Merge branch 'bpf-improvements-and-fixes'

Daniel Borkmann says:

====================
This set contains a small cleanup in cBPF prologue generation and
otherwise fixes an outstanding issue related to BPF to BPF calls
and exception handling. For details please see related patches.
Last but not least, BPF selftests is extended with several new
test cases.

Thanks!
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/arm/net/bpf_jit_32.c

@@ -363,15 +363,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
 	const u8 *tmp = bpf2a32[TMP_REG_1];
-	s32 jmp_offset;
 
-	/* checks if divisor is zero or not. If it is, then
-	 * exit directly.
-	 */
-	emit(ARM_CMP_I(rn, 0), ctx);
-	_emit(ARM_COND_EQ, ARM_MOV_I(ARM_R0, 0), ctx);
-	jmp_offset = epilogue_offset(ctx);
-	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
 		if (op == BPF_DIV)

arch/arm64/net/bpf_jit_comp.c

@@ -390,18 +390,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-	{
-		const u8 r0 = bpf2a64[BPF_REG_0];
-
-		/* if (src == 0) return 0 */
-		jmp_offset = 3; /* skip ahead to else path */
-		check_imm19(jmp_offset);
-		emit(A64_CBNZ(is64, src, jmp_offset), ctx);
-		emit(A64_MOVZ(1, r0, 0, 0), ctx);
-		jmp_offset = epilogue_offset(ctx);
-		check_imm26(jmp_offset);
-		emit(A64_B(jmp_offset), ctx);
-		/* else */
 		switch (BPF_OP(code)) {
 		case BPF_DIV:
 			emit(A64_UDIV(is64, dst, dst, src), ctx);
@@ -413,7 +401,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		}
 		break;
-	}
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(A64_LSLV(is64, dst, dst, src), ctx);

arch/mips/net/ebpf_jit.c

@@ -741,16 +741,11 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
 		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX)
 			/* sign extend */
@@ -770,19 +765,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU64 | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
 			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
-
 		if (insn->imm == 1) {
 			/* div by 1 is a nop, mod by 1 is zero */
 			if (bpf_op == BPF_MOD)
@@ -860,11 +849,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, ddivu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@@ -943,11 +927,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, divu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);

arch/powerpc/net/bpf_jit_comp64.c

@@ -381,10 +381,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
 		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
-			PPC_CMPWI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULW(b2p[TMP_REG_1], src_reg,
@@ -395,10 +391,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
-			PPC_CMPDI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,

arch/s390/net/bpf_jit_comp.c

@@ -610,11 +610,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltr %src,%src (if src == 0 goto fail) */
-		EMIT2(0x1200, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lhi %w0,0 */
 		EMIT4_IMM(0xa7080000, REG_W0, 0);
 		/* lr %w1,%dst */
@@ -630,11 +625,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltgr %src,%src (if src == 0 goto fail) */
-		EMIT4(0xb9020000, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lghi %w0,0 */
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */

arch/sparc/net/bpf_jit_comp_64.c

@@ -967,31 +967,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_alu(MULX, src, dst, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu(DIV, src, dst, ctx);
 		break;
-
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu(UDIVX, src, dst, ctx);
 		break;
-
 	case BPF_ALU | BPF_MOD | BPF_X: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu3(DIV, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
@@ -1003,10 +989,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu3(UDIVX, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
 		emit_alu3(SUB, dst, tmp, dst, ctx);

arch/x86/net/bpf_jit_comp.c

@@ -568,26 +568,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			 */
 			EMIT2(0x31, 0xd2);
 
-			if (BPF_SRC(insn->code) == BPF_X) {
-				/* if (src_reg == 0) return 0 */
-
-				/* cmp r11, 0 */
-				EMIT4(0x49, 0x83, 0xFB, 0x00);
-
-				/* jne .+9 (skip over pop, pop, xor and jmp) */
-				EMIT2(X86_JNE, 1 + 1 + 2 + 5);
-				EMIT1(0x5A); /* pop rdx */
-				EMIT1(0x58); /* pop rax */
-				EMIT2(0x31, 0xc0); /* xor eax, eax */
-
-				/* jmp cleanup_addr
-				 * addrs[i] - 11, because there are 11 bytes
-				 * after this insn: div, mov, pop, pop, mov
-				 */
-				jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
-				EMIT1_off32(0xE9, jmp_offset);
-			}
-
 			if (BPF_CLASS(insn->code) == BPF_ALU64)
 				/* div r11 */
 				EMIT3(0x49, 0xF7, 0xF3);

include/linux/filter.h

@@ -688,6 +688,8 @@ static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
 void bpf_prog_free(struct bpf_prog *fp);
 
