Skip to contentSkip to conversation

svc: SVC Transport Switch

PATCH In review Tom Tucker 2 participants 43 messages Dec 31, 2007 2 messages not in the archive

Subsystems (3)
lore
Share & tools
lore

Tom Tucker

author
#0 lore raw

cover svc: SVC Transport Switch

The Server Side Transport switch implements a pluggable transport provider layer for RPC servers. This allows network transport drivers to be dynamically loaded and registered, thereby extending the set of transports that can carry RPC. This patchset includes a transport provider driver for TCP and UDP sockets.

This version of the patchset is functionally equivalent to the preceding patchset and includes the following improvements:

- Fixed a bug in svc_create_socket that resulted in svc_xprt_received being called without holding the XPT_BUSY bit.

- Added a BUG_ON in svc_xprt_received to catch providers calling svc_xprt_received without holding the XPT_BUSY bit.

- Removed code setting the XPT_BUSY bit in the create path and moved this logic to common code.

- Cleaned up the SMP locking strategy comment and moved it to svc_xprt.c

- Changed return type of svc_unreg_xprt_class to void

- Simplified transport class removal logic

- Fixed a white-space abuse issue

- Made some style changes to the patch comments

- Created a separate patch that moves the connection limit code to generic logic

- Created a separate patch that moves the call to svc_xprt_received out of tcp_accept and into common logic

- Created a separate patch for removal of unnecessary call to svc_sock_enqueue in svc_tcp_accept function

- Removed silly BUG_ON from kref svc_xprt_free callback function

- Moved unlock of svc_xprt_class list to after the try_module_lock call.

- Refactored svc_create_xprt logic

- Removed unnecessary call to svc_find_xprt in portlist code

Signature · 1 line
Signed-off-by: Tom Tucker <[email protected]>

A message that is not in the archive (sent off-list or not yet received): 20071231030712.8430.45576.stgit-gUwIgmpLGaKNDNWfRnPdfg@public.gmane.org

author
#2 lore raw

PATCH 1/40 svc: Add an svc transport class

The transport class (svc_xprt_class) represents a type of transport, e.g. udp, tcp, rdma. A transport class has a unique name and a set of transport operations kept in the svc_xprt_ops structure.

A transport class can be dynamically registered and unregisterd. The svc_xprt_class represents the module that implements the transport type and keeps reference counts on the module to avoid unloading while there are active users.

The endpoint (svc_xprt) is a generic, transport independent endpoint that can be used to send and receive data for an RPC service. It inherits it's operations from the transport class.

A transport driver module registers and unregisters itself with svc sunrpc by calling svc_reg_xprt_class, and svc_unreg_xprt_class respectively.

---

 include/linux/sunrpc/debug.h    |    1 
 include/linux/sunrpc/svc_xprt.h |   31 +++++++++++++++
 net/sunrpc/Makefile             |    3 +
 net/sunrpc/svc_xprt.c           |   83 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 117 insertions(+), 1 deletions(-)
include/linux/sunrpc/debug.h +1 -0
index 3912cf1..092fcfa 100644
@@ -21,6 +21,7 @@
 #define RPCDBG_SCHED		0x0040
 #define RPCDBG_TRANS		0x0080
 #define RPCDBG_SVCSOCK		0x0100
+#define RPCDBG_SVCXPRT		0x0100
 #define RPCDBG_SVCDSP		0x0200
 #define RPCDBG_MISC		0x0400
 #define RPCDBG_CACHE		0x0800
include/linux/sunrpc/svc_xprt.h new file +31 -0
new file mode 100644
index 0000000..fe8e787
@@ -0,0 +1,31 @@
+/*
+ * linux/include/linux/sunrpc/svc_xprt.h
+ *
+ * RPC server transport I/O
+ */
+
+#ifndef SUNRPC_SVC_XPRT_H
+#define SUNRPC_SVC_XPRT_H
+
+#include <linux/sunrpc/svc.h>
+
+struct svc_xprt_ops {
+};
+
+struct svc_xprt_class {
+	const char		*xcl_name;
+	struct module		*xcl_owner;
+	struct svc_xprt_ops	*xcl_ops;
+	struct list_head	xcl_list;
+};
+
+struct svc_xprt {
+	struct svc_xprt_class	*xpt_class;
+	struct svc_xprt_ops	*xpt_ops;
+};
+
+int	svc_reg_xprt_class(struct svc_xprt_class *);
+void	svc_unreg_xprt_class(struct svc_xprt_class *);
+void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *);
+
+#endif /* SUNRPC_SVC_XPRT_H */
net/sunrpc/Makefile +2 -1
index 5c69a72..92e1dbe 100644
@@ -11,6 +11,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    auth.o auth_null.o auth_unix.o \
 	    svc.o svcsock.o svcauth.o svcauth_unix.o \
 	    rpcb_clnt.o timer.o xdr.o \
-	    sunrpc_syms.o cache.o rpc_pipe.o
+	    sunrpc_syms.o cache.o rpc_pipe.o \
+	    svc_xprt.o
 sunrpc-$(CONFIG_PROC_FS) += stats.o
 sunrpc-$(CONFIG_SYSCTL) += sysctl.o
net/sunrpc/svc_xprt.c new file +83 -0

83 lines not on this page · raw message

author
#3 lore raw

PATCH 2/40 svc: Make svc_sock the tcp/udp transport

In reply to a message not in the archive

Make TCP and UDP svc_sock transports, and register them with the svc transport core.

A transport type (svc_sock) has an svc_xprt as its first member, and calls svc_xprt_init to initialize this field.

---

 include/linux/sunrpc/debug.h   |    1 -
 include/linux/sunrpc/svcsock.h |    4 ++++
 net/sunrpc/sunrpc_syms.c       |    4 +++-
 net/sunrpc/svcsock.c           |   32 +++++++++++++++++++++++++++++++-
 4 files changed, 38 insertions(+), 3 deletions(-)
include/linux/sunrpc/debug.h +0 -1
index 092fcfa..10709cb 100644
@@ -20,7 +20,6 @@
 #define RPCDBG_BIND		0x0020
 #define RPCDBG_SCHED		0x0040
 #define RPCDBG_TRANS		0x0080
-#define RPCDBG_SVCSOCK		0x0100
 #define RPCDBG_SVCXPRT		0x0100
 #define RPCDBG_SVCDSP		0x0200
 #define RPCDBG_MISC		0x0400
include/linux/sunrpc/svcsock.h +4 -0
index a53e0fa..1878cbe 100644
@@ -10,11 +10,13 @@
 #define SUNRPC_SVCSOCK_H
 
 #include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/svc_xprt.h>
 
 /*
  * RPC server socket.
  */
 struct svc_sock {
+	struct svc_xprt		sk_xprt;
 	struct list_head	sk_ready;	/* list of ready sockets */
 	struct list_head	sk_list;	/* list of all sockets */
 	struct socket *		sk_sock;	/* berkeley socket layer */
@@ -78,6 +80,8 @@ int		svc_addsock(struct svc_serv *serv,
 			    int fd,
 			    char *name_return,
 			    int *proto);
+void		svc_init_xprt_sock(void);
+void		svc_cleanup_xprt_sock(void);
 
 /*
  * svc_makesock socket characteristics
net/sunrpc/sunrpc_syms.c +3 -1
index 33d89e8..79ea05f 100644
@@ -151,7 +151,8 @@ init_sunrpc(void)
 #endif
 	cache_register(&ip_map_cache);
 	cache_register(&unix_gid_cache);
-	init_socket_xprt();
+	svc_init_xprt_sock();	/* svc sock transport */
+	init_socket_xprt();	/* clnt sock transport */
 	rpcauth_init_module();
 out:
 	return err;
@@ -162,6 +163,7 @@ cleanup_sunrpc(void)
 {
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
+	svc_cleanup_xprt_sock();
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
 	if (cache_unregister(&ip_map_cache))
net/sunrpc/svcsock.c +31 -1
index c75bffe..54f1b3d 100644
@@ -75,7 +75,7 @@
  *
  */
 
-#define RPCDBG_FACILITY	RPCDBG_SVCSOCK
+#define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
 
 static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
@@ -900,12 +900,21 @@ svc_udp_sendto(struct svc_rqst *rqstp)
 	return error;
 }
 
+static struct svc_xprt_ops svc_udp_ops = {
+};
+
+static struct svc_xprt_class svc_udp_class = {
+	.xcl_name = "udp",
+	.xcl_ops = &svc_udp_ops,
+};
+
 static void
 svc_udp_init(struct svc_sock *svsk)
 {
 	int one = 1;
 	mm_segment_t oldfs;
 
+	svc_xprt_init(&svc_udp_class, &svsk->sk_xprt);
 	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
 	svsk->sk_sk->sk_write_space = svc_write_space;
 	svsk->sk_recvfrom = svc_udp_recvfrom;
@@ -1344,12 +1353,33 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 	return sent;
 }
 
+static struct svc_xprt_ops svc_tcp_ops = {
+};
+
+static struct svc_xprt_class svc_tcp_class = {
+	.xcl_name = "tcp",
+	.xcl_ops = &svc_tcp_ops,
+};
+
+void svc_init_xprt_sock(void)
+{
+	svc_reg_xprt_class(&svc_tcp_class);
+	svc_reg_xprt_class(&svc_udp_class);
+}
+
+void svc_cleanup_xprt_sock(void)
+{
+	svc_unreg_xprt_class(&svc_tcp_class);
+	svc_unreg_xprt_class(&svc_udp_class);
+}
+
 static void
 svc_tcp_init(struct svc_sock *svsk)
 {
 	struct sock	*sk = svsk->sk_sk;
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt);
 	svsk->sk_recvfrom = svc_tcp_recvfrom;
 	svsk->sk_sendto = svc_tcp_sendto;
 
author
#4 lore raw

PATCH 3/40 svc: Change the svc_sock in the rqstp structure to a transport

In reply to a message not in the archive

The rqstp structure contains a pointer to the transport for the RPC request. This functionaly trivial patch adds an unamed union with pointers to both svc_sock and svc_xprt. Ultimately the union will be removed and only the rq_xprt field will remain. This allows incrementally extracting transport independent interfaces without one gigundo patch.

---

 include/linux/sunrpc/svc.h |    5 ++++-
 1 files changed, 4 insertions(+), 1 deletions(-)
include/linux/sunrpc/svc.h +4 -1
index 8531a70..37f7448 100644
@@ -204,7 +204,10 @@ union svc_addr_u {
 struct svc_rqst {
 	struct list_head	rq_list;	/* idle list */
 	struct list_head	rq_all;		/* all threads list */
-	struct svc_sock *	rq_sock;	/* socket */
+	union {
+		struct svc_xprt *	rq_xprt;	/* transport ptr */
+		struct svc_sock *	rq_sock; 	/* socket ptr */
+	};
 	struct sockaddr_storage	rq_addr;	/* peer address */
 	size_t			rq_addrlen;
 
author
#5 lore raw

PATCH 4/40 svc: Add a max payload value to the transport

In reply to a message not in the archive

The svc_max_payload function currently looks at the socket type to determine the max payload. Add a max payload value to svc_xprt_class so it can be returned directly.

---

 include/linux/sunrpc/svc_xprt.h |    1 +
 net/sunrpc/svc.c                |    4 +---
 net/sunrpc/svcsock.c            |    2 ++
 3 files changed, 4 insertions(+), 3 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index fe8e787..187dc4e 100644
@@ -17,6 +17,7 @@ struct svc_xprt_class {
 	struct module		*xcl_owner;
 	struct svc_xprt_ops	*xcl_ops;
 	struct list_head	xcl_list;
+	u32			xcl_max_payload;
 };
 
 struct svc_xprt {
net/sunrpc/svc.c +1 -3
index a4a6bf7..ea3fa86 100644
@@ -1054,10 +1054,8 @@ err_bad:
  */
 u32 svc_max_payload(const struct svc_rqst *rqstp)
 {
-	int max = RPCSVC_MAXPAYLOAD_TCP;
+	u32 max = rqstp->rq_xprt->xpt_class->xcl_max_payload;
 
-	if (rqstp->rq_sock->sk_sock->type == SOCK_DGRAM)
-		max = RPCSVC_MAXPAYLOAD_UDP;
 	if (rqstp->rq_server->sv_max_payload < max)
 		max = rqstp->rq_server->sv_max_payload;
 	return max;
net/sunrpc/svcsock.c +2 -0
index 54f1b3d..c507f6f 100644
@@ -906,6 +906,7 @@ static struct svc_xprt_ops svc_udp_ops = {
 static struct svc_xprt_class svc_udp_class = {
 	.xcl_name = "udp",
 	.xcl_ops = &svc_udp_ops,
+	.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
 };
 
 static void
@@ -1359,6 +1360,7 @@ static struct svc_xprt_ops svc_tcp_ops = {
 static struct svc_xprt_class svc_tcp_class = {
 	.xcl_name = "tcp",
 	.xcl_ops = &svc_tcp_ops,
+	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
 };
 
 void svc_init_xprt_sock(void)
author
#6 lore raw

PATCH 5/40 svc: Move sk_sendto and sk_recvfrom to svc_xprt_class

In reply to a message not in the archive

The sk_sendto and sk_recvfrom are function pointers that allow svc_sock to be used for both UDP and TCP. Move these function pointers to the svc_xprt_ops structure.

---

 include/linux/sunrpc/svc_xprt.h |    2 ++
 include/linux/sunrpc/svcsock.h  |    3 ---
 net/sunrpc/svcsock.c            |   12 ++++++------
 3 files changed, 8 insertions(+), 9 deletions(-)
include/linux/sunrpc/svc_xprt.h +2 -0
index 187dc4e..7ae6c85 100644
@@ -10,6 +10,8 @@
 #include <linux/sunrpc/svc.h>
 
 struct svc_xprt_ops {
+	int		(*xpo_recvfrom)(struct svc_rqst *);
+	int		(*xpo_sendto)(struct svc_rqst *);
 };
 
 struct svc_xprt_class {
include/linux/sunrpc/svcsock.h +0 -3
index 1878cbe..08e78d0 100644
@@ -45,9 +45,6 @@ struct svc_sock {
 						 * be revisted */
 	struct mutex		sk_mutex;	/* to serialize sending data */
 
-	int			(*sk_recvfrom)(struct svc_rqst *rqstp);
-	int			(*sk_sendto)(struct svc_rqst *rqstp);
-
 	/* We keep the old state_change and data_ready CB's here */
 	void			(*sk_ostate)(struct sock *);
 	void			(*sk_odata)(struct sock *, int bytes);
net/sunrpc/svcsock.c +6 -6
index c507f6f..7817c7e 100644
@@ -901,6 +901,8 @@ svc_udp_sendto(struct svc_rqst *rqstp)
 }
 
 static struct svc_xprt_ops svc_udp_ops = {
+	.xpo_recvfrom = svc_udp_recvfrom,
+	.xpo_sendto = svc_udp_sendto,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -918,8 +920,6 @@ svc_udp_init(struct svc_sock *svsk)
 	svc_xprt_init(&svc_udp_class, &svsk->sk_xprt);
 	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
 	svsk->sk_sk->sk_write_space = svc_write_space;
-	svsk->sk_recvfrom = svc_udp_recvfrom;
-	svsk->sk_sendto = svc_udp_sendto;
 
 	/* initialise setting must have enough space to
 	 * receive and respond to one request.
@@ -1355,6 +1355,8 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 }
 
 static struct svc_xprt_ops svc_tcp_ops = {
+	.xpo_recvfrom = svc_tcp_recvfrom,
+	.xpo_sendto = svc_tcp_sendto,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
@@ -1382,8 +1384,6 @@ svc_tcp_init(struct svc_sock *svsk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt);
-	svsk->sk_recvfrom = svc_tcp_recvfrom;
-	svsk->sk_sendto = svc_tcp_sendto;
 
 	if (sk->sk_state == TCP_LISTEN) {
 		dprintk("setting up TCP socket for listening\n");
@@ -1531,7 +1531,7 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
 		 rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
-	len = svsk->sk_recvfrom(rqstp);
+	len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
 	dprintk("svc: got len=%d\n", len);
 
 	/* No data, incomplete (TCP) read, or accept() */
@@ -1591,7 +1591,7 @@ svc_send(struct svc_rqst *rqstp)
 	if (test_bit(SK_DEAD, &svsk->sk_flags))
 		len = -ENOTCONN;
 	else
-		len = svsk->sk_sendto(rqstp);
+		len = svsk->sk_xprt.xpt_ops->xpo_sendto(rqstp);
 	mutex_unlock(&svsk->sk_mutex);
 	svc_sock_release(rqstp);
 
author
#7 lore raw

PATCH 6/40 svc: Add transport specific xpo_release function

In reply to a message not in the archive

The svc_sock_release function releases pages allocated to a thread. For UDP this frees the receive skb. For RDMA it will post a receive WR and bump the client credit count.

---

 include/linux/sunrpc/svc.h      |    2 +-
 include/linux/sunrpc/svc_xprt.h |    1 +
 net/sunrpc/svcsock.c            |   17 +++++++++--------
 3 files changed, 11 insertions(+), 9 deletions(-)
include/linux/sunrpc/svc.h +1 -1
index 37f7448..cfb2652 100644
@@ -217,7 +217,7 @@ struct svc_rqst {
 	struct auth_ops *	rq_authop;	/* authentication flavour */
 	u32			rq_flavor;	/* pseudoflavor */
 	struct svc_cred		rq_cred;	/* auth info */
-	struct sk_buff *	rq_skbuff;	/* fast recv inet buffer */
+	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
 
 	struct xdr_buf		rq_arg;
include/linux/sunrpc/svc_xprt.h +1 -0
index 7ae6c85..01ee7bc 100644
@@ -12,6 +12,7 @@
 struct svc_xprt_ops {
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
+	void		(*xpo_release_rqst)(struct svc_rqst *);
 };
 
 struct svc_xprt_class {
net/sunrpc/svcsock.c +9 -8
index 7817c7e..d46abc8 100644
@@ -185,14 +185,13 @@ svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
 /*
  * Release an skbuff after use
  */
-static inline void
-svc_release_skb(struct svc_rqst *rqstp)
+static void svc_release_skb(struct svc_rqst *rqstp)
 {
-	struct sk_buff *skb = rqstp->rq_skbuff;
+	struct sk_buff *skb = rqstp->rq_xprt_ctxt;
 	struct svc_deferred_req *dr = rqstp->rq_deferred;
 
 	if (skb) {
-		rqstp->rq_skbuff = NULL;
+		rqstp->rq_xprt_ctxt = NULL;
 
 		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
 		skb_free_datagram(rqstp->rq_sock->sk_sk, skb);
@@ -395,7 +394,7 @@ svc_sock_release(struct svc_rqst *rqstp)
 {
 	struct svc_sock	*svsk = rqstp->rq_sock;
 
-	svc_release_skb(rqstp);
+	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
 
 	svc_free_res_pages(rqstp);
 	rqstp->rq_res.page_len = 0;
@@ -867,7 +866,7 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 			skb_free_datagram(svsk->sk_sk, skb);
 			return 0;
 		}
-		rqstp->rq_skbuff = skb;
+		rqstp->rq_xprt_ctxt = skb;
 	}
 
 	rqstp->rq_arg.page_base = 0;
@@ -903,6 +902,7 @@ svc_udp_sendto(struct svc_rqst *rqstp)
 static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
+	.xpo_release_rqst = svc_release_skb,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -1291,7 +1291,7 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
 	}
 
-	rqstp->rq_skbuff      = NULL;
+	rqstp->rq_xprt_ctxt   = NULL;
 	rqstp->rq_prot	      = IPPROTO_TCP;
 
 	/* Reset TCP read info */
@@ -1357,6 +1357,7 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
+	.xpo_release_rqst = svc_release_skb,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
@@ -1578,7 +1579,7 @@ svc_send(struct svc_rqst *rqstp)
 	}
 
 	/* release the receive skb before sending the reply */
-	svc_release_skb(rqstp);
+	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
 
 	/* calculate over-all length */
 	xb = & rqstp->rq_res;
author
#8 lore raw

PATCH 7/40 svc: Add per-transport delete functions

In reply to a message not in the archive

Add transport specific xpo_detach and xpo_free functions. The xpo_detach function causes the transport to stop delivering data-ready events and enqueing the transport for I/O.

