else if (dreq->flags == 0) {
 				nfs_direct_set_hdr_verf(dreq, hdr);
-				bit = NFS_IOHDR_NEED_COMMIT;
+				request_commit = true;
 				dreq->flags = NFS_ODIRECT_DO_COMMIT;
 			} else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) {
-				if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr)) {
+				request_commit = true;
+				if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr))
 					dreq->flags =
 						NFS_ODIRECT_RESCHED_WRITES;
-					bit = NFS_IOHDR_NEED_RESCHED;
-				} else
-					bit = NFS_IOHDR_NEED_COMMIT;
 			}
 		}
 	}
@@ -759,9 +752,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 
 		req = nfs_list_entry(hdr->pages.next);
 		nfs_list_remove_request(req);
-		switch (bit) {
-		case NFS_IOHDR_NEED_RESCHED:
-		case NFS_IOHDR_NEED_COMMIT:
+		if (request_commit) {
 			kref_get(&req->wb_kref);
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
 		}

fs/nfs/filelayout/filelayoutdev.c

@@ -695,7 +695,7 @@ filelayout_get_device_info(struct inode *inode,
 	if (pdev == NULL)
 		return NULL;
 
-	pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags);
+	pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
 	if (pages == NULL) {
 		kfree(pdev);
 		return NULL;

fs/nfs/inode.c

@@ -1002,6 +1002,15 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 }
 EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
+int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode)
+{
+	if (!(NFS_I(inode)->cache_validity &
+			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
+			&& !nfs_attribute_cache_expired(inode))
+		return NFS_STALE(inode) ? -ESTALE : 0;
+	return -ECHILD;
+}
+
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);

fs/nfs/internal.h

@@ -247,11 +247,11 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
 int nfs_iocounter_wait(struct nfs_io_counter *c);
 
 extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
-struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *);
-void nfs_rw_header_free(struct nfs_pgio_header *);
-void nfs_pgio_data_release(struct nfs_pgio_data *);
+struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
+void nfs_pgio_header_free(struct nfs_pgio_header *);
+void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
-int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *,
+int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *,
 		      const struct rpc_call_ops *, int, int);
 void nfs_free_request(struct nfs_page *req);
 
@@ -451,6 +451,7 @@ int nfs_scan_commit(struct inode *inode, struct list_head *dst,
 void nfs_mark_request_commit(struct nfs_page *req,
 			     struct pnfs_layout_segment *lseg,
 			     struct nfs_commit_info *cinfo);
+int nfs_write_need_commit(struct nfs_pgio_header *);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
@@ -491,7 +492,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
-extern void __nfs4_read_done_cb(struct nfs_pgio_data *);
+extern void __nfs4_read_done_cb(struct nfs_pgio_header *);
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
 			    const char *ip_addr);

fs/nfs/nfs3acl.c

@@ -256,7 +256,7 @@ nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data,
 	char *p = data + *result;
 
 	acl = get_acl(inode, type);
-	if (!acl)
+	if (IS_ERR_OR_NULL(acl))
 		return 0;
 
 	posix_acl_release(acl);

fs/nfs/nfs3proc.c

@@ -795,41 +795,44 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return status;
 }
 
-static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
+static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = data->header->inode;
+	struct inode *inode = hdr->inode;
 
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
 	nfs_invalidate_atime(inode);
-	nfs_refresh_inode(inode, &data->fattr);
+	nfs_refresh_inode(inode, &hdr->fattr);
 	return 0;
 }
 
-static void nfs3_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
+static void nfs3_proc_read_setup(struct nfs_pgio_header *hdr,
+				 struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
 }
 
-static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
+static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task,
+				      struct nfs_pgio_header *hdr)
 {
 	rpc_call_start(task);
 	return 0;
 }
 
-static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
+static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = data->header->inode;
+	struct inode *inode = hdr->inode;
 
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
+		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
 	return 0;
 }
 
-static void nfs3_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
+static void nfs3_proc_write_setup(struct nfs_pgio_header *hdr,
+				  struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
 }

fs/nfs/nfs4_fs.h

@@ -54,7 +54,7 @@ struct nfs4_minor_version_ops {
 			const nfs4_stateid *);
 	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
 			struct nfs_fsinfo *);
-	int	(*free_lock_state)(struct nfs_server *,
+	void	(*free_lock_state)(struct nfs_server *,
 			struct nfs4_lock_state *);
 	const struct rpc_call_ops *call_sync_ops;
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
@@ -129,27 +129,17 @@ enum {
  * LOCK: one nfs4_state (LOCK) to hold the lock stateid nfs4_state(OPEN)
  */
 
-struct nfs4_lock_owner {
-	unsigned int lo_type;
-#define NFS4_ANY_LOCK_TYPE	(0U)
-#define NFS4_FLOCK_LOCK_TYPE	(1U << 0)
-#define NFS4_POSIX_LOCK_TYPE	(1U << 1)
-	union {
-		fl_owner_t posix_owner;
-		pid_t flock_owner;
-	} lo_u;
-};
-
 struct nfs4_lock_state {
-	struct list_head	ls_locks;	/* Other lock stateids */
-	struct nfs4_state *	ls_state;	/* Pointer to open state */
+	struct list_head		ls_locks;   /* Other lock stateids */
+	struct nfs4_state *		ls_state;   /* Pointer to open state */
 #define NFS_LOCK_INITIALIZED 0
 #define NFS_LOCK_LOST        1
-	unsigned long		ls_flags;
+	unsigned long			ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
-	nfs4_stateid		ls_stateid;
-	atomic_t		ls_count;
-	struct nfs4_lock_owner	ls_owner;
+	nfs4_stateid			ls_stateid;
+	atomic_t			ls_count;
+	fl_owner_t			ls_owner;
+	struct work_struct		ls_release;
 };
 
 /* bits for nfs4_state->flags */
@@ -337,11 +327,11 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
  */
 static inline void
 nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
-			 struct rpc_message *msg, struct nfs_pgio_data *wdata)
+			 struct rpc_message *msg, struct nfs_pgio_header *hdr)
 {
 	if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) &&
 	    !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags))
-		wdata->args.stable = NFS_FILE_SYNC;
+		hdr->args.stable = NFS_FILE_SYNC;
 }
 #else /* CONFIG_NFS_v4_1 */
 static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
@@ -369,7 +359,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags,
 
 static inline void
 nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
-			 struct rpc_message *msg, struct nfs_pgio_data *wdata)
+			 struct rpc_message *msg, struct nfs_pgio_header *hdr)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */

fs/nfs/nfs4client.c

@@ -855,6 +855,11 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	};
 	struct rpc_timeout ds_timeout;
 	struct nfs_client *clp;
+	char buf[INET6_ADDRSTRLEN + 1];
+
+	if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
+		return ERR_PTR(-EINVAL);
+	cl_init.hostname = buf;
 
 	/*
 	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client

fs/nfs/nfs4state.c

@@ -787,33 +787,36 @@ void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode)
  * that is compatible with current->files
  */
 static struct nfs4_lock_state *
-__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
+__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 {
 	struct nfs4_lock_state *pos;
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
-		if (type != NFS4_ANY_LOCK_TYPE && pos->ls_owner.lo_type != type)
+		if (pos->ls_owner != fl_owner)
 			continue;
-		switch (pos->ls_owner.lo_type) {
-		case NFS4_POSIX_LOCK_TYPE:
-			if (pos->ls_owner.lo_u.posix_owner != fl_owner)
-				continue;
-			break;
-		case NFS4_FLOCK_LOCK_TYPE:
-			if (pos->ls_owner.lo_u.flock_owner != fl_pid)
-				continue;
-		}
 		atomic_inc(&pos->ls_count);
 		return pos;
 	}
 	return NULL;
 }
 
+static void
+free_lock_state_work(struct work_struct *work)
+{
+	struct nfs4_lock_state *lsp = container_of(work,
+					struct nfs4_lock_state, ls_release);
+	struct nfs4_state *state = lsp->ls_state;
+	struct nfs_server *server = state->owner->so_server;
+	struct nfs_client *clp = server->nfs_client;
+
+	clp->cl_mvops->free_lock_state(server, lsp);
+}
+
 /*
  * Return a compatible lock_state. If no initialized lock_state structure
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
+static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 {
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = state->owner->so_server;
@@ -824,21 +827,12 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 	nfs4_init_seqid_counter(&lsp->ls_seqid);
 	atomic_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
-	lsp->ls_owner.lo_type = type;
-	switch (lsp->ls_owner.lo_type) {
-	case NFS4_FLOCK_LOCK_TYPE:
-		lsp->ls_owner.lo_u.flock_owner = fl_pid;
-		break;
-	case NFS4_POSIX_LOCK_TYPE:
-		lsp->ls_owner.lo_u.posix_owner = fl_owner;
-		break;
-	default:
-		goto out_free;
-	}
+	lsp->ls_owner = fl_owner;
 	lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
 	if (lsp->ls_seqid.owner_id < 0)
 		goto out_free;
 	INIT_LIST_HEAD(&lsp->ls_locks);
+	INIT_WORK(&lsp->ls_release, free_lock_state_work);
 	return lsp;
 out_free:
 	kfree(lsp);
@@ -857,13 +851,13 @@ void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner, pid_t pid, unsigned int type)
+static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner)
 {
 	struct nfs4_lock_state *lsp, *new = NULL;
 	
