From b73042b8a28e2603ac178295ab96c876ba5a97a1 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:08 -0800
Subject: bpf: Add write access to tcp_sock and sock fields

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>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h | 9 +++++++++
 include/net/tcp.h      | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 425056c7f96c..daa5a676335f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1007,6 +1007,15 @@ struct bpf_sock_ops_kern {
 		u32 replylong[4];
 	};
 	u32	is_fullsock;
+	u64	temp;			/* temp and everything after is not
+					 * initialized to 0 before calling
+					 * the BPF program. New fields that
+					 * should be initialized to 0 should
+					 * be inserted before temp.
+					 * temp is scratch storage used by
+					 * sock_ops_convert_ctx_access
+					 * as temporary storage of a register.
+					 */
 };
 
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5a1d26a18599..6092eaff61cf 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2011,7 +2011,7 @@ 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);
-- 
cgit v1.2.3-59-g8ed1b


From de525be2ca2734865d29c4b67ddd29913b214906 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:09 -0800
Subject: bpf: Support passing args to sock_ops bpf function

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>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h   |  1 +
 include/net/tcp.h        | 40 +++++++++++++++++++++++++++++++++++-----
 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, 42 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index daa5a676335f..20384c4bed25 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 6092eaff61cf..093e967a2960 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2006,7 +2006,7 @@ 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;
@@ -2019,6 +2019,8 @@ 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(*args));
 
 	ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
 	if (ret == 0)
@@ -2027,18 +2029,46 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 		ret = -1;
 	return ret;
 }
+
+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);
+}
+
 #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_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;
+}
+
 #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;
@@ -2049,7 +2079,7 @@ 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;
@@ -2058,7 +2088,7 @@ 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 406c19d6016b..8d5874c2c4ff 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -952,8 +952,9 @@ 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 d7cf861bf699..88b62441e7e9 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 0b5a05bd82e3..ddbce73edae8 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 95461f02ac9a..d12f7f71c1c4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3469,7 +3469,7 @@ 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. */
-- 
cgit v1.2.3-59-g8ed1b


From b13d880721729384757f235166068c315326f4a1 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:10 -0800
Subject: bpf: Adds field bpf_sock_ops_cb_flags to tcp_sock

Adds field bpf_sock_ops_cb_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 it, 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. Reading is done by accessing the field directly.
However, writing is done through the helper function
bpf_sock_ops_cb_flags_set, in order to return an error if a BPF program
is trying to set a callback that is not supported in the current kernel
(i.e. running an older kernel). The helper function returns 0 if it was
able to set all of the bits set in the argument, a positive number
containing the bits that could not be set, or -EINVAL if the socket is
not a full TCP socket.

Examples of where one could 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>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/tcp.h      | 11 +++++++++++
 include/uapi/linux/bpf.h | 17 ++++++++++++++++-
 net/core/filter.c        | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 61 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4f93f0953c41..8f4c54986f97 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -335,6 +335,17 @@ struct tcp_sock {
 
 	int			linger2;
 
+
+/* Sock_ops bpf program related variables */
+#ifdef CONFIG_BPF
+	u8	bpf_sock_ops_cb_flags;  /* Control calling BPF programs
+					 * values defined in uapi/linux/tcp.h
+					 */
+#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG)
+#else
+#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
+#endif
+
 /* Receiver side RTT estimation */
 	struct {
 		u32	rtt_us;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8d5874c2c4ff..aa128407c44d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -642,6 +642,14 @@ union bpf_attr {
  *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
+ * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
+ *     Set callback flags for sock_ops
+ *     @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
+ *     @flags: flags value
+ *     Return: 0 for no error
+ *             -EINVAL if there is no full tcp socket
+ *             bits in flags that are not supported by current kernel
+ *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
  *     Grow or shrink room in sk_buff.
  *     @skb: pointer to skb
@@ -748,7 +756,8 @@ union bpf_attr {
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
 	FN(getsockopt),			\
-	FN(override_return),
+	FN(override_return),		\
+	FN(sock_ops_cb_flags_set),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -969,8 +978,14 @@ struct bpf_sock_ops {
 				 */
 	__u32 snd_cwnd;
 	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
+	__u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
 };
 
