Add napi_id access to __sk_buff for socket filter program types, tc
program types and other bpf_convert_ctx_access() users. Having access
to skb->napi_id is useful for per RX queue listener siloing, f.e.
in combination with SO_ATTACH_REUSEPORT_EBPF and when busy polling is
used, meaning SO_REUSEPORT enabled listeners can then select the
corresponding socket at SYN time already [1]. The skb is marked via
skb_mark_napi_id() early in the receive path (e.g., napi_gro_receive()).
Currently, sockets can only use SO_INCOMING_NAPI_ID from 6d4339028b35
("net: Introduce SO_INCOMING_NAPI_ID") as a socket option to look up
the NAPI ID associated with the queue for steering, which requires a
prior sk_mark_napi_id() after the socket was looked up.
Semantics for the __sk_buff napi_id access are similar, meaning if
skb->napi_id is < MIN_NAPI_ID (e.g. outgoing packets using sender_cpu),
then an invalid napi_id of 0 is returned to the program, otherwise a
valid non-zero napi_id.
[1] http://netdevconf.org/2.1/slides/apr6/dumazet-BUSY-POLLING-Netdev-2.1.pdf
Suggested-by: Eric Dumazet <eduma...@google.com>
Signed-off-by: Daniel Borkmann <dan...@iogearbox.net>
Acked-by: Alexei Starovoitov <a...@kernel.org>
---
include/uapi/linux/bpf.h | 1 +
net/core/filter.c | 14 ++++++++++++++
tools/include/uapi/linux/bpf.h | 1 +
tools/testing/selftests/bpf/test_verifier.c | 3 +++
4 files changed, 19 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1e062bb..e553529 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -603,6 +603,7 @@ struct __sk_buff {
__u32 tc_classid;
__u32 data;
__u32 data_end;
+ __u32 napi_id;
};
struct bpf_tunnel_key {
diff --git a/net/core/filter.c b/net/core/filter.c
index 19be954..70ff8c0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -53,6 +53,7 @@
#include <net/dst_metadata.h>
#include <net/dst.h>
#include <net/sock_reuseport.h>
+#include <net/busy_poll.h>
/**
* sk_filter_trim_cap - run a packet through a socket filter
@@ -3202,6 +3203,19 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type
type,
*insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
#endif
break;
+
+ case offsetof(struct __sk_buff, napi_id):
+#if defined(CONFIG_NET_RX_BUSY_POLL)
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, napi_id) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, napi_id));
+ *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1);
+ *insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
+#else
+ *insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
+#endif
+ break;
}
return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1e062bb..e553529 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -603,6 +603,7 @@ struct __sk_buff {
__u32 tc_classid;
__u32 data;
__u32 data_end;
+ __u32 napi_id;
};
struct bpf_tunnel_key {
diff --git a/tools/testing/selftests/bpf/test_verifier.c
b/tools/testing/selftests/bpf/test_verifier.c
index 6178b65..95a8d5f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -772,6 +772,9 @@ struct test_val {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
offsetof(struct __sk_buff, vlan_tci)),
BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, napi_id)),
+ BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
BPF_EXIT_INSN(),
},
.result = ACCEPT,
--
1.9.3
