[PATCH][Rebased] intel_idle: Add a new flag to initialize the AMX state

["Chang S. Bae" <chang.seok.bae@xxxxxxxxx>]

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Tested-by: Zhang Rui <rui.zhang@xxxxxxxxx>
Suggested-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Chang S. Bae <chang.seok.bae@xxxxxxxxx>
Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Link: https://lkml.kernel.org/r/20220608164748.11864-3-chang.seok.bae@xxxxxxxxx
[changb: Rebase to the upstream with peterz's help]
Signed-off-by: Chang S. Bae <chang.seok.bae@xxxxxxxxx>
---
The patch merged in the tip's x86/fpu branch [1] has conflict with the
upstream -- commit 32d4fd5751ea ("cpuidle,intel_idle: Fix
CPUIDLE_FLAG_IRQ_ENABLE") as of v5.19-rc2.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/log/?h=x86/fpu
---
 drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 424ef470223d..8a19ba1c2c1b 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -54,6 +54,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -105,6 +106,11 @@ static unsigned int mwait_substates __initdata;
  */
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
+/*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(16)
+
 /*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
@@ -159,6 +165,13 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 	return ret;
 }
 
+static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
+{
+	fpu_idle_fpregs();
+	return __intel_idle(dev, drv, index);
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -174,8 +187,12 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -910,7 +927,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -1819,6 +1837,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
 			drv->states[drv->state_count].enter = intel_idle_irq;
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
+			drv->states[drv->state_count].enter = intel_idle_xstate;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&
-- 
2.17.1