+/* Definitions for bpf_sock_ops_cb_flags */
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0		/* Mask of all currently
+							 * supported cb flags
+							 */
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
diff --git a/net/core/filter.c b/net/core/filter.c
index c356ec02b1a5..6936d19ac736 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3328,6 +3328,33 @@ static const struct bpf_func_proto bpf_getsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, argval)
+{
+	struct sock *sk = bpf_sock->sk;
+	int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;
+
+	if (!sk_fullsock(sk))
+		return -EINVAL;
+
+#ifdef CONFIG_INET
+	if (val)
+		tcp_sk(sk)->bpf_sock_ops_cb_flags = val;
+
+	return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS);
+#else
+	return -EINVAL;
+#endif
+}
+
+static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = {
+	.func		= bpf_sock_ops_cb_flags_set,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3510,6 +3537,8 @@ static const struct bpf_func_proto *
 		return &bpf_setsockopt_proto;
 	case BPF_FUNC_getsockopt:
 		return &bpf_getsockopt_proto;
+	case BPF_FUNC_sock_ops_cb_flags_set:
+		return &bpf_sock_ops_cb_flags_set_proto;
 	case BPF_FUNC_sock_map_update:
 		return &bpf_sock_map_update_proto;
 	default:
@@ -4546,6 +4575,11 @@ 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_cb_flags):
+		SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags,
+				   struct tcp_sock);
+		break;
 	}
 	return insn - insn_buf;
 }
-- 
cgit v1.2.3-59-g8ed1b


From f89013f66d0f1a0dad44c513318efb706399a36b Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:11 -0800
Subject: bpf: Add sock_ops RTO callback

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>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 8 +++++++-
 net/ipv4/tcp_timer.c     | 7 +++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index aa128407c44d..c8cecf9cf5bd 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -982,7 +982,8 @@ struct bpf_sock_ops {
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0		/* Mask of all currently
+#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x1		/* Mask of all currently
 							 * supported cb flags
 							 */
 
@@ -1019,6 +1020,11 @@ 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/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124cdbda..257abdde23b0 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;
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From 44f0e43037d3a17b043843ba67610ac7c7e37db6 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:12 -0800
Subject: bpf: Add support for reading sk_state and more

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
  lost_out
  sacked_out
  sk_txhash
  bytes_received (__u64)
  bytes_acked    (__u64)

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  22 ++++++++
 net/core/filter.c        | 143 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 154 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c8cecf9cf5bd..46520eae37fa 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -979,6 +979,28 @@ struct bpf_sock_ops {
 	__u32 snd_cwnd;
 	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
 	__u32 bpf_sock_ops_cb_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;
+	__u32 lost_out;
+	__u32 sacked_out;
+	__u32 sk_txhash;
+	__u64 bytes_received;
+	__u64 bytes_acked;
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
diff --git a/net/core/filter.c b/net/core/filter.c
index 6936d19ac736..a858ebc4ece4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3855,33 +3855,43 @@ 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, reply):
+			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,
@@ -4498,6 +4508,32 @@ 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 {								      \
@@ -4580,6 +4616,91 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags,
 				   struct tcp_sock);
 		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, lost_out):
+		SOCK_OPS_GET_FIELD(lost_out, lost_out, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, sacked_out):
+		SOCK_OPS_GET_FIELD(sacked_out, sacked_out, struct tcp_sock);
+		break;
+
+	case offsetof(struct bpf_sock_ops, sk_txhash):
+		SOCK_OPS_GET_FIELD(sk_txhash, sk_txhash, struct 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;
 }
-- 
cgit v1.2.3-59-g8ed1b


From a31ad29e6a30cb0b9084a9425b819cdcd97273ce Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:14 -0800
Subject: bpf: Add BPF_SOCK_OPS_RETRANS_CB

Adds support for calling sock_ops BPF program when there is a
retransmission. Three arguments are used; one for the sequence number,
another for the number of segments retransmitted, and the last one for
the return value of tcp_transmit_skb (0 => success).
Does not include syn-ack retransmissions.

New op: BPF_SOCK_OPS_RETRANS_CB.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 9 ++++++++-
 net/ipv4/tcp_output.c    | 4 ++++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 46520eae37fa..31c93a0bdbc2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1005,7 +1005,8 @@ struct bpf_sock_ops {
 
 /* Definitions for bpf_sock_ops_cb_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x1		/* Mask of all currently
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x3		/* Mask of all currently
 							 * supported cb flags
 							 */
 
@@ -1047,6 +1048,12 @@ 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
+					 * Arg3: return value of
+					 *       tcp_transmit_skb (0 => success)
+					 */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d12f7f71c1c4..e9f985e42405 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2905,6 +2905,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
 
