diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index be2b43a894f6..c06096df9118 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -206,7 +206,7 @@ struct jit_context {
 /* number of bytes emit_call() needs to generate call instruction */
 #define X86_CALL_SIZE		5
 
-#define PROLOGUE_SIZE		20
+#define PROLOGUE_SIZE		25
 
 /*
  * Emit x86-64 prologue code for BPF program and check its size.
@@ -215,8 +215,13 @@ struct jit_context {
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 {
 	u8 *prog = *pprog;
-	int cnt = 0;
+	int cnt = X86_CALL_SIZE;
 
+	/* BPF trampoline can be made to work without these nops,
+	 * but let's waste 5 bytes for now and optimize later
+	 */
+	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
+	prog += cnt;
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */