* [PATCH bpf-next v5 01/11] bpf: Make SOCK_OPS_GET_TCP size independent
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
@ 2018-01-09 21:06 ` Lawrence Brakmo
2018-01-09 21:06 ` [PATCH bpf-next v5 02/11] bpf: Make SOCK_OPS_GET_TCP struct independent Lawrence Brakmo
` (9 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:06 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Make SOCK_OPS_GET_TCP helper macro size independent (before only worked
with 4-byte fields.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
net/core/filter.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index acdb94c..549c70c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4468,9 +4468,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
break;
/* Helper macro for adding read access to tcp_sock fields. */
-#define SOCK_OPS_GET_TCP32(FIELD_NAME) \
+#define SOCK_OPS_GET_TCP(FIELD_NAME) \
do { \
- BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD_NAME) != 4); \
+ BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD_NAME) > \
+ FIELD_SIZEOF(struct bpf_sock_ops, FIELD_NAME)); \
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \
struct bpf_sock_ops_kern, \
is_fullsock), \
@@ -4482,16 +4483,18 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
struct bpf_sock_ops_kern, sk),\
si->dst_reg, si->src_reg, \
offsetof(struct bpf_sock_ops_kern, sk));\
- *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, \
+ *insn++ = BPF_LDX_MEM(FIELD_SIZEOF(struct tcp_sock, \
+ FIELD_NAME), si->dst_reg, \
+ si->dst_reg, \
offsetof(struct tcp_sock, FIELD_NAME)); \
} while (0)
case offsetof(struct bpf_sock_ops, snd_cwnd):
- SOCK_OPS_GET_TCP32(snd_cwnd);
+ SOCK_OPS_GET_TCP(snd_cwnd);
break;
case offsetof(struct bpf_sock_ops, srtt_us):
- SOCK_OPS_GET_TCP32(srtt_us);
+ SOCK_OPS_GET_TCP(srtt_us);
break;
}
return insn - insn_buf;
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 02/11] bpf: Make SOCK_OPS_GET_TCP struct independent
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
2018-01-09 21:06 ` [PATCH bpf-next v5 01/11] bpf: Make SOCK_OPS_GET_TCP size independent Lawrence Brakmo
@ 2018-01-09 21:06 ` Lawrence Brakmo
2018-01-09 21:06 ` [PATCH bpf-next v5 03/11] bpf: Add write access to tcp_sock and sock fields Lawrence Brakmo
` (8 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:06 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Changed SOCK_OPS_GET_TCP to SOCK_OPS_GET_FIELD and added 2
arguments so now it can also work with struct sock fields.
The first argument is the name of the field in the bpf_sock_ops
struct, the 2nd argument is the name of the field in the OBJ struct.
Previous: SOCK_OPS_GET_TCP(FIELD_NAME)
New: SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)
Where OBJ is either "struct tcp_sock" or "struct sock" (without
quotation). BPF_FIELD is the name of the field in the bpf_sock_ops
struct and OBJ_FIELD is the name of the field in the OBJ struct.
Although the field names are currently the same, the kernel struct names
could change in the future and this change makes it easier to support
that.
Note that adding access to tcp_sock fields in sock_ops programs does
not preclude the tcp_sock fields from being removed as long as we are
willing to do one of the following:
1) Return a fixed value (e.x. 0 or 0xffffffff), or
2) Make the verifier fail if that field is accessed (i.e. program
fails to load) so the user will know that field is no longer
supported.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
net/core/filter.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 549c70c..19aad0f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4467,11 +4467,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
is_fullsock));
break;
-/* Helper macro for adding read access to tcp_sock fields. */
-#define SOCK_OPS_GET_TCP(FIELD_NAME) \
+/* Helper macro for adding read access to tcp_sock or sock fields. */
+#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \
do { \
- BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD_NAME) > \
- FIELD_SIZEOF(struct bpf_sock_ops, FIELD_NAME)); \
+ BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \
+ FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \
struct bpf_sock_ops_kern, \
is_fullsock), \
@@ -4483,18 +4483,18 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
struct bpf_sock_ops_kern, sk),\
si->dst_reg, si->src_reg, \
offsetof(struct bpf_sock_ops_kern, sk));\
- *insn++ = BPF_LDX_MEM(FIELD_SIZEOF(struct tcp_sock, \
- FIELD_NAME), si->dst_reg, \
- si->dst_reg, \
- offsetof(struct tcp_sock, FIELD_NAME)); \
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \
+ OBJ_FIELD), \
+ si->dst_reg, si->dst_reg, \
+ offsetof(OBJ, OBJ_FIELD)); \
} while (0)
case offsetof(struct bpf_sock_ops, snd_cwnd):
- SOCK_OPS_GET_TCP(snd_cwnd);
+ SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock);
break;
case offsetof(struct bpf_sock_ops, srtt_us):
- SOCK_OPS_GET_TCP(srtt_us);
+ SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);
break;
}
return insn - insn_buf;
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 03/11] bpf: Add write access to tcp_sock and sock fields
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
2018-01-09 21:06 ` [PATCH bpf-next v5 01/11] bpf: Make SOCK_OPS_GET_TCP size independent Lawrence Brakmo
2018-01-09 21:06 ` [PATCH bpf-next v5 02/11] bpf: Make SOCK_OPS_GET_TCP struct independent Lawrence Brakmo
@ 2018-01-09 21:06 ` Lawrence Brakmo
2018-01-09 23:21 ` Eric Dumazet
2018-01-09 21:06 ` [PATCH bpf-next v5 04/11] bpf: Support passing args to sock_ops bpf function Lawrence Brakmo
` (7 subsequent siblings)
10 siblings, 1 reply; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:06 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
This patch adds a macro, SOCK_OPS_SET_FIELD, for writing to
struct tcp_sock or struct sock fields. This required adding a new
field "temp" to struct bpf_sock_ops_kern for temporary storage that
is used by sock_ops_convert_ctx_access. It is used to store and recover
the contents of a register, so the register can be used to store the
address of the sk. Since we cannot overwrite the dst_reg because it
contains the pointer to ctx, nor the src_reg since it contains the value
we want to store, we need an extra register to contain the address
of the sk.
Also adds the macro SOCK_OPS_GET_OR_SET_FIELD that calls one of the
GET or SET macros depending on the value of the TYPE field.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/linux/filter.h | 3 +++
include/net/tcp.h | 2 +-
net/core/filter.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 52 insertions(+), 1 deletion(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 425056c..139a9a3 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1007,6 +1007,9 @@ struct bpf_sock_ops_kern {
u32 replylong[4];
};
u32 is_fullsock;
+ u64 temp; /* Used by sock_ops_convert_ctx_access
+ * as temporary storaage of a register
+ */
};
#endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6939e69..108d16a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2010,7 +2010,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
struct bpf_sock_ops_kern sock_ops;
int ret;
- memset(&sock_ops, 0, sizeof(sock_ops));
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
if (sk_fullsock(sk)) {
sock_ops.is_fullsock = 1;
sock_owned_by_me(sk);
diff --git a/net/core/filter.c b/net/core/filter.c
index 19aad0f..2624859 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4489,6 +4489,54 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
offsetof(OBJ, OBJ_FIELD)); \
} while (0)
+/* Helper macro for adding write access to tcp_sock or sock fields.