 	for(;;) {
 		spin_lock(&state->state_lock);
-		lsp = __nfs4_find_lock_state(state, owner, pid, type);
+		lsp = __nfs4_find_lock_state(state, owner);
 		if (lsp != NULL)
 			break;
 		if (new != NULL) {
@@ -874,7 +868,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_
 			break;
 		}
 		spin_unlock(&state->state_lock);
-		new = nfs4_alloc_lock_state(state, owner, pid, type);
+		new = nfs4_alloc_lock_state(state, owner);
 		if (new == NULL)
 			return NULL;
 	}
@@ -902,13 +896,12 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
 	if (list_empty(&state->lock_states))
 		clear_bit(LK_STATE_IN_USE, &state->flags);
 	spin_unlock(&state->state_lock);
-	server = state->owner->so_server;
-	if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
-		struct nfs_client *clp = server->nfs_client;
-
-		clp->cl_mvops->free_lock_state(server, lsp);
-	} else
+	if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags))
+		queue_work(nfsiod_workqueue, &lsp->ls_release);
+	else {
+		server = state->owner->so_server;
 		nfs4_free_lock_state(server, lsp);
+	}
 }
 
 static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
@@ -935,13 +928,7 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 
 	if (fl->fl_ops != NULL)
 		return 0;
-	if (fl->fl_flags & FL_POSIX)
-		lsp = nfs4_get_lock_state(state, fl->fl_owner, 0, NFS4_POSIX_LOCK_TYPE);
-	else if (fl->fl_flags & FL_FLOCK)
-		lsp = nfs4_get_lock_state(state, NULL, fl->fl_pid,
-				NFS4_FLOCK_LOCK_TYPE);
-	else
-		return -EINVAL;
+	lsp = nfs4_get_lock_state(state, fl->fl_owner);
 	if (lsp == NULL)
 		return -ENOMEM;
 	fl->fl_u.nfs4_fl.owner = lsp;
@@ -955,7 +942,6 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 {
 	struct nfs4_lock_state *lsp;
 	fl_owner_t fl_owner;
-	pid_t fl_pid;
 	int ret = -ENOENT;
 
 
@@ -966,9 +952,8 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 		goto out;
 
 	fl_owner = lockowner->l_owner;
-	fl_pid = lockowner->l_pid;
 	spin_lock(&state->state_lock);
-	lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
+	lsp = __nfs4_find_lock_state(state, fl_owner);
 	if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
 		ret = -EIO;
 	else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {

fs/nfs/nfs4trace.h

@@ -932,11 +932,11 @@ DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group);
 
 DECLARE_EVENT_CLASS(nfs4_read_event,
 		TP_PROTO(
-			const struct nfs_pgio_data *data,
+			const struct nfs_pgio_header *hdr,
 			int error
 		),
 
-		TP_ARGS(data, error),
+		TP_ARGS(hdr, error),
 
 		TP_STRUCT__entry(
 			__field(dev_t, dev)
@@ -948,12 +948,12 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 		),
 
 		TP_fast_assign(
-			const struct inode *inode = data->header->inode;
+			const struct inode *inode = hdr->inode;
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
-			__entry->offset = data->args.offset;
-			__entry->count = data->args.count;
+			__entry->offset = hdr->args.offset;
+			__entry->count = hdr->args.count;
 			__entry->error = error;
 		),
 
@@ -972,10 +972,10 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 #define DEFINE_NFS4_READ_EVENT(name) \
 	DEFINE_EVENT(nfs4_read_event, name, \
 			TP_PROTO( \
-				const struct nfs_pgio_data *data, \
+				const struct nfs_pgio_header *hdr, \
 				int error \
 			), \
-			TP_ARGS(data, error))
+			TP_ARGS(hdr, error))
 DEFINE_NFS4_READ_EVENT(nfs4_read);
 #ifdef CONFIG_NFS_V4_1
 DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read);
@@ -983,11 +983,11 @@ DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read);
 
 DECLARE_EVENT_CLASS(nfs4_write_event,
 		TP_PROTO(
-			const struct nfs_pgio_data *data,
+			const struct nfs_pgio_header *hdr,
 			int error
 		),
 
-		TP_ARGS(data, error),
+		TP_ARGS(hdr, error),
 
 		TP_STRUCT__entry(
 			__field(dev_t, dev)
@@ -999,12 +999,12 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 		),
 
 		TP_fast_assign(
-			const struct inode *inode = data->header->inode;
+			const struct inode *inode = hdr->inode;
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
-			__entry->offset = data->args.offset;
-			__entry->count = data->args.count;
+			__entry->offset = hdr->args.offset;
+			__entry->count = hdr->args.count;
 			__entry->error = error;
 		),
 
@@ -1024,10 +1024,10 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 #define DEFINE_NFS4_WRITE_EVENT(name) \
 	DEFINE_EVENT(nfs4_write_event, name, \
 			TP_PROTO( \
-				const struct nfs_pgio_data *data, \
+				const struct nfs_pgio_header *hdr, \
 				int error \
 			), \
-			TP_ARGS(data, error))
+			TP_ARGS(hdr, error))
 DEFINE_NFS4_WRITE_EVENT(nfs4_write);
 #ifdef CONFIG_NFS_V4_1
 DEFINE_NFS4_WRITE_EVENT(nfs4_pnfs_write);

fs/nfs/nfs4xdr.c

@@ -7092,7 +7092,7 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
 	if (!status)
 		status = decode_sequence(xdr, &res->seq_res, rqstp);
 	if (!status)
-		status = decode_reclaim_complete(xdr, (void *)NULL);
+		status = decode_reclaim_complete(xdr, NULL);
 	return status;
 }
 

fs/nfs/objlayout/objio_osd.c

@@ -439,22 +439,21 @@ static void _read_done(struct ore_io_state *ios, void *private)
 	objlayout_read_done(&objios->oir, status, objios->sync);
 }
 
-int objio_read_pagelist(struct nfs_pgio_data *rdata)
+int objio_read_pagelist(struct nfs_pgio_header *hdr)
 {
-	struct nfs_pgio_header *hdr = rdata->header;
 	struct objio_state *objios;
 	int ret;
 
 	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
-			hdr->lseg, rdata->args.pages, rdata->args.pgbase,
-			rdata->args.offset, rdata->args.count, rdata,
+			hdr->lseg, hdr->args.pages, hdr->args.pgbase,
+			hdr->args.offset, hdr->args.count, hdr,
 			GFP_KERNEL, &objios);
 	if (unlikely(ret))
 		return ret;
 
 	objios->ios->done = _read_done;
 	dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
-		rdata->args.offset, rdata->args.count);
+		hdr->args.offset, hdr->args.count);
 	ret = ore_read(objios->ios);
 	if (unlikely(ret))
 		objio_free_result(&objios->oir);
@@ -487,11 +486,11 @@ static void _write_done(struct ore_io_state *ios, void *private)
 static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 {
 	struct objio_state *objios = priv;
-	struct nfs_pgio_data *wdata = objios->oir.rpcdata;
-	struct address_space *mapping = wdata->header->inode->i_mapping;
+	struct nfs_pgio_header *hdr = objios->oir.rpcdata;
+	struct address_space *mapping = hdr->inode->i_mapping;
 	pgoff_t index = offset / PAGE_SIZE;
 	struct page *page;
-	loff_t i_size = i_size_read(wdata->header->inode);
+	loff_t i_size = i_size_read(hdr->inode);
 
 	if (offset >= i_size) {
 		*uptodate = true;
@@ -531,15 +530,14 @@ static const struct _ore_r4w_op _r4w_op = {
 	.put_page = &__r4w_put_page,
 };
 
-int objio_write_pagelist(struct nfs_pgio_data *wdata, int how)
+int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
 {
-	struct nfs_pgio_header *hdr = wdata->header;
 	struct objio_state *objios;
 	int ret;
 
 	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
-			hdr->lseg, wdata->args.pages, wdata->args.pgbase,
-			wdata->args.offset, wdata->args.count, wdata, GFP_NOFS,
+			hdr->lseg, hdr->args.pages, hdr->args.pgbase,
+			hdr->args.offset, hdr->args.count, hdr, GFP_NOFS,
 			&objios);
 	if (unlikely(ret))
 		return ret;
@@ -551,7 +549,7 @@ int objio_write_pagelist(struct nfs_pgio_data *wdata, int how)
 		objios->ios->done = _write_done;
 
 	dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
-		wdata->args.offset, wdata->args.count);
+		hdr->args.offset, hdr->args.count);
 	ret = ore_write(objios->ios);
 	if (unlikely(ret)) {
 		objio_free_result(&objios->oir);

fs/nfs/objlayout/objlayout.c

@@ -229,36 +229,36 @@ objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
 static void _rpc_read_complete(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_pgio_data *rdata;
+	struct nfs_pgio_header *hdr;
 
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	rdata = container_of(task, struct nfs_pgio_data, task);
+	hdr = container_of(task, struct nfs_pgio_header, task);
 
-	pnfs_ld_read_done(rdata);
+	pnfs_ld_read_done(hdr);
 }
 
 void
 objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 {
-	struct nfs_pgio_data *rdata = oir->rpcdata;
+	struct nfs_pgio_header *hdr = oir->rpcdata;
 
-	oir->status = rdata->task.tk_status = status;
+	oir->status = hdr->task.tk_status = status;
 	if (status >= 0)
-		rdata->res.count = status;
+		hdr->res.count = status;
 	else
-		rdata->header->pnfs_error = status;
+		hdr->pnfs_error = status;
 	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);
+		status, hdr->res.eof, sync);
 
 	if (sync)
-		pnfs_ld_read_done(rdata);
+		pnfs_ld_read_done(hdr);
 	else {
-		INIT_WORK(&rdata->task.u.tk_work, _rpc_read_complete);
-		schedule_work(&rdata->task.u.tk_work);
+		INIT_WORK(&hdr->task.u.tk_work, _rpc_read_complete);
+		schedule_work(&hdr->task.u.tk_work);
 	}
 }
 
