diff mbox series

[v1,bpf-next,08/11] bpf: Add migration to sk_reuseport_(kern|md).

Message ID 20201201144418.35045-9-kuniyu@amazon.co.jp
State Superseded
Headers show
Series Socket migration for SO_REUSEPORT. | expand

Commit Message

Kuniyuki Iwashima Dec. 1, 2020, 2:44 p.m. UTC 
This patch adds u8 migration field to sk_reuseport_kern and sk_reuseport_md
to signal the eBPF program if the kernel calls it for selecting a listener
for SYN or migrating sockets in the accept queue or an immature socket
during 3WHS.

Note that this field is accessible only if the attached type is
BPF_SK_REUSEPORT_SELECT_OR_MIGRATE.

Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
---
 include/linux/bpf.h            |  1 +
 include/linux/filter.h         |  4 ++--
 include/uapi/linux/bpf.h       |  1 +
 net/core/filter.c              | 15 ++++++++++++---
 net/core/sock_reuseport.c      |  2 +-
 tools/include/uapi/linux/bpf.h |  1 +
 6 files changed, 18 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 581b2a2e78eb..244f823f1f84 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1897,6 +1897,7 @@  struct sk_reuseport_kern {
 	u32 hash;
 	u32 reuseport_id;
 	bool bind_inany;
+	u8 migration;
 };
 bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 				  struct bpf_insn_access_aux *info);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1b62397bd124..15d5bf13a905 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -967,12 +967,12 @@  void bpf_warn_invalid_xdp_action(u32 act);
 #ifdef CONFIG_INET
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
-				  u32 hash);
+				  u32 hash, u8 migration);
 #else
 static inline struct sock *
 bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 		     struct bpf_prog *prog, struct sk_buff *skb,
-		     u32 hash)
+		     u32 hash, u8 migration)
 {
 	return NULL;
 }
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cfc207ae7782..efe342bf3dbc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4419,6 +4419,7 @@  struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	__u8 migration;		/* Migration type */
 };
 
 #define BPF_TAG_SIZE	8
diff --git a/net/core/filter.c b/net/core/filter.c
index 2ca5eecebacf..0a0634787bb4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9853,7 +9853,7 @@  int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 				    struct sock_reuseport *reuse,
 				    struct sock *sk, struct sk_buff *skb,
-				    u32 hash)
+				    u32 hash, u8 migration)
 {
 	reuse_kern->skb = skb;
 	reuse_kern->sk = sk;
@@ -9862,16 +9862,17 @@  static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 	reuse_kern->hash = hash;
 	reuse_kern->reuseport_id = reuse->reuseport_id;
 	reuse_kern->bind_inany = reuse->bind_inany;
+	reuse_kern->migration = migration;
 }
 
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
-				  u32 hash)
+				  u32 hash, u8 migration)
 {
 	struct sk_reuseport_kern reuse_kern;
 	enum sk_action action;
 
-	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash, migration);
 	action = BPF_PROG_RUN(prog, &reuse_kern);
 
 	if (action == SK_PASS)
@@ -10010,6 +10011,10 @@  sk_reuseport_is_valid_access(int off, int size,
 	case offsetof(struct sk_reuseport_md, hash):
 		return size == size_default;
 
+	case bpf_ctx_range(struct sk_reuseport_md, migration):
+		return prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE &&
+			size == sizeof(__u8);
+
 	/* Fields that allow narrowing */
 	case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
 		if (size < sizeof_field(struct sk_buff, protocol))
@@ -10082,6 +10087,10 @@  static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct sk_reuseport_md, bind_inany):
 		SK_REUSEPORT_LOAD_FIELD(bind_inany);
 		break;
+
+	case offsetof(struct sk_reuseport_md, migration):
+		SK_REUSEPORT_LOAD_FIELD(migration);
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index b4fe0829c9ab..96d65b4c6974 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -349,7 +349,7 @@  struct sock *__reuseport_select_sock(struct sock *sk, u32 hash,
 			goto select_by_hash;
 
 		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
-			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash, migration);
 		else
 			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cfc207ae7782..efe342bf3dbc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4419,6 +4419,7 @@  struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	__u8 migration;		/* Migration type */
 };
 
 #define BPF_TAG_SIZE	8