Merge tag 'nfs-for-6.18-1' of git://git.linux-nfs.org/projects/anna/linux-nfsHEADmaster

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Add a Kconfig option to redirect dfprintk() to the trace buffer
   - Enable use of the RWF_DONTCACHE flag on the NFS client
   - Add striped layout handling to pNFS flexfiles
   - Add proper localio handling for READ and WRITE O_DIRECT

  Bugfixes:
   - Handle NFS4ERR_GRACE errors during delegation recall
   - Fix NFSv4.1 backchannel max_resp_sz verification check
   - Fix mount hang after CREATE_SESSION failure
   - Fix d_parent->d_inode locking in nfs4_setup_readdir()

  Other Cleanups and Improvements:
   - Improvements to write handling tracepoints
   - Fix a few trivial spelling mistakes
   - Cleanups to the rpcbind cleanup call sites
   - Convert the SUNRPC xdr_buf to use a scratch folio instead of
     scratch page
   - Remove unused NFS_WBACK_BUSY() macro
   - Remove __GFP_NOWARN flags
   - Unexport rpc_malloc() and rpc_free()"

* tag 'nfs-for-6.18-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (46 commits)
  NFS: add basic STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
  nfs/localio: add tracepoints for misaligned DIO READ and WRITE support
  nfs/localio: add proper O_DIRECT support for READ and WRITE
  nfs/localio: refactor iocb initialization
  nfs/localio: refactor iocb and iov_iter_bvec initialization
  nfs/localio: avoid issuing misaligned IO using O_DIRECT
  nfs/localio: make trace_nfs_local_open_fh more useful
  NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
  sunrpc: unexport rpc_malloc() and rpc_free()
  NFSv4/flexfiles: Add support for striped layouts
  NFSv4/flexfiles: Update layout stats & error paths for striped layouts
  NFSv4/flexfiles: Write path updates for striped layouts
  NFSv4/flexfiles: Commit path updates for striped layouts
  NFSv4/flexfiles: Read path updates for striped layouts
  NFSv4/flexfiles: Update low level helper functions to be DS stripe aware.
  NFSv4/flexfiles: Add data structure support for striped layouts
  NFSv4/flexfiles: Use ds_commit_idx when marking a write commit
  NFSv4/flexfiles: Remove cred local variable dependency
  nfs4_setup_readdir(): insufficient locking for ->d_parent->d_inode dereferencing
  NFS: Enable use of the RWF_DONTCACHE flag on the NFS client
  ...

7 files changed, 31 insertions, 15 deletions

diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 2d8b67dac7b5..a570e7adf270 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -101,6 +101,20 @@ config SUNRPC_DEBUG
 
 	  If unsure, say Y.
 
+config SUNRPC_DEBUG_TRACE
+	bool "RPC: Send dfprintk() output to the trace buffer"
+	depends on SUNRPC_DEBUG && TRACING
+	default n
+	help
+          dprintk() output can be voluminous, which can overwhelm the
+          kernel's logging facility as it must be sent to the console.
+          This option causes dprintk() output to go to the trace buffer
+          instead of the kernel log.
+
+          This will cause warnings about trace_printk() being used to be
+          logged at boot time, so say N unless you are debugging a problem
+          with sunrpc-based clients or services.
+
 config SUNRPC_XPRT_RDMA
 	tristate "RPC-over-RDMA transport"
 	depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index cb32ab9a8395..7d2cdc2bd374 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -794,12 +794,12 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	struct gssx_res_accept_sec_context *res = data;
 	u32 value_follows;
 	int err;
-	struct page *scratch;
+	struct folio *scratch;
 
-	scratch = alloc_page(GFP_KERNEL);
+	scratch = folio_alloc(GFP_KERNEL, 0);
 	if (!scratch)
 		return -ENOMEM;
-	xdr_set_scratch_page(xdr, scratch);
+	xdr_set_scratch_folio(xdr, scratch);
 
 	/* res->status */
 	err = gssx_dec_status(xdr, &res->status);
@@ -844,6 +844,6 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	err = gssx_dec_option_array(xdr, &res->options);
 
 out_free:
-	__free_page(scratch);
+	folio_put(scratch);
 	return err;
 }
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 9b45fbdc90ca..016f16ca5779 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -1074,7 +1074,6 @@ int rpc_malloc(struct rpc_task *task)
 	rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(rpc_malloc);
 