@@ -266,12 +266,11 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
  * Perform sync or async reads.
  */
 enum pnfs_try_status
-objlayout_read_pagelist(struct nfs_pgio_data *rdata)
+objlayout_read_pagelist(struct nfs_pgio_header *hdr)
 {
-	struct nfs_pgio_header *hdr = rdata->header;
 	struct inode *inode = hdr->inode;
-	loff_t offset = rdata->args.offset;
-	size_t count = rdata->args.count;
+	loff_t offset = hdr->args.offset;
+	size_t count = hdr->args.count;
 	int err;
 	loff_t eof;
 
@@ -279,23 +278,23 @@ objlayout_read_pagelist(struct nfs_pgio_data *rdata)
 	if (unlikely(offset + count > eof)) {
 		if (offset >= eof) {
 			err = 0;
-			rdata->res.count = 0;
-			rdata->res.eof = 1;
+			hdr->res.count = 0;
+			hdr->res.eof = 1;
 			/*FIXME: do we need to call pnfs_ld_read_done() */
 			goto out;
 		}
 		count = eof - offset;
 	}
 
-	rdata->res.eof = (offset + count) >= eof;
-	_fix_verify_io_params(hdr->lseg, &rdata->args.pages,
-			      &rdata->args.pgbase,
-			      rdata->args.offset, rdata->args.count);
+	hdr->res.eof = (offset + count) >= eof;
+	_fix_verify_io_params(hdr->lseg, &hdr->args.pages,
+			      &hdr->args.pgbase,
+			      hdr->args.offset, hdr->args.count);
 
 	dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
-		__func__, inode->i_ino, offset, count, rdata->res.eof);
+		__func__, inode->i_ino, offset, count, hdr->res.eof);
 
-	err = objio_read_pagelist(rdata);
+	err = objio_read_pagelist(hdr);
  out:
 	if (unlikely(err)) {
 		hdr->pnfs_error = err;
@@ -312,38 +311,38 @@ objlayout_read_pagelist(struct nfs_pgio_data *rdata)
 static void _rpc_write_complete(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_pgio_data *wdata;
+	struct nfs_pgio_header *hdr;
 
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	wdata = container_of(task, struct nfs_pgio_data, task);
+	hdr = container_of(task, struct nfs_pgio_header, task);
 
-	pnfs_ld_write_done(wdata);
+	pnfs_ld_write_done(hdr);
 }
 
 void
 objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 {
-	struct nfs_pgio_data *wdata = oir->rpcdata;
+	struct nfs_pgio_header *hdr = oir->rpcdata;
 
-	oir->status = wdata->task.tk_status = status;
+	oir->status = hdr->task.tk_status = status;
 	if (status >= 0) {
-		wdata->res.count = status;
-		wdata->verf.committed = oir->committed;
+		hdr->res.count = status;
+		hdr->verf.committed = oir->committed;
 	} else {
-		wdata->header->pnfs_error = status;
+		hdr->pnfs_error = status;
 	}
 	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);
+		status, hdr->verf.committed, sync);
 
 	if (sync)
-		pnfs_ld_write_done(wdata);
+		pnfs_ld_write_done(hdr);
 	else {
-		INIT_WORK(&wdata->task.u.tk_work, _rpc_write_complete);
-		schedule_work(&wdata->task.u.tk_work);
+		INIT_WORK(&hdr->task.u.tk_work, _rpc_write_complete);
+		schedule_work(&hdr->task.u.tk_work);
 	}
 }
 
@@ -351,17 +350,15 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
  * Perform sync or async writes.
  */
 enum pnfs_try_status
-objlayout_write_pagelist(struct nfs_pgio_data *wdata,
-			 int how)
+objlayout_write_pagelist(struct nfs_pgio_header *hdr, int how)
 {
-	struct nfs_pgio_header *hdr = wdata->header;
 	int err;
 
-	_fix_verify_io_params(hdr->lseg, &wdata->args.pages,
-			      &wdata->args.pgbase,
-			      wdata->args.offset, wdata->args.count);
+	_fix_verify_io_params(hdr->lseg, &hdr->args.pages,
+			      &hdr->args.pgbase,
+			      hdr->args.offset, hdr->args.count);
 
-	err = objio_write_pagelist(wdata, how);
+	err = objio_write_pagelist(hdr, how);
 	if (unlikely(err)) {
 		hdr->pnfs_error = err;
 		dprintk("%s: Returned Error %d\n", __func__, err);

fs/nfs/objlayout/objlayout.h

@@ -119,8 +119,8 @@ extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
  */
 extern void objio_free_result(struct objlayout_io_res *oir);
 
-extern int objio_read_pagelist(struct nfs_pgio_data *rdata);
-extern int objio_write_pagelist(struct nfs_pgio_data *wdata, int how);
+extern int objio_read_pagelist(struct nfs_pgio_header *rdata);
+extern int objio_write_pagelist(struct nfs_pgio_header *wdata, int how);
 
 /*
  * callback API
@@ -168,10 +168,10 @@ extern struct pnfs_layout_segment *objlayout_alloc_lseg(
 extern void objlayout_free_lseg(struct pnfs_layout_segment *);
 
 extern enum pnfs_try_status objlayout_read_pagelist(
-	struct nfs_pgio_data *);
+	struct nfs_pgio_header *);
 
 extern enum pnfs_try_status objlayout_write_pagelist(
-	struct nfs_pgio_data *,
+	struct nfs_pgio_header *,
 	int how);
 
 extern void objlayout_encode_layoutcommit(

fs/nfs/pnfs.h

@@ -32,6 +32,7 @@
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
+#include <linux/workqueue.h>
 
 enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
@@ -46,6 +47,7 @@ struct pnfs_layout_segment {
 	atomic_t pls_refcount;
 	unsigned long pls_flags;
 	struct pnfs_layout_hdr *pls_layout;
+	struct work_struct pls_work;
 };
 
 enum pnfs_try_status {
@@ -104,6 +106,8 @@ struct pnfs_layoutdriver_type {
 				  int max);
 	void (*recover_commit_reqs) (struct list_head *list,
 				     struct nfs_commit_info *cinfo);
+	struct nfs_page * (*search_commit_reqs)(struct nfs_commit_info *cinfo,
+						struct page *page);
 	int (*commit_pagelist)(struct inode *inode,
 			       struct list_head *mds_pages,
 			       int how,
@@ -113,8 +117,8 @@ struct pnfs_layoutdriver_type {
 	 * Return PNFS_ATTEMPTED to indicate the layout code has attempted
 	 * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
 	 */
-	enum pnfs_try_status (*read_pagelist) (struct nfs_pgio_data *nfs_data);
-	enum pnfs_try_status (*write_pagelist) (struct nfs_pgio_data *nfs_data, int how);
+	enum pnfs_try_status (*read_pagelist)(struct nfs_pgio_header *);
+	enum pnfs_try_status (*write_pagelist)(struct nfs_pgio_header *, int);
 
 	void (*free_deviceid_node) (struct nfs4_deviceid_node *);
 
@@ -179,6 +183,7 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 /* pnfs.c */
 void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
+void pnfs_put_lseg_async(struct pnfs_layout_segment *lseg);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
@@ -213,13 +218,13 @@ bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
-void pnfs_set_layoutcommit(struct nfs_pgio_data *wdata);
+void pnfs_set_layoutcommit(struct nfs_pgio_header *);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
-void pnfs_ld_write_done(struct nfs_pgio_data *);
-void pnfs_ld_read_done(struct nfs_pgio_data *);
+void pnfs_ld_write_done(struct nfs_pgio_header *);
+void pnfs_ld_read_done(struct nfs_pgio_header *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
@@ -228,12 +233,8 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       gfp_t gfp_flags);
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
-int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head,
-			const struct nfs_pgio_completion_ops *compl_ops,
-			struct nfs_direct_req *dreq);
-int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head,
-			const struct nfs_pgio_completion_ops *compl_ops,
-			struct nfs_direct_req *dreq);
+int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *);
+int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *);
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 
 /* nfs4_deviceid_flags */
@@ -345,6 +346,17 @@ pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
 	NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
 }
 
+static inline struct nfs_page *
+pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
+			struct page *page)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+	if (ld == NULL || ld->search_commit_reqs == NULL)
+		return NULL;
+	return ld->search_commit_reqs(cinfo, page);
+}
+
 /* Should the pNFS client commit and return the layout upon a setattr */
 static inline bool
 pnfs_ld_layoutret_on_setattr(struct inode *inode)
@@ -410,6 +422,10 @@ static inline void pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
 }
 
+static inline void pnfs_put_lseg_async(struct pnfs_layout_segment *lseg)
+{
+}
+
 static inline int pnfs_return_layout(struct inode *ino)
 {
 	return 0;
@@ -496,6 +512,13 @@ pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
 {
 }
 
+static inline struct nfs_page *
+pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
+			struct page *page)
+{
+	return NULL;
+}
+
 static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	return 0;

fs/nfs/proc.c

@@ -578,46 +578,49 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return 0;
 }
 
-static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
+static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = data->header->inode;
+	struct inode *inode = hdr->inode;
 
 	nfs_invalidate_atime(inode);
 	if (task->tk_status >= 0) {
-		nfs_refresh_inode(inode, data->res.fattr);
+		nfs_refresh_inode(inode, hdr->res.fattr);
 		/* Emulate the eof flag, which isn't normally needed in NFSv2
 		 * as it is guaranteed to always return the file attributes
 		 */
-		if (data->args.offset + data->res.count >= data->res.fattr->size)
-			data->res.eof = 1;
+		if (hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
+			hdr->res.eof = 1;
 	}
 	return 0;
 }
 
-static void nfs_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
+static void nfs_proc_read_setup(struct nfs_pgio_header *hdr,
+				struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs_procedures[NFSPROC_READ];
 }
 
-static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
+static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task,
+				     struct nfs_pgio_header *hdr)
 {
 	rpc_call_start(task);
 	return 0;
 }
 
