bpf, sparc64: remove ld_abs/ld_ind

Since LD_ABS/LD_IND instructions are now removed from the core and
reimplemented through a combination of inlined BPF instructions and
a slow-path helper, we can get rid of the complexity from sparc64 JIT.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 6 insertions, 269 deletions

diff --git a/arch/sparc/net/Makefile b/arch/sparc/net/Makefile
index 76fa8e9..d32aac3 100644
--- a/arch/sparc/net/Makefile
+++ b/arch/sparc/net/Makefile
@@ -1,4 +1,7 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp_$(BITS).o
+ifeq ($(BITS),32)
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_32.o
+endif
diff --git a/arch/sparc/net/bpf_jit_64.h b/arch/sparc/net/bpf_jit_64.h
index 428f7fd..fbc836f 100644
--- a/arch/sparc/net/bpf_jit_64.h
+++ b/arch/sparc/net/bpf_jit_64.h
@@ -33,35 +33,6 @@
 #define I5		0x1d
 #define FP		0x1e
 #define I7		0x1f
-
-#define r_SKB		L0
-#define r_HEADLEN	L4
-#define r_SKB_DATA	L5
-#define r_TMP		G1
-#define r_TMP2		G3
-
-/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */
-extern u32 bpf_jit_load_word[];
-extern u32 bpf_jit_load_half[];
-extern u32 bpf_jit_load_byte[];
-extern u32 bpf_jit_load_byte_msh[];
-extern u32 bpf_jit_load_word_positive_offset[];
-extern u32 bpf_jit_load_half_positive_offset[];
-extern u32 bpf_jit_load_byte_positive_offset[];
-extern u32 bpf_jit_load_byte_msh_positive_offset[];
-extern u32 bpf_jit_load_word_negative_offset[];
-extern u32 bpf_jit_load_half_negative_offset[];
-extern u32 bpf_jit_load_byte_negative_offset[];
-extern u32 bpf_jit_load_byte_msh_negative_offset[];
-
-#else
-#define r_RESULT	%o0
-#define r_SKB		%o0
-#define r_OFF		%o1
-#define r_HEADLEN	%l4
-#define r_SKB_DATA	%l5
-#define r_TMP		%g1
-#define r_TMP2		%g3
 #endif
 
 #endif /* _BPF_JIT_H */
diff --git a/arch/sparc/net/bpf_jit_asm_64.S b/arch/sparc/net/bpf_jit_asm_64.S
deleted file mode 100644
index 7177867..0000000
--- a/arch/sparc/net/bpf_jit_asm_64.S
+++ /dev/null
@@ -1,162 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm/ptrace.h>
-
-#include "bpf_jit_64.h"
-
-#define SAVE_SZ		176
-#define SCRATCH_OFF	STACK_BIAS + 128
-#define BE_PTR(label)	be,pn %xcc, label
-#define SIGN_EXTEND(reg)	sra reg, 0, reg
-
-#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_TMP], r_RESULT
-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_RESULT
-
-	.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_TMP], r_RESULT
-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_RESULT
-
-	.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_RESULT
-
-#define bpf_slow_path_common(LEN)	\
-	save	%sp, -SAVE_SZ, %sp;	\
-	mov	%i0, %o0;		\
-	mov	%i1, %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_RESULT
-	retl
-	 nop
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	bl	bpf_error
-	 lduh	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	bl	bpf_error
-	 ldub	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-
-#define bpf_negative_common(LEN)			\
-	save	%sp, -SAVE_SZ, %sp;			\
-	mov	%i0, %o0;				\
-	mov	%i1, %o1;				\
-	SIGN_EXTEND(%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_RESULT
-
-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_RESULT
-
-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_RESULT
-
-bpf_error:
-	/* Make the JIT program itself return zero. */
-	ret
-	restore	%g0, %g0, %o0
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 48a2586..9f5918e 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -48,10 +48,6 @@ static void bpf_flush_icache(void *start_, void *end_)
 	}
 }
 