+	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+		tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+				  TCP_SKB_CB(skb)->seq, segs, err);
+
 	if (likely(!err)) {
 		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
 		trace_tcp_retransmit_skb(sk, skb);
-- 
cgit v1.2.3-59-g8ed1b


From d44874910a26f3a8f81edf873a2473363f07f660 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:15 -0800
Subject: bpf: Add BPF_SOCK_OPS_STATE_CB

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>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 29 ++++++++++++++++++++++++++++-
 net/ipv4/tcp.c           | 24 ++++++++++++++++++++++++
 2 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 31c93a0bdbc2..db6bdc375126 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1006,7 +1006,8 @@ struct bpf_sock_ops {
 /* Definitions for bpf_sock_ops_cb_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
 #define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x3		/* Mask of all currently
+#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7		/* Mask of all currently
 							 * supported cb flags
 							 */
 
@@ -1054,6 +1055,32 @@ enum {
 					 * Arg3: return value of
 					 *       tcp_transmit_skb (0 => success)
 					 */
+	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/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 88b62441e7e9..f013ddc191e0 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)
-- 
cgit v1.2.3-59-g8ed1b


From 5e581dad4fec0e6d062740dc35b8dc248b39d224 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 26 Jan 2018 23:33:38 +0100
Subject: bpf: make unknown opcode handling more robust

Recent findings by syzcaller fixed in 7891a87efc71 ("bpf: arsh is
not supported in 32 bit alu thus reject it") triggered a warning
in the interpreter due to unknown opcode not being rejected by
the verifier. The 'return 0' for an unknown opcode is really not
optimal, since with BPF to BPF calls, this would go untracked by
the verifier.

Do two things here to improve the situation: i) perform basic insn
sanity check early on in the verification phase and reject every
non-uapi insn right there. The bpf_opcode_in_insntable() table
reuses the same mapping as the jumptable in ___bpf_prog_run() sans
the non-public mappings. And ii) in ___bpf_prog_run() we do need
to BUG in the case where the verifier would ever create an unknown
opcode due to some rewrites.

Note that JITs do not have such issues since they would punt to
interpreter in these situations. Moreover, the BPF_JIT_ALWAYS_ON
would also help to avoid such unknown opcodes in the first place.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h |   2 +
 kernel/bpf/core.c      | 250 ++++++++++++++++++++++++++++---------------------
 kernel/bpf/verifier.c  |   7 ++
 3 files changed, 154 insertions(+), 105 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 20384c4bed25..276932d75975 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -688,6 +688,8 @@ static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
 void bpf_prog_free(struct bpf_prog *fp);
 
+bool bpf_opcode_in_insntable(u8 code);
+
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 3aa0658add76..8301de2d1f96 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -782,6 +782,137 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 EXPORT_SYMBOL_GPL(__bpf_call_base);
 