The xpo_free function frees all resources associated with the particular transport instance.

---

 include/linux/sunrpc/svc_xprt.h |    2 +
 net/sunrpc/svcsock.c            |   56 ++++++++++++++++++++++++++++++---------
 2 files changed, 45 insertions(+), 13 deletions(-)
include/linux/sunrpc/svc_xprt.h +2 -0
index 01ee7bc..f032fb6 100644
@@ -13,6 +13,8 @@ struct svc_xprt_ops {
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
+	void		(*xpo_detach)(struct svc_xprt *);
+	void		(*xpo_free)(struct svc_xprt *);
 };
 
 struct svc_xprt_class {
net/sunrpc/svcsock.c +43 -13

92 lines not on this page · raw message

author
#9 lore raw

PATCH 8/40 svc: Add xpo_prep_reply_hdr

In reply to a message not in the archive

Some transports add fields to the RPC header for replies, e.g. the TCP record length. This function is called when preparing the reply header to allow each transport to add whatever fields it requires.

---

 include/linux/sunrpc/svc_xprt.h |    1 +
 net/sunrpc/svc.c                |    6 +++---
 net/sunrpc/svcsock.c            |   17 +++++++++++++++++
 3 files changed, 21 insertions(+), 3 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index f032fb6..199cfcb 100644
@@ -11,6 +11,7 @@
 
 struct svc_xprt_ops {
 	int		(*xpo_recvfrom)(struct svc_rqst *);
+	void		(*xpo_prep_reply_hdr)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);
net/sunrpc/svc.c +3 -3
index ea3fa86..3cc945d 100644
@@ -839,9 +839,9 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_len = 0;
 	/* Will be turned off only in gss privacy case: */
 	rqstp->rq_splice_ok = 1;
-	/* tcp needs a space for the record length... */
-	if (rqstp->rq_prot == IPPROTO_TCP)
-		svc_putnl(resv, 0);
+
+	/* Setup reply header */
+	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
 
 	rqstp->rq_xid = svc_getu32(argv);
 	svc_putu32(resv, rqstp->rq_xid);
net/sunrpc/svcsock.c +17 -0
index 44a729d..492a1dc 100644
@@ -893,12 +893,17 @@ svc_udp_sendto(struct svc_rqst *rqstp)
 	return error;
 }
 
+static void svc_udp_prep_reply_hdr(struct svc_rqst *rqstp)
+{
+}
+
 static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
 	.xpo_release_rqst = svc_release_skb,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
+	.xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -1350,12 +1355,24 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 	return sent;
 }
 
+/*
+ * Setup response header. TCP has a 4B record length field.
+ */
+static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+{
+	struct kvec *resv = &rqstp->rq_res.head[0];
+
+	/* tcp needs a space for the record length... */
+	svc_putnl(resv, 0);
+}
+
 static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
 	.xpo_release_rqst = svc_release_skb,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
+	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
author
#10 lore raw

PATCH 9/40 svc: Add a transport function that checks for write space

In reply to a message not in the archive

In order to avoid blocking a service thread, the receive side checks to see if there is sufficient write space to reply to the request. Each transport has a different mechanism for determining if there is enough write space to reply.

The code that checked for write space was coupled with code that checked for CLOSE and CONN. These checks have been broken out into separate statements to make the code easier to read.

---

 include/linux/sunrpc/svc_xprt.h |    1 
 net/sunrpc/svcsock.c            |   82 +++++++++++++++++++++++++++------------
 2 files changed, 57 insertions(+), 26 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index 199cfcb..85df97a 100644
@@ -10,6 +10,7 @@
 #include <linux/sunrpc/svc.h>
 
 struct svc_xprt_ops {
+	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	void		(*xpo_prep_reply_hdr)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
net/sunrpc/svcsock.c +56 -26

124 lines not on this page · raw message

author
#11 lore raw

PATCH 10/40 svc: Move close processing to a single place

In reply to a message not in the archive

Close handling was duplicated in the UDP and TCP recvfrom methods. This code has been moved to the transport independent svc_recv function.

---

 net/sunrpc/svcsock.c |   26 +++++++++++---------------
 1 files changed, 11 insertions(+), 15 deletions(-)
net/sunrpc/svcsock.c +11 -15
index 2007881..603db98 100644
@@ -776,11 +776,6 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 		return svc_deferred_recv(rqstp);
 	}
 
-	if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
-		svc_delete_socket(svsk);
-		return 0;
-	}
-
 	clear_bit(SK_DATA, &svsk->sk_flags);
 	skb = NULL;
 	err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
@@ -1181,11 +1176,6 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		return svc_deferred_recv(rqstp);
 	}
 
-	if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
-		svc_delete_socket(svsk);
-		return 0;
-	}
-
 	if (svsk->sk_sk->sk_state == TCP_LISTEN) {
 		svc_tcp_accept(svsk);
 		svc_sock_received(svsk);
@@ -1311,7 +1301,7 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
 	return len;
 
  err_delete:
-	svc_delete_socket(svsk);
+	set_bit(SK_CLOSE, &svsk->sk_flags);
 	return -EAGAIN;
 
  error:
@@ -1575,10 +1565,16 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 	}
 	spin_unlock_bh(&pool->sp_lock);
 
-	dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
-		 rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
-	len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
-	dprintk("svc: got len=%d\n", len);
+	len = 0;
+	if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
+		dprintk("svc_recv: found SK_CLOSE\n");
+		svc_delete_socket(svsk);
+	} else {
+		dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
+			rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
+		len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
+		dprintk("svc: got len=%d\n", len);
+	}
 
 	/* No data, incomplete (TCP) read, or accept() */
 	if (len == 0 || len == -EAGAIN) {
author
#12 lore raw

PATCH 11/40 svc: Add xpo_accept transport function

In reply to a message not in the archive

Previously, the accept logic looked into the socket state to determine whether to call accept or recv when data-ready was indicated on an endpoint. Since some transports don't use sockets, this logic now uses a flag bit (SK_LISTENER) to identify listening endpoints. A transport function (xpo_accept) allows each transport to define its own accept processing. A transport's initialization logic is reponsible for setting the SK_LISTENER bit. I didn't see any way to do this in transport independent logic since the passive side of a UDP connection doesn't listen and always recv's.

In the svc_recv function, if the SK_LISTENER bit is set, the transport xpo_accept function is called to handle accept processing.

Note that all functions are defined even if they don't make sense for a given transport. For example, accept doesn't mean anything for UDP. The function is defined anyway and bug checks if called. The UDP transport should never set the SK_LISTENER bit.

---

 include/linux/sunrpc/svc_xprt.h |    1 +
 include/linux/sunrpc/svcsock.h  |    1 +
 net/sunrpc/svcsock.c            |   31 +++++++++++++++++++------------
 3 files changed, 21 insertions(+), 12 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index 85df97a..31a44f4 100644
@@ -10,6 +10,7 @@
 #include <linux/sunrpc/svc.h>
 
 struct svc_xprt_ops {
+	struct svc_xprt	*(*xpo_accept)(struct svc_xprt *);
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	void		(*xpo_prep_reply_hdr)(struct svc_rqst *);
include/linux/sunrpc/svcsock.h +1 -0
index 08e78d0..9882ce0 100644
@@ -36,6 +36,7 @@ struct svc_sock {
 #define	SK_DEFERRED	8			/* request on sk_deferred */
 #define	SK_OLD		9			/* used for temp socket aging mark+sweep */
 #define	SK_DETACHED	10			/* detached from tempsocks list */
+#define SK_LISTENER	11			/* listening endpoint */
 
 	atomic_t    	    	sk_reserved;	/* space on outq that is reserved */
 
net/sunrpc/svcsock.c +19 -12
index 603db98..41d1f81 100644
@@ -896,6 +896,12 @@ static int svc_udp_has_wspace(struct svc_xprt *xprt)
 	return 1;
 }
 
+static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
+{
+	BUG();
+	return NULL;
+}
+
 static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
@@ -904,6 +910,7 @@ static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_free = svc_sock_free,
 	.xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
 	.xpo_has_wspace = svc_udp_has_wspace,
+	.xpo_accept = svc_udp_accept,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -1028,9 +1035,9 @@ static inline int svc_port_is_privileged(struct sockaddr *sin)
 /*
  * Accept a TCP connection
  */
-static void
-svc_tcp_accept(struct svc_sock *svsk)
+static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 {
+	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 	struct sockaddr_storage addr;
 	struct sockaddr	*sin = (struct sockaddr *) &addr;
 	struct svc_serv	*serv = svsk->sk_server;
@@ -1042,7 +1049,7 @@ svc_tcp_accept(struct svc_sock *svsk)
 
 	dprintk("svc: tcp_accept %p sock %p\n", svsk, sock);
 	if (!sock)
-		return;
+		return NULL;
 
 	clear_bit(SK_CONN, &svsk->sk_flags);
 	err = kernel_accept(sock, &newsock, O_NONBLOCK);
@@ -1053,7 +1060,7 @@ svc_tcp_accept(struct svc_sock *svsk)
 		else if (err != -EAGAIN && net_ratelimit())
 			printk(KERN_WARNING "%s: accept failed (err %d)!\n",
 				   serv->sv_name, -err);
-		return;
+		return NULL;
 	}
 
 	set_bit(SK_CONN, &svsk->sk_flags);
@@ -1147,11 +1154,11 @@ svc_tcp_accept(struct svc_sock *svsk)
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpconn++;
 
-	return;
+	return &newsvsk->sk_xprt;
 
 failed:
 	sock_release(newsock);
-	return;
+	return NULL;
 }
 
 /*
@@ -1176,12 +1183,6 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		return svc_deferred_recv(rqstp);
 	}
 
-	if (svsk->sk_sk->sk_state == TCP_LISTEN) {
-		svc_tcp_accept(svsk);
-		svc_sock_received(svsk);
-		return 0;
-	}
-
 	if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
 		/* sndbuf needs to have room for one request
 		 * per thread, otherwise we can stall even when the
@@ -1393,6 +1394,7 @@ static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_free = svc_sock_free,
 	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
 	.xpo_has_wspace = svc_tcp_has_wspace,
+	.xpo_accept = svc_tcp_accept,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
@@ -1423,6 +1425,7 @@ svc_tcp_init(struct svc_sock *svsk)
 
 	if (sk->sk_state == TCP_LISTEN) {
 		dprintk("setting up TCP socket for listening\n");
+		set_bit(SK_LISTENER, &svsk->sk_flags);
 		sk->sk_data_ready = svc_tcp_listen_data_ready;
 		set_bit(SK_CONN, &svsk->sk_flags);
 	} else {
@@ -1569,6 +1572,10 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 	if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
 		dprintk("svc_recv: found SK_CLOSE\n");
 		svc_delete_socket(svsk);
+	} else if (test_bit(SK_LISTENER, &svsk->sk_flags)) {
+		struct svc_xprt *newxpt;
+		newxpt = svsk->sk_xprt.xpt_ops->xpo_accept(&svsk->sk_xprt);
+		svc_sock_received(svsk);
 	} else {
 		dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
 			rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
author
#13 lore raw

PATCH 12/40 svc: Remove unnecessary call to svc_sock_enqueue

In reply to a message not in the archive

The svc_tcp_accept function calls svc_sock_enqueue after setting the SK_CONN bit. This doesn't actually do anything because the SK_BUSY bit is still set. The call is unnecessary anyway because the generic code in svc_recv calls svc_sock_received after calling the accept function.

---

 net/sunrpc/svcsock.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)
net/sunrpc/svcsock.c +0 -1
index 41d1f81..962dbf4 100644
@@ -1064,7 +1064,6 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	}
 
 	set_bit(SK_CONN, &svsk->sk_flags);
-	svc_sock_enqueue(svsk);
 
 	err = kernel_getpeername(newsock, sin, &slen);
 	if (err < 0) {
author
#14 lore raw

PATCH 13/40 svc: Move connection limit checking to its own function

In reply to a message not in the archive

Move the code that poaches connections when the connection limit is hit to a subroutine to make the accept logic path easier to follow. Since this is in the new connection path, it should not be a performance issue.

---

 net/sunrpc/svcsock.c |   57 +++++++++++++++++++++++++-------------------------
 1 files changed, 29 insertions(+), 28 deletions(-)
net/sunrpc/svcsock.c +29 -28
index 962dbf4..6e9dc8f 100644
@@ -1105,17 +1105,30 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 
 	svc_sock_received(newsvsk);
 
-	/* make sure that we don't have too many active connections.
-	 * If we have, something must be dropped.
-	 *
-	 * There's no point in trying to do random drop here for
-	 * DoS prevention. The NFS clients does 1 reconnect in 15
-	 * seconds. An attacker can easily beat that.
-	 *
-	 * The only somewhat efficient mechanism would be if drop
-	 * old connections from the same IP first. But right now
-	 * we don't even record the client IP in svc_sock.
-	 */
+	if (serv->sv_stats)
+		serv->sv_stats->nettcpconn++;
+
+	return &newsvsk->sk_xprt;
+
+failed:
+	sock_release(newsock);
+	return NULL;
+}
+
+/*
+ * Make sure that we don't have too many active connections.  If we
+ * have, something must be dropped.
+ *
+ * There's no point in trying to do random drop here for DoS
+ * prevention. The NFS clients does 1 reconnect in 15 seconds. An
+ * attacker can easily beat that.
+ *
+ * The only somewhat efficient mechanism would be if drop old
+ * connections from the same IP first. But right now we don't even
+ * record the client IP in svc_sock.
+ */
+static void svc_check_conn_limits(struct svc_serv *serv)
+{
 	if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
 		struct svc_sock *svsk = NULL;
 		spin_lock_bh(&serv->sv_lock);
@@ -1123,13 +1136,9 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 			if (net_ratelimit()) {
 				/* Try to help the admin */
 				printk(KERN_NOTICE "%s: too many open TCP "
-					"sockets, consider increasing the "
-					"number of nfsd threads\n",
-						   serv->sv_name);
-				printk(KERN_NOTICE
-				       "%s: last TCP connect from %s\n",
-				       serv->sv_name, __svc_print_addr(sin,
-							buf, sizeof(buf)));
+				       "sockets, consider increasing the "
+				       "number of nfsd threads\n",
+				       serv->sv_name);
 			}
 			/*
 			 * Always select the oldest socket. It's not fair,
@@ -1147,17 +1156,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 			svc_sock_enqueue(svsk);
 			svc_sock_put(svsk);
 		}
-
 	}
-
-	if (serv->sv_stats)
-		serv->sv_stats->nettcpconn++;
-
-	return &newsvsk->sk_xprt;
-
-failed:
-	sock_release(newsock);
-	return NULL;
 }
 
 /*
@@ -1574,6 +1573,8 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 	} else if (test_bit(SK_LISTENER, &svsk->sk_flags)) {
 		struct svc_xprt *newxpt;
 		newxpt = svsk->sk_xprt.xpt_ops->xpo_accept(&svsk->sk_xprt);
+		if (newxpt)
+			svc_check_conn_limits(svsk->sk_server);
 		svc_sock_received(svsk);
 	} else {
 		dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
author
#15 lore raw

PATCH 14/40 svc: Add a generic transport svc_create_xprt function

In reply to a message not in the archive

The svc_create_xprt function is a transport independent version of the svc_makesock function.

Since transport instance creation contains transport dependent and independent components, add an xpo_create transport function. The transport implementation of this function allocates the memory for the endpoint, implements the transport dependent initialization logic, and calls svc_xprt_init to initialize the transport independent field (svc_xprt) in it's data structure.

---

 include/linux/sunrpc/svc_xprt.h |    4 +++
 net/sunrpc/svc_xprt.c           |   37 ++++++++++++++++++++++++
 net/sunrpc/svcsock.c            |   59 +++++++++++++++++++++++++++++----------
 3 files changed, 85 insertions(+), 15 deletions(-)
include/linux/sunrpc/svc_xprt.h +4 -0
index 31a44f4..986a5a0 100644
@@ -10,6 +10,9 @@
 #include <linux/sunrpc/svc.h>
 
 struct svc_xprt_ops {
+	struct svc_xprt	*(*xpo_create)(struct svc_serv *,
+				       struct sockaddr *, int,
+				       int);
 	struct svc_xprt	*(*xpo_accept)(struct svc_xprt *);
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
@@ -36,5 +39,6 @@ struct svc_xprt {
 int	svc_reg_xprt_class(struct svc_xprt_class *);
 void	svc_unreg_xprt_class(struct svc_xprt_class *);
 void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *);
+int	svc_create_xprt(struct svc_serv *, char *, unsigned short, int);
 
 #endif /* SUNRPC_SVC_XPRT_H */
net/sunrpc/svc_xprt.c +37 -0
index fe5270f..6ff5ca7 100644
@@ -81,3 +81,40 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt)
 	xprt->xpt_ops = xcl->xcl_ops;
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
+
+int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
+		    int flags)
+{
+	struct svc_xprt_class *xcl;
+	int ret = -ENOENT;
+	struct sockaddr_in sin = {
+		.sin_family		= AF_INET,
+		.sin_addr.s_addr	= INADDR_ANY,
+		.sin_port		= htons(port),
+	};
+	dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
+	spin_lock(&svc_xprt_class_lock);
+	list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
+		if (strcmp(xprt_name, xcl->xcl_name) == 0) {
+			spin_unlock(&svc_xprt_class_lock);
+			if (try_module_get(xcl->xcl_owner)) {
+				struct svc_xprt *newxprt;
+				ret = 0;
+				newxprt = xcl->xcl_ops->xpo_create
+					(serv,
+					 (struct sockaddr *)&sin, sizeof(sin),
+					 flags);
+				if (IS_ERR(newxprt)) {
+					module_put(xcl->xcl_owner);
+					ret = PTR_ERR(newxprt);
+				}
+			}
+			goto out;
+		}
+	}
+	spin_unlock(&svc_xprt_class_lock);
+	dprintk("svc: transport %s not found\n", xprt_name);
+ out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(svc_create_xprt);
net/sunrpc/svcsock.c +44 -15

139 lines not on this page · raw message

author
#16 lore raw

PATCH 15/40 svc: Change services to use new svc_create_xprt service

In reply to a message not in the archive

Modify the various kernel RPC svcs to use the svc_create_xprt service.

