Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-05-31

The following pull-request contains BPF updates for your *net-next* tree.

Lots of exciting new features in the first PR of this developement cycle!
The main changes are:

1) misc verifier improvements, from Alexei.

2) bpftool can now convert btf to valid C, from Andrii.

3) verifier can insert explicit ZEXT insn when requested by 32-bit JITs.
   This feature greatly improves BPF speed on 32-bit architectures. From Jiong.

4) cgroups will now auto-detach bpf programs. This fixes issue of thousands
   bpf programs got stuck in dying cgroups. From Roman.

5) new bpf_send_signal() helper, from Yonghong.

6) cgroup inet skb programs can signal CN to the stack, from Lawrence.

7) miscellaneous cleanups, from many developers.
====================

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

6 files changed, 211 insertions, 63 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c8bfbbfdfcc3..97a6b4b2a115 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -736,7 +736,8 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 
 		/* ALU operation */
 		emit_alu_r(rd[1], rs, true, false, op, ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 	}
 
 	arm_bpf_put_reg64(dst, rd, ctx);
@@ -758,8 +759,9 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
 		emit_a32_mov_r(dst_lo, src_lo, ctx);
-		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			/* Zero out high 4 bytes */
+			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
@@ -1060,17 +1062,20 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -1359,6 +1364,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
+			if (imm == 1) {
+				/* Special mov32 for zext */
+				emit_a32_mov_i(dst_hi, 0, ctx);
+				break;
+			}
 			emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
@@ -1438,7 +1448,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		}
 		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
 		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1453,7 +1464,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			return -EINVAL;
 		if (imm)
 			emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = dst << imm */
 	case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -1488,7 +1500,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = ~dst */
 	case BPF_ALU | BPF_NEG:
 		emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = ~dst (64 bit) */
 	case BPF_ALU64 | BPF_NEG:
@@ -1544,11 +1557,13 @@ emit_bswap_uxt:
 #else /* ARMv6+ */
 			emit(ARM_UXTH(rd[1], rd[1]), ctx);
 #endif
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 32:
 			/* zero-extend 32 bits into 64 bits */
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 64:
 			/* nop */
@@ -1838,6 +1853,11 @@ void bpf_jit_compile(struct bpf_prog *prog)
 	/* Nothing to do here. We support Internal BPF. */
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 21a1dcd4b156..0ebd946f178b 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -504,6 +504,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
 			/* slw clears top 32 bits */
 			PPC_SLW(dst_reg, dst_reg, src_reg);
+			/* skip zero extension move, but set address map. */
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
 			PPC_SLD(dst_reg, dst_reg, src_reg);
@@ -511,6 +514,8 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
 			/* with imm 0, we still need to clear top 32 bits */
 			PPC_SLWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
 			if (imm != 0)
@@ -518,12 +523,16 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			break;
 		case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
 			PPC_SRW(dst_reg, dst_reg, src_reg);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
 			PPC_SRD(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
 			PPC_SRWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
 			if (imm != 0)
@@ -548,6 +557,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		 */
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
+			if (imm == 1) {
+				/* special mov32 for zext */
+				PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+				break;
+			}
 			PPC_MR(dst_reg, src_reg);
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
@@ -555,11 +569,13 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			PPC_LI32(dst_reg, imm);
 			if (imm < 0)
 				goto bpf_alu32_trunc;
+			else if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 
 bpf_alu32_trunc:
 		/* Truncate to 32-bits */
-		if (BPF_CLASS(code) == BPF_ALU)
+		if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext)
 			PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
 		break;
 
