[PATCH v3 net-next 1/3] net: flow_dissector: avoid multiple calls in BPF

[Chema Gonzalez <chema@google.com>]

We want multiple calls to __skb_get_poff() in the same filter to only
cause one invocation to the flow dissector. In order to reuse the result
of the flow dissector invocation (skb_flow_dissect()), we add a flow_keys
variable in the eBPF runner stack (__sk_run_filter() function), and pass
it as an argument to __skb_get_poff(). __skb_get_poff() inits the variable
the very first time it is called, and reuses the result in any further
invocation.

We also add handy function to init/check for inited flow_keys.

Signed-off-by: Chema Gonzalez <chema@google.com>
---
 include/linux/skbuff.h    |  4 +++-
 net/core/filter.c         | 14 ++++++++++++--
 net/core/flow_dissector.c | 28 ++++++++++++++++++++++------
 3 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7a9beeb..858d7af 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3065,7 +3065,9 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
 
 int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
 
-u32 __skb_get_poff(const struct sk_buff *skb);
+void __flow_keys_reset(struct flow_keys *flow);
+bool __flow_keys_inited(struct flow_keys *flow);
+u32 __skb_get_poff(const struct sk_buff *skb, struct flow_keys *flow);
 
 /**
  * skb_head_is_locked - Determine if the skb->head is locked down
diff --git a/net/core/filter.c b/net/core/filter.c
index c442a0d..b71948b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -66,6 +66,11 @@
 #define CTX	regs[BPF_REG_CTX]
 #define K	insn->imm
 
+struct sk_run_filter_ctx {
+	struct sk_buff *skb;
+	struct flow_keys *flow;
+};
+
 /* No hurry in this branch
  *
  * Exported for the bpf jit load helper.
@@ -252,12 +257,15 @@ unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
 	};
 	void *ptr;
 	int off;
+	struct flow_keys flow;
+	struct sk_run_filter_ctx context = { ctx, &flow };
 
 #define CONT	 ({ insn++; goto select_insn; })
 #define CONT_JMP ({ insn++; goto select_insn; })
 
+	memset(&flow, 0, sizeof(flow));
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
-	ARG1 = (u64) (unsigned long) ctx;
+	ARG1 = (u64) (unsigned long) &context;
 
 	/* Register for user BPF programs need to be reset first. */
 	regs[BPF_REG_A] = 0;
@@ -602,7 +610,9 @@ static unsigned int pkt_type_offset(void)
 
 static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
-	return __skb_get_poff((struct sk_buff *)(unsigned long) ctx);
+	struct sk_run_filter_ctx *context = (struct sk_run_filter_ctx *)
+			(unsigned long) ctx;
+	return __skb_get_poff(context->skb, context->flow);
 }
 
 static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 107ed12..4d431f0 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -270,21 +270,37 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 }
 EXPORT_SYMBOL(__skb_tx_hash);
 
+/* __flow_keys_reset() zeroes a flow_keys struct */
+void __flow_keys_reset(struct flow_keys *flow)
+{
+	memset(flow, 0, sizeof(struct flow_keys));
+}
+
+/* __flow_keys_inited() checks whether a flow_keys struct is init */
+bool __flow_keys_inited(struct flow_keys *flow)
+{
+	struct flow_keys zero_flow;
+
+	__flow_keys_reset(&zero_flow);
+	return memcmp(flow, &zero_flow, sizeof(struct flow_keys));
+}
+
 /* __skb_get_poff() returns the offset to the payload as far as it could
  * be dissected. The main user is currently BPF, so that we can dynamically
  * truncate packets without needing to push actual payload to the user
  * space and can analyze headers only, instead.
  */
-u32 __skb_get_poff(const struct sk_buff *skb)
+u32 __skb_get_poff(const struct sk_buff *skb, struct flow_keys *flow)
 {
-	struct flow_keys keys;
 	u32 poff = 0;
 
-	if (!skb_flow_dissect(skb, &keys))
-		return 0;
+	/* check whether the flow dissector has already been run */
+	if (!__flow_keys_inited(flow))
+		if (!skb_flow_dissect(skb, flow))
+			return 0;
 
-	poff += keys.thoff;
-	switch (keys.ip_proto) {
+	poff += flow->thoff;
+	switch (flow->ip_proto) {
 	case IPPROTO_TCP: {
 		const struct tcphdr *tcph;
 		struct tcphdr _tcph;
-- 
1.9.1.423.g4596e3a