net: filter: Just In Time compiler for x86-64

In order to speedup packet filtering, here is an implementation of a
JIT compiler for x86_64

It is disabled by default, and must be enabled by the admin.

echo 1 >/proc/sys/net/core/bpf_jit_enable

It uses module_alloc() and module_free() to get memory in the 2GB text
kernel range since we call helpers functions from the generated code.

EAX : BPF A accumulator
EBX : BPF X accumulator
RDI : pointer to skb   (first argument given to JIT function)
RBP : frame pointer (even if CONFIG_FRAME_POINTER=n)
r9d : skb->len - skb->data_len (headlen)
r8  : skb->data

To get a trace of generated code, use :

echo 2 >/proc/sys/net/core/bpf_jit_enable

Example of generated code :

# tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24

flen=18 proglen=147 pass=3 image=ffffffffa00b5000
JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60
JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00
JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00
JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be
JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0
JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00
JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00
JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24
JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31
JIT code: ffffffffa00b5090: c0 c9 c3

BPF program is 144 bytes long, so native program is almost same size ;)

(000) ldh      [12]
(001) jeq      #0x800           jt 2    jf 8
(002) ld       [26]
(003) and      #0xffffff00
(004) jeq      #0xc0a81400      jt 16   jf 5
(005) ld       [30]
(006) and      #0xffffff00
(007) jeq      #0xc0a81400      jt 16   jf 17
(008) jeq      #0x806           jt 10   jf 9
(009) jeq      #0x8035          jt 10   jf 17
(010) ld       [28]
(011) and      #0xffffff00
(012) jeq      #0xc0a81400      jt 16   jf 13
(013) ld       [38]
(014) and      #0xffffff00
(015) jeq      #0xc0a81400      jt 16   jf 17
(016) ret      #65535
(017) ret      #0

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 28 insertions, 61 deletions

diff --git a/net/Kconfig b/net/Kconfig
index 79cabf1ee68..745fb02d2fd 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -232,6 +232,19 @@ config XPS
 	depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
 	default y
 
+config HAVE_BPF_JIT
+	bool
+
+config BPF_JIT
+	bool "enable BPF Just In Time compiler"
+	depends on HAVE_BPF_JIT
+	---help---
+	  Berkeley Packet Filter filtering capabilities are normally handled
+	  by an interpreter. This option allows kernel to generate a native
+	  code when filter is loaded in memory. This should speedup
+	  packet sniffing (libpcap/tcpdump). Note : Admin should enable
+	  this feature changing /proc/sys/net/core/bpf_jit_enable
+
 menu "Network testing"
 
 config NET_PKTGEN
diff --git a/net/core/filter.c b/net/core/filter.c
index afb8afb066b..0eb8c4466ea 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -39,65 +39,6 @@
 #include <linux/filter.h>
 #include <linux/reciprocal_div.h>
 
-enum {
-	BPF_S_RET_K = 1,
-	BPF_S_RET_A,
-	BPF_S_ALU_ADD_K,
-	BPF_S_ALU_ADD_X,
-	BPF_S_ALU_SUB_K,
-	BPF_S_ALU_SUB_X,
-	BPF_S_ALU_MUL_K,
-	BPF_S_ALU_MUL_X,
-	BPF_S_ALU_DIV_X,
-	BPF_S_ALU_AND_K,
-	BPF_S_ALU_AND_X,
-	BPF_S_ALU_OR_K,
-	BPF_S_ALU_OR_X,
-	BPF_S_ALU_LSH_K,
-	BPF_S_ALU_LSH_X,
-	BPF_S_ALU_RSH_K,
-	BPF_S_ALU_RSH_X,
-	BPF_S_ALU_NEG,
-	BPF_S_LD_W_ABS,
-	BPF_S_LD_H_ABS,
-	BPF_S_LD_B_ABS,
-	BPF_S_LD_W_LEN,
-	BPF_S_LD_W_IND,
-	BPF_S_LD_H_IND,
-	BPF_S_LD_B_IND,
-	BPF_S_LD_IMM,
-	BPF_S_LDX_W_LEN,
-	BPF_S_LDX_B_MSH,
-	BPF_S_LDX_IMM,
-	BPF_S_MISC_TAX,
-	BPF_S_MISC_TXA,
-	BPF_S_ALU_DIV_K,
-	BPF_S_LD_MEM,
-	BPF_S_LDX_MEM,
-	BPF_S_ST,
-	BPF_S_STX,
-	BPF_S_JMP_JA,
-	BPF_S_JMP_JEQ_K,
-	BPF_S_JMP_JEQ_X,
-	BPF_S_JMP_JGE_K,
-	BPF_S_JMP_JGE_X,
-	BPF_S_JMP_JGT_K,
-	BPF_S_JMP_JGT_X,
-	BPF_S_JMP_JSET_K,
-	BPF_S_JMP_JSET_X,
-	/* Ancillary data */
-	BPF_S_ANC_PROTOCOL,
-	BPF_S_ANC_PKTTYPE,
-	BPF_S_ANC_IFINDEX,
-	BPF_S_ANC_NLATTR,
-	BPF_S_ANC_NLATTR_NEST,
-	BPF_S_ANC_MARK,
-	BPF_S_ANC_QUEUE,
-	BPF_S_ANC_HATYPE,
-	BPF_S_ANC_RXHASH,
-	BPF_S_ANC_CPU,
-};
-
 /* No hurry in this branch */
 static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
 {
@@ -145,7 +86,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 	rcu_read_lock();
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
-		unsigned int pkt_len = sk_run_filter(skb, filter->insns);
+		unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
 
 		err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
 	}
@@ -638,6 +579,7 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
 {
 	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
+	bpf_jit_free(fp);
 	kfree(fp);
 }
 EXPORT_SYMBOL(sk_filter_release_rcu);
@@ -672,6 +614,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 	atomic_set(&fp->refcnt, 1);
 	fp->len = fprog->len;
+	fp->bpf_func = sk_run_filter;
 
 	err = sk_chk_filter(fp->insns, fp->len);
 	if (err) {
@@ -679,6 +622,8 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 		return err;
 	}
 
+	bpf_jit_compile(fp);
+
 	old_fp = rcu_dereference_protected(sk->sk_filter,
 					   sock_owned_by_user(sk));
 	rcu_assign_pointer(sk->sk_filter, fp);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 385b6095fdc..a829e3f60ae 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -122,6 +122,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+#ifdef CONFIG_BPF_JIT
+	{
+		.procname	= "bpf_jit_enable",
+		.data		= &bpf_jit_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif
 	{
 		.procname	= "netdev_tstamp_prequeue",
 		.data		= &netdev_tstamp_prequeue,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b5362e96022..549527bca87 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -538,7 +538,7 @@ static inline unsigned int run_filter(const struct sk_buff *skb,
 	rcu_read_lock();
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter != NULL)
-		res = sk_run_filter(skb, filter->insns);
+		res = SK_RUN_FILTER(filter, skb);
 	rcu_read_unlock();
 
 	return res;