Merge tag 'nfs-for-4.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Another set of mainly bugfixes and a couple of cleanups.  No new
  functionality in this round.

  Highlights include:

  Stable patches:
   - Fix a regression in /proc/self/mountstats
   - Fix the pNFS flexfiles O_DIRECT support
   - Fix high load average due to callback thread sleeping

  Bugfixes:
   - Various patches to fix the pNFS layoutcommit support
   - Do not cache pNFS deviceids unless server notifications are enabled
   - Fix a SUNRPC transport reconnection regression
   - make debugfs file creation failure non-fatal in SUNRPC
   - Another fix for circular directory warnings on NFSv4 "junctioned"
     mountpoints
   - Fix locking around NFSv4.2 fallocate() support
   - Truncating NFSv4 file opens should also sync O_DIRECT writes
   - Prevent infinite loop in rpcrdma_ep_create()

  Features:
   - Various improvements to the RDMA transport code's handling of
     memory registration
   - Various code cleanups"

* tag 'nfs-for-4.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (55 commits)
  fs/nfs: fix new compiler warning about boolean in switch
  nfs: Remove unneeded casts in nfs
  NFS: Don't attempt to decode missing directory entries
  Revert "nfs: replace nfs_add_stats with nfs_inc_stats when add one"
  NFS: Rename idmap.c to nfs4idmap.c
  NFS: Move nfs_idmap.h into fs/nfs/
  NFS: Remove CONFIG_NFS_V4 checks from nfs_idmap.h
  NFS: Add a stub for GETDEVICELIST
  nfs: remove WARN_ON_ONCE from nfs_direct_good_bytes
  nfs: fix DIO good bytes calculation
  nfs: Fetch MOUNTED_ON_FILEID when updating an inode
  sunrpc: make debugfs file creation failure non-fatal
  nfs: fix high load average due to callback thread sleeping
  NFS: Reduce time spent holding the i_mutex during fallocate()
  NFS: Don't zap caches on fallocate()
  xprtrdma: Make rpcrdma_{un}map_one() into inline functions
  xprtrdma: Handle non-SEND completions via a callout
  xprtrdma: Add "open" memreg op
  xprtrdma: Add "destroy MRs" memreg op
  xprtrdma: Add "reset MRs" memreg op
  ...

fs/nfs/Makefile

@@ -22,7 +22,7 @@ nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
 obj-$(CONFIG_NFS_V4) += nfsv4.o
 CFLAGS_nfs4trace.o += -I$(src)
 nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
-	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
+	  delegation.o nfs4idmap.o callback.o callback_xdr.o callback_proc.o \
 	  nfs4namespace.o nfs4getroot.o nfs4client.o nfs4session.o \
 	  dns_resolve.o nfs4trace.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o

fs/nfs/blocklayout/blocklayout.c

@@ -890,6 +890,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.free_deviceid_node		= bl_free_deviceid_node,
 	.pg_read_ops			= &bl_pg_read_ops,
 	.pg_write_ops			= &bl_pg_write_ops,
+	.sync				= pnfs_generic_sync,
 };
 
 static int __init nfs4blocklayout_init(void)

fs/nfs/blocklayout/dev.c

@@ -33,7 +33,7 @@ bl_free_deviceid_node(struct nfs4_deviceid_node *d)
 		container_of(d, struct pnfs_block_dev, node);
 
 	bl_free_device(dev);
-	kfree(dev);
+	kfree_rcu(dev, node.rcu);
 }
 
 static int

fs/nfs/callback.c

@@ -128,7 +128,7 @@ nfs41_callback_svc(void *vrqstp)
 		if (try_to_freeze())
 			continue;
 
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
 			req = list_first_entry(&serv->sv_cb_list,
@@ -142,10 +142,10 @@ nfs41_callback_svc(void *vrqstp)
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			/* schedule_timeout to game the hung task watchdog */
-			schedule_timeout(60 * HZ);
+			schedule();
 			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
+		flush_signals(current);
 	}
 	return 0;
 }

fs/nfs/client.c

@@ -31,7 +31,6 @@
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>

fs/nfs/delegation.c

@@ -378,7 +378,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 		if (freeme == NULL)
 			goto out;
 	}
-	list_add_rcu(&delegation->super_list, &server->delegations);
+	list_add_tail_rcu(&delegation->super_list, &server->delegations);
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
 
@@ -514,7 +514,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
 
 	delegation = nfs_inode_detach_delegation(inode);
 	if (delegation != NULL)
-		nfs_do_return_delegation(inode, delegation, 0);
+		nfs_do_return_delegation(inode, delegation, 1);
 }
 
 /**

fs/nfs/dir.c

@@ -543,6 +543,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 	if (scratch == NULL)
 		return -ENOMEM;
 
+	if (buflen == 0)
+		goto out_nopages;
+
 	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
@@ -564,6 +567,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 			break;
 	} while (!entry->eof);
 
+out_nopages:
 	if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
 		array = nfs_readdir_get_array(page);
 		if (!IS_ERR(array)) {

fs/nfs/direct.c

@@ -129,22 +129,25 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
 	int i;
 	ssize_t count;
 
-	WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count);
-
-	count = dreq->mirrors[hdr->pgio_mirror_idx].count;
-	if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
-		count = hdr->io_start + hdr->good_bytes - dreq->io_start;
-		dreq->mirrors[hdr->pgio_mirror_idx].count = count;
-	}
-
-	/* update the dreq->count by finding the minimum agreed count from all
-	 * mirrors */
-	count = dreq->mirrors[0].count;
+	if (dreq->mirror_count == 1) {
+		dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
+		dreq->count += hdr->good_bytes;
+	} else {
+		/* mirrored writes */
+		count = dreq->mirrors[hdr->pgio_mirror_idx].count;
+		if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
+			count = hdr->io_start + hdr->good_bytes - dreq->io_start;
+			dreq->mirrors[hdr->pgio_mirror_idx].count = count;
+		}
+		/* update the dreq->count by finding the minimum agreed count from all
+		 * mirrors */
+		count = dreq->mirrors[0].count;
 
-	for (i = 1; i < dreq->mirror_count; i++)
-		count = min(count, dreq->mirrors[i].count);
+		for (i = 1; i < dreq->mirror_count; i++)
+			count = min(count, dreq->mirrors[i].count);
 
-	dreq->count = count;
+		dreq->count = count;
+	}
 }
 
 /*
@@ -258,18 +261,11 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 	if (!IS_SWAPFILE(inode))
 		return 0;
 
-#ifndef CONFIG_NFS_SWAP
-	dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
-			iocb->ki_filp, (long long) pos, iter->nr_segs);
-
-	return -EINVAL;
-#else
 	VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
 
 	if (iov_iter_rw(iter) == READ)
 		return nfs_file_direct_read(iocb, iter, pos);
 	return nfs_file_direct_write(iocb, iter);
-#endif /* CONFIG_NFS_SWAP */
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -1030,6 +1026,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 			if (i_size_read(inode) < iocb->ki_pos)
 				i_size_write(inode, iocb->ki_pos);
 			spin_unlock(&inode->i_lock);
+			generic_write_sync(file, pos, result);
 		}
 	}
 	nfs_direct_req_release(dreq);

fs/nfs/file.c

@@ -280,6 +280,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_nfs_fsync_enter(inode);
 
+	nfs_inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
@@ -782,7 +783,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * Flush all pending writes before doing anything
 	 * with locks..
 	 */
-	nfs_sync_mapping(filp->f_mapping);
+	vfs_fsync(filp, 0);
 
 	l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
 	if (!IS_ERR(l_ctx)) {

fs/nfs/filelayout/filelayout.c

@@ -258,7 +258,8 @@ filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
 	    hdr->res.verf->committed != NFS_DATA_SYNC)
 		return;
 
-	pnfs_set_layoutcommit(hdr);
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
+			hdr->mds_offset + hdr->res.count);
 	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
@@ -373,7 +374,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 	}
 
 	if (data->verf.committed == NFS_UNSTABLE)
-		pnfs_commit_set_layoutcommit(data);
+		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
@@ -1086,7 +1087,7 @@ filelayout_alloc_deviceid_node(struct nfs_server *server,
 }
 
 static void
-filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+filelayout_free_deviceid_node(struct nfs4_deviceid_node *d)
 {
 	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
 }
@@ -1137,7 +1138,8 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,
 	.alloc_deviceid_node	= filelayout_alloc_deviceid_node,
-	.free_deviceid_node	= filelayout_free_deveiceid_node,
+	.free_deviceid_node	= filelayout_free_deviceid_node,
+	.sync			= pnfs_nfs_generic_sync,
 };
 
 static int __init nfs4filelayout_init(void)

fs/nfs/filelayout/filelayoutdev.c

@@ -55,7 +55,7 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 			nfs4_pnfs_ds_put(ds);
 	}
 	kfree(dsaddr->stripe_indices);
-	kfree(dsaddr);
+	kfree_rcu(dsaddr, id_node.rcu);
 }
 
 /* Decode opaque device data and return the result */

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -11,10 +11,10 @@
 #include <linux/module.h>
 