@@ -618,10 +634,13 @@ emit_clear:
 			case 16:
 				/* zero-extend 16 bits into 64 bits */
 				PPC_RLDICL(dst_reg, dst_reg, 0, 48);
+				if (insn_is_zext(&insn[i + 1]))
+					addrs[++i] = ctx->idx * 4;
 				break;
 			case 32:
-				/* zero-extend 32 bits into 64 bits */
-				PPC_RLDICL(dst_reg, dst_reg, 0, 32);
+				if (!fp->aux->verifier_zext)
+					/* zero-extend 32 bits into 64 bits */
+					PPC_RLDICL(dst_reg, dst_reg, 0, 32);
 				break;
 			case 64:
 				/* nop */
@@ -698,14 +717,20 @@ emit_clear:
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 			PPC_LBZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
 			PPC_LHZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
 			PPC_LWZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
@@ -1046,6 +1071,11 @@ struct powerpc64_jit_data {
 	struct codegen_context ctx;
 };
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
 	u32 proglen;
diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c
index 80b12aa5e10d..c4c836e3d318 100644
--- a/arch/riscv/net/bpf_jit_comp.c
+++ b/arch/riscv/net/bpf_jit_comp.c
@@ -731,6 +731,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 {
 	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
 		    BPF_CLASS(insn->code) == BPF_JMP;
+	struct bpf_prog_aux *aux = ctx->prog->aux;
 	int rvoff, i = insn - ctx->prog->insnsi;
 	u8 rd = -1, rs = -1, code = insn->code;
 	s16 off = insn->off;
@@ -742,8 +743,13 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
+		if (imm == 1) {
+			/* Special mov32 for zext */
+			emit_zext_32(rd, ctx);
+			break;
+		}
 		emit(is64 ? rv_addi(rd, rs, 0) : rv_addiw(rd, rs, 0), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -771,19 +777,19 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_X:
 		emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 		emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
 		emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_X:
@@ -867,7 +873,7 @@ out_be:
 	case BPF_ALU | BPF_MOV | BPF_K:
 	case BPF_ALU64 | BPF_MOV | BPF_K:
 		emit_imm(rd, imm, ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -882,7 +888,7 @@ out_be:
 			emit(is64 ? rv_add(rd, rd, RV_REG_T1) :
 			     rv_addw(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_K:
@@ -895,7 +901,7 @@ out_be:
 			emit(is64 ? rv_sub(rd, rd, RV_REG_T1) :
 			     rv_subw(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
@@ -906,7 +912,7 @@ out_be:
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_and(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
@@ -917,7 +923,7 @@ out_be:
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_or(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
@@ -928,7 +934,7 @@ out_be:
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_xor(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
@@ -936,7 +942,7 @@ out_be:
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_mul(rd, rd, RV_REG_T1) :
 		     rv_mulw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K:
@@ -944,7 +950,7 @@ out_be:
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
 		     rv_divuw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_K:
@@ -952,7 +958,7 @@ out_be:
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
 		     rv_remuw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
@@ -1239,6 +1245,8 @@ out_be:
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_H:
 		if (is_12b_int(off)) {
@@ -1249,6 +1257,8 @@ out_be:
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_W:
 		if (is_12b_int(off)) {
@@ -1259,6 +1269,8 @@ out_be:
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_DW:
 		if (is_12b_int(off)) {
@@ -1503,6 +1515,11 @@ static void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	bool tmp_blinded = false, extra_pass = false;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5e7c63033159..e636728ab452 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -299,9 +299,11 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 
 #define EMIT_ZERO(b1)						\
 ({								\
-	/* llgfr %dst,%dst (zero extend to 64 bit) */		\
-	EMIT4(0xb9160000, b1, b1);				\
-	REG_SET_SEEN(b1);					\
+	if (!fp->aux->verifier_zext) {				\
+		/* llgfr %dst,%dst (zero extend to 64 bit) */	\
+		EMIT4(0xb9160000, b1, b1);			\
+		REG_SET_SEEN(b1);				\
+	}							\
 })
 