+ * The macro is called with two registers, dst_reg which contains a pointer
+ * to ctx (context) and src_reg which contains the value that should be
+ * stored. However, we need an additional register since we cannot overwrite
+ * dst_reg because it may be used later in the program.
+ * Instead we "borrow" one of the other register. We first save its value
+ * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore
+ * it at the end of the macro.
+ */
+#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \
+ do { \
+ int reg = BPF_REG_9; \
+ BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \
+ FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \
+ if (si->dst_reg == reg || si->src_reg == reg) \
+ reg--; \
+ if (si->dst_reg == reg || si->src_reg == reg) \
+ reg--; \
+ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \
+ offsetof(struct bpf_sock_ops_kern, \
+ temp)); \
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \
+ struct bpf_sock_ops_kern, \
+ is_fullsock), \
+ reg, si->dst_reg, \
+ offsetof(struct bpf_sock_ops_kern, \
+ is_fullsock)); \
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \
+ struct bpf_sock_ops_kern, sk),\
+ reg, si->dst_reg, \
+ offsetof(struct bpf_sock_ops_kern, sk));\
+ *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD), \
+ reg, si->src_reg, \
+ offsetof(OBJ, OBJ_FIELD)); \
+ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \
+ offsetof(struct bpf_sock_ops_kern, \
+ temp)); \
+ } while (0)
+
+#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \
+ do { \
+ if (TYPE == BPF_WRITE) \
+ SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \
+ else \
+ SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \
+ } while (0)
+
case offsetof(struct bpf_sock_ops, snd_cwnd):
SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock);
break;
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH bpf-next v5 03/11] bpf: Add write access to tcp_sock and sock fields
2018-01-09 21:06 ` [PATCH bpf-next v5 03/11] bpf: Add write access to tcp_sock and sock fields Lawrence Brakmo
@ 2018-01-09 23:21 ` Eric Dumazet
2018-01-09 23:41 ` Lawrence Brakmo
0 siblings, 1 reply; 16+ messages in thread
From: Eric Dumazet @ 2018-01-09 23:21 UTC (permalink / raw)
To: Lawrence Brakmo, netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Neal Cardwell, Yuchung Cheng
On Tue, 2018-01-09 at 13:06 -0800, Lawrence Brakmo wrote:
> This patch adds a macro, SOCK_OPS_SET_FIELD, for writing to
> struct tcp_sock or struct sock fields. This required adding a new
> field "temp" to struct bpf_sock_ops_kern for temporary storage that
> is used by sock_ops_convert_ctx_access. It is used to store and recover
> the contents of a register, so the register can be used to store the
> address of the sk. Since we cannot overwrite the dst_reg because it
> contains the pointer to ctx, nor the src_reg since it contains the value
> we want to store, we need an extra register to contain the address
> of the sk.
>
> Also adds the macro SOCK_OPS_GET_OR_SET_FIELD that calls one of the
> GET or SET macros depending on the value of the TYPE field.
>
> Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
> ---
> include/linux/filter.h | 3 +++
> include/net/tcp.h | 2 +-
> net/core/filter.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 52 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 425056c..139a9a3 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -1007,6 +1007,9 @@ struct bpf_sock_ops_kern {
> u32 replylong[4];
> };
> u32 is_fullsock;
> + u64 temp; /* Used by sock_ops_convert_ctx_access
> + * as temporary storaage of a register
typo on storage
> + */
> };
>
> #endif /* __LINUX_FILTER_H__ */
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 6939e69..108d16a 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -2010,7 +2010,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
> struct bpf_sock_ops_kern sock_ops;
> int ret;
>
> - memset(&sock_ops, 0, sizeof(sock_ops));
> + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
>
This lacks proper comment, stating that every field added after .temp
in struct bpf_sock_ops_kern is considered as scratch and could contain
garbage.
^ permalink raw reply [flat|nested] 16+ messages in thread* Re: [PATCH bpf-next v5 03/11] bpf: Add write access to tcp_sock and sock fields
2018-01-09 23:21 ` Eric Dumazet
@ 2018-01-09 23:41 ` Lawrence Brakmo
0 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 23:41 UTC (permalink / raw)
To: Eric Dumazet, netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Neal Cardwell, Yuchung Cheng
On 1/9/18, 3:22 PM, "netdev-owner@vger.kernel.org on behalf of Eric Dumazet" <netdev-owner@vger.kernel.org on behalf of eric.dumazet@gmail.com> wrote:
On Tue, 2018-01-09 at 13:06 -0800, Lawrence Brakmo wrote:
> This patch adds a macro, SOCK_OPS_SET_FIELD, for writing to
> struct tcp_sock or struct sock fields. This required adding a new
> field "temp" to struct bpf_sock_ops_kern for temporary storage that
> is used by sock_ops_convert_ctx_access. It is used to store and recover
> the contents of a register, so the register can be used to store the
> address of the sk. Since we cannot overwrite the dst_reg because it
> contains the pointer to ctx, nor the src_reg since it contains the value
> we want to store, we need an extra register to contain the address
> of the sk.
>
> Also adds the macro SOCK_OPS_GET_OR_SET_FIELD that calls one of the
> GET or SET macros depending on the value of the TYPE field.
>
> Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
> ---
> include/linux/filter.h | 3 +++
> include/net/tcp.h | 2 +-
> net/core/filter.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 52 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 425056c..139a9a3 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -1007,6 +1007,9 @@ struct bpf_sock_ops_kern {
> u32 replylong[4];
> };
> u32 is_fullsock;
> + u64 temp; /* Used by sock_ops_convert_ctx_access
> + * as temporary storaage of a register
typo on storage
Thanks, will fix.
> + */
> };
>
> #endif /* __LINUX_FILTER_H__ */
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 6939e69..108d16a 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -2010,7 +2010,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
> struct bpf_sock_ops_kern sock_ops;
> int ret;
>
> - memset(&sock_ops, 0, sizeof(sock_ops));
> + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
>
This lacks proper comment, stating that every field added after .temp
in struct bpf_sock_ops_kern is considered as scratch and could contain
garbage.
I assumed that one would modify this initialization appropriately when adding
a new field. But it would certainly make sense to indicate that new, non-scratch,
fields should be added before temp so there would be no need to modify this
initialization code. Makes sense?
