From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Wed, 2 Mar 2022 10:15:59 +0200
Subject: intel_idle: add 'preferred_cstates' module argument
Patch-mainline: v5.18-rc1
Git-commit: da0e58c038e60e7e65d30813ebdfe91687aa8a24
References: bsc#1198602

On Sapphire Rapids Xeon (SPR) the C1 and C1E states are basically mutually
exclusive - only one of them can be enabled. By default, 'intel_idle' driver
enables C1 and disables C1E. However, some users prefer to use C1E instead of
C1, because it saves more energy.

This patch adds a new module parameter ('preferred_cstates') for enabling C1E
and disabling C1. Here is the idea behind it.

1. This option has effect only for "mutually exclusive" C-states like C1 and
   C1E on SPR.
2. It does not have any effect on independent C-states, which do not require
   other C-states to be disabled (most states on most platforms as of today).
3. For mutually exclusive C-states, the 'intel_idle' driver always has a
   reasonable default, such as enabling C1 on SPR by default. On other
   platforms, the default may be different.
4. Users can override the default using the 'preferred_cstates' parameter.
5. The parameter accepts the preferred C-states bit-mask, similarly to the
   existing 'states_off' parameter.
6. This parameter is not limited to C1/C1E, and leaves room for supporting
   other mutually exclusive C-states, if they come in the future.

Today 'intel_idle' can only be compiled-in, which means that on SPR, in order
to disable C1 and enable C1E, users should boot with the following kernel
argument: intel_idle.preferred_cstates=4

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Giovanni Gherdovich <ggherdovich@suse.cz>
---
 drivers/idle/intel_idle.c |   46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -64,6 +64,7 @@ static struct cpuidle_driver intel_idle_
 /* intel_idle.max_cstate=0 disables driver */
 static int max_cstate = CPUIDLE_STATE_MAX - 1;
 static unsigned int disabled_states_mask;
+static unsigned int preferred_states_mask;
 
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
@@ -1400,6 +1401,8 @@ static inline void intel_idle_init_cstat
 static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; }
 #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */
 
+static void c1e_promotion_enable(void);
+
 /**
  * ivt_idle_state_table_update - Tune the idle states table for Ivy Town.
  *
@@ -1570,6 +1573,26 @@ static void __init skx_idle_state_table_
 	}
 }
 
+/**
+ * spr_idle_state_table_update - Adjust Sapphire Rapids idle states table.
+ */
+static void __init spr_idle_state_table_update(void)
+{
+	/* Check if user prefers C1E over C1. */
+	if (preferred_states_mask & BIT(2)) {
+		if (preferred_states_mask & BIT(1))
+			/* Both can't be enabled, stick to the defaults. */
+			return;
+
+		spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE;
+		spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE;
+
+		/* Enable C1E using the "C1E promotion" bit. */
+		c1e_promotion_enable();
+		disable_promotion_to_c1e = false;
+	}
+}
+
 static bool __init intel_idle_verify_cstate(unsigned int mwait_hint)
 {
 	unsigned int mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint) + 1;
@@ -1604,6 +1627,9 @@ static void __init intel_idle_init_cstat
 	case INTEL_FAM6_SKYLAKE_X:
 		skx_idle_state_table_update();
 		break;
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+		spr_idle_state_table_update();
+		break;
 	}
 
 	for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
@@ -1676,6 +1702,15 @@ static void auto_demotion_disable(void)
 	wrmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits);
 }
 
+static void c1e_promotion_enable(void)
+{
+	unsigned long long msr_bits;
+
+	rdmsrl(MSR_IA32_POWER_CTL, msr_bits);
+	msr_bits |= 0x2;
+	wrmsrl(MSR_IA32_POWER_CTL, msr_bits);
+}
+
 static void c1e_promotion_disable(void)
 {
 	unsigned long long msr_bits;
@@ -1845,3 +1880,14 @@ module_param(max_cstate, int, 0444);
  */
 module_param_named(states_off, disabled_states_mask, uint, 0444);
 MODULE_PARM_DESC(states_off, "Mask of disabled idle states");
+/*
+ * Some platforms come with mutually exclusive C-states, so that if one is
+ * enabled, the other C-states must not be used. Example: C1 and C1E on
+ * Sapphire Rapids platform. This parameter allows for selecting the
+ * preferred C-states among the groups of mutually exclusive C-states - the
+ * selected C-states will be registered, the other C-states from the mutually
+ * exclusive group won't be registered. If the platform has no mutually
+ * exclusive C-states, this parameter has no effect.
+ */
+module_param_named(preferred_cstates, preferred_states_mask, uint, 0444);
+MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states");