bpf: Create links for BPF struct_ops maps.

Make bpf_link support struct_ops.  Previously, struct_ops were always
used alone without any associated links. Upon updating its value, a
struct_ops would be activated automatically. Yet other BPF program
types required to make a bpf_link with their instances before they
could become active. Now, however, you can create an inactive
struct_ops, and create a link to activate it later.

With bpf_links, struct_ops has a behavior similar to other BPF program
types. You can pin/unpin them from their links and the struct_ops will
be deactivated when its link is removed while previously need someone
to delete the value for it to be deactivated.

bpf_links are responsible for registering their associated
struct_ops. You can only use a struct_ops that has the BPF_F_LINK flag
set to create a bpf_link, while a structs without this flag behaves in
the same manner as before and is registered upon updating its value.

The BPF_LINK_TYPE_STRUCT_OPS serves a dual purpose. Not only is it
used to craft the links for BPF struct_ops programs, but also to
create links for BPF struct_ops them-self.  Since the links of BPF
struct_ops programs are only used to create trampolines internally,
they are never seen in other contexts. Thus, they can be reused for
struct_ops themself.

To maintain a reference to the map supporting this link, we add
bpf_struct_ops_link as an additional type. The pointer of the map is
RCU and won't be necessary until later in the patchset.

Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
Link: https://lore.kernel.org/r/20230323032405.3735486-4-kuifeng@meta.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

6 files changed, 190 insertions, 15 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f04098468d7a..8552279efe46 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1518,6 +1518,7 @@ struct bpf_struct_ops {
 			   void *kdata, const void *udata);
 	int (*reg)(void *kdata);
 	void (*unreg)(void *kdata);
+	int (*validate)(void *kdata);
 	const struct btf_type *type;
 	const struct btf_type *value_type;
 	const char *name;
@@ -1552,6 +1553,7 @@ static inline void bpf_module_put(const void *data, struct module *owner)
 	else
 		module_put(owner);
 }
+int bpf_struct_ops_link_create(union bpf_attr *attr);
 
 #ifdef CONFIG_NET
 /* Define it here to avoid the use of forward declaration */
@@ -1592,6 +1594,11 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
 {
 	return -EINVAL;
 }
+static inline int bpf_struct_ops_link_create(union bpf_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 13129df937cd..42f40ee083bf 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1033,6 +1033,7 @@ enum bpf_attach_type {
 	BPF_PERF_EVENT,
 	BPF_TRACE_KPROBE_MULTI,
 	BPF_LSM_CGROUP,
+	BPF_STRUCT_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1266,6 +1267,9 @@ enum {
 
 /* Create a map that is suitable to be an inner map with dynamic max entries */
 	BPF_F_INNER_MAP		= (1U << 12),
+
+/* Create a map that will be registered/unregesitered by the backed bpf_link */
+	BPF_F_LINK		= (1U << 13),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1507,7 +1511,10 @@ union bpf_attr {
 	} task_fd_query;
 
 	struct { /* struct used by BPF_LINK_CREATE command */
-		__u32		prog_fd;	/* eBPF program to attach */
+		union {
+			__u32		prog_fd;	/* eBPF program to attach */
+			__u32		map_fd;		/* struct_ops to attach */
+		};
 		union {
 			__u32		target_fd;	/* object to attach to */
 			__u32		target_ifindex; /* target ifindex */
@@ -6379,6 +6386,9 @@ struct bpf_link_info {
 		struct {
 			__u32 ifindex;
 		} xdp;
+		struct {
+			__u32 map_id;
+		} struct_ops;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 2f3c4a0e03ee..3d6b5240c25a 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -17,6 +17,7 @@ enum bpf_struct_ops_state {
 	BPF_STRUCT_OPS_STATE_INIT,
 	BPF_STRUCT_OPS_STATE_INUSE,
 	BPF_STRUCT_OPS_STATE_TOBEFREE,
+	BPF_STRUCT_OPS_STATE_READY,
 };
 
 #define BPF_STRUCT_OPS_COMMON_VALUE			\
@@ -59,6 +60,11 @@ struct bpf_struct_ops_map {
 	struct bpf_struct_ops_value kvalue;
 };
 
+struct bpf_struct_ops_link {
+	struct bpf_link link;
+	struct bpf_map __rcu *map;
+};
+
 #define VALUE_PREFIX "bpf_struct_ops_"
 #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1)
 
@@ -500,11 +506,29 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		*(unsigned long *)(udata + moff) = prog->aux->id;
 	}
 