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH bpf-next v5 04/11] bpf: Support passing args to sock_ops bpf function
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (2 preceding siblings ...)
2018-01-09 21:06 ` [PATCH bpf-next v5 03/11] bpf: Add write access to tcp_sock and sock fields Lawrence Brakmo
@ 2018-01-09 21:06 ` Lawrence Brakmo
2018-01-09 21:06 ` [PATCH bpf-next v5 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock Lawrence Brakmo
` (6 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:06 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Adds support for passing up to 4 arguments to sock_ops bpf functions. It
reusues the reply union, so the bpf_sock_ops structures are not
increased in size.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/linux/filter.h | 1 +
include/net/tcp.h | 64 ++++++++++++++++++++++++++++++++++++++++++++----
include/uapi/linux/bpf.h | 5 ++--
net/ipv4/tcp.c | 2 +-
net/ipv4/tcp_nv.c | 2 +-
net/ipv4/tcp_output.c | 2 +-
6 files changed, 66 insertions(+), 10 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 139a9a3..bbeb781 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1003,6 +1003,7 @@ struct bpf_sock_ops_kern {
struct sock *sk;
u32 op;
union {
+ u32 args[4];
u32 reply;
u32 replylong[4];
};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 108d16a..8e9111f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2005,7 +2005,7 @@ void tcp_cleanup_ulp(struct sock *sk);
* program loaded).
*/
#ifdef CONFIG_BPF
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
struct bpf_sock_ops_kern sock_ops;
int ret;
@@ -2018,6 +2018,8 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
sock_ops.sk = sk;
sock_ops.op = op;
+ if (nargs > 0)
+ memcpy(sock_ops.args, args, nargs*sizeof(u32));
ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
if (ret == 0)
@@ -2026,18 +2028,70 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
ret = -1;
return ret;
}
+
+static inline int tcp_call_bpf_1arg(struct sock *sk, int op, u32 arg)
+{
+ return tcp_call_bpf(sk, op, 1, &arg);
+}
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+ u32 args[2] = {arg1, arg2};
+
+ return tcp_call_bpf(sk, op, 2, args);
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3)
+{
+ u32 args[3] = {arg1, arg2, arg3};
+
+ return tcp_call_bpf(sk, op, 3, args);
+}
+
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3, u32 arg4)
+{
+ u32 args[4] = {arg1, arg2, arg3, arg4};
+
+ return tcp_call_bpf(sk, op, 4, args);
+}
+
#else
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
return -EPERM;
}
+
+static inline int tcp_call_bpf_1arg(struct sock *sk, int op, u32 arg)
+{
+ return -EPERM;
+}
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+ return -EPERM;
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3)
+{
+ return -EPERM;
+}
+
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3, u32 arg4)
+{
+ return -EPERM;
+}
+
#endif
static inline u32 tcp_timeout_init(struct sock *sk)
{
int timeout;
- timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+ timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL);
if (timeout <= 0)
timeout = TCP_TIMEOUT_INIT;
@@ -2048,7 +2102,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
{
int rwnd;
- rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
+ rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL);
if (rwnd < 0)
rwnd = 0;
@@ -2057,7 +2111,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
{
- return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
+ return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
}
#if IS_ENABLED(CONFIG_SMC)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 405317f..94212da 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -948,8 +948,9 @@ struct bpf_map_info {
struct bpf_sock_ops {
__u32 op;
union {
- __u32 reply;
- __u32 replylong[4];
+ __u32 args[4]; /* Optionally passed to bpf program */
+ __u32 reply; /* Returned by bpf program */
+ __u32 replylong[4]; /* Optionally returned by bpf prog */
};
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f68cb33..fcec082 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -463,7 +463,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
tcp_mtup_init(sk);
icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_metrics(sk);
- tcp_call_bpf(sk, bpf_op);
+ tcp_call_bpf(sk, bpf_op, 0, NULL);
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
}
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 0b5a05b..ddbce73 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -146,7 +146,7 @@ static void tcpnv_init(struct sock *sk)
* within a datacenter, where we have reasonable estimates of
* RTTs
*/
- base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+ base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT, 0, NULL);
if (base_rtt > 0) {
ca->nv_base_rtt = base_rtt;
ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 04be9f83..b093985 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3468,7 +3468,7 @@ int tcp_connect(struct sock *sk)
struct sk_buff *buff;
int err;
- tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
+ tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (3 preceding siblings ...)
2018-01-09 21:06 ` [PATCH bpf-next v5 04/11] bpf: Support passing args to sock_ops bpf function Lawrence Brakmo
@ 2018-01-09 21:06 ` Lawrence Brakmo
2018-01-09 23:30 ` Eric Dumazet
2018-01-09 21:06 ` [PATCH bpf-next v5 06/11] bpf: Add sock_ops RTO callback Lawrence Brakmo
` (5 subsequent siblings)
10 siblings, 1 reply; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:06 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Adds field bpf_sock_ops_flags to tcp_sock and bpf_sock_ops. Its primary
use is to determine if there should be calls to sock_ops bpf program at
various points in the TCP code. The field is initialized to zero,
disabling the calls. A sock_ops BPF program can set, per connection and
as necessary, when the connection is established.
It also adds support for reading and writting the field within a
sock_ops BPF program.
Examples of where to call the bpf program:
1) When RTO fires
2) When a packet is retransmitted
3) When the connection terminates
4) When a packet is sent
5) When a packet is received
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/linux/tcp.h | 8 ++++++++
include/uapi/linux/bpf.h | 1 +
net/core/filter.c | 7 +++++++
3 files changed, 16 insertions(+)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4f93f095..62f4388 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -373,6 +373,14 @@ struct tcp_sock {
*/
struct request_sock *fastopen_rsk;
u32 *saved_syn;
+
+/* Sock_ops bpf program related variables */
+#ifdef CONFIG_BPF
+ u32 bpf_sock_ops_flags; /* values defined in uapi/linux/tcp.h */
+#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_flags & ARG)
+#else
+#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
+#endif
};
enum tsq_enum {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 94212da..78de185 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -965,6 +965,7 @@ struct bpf_sock_ops {
*/
__u32 snd_cwnd;
__u32 srtt_us; /* Averaged RTT << 3 in usecs */
+ __u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
};
/* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 2624859..602bb76 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3843,6 +3843,7 @@ static bool sock_ops_is_valid_access(int off, int size,
switch (off) {
case offsetof(struct bpf_sock_ops, op) ...
