Merge branch 'bpf-flow-dissector-fixes'

Stanislav Fomichev says:

====================
This patch series fixes the existing BPF flow dissector API to
support calling BPF progs from the eth_get_headlen context (the
support itself will be added in bpf-next tree).

The summary of the changes:

  * fix VLAN handling in bpf_flow.c, we don't need to peek back and look
    at skb->vlan_present; add selftests
  * pass and use flow_keys->n_proto instead of skb->protocol
  * fix clamping of flow_keys->nhoff for packets with nhoff > 0
  * prohibit access to most of the __sk_buff fields from BPF flow
    dissector progs; only data/data_end/flow_keys are allowed (all input
    is now passed via flow_keys)
  * finally, document BPF flow dissector program environment
====================
Acked-by: NWillem de Bruijn <willemb@google.com>
Acked-by: NPetar Penkov <peterpenkov96@gmail.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Documentation/networking/bpf_flow_dissector.txt

+==================
+BPF Flow Dissector
+==================
+
+Overview
+========
+
+Flow dissector is a routine that parses metadata out of the packets. It's
+used in the various places in the networking subsystem (RFS, flow hash, etc).
+
+BPF flow dissector is an attempt to reimplement C-based flow dissector logic
+in BPF to gain all the benefits of BPF verifier (namely, limits on the
+number of instructions and tail calls).
+
+API
+===
+
+BPF flow dissector programs operate on an __sk_buff. However, only the
+limited set of fields is allowed: data, data_end and flow_keys. flow_keys
+is 'struct bpf_flow_keys' and contains flow dissector input and
+output arguments.
+
+The inputs are:
+  * nhoff - initial offset of the networking header
+  * thoff - initial offset of the transport header, initialized to nhoff
+  * n_proto - L3 protocol type, parsed out of L2 header
+
+Flow dissector BPF program should fill out the rest of the 'struct
+bpf_flow_keys' fields. Input arguments nhoff/thoff/n_proto should be also
+adjusted accordingly.
+
+The return code of the BPF program is either BPF_OK to indicate successful
+dissection, or BPF_DROP to indicate parsing error.
+
+__sk_buff->data
+===============
+
+In the VLAN-less case, this is what the initial state of the BPF flow
+dissector looks like:
++------+------+------------+-----------+
+| DMAC | SMAC | ETHER_TYPE | L3_HEADER |
++------+------+------------+-----------+
+                            ^
+                            |
+                            +-- flow dissector starts here
+
+skb->data + flow_keys->nhoff point to the first byte of L3_HEADER.
+flow_keys->thoff = nhoff
+flow_keys->n_proto = ETHER_TYPE
+
+
+In case of VLAN, flow dissector can be called with the two different states.
+
+Pre-VLAN parsing:
++------+------+------+-----+-----------+-----------+
+| DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER |
++------+------+------+-----+-----------+-----------+
+                      ^
+                      |
+                      +-- flow dissector starts here
+
+skb->data + flow_keys->nhoff point the to first byte of TCI.
+flow_keys->thoff = nhoff
+flow_keys->n_proto = TPID
+
+Please note that TPID can be 802.1AD and, hence, BPF program would
+have to parse VLAN information twice for double tagged packets.
+
+
+Post-VLAN parsing:
++------+------+------+-----+-----------+-----------+
+| DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER |
++------+------+------+-----+-----------+-----------+
+                                        ^
+                                        |
+                                        +-- flow dissector starts here
+
+skb->data + flow_keys->nhoff point the to first byte of L3_HEADER.
+flow_keys->thoff = nhoff
+flow_keys->n_proto = ETHER_TYPE
+
+In this case VLAN information has been processed before the flow dissector
+and BPF flow dissector is not required to handle it.
+
+
+The takeaway here is as follows: BPF flow dissector program can be called with
+the optional VLAN header and should gracefully handle both cases: when single
+or double VLAN is present and when it is not present. The same program
+can be called for both cases and would have to be written carefully to
+handle both cases.
+
+
+Reference Implementation
+========================
+
+See tools/testing/selftests/bpf/progs/bpf_flow.c for the reference
+implementation and tools/testing/selftests/bpf/flow_dissector_load.[hc] for
+the loader. bpftool can be used to load BPF flow dissector program as well.
+
+The reference implementation is organized as follows:
+* jmp_table map that contains sub-programs for each supported L3 protocol
+* _dissect routine - entry point; it does input n_proto parsing and does
+  bpf_tail_call to the appropriate L3 handler
+
+Since BPF at this point doesn't support looping (or any jumping back),
+jmp_table is used instead to handle multiple levels of encapsulation (and
+IPv6 options).
+
+
+Current Limitations
+===================
+BPF flow dissector doesn't support exporting all the metadata that in-kernel
+C-based implementation can export. Notable example is single VLAN (802.1Q)
+and double VLAN (802.1AD) tags. Please refer to the 'struct bpf_flow_keys'
+for a set of information that's currently can be exported from the BPF context.

