x86/umwait: Initialize umwait control values

umwait or tpause allows the processor to enter a light-weight
power/performance optimized state (C0.1 state) or an improved
power/performance optimized state (C0.2 state) for a period specified by
the instruction or until the system time limit or until a store to the
monitored address range in umwait.

IA32_UMWAIT_CONTROL MSR register allows the OS to enable/disable C0.2 on
the processor and to set the maximum time the processor can reside in C0.1
or C0.2.

By default C0.2 is enabled so the user wait instructions can enter the
C0.2 state to save more power with slower wakeup time.

Andy Lutomirski proposed to set the maximum umwait time to 100000 cycles by
default. A quote from Andy:

  "What I want to avoid is the case where it works dramatically differently
   on NO_HZ_FULL systems as compared to everything else. Also, UMWAIT may
   behave a bit differently if the max timeout is hit, and I'd like that
   path to get exercised widely by making it happen even on default
   configs."

A sysfs interface to adjust the time and the C0.2 enablement is provided in
a follow up change.

[ tglx: Renamed MSR_IA32_UMWAIT_CONTROL_MAX_TIME to
  	MSR_IA32_UMWAIT_CONTROL_TIME_MASK because the constant is used as
  	mask throughout the code.
	Massaged comments and changelog ]

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Cc: "Borislav Petkov" <bp@alien8.de>
Cc: "H Peter Anvin" <hpa@zytor.com>
Cc: "Peter Zijlstra" <peterz@infradead.org>
Cc: "Tony Luck" <tony.luck@intel.com>
Cc: "Ravi V Shankar" <ravi.v.shankar@intel.com>
Link: https://lkml.kernel.org/r/1560994438-235698-3-git-send-email-fenghua.yu@intel.com

2 files changed, 63 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a7d9a4cb3ab6..4b4eb06e117c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,6 +24,7 @@ obj-y			+= match.o
 obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
 obj-y			+= cpuid-deps.o
+obj-y			+= umwait.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
new file mode 100644
index 000000000000..0a113c731df3
--- /dev/null
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE	0
+
+#define UMWAIT_CTRL_VAL(maxtime, c02_disable)				\
+	(((maxtime) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) |		\
+	((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/* Set IA32_UMWAIT_CONTROL MSR on this CPU to the current global setting. */
+static int umwait_cpu_online(unsigned int cpu)
+{
+	wrmsr(MSR_IA32_UMWAIT_CONTROL, umwait_control_cached, 0);
+	return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+	wrmsr(MSR_IA32_UMWAIT_CONTROL, umwait_control_cached, 0);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+	.resume	= umwait_syscore_resume,
+};
+
+static int __init umwait_init(void)
+{
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+		return -ENODEV;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
+				umwait_cpu_online, NULL);
+	if (ret < 0)
+		return ret;
+
+	register_syscore_ops(&umwait_syscore_ops);
+
+	return 0;
+}
+device_initcall(umwait_init);