Merge tag 'nfsd-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "Notable features of this release include:

   - Pre-requisites for automatically determining the RPC server thread
     count

   - Clean-up and preparation for supporting LOCALIO, which will be
     merged via the NFS client tree

   - Enhancements and fixes to NFSv4.2 COPY offload

   - A new Python-based tool for generating kernel SunRPC XDR encoding
     and decoding functions, added as an aid for prototyping features in
     protocols based on the Linux kernel's SunRPC implementation

  As always I am grateful to the NFSD contributors, reviewers, testers,
  and bug reporters who participated during this cycle"

* tag 'nfsd-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (57 commits)
  xdrgen: Prevent reordering of encoder and decoder functions
  xdrgen: typedefs should use the built-in string and opaque functions
  xdrgen: Fix return code checking in built-in XDR decoders
  tools: Add xdrgen
  nfsd: fix delegation_blocked() to block correctly for at least 30 seconds
  nfsd: fix initial getattr on write delegation
  nfsd: untangle code in nfsd4_deleg_getattr_conflict()
  nfsd: enforce upper limit for namelen in __cld_pipe_inprogress_downcall()
  nfsd: return -EINVAL when namelen is 0
  NFSD: Wrap async copy operations with trace points
  NFSD: Clean up extra whitespace in trace_nfsd_copy_done
  NFSD: Record the callback stateid in copy tracepoints
  NFSD: Display copy stateids with conventional print formatting
  NFSD: Limit the number of concurrent async COPY operations
  NFSD: Async COPY result needs to return a write verifier
  nfsd: avoid races with wake_up_var()
  nfsd: use clear_and_wake_up_bit()
  sunrpc: xprtrdma: Use ERR_CAST() to return
  NFSD: Annotate struct pnfs_block_deviceaddr with __counted_by()
  nfsd: call cache_put if xdr_reserve_space returns NULL
  ...

10 files changed, 339 insertions, 22 deletions

diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 1b95fe31051f..61c4b9c41904 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -200,7 +200,7 @@ extern const struct svc_procedure nlmsvc_procedures[24];
 extern const struct svc_procedure nlmsvc_procedures4[24];
 #endif
 extern int			nlmsvc_grace_period;
-extern unsigned long		nlmsvc_timeout;
+extern unsigned long		nlm_timeout;
 extern bool			nsm_use_hostnames;
 extern u32			nsm_local_state;
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index f9df88091c6d..8d7430d9f218 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -281,15 +281,18 @@ enum nfsstat4 {
 	/* nfs42 */
 	NFS4ERR_PARTNER_NOTSUPP	= 10088,
 	NFS4ERR_PARTNER_NO_AUTH	= 10089,
-	NFS4ERR_UNION_NOTSUPP = 10090,
-	NFS4ERR_OFFLOAD_DENIED = 10091,
-	NFS4ERR_WRONG_LFS = 10092,
-	NFS4ERR_BADLABEL = 10093,
-	NFS4ERR_OFFLOAD_NO_REQS = 10094,
+	NFS4ERR_UNION_NOTSUPP	= 10090,
+	NFS4ERR_OFFLOAD_DENIED	= 10091,
+	NFS4ERR_WRONG_LFS	= 10092,
+	NFS4ERR_BADLABEL	= 10093,
+	NFS4ERR_OFFLOAD_NO_REQS	= 10094,
 
 	/* xattr (RFC8276) */
-	NFS4ERR_NOXATTR        = 10095,
-	NFS4ERR_XATTR2BIG      = 10096,
+	NFS4ERR_NOXATTR		= 10095,
+	NFS4ERR_XATTR2BIG	= 10096,
+
+	/* can be used for internal errors */
+	NFS4ERR_FIRST_FREE
 };
 
 /* error codes for internal client use */
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index a7d0406b9ef5..c419a61f60e5 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -21,6 +21,7 @@
 #include <linux/wait.h>
 #include <linux/mm.h>
 #include <linux/pagevec.h>
+#include <linux/kthread.h>
 
