net/smc: Introduce smc_ops

include/net/netns/smc.h

@@ -17,6 +17,9 @@ struct netns_smc {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header		*smc_hdr;
 #endif
+#if IS_ENABLED(CONFIG_SMC_OPS)
+	struct smc_ops __rcu *ops;
+#endif /* CONFIG_SMC_OPS */
 	unsigned int			sysctl_autocorking_size;
 	unsigned int			sysctl_smcr_buf_type;
 	int				sysctl_smcr_testlink_time;

include/net/smc.h

@@ -18,6 +18,8 @@
 #include "linux/ism.h"
 
 struct sock;
+struct tcp_sock;
+struct inet_request_sock;
 
 #define SMC_MAX_PNETID_LEN	16	/* Max. length of PNET id */
 
@@ -97,4 +99,53 @@ struct smcd_dev {
 	u8 going_away : 1;
 };
 
+#define  SMC_OPS_NAME_MAX 16
+
+enum {
+	/* ops can be inherit from init_net */
+	SMC_OPS_FLAG_INHERITABLE = 0x1,
+
+	SMC_OPS_ALL_FLAGS = SMC_OPS_FLAG_INHERITABLE,
+};
+
+struct smc_ops {
+	/* priavte */
+
+	struct list_head list;
+	struct module *owner;
+
+	/* public */
+
+	/* unique name */
+	char name[SMC_OPS_NAME_MAX];
+	int flags;
+
+	/* Invoked before computing SMC option for SYN packets.
+	 * We can control whether to set SMC options by returning varios value.
+	 * Return 0 to disable SMC, or return any other value to enable it.
+	 */
+	int (*set_option)(struct tcp_sock *tp);
+
+	/* Invoked before Set up SMC options for SYN-ACK packets
+	 * We can control whether to respond SMC options by returning varios value.
+	 * Return 0 to disable SMC, or return any other value to enable it.
+	 */
+	int (*set_option_cond)(const struct tcp_sock *tp, struct inet_request_sock *ireq);
+};
+
+#if IS_ENABLED(CONFIG_SMC_OPS)
+#define smc_call_retops(init_val, sk, func, ...) ({	\
+	typeof(init_val) __ret = (init_val);		\
+	struct smc_ops *ops;				\
+	rcu_read_lock();				\
+	ops = READ_ONCE(sock_net(sk)->smc.ops);		\
+	if (ops && ops->func)				\
+		__ret = ops->func(__VA_ARGS__);		\
+	rcu_read_unlock();				\
+	!!__ret;					\
+})
+#else
+#define smc_call_retops(init_val, ...) (init_val)
+#endif /* CONFIG_SMC_OPS */
+
 #endif	/* _SMC_H */

kernel/bpf/bpf_struct_ops.c

@@ -1140,6 +1140,7 @@ bool bpf_struct_ops_get(const void *kdata)
 	map = __bpf_map_inc_not_zero(&st_map->map, false);
 	return !IS_ERR(map);
 }
+EXPORT_SYMBOL_GPL(bpf_struct_ops_get);
 
 void bpf_struct_ops_put(const void *kdata)
 {
@@ -1151,6 +1152,7 @@ void bpf_struct_ops_put(const void *kdata)
 
 	bpf_map_put(&st_map->map);
 }
+EXPORT_SYMBOL_GPL(bpf_struct_ops_put);
 
 int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff)
 {

kernel/bpf/syscall.c

@@ -1167,6 +1167,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size)
 
 	return src - orig_src;
 }
+EXPORT_SYMBOL_GPL(bpf_obj_name_cpy);
 
 int map_check_no_btf(const struct bpf_map *map,
 		     const struct btf *btf,

net/ipv4/tcp_output.c

@@ -48,6 +48,7 @@
 #include <linux/skbuff_ref.h>
 
 #include <trace/events/tcp.h>
+#include <net/smc.h>
 
 /* Refresh clocks of a TCP socket,
  * ensuring monotically increasing values.
@@ -759,14 +760,17 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 	mptcp_options_write(th, ptr, tp, opts);
 }
 