-static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
+static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = data->header->inode;
+	struct inode *inode = hdr->inode;
 
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
+		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
 	return 0;
 }
 
-static void nfs_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
+static void nfs_proc_write_setup(struct nfs_pgio_header *hdr,
+				 struct rpc_message *msg)
 {
 	/* Note: NFSv2 ignores @stable and always uses NFS_FILE_SYNC */
-	data->args.stable = NFS_FILE_SYNC;
+	hdr->args.stable = NFS_FILE_SYNC;
 	msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE];
 }
 

fs/nfs/read.c

@@ -33,12 +33,12 @@ static const struct nfs_rw_ops nfs_rw_read_ops;
 
 static struct kmem_cache *nfs_rdata_cachep;
 
-static struct nfs_rw_header *nfs_readhdr_alloc(void)
+static struct nfs_pgio_header *nfs_readhdr_alloc(void)
 {
 	return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
 }
 
-static void nfs_readhdr_free(struct nfs_rw_header *rhdr)
+static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
 {
 	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
@@ -115,12 +115,6 @@ static void nfs_readpage_release(struct nfs_page *req)
 
 		unlock_page(req->wb_page);
 	}
-
-	dprintk("NFS: read done (%s/%Lu %d@%Ld)\n",
-			req->wb_context->dentry->d_inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
-			req->wb_bytes,
-			(long long)req_offset(req));
 	nfs_release_request(req);
 }
 
@@ -172,14 +166,15 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
 	hdr->release(hdr);
 }
 
-static void nfs_initiate_read(struct nfs_pgio_data *data, struct rpc_message *msg,
+static void nfs_initiate_read(struct nfs_pgio_header *hdr,
+			      struct rpc_message *msg,
 			      struct rpc_task_setup *task_setup_data, int how)
 {
-	struct inode *inode = data->header->inode;
+	struct inode *inode = hdr->inode;
 	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
 
 	task_setup_data->flags |= swap_flags;
-	NFS_PROTO(inode)->read_setup(data, msg);
+	NFS_PROTO(inode)->read_setup(hdr, msg);
 }
 
 static void
@@ -203,14 +198,15 @@ static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
  * This is the callback from RPC telling us whether a reply was
  * received or some error occurred (timeout or socket shutdown).
  */
-static int nfs_readpage_done(struct rpc_task *task, struct nfs_pgio_data *data,
+static int nfs_readpage_done(struct rpc_task *task,
+			     struct nfs_pgio_header *hdr,
 			     struct inode *inode)
 {
-	int status = NFS_PROTO(inode)->read_done(task, data);
+	int status = NFS_PROTO(inode)->read_done(task, hdr);
 	if (status != 0)
 		return status;
 
-	nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count);
+	nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, hdr->res.count);
 
 	if (task->tk_status == -ESTALE) {
 		set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
@@ -219,34 +215,34 @@ static int nfs_readpage_done(struct rpc_task *task, struct nfs_pgio_data *data,
 	return 0;
 }
 
-static void nfs_readpage_retry(struct rpc_task *task, struct nfs_pgio_data *data)
+static void nfs_readpage_retry(struct rpc_task *task,
+			       struct nfs_pgio_header *hdr)
 {
-	struct nfs_pgio_args *argp = &data->args;
-	struct nfs_pgio_res  *resp = &data->res;
+	struct nfs_pgio_args *argp = &hdr->args;
+	struct nfs_pgio_res  *resp = &hdr->res;
 
 	/* This is a short read! */
-	nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD);
+	nfs_inc_stats(hdr->inode, NFSIOS_SHORTREAD);
 	/* Has the server at least made some progress? */
 	if (resp->count == 0) {
-		nfs_set_pgio_error(data->header, -EIO, argp->offset);
+		nfs_set_pgio_error(hdr, -EIO, argp->offset);
 		return;
 	}
-	/* Yes, so retry the read at the end of the data */
-	data->mds_offset += resp->count;
+	/* Yes, so retry the read at the end of the hdr */
+	hdr->mds_offset += resp->count;
 	argp->offset += resp->count;
 	argp->pgbase += resp->count;
 	argp->count -= resp->count;
 	rpc_restart_call_prepare(task);
 }
 
-static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_data *data)
+static void nfs_readpage_result(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
 {
-	struct nfs_pgio_header *hdr = data->header;
-
-	if (data->res.eof) {
+	if (hdr->res.eof) {
 		loff_t bound;
 
-		bound = data->args.offset + data->res.count;
+		bound = hdr->args.offset + hdr->res.count;
 		spin_lock(&hdr->lock);
 		if (bound < hdr->io_start + hdr->good_bytes) {
 			set_bit(NFS_IOHDR_EOF, &hdr->flags);
@@ -254,8 +250,8 @@ static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_data *dat
 			hdr->good_bytes = bound - hdr->io_start;
 		}
 		spin_unlock(&hdr->lock);
-	} else if (data->res.count != data->args.count)
-		nfs_readpage_retry(task, data);
+	} else if (hdr->res.count != hdr->args.count)
+		nfs_readpage_retry(task, hdr);
 }
 
 /*
@@ -404,7 +400,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 int __init nfs_init_readpagecache(void)
 {
 	nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
-					     sizeof(struct nfs_rw_header),
+					     sizeof(struct nfs_pgio_header),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_rdata_cachep == NULL)

fs/nfs/super.c

@@ -1027,8 +1027,7 @@ static bool nfs_auth_info_add(struct nfs_auth_info *auth_info,
 			      rpc_authflavor_t flavor)
 {
 	unsigned int i;
-	unsigned int max_flavor_len = (sizeof(auth_info->flavors) /
-				       sizeof(auth_info->flavors[0]));
+	unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors);
 
 	/* make sure this flavor isn't already in the list */
 	for (i = 0; i < auth_info->flavor_len; i++) {
@@ -2180,7 +2179,7 @@ static int nfs_validate_text_mount_data(void *options,
 	return -EINVAL;
 }
 
-#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
+#define NFS_REMOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
 		| NFS_MOUNT_SECURE \
 		| NFS_MOUNT_TCP \
 		| NFS_MOUNT_VER3 \
@@ -2188,15 +2187,16 @@ static int nfs_validate_text_mount_data(void *options,
 		| NFS_MOUNT_NONLM \
 		| NFS_MOUNT_BROKEN_SUID \
 		| NFS_MOUNT_STRICTLOCK \
-		| NFS_MOUNT_UNSHARED \
-		| NFS_MOUNT_NORESVPORT \
 		| NFS_MOUNT_LEGACY_INTERFACE)
 
+#define NFS_MOUNT_CMP_FLAGMASK (NFS_REMOUNT_CMP_FLAGMASK & \
+		~(NFS_MOUNT_UNSHARED | NFS_MOUNT_NORESVPORT))
+
 static int
 nfs_compare_remount_data(struct nfs_server *nfss,
 			 struct nfs_parsed_mount_data *data)
 {
-	if ((data->flags ^ nfss->flags) & NFS_MOUNT_CMP_FLAGMASK ||
+	if ((data->flags ^ nfss->flags) & NFS_REMOUNT_CMP_FLAGMASK ||
 	    data->rsize != nfss->rsize ||
 	    data->wsize != nfss->wsize ||
 	    data->version != nfss->nfs_client->rpc_ops->version ||

fs/nfs_common/nfsacl.c

@@ -30,9 +30,6 @@
 
 MODULE_LICENSE("GPL");
 
-EXPORT_SYMBOL_GPL(nfsacl_encode);
-EXPORT_SYMBOL_GPL(nfsacl_decode);
-
 struct nfsacl_encode_desc {
 	struct xdr_array2_desc desc;
 	unsigned int count;
@@ -136,6 +133,7 @@ int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
 			  nfsacl_desc.desc.array_len;
 	return err;
 }
+EXPORT_SYMBOL_GPL(nfsacl_encode);
 
 struct nfsacl_decode_desc {
 	struct xdr_array2_desc desc;
@@ -295,3 +293,4 @@ int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt,
 	return 8 + nfsacl_desc.desc.elem_size *
 		   nfsacl_desc.desc.array_len;
 }
+EXPORT_SYMBOL_GPL(nfsacl_decode);

include/linux/nfs_fs.h

@@ -52,6 +52,7 @@ struct nfs_access_entry {
 	unsigned long		jiffies;
 	struct rpc_cred *	cred;
 	int			mask;
+	struct rcu_head		rcu_head;
 };
 
 struct nfs_lockowner {
@@ -352,6 +353,7 @@ extern int nfs_release(struct inode *, struct file *);
 extern int nfs_attribute_timeout(struct inode *inode);
 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_rcu(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);

include/linux/nfs_fs_sb.h

@@ -45,6 +45,7 @@ struct nfs_client {
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
+	char *			cl_acceptor;	/* GSSAPI acceptor name */
 	struct list_head	cl_share_link;	/* link in global client list */
 	struct list_head	cl_superblocks;	/* List of nfs_server structs */
 

include/linux/nfs_page.h

@@ -26,7 +26,7 @@ enum {
 	PG_MAPPED,		/* page private set for buffered io */
 	PG_CLEAN,		/* write succeeded */
 	PG_COMMIT_TO_DS,	/* used by pnfs layouts */
-	PG_INODE_REF,		/* extra ref held by inode (head req only) */
+	PG_INODE_REF,		/* extra ref held by inode when in writeback */
 	PG_HEADLOCK,		/* page group lock of wb_head */
 	PG_TEARDOWN,		/* page group sync for destroy */
 	PG_UNLOCKPAGE,		/* page group sync bit in read path */
@@ -62,12 +62,13 @@ struct nfs_pageio_ops {
 
 struct nfs_rw_ops {
 	const fmode_t rw_mode;
-	struct nfs_rw_header *(*rw_alloc_header)(void);
-	void (*rw_free_header)(struct nfs_rw_header *);
-	void (*rw_release)(struct nfs_pgio_data *);
-	int  (*rw_done)(struct rpc_task *, struct nfs_pgio_data *, struct inode *);
-	void (*rw_result)(struct rpc_task *, struct nfs_pgio_data *);
-	void (*rw_initiate)(struct nfs_pgio_data *, struct rpc_message *,
+	struct nfs_pgio_header *(*rw_alloc_header)(void);
+	void (*rw_free_header)(struct nfs_pgio_header *);
+	void (*rw_release)(struct nfs_pgio_header *);
+	int  (*rw_done)(struct rpc_task *, struct nfs_pgio_header *,
+			struct inode *);
+	void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *);
+	void (*rw_initiate)(struct nfs_pgio_header *, struct rpc_message *,
 			    struct rpc_task_setup *, int);
 };
 
