From: Mark Pashmfouroush <markpash@cloudflare.com>
To: markpash@cloudflare.com, Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
"David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>,
Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>,
David Ahern <dsahern@kernel.org>
Cc: kernel-team@cloudflare.com, netdev@vger.kernel.org,
bpf@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH bpf-next v3 1/2] bpf: Add ingress_ifindex to bpf_sk_lookup
Date: Wed, 10 Nov 2021 11:10:15 +0000 [thread overview]
Message-ID: <20211110111016.5670-2-markpash@cloudflare.com> (raw)
In-Reply-To: <20211110111016.5670-1-markpash@cloudflare.com>
It may be helpful to have access to the ifindex during bpf socket
lookup. An example may be to scope certain socket lookup logic to
specific interfaces, i.e. an interface may be made exempt from custom
lookup code.
Add the ifindex of the arriving connection to the bpf_sk_lookup API.
Signed-off-by: Mark Pashmfouroush <markpash@cloudflare.com>
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 24b7ed2677af..b6a216eb217a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1374,6 +1374,7 @@ struct bpf_sk_lookup_kern {
const struct in6_addr *daddr;
} v6;
struct sock *selected_sk;
+ u32 ingress_ifindex;
bool no_reuseport;
};
@@ -1436,7 +1437,7 @@ extern struct static_key_false bpf_sk_lookup_enabled;
static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const u16 dport,
- struct sock **psk)
+ const int ifindex, struct sock **psk)
{
struct bpf_prog_array *run_array;
struct sock *selected_sk = NULL;
@@ -1452,6 +1453,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
.v4.daddr = daddr,
.sport = sport,
.dport = dport,
+ .ingress_ifindex = ifindex,
};
u32 act;
@@ -1474,7 +1476,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
const __be16 sport,
const struct in6_addr *daddr,
const u16 dport,
- struct sock **psk)
+ const int ifindex, struct sock **psk)
{
struct bpf_prog_array *run_array;
struct sock *selected_sk = NULL;
@@ -1490,6 +1492,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
.v6.daddr = daddr,
.sport = sport,
.dport = dport,
+ .ingress_ifindex = ifindex,
};
u32 act;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 509eee5f0393..6297eafdc40f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6316,6 +6316,7 @@ struct bpf_sk_lookup {
__u32 local_ip4; /* Network byte order */
__u32 local_ip6[4]; /* Network byte order */
__u32 local_port; /* Host byte order */
+ __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */
};
/*
diff --git a/net/core/filter.c b/net/core/filter.c
index 8e8d3b49c297..315a58466fc9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10491,6 +10491,7 @@ static bool sk_lookup_is_valid_access(int off, int size,
case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]):
case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
case bpf_ctx_range(struct bpf_sk_lookup, local_port):
+ case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex):
bpf_ctx_record_field_size(info, sizeof(__u32));
return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32));
@@ -10580,6 +10581,12 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type,
bpf_target_off(struct bpf_sk_lookup_kern,
dport, 2, target_size));
break;
+
+ case offsetof(struct bpf_sk_lookup, ingress_ifindex):
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+ bpf_target_off(struct bpf_sk_lookup_kern,
+ ingress_ifindex, 4, target_size));
+ break;
}
return insn - insn_buf;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 75737267746f..30ab717ff1b8 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -307,7 +307,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
__be32 saddr, __be16 sport,
- __be32 daddr, u16 hnum)
+ __be32 daddr, u16 hnum, const int dif)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
@@ -315,8 +315,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net,
if (hashinfo != &tcp_hashinfo)
return NULL; /* only TCP is supported */
- no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP,
- saddr, sport, daddr, hnum, &sk);
+ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport,
+ daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
@@ -340,7 +340,7 @@ struct sock *__inet_lookup_listener(struct net *net,
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
- saddr, sport, daddr, hnum);
+ saddr, sport, daddr, hnum, dif);
if (result)
goto done;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2fffcf2b54f3..5fceee3de65d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -460,7 +460,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
struct udp_table *udptable,
struct sk_buff *skb,
__be32 saddr, __be16 sport,
- __be32 daddr, u16 hnum)
+ __be32 daddr, u16 hnum, const int dif)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
@@ -468,8 +468,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
if (udptable != &udp_table)
return NULL; /* only UDP is supported */
- no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP,
- saddr, sport, daddr, hnum, &sk);
+ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
+ daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
@@ -505,7 +505,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
sk = udp4_lookup_run_bpf(net, udptable, skb,
- saddr, sport, daddr, hnum);
+ saddr, sport, daddr, hnum, dif);
if (sk) {
result = sk;
goto done;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 67c9114835c8..4514444e96c8 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -165,7 +165,7 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
- const u16 hnum)
+ const u16 hnum, const int dif)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
@@ -173,8 +173,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net,
if (hashinfo != &tcp_hashinfo)
return NULL; /* only TCP is supported */
- no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP,
- saddr, sport, daddr, hnum, &sk);
+ no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport,
+ daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
@@ -198,7 +198,7 @@ struct sock *inet6_lookup_listener(struct net *net,
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
- saddr, sport, daddr, hnum);
+ saddr, sport, daddr, hnum, dif);
if (result)
goto done;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 12c12619ee35..ea4ea525f94a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -195,7 +195,7 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net,
const struct in6_addr *saddr,
__be16 sport,
const struct in6_addr *daddr,
- u16 hnum)
+ u16 hnum, const int dif)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
@@ -203,8 +203,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net,
if (udptable != &udp_table)
return NULL; /* only UDP is supported */
- no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP,
- saddr, sport, daddr, hnum, &sk);
+ no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
+ daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
@@ -240,7 +240,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
sk = udp6_lookup_run_bpf(net, udptable, skb,
- saddr, sport, daddr, hnum);
+ saddr, sport, daddr, hnum, dif);
if (sk) {
result = sk;
goto done;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 509eee5f0393..6297eafdc40f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6316,6 +6316,7 @@ struct bpf_sk_lookup {
__u32 local_ip4; /* Network byte order */
__u32 local_ip6[4]; /* Network byte order */
__u32 local_port; /* Host byte order */
+ __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */
};
/*
--
2.31.1
next prev parent reply other threads:[~2021-11-10 11:12 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-10 11:10 [PATCH bpf-next v3 0/2] Get ingress_ifindex in BPF_SK_LOOKUP prog type Mark Pashmfouroush
2021-11-10 11:10 ` Mark Pashmfouroush [this message]
2021-11-10 11:10 ` [PATCH bpf-next v3 2/2] selftests/bpf: Add tests for accessing ingress_ifindex in bpf_sk_lookup Mark Pashmfouroush
2021-11-10 11:54 ` [PATCH bpf-next v3 0/2] Get ingress_ifindex in BPF_SK_LOOKUP prog type Lorenz Bauer
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211110111016.5670-2-markpash@cloudflare.com \
--to=markpash@cloudflare.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=kernel-team@cloudflare.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=yoshfuji@linux-ipv6.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).