 #include <linux/sunrpc/metrics.h>
-#include <linux/nfs_idmap.h>
 
 #include "flexfilelayout.h"
 #include "../nfs4session.h"
+#include "../nfs4idmap.h"
 #include "../internal.h"
 #include "../delegation.h"
 #include "../nfs4trace.h"
@@ -891,7 +891,8 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 static void
 ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
 {
-	pnfs_set_layoutcommit(hdr);
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
+			hdr->mds_offset + hdr->res.count);
 	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
@@ -1074,7 +1075,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 	}
 
 	if (data->verf.committed == NFS_UNSTABLE)
-		pnfs_commit_set_layoutcommit(data);
+		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
@@ -1414,7 +1415,7 @@ ff_layout_get_ds_info(struct inode *inode)
 }
 
 static void
-ff_layout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+ff_layout_free_deviceid_node(struct nfs4_deviceid_node *d)
 {
 	nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds,
 						  id_node));
@@ -1498,7 +1499,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.pg_read_ops		= &ff_layout_pg_read_ops,
 	.pg_write_ops		= &ff_layout_pg_write_ops,
 	.get_ds_info		= ff_layout_get_ds_info,
-	.free_deviceid_node	= ff_layout_free_deveiceid_node,
+	.free_deviceid_node	= ff_layout_free_deviceid_node,
 	.mark_request_commit	= pnfs_layout_mark_request_commit,
 	.clear_request_commit	= pnfs_generic_clear_request_commit,
 	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
@@ -1508,6 +1509,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.write_pagelist		= ff_layout_write_pagelist,
 	.alloc_deviceid_node    = ff_layout_alloc_deviceid_node,
 	.encode_layoutreturn    = ff_layout_encode_layoutreturn,
+	.sync			= pnfs_nfs_generic_sync,
 };
 
 static int __init nfs4flexfilelayout_init(void)

fs/nfs/flexfilelayout/flexfilelayoutdev.c

@@ -30,7 +30,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
 {
 	nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
 	nfs4_pnfs_ds_put(mirror_ds->ds);
-	kfree(mirror_ds);
+	kfree_rcu(mirror_ds, id_node.rcu);
 }
 
 /* Decode opaque device data and construct new_ds using it */

fs/nfs/inode.c

@@ -133,6 +133,13 @@ void nfs_evict_inode(struct inode *inode)
 	nfs_clear_inode(inode);
 }
 
+int nfs_sync_inode(struct inode *inode)
+{
+	nfs_inode_dio_wait(inode);
+	return nfs_wb_all(inode);
+}
+EXPORT_SYMBOL_GPL(nfs_sync_inode);
+
 /**
  * nfs_sync_mapping - helper to flush all mmapped dirty data to disk
  */
@@ -192,7 +199,6 @@ void nfs_zap_caches(struct inode *inode)
 	nfs_zap_caches_locked(inode);
 	spin_unlock(&inode->i_lock);
 }
-EXPORT_SYMBOL_GPL(nfs_zap_caches);
 
 void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 {
@@ -525,10 +531,8 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode)) {
-		nfs_inode_dio_wait(inode);
-		nfs_wb_all(inode);
-	}
+	if (S_ISREG(inode->i_mode))
+		nfs_sync_inode(inode);
 
 	fattr = nfs_alloc_fattr();
 	if (fattr == NULL)
@@ -644,8 +648,9 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if (S_ISREG(inode->i_mode)) {
-		nfs_inode_dio_wait(inode);
-		err = filemap_write_and_wait(inode->i_mapping);
+		mutex_lock(&inode->i_mutex);
+		err = nfs_sync_inode(inode);
+		mutex_unlock(&inode->i_mutex);
 		if (err)
 			goto out;
 	}
@@ -1588,6 +1593,19 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 }
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
 
+
+static inline bool nfs_fileid_valid(struct nfs_inode *nfsi,
+				    struct nfs_fattr *fattr)
+{
+	bool ret1 = true, ret2 = true;
+
+	if (fattr->valid & NFS_ATTR_FATTR_FILEID)
+		ret1 = (nfsi->fileid == fattr->fileid);
+	if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
+		ret2 = (nfsi->fileid == fattr->mounted_on_fileid);
+	return ret1 || ret2;
+}
+
 /*
  * Many nfs protocol calls return the new file attributes after
  * an operation.  Here we update the inode to reflect the state
@@ -1614,7 +1632,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
 
-	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) {
+	if (!nfs_fileid_valid(nfsi, fattr)) {
 		printk(KERN_ERR "NFS: server %s error: fileid changed\n"
 			"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
 			NFS_SERVER(inode)->nfs_client->cl_hostname,
@@ -1819,7 +1837,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 struct inode *nfs_alloc_inode(struct super_block *sb)
 {
 	struct nfs_inode *nfsi;
-	nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
+	nfsi = kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
 	if (!nfsi)
 		return NULL;
 	nfsi->flags = 0UL;

fs/nfs/nfs42proc.c

@@ -36,13 +36,16 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 				 loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(filep);
+	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs42_falloc_args args = {
 		.falloc_fh	= NFS_FH(inode),
 		.falloc_offset	= offset,
 		.falloc_length	= len,
+		.falloc_bitmask	= server->cache_consistency_bitmask,
+	};
+	struct nfs42_falloc_res res = {
+		.falloc_server	= server,
 	};
-	struct nfs42_falloc_res res;
-	struct nfs_server *server = NFS_SERVER(inode);
 	int status;
 
 	msg->rpc_argp = &args;
@@ -52,8 +55,17 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	if (status)
 		return status;
 
-	return nfs4_call_sync(server->client, server, msg,
-			      &args.seq_args, &res.seq_res, 0);
+	res.falloc_fattr = nfs_alloc_fattr();
+	if (!res.falloc_fattr)
+		return -ENOMEM;
+
+	status = nfs4_call_sync(server->client, server, msg,
+				&args.seq_args, &res.seq_res, 0);
+	if (status == 0)
+		status = nfs_post_op_update_inode(inode, res.falloc_fattr);
+
+	kfree(res.falloc_fattr);
+	return status;
 }
 
 static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
@@ -84,9 +96,13 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 	if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&inode->i_mutex);
+
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
+
+	mutex_unlock(&inode->i_mutex);
 	return err;
 }
 
@@ -101,9 +117,16 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE))
 		return -EOPNOTSUPP;
 
+	nfs_wb_all(inode);
+	mutex_lock(&inode->i_mutex);
+
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
+	if (err == 0)
+		truncate_pagecache_range(inode, offset, (offset + len) -1);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
+
+	mutex_unlock(&inode->i_mutex);
 	return err;
 }
 

fs/nfs/nfs42xdr.c

@@ -25,16 +25,20 @@
 
 #define NFS4_enc_allocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
-					 encode_allocate_maxsz)
+					 encode_allocate_maxsz + \
+					 encode_getattr_maxsz)
 #define NFS4_dec_allocate_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
-					 decode_allocate_maxsz)
+					 decode_allocate_maxsz + \
+					 decode_getattr_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
-					 encode_deallocate_maxsz)
+					 encode_deallocate_maxsz + \
+					 encode_getattr_maxsz)
 #define NFS4_dec_deallocate_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
-					 decode_deallocate_maxsz)
+					 decode_deallocate_maxsz + \
+					 decode_getattr_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_seek_maxsz)
@@ -92,6 +96,7 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->falloc_fh, &hdr);
 	encode_allocate(xdr, args, &hdr);
+	encode_getfattr(xdr, args->falloc_bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -110,6 +115,7 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->falloc_fh, &hdr);
 	encode_deallocate(xdr, args, &hdr);
+	encode_getfattr(xdr, args->falloc_bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -183,6 +189,9 @@ static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp,
 	if (status)
 		goto out;
 	status = decode_allocate(xdr, res);
+	if (status)
+		goto out;
+	decode_getfattr(xdr, res->falloc_fattr, res->falloc_server);
 out:
 	return status;
 }
@@ -207,6 +216,9 @@ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
 	if (status)
 		goto out;
 	status = decode_deallocate(xdr, res);
+	if (status)
+		goto out;
+	decode_getfattr(xdr, res->falloc_fattr, res->falloc_server);
 out:
 	return status;
 }

fs/nfs/nfs4client.c

@@ -4,7 +4,6 @@
  */
 #include <linux/module.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs_mount.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/auth.h>
@@ -15,6 +14,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "nfs4session.h"
+#include "nfs4idmap.h"
 #include "pnfs.h"
 #include "netns.h"
 

fs/nfs/nfs4file.c

@@ -10,6 +10,8 @@
 #include "fscache.h"
 #include "pnfs.h"
 
+#include "nfstrace.h"
+
 #ifdef CONFIG_NFS_V4_2
 #include "nfs42.h"
 #endif
@@ -57,7 +59,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	if (openflags & O_TRUNC) {
 		attr.ia_valid |= ATTR_SIZE;
 		attr.ia_size = 0;
-		nfs_wb_all(inode);
+		nfs_sync_inode(inode);
 	}
 
 	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, &opened);
@@ -100,6 +102,9 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct inode *inode = file_inode(file);
 
+	trace_nfs_fsync_enter(inode);
+
+	nfs_inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
@@ -107,7 +112,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		mutex_lock(&inode->i_mutex);
 		ret = nfs_file_fsync_commit(file, start, end, datasync);
 		if (!ret)
-			ret = pnfs_layoutcommit_inode(inode, true);
+			ret = pnfs_sync_inode(inode, !!datasync);
 		mutex_unlock(&inode->i_mutex);
 		/*
 		 * If nfs_file_fsync_commit detected a server reboot, then
@@ -118,6 +123,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		end = LLONG_MAX;
 	} while (ret == -EAGAIN);
 
