diff --git a/kernel/smp.c b/kernel/smp.c
index a0bb56bd8dda..8a847a34f132 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -182,16 +182,22 @@ static atomic_t csd_bug_count = ATOMIC_INIT(0);
 static void __csd_lock_record(call_single_data_t *csd)
 {
 	if (!csd) {
-		smp_mb(); /* NULL cur_csd after unlock. */
-		__this_cpu_write(cur_csd, NULL);
+		/*
+		 * Pairs with smp_load_acquire() of cur_csd in
+		 * csd_lock_wait_toolong(): orders any preceding CSD
+		 * callback/unlock before a remote reader observes NULL.
+		 */
+		smp_store_release(this_cpu_ptr(&cur_csd), NULL);
 		return;
 	}
 	__this_cpu_write(cur_csd_func, csd->func);
 	__this_cpu_write(cur_csd_info, csd->info);
-	smp_wmb(); /* func and info before csd. */
-	__this_cpu_write(cur_csd, csd);
-	smp_mb(); /* Update cur_csd before function call. */
-		  /* Or before unlock, as the case may be. */
+	/*
+	 * Pairs with smp_load_acquire() of cur_csd in
+	 * csd_lock_wait_toolong(): publishes cur_csd_func and
+	 * cur_csd_info before the non-NULL pointer becomes visible.
+	 */
+	smp_store_release(this_cpu_ptr(&cur_csd), csd);
 }
 
 static __always_inline void csd_lock_record(call_single_data_t *csd)
@@ -272,7 +278,13 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
 		cpux = 0;
 	else
 		cpux = cpu;
-	cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
+	/*
+	 * Pairs with smp_store_release() of cur_csd in __csd_lock_record():
+	 * a non-NULL cur_csd here implies cur_csd_func and cur_csd_info
+	 * are the matching publication; a NULL value is ordered after any
+	 * preceding CSD callback/unlock on the remote CPU.
+	 */
+	cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux));
 	/* How long since this CSD lock was stuck. */
 	ts_delta = ts2 - ts0;
 	pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n",