diff mbox series

[net-next,v5,3/3] net/smc: Introduce IPPROTO_SMC

Message ID 1717061440-59937-4-git-send-email-alibuda@linux.alibaba.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series Introduce IPPROTO_SMC | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 4984 this patch: 4984
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers success CCed 10 of 10 maintainers
netdev/build_clang success Errors and warnings before: 1011 this patch: 1011
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 5254 this patch: 5254
netdev/checkpatch warning WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: line length of 89 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns WARNING: please, no spaces at the start of a line
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-05-31--03-00 (tests: 1040)

Commit Message

D. Wythe May 30, 2024, 9:30 a.m. UTC 
From: "D. Wythe" <alibuda@linux.alibaba.com>

This patch allows to create smc socket via AF_INET,
similar to the following code,

/* create v4 smc sock */
v4 = socket(AF_INET, SOCK_STREAM, IPPROTO_SMC);

/* create v6 smc sock */
v6 = socket(AF_INET6, SOCK_STREAM, IPPROTO_SMC);

There are several reasons why we believe it is appropriate here:

1. For smc sockets, it actually use IPv4 (AF-INET) or IPv6 (AF-INET6)
address. There is no AF_SMC address at all.

2. Create smc socket in the AF_INET(6) path, which allows us to reuse
the infrastructure of AF_INET(6) path, such as common ebpf hooks.
Otherwise, smc have to implement it again in AF_SMC path.

Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
 include/uapi/linux/in.h |   2 +
 net/smc/Makefile        |   2 +-
 net/smc/af_smc.c        |  16 ++++-
 net/smc/smc_inet.c      | 170 ++++++++++++++++++++++++++++++++++++++++++++++++
 net/smc/smc_inet.h      |  22 +++++++
 5 files changed, 209 insertions(+), 3 deletions(-)
 create mode 100644 net/smc/smc_inet.c
 create mode 100644 net/smc/smc_inet.h

Comments

Ratheesh Kannoth June 3, 2024, 3:49 a.m. UTC | #1 
On 2024-05-30 at 15:00:40, D. Wythe (alibuda@linux.alibaba.com) wrote:
> From: "D. Wythe" <alibuda@linux.alibaba.com>
>
> +
> +int __init smc_inet_init(void)
> +{
> +	int rc;
> +
> +	rc = proto_register(&smc_inet_prot, 1);
> +	if (rc) {
> +		pr_err("%s: proto_register smc_inet_prot fails with %d\n", __func__, rc);
> +		return rc;
> +	}
> +	/* no return value */
> +	inet_register_protosw(&smc_inet_protosw);
> +
> +#if IS_ENABLED(CONFIG_IPV6)
> +	rc = proto_register(&smc_inet6_prot, 1);
> +	if (rc) {
> +		pr_err("%s: proto_register smc_inet6_prot fails with %d\n", __func__, rc);
> +		goto out_inet6_prot;
> +	}
> +	rc = inet6_register_protosw(&smc_inet6_protosw);
> +	if (rc) {
> +		pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n",
> +		       __func__, rc);
> +		goto out_inet6_protosw;
> +	}
> +#endif /* CONFIG_IPV6 */
> +
> +	return rc;
> +#if IS_ENABLED(CONFIG_IPV6)
Can you combine this #if with above one ? Any way you need this only in case of ipv6.
Error handling with #if is an hindrance to a good readability.

