x86/microcode: Add per CPU result state

The microcode rendezvous is purely acting on global state, which does
not allow to analyze fails in a coherent way.

Introduce per CPU state where the results are written into, which allows to
analyze the return codes of the individual CPUs.

Initialize the state when walking the cpu_present_mask in the online
check to avoid another for_each_cpu() loop.

Enhance the result print out with that.

The structure is intentionally named ucode_ctrl as it will gain control
fields in subsequent changes.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20231017211723.632681010@linutronix.de

diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 9fd5a9618c50dd7a8e3fde9783090dbb24cc7d3d..67b8932b9c801a28edb4f951e8f4ffaaa2c6529e 100644 (file)
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -252,6 +252,11 @@ static struct platform_device      *microcode_pdev;
  *   requirement can be relaxed in the future. Right now, this is conservative
  *   and good.
  */
+struct microcode_ctrl {
+       enum ucode_state        result;
+};
+
+static DEFINE_PER_CPU(struct microcode_ctrl, ucode_ctrl);
 static atomic_t late_cpus_in, late_cpus_out;
 
 static bool wait_for_cpus(atomic_t *cnt)
@@ -274,23 +279,19 @@ static bool wait_for_cpus(atomic_t *cnt)
        return false;
 }
 
-/*
- * Returns:
- * < 0 - on error
- *   0 - success (no update done or microcode was updated)
- */
-static int __reload_late(void *info)
+static int load_cpus_stopped(void *unused)
 {
        int cpu = smp_processor_id();
-       enum ucode_state err;
-       int ret = 0;
+       enum ucode_state ret;
 
        /*
         * Wait for all CPUs to arrive. A load will not be attempted unless all
         * CPUs show up.
         * */
-       if (!wait_for_cpus(&late_cpus_in))
-               return -1;
+       if (!wait_for_cpus(&late_cpus_in)) {
+               this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+               return 0;
+       }
 
        /*
         * On an SMT system, it suffices to load the microcode on one sibling of
@@ -299,17 +300,11 @@ static int __reload_late(void *info)
         * loading attempts happen on multiple threads of an SMT core. See
         * below.
         */
-       if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
-               err = microcode_ops->apply_microcode(cpu);
-       else
+       if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
                goto wait_for_siblings;
 
-       if (err >= UCODE_NFOUND) {
-               if (err == UCODE_ERROR) {
-                       pr_warn("Error reloading microcode on CPU %d\n", cpu);
-                       ret = -1;
-               }
-       }
+       ret = microcode_ops->apply_microcode(cpu);
+       this_cpu_write(ucode_ctrl.result, ret);
 
 wait_for_siblings:
        if (!wait_for_cpus(&late_cpus_out))
@@ -321,19 +316,18 @@ wait_for_siblings:
         * per-cpu cpuinfo can be updated with right microcode
         * revision.
         */
-       if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
-               err = microcode_ops->apply_microcode(cpu);
+       if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
+               return 0;
 
-       return ret;
+       ret = microcode_ops->apply_microcode(cpu);
+       this_cpu_write(ucode_ctrl.result, ret);
+       return 0;
 }
 
-/*
- * Reload microcode late on all CPUs. Wait for a sec until they
- * all gather together.
- */
-static int microcode_reload_late(void)
+static int load_late_stop_cpus(void)
 {
-       int old = boot_cpu_data.microcode, ret;
+       unsigned int cpu, updated = 0, failed = 0, timedout = 0, siblings = 0;
+       int old_rev = boot_cpu_data.microcode;
        struct cpuinfo_x86 prev_info;
 
        pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
@@ -348,26 +342,47 @@ static int microcode_reload_late(void)
         */
        store_cpu_caps(&prev_info);
 
-       ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+       stop_machine_cpuslocked(load_cpus_stopped, NULL, cpu_online_mask);
+
+       /* Analyze the results */
+       for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) {
+               switch (per_cpu(ucode_ctrl.result, cpu)) {
+               case UCODE_UPDATED:     updated++; break;
+               case UCODE_TIMEOUT:     timedout++; break;
+               case UCODE_OK:          siblings++; break;
+               default:                failed++; break;
+               }
+       }
 
        if (microcode_ops->finalize_late_load)
-               microcode_ops->finalize_late_load(ret);
-
-       if (!ret) {
-               pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n",
-                       old, boot_cpu_data.microcode);
-               microcode_check(&prev_info);
-               add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
-       } else {
-               pr_info("Reload failed, current microcode revision: 0x%x\n",
-                       boot_cpu_data.microcode);
+               microcode_ops->finalize_late_load(!updated);
+
+       if (!updated) {
+               /* Nothing changed. */
+               if (!failed && !timedout)
+                       return 0;
+               pr_err("update failed: %u CPUs failed %u CPUs timed out\n",
+                      failed, timedout);
+               return -EIO;
+       }
+
+       add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+       pr_info("load: updated on %u primary CPUs with %u siblings\n", updated, siblings);
+       if (failed || timedout) {
+               pr_err("load incomplete. %u CPUs timed out or failed\n",
+                      num_online_cpus() - (updated + siblings));
        }
-       return ret;
+       pr_info("revision: 0x%x -> 0x%x\n", old_rev, boot_cpu_data.microcode);
+       microcode_check(&prev_info);
+
+       return updated + siblings == num_online_cpus() ? 0 : -EIO;
 }
 
 /*
- *  Ensure that all required CPUs which are present and have been booted
- *  once are online.
+ * This function does two things:
+ *
+ * 1) Ensure that all required CPUs which are present and have been booted
+ *    once are online.
  *
  *    To pass this check, all primary threads must be online.
  *
@@ -378,9 +393,12 @@ static int microcode_reload_late(void)
  *    behaviour is undefined. The default play_dead() implementation on
  *    modern CPUs uses MWAIT, which is also not guaranteed to be safe
  *    against a microcode update which affects MWAIT.
+ *
+ * 2) Initialize the per CPU control structure
  */
-static bool ensure_cpus_are_online(void)
+static bool setup_cpus(void)
 {
+       struct microcode_ctrl ctrl = { .result = -1, };
        unsigned int cpu;
 
        for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) {
@@ -390,18 +408,20 @@ static bool ensure_cpus_are_online(void)
                                return false;
                        }
                }
+               /* Initialize the per CPU state */
+               per_cpu(ucode_ctrl, cpu) = ctrl;
        }
        return true;
 }
 
-static int ucode_load_late_locked(void)
+static int load_late_locked(void)
 {
-       if (!ensure_cpus_are_online())
+       if (!setup_cpus())
                return -EBUSY;
 
        switch (microcode_ops->request_microcode_fw(0, &microcode_pdev->dev)) {
        case UCODE_NEW:
-               return microcode_reload_late();
+               return load_late_stop_cpus();
        case UCODE_NFOUND:
                return -ENOENT;
        default:
@@ -421,7 +441,7 @@ static ssize_t reload_store(struct device *dev,
                return -EINVAL;
 
        cpus_read_lock();
-       ret = ucode_load_late_locked();
+       ret = load_late_locked();
        cpus_read_unlock();
 
        return ret ? : size;

diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 07aa5f8be69bdf0597eeb442e4763e1db909f003..c6990431b5dea406cac4327217ce32d6da472031 100644 (file)
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -16,6 +16,7 @@ enum ucode_state {
        UCODE_UPDATED,
        UCODE_NFOUND,
        UCODE_ERROR,
+       UCODE_TIMEOUT,
 };
 
 struct microcode_ops {