---

 fs/lockd/svc.c                 |   17 ++++++++---------
 fs/nfs/callback.c              |    4 ++--
 fs/nfsd/nfssvc.c               |    4 ++--
 include/linux/sunrpc/svcsock.h |    1 -
 net/sunrpc/sunrpc_syms.c       |    1 -
 net/sunrpc/svcsock.c           |   22 ----------------------
 6 files changed, 12 insertions(+), 37 deletions(-)
fs/lockd/svc.c +8 -9
index 82e2192..8686915 100644
@@ -219,13 +219,12 @@ lockd(struct svc_rqst *rqstp)
 	module_put_and_exit(0);
 }
 
-
-static int find_socket(struct svc_serv *serv, int proto)
+static int find_xprt(struct svc_serv *serv, char *proto)
 {
 	struct svc_sock *svsk;
 	int found = 0;
 	list_for_each_entry(svsk, &serv->sv_permsocks, sk_list)
-		if (svsk->sk_sk->sk_protocol == proto) {
+		if (strcmp(svsk->sk_xprt.xpt_class->xcl_name, proto) == 0) {
 			found = 1;
 			break;
 		}
@@ -243,13 +242,13 @@ static int make_socks(struct svc_serv *serv, int proto)
 	int err = 0;
 
 	if (proto == IPPROTO_UDP || nlm_udpport)
-		if (!find_socket(serv, IPPROTO_UDP))
-			err = svc_makesock(serv, IPPROTO_UDP, nlm_udpport,
-						SVC_SOCK_DEFAULTS);
+		if (!find_xprt(serv, "udp"))
+			err = svc_create_xprt(serv, "udp", nlm_udpport,
+					      SVC_SOCK_DEFAULTS);
 	if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport))
-		if (!find_socket(serv, IPPROTO_TCP))
-			err = svc_makesock(serv, IPPROTO_TCP, nlm_tcpport,
-						SVC_SOCK_DEFAULTS);
+		if (!find_xprt(serv, "tcp"))
+			err = svc_create_xprt(serv, "tcp", nlm_tcpport,
+					      SVC_SOCK_DEFAULTS);
 
 	if (err >= 0) {
 		warned = 0;
fs/nfs/callback.c +2 -2
index a796be5..e27ca14 100644
@@ -123,8 +123,8 @@ int nfs_callback_up(void)
 	if (!serv)
 		goto out_err;
 
-	ret = svc_makesock(serv, IPPROTO_TCP, nfs_callback_set_tcpport,
-							SVC_SOCK_ANONYMOUS);
+	ret = svc_create_xprt(serv, "tcp", nfs_callback_set_tcpport,
+			      SVC_SOCK_ANONYMOUS);
 	if (ret <= 0)
 		goto out_destroy;
 	nfs_callback_tcpport = ret;
fs/nfsd/nfssvc.c +2 -2
index 1190aea..a828b0b 100644
@@ -236,7 +236,7 @@ static int nfsd_init_socks(int port)
 
 	error = lockd_up(IPPROTO_UDP);
 	if (error >= 0) {
-		error = svc_makesock(nfsd_serv, IPPROTO_UDP, port,
+		error = svc_create_xprt(nfsd_serv, "udp", port,
 					SVC_SOCK_DEFAULTS);
 		if (error < 0)
 			lockd_down();
@@ -247,7 +247,7 @@ static int nfsd_init_socks(int port)
 #ifdef CONFIG_NFSD_TCP
 	error = lockd_up(IPPROTO_TCP);
 	if (error >= 0) {
-		error = svc_makesock(nfsd_serv, IPPROTO_TCP, port,
+		error = svc_create_xprt(nfsd_serv, "tcp", port,
 					SVC_SOCK_DEFAULTS);
 		if (error < 0)
 			lockd_down();
include/linux/sunrpc/svcsock.h +0 -1
index 9882ce0..3181d9d 100644
@@ -67,7 +67,6 @@ struct svc_sock {
 /*
  * Function prototypes.
  */
-int		svc_makesock(struct svc_serv *, int, unsigned short, int flags);
 void		svc_force_close_socket(struct svc_sock *);
 int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
net/sunrpc/sunrpc_syms.c +0 -1
index 79ea05f..52eea54 100644
@@ -72,7 +72,6 @@ EXPORT_SYMBOL(svc_drop);
 EXPORT_SYMBOL(svc_process);
 EXPORT_SYMBOL(svc_recv);
 EXPORT_SYMBOL(svc_wake_up);
-EXPORT_SYMBOL(svc_makesock);
 EXPORT_SYMBOL(svc_reserve);
 EXPORT_SYMBOL(svc_auth_register);
 EXPORT_SYMBOL(auth_domain_lookup);
net/sunrpc/svcsock.c +0 -22
index 9f0f6d0..e6bb1b0 100644
@@ -1988,28 +1988,6 @@ void svc_force_close_socket(struct svc_sock *svsk)
 	svc_close_socket(svsk);
 }
 
-/**
- * svc_makesock - Make a socket for nfsd and lockd
- * @serv: RPC server structure
- * @protocol: transport protocol to use
- * @port: port to use
- * @flags: requested socket characteristics
- *
- */
-int svc_makesock(struct svc_serv *serv, int protocol, unsigned short port,
-			int flags)
-{
-	dprintk("svc: creating socket proto = %d\n", protocol);
-	switch (protocol) {
-	case IPPROTO_TCP:
-		return svc_create_xprt(serv, "tcp", port, flags);
-	case IPPROTO_UDP:
-		return svc_create_xprt(serv, "udp", port, flags);
-	default:
-		return -EINVAL;
-	}
-}
-
 /*
  * Handle defer and revisit of requests
  */
author
#17 lore raw

PATCH 16/40 svc: Change sk_inuse to a kref

In reply to a message not in the archive

Change the atomic_t reference count to a kref and move it to the transport indepenent svc_xprt structure. Change the reference count wrapper names to be generic.

---

 include/linux/sunrpc/svc_xprt.h |    8 ++
 include/linux/sunrpc/svcsock.h  |    1 
 net/sunrpc/svc_xprt.c           |   16 +++++
 net/sunrpc/svcsock.c            |  138 ++++++++++++++++++---------------------
 4 files changed, 87 insertions(+), 76 deletions(-)
include/linux/sunrpc/svc_xprt.h +8 -0
index 986a5a0..6374805 100644
@@ -8,6 +8,7 @@
 #define SUNRPC_SVC_XPRT_H
 
 #include <linux/sunrpc/svc.h>
+#include <linux/module.h>
 
 struct svc_xprt_ops {
 	struct svc_xprt	*(*xpo_create)(struct svc_serv *,
@@ -34,11 +35,18 @@ struct svc_xprt_class {
 struct svc_xprt {
 	struct svc_xprt_class	*xpt_class;
 	struct svc_xprt_ops	*xpt_ops;
+	struct kref		xpt_ref;
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
 void	svc_unreg_xprt_class(struct svc_xprt_class *);
 void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *);
 int	svc_create_xprt(struct svc_serv *, char *, unsigned short, int);
+void	svc_xprt_put(struct svc_xprt *xprt);
+
+static inline void svc_xprt_get(struct svc_xprt *xprt)
+{
+	kref_get(&xprt->xpt_ref);
+}
 
 #endif /* SUNRPC_SVC_XPRT_H */
include/linux/sunrpc/svcsock.h +0 -1
index 3181d9d..ba07d50 100644
@@ -24,7 +24,6 @@ struct svc_sock {
 
 	struct svc_pool *	sk_pool;	/* current pool iff queued */
 	struct svc_serv *	sk_server;	/* service for this socket */
-	atomic_t		sk_inuse;	/* use count */
 	unsigned long		sk_flags;
 #define	SK_BUSY		0			/* enqueued/receiving */
 #define	SK_CONN		1			/* conn pending */
net/sunrpc/svc_xprt.c +16 -0
index 6ff5ca7..31853bf 100644
@@ -70,6 +70,21 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
 }
 EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
 
+static void svc_xprt_free(struct kref *kref)
+{
+	struct svc_xprt *xprt =
+		container_of(kref, struct svc_xprt, xpt_ref);
+	struct module *owner = xprt->xpt_class->xcl_owner;
+	xprt->xpt_ops->xpo_free(xprt);
+	module_put(owner);
+}
+
+void svc_xprt_put(struct svc_xprt *xprt)
+{
+	kref_put(&xprt->xpt_ref, svc_xprt_free);
+}
+EXPORT_SYMBOL_GPL(svc_xprt_put);
+
 /*
  * Called by transport drivers to initialize the transport independent
  * portion of the transport instance.
@@ -79,6 +94,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt)
 	memset(xprt, 0, sizeof(*xprt));
 	xprt->xpt_class = xcl;
 	xprt->xpt_ops = xcl->xcl_ops;
+	kref_init(&xprt->xpt_ref);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
net/sunrpc/svcsock.c +63 -75

245 lines not on this page · raw message

author
#18 lore raw

PATCH 17/40 svc: Move sk_flags to the svc_xprt structure

In reply to a message not in the archive

This functionally trivial change moves the transport independent sk_flags field to the transport independent svc_xprt structure.

---

 include/linux/sunrpc/svc_xprt.h |   12 +++
 include/linux/sunrpc/svcsock.h  |   13 ---
 net/sunrpc/svcsock.c            |  151 ++++++++++++++++++++-------------------
 3 files changed, 88 insertions(+), 88 deletions(-)
include/linux/sunrpc/svc_xprt.h +12 -0
index 6374805..2edeb0d 100644
@@ -36,6 +36,18 @@ struct svc_xprt {
 	struct svc_xprt_class	*xpt_class;
 	struct svc_xprt_ops	*xpt_ops;
 	struct kref		xpt_ref;
+	unsigned long		xpt_flags;
+#define	XPT_BUSY	0		/* enqueued/receiving */
+#define	XPT_CONN	1		/* conn pending */
+#define	XPT_CLOSE	2		/* dead or dying */
+#define	XPT_DATA	3		/* data pending */
+#define	XPT_TEMP	4		/* connected transport */
+#define	XPT_DEAD	6		/* transport closed */
+#define	XPT_CHNGBUF	7		/* need to change snd/rcv buf sizes */
+#define	XPT_DEFERRED	8		/* deferred request pending */
+#define	XPT_OLD		9		/* used for xprt aging mark+sweep */
+#define	XPT_DETACHED	10		/* detached from tempsocks list */
+#define XPT_LISTENER	11		/* listening endpoint */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
include/linux/sunrpc/svcsock.h +0 -13
index ba07d50..b8a8496 100644
@@ -24,19 +24,6 @@ struct svc_sock {
 
 	struct svc_pool *	sk_pool;	/* current pool iff queued */
 	struct svc_serv *	sk_server;	/* service for this socket */
-	unsigned long		sk_flags;
-#define	SK_BUSY		0			/* enqueued/receiving */
-#define	SK_CONN		1			/* conn pending */
-#define	SK_CLOSE	2			/* dead or dying */
-#define	SK_DATA		3			/* data pending */
-#define	SK_TEMP		4			/* temp (TCP) socket */
-#define	SK_DEAD		6			/* socket closed */
-#define	SK_CHNGBUF	7			/* need to change snd/rcv buffer sizes */
-#define	SK_DEFERRED	8			/* request on sk_deferred */
-#define	SK_OLD		9			/* used for temp socket aging mark+sweep */
-#define	SK_DETACHED	10			/* detached from tempsocks list */
-#define SK_LISTENER	11			/* listening endpoint */
-
 	atomic_t    	    	sk_reserved;	/* space on outq that is reserved */
 
 	spinlock_t		sk_lock;	/* protects sk_deferred and
net/sunrpc/svcsock.c +76 -75

464 lines not on this page · raw message

author
#19 lore raw

PATCH 18/40 svc: Move sk_server and sk_pool to svc_xprt

In reply to a message not in the archive

This is another incremental change that moves transport independent fields from svc_sock to the svc_xprt structure. The changes should be functionally null.

---

 include/linux/sunrpc/svc_xprt.h |    6 +++-
 include/linux/sunrpc/svcsock.h  |    2 -
 net/sunrpc/svc_xprt.c           |    4 ++-
 net/sunrpc/svcsock.c            |   57 ++++++++++++++++++---------------------
 4 files changed, 35 insertions(+), 34 deletions(-)
include/linux/sunrpc/svc_xprt.h +5 -1
index 2edeb0d..4042cdf 100644
@@ -48,11 +48,15 @@ struct svc_xprt {
 #define	XPT_OLD		9		/* used for xprt aging mark+sweep */
 #define	XPT_DETACHED	10		/* detached from tempsocks list */
 #define XPT_LISTENER	11		/* listening endpoint */
+
+	struct svc_pool		*xpt_pool;	/* current pool iff queued */
+	struct svc_serv		*xpt_server;	/* service for transport */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
 void	svc_unreg_xprt_class(struct svc_xprt_class *);
-void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *);
+void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *,
+		      struct svc_serv *);
 int	svc_create_xprt(struct svc_serv *, char *, unsigned short, int);
 void	svc_xprt_put(struct svc_xprt *xprt);
 
include/linux/sunrpc/svcsock.h +0 -2
index b8a8496..92d4cc9 100644
@@ -22,8 +22,6 @@ struct svc_sock {
 	struct socket *		sk_sock;	/* berkeley socket layer */
 	struct sock *		sk_sk;		/* INET layer */
 
-	struct svc_pool *	sk_pool;	/* current pool iff queued */
-	struct svc_serv *	sk_server;	/* service for this socket */
 	atomic_t    	    	sk_reserved;	/* space on outq that is reserved */
 
 	spinlock_t		sk_lock;	/* protects sk_deferred and
net/sunrpc/svc_xprt.c +3 -1
index 31853bf..ea17b53 100644
@@ -89,12 +89,14 @@ EXPORT_SYMBOL_GPL(svc_xprt_put);
  * Called by transport drivers to initialize the transport independent
  * portion of the transport instance.
  */
-void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt)
+void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
+		   struct svc_serv *serv)
 {
 	memset(xprt, 0, sizeof(*xprt));
 	xprt->xpt_class = xcl;
 	xprt->xpt_ops = xcl->xcl_ops;
 	kref_init(&xprt->xpt_ref);
+	xprt->xpt_server = serv;
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
net/sunrpc/svcsock.c +27 -30

196 lines not on this page · raw message

author
#20 lore raw

PATCH 19/40 svc: Make close transport independent

In reply to a message not in the archive

Move sk_list and sk_ready to svc_xprt. This involves close because these lists are walked by svcs when closing all their transports. So I combined the moving of these lists to svc_xprt with making close transport independent.

The svc_force_sock_close has been changed to svc_close_all and takes a list as an argument. This removes some svc internals knowledge from the svcs.

This code races with module removal and transport addition.

---

 fs/lockd/svc.c                  |    6 +-
 fs/nfsd/nfssvc.c                |    4 +-
 include/linux/sunrpc/svc_xprt.h |    2 +
 include/linux/sunrpc/svcsock.h  |    4 --
 net/sunrpc/svc.c                |    9 +--
 net/sunrpc/svc_xprt.c           |    2 +
 net/sunrpc/svcsock.c            |  102 +++++++++++++++++++--------------------
 7 files changed, 61 insertions(+), 68 deletions(-)
fs/lockd/svc.c +3 -3
index 8686915..a8e79a9 100644
@@ -221,10 +221,10 @@ lockd(struct svc_rqst *rqstp)
 
 static int find_xprt(struct svc_serv *serv, char *proto)
 {
-	struct svc_sock *svsk;
+	struct svc_xprt *xprt;
 	int found = 0;
-	list_for_each_entry(svsk, &serv->sv_permsocks, sk_list)
-		if (strcmp(svsk->sk_xprt.xpt_class->xcl_name, proto) == 0) {
+	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list)
+		if (strcmp(xprt->xpt_class->xcl_name, proto) == 0) {
 			found = 1;
 			break;
 		}
fs/nfsd/nfssvc.c +2 -2
index a828b0b..9647b0f 100644
@@ -155,8 +155,8 @@ static int killsig;	/* signal that was used to kill last nfsd */
 static void nfsd_last_thread(struct svc_serv *serv)
 {
 	/* When last nfsd thread exits we need to do some clean-up */
-	struct svc_sock *svsk;
-	list_for_each_entry(svsk, &serv->sv_permsocks, sk_list)
+	struct svc_xprt *xprt;
+	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list)
 		lockd_down();
 	nfsd_serv = NULL;
 	nfsd_racache_shutdown();
include/linux/sunrpc/svc_xprt.h +2 -0
index 4042cdf..0a3e09b 100644
@@ -36,6 +36,8 @@ struct svc_xprt {
 	struct svc_xprt_class	*xpt_class;
 	struct svc_xprt_ops	*xpt_ops;
 	struct kref		xpt_ref;
+	struct list_head	xpt_list;
+	struct list_head	xpt_ready;
 	unsigned long		xpt_flags;
 #define	XPT_BUSY	0		/* enqueued/receiving */
 #define	XPT_CONN	1		/* conn pending */
include/linux/sunrpc/svcsock.h +1 -3
index 92d4cc9..060508b 100644
@@ -17,8 +17,6 @@
  */
 struct svc_sock {
 	struct svc_xprt		sk_xprt;
-	struct list_head	sk_ready;	/* list of ready sockets */
-	struct list_head	sk_list;	/* list of all sockets */
 	struct socket *		sk_sock;	/* berkeley socket layer */
 	struct sock *		sk_sk;		/* INET layer */
 
@@ -51,7 +49,7 @@ struct svc_sock {
 /*
  * Function prototypes.
  */
-void		svc_force_close_socket(struct svc_sock *);
+void		svc_close_all(struct list_head *);
 int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);
net/sunrpc/svc.c +2 -7
index 3cc945d..be18734 100644
@@ -458,9 +458,6 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
 void
 svc_destroy(struct svc_serv *serv)
 {
-	struct svc_sock	*svsk;
-	struct svc_sock *tmp;
-
 	dprintk("svc: svc_destroy(%s, %d)\n",
 				serv->sv_program->pg_name,
 				serv->sv_nrthreads);
@@ -475,14 +472,12 @@ svc_destroy(struct svc_serv *serv)
 
 	del_timer_sync(&serv->sv_temptimer);
 
-	list_for_each_entry_safe(svsk, tmp, &serv->sv_tempsocks, sk_list)
-		svc_force_close_socket(svsk);
+	svc_close_all(&serv->sv_tempsocks);
 
 	if (serv->sv_shutdown)
 		serv->sv_shutdown(serv);
 
-	list_for_each_entry_safe(svsk, tmp, &serv->sv_permsocks, sk_list)
-		svc_force_close_socket(svsk);
+	svc_close_all(&serv->sv_permsocks);
 
 	BUG_ON(!list_empty(&serv->sv_permsocks));
 	BUG_ON(!list_empty(&serv->sv_tempsocks));
net/sunrpc/svc_xprt.c +2 -0
index ea17b53..95186b5 100644
@@ -97,6 +97,8 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	xprt->xpt_ops = xcl->xcl_ops;
 	kref_init(&xprt->xpt_ref);
 	xprt->xpt_server = serv;
+	INIT_LIST_HEAD(&xprt->xpt_list);
+	INIT_LIST_HEAD(&xprt->xpt_ready);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
net/sunrpc/svcsock.c +49 -53

218 lines not on this page · raw message

author
#21 lore raw

PATCH 20/40 svc: Move sk_reserved to svc_xprt

In reply to a message not in the archive

This functionally trivial patch moves the sk_reserved field to the transport independent svc_xprt structure.