> +out_inet6_protosw:
> +	proto_unregister(&smc_inet6_prot);
> +out_inet6_prot:
> +	inet_unregister_protosw(&smc_inet_protosw);
> +	proto_unregister(&smc_inet_prot);
> +	return rc;
> +#endif /* CONFIG_IPV6 */
> +}
> +
> +void smc_inet_exit(void)
> +{
> +#if IS_ENABLED(CONFIG_IPV6)
> +	inet6_unregister_protosw(&smc_inet6_protosw);
> +	proto_unregister(&smc_inet6_prot);
> +#endif /* CONFIG_IPV6 */
> +	inet_unregister_protosw(&smc_inet_protosw);
> +	proto_unregister(&smc_inet_prot);
> +}
> diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h
> new file mode 100644
> index 00000000..a489c8a
> --- /dev/null
> +++ b/net/smc/smc_inet.h
> @@ -0,0 +1,22 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + *  Shared Memory Communications over RDMA (SMC-R) and RoCE
> + *
> + *  Definitions for the IPPROTO_SMC (socket related)
> +
> + *  Copyright IBM Corp. 2016
> + *  Copyright (c) 2024, Alibaba Inc.
> + *
> + *  Author: D. Wythe <alibuda@linux.alibaba.com>
> + */
> +#ifndef __INET_SMC
> +#define __INET_SMC
> +
> +/* Initialize protocol registration on IPPROTO_SMC,
> + * @return 0 on success
> + */
> +int smc_inet_init(void);
> +
> +void smc_inet_exit(void);
> +
> +#endif /* __INET_SMC */
> --
> 1.8.3.1
>
D. Wythe June 3, 2024, 2:43 p.m. UTC | #2 
On 6/3/24 11:49 AM, Ratheesh Kannoth wrote:
> On 2024-05-30 at 15:00:40, D. Wythe (alibuda@linux.alibaba.com) wrote:
>> From: "D. Wythe" <alibuda@linux.alibaba.com>
>>
>> +
>> +int __init smc_inet_init(void)
>> +{
>> +	int rc;
>> +
>> +	rc = proto_register(&smc_inet_prot, 1);
>> +	if (rc) {
>> +		pr_err("%s: proto_register smc_inet_prot fails with %d\n", __func__, rc);
>> +		return rc;
>> +	}
>> +	/* no return value */
>> +	inet_register_protosw(&smc_inet_protosw);
>> +
>> +#if IS_ENABLED(CONFIG_IPV6)
>> +	rc = proto_register(&smc_inet6_prot, 1);
>> +	if (rc) {
>> +		pr_err("%s: proto_register smc_inet6_prot fails with %d\n", __func__, rc);
>> +		goto out_inet6_prot;
>> +	}
>> +	rc = inet6_register_protosw(&smc_inet6_protosw);
>> +	if (rc) {
>> +		pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n",
>> +		       __func__, rc);
>> +		goto out_inet6_protosw;
>> +	}
>> +#endif /* CONFIG_IPV6 */
>> +
>> +	return rc;
>> +#if IS_ENABLED(CONFIG_IPV6)
> Can you combine this #if with above one ? Any way you need this only in case of ipv6.
> Error handling with #if is an hindrance to a good readability.

Hi Ratheesh,

Thanks for your advice. Totally agreed with that.
I'll give it a fix in next version.

Best wishes,
D. Wythe

>> +out_inet6_protosw:
>> +	proto_unregister(&smc_inet6_prot);
>> +out_inet6_prot:
>> +	inet_unregister_protosw(&smc_inet_protosw);
>> +	proto_unregister(&smc_inet_prot);
>> +	return rc;
>> +#endif /* CONFIG_IPV6 */
>> +}
>> +
>> +void smc_inet_exit(void)
>> +{
>> +#if IS_ENABLED(CONFIG_IPV6)
>> +	inet6_unregister_protosw(&smc_inet6_protosw);
>> +	proto_unregister(&smc_inet6_prot);
>> +#endif /* CONFIG_IPV6 */
>> +	inet_unregister_protosw(&smc_inet_protosw);
>> +	proto_unregister(&smc_inet_prot);
>> +}
>> diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h
>> new file mode 100644
>> index 00000000..a489c8a
>> --- /dev/null
>> +++ b/net/smc/smc_inet.h
>> @@ -0,0 +1,22 @@
>> +/* SPDX-License-Identifier: GPL-2.0 */
>> +/*
>> + *  Shared Memory Communications over RDMA (SMC-R) and RoCE
>> + *
>> + *  Definitions for the IPPROTO_SMC (socket related)
>> +
>> + *  Copyright IBM Corp. 2016
>> + *  Copyright (c) 2024, Alibaba Inc.
>> + *
>> + *  Author: D. Wythe <alibuda@linux.alibaba.com>
>> + */
>> +#ifndef __INET_SMC
>> +#define __INET_SMC
>> +
>> +/* Initialize protocol registration on IPPROTO_SMC,
>> + * @return 0 on success
>> + */
>> +int smc_inet_init(void);
>> +
>> +void smc_inet_exit(void);
>> +
>> +#endif /* __INET_SMC */
>> --
>> 1.8.3.1
>>
diff mbox series