@@ -111,6 +112,8 @@ extern	void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 			     int how);
 extern	int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
 				   struct nfs_page *);
+extern  int nfs_pageio_resend(struct nfs_pageio_descriptor *,
+			      struct nfs_pgio_header *);
 extern	void nfs_pageio_complete(struct nfs_pageio_descriptor *desc);
 extern	void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t);
 extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
@@ -119,7 +122,7 @@ extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
 extern	void nfs_unlock_and_release_request(struct nfs_page *);
-extern void nfs_page_group_lock(struct nfs_page *);
+extern int nfs_page_group_lock(struct nfs_page *, bool);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
 

include/linux/nfs_xdr.h

@@ -993,6 +993,7 @@ struct nfs4_setclientid {
 	unsigned int			sc_uaddr_len;
 	char				sc_uaddr[RPCBIND_MAXUADDRLEN + 1];
 	u32				sc_cb_ident;
+	struct rpc_cred			*sc_cred;
 };
 
 struct nfs4_setclientid_res {
@@ -1253,18 +1254,12 @@ enum {
 	NFS_IOHDR_ERROR = 0,
 	NFS_IOHDR_EOF,
 	NFS_IOHDR_REDO,
-	NFS_IOHDR_NEED_COMMIT,
-	NFS_IOHDR_NEED_RESCHED,
 };
 
-struct nfs_pgio_data;
-
 struct nfs_pgio_header {
 	struct inode		*inode;
 	struct rpc_cred		*cred;
 	struct list_head	pages;
-	struct nfs_pgio_data	*data;
-	atomic_t		refcnt;
 	struct nfs_page		*req;
 	struct nfs_writeverf	verf;		/* Used for writes */
 	struct pnfs_layout_segment *lseg;
@@ -1281,28 +1276,22 @@ struct nfs_pgio_header {
 	int			error;		/* merge with pnfs_error */
 	unsigned long		good_bytes;	/* boundary of good data */
 	unsigned long		flags;
-};
 
-struct nfs_pgio_data {
-	struct nfs_pgio_header	*header;
+	/*
+	 * rpc data
+	 */
 	struct rpc_task		task;
 	struct nfs_fattr	fattr;
-	struct nfs_writeverf	verf;		/* Used for writes */
 	struct nfs_pgio_args	args;		/* argument struct */
 	struct nfs_pgio_res	res;		/* result struct */
 	unsigned long		timestamp;	/* For lease renewal */
-	int (*pgio_done_cb) (struct rpc_task *task, struct nfs_pgio_data *data);
+	int (*pgio_done_cb)(struct rpc_task *, struct nfs_pgio_header *);
 	__u64			mds_offset;	/* Filelayout dense stripe */
-	struct nfs_page_array	pages;
+	struct nfs_page_array	page_array;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
 	int			ds_idx;		/* ds index if ds_clp is set */
 };
 
-struct nfs_rw_header {
-	struct nfs_pgio_header	header;
-	struct nfs_pgio_data	rpc_data;
-};
-
 struct nfs_mds_commit_info {
 	atomic_t rpcs_out;
 	unsigned long		ncommit;
@@ -1432,11 +1421,12 @@ struct nfs_rpc_ops {
 			     struct nfs_pathconf *);
 	int	(*set_capabilities)(struct nfs_server *, struct nfs_fh *);
 	int	(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int);
-	int	(*pgio_rpc_prepare)(struct rpc_task *, struct nfs_pgio_data *);
-	void	(*read_setup)   (struct nfs_pgio_data *, struct rpc_message *);
-	int	(*read_done)  (struct rpc_task *, struct nfs_pgio_data *);
-	void	(*write_setup)  (struct nfs_pgio_data *, struct rpc_message *);
-	int	(*write_done)  (struct rpc_task *, struct nfs_pgio_data *);
+	int	(*pgio_rpc_prepare)(struct rpc_task *,
+				    struct nfs_pgio_header *);
+	void	(*read_setup)(struct nfs_pgio_header *, struct rpc_message *);
+	int	(*read_done)(struct rpc_task *, struct nfs_pgio_header *);
+	void	(*write_setup)(struct nfs_pgio_header *, struct rpc_message *);
+	int	(*write_done)(struct rpc_task *, struct nfs_pgio_header *);
 	void	(*commit_setup) (struct nfs_commit_data *, struct rpc_message *);
 	void	(*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *);
 	int	(*commit_done) (struct rpc_task *, struct nfs_commit_data *);

include/linux/sunrpc/auth.h

@@ -103,6 +103,7 @@ struct rpc_auth_create_args {
 
 /* Flags for rpcauth_lookupcred() */
 #define RPCAUTH_LOOKUP_NEW		0x01	/* Accept an uninitialised cred */
+#define RPCAUTH_LOOKUP_RCU		0x02	/* lock-less lookup */
 
 /*
  * Client authentication ops
@@ -140,6 +141,7 @@ struct rpc_credops {
 						void *, __be32 *, void *);
 	int			(*crkey_timeout)(struct rpc_cred *);
 	bool			(*crkey_to_expire)(struct rpc_cred *);
+	char *			(*crstringify_acceptor)(struct rpc_cred *);
 };
 
 extern const struct rpc_authops	authunix_ops;
@@ -153,6 +155,7 @@ void			rpc_destroy_generic_auth(void);
 void 			rpc_destroy_authunix(void);
 
 struct rpc_cred *	rpc_lookup_cred(void);
+struct rpc_cred *	rpc_lookup_cred_nonblock(void);
 struct rpc_cred *	rpc_lookup_machine_cred(const char *service_name);
 int			rpcauth_register(const struct rpc_authops *);
 int			rpcauth_unregister(const struct rpc_authops *);
@@ -182,6 +185,7 @@ void			rpcauth_clear_credcache(struct rpc_cred_cache *);
 int			rpcauth_key_timeout_notify(struct rpc_auth *,
 						struct rpc_cred *);
 bool			rpcauth_cred_key_to_expire(struct rpc_cred *);
+char *			rpcauth_stringify_acceptor(struct rpc_cred *);
 
 static inline
 struct rpc_cred *	get_rpccred(struct rpc_cred *cred)

include/linux/sunrpc/auth_gss.h

@@ -69,8 +69,9 @@ struct gss_cl_ctx {
 	enum rpc_gss_proc	gc_proc;
 	u32			gc_seq;
 	spinlock_t		gc_seq_lock;
-	struct gss_ctx __rcu	*gc_gss_ctx;
+	struct gss_ctx		*gc_gss_ctx;
 	struct xdr_netobj	gc_wire_ctx;
+	struct xdr_netobj	gc_acceptor;
 	u32			gc_win;
 	unsigned long		gc_expiry;
 	struct rcu_head		gc_rcu;

include/linux/sunrpc/gss_krb5.h

@@ -81,7 +81,7 @@ struct gss_krb5_enctype {
 		       struct xdr_netobj *in,
 		       struct xdr_netobj *out);	/* complete key generation */
 	u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset,
-			   struct xdr_buf *buf, int ec,
+			   struct xdr_buf *buf,
 			   struct page **pages); /* v2 encryption function */
 	u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset,
 			   struct xdr_buf *buf, u32 *headskip,
@@ -310,7 +310,7 @@ gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e,
 
 u32
 gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
-		     struct xdr_buf *buf, int ec,
+		     struct xdr_buf *buf,
 		     struct page **pages);
 
 u32

include/linux/sunrpc/xprtrdma.h

@@ -62,8 +62,6 @@
 #define RPCRDMA_INLINE_PAD_THRESH  (512)/* payload threshold to pad (bytes) */
 
 /* memory registration strategies */
-#define RPCRDMA_PERSISTENT_REGISTRATION (1)
-
 enum rpcrdma_memreg {
 	RPCRDMA_BOUNCEBUFFERS = 0,
 	RPCRDMA_REGISTER,

net/sunrpc/addr.c

@@ -176,7 +176,7 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 	len = (buf + buflen) - delim - 1;
 	p = kstrndup(delim + 1, len, GFP_KERNEL);
 	if (p) {
-		unsigned long scope_id = 0;
+		u32 scope_id = 0;
 		struct net_device *dev;
 
 		dev = dev_get_by_name(net, p);
@@ -184,7 +184,7 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 			scope_id = dev->ifindex;
 			dev_put(dev);
 		} else {
-			if (strict_strtoul(p, 10, &scope_id) == 0) {
+			if (kstrtou32(p, 10, &scope_id) == 0) {
 				kfree(p);
 				return 0;
 			}
@@ -304,7 +304,7 @@ char *rpc_sockaddr2uaddr(const struct sockaddr *sap, gfp_t gfp_flags)
  * @sap: buffer into which to plant socket address
  * @salen: size of buffer
  *
- * @uaddr does not have to be '\0'-terminated, but strict_strtoul() and
+ * @uaddr does not have to be '\0'-terminated, but kstrtou8() and
  * rpc_pton() require proper string termination to be successful.
  *
  * Returns the size of the socket address if successful; otherwise
@@ -315,7 +315,7 @@ size_t rpc_uaddr2sockaddr(struct net *net, const char *uaddr,
 			  const size_t salen)
 {
 	char *c, buf[RPCBIND_MAXUADDRLEN + sizeof('\0')];
-	unsigned long portlo, porthi;
+	u8 portlo, porthi;
 	unsigned short port;
 
 	if (uaddr_len > RPCBIND_MAXUADDRLEN)
@@ -327,18 +327,14 @@ size_t rpc_uaddr2sockaddr(struct net *net, const char *uaddr,
 	c = strrchr(buf, '.');
 	if (unlikely(c == NULL))
 		return 0;
-	if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0))
-		return 0;
-	if (unlikely(portlo > 255))
+	if (unlikely(kstrtou8(c + 1, 10, &portlo) != 0))
 		return 0;
 