---

 include/linux/sunrpc/svc_xprt.h |    1 +
 include/linux/sunrpc/svcsock.h  |    2 --
 net/sunrpc/svcsock.c            |   10 +++++-----
 3 files changed, 6 insertions(+), 7 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index 0a3e09b..0b8ee06 100644
@@ -53,6 +53,7 @@ struct svc_xprt {
 
 	struct svc_pool		*xpt_pool;	/* current pool iff queued */
 	struct svc_serv		*xpt_server;	/* service for transport */
+	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
include/linux/sunrpc/svcsock.h +0 -2
index 060508b..ba41f11 100644
@@ -20,8 +20,6 @@ struct svc_sock {
 	struct socket *		sk_sock;	/* berkeley socket layer */
 	struct sock *		sk_sk;		/* INET layer */
 
-	atomic_t    	    	sk_reserved;	/* space on outq that is reserved */
-
 	spinlock_t		sk_lock;	/* protects sk_deferred and
 						 * sk_info_authunix */
 	struct list_head	sk_deferred;	/* deferred requests that need to
net/sunrpc/svcsock.c +5 -5
index 6dffdda..ec5ad81 100644
@@ -288,7 +288,7 @@ svc_sock_enqueue(struct svc_sock *svsk)
 		rqstp->rq_sock = svsk;
 		svc_xprt_get(&svsk->sk_xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
-		atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
+		atomic_add(rqstp->rq_reserved, &svsk->sk_xprt.xpt_reserved);
 		BUG_ON(svsk->sk_xprt.xpt_pool != pool);
 		wake_up(&rqstp->rq_wait);
 	} else {
@@ -353,7 +353,7 @@ void svc_reserve(struct svc_rqst *rqstp, int space)
 
 	if (space < rqstp->rq_reserved) {
 		struct svc_sock *svsk = rqstp->rq_sock;
-		atomic_sub((rqstp->rq_reserved - space), &svsk->sk_reserved);
+		atomic_sub((rqstp->rq_reserved - space), &svsk->sk_xprt.xpt_reserved);
 		rqstp->rq_reserved = space;
 
 		svc_sock_enqueue(svsk);
@@ -881,7 +881,7 @@ static int svc_udp_has_wspace(struct svc_xprt *xprt)
 	 * sock space.
 	 */
 	set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
-	required = atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg;
+	required = atomic_read(&svsk->sk_xprt.xpt_reserved) + serv->sv_max_mesg;
 	if (required*2 > sock_wspace(svsk->sk_sk))
 		return 0;
 	clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
@@ -1327,7 +1327,7 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)
 	 * sock space.
 	 */
 	set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
-	required = atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg;
+	required = atomic_read(&svsk->sk_xprt.xpt_reserved) + serv->sv_max_mesg;
 	wspace = sk_stream_wspace(svsk->sk_sk);
 
 	if (wspace < sk_stream_min_wspace(svsk->sk_sk))
@@ -1544,7 +1544,7 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 		rqstp->rq_sock = svsk;
 		svc_xprt_get(&svsk->sk_xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
-		atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
+		atomic_add(rqstp->rq_reserved, &svsk->sk_xprt.xpt_reserved);
 	} else {
 		/* No data pending. Go to sleep */
 		svc_thread_enqueue(pool, rqstp);
author
#22 lore raw

PATCH 21/40 svc: Make the enqueue service transport neutral and export it.

In reply to a message not in the archive

The svc_sock_enqueue function is now transport independent since all of the fields it touches have been moved to the transport independent svc_xprt structure. Change the function to use the svc_xprt structure directly instead of the transport specific svc_sock structure.

Transport specific data-ready handlers need to call this function, so export it.

---

 net/sunrpc/svcsock.c |   94 ++++++++++++++++++++++++++------------------------
 1 files changed, 48 insertions(+), 46 deletions(-)
net/sunrpc/svcsock.c +48 -46
index ec5ad81..f356c02 100644
@@ -5,7 +5,7 @@
  *
  * The server scheduling algorithm does not always distribute the load
  * evenly when servicing a single client. May need to modify the
- * svc_sock_enqueue procedure...
+ * svc_xprt_enqueue procedure...
  *
  * TCP support is largely untested and may be a little slow. The problem
  * is that we currently do two separate recvfrom's, one for the 4-byte
@@ -63,7 +63,7 @@
  *	providing that certain rules are followed:
  *
  *	XPT_CONN, XPT_DATA, can be set or cleared at any time.
- *		after a set, svc_sock_enqueue must be called.
+ *		after a set, svc_xprt_enqueue must be called.
  *		after a clear, the socket must be read/accepted
  *		 if this succeeds, it must be set again.
  *	XPT_CLOSE can set at any time. It is never cleared.
@@ -212,22 +212,21 @@ static void svc_release_skb(struct svc_rqst *rqstp)
  * processes, wake 'em up.
  *
  */
-static void
-svc_sock_enqueue(struct svc_sock *svsk)
+void svc_xprt_enqueue(struct svc_xprt *xprt)
 {
-	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
+	struct svc_serv	*serv = xprt->xpt_server;
 	struct svc_pool *pool;
 	struct svc_rqst	*rqstp;
 	int cpu;
 
-	if (!(svsk->sk_xprt.xpt_flags &
+	if (!(xprt->xpt_flags &
 	      ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
 		return;
-	if (test_bit(XPT_DEAD, &svsk->sk_xprt.xpt_flags))
+	if (test_bit(XPT_DEAD, &xprt->xpt_flags))
 		return;
 
 	cpu = get_cpu();
-	pool = svc_pool_for_cpu(svsk->sk_xprt.xpt_server, cpu);
+	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
 	put_cpu();
 
 	spin_lock_bh(&pool->sp_lock);
@@ -235,11 +234,12 @@ svc_sock_enqueue(struct svc_sock *svsk)
 	if (!list_empty(&pool->sp_threads) &&
 	    !list_empty(&pool->sp_sockets))
 		printk(KERN_ERR
-			"svc_sock_enqueue: threads and sockets both waiting??\n");
+		       "svc_xprt_enqueue: "
+		       "threads and transports both waiting??\n");
 
-	if (test_bit(XPT_DEAD, &svsk->sk_xprt.xpt_flags)) {
+	if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
 		/* Don't enqueue dead sockets */
-		dprintk("svc: socket %p is dead, not enqueued\n", svsk->sk_sk);
+		dprintk("svc: transport %p is dead, not enqueued\n", xprt);
 		goto out_unlock;
 	}
 
@@ -248,28 +248,29 @@ svc_sock_enqueue(struct svc_sock *svsk)
 	 * on the idle list.  We update XPT_BUSY atomically because
 	 * it also guards against trying to enqueue the svc_sock twice.
 	 */
-	if (test_and_set_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)) {
+	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
 		/* Don't enqueue socket while already enqueued */
-		dprintk("svc: socket %p busy, not enqueued\n", svsk->sk_sk);
+		dprintk("svc: transport %p busy, not enqueued\n", xprt);
 		goto out_unlock;
 	}
-	BUG_ON(svsk->sk_xprt.xpt_pool != NULL);
-	svsk->sk_xprt.xpt_pool = pool;
+	BUG_ON(xprt->xpt_pool != NULL);
+	xprt->xpt_pool = pool;
 
 	/* Handle pending connection */
-	if (test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags))
+	if (test_bit(XPT_CONN, &xprt->xpt_flags))
 		goto process;
 
 	/* Handle close in-progress */
-	if (test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags))
+	if (test_bit(XPT_CLOSE, &xprt->xpt_flags))
 		goto process;
 
 	/* Check if we have space to reply to a request */
-	if (!svsk->sk_xprt.xpt_ops->xpo_has_wspace(&svsk->sk_xprt)) {
+	if (!xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		/* Don't enqueue while not enough space for reply */
-		dprintk("svc: no write space, socket %p  not enqueued\n", svsk);
-		svsk->sk_xprt.xpt_pool = NULL;
-		clear_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags);
+		dprintk("svc: no write space, transport %p  not enqueued\n",
+			xprt);
+		xprt->xpt_pool = NULL;
+		clear_bit(XPT_BUSY, &xprt->xpt_flags);
 		goto out_unlock;
 	}
 
@@ -278,28 +279,29 @@ svc_sock_enqueue(struct svc_sock *svsk)
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
 				   rq_list);
-		dprintk("svc: socket %p served by daemon %p\n",
-			svsk->sk_sk, rqstp);
+		dprintk("svc: transport %p served by daemon %p\n",
+			xprt, rqstp);
 		svc_thread_dequeue(pool, rqstp);
-		if (rqstp->rq_sock)
+		if (rqstp->rq_xprt)
 			printk(KERN_ERR
-				"svc_sock_enqueue: server %p, rq_sock=%p!\n",
-				rqstp, rqstp->rq_sock);
-		rqstp->rq_sock = svsk;
-		svc_xprt_get(&svsk->sk_xprt);
+				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
+				rqstp, rqstp->rq_xprt);
+		rqstp->rq_xprt = xprt;
+		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
-		atomic_add(rqstp->rq_reserved, &svsk->sk_xprt.xpt_reserved);
-		BUG_ON(svsk->sk_xprt.xpt_pool != pool);
+		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+		BUG_ON(xprt->xpt_pool != pool);
 		wake_up(&rqstp->rq_wait);
 	} else {
-		dprintk("svc: socket %p put into queue\n", svsk->sk_sk);
-		list_add_tail(&svsk->sk_xprt.xpt_ready, &pool->sp_sockets);
-		BUG_ON(svsk->sk_xprt.xpt_pool != pool);
+		dprintk("svc: transport %p put into queue\n", xprt);
+		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
+		BUG_ON(xprt->xpt_pool != pool);
 	}
 
 out_unlock:
 	spin_unlock_bh(&pool->sp_lock);
 }
+EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
 
 /*
  * Dequeue the first socket.  Must be called with the pool->sp_lock held.
@@ -333,7 +335,7 @@ svc_sock_received(struct svc_sock *svsk)
 {
 	svsk->sk_xprt.xpt_pool = NULL;
 	clear_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags);
-	svc_sock_enqueue(svsk);
+	svc_xprt_enqueue(&svsk->sk_xprt);
 }
 
 
@@ -352,11 +354,11 @@ void svc_reserve(struct svc_rqst *rqstp, int space)
 	space += rqstp->rq_res.head[0].iov_len;
 
 	if (space < rqstp->rq_reserved) {
-		struct svc_sock *svsk = rqstp->rq_sock;
-		atomic_sub((rqstp->rq_reserved - space), &svsk->sk_xprt.xpt_reserved);
+		struct svc_xprt *xprt = rqstp->rq_xprt;
+		atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
 		rqstp->rq_reserved = space;
 
-		svc_sock_enqueue(svsk);
+		svc_xprt_enqueue(xprt);
 	}
 }
 
@@ -684,7 +686,7 @@ svc_udp_data_ready(struct sock *sk, int count)
 			svsk, sk, count,
 			test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-		svc_sock_enqueue(svsk);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
 		wake_up_interruptible(sk->sk_sleep);
@@ -701,7 +703,7 @@ svc_write_space(struct sock *sk)
 	if (svsk) {
 		dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
 			svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
-		svc_sock_enqueue(svsk);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 
 	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) {
@@ -973,7 +975,7 @@ svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
 	if (sk->sk_state == TCP_LISTEN) {
 		if (svsk) {
 			set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
-			svc_sock_enqueue(svsk);
+			svc_xprt_enqueue(&svsk->sk_xprt);
 		} else
 			printk("svc: socket %p: no user data\n", sk);
 	}
@@ -997,7 +999,7 @@ svc_tcp_state_change(struct sock *sk)
 		printk("svc: socket %p: no user data\n", sk);
 	else {
 		set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-		svc_sock_enqueue(svsk);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
 		wake_up_interruptible_all(sk->sk_sleep);
@@ -1012,7 +1014,7 @@ svc_tcp_data_ready(struct sock *sk, int count)
 		sk, sk->sk_user_data);
 	if (svsk) {
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-		svc_sock_enqueue(svsk);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
 		wake_up_interruptible(sk->sk_sleep);
@@ -1298,7 +1300,7 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 		       (sent<0)?"got error":"sent only",
 		       sent, xbufp->len);
 		set_bit(XPT_CLOSE, &rqstp->rq_sock->sk_xprt.xpt_flags);
-		svc_sock_enqueue(rqstp->rq_sock);
+		svc_xprt_enqueue(rqstp->rq_xprt);
 		sent = -EAGAIN;
 	}
 	return sent;
@@ -1476,7 +1478,7 @@ static void svc_check_conn_limits(struct svc_serv *serv)
 		spin_unlock_bh(&serv->sv_lock);
 
 		if (svsk) {
-			svc_sock_enqueue(svsk);
+			svc_xprt_enqueue(&svsk->sk_xprt);
 			svc_xprt_put(&svsk->sk_xprt);
 		}
 	}
@@ -1709,7 +1711,7 @@ svc_age_temp_sockets(unsigned long closure)
 			svsk, get_seconds() - svsk->sk_lastrecv);
 
 		/* a thread will dequeue and close it soon */
-		svc_sock_enqueue(svsk);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 		svc_xprt_put(&svsk->sk_xprt);
 	}
 
@@ -1991,7 +1993,7 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
 	list_add(&dr->handle.recent, &svsk->sk_deferred);
 	spin_unlock(&svsk->sk_lock);
 	set_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
-	svc_sock_enqueue(svsk);
+	svc_xprt_enqueue(&svsk->sk_xprt);
 	svc_xprt_put(&svsk->sk_xprt);
 }
 
author
#23 lore raw

PATCH 22/40 svc: Make svc_send transport neutral

In reply to a message not in the archive

Move the sk_mutex field to the transport independent svc_xprt structure. Now all the fields that svc_send touches are transport neutral. Change the svc_send function to use the transport independent svc_xprt directly instead of the transport dependent svc_sock structure.

---

 include/linux/sunrpc/svc_xprt.h |    1 +
 include/linux/sunrpc/svcsock.h  |    1 -
 net/sunrpc/svc_xprt.c           |    1 +
 net/sunrpc/svcsock.c            |   19 ++++++++-----------
 4 files changed, 10 insertions(+), 12 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index 0b8ee06..1b8c596 100644
@@ -54,6 +54,7 @@ struct svc_xprt {
 	struct svc_pool		*xpt_pool;	/* current pool iff queued */
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
+	struct mutex		xpt_mutex;	/* to serialize sending data */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
include/linux/sunrpc/svcsock.h +0 -1
index ba41f11..41c2dfa 100644
@@ -24,7 +24,6 @@ struct svc_sock {
 						 * sk_info_authunix */
 	struct list_head	sk_deferred;	/* deferred requests that need to
 						 * be revisted */
-	struct mutex		sk_mutex;	/* to serialize sending data */
 
 	/* We keep the old state_change and data_ready CB's here */
 	void			(*sk_ostate)(struct sock *);
net/sunrpc/svc_xprt.c +1 -0
index 95186b5..3e6a1c8 100644
@@ -99,6 +99,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	xprt->xpt_server = serv;
 	INIT_LIST_HEAD(&xprt->xpt_list);
 	INIT_LIST_HEAD(&xprt->xpt_ready);
+	mutex_init(&xprt->xpt_mutex);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
net/sunrpc/svcsock.c +8 -11
index f356c02..7f6ee48 100644
@@ -1632,15 +1632,13 @@ svc_drop(struct svc_rqst *rqstp)
 int
 svc_send(struct svc_rqst *rqstp)
 {
-	struct svc_sock	*svsk;
+	struct svc_xprt	*xprt;
 	int		len;
 	struct xdr_buf	*xb;
 
-	if ((svsk = rqstp->rq_sock) == NULL) {
-		printk(KERN_WARNING "NULL socket pointer in %s:%d\n",
-				__FILE__, __LINE__);
+	xprt = rqstp->rq_xprt;
+	if (!xprt)
 		return -EFAULT;
-	}
 
 	/* release the receive skb before sending the reply */
 	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
@@ -1651,13 +1649,13 @@ svc_send(struct svc_rqst *rqstp)
 		xb->page_len +
 		xb->tail[0].iov_len;
 
-	/* Grab svsk->sk_mutex to serialize outgoing data. */
-	mutex_lock(&svsk->sk_mutex);
-	if (test_bit(XPT_DEAD, &svsk->sk_xprt.xpt_flags))
+	/* Grab mutex to serialize outgoing data. */
+	mutex_lock(&xprt->xpt_mutex);
+	if (test_bit(XPT_DEAD, &xprt->xpt_flags))
 		len = -ENOTCONN;
 	else
-		len = svsk->sk_xprt.xpt_ops->xpo_sendto(rqstp);
-	mutex_unlock(&svsk->sk_mutex);
+		len = xprt->xpt_ops->xpo_sendto(rqstp);
+	mutex_unlock(&xprt->xpt_mutex);
 	svc_sock_release(rqstp);
 
 	if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
@@ -1759,7 +1757,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	svsk->sk_lastrecv = get_seconds();
 	spin_lock_init(&svsk->sk_lock);
 	INIT_LIST_HEAD(&svsk->sk_deferred);
-	mutex_init(&svsk->sk_mutex);
 
 	/* Initialize the socket */
 	if (sock->type == SOCK_DGRAM)
author
#24 lore raw

PATCH 23/40 svc: Change svc_sock_received to svc_xprt_received and export it

In reply to a message not in the archive

All fields touched by svc_sock_received are now transport independent. Change it to use svc_xprt directly. This function is called from transport dependent code, so export it.

Update the comment to clearly state the rules for calling this function.

---

 include/linux/sunrpc/svc_xprt.h |    2 +-
 net/sunrpc/svcsock.c            |   46 ++++++++++++++++++++-------------------
 2 files changed, 25 insertions(+), 23 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -1
index 1b8c596..936e0dc 100644
@@ -62,8 +62,8 @@ void	svc_unreg_xprt_class(struct svc_xprt_class *);
 void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *,
 		      struct svc_serv *);
 int	svc_create_xprt(struct svc_serv *, char *, unsigned short, int);
+void	svc_xprt_received(struct svc_xprt *);
 void	svc_xprt_put(struct svc_xprt *xprt);
-
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {
 	kref_get(&xprt->xpt_ref);
net/sunrpc/svcsock.c +24 -22

127 lines not on this page · raw message

author
#25 lore raw

PATCH 24/40 svc: Move accept call to svc_xprt_received to common code

In reply to a message not in the archive

Now that the svc_xprt_received function handles transports, the call to svc_xprt_received in the xpo_tcp_accept function can be moved to common code.

---

 net/sunrpc/svcsock.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)
net/sunrpc/svcsock.c +1 -2
index 201217f..1d48784 100644
@@ -1106,8 +1106,6 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	}
 	memcpy(&newsvsk->sk_local, sin, slen);
 
-	svc_xprt_received(&newsvsk->sk_xprt);
-
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpconn++;
 
@@ -1591,6 +1589,7 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 			 */
 			__module_get(newxpt->xpt_class->xcl_owner);
 			svc_check_conn_limits(svsk->sk_xprt.xpt_server);
+			svc_xprt_received(newxpt);
 		}
 		svc_xprt_received(&svsk->sk_xprt);
 	} else {
author
#26 lore raw

PATCH 25/40 svc: Remove sk_lastrecv

In reply to a message not in the archive

With the implementation of the new mark and sweep algorithm for shutting down old connections, the sk_lastrecv field is no longer needed.

---

 include/linux/sunrpc/svcsock.h |    1 -
 net/sunrpc/svcsock.c           |    5 +----
 2 files changed, 1 insertions(+), 5 deletions(-)
include/linux/sunrpc/svcsock.h +0 -1
index 41c2dfa..406d003 100644
@@ -33,7 +33,6 @@ struct svc_sock {
 	/* private TCP part */
 	int			sk_reclen;	/* length of record */
 	int			sk_tcplen;	/* current read length */
-	time_t			sk_lastrecv;	/* time of last received request */
 
 	/* cache of various info for TCP sockets */
 	void			*sk_info_authunix;
net/sunrpc/svcsock.c +1 -4
index 1d48784..e98ea4d 100644
@@ -1606,7 +1606,6 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 		svc_sock_release(rqstp);
 		return -EAGAIN;
 	}
-	svsk->sk_lastrecv = get_seconds();
 	clear_bit(XPT_OLD, &svsk->sk_xprt.xpt_flags);
 
 	rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp));
@@ -1706,8 +1705,7 @@ svc_age_temp_sockets(unsigned long closure)
 		list_del_init(le);
 		svsk = list_entry(le, struct svc_sock, sk_xprt.xpt_list);
 
-		dprintk("queuing svsk %p for closing, %lu seconds old\n",
-			svsk, get_seconds() - svsk->sk_lastrecv);
+		dprintk("queuing svsk %p for closing\n", svsk);
 
 		/* a thread will dequeue and close it soon */
 		svc_xprt_enqueue(&svsk->sk_xprt);
@@ -1755,7 +1753,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	svsk->sk_ostate = inet->sk_state_change;
 	svsk->sk_odata = inet->sk_data_ready;
 	svsk->sk_owspace = inet->sk_write_space;
-	svsk->sk_lastrecv = get_seconds();
 	spin_lock_init(&svsk->sk_lock);
 	INIT_LIST_HEAD(&svsk->sk_deferred);
 
author
#27 lore raw

PATCH 26/40 svc: Move the authinfo cache to svc_xprt.

