diff options
author | Arjan van de Ven <arjan@linux.intel.com> | 2023-06-05 15:47:15 +0000 |
---|---|---|
committer | Rafael J. Wysocki <rafael.j.wysocki@intel.com> | 2023-06-16 19:12:36 +0200 |
commit | 2f3d08f074b02aa449de27238fda72496c789034 (patch) | |
tree | 4e4491e37d7e578e22dc52cc083d7998e723fbb2 | |
parent | 7826c069c8765969cfb7a364f8e0e663fc132b10 (diff) | |
download | linux-stable-2f3d08f074b02aa449de27238fda72496c789034.tar.gz linux-stable-2f3d08f074b02aa449de27238fda72496c789034.tar.bz2 linux-stable-2f3d08f074b02aa449de27238fda72496c789034.zip |
intel_idle: Add support for using intel_idle in a VM guest using just hlt
In a typical VM guest, the mwait instruction is not available, leaving
only the 'hlt' instruction (which causes a VMEXIT to the host).
So for this common case, 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).
Other (non-common) cases exist; the table below shows the before/after
for these:
+------------+--------------------------+-------------------------+
| Hypervisor | Idle method before patch | Idle method after patch |
| exposes | | |
+============+==========================+=========================+
| nothing | default_idle fallback | intel_idle VM table |
| (common) | (straight "hlt") | |
+------------+--------------------------+-------------------------+
| mwait | intel_idle mwait table | intel_idle mwait table |
+------------+--------------------------+-------------------------+
| ACPI | ACPI C1 state ("hlt") | intel_idle VM table |
+------------+--------------------------+-------------------------+
This is only applicable to CPUs known by intel_idle. For the bare metal
case, unknown CPU models will use the ACPI tables (when available) to
get estimates for latency and break even point for longer idle states.
In guests, the common case is that ACPI tables are not available, but
even when they are available, they can't and don't provide the latency
information for the longer (mwait based) states. For this scenario
(unknown CPU model), the default_idle mode (no ACPI) or ACPI C1 (ACPI
avaible) will be used.
By providing capability to do this with the intel_idle driver, we can
do better than the fallback or ACPI table methods. While this current
change only gets us to the existing behavior, later patches in this
series will add new capabilities such as optimized TLB flushing.
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 max 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>
[ rjw: Dropped redundant checks from should_verify_mwait() ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
-rw-r--r-- | drivers/idle/intel_idle.c | 117 |
1 files changed, 116 insertions, 1 deletions
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 256c2d42e350..a80e1f520293 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -199,6 +199,43 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev, return __intel_idle(dev, drv, index); } +static __always_inline int __intel_idle_hlt(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + raw_safe_halt(); + raw_local_irq_disable(); + return index; +} + +/** + * intel_idle_hlt - Ask the processor to enter the given idle state using hlt. + * @dev: cpuidle device of the target CPU. + * @drv: cpuidle driver (assumed to point to intel_idle_driver). + * @index: Target idle state index. + * + * Use the HLT instruction to notify the processor that the CPU represented by + * @dev is idle and it can try to enter the idle state corresponding to @index. + * + * Must be called under local_irq_disable(). + */ +static __cpuidle int intel_idle_hlt(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + return __intel_idle_hlt(dev, drv, index); +} + +static __cpuidle int intel_idle_hlt_irq_on(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + int ret; + + raw_local_irq_enable(); + ret = __intel_idle_hlt(dev, drv, index); + raw_local_irq_disable(); + + return ret; +} + /** * intel_idle_s2idle - Ask the processor to enter the given idle state. * @dev: cpuidle device of the target CPU. @@ -1242,6 +1279,18 @@ 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, }, + { + .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, @@ -1841,6 +1890,16 @@ static bool __init intel_idle_verify_cstate(unsigned int mwait_hint) static void state_update_enter_method(struct cpuidle_state *state, int cstate) { + if (state->enter == intel_idle_hlt) { + if (force_irq_on) { + pr_info("forced intel_idle_irq for state %d\n", cstate); + state->enter = intel_idle_hlt_irq_on; + } + return; + } + if (state->enter == intel_idle_hlt_irq_on) + return; /* no update scenarios */ + if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) { /* * Combining with XSTATE with IBRS or IRQ_ENABLE flags @@ -1874,6 +1933,21 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) } } +/* + * For mwait based states, we want to verify the cpuid data to see if the state + * is actually supported by this specific CPU. + * For non-mwait based states, this check should be skipped. + */ +static bool should_verify_mwait(struct cpuidle_state *state) +{ + if (state->enter == intel_idle_hlt) + return false; + if (state->enter == intel_idle_hlt_irq_on) + return false; + + return true; +} + static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) { int cstate; @@ -1922,7 +1996,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) } mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags); - if (!intel_idle_verify_cstate(mwait_hint)) + if (should_verify_mwait(&cpuidle_state_table[cstate]) && !intel_idle_verify_cstate(mwait_hint)) continue; /* Structure copy. */ @@ -2056,6 +2130,45 @@ 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; + + 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; @@ -2074,6 +2187,8 @@ 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; } |