 /*
@@ -520,6 +522,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */
 		/* llgfr %dst,%src */
 		EMIT4(0xb9160000, dst_reg, src_reg);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
 		/* lgr %dst,%src */
@@ -528,6 +532,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */
 		/* llilf %dst,imm */
 		EMIT6_IMM(0xc00f0000, dst_reg, imm);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = imm */
 		/* lgfi %dst,imm */
@@ -639,6 +645,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT4(0xb9970000, REG_W0, src_reg);
 		/* llgfr %dst,%rc */
 		EMIT4(0xb9160000, dst_reg, rc_reg);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	}
 	case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
@@ -676,6 +684,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 			      EMIT_CONST_U32(imm));
 		/* llgfr %dst,%rc */
 		EMIT4(0xb9160000, dst_reg, rc_reg);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	}
 	case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
@@ -864,10 +874,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		case 16: /* dst = (u16) cpu_to_be16(dst) */
 			/* llghr %dst,%dst */
 			EMIT4(0xb9850000, dst_reg, dst_reg);
+			if (insn_is_zext(&insn[1]))
+				insn_count = 2;
 			break;
 		case 32: /* dst = (u32) cpu_to_be32(dst) */
-			/* llgfr %dst,%dst */
-			EMIT4(0xb9160000, dst_reg, dst_reg);
+			if (!fp->aux->verifier_zext)
+				/* llgfr %dst,%dst */
+				EMIT4(0xb9160000, dst_reg, dst_reg);
 			break;
 		case 64: /* dst = (u64) cpu_to_be64(dst) */
 			break;
@@ -882,12 +895,15 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 			EMIT4_DISP(0x88000000, dst_reg, REG_0, 16);
 			/* llghr %dst,%dst */
 			EMIT4(0xb9850000, dst_reg, dst_reg);
+			if (insn_is_zext(&insn[1]))
+				insn_count = 2;
 			break;
 		case 32: /* dst = (u32) cpu_to_le32(dst) */
 			/* lrvr %dst,%dst */
 			EMIT4(0xb91f0000, dst_reg, dst_reg);
-			/* llgfr %dst,%dst */
-			EMIT4(0xb9160000, dst_reg, dst_reg);
+			if (!fp->aux->verifier_zext)
+				/* llgfr %dst,%dst */
+				EMIT4(0xb9160000, dst_reg, dst_reg);
 			break;
 		case 64: /* dst = (u64) cpu_to_le64(dst) */
 			/* lrvgr %dst,%dst */
@@ -968,16 +984,22 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		/* llgc %dst,0(off,%src) */
 		EMIT6_DISP_LH(0xe3000000, 0x0090, dst_reg, src_reg, REG_0, off);
 		jit->seen |= SEEN_MEM;
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
 		/* llgh %dst,0(off,%src) */
 		EMIT6_DISP_LH(0xe3000000, 0x0091, dst_reg, src_reg, REG_0, off);
 		jit->seen |= SEEN_MEM;
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
 		/* llgf %dst,off(%src) */
 		jit->seen |= SEEN_MEM;
 		EMIT6_DISP_LH(0xe3000000, 0x0016, dst_reg, src_reg, REG_0, off);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
 		/* lg %dst,0(off,%src) */
@@ -1282,6 +1304,11 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 	return 0;
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 /*
  * Compile eBPF program "fp"
  */
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 65428e79b2f3..3364e2a00989 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -908,6 +908,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 		emit_alu3_K(SRL, src, 0, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		emit_reg_move(src, dst, ctx);
@@ -942,6 +944,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_DIV | BPF_X:
 		emit_write_y(G0, ctx);
 		emit_alu(DIV, src, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 		emit_alu(UDIVX, src, dst, ctx);
@@ -975,6 +979,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	case BPF_ALU | BPF_RSH | BPF_X:
 		emit_alu(SRL, src, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit_alu(SRLX, src, dst, ctx);
@@ -997,9 +1003,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		case 16:
 			emit_alu_K(SLL, dst, 16, ctx);
 			emit_alu_K(SRL, dst, 16, ctx);
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
 		case 32:
-			emit_alu_K(SRL, dst, 0, ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit_alu_K(SRL, dst, 0, ctx);
 			break;
 		case 64:
 			/* nop */
@@ -1021,6 +1030,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			emit_alu3_K(AND, dst, 0xff, dst, ctx);
 			emit_alu3_K(SLL, tmp, 8, tmp, ctx);
 			emit_alu(OR, tmp, dst, ctx);
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
 
