net: filter: Just In Time compiler for sparc

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/Kconfig

@@ -30,6 +30,7 @@ config SPARC
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select GENERIC_PCI_IOMAP
 	select HAVE_NMI_WATCHDOG if SPARC64
+	select HAVE_BPF_JIT
 
 config SPARC32
 	def_bool !64BIT

arch/sparc/Makefile

@@ -66,6 +66,7 @@ head-y                 += arch/sparc/kernel/init_task.o
 
 core-y                 += arch/sparc/kernel/
 core-y                 += arch/sparc/mm/ arch/sparc/math-emu/
+core-y                 += arch/sparc/net/
 
 libs-y                 += arch/sparc/prom/
 libs-y                 += arch/sparc/lib/

arch/sparc/net/Makefile

+#
+# Arch-specific network modules
+#
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o

arch/sparc/net/bpf_jit.h

+#ifndef _BPF_JIT_H
+#define _BPF_JIT_H
+
+/* Conventions:
+ *  %g1 : temporary
+ *  %g2 : Secondary temporary used by SKB data helper stubs.
+ *  %o0 : pointer to skb (first argument given to JIT function)
+ *  %o1 : BPF A accumulator
+ *  %o2 : BPF X accumulator
+ *  %o3 : Holds saved %o7 so we can call helper functions without needing
+ *        to allocate a register window.
+ *  %o4 : skb->data
+ *  %o5 : skb->len - skb->data_len
+ */
+
+#ifndef __ASSEMBLER__
+#define G0		0x00
+#define G1		0x01
+#define G3		0x03
+#define G6		0x06
+#define O0		0x08
+#define O1		0x09
+#define O2		0x0a
+#define O3		0x0b
+#define O4		0x0c
+#define O5		0x0d
+#define SP		0x0e
+#define O7		0x0f
+#define FP		0x1e
+
+#define r_SKB		O0
+#define r_A		O1
+#define r_X		O2
+#define r_saved_O7	O3
+#define r_HEADLEN	O4
+#define r_SKB_DATA	O5
+#define r_TMP		G1
+#define r_TMP2		G2
+#define r_OFF		G3
+#else
+#define r_SKB		%o0
+#define r_A		%o1
+#define r_X		%o2
+#define r_saved_O7	%o3
+#define r_HEADLEN	%o4
+#define r_SKB_DATA	%o5
+#define r_TMP		%g1
+#define r_TMP2		%g2
+#define r_OFF		%g3
+#endif
+
+#endif /* _BPF_JIT_H */

