Commit 3dee9fb2 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull RAS updates from Ingo Molnar:
 "The main changes in this cycle were:

   - add the 'Corrected Errors Collector' kernel feature which collect
     and monitor correctable errors statistics and will preemptively
     (soft-)offline physical pages that have a suspiciously high error
     count.

   - handle MCE errors during kexec() more gracefully

   - factor out and deprecate the /dev/mcelog driver

   - ... plus misc fixes and cleanpus"

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Check MCi_STATUS[MISCV] for usable addr on Intel only
  ACPI/APEI: Use setup_deferrable_timer()
  x86/mce: Update notifier priority check
  x86/mce: Enable PPIN for Knights Landing/Mill
  x86/mce: Do not register notifiers with invalid prio
  x86/mce: Factor out and deprecate the /dev/mcelog driver
  RAS: Add a Corrected Errors Collector
  x86/mce: Rename mce_log to mce_log_buffer
  x86/mce: Rename mce_log()'s argument
  x86/mce: Init some CPU features early
  x86/mce: Handle broadcasted MCE gracefully with kexec
parents 7c8c03bf c6a9583f

Documentation/admin-guide/kernel-parameters.txt

+6 −0
Original line number Diff line number Diff line
@@ -3177,6 +3177,12 @@ 
	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes

			See Documentation/blockdev/ramdisk.txt.



	ras=option[,option,...]	[KNL] RAS-specific options



		cec_disable	[X86]

				Disable the Correctable Errors Collector,

				see CONFIG_RAS_CEC help text.



	rcu_nocbs=	[KNL]

			The argument is a cpu list, as described above.

arch/x86/Kconfig

+9 −1
Original line number Diff line number Diff line
@@ -1042,6 +1042,14 @@ config X86_MCE 
	  The action the kernel takes depends on the severity of the problem,

	  ranging from warning messages to halting the machine.



config X86_MCELOG_LEGACY

	bool "Support for deprecated /dev/mcelog character device"

	depends on X86_MCE

	---help---

	  Enable support for /dev/mcelog which is needed by the old mcelog

	  userspace logging daemon. Consider switching to the new generation

	  rasdaemon solution.



config X86_MCE_INTEL

	def_bool y

	prompt "Intel MCE features"
@@ -1071,7 +1079,7 @@ config X86_MCE_THRESHOLD 
	def_bool y



config X86_MCE_INJECT

	depends on X86_MCE && X86_LOCAL_APIC

	depends on X86_MCE && X86_LOCAL_APIC && X86_MCELOG_LEGACY

	tristate "Machine check injector support"

	---help---

	  Provide support for injecting machine checks for testing purposes.

arch/x86/include/asm/mce.h

+7 −5
Original line number Diff line number Diff line
@@ -128,7 +128,7 @@ 
 * debugging tools.  Each entry is only valid when its finished flag

 * is set.

 */

struct mce_log {

struct mce_log_buffer {

	char signature[12]; /* "MACHINECHECK" */

	unsigned len;	    /* = MCE_LOG_LEN */

	unsigned next;
@@ -191,10 +191,12 @@ extern struct mca_config mca_cfg; 
extern struct mca_msr_regs msr_ops;



enum mce_notifier_prios {

	MCE_PRIO_SRAO		= INT_MAX,

	MCE_PRIO_EXTLOG		= INT_MAX - 1,

	MCE_PRIO_NFIT		= INT_MAX - 2,

	MCE_PRIO_EDAC		= INT_MAX - 3,

	MCE_PRIO_FIRST		= INT_MAX,

	MCE_PRIO_SRAO		= INT_MAX - 1,

	MCE_PRIO_EXTLOG		= INT_MAX - 2,

	MCE_PRIO_NFIT		= INT_MAX - 3,

	MCE_PRIO_EDAC		= INT_MAX - 4,

	MCE_PRIO_MCELOG		= 1,

	MCE_PRIO_LOWEST		= 0,

};

arch/x86/include/asm/reboot.h

+1 −0
Original line number Diff line number Diff line
@@ -15,6 +15,7 @@ struct machine_ops { 
};



extern struct machine_ops machine_ops;

extern int crashing_cpu;



void native_machine_crash_shutdown(struct pt_regs *regs);

void native_machine_shutdown(void);

arch/x86/kernel/cpu/mcheck/Makefile

+2 −0
Original line number Diff line number Diff line
@@ -9,3 +9,5 @@ obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o 
obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o



obj-$(CONFIG_ACPI_APEI)		+= mce-apei.o



obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o

CRA Git | Maintained and supported by SUSTech CRA and CCSE