[RFC PATCH v2 2/2] x86/mce: Prevent CPU offline for SMCA CPUs with non-core banks

[Yazen Ghannam]

Logical CPUs in AMD Scalable MCA (SMCA) systems can manage non-core
banks. Each of these banks represents unique and separate hardware
located within the system. Each bank is managed by a single logical CPU;
they are not shared. Furthermore, the "CPU to MCA bank" assignment
cannot be modified at run time.

The MCE subsystem supports run time CPU hotplug. Many vendors have
non-core MCA banks, so MCA settings are not cleared when a CPU is
offlined for these vendors.

Even though the non-core MCA banks remain enabled, MCA errors will not
be handled (reported, cleared, etc.) on SMCA systems when the managing
CPU is offline.

Mark a CPU as not hotpluggable if it manages non-core MCA banks. This
prevents the CPU from being marked offline from sysfs.

Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
---
 arch/x86/include/asm/mce.h     |  2 ++
 arch/x86/kernel/cpu/mce/core.c | 15 +++++++++++++++
 arch/x86/kernel/setup.c        |  2 +-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 3b9970117a0f..bd9ac102ba49 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -213,12 +213,14 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c);
 void mcheck_cpu_clear(struct cpuinfo_x86 *c);
 int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info,
 			       u64 lapic_id);
+bool mce_cpu_is_hotpluggable(unsigned int cpu);
 #else
 static inline int mcheck_init(void) { return 0; }
 static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
 static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
 static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info,
 					     u64 lapic_id) { return -EINVAL; }
+static inline bool mce_cpu_is_hotpluggable(unsigned int cpu) { return true; }
 #endif
 
 void mce_prep_record(struct mce *m);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 33893b5c8b0c..2f4a04092dd0 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2775,6 +2775,21 @@ static int mce_cpu_online(unsigned int cpu)
 	return 0;
 }
 
+bool mce_cpu_is_hotpluggable(unsigned int cpu)
+{
+	if (!mce_flags.smca)
+		return true;
+
+	/*
+	 * SMCA systems use banks 0-6 for core units. Banks 7 and later are
+	 * used for non-core units.
+	 *
+	 * Logical CPUs with 7 or fewer banks can be offlined, since they are not
+	 * managing any non-core units.
+	 */
+	return per_cpu(mce_num_banks, cpu) <= 7;
+}
+
 static int mce_cpu_pre_down(unsigned int cpu)
 {
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d34cad9b7b1..754089334591 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1222,6 +1222,6 @@ __initcall(register_kernel_offset_dumper);
 #ifdef CONFIG_HOTPLUG_CPU
 bool arch_cpu_is_hotpluggable(int cpu)
 {
-	return cpu > 0;
+	return cpu > 0 && mce_cpu_is_hotpluggable(cpu);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
-- 
2.34.1