+	trace_nfs_fsync_exit(inode, ret);
 	return ret;
 }
 
@@ -152,15 +158,9 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 	if (ret < 0)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
 	if (mode & FALLOC_FL_PUNCH_HOLE)
-		ret = nfs42_proc_deallocate(filep, offset, len);
-	else
-		ret = nfs42_proc_allocate(filep, offset, len);
-	mutex_unlock(&inode->i_mutex);
-
-	nfs_zap_caches(inode);
-	return ret;
+		return nfs42_proc_deallocate(filep, offset, len);
+	return nfs42_proc_allocate(filep, offset, len);
 }
 #endif /* CONFIG_NFS_V4_2 */
 

fs/nfs/idmap.c → fs/nfs/nfs4idmap.c

@@ -36,7 +36,6 @@
 #include <linux/types.h>
 #include <linux/parser.h>
 #include <linux/fs.h>
-#include <linux/nfs_idmap.h>
 #include <net/net_namespace.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/nfs_fs.h>
@@ -49,6 +48,7 @@
 
 #include "internal.h"
 #include "netns.h"
+#include "nfs4idmap.h"
 #include "nfs4trace.h"
 
 #define NFS_UINT_MAXLEN 11

include/linux/nfs_idmap.h → fs/nfs/nfs4idmap.h

 /*
- * include/linux/nfs_idmap.h
+ * fs/nfs/nfs4idmap.h
  *
  *  UID and GID to name mapping for clients.
  *
@@ -46,19 +46,8 @@ struct nfs_server;
 struct nfs_fattr;
 struct nfs4_string;
 
-#if IS_ENABLED(CONFIG_NFS_V4)
 int nfs_idmap_init(void);
 void nfs_idmap_quit(void);
-#else
-static inline int nfs_idmap_init(void)
-{
-	return 0;
-}
-
-static inline void nfs_idmap_quit(void)
-{}
-#endif
-
 int nfs_idmap_new(struct nfs_client *);
 void nfs_idmap_delete(struct nfs_client *);
 

fs/nfs/nfs4proc.c

@@ -51,7 +51,6 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/module.h>
-#include <linux/nfs_idmap.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
 #include <linux/freezer.h>
@@ -63,6 +62,7 @@
 #include "callback.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "fscache.h"
 
@@ -185,7 +185,8 @@ const u32 nfs4_fattr_bitmap[3] = {
 	| FATTR4_WORD1_SPACE_USED
 	| FATTR4_WORD1_TIME_ACCESS
 	| FATTR4_WORD1_TIME_METADATA
-	| FATTR4_WORD1_TIME_MODIFY,
+	| FATTR4_WORD1_TIME_MODIFY
+	| FATTR4_WORD1_MOUNTED_ON_FILEID,
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 	FATTR4_WORD2_SECURITY_LABEL
 #endif
@@ -3095,16 +3096,13 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
 			 struct nfs_fsinfo *info,
 			 bool auth_probe)
 {
-	int status;
+	int status = 0;
 
-	switch (auth_probe) {
-	case false:
+	if (!auth_probe)
 		status = nfs4_lookup_root(server, fhandle, info);
-		if (status != -NFS4ERR_WRONGSEC)
-			break;
-	default:
+
+	if (auth_probe || status == NFS4ERR_WRONGSEC)
 		status = nfs4_do_find_root_sec(server, fhandle, info);
-	}
 
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
@@ -7944,6 +7942,8 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server,
 {
 	struct nfs4_getdeviceinfo_args args = {
 		.pdev = pdev,
+		.notify_types = NOTIFY_DEVICEID4_CHANGE |
+			NOTIFY_DEVICEID4_DELETE,
 	};
 	struct nfs4_getdeviceinfo_res res = {
 		.pdev = pdev,
@@ -7958,6 +7958,11 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server,
 
 	dprintk("--> %s\n", __func__);
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
+	if (res.notification & ~args.notify_types)
+		dprintk("%s: unsupported notification\n", __func__);
+	if (res.notification != args.notify_types)
+		pdev->nocache = 1;
+
 	dprintk("<-- %s status=%d\n", __func__, status);
 
 	return status;

fs/nfs/nfs4state.c

@@ -42,7 +42,6 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
@@ -57,6 +56,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"

fs/nfs/nfs4super.c

@@ -3,12 +3,12 @@
  */
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs4_mount.h>
 #include <linux/nfs_fs.h>
 #include "delegation.h"
 #include "internal.h"
 #include "nfs4_fs.h"
+#include "nfs4idmap.h"
 #include "dns_resolve.h"
 #include "pnfs.h"
 #include "nfs.h"
@@ -91,10 +91,11 @@ static void nfs4_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
-	pnfs_return_layout(inode);
-	pnfs_destroy_layout(NFS_I(inode));
 	/* If we are holding a delegation, return it! */
 	nfs_inode_return_delegation_noreclaim(inode);
+	/* Note that above delegreturn would trigger pnfs return-on-close */
+	pnfs_return_layout(inode);
+	pnfs_destroy_layout(NFS_I(inode));
 	/* First call standard NFS clear_inode() code */
 	nfs_clear_inode(inode);
 }

fs/nfs/nfs4sysctl.c

@@ -6,10 +6,10 @@
  * Copyright (c) 2006 Trond Myklebust <Trond.Myklebust@netapp.com>
  */
 #include <linux/sysctl.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs_fs.h>
 
 #include "nfs4_fs.h"
+#include "nfs4idmap.h"
 #include "callback.h"
 
 static const int nfs_set_port_min = 0;

fs/nfs/nfs4xdr.c

@@ -52,10 +52,10 @@
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 
 #include "nfs4_fs.h"
 #include "internal.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
@@ -1920,7 +1920,7 @@ encode_getdeviceinfo(struct xdr_stream *xdr,
 
 	p = reserve_space(xdr, 4 + 4);
 	*p++ = cpu_to_be32(1);			/* bitmap length */
-	*p++ = cpu_to_be32(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE);
+	*p++ = cpu_to_be32(args->notify_types);
 }
 
 static void
@@ -5753,8 +5753,9 @@ static int decode_sequence(struct xdr_stream *xdr,
 
 #if defined(CONFIG_NFS_V4_1)
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
-				struct pnfs_device *pdev)
+				struct nfs4_getdeviceinfo_res *res)
 {
+	struct pnfs_device *pdev = res->pdev;
 	__be32 *p;
 	uint32_t len, type;
 	int status;
@@ -5802,12 +5803,7 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr,
 		if (unlikely(!p))
 			goto out_overflow;
 
-		if (be32_to_cpup(p++) &
-		    ~(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE)) {
-			dprintk("%s: unsupported notification\n",
-				__func__);
-		}
-
+		res->notification = be32_to_cpup(p++);
 		for (i = 1; i < len; i++) {
 			if (be32_to_cpup(p++)) {
 				dprintk("%s: unsupported notification\n",
@@ -7061,7 +7057,7 @@ static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp,
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
 	if (status != 0)
 		goto out;
-	status = decode_getdeviceinfo(xdr, res->pdev);
+	status = decode_getdeviceinfo(xdr, res);
 out:
 	return status;
 }
@@ -7365,6 +7361,11 @@ nfs4_stat_to_errno(int stat)
 	.p_name   = #proc,					\
 }
 
+#define STUB(proc)		\
+[NFSPROC4_CLNT_##proc] = {	\
+	.p_name = #proc,	\
+}
+
 struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
@@ -7417,6 +7418,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	STUB(GETDEVICELIST),
 	PROC(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),

fs/nfs/nfstrace.c

@@ -7,3 +7,6 @@
 
 #define CREATE_TRACE_POINTS
 #include "nfstrace.h"
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_enter);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_exit);

fs/nfs/objlayout/objio_osd.c

@@ -57,7 +57,7 @@ objio_free_deviceid_node(struct nfs4_deviceid_node *d)
 
 	dprintk("%s: free od=%p\n", __func__, de->od.od);
 	osduld_put_device(de->od.od);
-	kfree(de);
+	kfree_rcu(d, rcu);
 }
 
 struct objio_segment {
@@ -637,6 +637,8 @@ static struct pnfs_layoutdriver_type objlayout_type = {
 	.pg_read_ops             = &objio_pg_read_ops,
 	.pg_write_ops            = &objio_pg_write_ops,
 
+	.sync			 = pnfs_generic_sync,
+
 	.free_deviceid_node	 = objio_free_deviceid_node,
 
 	.encode_layoutcommit	 = objlayout_encode_layoutcommit,

fs/nfs/pnfs.c

@@ -1090,6 +1090,7 @@ bool pnfs_roc(struct inode *ino)
 	pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
+	pnfs_layoutcommit_inode(ino, true);
 	return true;
 
 out_noroc:
@@ -1104,8 +1105,10 @@ bool pnfs_roc(struct inode *ino)
 		}
 	}
 	spin_unlock(&ino->i_lock);
-	if (layoutreturn)
+	if (layoutreturn) {
+		pnfs_layoutcommit_inode(ino, true);
 		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+	}
 	return false;
 }
 
