Merge tag 'nfsd-5.4' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - Add a new knfsd file cache, so that we don't have to open and close
     on each (NFSv2/v3) READ or WRITE. This can speed up read and write
     in some cases. It also replaces our readahead cache.

   - Prevent silent data loss on write errors, by treating write errors
     like server reboots for the purposes of write caching, thus forcing
     clients to resend their writes.

   - Tweak the code that allocates sessions to be more forgiving, so
     that NFSv4.1 mounts are less likely to hang when a server already
     has a lot of clients.

   - Eliminate an arbitrary limit on NFSv4 ACL sizes; they should now be
     limited only by the backend filesystem and the maximum RPC size.

   - Allow the server to enforce use of the correct kerberos credentials
     when a client reclaims state after a reboot.

  And some miscellaneous smaller bugfixes and cleanup"

* tag 'nfsd-5.4' of git://linux-nfs.org/~bfields/linux: (34 commits)
  sunrpc: clean up indentation issue
  nfsd: fix nfs read eof detection
  nfsd: Make nfsd_reset_boot_verifier_locked static
  nfsd: degraded slot-count more gracefully as allocation nears exhaustion.
  nfsd: handle drc over-allocation gracefully.
  nfsd: add support for upcall version 2
  nfsd: add a "GetVersion" upcall for nfsdcld
  nfsd: Reset the boot verifier on all write I/O errors
  nfsd: Don't garbage collect files that might contain write errors
  nfsd: Support the server resetting the boot verifier
  nfsd: nfsd_file cache entries should be per net namespace
  nfsd: eliminate an unnecessary acl size limit
  Deprecate nfsd fault injection
  nfsd: remove duplicated include from filecache.c
  nfsd: Fix the documentation for svcxdr_tmpalloc()
  nfsd: Fix up some unused variable warnings
  nfsd: close cached files prior to a REMOVE or RENAME that would replace target
  nfsd: rip out the raparms cache
  nfsd: have nfsd_test_lock use the nfsd_file cache
  nfsd: hook up nfs4_preprocess_stateid_op to the nfsd_file cache
  ...

5 files changed, 26 insertions, 30 deletions

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 6f1528f271ee..a349094f6fb7 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -373,7 +373,7 @@ void sunrpc_init_cache_detail(struct cache_detail *cd)
 	spin_lock(&cache_list_lock);
 	cd->nextcheck = 0;
 	cd->entries = 0;
-	atomic_set(&cd->readers, 0);
+	atomic_set(&cd->writers, 0);
 	cd->last_close = 0;
 	cd->last_warn = -1;
 	list_add(&cd->others, &cache_list);
@@ -1029,11 +1029,13 @@ static int cache_open(struct inode *inode, struct file *filp,
 		}
 		rp->offset = 0;
 		rp->q.reader = 1;
-		atomic_inc(&cd->readers);
+
 		spin_lock(&queue_lock);
 		list_add(&rp->q.list, &cd->queue);
 		spin_unlock(&queue_lock);
 	}
+	if (filp->f_mode & FMODE_WRITE)
+		atomic_inc(&cd->writers);
 	filp->private_data = rp;
 	return 0;
 }
@@ -1062,8 +1064,10 @@ static int cache_release(struct inode *inode, struct file *filp,
 		filp->private_data = NULL;
 		kfree(rp);
 
+	}
+	if (filp->f_mode & FMODE_WRITE) {
+		atomic_dec(&cd->writers);
 		cd->last_close = seconds_since_boot();
-		atomic_dec(&cd->readers);
 	}
 	module_put(cd->owner);
 	return 0;
@@ -1171,7 +1175,7 @@ static void warn_no_listener(struct cache_detail *detail)
 
 static bool cache_listeners_exist(struct cache_detail *detail)
 {
-	if (atomic_read(&detail->readers))
+	if (atomic_read(&detail->writers))
 		return true;
 	if (detail->last_close == 0)
 		/* This cache was never opened */
@@ -1520,6 +1524,9 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
 	cd->nextcheck = now;
 	cache_flush();
 
+	if (cd->flush)
+		cd->flush();
+
 	*ppos += count;
 	return count;
 }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 220b79988000..d11b70552c33 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1233,8 +1233,8 @@ svc_generic_init_request(struct svc_rqst *rqstp,
 
 	if (rqstp->rq_vers >= progp->pg_nvers )
 		goto err_bad_vers;
-	  versp = progp->pg_vers[rqstp->rq_vers];
-	  if (!versp)
+	versp = progp->pg_vers[rqstp->rq_vers];
+	if (!versp)
 		goto err_bad_vers;
 
