powerpc: bpf: eliminate zero extension code-gen

Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

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 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			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 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		/* 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;