diff mbox series

[SRU,focal:linux-gcp,15/17] intel_idle: add SPR support

Message ID 20240911042726.959018-16-marcelo.cerri@canonical.com
State New
Headers show
Series lp:#2080324 - linux-gcp: Improve idle support | expand

Commit Message

Marcelo Henrique Cerri Sept. 11, 2024, 4:27 a.m. UTC 
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

BugLink: https://bugs.launchpad.net/bugs/2080324

Add Sapphire Rapids Xeon support.

Up until very recently, the C1 and C1E C-states were independent, but this
has changed in some new chips, including Sapphire Rapids Xeon (SPR). In these
chips the C1 and C1E states cannot be enabled at the same time. The "C1E
promotion" bit in 'MSR_IA32_POWER_CTL' also has its semantics changed a bit.

Here are the C1, C1E, and "C1E promotion" bit rules on Xeons before SPR.

1. If C1E promotion bit is disabled.
   a. C1  requests end up with C1  C-state.
   b. C1E requests end up with C1E C-state.
2. If C1E promotion bit is enabled.
   a. C1  requests end up with C1E C-state.
   b. C1E requests end up with C1E C-state.

Here are the C1, C1E, and "C1E promotion" bit rules on Sapphire Rapids Xeon.
1. If C1E promotion bit is disabled.
   a. C1  requests end up with C1 C-state.
   b. C1E requests end up with C1 C-state.
2. If C1E promotion bit is enabled.
   a. C1  requests end up with C1E C-state.
   b. C1E requests end up with C1E C-state.

Before SPR Xeon, the 'intel_idle' driver was disabling C1E promotion and was
exposing C1 and C1E as independent C-states. But on SPR, C1 and C1E cannot be
enabled at the same time.

This patch adds both C1 and C1E states. However, C1E is marked as with the
"CPUIDLE_FLAG_UNUSABLE" flag, which means that in won't be registered by
default. The C1E promotion bit will be cleared, which means that by default
only C1 and C6 will be registered on SPR.

The next patch will add an option for enabling C1E and disabling C1 on SPR.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
(back ported from commit 9edf3c0ffef0ec1bed8300315852b5c6a0997130)
[marcelo.cerri: Fix context in several places and replaced
 X86_MATCH_INTEL_FAM6_MODEL() with INTEL_CPU_FAM6()]
Signed-off-by: Marcelo Henrique Cerri <marcelo.cerri@canonical.com>
---
 drivers/idle/intel_idle.c | 48 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
diff mbox series

Patch

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 4abbae526a3f..8d6aa90acf35 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -708,6 +708,46 @@  static struct cpuidle_state skx_cstates[] = {
 		.enter = NULL }
 };
 
+/*
+ * On Sapphire Rapids Xeon C1 has to be disabled if C1E is enabled, and vice
+ * versa. On SPR C1E is enabled only if "C1E promotion" bit is set in
+ * MSR_IA32_POWER_CTL. But in this case there effectively no C1, because C1
+ * requests are promoted to C1E. If the "C1E promotion" bit is cleared, then
+ * both C1 and C1E requests end up with C1, so there is effectively no C1E.
+ *
+ * By default we enable C1 and disable C1E by marking it with
+ * 'CPUIDLE_FLAG_UNUSABLE'.
+ */
+static struct cpuidle_state spr_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE | \
+					   CPUIDLE_FLAG_UNUSABLE,
+		.exit_latency = 2,
+		.target_residency = 4,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 290,
+		.target_residency = 800,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state atom_cstates[] = {
 	{
 		.name = "C1E",
@@ -744,6 +784,7 @@  static struct cpuidle_state atom_cstates[] = {
 	{
 		.enter = NULL }
 };
+
 static struct cpuidle_state tangier_cstates[] = {
 	{
 		.name = "C1",
@@ -1089,6 +1130,12 @@  static const struct idle_cpu idle_cpu_avn = {
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_spr __initconst = {
+	.state_table = spr_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
 static const struct idle_cpu idle_cpu_knl = {
 	.state_table = knl_cstates,
 };
@@ -1135,6 +1182,7 @@  static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	INTEL_CPU_FAM6(KABYLAKE_L,		idle_cpu_skl),
 	INTEL_CPU_FAM6(KABYLAKE,		idle_cpu_skl),
 	INTEL_CPU_FAM6(SKYLAKE_X,		idle_cpu_skx),
+	INTEL_CPU_FAM6(SAPPHIRERAPIDS_X,	idle_cpu_spr),
 	INTEL_CPU_FAM6(XEON_PHI_KNL,		idle_cpu_knl),
 	INTEL_CPU_FAM6(XEON_PHI_KNM,		idle_cpu_knl),
 	INTEL_CPU_FAM6(ATOM_GOLDMONT,		idle_cpu_bxt),