[PATCH 4.4 203/210] intel_idle: prevent SKL-H boot failure when C8+C9+C10 enabled

[Greg Kroah-Hartman]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Len Brown <len.brown@xxxxxxxxx>

commit d70e28f57e14a481977436695b0c9ba165472431 upstream.

Some SKL-H configurations require "intel_idle.max_cstate=7" to boot.
While that is an effective workaround, it disables C10.

This patch detects the problematic configuration,
and disables C8 and C9, keeping C10 enabled.

Note that enabling SGX in BIOS SETUP can also prevent this issue,
if the system BIOS provides that option.

https://bugzilla.kernel.org/show_bug.cgi?id=109081
"Freezes with Intel i7 6700HQ (Skylake), unless intel_idle.max_cstate=7"

Signed-off-by: Len Brown <len.brown@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 drivers/idle/intel_idle.c |  106 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 85 insertions(+), 21 deletions(-)

--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -65,7 +65,7 @@
 #include <asm/mwait.h>
 #include <asm/msr.h>
 
-#define INTEL_IDLE_VERSION "0.4"
+#define INTEL_IDLE_VERSION "0.4.1"
 #define PREFIX "intel_idle: "
 
 static struct cpuidle_driver intel_idle_driver = {
@@ -994,36 +994,92 @@ static void intel_idle_cpuidle_devices_u
 }
 
 /*
- * intel_idle_state_table_update()
- *
- * Update the default state_table for this CPU-id
+ * ivt_idle_state_table_update(void)
  *
- * Currently used to access tuned IVT multi-socket targets
+ * Tune IVT multi-socket targets
  * Assumption: num_sockets == (max_package_num + 1)
  */
-void intel_idle_state_table_update(void)
+static void ivt_idle_state_table_update(void)
 {
 	/* IVT uses a different table for 1-2, 3-4, and > 4 sockets */
-	if (boot_cpu_data.x86_model == 0x3e) { /* IVT */
-		int cpu, package_num, num_sockets = 1;
+	int cpu, package_num, num_sockets = 1;
 
-		for_each_online_cpu(cpu) {
-			package_num = topology_physical_package_id(cpu);
-			if (package_num + 1 > num_sockets) {
-				num_sockets = package_num + 1;
-
-				if (num_sockets > 4) {
-					cpuidle_state_table = ivt_cstates_8s;
-					return;
-				}
+	for_each_online_cpu(cpu) {
+		package_num = topology_physical_package_id(cpu);
+		if (package_num + 1 > num_sockets) {
+			num_sockets = package_num + 1;
+
+			if (num_sockets > 4) {
+				cpuidle_state_table = ivt_cstates_8s;
+				return;
 			}
 		}
+	}
+
+	if (num_sockets > 2)
+		cpuidle_state_table = ivt_cstates_4s;
+
+	/* else, 1 and 2 socket systems use default ivt_cstates */
+}
+/*
+ * sklh_idle_state_table_update(void)
+ *
+ * On SKL-H (model 0x5e) disable C8 and C9 if:
+ * C10 is enabled and SGX disabled
+ */
+static void sklh_idle_state_table_update(void)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+
+
+	/* if PC10 disabled via cmdline intel_idle.max_cstate=7 or shallower */
+	if (max_cstate <= 7)
+		return;
+
+	/* if PC10 not present in CPUID.MWAIT.EDX */
+	if ((mwait_substates & (0xF << 28)) == 0)
+		return;
+
+	rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr);
+
+	/* PC10 is not enabled in PKG C-state limit */
+	if ((msr & 0xF) != 8)
+		return;
+
+	ecx = 0;
+	cpuid(7, &eax, &ebx, &ecx, &edx);
+
+	/* if SGX is present */
+	if (ebx & (1 << 2)) {
+
+		rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
 
-		if (num_sockets > 2)
-			cpuidle_state_table = ivt_cstates_4s;
-		/* else, 1 and 2 socket systems use default ivt_cstates */
+		/* if SGX is enabled */
+		if (msr & (1 << 18))
+			return;
+	}
+
+	skl_cstates[5].disabled = 1;	/* C8-SKL */
+	skl_cstates[6].disabled = 1;	/* C9-SKL */
+}
+/*
+ * intel_idle_state_table_update()
+ *
+ * Update the default state_table for this CPU-id
+ */
+
+static void intel_idle_state_table_update(void)
+{
+	switch (boot_cpu_data.x86_model) {
+
+	case 0x3e: /* IVT */
+		ivt_idle_state_table_update();
+		break;
+	case 0x5e: /* SKL-H */
+		sklh_idle_state_table_update();
+		break;
 	}
-	return;
 }
 
 /*
@@ -1063,6 +1119,14 @@ static int __init intel_idle_cpuidle_dri
 		if (num_substates == 0)
 			continue;
 
+		/* if state marked as disabled, skip it */
+		if (cpuidle_state_table[cstate].disabled != 0) {
+			pr_debug(PREFIX "state %s is disabled",
+				cpuidle_state_table[cstate].name);
+			continue;
+		}
+
+
 		if (((mwait_cstate + 1) > 2) &&
 			!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 			mark_tsc_unstable("TSC halts in idle"