 		case 32:
@@ -1037,6 +1048,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			emit_alu3_K(AND, dst, 0xff, dst, ctx);	/* dst	= dst & 0xff */
 			emit_alu3_K(SLL, dst, 24, dst, ctx);	/* dst  = dst << 24 */
 			emit_alu(OR, tmp, dst, ctx);		/* dst  = dst | tmp */
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
 
 		case 64:
@@ -1050,6 +1063,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = imm */
 	case BPF_ALU | BPF_MOV | BPF_K:
 		emit_loadimm32(imm, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_K:
 		emit_loadimm_sext(imm, dst, ctx);
@@ -1132,6 +1147,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	case BPF_ALU | BPF_RSH | BPF_K:
 		emit_alu_K(SRL, dst, imm, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		emit_alu_K(SRLX, dst, imm, ctx);
@@ -1144,7 +1161,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 
 	do_alu32_trunc:
-		if (BPF_CLASS(code) == BPF_ALU)
+		if (BPF_CLASS(code) == BPF_ALU &&
+		    !ctx->prog->aux->verifier_zext)
 			emit_alu_K(SRL, dst, 0, ctx);
 		break;
 
@@ -1265,6 +1283,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			rs2 = RS2(tmp);
 		}
 		emit(opcode | RS1(src) | rs2 | RD(dst), ctx);
+		if (opcode != LD64 && insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	}
 	/* ST: *(size *)(dst + off) = imm */
@@ -1432,6 +1452,11 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = 0x91d02005; /* ta 5 */
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct sparc64_jit_data {
 	struct bpf_binary_header *header;
 	u8 *image;
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index b29e82f190c7..133433d181ba 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -253,13 +253,14 @@ static inline void emit_ia32_mov_r(const u8 dst, const u8 src, bool dstk,
 /* dst = src */
 static inline void emit_ia32_mov_r64(const bool is64, const u8 dst[],
 				     const u8 src[], bool dstk,
-				     bool sstk, u8 **pprog)
+				     bool sstk, u8 **pprog,
+				     const struct bpf_prog_aux *aux)
 {
 	emit_ia32_mov_r(dst_lo, src_lo, dstk, sstk, pprog);
 	if (is64)
 		/* complete 8 byte move */
 		emit_ia32_mov_r(dst_hi, src_hi, dstk, sstk, pprog);
-	else
+	else if (!aux->verifier_zext)
 		/* zero out high 4 bytes */
 		emit_ia32_mov_i(dst_hi, 0, dstk, pprog);
 }
@@ -313,7 +314,8 @@ static inline void emit_ia32_mul_r(const u8 dst, const u8 src, bool dstk,
 }
 
 static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
-					 bool dstk, u8 **pprog)
+					 bool dstk, u8 **pprog,
+					 const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -334,12 +336,14 @@ static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
 		 */
 		EMIT2(0x0F, 0xB7);
 		EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 32:
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 64:
 		/* nop */
@@ -358,7 +362,8 @@ static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
 }
 
 static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val,
-				       bool dstk, u8 **pprog)
+				       bool dstk, u8 **pprog,
+				       const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -380,16 +385,18 @@ static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val,
 		EMIT2(0x0F, 0xB7);
 		EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
 
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 32:
 		/* Emit 'bswap eax' to swap lower 4 bytes */
 		EMIT1(0x0F);
 		EMIT1(add_1reg(0xC8, dreg_lo));
 