offsetof(struct bpf_sock_ops, replylong[3]):
+ case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
break;
default:
return false;
@@ -4544,6 +4545,12 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct bpf_sock_ops, srtt_us):
SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);
break;
+
+ case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
+ SOCK_OPS_GET_OR_SET_FIELD(bpf_sock_ops_flags,
+ bpf_sock_ops_flags,
+ struct tcp_sock, type);
+ break;
}
return insn - insn_buf;
}
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH bpf-next v5 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock
2018-01-09 21:06 ` [PATCH bpf-next v5 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock Lawrence Brakmo
@ 2018-01-09 23:30 ` Eric Dumazet
2018-01-10 0:31 ` Lawrence Brakmo
0 siblings, 1 reply; 16+ messages in thread
From: Eric Dumazet @ 2018-01-09 23:30 UTC (permalink / raw)
To: Lawrence Brakmo, netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Neal Cardwell, Yuchung Cheng
On Tue, 2018-01-09 at 13:06 -0800, Lawrence Brakmo wrote:
> Adds field bpf_sock_ops_flags to tcp_sock and bpf_sock_ops. Its primary
> use is to determine if there should be calls to sock_ops bpf program at
> various points in the TCP code. The field is initialized to zero,
> disabling the calls. A sock_ops BPF program can set, per connection and
> as necessary, when the connection is established.
>
> It also adds support for reading and writting the field within a
> sock_ops BPF program.
>
> Examples of where to call the bpf program:
>
> 1) When RTO fires
> 2) When a packet is retransmitted
> 3) When the connection terminates
> 4) When a packet is sent
> 5) When a packet is received
>
> Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
> ---
> include/linux/tcp.h | 8 ++++++++
> include/uapi/linux/bpf.h | 1 +
> net/core/filter.c | 7 +++++++
> 3 files changed, 16 insertions(+)
>
> diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> index 4f93f095..62f4388 100644
> --- a/include/linux/tcp.h
> +++ b/include/linux/tcp.h
> @@ -373,6 +373,14 @@ struct tcp_sock {
> */
> struct request_sock *fastopen_rsk;
> u32 *saved_syn;
> +
> +/* Sock_ops bpf program related variables */
> +#ifdef CONFIG_BPF
> + u32 bpf_sock_ops_flags; /* values defined in uapi/linux/tcp.h */
> +#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_flags & ARG)
> +#else
> +#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
> +#endif
> };
>
It looks like we add yet another TCP socket field for some feature that
is only used by you or FB :/
At least please try to fill a hole (on 64bit kernels), instead of
adding one more.
Also, should not we reject attempts to use bits that are not yet
supported by the kernel ?
If a BPF filter expects to be called for every retransmit, but kernel
is too old, this wont work.
^ permalink raw reply [flat|nested] 16+ messages in thread* Re: [PATCH bpf-next v5 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock
2018-01-09 23:30 ` Eric Dumazet
@ 2018-01-10 0:31 ` Lawrence Brakmo
0 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-10 0:31 UTC (permalink / raw)
To: Eric Dumazet, netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Neal Cardwell, Yuchung Cheng
On 1/9/18, 3:31 PM, "Eric Dumazet" <eric.dumazet@gmail.com> wrote:
On Tue, 2018-01-09 at 13:06 -0800, Lawrence Brakmo wrote:
> Adds field bpf_sock_ops_flags to tcp_sock and bpf_sock_ops. Its primary
> use is to determine if there should be calls to sock_ops bpf program at
> various points in the TCP code. The field is initialized to zero,
> disabling the calls. A sock_ops BPF program can set, per connection and
> as necessary, when the connection is established.
>
> It also adds support for reading and writting the field within a
> sock_ops BPF program.
>
> Examples of where to call the bpf program:
>
> 1) When RTO fires
> 2) When a packet is retransmitted
> 3) When the connection terminates
> 4) When a packet is sent
> 5) When a packet is received
>
> Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
> ---
> include/linux/tcp.h | 8 ++++++++
> include/uapi/linux/bpf.h | 1 +
> net/core/filter.c | 7 +++++++
> 3 files changed, 16 insertions(+)
>
> diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> index 4f93f095..62f4388 100644
> --- a/include/linux/tcp.h
> +++ b/include/linux/tcp.h
> @@ -373,6 +373,14 @@ struct tcp_sock {
> */
> struct request_sock *fastopen_rsk;
> u32 *saved_syn;
> +
> +/* Sock_ops bpf program related variables */
> +#ifdef CONFIG_BPF
> + u32 bpf_sock_ops_flags; /* values defined in uapi/linux/tcp.h */
> +#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_flags & ARG)
> +#else
> +#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
> +#endif
> };
>
It looks like we add yet another TCP socket field for some feature that
is only used by you or FB :/
I am certainly hoping it will be used by others as well, but it is not possible
until it is available (many people expressed interest at Netdev 2.2).
At least please try to fill a hole (on 64bit kernels), instead of
adding one more.
Makes sense.
Also, should not we reject attempts to use bits that are not yet
supported by the kernel ?
If a BPF filter expects to be called for every retransmit, but kernel
is too old, this wont work.
Thanks, good point. I will add a helper function that returns which
callbacks are supported by the current kernel so the bpf program can
take appropriate action.
Eric, thank you for the feedback.
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH bpf-next v5 06/11] bpf: Add sock_ops RTO callback
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (4 preceding siblings ...)
2018-01-09 21:06 ` [PATCH bpf-next v5 05/11] bpf: Adds field bpf_sock_ops_flags to tcp_sock Lawrence Brakmo
@ 2018-01-09 21:06 ` Lawrence Brakmo
2018-01-09 21:07 ` [PATCH bpf-next v5 07/11] bpf: Add support for reading sk_state and more Lawrence Brakmo
` (4 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:06 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Adds an optional call to sock_ops BPF program based on whether the
BPF_SOCK_OPS_RTO_CB_FLAG is set in bpf_sock_ops_flags.
The BPF program is passed 2 arguments: icsk_retransmits and whether the
RTO has expired.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/uapi/linux/bpf.h | 5 +++++
include/uapi/linux/tcp.h | 3 +++
net/ipv4/tcp_timer.c | 7 +++++++
3 files changed, 15 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 78de185..e74a91b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1001,6 +1001,11 @@ enum {
* a congestion threshold. RTTs above
* this indicate congestion
*/
+ BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered.
+ * Arg1: value of icsk_retransmits
+ * Arg2: value of icsk_rto
+ * Arg3: whether RTO has expired
+ */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index b4a4f64..089c19e 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -259,6 +259,9 @@ struct tcp_md5sig {
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
};
+/* Definitions for bpf_sock_ops_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
+
/* INET_DIAG_MD5SIG */
struct tcp_diag_md5sig {
__u8 tcpm_family;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124..257abdd 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -213,11 +213,18 @@ static int tcp_write_timeout(struct sock *sk)
icsk->icsk_user_timeout);
}
tcp_fastopen_active_detect_blackhole(sk, expired);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
+ tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
+ icsk->icsk_retransmits,
+ icsk->icsk_rto, (int)expired);
+
if (expired) {
/* Has it gone just too far? */
tcp_write_err(sk);
return 1;
}
+
return 0;
}
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 07/11] bpf: Add support for reading sk_state and more
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (5 preceding siblings ...)