+bool bpf_opcode_in_insntable(u8 code);
+
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);

kernel/bpf/core.c

@@ -782,6 +782,137 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 EXPORT_SYMBOL_GPL(__bpf_call_base);
 
+/* All UAPI available opcodes. */
+#define BPF_INSN_MAP(INSN_2, INSN_3)		\
+	/* 32 bit ALU operations. */		\
+	/*   Register based. */			\
+	INSN_3(ALU, ADD, X),			\
+	INSN_3(ALU, SUB, X),			\
+	INSN_3(ALU, AND, X),			\
+	INSN_3(ALU, OR,  X),			\
+	INSN_3(ALU, LSH, X),			\
+	INSN_3(ALU, RSH, X),			\
+	INSN_3(ALU, XOR, X),			\
+	INSN_3(ALU, MUL, X),			\
+	INSN_3(ALU, MOV, X),			\
+	INSN_3(ALU, DIV, X),			\
+	INSN_3(ALU, MOD, X),			\
+	INSN_2(ALU, NEG),			\
+	INSN_3(ALU, END, TO_BE),		\
+	INSN_3(ALU, END, TO_LE),		\
+	/*   Immediate based. */		\
+	INSN_3(ALU, ADD, K),			\
+	INSN_3(ALU, SUB, K),			\
+	INSN_3(ALU, AND, K),			\
+	INSN_3(ALU, OR,  K),			\
+	INSN_3(ALU, LSH, K),			\
+	INSN_3(ALU, RSH, K),			\
+	INSN_3(ALU, XOR, K),			\
+	INSN_3(ALU, MUL, K),			\
+	INSN_3(ALU, MOV, K),			\
+	INSN_3(ALU, DIV, K),			\
+	INSN_3(ALU, MOD, K),			\
+	/* 64 bit ALU operations. */		\
+	/*   Register based. */			\
+	INSN_3(ALU64, ADD,  X),			\
+	INSN_3(ALU64, SUB,  X),			\
+	INSN_3(ALU64, AND,  X),			\
+	INSN_3(ALU64, OR,   X),			\
+	INSN_3(ALU64, LSH,  X),			\
+	INSN_3(ALU64, RSH,  X),			\
+	INSN_3(ALU64, XOR,  X),			\
+	INSN_3(ALU64, MUL,  X),			\
+	INSN_3(ALU64, MOV,  X),			\
+	INSN_3(ALU64, ARSH, X),			\
+	INSN_3(ALU64, DIV,  X),			\
+	INSN_3(ALU64, MOD,  X),			\
+	INSN_2(ALU64, NEG),			\
+	/*   Immediate based. */		\
+	INSN_3(ALU64, ADD,  K),			\
+	INSN_3(ALU64, SUB,  K),			\
+	INSN_3(ALU64, AND,  K),			\
+	INSN_3(ALU64, OR,   K),			\
+	INSN_3(ALU64, LSH,  K),			\
+	INSN_3(ALU64, RSH,  K),			\
+	INSN_3(ALU64, XOR,  K),			\
+	INSN_3(ALU64, MUL,  K),			\
+	INSN_3(ALU64, MOV,  K),			\
+	INSN_3(ALU64, ARSH, K),			\
+	INSN_3(ALU64, DIV,  K),			\
+	INSN_3(ALU64, MOD,  K),			\
+	/* Call instruction. */			\
+	INSN_2(JMP, CALL),			\
+	/* Exit instruction. */			\
+	INSN_2(JMP, EXIT),			\
+	/* Jump instructions. */		\
+	/*   Register based. */			\
+	INSN_3(JMP, JEQ,  X),			\
+	INSN_3(JMP, JNE,  X),			\
+	INSN_3(JMP, JGT,  X),			\
+	INSN_3(JMP, JLT,  X),			\
+	INSN_3(JMP, JGE,  X),			\
+	INSN_3(JMP, JLE,  X),			\
+	INSN_3(JMP, JSGT, X),			\
+	INSN_3(JMP, JSLT, X),			\
+	INSN_3(JMP, JSGE, X),			\
+	INSN_3(JMP, JSLE, X),			\
+	INSN_3(JMP, JSET, X),			\
+	/*   Immediate based. */		\
+	INSN_3(JMP, JEQ,  K),			\
+	INSN_3(JMP, JNE,  K),			\
+	INSN_3(JMP, JGT,  K),			\
+	INSN_3(JMP, JLT,  K),			\
+	INSN_3(JMP, JGE,  K),			\
+	INSN_3(JMP, JLE,  K),			\
+	INSN_3(JMP, JSGT, K),			\
+	INSN_3(JMP, JSLT, K),			\
+	INSN_3(JMP, JSGE, K),			\
+	INSN_3(JMP, JSLE, K),			\
+	INSN_3(JMP, JSET, K),			\
+	INSN_2(JMP, JA),			\
+	/* Store instructions. */		\
+	/*   Register based. */			\
+	INSN_3(STX, MEM,  B),			\
+	INSN_3(STX, MEM,  H),			\
+	INSN_3(STX, MEM,  W),			\
+	INSN_3(STX, MEM,  DW),			\
+	INSN_3(STX, XADD, W),			\
+	INSN_3(STX, XADD, DW),			\
+	/*   Immediate based. */		\
+	INSN_3(ST, MEM, B),			\
+	INSN_3(ST, MEM, H),			\
+	INSN_3(ST, MEM, W),			\
+	INSN_3(ST, MEM, DW),			\
+	/* Load instructions. */		\
+	/*   Register based. */			\
+	INSN_3(LDX, MEM, B),			\
+	INSN_3(LDX, MEM, H),			\
+	INSN_3(LDX, MEM, W),			\
+	INSN_3(LDX, MEM, DW),			\
+	/*   Immediate based. */		\
+	INSN_3(LD, IMM, DW),			\
+	/*   Misc (old cBPF carry-over). */	\
+	INSN_3(LD, ABS, B),			\
+	INSN_3(LD, ABS, H),			\
+	INSN_3(LD, ABS, W),			\
+	INSN_3(LD, IND, B),			\
+	INSN_3(LD, IND, H),			\
+	INSN_3(LD, IND, W)
+
+bool bpf_opcode_in_insntable(u8 code)
+{
+#define BPF_INSN_2_TBL(x, y)    [BPF_##x | BPF_##y] = true
+#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