-static void smc_set_option(const struct tcp_sock *tp,
+static void smc_set_option(struct tcp_sock *tp,
 			   struct tcp_out_options *opts,
 			   unsigned int *remaining)
 {
 #if IS_ENABLED(CONFIG_SMC)
 	if (static_branch_unlikely(&tcp_have_smc)) {
 		if (tp->syn_smc) {
-			if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+			tp->syn_smc = smc_call_retops(1, &tp->inet_conn.icsk_inet.sk,
+						      set_option, tp);
+			/* re-check syn_smc */
+			if (tp->syn_smc && *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
 				opts->options |= OPTION_SMC;
 				*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
 			}
@@ -776,14 +780,17 @@ static void smc_set_option(const struct tcp_sock *tp,
 }
 
 static void smc_set_option_cond(const struct tcp_sock *tp,
-				const struct inet_request_sock *ireq,
+				struct inet_request_sock *ireq,
 				struct tcp_out_options *opts,
 				unsigned int *remaining)
 {
 #if IS_ENABLED(CONFIG_SMC)
 	if (static_branch_unlikely(&tcp_have_smc)) {
 		if (tp->syn_smc && ireq->smc_ok) {
-			if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+			ireq->smc_ok = smc_call_retops(1, &tp->inet_conn.icsk_inet.sk,
+						       set_option_cond, tp, ireq);
+			/* re-check smc_ok */
+			if (ireq->smc_ok && *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
 				opts->options |= OPTION_SMC;
 				*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
 			}

net/smc/Kconfig

@@ -33,3 +33,15 @@ config SMC_LO
 	  of architecture or hardware.
 
 	  if unsure, say N.
+
+config SMC_OPS
+	bool "Generic hook for SMC subsystem"
+	depends on SMC && BPF_SYSCALL
+	default n
+	help
+	  SMC_OPS enables support to register genericfor hook via eBPF programs
+	  for SMC subsystem. eBPF programs offer much greater flexibility
+	  in modifying the behavior of the SMC protocol stack compared
+	  to a complete kernel-based approach.
+
+	  if unsure, say N.

net/smc/Makefile

@@ -7,3 +7,4 @@ smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_sta
 smc-y += smc_tracepoint.o smc_inet.o
 smc-$(CONFIG_SYSCTL) += smc_sysctl.o
 smc-$(CONFIG_SMC_LO) += smc_loopback.o
+smc-$(CONFIG_SMC_OPS) += smc_ops.o

net/smc/af_smc.c

@@ -55,6 +55,7 @@
 #include "smc_sysctl.h"
 #include "smc_loopback.h"
 #include "smc_inet.h"
+#include "smc_ops.h"
 
 static DEFINE_MUTEX(smc_server_lgr_pending);	/* serialize link group
 						 * creation on server
@@ -3576,8 +3577,17 @@ static int __init smc_init(void)
 		pr_err("%s: smc_inet_init fails with %d\n", __func__, rc);
 		goto out_ulp;
 	}
+
+	rc = smc_bpf_struct_ops_init();
+	if (rc) {
+		pr_err("%s: smc_bpf_struct_ops_init fails with %d\n", __func__, rc);
+		goto out_inet;
+	}
+
 	static_branch_enable(&tcp_have_smc);
 	return 0;
+out_inet:
+	smc_inet_exit();
 out_ulp:
 	tcp_unregister_ulp(&smc_ulp_ops);
 out_lo:

