powerpc/bpf: Only pad length-variable code at initial pass

Now that two real additional passes are performed in case of extra pass
requested by BPF core, padding is not needed anymore except during
initial pass done before memory allocation to count maximum possible
program size.

So, only do the padding when 'image' is NULL.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/921851d6577badc1e6b08b270a0ced80a6a26d03.1675245773.git.christophe.leroy@csgroup.eu

arch/powerpc/net/bpf_jit_comp32.c

@@ -206,9 +206,6 @@ int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
 
 	if (image && rel < 0x2000000 && rel >= -0x2000000) {
 		PPC_BL(func);
-		EMIT(PPC_RAW_NOP());
-		EMIT(PPC_RAW_NOP());
-		EMIT(PPC_RAW_NOP());
 	} else {
 		/* Load function address into r0 */
 		EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));
@@ -973,8 +970,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
 			PPC_LI32(dst_reg, (u32)insn[i].imm);
 			/* padding to allow full 4 instructions for later patching */
-			for (j = ctx->idx - tmp_idx; j < 4; j++)
-				EMIT(PPC_RAW_NOP());
+			if (!image)
+				for (j = ctx->idx - tmp_idx; j < 4; j++)
+					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;

arch/powerpc/net/bpf_jit_comp64.c

@@ -240,13 +240,14 @@ int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
 	 * load the callee's address, but this may optimize the number of
 	 * instructions required based on the nature of the address.
 	 *
-	 * Since we don't want the number of instructions emitted to change,
+	 * Since we don't want the number of instructions emitted to increase,
 	 * we pad the optimized PPC_LI64() call with NOPs to guarantee that
 	 * we always have a five-instruction sequence, which is the maximum
 	 * that PPC_LI64() can emit.
 	 */
-	for (i = ctx->idx - ctx_idx; i < 5; i++)
-		EMIT(PPC_RAW_NOP());
+	if (!image)
+		for (i = ctx->idx - ctx_idx; i < 5; i++)
+			EMIT(PPC_RAW_NOP());
 
 	EMIT(PPC_RAW_MTCTR(_R12));
 	EMIT(PPC_RAW_BCTRL());
@@ -938,8 +939,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			tmp_idx = ctx->idx;
 			PPC_LI64(dst_reg, imm64);
 			/* padding to allow full 5 instructions for later patching */
-			for (j = ctx->idx - tmp_idx; j < 5; j++)
-				EMIT(PPC_RAW_NOP());
+			if (!image)
+				for (j = ctx->idx - tmp_idx; j < 5; j++)
+					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;