 	*c = '\0';
 	c = strrchr(buf, '.');
 	if (unlikely(c == NULL))
 		return 0;
-	if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0))
-		return 0;
-	if (unlikely(porthi > 255))
+	if (unlikely(kstrtou8(c + 1, 10, &porthi) != 0))
 		return 0;
 
 	port = (unsigned short)((porthi << 8) | portlo);

net/sunrpc/auth.c

@@ -48,7 +48,7 @@ static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp)
 
 	if (!val)
 		goto out_inval;
-	ret = strict_strtoul(val, 0, &num);
+	ret = kstrtoul(val, 0, &num);
 	if (ret == -EINVAL)
 		goto out_inval;
 	nbits = fls(num);
@@ -80,6 +80,10 @@ static struct kernel_param_ops param_ops_hashtbl_sz = {
 module_param_named(auth_hashtable_size, auth_hashbits, hashtbl_sz, 0644);
 MODULE_PARM_DESC(auth_hashtable_size, "RPC credential cache hashtable size");
 
+static unsigned long auth_max_cred_cachesize = ULONG_MAX;
+module_param(auth_max_cred_cachesize, ulong, 0644);
+MODULE_PARM_DESC(auth_max_cred_cachesize, "RPC credential maximum total cache size");
+
 static u32
 pseudoflavor_to_flavor(u32 flavor) {
 	if (flavor > RPC_AUTH_MAXFLAVOR)
@@ -363,6 +367,15 @@ rpcauth_cred_key_to_expire(struct rpc_cred *cred)
 }
 EXPORT_SYMBOL_GPL(rpcauth_cred_key_to_expire);
 
+char *
+rpcauth_stringify_acceptor(struct rpc_cred *cred)
+{
+	if (!cred->cr_ops->crstringify_acceptor)
+		return NULL;
+	return cred->cr_ops->crstringify_acceptor(cred);
+}
+EXPORT_SYMBOL_GPL(rpcauth_stringify_acceptor);
+
 /*
  * Destroy a list of credentials
  */
@@ -472,6 +485,20 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
 	return freed;
 }
 
+static unsigned long
+rpcauth_cache_do_shrink(int nr_to_scan)
+{
+	LIST_HEAD(free);
+	unsigned long freed;
+
+	spin_lock(&rpc_credcache_lock);
+	freed = rpcauth_prune_expired(&free, nr_to_scan);
+	spin_unlock(&rpc_credcache_lock);
+	rpcauth_destroy_credlist(&free);
+
+	return freed;
+}
+
 /*
  * Run memory cache shrinker.
  */
@@ -479,9 +506,6 @@ static unsigned long
 rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 
 {
-	LIST_HEAD(free);
-	unsigned long freed;
-
 	if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL)
 		return SHRINK_STOP;
 
@@ -489,12 +513,7 @@ rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	if (list_empty(&cred_unused))
 		return SHRINK_STOP;
 
-	spin_lock(&rpc_credcache_lock);
-	freed = rpcauth_prune_expired(&free, sc->nr_to_scan);
-	spin_unlock(&rpc_credcache_lock);
-	rpcauth_destroy_credlist(&free);
-
-	return freed;
+	return rpcauth_cache_do_shrink(sc->nr_to_scan);
 }
 
 static unsigned long
@@ -504,6 +523,21 @@ rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	return (number_cred_unused / 100) * sysctl_vfs_cache_pressure;
 }
 
+static void
+rpcauth_cache_enforce_limit(void)
+{
+	unsigned long diff;
+	unsigned int nr_to_scan;
+
+	if (number_cred_unused <= auth_max_cred_cachesize)
+		return;
+	diff = number_cred_unused - auth_max_cred_cachesize;
+	nr_to_scan = 100;
+	if (diff < nr_to_scan)
+		nr_to_scan = diff;
+	rpcauth_cache_do_shrink(nr_to_scan);
+}
+
 /*
  * Look up a process' credentials in the authentication cache
  */
@@ -523,6 +557,12 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
 	hlist_for_each_entry_rcu(entry, &cache->hashtable[nr], cr_hash) {
 		if (!entry->cr_ops->crmatch(acred, entry, flags))
 			continue;
+		if (flags & RPCAUTH_LOOKUP_RCU) {
+			if (test_bit(RPCAUTH_CRED_HASHED, &entry->cr_flags) &&
+			    !test_bit(RPCAUTH_CRED_NEW, &entry->cr_flags))
+				cred = entry;
+			break;
+		}
 		spin_lock(&cache->lock);
 		if (test_bit(RPCAUTH_CRED_HASHED, &entry->cr_flags) == 0) {
 			spin_unlock(&cache->lock);
@@ -537,6 +577,9 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
 	if (cred != NULL)
 		goto found;
 
+	if (flags & RPCAUTH_LOOKUP_RCU)
+		return ERR_PTR(-ECHILD);
+
 	new = auth->au_ops->crcreate(auth, acred, flags);
 	if (IS_ERR(new)) {
 		cred = new;
@@ -557,6 +600,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
 	} else
 		list_add_tail(&new->cr_lru, &free);
 	spin_unlock(&cache->lock);
+	rpcauth_cache_enforce_limit();
 found:
 	if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags) &&
 	    cred->cr_ops->cr_init != NULL &&
@@ -586,10 +630,8 @@ rpcauth_lookupcred(struct rpc_auth *auth, int flags)
 	memset(&acred, 0, sizeof(acred));
 	acred.uid = cred->fsuid;
 	acred.gid = cred->fsgid;
-	acred.group_info = get_group_info(((struct cred *)cred)->group_info);
-
+	acred.group_info = cred->group_info;
 	ret = auth->au_ops->lookup_cred(auth, &acred, flags);
-	put_group_info(acred.group_info);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(rpcauth_lookupcred);

net/sunrpc/auth_generic.c

@@ -38,6 +38,12 @@ struct rpc_cred *rpc_lookup_cred(void)
 }
 EXPORT_SYMBOL_GPL(rpc_lookup_cred);
 
+struct rpc_cred *rpc_lookup_cred_nonblock(void)
+{
+	return rpcauth_lookupcred(&generic_auth, RPCAUTH_LOOKUP_RCU);
+}
+EXPORT_SYMBOL_GPL(rpc_lookup_cred_nonblock);
+
 /*
  * Public call interface for looking up machine creds.
  */

net/sunrpc/auth_gss/auth_gss.c

@@ -183,8 +183,9 @@ gss_cred_get_ctx(struct rpc_cred *cred)
 	struct gss_cl_ctx *ctx = NULL;
 
 	rcu_read_lock();
-	if (gss_cred->gc_ctx)
-		ctx = gss_get_ctx(gss_cred->gc_ctx);
+	ctx = rcu_dereference(gss_cred->gc_ctx);
+	if (ctx)
+		gss_get_ctx(ctx);
 	rcu_read_unlock();
 	return ctx;
 }
@@ -262,9 +263,22 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct
 		p = ERR_PTR(ret);
 		goto err;
 	}
-	dprintk("RPC:       %s Success. gc_expiry %lu now %lu timeout %u\n",
-		__func__, ctx->gc_expiry, now, timeout);
-	return q;
+
+	/* is there any trailing data? */
+	if (q == end) {
+		p = q;
+		goto done;
+	}
+
+	/* pull in acceptor name (if there is one) */
+	p = simple_get_netobj(q, end, &ctx->gc_acceptor);
+	if (IS_ERR(p))
+		goto err;
+done:
+	dprintk("RPC:       %s Success. gc_expiry %lu now %lu timeout %u acceptor %.*s\n",
+		__func__, ctx->gc_expiry, now, timeout, ctx->gc_acceptor.len,
+		ctx->gc_acceptor.data);
+	return p;
 err:
 	dprintk("RPC:       %s returns error %ld\n", __func__, -PTR_ERR(p));
 	return p;
@@ -1194,13 +1208,13 @@ gss_destroying_context(struct rpc_cred *cred)
 {
 	struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base);
 	struct gss_auth *gss_auth = container_of(cred->cr_auth, struct gss_auth, rpc_auth);
+	struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1);
 	struct rpc_task *task;
 
-	if (gss_cred->gc_ctx == NULL ||
-	    test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0)
+	if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0)
 		return 0;
 
-	gss_cred->gc_ctx->gc_proc = RPC_GSS_PROC_DESTROY;
+	ctx->gc_proc = RPC_GSS_PROC_DESTROY;
 	cred->cr_ops = &gss_nullops;
 
 	/* Take a reference to ensure the cred will be destroyed either
@@ -1225,6 +1239,7 @@ gss_do_free_ctx(struct gss_cl_ctx *ctx)
 
 	gss_delete_sec_context(&ctx->gc_gss_ctx);
 	kfree(ctx->gc_wire_ctx.data);
+	kfree(ctx->gc_acceptor.data);
 	kfree(ctx);
 }
 
