intel_idle: disable NHM/WSM HW C-state auto-demotion

commit 14796fca2bd22acc73dd0887248d003b0f441d08 upstream.

Hardware C-state auto-demotion is a mechanism where the HW overrides
the OS C-state request, instead demoting to a shallower state,
which is less expensive, but saves less power.

Modern Linux should generally get exactly the states it requests.
In particular, when a CPU is taken off-line, it must not be demoted, else
it can prevent the entire package from reaching deep C-states.

https://bugzilla.kernel.org/show_bug.cgi?id=25252

Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6b89f5e860214266d7270160f739e9a9be290802..05c302c697c3188aae71c3f71e0b9395ff44d273 100644 (file)
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -36,6 +36,10 @@
 #define MSR_IA32_PERFCTR1              0x000000c2
 #define MSR_FSB_FREQ                   0x000000cd
 
+#define MSR_NHM_SNB_PKG_CST_CFG_CTL    0x000000e2
+#define NHM_C3_AUTO_DEMOTE             (1UL << 25)
+#define NHM_C1_AUTO_DEMOTE             (1UL << 26)
+
 #define MSR_MTRRcap                    0x000000fe
 #define MSR_IA32_BBL_CR_CTL            0x00000119
 

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index a1e141ea8f52907eac9e85ea44de81cded2ea5e3..cba861716af93c46697a23024374442f271e700e 100644 (file)
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -62,6 +62,7 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <asm/mwait.h>
+#include <asm/msr.h>
 
 #define INTEL_IDLE_VERSION "0.4"
 #define PREFIX "intel_idle: "
@@ -84,6 +85,12 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state);
 
 static struct cpuidle_state *cpuidle_state_table;
 
+/*
+ * Hardware C-state auto-demotion may not always be optimal.
+ * Indicate which enable bits to clear here.
+ */
+static unsigned long long auto_demotion_disable_flags;
+
 /*
  * States are indexed by the cstate number,
  * which is also the index into the MWAIT hint array.
@@ -276,6 +283,15 @@ static struct notifier_block setup_broadcast_notifier = {
        .notifier_call = setup_broadcast_cpuhp_notify,
 };
 
+static void auto_demotion_disable(void *dummy)
+{
+       unsigned long long msr_bits;
+
+       rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
+       msr_bits &= ~auto_demotion_disable_flags;
+       wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
+}
+
 /*
  * intel_idle_probe()
  */
@@ -319,6 +335,8 @@ static int intel_idle_probe(void)
        case 0x25:      /* Westmere */
        case 0x2C:      /* Westmere */
                cpuidle_state_table = nehalem_cstates;
+               auto_demotion_disable_flags =
+                       (NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE);
                break;
 
        case 0x1C:      /* 28 - Atom Processor */
@@ -431,6 +449,8 @@ static int intel_idle_cpuidle_devices_init(void)
                        return -EIO;
                }
        }
+       if (auto_demotion_disable_flags)
+               smp_call_function(auto_demotion_disable, NULL, 1);
 
        return 0;
 }