 /*
  *
@@ -33,9 +34,9 @@
  * node traffic on multi-node NUMA NFS servers.
  */
 struct svc_pool {
-	unsigned int		sp_id;	    	/* pool id; also node id on NUMA */
+	unsigned int		sp_id;		/* pool id; also node id on NUMA */
 	struct lwq		sp_xprts;	/* pending transports */
-	atomic_t		sp_nrthreads;	/* # of threads in pool */
+	unsigned int		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
 	struct llist_head	sp_idle_threads; /* idle server threads */
 
@@ -232,6 +233,11 @@ struct svc_rqst {
 	struct net		*rq_bc_net;	/* pointer to backchannel's
 						 * net namespace
 						 */
+
+	int			rq_err;		/* Thread sets this to inidicate
+						 * initialisation success.
+						 */
+
 	unsigned long	bc_to_initval;
 	unsigned int	bc_to_retries;
 	void **			rq_lease_breaker; /* The v4 client breaking a lease */
@@ -305,6 +311,31 @@ static inline bool svc_thread_should_stop(struct svc_rqst *rqstp)
 	return test_bit(RQ_VICTIM, &rqstp->rq_flags);
 }
 
+/**
+ * svc_thread_init_status - report whether thread has initialised successfully
+ * @rqstp: the thread in question
+ * @err: errno code
+ *
+ * After performing any initialisation that could fail, and before starting
+ * normal work, each sunrpc svc_thread must call svc_thread_init_status()
+ * with an appropriate error, or zero.
+ *
+ * If zero is passed, the thread is ready and must continue until
+ * svc_thread_should_stop() returns true.  If a non-zero error is passed
+ * the call will not return - the thread will exit.
+ */
+static inline void svc_thread_init_status(struct svc_rqst *rqstp, int err)
+{
+	rqstp->rq_err = err;
+	/* memory barrier ensures assignment to error above is visible before
+	 * waitqueue_active() test below completes.
+	 */
+	smp_mb();
+	wake_up_var(&rqstp->rq_err);
+	if (err)
+		kthread_exit(1);
+}
+
 struct svc_deferred_req {
 	u32			prot;	/* protocol (UDP or TCP) */
 	struct svc_xprt		*xprt;
@@ -401,17 +432,13 @@ struct svc_procedure {
  */
 int sunrpc_set_pool_mode(const char *val);
 int sunrpc_get_pool_mode(char *val, size_t size);
-int svc_rpcb_setup(struct svc_serv *serv, struct net *net);
 void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net);
 int svc_bind(struct svc_serv *serv, struct net *net);
 struct svc_serv *svc_create(struct svc_program *, unsigned int,
 			    int (*threadfn)(void *data));
-struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv,
-					struct svc_pool *pool, int node);
 bool		   svc_rqst_replace_page(struct svc_rqst *rqstp,
 					 struct page *page);
 void		   svc_rqst_release_pages(struct svc_rqst *rqstp);
-void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
 struct svc_serv *  svc_create_pooled(struct svc_program *prog,
 				     struct svc_stat *stats,
@@ -446,11 +473,6 @@ int		   svc_generic_rpcbind_set(struct net *net,
 					   u32 version, int family,
 					   unsigned short proto,
 					   unsigned short port);
-int		   svc_rpcbind_set_version(struct net *net,
-					   const struct svc_program *progp,
-					   u32 version, int family,
-					   unsigned short proto,
-					   unsigned short port);
 
 #define	RPC_MAX_ADDRBUFLEN	(63U)
 
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index d33bab33099a..619fc0bd837a 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -48,6 +48,7 @@
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/rpc_rdma_cid.h>
 #include <linux/sunrpc/svc_rdma_pcl.h>
+#include <linux/sunrpc/rdma_rn.h>
 
