Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-04-28

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Introduce BPF socket local storage map so that BPF programs can store
   private data they associate with a socket (instead of e.g. separate hash
   table), from Martin.

2) Add support for bpftool to dump BTF types. This is done through a new
   `bpftool btf dump` sub-command, from Andrii.

3) Enable BPF-based flow dissector for skb-less eth_get_headlen() calls which
   was currently not supported since skb was used to lookup netns, from Stanislav.

4) Add an opt-in interface for tracepoints to expose a writable context
   for attached BPF programs, used here for NBD sockets, from Matt.

5) BPF xadd related arm64 JIT fixes and scalability improvements, from Daniel.

6) Change the skb->protocol for bpf_skb_adjust_room() helper in order to
   support tunnels such as sit. Add selftests as well, from Willem.

7) Various smaller misc fixes.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 102 insertions, 23 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 9d28e7e8a4cb..55bfc941d17a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -75,6 +75,7 @@
 #include <net/seg6_local.h>
 #include <net/lwtunnel.h>
 #include <net/ipv6_stubs.h>
+#include <net/bpf_sk_storage.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -1730,6 +1731,40 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_4(bpf_flow_dissector_load_bytes,
+	   const struct bpf_flow_dissector *, ctx, u32, offset,
+	   void *, to, u32, len)
+{
+	void *ptr;
+
+	if (unlikely(offset > 0xffff))
+		goto err_clear;
+
+	if (unlikely(!ctx->skb))
+		goto err_clear;
+
+	ptr = skb_header_pointer(ctx->skb, offset, len, to);
+	if (unlikely(!ptr))
+		goto err_clear;
+	if (ptr != to)
+		memcpy(to, ptr, len);
+
+	return 0;
+err_clear:
+	memset(to, 0, len);
+	return -EFAULT;
+}
+
+static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = {
+	.func		= bpf_flow_dissector_load_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
 	   u32, offset, void *, to, u32, len, u32, start_header)
 {
@@ -3047,6 +3082,14 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 
 			skb_set_transport_header(skb, mac_len + nh_len);
 		}
+
+		/* Match skb->protocol to new outer l3 protocol */
+		if (skb->protocol == htons(ETH_P_IP) &&
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+			skb->protocol = htons(ETH_P_IPV6);
+		else if (skb->protocol == htons(ETH_P_IPV6) &&
+			 flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
+			skb->protocol = htons(ETH_P_IP);
 	}
 
 	if (skb_is_gso(skb)) {
@@ -5861,6 +5904,9 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
+const struct bpf_func_proto bpf_sk_storage_get_proto __weak;
+const struct bpf_func_proto bpf_sk_storage_delete_proto __weak;
+
 static const struct bpf_func_proto *
 cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -5869,6 +5915,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
@@ -5950,6 +6000,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_fib_lookup_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
 #ifdef CONFIG_XFRM
 	case BPF_FUNC_skb_get_xfrm_state:
 		return &bpf_skb_get_xfrm_state_proto;
@@ -6121,7 +6175,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
-		return &bpf_skb_load_bytes_proto;
+		return &bpf_flow_dissector_load_bytes_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6248,9 +6302,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 			return false;
 		break;
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
-		if (size != sizeof(__u64))
-			return false;
-		break;
+		return false;
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 		if (size != sizeof(__u64))
 			return false;
@@ -6285,7 +6337,6 @@ static bool sk_filter_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
@@ -6312,7 +6363,6 @@ static bool cg_skb_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
@@ -6358,7 +6408,6 @@ static bool lwt_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
@@ -6601,7 +6650,6 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 		return false;
 	}
@@ -6803,7 +6851,6 @@ static bool sk_skb_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
@@ -6877,24 +6924,65 @@ static bool flow_dissector_is_valid_access(int off, int size,
 					   const struct bpf_prog *prog,
 					   struct bpf_insn_access_aux *info)
 {
+	const int size_default = sizeof(__u32);
+
+	if (off < 0 || off >= sizeof(struct __sk_buff))
+		return false;
+
 	if (type == BPF_WRITE)
 		return false;
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, data):
+		if (size != size_default)
+			return false;
 		info->reg_type = PTR_TO_PACKET;
-		break;
+		return true;
 	case bpf_ctx_range(struct __sk_buff, data_end):
+		if (size != size_default)
+			return false;
 		info->reg_type = PTR_TO_PACKET_END;
-		break;
+		return true;
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+		if (size != sizeof(__u64))
+			return false;
 		info->reg_type = PTR_TO_FLOW_KEYS;
-		break;
+		return true;
 	default:
 		return false;
 	}
+}
 
-	return bpf_skb_is_valid_access(off, size, type, prog, info);
+static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type,
+					     const struct bpf_insn *si,
+					     struct bpf_insn *insn_buf,
+					     struct bpf_prog *prog,
+					     u32 *target_size)
+
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct __sk_buff, data):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_flow_dissector, data));
+		break;
+
+	case offsetof(struct __sk_buff, data_end):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_flow_dissector, data_end));
+		break;
+
+	case offsetof(struct __sk_buff, flow_keys):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_flow_dissector, flow_keys));
+		break;
+	}
+
+	return insn - insn_buf;
 }
 
 static u32 bpf_convert_ctx_access(enum bpf_access_type type,
@@ -7201,15 +7289,6 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 						     skc_num, 2, target_size));
 		break;
 
-	case offsetof(struct __sk_buff, flow_keys):
-		off  = si->off;
-		off -= offsetof(struct __sk_buff, flow_keys);
-		off += offsetof(struct sk_buff, cb);
-		off += offsetof(struct qdisc_skb_cb, flow_keys);
-		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
-				      si->src_reg, off);
-		break;
-
 	case offsetof(struct __sk_buff, tstamp):
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8);
 
@@ -8214,7 +8293,7 @@ const struct bpf_prog_ops sk_msg_prog_ops = {
 const struct bpf_verifier_ops flow_dissector_verifier_ops = {
 	.get_func_proto		= flow_dissector_func_proto,
 	.is_valid_access	= flow_dissector_is_valid_access,
-	.convert_ctx_access	= bpf_convert_ctx_access,
+	.convert_ctx_access	= flow_dissector_convert_ctx_access,
 };
 
 const struct bpf_prog_ops flow_dissector_prog_ops = {