Commit 42efa5e3 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'x86_cpu_for_v6.0_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull x86 cpu updates from Borislav Petkov:

 - Remove the vendor check when selecting MWAIT as the default idle
   state

 - Respect idle=nomwait when supplied on the kernel cmdline

 - Two small cleanups

* tag 'x86_cpu_for_v6.0_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Use MSR_IA32_MISC_ENABLE constants
  x86: Fix comment for X86_FEATURE_ZEN
  x86: Remove vendor checks from prefer_mwait_c1_over_halt
  x86: Handle idle=nomwait cmdline properly for x86_idle
parents 650ea1f6 3f2adf00

Documentation/admin-guide/pm/cpuidle.rst

+9 −6
Original line number Diff line number Diff line
@@ -612,8 +612,8 @@ the ``menu`` governor to be used on the systems that use the ``ladder`` governor 
by default this way, for example.



The other kernel command line parameters controlling CPU idle time management

described below are only relevant for the *x86* architecture and some of

them affect Intel processors only.

described below are only relevant for the *x86* architecture and references

to ``intel_idle`` affect Intel processors only.



The *x86* architecture support code recognizes three kernel command line

options related to CPU idle time management: ``idle=poll``, ``idle=halt``,
@@ -635,10 +635,13 @@ idle, so it very well may hurt single-thread computations performance as well as 
energy-efficiency.  Thus using it for performance reasons may not be a good idea

at all.]



The ``idle=nomwait`` option disables the ``intel_idle`` driver and causes

``acpi_idle`` to be used (as long as all of the information needed by it is

there in the system's ACPI tables), but it is not allowed to use the

``MWAIT`` instruction of the CPUs to ask the hardware to enter idle states.

The ``idle=nomwait`` option prevents the use of ``MWAIT`` instruction of

the CPU to enter idle states. When this option is used, the ``acpi_idle``

driver will use the ``HLT`` instruction instead of ``MWAIT``. On systems

running Intel processors, this option disables the ``intel_idle`` driver

and forces the use of the ``acpi_idle`` driver instead. Note that in either

case, ``acpi_idle`` driver will function only if all the information needed

by it is in the system's ACPI tables.



In addition to the architecture-level kernel command line options affecting CPU

idle time management, there are parameters affecting individual ``CPUIdle``

arch/x86/include/asm/cpufeatures.h

+1 −1
Original line number Diff line number Diff line
@@ -219,7 +219,7 @@ 
#define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */

#define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */

#define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */

#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */

#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */

#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */

#define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */

#define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */

arch/x86/include/asm/mwait.h

+1 −0
Original line number Diff line number Diff line
@@ -13,6 +13,7 @@ 
#define MWAIT_SUBSTATE_SIZE		4

#define MWAIT_HINT2CSTATE(hint)		(((hint) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK)

#define MWAIT_HINT2SUBSTATE(hint)	((hint) & MWAIT_CSTATE_MASK)

#define MWAIT_C1_SUBSTATE_MASK  0xf0



#define CPUID_MWAIT_LEAF		5

#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1

arch/x86/kernel/cpu/intel.c

+2 −2
Original line number Diff line number Diff line
@@ -682,9 +682,9 @@ static void init_intel(struct cpuinfo_x86 *c) 
		unsigned int l1, l2;



		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);

		if (!(l1 & (1<<11)))

		if (!(l1 & MSR_IA32_MISC_ENABLE_BTS_UNAVAIL))

			set_cpu_cap(c, X86_FEATURE_BTS);

		if (!(l1 & (1<<12)))

		if (!(l1 & MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL))

			set_cpu_cap(c, X86_FEATURE_PEBS);

	}

arch/x86/kernel/process.c

+31 −13
Original line number Diff line number Diff line
@@ -810,24 +810,43 @@ static void amd_e400_idle(void) 
}



/*

 * Intel Core2 and older machines prefer MWAIT over HALT for C1.

 * We can't rely on cpuidle installing MWAIT, because it will not load

 * on systems that support only C1 -- so the boot default must be MWAIT.

 * Prefer MWAIT over HALT if MWAIT is supported, MWAIT_CPUID leaf

 * exists and whenever MONITOR/MWAIT extensions are present there is at

 * least one C1 substate.

 *

 * Some AMD machines are the opposite, they depend on using HALT.

 *

 * So for default C1, which is used during boot until cpuidle loads,

 * use MWAIT-C1 on Intel HW that has it, else use HALT.

 * Do not prefer MWAIT if MONITOR instruction has a bug or idle=nomwait

 * is passed to kernel commandline parameter.

 */

static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)

{

	if (c->x86_vendor != X86_VENDOR_INTEL)

	u32 eax, ebx, ecx, edx;



	/* User has disallowed the use of MWAIT. Fallback to HALT */

	if (boot_option_idle_override == IDLE_NOMWAIT)

		return 0;



	if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))

	/* MWAIT is not supported on this platform. Fallback to HALT */

	if (!cpu_has(c, X86_FEATURE_MWAIT))

		return 0;



	/* Monitor has a bug. Fallback to HALT */

	if (boot_cpu_has_bug(X86_BUG_MONITOR))

		return 0;



	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);



	/*

	 * If MWAIT extensions are not available, it is safe to use MWAIT

	 * with EAX=0, ECX=0.

	 */

	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED))

		return 1;



	/*

	 * If MWAIT extensions are available, there should be at least one

	 * MWAIT C1 substate present.

	 */

	return (edx & MWAIT_C1_SUBSTATE_MASK);

}



/*
@@ -932,9 +951,8 @@ static int __init idle_setup(char *str) 
	} else if (!strcmp(str, "nomwait")) {

		/*

		 * If the boot option of "idle=nomwait" is added,

		 * it means that mwait will be disabled for CPU C2/C3

		 * states. In such case it won't touch the variable

		 * of boot_option_idle_override.

		 * it means that mwait will be disabled for CPU C1/C2/C3

		 * states.

		 */

		boot_option_idle_override = IDLE_NOMWAIT;

	} else