Patch

diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index e682ab6..0c6322b 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -83,6 +83,8 @@  enum {
 #define IPPROTO_RAW		IPPROTO_RAW
   IPPROTO_MPTCP = 262,		/* Multipath TCP connection		*/
 #define IPPROTO_MPTCP		IPPROTO_MPTCP
+  IPPROTO_SMC = 263,		/* Shared Memory Communications		*/
+#define IPPROTO_SMC		IPPROTO_SMC
   IPPROTO_MAX
 };
 #endif
diff --git a/net/smc/Makefile b/net/smc/Makefile
index 2c510d54..60f1c87 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -4,6 +4,6 @@  obj-$(CONFIG_SMC)	+= smc.o
 obj-$(CONFIG_SMC_DIAG)	+= smc_diag.o
 smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
 smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o
-smc-y += smc_tracepoint.o
+smc-y += smc_tracepoint.o smc_inet.o
 smc-$(CONFIG_SYSCTL) += smc_sysctl.o
 smc-$(CONFIG_SMC_LO) += smc_loopback.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8e3ce76..743c27e 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -54,6 +54,7 @@ 
 #include "smc_tracepoint.h"
 #include "smc_sysctl.h"
 #include "smc_loopback.h"
+#include "smc_inet.h"
 
 static DEFINE_MUTEX(smc_server_lgr_pending);	/* serialize link group
 						 * creation on server
@@ -3593,10 +3594,15 @@  static int __init smc_init(void)
 		pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc);
 		goto out_lo;
 	}
-
+	rc = smc_inet_init();
+	if (rc) {
+		pr_err("%s: smc_inet_init fails with %d\n", __func__, rc);
+		goto out_ulp;
+	}
 	static_branch_enable(&tcp_have_smc);
 	return 0;
-
+out_ulp:
+	tcp_unregister_ulp(&smc_ulp_ops);
 out_lo:
 	smc_loopback_exit();
 out_ib:
@@ -3633,6 +3639,7 @@  static int __init smc_init(void)
 static void __exit smc_exit(void)
 {
 	static_branch_disable(&tcp_have_smc);
+	smc_inet_exit();
 	tcp_unregister_ulp(&smc_ulp_ops);
 	sock_unregister(PF_SMC);
 	smc_core_exit();
@@ -3660,4 +3667,9 @@  static void __exit smc_exit(void)
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_SMC);
 MODULE_ALIAS_TCP_ULP("smc");
+/* 263 for IPPROTO_SMC and 1 for SOCK_STREAM */
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 263, 1);
+#if IS_ENABLED(CONFIG_IPV6)
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 263, 1);
+#endif /* CONFIG_IPV6 */
 MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME);
diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c
new file mode 100644
index 00000000..72e4f61
--- /dev/null
+++ b/net/smc/smc_inet.c
@@ -0,0 +1,170 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for the IPPROTO_SMC (socket related)
+ *
+ *  Copyright IBM Corp. 2016, 2018
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: D. Wythe <alibuda@linux.alibaba.com>
+ */
+
+#include <net/protocol.h>
+#include <net/sock.h>
+
+#include "smc_inet.h"
+#include "smc.h"
+
+static struct proto smc_inet_prot;
+static const struct proto_ops smc_inet_stream_ops;
+static struct inet_protosw smc_inet_protosw;
+
+#if IS_ENABLED(CONFIG_IPV6)
+static struct proto smc_inet6_prot;
+static const struct proto_ops smc_inet6_stream_ops;
+static struct inet_protosw smc_inet6_protosw;
+#endif /* CONFIG_IPV6 */
+
+static int smc_inet_init_sock(struct sock *sk);
+
+static struct proto smc_inet_prot = {
+	.name		= "INET_SMC",
+	.owner		= THIS_MODULE,
+	.init		= smc_inet_init_sock,
+	.hash		= smc_hash_sk,
+	.unhash		= smc_unhash_sk,
+	.release_cb	= smc_release_cb,
+	.obj_size	= sizeof(struct smc_sock),
+	.h.smc_hash	= &smc_v4_hashinfo,
+	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
+};
+
+static const struct proto_ops smc_inet_stream_ops = {
+	.family		= PF_INET,
+	.owner		= THIS_MODULE,
+	.release	= smc_release,
+	.bind		= smc_bind,
+	.connect	= smc_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= smc_accept,