+/* All UAPI available opcodes. */
+#define BPF_INSN_MAP(INSN_2, INSN_3)		\
+	/* 32 bit ALU operations. */		\
+	/*   Register based. */			\
+	INSN_3(ALU, ADD, X),			\
+	INSN_3(ALU, SUB, X),			\
+	INSN_3(ALU, AND, X),			\
+	INSN_3(ALU, OR,  X),			\
+	INSN_3(ALU, LSH, X),			\
+	INSN_3(ALU, RSH, X),			\
+	INSN_3(ALU, XOR, X),			\
+	INSN_3(ALU, MUL, X),			\
+	INSN_3(ALU, MOV, X),			\
+	INSN_3(ALU, DIV, X),			\
+	INSN_3(ALU, MOD, X),			\
+	INSN_2(ALU, NEG),			\
+	INSN_3(ALU, END, TO_BE),		\
+	INSN_3(ALU, END, TO_LE),		\
+	/*   Immediate based. */		\
+	INSN_3(ALU, ADD, K),			\
+	INSN_3(ALU, SUB, K),			\
+	INSN_3(ALU, AND, K),			\
+	INSN_3(ALU, OR,  K),			\
+	INSN_3(ALU, LSH, K),			\
+	INSN_3(ALU, RSH, K),			\
+	INSN_3(ALU, XOR, K),			\
+	INSN_3(ALU, MUL, K),			\
+	INSN_3(ALU, MOV, K),			\
+	INSN_3(ALU, DIV, K),			\
+	INSN_3(ALU, MOD, K),			\
+	/* 64 bit ALU operations. */		\
+	/*   Register based. */			\
+	INSN_3(ALU64, ADD,  X),			\
+	INSN_3(ALU64, SUB,  X),			\
+	INSN_3(ALU64, AND,  X),			\
+	INSN_3(ALU64, OR,   X),			\
+	INSN_3(ALU64, LSH,  X),			\
+	INSN_3(ALU64, RSH,  X),			\
+	INSN_3(ALU64, XOR,  X),			\
+	INSN_3(ALU64, MUL,  X),			\
+	INSN_3(ALU64, MOV,  X),			\
+	INSN_3(ALU64, ARSH, X),			\
+	INSN_3(ALU64, DIV,  X),			\
+	INSN_3(ALU64, MOD,  X),			\
+	INSN_2(ALU64, NEG),			\
+	/*   Immediate based. */		\
+	INSN_3(ALU64, ADD,  K),			\
+	INSN_3(ALU64, SUB,  K),			\
+	INSN_3(ALU64, AND,  K),			\
+	INSN_3(ALU64, OR,   K),			\
+	INSN_3(ALU64, LSH,  K),			\
+	INSN_3(ALU64, RSH,  K),			\
+	INSN_3(ALU64, XOR,  K),			\
+	INSN_3(ALU64, MUL,  K),			\
+	INSN_3(ALU64, MOV,  K),			\
+	INSN_3(ALU64, ARSH, K),			\
+	INSN_3(ALU64, DIV,  K),			\
+	INSN_3(ALU64, MOD,  K),			\
+	/* Call instruction. */			\
+	INSN_2(JMP, CALL),			\
+	/* Exit instruction. */			\
+	INSN_2(JMP, EXIT),			\
+	/* Jump instructions. */		\
+	/*   Register based. */			\
+	INSN_3(JMP, JEQ,  X),			\
+	INSN_3(JMP, JNE,  X),			\
+	INSN_3(JMP, JGT,  X),			\
+	INSN_3(JMP, JLT,  X),			\
+	INSN_3(JMP, JGE,  X),			\
+	INSN_3(JMP, JLE,  X),			\
+	INSN_3(JMP, JSGT, X),			\
+	INSN_3(JMP, JSLT, X),			\
+	INSN_3(JMP, JSGE, X),			\
+	INSN_3(JMP, JSLE, X),			\
+	INSN_3(JMP, JSET, X),			\
+	/*   Immediate based. */		\
+	INSN_3(JMP, JEQ,  K),			\
+	INSN_3(JMP, JNE,  K),			\
+	INSN_3(JMP, JGT,  K),			\
+	INSN_3(JMP, JLT,  K),			\
+	INSN_3(JMP, JGE,  K),			\
+	INSN_3(JMP, JLE,  K),			\
+	INSN_3(JMP, JSGT, K),			\
+	INSN_3(JMP, JSLT, K),			\
+	INSN_3(JMP, JSGE, K),			\
+	INSN_3(JMP, JSLE, K),			\
+	INSN_3(JMP, JSET, K),			\
+	INSN_2(JMP, JA),			\
+	/* Store instructions. */		\
+	/*   Register based. */			\
+	INSN_3(STX, MEM,  B),			\
+	INSN_3(STX, MEM,  H),			\
+	INSN_3(STX, MEM,  W),			\
+	INSN_3(STX, MEM,  DW),			\
+	INSN_3(STX, XADD, W),			\
+	INSN_3(STX, XADD, DW),			\
+	/*   Immediate based. */		\
+	INSN_3(ST, MEM, B),			\
+	INSN_3(ST, MEM, H),			\
+	INSN_3(ST, MEM, W),			\
+	INSN_3(ST, MEM, DW),			\
+	/* Load instructions. */		\
+	/*   Register based. */			\
+	INSN_3(LDX, MEM, B),			\
+	INSN_3(LDX, MEM, H),			\
+	INSN_3(LDX, MEM, W),			\
+	INSN_3(LDX, MEM, DW),			\
+	/*   Immediate based. */		\
+	INSN_3(LD, IMM, DW),			\
+	/*   Misc (old cBPF carry-over). */	\
+	INSN_3(LD, ABS, B),			\
+	INSN_3(LD, ABS, H),			\
+	INSN_3(LD, ABS, W),			\
+	INSN_3(LD, IND, B),			\
+	INSN_3(LD, IND, H),			\
+	INSN_3(LD, IND, W)
+
+bool bpf_opcode_in_insntable(u8 code)
+{
+#define BPF_INSN_2_TBL(x, y)    [BPF_##x | BPF_##y] = true
+#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
+	static const bool public_insntable[256] = {
+		[0 ... 255] = false,
+		/* Now overwrite non-defaults ... */
+		BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+	};
+#undef BPF_INSN_3_TBL
+#undef BPF_INSN_2_TBL
+	return public_insntable[code];
+}
+
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 /**
  *	__bpf_prog_run - run eBPF program on a given context
@@ -793,115 +924,18 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
 	u64 tmp;
+#define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
+#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
 	static const void *jumptable[256] = {
 		[0 ... 255] = &&default_label,
 		/* Now overwrite non-defaults ... */
-		/* 32 bit ALU operations */
-		[BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
-		[BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
-		[BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
-		[BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
-		[BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
-		[BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
-		[BPF_ALU | BPF_OR | BPF_X]  = &&ALU_OR_X,
-		[BPF_ALU | BPF_OR | BPF_K]  = &&ALU_OR_K,
-		[BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
-		[BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
-		[BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
-		[BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
-		[BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
-		[BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
-		[BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
-		[BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
-		[BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
-		[BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
-		[BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
-		[BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
-		[BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
-		[BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
-		[BPF_ALU | BPF_NEG] = &&ALU_NEG,
-		[BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
-		[BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