@@ -1841,7 +1844,8 @@ void pnfs_ld_write_done(struct nfs_pgio_header *hdr)
 {
 	trace_nfs4_pnfs_write(hdr, hdr->pnfs_error);
 	if (!hdr->pnfs_error) {
-		pnfs_set_layoutcommit(hdr);
+		pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
+				hdr->mds_offset + hdr->res.count);
 		hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
 	} else
 		pnfs_ld_handle_write_error(hdr);
@@ -1902,7 +1906,6 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 	pnfs_put_lseg(hdr->lseg);
 	nfs_pgio_header_free(hdr);
 }
-EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
@@ -2032,7 +2035,6 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 	pnfs_put_lseg(hdr->lseg);
 	nfs_pgio_header_free(hdr);
 }
-EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
@@ -2099,64 +2101,34 @@ void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
 EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
 
 void
-pnfs_set_layoutcommit(struct nfs_pgio_header *hdr)
+pnfs_set_layoutcommit(struct inode *inode, struct pnfs_layout_segment *lseg,
+		loff_t end_pos)
 {
-	struct inode *inode = hdr->inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	loff_t end_pos = hdr->mds_offset + hdr->res.count;
 	bool mark_as_dirty = false;
 
 	spin_lock(&inode->i_lock);
 	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
-		mark_as_dirty = true;
-		dprintk("%s: Set layoutcommit for inode %lu ",
-			__func__, inode->i_ino);
-	}
-	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) {
-		/* references matched in nfs4_layoutcommit_release */
-		pnfs_get_lseg(hdr->lseg);
-	}
-	if (end_pos > nfsi->layout->plh_lwb)
 		nfsi->layout->plh_lwb = end_pos;
-	spin_unlock(&inode->i_lock);
-	dprintk("%s: lseg %p end_pos %llu\n",
-		__func__, hdr->lseg, nfsi->layout->plh_lwb);
-
-	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
-	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
-	if (mark_as_dirty)
-		mark_inode_dirty_sync(inode);
-}
-EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
-
-void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data)
-{
-	struct inode *inode = data->inode;
-	struct nfs_inode *nfsi = NFS_I(inode);
-	bool mark_as_dirty = false;
-
-	spin_lock(&inode->i_lock);
-	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
 		mark_as_dirty = true;
 		dprintk("%s: Set layoutcommit for inode %lu ",
 			__func__, inode->i_ino);
-	}
-	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &data->lseg->pls_flags)) {
+	} else if (end_pos > nfsi->layout->plh_lwb)
+		nfsi->layout->plh_lwb = end_pos;
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) {
 		/* references matched in nfs4_layoutcommit_release */
-		pnfs_get_lseg(data->lseg);
+		pnfs_get_lseg(lseg);
 	}
-	if (data->lwb > nfsi->layout->plh_lwb)
-		nfsi->layout->plh_lwb = data->lwb;
 	spin_unlock(&inode->i_lock);
 	dprintk("%s: lseg %p end_pos %llu\n",
-		__func__, data->lseg, nfsi->layout->plh_lwb);
+		__func__, lseg, nfsi->layout->plh_lwb);
 
 	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
 	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
 	if (mark_as_dirty)
 		mark_inode_dirty_sync(inode);
 }
-EXPORT_SYMBOL_GPL(pnfs_commit_set_layoutcommit);
+EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 {
@@ -2216,7 +2188,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	pnfs_list_write_lseg(inode, &data->lseg_list);
 
 	end_pos = nfsi->layout->plh_lwb;
-	nfsi->layout->plh_lwb = 0;
 
 	nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid);
 	spin_unlock(&inode->i_lock);
@@ -2233,11 +2204,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 		status = ld->prepare_layoutcommit(&data->args);
 		if (status) {
 			spin_lock(&inode->i_lock);
-			if (end_pos < nfsi->layout->plh_lwb)
+			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
+			if (end_pos > nfsi->layout->plh_lwb)
 				nfsi->layout->plh_lwb = end_pos;
 			spin_unlock(&inode->i_lock);
 			put_rpccred(data->cred);
-			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
 			goto clear_layoutcommitting;
 		}
 	}
@@ -2258,6 +2229,13 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 }
 EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode);
 
+int
+pnfs_generic_sync(struct inode *inode, bool datasync)
+{
+	return pnfs_layoutcommit_inode(inode, true);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_sync);
+
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {
 	struct nfs4_threshold *thp;

fs/nfs/pnfs.h

@@ -155,6 +155,8 @@ struct pnfs_layoutdriver_type {
 			       int how,
 			       struct nfs_commit_info *cinfo);
 
+	int (*sync)(struct inode *inode, bool datasync);
+
 	/*
 	 * Return PNFS_ATTEMPTED to indicate the layout code has attempted
 	 * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
@@ -203,6 +205,7 @@ struct pnfs_device {
 	struct page **pages;
 	unsigned int  pgbase;
 	unsigned int  pglen;	/* reply buffer length */
+	unsigned char nocache : 1;/* May not be cached */
 };
 
 #define NFS4_PNFS_GETDEVLIST_MAXNUM 16
@@ -263,10 +266,11 @@ 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_header *);
-void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data);
+void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
+int pnfs_generic_sync(struct inode *inode, bool datasync);
+int pnfs_nfs_generic_sync(struct inode *inode, bool datasync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_pgio_header *);
@@ -291,6 +295,7 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
 enum {
 	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
 	NFS_DEVICEID_UNAVAILABLE,	/* device temporarily unavailable */
+	NFS_DEVICEID_NOCACHE,		/* device may not be cached */
 };
 
 /* pnfs_dev.c */
@@ -302,6 +307,7 @@ struct nfs4_deviceid_node {
 	unsigned long 			flags;
 	unsigned long			timestamp_unavailable;
 	struct nfs4_deviceid		deviceid;
+	struct rcu_head			rcu;
 	atomic_t			ref;
 };
 
@@ -486,6 +492,14 @@ pnfs_ld_read_whole_page(struct inode *inode)
 	return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE;
 }
 
+static inline int
+pnfs_sync_inode(struct inode *inode, bool datasync)
+{
+	if (!pnfs_enabled_sb(NFS_SERVER(inode)))
+		return 0;
+	return NFS_SERVER(inode)->pnfs_curr_ld->sync(inode, datasync);
+}
+
 static inline bool
 pnfs_layoutcommit_outstanding(struct inode *inode)
 {
@@ -568,6 +582,12 @@ pnfs_ld_read_whole_page(struct inode *inode)
 	return false;
 }
 
+static inline int
+pnfs_sync_inode(struct inode *inode, bool datasync)
+{
+	return 0;
+}
+
 static inline bool
 pnfs_roc(struct inode *ino)
 {

fs/nfs/pnfs_dev.c

@@ -149,6 +149,8 @@ nfs4_get_device_info(struct nfs_server *server,
 	 */
 	d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev,
 			gfp_flags);
+	if (d && pdev->nocache)
+		set_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 
 out_free_pages:
 	for (i = 0; i < max_pages; i++)
@@ -175,8 +177,8 @@ __nfs4_find_get_deviceid(struct nfs_server *server,
 	rcu_read_lock();
 	d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id,
 			hash);
-	if (d != NULL)
-		atomic_inc(&d->ref);
+	if (d != NULL && !atomic_inc_not_zero(&d->ref))
+		d = NULL;
 	rcu_read_unlock();
 	return d;
 }
@@ -235,12 +237,11 @@ nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
 		return;
 	}
 	hlist_del_init_rcu(&d->node);
+	clear_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 	spin_unlock(&nfs4_deviceid_lock);
-	synchronize_rcu();
 
 	/* balance the initial ref set in pnfs_insert_deviceid */
-	if (atomic_dec_and_test(&d->ref))
-		d->ld->free_deviceid_node(d);
+	nfs4_put_deviceid_node(d);
 }
 EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
 
@@ -271,6 +272,11 @@ EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);
 bool
 nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
 {
+	if (test_bit(NFS_DEVICEID_NOCACHE, &d->flags)) {
+		if (atomic_add_unless(&d->ref, -1, 2))
+			return false;
+		nfs4_delete_deviceid(d->ld, d->nfs_client, &d->deviceid);
+	}
 	if (!atomic_dec_and_test(&d->ref))
 		return false;
 	d->ld->free_deviceid_node(d);
@@ -314,6 +320,7 @@ _deviceid_purge_client(const struct nfs_client *clp, long hash)
 		if (d->nfs_client == clp && atomic_read(&d->ref)) {
 			hlist_del_init_rcu(&d->node);
 			hlist_add_head(&d->tmpnode, &tmp);
+			clear_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 		}
 	rcu_read_unlock();
 	spin_unlock(&nfs4_deviceid_lock);
@@ -321,12 +328,10 @@ _deviceid_purge_client(const struct nfs_client *clp, long hash)
 	if (hlist_empty(&tmp))
 		return;
 
-	synchronize_rcu();
 	while (!hlist_empty(&tmp)) {
 		d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode);
 		hlist_del(&d->tmpnode);
-		if (atomic_dec_and_test(&d->ref))
-			d->ld->free_deviceid_node(d);
+		nfs4_put_deviceid_node(d);
 	}
 }
 

fs/nfs/pnfs_nfs.c

@@ -561,7 +561,7 @@ static bool load_v3_ds_connect(void)
 	return(get_v3_ds_connect != NULL);
 }
 