-	bpf_map_inc(map);
+	if (st_map->map.map_flags & BPF_F_LINK) {
+		err = st_ops->validate(kdata);
+		if (err)
+			goto reset_unlock;
+		set_memory_rox((long)st_map->image, 1);
+		/* Let bpf_link handle registration & unregistration.
+		 *
+		 * Pair with smp_load_acquire() during lookup_elem().
+		 */
+		smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY);
+		goto unlock;
+	}
 
 	set_memory_rox((long)st_map->image, 1);
 	err = st_ops->reg(kdata);
 	if (likely(!err)) {
+		/* This refcnt increment on the map here after
+		 * 'st_ops->reg()' is secure since the state of the
+		 * map must be set to INIT at this moment, and thus
+		 * bpf_struct_ops_map_delete_elem() can't unregister
+		 * or transition it to TOBEFREE concurrently.
+		 */
+		bpf_map_inc(map);
 		/* Pair with smp_load_acquire() during lookup_elem().
 		 * It ensures the above udata updates (e.g. prog->aux->id)
 		 * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set.
@@ -520,7 +544,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	 */
 	set_memory_nx((long)st_map->image, 1);
 	set_memory_rw((long)st_map->image, 1);
-	bpf_map_put(map);
 
 reset_unlock:
 	bpf_struct_ops_map_put_progs(st_map);
@@ -538,6 +561,9 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
 	struct bpf_struct_ops_map *st_map;
 
 	st_map = (struct bpf_struct_ops_map *)map;
+	if (st_map->map.map_flags & BPF_F_LINK)
+		return -EOPNOTSUPP;
+
 	prev_state = cmpxchg(&st_map->kvalue.state,
 			     BPF_STRUCT_OPS_STATE_INUSE,
 			     BPF_STRUCT_OPS_STATE_TOBEFREE);
@@ -614,7 +640,7 @@ static void bpf_struct_ops_map_free(struct bpf_map *map)
 static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
 {
 	if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 ||
-	    attr->map_flags || !attr->btf_vmlinux_value_type_id)
+	    (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id)
 		return -EINVAL;
 	return 0;
 }
@@ -638,6 +664,9 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	if (attr->value_size != vt->size)
 		return ERR_PTR(-EINVAL);
 
+	if (attr->map_flags & BPF_F_LINK && !st_ops->validate)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	t = st_ops->type;
 
 	st_map_size = sizeof(*st_map) +
@@ -725,3 +754,111 @@ void bpf_struct_ops_put(const void *kdata)
 
 	bpf_map_put(&st_map->map);
 }
+
+static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map)
+{
+	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+
+	return map->map_type == BPF_MAP_TYPE_STRUCT_OPS &&
+		map->map_flags & BPF_F_LINK &&
+		/* Pair with smp_store_release() during map_update */
+		smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY;
+}
+
+static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_struct_ops_link *st_link;
+	struct bpf_struct_ops_map *st_map;
+
+	st_link = container_of(link, struct bpf_struct_ops_link, link);
+	st_map = (struct bpf_struct_ops_map *)
+		rcu_dereference_protected(st_link->map, true);
+	if (st_map) {
+		/* st_link->map can be NULL if
+		 * bpf_struct_ops_link_create() fails to register.
+		 */
+		st_map->st_ops->unreg(&st_map->kvalue.data);
+		bpf_map_put(&st_map->map);
+	}
+	kfree(st_link);
+}
+
+static void bpf_struct_ops_map_link_show_fdinfo(const struct bpf_link *link,
+					    struct seq_file *seq)
+{
+	struct bpf_struct_ops_link *st_link;
+	struct bpf_map *map;
+
+	st_link = container_of(link, struct bpf_struct_ops_link, link);
+	rcu_read_lock();
+	map = rcu_dereference(st_link->map);
+	seq_printf(seq, "map_id:\t%d\n", map->id);
+	rcu_read_unlock();
+}
+
+static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
+					       struct bpf_link_info *info)
+{
+	struct bpf_struct_ops_link *st_link;
+	struct bpf_map *map;
+
+	st_link = container_of(link, struct bpf_struct_ops_link, link);
+	rcu_read_lock();
+	map = rcu_dereference(st_link->map);
+	info->struct_ops.map_id = map->id;
+	rcu_read_unlock();
+	return 0;
+}
+
+static const struct bpf_link_ops bpf_struct_ops_map_lops = {
+	.dealloc = bpf_struct_ops_map_link_dealloc,
+	.show_fdinfo = bpf_struct_ops_map_link_show_fdinfo,
+	.fill_link_info = bpf_struct_ops_map_link_fill_link_info,
+};
+
+int bpf_struct_ops_link_create(union bpf_attr *attr)
+{
+	struct bpf_struct_ops_link *link = NULL;
+	struct bpf_link_primer link_primer;
+	struct bpf_struct_ops_map *st_map;
+	struct bpf_map *map;
+	int err;
+
+	map = bpf_map_get(attr->link_create.map_fd);
+	if (!map)
+		return -EINVAL;
+
+	st_map = (struct bpf_struct_ops_map *)map;
+
+	if (!bpf_struct_ops_valid_to_reg(map)) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL);
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto err_out;
+
+	err = st_map->st_ops->reg(st_map->kvalue.data);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		link = NULL;
+		goto err_out;
+	}
+	RCU_INIT_POINTER(link->map, map);
+
+	return bpf_link_settle(&link_primer);
+
+err_out:
+	bpf_map_put(map);
+	kfree(link);
+	return err;
+}
+
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cff0348a2871..21f76698875c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2825,16 +2825,19 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 	const struct bpf_prog *prog = link->prog;
 	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
 