2018-01-09 21:06 ` [PATCH bpf-next v5 06/11] bpf: Add sock_ops RTO callback Lawrence Brakmo
@ 2018-01-09 21:07 ` Lawrence Brakmo
2018-01-09 21:07 ` [PATCH bpf-next v5 08/11] bpf: Add sock_ops R/W access to tclass & sk_txhash Lawrence Brakmo
` (3 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:07 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Add support for reading many more tcp_sock fields
state, same as sk->sk_state
rtt_min same as sk->rtt_min.s[0].v (current rtt_min)
snd_ssthresh
rcv_nxt
snd_nxt
snd_una
mss_cache
ecn_flags
rate_delivered
rate_interval_us
packets_out
retrans_out
total_retrans
segs_in
data_segs_in
segs_out
data_segs_out
bytes_received (__u64)
bytes_acked (__u64)
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/uapi/linux/bpf.h | 19 +++++++
net/core/filter.c | 136 ++++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 141 insertions(+), 14 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e74a91b..9329925 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -966,6 +966,25 @@ struct bpf_sock_ops {
__u32 snd_cwnd;
__u32 srtt_us; /* Averaged RTT << 3 in usecs */
__u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
+ __u32 state;
+ __u32 rtt_min;
+ __u32 snd_ssthresh;
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u32 mss_cache;
+ __u32 ecn_flags;
+ __u32 rate_delivered;
+ __u32 rate_interval_us;
+ __u32 packets_out;
+ __u32 retrans_out;
+ __u32 total_retrans;
+ __u32 segs_in;
+ __u32 data_segs_in;
+ __u32 segs_out;
+ __u32 data_segs_out;
+ __u64 bytes_received;
+ __u64 bytes_acked;
};
/* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 602bb76..1a156f0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3822,35 +3822,44 @@ void bpf_warn_invalid_xdp_action(u32 act)
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
-static bool __is_valid_sock_ops_access(int off, int size)
+static bool sock_ops_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ struct bpf_insn_access_aux *info)
{
+ const int size_default = sizeof(__u32);
+
if (off < 0 || off >= sizeof(struct bpf_sock_ops))
return false;
+
/* The verifier guarantees that size > 0. */
if (off % size != 0)
return false;
- if (size != sizeof(__u32))
- return false;
- return true;
-}
-
-static bool sock_ops_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 offsetof(struct bpf_sock_ops, op) ...
- offsetof(struct bpf_sock_ops, replylong[3]):
- case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
+ case bpf_ctx_range_till(struct bpf_sock_ops, op, replylong[3]):
+ case bpf_ctx_range(struct bpf_sock_ops, bpf_sock_ops_flags):
+ if (size != size_default)
+ return false;
break;
default:
return false;
}
+ } else {
+ switch (off) {
+ case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received,
+ bytes_acked):
+ if (size != sizeof(__u64))
+ return false;
+ break;
+ default:
+ if (size != size_default)
+ return false;
+ break;
+ }
}
- return __is_valid_sock_ops_access(off, size);
+ return true;
}
static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write,
@@ -4468,6 +4477,32 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
is_fullsock));
break;
+ case offsetof(struct bpf_sock_ops, state):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1);
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+ struct bpf_sock_ops_kern, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern, sk));
+ *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->dst_reg,
+ offsetof(struct sock_common, skc_state));
+ break;
+
+ case offsetof(struct bpf_sock_ops, rtt_min):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) !=
+ sizeof(struct minmax));
+ BUILD_BUG_ON(sizeof(struct minmax) <
+ sizeof(struct minmax_sample));
+
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+ struct bpf_sock_ops_kern, sk),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern, sk));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ offsetof(struct tcp_sock, rtt_min) +
+ FIELD_SIZEOF(struct minmax_sample, t));
+ break;
+
/* Helper macro for adding read access to tcp_sock or sock fields. */
#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \
do { \
@@ -4551,6 +4586,79 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
bpf_sock_ops_flags,
struct tcp_sock, type);
break;
+
+ case offsetof(struct bpf_sock_ops, snd_ssthresh):
+ SOCK_OPS_GET_FIELD(snd_ssthresh, snd_ssthresh, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, rcv_nxt):
+ SOCK_OPS_GET_FIELD(rcv_nxt, rcv_nxt, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, snd_nxt):
+ SOCK_OPS_GET_FIELD(snd_nxt, snd_nxt, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, snd_una):
+ SOCK_OPS_GET_FIELD(snd_una, snd_una, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, mss_cache):
+ SOCK_OPS_GET_FIELD(mss_cache, mss_cache, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, ecn_flags):
+ SOCK_OPS_GET_FIELD(ecn_flags, ecn_flags, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, rate_delivered):
+ SOCK_OPS_GET_FIELD(rate_delivered, rate_delivered,
+ struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, rate_interval_us):
+ SOCK_OPS_GET_FIELD(rate_interval_us, rate_interval_us,
+ struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, packets_out):
+ SOCK_OPS_GET_FIELD(packets_out, packets_out, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, retrans_out):
+ SOCK_OPS_GET_FIELD(retrans_out, retrans_out, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, total_retrans):
+ SOCK_OPS_GET_FIELD(total_retrans, total_retrans,
+ struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, segs_in):
+ SOCK_OPS_GET_FIELD(segs_in, segs_in, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, data_segs_in):
+ SOCK_OPS_GET_FIELD(data_segs_in, data_segs_in, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, segs_out):
+ SOCK_OPS_GET_FIELD(segs_out, segs_out, struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, data_segs_out):
+ SOCK_OPS_GET_FIELD(data_segs_out, data_segs_out,
+ struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, bytes_received):
+ SOCK_OPS_GET_FIELD(bytes_received, bytes_received,
+ struct tcp_sock);
+ break;
+
+ case offsetof(struct bpf_sock_ops, bytes_acked):
+ SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock);
+ break;
}
return insn - insn_buf;
}
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 08/11] bpf: Add sock_ops R/W access to tclass & sk_txhash
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (6 preceding siblings ...)
2018-01-09 21:07 ` [PATCH bpf-next v5 07/11] bpf: Add support for reading sk_state and more Lawrence Brakmo
@ 2018-01-09 21:07 ` Lawrence Brakmo
2018-01-09 21:07 ` [PATCH bpf-next v5 09/11] bpf: Add BPF_SOCK_OPS_RETRANS_CB Lawrence Brakmo
` (2 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:07 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Adds direct R/W access to sk_txhash and access to tclass for ipv6 flows
through getsockopt and setsockopt. Sample usage for tclass:
bpf_getsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, sizeof(v))
where skops is a pointer to the ctx (struct bpf_sock_ops).