-void __exit nfs4_pnfs_v3_ds_connect_unload(void)
+void nfs4_pnfs_v3_ds_connect_unload(void)
 {
 	if (get_v3_ds_connect) {
 		symbol_put(nfs3_set_ds_client);
@@ -868,3 +868,13 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
 	nfs_request_add_commit_list(req, list, cinfo);
 }
 EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
+
+int
+pnfs_nfs_generic_sync(struct inode *inode, bool datasync)
+{
+	if (datasync)
+		return 0;
+	return pnfs_layoutcommit_inode(inode, true);
+}
+EXPORT_SYMBOL_GPL(pnfs_nfs_generic_sync);
+

fs/nfs/read.c

@@ -284,7 +284,7 @@ int nfs_readpage(struct file *file, struct page *page)
 	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
 		page, PAGE_CACHE_SIZE, page_file_index(page));
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
-	nfs_inc_stats(inode, NFSIOS_READPAGES);
+	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
 
 	/*
 	 * Try to flush any pending writes to the file..

fs/nfs/super.c

@@ -43,7 +43,6 @@
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
@@ -2193,7 +2192,7 @@ nfs_compare_remount_data(struct nfs_server *nfss,
 	    data->version != nfss->nfs_client->rpc_ops->version ||
 	    data->minorversion != nfss->nfs_client->cl_minorversion ||
 	    data->retrans != nfss->client->cl_timeout->to_retries ||
-	    data->selected_flavor != nfss->client->cl_auth->au_flavor ||
+	    !nfs_auth_info_match(&data->auth_info, nfss->client->cl_auth->au_flavor) ||
 	    data->acregmin != nfss->acregmin / HZ ||
 	    data->acregmax != nfss->acregmax / HZ ||
 	    data->acdirmin != nfss->acdirmin / HZ ||
@@ -2241,7 +2240,6 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->wsize = nfss->wsize;
 	data->retrans = nfss->client->cl_timeout->to_retries;
 	data->selected_flavor = nfss->client->cl_auth->au_flavor;
-	data->auth_info = nfss->auth_info;
 	data->acregmin = nfss->acregmin / HZ;
 	data->acregmax = nfss->acregmax / HZ;
 	data->acdirmin = nfss->acdirmin / HZ;

fs/nfs/write.c

@@ -580,7 +580,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st
 	int ret;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
-	nfs_inc_stats(inode, NFSIOS_WRITEPAGES);
+	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
 	nfs_pageio_cond_complete(pgio, page_file_index(page));
 	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
@@ -1840,17 +1840,16 @@ EXPORT_SYMBOL_GPL(nfs_write_inode);
  */
 int nfs_wb_all(struct inode *inode)
 {
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = LONG_MAX,
-		.range_start = 0,
-		.range_end = LLONG_MAX,
-	};
 	int ret;
 
 	trace_nfs_writeback_inode_enter(inode);
 
-	ret = sync_inode(inode, &wbc);
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (!ret) {
+		ret = nfs_commit_inode(inode, FLUSH_SYNC);
+		if (!ret)
+			pnfs_sync_inode(inode, true);
+	}
 
 	trace_nfs_writeback_inode_exit(inode, ret);
 	return ret;

include/linux/nfs_fs.h

@@ -511,6 +511,7 @@ extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned
  * Try to write back everything synchronously (but check the
  * return value!)
  */
+extern int nfs_sync_inode(struct inode *inode);
 extern int nfs_wb_all(struct inode *inode);
 extern int nfs_wb_page(struct inode *inode, struct page* page);
 extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);

include/linux/nfs_xdr.h

@@ -255,11 +255,13 @@ struct nfs4_layoutget {
 struct nfs4_getdeviceinfo_args {
 	struct nfs4_sequence_args seq_args;
 	struct pnfs_device *pdev;
+	__u32 notify_types;
 };
 
 struct nfs4_getdeviceinfo_res {
 	struct nfs4_sequence_res seq_res;
 	struct pnfs_device *pdev;
+	__u32 notification;
 };
 
 struct nfs4_layoutcommit_args {
@@ -1271,11 +1273,15 @@ struct nfs42_falloc_args {
 	nfs4_stateid			 falloc_stateid;
 	u64				 falloc_offset;
 	u64				 falloc_length;
+	const u32			*falloc_bitmask;
 };
 
 struct nfs42_falloc_res {
 	struct nfs4_sequence_res	seq_res;
 	unsigned int			status;
+
+	struct nfs_fattr		*falloc_fattr;
+	const struct nfs_server		*falloc_server;
 };
 
 struct nfs42_seek_args {

include/linux/sunrpc/msg_prot.h

@@ -142,12 +142,18 @@ typedef __be32	rpc_fraghdr;
 	(RPC_REPHDRSIZE + (2 + RPC_MAX_AUTH_SIZE/4))
 
 /*
- * RFC1833/RFC3530 rpcbind (v3+) well-known netid's.
+ * Well-known netids. See:
+ *
+ *   http://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
  */
 #define RPCBIND_NETID_UDP	"udp"
 #define RPCBIND_NETID_TCP	"tcp"
+#define RPCBIND_NETID_RDMA	"rdma"
+#define RPCBIND_NETID_SCTP	"sctp"
 #define RPCBIND_NETID_UDP6	"udp6"
 #define RPCBIND_NETID_TCP6	"tcp6"
+#define RPCBIND_NETID_RDMA6	"rdma6"
+#define RPCBIND_NETID_SCTP6	"sctp6"
 #define RPCBIND_NETID_LOCAL	"local"
 
 /*

include/linux/sunrpc/xprtrdma.h

@@ -40,11 +40,6 @@
 #ifndef _LINUX_SUNRPC_XPRTRDMA_H
 #define _LINUX_SUNRPC_XPRTRDMA_H
 
-/*
- * rpcbind (v3+) RDMA netid.
- */
-#define RPCBIND_NETID_RDMA	"rdma"
-
 /*
  * Constants. Max RPC/NFS header is big enough to account for
  * additional marshaling buffers passed down by Linux client.

include/uapi/linux/nfs_idmap.h

 /*
- * include/linux/nfs_idmap.h
+ * include/uapi/linux/nfs_idmap.h
  *
  *  UID and GID to name mapping for clients.
  *

net/sunrpc/sched.c

@@ -89,8 +89,8 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	if (!task->tk_timeout)
 		return;
 
-	dprintk("RPC: %5u setting alarm for %lu ms\n",
-			task->tk_pid, task->tk_timeout * 1000 / HZ);
+	dprintk("RPC: %5u setting alarm for %u ms\n",
+		task->tk_pid, jiffies_to_msecs(task->tk_timeout));
 
 	task->u.tk_wait.expires = jiffies + task->tk_timeout;
 	if (list_empty(&queue->timer_list.list) || time_before(task->u.tk_wait.expires, queue->timer_list.expires))

net/sunrpc/xprt.c

@@ -326,6 +326,15 @@ static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt)
 	xprt_clear_locked(xprt);
 }
 
+static void xprt_task_clear_bytes_sent(struct rpc_task *task)
+{
+	if (task != NULL) {
+		struct rpc_rqst *req = task->tk_rqstp;
+		if (req != NULL)
+			req->rq_bytes_sent = 0;
+	}
+}
+
 /**
  * xprt_release_xprt - allow other requests to use a transport
  * @xprt: transport with other tasks potentially waiting
@@ -336,11 +345,7 @@ static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt)
 void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	if (xprt->snd_task == task) {
-		if (task != NULL) {
-			struct rpc_rqst *req = task->tk_rqstp;
-			if (req != NULL)
-				req->rq_bytes_sent = 0;
-		}
+		xprt_task_clear_bytes_sent(task);
 		xprt_clear_locked(xprt);
 		__xprt_lock_write_next(xprt);
 	}
@@ -358,11 +363,7 @@ EXPORT_SYMBOL_GPL(xprt_release_xprt);
 void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	if (xprt->snd_task == task) {
-		if (task != NULL) {
-			struct rpc_rqst *req = task->tk_rqstp;
-			if (req != NULL)
-				req->rq_bytes_sent = 0;
-		}
+		xprt_task_clear_bytes_sent(task);
 		xprt_clear_locked(xprt);
 		__xprt_lock_write_next_cong(xprt);
 	}
@@ -700,6 +701,7 @@ bool xprt_lock_connect(struct rpc_xprt *xprt,
 		goto out;
 	if (xprt->snd_task != task)
 		goto out;
+	xprt_task_clear_bytes_sent(task);
 	xprt->snd_task = cookie;
 	ret = true;
 out:

net/sunrpc/xprtrdma/Makefile

 obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o
 
-xprtrdma-y := transport.o rpc_rdma.o verbs.o
+xprtrdma-y := transport.o rpc_rdma.o verbs.o \
+	fmr_ops.o frwr_ops.o physical_ops.o
 
 obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o
 

net/sunrpc/xprtrdma/fmr_ops.c

+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* Lightweight memory registration using Fast Memory Regions (FMR).
+ * Referred to sometimes as MTHCAFMR mode.
+ *
+ * FMR uses synchronous memory registration and deregistration.
+ * FMR registration is known to be fast, but FMR deregistration
+ * can take tens of usecs to complete.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+/* Maximum scatter/gather per FMR */
+#define RPCRDMA_MAX_FMR_SGES	(64)
+
+static int
+fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+	    struct rpcrdma_create_data_internal *cdata)
+{
+	return 0;
+}
+
+/* FMR mode conveys up to 64 pages of payload per chunk segment.
+ */
+static size_t
+fmr_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt) * RPCRDMA_MAX_FMR_SGES);
+}
+
+static int
+fmr_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ;
+	struct ib_fmr_attr fmr_attr = {
+		.max_pages	= RPCRDMA_MAX_FMR_SGES,
+		.max_maps	= 1,
+		.page_shift	= PAGE_SHIFT
+	};
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	struct rpcrdma_mw *r;
+	int i, rc;
+
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+
+	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
+	dprintk("RPC:       %s: initializing %d FMRs\n", __func__, i);
+
+	while (i--) {
+		r = kzalloc(sizeof(*r), GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
+
+		r->r.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
+		if (IS_ERR(r->r.fmr))
+			goto out_fmr_err;
+
+		list_add(&r->mw_list, &buf->rb_mws);
+		list_add(&r->mw_all, &buf->rb_all);
+	}
+	return 0;
+
+out_fmr_err:
+	rc = PTR_ERR(r->r.fmr);
+	dprintk("RPC:       %s: ib_alloc_fmr status %i\n", __func__, rc);
+	kfree(r);
+	return rc;
+}
+
+/* Use the ib_map_phys_fmr() verb to register a memory region
+ * for remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+	   int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_device *device = ia->ri_id->device;
+	enum dma_data_direction direction = rpcrdma_data_dir(writing);
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
+	u64 physaddrs[RPCRDMA_MAX_DATA_SEGS];
+	int len, pageoff, i, rc;
+
+	pageoff = offset_in_page(seg1->mr_offset);
+	seg1->mr_offset -= pageoff;	/* start of page */
+	seg1->mr_len += pageoff;
+	len = -pageoff;
+	if (nsegs > RPCRDMA_MAX_FMR_SGES)
+		nsegs = RPCRDMA_MAX_FMR_SGES;
+	for (i = 0; i < nsegs;) {
+		rpcrdma_map_one(device, seg, direction);
+		physaddrs[i] = seg->mr_dma;
+		len += seg->mr_len;
+		++seg;
+		++i;
+		/* Check for holes */
+		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
+			break;
+	}
+
+	rc = ib_map_phys_fmr(mw->r.fmr, physaddrs, i, seg1->mr_dma);
+	if (rc)
+		goto out_maperr;
+
+	seg1->mr_rkey = mw->r.fmr->rkey;
+	seg1->mr_base = seg1->mr_dma + pageoff;
+	seg1->mr_nsegs = i;
+	seg1->mr_len = len;
+	return i;
+
+out_maperr:
+	dprintk("RPC:       %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
+		__func__, len, (unsigned long long)seg1->mr_dma,
+		pageoff, i, rc);
+	while (i--)
+		rpcrdma_unmap_one(device, --seg);
+	return rc;
+}
+
+/* Use the ib_unmap_fmr() verb to prevent further remote
+ * access via RDMA READ or RDMA WRITE.
+ */
+static int
+fmr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct ib_device *device;
+	int rc, nsegs = seg->mr_nsegs;
+	LIST_HEAD(l);
+
+	list_add(&seg1->rl_mw->r.fmr->list, &l);
+	rc = ib_unmap_fmr(&l);
+	read_lock(&ia->ri_qplock);
+	device = ia->ri_id->device;
+	while (seg1->mr_nsegs--)
+		rpcrdma_unmap_one(device, seg++);
+	read_unlock(&ia->ri_qplock);
+	if (rc)
+		goto out_err;
+	return nsegs;
+
+out_err:
+	dprintk("RPC:       %s: ib_unmap_fmr status %i\n", __func__, rc);
+	return nsegs;
+}
+
+/* After a disconnect, unmap all FMRs.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_fmr_external().
+ */
+static void
+fmr_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_mw *r;
+	LIST_HEAD(list);
+	int rc;
+
+	list_for_each_entry(r, &buf->rb_all, mw_all)
+		list_add(&r->r.fmr->list, &list);
+
+	rc = ib_unmap_fmr(&list);
+	if (rc)
+		dprintk("RPC:       %s: ib_unmap_fmr failed %i\n",
+			__func__, rc);
+}
+
+static void
+fmr_op_destroy(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_mw *r;
+	int rc;
+
+	while (!list_empty(&buf->rb_all)) {
+		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&r->mw_all);
+		rc = ib_dealloc_fmr(r->r.fmr);
+		if (rc)
+			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
+				__func__, rc);
+		kfree(r);
+	}
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = {
+	.ro_map				= fmr_op_map,
+	.ro_unmap			= fmr_op_unmap,
+	.ro_open			= fmr_op_open,
+	.ro_maxpages			= fmr_op_maxpages,
+	.ro_init			= fmr_op_init,
+	.ro_reset			= fmr_op_reset,
+	.ro_destroy			= fmr_op_destroy,
+	.ro_displayname			= "fmr",
+};

net/sunrpc/xprtrdma/frwr_ops.c

+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* Lightweight memory registration using Fast Registration Work
+ * Requests (FRWR). Also referred to sometimes as FRMR mode.
+ *
+ * FRWR features ordered asynchronous registration and deregistration
+ * of arbitrarily sized memory regions. This is the fastest and safest
+ * but most complex memory registration mode.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+static int
+__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
+	    unsigned int depth)
+{
+	struct rpcrdma_frmr *f = &r->r.frmr;
+	int rc;
+
+	f->fr_mr = ib_alloc_fast_reg_mr(pd, depth);
+	if (IS_ERR(f->fr_mr))
+		goto out_mr_err;
+	f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth);
+	if (IS_ERR(f->fr_pgl))
+		goto out_list_err;
+	return 0;
+
+out_mr_err:
+	rc = PTR_ERR(f->fr_mr);
+	dprintk("RPC:       %s: ib_alloc_fast_reg_mr status %i\n",
+		__func__, rc);
+	return rc;
+
+out_list_err:
+	rc = PTR_ERR(f->fr_pgl);
+	dprintk("RPC:       %s: ib_alloc_fast_reg_page_list status %i\n",
+		__func__, rc);
+	ib_dereg_mr(f->fr_mr);
+	return rc;
+}
+
+static void
+__frwr_release(struct rpcrdma_mw *r)
+{
+	int rc;
+
+	rc = ib_dereg_mr(r->r.frmr.fr_mr);
+	if (rc)
+		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
+			__func__, rc);
+	ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
+}
+
+static int
+frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+	     struct rpcrdma_create_data_internal *cdata)
+{
+	struct ib_device_attr *devattr = &ia->ri_devattr;
+	int depth, delta;
+
+	ia->ri_max_frmr_depth =
+			min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+			      devattr->max_fast_reg_page_list_len);
+	dprintk("RPC:       %s: device's max FR page list len = %u\n",
+		__func__, ia->ri_max_frmr_depth);
+
+	/* Add room for frmr register and invalidate WRs.
+	 * 1. FRMR reg WR for head
+	 * 2. FRMR invalidate WR for head
+	 * 3. N FRMR reg WRs for pagelist
+	 * 4. N FRMR invalidate WRs for pagelist
+	 * 5. FRMR reg WR for tail
+	 * 6. FRMR invalidate WR for tail
+	 * 7. The RDMA_SEND WR
+	 */
+	depth = 7;
+
+	/* Calculate N if the device max FRMR depth is smaller than
+	 * RPCRDMA_MAX_DATA_SEGS.
+	 */
+	if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) {
+		delta = RPCRDMA_MAX_DATA_SEGS - ia->ri_max_frmr_depth;
+		do {
+			depth += 2; /* FRMR reg + invalidate */
+			delta -= ia->ri_max_frmr_depth;
+		} while (delta > 0);
+	}
+
+	ep->rep_attr.cap.max_send_wr *= depth;
+	if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) {
+		cdata->max_requests = devattr->max_qp_wr / depth;
+		if (!cdata->max_requests)
+			return -EINVAL;
+		ep->rep_attr.cap.max_send_wr = cdata->max_requests *
+					       depth;
+	}
+
+	return 0;
+}
+
+/* FRWR mode conveys a list of pages per chunk segment. The
+ * maximum length of that list is the FRWR page list depth.
+ */
+static size_t
+frwr_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth);
+}
+
+/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */
+static void
+frwr_sendcompletion(struct ib_wc *wc)
+{
+	struct rpcrdma_mw *r;
+
+	if (likely(wc->status == IB_WC_SUCCESS))
+		return;
+
+	/* WARNING: Only wr_id and status are reliable at this point */
+	r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	dprintk("RPC:       %s: frmr %p (stale), status %d\n",
+		__func__, r, wc->status);
+	r->r.frmr.fr_state = FRMR_IS_STALE;
+}
+
+static int
+frwr_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	int i;
+
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+
+	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
+	dprintk("RPC:       %s: initializing %d FRMRs\n", __func__, i);
+
+	while (i--) {
+		struct rpcrdma_mw *r;
+		int rc;
+
+		r = kzalloc(sizeof(*r), GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
+
+		rc = __frwr_init(r, pd, device, depth);
+		if (rc) {
+			kfree(r);
+			return rc;
+		}
+
+		list_add(&r->mw_list, &buf->rb_mws);
+		list_add(&r->mw_all, &buf->rb_all);
+		r->mw_sendcompletion = frwr_sendcompletion;
+	}
+
+	return 0;
+}
+
+/* Post a FAST_REG Work Request to register a memory region
+ * for remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+	    int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_device *device = ia->ri_id->device;
+	enum dma_data_direction direction = rpcrdma_data_dir(writing);
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
+	struct rpcrdma_frmr *frmr = &mw->r.frmr;
+	struct ib_mr *mr = frmr->fr_mr;
+	struct ib_send_wr fastreg_wr, *bad_wr;
+	u8 key;
+	int len, pageoff;
+	int i, rc;
+	int seg_len;
+	u64 pa;
+	int page_no;
+
+	pageoff = offset_in_page(seg1->mr_offset);
+	seg1->mr_offset -= pageoff;	/* start of page */
+	seg1->mr_len += pageoff;
+	len = -pageoff;
+	if (nsegs > ia->ri_max_frmr_depth)
+		nsegs = ia->ri_max_frmr_depth;
+	for (page_no = i = 0; i < nsegs;) {
+		rpcrdma_map_one(device, seg, direction);
+		pa = seg->mr_dma;
+		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
+			frmr->fr_pgl->page_list[page_no++] = pa;
+			pa += PAGE_SIZE;
+		}
+		len += seg->mr_len;
+		++seg;
+		++i;
+		/* Check for holes */
+		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
+			break;
+	}
+	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
+		__func__, mw, i, len);
+
+	frmr->fr_state = FRMR_IS_VALID;
+
+	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
+	fastreg_wr.wr_id = (unsigned long)(void *)mw;
+	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
+	fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma + pageoff;
+	fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl;
+	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
+	fastreg_wr.wr.fast_reg.page_list_len = page_no;
+	fastreg_wr.wr.fast_reg.length = len;
+	fastreg_wr.wr.fast_reg.access_flags = writing ?
+				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+				IB_ACCESS_REMOTE_READ;
+	key = (u8)(mr->rkey & 0x000000FF);
+	ib_update_fast_reg_key(mr, ++key);
+	fastreg_wr.wr.fast_reg.rkey = mr->rkey;
+
+	DECR_CQCOUNT(&r_xprt->rx_ep);
+	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr);
+	if (rc)
+		goto out_senderr;
+
+	seg1->mr_rkey = mr->rkey;
+	seg1->mr_base = seg1->mr_dma + pageoff;
+	seg1->mr_nsegs = i;
+	seg1->mr_len = len;
+	return i;
+
+out_senderr:
+	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	ib_update_fast_reg_key(mr, --key);
+	frmr->fr_state = FRMR_IS_INVALID;
+	while (i--)
+		rpcrdma_unmap_one(device, --seg);
+	return rc;
+}
+
+/* Post a LOCAL_INV Work Request to prevent further remote access
+ * via RDMA READ or RDMA WRITE.
+ */
+static int
+frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_send_wr invalidate_wr, *bad_wr;
+	int rc, nsegs = seg->mr_nsegs;
+	struct ib_device *device;
+
+	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID;
+
+	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
+	invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw;
+	invalidate_wr.opcode = IB_WR_LOCAL_INV;
+	invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey;
+	DECR_CQCOUNT(&r_xprt->rx_ep);
+
+	read_lock(&ia->ri_qplock);
+	device = ia->ri_id->device;
+	while (seg1->mr_nsegs--)
+		rpcrdma_unmap_one(device, seg++);
+	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
+	read_unlock(&ia->ri_qplock);
+	if (rc)
+		goto out_err;
+	return nsegs;
+
+out_err:
+	/* Force rpcrdma_buffer_get() to retry */
+	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE;
+	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	return nsegs;
+}
+
+/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in
+ * an unusable state. Find FRMRs in this state and dereg / reg
+ * each.  FRMRs that are VALID and attached to an rpcrdma_req are
+ * also torn down.
+ *
+ * This gives all in-use FRMRs a fresh rkey and leaves them INVALID.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_frmr_external().
+ */
+static void
+frwr_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	struct rpcrdma_mw *r;
+	int rc;
+
+	list_for_each_entry(r, &buf->rb_all, mw_all) {
+		if (r->r.frmr.fr_state == FRMR_IS_INVALID)
+			continue;
+
+		__frwr_release(r);
+		rc = __frwr_init(r, pd, device, depth);
+		if (rc) {
+			dprintk("RPC:       %s: mw %p left %s\n",
+				__func__, r,
+				(r->r.frmr.fr_state == FRMR_IS_STALE ?
+					"stale" : "valid"));
+			continue;
+		}
+
+		r->r.frmr.fr_state = FRMR_IS_INVALID;
+	}
+}
+
+static void
+frwr_op_destroy(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_mw *r;
+
+	while (!list_empty(&buf->rb_all)) {
+		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&r->mw_all);
+		__frwr_release(r);
+		kfree(r);
+	}
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = {
+	.ro_map				= frwr_op_map,
+	.ro_unmap			= frwr_op_unmap,
+	.ro_open			= frwr_op_open,
+	.ro_maxpages			= frwr_op_maxpages,
+	.ro_init			= frwr_op_init,
+	.ro_reset			= frwr_op_reset,
+	.ro_destroy			= frwr_op_destroy,
+	.ro_displayname			= "frwr",
+};

