Move ...mce/therm_throt.c to drivers/thermal/

PATCH Superseded Borislav Petkov 2 participants 4 messages Jan 8, 2021

Subsystems (3)

x86 Thermal x86 MCE infrastructure

lore

Share & tools

lore

Borislav Petkov

author maintainer

2021-01-08 08:55 UTC #0 lore raw

cover Move ...mce/therm_throt.c to drivers/thermal/

From: Borislav Petkov <[email protected]>

Hi,

so this has come up a bunch of times in the past and PeterZ is right
- that thing doesn't have anything to do with the MCE glue so move it where it belongs.

Thx.

Borislav Petkov (2):
x86/mce: Get rid of mcheck_intel_therm_init()
thermal: Move therm_throt there from x86/mce

 arch/x86/Kconfig                              |  4 --
 arch/x86/include/asm/irq.h                    |  4 ++
 arch/x86/include/asm/mce.h                    | 22 -----------
 arch/x86/include/asm/thermal.h                | 21 ++++++++++
 arch/x86/kernel/cpu/intel.c                   |  3 ++
 arch/x86/kernel/cpu/mce/Makefile              |  2 -
 arch/x86/kernel/cpu/mce/core.c                |  1 -
 arch/x86/kernel/cpu/mce/intel.c               |  1 -
 arch/x86/kernel/irq.c                         | 28 +++++++++++++
 drivers/thermal/intel/Kconfig                 |  4 ++
 drivers/thermal/intel/Makefile                |  1 +
 .../thermal/intel}/therm_throt.c              | 39 +++----------------
 drivers/thermal/intel/x86_pkg_temp_thermal.c  |  3 +-
 13 files changed, 69 insertions(+), 64 deletions(-)
 create mode 100644 arch/x86/include/asm/thermal.h
 rename {arch/x86/kernel/cpu/mce => drivers/thermal/intel}/therm_throt.c (96%)

Signature · 1 line

2.29.2

Borislav Petkov

author maintainer

2021-01-08 08:55 UTC #1 lore raw

PATCH 1/2 x86/mce: Get rid of mcheck_intel_therm_init()

From: Borislav Petkov <[email protected]>

Move the APIC_LVTTHMR read which needs to happen on the BSP, to intel_init_thermal(). One less boot dependency.

No functional changes.

Signed-off-by Borislav Petkov <[email protected]>

---
 arch/x86/include/asm/mce.h            |  6 ------
 arch/x86/kernel/cpu/mce/core.c        |  1 -
 arch/x86/kernel/cpu/mce/therm_throt.c | 14 +++-----------
 3 files changed, 3 insertions(+), 18 deletions(-)

arch/x86/include/asm/mce.h +0 -6

index 56cdeaac76a0..def9aa5e1fa4 100644
@@ -304,12 +304,6 @@ extern int (*platform_thermal_package_notify)(__u64 msr_val);
  * callback has rate control */
 extern bool (*platform_thermal_package_rate_control)(void);
 
-#ifdef CONFIG_X86_THERMAL_VECTOR
-extern void mcheck_intel_therm_init(void);
-#else
-static inline void mcheck_intel_therm_init(void) { }
-#endif
-
 /*
  * Used by APEI to report memory error via /dev/mcelog
  */

arch/x86/kernel/cpu/mce/core.c +0 -1

index 13d3f1cbda17..7b1bed514be1 100644
@@ -2177,7 +2177,6 @@ __setup("mce", mcheck_enable);
 
 int __init mcheck_init(void)
 {
-	mcheck_intel_therm_init();
 	mce_register_decode_chain(&early_nb);
 	mce_register_decode_chain(&mce_uc_nb);
 	mce_register_decode_chain(&mce_default_nb);

arch/x86/kernel/cpu/mce/therm_throt.c +3 ~~-11~~

index a7cd2d203ced..5b1aa0f30655 100644
@@ -633,23 +633,15 @@ static int intel_thermal_supported(struct cpuinfo_x86 *c)
 	return 1;
 }
 