In reply to a message not in the archive

Move the authinfo cache to svc_xprt. This allows both the TCP and RDMA transports to share this logic. A flag bit is used to determine if auth information is to be cached or not. Previously, this code looked at the transport protocol.

I've also changed the spin_lock/unlock logic so that a lock is not taken for transports that are not caching auth info.

---

 include/linux/sunrpc/svc_xprt.h |    4 +++
 include/linux/sunrpc/svcsock.h  |    5 ----
 net/sunrpc/svc_xprt.c           |    4 +++
 net/sunrpc/svcauth_unix.c       |   54 +++++++++++++++++++++------------------
 net/sunrpc/svcsock.c            |   22 +++++++++-------
 5 files changed, 49 insertions(+), 40 deletions(-)
include/linux/sunrpc/svc_xprt.h +4 -0
index 936e0dc..1b5da39 100644
@@ -50,11 +50,15 @@ struct svc_xprt {
 #define	XPT_OLD		9		/* used for xprt aging mark+sweep */
 #define	XPT_DETACHED	10		/* detached from tempsocks list */
 #define XPT_LISTENER	11		/* listening endpoint */
+#define XPT_CACHE_AUTH	12		/* cache auth info */
 
 	struct svc_pool		*xpt_pool;	/* current pool iff queued */
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
 	struct mutex		xpt_mutex;	/* to serialize sending data */
+	spinlock_t		xpt_lock;	/* protects sk_deferred
+						 * and xpt_auth_cache */
+	void			*xpt_auth_cache;/* auth cache */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
include/linux/sunrpc/svcsock.h +0 -5
index 406d003..f2ed6a2 100644
@@ -20,8 +20,6 @@ struct svc_sock {
 	struct socket *		sk_sock;	/* berkeley socket layer */
 	struct sock *		sk_sk;		/* INET layer */
 
-	spinlock_t		sk_lock;	/* protects sk_deferred and
-						 * sk_info_authunix */
 	struct list_head	sk_deferred;	/* deferred requests that need to
 						 * be revisted */
 
@@ -34,9 +32,6 @@ struct svc_sock {
 	int			sk_reclen;	/* length of record */
 	int			sk_tcplen;	/* current read length */
 
-	/* cache of various info for TCP sockets */
-	void			*sk_info_authunix;
-
 	struct sockaddr_storage	sk_local;	/* local address */
 	struct sockaddr_storage	sk_remote;	/* remote peer's address */
 	int			sk_remotelen;	/* length of address */
net/sunrpc/svc_xprt.c +4 -0
index 3e6a1c8..d2ac130 100644
@@ -75,6 +75,9 @@ static void svc_xprt_free(struct kref *kref)
 	struct svc_xprt *xprt =
 		container_of(kref, struct svc_xprt, xpt_ref);
 	struct module *owner = xprt->xpt_class->xcl_owner;
+	if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)
+	    && xprt->xpt_auth_cache != NULL)
+		svcauth_unix_info_release(xprt->xpt_auth_cache);
 	xprt->xpt_ops->xpo_free(xprt);
 	module_put(owner);
 }
@@ -100,6 +103,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	INIT_LIST_HEAD(&xprt->xpt_list);
 	INIT_LIST_HEAD(&xprt->xpt_ready);
 	mutex_init(&xprt->xpt_mutex);
+	spin_lock_init(&xprt->xpt_lock);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
net/sunrpc/svcauth_unix.c +29 -25

70 lines not on this page · raw message

net/sunrpc/svcsock.c +12 -10
index e98ea4d..073e832 100644
@@ -113,12 +113,16 @@ static inline void svc_reclassify_socket(struct socket *sock)
 	switch (sk->sk_family) {
 	case AF_INET:
 		sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
-		    &svc_slock_key[0], "sk_lock-AF_INET-NFSD", &svc_key[0]);
+					      &svc_slock_key[0],
+					      "sk_xprt.xpt_lock-AF_INET-NFSD",
+					      &svc_key[0]);
 		break;
 
 	case AF_INET6:
 		sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFSD",
-		    &svc_slock_key[1], "sk_lock-AF_INET6-NFSD", &svc_key[1]);
+					      &svc_slock_key[1],
+					      "sk_xprt.xpt_lock-AF_INET6-NFSD",
+					      &svc_key[1]);
 		break;
 
 	default:
@@ -930,6 +934,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	mm_segment_t oldfs;
 
 	svc_xprt_init(&svc_udp_class, &svsk->sk_xprt, serv);
+	clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
 	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
 	svsk->sk_sk->sk_write_space = svc_write_space;
 
@@ -1385,7 +1390,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt, serv);
-
+	set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
 	if (sk->sk_state == TCP_LISTEN) {
 		dprintk("setting up TCP socket for listening\n");
 		set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
@@ -1753,7 +1758,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	svsk->sk_ostate = inet->sk_state_change;
 	svsk->sk_odata = inet->sk_data_ready;
 	svsk->sk_owspace = inet->sk_write_space;
-	spin_lock_init(&svsk->sk_lock);
 	INIT_LIST_HEAD(&svsk->sk_deferred);
 
 	/* Initialize the socket */
@@ -1898,8 +1902,6 @@ static void svc_sock_free(struct svc_xprt *xprt)
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 	dprintk("svc: svc_sock_free(%p)\n", svsk);
 
-	if (svsk->sk_info_authunix != NULL)
-		svcauth_unix_info_release(svsk->sk_info_authunix);
 	if (svsk->sk_sock->file)
 		sockfd_put(svsk->sk_sock);
 	else
@@ -1984,9 +1986,9 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
 	dprintk("revisit queued\n");
 	svsk = dr->svsk;
 	dr->svsk = NULL;
-	spin_lock(&svsk->sk_lock);
+	spin_lock(&svsk->sk_xprt.xpt_lock);
 	list_add(&dr->handle.recent, &svsk->sk_deferred);
-	spin_unlock(&svsk->sk_lock);
+	spin_unlock(&svsk->sk_xprt.xpt_lock);
 	set_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
 	svc_xprt_enqueue(&svsk->sk_xprt);
 	svc_xprt_put(&svsk->sk_xprt);
@@ -2052,7 +2054,7 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
 
 	if (!test_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags))
 		return NULL;
-	spin_lock(&svsk->sk_lock);
+	spin_lock(&svsk->sk_xprt.xpt_lock);
 	clear_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
 	if (!list_empty(&svsk->sk_deferred)) {
 		dr = list_entry(svsk->sk_deferred.next,
@@ -2061,6 +2063,6 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
 		list_del_init(&dr->handle.recent);
 		set_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
 	}
-	spin_unlock(&svsk->sk_lock);
+	spin_unlock(&svsk->sk_xprt.xpt_lock);
 	return dr;
 }
author
#28 lore raw

PATCH 27/40 svc: Make deferral processing xprt independent

In reply to a message not in the archive

This patch moves the transport independent sk_deferred list to the svc_xprt structure and updates the svc_deferred_req structure to keep pointers to svc_xprt's directly. The deferral processing code is also moved out of the transport dependent recvfrom functions and into the generic svc_recv path.

---

 include/linux/sunrpc/svc.h      |    2 +
 include/linux/sunrpc/svc_xprt.h |    2 +
 include/linux/sunrpc/svcsock.h  |    3 --
 net/sunrpc/svc_xprt.c           |    1 +
 net/sunrpc/svcsock.c            |   57 +++++++++++++++++----------------------
 5 files changed, 29 insertions(+), 36 deletions(-)
include/linux/sunrpc/svc.h +1 -1
index cfb2652..40adc9d 100644
@@ -320,7 +320,7 @@ static inline void svc_free_res_pages(struct svc_rqst *rqstp)
 
 struct svc_deferred_req {
 	u32			prot;	/* protocol (UDP or TCP) */
-	struct svc_sock		*svsk;
+	struct svc_xprt		*xprt;
 	struct sockaddr_storage	addr;	/* where reply must go */
 	size_t			addrlen;
 	union svc_addr_u	daddr;	/* where reply must come from */
include/linux/sunrpc/svc_xprt.h +2 -0
index 1b5da39..6a8445b 100644
@@ -59,6 +59,8 @@ struct svc_xprt {
 	spinlock_t		xpt_lock;	/* protects sk_deferred
 						 * and xpt_auth_cache */
 	void			*xpt_auth_cache;/* auth cache */
+	struct list_head	xpt_deferred;	/* deferred requests that need
+						 * to be revisted */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
include/linux/sunrpc/svcsock.h +0 -3
index f2ed6a2..96a229e 100644
@@ -20,9 +20,6 @@ struct svc_sock {
 	struct socket *		sk_sock;	/* berkeley socket layer */
 	struct sock *		sk_sk;		/* INET layer */
 
-	struct list_head	sk_deferred;	/* deferred requests that need to
-						 * be revisted */
-
 	/* We keep the old state_change and data_ready CB's here */
 	void			(*sk_ostate)(struct sock *);
 	void			(*sk_odata)(struct sock *, int bytes);
net/sunrpc/svc_xprt.c +1 -0
index d2ac130..023aeb0 100644
@@ -102,6 +102,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	xprt->xpt_server = serv;
 	INIT_LIST_HEAD(&xprt->xpt_list);
 	INIT_LIST_HEAD(&xprt->xpt_ready);
+	INIT_LIST_HEAD(&xprt->xpt_deferred);
 	mutex_init(&xprt->xpt_mutex);
 	spin_lock_init(&xprt->xpt_lock);
 }
net/sunrpc/svcsock.c +25 -32

118 lines not on this page · raw message

author
#29 lore raw

PATCH 28/40 svc: Move the sockaddr information to svc_xprt

In reply to a message not in the archive

This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr.

A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation.

For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there.

A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port.

---

 include/linux/sunrpc/svc_xprt.h |   51 ++++++++++++++++++++++++++++++++++++
 include/linux/sunrpc/svcsock.h  |    4 ---
 net/sunrpc/svc_xprt.c           |   31 ++++++++++++++++++++--
 net/sunrpc/svcsock.c            |   56 +++++++++++++++++++++------------------
 4 files changed, 110 insertions(+), 32 deletions(-)
include/linux/sunrpc/svc_xprt.h +51 -0
index 6a8445b..09de12b 100644
@@ -61,6 +61,10 @@ struct svc_xprt {
 	void			*xpt_auth_cache;/* auth cache */
 	struct list_head	xpt_deferred;	/* deferred requests that need
 						 * to be revisted */
+	struct sockaddr_storage	xpt_local;	/* local address */
+	size_t			xpt_locallen;	/* length of address */
+	struct sockaddr_storage	xpt_remote;	/* remote peer's address */
+	size_t			xpt_remotelen;	/* length of address */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);
@@ -70,9 +74,56 @@ void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *,
 int	svc_create_xprt(struct svc_serv *, char *, unsigned short, int);
 void	svc_xprt_received(struct svc_xprt *);
 void	svc_xprt_put(struct svc_xprt *xprt);
+void	svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt);
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {
 	kref_get(&xprt->xpt_ref);
 }
+static inline void svc_xprt_set_local(struct svc_xprt *xprt,
+				      struct sockaddr *sa, int salen)
+{
+	memcpy(&xprt->xpt_local, sa, salen);
+	xprt->xpt_locallen = salen;
+}
+static inline void svc_xprt_set_remote(struct svc_xprt *xprt,
+				       struct sockaddr *sa, int salen)
+{
+	memcpy(&xprt->xpt_remote, sa, salen);
+	xprt->xpt_remotelen = salen;
+}
+static inline unsigned short svc_addr_port(struct sockaddr *sa)
+{
+	unsigned short ret = 0;
+	switch (sa->sa_family) {
+	case AF_INET:
+		ret = ntohs(((struct sockaddr_in *)sa)->sin_port);
+		break;
+	case AF_INET6:
+		ret = ntohs(((struct sockaddr_in6 *)sa)->sin6_port);
+		break;
+	}
+	return ret;
+}
+
+static inline size_t svc_addr_len(struct sockaddr *sa)
+{
+	switch (sa->sa_family) {
+	case AF_INET:
+		return sizeof(struct sockaddr_in);
+	case AF_INET6:
+		return sizeof(struct sockaddr_in6);
+	}
+	return -EAFNOSUPPORT;
+}
+
+static inline unsigned short svc_xprt_local_port(struct svc_xprt *xprt)
+{
+	return svc_addr_port((struct sockaddr *)&xprt->xpt_local);
+}
+
+static inline unsigned short svc_xprt_remote_port(struct svc_xprt *xprt)
+{
+	return svc_addr_port((struct sockaddr *)&xprt->xpt_remote);
+}
 
 #endif /* SUNRPC_SVC_XPRT_H */
include/linux/sunrpc/svcsock.h +0 -4
index 96a229e..206f092 100644
@@ -28,10 +28,6 @@ struct svc_sock {
 	/* private TCP part */
 	int			sk_reclen;	/* length of record */
 	int			sk_tcplen;	/* current read length */
-
-	struct sockaddr_storage	sk_local;	/* local address */
-	struct sockaddr_storage	sk_remote;	/* remote peer's address */
-	int			sk_remotelen;	/* length of address */
 };
 
 /*
net/sunrpc/svc_xprt.c +29 -2
index 023aeb0..eb650af 100644
@@ -125,7 +125,6 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
 			spin_unlock(&svc_xprt_class_lock);
 			if (try_module_get(xcl->xcl_owner)) {
 				struct svc_xprt *newxprt;
-				ret = 0;
 				newxprt = xcl->xcl_ops->xpo_create
 					(serv,
 					 (struct sockaddr *)&sin, sizeof(sin),
@@ -133,7 +132,8 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
 				if (IS_ERR(newxprt)) {
 					module_put(xcl->xcl_owner);
 					ret = PTR_ERR(newxprt);
-				}
+				} else
+					ret = svc_xprt_local_port(newxprt);
 			}
 			goto out;
 		}
@@ -144,3 +144,30 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(svc_create_xprt);
+
+/*
+ * Copy the local and remote xprt addresses to the rqstp structure
+ */
+void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt)
+{
+	struct sockaddr *sin;
+
+	memcpy(&rqstp->rq_addr, &xprt->xpt_remote, xprt->xpt_remotelen);
+	rqstp->rq_addrlen = xprt->xpt_remotelen;
+
+	/*
+	 * Destination address in request is needed for binding the
+	 * source address in RPC replies/callbacks later.
+	 */
+	sin = (struct sockaddr *)&xprt->xpt_local;
+	switch (sin->sa_family) {
+	case AF_INET:
+		rqstp->rq_daddr.addr = ((struct sockaddr_in *)sin)->sin_addr;
+		break;
+	case AF_INET6:
+		rqstp->rq_daddr.addr6 = ((struct sockaddr_in6 *)sin)->sin6_addr;
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(svc_xprt_copy_addrs);
+
net/sunrpc/svcsock.c +30 -26

122 lines not on this page · raw message

author
#30 lore raw

PATCH 29/40 svc: Make svc_sock_release svc_xprt_release

In reply to a message not in the archive

The svc_sock_release function only touches transport independent fields. Change the function to manipulate svc_xprt directly instead of the transport dependent svc_sock structure.

---

 net/sunrpc/svcsock.c |   16 +++++++---------
 1 files changed, 7 insertions(+), 9 deletions(-)
net/sunrpc/svcsock.c +7 -9
index 298c95e..505336e 100644
@@ -368,10 +368,9 @@ void svc_reserve(struct svc_rqst *rqstp, int space)
 	}
 }
 
-static void
-svc_sock_release(struct svc_rqst *rqstp)
+static void svc_xprt_release(struct svc_rqst *rqstp)
 {
-	struct svc_sock	*svsk = rqstp->rq_sock;
+	struct svc_xprt	*xprt = rqstp->rq_xprt;
 
 	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
 
@@ -379,7 +378,6 @@ svc_sock_release(struct svc_rqst *rqstp)
 	rqstp->rq_res.page_len = 0;
 	rqstp->rq_res.page_base = 0;
 
-
 	/* Reset response buffer and release
 	 * the reservation.
 	 * But first, check that enough space was reserved
@@ -392,9 +390,9 @@ svc_sock_release(struct svc_rqst *rqstp)
 
 	rqstp->rq_res.head[0].iov_len = 0;
 	svc_reserve(rqstp, 0);
-	rqstp->rq_sock = NULL;
+	rqstp->rq_xprt = NULL;
 
-	svc_xprt_put(&svsk->sk_xprt);
+	svc_xprt_put(xprt);
 }
 
 /*
@@ -1593,7 +1591,7 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 	/* No data, incomplete (TCP) read, or accept() */
 	if (len == 0 || len == -EAGAIN) {
 		rqstp->rq_res.len = 0;
-		svc_sock_release(rqstp);
+		svc_xprt_release(rqstp);
 		return -EAGAIN;
 	}
 	clear_bit(XPT_OLD, &svsk->sk_xprt.xpt_flags);
@@ -1613,7 +1611,7 @@ void
 svc_drop(struct svc_rqst *rqstp)
 {
 	dprintk("svc: socket %p dropped request\n", rqstp->rq_sock);
-	svc_sock_release(rqstp);
+	svc_xprt_release(rqstp);
 }
 
 /*
@@ -1646,7 +1644,7 @@ svc_send(struct svc_rqst *rqstp)
 	else
 		len = xprt->xpt_ops->xpo_sendto(rqstp);
 	mutex_unlock(&xprt->xpt_mutex);
-	svc_sock_release(rqstp);
+	svc_xprt_release(rqstp);
 
 	if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
 		return 0;
author
#31 lore raw

PATCH 30/40 svc: Make svc_recv transport neutral

In reply to a message not in the archive

All of the transport field and functions used by svc_recv are now transport independent. Change the svc_recv function to use the svc_xprt structure directly instead of the transport specific svc_sock structure.