net/sunrpc/xprtrdma/physical_ops.c

+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* No-op chunk preparation. All client memory is pre-registered.
+ * Sometimes referred to as ALLPHYSICAL mode.
+ *
+ * Physical registration is simple because all client memory is
+ * pre-registered and never deregistered. This mode is good for
+ * adapter bring up, but is considered not safe: the server is
+ * trusted not to abuse its access to client memory not involved
+ * in RDMA I/O.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+static int
+physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+		 struct rpcrdma_create_data_internal *cdata)
+{
+	return 0;
+}
+
+/* PHYSICAL memory registration conveys one page per chunk segment.
+ */
+static size_t
+physical_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt));
+}
+
+static int
+physical_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	return 0;
+}
+
+/* The client's physical memory is already exposed for
+ * remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+		int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	rpcrdma_map_one(ia->ri_id->device, seg,
+			rpcrdma_data_dir(writing));
+	seg->mr_rkey = ia->ri_bind_mem->rkey;
+	seg->mr_base = seg->mr_dma;
+	seg->mr_nsegs = 1;
+	return 1;
+}
+
+/* Unmap a memory region, but leave it registered.
+ */
+static int
+physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	read_lock(&ia->ri_qplock);
+	rpcrdma_unmap_one(ia->ri_id->device, seg);
+	read_unlock(&ia->ri_qplock);
+
+	return 1;
+}
+
+static void
+physical_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+}
+
+static void
+physical_op_destroy(struct rpcrdma_buffer *buf)
+{
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = {
+	.ro_map				= physical_op_map,
+	.ro_unmap			= physical_op_unmap,
+	.ro_open			= physical_op_open,
+	.ro_maxpages			= physical_op_maxpages,
+	.ro_init			= physical_op_init,
+	.ro_reset			= physical_op_reset,
+	.ro_destroy			= physical_op_destroy,
+	.ro_displayname			= "physical",
+};

net/sunrpc/xprtrdma/rpc_rdma.c

@@ -53,6 +53,14 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
+enum rpcrdma_chunktype {
+	rpcrdma_noch = 0,
+	rpcrdma_readch,
+	rpcrdma_areadch,
+	rpcrdma_writech,
+	rpcrdma_replych
+};
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char transfertypes[][12] = {
 	"pure inline",	/* no chunks */
@@ -179,6 +187,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	struct rpcrdma_write_array *warray = NULL;
 	struct rpcrdma_write_chunk *cur_wchunk = NULL;
 	__be32 *iptr = headerp->rm_body.rm_chunks;
+	int (*map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool);
 
 	if (type == rpcrdma_readch || type == rpcrdma_areadch) {
 		/* a read chunk - server will RDMA Read our memory */
@@ -201,9 +210,9 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	if (nsegs < 0)
 		return nsegs;
 
+	map = r_xprt->rx_ia.ri_ops->ro_map;
 	do {
-		n = rpcrdma_register_external(seg, nsegs,
-						cur_wchunk != NULL, r_xprt);
+		n = map(r_xprt, seg, nsegs, cur_wchunk != NULL);
 		if (n <= 0)
 			goto out;
 		if (cur_rchunk) {	/* read */
@@ -275,34 +284,13 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	return (unsigned char *)iptr - (unsigned char *)headerp;
 
 out:
-	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;
-}
+	if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+		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 = rdmab_to_msg(req->rl_rdmabuf);
-
-	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;
+	for (pos = 0; nchunks--;)
+		pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
+						      &req->rl_segments[pos]);
+	return n;
 }
 
 /*
@@ -397,6 +385,7 @@ 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;
 
 	/*
@@ -433,13 +422,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * into pages; otherwise use reply chunks.
 	 */
 	if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst))
-		req->rl_wtype = rpcrdma_noch;
+		wtype = rpcrdma_noch;
 	else if (rqst->rq_rcv_buf.page_len == 0)
-		req->rl_wtype = rpcrdma_replych;
+		wtype = rpcrdma_replych;
 	else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
-		req->rl_wtype = rpcrdma_writech;
+		wtype = rpcrdma_writech;
 	else
-		req->rl_wtype = rpcrdma_replych;
+		wtype = rpcrdma_replych;
 
 	/*
 	 * Chunks needed for arguments?
@@ -456,16 +445,16 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * TBD check NFSv4 setacl
 	 */
 	if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst))
-		req->rl_rtype = rpcrdma_noch;
+		rtype = rpcrdma_noch;
 	else if (rqst->rq_snd_buf.page_len == 0)
-		req->rl_rtype = rpcrdma_areadch;
+		rtype = rpcrdma_areadch;
 	else
-		req->rl_rtype = rpcrdma_readch;
+		rtype = rpcrdma_readch;
 