+	static const bool public_insntable[256] = {
+		[0 ... 255] = false,
+		/* Now overwrite non-defaults ... */
+		BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+	};
+#undef BPF_INSN_3_TBL
+#undef BPF_INSN_2_TBL
+	return public_insntable[code];
+}
+
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 /**
  *	__bpf_prog_run - run eBPF program on a given context
@@ -793,115 +924,18 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
 	u64 tmp;
+#define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
+#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
 	static const void *jumptable[256] = {
 		[0 ... 255] = &&default_label,
 		/* Now overwrite non-defaults ... */
-		/* 32 bit ALU operations */
-		[BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
-		[BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
-		[BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
-		[BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
-		[BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
-		[BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
-		[BPF_ALU | BPF_OR | BPF_X]  = &&ALU_OR_X,
-		[BPF_ALU | BPF_OR | BPF_K]  = &&ALU_OR_K,
-		[BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
-		[BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
-		[BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
-		[BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
-		[BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
-		[BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
-		[BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
-		[BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
-		[BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
-		[BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
-		[BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
-		[BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
-		[BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
-		[BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
-		[BPF_ALU | BPF_NEG] = &&ALU_NEG,
-		[BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
-		[BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
-		/* 64 bit ALU operations */
-		[BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
-		[BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
-		[BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
-		[BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
-		[BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
-		[BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
-		[BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
-		[BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
-		[BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
-		[BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
-		[BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
-		[BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
-		[BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
-		[BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
-		[BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
-		[BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
-		[BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
-		[BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
-		[BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
-		[BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
-		[BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
-		[BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
-		[BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
-		[BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
-		[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