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 64:
 		/* Emit 'bswap eax' to swap lower 4 bytes */
@@ -569,7 +576,7 @@ static inline void emit_ia32_alu_r(const bool is64, const bool hi, const u8 op,
 static inline void emit_ia32_alu_r64(const bool is64, const u8 op,
 				     const u8 dst[], const u8 src[],
 				     bool dstk,  bool sstk,
-				     u8 **pprog)
+				     u8 **pprog, const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 
@@ -577,7 +584,7 @@ static inline void emit_ia32_alu_r64(const bool is64, const u8 op,
 	if (is64)
 		emit_ia32_alu_r(is64, true, op, dst_hi, src_hi, dstk, sstk,
 				&prog);
-	else
+	else if (!aux->verifier_zext)
 		emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 	*pprog = prog;
 }
@@ -668,7 +675,8 @@ static inline void emit_ia32_alu_i(const bool is64, const bool hi, const u8 op,
 /* ALU operation (64 bit) */
 static inline void emit_ia32_alu_i64(const bool is64, const u8 op,
 				     const u8 dst[], const u32 val,
-				     bool dstk, u8 **pprog)
+				     bool dstk, u8 **pprog,
+				     const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 	u32 hi = 0;
@@ -679,7 +687,7 @@ static inline void emit_ia32_alu_i64(const bool is64, const u8 op,
 	emit_ia32_alu_i(is64, false, op, dst_lo, val, dstk, &prog);
 	if (is64)
 		emit_ia32_alu_i(is64, true, op, dst_hi, hi, dstk, &prog);
-	else
+	else if (!aux->verifier_zext)
 		emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 
 	*pprog = prog;
@@ -1713,8 +1721,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_MOV | BPF_X:
 			switch (BPF_SRC(code)) {
 			case BPF_X:
-				emit_ia32_mov_r64(is64, dst, src, dstk,
-						  sstk, &prog);
+				if (imm32 == 1) {
+					/* Special mov32 for zext. */
+					emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+					break;
+				}
+				emit_ia32_mov_r64(is64, dst, src, dstk, sstk,
+						  &prog, bpf_prog->aux);
 				break;
 			case BPF_K:
 				/* Sign-extend immediate value to dst reg */
@@ -1754,11 +1767,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			switch (BPF_SRC(code)) {
 			case BPF_X:
 				emit_ia32_alu_r64(is64, BPF_OP(code), dst,
-						  src, dstk, sstk, &prog);
+						  src, dstk, sstk, &prog,
+						  bpf_prog->aux);
 				break;
 			case BPF_K:
 				emit_ia32_alu_i64(is64, BPF_OP(code), dst,
-						  imm32, dstk, &prog);
+						  imm32, dstk, &prog,
+						  bpf_prog->aux);
 				break;
 			}
 			break;
@@ -1777,7 +1792,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 						false, &prog);
 				break;
 			}
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		case BPF_ALU | BPF_LSH | BPF_X:
 		case BPF_ALU | BPF_RSH | BPF_X:
@@ -1797,7 +1813,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 						  &prog);
 				break;
 			}
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		/* dst = dst / src(imm) */
 		/* dst = dst % src(imm) */
@@ -1819,7 +1836,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 						    &prog);
 				break;
 			}
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		case BPF_ALU64 | BPF_DIV | BPF_K:
 		case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1836,7 +1854,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
 			emit_ia32_shift_r(BPF_OP(code), dst_lo, IA32_ECX, dstk,
 					  false, &prog);
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		/* dst = dst << imm */
 		case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -1872,7 +1891,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_NEG:
 			emit_ia32_alu_i(is64, false, BPF_OP(code),
 					dst_lo, 0, dstk, &prog);
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		/* dst = ~dst (64 bit) */
 		case BPF_ALU64 | BPF_NEG:
@@ -1892,11 +1912,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 		/* dst = htole(dst) */
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
-			emit_ia32_to_le_r64(dst, imm32, dstk, &prog);
+			emit_ia32_to_le_r64(dst, imm32, dstk, &prog,
+					    bpf_prog->aux);
 			break;
 		/* dst = htobe(dst) */
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
-			emit_ia32_to_be_r64(dst, imm32, dstk, &prog);
+			emit_ia32_to_be_r64(dst, imm32, dstk, &prog,
+					    bpf_prog->aux);
 			break;
 		/* dst = imm64 */
 		case BPF_LD | BPF_IMM | BPF_DW: {
@@ -2051,6 +2073,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			case BPF_B:
 			case BPF_H:
 			case BPF_W:
+				if (!bpf_prog->aux->verifier_zext)
+					break;
 				if (dstk) {
 					EMIT3(0xC7, add_1reg(0x40, IA32_EBP),
 					      STACK_VAR(dst_hi));
@@ -2475,6 +2499,11 @@ notyet:
 	return proglen;
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;