diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 43f1c76d48ce..a379b0ce19ff 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -113,23 +113,19 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
 
+	/* Initialize tail_call_cnt, to be skipped if we do tail calls. */
+	EMIT(PPC_RAW_LI(_R4, 0));
+
+#define BPF_TAILCALL_PROLOGUE_SIZE	4
+
+	EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
+
+	if (ctx->seen & SEEN_TAILCALL)
+		EMIT(PPC_RAW_STW(_R4, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
+
 	/* First arg comes in as a 32 bits pointer. */
 	EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
 	EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
-	EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
-
-	/*
-	 * Initialize tail_call_cnt in stack frame if we do tail calls.
-	 * Otherwise, put in NOPs so that it can be skipped when we are
-	 * invoked through a tail call.
-	 */
-	if (ctx->seen & SEEN_TAILCALL)
-		EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1,
-				 bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-	else
-		EMIT(PPC_RAW_NOP());
-
-#define BPF_TAILCALL_PROLOGUE_SIZE	16
 
 	/*
 	 * We need a stack frame, but we don't necessarily need to
@@ -170,6 +166,16 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 	for (i = BPF_PPC_NVR_MIN; i <= 31; i++)
 		if (bpf_is_seen_register(ctx, i))
 			EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, i)));
+
+	if (ctx->seen & SEEN_FUNC)
+		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
+
+	/* Tear down our stack frame */
+	EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));
+
+	if (ctx->seen & SEEN_FUNC)
+		EMIT(PPC_RAW_MTLR(_R0));
+
 }
 
 void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
@@ -178,16 +184,6 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 	bpf_jit_emit_common_epilogue(image, ctx);
 
-	/* Tear down our stack frame */
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
-
-	EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_MTLR(_R0));
-
 	EMIT(PPC_RAW_BLR());
 }
 
@@ -244,7 +240,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29));
 	EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array));
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs)));
-	EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
 
 	/*
 	 * if (prog == NULL)
@@ -255,19 +250,14 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 
 	/* goto *(prog->bpf_func + prologue_size); */
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func)));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
-
 	EMIT(PPC_RAW_ADDIC(_R3, _R3, BPF_TAILCALL_PROLOGUE_SIZE));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_MTLR(_R0));
-
 	EMIT(PPC_RAW_MTCTR(_R3));
 
 	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_1)));
 
+	/* Put tail_call_cnt in r4 */
+	EMIT(PPC_RAW_MR(_R4, _R0));
+
 	/* tear restore NVRs, ... */
 	bpf_jit_emit_common_epilogue(image, ctx);