-		/* Call instruction */
-		[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+		BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
+		/* Non-UAPI available opcodes. */
 		[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
 		[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
-		/* Jumps */
-		[BPF_JMP | BPF_JA] = &&JMP_JA,
-		[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
-		[BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
-		[BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
-		[BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
-		[BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
-		[BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
-		[BPF_JMP | BPF_JLT | BPF_X] = &&JMP_JLT_X,
-		[BPF_JMP | BPF_JLT | BPF_K] = &&JMP_JLT_K,
-		[BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
-		[BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
-		[BPF_JMP | BPF_JLE | BPF_X] = &&JMP_JLE_X,
-		[BPF_JMP | BPF_JLE | BPF_K] = &&JMP_JLE_K,
-		[BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
-		[BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
-		[BPF_JMP | BPF_JSLT | BPF_X] = &&JMP_JSLT_X,
-		[BPF_JMP | BPF_JSLT | BPF_K] = &&JMP_JSLT_K,
-		[BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
-		[BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
-		[BPF_JMP | BPF_JSLE | BPF_X] = &&JMP_JSLE_X,
-		[BPF_JMP | BPF_JSLE | BPF_K] = &&JMP_JSLE_K,
-		[BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
-		[BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
-		/* Program return */
-		[BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
-		/* Store instructions */
-		[BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
-		[BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
-		[BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
-		[BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
-		[BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
-		[BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
-		[BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
-		[BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
-		[BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
-		[BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
-		/* Load instructions */
-		[BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
-		[BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
-		[BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
-		[BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
-		[BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
-		[BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
-		[BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
-		[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
-		[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
-		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
-		[BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW,
 	};
+#undef BPF_INSN_3_LBL
+#undef BPF_INSN_2_LBL
 	u32 tail_call_cnt = 0;
 	void *ptr;
 	int off;
@@ -965,14 +999,10 @@ select_insn:
 		(*(s64 *) &DST) >>= IMM;
 		CONT;
 	ALU64_MOD_X:
-		if (unlikely(SRC == 0))
-			return 0;
 		div64_u64_rem(DST, SRC, &tmp);
 		DST = tmp;
 		CONT;
 	ALU_MOD_X:
-		if (unlikely((u32)SRC == 0))
-			return 0;
 		tmp = (u32) DST;
 		DST = do_div(tmp, (u32) SRC);
 		CONT;
@@ -985,13 +1015,9 @@ select_insn:
 		DST = do_div(tmp, (u32) IMM);
 		CONT;
 	ALU64_DIV_X:
-		if (unlikely(SRC == 0))
-			return 0;
 		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
-		if (unlikely((u32)SRC == 0))
-			return 0;
 		tmp = (u32) DST;
 		do_div(tmp, (u32) SRC);
 		DST = (u32) tmp;
@@ -1302,8 +1328,14 @@ load_byte:
 		goto load_byte;
 
