3 files changed, 26 insertions, 19 deletions

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a0e52bd00ecc..3f6b137ef4e6 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 void reload_ucode_amd(void)
 {
 	struct microcode_amd *mc;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	mc = (struct microcode_amd *)amd_ucode_patch;
 
@@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
 	enum ucode_state ret;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index cb0fdcaf1415..7019d4b2df0c 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
-/*
- * Serialize late loading so that CPUs get updated one-by-one.
- */
-static DEFINE_RAW_SPINLOCK(update_lock);
-
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -566,11 +561,18 @@ static int __reload_late(void *info)
 	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
 		return -1;
 
-	raw_spin_lock(&update_lock);
-	apply_microcode_local(&err);
-	raw_spin_unlock(&update_lock);
+	/*
+	 * On an SMT system, it suffices to load the microcode on one sibling of
+	 * the core because the microcode engine is shared between the threads.
+	 * Synchronization still needs to take place so that no concurrent
+	 * loading attempts happen on multiple threads of an SMT core. See
+	 * below.
+	 */
+	if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
+		apply_microcode_local(&err);
+	else
+		goto wait_for_siblings;
 
-	/* siblings return UCODE_OK because their engine got updated already */
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
 		ret = -1;
@@ -578,14 +580,18 @@ static int __reload_late(void *info)
 		ret = 1;
 	}
 
+wait_for_siblings:
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
+		panic("Timeout during microcode update!\n");
+
 	/*
-	 * Increase the wait timeout to a safe value here since we're
-	 * serializing the microcode update and that could take a while on a
-	 * large number of CPUs. And that is fine as the *actual* timeout will
-	 * be determined by the last CPU finished updating and thus cut short.
+	 * At least one thread has completed update on each core.
+	 * For others, simply call the update to make sure the
+	 * per-cpu cpuinfo can be updated with right microcode
+	 * revision.
 	 */
-	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
-		panic("Timeout during microcode update!\n");
+	if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
+		apply_microcode_local(&err);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ce799cfe9434..6a99535d7f37 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	struct microcode_intel *mc;
 	enum ucode_state ret;
 	static int prev_rev;
@@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		return UCODE_ERROR;
 	}
 
-	if (rev != prev_rev) {
+	if (bsp && rev != prev_rev) {
 		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
 			rev,
 			mc->hdr.date & 0xffff,
@@ -852,7 +853,7 @@ out:
 	c->microcode	 = rev;
 
 	/* Update boot_cpu_data's revision too, if we're on the BSP: */
-	if (c->cpu_index == boot_cpu_data.cpu_index)
+	if (bsp)
 		boot_cpu_data.microcode = rev;
 
 	return ret;