 #include <linux/percpu_counter.h>
 #include <rdma/ib_verbs.h>
@@ -76,6 +77,7 @@ struct svcxprt_rdma {
 	struct svc_xprt      sc_xprt;		/* SVC transport structure */
 	struct rdma_cm_id    *sc_cm_id;		/* RDMA connection id */
 	struct list_head     sc_accept_q;	/* Conn. waiting accept */
+	struct rpcrdma_notification sc_rn;	/* removal notification */
 	int		     sc_ord;		/* RDMA read limit */
 	int                  sc_max_send_sges;
 	bool		     sc_snd_w_inv;	/* OK to use Send With Invalidate */
diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 61c455f1e1f5..63cf6fb26dcc 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -151,7 +151,6 @@ struct auth_ops {
 
 struct svc_xprt;
 
-extern enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp);
 extern rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp);
 extern int	svc_authorise(struct svc_rqst *rqstp);
 extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp);
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 7c78ec6356b9..bf45d9e8492a 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -58,8 +58,6 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk)
  */
 void		svc_recv(struct svc_rqst *rqstp);
 void		svc_send(struct svc_rqst *rqstp);
-void		svc_drop(struct svc_rqst *);
-void		svc_sock_update_bufs(struct svc_serv *serv);
 int		svc_addsock(struct svc_serv *serv, struct net *net,
 			    const int fd, char *name_return, const size_t len,
 			    const struct cred *cred);
diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h
new file mode 100644
index 000000000000..66ca3ece951a
--- /dev/null
+++ b/include/linux/sunrpc/xdrgen/_builtins.h
@@ -0,0 +1,243 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Oracle and/or its affiliates.
+ *
+ * This header defines XDR data type primitives specified in
+ * Section 4 of RFC 4506, used by RPC programs implemented
+ * in the Linux kernel.
+ */
+
+#ifndef _SUNRPC_XDRGEN__BUILTINS_H_
+#define _SUNRPC_XDRGEN__BUILTINS_H_
+
+#include <linux/sunrpc/xdr.h>
+
+static inline bool
+xdrgen_decode_void(struct xdr_stream *xdr)
+{
+	return true;
+}
+
+static inline bool
+xdrgen_encode_void(struct xdr_stream *xdr)
+{
+	return true;
+}
+
+static inline bool
+xdrgen_decode_bool(struct xdr_stream *xdr, bool *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = (*p != xdr_zero);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_bool(struct xdr_stream *xdr, bool val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*p = val ? xdr_one : xdr_zero;
+	return true;
+}
+
+static inline bool
+xdrgen_decode_int(struct xdr_stream *xdr, s32 *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = be32_to_cpup(p);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_int(struct xdr_stream *xdr, s32 val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*p = cpu_to_be32(val);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_unsigned_int(struct xdr_stream *xdr, u32 *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = be32_to_cpup(p);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_unsigned_int(struct xdr_stream *xdr, u32 val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*p = cpu_to_be32(val);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_long(struct xdr_stream *xdr, s32 *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = be32_to_cpup(p);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_long(struct xdr_stream *xdr, s32 val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*p = cpu_to_be32(val);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_unsigned_long(struct xdr_stream *xdr, u32 *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = be32_to_cpup(p);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_unsigned_long(struct xdr_stream *xdr, u32 val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+	if (unlikely(!p))
+		return false;