 	default_label:
-		/* If we ever reach this, we have a bug somewhere. */
-		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+		/* If we ever reach this, we have a bug somewhere. Die hard here
+		 * instead of just returning 0; we could be somewhere in a subprog,
+		 * so execution could continue otherwise which we do /not/ want.
+		 *
+		 * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable().
+		 */
+		pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code);
+		BUG_ON(1);
 		return 0;
 }
 STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */

kernel/bpf/verifier.c

@@ -4981,6 +4981,13 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 next_insn:
 			insn++;
 			i++;
+			continue;
+		}
+
+		/* Basic sanity check before we invest more work here. */
+		if (!bpf_opcode_in_insntable(insn->code)) {
+			verbose(env, "unknown opcode %02x\n", insn->code);
+			return -EINVAL;
 		}
 	}
 
@@ -5064,14 +5071,21 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	return new_prog;
 }
 
-/* The verifier does more data flow analysis than llvm and will not explore
- * branches that are dead at run time. Malicious programs can have dead code
- * too. Therefore replace all dead at-run-time code with nops.
+/* The verifier does more data flow analysis than llvm and will not
+ * explore branches that are dead at run time. Malicious programs can
+ * have dead code too. Therefore replace all dead at-run-time code
+ * with 'ja -1'.
+ *
+ * Just nops are not optimal, e.g. if they would sit at the end of the
+ * program and through another bug we would manage to jump there, then
+ * we'd execute beyond program memory otherwise. Returning exception
+ * code also wouldn't work since we can have subprogs where the dead
+ * code could be located.
  */
 static void sanitize_dead_code(struct bpf_verifier_env *env)
 {
 	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
-	struct bpf_insn nop = BPF_MOV64_REG(BPF_REG_0, BPF_REG_0);
+	struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1);
 	struct bpf_insn *insn = env->prog->insnsi;
 	const int insn_cnt = env->prog->len;
 	int i;
@@ -5079,7 +5093,7 @@ static void sanitize_dead_code(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++) {
 		if (aux_data[i].seen)
 			continue;
-		memcpy(insn + i, &nop, sizeof(nop));
+		memcpy(insn + i, &trap, sizeof(trap));
 	}
 }
 
@@ -5386,15 +5400,37 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 	int i, cnt, delta = 0;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
-		if (insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
+		if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
+		    insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
+		    insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
 		    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
-			/* due to JIT bugs clear upper 32-bits of src register
-			 * before div/mod operation
-			 */
-			insn_buf[0] = BPF_MOV32_REG(insn->src_reg, insn->src_reg);
-			insn_buf[1] = *insn;
-			cnt = 2;
-			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+			struct bpf_insn mask_and_div[] = {
+				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
+				/* Rx div 0 -> 0 */
+				BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2),
+				BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
+				BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+				*insn,
+			};
+			struct bpf_insn mask_and_mod[] = {
+				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
+				/* Rx mod 0 -> Rx */
+				BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1),
+				*insn,
+			};
+			struct bpf_insn *patchlet;
+
+			if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
+			    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
+				patchlet = mask_and_div + (is64 ? 1 : 0);
+				cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0);
+			} else {
+				patchlet = mask_and_mod + (is64 ? 1 : 0);
+				cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0);
+			}
+
+			new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
 			if (!new_prog)
 				return -ENOMEM;
 

lib/test_bpf.c

@@ -2003,10 +2003,14 @@ static struct bpf_test tests[] = {
 		{ { 4, 0 }, { 5, 10 } }
 	},
 	{
-		"INT: DIV by zero",
+		/* This one doesn't go through verifier, but is just raw insn
+		 * as opposed to cBPF tests from here. Thus div by 0 tests are
+		 * done in test_verifier in BPF kselftests.
+		 */
+		"INT: DIV by -1",
 		.u.insns_int = {
 			BPF_ALU64_REG(BPF_MOV, R6, R1),
-			BPF_ALU64_IMM(BPF_MOV, R7, 0),
+			BPF_ALU64_IMM(BPF_MOV, R7, -1),
 			BPF_LD_ABS(BPF_B, 3),
 			BPF_ALU32_REG(BPF_DIV, R0, R7),
 			BPF_EXIT_INSN(),

net/core/filter.c

@@ -401,8 +401,8 @@ do_pass:
 		/* Classic BPF expects A and X to be reset first. These need
 		 * to be guaranteed to be the first two instructions.
 		 */
-		*new_insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
-		*new_insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_X, BPF_REG_X);
+		*new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
+		*new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X);
 
 		/* All programs must keep CTX in callee saved BPF_REG_CTX.
 		 * In eBPF case it's done by the compiler, here we need to
@@ -459,8 +459,15 @@ do_pass:
 				break;
 
 			if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) ||
-			    fp->code == (BPF_ALU | BPF_MOD | BPF_X))
+			    fp->code == (BPF_ALU | BPF_MOD | BPF_X)) {
 				*insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X);
+				/* Error with exception code on div/mod by 0.
+				 * For cBPF programs, this was always return 0.
+				 */
+				*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2);
+				*insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
+				*insn++ = BPF_EXIT_INSN();
+			}
 
 			*insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k);
 			break;

tools/testing/selftests/bpf/test_verifier.c

@@ -21,6 +21,7 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <sched.h>
+#include <limits.h>
 