-void __init mcheck_intel_therm_init(void)
-{
-	/*
-	 * This function is only called on boot CPU. Save the init thermal
-	 * LVT value on BSP and use that value to restore APs' thermal LVT
-	 * entry BIOS programmed later
-	 */
-	if (intel_thermal_supported(&boot_cpu_data))
-		lvtthmr_init = apic_read(APIC_LVTTHMR);
-}
-
 void intel_init_thermal(struct cpuinfo_x86 *c)
 {
 	unsigned int cpu = smp_processor_id();
 	int tm2 = 0;
 	u32 l, h;
 
+	if ((c == &boot_cpu_data) && intel_thermal_supported(c))
+		lvtthmr_init = apic_read(APIC_LVTTHMR);
+
 	if (!intel_thermal_supported(c))
 		return;

Signature · 1 line

2.29.2

Borislav Petkov

author maintainer

2021-01-08 08:55 UTC #2 lore raw

PATCH 2/2 thermal: Move therm_throt there from x86/mce

In reply to Borislav Petkov

From: Borislav Petkov <[email protected]>

This functionality has nothing to do with MCE, move it to the thermal framework and untangle it from MCE.

Requested-by Peter Zijlstra <[email protected]>

Signed-off-by Borislav Petkov <[email protected]>

---
 arch/x86/Kconfig                              |  4 ---
 arch/x86/include/asm/irq.h                    |  4 +++
 arch/x86/include/asm/mce.h                    | 16 -----------
 arch/x86/include/asm/thermal.h                | 21 ++++++++++++++
 arch/x86/kernel/cpu/intel.c                   |  3 ++
 arch/x86/kernel/cpu/mce/Makefile              |  2 --
 arch/x86/kernel/cpu/mce/intel.c               |  1 -
 arch/x86/kernel/irq.c                         | 28 +++++++++++++++++++
 drivers/thermal/intel/Kconfig                 |  4 +++
 drivers/thermal/intel/Makefile                |  1 +
 .../thermal/intel}/therm_throt.c              | 25 ++---------------
 drivers/thermal/intel/x86_pkg_temp_thermal.c  |  3 +-
 12 files changed, 66 insertions(+), 46 deletions(-)
 create mode 100644 arch/x86/include/asm/thermal.h
 rename {arch/x86/kernel/cpu/mce => drivers/thermal/intel}/therm_throt.c (97%)

arch/x86/Kconfig +0 -4

index 21f851179ff0..9989db3a9bf5 100644
@@ -1158,10 +1158,6 @@ config X86_MCE_INJECT
 	  If you don't know what a machine check is and you don't do kernel
 	  QA it is safe to say n.
 
-config X86_THERMAL_VECTOR
-	def_bool y
-	depends on X86_MCE_INTEL
-
 source "arch/x86/events/Kconfig"
 
 config X86_LEGACY_VM86

arch/x86/include/asm/irq.h +4 -0

index 528c8a71fe7f..ad65fe7dceb1 100644
@@ -53,4 +53,8 @@ void arch_trigger_cpumask_backtrace(const struct cpumask *mask,
 #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
 #endif
 
+#ifdef CONFIG_X86_THERMAL_VECTOR
+void thermal_set_handler(void (*handler)(void));
+#endif
+
 #endif /* _ASM_X86_IRQ_H */

arch/x86/include/asm/mce.h +0 ~~-16~~

index def9aa5e1fa4..ddfb3cad8dff 100644
@@ -288,22 +288,6 @@ extern void (*mce_threshold_vector)(void);
 /* Deferred error interrupt handler */
 extern void (*deferred_error_int_vector)(void);
 