---

 net/sunrpc/svcsock.c |   61 +++++++++++++++++++++++++-------------------------
 1 files changed, 31 insertions(+), 30 deletions(-)
net/sunrpc/svcsock.c +31 -30
index 505336e..b3a64bf 100644
@@ -310,22 +310,21 @@ EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
 /*
  * Dequeue the first socket.  Must be called with the pool->sp_lock held.
  */
-static inline struct svc_sock *
-svc_sock_dequeue(struct svc_pool *pool)
+static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 {
-	struct svc_sock	*svsk;
+	struct svc_xprt	*xprt;
 
 	if (list_empty(&pool->sp_sockets))
 		return NULL;
 
-	svsk = list_entry(pool->sp_sockets.next,
-			  struct svc_sock, sk_xprt.xpt_ready);
-	list_del_init(&svsk->sk_xprt.xpt_ready);
+	xprt = list_entry(pool->sp_sockets.next,
+			  struct svc_xprt, xpt_ready);
+	list_del_init(&xprt->xpt_ready);
 
-	dprintk("svc: socket %p dequeued, inuse=%d\n",
-		svsk->sk_sk, atomic_read(&svsk->sk_xprt.xpt_ref.refcount));
+	dprintk("svc: transport %p dequeued, inuse=%d\n",
+		xprt, atomic_read(&xprt->xpt_ref.refcount));
 
-	return svsk;
+	return xprt;
 }
 
 /*
@@ -1475,20 +1474,20 @@ static void svc_check_conn_limits(struct svc_serv *serv)
 int
 svc_recv(struct svc_rqst *rqstp, long timeout)
 {
-	struct svc_sock		*svsk = NULL;
+	struct svc_xprt		*xprt = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
 	struct svc_pool		*pool = rqstp->rq_pool;
 	int			len, i;
-	int 			pages;
+	int			pages;
 	struct xdr_buf		*arg;
 	DECLARE_WAITQUEUE(wait, current);
 
 	dprintk("svc: server %p waiting for data (to = %ld)\n",
 		rqstp, timeout);
 
-	if (rqstp->rq_sock)
+	if (rqstp->rq_xprt)
 		printk(KERN_ERR
-			"svc_recv: service %p, socket not NULL!\n",
+			"svc_recv: service %p, transport not NULL!\n",
 			 rqstp);
 	if (waitqueue_active(&rqstp->rq_wait))
 		printk(KERN_ERR
@@ -1525,11 +1524,12 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 		return -EINTR;
 
 	spin_lock_bh(&pool->sp_lock);
-	if ((svsk = svc_sock_dequeue(pool)) != NULL) {
-		rqstp->rq_sock = svsk;
-		svc_xprt_get(&svsk->sk_xprt);
+	xprt = svc_xprt_dequeue(pool);
+	if (xprt) {
+		rqstp->rq_xprt = xprt;
+		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
-		atomic_add(rqstp->rq_reserved, &svsk->sk_xprt.xpt_reserved);
+		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
 	} else {
 		/* No data pending. Go to sleep */
 		svc_thread_enqueue(pool, rqstp);
@@ -1549,7 +1549,8 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 		spin_lock_bh(&pool->sp_lock);
 		remove_wait_queue(&rqstp->rq_wait, &wait);
 
-		if (!(svsk = rqstp->rq_sock)) {
+		xprt = rqstp->rq_xprt;
+		if (!xprt) {
 			svc_thread_dequeue(pool, rqstp);
 			spin_unlock_bh(&pool->sp_lock);
 			dprintk("svc: server %p, no data yet\n", rqstp);
@@ -1559,12 +1560,12 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 	spin_unlock_bh(&pool->sp_lock);
 
 	len = 0;
-	if (test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)) {
+	if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
 		dprintk("svc_recv: found XPT_CLOSE\n");
-		svc_delete_xprt(&svsk->sk_xprt);
-	} else if (test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags)) {
+		svc_delete_xprt(xprt);
+	} else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
 		struct svc_xprt *newxpt;
-		newxpt = svsk->sk_xprt.xpt_ops->xpo_accept(&svsk->sk_xprt);
+		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt) {
 			/*
 			 * We know this module_get will succeed because the
@@ -1574,17 +1575,17 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 			svc_check_conn_limits(svsk->sk_xprt.xpt_server);
 			svc_xprt_received(newxpt);
 		}
-		svc_xprt_received(&svsk->sk_xprt);
+		svc_xprt_received(xprt);
 	} else {
-		dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
-			rqstp, pool->sp_id, svsk,
-			atomic_read(&svsk->sk_xprt.xpt_ref.refcount));
-		rqstp->rq_deferred = svc_deferred_dequeue(&svsk->sk_xprt);
+		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
+			rqstp, pool->sp_id, xprt,
+			atomic_read(&xprt->xpt_ref.refcount));
+		rqstp->rq_deferred = svc_deferred_dequeue(xprt);
 		if (rqstp->rq_deferred) {
-			svc_xprt_received(&svsk->sk_xprt);
+			svc_xprt_received(xprt);
 			len = svc_deferred_recv(rqstp);
 		} else
-			len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
+			len = xprt->xpt_ops->xpo_recvfrom(rqstp);
 		dprintk("svc: got len=%d\n", len);
 	}
 
@@ -1594,7 +1595,7 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 		svc_xprt_release(rqstp);
 		return -EAGAIN;
 	}
-	clear_bit(XPT_OLD, &svsk->sk_xprt.xpt_flags);
+	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
 	rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp));
 	rqstp->rq_chandle.defer = svc_defer;
author
#32 lore raw

PATCH 31/40 svc: Make svc_age_temp_sockets svc_age_temp_transports

In reply to a message not in the archive

This function is transport independent. Change it to use svc_xprt directly and change it's name to reflect this.

---

 net/sunrpc/svcsock.c |   37 +++++++++++++++++++------------------
 1 files changed, 19 insertions(+), 18 deletions(-)
net/sunrpc/svcsock.c +19 -18
index b3a64bf..822ccb6 100644
@@ -1656,49 +1656,50 @@ svc_send(struct svc_rqst *rqstp)
  * Timer function to close old temporary sockets, using
  * a mark-and-sweep algorithm.
  */
-static void
-svc_age_temp_sockets(unsigned long closure)
+static void svc_age_temp_xprts(unsigned long closure)
 {
 	struct svc_serv *serv = (struct svc_serv *)closure;
-	struct svc_sock *svsk;
+	struct svc_xprt *xprt;
 	struct list_head *le, *next;
 	LIST_HEAD(to_be_aged);
 
-	dprintk("svc_age_temp_sockets\n");
+	dprintk("svc_age_temp_xprts\n");
 
 	if (!spin_trylock_bh(&serv->sv_lock)) {
 		/* busy, try again 1 sec later */
-		dprintk("svc_age_temp_sockets: busy\n");
+		dprintk("svc_age_temp_xprts: busy\n");
 		mod_timer(&serv->sv_temptimer, jiffies + HZ);
 		return;
 	}
 
 	list_for_each_safe(le, next, &serv->sv_tempsocks) {
-		svsk = list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+		xprt = list_entry(le, struct svc_xprt, xpt_list);
 
-		if (!test_and_set_bit(XPT_OLD, &svsk->sk_xprt.xpt_flags))
+		/* First time through, just mark it OLD. Second time
+		 * through, close it. */
+		if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags))
 			continue;
-		if (atomic_read(&svsk->sk_xprt.xpt_ref.refcount) > 1
-		    || test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags))
+		if (atomic_read(&xprt->xpt_ref.refcount) > 1
+		    || test_bit(XPT_BUSY, &xprt->xpt_flags))
 			continue;
-		svc_xprt_get(&svsk->sk_xprt);
+		svc_xprt_get(xprt);
 		list_move(le, &to_be_aged);
-		set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-		set_bit(XPT_DETACHED, &svsk->sk_xprt.xpt_flags);
+		set_bit(XPT_CLOSE, &xprt->xpt_flags);
+		set_bit(XPT_DETACHED, &xprt->xpt_flags);
 	}
 	spin_unlock_bh(&serv->sv_lock);
 
 	while (!list_empty(&to_be_aged)) {
 		le = to_be_aged.next;
-		/* fiddling the sk_xprt.xpt_list node is safe 'cos we're XPT_DETACHED */
+		/* fiddling the xpt_list node is safe 'cos we're XPT_DETACHED */
 		list_del_init(le);
-		svsk = list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+		xprt = list_entry(le, struct svc_xprt, xpt_list);
 
-		dprintk("queuing svsk %p for closing\n", svsk);
+		dprintk("queuing xprt %p for closing\n", xprt);
 
 		/* a thread will dequeue and close it soon */
-		svc_xprt_enqueue(&svsk->sk_xprt);
-		svc_xprt_put(&svsk->sk_xprt);
+		svc_xprt_enqueue(xprt);
+		svc_xprt_put(xprt);
 	}
 
 	mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
@@ -1756,7 +1757,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 		serv->sv_tmpcnt++;
 		if (serv->sv_temptimer.function == NULL) {
 			/* setup timer to age temp sockets */
-			setup_timer(&serv->sv_temptimer, svc_age_temp_sockets,
+			setup_timer(&serv->sv_temptimer, svc_age_temp_xprts,
 					(unsigned long)serv);
 			mod_timer(&serv->sv_temptimer,
 					jiffies + svc_conn_age_period * HZ);
author
#33 lore raw

PATCH 32/40 svc: Move create logic to common code

In reply to a message not in the archive

Move the svc transport list logic into common transport creation code. Refactor this code path to make the flow of control easier to read.

Move the setting and clearing of the BUSY_BIT during transport creation to common code.

---

 net/sunrpc/svc_xprt.c |   43 +++++++++++++++++++++++++------------------
 net/sunrpc/svcsock.c  |   41 +++++++++++++++++++----------------------
 2 files changed, 44 insertions(+), 40 deletions(-)
net/sunrpc/svc_xprt.c +25 -18
index eb650af..271467c 100644
@@ -105,6 +105,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	INIT_LIST_HEAD(&xprt->xpt_deferred);
 	mutex_init(&xprt->xpt_mutex);
 	spin_lock_init(&xprt->xpt_lock);
+	set_bit(XPT_BUSY, &xprt->xpt_flags);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
@@ -112,7 +113,6 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
 		    int flags)
 {
 	struct svc_xprt_class *xcl;
-	int ret = -ENOENT;
 	struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
 		.sin_addr.s_addr	= INADDR_ANY,
@@ -121,27 +121,34 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
 	dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
 	spin_lock(&svc_xprt_class_lock);
 	list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
-		if (strcmp(xprt_name, xcl->xcl_name) == 0) {
-			spin_unlock(&svc_xprt_class_lock);
-			if (try_module_get(xcl->xcl_owner)) {
-				struct svc_xprt *newxprt;
-				newxprt = xcl->xcl_ops->xpo_create
-					(serv,
-					 (struct sockaddr *)&sin, sizeof(sin),
-					 flags);
-				if (IS_ERR(newxprt)) {
-					module_put(xcl->xcl_owner);
-					ret = PTR_ERR(newxprt);
-				} else
-					ret = svc_xprt_local_port(newxprt);
-			}
-			goto out;
+		struct svc_xprt *newxprt;
+
+		if (strcmp(xprt_name, xcl->xcl_name))
+			continue;
+
+		if (!try_module_get(xcl->xcl_owner))
+			goto err;
+
+		spin_unlock(&svc_xprt_class_lock);
+		newxprt = xcl->xcl_ops->
+			xpo_create(serv, (struct sockaddr *)&sin, sizeof(sin),
+				   flags);
+		if (IS_ERR(newxprt)) {
+			module_put(xcl->xcl_owner);
+			return PTR_ERR(newxprt);
 		}
+
+		clear_bit(XPT_TEMP, &newxprt->xpt_flags);
+		spin_lock_bh(&serv->sv_lock);
+		list_add(&newxprt->xpt_list, &serv->sv_permsocks);
+		spin_unlock_bh(&serv->sv_lock);
+		clear_bit(XPT_BUSY, &newxprt->xpt_flags);
+		return svc_xprt_local_port(newxprt);
 	}
+ err:
 	spin_unlock(&svc_xprt_class_lock);
 	dprintk("svc: transport %s not found\n", xprt_name);
- out:
-	return ret;
+	return -ENOENT;
 }
 EXPORT_SYMBOL_GPL(svc_create_xprt);
 
net/sunrpc/svcsock.c +19 -22

83 lines not on this page · raw message

author
#34 lore raw

PATCH 33/40 svc: Removing remaining references to rq_sock in rqstp

In reply to a message not in the archive

This functionally empty patch removes rq_sock and unamed union from rqstp structure.

---

 include/linux/sunrpc/svc.h |    5 +----
 net/sunrpc/svcsock.c       |   38 ++++++++++++++++++++++++--------------
 2 files changed, 25 insertions(+), 18 deletions(-)
include/linux/sunrpc/svc.h +1 -4
index 40adc9d..04eb20e 100644
@@ -204,10 +204,7 @@ union svc_addr_u {
 struct svc_rqst {
 	struct list_head	rq_list;	/* idle list */
 	struct list_head	rq_all;		/* all threads list */
-	union {
-		struct svc_xprt *	rq_xprt;	/* transport ptr */
-		struct svc_sock *	rq_sock; 	/* socket ptr */
-	};
+	struct svc_xprt *	rq_xprt;	/* transport ptr */
 	struct sockaddr_storage	rq_addr;	/* peer address */
 	size_t			rq_addrlen;
 
net/sunrpc/svcsock.c +24 -14
index db9a541..03aa392 100644
@@ -201,10 +201,12 @@ static void svc_release_skb(struct svc_rqst *rqstp)
 	struct svc_deferred_req *dr = rqstp->rq_deferred;
 
 	if (skb) {
+		struct svc_sock *svsk =
+			container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
 		rqstp->rq_xprt_ctxt = NULL;
 
 		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
-		skb_free_datagram(rqstp->rq_sock->sk_sk, skb);
+		skb_free_datagram(svsk->sk_sk, skb);
 	}
 	if (dr) {
 		rqstp->rq_deferred = NULL;
@@ -418,7 +420,7 @@ svc_wake_up(struct svc_serv *serv)
 			dprintk("svc: daemon %p woken up.\n", rqstp);
 			/*
 			svc_thread_dequeue(pool, rqstp);
-			rqstp->rq_sock = NULL;
+			rqstp->rq_xprt = NULL;
 			 */
 			wake_up(&rqstp->rq_wait);
 		}
@@ -435,7 +437,9 @@ union svc_pktinfo_u {
 
 static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 {
-	switch (rqstp->rq_sock->sk_sk->sk_family) {
+	struct svc_sock *svsk =
+		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
+	switch (svsk->sk_sk->sk_family) {
 	case AF_INET: {
 			struct in_pktinfo *pki = CMSG_DATA(cmh);
 
@@ -468,7 +472,8 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 static int
 svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
 {
-	struct svc_sock	*svsk = rqstp->rq_sock;
+	struct svc_sock	*svsk =
+		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
 	struct socket	*sock = svsk->sk_sock;
 	int		slen;
 	union {
@@ -541,7 +546,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
 	}
 out:
 	dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %s)\n",
-		rqstp->rq_sock, xdr->head[0].iov_base, xdr->head[0].iov_len,
+		svsk, xdr->head[0].iov_base, xdr->head[0].iov_len,
 		xdr->len, len, svc_print_addr(rqstp, buf, sizeof(buf)));
 
 	return len;
@@ -617,7 +622,8 @@ svc_recv_available(struct svc_sock *svsk)
 static int
 svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
 {
-	struct svc_sock *svsk = rqstp->rq_sock;
+	struct svc_sock *svsk =
+		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
 	struct msghdr msg = {
 		.msg_flags	= MSG_DONTWAIT,
 	};
@@ -707,7 +713,9 @@ svc_write_space(struct sock *sk)
 static void svc_udp_get_dest_address(struct svc_rqst *rqstp,
 				     struct cmsghdr *cmh)
 {
-	switch (rqstp->rq_sock->sk_sk->sk_family) {
+	struct svc_sock *svsk =
+		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
+	switch (svsk->sk_sk->sk_family) {
 	case AF_INET: {
 		struct in_pktinfo *pki = CMSG_DATA(cmh);
 		rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr;
@@ -727,7 +735,8 @@ static void svc_udp_get_dest_address(struct svc_rqst *rqstp,
 static int
 svc_udp_recvfrom(struct svc_rqst *rqstp)
 {
-	struct svc_sock	*svsk = rqstp->rq_sock;
+	struct svc_sock	*svsk =
+		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
 	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
 	struct sk_buff	*skb;
 	union {
@@ -1109,7 +1118,8 @@ failed:
 static int
 svc_tcp_recvfrom(struct svc_rqst *rqstp)
 {
-	struct svc_sock	*svsk = rqstp->rq_sock;
+	struct svc_sock	*svsk =
+		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
 	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
 	int		len;
 	struct kvec *vec;
@@ -1273,16 +1283,16 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 	reclen = htonl(0x80000000|((xbufp->len ) - 4));
 	memcpy(xbufp->head[0].iov_base, &reclen, 4);
 
-	if (test_bit(XPT_DEAD, &rqstp->rq_sock->sk_xprt.xpt_flags))
+	if (test_bit(XPT_DEAD, &rqstp->rq_xprt->xpt_flags))
 		return -ENOTCONN;
 
 	sent = svc_sendto(rqstp, &rqstp->rq_res);
 	if (sent != xbufp->len) {
 		printk(KERN_NOTICE "rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n",
-		       rqstp->rq_sock->sk_xprt.xpt_server->sv_name,
+		       rqstp->rq_xprt->xpt_server->sv_name,
 		       (sent<0)?"got error":"sent only",
 		       sent, xbufp->len);
-		set_bit(XPT_CLOSE, &rqstp->rq_sock->sk_xprt.xpt_flags);
+		set_bit(XPT_CLOSE, &rqstp->rq_xprt->xpt_flags);
 		svc_xprt_enqueue(rqstp->rq_xprt);
 		sent = -EAGAIN;
 	}
@@ -1302,7 +1312,7 @@ static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
 
 static int svc_tcp_has_wspace(struct svc_xprt *xprt)
 {
-	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+	struct svc_sock *svsk =	container_of(xprt, struct svc_sock, sk_xprt);
 	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
 	int required;
 	int wspace;
@@ -1625,7 +1635,7 @@ svc_recv(struct svc_rqst *rqstp, long timeout)
 void
 svc_drop(struct svc_rqst *rqstp)
 {
-	dprintk("svc: socket %p dropped request\n", rqstp->rq_sock);
+	dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt);
 	svc_xprt_release(rqstp);
 }
 
author
#35 lore raw

PATCH 34/40 svc: Make svc_check_conn_limits xprt independent

In reply to a message not in the archive

The svc_check_conn_limits function only manipulates xprt fields. Change references to svc_sock->sk_xprt to svc_xprt directly.

---

 net/sunrpc/svcsock.c |   24 ++++++++++++------------
 1 files changed, 12 insertions(+), 12 deletions(-)
net/sunrpc/svcsock.c +12 -12
index 03aa392..4d03e87 100644
@@ -1448,31 +1448,31 @@ svc_sock_update_bufs(struct svc_serv *serv)
 static void svc_check_conn_limits(struct svc_serv *serv)
 {
 	if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
-		struct svc_sock *svsk = NULL;
+		struct svc_xprt *xprt = NULL;
 		spin_lock_bh(&serv->sv_lock);
 		if (!list_empty(&serv->sv_tempsocks)) {
 			if (net_ratelimit()) {
 				/* Try to help the admin */
-				printk(KERN_NOTICE "%s: too many open TCP "
-				       "sockets, consider increasing the "
+				printk(KERN_NOTICE "%s: too many open  "
+				       "connections, consider increasing the "
 				       "number of nfsd threads\n",
 				       serv->sv_name);
 			}
 			/*
-			 * Always select the oldest socket. It's not fair,
+			 * Always select the oldest connection. It's not fair,
 			 * but so is life
 			 */
-			svsk = list_entry(serv->sv_tempsocks.prev,
-					  struct svc_sock,
-					  sk_xprt.xpt_list);
-			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-			svc_xprt_get(&svsk->sk_xprt);
+			xprt = list_entry(serv->sv_tempsocks.prev,
+					  struct svc_xprt,
+					  xpt_list);
+			set_bit(XPT_CLOSE, &xprt->xpt_flags);
+			svc_xprt_get(xprt);
 		}
 		spin_unlock_bh(&serv->sv_lock);
 
-		if (svsk) {
-			svc_xprt_enqueue(&svsk->sk_xprt);
-			svc_xprt_put(&svsk->sk_xprt);
+		if (xprt) {
+			svc_xprt_enqueue(xprt);
+			svc_xprt_put(xprt);
 		}
 	}
 }
author
#36 lore raw

PATCH 35/40 svc: Move the xprt independent code to the svc_xprt.c file

In reply to a message not in the archive

This functionally trivial patch moves all of the transport independent functions from the svcsock.c file to the transport independent svc_xprt.c file.