 #include <sys/capability.h>
 #include <sys/resource.h>
@@ -111,7 +112,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"DIV32 by 0, zero check 2",
@@ -123,7 +124,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"DIV64 by 0, zero check",
@@ -135,7 +136,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"MOD32 by 0, zero check 1",
@@ -147,7 +148,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"MOD32 by 0, zero check 2",
@@ -159,7 +160,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"MOD64 by 0, zero check",
@@ -171,13 +172,245 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"DIV32 by 0, zero check ok, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 2),
+			BPF_MOV32_IMM(BPF_REG_2, 16),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 8,
+	},
+	{
+		"DIV32 by 0, zero check 1, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV32 by 0, zero check 2, cls",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV64 by 0, zero check, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"MOD32 by 0, zero check ok, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 3),
+			BPF_MOV32_IMM(BPF_REG_2, 5),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"MOD32 by 0, zero check 1, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"MOD32 by 0, zero check 2, cls",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"MOD64 by 0, zero check 1, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 2),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"MOD64 by 0, zero check 2, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, -1),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = -1,
+	},
+	/* Just make sure that JITs used udiv/umod as otherwise we get
+	 * an exception from INT_MIN/-1 overflow similarly as with div
+	 * by zero.
+	 */
+	{
+		"DIV32 overflow, check 1",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, -1),
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV32 overflow, check 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_IMM(BPF_DIV, BPF_REG_0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV64 overflow, check 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, -1),
+			BPF_LD_IMM64(BPF_REG_0, LLONG_MIN),
+			BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV64 overflow, check 2",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_0, LLONG_MIN),
+			BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
 		.retval = 0,
 	},
+	{
+		"MOD32 overflow, check 1",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, -1),
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = INT_MIN,
+	},
+	{
+		"MOD32 overflow, check 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_IMM(BPF_MOD, BPF_REG_0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = INT_MIN,
+	},
+	{
+		"MOD64 overflow, check 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, -1),
+			BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_3, BPF_REG_2, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"MOD64 overflow, check 2",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_MOD, BPF_REG_2, -1),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_3, BPF_REG_2, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"xor32 zero extend check",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_2, -1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 32),
+			BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 0xffff),
+			BPF_ALU32_REG(BPF_XOR, BPF_REG_2, BPF_REG_2),
+			BPF_MOV32_IMM(BPF_REG_0, 2),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
 	{
 		"empty prog",
 		.insns = {
 		},
-		.errstr = "last insn is not an exit or jmp",
+		.errstr = "unknown opcode 00",
 		.result = REJECT,
 	},
 	{
@@ -374,7 +607,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_ARSH not supported for 32 bit ALU",
+		.errstr = "unknown opcode c4",
 	},
 	{
 		"arsh32 on reg",
@@ -385,7 +618,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_ARSH not supported for 32 bit ALU",
+		.errstr = "unknown opcode cc",
 	},
 	{
 		"arsh64 on imm",
@@ -501,7 +734,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL | BPF_X, 0, 0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_CALL uses reserved",
+		.errstr = "unknown opcode 8d",
 		.result = REJECT,
 	},
 	{
@@ -691,7 +924,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(0, 0, 0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid BPF_LD_IMM",
+		.errstr = "unknown opcode 00",
 		.result = REJECT,
 	},
 	{
@@ -709,7 +942,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(-1, 0, 0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid BPF_ALU opcode f0",
+		.errstr = "unknown opcode ff",
 		.result = REJECT,
 	},
 	{
@@ -718,7 +951,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(-1, -1, -1, -1, -1),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid BPF_ALU opcode f0",
+		.errstr = "unknown opcode ff",
 		.result = REJECT,
 	},
 	{
@@ -7543,7 +7776,7 @@ static struct bpf_test tests[] = {
 			},
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_END uses reserved fields",
+		.errstr = "unknown opcode d7",
 		.result = REJECT,
 	},
 	{
@@ -8963,6 +9196,90 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.retval = 1,
 	},
+	{
+		"calls: div by 0 in subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(BPF_REG_2, 0),
+			BPF_MOV32_IMM(BPF_REG_3, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_3, BPF_REG_2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"calls: multiple ret types in subprog 1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = REJECT,
+		.errstr = "R0 invalid mem access 'inv'",
+	},
+	{
+		"calls: multiple ret types in subprog 2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 9),
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				    offsetof(struct __sk_buff, data)),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 64),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 16 },
+		.result = REJECT,
+		.errstr = "R0 min value is outside of the array range",
+	},
 	{
 		"calls: overlapping caller/callee",
 		.insns = {