-	bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
 	seq_printf(m,
 		   "link_type:\t%s\n"
-		   "link_id:\t%u\n"
-		   "prog_tag:\t%s\n"
-		   "prog_id:\t%u\n",
+		   "link_id:\t%u\n",
 		   bpf_link_type_strs[link->type],
-		   link->id,
-		   prog_tag,
-		   prog->aux->id);
+		   link->id);
+	if (prog) {
+		bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
+		seq_printf(m,
+			   "prog_tag:\t%s\n"
+			   "prog_id:\t%u\n",
+			   prog_tag,
+			   prog->aux->id);
+	}
 	if (link->ops->show_fdinfo)
 		link->ops->show_fdinfo(link, m);
 }
@@ -4314,7 +4317,8 @@ static int bpf_link_get_info_by_fd(struct file *file,
 
 	info.type = link->type;
 	info.id = link->id;
-	info.prog_id = link->prog->aux->id;
+	if (link->prog)
+		info.prog_id = link->prog->aux->id;
 
 	if (link->ops->fill_link_info) {
 		err = link->ops->fill_link_info(link, &info);
@@ -4577,6 +4581,9 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	if (CHECK_ATTR(BPF_LINK_CREATE))
 		return -EINVAL;
 
+	if (attr->link_create.attach_type == BPF_STRUCT_OPS)
+		return bpf_struct_ops_link_create(attr);
+
 	prog = bpf_prog_get(attr->link_create.prog_fd);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 13fc0c185cd9..bbbd5eb94db2 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -239,8 +239,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
 		if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name,
 				     sizeof(tcp_ca->name)) <= 0)
 			return -EINVAL;
-		if (tcp_ca_find(utcp_ca->name))
-			return -EEXIST;
 		return 1;
 	}
 
@@ -266,6 +264,11 @@ static void bpf_tcp_ca_unreg(void *kdata)
 	tcp_unregister_congestion_control(kdata);
 }
 
+static int bpf_tcp_ca_validate(void *kdata)
+{
+	return tcp_validate_congestion_control(kdata);
+}
+
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
@@ -273,6 +276,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.check_member = bpf_tcp_ca_check_member,
 	.init_member = bpf_tcp_ca_init_member,
 	.init = bpf_tcp_ca_init,
+	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
 };
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 13129df937cd..9cf1deaf21f2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1033,6 +1033,7 @@ enum bpf_attach_type {
 	BPF_PERF_EVENT,
 	BPF_TRACE_KPROBE_MULTI,
 	BPF_LSM_CGROUP,
+	BPF_STRUCT_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1266,6 +1267,9 @@ enum {
 
 /* Create a map that is suitable to be an inner map with dynamic max entries */
 	BPF_F_INNER_MAP		= (1U << 12),
+
+/* Create a map that will be registered/unregesitered by the backed bpf_link */
+	BPF_F_LINK		= (1U << 13),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1507,7 +1511,10 @@ union bpf_attr {
 	} task_fd_query;
 
 	struct { /* struct used by BPF_LINK_CREATE command */
-		__u32		prog_fd;	/* eBPF program to attach */
+		union {
+			__u32		prog_fd;	/* eBPF program to attach */
+			__u32		map_fd;		/* eBPF struct_ops to attach */
+		};
 		union {
 			__u32		target_fd;	/* object to attach to */
 			__u32		target_ifindex; /* target ifindex */
@@ -6379,6 +6386,9 @@ struct bpf_link_info {
 		struct {
 			__u32 ifindex;
 		} xdp;
+		struct {
+			__u32 map_id;
+		} struct_ops;
 	};
 } __attribute__((aligned(8)));