In addition the following formatting changes were made:
- White space cleanup
- Function signatures on single line
- The inline directive was removed
- Lines over 80 columns were reformatted
- The term 'socket' was changed to 'transport' in comments
- The SMP comment was moved and updated.

---

 include/linux/sunrpc/svc_xprt.h |   27 +
 net/sunrpc/svc_xprt.c           |  753 +++++++++++++++++++++++++++++++++++
 net/sunrpc/svcsock.c            |  834 +--------------------------------------
 3 files changed, 804 insertions(+), 810 deletions(-)
include/linux/sunrpc/svc_xprt.h +27 -0
index 09de12b..405281e 100644
@@ -72,9 +72,14 @@ void	svc_unreg_xprt_class(struct svc_xprt_class *);
 void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *,
 		      struct svc_serv *);
 int	svc_create_xprt(struct svc_serv *, char *, unsigned short, int);
+void	svc_xprt_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_received(struct svc_xprt *);
 void	svc_xprt_put(struct svc_xprt *xprt);
 void	svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt);
+void	svc_close_xprt(struct svc_xprt *xprt);
+void	svc_delete_xprt(struct svc_xprt *xprt);
+int	svc_port_is_privileged(struct sockaddr *sin);
+
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {
 	kref_get(&xprt->xpt_ref);
@@ -126,4 +131,26 @@ static inline unsigned short svc_xprt_remote_port(struct svc_xprt *xprt)
 	return svc_addr_port((struct sockaddr *)&xprt->xpt_remote);
 }
 
+static inline char *__svc_print_addr(struct sockaddr *addr,
+				     char *buf, size_t len)
+{
+	switch (addr->sa_family) {
+	case AF_INET:
+		snprintf(buf, len, "%u.%u.%u.%u, port=%u",
+			NIPQUAD(((struct sockaddr_in *) addr)->sin_addr),
+			ntohs(((struct sockaddr_in *) addr)->sin_port));
+		break;
+
+	case AF_INET6:
+		snprintf(buf, len, "%x:%x:%x:%x:%x:%x:%x:%x, port=%u",
+			NIP6(((struct sockaddr_in6 *) addr)->sin6_addr),
+			ntohs(((struct sockaddr_in6 *) addr)->sin6_port));
+		break;
+
+	default:
+		snprintf(buf, len, "unknown address type: %d", addr->sa_family);
+		break;
+	}
+	return buf;
+}
 #endif /* SUNRPC_SVC_XPRT_H */
net/sunrpc/svc_xprt.c +753 -0

766 lines not on this page · raw message

net/sunrpc/svcsock.c +24 -810

984 lines not on this page · raw message

A message that is not in the archive (sent off-list or not yet received): 20071231030827.8430.76850.stgit-gUwIgmpLGaKNDNWfRnPdfg@public.gmane.org

#38 lore raw

Re: [PATCH 35/40] svc: Move the xprt independent code to the svc_xprt.c file

Quoted 526 lines · Tom Tucker
net/sunrpc/svcsock.c +20 -354
index 4d03e87..fbbeeae 100644
@@ -48,66 +48,24 @@
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/stats.h>
 
-/* SMP locking strategy:
- *
- *	svc_pool->sp_lock protects most of the fields of that pool.
- * 	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
- *	when both need to be taken (rare), svc_serv->sv_lock is first.
- *	BKL protects svc_serv->sv_nrthread.
- *	svc_sock->sk_lock protects the svc_sock->sk_deferred list
- *             and the ->sk_info_authunix cache.
- *	svc_sock->sk_xprt.xpt_flags.XPT_BUSY prevents a svc_sock being
- *	enqueued multiply.
- *
- *	Some flags can be set to certain values at any time
- *	providing that certain rules are followed:
- *
- *	XPT_CONN, XPT_DATA, can be set or cleared at any time.
- *		after a set, svc_xprt_enqueue must be called.
- *		after a clear, the socket must be read/accepted
- *		 if this succeeds, it must be set again.
- *	XPT_CLOSE can set at any time. It is never cleared.
- *      xpt_ref contains a bias of '1' until XPT_DEAD is set.
- *             so when xprt_ref hits zero, we know the transport is dead
- *             and no-one is using it.
- *      XPT_DEAD can only be set while XPT_BUSY is held which ensures
- *             no other thread will be using the socket or will try to
- *	       set XPT_DEAD.
- *
- */
-
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
 
 static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
 					 int *errp, int flags);
-static void		svc_delete_xprt(struct svc_xprt *xprt);
 static void		svc_udp_data_ready(struct sock *, int);
 static int		svc_udp_recvfrom(struct svc_rqst *);
 static int		svc_udp_sendto(struct svc_rqst *);
-static void		svc_close_xprt(struct svc_xprt *xprt);
 static void		svc_sock_detach(struct svc_xprt *);
 static void		svc_sock_free(struct svc_xprt *);
 
-static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
-static int svc_deferred_recv(struct svc_rqst *rqstp);
-static struct cache_deferred_req *svc_defer(struct cache_req *req);
 static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
 					  struct sockaddr *, int, int);
-static void svc_age_temp_xprts(unsigned long closure);
-
-/* apparently the "standard" is that clients close
- * idle connections after 5 minutes, servers after
- * 6 minutes
- *   http://www.connectathon.org/talks96/nfstcp.pdf
- */
-static int svc_conn_age_period = 6*60;
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key svc_key[2];
 static struct lock_class_key svc_slock_key[2];
 
-static inline void svc_reclassify_socket(struct socket *sock)
+static void svc_reclassify_socket(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	BUG_ON(sock_owned_by_user(sk));
@@ -131,67 +89,11 @@ static inline void svc_reclassify_socket(struct socket *sock)
 	}
 }
 #else
-static inline void svc_reclassify_socket(struct socket *sock)
+static void svc_reclassify_socket(struct socket *sock)
 {
 }
 #endif
 
-static char *__svc_print_addr(struct sockaddr *addr, char *buf, size_t len)
-{
-	switch (addr->sa_family) {
-	case AF_INET:
-		snprintf(buf, len, "%u.%u.%u.%u, port=%u",
-			NIPQUAD(((struct sockaddr_in *) addr)->sin_addr),
-			ntohs(((struct sockaddr_in *) addr)->sin_port));
-		break;
-
-	case AF_INET6:
-		snprintf(buf, len, "%x:%x:%x:%x:%x:%x:%x:%x, port=%u",
-			NIP6(((struct sockaddr_in6 *) addr)->sin6_addr),
-			ntohs(((struct sockaddr_in6 *) addr)->sin6_port));
-		break;
-
-	default:
-		snprintf(buf, len, "unknown address type: %d", addr->sa_family);
-		break;
-	}
-	return buf;
-}
-
-/**
- * svc_print_addr - Format rq_addr field for printing
- * @rqstp: svc_rqst struct containing address to print
- * @buf: target buffer for formatted address
- * @len: length of target buffer
- *
- */
-char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
-{
-	return __svc_print_addr(svc_addr(rqstp), buf, len);
-}
-EXPORT_SYMBOL_GPL(svc_print_addr);
-
-/*
- * Queue up an idle server thread.  Must have pool->sp_lock held.
- * Note: this is really a stack rather than a queue, so that we only
- * use as many different threads as we need, and the rest don't pollute
- * the cache.
- */
-static inline void
-svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
-	list_add(&rqstp->rq_list, &pool->sp_threads);
-}
-
-/*
- * Dequeue an nfsd thread.  Must have pool->sp_lock held.
- */
-static inline void
-svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
-	list_del(&rqstp->rq_list);
-}
-
 /*
  * Release an skbuff after use
  */
@@ -214,220 +116,6 @@ static void svc_release_skb(struct svc_rqst *rqstp)
 	}
 }
 
-/*
- * Queue up a socket with data pending. If there are idle nfsd
- * processes, wake 'em up.
- *
- */
-void svc_xprt_enqueue(struct svc_xprt *xprt)
-{
-	struct svc_serv	*serv = xprt->xpt_server;
-	struct svc_pool *pool;
-	struct svc_rqst	*rqstp;
-	int cpu;
-
-	if (!(xprt->xpt_flags &
-	      ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
-		return;
-	if (test_bit(XPT_DEAD, &xprt->xpt_flags))
-		return;
-
-	cpu = get_cpu();
-	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
-
-	spin_lock_bh(&pool->sp_lock);
-
-	if (!list_empty(&pool->sp_threads) &&
-	    !list_empty(&pool->sp_sockets))
-		printk(KERN_ERR
-		       "svc_xprt_enqueue: "
-		       "threads and transports both waiting??\n");
-
-	if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
-		/* Don't enqueue dead sockets */
-		dprintk("svc: transport %p is dead, not enqueued\n", xprt);
-		goto out_unlock;
-	}
-
-	/* Mark socket as busy. It will remain in this state until the
-	 * server has processed all pending data and put the socket back
-	 * on the idle list.  We update XPT_BUSY atomically because
-	 * it also guards against trying to enqueue the svc_sock twice.
-	 */
-	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
-		/* Don't enqueue socket while already enqueued */
-		dprintk("svc: transport %p busy, not enqueued\n", xprt);
-		goto out_unlock;
-	}
-	BUG_ON(xprt->xpt_pool != NULL);
-	xprt->xpt_pool = pool;
-
-	/* Handle pending connection */
-	if (test_bit(XPT_CONN, &xprt->xpt_flags))
-		goto process;
-
-	/* Handle close in-progress */
-	if (test_bit(XPT_CLOSE, &xprt->xpt_flags))
-		goto process;
-
-	/* Check if we have space to reply to a request */
-	if (!xprt->xpt_ops->xpo_has_wspace(xprt)) {
-		/* Don't enqueue while not enough space for reply */
-		dprintk("svc: no write space, transport %p  not enqueued\n",
-			xprt);
-		xprt->xpt_pool = NULL;
-		clear_bit(XPT_BUSY, &xprt->xpt_flags);
-		goto out_unlock;
-	}
-
- process:
-	if (!list_empty(&pool->sp_threads)) {
-		rqstp = list_entry(pool->sp_threads.next,
-				   struct svc_rqst,
-				   rq_list);
-		dprintk("svc: transport %p served by daemon %p\n",
-			xprt, rqstp);
-		svc_thread_dequeue(pool, rqstp);
-		if (rqstp->rq_xprt)
-			printk(KERN_ERR
-				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
-				rqstp, rqstp->rq_xprt);
-		rqstp->rq_xprt = xprt;
-		svc_xprt_get(xprt);
-		rqstp->rq_reserved = serv->sv_max_mesg;
-		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
-		BUG_ON(xprt->xpt_pool != pool);
-		wake_up(&rqstp->rq_wait);
-	} else {
-		dprintk("svc: transport %p put into queue\n", xprt);
-		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
-		BUG_ON(xprt->xpt_pool != pool);
-	}
-
-out_unlock:
-	spin_unlock_bh(&pool->sp_lock);
-}
-EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
-
-/*
- * Dequeue the first socket.  Must be called with the pool->sp_lock held.
- */
-static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
-{
-	struct svc_xprt	*xprt;
-
-	if (list_empty(&pool->sp_sockets))
-		return NULL;
-
-	xprt = list_entry(pool->sp_sockets.next,
-			  struct svc_xprt, xpt_ready);
-	list_del_init(&xprt->xpt_ready);
-
-	dprintk("svc: transport %p dequeued, inuse=%d\n",
-		xprt, atomic_read(&xprt->xpt_ref.refcount));
-
-	return xprt;
-}
-
-/*
- * svc_xprt_received conditionally queues the transport for processing
- * by another thread. The caller must hold the XPT_BUSY bit and must
- * not thereafter touch transport data.
- *
- * Note: XPT_DATA only gets cleared when a read-attempt finds no (or
- * insufficient) data.
- */
-void svc_xprt_received(struct svc_xprt *xprt)
-{
-	BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags));
-	xprt->xpt_pool = NULL;
-	clear_bit(XPT_BUSY, &xprt->xpt_flags);
-	svc_xprt_enqueue(xprt);
-}
-EXPORT_SYMBOL_GPL(svc_xprt_received);
-
-/**
- * svc_reserve - change the space reserved for the reply to a request.
- * @rqstp:  The request in question
- * @space: new max space to reserve
- *
- * Each request reserves some space on the output queue of the socket
- * to make sure the reply fits.  This function reduces that reserved
- * space to be the amount of space used already, plus @space.
- *
- */
-void svc_reserve(struct svc_rqst *rqstp, int space)
-{
-	space += rqstp->rq_res.head[0].iov_len;
-
-	if (space < rqstp->rq_reserved) {
-		struct svc_xprt *xprt = rqstp->rq_xprt;
-		atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
-		rqstp->rq_reserved = space;
-
-		svc_xprt_enqueue(xprt);
-	}
-}
-
-static void svc_xprt_release(struct svc_rqst *rqstp)
-{
-	struct svc_xprt	*xprt = rqstp->rq_xprt;
-
-	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
-
-	svc_free_res_pages(rqstp);
-	rqstp->rq_res.page_len = 0;
-	rqstp->rq_res.page_base = 0;
-
-	/* Reset response buffer and release
-	 * the reservation.
-	 * But first, check that enough space was reserved
-	 * for the reply, otherwise we have a bug!
-	 */
-	if ((rqstp->rq_res.len) >  rqstp->rq_reserved)
-		printk(KERN_ERR "RPC request reserved %d but used %d\n",
-		       rqstp->rq_reserved,
-		       rqstp->rq_res.len);
-
-	rqstp->rq_res.head[0].iov_len = 0;
-	svc_reserve(rqstp, 0);
-	rqstp->rq_xprt = NULL;
-
-	svc_xprt_put(xprt);
-}
-
-/*
- * External function to wake up a server waiting for data
- * This really only makes sense for services like lockd
- * which have exactly one thread anyway.
- */
-void
-svc_wake_up(struct svc_serv *serv)
-{
-	struct svc_rqst	*rqstp;
-	unsigned int i;
-	struct svc_pool *pool;
-
-	for (i = 0; i < serv->sv_nrpools; i++) {
-		pool = &serv->sv_pools[i];
-
-		spin_lock_bh(&pool->sp_lock);
-		if (!list_empty(&pool->sp_threads)) {
-			rqstp = list_entry(pool->sp_threads.next,
-					   struct svc_rqst,
-					   rq_list);
-			dprintk("svc: daemon %p woken up.\n", rqstp);
-			/*
-			svc_thread_dequeue(pool, rqstp);
-			rqstp->rq_xprt = NULL;
-			 */
-			wake_up(&rqstp->rq_wait);
-		}
-		spin_unlock_bh(&pool->sp_lock);
-	}
-}
-
 union svc_pktinfo_u {
 	struct in_pktinfo pkti;
 	struct in6_pktinfo pkti6;
@@ -469,8 +157,7 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 /*
  * Generic sendto routine
  */
-static int
-svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
+static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
 {
 	struct svc_sock	*svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
@@ -605,8 +292,7 @@ EXPORT_SYMBOL(svc_sock_names);
 /*
  * Check input queue length
  */
-static int
-svc_recv_available(struct svc_sock *svsk)
+static int svc_recv_available(struct svc_sock *svsk)
 {
 	struct socket	*sock = svsk->sk_sock;
 	int		avail, err;
@@ -619,8 +305,8 @@ svc_recv_available(struct svc_sock *svsk)
 /*
  * Generic recvfrom routine.
  */
-static int
-svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
+static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
+			int buflen)
 {
 	struct svc_sock *svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
@@ -640,8 +326,8 @@ svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
 /*
  * Set socket snd and rcv buffer lengths
  */
-static inline void
-svc_sock_setbufsize(struct socket *sock, unsigned int snd, unsigned int rcv)
+static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
+				unsigned int rcv)
 {
 #if 0
 	mm_segment_t	oldfs;
@@ -666,8 +352,7 @@ svc_sock_setbufsize(struct socket *sock, unsigned int snd, unsigned int rcv)
 /*
  * INET callback when data has been received on the socket.
  */
-static void
-svc_udp_data_ready(struct sock *sk, int count)
+static void svc_udp_data_ready(struct sock *sk, int count)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 
@@ -685,8 +370,7 @@ svc_udp_data_ready(struct sock *sk, int count)
 /*
  * INET callback when space is newly available on the socket.
  */
-static void
-svc_write_space(struct sock *sk)
+static void svc_write_space(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)(sk->sk_user_data);
 
@@ -732,8 +416,7 @@ static void svc_udp_get_dest_address(struct svc_rqst *rqstp,
 /*
  * Receive a datagram from a UDP socket.
  */
-static int
-svc_udp_recvfrom(struct svc_rqst *rqstp)
+static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 {
 	struct svc_sock	*svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
@@ -827,7 +510,8 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 		skb_free_datagram(svsk->sk_sk, skb);
 	} else {
 		/* we can use it in-place */
-		rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr);
+		rqstp->rq_arg.head[0].iov_base = skb->data +
+			sizeof(struct udphdr);
 		rqstp->rq_arg.head[0].iov_len = len;
 		if (skb_checksum_complete(skb)) {
 			skb_free_datagram(svsk->sk_sk, skb);
@@ -938,7 +622,8 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 			    3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
 			    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
 
-	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* might have come in before data_ready set up */
+	/* data might have come in before data_ready set up */
+	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 
 	oldfs = get_fs();
@@ -953,8 +638,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
  * A data_ready event on a listening socket means there's a connection
  * pending. Do not use state_change as a substitute for it.
  */
-static void
-svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
+static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 
@@ -986,8 +670,7 @@ svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
 /*
  * A state change on a connected socket means it's dying or dead.
  */
-static void
-svc_tcp_state_change(struct sock *sk)
+static void svc_tcp_state_change(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 
@@ -1004,8 +687,7 @@ svc_tcp_state_change(struct sock *sk)
 		wake_up_interruptible_all(sk->sk_sleep);
 }
 
-static void
-svc_tcp_data_ready(struct sock *sk, int count)
+static void svc_tcp_data_ready(struct sock *sk, int count)
 {
 	struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
 
@@ -1019,20 +701,6 @@ svc_tcp_data_ready(struct sock *sk, int count)
 		wake_up_interruptible(sk->sk_sleep);
 }
 
-static inline int svc_port_is_privileged(struct sockaddr *sin)
-{
-	switch (sin->sa_family) {
-	case AF_INET:
-		return ntohs(((struct sockaddr_in *)sin)->sin_port)
-			< PROT_SOCK;
-	case AF_INET6:
-		return ntohs(((struct sockaddr_in6 *)sin)->sin6_port)
-			< PROT_SOCK;
-	default:
-		return 0;
-	}
-}
-
 /*
  * Accept a TCP connection
  */
@@ -1115,8 +783,7 @@ failed:
 /*
  * Receive data from a TCP socket.
  */
-static int
-svc_tcp_recvfrom(struct svc_rqst *rqstp)
+static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 {
 	struct svc_sock	*svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
@@ -1269,8 +936,7 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
 /*
  * Send out data on TCP socket.
  */
-static int
-svc_tcp_sendto(struct svc_rqst *rqstp)
+static int svc_tcp_sendto(struct svc_rqst *rqstp)
 {
 	struct xdr_buf	*xbufp = &rqstp->rq_res;
 	int sent;

net/sunrpc/svcsock.c svc_tcp_sendto(struct svc_rqst *rqstp) · line 957

Quoted 5 lines
net/sunrpc/svcsock.c +1 -1
@@ -1288,7 +954,9 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
 
 	sent = svc_sendto(rqstp, &rqstp->rq_res);
 	if (sent != xbufp->len) {
-		printk(KERN_NOTICE "rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n",
+		printk(KERN_NOTICE 

Nit--git complained about trailing whitespace here; fixed in my version.