net/core/filter.c

@@ -6613,14 +6613,8 @@ static bool flow_dissector_is_valid_access(int off, int size,
 					   const struct bpf_prog *prog,
 					   struct bpf_insn_access_aux *info)
 {
-	if (type == BPF_WRITE) {
-		switch (off) {
-		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
-			break;
-		default:
-			return false;
-		}
-	}
+	if (type == BPF_WRITE)
+		return false;
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, data):
@@ -6632,11 +6626,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		info->reg_type = PTR_TO_FLOW_KEYS;
 		break;
-	case bpf_ctx_range(struct __sk_buff, tc_classid):
-	case bpf_ctx_range(struct __sk_buff, data_meta):
-	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):
+	default:
 		return false;
 	}
 

net/core/flow_dissector.c

@@ -707,6 +707,7 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	/* Pass parameters to the BPF program */
 	memset(flow_keys, 0, sizeof(*flow_keys));
 	cb->qdisc_cb.flow_keys = flow_keys;
+	flow_keys->n_proto = skb->protocol;
 	flow_keys->nhoff = skb_network_offset(skb);
 	flow_keys->thoff = flow_keys->nhoff;
 
@@ -716,7 +717,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	/* Restore state */
 	memcpy(cb, &cb_saved, sizeof(cb_saved));
 
-	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len);
+	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff,
+				   skb_network_offset(skb), skb->len);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
 				   flow_keys->nhoff, skb->len);
 

tools/testing/selftests/bpf/prog_tests/flow_dissector.c

@@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = {
 	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
 };
 
+#define VLAN_HLEN	4
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v4 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto = __bpf_constant_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = IPPROTO_TCP,
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
+	.nhoff = VLAN_HLEN,
+	.thoff = VLAN_HLEN + sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	__u16 vlan_tci2;
+	__u16 vlan_proto2;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v6 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+	.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+	.iph.nexthdr = IPPROTO_TCP,
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
+	.nhoff = VLAN_HLEN * 2,
+	.thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
 void test_flow_dissector(void)
 {
 	struct bpf_flow_keys flow_keys;
@@ -68,5 +120,21 @@ void test_flow_dissector(void)
 	      err, errno, retval, duration, size, sizeof(flow_keys));
 	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
 
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
+			pkt_vlan_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
+			pkt_vlan_v6_flow_keys);
+
 	bpf_object__close(obj);
 }

tools/testing/selftests/bpf/progs/bpf_flow.c

@@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 
-	keys->n_proto = proto;
 	switch (proto) {
 	case bpf_htons(ETH_P_IP):
 		bpf_tail_call(skb, &jmp_table, IP);
@@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 SEC("flow_dissector")
 int _dissect(struct __sk_buff *skb)
 {
-	if (!skb->vlan_present)
-		return parse_eth_proto(skb, skb->protocol);
-	else
-		return parse_eth_proto(skb, skb->vlan_proto);
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	return parse_eth_proto(skb, keys->n_proto);
 }
 
 /* Parses on IPPROTO_* */
@@ -336,15 +334,9 @@ PROG(VLAN)(struct __sk_buff *skb)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 	struct vlan_hdr *vlan, _vlan;
-	__be16 proto;
-
-	/* Peek back to see if single or double-tagging */
-	if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto,
-			       sizeof(proto)))
-		return BPF_DROP;
 
 	/* Account for double-tagging */
-	if (proto == bpf_htons(ETH_P_8021AD)) {
+	if (keys->n_proto == bpf_htons(ETH_P_8021AD)) {
 		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
 		if (!vlan)
 			return BPF_DROP;
@@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb)
 		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
 			return BPF_DROP;
 
+		keys->nhoff += sizeof(*vlan);
 		keys->thoff += sizeof(*vlan);
 	}
 
@@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb)
 	if (!vlan)
 		return BPF_DROP;
 
+	keys->nhoff += sizeof(*vlan);
 	keys->thoff += sizeof(*vlan);
 	/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
 	if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
 	    vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
 		return BPF_DROP;
 
+	keys->n_proto = vlan->h_vlan_encapsulated_proto;
 	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
 }