summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/linux/bpf.h1
-rw-r--r--include/linux/filter.h2
-rw-r--r--include/uapi/linux/bpf.h15
-rw-r--r--kernel/bpf/syscall.c13
-rw-r--r--net/core/filter.c13
-rw-r--r--net/core/sock_reuseport.c34
-rw-r--r--tools/include/uapi/linux/bpf.h15
7 files changed, 88 insertions, 5 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 86dec5001ae2..f309fc1509f2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2048,6 +2048,7 @@ struct sk_reuseport_kern {
struct sk_buff *skb;
struct sock *sk;
struct sock *selected_sk;
+ struct sock *migrating_sk;
void *data_end;
u32 hash;
u32 reuseport_id;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c5ad7df029ed..688856e0b28a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -996,11 +996,13 @@ 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,
+ struct sock *migrating_sk,
u32 hash);
#else
static inline struct sock *
bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
struct bpf_prog *prog, struct sk_buff *skb,
+ struct sock *migrating_sk,
u32 hash)
{
return NULL;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f3b72588442b..bf9252c7381e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -994,6 +994,8 @@ enum bpf_attach_type {
BPF_SK_LOOKUP,
BPF_XDP,
BPF_SK_SKB_VERDICT,
+ BPF_SK_REUSEPORT_SELECT,
+ BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
__MAX_BPF_ATTACH_TYPE
};
@@ -5416,7 +5418,20 @@ 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 */
+ /* When reuse->migrating_sk is NULL, it is selecting a sk for the
+ * new incoming connection request (e.g. selecting a listen sk for
+ * the received SYN in the TCP case). reuse->sk is one of the sk
+ * in the reuseport group. The bpf prog can use reuse->sk to learn
+ * the local listening ip/port without looking into the skb.
+ *
+ * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+ * reuse->migrating_sk is the socket that needs to be migrated
+ * to another listening socket. migrating_sk could be a fullsock
+ * sk that is fully established or a reqsk that is in-the-middle
+ * of 3-way handshake.
+ */
__bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(struct bpf_sock *, migrating_sk);
};
#define BPF_TAG_SIZE 8
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50457019da27..dbbc5342f221 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1972,6 +1972,11 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
attr->expected_attach_type =
BPF_CGROUP_INET_SOCK_CREATE;
break;
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ if (!attr->expected_attach_type)
+ attr->expected_attach_type =
+ BPF_SK_REUSEPORT_SELECT;
+ break;
}
}
@@ -2055,6 +2060,14 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
if (expected_attach_type == BPF_SK_LOOKUP)
return 0;
return -EINVAL;
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ switch (expected_attach_type) {
+ case BPF_SK_REUSEPORT_SELECT:
+ case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE:
+ return 0;
+ default:
+ return -EINVAL;
+ }
case BPF_PROG_TYPE_SYSCALL:
case BPF_PROG_TYPE_EXT:
if (expected_attach_type)
diff --git a/net/core/filter.c b/net/core/filter.c
index f753ab550525..5b86e47ef079 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10044,11 +10044,13 @@ out:
static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
struct sock_reuseport *reuse,
struct sock *sk, struct sk_buff *skb,
+ struct sock *migrating_sk,
u32 hash)
{
reuse_kern->skb = skb;
reuse_kern->sk = sk;
reuse_kern->selected_sk = NULL;
+ reuse_kern->migrating_sk = migrating_sk;
reuse_kern->data_end = skb->data + skb_headlen(skb);
reuse_kern->hash = hash;
reuse_kern->reuseport_id = reuse->reuseport_id;
@@ -10057,12 +10059,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
struct bpf_prog *prog, struct sk_buff *skb,
+ struct sock *migrating_sk,
u32 hash)
{
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, migrating_sk, hash);
action = BPF_PROG_RUN(prog, &reuse_kern);
if (action == SK_PASS)
@@ -10207,6 +10210,10 @@ sk_reuseport_is_valid_access(int off, int size,
info->reg_type = PTR_TO_SOCKET;
return size == sizeof(__u64);
+ case offsetof(struct sk_reuseport_md, migrating_sk):
+ info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL;
+ return size == sizeof(__u64);
+
/* Fields that allow narrowing */
case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
if (size < sizeof_field(struct sk_buff, protocol))
@@ -10283,6 +10290,10 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct sk_reuseport_md, sk):
SK_REUSEPORT_LOAD_FIELD(sk);
break;
+
+ case offsetof(struct sk_reuseport_md, migrating_sk):
+ SK_REUSEPORT_LOAD_FIELD(migrating_sk);
+ break;
}
return insn - insn_buf;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index b239f8cd9d39..de5ee3ae86d5 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -377,13 +377,17 @@ void reuseport_stop_listen_sock(struct sock *sk)
{
if (sk->sk_protocol == IPPROTO_TCP) {
struct sock_reuseport *reuse;
+ struct bpf_prog *prog;
spin_lock_bh(&reuseport_lock);
reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
lockdep_is_held(&reuseport_lock));
+ prog = rcu_dereference_protected(reuse->prog,
+ lockdep_is_held(&reuseport_lock));
- if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) {
+ if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
+ (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
/* Migration capable, move sk from the listening section
* to the closed section.
*/
@@ -488,7 +492,7 @@ struct sock *reuseport_select_sock(struct sock *sk,
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, NULL, hash);
else
sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
@@ -519,6 +523,8 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
{
struct sock_reuseport *reuse;
struct sock *nsk = NULL;
+ bool allocated = false;
+ struct bpf_prog *prog;
u16 socks;
u32 hash;
@@ -536,10 +542,30 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
smp_rmb();
hash = migrating_sk->sk_hash;
- if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+ prog = rcu_dereference(reuse->prog);
+ if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
+ if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+ goto select_by_hash;
+ goto out;
+ }
+
+ if (!skb) {
+ skb = alloc_skb(0, GFP_ATOMIC);
+ if (!skb)
+ goto out;
+ allocated = true;
+ }
+
+ nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash);
+
+ if (allocated)
+ kfree_skb(skb);
+
+select_by_hash:
+ if (!nsk)
nsk = reuseport_select_sock_by_hash(reuse, hash, socks);
- if (nsk && unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt)))
+ if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt)))
nsk = NULL;
out:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f3b72588442b..bf9252c7381e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -994,6 +994,8 @@ enum bpf_attach_type {
BPF_SK_LOOKUP,
BPF_XDP,
BPF_SK_SKB_VERDICT,
+ BPF_SK_REUSEPORT_SELECT,
+ BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
__MAX_BPF_ATTACH_TYPE
};
@@ -5416,7 +5418,20 @@ 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 */
+ /* When reuse->migrating_sk is NULL, it is selecting a sk for the
+ * new incoming connection request (e.g. selecting a listen sk for
+ * the received SYN in the TCP case). reuse->sk is one of the sk
+ * in the reuseport group. The bpf prog can use reuse->sk to learn
+ * the local listening ip/port without looking into the skb.
+ *
+ * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+ * reuse->migrating_sk is the socket that needs to be migrated
+ * to another listening socket. migrating_sk could be a fullsock
+ * sk that is fully established or a reqsk that is in-the-middle
+ * of 3-way handshake.
+ */
__bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(struct bpf_sock *, migrating_sk);
};
#define BPF_TAG_SIZE 8