arch/sparc/net/bpf_jit_asm.S

+#include <asm/ptrace.h>
+
+#include "bpf_jit.h"
+
+#ifdef CONFIG_SPARC64
+#define SAVE_SZ		176
+#define SCRATCH_OFF	STACK_BIAS + 128
+#define BE_PTR(label)	be,pn %xcc, label
+#else
+#define SAVE_SZ		96
+#define SCRATCH_OFF	72
+#define BE_PTR(label)	be label
+#endif
+
+#define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
+
+	.text
+	.globl	bpf_jit_load_word
+bpf_jit_load_word:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_word_neg
+	 nop
+	.globl	bpf_jit_load_word_positive_offset
+bpf_jit_load_word_positive_offset:
+	sub	r_HEADLEN, r_OFF, r_TMP
+	cmp	r_TMP, 3
+	ble	bpf_slow_path_word
+	 add	r_SKB_DATA, r_OFF, r_TMP
+	andcc	r_TMP, 3, %g0
+	bne	load_word_unaligned
+	 nop
+	retl
+	 ld	[r_SKB_DATA + r_OFF], r_A
+load_word_unaligned:
+	ldub	[r_TMP + 0x0], r_OFF
+	ldub	[r_TMP + 0x1], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	or	r_OFF, r_TMP2, r_OFF
+	ldub	[r_TMP + 0x2], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	or	r_OFF, r_TMP2, r_OFF
+	ldub	[r_TMP + 0x3], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	retl
+	 or	r_OFF, r_TMP2, r_A
+
+	.globl	bpf_jit_load_half
+bpf_jit_load_half:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_half_neg
+	 nop
+	.globl	bpf_jit_load_half_positive_offset
+bpf_jit_load_half_positive_offset:
+	sub	r_HEADLEN, r_OFF, r_TMP
+	cmp	r_TMP, 1
+	ble	bpf_slow_path_half
+	 add	r_SKB_DATA, r_OFF, r_TMP
+	andcc	r_TMP, 1, %g0
+	bne	load_half_unaligned
+	 nop
+	retl
+	 lduh	[r_SKB_DATA + r_OFF], r_A
+load_half_unaligned:
+	ldub	[r_TMP + 0x0], r_OFF
+	ldub	[r_TMP + 0x1], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	retl
+	 or	r_OFF, r_TMP2, r_A
+
+	.globl	bpf_jit_load_byte
+bpf_jit_load_byte:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_byte_neg
+	 nop
+	.globl	bpf_jit_load_byte_positive_offset
+bpf_jit_load_byte_positive_offset:
+	cmp	r_OFF, r_HEADLEN
+	bge	bpf_slow_path_byte
+	 nop
+	retl
+	 ldub	[r_SKB_DATA + r_OFF], r_A
+
+	.globl	bpf_jit_load_byte_msh
+bpf_jit_load_byte_msh:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_byte_msh_neg
+	 nop
+	.globl	bpf_jit_load_byte_msh_positive_offset
+bpf_jit_load_byte_msh_positive_offset:
+	cmp	r_OFF, r_HEADLEN
+	bge	bpf_slow_path_byte_msh
+	 nop
+	ldub	[r_SKB_DATA + r_OFF], r_OFF
+	and	r_OFF, 0xf, r_OFF
+	retl
+	 sll	r_OFF, 2, r_X
+
+#define bpf_slow_path_common(LEN)	\
+	save	%sp, -SAVE_SZ, %sp;	\
+	mov	%i0, %o0;		\
+	mov	r_OFF, %o1;		\
+	add	%fp, SCRATCH_OFF, %o2;	\
+	call	skb_copy_bits;		\
+	 mov	(LEN), %o3;		\
+	cmp	%o0, 0;			\
+	restore;
+
+bpf_slow_path_word:
+	bpf_slow_path_common(4)
+	bl	bpf_error
+	 ld	[%sp + SCRATCH_OFF], r_A
+	retl
+	 nop
+bpf_slow_path_half:
+	bpf_slow_path_common(2)
+	bl	bpf_error
+	 lduh	[%sp + SCRATCH_OFF], r_A
+	retl
+	 nop
+bpf_slow_path_byte:
+	bpf_slow_path_common(1)
+	bl	bpf_error
+	 ldub	[%sp + SCRATCH_OFF], r_A
+	retl
+	 nop
+bpf_slow_path_byte_msh:
+	bpf_slow_path_common(1)
+	bl	bpf_error
+	 ldub	[%sp + SCRATCH_OFF], r_A
+	and	r_OFF, 0xf, r_OFF
+	retl
+	 sll	r_OFF, 2, r_X
+
+#define bpf_negative_common(LEN)			\
+	save	%sp, -SAVE_SZ, %sp;			\
+	mov	%i0, %o0;				\
+	mov	r_OFF, %o1;				\
+	call	bpf_internal_load_pointer_neg_helper;	\
+	 mov	(LEN), %o2;				\
+	mov	%o0, r_TMP;				\
+	cmp	%o0, 0;					\
+	BE_PTR(bpf_error);				\
+	 restore;
+
+bpf_slow_path_word_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_word_negative_offset
+bpf_jit_load_word_negative_offset:
+	bpf_negative_common(4)
+	andcc	r_TMP, 3, %g0
+	bne	load_word_unaligned
+	 nop
+	retl
+	 ld	[r_TMP], r_A
+
+bpf_slow_path_half_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_half_negative_offset
+bpf_jit_load_half_negative_offset:
+	bpf_negative_common(2)
+	andcc	r_TMP, 1, %g0
+	bne	load_half_unaligned
+	 nop
+	retl
+	 lduh	[r_TMP], r_A
+
+bpf_slow_path_byte_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_byte_negative_offset
+bpf_jit_load_byte_negative_offset:
+	bpf_negative_common(1)
+	retl
+	 ldub	[r_TMP], r_A
+
+bpf_slow_path_byte_msh_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_byte_msh_negative_offset
+bpf_jit_load_byte_msh_negative_offset:
+	bpf_negative_common(1)
+	ldub	[r_TMP], r_OFF
+	and	r_OFF, 0xf, r_OFF
+	retl
+	 sll	r_OFF, 2, r_X
+
+bpf_error:
+	jmpl	r_saved_O7 + 8, %g0
+	 clr	%o0