From 4ed9ef32606386efc562bada891d7baa16fc46b4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Jul 2024 17:14:14 +1000 Subject: lockd: discard nlmsvc_timeout nlmsvc_timeout always has the same value as (nlm_timeout * HZ), so use that in the one place that nlmsvc_timeout is used. In truth it *might* not always be the same as nlmsvc_timeout is only set when lockd is started while nlm_timeout can be set at anytime via sysctl. I think this difference it not helpful so removing it is good. Also remove the test for nlm_timout being 0. This is not possible - unless a module parameter is used to set the minimum timeout to 0, and if that happens then it probably should be honoured. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') 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; -- cgit v1.2.3 From f2b27e1d72527f94f030b6356b3187576e60885b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Jul 2024 17:14:15 +1000 Subject: SUNRPC: make various functions static, or not exported. Various functions are only used within the sunrpc module, and several are only use in the one file. So clean up: These are marked static, and any EXPORT is removed. svc_rcpb_setup() svc_rqst_alloc() svc_rqst_free() - also moved before first use svc_rpcbind_set_version() svc_drop() - also moved to svc.c These are now not EXPORTed, but are not static. svc_authenticate() svc_sock_update_bufs() Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 9 --------- include/linux/sunrpc/svcauth.h | 1 - include/linux/sunrpc/svcsock.h | 2 -- 3 files changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a7d0406b9ef5..e4fa25fafa97 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -401,17 +401,13 @@ 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 +442,6 @@ 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/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); -- cgit v1.2.3 From 60749cbe3d8ae572a6c7dda675de3e8b25797a18 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Jul 2024 17:14:18 +1000 Subject: sunrpc: change sp_nrthreads from atomic_t to unsigned int. sp_nrthreads is only ever accessed under the service mutex nlmsvc_mutex nfs_callback_mutex nfsd_mutex so these is no need for it to be an atomic_t. The fact that all code using it is single-threaded means that we can simplify svc_pool_victim and remove the temporary elevation of sp_nrthreads. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index e4fa25fafa97..99e9345d829e 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -33,9 +33,9 @@ * 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 */ -- cgit v1.2.3 From 3391fc92db8e761f1a2df5612fcb999dac6bc00a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 16 Sep 2024 09:45:40 +1000 Subject: sunrpc: allow svc threads to fail initialisation cleanly If an svc thread needs to perform some initialisation that might fail, it has no good way to handle the failure. Before the thread can exit it must call svc_exit_thread(), but that requires the service mutex to be held. The thread cannot simply take the mutex as that could deadlock if there is a concurrent attempt to shut down all threads (which is unlikely, but not impossible). nfsd currently call svc_exit_thread() unprotected in the unlikely event that unshare_fs_struct() fails. We can clean this up by introducing svc_thread_init_status() by which an svc thread can report whether initialisation has succeeded. If it has, it continues normally into the action loop. If it has not, svc_thread_init_status() immediately aborts the thread. svc_start_kthread() waits for either of these to happen, and calls svc_exit_thread() (under the mutex) if the thread aborted. Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 99e9345d829e..c419a61f60e5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -21,6 +21,7 @@ #include #include #include +#include /* * @@ -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; -- cgit v1.2.3 From 36ffa3d0de54c1cf516ea32a5ec556f5c9874795 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Jul 2024 11:47:23 +1000 Subject: nfsd: be more systematic about selecting error codes for internal use. Rather than using ad hoc values for internal errors (30000, 11000, ...) use 'enum' to sequentially allocate numbers starting from the first known available number - now visible as NFS4ERR_FIRST_FREE. The goal is values that are distinct from all be32 error codes. To get those we must first select integers that are not already used, then convert them with cpu_to_be32(). Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Reviewed-by: Christoph Hellwig Signed-off-by: Chuck Lever --- include/linux/nfs4.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') 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 */ -- cgit v1.2.3 From c4de97f7c45434985e5dbf2d6ccc9eca676e37fe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 29 Jul 2024 16:52:32 -0400 Subject: svcrdma: Handle device removal outside of the CM event handler Synchronously wait for all disconnects to complete to ensure the transports have divested all hardware resources before the underlying RDMA device can safely be removed. Reviewed-by: Sagi Grimberg Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') 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 #include #include +#include #include #include @@ -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 */ -- cgit v1.2.3 From 4b132aacb0768ac1e652cf517097ea6f237214b9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 13 Sep 2024 14:08:13 -0400 Subject: tools: Add xdrgen Add a Python-based tool for translating XDR specifications into XDR encoder and decoder functions written in the Linux kernel's C coding style. The generator attempts to match the usual C coding style of the Linux kernel's SunRPC consumers. This approach is similar to the netlink code generator in tools/net/ynl . The maintainability benefits of machine-generated XDR code include: - Stronger type checking - Reduces the number of bugs introduced by human error - Makes the XDR code easier to audit and analyze - Enables rapid prototyping of new RPC-based protocols - Hardens the layering between protocol logic and marshaling - Makes it easier to add observability on demand - Unit tests might be built for both the tool and (automatically) for the generated code In addition, converting the XDR layer to use memory-safe languages such as Rust will be easier if much of the code can be converted automatically. Tested-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdrgen/_builtins.h | 243 ++++++++++++++++++++++++++++++++ include/linux/sunrpc/xdrgen/_defs.h | 26 ++++ 2 files changed, 269 insertions(+) create mode 100644 include/linux/sunrpc/xdrgen/_builtins.h create mode 100644 include/linux/sunrpc/xdrgen/_defs.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h new file mode 100644 index 000000000000..68746c59fc9a --- /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 + +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) != XDR_UNIT)) + 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) != XDR_UNIT)) + 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_ */ -- cgit v1.2.3 From 663ad8b1df8724cd5e01df66ea67ce0424fbcdf6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 Sep 2024 15:31:19 -0400 Subject: xdrgen: Fix return code checking in built-in XDR decoders xdr_stream_encode_u32() returns XDR_UNIT on success. xdr_stream_decode_u32() returns zero or -EMSGSIZE, but never XDR_UNIT. Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdrgen/_builtins.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h index 68746c59fc9a..66ca3ece951a 100644 --- a/include/linux/sunrpc/xdrgen/_builtins.h +++ b/include/linux/sunrpc/xdrgen/_builtins.h @@ -184,7 +184,7 @@ xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen) __be32 *p; u32 len; - if (unlikely(xdr_stream_decode_u32(xdr, &len) != XDR_UNIT)) + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return false; if (unlikely(maxlen && len > maxlen)) return false; @@ -215,7 +215,7 @@ xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen) __be32 *p; u32 len; - if (unlikely(xdr_stream_decode_u32(xdr, &len) != XDR_UNIT)) + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return false; if (unlikely(maxlen && len > maxlen)) return false; -- cgit v1.2.3