-/*
- * Thermal handler
- */
-
-void intel_init_thermal(struct cpuinfo_x86 *c);
-
-/* Interrupt Handler for core thermal thresholds */
-extern int (*platform_thermal_notify)(__u64 msr_val);
-
-/* Interrupt Handler for package thermal thresholds */
-extern int (*platform_thermal_package_notify)(__u64 msr_val);
-
-/* Callback support of rate control, return true, if
- * callback has rate control */
-extern bool (*platform_thermal_package_rate_control)(void);
-
 /*
  * Used by APEI to report memory error via /dev/mcelog
  */

arch/x86/include/asm/thermal.h new file +21 -0

new file mode 100644
index 000000000000..58b0e0a4af6e
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_THERMAL_H
+#define _ASM_X86_THERMAL_H
+
+/* Interrupt Handler for package thermal thresholds */
+extern int (*platform_thermal_package_notify)(__u64 msr_val);
+
+/* Interrupt Handler for core thermal thresholds */
+extern int (*platform_thermal_notify)(__u64 msr_val);
+
+/* Callback support of rate control, return true, if
+ * callback has rate control */
+extern bool (*platform_thermal_package_rate_control)(void);
+
+#ifdef CONFIG_X86_THERMAL_VECTOR
+void intel_init_thermal(struct cpuinfo_x86 *c);
+#else
+static inline void intel_init_thermal(struct cpuinfo_x86 *c) { }
+#endif
+
+#endif /* _ASM_X86_THERMAL_H */

arch/x86/kernel/cpu/intel.c +3 -0

index 59a1e3ce3f14..71221af87cb1 100644
@@ -24,6 +24,7 @@
 #include <asm/traps.h>
 #include <asm/resctrl.h>
 #include <asm/numa.h>
+#include <asm/thermal.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>

@@ -719,6 +720,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		tsx_disable();
 
 	split_lock_init();
+
+	intel_init_thermal(c);
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/cpu/mce/Makefile +0 -2

index 9f020c994154..015856abdbb1 100644
@@ -9,8 +9,6 @@ obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
 mce-inject-y			:= inject.o
 obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
 
-obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
-
 obj-$(CONFIG_ACPI_APEI)		+= apei.o
 
 obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o

arch/x86/kernel/cpu/mce/intel.c +0 -1

index c2476fe0682e..e309476743b7 100644
@@ -531,7 +531,6 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
 
 void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
-	intel_init_thermal(c);
 	intel_init_cmci();
 	intel_init_lmce();
 	intel_ppin_init(c);

arch/x86/kernel/irq.c +28 -0

index c5dd50369e2f..f23037c79e04 100644
@@ -374,3 +374,31 @@ void fixup_irqs(void)
 	}
 }
 #endif
+
+#ifdef CONFIG_X86_THERMAL_VECTOR
+static void unexpected_thermal_interrupt(void)
+{
+	pr_err("CPU%d: Unexpected LVT thermal interrupt!\n",
+		smp_processor_id());
+}
+
+static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
+
+void thermal_set_handler(void (*handler)(void))
+{
+	if (handler)
+		smp_thermal_vector = handler;
+	else
+		smp_thermal_vector = unexpected_thermal_interrupt;
+}
+EXPORT_SYMBOL_GPL(thermal_set_handler);
+
+DEFINE_IDTENTRY_SYSVEC(sysvec_thermal)
+{
+	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
+	inc_irq_stat(irq_thermal_count);
+	smp_thermal_vector();
+	trace_thermal_apic_exit(THERMAL_APIC_VECTOR);
+	ack_APIC_irq();
+}
+#endif

drivers/thermal/intel/Kconfig +4 -0

index 8025b21f43fa..ce4f59213c7a 100644
@@ -8,6 +8,10 @@ config INTEL_POWERCLAMP
 	  enforce idle time which results in more package C-state residency. The
 	  user interface is exposed via generic thermal framework.
 
+config X86_THERMAL_VECTOR
+	def_bool y
+	depends on X86 && CPU_SUP_INTEL && X86_LOCAL_APIC
+
 config X86_PKG_TEMP_THERMAL
 	tristate "X86 package temperature thermal driver"
 	depends on X86_THERMAL_VECTOR

drivers/thermal/intel/Makefile +1 -0

index 0d9736ced5d4..ff2ad30ef397 100644
@@ -10,3 +10,4 @@ obj-$(CONFIG_INTEL_QUARK_DTS_THERMAL)	+= intel_quark_dts_thermal.o
 obj-$(CONFIG_INT340X_THERMAL)  += int340x_thermal/
 obj-$(CONFIG_INTEL_BXT_PMIC_THERMAL) += intel_bxt_pmic_thermal.o
 obj-$(CONFIG_INTEL_PCH_THERMAL)	+= intel_pch_thermal.o
+obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o

