From: John Fastabend <john.fastabend@gmail.com>
To: davem@davemloft.net, daniel@iogearbox.net, ast@fb.com
Cc: tgraf@suug.ch, netdev@vger.kernel.org, john.fastabend@gmail.com,
tom@herbertland.com
Subject: [net-next PATCH 07/10] bpf: add access to sock fields and pkt data from sk_skb programs
Date: Tue, 15 Aug 2017 22:33:09 -0700 [thread overview]
Message-ID: <20170816053309.15445.97681.stgit@john-Precision-Tower-5810> (raw)
In-Reply-To: <20170816052338.15445.83732.stgit@john-Precision-Tower-5810>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
include/uapi/linux/bpf.h | 9 ++
kernel/bpf/verifier.c | 1
net/core/filter.c | 169 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 179 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7f77476..5ecbe81 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -712,6 +712,15 @@ struct __sk_buff {
__u32 data;
__u32 data_end;
__u32 napi_id;
+
+ /* accessed by BPF_PROG_TYPE_sk_skb types */
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
};
struct bpf_tunnel_key {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a439ad5..bfed82e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -848,6 +848,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
case BPF_PROG_TYPE_LWT_XMIT:
+ case BPF_PROG_TYPE_SK_SKB:
if (meta)
return meta->pkt_access;
diff --git a/net/core/filter.c b/net/core/filter.c
index 934b92f..9a9e31f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3278,8 +3278,16 @@ static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
+ case BPF_FUNC_skb_store_bytes:
+ return &bpf_skb_store_bytes_proto;
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_skb_pull_data:
+ return &bpf_skb_pull_data_proto;
+ case BPF_FUNC_skb_change_tail:
+ return &bpf_skb_change_tail_proto;
+ case BPF_FUNC_skb_change_head:
+ return &bpf_skb_change_head_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
@@ -3343,6 +3351,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
if (off + size > offsetofend(struct __sk_buff, cb[4]))
return false;
break;
+ case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]):
+ case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]):
+ case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
+ case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
if (size != size_default)
@@ -3371,6 +3383,7 @@ static bool sk_filter_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
+ case bpf_ctx_range_till(struct __sk_buff, family, local_port):
return false;
}
@@ -3392,6 +3405,7 @@ static bool lwt_is_valid_access(int off, int size,
{
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
+ case bpf_ctx_range_till(struct __sk_buff, family, local_port):
return false;
}
@@ -3505,6 +3519,8 @@ static bool tc_cls_act_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
+ case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+ return false;
}
return bpf_skb_is_valid_access(off, size, type, info);
@@ -3582,11 +3598,63 @@ static bool sock_ops_is_valid_access(int off, int size,
return __is_valid_sock_ops_access(off, size);
}
+static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write,
+ const struct bpf_prog *prog)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ if (!direct_write)
+ return 0;
+
+ /* if (!skb->cloned)
+ * goto start;
+ *
+ * (Fast-path, otherwise approximation that we might be
+ * a clone, do the rest in helper.)
+ */
+ *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET());
+ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK);
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7);
+
+ /* ret = bpf_skb_pull_data(skb, 0); */
+ *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+ *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2);
+ *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_pull_data);
+ /* if (!ret)
+ * goto restore;
+ * return SK_DROP;
+ */
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2);
+ *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, SK_DROP);
+ *insn++ = BPF_EXIT_INSN();
+
+ /* restore: */
+ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+ /* start: */
+ *insn++ = prog->insnsi[0];
+
+ return insn - insn_buf;
+}
+
static bool sk_skb_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
+ if (type == BPF_WRITE) {
+ switch (off) {
+ case bpf_ctx_range(struct __sk_buff, mark):
+ case bpf_ctx_range(struct __sk_buff, tc_index):
+ case bpf_ctx_range(struct __sk_buff, priority):
+ break;
+ default:
+ return false;
+ }
+ }
+
switch (off) {
+ case bpf_ctx_range(struct __sk_buff, tc_classid):
+ return false;
case bpf_ctx_range(struct __sk_buff, data):
info->reg_type = PTR_TO_PACKET;
break;
@@ -3781,6 +3849,106 @@ 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, family):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct sock_common,
+ skc_family,
+ 2, target_size));
+ break;
+ case offsetof(struct __sk_buff, remote_ip4):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct sock_common,
+ skc_daddr,
+ 4, target_size));
+ break;
+ case offsetof(struct __sk_buff, local_ip4):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common,
+ skc_rcv_saddr) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct sock_common,
+ skc_rcv_saddr,
+ 4, target_size));
+ break;
+ case offsetof(struct __sk_buff, remote_ip6[0]) ...
+ offsetof(struct __sk_buff, remote_ip6[3]):
+#if IS_ENABLED(CONFIG_IPV6)
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common,
+ skc_v6_daddr.s6_addr32[0]) != 4);
+
+ off = si->off;
+ off -= offsetof(struct __sk_buff, remote_ip6[0]);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ offsetof(struct sock_common,
+ skc_v6_daddr.s6_addr32[0]) +
+ off);
+#else
+ *insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+ break;
+ case offsetof(struct __sk_buff, local_ip6[0]) ...
+ offsetof(struct __sk_buff, local_ip6[3]):
+#if IS_ENABLED(CONFIG_IPV6)
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common,
+ skc_v6_rcv_saddr.s6_addr32[0]) != 4);
+
+ off = si->off;
+ off -= offsetof(struct __sk_buff, local_ip6[0]);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ offsetof(struct sock_common,
+ skc_v6_rcv_saddr.s6_addr32[0]) +
+ off);
+#else
+ *insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+ break;
+
+ case offsetof(struct __sk_buff, remote_port):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct sock_common,
+ skc_dport,
+ 2, target_size));
+#ifndef __BIG_ENDIAN_BITFIELD
+ *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16);
+#endif
+ break;
+
+ case offsetof(struct __sk_buff, local_port):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, sk));
+ *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct sock_common,
+ skc_num, 2, target_size));
+ break;
}
return insn - insn_buf;
@@ -4069,6 +4237,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
.get_func_proto = sk_skb_func_proto,
.is_valid_access = sk_skb_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+ .gen_prologue = sk_skb_prologue,
};
int sk_detach_filter(struct sock *sk)
next prev parent reply other threads:[~2017-08-16 5:33 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-16 5:30 [net-next PATCH 00/10] BPF: sockmap and sk redirect support John Fastabend
2017-08-16 5:30 ` [net-next PATCH 01/10] net: early init support for strparser John Fastabend
2017-08-16 5:31 ` [net-next PATCH 02/10] net: add sendmsg_locked and sendpage_locked to af_inet6 John Fastabend
2017-08-16 5:31 ` [net-next PATCH 03/10] net: fixes for skb_send_sock John Fastabend
2017-08-16 5:31 ` [net-next PATCH 04/10] bpf: introduce new program type for skbs on sockets John Fastabend
2017-08-16 5:32 ` [net-next PATCH 05/10] bpf: export bpf_prog_inc_not_zero John Fastabend
2017-08-16 5:32 ` [net-next PATCH 06/10] bpf: sockmap with sk redirect support John Fastabend
2017-08-17 5:40 ` Alexei Starovoitov
2017-08-17 18:58 ` John Fastabend
2017-08-17 22:28 ` Alexei Starovoitov
2017-08-18 7:35 ` John Fastabend
2017-08-18 18:32 ` Alexei Starovoitov
2017-08-19 3:30 ` John Fastabend
2017-08-19 4:50 ` Alexei Starovoitov
2017-08-19 20:52 ` John Fastabend
2017-08-16 5:33 ` John Fastabend [this message]
2017-08-17 5:42 ` [net-next PATCH 07/10] bpf: add access to sock fields and pkt data from sk_skb programs Alexei Starovoitov
2017-08-17 12:40 ` Daniel Borkmann
2017-08-16 5:33 ` [net-next PATCH 08/10] bpf: sockmap sample program John Fastabend
2017-08-16 5:33 ` [net-next PATCH 09/10] bpf: selftests: add tests for new __sk_buff members John Fastabend
2017-08-16 5:34 ` [net-next PATCH 10/10] bpf: selftests add sockmap tests John Fastabend
2017-08-16 15:25 ` [net-next PATCH 00/10] BPF: sockmap and sk redirect support Daniel Borkmann
2017-08-16 18:28 ` David Miller
2017-08-16 18:35 ` David Miller
2017-08-16 19:06 ` John Fastabend
2017-08-16 19:13 ` David Miller
2017-08-16 19:17 ` Eric Dumazet
2017-08-16 19:34 ` John Fastabend
2017-08-16 21:22 ` David Miller
2017-08-16 21:35 ` David Ahern
2017-08-16 21:37 ` John Fastabend
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=20170816053309.15445.97681.stgit@john-Precision-Tower-5810 \
--to=john.fastabend@gmail.com \
--cc=ast@fb.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=tgraf@suug.ch \
--cc=tom@herbertland.com \
/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