File 6808f549-x86-Intel-work-around-MONITOR-MWAIT-errata.patch of Package xen

# Commit 4aae4452efeee3d3bba092b875e37d1e7c8f6db9
# Date 2025-04-23 16:12:25 +0200
# Author Roger Pau Monne <roger.pau@citrix.com>
# Committer Roger Pau Monne <roger.pau@citrix.com>
x86/intel: workaround several MONITOR/MWAIT errata

There are several errata on Intel regarding the usage of the MONITOR/MWAIT
instructions, all having in common that stores to the monitored region
might not wake up the CPU.

Fix them by forcing the sending of an IPI for the affected models.

The Ice Lake issue has been reproduced internally on XenServer hardware,
and the fix does seem to prevent it.  The symptom was APs getting stuck in
the idle loop immediately after bring up, which in turn prevented the BSP
from making progress.  This would happen before the watchdog was
initialized, and hence the whole system would get stuck.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>

--- a/xen/arch/x86/acpi/cpu_idle.c
+++ b/xen/arch/x86/acpi/cpu_idle.c
@@ -441,8 +441,14 @@ void cpuidle_wakeup_mwait(cpumask_t *mas
     cpumask_andnot(mask, mask, &target);
 }
 
+/* Force sending of a wakeup IPI regardless of mwait usage. */
+bool __ro_after_init force_mwait_ipi_wakeup;
+
 bool arch_skip_send_event_check(unsigned int cpu)
 {
+    if ( force_mwait_ipi_wakeup )
+        return false;
+
     /*
      * This relies on softirq_pending() and mwait_wakeup() to access data
      * on the same cache line.
--- a/xen/arch/x86/cpu/intel.c
+++ b/xen/arch/x86/cpu/intel.c
@@ -8,6 +8,7 @@
 #include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
+#include <asm/mwait.h>
 #include <asm/uaccess.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
@@ -368,7 +369,6 @@ static void probe_c3_errata(const struct
         INTEL_FAM6_MODEL(0x25),
         { }
     };
-#undef INTEL_FAM6_MODEL
 
     /* Serialized by the AP bringup code. */
     if ( max_cstate > 1 && (c->apicid & (c->x86_num_siblings - 1)) &&
@@ -381,6 +381,38 @@ static void probe_c3_errata(const struct
 }
 
 /*
+ * APL30: One use of the MONITOR/MWAIT instruction pair is to allow a logical
+ * processor to wait in a sleep state until a store to the armed address range
+ * occurs. Due to this erratum, stores to the armed address range may not
+ * trigger MWAIT to resume execution.
+ *
+ * ICX143: Under complex microarchitectural conditions, a monitor that is armed
+ * with the MWAIT instruction may not be triggered, leading to a processor
+ * hang.
+ *
+ * LNL030: Problem P-cores may not exit power state Core C6 on monitor hit.
+ *
+ * Force the sending of an IPI in those cases.
+ */
+static void __init probe_mwait_errata(void)
+{
+    static const struct x86_cpu_id __initconst models[] = {
+        INTEL_FAM6_MODEL(INTEL_FAM6_ATOM_GOLDMONT), /* APL30  */
+        INTEL_FAM6_MODEL(INTEL_FAM6_ICELAKE_X),     /* ICX143 */
+        INTEL_FAM6_MODEL(INTEL_FAM6_LUNARLAKE_M),   /* LNL030 */
+        { }
+    };
+#undef INTEL_FAM6_MODEL
+
+    if ( boot_cpu_has(X86_FEATURE_MONITOR) && x86_match_cpu(models) )
+    {
+        printk(XENLOG_WARNING
+               "Forcing IPI MWAIT wakeup due to CPU erratum\n");
+        force_mwait_ipi_wakeup = true;
+    }
+}
+
+/*
  * P4 Xeon errata 037 workaround.
  * Hardware prefetcher may cause stale data to be loaded into the cache.
  *
@@ -406,6 +438,8 @@ static void Intel_errata_workarounds(str
 		__set_bit(X86_FEATURE_CLFLUSH_MONITOR, c->x86_capability);
 
 	probe_c3_errata(c);
+	if (system_state < SYS_STATE_smp_boot)
+		probe_mwait_errata();
 }
 
 
--- a/xen/arch/x86/include/asm/mwait.h
+++ b/xen/arch/x86/include/asm/mwait.h
@@ -13,6 +13,9 @@
 
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
 
+/* Force sending of a wakeup IPI regardless of mwait usage. */
+extern bool force_mwait_ipi_wakeup;
+
 void mwait_idle_with_hints(unsigned int eax, unsigned int ecx);
 #ifdef CONFIG_INTEL
 bool mwait_pc10_supported(void);