drivers/thermal/intel/therm_throt.c renamed from arch/x86/kernel/cpu/mce/therm_throt.c +3 ~~-22~~

similarity index 97%
rename from arch/x86/kernel/cpu/mce/therm_throt.c
rename to drivers/thermal/intel/therm_throt.c
index 5b1aa0f30655..4f12fcd0e40a 100644
@@ -26,13 +26,11 @@
 #include <linux/cpu.h>
 
 #include <asm/processor.h>
+#include <asm/thermal.h>
 #include <asm/traps.h>
 #include <asm/apic.h>
-#include <asm/mce.h>
+#include <asm/irq.h>
 #include <asm/msr.h>
-#include <asm/trace/irq_vectors.h>
-
-#include "internal.h"
 
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL		(300 * HZ)

@@ -606,23 +604,6 @@ static void intel_thermal_interrupt(void)
 	}
 }
 
-static void unexpected_thermal_interrupt(void)
-{
-	pr_err("CPU%d: Unexpected LVT thermal interrupt!\n",
-		smp_processor_id());
-}
-
-static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
-
-DEFINE_IDTENTRY_SYSVEC(sysvec_thermal)
-{
-	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
-	inc_irq_stat(irq_thermal_count);
-	smp_thermal_vector();
-	trace_thermal_apic_exit(THERMAL_APIC_VECTOR);
-	ack_APIC_irq();
-}
-
 /* Thermal monitoring depends on APIC, ACPI and clock modulation */
 static int intel_thermal_supported(struct cpuinfo_x86 *c)
 {

@@ -718,7 +699,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 				| PACKAGE_THERM_INT_HIGH_ENABLE), h);
 	}
 
-	smp_thermal_vector = intel_thermal_interrupt;
+	thermal_set_handler(intel_thermal_interrupt);
 
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 	wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);

drivers/thermal/intel/x86_pkg_temp_thermal.c +2 -1

index b81c33202f41..090f9176ba62 100644
@@ -17,8 +17,9 @@
 #include <linux/pm.h>
 #include <linux/thermal.h>
 #include <linux/debugfs.h>
+
 #include <asm/cpu_device_id.h>
-#include <asm/mce.h>
+#include <asm/thermal.h>
 
 /*
 * Rate control delay: Idea is to introduce denounce effect

Signature · 1 line

2.29.2

Peter Zijlstra

2021-01-08 09:47 UTC #3 lore raw

Re: [PATCH 2/2] thermal: Move therm_throt there from x86/mce

arch/x86/kernel/irq.c void fixup_irqs(void)

Quoted 12 lines · Borislav Petkov

arch/x86/kernel/irq.c +12 -0

+#ifdef CONFIG_X86_THERMAL_VECTOR
+static void unexpected_thermal_interrupt(void)
+{
+	pr_err("CPU%d: Unexpected LVT thermal interrupt!\n",
+		smp_processor_id());
+}
+
+static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
+
+void thermal_set_handler(void (*handler)(void))
+{
+	if (handler) {

		WARN_ON(smp_thermal_vector != unexpected_thermal_interrupt);

arch/x86/kernel/irq.c void fixup_irqs(void) · line 394

Quoted 5 lines

arch/x86/kernel/irq.c +5 -0

+		smp_thermal_vector = handler;
+	} else
+		smp_thermal_vector = unexpected_thermal_interrupt;
+}
+EXPORT_SYMBOL_GPL(thermal_set_handler);

You really don't want multiple modules to touch that at the same time.

Quoted 9 lines

arch/x86/kernel/irq.c +9 -0

+DEFINE_IDTENTRY_SYSVEC(sysvec_thermal)
+{
+	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
+	inc_irq_stat(irq_thermal_count);
+	smp_thermal_vector();
+	trace_thermal_apic_exit(THERMAL_APIC_VECTOR);
+	ack_APIC_irq();
+}
+#endif