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>
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
new file mode 100644
index 0000000..6687022
--- /dev/null
+++ b/arch/x86/net/bpf_jit.S
@@ -0,0 +1,140 @@
+/* bpf_jit.S : BPF JIT helper functions
+ *
+ * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+
+/*
+ * Calling convention :
+ * rdi : skb pointer
+ * esi : offset of byte(s) to fetch in skb (can be scratched)
+ * r8  : copy of skb->data
+ * r9d : hlen = skb->len - skb->data_len
+ */
+#define SKBDATA	%r8
+
+sk_load_word_ind:
+	.globl	sk_load_word_ind
+
+	add	%ebx,%esi	/* offset += X */
+#	test    %esi,%esi	/* if (offset < 0) goto bpf_error; */
+	js	bpf_error
+
+sk_load_word:
+	.globl	sk_load_word
+
+	mov	%r9d,%eax		# hlen
+	sub	%esi,%eax		# hlen - offset
+	cmp	$3,%eax
+	jle	bpf_slow_path_word
+	mov     (SKBDATA,%rsi),%eax
+	bswap   %eax  			/* ntohl() */
+	ret
+
+
+sk_load_half_ind:
+	.globl sk_load_half_ind
+
+	add	%ebx,%esi	/* offset += X */
+	js	bpf_error
+
+sk_load_half:
+	.globl	sk_load_half
+
+	mov	%r9d,%eax
+	sub	%esi,%eax		#	hlen - offset
+	cmp	$1,%eax
+	jle	bpf_slow_path_half
+	movzwl	(SKBDATA,%rsi),%eax
+	rol	$8,%ax			# ntohs()
+	ret
+
+sk_load_byte_ind:
+	.globl sk_load_byte_ind
+	add	%ebx,%esi	/* offset += X */
+	js	bpf_error
+
+sk_load_byte:
+	.globl	sk_load_byte
+
+	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
+	jle	bpf_slow_path_byte
+	movzbl	(SKBDATA,%rsi),%eax
+	ret
+
+/**
+ * sk_load_byte_msh - BPF_S_LDX_B_MSH helper
+ *
+ * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
+ * Must preserve A accumulator (%eax)
+ * Inputs : %esi is the offset value, already known positive
+ */
+ENTRY(sk_load_byte_msh)
+	CFI_STARTPROC
+	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
+	jle	bpf_slow_path_byte_msh
+	movzbl	(SKBDATA,%rsi),%ebx
+	and	$15,%bl
+	shl	$2,%bl
+	ret
+	CFI_ENDPROC
+ENDPROC(sk_load_byte_msh)
+
+bpf_error:
+# force a return 0 from jit handler
+	xor		%eax,%eax
+	mov		-8(%rbp),%rbx
+	leaveq
+	ret
+
+/* rsi contains offset and can be scratched */
+#define bpf_slow_path_common(LEN)		\
+	push	%rdi;    /* save skb */		\
+	push	%r9;				\
+	push	SKBDATA;			\
+/* rsi already has offset */			\
+	mov	$LEN,%ecx;	/* len */	\
+	lea	-12(%rbp),%rdx;			\
+	call	skb_copy_bits;			\
+	test    %eax,%eax;			\
+	pop	SKBDATA;			\
+	pop	%r9;				\
+	pop	%rdi
+
+
+bpf_slow_path_word:
+	bpf_slow_path_common(4)
+	js	bpf_error
+	mov	-12(%rbp),%eax
+	bswap	%eax
+	ret
+
+bpf_slow_path_half:
+	bpf_slow_path_common(2)
+	js	bpf_error
+	mov	-12(%rbp),%ax
+	rol	$8,%ax
+	movzwl	%ax,%eax
+	ret
+
+bpf_slow_path_byte:
+	bpf_slow_path_common(1)
+	js	bpf_error
+	movzbl	-12(%rbp),%eax
+	ret
+
+bpf_slow_path_byte_msh:
+	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
+	bpf_slow_path_common(1)
+	js	bpf_error
+	movzbl	-12(%rbp),%eax
+	and	$15,%al
+	shl	$2,%al
+	xchg	%eax,%ebx
+	ret