--b.

author
#39 lore raw

PATCH 36/40 svc: Add transport hdr size for defer/revisit

In reply to a message not in the archive

Some transports have a header in front of the RPC header. The current defer/revisit processing considers only the iov_len and arg_len to determine how much to back up when saving the original request to revisit. Add a field to the rqstp structure to save the size of the transport header so svc_defer can correctly compute the start of a request.

---

 include/linux/sunrpc/svc.h |    2 ++
 net/sunrpc/svc_xprt.c      |   36 +++++++++++++++++++++++++++---------
 net/sunrpc/svcsock.c       |    2 ++
 3 files changed, 31 insertions(+), 9 deletions(-)
include/linux/sunrpc/svc.h +2 -0
index 04eb20e..742ab46 100644
@@ -217,6 +217,7 @@ struct svc_rqst {
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
 
+	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
 	struct xdr_buf		rq_res;
 	struct page *		rq_pages[RPCSVC_MAXPAGES];
@@ -322,6 +323,7 @@ struct svc_deferred_req {
 	size_t			addrlen;
 	union svc_addr_u	daddr;	/* where reply must come from */
 	struct cache_deferred_req handle;
+	size_t			xprt_hlen;
 	int			argslen;
 	__be32			args[0];
 };
net/sunrpc/svc_xprt.c +27 -9
index 23165ae..000c7dc 100644
@@ -29,7 +29,6 @@
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svc_xprt.h>
 
@@ -859,10 +858,18 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
 	svc_xprt_put(xprt);
 }
 
+/*
+ * Save the request off for later processing. The request buffer looks
+ * like this:
+ *
+ * <xprt-header><rpc-header><rpc-pagelist><rpc-tail>
+ *
+ * This code can only handle requests that consist of an xprt-header
+ * and rpc-header.
+ */
 static struct cache_deferred_req *svc_defer(struct cache_req *req)
 {
 	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
-	int size = sizeof(struct svc_deferred_req) + (rqstp->rq_arg.len);
 	struct svc_deferred_req *dr;
 
 	if (rqstp->rq_arg.page_len)
@@ -871,8 +878,10 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 		dr = rqstp->rq_deferred;
 		rqstp->rq_deferred = NULL;
 	} else {
-		int skip  = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
+		size_t skip;
+		size_t size;
 		/* FIXME maybe discard if size too large */
+		size = sizeof(struct svc_deferred_req) + rqstp->rq_arg.len;
 		dr = kmalloc(size, GFP_KERNEL);
 		if (dr == NULL)
 			return NULL;
@@ -883,8 +892,12 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 		dr->addrlen = rqstp->rq_addrlen;
 		dr->daddr = rqstp->rq_daddr;
 		dr->argslen = rqstp->rq_arg.len >> 2;
-		memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip,
-		       dr->argslen<<2);
+		dr->xprt_hlen = rqstp->rq_xprt_hlen;
+
+		/* back up head to the start of the buffer and copy */
+		skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
+		memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip,
+		       dr->argslen << 2);
 	}
 	svc_xprt_get(rqstp->rq_xprt);
 	dr->xprt = rqstp->rq_xprt;
@@ -900,16 +913,21 @@ static int svc_deferred_recv(struct svc_rqst *rqstp)
 {
 	struct svc_deferred_req *dr = rqstp->rq_deferred;
 
-	rqstp->rq_arg.head[0].iov_base = dr->args;
-	rqstp->rq_arg.head[0].iov_len = dr->argslen<<2;
+	/* setup iov_base past transport header */
+	rqstp->rq_arg.head[0].iov_base = dr->args + (dr->xprt_hlen>>2);
+	/* The iov_len does not include the transport header bytes */
+	rqstp->rq_arg.head[0].iov_len = (dr->argslen<<2) - dr->xprt_hlen;
 	rqstp->rq_arg.page_len = 0;
-	rqstp->rq_arg.len = dr->argslen<<2;
+	/* The rq_arg.len includes the transport header bytes */
+	rqstp->rq_arg.len     = dr->argslen<<2;
 	rqstp->rq_prot        = dr->prot;
 	memcpy(&rqstp->rq_addr, &dr->addr, dr->addrlen);
 	rqstp->rq_addrlen     = dr->addrlen;
+	/* Save off transport header len in case we get deferred again */
+	rqstp->rq_xprt_hlen   = dr->xprt_hlen;
 	rqstp->rq_daddr       = dr->daddr;
 	rqstp->rq_respages    = rqstp->rq_pages;
-	return dr->argslen<<2;
+	return (dr->argslen<<2) - dr->xprt_hlen;
 }
 
 
net/sunrpc/svcsock.c +2 -0
index fbbeeae..2d24d20 100644
@@ -315,6 +315,8 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
 	};
 	int len;
 
+	rqstp->rq_xprt_hlen = 0;
+
 	len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
 				msg.msg_flags);
 
author
#40 lore raw

PATCH 37/40 svc: Add /proc/sys/sunrpc/transport files

In reply to a message not in the archive

Add a file that when read lists the set of registered svc transports.

---

 include/linux/sunrpc/svc_xprt.h |    1 +
 net/sunrpc/svc_xprt.c           |   28 ++++++++++++++++++++++++++++
 net/sunrpc/sysctl.c             |   31 +++++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+), 0 deletions(-)
include/linux/sunrpc/svc_xprt.h +1 -0
index 405281e..01e71b7 100644
@@ -79,6 +79,7 @@ void	svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt);
 void	svc_close_xprt(struct svc_xprt *xprt);
 void	svc_delete_xprt(struct svc_xprt *xprt);
 int	svc_port_is_privileged(struct sockaddr *sin);
+int	svc_print_xprts(char *buf, int maxlen);
 
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {
net/sunrpc/svc_xprt.c +28 -0
index 000c7dc..2e5b92a 100644
@@ -112,6 +112,34 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
 }
 EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
 
+/*
+ * Format the transport list for printing
+ */
+int svc_print_xprts(char *buf, int maxlen)
+{
+	struct list_head *le;
+	char tmpstr[80];
+	int len = 0;
+	buf[0] = '\0';
+
+	spin_lock(&svc_xprt_class_lock);
+	list_for_each(le, &svc_xprt_class_list) {
+		int slen;
+		struct svc_xprt_class *xcl =
+			list_entry(le, struct svc_xprt_class, xcl_list);
+
+		sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
+		slen = strlen(tmpstr);
+		if (len + slen > maxlen)
+			break;
+		len += slen;
+		strcat(buf, tmpstr);
+	}
+	spin_unlock(&svc_xprt_class_lock);
+
+	return len;
+}
+
 static void svc_xprt_free(struct kref *kref)
 {
 	struct svc_xprt *xprt =
net/sunrpc/sysctl.c +31 -0
index 2be714e..fd7cf59 100644
@@ -18,6 +18,7 @@
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/svc_xprt.h>
 
 /*
  * Declare the debug flags here
@@ -48,6 +49,30 @@ rpc_unregister_sysctl(void)
 	}
 }
 
+static int proc_do_xprt(ctl_table *table, int write, struct file *file,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	char tmpbuf[256];
+	int len;
+	if ((*ppos && !write) || !*lenp) {
+		*lenp = 0;
+		return 0;
+	}
+	if (write)
+		return -EINVAL;
+	else {
+		len = svc_print_xprts(tmpbuf, sizeof(tmpbuf));
+		if (!access_ok(VERIFY_WRITE, buffer, len))
+			return -EFAULT;
+
+		if (__copy_to_user(buffer, tmpbuf, len))
+			return -EFAULT;
+	}
+	*lenp -= len;
+	*ppos += len;
+	return 0;
+}
+
 static int
 proc_dodebug(ctl_table *table, int write, struct file *file,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -140,6 +165,12 @@ static ctl_table debug_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dodebug
 	},
+	{
+		.procname	= "transports",
+		.maxlen		= 256,
+		.mode		= 0444,
+		.proc_handler	= &proc_do_xprt,
+	},
 	{ .ctl_name = 0 }
 };
 
author
#41 lore raw

PATCH 38/40 svc: Add svc API that queries for a transport instance

In reply to a message not in the archive

Add a new svc function that allows a service to query whether a transport instance has already been created. This is used in lockd to determine whether or not a transport needs to be created when a lockd instance is brought up.

Specifying 0 for the address family or port is effectively a wild-card, and will result in matching the first transport in the service's list that has a matching class name.

---

 fs/lockd/svc.c                  |   16 ++--------------
 include/linux/sunrpc/svc_xprt.h |    1 +
 net/sunrpc/svc_xprt.c           |   35 +++++++++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+), 14 deletions(-)
fs/lockd/svc.c +2 -14
index a8e79a9..470af01 100644
@@ -219,18 +219,6 @@ lockd(struct svc_rqst *rqstp)
 	module_put_and_exit(0);
 }
 
-static int find_xprt(struct svc_serv *serv, char *proto)
-{
-	struct svc_xprt *xprt;
-	int found = 0;
-	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list)
-		if (strcmp(xprt->xpt_class->xcl_name, proto) == 0) {
-			found = 1;
-			break;
-		}
-	return found;
-}
-
 /*
  * Make any sockets that are needed but not present.
  * If nlm_udpport or nlm_tcpport were set as module
@@ -242,11 +230,11 @@ static int make_socks(struct svc_serv *serv, int proto)
 	int err = 0;
 
 	if (proto == IPPROTO_UDP || nlm_udpport)
-		if (!find_xprt(serv, "udp"))
+		if (!svc_find_xprt(serv, "udp", 0, 0))
 			err = svc_create_xprt(serv, "udp", nlm_udpport,
 					      SVC_SOCK_DEFAULTS);
 	if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport))
-		if (!find_xprt(serv, "tcp"))
+		if (!svc_find_xprt(serv, "tcp", 0, 0))
 			err = svc_create_xprt(serv, "tcp", nlm_tcpport,
 					      SVC_SOCK_DEFAULTS);
 
include/linux/sunrpc/svc_xprt.h +1 -0
index 01e71b7..68862d5 100644
@@ -80,6 +80,7 @@ void	svc_close_xprt(struct svc_xprt *xprt);
 void	svc_delete_xprt(struct svc_xprt *xprt);
 int	svc_port_is_privileged(struct sockaddr *sin);
 int	svc_print_xprts(char *buf, int maxlen);
+struct	svc_xprt *svc_find_xprt(struct svc_serv *, char *, int, int);
 
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {
net/sunrpc/svc_xprt.c +35 -0
index 2e5b92a..512c10f 100644
@@ -977,3 +977,38 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt)
 	spin_unlock(&xprt->xpt_lock);
 	return dr;
 }
+
+/*
+ * Return the transport instance pointer for the endpoint accepting
+ * connections/peer traffic from the specified transport class,
+ * address family and port.
+ *
+ * Specifying 0 for the address family or port is effectively a
+ * wild-card, and will result in matching the first transport in the
+ * service's list that has a matching class name.
+ */
+struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name,
+			       int af, int port)
+{
+	struct svc_xprt *xprt;
+	struct svc_xprt *found = NULL;
+
+	/* Sanity check the args */
+	if (!serv || !xcl_name)
+		return found;
+
+	spin_lock_bh(&serv->sv_lock);
+	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+		if (strcmp(xprt->xpt_class->xcl_name, xcl_name))
+			continue;
+		if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family)
+			continue;
+		if (port && port != svc_xprt_local_port(xprt))
+			continue;
+		found = xprt;
+		break;
+	}
+	spin_unlock_bh(&serv->sv_lock);
+	return found;
+}
+EXPORT_SYMBOL_GPL(svc_find_xprt);
author
#42 lore raw

PATCH 39/40 knfsd: Support adding transports by writing portlist file

In reply to a message not in the archive

Update the write handler for the portlist file to allow creating new listening endpoints on a transport. The general form of the string is:

<transport_name><space><port number>

For example:

echo "tcp 2049" > /proc/fs/nfsd/portlist

This is intended to support the creation of a listening endpoint for RDMA transports without adding #ifdef code to the nfssvc.c file.

Transports can also be removed as follows:

'-'<transport_name><space><port number>

For example:

echo "-tcp 2049" > /proc/fs/nfsd/portlist

Attempting to add a listener with an invalid transport string results in EPROTONOSUPPORT and a perror string of "Protocol not supported".

Attempting to remove an non-existent listener (.e.g. bad proto or port) results in ENOTCONN and a perror string of
"Transport endpoint is not connected"

---

 fs/nfsd/nfsctl.c      |   48 +++++++++++++++++++++++++++++++++++++++++++++++-
 net/sunrpc/svc_xprt.c |    1 +
 2 files changed, 48 insertions(+), 1 deletions(-)
fs/nfsd/nfsctl.c +47 -1
index 77dc989..2e4e6ff 100644
@@ -540,7 +540,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
 		}
 		return err < 0 ? err : 0;
 	}
-	if (buf[0] == '-') {
+	if (buf[0] == '-' && isdigit(buf[1])) {
 		char *toclose = kstrdup(buf+1, GFP_KERNEL);
 		int len = 0;
 		if (!toclose)
@@ -554,6 +554,52 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
 		kfree(toclose);
 		return len;
 	}
+	/*
+	 * Add a transport listener by writing it's transport name
+	 */
+	if (isalpha(buf[0])) {
+		int err;
+		char transport[16];
+		int port;
+		if (sscanf(buf, "%15s %4d", transport, &port) == 2) {
+			err = nfsd_create_serv();
+			if (!err) {
+				err = svc_create_xprt(nfsd_serv,
+						      transport, port,
+						      SVC_SOCK_ANONYMOUS);
+				if (err == -ENOENT)
+					/* Give a reasonable perror msg for
+					 * bad transport string */
+					err = -EPROTONOSUPPORT;
+			}
+			return err < 0 ? err : 0;
+		}
+	}
+	/*
+	 * Remove a transport by writing it's transport name and port number
+	 */
+	if (buf[0] == '-' && isalpha(buf[1])) {
+		struct svc_xprt *xprt;
+		int err = -EINVAL;
+		char transport[16];
+		int port;
+		if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) {
+			if (port == 0)
+				return -EINVAL;
+			lock_kernel();
+			if (nfsd_serv) {
+				xprt = svc_find_xprt(nfsd_serv, transport,
+						     AF_UNSPEC, port);
+				if (xprt) {
+					svc_close_xprt(xprt);
+					err = 0;
+				} else
+					err = -ENOTCONN;
+			}
+			unlock_kernel();
+			return err < 0 ? err : 0;
+		}
+	}
 	return -EINVAL;
 }
 
net/sunrpc/svc_xprt.c +1 -0
index 512c10f..f239928 100644
@@ -842,6 +842,7 @@ void svc_close_xprt(struct svc_xprt *xprt)
 	clear_bit(XPT_BUSY, &xprt->xpt_flags);
 	svc_xprt_put(xprt);
 }
+EXPORT_SYMBOL_GPL(svc_close_xprt);
 
 void svc_close_all(struct list_head *xprt_list)
 {
author
#43 lore raw

PATCH 40/40 svc: Add svc_xprt_names service to replace svc_sock_names

In reply to a message not in the archive

Create a transport independent version of the svc_sock_names function.

The toclose capability of the svc_sock_names service can be implemented using the svc_xprt_find and svc_xprt_close services.

---

 fs/nfsd/nfsctl.c                |    2 +-
 include/linux/sunrpc/svc_xprt.h |    1 +
 net/sunrpc/svc_xprt.c           |   35 +++++++++++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 1 deletions(-)
fs/nfsd/nfsctl.c +1 -1
index 2e4e6ff..10c13ed 100644
@@ -503,7 +503,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
 		int len = 0;
 		lock_kernel();
 		if (nfsd_serv)
-			len = svc_sock_names(buf, nfsd_serv, NULL);
+			len = svc_xprt_names(nfsd_serv, buf, 0);
 		unlock_kernel();
 		return len;
 	}
include/linux/sunrpc/svc_xprt.h +1 -0
index 68862d5..6fd7b01 100644
@@ -81,6 +81,7 @@ void	svc_delete_xprt(struct svc_xprt *xprt);
 int	svc_port_is_privileged(struct sockaddr *sin);
 int	svc_print_xprts(char *buf, int maxlen);
 struct	svc_xprt *svc_find_xprt(struct svc_serv *, char *, int, int);
+int	svc_xprt_names(struct svc_serv *serv, char *buf, int buflen);
 
 static inline void svc_xprt_get(struct svc_xprt *xprt)
 {
net/sunrpc/svc_xprt.c +35 -0
index f239928..5545c1e 100644
@@ -1013,3 +1013,38 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name,
 	return found;
 }
 EXPORT_SYMBOL_GPL(svc_find_xprt);
+
+/*
+ * Format a buffer with a list of the active transports. A zero for
+ * the buflen parameter disables target buffer overflow checking.
+ */
+int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen)
+{
+	struct svc_xprt *xprt;
+	char xprt_str[64];
+	int totlen = 0;
+	int len;
+
+	/* Sanity check args */
+	if (!serv)
+		return 0;
+
+	spin_lock_bh(&serv->sv_lock);
+	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+		len = snprintf(xprt_str, sizeof(xprt_str),
+			       "%s %d\n", xprt->xpt_class->xcl_name,
+			       svc_xprt_local_port(xprt));
+		/* If the string was truncated, replace with error string */
+		if (len >= sizeof(xprt_str))
+			strcpy(xprt_str, "name-too-long\n");
+		/* Don't overflow buffer */
+		len = strlen(xprt_str);
+		if (buflen && (len + totlen >= buflen))
+			break;
+		strcpy(buf+totlen, xprt_str);
+		totlen += len;
+	}
+	spin_unlock_bh(&serv->sv_lock);
+	return totlen;
+}
+EXPORT_SYMBOL_GPL(svc_xprt_names);
#44 lore raw
In reply to a message not in the archive
Quoted 10 lines · Tom Tucker

The Server Side Transport switch implements a pluggable transport provider layer for RPC servers. This allows network transport drivers to be dynamically loaded and registered, thereby extending the set of transports that can carry RPC. This patchset includes a transport provider driver for TCP and UDP sockets.

This version of the patchset is functionally equivalent to the preceding patchset and includes the following improvements:

Thanks! Got it.

--b.

Quoted 41 lines

- Fixed a bug in svc_create_socket that resulted in svc_xprt_received being called without holding the XPT_BUSY bit.

- Added a BUG_ON in svc_xprt_received to catch providers calling svc_xprt_received without holding the XPT_BUSY bit.

- Removed code setting the XPT_BUSY bit in the create path and moved this logic to common code.

- Cleaned up the SMP locking strategy comment and moved it to svc_xprt.c

- Changed return type of svc_unreg_xprt_class to void

- Simplified transport class removal logic

- Fixed a white-space abuse issue

- Made some style changes to the patch comments

- Created a separate patch that moves the connection limit code to generic logic

- Created a separate patch that moves the call to svc_xprt_received out of tcp_accept and into common logic

- Created a separate patch for removal of unnecessary call to svc_sock_enqueue in svc_tcp_accept function

- Removed silly BUG_ON from kref svc_xprt_free callback function

- Moved unlock of svc_xprt_class list to after the try_module_lock call.

- Refactored svc_create_xprt logic

- Removed unnecessary call to svc_find_xprt in portlist code

Signature · 1 line
Signed-off-by: Tom Tucker <[email protected]>