intel_idle: Fix the 'preferred_cstates' module parameter

Problem description.

When user boots kernel up with the 'intel_idle.preferred_cstates=4' option,
we enable C1E and disable C1 states on Sapphire Rapids Xeon (SPR). In order
for C1E to work on SPR, we have to enable the C1E promotion bit on all
CPUs.  However, we enable it only on one CPU.

Fix description.

The 'intel_idle' driver already has the infrastructure for disabling C1E
promotion on every CPU. This patch uses the same infrastructure for
enabling C1E promotion on every CPU. It changes the boolean
'disable_promotion_to_c1e' variable to a tri-state 'c1e_promotion'
variable.

Tested on a 2-socket SPR system. I verified the following combinations:

 * C1E promotion enabled and disabled in BIOS.
 * Booted with and without the 'intel_idle.preferred_cstates=4' kernel
   argument.

In all 4 cases C1E promotion was correctly set on all CPUs.

Also tested on an old Broadwell system, just to make sure it does not cause
a regression. C1E promotion was correctly disabled on that system, both C1
and C1E were exposed (as expected).

Fixes: da0e58c038e6 ("intel_idle: add 'preferred_cstates' module argument")
Reported-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
[ rjw: Minor changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b7640cf..cf5ed4c 100644 (file)
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -69,7 +69,12 @@ static unsigned int preferred_states_mask;
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
 static unsigned long auto_demotion_disable_flags;
-static bool disable_promotion_to_c1e;
+
+static enum {
+       C1E_PROMOTION_PRESERVE,
+       C1E_PROMOTION_ENABLE,
+       C1E_PROMOTION_DISABLE
+} c1e_promotion = C1E_PROMOTION_PRESERVE;
 
 struct idle_cpu {
        struct cpuidle_state *state_table;
@@ -1398,8 +1403,6 @@ static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { }
 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.
  *
@@ -1587,8 +1590,7 @@ static void __init spr_idle_state_table_update(void)
                spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE;
 
                /* Enable C1E using the "C1E promotion" bit. */
-               c1e_promotion_enable();
-               disable_promotion_to_c1e = false;
+               c1e_promotion = C1E_PROMOTION_ENABLE;
        }
 
        /*
@@ -1754,7 +1756,9 @@ static int intel_idle_cpu_init(unsigned int cpu)
        if (auto_demotion_disable_flags)
                auto_demotion_disable();
 
-       if (disable_promotion_to_c1e)
+       if (c1e_promotion == C1E_PROMOTION_ENABLE)
+               c1e_promotion_enable();
+       else if (c1e_promotion == C1E_PROMOTION_DISABLE)
                c1e_promotion_disable();
 
        return 0;
@@ -1833,7 +1837,8 @@ static int __init intel_idle_init(void)
        if (icpu) {
                cpuidle_state_table = icpu->state_table;
                auto_demotion_disable_flags = icpu->auto_demotion_disable_flags;
-               disable_promotion_to_c1e = icpu->disable_promotion_to_c1e;
+               if (icpu->disable_promotion_to_c1e)
+                       c1e_promotion = C1E_PROMOTION_DISABLE;
                if (icpu->use_acpi || force_use_acpi)
                        intel_idle_acpi_cst_extract();
        } else if (!intel_idle_acpi_cst_extract()) {