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/uapi/linux/bpf.h | 1 +
net/core/filter.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 48 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9329925..b5f698f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -985,6 +985,7 @@ struct bpf_sock_ops {
__u32 data_segs_out;
__u64 bytes_received;
__u64 bytes_acked;
+ __u32 sk_txhash;
};
/* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 1a156f0..d458e75 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3230,6 +3230,29 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
ret = -EINVAL;
}
#ifdef CONFIG_INET
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (level == SOL_IPV6) {
+ if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
+ return -EINVAL;
+
+ val = *((int *)optval);
+ /* Only some options are supported */
+ switch (optname) {
+ case IPV6_TCLASS:
+ if (val < -1 || val > 0xff) {
+ ret = -EINVAL;
+ } else {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (val == -1)
+ val = 0;
+ np->tclass = val;
+ }
+ break;
+ default:
+ ret = -EINVAL;
+ }
+#endif
} else if (level == SOL_TCP &&
sk->sk_prot->setsockopt == tcp_setsockopt) {
if (optname == TCP_CONGESTION) {
@@ -3239,7 +3262,8 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
strncpy(name, optval, min_t(long, optlen,
TCP_CA_NAME_MAX-1));
name[TCP_CA_NAME_MAX-1] = 0;
- ret = tcp_set_congestion_control(sk, name, false, reinit);
+ ret = tcp_set_congestion_control(sk, name, false,
+ reinit);
} else {
struct tcp_sock *tp = tcp_sk(sk);
@@ -3305,6 +3329,22 @@ BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
} else {
goto err_clear;
}
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (level == SOL_IPV6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
+ goto err_clear;
+
+ /* Only some options are supported */
+ switch (optname) {
+ case IPV6_TCLASS:
+ *((int *)optval) = (int)np->tclass;
+ break;
+ default:
+ goto err_clear;
+ }
+#endif
} else {
goto err_clear;
}
@@ -3839,6 +3879,7 @@ static bool sock_ops_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range_till(struct bpf_sock_ops, op, replylong[3]):
case bpf_ctx_range(struct bpf_sock_ops, bpf_sock_ops_flags):
+ case bpf_ctx_range(struct bpf_sock_ops, sk_txhash):
if (size != size_default)
return false;
break;
@@ -4659,6 +4700,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct bpf_sock_ops, bytes_acked):
SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock);
break;
+
+ case offsetof(struct bpf_sock_ops, sk_txhash):
+ SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash,
+ struct sock, type);
+ break;
}
return insn - insn_buf;
}
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 09/11] bpf: Add BPF_SOCK_OPS_RETRANS_CB
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (7 preceding siblings ...)
2018-01-09 21:07 ` [PATCH bpf-next v5 08/11] bpf: Add sock_ops R/W access to tclass & sk_txhash Lawrence Brakmo
@ 2018-01-09 21:07 ` Lawrence Brakmo
2018-01-09 21:07 ` [PATCH bpf-next v5 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB Lawrence Brakmo
2018-01-09 21:07 ` [PATCH bpf-next v5 11/11] bpf: add selftest for tcpbpf Lawrence Brakmo
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:07 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Adds support for calling sock_ops BPF program when there is a
retransmission. Two arguments are used; one for the sequence number and
other for the number of segments retransmitted. Does not include syn-ack
retransmissions.
New op: BPF_SOCK_OPS_RETRANS_CB.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/uapi/linux/bpf.h | 4 ++++
include/uapi/linux/tcp.h | 1 +
net/ipv4/tcp_output.c | 3 +++
3 files changed, 8 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b5f698f..5b804bc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1026,6 +1026,10 @@ enum {
* Arg2: value of icsk_rto
* Arg3: whether RTO has expired
*/
+ BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted.
+ * Arg1: sequence number of 1st byte
+ * Arg2: # segments
+ */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 089c19e..dc36d3c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -261,6 +261,7 @@ struct tcp_md5sig {
/* Definitions for bpf_sock_ops_flags */
#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
/* INET_DIAG_MD5SIG */
struct tcp_diag_md5sig {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b093985..8109675 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2907,6 +2907,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
if (likely(!err)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
trace_tcp_retransmit_skb(sk, skb);
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+ tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+ TCP_SKB_CB(skb)->seq, segs);
} else if (err != -EBUSY) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
}
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (8 preceding siblings ...)
2018-01-09 21:07 ` [PATCH bpf-next v5 09/11] bpf: Add BPF_SOCK_OPS_RETRANS_CB Lawrence Brakmo
@ 2018-01-09 21:07 ` Lawrence Brakmo
2018-01-09 21:07 ` [PATCH bpf-next v5 11/11] bpf: add selftest for tcpbpf Lawrence Brakmo
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:07 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Adds support for calling sock_ops BPF program when there is a TCP state
change. Two arguments are used; one for the old state and another for
the new state.
There is a new enum in include/uapi/linux/bpf.h that exports the TCP
states that prepends BPF_ to the current TCP state names. If it is ever
necessary to change the internal TCP state values (other than adding
more to the end), then it will become necessary to convert from the
internal TCP state value to the BPF value before calling the BPF
sock_ops function. There are a set of compile checks added in tcp.c
to detect if the internal and BPF values differ so we can make the
necessary fixes.
New op: BPF_SOCK_OPS_STATE_CB.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++
include/uapi/linux/tcp.h | 1 +
net/ipv4/tcp.c | 24 ++++++++++++++++++++++++
3 files changed, 51 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5b804bc..b3c4fc7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1030,6 +1030,32 @@ enum {
* Arg1: sequence number of 1st byte
* Arg2: # segments
*/
+ BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state.
+ * Arg1: old_state
+ * Arg2: new_state
+ */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+ BPF_TCP_ESTABLISHED = 1,
+ BPF_TCP_SYN_SENT,
+ BPF_TCP_SYN_RECV,
+ BPF_TCP_FIN_WAIT1,
+ BPF_TCP_FIN_WAIT2,
+ BPF_TCP_TIME_WAIT,
+ BPF_TCP_CLOSE,
+ BPF_TCP_CLOSE_WAIT,
+ BPF_TCP_LAST_ACK,
+ BPF_TCP_LISTEN,
+ BPF_TCP_CLOSING, /* Now a valid state */
+ BPF_TCP_NEW_SYN_RECV,
+
+ BPF_TCP_MAX_STATES /* Leave at the end! */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index dc36d3c..211322c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -262,6 +262,7 @@ struct tcp_md5sig {
/* Definitions for bpf_sock_ops_flags */
#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2)
/* INET_DIAG_MD5SIG */
struct tcp_diag_md5sig {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fcec082..5db8669 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2042,6 +2042,30 @@ void tcp_set_state(struct sock *sk, int state)
{
int oldstate = sk->sk_state;
+ /* We defined a new enum for TCP states that are exported in BPF
+ * so as not force the internal TCP states to be frozen. The
+ * following checks will detect if an internal state value ever
+ * differs from the BPF value. If this ever happens, then we will
+ * need to remap the internal value to the BPF value before calling
+ * tcp_call_bpf_2arg.
