Merge branch 'bpf-eth-get-headlen'

Stanislav Fomichev says:

====================
Currently, when eth_get_headlen calls flow dissector, it doesn't pass any
skb. Because we use passed skb to lookup associated networking namespace
to find whether we have a BPF program attached or not, we always use
C-based flow dissector in this case.

The goal of this patch series is to add new networking namespace argument
to the eth_get_headlen and make BPF flow dissector programs be able to
work in the skb-less case.

The series goes like this:
* use new kernel context (struct bpf_flow_dissector) for flow dissector
  programs; this makes it easy to distinguish between skb and no-skb
  case and supports calling BPF flow dissector on a chunk of raw data
* convert BPF_PROG_TEST_RUN to use raw data
* plumb network namespace into __skb_flow_dissect from all callers
* handle no-skb case in __skb_flow_dissect
* update eth_get_headlen to include net namespace argument and
  convert all existing users
* add selftest to make sure bpf_skb_load_bytes is not allowed in
  the no-skb mode
* extend test_progs to exercise skb-less flow dissection as well
* stop adjusting nhoff/thoff by ETH_HLEN in BPF_PROG_TEST_RUN

v6:
* more suggestions by Alexei:
  * eth_get_headlen now takes net dev, not net namespace
  * test skb-less case via tun eth_get_headlen
* fix return errors in bpf_flow_load
* don't adjust nhoff/thoff by ETH_HLEN

v5:
* API changes have been submitted via bpf/stable tree

v4:
* prohibit access to vlan fields as well (otherwise, inconsistent
  between skb/skb-less cases)
* drop extra unneeded check for skb->vlan_present in bpf_flow.c

v3:
* new kernel xdp_buff-like context per Alexei suggestion
* drop skb_net helper
* properly clamp flow_keys->nhoff

v2:
* moved temporary skb from stack into percpu (avoids memset of ~200 bytes
  per packet)
* tightened down access to __sk_buff fields from flow dissector programs to
  avoid touching shinfo (whitelist only relevant fields)
* addressed suggestions from Willem
====================

Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

2 files changed, 127 insertions, 68 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index fa8fb0548217..edb3a7c22f6c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1730,6 +1730,40 @@ 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)
 {
@@ -6121,7 +6155,7 @@ 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 +6282,7 @@ 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 +6317,6 @@ 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 +6343,6 @@ 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 +6388,6 @@ 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 +6630,6 @@ 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 +6831,6 @@ 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 +6904,65 @@ 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 +7269,6 @@ 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 +8273,7 @@ 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 = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 795449713ba4..fac712cee9d5 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -683,50 +683,30 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	}
 }
 
-bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
-			    const struct sk_buff *skb,
-			    struct flow_dissector *flow_dissector,
-			    struct bpf_flow_keys *flow_keys)
+bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
+		      __be16 proto, int nhoff, int hlen)
 {
-	struct bpf_skb_data_end cb_saved;
-	struct bpf_skb_data_end *cb;
+	struct bpf_flow_keys *flow_keys = ctx->flow_keys;
 	u32 result;
 
-	/* Note that even though the const qualifier is discarded
-	 * throughout the execution of the BPF program, all changes(the
-	 * control block) are reverted after the BPF program returns.
-	 * Therefore, __skb_flow_dissect does not alter the skb.
-	 */
-
-	cb = (struct bpf_skb_data_end *)skb->cb;
-
-	/* Save Control Block */
-	memcpy(&cb_saved, cb, sizeof(cb_saved));
-	memset(cb, 0, sizeof(*cb));
-
 	/* 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->n_proto = proto;
+	flow_keys->nhoff = nhoff;
 	flow_keys->thoff = flow_keys->nhoff;
 
-	bpf_compute_data_pointers((struct sk_buff *)skb);
-	result = BPF_PROG_RUN(prog, skb);
-
-	/* Restore state */
-	memcpy(cb, &cb_saved, sizeof(cb_saved));
+	result = BPF_PROG_RUN(prog, ctx);
 
-	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff,
-				   skb_network_offset(skb), skb->len);
+	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
-				   flow_keys->nhoff, skb->len);
+				   flow_keys->nhoff, hlen);
 
 	return result == BPF_OK;
 }
 
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
+ * @net: associated network namespace, derived from @skb if NULL
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
  * @flow_dissector: list of keys to dissect
  * @target_container: target structure to put dissected values into
@@ -743,7 +723,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
  *
  * Caller must take care of zeroing target container memory.
  */
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(const struct net *net,
+			const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
 			void *target_container,
 			void *data, __be16 proto, int nhoff, int hlen,
@@ -756,6 +737,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
+	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
 	int num_hdrs = 0;
@@ -798,22 +780,39 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 					      target_container);
 
 	if (skb) {
-		struct bpf_flow_keys flow_keys;
-		struct bpf_prog *attached = NULL;
+		if (!net) {
+			if (skb->dev)
+				net = dev_net(skb->dev);
+			else if (skb->sk)
+				net = sock_net(skb->sk);
+		}
+	}
 
+	WARN_ON_ONCE(!net);
+	if (net) {
 		rcu_read_lock();
-
-		if (skb->dev)
-			attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog);
-		else if (skb->sk)
-			attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog);
-		else
-			WARN_ON_ONCE(1);
+		attached = rcu_dereference(net->flow_dissector_prog);
 
 		if (attached) {
-			ret = __skb_flow_bpf_dissect(attached, skb,
-						     flow_dissector,
-						     &flow_keys);
+			struct bpf_flow_keys flow_keys;
+			struct bpf_flow_dissector ctx = {
+				.flow_keys = &flow_keys,
+				.data = data,
+				.data_end = data + hlen,
+			};
+			__be16 n_proto = proto;
+
+			if (skb) {
+				ctx.skb = skb;
+				/* we can't use 'proto' in the skb case
+				 * because it might be set to skb->vlan_proto
+				 * which has been pulled from the data
+				 */
+				n_proto = skb->protocol;
+			}
+
+			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
+					       hlen);
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
 			rcu_read_unlock();
@@ -1410,8 +1409,8 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
 	__flow_hash_secret_init();
 
 	memset(&keys, 0, sizeof(keys));
-	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
-			   NULL, 0, 0, 0,
+	__skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric,
+			   &keys, NULL, 0, 0, 0,
 			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
 
 	return __flow_hash_from_keys(&keys, hashrnd);
@@ -1512,7 +1511,8 @@ u32 skb_get_poff(const struct sk_buff *skb)
 {
 	struct flow_keys_basic keys;
 
-	if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
+	if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+					      NULL, 0, 0, 0, 0))
 		return 0;
 
 	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));