[PATCH 6/7] intel_idle: Add support for using intel_idle in a VM guest using just hlt

[arjan@linux.intel.com]

From: Arjan van de Ven <arjan.van.de.ven@intel.com>

In a typical VM guest, the mwait instruction is not available, leaving only the
'hlt' instruction (which causes a VMEXIT to the host).

So currently, intel_idle will detect the lack of mwait, and fail
to initialize (after which another idle method would step in which will
just use hlt always).

By providing capability to do this with the intel_idle driver, we can
do better than this fallback. While this current change only gets us parity
to the existing behavior, later patches in this series will add new capabilities.

In order to do this, a simplified version of the initialization function
for VM guests is created, and this will be called if the CPU is recognized,
but mwait is not supported, and we're in a VM guest.

One thing to note is that the latency (and break even) of this C1 state
is higher than the typical bare metal C1 state. Because hlt causes a vmexit,
and the cost of vmexit + hypervisor overhead + vmenter is typically in the
order of upto 5 microseconds... even if the hypervisor does not actually
goes into a hardware power saving state.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 drivers/idle/intel_idle.c | 54 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 55c3e6ece3dd..c4929d8a35a4 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1280,6 +1280,18 @@ static struct cpuidle_state snr_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state vmguest_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "HLT",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_IRQ_ENABLE,
+		.exit_latency = 5,
+		.target_residency = 10,
+		.enter = &intel_idle_hlt_irq, },
+	{
+		.enter = NULL }
+};
+
 static const struct idle_cpu idle_cpu_nehalem __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
@@ -2105,6 +2117,46 @@ static void __init intel_idle_cpuidle_devices_uninit(void)
 		cpuidle_unregister_device(per_cpu_ptr(intel_idle_cpuidle_devices, i));
 }
 
+static int __init intel_idle_vminit(const struct x86_cpu_id *id)
+{
+	int retval;
+
+	cpuidle_state_table = vmguest_cstates;
+	skip_mwait_check = true; /* hypervisor hides mwait from us normally */
+
+	icpu = (const struct idle_cpu *)id->driver_data;
+
+	pr_debug("v" INTEL_IDLE_VERSION " model 0x%X\n",
+		 boot_cpu_data.x86_model);
+
+	intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+	if (!intel_idle_cpuidle_devices)
+		return -ENOMEM;
+
+	intel_idle_cpuidle_driver_init(&intel_idle_driver);
+
+	retval = cpuidle_register_driver(&intel_idle_driver);
+	if (retval) {
+		struct cpuidle_driver *drv = cpuidle_get_driver();
+		printk(KERN_DEBUG pr_fmt("intel_idle yielding to %s\n"),
+		       drv ? drv->name : "none");
+		goto init_driver_fail;
+	}
+
+	retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online",
+				   intel_idle_cpu_online, NULL);
+	if (retval < 0)
+		goto hp_setup_fail;
+
+	return 0;
+hp_setup_fail:
+	intel_idle_cpuidle_devices_uninit();
+	cpuidle_unregister_driver(&intel_idle_driver);
+init_driver_fail:
+	free_percpu(intel_idle_cpuidle_devices);
+	return retval;
+}
+
 static int __init intel_idle_init(void)
 {
 	const struct x86_cpu_id *id;
@@ -2123,6 +2175,8 @@ static int __init intel_idle_init(void)
 	id = x86_match_cpu(intel_idle_ids);
 	if (id) {
 		if (!boot_cpu_has(X86_FEATURE_MWAIT)) {
+			if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+				return intel_idle_vminit(id);
 			pr_debug("Please enable MWAIT in BIOS SETUP\n");
 			return -ENODEV;
 		}
-- 
2.40.1