+	*p = cpu_to_be32(val);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_hyper(struct xdr_stream *xdr, s64 *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT * 2);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = get_unaligned_be64(p);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_hyper(struct xdr_stream *xdr, s64 val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2);
+
+	if (unlikely(!p))
+		return false;
+	put_unaligned_be64(val, p);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_unsigned_hyper(struct xdr_stream *xdr, u64 *ptr)
+{
+	__be32 *p = xdr_inline_decode(xdr, XDR_UNIT * 2);
+
+	if (unlikely(!p))
+		return false;
+	*ptr = get_unaligned_be64(p);
+	return true;
+}
+
+static inline bool
+xdrgen_encode_unsigned_hyper(struct xdr_stream *xdr, u64 val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2);
+
+	if (unlikely(!p))
+		return false;
+	put_unaligned_be64(val, p);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen)
+{
+	__be32 *p;
+	u32 len;
+
+	if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0))
+		return false;
+	if (unlikely(maxlen && len > maxlen))
+		return false;
+	if (len != 0) {
+		p = xdr_inline_decode(xdr, len);
+		if (unlikely(!p))
+			return false;
+		ptr->data = (unsigned char *)p;
+	}
+	ptr->len = len;
+	return true;
+}
+
+static inline bool
+xdrgen_encode_string(struct xdr_stream *xdr, string val, u32 maxlen)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(val.len));
+
+	if (unlikely(!p))
+		return false;
+	xdr_encode_opaque(p, val.data, val.len);
+	return true;
+}
+
+static inline bool
+xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen)
+{
+	__be32 *p;
+	u32 len;
+
+	if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0))
+		return false;
+	if (unlikely(maxlen && len > maxlen))
+		return false;
+	if (len != 0) {
+		p = xdr_inline_decode(xdr, len);
+		if (unlikely(!p))
+			return false;
+		ptr->data = (u8 *)p;
+	}
+	ptr->len = len;
+	return true;
+}
+
+static inline bool
+xdrgen_encode_opaque(struct xdr_stream *xdr, opaque val)
+{
+	__be32 *p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(val.len));
+
+	if (unlikely(!p))
+		return false;
+	xdr_encode_opaque(p, val.data, val.len);
+	return true;
+}
+
+#endif /* _SUNRPC_XDRGEN__BUILTINS_H_ */
diff --git a/include/linux/sunrpc/xdrgen/_defs.h b/include/linux/sunrpc/xdrgen/_defs.h
new file mode 100644
index 000000000000..be9e62371758
--- /dev/null
+++ b/include/linux/sunrpc/xdrgen/_defs.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Oracle and/or its affiliates.
+ *
+ * This header defines XDR data type primitives specified in
+ * Section 4 of RFC 4506, used by RPC programs implemented
+ * in the Linux kernel.
+ */
+
+#ifndef _SUNRPC_XDRGEN__DEFS_H_
+#define _SUNRPC_XDRGEN__DEFS_H_
+
+#define TRUE	(true)
+#define FALSE	(false)
+
+typedef struct {
+	u32 len;
+	unsigned char *data;
+} string;
+
+typedef struct {
+	u32 len;
+	u8 *data;
+} opaque;
+
+#endif /* _SUNRPC_XDRGEN__DEFS_H_ */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index a96a985c49b3..e6a72646c507 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2172,6 +2172,29 @@ TRACE_EVENT(svcrdma_qp_error,
 	)
 );
 
+TRACE_EVENT(svcrdma_device_removal,
+	TP_PROTO(
+		const struct rdma_cm_id *id
+	),
+
+	TP_ARGS(id),
+
+	TP_STRUCT__entry(
+		__string(name, id->device->name)
+		__array(unsigned char, addr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		memcpy(__entry->addr, &id->route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("device %s to be removed, disconnecting %pISpc\n",
+		__get_str(name), __entry->addr
+	)
+);
+
 DECLARE_EVENT_CLASS(svcrdma_sendqueue_class,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h
index 7b221d51133a..c82233e950ac 100644
--- a/include/trace/misc/nfs.h
+++ b/include/trace/misc/nfs.h
@@ -51,6 +51,7 @@ TRACE_DEFINE_ENUM(NFSERR_JUKEBOX);
 		{ NFSERR_IO,			"IO" }, \
 		{ NFSERR_NXIO,			"NXIO" }, \
 		{ ECHILD,			"CHILD" }, \
+		{ ETIMEDOUT,			"TIMEDOUT" }, \
 		{ NFSERR_EAGAIN,		"AGAIN" }, \
 		{ NFSERR_ACCES,			"ACCES" }, \
 		{ NFSERR_EXIST,			"EXIST" }, \