@@ -1260,7 +1275,7 @@ gss_destroy_nullcred(struct rpc_cred *cred)
 {
 	struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base);
 	struct gss_auth *gss_auth = container_of(cred->cr_auth, struct gss_auth, rpc_auth);
-	struct gss_cl_ctx *ctx = gss_cred->gc_ctx;
+	struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1);
 
 	RCU_INIT_POINTER(gss_cred->gc_ctx, NULL);
 	call_rcu(&cred->cr_rcu, gss_free_cred_callback);
@@ -1332,6 +1347,36 @@ gss_cred_init(struct rpc_auth *auth, struct rpc_cred *cred)
 	return err;
 }
 
+static char *
+gss_stringify_acceptor(struct rpc_cred *cred)
+{
+	char *string = NULL;
+	struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base);
+	struct gss_cl_ctx *ctx;
+	struct xdr_netobj *acceptor;
+
+	rcu_read_lock();
+	ctx = rcu_dereference(gss_cred->gc_ctx);
+	if (!ctx)
+		goto out;
+
+	acceptor = &ctx->gc_acceptor;
+
+	/* no point if there's no string */
+	if (!acceptor->len)
+		goto out;
+
+	string = kmalloc(acceptor->len + 1, GFP_KERNEL);
+	if (!string)
+		goto out;
+
+	memcpy(string, acceptor->data, acceptor->len);
+	string[acceptor->len] = '\0';
+out:
+	rcu_read_unlock();
+	return string;
+}
+
 /*
  * Returns -EACCES if GSS context is NULL or will expire within the
  * timeout (miliseconds)
@@ -1340,15 +1385,16 @@ static int
 gss_key_timeout(struct rpc_cred *rc)
 {
 	struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base);
+	struct gss_cl_ctx *ctx;
 	unsigned long now = jiffies;
 	unsigned long expire;
 
-	if (gss_cred->gc_ctx == NULL)
-		return -EACCES;
-
-	expire = gss_cred->gc_ctx->gc_expiry - (gss_key_expire_timeo * HZ);
-
-	if (time_after(now, expire))
+	rcu_read_lock();
+	ctx = rcu_dereference(gss_cred->gc_ctx);
+	if (ctx)
+		expire = ctx->gc_expiry - (gss_key_expire_timeo * HZ);
+	rcu_read_unlock();
+	if (!ctx || time_after(now, expire))
 		return -EACCES;
 	return 0;
 }
@@ -1357,13 +1403,19 @@ static int
 gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags)
 {
 	struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base);
+	struct gss_cl_ctx *ctx;
 	int ret;
 
 	if (test_bit(RPCAUTH_CRED_NEW, &rc->cr_flags))
 		goto out;
 	/* Don't match with creds that have expired. */
-	if (time_after(jiffies, gss_cred->gc_ctx->gc_expiry))
+	rcu_read_lock();
+	ctx = rcu_dereference(gss_cred->gc_ctx);
+	if (!ctx || time_after(jiffies, ctx->gc_expiry)) {
+		rcu_read_unlock();
 		return 0;
+	}
+	rcu_read_unlock();
 	if (!test_bit(RPCAUTH_CRED_UPTODATE, &rc->cr_flags))
 		return 0;
 out:
@@ -1909,29 +1961,31 @@ static const struct rpc_authops authgss_ops = {
 };
 
 static const struct rpc_credops gss_credops = {
-	.cr_name	= "AUTH_GSS",
-	.crdestroy	= gss_destroy_cred,
-	.cr_init	= gss_cred_init,
-	.crbind		= rpcauth_generic_bind_cred,
-	.crmatch	= gss_match,
-	.crmarshal	= gss_marshal,
-	.crrefresh	= gss_refresh,
-	.crvalidate	= gss_validate,
-	.crwrap_req	= gss_wrap_req,
-	.crunwrap_resp	= gss_unwrap_resp,
-	.crkey_timeout	= gss_key_timeout,
+	.cr_name		= "AUTH_GSS",
+	.crdestroy		= gss_destroy_cred,
+	.cr_init		= gss_cred_init,
+	.crbind			= rpcauth_generic_bind_cred,
+	.crmatch		= gss_match,
+	.crmarshal		= gss_marshal,
+	.crrefresh		= gss_refresh,
+	.crvalidate		= gss_validate,
+	.crwrap_req		= gss_wrap_req,
+	.crunwrap_resp		= gss_unwrap_resp,
+	.crkey_timeout		= gss_key_timeout,
+	.crstringify_acceptor	= gss_stringify_acceptor,
 };
 
 static const struct rpc_credops gss_nullops = {
-	.cr_name	= "AUTH_GSS",
-	.crdestroy	= gss_destroy_nullcred,
-	.crbind		= rpcauth_generic_bind_cred,
-	.crmatch	= gss_match,
-	.crmarshal	= gss_marshal,
-	.crrefresh	= gss_refresh_null,
-	.crvalidate	= gss_validate,
-	.crwrap_req	= gss_wrap_req,
-	.crunwrap_resp	= gss_unwrap_resp,
+	.cr_name		= "AUTH_GSS",
+	.crdestroy		= gss_destroy_nullcred,
+	.crbind			= rpcauth_generic_bind_cred,
+	.crmatch		= gss_match,
+	.crmarshal		= gss_marshal,
+	.crrefresh		= gss_refresh_null,
+	.crvalidate		= gss_validate,
+	.crwrap_req		= gss_wrap_req,
+	.crunwrap_resp		= gss_unwrap_resp,
+	.crstringify_acceptor	= gss_stringify_acceptor,
 };
 
 static const struct rpc_pipe_ops gss_upcall_ops_v0 = {

net/sunrpc/auth_gss/gss_krb5_crypto.c

@@ -641,7 +641,7 @@ gss_krb5_cts_crypt(struct crypto_blkcipher *cipher, struct xdr_buf *buf,
 
 u32
 gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
-		     struct xdr_buf *buf, int ec, struct page **pages)
+		     struct xdr_buf *buf, struct page **pages)
 {
 	u32 err;
 	struct xdr_netobj hmac;
@@ -684,13 +684,8 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 		ecptr = buf->tail[0].iov_base;
 	}
 
-	memset(ecptr, 'X', ec);
-	buf->tail[0].iov_len += ec;
-	buf->len += ec;
-
 	/* copy plaintext gss token header after filler (if any) */
-	memcpy(ecptr + ec, buf->head[0].iov_base + offset,
-						GSS_KRB5_TOK_HDR_LEN);
+	memcpy(ecptr, buf->head[0].iov_base + offset, GSS_KRB5_TOK_HDR_LEN);
 	buf->tail[0].iov_len += GSS_KRB5_TOK_HDR_LEN;
 	buf->len += GSS_KRB5_TOK_HDR_LEN;
 

net/sunrpc/auth_gss/gss_krb5_seal.c

@@ -70,31 +70,37 @@
 
 DEFINE_SPINLOCK(krb5_seq_lock);
 
-static char *
+static void *
 setup_token(struct krb5_ctx *ctx, struct xdr_netobj *token)
 {
-	__be16 *ptr, *krb5_hdr;
+	u16 *ptr;
+	void *krb5_hdr;
 	int body_size = GSS_KRB5_TOK_HDR_LEN + ctx->gk5e->cksumlength;
 
 	token->len = g_token_size(&ctx->mech_used, body_size);
 
-	ptr = (__be16 *)token->data;
+	ptr = (u16 *)token->data;
 	g_make_token_header(&ctx->mech_used, body_size, (unsigned char **)&ptr);
 
 	/* ptr now at start of header described in rfc 1964, section 1.2.1: */
 	krb5_hdr = ptr;
 	*ptr++ = KG_TOK_MIC_MSG;
-	*ptr++ = cpu_to_le16(ctx->gk5e->signalg);
+	/*
+	 * signalg is stored as if it were converted from LE to host endian, even
+	 * though it's an opaque pair of bytes according to the RFC.
+	 */
+	*ptr++ = (__force u16)cpu_to_le16(ctx->gk5e->signalg);
 	*ptr++ = SEAL_ALG_NONE;
-	*ptr++ = 0xffff;
+	*ptr = 0xffff;
 
-	return (char *)krb5_hdr;
+	return krb5_hdr;
 }
 
 static void *
 setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token)
 {
-	__be16 *ptr, *krb5_hdr;
+	u16 *ptr;
+	void *krb5_hdr;
 	u8 *p, flags = 0x00;
 
 	if ((ctx->flags & KRB5_CTX_FLAG_INITIATOR) == 0)
@@ -104,15 +110,15 @@ setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token)
 
 	/* Per rfc 4121, sec 4.2.6.1, there is no header,
 	 * just start the token */
-	krb5_hdr = ptr = (__be16 *)token->data;
+	krb5_hdr = ptr = (u16 *)token->data;
 
 	*ptr++ = KG2_TOK_MIC;
 	p = (u8 *)ptr;
 	*p++ = flags;
 	*p++ = 0xff;
-	ptr = (__be16 *)p;
-	*ptr++ = 0xffff;
+	ptr = (u16 *)p;
 	*ptr++ = 0xffff;
+	*ptr = 0xffff;
 
 	token->len = GSS_KRB5_TOK_HDR_LEN + ctx->gk5e->cksumlength;
 	return krb5_hdr;
@@ -181,7 +187,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text,
 	spin_lock(&krb5_seq_lock);
 	seq_send = ctx->seq_send64++;
 	spin_unlock(&krb5_seq_lock);
-	*((u64 *)(krb5_hdr + 8)) = cpu_to_be64(seq_send);
+	*((__be64 *)(krb5_hdr + 8)) = cpu_to_be64(seq_send);
 
 	if (ctx->initiate) {
 		cksumkey = ctx->initiator_sign;

net/sunrpc/auth_gss/gss_krb5_wrap.c

@@ -201,9 +201,15 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 
 	msg_start = ptr + GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength;
 