+	.getname	= smc_getname,
+	.poll		= smc_poll,
+	.ioctl		= smc_ioctl,
+	.listen		= smc_listen,
+	.shutdown	= smc_shutdown,
+	.setsockopt	= smc_setsockopt,
+	.getsockopt	= smc_getsockopt,
+	.sendmsg	= smc_sendmsg,
+	.recvmsg	= smc_recvmsg,
+	.mmap		= sock_no_mmap,
+	.splice_read	= smc_splice_read,
+};
+
+static struct inet_protosw smc_inet_protosw = {
+	.type		= SOCK_STREAM,
+	.protocol	= IPPROTO_SMC,
+	.prot		= &smc_inet_prot,
+	.ops		= &smc_inet_stream_ops,
+	.flags		= INET_PROTOSW_ICSK,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static struct proto smc_inet6_prot = {
+	.name		= "INET6_SMC",
+	.owner		= THIS_MODULE,
+	.init		= smc_inet_init_sock,
+	.hash		= smc_hash_sk,
+	.unhash		= smc_unhash_sk,
+	.release_cb	= smc_release_cb,
+	.obj_size	= sizeof(struct smc_sock),
+	.h.smc_hash	= &smc_v6_hashinfo,
+	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
+};
+
+static const struct proto_ops smc_inet6_stream_ops = {
+	.family		= PF_INET6,
+	.owner		= THIS_MODULE,
+	.release	= smc_release,
+	.bind		= smc_bind,
+	.connect	= smc_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= smc_accept,
+	.getname	= smc_getname,
+	.poll		= smc_poll,
+	.ioctl		= smc_ioctl,
+	.listen		= smc_listen,
+	.shutdown	= smc_shutdown,
+	.setsockopt	= smc_setsockopt,
+	.getsockopt	= smc_getsockopt,
+	.sendmsg	= smc_sendmsg,
+	.recvmsg	= smc_recvmsg,
+	.mmap		= sock_no_mmap,
+	.splice_read	= smc_splice_read,
+};
+
+static struct inet_protosw smc_inet6_protosw = {
+	.type		= SOCK_STREAM,
+	.protocol	= IPPROTO_SMC,
+	.prot		= &smc_inet6_prot,
+	.ops		= &smc_inet6_stream_ops,
+	.flags		= INET_PROTOSW_ICSK,
+};
+#endif /* CONFIG_IPV6 */
+
+static int smc_inet_init_sock(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	/* init common smc sock */
+	smc_sk_init(net, sk, IPPROTO_SMC);
+	/* create clcsock */
+	return smc_create_clcsk(net, sk, sk->sk_family);
+}
+
+int __init smc_inet_init(void)
+{
+	int rc;
+
+	rc = proto_register(&smc_inet_prot, 1);
+	if (rc) {
+		pr_err("%s: proto_register smc_inet_prot fails with %d\n", __func__, rc);
+		return rc;
+	}
+	/* no return value */
+	inet_register_protosw(&smc_inet_protosw);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	rc = proto_register(&smc_inet6_prot, 1);
+	if (rc) {
+		pr_err("%s: proto_register smc_inet6_prot fails with %d\n", __func__, rc);
+		goto out_inet6_prot;
+	}
+	rc = inet6_register_protosw(&smc_inet6_protosw);
+	if (rc) {
+		pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n",
+		       __func__, rc);
+		goto out_inet6_protosw;
+	}
+#endif /* CONFIG_IPV6 */
+
+	return rc;
+#if IS_ENABLED(CONFIG_IPV6)
+out_inet6_protosw:
+	proto_unregister(&smc_inet6_prot);
+out_inet6_prot:
+	inet_unregister_protosw(&smc_inet_protosw);
+	proto_unregister(&smc_inet_prot);
+	return rc;
+#endif /* CONFIG_IPV6 */
+}
+
+void smc_inet_exit(void)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	inet6_unregister_protosw(&smc_inet6_protosw);
+	proto_unregister(&smc_inet6_prot);
+#endif /* CONFIG_IPV6 */
+	inet_unregister_protosw(&smc_inet_protosw);
+	proto_unregister(&smc_inet_prot);
+}
diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h
new file mode 100644
index 00000000..a489c8a
--- /dev/null
+++ b/net/smc/smc_inet.h
@@ -0,0 +1,22 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for the IPPROTO_SMC (socket related)
+
+ *  Copyright IBM Corp. 2016
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: D. Wythe <alibuda@linux.alibaba.com>
+ */
+#ifndef __INET_SMC
+#define __INET_SMC
+
+/* Initialize protocol registration on IPPROTO_SMC,
+ * @return 0 on success
+ */
+int smc_inet_init(void);
+
+void smc_inet_exit(void);
+
+#endif /* __INET_SMC */