+ */
+ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED);
+ BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT);
+ BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV);
+ BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1);
+ BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2);
+ BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT);
+ BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK);
+ BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING);
+ BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV);
+ BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
+ tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
+
switch (state) {
case TCP_ESTABLISHED:
if (oldstate != TCP_ESTABLISHED)
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH bpf-next v5 11/11] bpf: add selftest for tcpbpf
2018-01-09 21:06 [PATCH bpf-next v5 00/11] bpf: More sock_ops callbacks Lawrence Brakmo
` (9 preceding siblings ...)
2018-01-09 21:07 ` [PATCH bpf-next v5 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB Lawrence Brakmo
@ 2018-01-09 21:07 ` Lawrence Brakmo
10 siblings, 0 replies; 16+ messages in thread
From: Lawrence Brakmo @ 2018-01-09 21:07 UTC (permalink / raw)
To: netdev
Cc: Kernel Team, Blake Matheny, Alexei Starovoitov, Daniel Borkmann,
Eric Dumazet, Neal Cardwell, Yuchung Cheng
Added a selftest for tcpbpf (sock_ops) that checks that the appropriate
callbacks occured and that it can access tcp_sock fields and that their
values are correct.
Run with command: ./test_tcpbpf_user
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
tools/include/uapi/linux/bpf.h | 70 +++++++++++++++-
tools/testing/selftests/bpf/Makefile | 5 +-
tools/testing/selftests/bpf/tcp_client.py | 52 ++++++++++++
tools/testing/selftests/bpf/tcp_server.py | 79 ++++++++++++++++++
tools/testing/selftests/bpf/test_tcpbpf.h | 14 ++++
tools/testing/selftests/bpf/test_tcpbpf_kern.c | 109 +++++++++++++++++++++++++
tools/testing/selftests/bpf/test_tcpbpf_user.c | 103 +++++++++++++++++++++++
7 files changed, 427 insertions(+), 5 deletions(-)
create mode 100755 tools/testing/selftests/bpf/tcp_client.py
create mode 100755 tools/testing/selftests/bpf/tcp_server.py
create mode 100644 tools/testing/selftests/bpf/test_tcpbpf.h
create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_kern.c
create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_user.c
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e8c60a..1fcd86f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -945,8 +945,9 @@ struct bpf_map_info {
struct bpf_sock_ops {
__u32 op;
union {
- __u32 reply;
- __u32 replylong[4];
+ __u32 args[4]; /* Optionally passed to bpf program */
+ __u32 reply; /* Returned by bpf program */
+ __u32 replylong[4]; /* Optionally returned by bpf prog */
};
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
@@ -955,6 +956,33 @@ struct bpf_sock_ops {
__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 */
+ __u32 is_fullsock; /* Some TCP fields are only valid if
+ * there is a full socket. If not, the
+ * fields read as zero.
+ */
+ __u32 snd_cwnd;
+ __u32 srtt_us; /* Averaged RTT << 3 in usecs */
+ __u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
+ __u32 state;
+ __u32 rtt_min;
+ __u32 snd_ssthresh;
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u32 mss_cache;
+ __u32 ecn_flags;
+ __u32 rate_delivered;
+ __u32 rate_interval_us;
+ __u32 packets_out;
+ __u32 retrans_out;
+ __u32 total_retrans;
+ __u32 segs_in;
+ __u32 data_segs_in;
+ __u32 segs_out;
+ __u32 data_segs_out;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+ __u32 sk_txhash;
};
/* List of known BPF sock_ops operators.
@@ -990,6 +1018,41 @@ enum {
* a congestion threshold. RTTs above
* this indicate congestion
*/
+ BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered.
+ * Arg1: value of icsk_retransmits
+ * Arg2: value of icsk_rto
+ * Arg3: whether RTO has expired
+ */
+ BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted.
+ * Arg1: sequence number of 1st byte
+ * Arg2: # segments
+ */
+ BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state.
+ * Arg1: old_state
+ * Arg2: new_state
+ */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+ BPF_TCP_ESTABLISHED = 1,
+ BPF_TCP_SYN_SENT,
+ BPF_TCP_SYN_RECV,
+ BPF_TCP_FIN_WAIT1,
+ BPF_TCP_FIN_WAIT2,
+ BPF_TCP_TIME_WAIT,
+ BPF_TCP_CLOSE,
+ BPF_TCP_CLOSE_WAIT,
+ BPF_TCP_LAST_ACK,
+ BPF_TCP_LISTEN,
+ BPF_TCP_CLOSING, /* Now a valid state */
+ BPF_TCP_NEW_SYN_RECV,
+
+ BPF_TCP_MAX_STATES /* Leave at the end! */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
@@ -1009,7 +1072,8 @@ struct bpf_perf_event_value {
#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
struct bpf_cgroup_dev_ctx {
- __u32 access_type; /* (access << 16) | type */
+ /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+ __u32 access_type;
__u32 major;
__u32 minor;
};
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a8aa7e2..22cc565 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -14,12 +14,13 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i
LDLIBS += -lcap -lelf -lrt
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
- test_align test_verifier_log test_dev_cgroup
+ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
- test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o
+ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+ test_tcpbpf_kern.o
TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
test_offload.py
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
new file mode 100755
index 0000000..ac2ce32
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -0,0 +1,52 @@
+#!/usr/local/bin/python
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+ buf = ''
+ while len(buf) < n:
+ rem = n - len(buf)
+ try: s = sock.recv(rem)
+ except (socket.error), e: return ''
+ buf += s
+ return buf
+
+def send(sock, s):
+ total = len(s)
+ count = 0
+ while count < total:
+ try: n = sock.send(s)
+ except (socket.error), e: n = 0
+ if n == 0:
+ return count;
+ count += n
+ return count
+
+
+serverPort = int(sys.argv[1])
+HostName = socket.gethostname()
+
+time.sleep(1)
+
+# create active socket
+sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+try:
+ sock.connect((HostName, serverPort))
+except socket.error as e:
+ sys.exit(1)
+
+buf = ''
+n = 0
+while n < 1000:
+ buf += '+'
+ n += 1
+
+n = send(sock, buf)
+n = read(sock, 500)
+sys.exit(0)
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
new file mode 100755
index 0000000..9e5db0d
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -0,0 +1,79 @@
+#!/usr/local/bin/python
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+ buf = ''
+ while len(buf) < n:
+ rem = n - len(buf)
+ try: s = sock.recv(rem)
+ except (socket.error), e: return ''
+ buf += s
+ return buf
+
+def send(sock, s):
+ total = len(s)
+ count = 0
+ while count < total:
+ try: n = sock.send(s)
+ except (socket.error), e: n = 0
+ if n == 0:
+ return count;
+ count += n
+ return count
+
+
+SERVER_PORT = 12877
+MAX_PORTS = 2
+
+serverPort = SERVER_PORT
+serverSocket = None
+
+HostName = socket.gethostname()
+
+# create passive socket
+serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+host = socket.gethostname()
+
+while serverPort < SERVER_PORT + 5:
+ try: serverSocket.bind((host, serverPort))
+ except socket.error as msg:
+ serverPort += 1
+ continue
+ break
+
+cmdStr = ("./tcp_client.py %d &") % (serverPort)
+os.system(cmdStr)
+
+buf = ''
+n = 0
+while n < 500:
+ buf += '.'