-	*(__be16 *)(ptr + 2) = cpu_to_le16(kctx->gk5e->signalg);
-	memset(ptr + 4, 0xff, 4);
-	*(__be16 *)(ptr + 4) = cpu_to_le16(kctx->gk5e->sealalg);
+	/*
+	 * signalg and sealalg are stored as if they were converted from LE
+	 * to host endian, even though they're opaque pairs of bytes according
+	 * to the RFC.
+	 */
+	*(__le16 *)(ptr + 2) = cpu_to_le16(kctx->gk5e->signalg);
+	*(__le16 *)(ptr + 4) = cpu_to_le16(kctx->gk5e->sealalg);
+	ptr[6] = 0xff;
+	ptr[7] = 0xff;
 
 	gss_krb5_make_confounder(msg_start, conflen);
 
@@ -438,7 +444,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 	u8		*ptr, *plainhdr;
 	s32		now;
 	u8		flags = 0x00;
-	__be16		*be16ptr, ec = 0;
+	__be16		*be16ptr;
 	__be64		*be64ptr;
 	u32		err;
 
@@ -468,16 +474,16 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 	be16ptr = (__be16 *)ptr;
 
 	blocksize = crypto_blkcipher_blocksize(kctx->acceptor_enc);
-	*be16ptr++ = cpu_to_be16(ec);
+	*be16ptr++ = 0;
 	/* "inner" token header always uses 0 for RRC */
-	*be16ptr++ = cpu_to_be16(0);
+	*be16ptr++ = 0;
 
 	be64ptr = (__be64 *)be16ptr;
 	spin_lock(&krb5_seq_lock);
 	*be64ptr = cpu_to_be64(kctx->seq_send64++);
 	spin_unlock(&krb5_seq_lock);
 
-	err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, ec, pages);
+	err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, pages);
 	if (err)
 		return err;
 

net/sunrpc/auth_null.c

@@ -35,6 +35,8 @@ nul_destroy(struct rpc_auth *auth)
 static struct rpc_cred *
 nul_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 {
+	if (flags & RPCAUTH_LOOKUP_RCU)
+		return &null_cred;
 	return get_rpccred(&null_cred);
 }
 

net/sunrpc/clnt.c

@@ -1746,6 +1746,7 @@ call_bind_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+	case -ENOBUFS:
 	case -EPIPE:
 		dprintk("RPC: %5u remote rpcbind unreachable: %d\n",
 				task->tk_pid, task->tk_status);
@@ -1812,6 +1813,8 @@ call_connect_status(struct rpc_task *task)
 	case -ECONNABORTED:
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
+	case -ENOBUFS:
+	case -EPIPE:
 		if (RPC_IS_SOFTCONN(task))
 			break;
 		/* retry with existing socket, after a delay */
@@ -1918,6 +1921,7 @@ call_transmit_status(struct rpc_task *task)
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENOTCONN:
+	case -ENOBUFS:
 	case -EPIPE:
 		rpc_task_force_reencode(task);
 	}
@@ -2034,6 +2038,7 @@ call_status(struct rpc_task *task)
 	case -ECONNRESET:
 	case -ECONNABORTED:
 		rpc_force_rebind(clnt);
+	case -ENOBUFS:
 		rpc_delay(task, 3*HZ);
 	case -EPIPE:
 	case -ENOTCONN:

net/sunrpc/rpc_pipe.c

@@ -195,7 +195,7 @@ static struct inode *
 rpc_alloc_inode(struct super_block *sb)
 {
 	struct rpc_inode *rpci;
-	rpci = (struct rpc_inode *)kmem_cache_alloc(rpc_inode_cachep, GFP_KERNEL);
+	rpci = kmem_cache_alloc(rpc_inode_cachep, GFP_KERNEL);
 	if (!rpci)
 		return NULL;
 	return &rpci->vfs_inode;

net/sunrpc/xprt.c

@@ -744,6 +744,7 @@ static void xprt_connect_status(struct rpc_task *task)
 	case -ECONNABORTED:
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
+	case -EPIPE:
 	case -EAGAIN:
 		dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid);
 		break;

net/sunrpc/xprtrdma/rpc_rdma.c

@@ -53,14 +53,6 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-enum rpcrdma_chunktype {
-	rpcrdma_noch = 0,
-	rpcrdma_readch,
-	rpcrdma_areadch,
-	rpcrdma_writech,
-	rpcrdma_replych
-};
-
 #ifdef RPC_DEBUG
 static const char transfertypes[][12] = {
 	"pure inline",	/* no chunks */
@@ -279,12 +271,36 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	return (unsigned char *)iptr - (unsigned char *)headerp;
 
 out:
-	for (pos = 0; nchunks--;)
-		pos += rpcrdma_deregister_external(
-				&req->rl_segments[pos], r_xprt);
+	if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_FRMR) {
+		for (pos = 0; nchunks--;)
+			pos += rpcrdma_deregister_external(
+					&req->rl_segments[pos], r_xprt);
+	}
 	return n;
 }
 
+/*
+ * Marshal chunks. This routine returns the header length
+ * consumed by marshaling.
+ *
+ * Returns positive RPC/RDMA header size, or negative errno.
+ */
+
+ssize_t
+rpcrdma_marshal_chunks(struct rpc_rqst *rqst, ssize_t result)
+{
+	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
+	struct rpcrdma_msg *headerp = (struct rpcrdma_msg *)req->rl_base;
+
+	if (req->rl_rtype != rpcrdma_noch)
+		result = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf,
+					       headerp, req->rl_rtype);
+	else if (req->rl_wtype != rpcrdma_noch)
+		result = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf,
+					       headerp, req->rl_wtype);
+	return result;
+}
+
 /*
  * Copy write data inline.
  * This function is used for "small" requests. Data which is passed
@@ -377,7 +393,6 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	char *base;
 	size_t rpclen, padlen;
 	ssize_t hdrlen;
-	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
 
 	/*
@@ -415,13 +430,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * into pages; otherwise use reply chunks.
 	 */
 	if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst))
-		wtype = rpcrdma_noch;
+		req->rl_wtype = rpcrdma_noch;
 	else if (rqst->rq_rcv_buf.page_len == 0)
-		wtype = rpcrdma_replych;
+		req->rl_wtype = rpcrdma_replych;
 	else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
-		wtype = rpcrdma_writech;
+		req->rl_wtype = rpcrdma_writech;
 	else
-		wtype = rpcrdma_replych;
+		req->rl_wtype = rpcrdma_replych;
 
 	/*
 	 * Chunks needed for arguments?
@@ -438,16 +453,16 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * TBD check NFSv4 setacl
 	 */
 	if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst))
-		rtype = rpcrdma_noch;
+		req->rl_rtype = rpcrdma_noch;
 	else if (rqst->rq_snd_buf.page_len == 0)
-		rtype = rpcrdma_areadch;
+		req->rl_rtype = rpcrdma_areadch;
 	else
-		rtype = rpcrdma_readch;
+		req->rl_rtype = rpcrdma_readch;
 
 	/* The following simplification is not true forever */
-	if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
-		wtype = rpcrdma_noch;
-	if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
+	if (req->rl_rtype != rpcrdma_noch && req->rl_wtype == rpcrdma_replych)
+		req->rl_wtype = rpcrdma_noch;
+	if (req->rl_rtype != rpcrdma_noch && req->rl_wtype != rpcrdma_noch) {
 		dprintk("RPC:       %s: cannot marshal multiple chunk lists\n",
 			__func__);
 		return -EIO;
@@ -461,7 +476,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * When padding is in use and applies to the transfer, insert
 	 * it and change the message type.
 	 */
-	if (rtype == rpcrdma_noch) {
+	if (req->rl_rtype == rpcrdma_noch) {
 
 		padlen = rpcrdma_inline_pullup(rqst,
 						RPCRDMA_INLINE_PAD_VALUE(rqst));
@@ -476,7 +491,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero;
 			headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero;
 			hdrlen += 2 * sizeof(u32); /* extra words in padhdr */
-			if (wtype != rpcrdma_noch) {
+			if (req->rl_wtype != rpcrdma_noch) {
 				dprintk("RPC:       %s: invalid chunk list\n",
 					__func__);
 				return -EIO;
@@ -497,30 +512,18 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			 * on receive. Therefore, we request a reply chunk
 			 * for non-writes wherever feasible and efficient.
 			 */
-			if (wtype == rpcrdma_noch)
-				wtype = rpcrdma_replych;
+			if (req->rl_wtype == rpcrdma_noch)
+				req->rl_wtype = rpcrdma_replych;
 		}
 	}
 
-	/*
-	 * Marshal chunks. This routine will return the header length
-	 * consumed by marshaling.
-	 */
-	if (rtype != rpcrdma_noch) {
-		hdrlen = rpcrdma_create_chunks(rqst,
-					&rqst->rq_snd_buf, headerp, rtype);
-		wtype = rtype;	/* simplify dprintk */
-
-	} else if (wtype != rpcrdma_noch) {
-		hdrlen = rpcrdma_create_chunks(rqst,
-					&rqst->rq_rcv_buf, headerp, wtype);
-	}
+	hdrlen = rpcrdma_marshal_chunks(rqst, hdrlen);
 	if (hdrlen < 0)
 		return hdrlen;
 
 	dprintk("RPC:       %s: %s: hdrlen %zd rpclen %zd padlen %zd"
 		" headerp 0x%p base 0x%p lkey 0x%x\n",
-		__func__, transfertypes[wtype], hdrlen, rpclen, padlen,
+		__func__, transfertypes[req->rl_wtype], hdrlen, rpclen, padlen,
 		headerp, base, req->rl_iov.lkey);
 
 	/*