 /**
  * rpc_free - free RPC buffer resources allocated via rpc_malloc
@@ -1095,7 +1094,6 @@ void rpc_free(struct rpc_task *task)
 	else
 		kfree(buf);
 }
-EXPORT_SYMBOL_GPL(rpc_free);
 
 /*
  * Creation and deletion of RPC task structures
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 4e92e2a50168..d8d8842c7de5 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -86,7 +86,7 @@ xdr_partial_copy_from_skb(struct xdr_buf *xdr, struct xdr_skb_reader *desc)
 		/* ACL likes to be lazy in allocating pages - ACLs
 		 * are small by default but can get huge. */
 		if ((xdr->flags & XDRBUF_SPARSE_PAGES) && *ppage == NULL) {
-			*ppage = alloc_page(GFP_NOWAIT | __GFP_NOWARN);
+			*ppage = alloc_page(GFP_NOWAIT);
 			if (unlikely(*ppage == NULL)) {
 				if (copied == 0)
 					return -ENOMEM;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index b1fab3a69544..de05ef637bdc 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -352,7 +352,7 @@ static int svc_pool_map_get_node(unsigned int pidx)
 		if (m->mode == SVC_POOL_PERNODE)
 			return m->pool_to[pidx];
 	}
-	return NUMA_NO_NODE;
+	return numa_mem_id();
 }
 /*
  * Set the given thread's cpus_allowed mask so that it
@@ -436,7 +436,6 @@ void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net)
 	svc_unregister(serv, net);
 	rpcb_put_local(net);
 }
-EXPORT_SYMBOL_GPL(svc_rpcb_cleanup);
 
 static int svc_uses_rpcbind(struct svc_serv *serv)
 {
@@ -670,8 +669,8 @@ svc_rqst_free(struct svc_rqst *rqstp)
 	folio_batch_release(&rqstp->rq_fbatch);
 	kfree(rqstp->rq_bvec);
 	svc_release_buffer(rqstp);
-	if (rqstp->rq_scratch_page)
-		put_page(rqstp->rq_scratch_page);
+	if (rqstp->rq_scratch_folio)
+		folio_put(rqstp->rq_scratch_folio);
 	kfree(rqstp->rq_resp);
 	kfree(rqstp->rq_argp);
 	kfree(rqstp->rq_auth_data);
@@ -692,8 +691,8 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
 
-	rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0);
-	if (!rqstp->rq_scratch_page)
+	rqstp->rq_scratch_folio = __folio_alloc_node(GFP_KERNEL, 0, node);
+	if (!rqstp->rq_scratch_folio)
 		goto out_enomem;
 
 	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 8b1837228799..049ab53088e9 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1102,6 +1102,7 @@ static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net)
  * svc_xprt_destroy_all - Destroy transports associated with @serv
  * @serv: RPC service to be shut down
  * @net: target network namespace
+ * @unregister: true if it is OK to unregister the destroyed xprts
  *
  * Server threads may still be running (especially in the case where the
  * service is still running in other network namespaces).
@@ -1114,7 +1115,8 @@ static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net)
  * threads, we may need to wait a little while and then check again to
  * see if they're done.
  */
-void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net)
+void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net,
+			  bool unregister)
 {
 	int delay = 0;
 
@@ -1124,6 +1126,9 @@ void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net)
 		svc_clean_up_xprts(serv, net);
 		msleep(delay++);
 	}
+
+	if (unregister)
+		svc_rpcb_cleanup(serv, net);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_destroy_all);
 
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 1478c41c7e9d..3aac1456e23e 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -190,7 +190,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf)
 	ppages = buf->pages + (buf->page_base >> PAGE_SHIFT);
 	while (len > 0) {
 		if (!*ppages)
-			*ppages = alloc_page(GFP_NOWAIT | __GFP_NOWARN);
+			*ppages = alloc_page(GFP_NOWAIT);
 		if (!*ppages)
 			return -ENOBUFS;
 		ppages++;