 	/*
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index abdb3004a1e3..97bca509a391 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -73,8 +73,6 @@ atomic_t rdma_stat_rq_prod;
 atomic_t rdma_stat_sq_poll;
 atomic_t rdma_stat_sq_prod;
 
-struct workqueue_struct *svc_rdma_wq;
-
 /*
  * This function implements reading and resetting an atomic_t stat
  * variable through read/write to a proc file. Any write to the file
@@ -230,7 +228,6 @@ static struct ctl_table svcrdma_root_table[] = {
 void svc_rdma_cleanup(void)
 {
 	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
-	destroy_workqueue(svc_rdma_wq);
 	if (svcrdma_table_header) {
 		unregister_sysctl_table(svcrdma_table_header);
 		svcrdma_table_header = NULL;
@@ -246,10 +243,6 @@ int svc_rdma_init(void)
 	dprintk("\tmax_bc_requests  : %u\n", svcrdma_max_bc_requests);
 	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
 
-	svc_rdma_wq = alloc_workqueue("svc_rdma", 0, 0);
-	if (!svc_rdma_wq)
-		return -ENOMEM;
-
 	if (!svcrdma_table_header)
 		svcrdma_table_header =
 			register_sysctl_table(svcrdma_root_table);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 65e2fb9aac65..96bccd398469 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -172,9 +172,10 @@ static void svc_rdma_recv_ctxt_destroy(struct svcxprt_rdma *rdma,
 void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
+	struct llist_node *node;
 
-	while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_recv_ctxts))) {
-		list_del(&ctxt->rc_list);
+	while ((node = llist_del_first(&rdma->sc_recv_ctxts))) {
+		ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node);
 		svc_rdma_recv_ctxt_destroy(rdma, ctxt);
 	}
 }
@@ -183,21 +184,18 @@ static struct svc_rdma_recv_ctxt *
 svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
+	struct llist_node *node;
 
-	spin_lock(&rdma->sc_recv_lock);
-	ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_recv_ctxts);
-	if (!ctxt)
+	node = llist_del_first(&rdma->sc_recv_ctxts);
+	if (!node)
 		goto out_empty;
-	list_del(&ctxt->rc_list);
-	spin_unlock(&rdma->sc_recv_lock);
+	ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node);
 
 out:
 	ctxt->rc_page_count = 0;
 	return ctxt;
 
 out_empty:
-	spin_unlock(&rdma->sc_recv_lock);
-
 	ctxt = svc_rdma_recv_ctxt_alloc(rdma);
 	if (!ctxt)
 		return NULL;
@@ -218,11 +216,9 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 	for (i = 0; i < ctxt->rc_page_count; i++)
 		put_page(ctxt->rc_pages[i]);
 
-	if (!ctxt->rc_temp) {
-		spin_lock(&rdma->sc_recv_lock);
-		list_add(&ctxt->rc_list, &rdma->sc_recv_ctxts);
-		spin_unlock(&rdma->sc_recv_lock);
-	} else
+	if (!ctxt->rc_temp)
+		llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts);
+	else
 		svc_rdma_recv_ctxt_destroy(rdma, ctxt);
 }
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 4d3db6ee7f09..145a3615c319 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -140,14 +140,13 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_send_ctxts);
-	INIT_LIST_HEAD(&cma_xprt->sc_recv_ctxts);
+	init_llist_head(&cma_xprt->sc_recv_ctxts);
 	INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts);
 	init_waitqueue_head(&cma_xprt->sc_send_wait);
 
 	spin_lock_init(&cma_xprt->sc_lock);
 	spin_lock_init(&cma_xprt->sc_rq_dto_lock);
 	spin_lock_init(&cma_xprt->sc_send_lock);
-	spin_lock_init(&cma_xprt->sc_recv_lock);
 	spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);
 
 	/*
@@ -630,8 +629,9 @@ static void svc_rdma_free(struct svc_xprt *xprt)
 {
 	struct svcxprt_rdma *rdma =
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
+
 	INIT_WORK(&rdma->sc_work, __svc_rdma_free);
-	queue_work(svc_rdma_wq, &rdma->sc_work);
+	schedule_work(&rdma->sc_work);
 }
 
 static int svc_rdma_has_wspace(struct svc_xprt *xprt)