-		/* 64 bit ALU operations */
-		[BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
-		[BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
-		[BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
-		[BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
-		[BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
-		[BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
-		[BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
-		[BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
-		[BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
-		[BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
-		[BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
-		[BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
-		[BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
-		[BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
-		[BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
-		[BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
-		[BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
-		[BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
-		[BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
-		[BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
-		[BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
-		[BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
-		[BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
-		[BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
-		[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
-		/* Call instruction */
-		[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+		BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
+		/* Non-UAPI available opcodes. */
 		[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
 		[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
-		/* Jumps */
-		[BPF_JMP | BPF_JA] = &&JMP_JA,
-		[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
-		[BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
-		[BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
-		[BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
-		[BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
-		[BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
-		[BPF_JMP | BPF_JLT | BPF_X] = &&JMP_JLT_X,
-		[BPF_JMP | BPF_JLT | BPF_K] = &&JMP_JLT_K,
-		[BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
-		[BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
-		[BPF_JMP | BPF_JLE | BPF_X] = &&JMP_JLE_X,
-		[BPF_JMP | BPF_JLE | BPF_K] = &&JMP_JLE_K,
-		[BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
-		[BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
-		[BPF_JMP | BPF_JSLT | BPF_X] = &&JMP_JSLT_X,
-		[BPF_JMP | BPF_JSLT | BPF_K] = &&JMP_JSLT_K,
-		[BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
-		[BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
-		[BPF_JMP | BPF_JSLE | BPF_X] = &&JMP_JSLE_X,
-		[BPF_JMP | BPF_JSLE | BPF_K] = &&JMP_JSLE_K,
-		[BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
-		[BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
-		/* Program return */
-		[BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
-		/* Store instructions */
-		[BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
-		[BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
-		[BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
-		[BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
-		[BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
-		[BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
-		[BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
-		[BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
-		[BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
-		[BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
-		/* Load instructions */
-		[BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
-		[BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
-		[BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
-		[BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
-		[BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
-		[BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
-		[BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
-		[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
-		[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
-		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
-		[BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW,
 	};
+#undef BPF_INSN_3_LBL
+#undef BPF_INSN_2_LBL
 	u32 tail_call_cnt = 0;
 	void *ptr;
 	int off;
@@ -1302,8 +1336,14 @@ load_byte:
 		goto load_byte;
 
 	default_label:
-		/* If we ever reach this, we have a bug somewhere. */
-		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+		/* If we ever reach this, we have a bug somewhere. Die hard here
+		 * instead of just returning 0; we could be somewhere in a subprog,
+		 * so execution could continue otherwise which we do /not/ want.
+		 *
+		 * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable().
+		 */
+		pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code);
+		BUG_ON(1);
 		return 0;
 }
 STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8365259a7c5a..0c5269415090 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4981,6 +4981,13 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 next_insn:
 			insn++;
 			i++;
+			continue;
+		}
+
+		/* Basic sanity check before we invest more work here. */
+		if (!bpf_opcode_in_insntable(insn->code)) {
+			verbose(env, "unknown opcode %02x\n", insn->code);
+			return -EINVAL;
 		}
 	}
 
-- 
cgit v1.2.3-59-g8ed1b