diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index bf82c6f7d690..85089c79a828 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -2474,28 +2474,29 @@ struct text_poke_loc {
 struct bp_patching_desc {
 	struct text_poke_loc *vec;
 	int nr_entries;
-	atomic_t refs;
 };
 
+static DEFINE_PER_CPU(atomic_t, bp_refs);
+
 static struct bp_patching_desc bp_desc;
 
 static __always_inline
 struct bp_patching_desc *try_get_desc(void)
 {
-	struct bp_patching_desc *desc = &bp_desc;
+	atomic_t *refs = this_cpu_ptr(&bp_refs);
 
-	if (!raw_atomic_inc_not_zero(&desc->refs))
+	if (!raw_atomic_inc_not_zero(refs))
 		return NULL;
 
-	return desc;
+	return &bp_desc;
 }
 
 static __always_inline void put_desc(void)
 {
-	struct bp_patching_desc *desc = &bp_desc;
+	atomic_t *refs = this_cpu_ptr(&bp_refs);
 
 	smp_mb__before_atomic();
-	raw_atomic_dec(&desc->refs);
+	raw_atomic_dec(refs);
 }
 
 static __always_inline void *text_poke_addr(struct text_poke_loc *tp)
@@ -2528,9 +2529,9 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 	 * Having observed our INT3 instruction, we now must observe
 	 * bp_desc with non-zero refcount:
 	 *
-	 *	bp_desc.refs = 1		INT3
-	 *	WMB				RMB
-	 *	write INT3			if (bp_desc.refs != 0)
+	 *	bp_refs = 1		INT3
+	 *	WMB			RMB
+	 *	write INT3		if (bp_refs != 0)
 	 */
 	smp_rmb();
 
@@ -2636,7 +2637,8 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Corresponds to the implicit memory barrier in try_get_desc() to
 	 * ensure reading a non-zero refcount provides up to date bp_desc data.
 	 */
-	atomic_set_release(&bp_desc.refs, 1);
+	for_each_possible_cpu(i)
+		atomic_set_release(per_cpu_ptr(&bp_refs, i), 1);
 
 	/*
 	 * Function tracing can enable thousands of places that need to be
@@ -2750,8 +2752,12 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * Remove and wait for refs to be zero.
 	 */
-	if (!atomic_dec_and_test(&bp_desc.refs))
-		atomic_cond_read_acquire(&bp_desc.refs, !VAL);
+	for_each_possible_cpu(i) {
+		atomic_t *refs = per_cpu_ptr(&bp_refs, i);
+
+		if (unlikely(!atomic_dec_and_test(refs)))
+			atomic_cond_read_acquire(refs, !VAL);
+	}
 }
 
 static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,