+ n += 1
+
+serverSocket.listen(MAX_PORTS)
+readList = [serverSocket]
+
+while True:
+ readyRead, readyWrite, inError = \
+ select.select(readList, [], [], 10)
+
+ if len(readyRead) > 0:
+ waitCount = 0
+ for sock in readyRead:
+ if sock == serverSocket:
+ (clientSocket, address) = serverSocket.accept()
+ address = str(address[0])
+ readList.append(clientSocket)
+ else:
+ s = read(sock, 1000)
+ n = send(sock, buf)
+ sock.close()
+ time.sleep(1)
+ sys.exit(0)
diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
new file mode 100644
index 0000000..a9d5372
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpbpf_globals {
+ __u32 event_map;
+ __u32 total_retrans;
+ __u32 data_segs_in;
+ __u32 data_segs_out;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+};
+#endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
new file mode 100644
index 0000000..e29e010
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcbbpf.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct tcpbpf_globals),
+ .max_entries = 2,
+};
+
+static inline void update_event_map(int event)
+{
+ __u32 key = 0;
+ struct tcpbpf_globals g, *gp;
+
+ gp = bpf_map_lookup_elem(&global_map, &key);
+ if (gp == NULL) {
+ struct tcpbpf_globals g = {0, 0, 0, 0, 0, 0};
+
+ g.event_map |= (1 << event);
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ } else {
+ g = *gp;
+ g.event_map |= (1 << event);
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ }
+}
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+ int rv = -1;
+ int op;
+ int init_seq = 0;
+ int ret = 0;
+ int v = 0;
+
+ /* For testing purposes, only execute rest of BPF program
+ * if remote port number is in the range 12877..12887
+ * I.e. the active side of the connection
+ */
+ if ((bpf_ntohl(skops->remote_port) < 12877 ||
+ bpf_ntohl(skops->remote_port) >= 12887)) {
+ skops->reply = -1;
+ return 1;
+ }
+
+ op = (int) skops->op;
+
+ update_event_map(op);
+
+ switch (op) {
+ case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+ skops->bpf_sock_ops_flags = 0xfff;
+ init_seq = skops->snd_nxt;
+ break;
+ case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+ init_seq = skops->snd_nxt;
+ skops->bpf_sock_ops_flags = 0xfff;
+ skops->sk_txhash = 0x12345f;
+ v = 0xff;
+ ret = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
+ sizeof(v));
+ break;
+ case BPF_SOCK_OPS_RTO_CB:
+ break;
+ case BPF_SOCK_OPS_RETRANS_CB:
+ break;
+ case BPF_SOCK_OPS_STATE_CB:
+ if (skops->args[1] == BPF_TCP_CLOSE) {
+ __u32 key = 0;
+ struct tcpbpf_globals g, *gp;
+
+ gp = bpf_map_lookup_elem(&global_map, &key);
+ if (!gp)
+ break;
+ g = *gp;
+ g.total_retrans = skops->total_retrans;
+ g.data_segs_in = skops->data_segs_in;
+ g.data_segs_out = skops->data_segs_out;
+ g.bytes_received = skops->bytes_received;
+ g.bytes_acked = skops->bytes_acked;
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ }
+ break;
+ default:
+ rv = -1;
+ }
+ skops->reply = rv;
+ return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
new file mode 100644
index 0000000..266242f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <assert.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include <linux/perf_event.h>
+#include "test_tcpbpf.h"
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+ const char *name)
+{
+ struct bpf_map *map;
+
+ map = bpf_object__find_map_by_name(obj, name);
+ if (!map) {
+ printf("%s:FAIL:map '%s' not found\n", test, name);
+ return -1;
+ }
+ return bpf_map__fd(map);
+}
+
+#define SYSTEM(CMD) \
+ do { \
+ if (system(CMD)) { \
+ printf("system(%s) FAILS!\n", CMD); \
+ } \
+ } while (0)
+
+int main(int argc, char **argv)
+{
+ struct tcpbpf_globals g = {0, 0, 0, 0, 0, 0};
+ __u32 key = 0;
+ int rv;
+ int pid;
+ int error = EXIT_FAILURE;
+ int cg_fd, prog_fd, map_fd;
+ char cmd[100], *dir;
+ const char *file = "test_tcpbpf_kern.o";
+ struct bpf_object *obj;
+ struct stat buffer;
+
+ dir = "/tmp/cgroupv2/foo";
+
+ if (stat(dir, &buffer) != 0) {
+ SYSTEM("mkdir -p /tmp/cgroupv2");
+ SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
+ SYSTEM("mkdir -p /tmp/cgroupv2/foo");
+ }
+ pid = (int) getpid();
+ sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
+ SYSTEM(cmd);
+
+ cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
+ if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+ printf("FAILED: load_bpf_file failed for: %s\n", file);
+ goto err;
+ }
+
+ rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+ if (rv) {
+ printf("FAILED: bpf_prog_attach: %d (%s)\n",
+ error, strerror(errno));
+ goto err;
+ }
+
+ SYSTEM("./tcp_server.py");
+
+ map_fd = bpf_find_map(__func__, obj, "global_map");
+ if (map_fd < 0)
+ goto err;
+
+ rv = bpf_map_lookup_elem(map_fd, &key, &g);
+ if (rv != 0) {
+ printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+ goto err;
+ }
+
+ if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
+ g.data_segs_in != 1 || g.data_segs_out != 1 ||
+ g.event_map != 0x45e) {
+ printf("FAILED: Wrong stats\n");
+ goto err;
+ }
+ printf("PASSED!\n");
+ error = 0;
+err:
+ bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+ return error;
+}
--
2.9.5
^ permalink raw reply related [flat|nested] 16+ messages in thread