Linux-libre 4.4-gnupck-4.4-gnu

2 files changed, 42 insertions, 24 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index b8efb8cd1..93d0b6d0b 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -125,7 +125,7 @@ static u64 jit_get_skb_w(struct sk_buff *skb, int offset)
 }
 
 /*
- * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
+ * Wrappers which handle both OABI and EABI and assures Thumb2 interworking
  * (where the assembly routines like __aeabi_uidiv could cause problems).
  */
 static u32 jit_udiv(u32 dividend, u32 divisor)
@@ -133,6 +133,11 @@ static u32 jit_udiv(u32 dividend, u32 divisor)
 	return dividend / divisor;
 }
 
+static u32 jit_mod(u32 dividend, u32 divisor)
+{
+	return dividend % divisor;
+}
+
 static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
 {
 	inst |= (cond << 28);
@@ -182,19 +187,6 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 	return fls(ctx->seen & SEEN_MEM);
 }
 
-static inline bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	u32 *ptr;
@@ -206,7 +198,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 static void build_prologue(struct jit_ctx *ctx)
 {
 	u16 reg_set = saved_regs(ctx);
-	u16 first_inst = ctx->skf->insns[0].code;
 	u16 off;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -236,7 +227,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */
@@ -471,11 +462,17 @@ static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
 #endif
 }
 
-static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
+static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx,
+				int bpf_op)
 {
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
-		emit(ARM_UDIV(rd, rm, rn), ctx);
+		if (bpf_op == BPF_DIV)
+			emit(ARM_UDIV(rd, rm, rn), ctx);
+		else {
+			emit(ARM_UDIV(ARM_R3, rm, rn), ctx);
+			emit(ARM_MLS(rd, rn, ARM_R3, rm), ctx);
+		}
 		return;
 	}
 #endif
@@ -496,7 +493,8 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
 		emit(ARM_MOV_R(ARM_R0, rm), ctx);
 
 	ctx->seen |= SEEN_CALL;
-	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
+	emit_mov_i(ARM_R3, bpf_op == BPF_DIV ? (u32)jit_udiv : (u32)jit_mod,
+		   ctx);
 	emit_blx_r(ARM_R3, ctx);
 
 	if (rd != ARM_R0)
@@ -698,13 +696,27 @@ load_ind:
 			if (k == 1)
 				break;
 			emit_mov_i(r_scratch, k, ctx);
-			emit_udiv(r_A, r_A, r_scratch, ctx);
+			emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_DIV);
 			break;
 		case BPF_ALU | BPF_DIV | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_CMP_I(r_X, 0), ctx);
 			emit_err_ret(ARM_COND_EQ, ctx);
-			emit_udiv(r_A, r_A, r_X, ctx);
+			emit_udivmod(r_A, r_A, r_X, ctx, BPF_DIV);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_K:
+			if (k == 1) {
+				emit_mov_i(r_A, 0, ctx);
+				break;
+			}
+			emit_mov_i(r_scratch, k, ctx);
+			emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_MOD);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_X:
+			update_on_xread(ctx);
+			emit(ARM_CMP_I(r_X, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+			emit_udivmod(r_A, r_A, r_X, ctx, BPF_MOD);
 			break;
 		case BPF_ALU | BPF_OR | BPF_K:
 			/* A |= K */
@@ -744,7 +756,8 @@ load_ind:
 		case BPF_ALU | BPF_RSH | BPF_K:
 			if (unlikely(k > 31))
 				return -1;
-			emit(ARM_LSR_I(r_A, r_A, k), ctx);
+			if (k)
+				emit(ARM_LSR_I(r_A, r_A, k), ctx);
 			break;
 		case BPF_ALU | BPF_RSH | BPF_X:
 			update_on_xread(ctx);
@@ -1035,7 +1048,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 	}
 	build_epilogue(&ctx);
 
-	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+	flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx));
 
 #if __LINUX_ARM_ARCH__ < 7
 	if (ctx.imm_count)
@@ -1048,7 +1061,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 
 	set_memory_ro((unsigned long)header, header->pages);
 	fp->bpf_func = (void *)ctx.target;
-	fp->jited = true;
+	fp->jited = 1;
 out:
 	kfree(ctx.offsets);
 	return;
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index 4b17d5ab6..c46fca297 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -115,6 +115,8 @@
 
 #define ARM_INST_UMULL		0x00800090
 
+#define ARM_INST_MLS		0x00600090
+
 /*
  * Use a suitable undefined instruction to use for ARM/Thumb2 faulting.
  * We need to be careful not to conflict with those used by other modules
@@ -210,4 +212,7 @@
 #define ARM_UMULL(rd_lo, rd_hi, rn, rm)	(ARM_INST_UMULL | (rd_hi) << 16 \
 					 | (rd_lo) << 12 | (rm) << 8 | rn)
 
+#define ARM_MLS(rd, rn, rm, ra)	(ARM_INST_MLS | (rd) << 16 | (rn) | (rm) << 8 \
+				 | (ra) << 12)
+
 #endif /* PFILTER_OPCODES_ARM_H */