-#define SEEN_DATAREF 1 /* might call external helpers */
-#define SEEN_XREG    2 /* ebx is used */
-#define SEEN_MEM     4 /* use mem[] for temporary storage */
-
 #define S13(X)		((X) & 0x1fff)
 #define S5(X)		((X) & 0x1f)
 #define IMMED		0x00002000
@@ -198,7 +194,6 @@ struct jit_ctx {
 	bool 			tmp_1_used;
 	bool 			tmp_2_used;
 	bool 			tmp_3_used;
-	bool			saw_ld_abs_ind;
 	bool			saw_frame_pointer;
 	bool			saw_call;
 	bool			saw_tail_call;
@@ -207,9 +202,7 @@ struct jit_ctx {
 
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
-#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 2)
-#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 3)
-#define TMP_REG_3	(MAX_BPF_JIT_REG + 4)
+#define TMP_REG_3	(MAX_BPF_JIT_REG + 2)
 
 /* Map BPF registers to SPARC registers */
 static const int bpf2sparc[] = {
@@ -238,9 +231,6 @@ static const int bpf2sparc[] = {
 	[TMP_REG_1] = G1,
 	[TMP_REG_2] = G2,
 	[TMP_REG_3] = G3,
-
-	[SKB_HLEN_REG] = L4,
-	[SKB_DATA_REG] = L5,
 };
 
 static void emit(const u32 insn, struct jit_ctx *ctx)
@@ -800,25 +790,6 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
 	return 0;
 }
 
-static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb)
-{
-	const u8 r_headlen = bpf2sparc[SKB_HLEN_REG];
-	const u8 r_data = bpf2sparc[SKB_DATA_REG];
-	const u8 r_tmp = bpf2sparc[TMP_REG_1];
-	unsigned int off;
-
-	off = offsetof(struct sk_buff, len);
-	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx);
-
-	off = offsetof(struct sk_buff, data_len);
-	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx);
-
-	emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx);
-
-	off = offsetof(struct sk_buff, data);
-	emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx);
-}
-
 /* Just skip the save instruction and the ctx register move.  */
 #define BPF_TAILCALL_PROLOGUE_SKIP	16
 #define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
@@ -857,9 +828,6 @@ static void build_prologue(struct jit_ctx *ctx)
 
 	emit_reg_move(I0, O0, ctx);
 	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
-
-	if (ctx->saw_ld_abs_ind)
-		load_skb_regs(ctx, bpf2sparc[BPF_REG_1]);
 }
 
 static void build_epilogue(struct jit_ctx *ctx)
@@ -1225,16 +1193,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		u8 *func = ((u8 *)__bpf_call_base) + imm;
 
 		ctx->saw_call = true;
-		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
-			emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
 
 		emit_call((u32 *)func, ctx);
 		emit_nop(ctx);
 
 		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-
-		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
-			load_skb_regs(ctx, L7);
 		break;
 	}
 
@@ -1412,43 +1375,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_nop(ctx);
 		break;
 	}
-#define CHOOSE_LOAD_FUNC(K, func) \
-		((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word);
-		goto common_load;
-	case BPF_LD | BPF_ABS | BPF_H:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half);
-		goto common_load;
-	case BPF_LD | BPF_ABS | BPF_B:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte);
-		goto common_load;
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-		func = bpf_jit_load_word;
-		goto common_load;
-	case BPF_LD | BPF_IND | BPF_H:
-		func = bpf_jit_load_half;
-		goto common_load;
-
-	case BPF_LD | BPF_IND | BPF_B:
-		func = bpf_jit_load_byte;
-	common_load:
-		ctx->saw_ld_abs_ind = true;
-
-		emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx);
-		emit_loadimm(imm, O1, ctx);
-
-		if (BPF_MODE(code) == BPF_IND)
-			emit_alu(ADD, src, O1, ctx);
-
-		emit_call(func, ctx);
-		emit_alu_K(SRA, O1, 0, ctx);
-
-		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-		break;
 
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
@@ -1583,12 +1509,11 @@ skip_init_ctx:
 		build_epilogue(&ctx);
 
 		if (bpf_jit_enable > 1)
-			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass,
+			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass,
 				image_size - (ctx.idx * 4),
 				ctx.tmp_1_used ? '1' : ' ',
 				ctx.tmp_2_used ? '2' : ' ',
 				ctx.tmp_3_used ? '3' : ' ',
-				ctx.saw_ld_abs_ind ? 'L' : ' ',
 				ctx.saw_frame_pointer ? 'F' : ' ',
 				ctx.saw_call ? 'C' : ' ',
 				ctx.saw_tail_call ? 'T' : ' ');