 	/* The following simplification is not true forever */
-	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) {
+	if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
+		wtype = rpcrdma_noch;
+	if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
 		dprintk("RPC:       %s: cannot marshal multiple chunk lists\n",
 			__func__);
 		return -EIO;
@@ -479,7 +468,7 @@ 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 (req->rl_rtype == rpcrdma_noch) {
+	if (rtype == rpcrdma_noch) {
 
 		padlen = rpcrdma_inline_pullup(rqst,
 						RPCRDMA_INLINE_PAD_VALUE(rqst));
@@ -494,7 +483,7 @@ 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 (req->rl_wtype != rpcrdma_noch) {
+			if (wtype != rpcrdma_noch) {
 				dprintk("RPC:       %s: invalid chunk list\n",
 					__func__);
 				return -EIO;
@@ -515,18 +504,26 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			 * on receive. Therefore, we request a reply chunk
 			 * for non-writes wherever feasible and efficient.
 			 */
-			if (req->rl_wtype == rpcrdma_noch)
-				req->rl_wtype = rpcrdma_replych;
+			if (wtype == rpcrdma_noch)
+				wtype = rpcrdma_replych;
 		}
 	}
 
-	hdrlen = rpcrdma_marshal_chunks(rqst, hdrlen);
+	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);
+	}
 	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[req->rl_wtype], hdrlen, rpclen, padlen,
+		__func__, transfertypes[wtype], hdrlen, rpclen, padlen,
 		headerp, base, rdmab_lkey(req->rl_rdmabuf));
 
 	/*

net/sunrpc/xprtrdma/transport.c

@@ -156,13 +156,48 @@ static struct ctl_table sunrpc_table[] = {
 
 static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 
+static void
+xprt_rdma_format_addresses4(struct rpc_xprt *xprt, struct sockaddr *sap)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	char buf[20];
+
+	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA;
+}
+
+static void
+xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	char buf[40];
+
+	snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA6;
+}
+
 static void
 xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 {
 	struct sockaddr *sap = (struct sockaddr *)
 					&rpcx_to_rdmad(xprt).addr;
-	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	char buf[64];
+	char buf[128];
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		xprt_rdma_format_addresses4(xprt, sap);
+		break;
+	case AF_INET6:
+		xprt_rdma_format_addresses6(xprt, sap);
+		break;
+	default:
+		pr_err("rpcrdma: Unrecognized address family\n");
+		return;
+	}
 
 	(void)rpc_ntop(sap, buf, sizeof(buf));
 	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
@@ -170,16 +205,10 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 	snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
 	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
 
-	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
-
-	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
-
 	snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
 	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
 
-	/* netid */
-	xprt->address_strings[RPC_DISPLAY_NETID] = "rdma";
+	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
 }
 
 static void
@@ -377,7 +406,10 @@ xprt_setup_rdma(struct xprt_create *args)
 			  xprt_rdma_connect_worker);
 
 	xprt_rdma_format_addresses(xprt);
-	xprt->max_payload = rpcrdma_max_payload(new_xprt);
+	xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt);
+	if (xprt->max_payload == 0)
+		goto out4;
+	xprt->max_payload <<= PAGE_SHIFT;
 	dprintk("RPC:       %s: transport data payload maximum: %zu bytes\n",
 		__func__, xprt->max_payload);
 
@@ -552,8 +584,8 @@ xprt_rdma_free(void *buffer)
 
 	for (i = 0; req->rl_nchunks;) {
 		--req->rl_nchunks;
-		i += rpcrdma_deregister_external(
-			&req->rl_segments[i], r_xprt);
+		i += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
+						    &req->rl_segments[i]);
 	}
 
 	rpcrdma_buffer_put(req);
@@ -579,10 +611,7 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	int rc = 0;
 
-	if (req->rl_niovs == 0)
-		rc = rpcrdma_marshal_req(rqst);
-	else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL)
-		rc = rpcrdma_marshal_chunks(rqst, 0);
+	rc = rpcrdma_marshal_req(rqst);
 	if (rc < 0)
 		goto failed_marshal;
 

net/sunrpc/xprtrdma/xprt_rdma.h

@@ -60,6 +60,7 @@
  * Interface Adapter -- one per transport instance
  */
 struct rpcrdma_ia {
+	const struct rpcrdma_memreg_ops	*ri_ops;
 	rwlock_t		ri_qplock;
 	struct rdma_cm_id 	*ri_id;
 	struct ib_pd		*ri_pd;
@@ -105,6 +106,10 @@ struct rpcrdma_ep {
 #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit)
 #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount)
 
+/* Force completion handler to ignore the signal
+ */
+#define RPCRDMA_IGNORE_COMPLETION	(0ULL)
+
 /* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV
  *
  * The below structure appears at the front of a large region of kmalloc'd
@@ -143,14 +148,6 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb)
 	return (struct rpcrdma_msg *)rb->rg_base;
 }
 
-enum rpcrdma_chunktype {
-	rpcrdma_noch = 0,
-	rpcrdma_readch,
-	rpcrdma_areadch,
-	rpcrdma_writech,
-	rpcrdma_replych
-};
-
 /*
  * struct rpcrdma_rep -- this structure encapsulates state required to recv
  * and complete a reply, asychronously. It needs several pieces of
@@ -213,6 +210,7 @@ struct rpcrdma_mw {
 		struct ib_fmr		*fmr;
 		struct rpcrdma_frmr	frmr;
 	} r;
+	void			(*mw_sendcompletion)(struct ib_wc *);
 	struct list_head	mw_list;
 	struct list_head	mw_all;
 };
@@ -258,7 +256,6 @@ struct rpcrdma_req {
 	unsigned int	rl_niovs;	/* 0, 2 or 4 */
 	unsigned int	rl_nchunks;	/* non-zero if chunks */
 	unsigned int	rl_connect_cookie;	/* retry detection */
-	enum rpcrdma_chunktype	rl_rtype, rl_wtype;
 	struct rpcrdma_buffer *rl_buffer; /* home base for this structure */
 	struct rpcrdma_rep	*rl_reply;/* holder for reply buffer */
 	struct ib_sge	rl_send_iov[4];	/* for active requests */
@@ -339,6 +336,29 @@ struct rpcrdma_stats {
 	unsigned long		bad_reply_count;
 };
 
+/*
+ * Per-registration mode operations
+ */
+struct rpcrdma_xprt;
+struct rpcrdma_memreg_ops {
+	int		(*ro_map)(struct rpcrdma_xprt *,
+				  struct rpcrdma_mr_seg *, int, bool);
+	int		(*ro_unmap)(struct rpcrdma_xprt *,
+				    struct rpcrdma_mr_seg *);
+	int		(*ro_open)(struct rpcrdma_ia *,
+				   struct rpcrdma_ep *,
+				   struct rpcrdma_create_data_internal *);
+	size_t		(*ro_maxpages)(struct rpcrdma_xprt *);
+	int		(*ro_init)(struct rpcrdma_xprt *);
+	void		(*ro_reset)(struct rpcrdma_xprt *);
+	void		(*ro_destroy)(struct rpcrdma_buffer *);
+	const char	*ro_displayname;
+};
+
+extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops;
+extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops;
+extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops;
+
 /*
  * RPCRDMA transport -- encapsulates the structures above for
  * integration with RPC.
@@ -398,16 +418,56 @@ void rpcrdma_buffer_put(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
 
-int rpcrdma_register_external(struct rpcrdma_mr_seg *,
-				int, int, struct rpcrdma_xprt *);
-int rpcrdma_deregister_external(struct rpcrdma_mr_seg *,
-				struct rpcrdma_xprt *);
-
 struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *,
 					    size_t, gfp_t);
 void rpcrdma_free_regbuf(struct rpcrdma_ia *,
 			 struct rpcrdma_regbuf *);
 
+unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *);
+
+/*
+ * Wrappers for chunk registration, shared by read/write chunk code.
+ */
+
+void rpcrdma_mapping_error(struct rpcrdma_mr_seg *);
+
+static inline enum dma_data_direction
+rpcrdma_data_dir(bool writing)
+{
+	return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+}
+
+static inline void
+rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg,
+		enum dma_data_direction direction)
+{
+	seg->mr_dir = direction;
+	seg->mr_dmalen = seg->mr_len;
+
+	if (seg->mr_page)
+		seg->mr_dma = ib_dma_map_page(device,
+				seg->mr_page, offset_in_page(seg->mr_offset),
+				seg->mr_dmalen, seg->mr_dir);
+	else
+		seg->mr_dma = ib_dma_map_single(device,
+				seg->mr_offset,
+				seg->mr_dmalen, seg->mr_dir);
+
+	if (ib_dma_mapping_error(device, seg->mr_dma))
+		rpcrdma_mapping_error(seg);
+}
+
+static inline void
+rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg)
+{
+	if (seg->mr_page)
+		ib_dma_unmap_page(device,
+				  seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
+	else
+		ib_dma_unmap_single(device,
+				    seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
+}
+
 /*
  * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
  */
@@ -418,9 +478,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *);
 /*
  * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
  */
-ssize_t rpcrdma_marshal_chunks(struct rpc_rqst *, ssize_t);
 int rpcrdma_marshal_req(struct rpc_rqst *);
-size_t rpcrdma_max_payload(struct rpcrdma_xprt *);
 
 /* Temporary NFS request map cache. Created in svc_rdma.c  */
 extern struct kmem_cache *svc_rdma_map_cachep;