net/smc/smc_ops.c

@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Generic hook for SMC subsystem.
+ *
+ *  Copyright IBM Corp. 2016
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: D. Wythe <[email protected]>
+ */
+
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+
+#include "smc_ops.h"
+
+static DEFINE_SPINLOCK(smc_ops_list_lock);
+static LIST_HEAD(smc_ops_list);
+
+static int smc_ops_reg(struct smc_ops *ops)
+{
+	int ret = 0;
+
+	spin_lock(&smc_ops_list_lock);
+	/* already exist or duplicate name */
+	if (smc_ops_find_by_name(ops->name))
+		ret = -EEXIST;
+	else
+		list_add_tail_rcu(&ops->list, &smc_ops_list);
+	spin_unlock(&smc_ops_list_lock);
+	return ret;
+}
+
+static void smc_ops_unreg(struct smc_ops *ops)
+{
+	spin_lock(&smc_ops_list_lock);
+	list_del_rcu(&ops->list);
+	spin_unlock(&smc_ops_list_lock);
+
+	/* Ensure that all readers to complete */
+	synchronize_rcu();
+}
+
+struct smc_ops *smc_ops_find_by_name(const char *name)
+{
+	struct smc_ops *ops;
+
+	list_for_each_entry_rcu(ops, &smc_ops_list, list) {
+		if (strcmp(ops->name, name) == 0)
+			return ops;
+	}
+	return NULL;
+}
+
+static int __bpf_smc_stub_set_tcp_option(struct tcp_sock *tp) { return 1; }
+static int __bpf_smc_stub_set_tcp_option_cond(const struct tcp_sock *tp,
+					      struct inet_request_sock *ireq)
+{
+	return 1;
+}
+
+static struct smc_ops __bpf_smc_bpf_ops = {
+	.set_option		= __bpf_smc_stub_set_tcp_option,
+	.set_option_cond	= __bpf_smc_stub_set_tcp_option_cond,
+};
+
+static int smc_bpf_ops_init(struct btf *btf) { return 0; }
+
+static int smc_bpf_ops_reg(void *kdata, struct bpf_link *link)
+{
+	return smc_ops_reg(kdata);
+}
+
+static void smc_bpf_ops_unreg(void *kdata, struct bpf_link *link)
+{
+	smc_ops_unreg(kdata);
+}
+
+static int smc_bpf_ops_init_member(const struct btf_type *t,
+				   const struct btf_member *member,
+				   void *kdata, const void *udata)
+{
+	const struct smc_ops *u_ops;
+	struct smc_ops *k_ops;
+	u32 moff;
+
+	u_ops = (const struct smc_ops *)udata;
+	k_ops = (struct smc_ops *)kdata;
+
+	moff = __btf_member_bit_offset(t, member) / 8;
+	switch (moff) {
+	case offsetof(struct smc_ops, name):
+		if (bpf_obj_name_cpy(k_ops->name, u_ops->name,
+				     sizeof(u_ops->name)) <= 0)
+			return -EINVAL;
+		return 1;
+	case offsetof(struct smc_ops, flags):
+		if (u_ops->flags & ~SMC_OPS_ALL_FLAGS)
+			return -EINVAL;
+		k_ops->flags = u_ops->flags;
+		return 1;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct bpf_verifier_ops smc_bpf_verifier_ops = {
+	.get_func_proto		= bpf_base_func_proto,
+	.is_valid_access	= bpf_tracing_btf_ctx_access,
+};
+
+static struct bpf_struct_ops bpf_smc_bpf_ops = {
+	.name		= "smc_ops",
+	.init		= smc_bpf_ops_init,
+	.reg		= smc_bpf_ops_reg,
+	.unreg		= smc_bpf_ops_unreg,
+	.cfi_stubs	= &__bpf_smc_bpf_ops,
+	.verifier_ops	= &smc_bpf_verifier_ops,
+	.init_member	= smc_bpf_ops_init_member,
+	.owner		= THIS_MODULE,
+};
+
+int smc_bpf_struct_ops_init(void)
+{
+	return register_bpf_struct_ops(&bpf_smc_bpf_ops, smc_ops);
+}

net/smc/smc_ops.h

@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Generic hook for SMC subsystem.
+ *
+ *  Copyright IBM Corp. 2016
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: D. Wythe <[email protected]>
+ */
+
+#ifndef __SMC_OPS
+#define __SMC_OPS
+
+#include <net/smc.h>
+
+/* Find ops by the target name, which required to be a c-string.
+ * Return NULL if no such ops was found,otherwise, return a valid ops.
+ *
+ * Note: Caller MUST ensure it's was invoked under rcu_read_lock.
+ */
+struct smc_ops *smc_ops_find_by_name(const char *name);
+#if IS_ENABLED(CONFIG_SMC_OPS)
+int smc_bpf_struct_ops_init(void);
+#else
+static inline int smc_bpf_struct_ops_init(void) { return 0; }
+#endif
+
+#endif /* __SMC_OPS */