Commit bf5835bcdb96 ("intel_idle: Disable IBRS during long idle")
disables IBRS when the cstate is 6 or lower. However, there are
some use cases where a customer may want to use max_cstate=1 to
lower latency. Such use cases will suffer from the performance
degradation caused by the enabling of IBRS in the sibling idle thread.
Add a "no_ibrs" module parameter to force disable IBRS and the
CPUIDLE_FLAG_IRQ_ENABLE flag if set.
In the case of a Skylake server with max_cstate=1, this new no_ibrs
option will increase the IRQ response latency as IRQ will now be
disabled.
Signed-off-by: Waiman Long <[email protected]>
---
drivers/idle/intel_idle.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 07fa23707b3c..366dacccc971 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -69,6 +69,7 @@ static int max_cstate = CPUIDLE_STATE_MAX - 1;
static unsigned int disabled_states_mask __read_mostly;
static unsigned int preferred_states_mask __read_mostly;
static bool force_irq_on __read_mostly;
+static bool no_ibrs __read_mostly;
static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
@@ -1907,12 +1908,15 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
state->enter = intel_idle_xstate;
} else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
- state->flags & CPUIDLE_FLAG_IBRS) {
+ ((state->flags & CPUIDLE_FLAG_IBRS) || no_ibrs)) {
/*
* IBRS mitigation requires that C-states are entered
* with interrupts disabled.
*/
- WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
+ if (no_ibrs && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE))
+ state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE;
+ else
+ WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
state->enter = intel_idle_ibrs;
} else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) {
state->enter = intel_idle_irq;
@@ -2165,3 +2169,9 @@ MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states");
* 'CPUIDLE_FLAG_INIT_XSTATE' and 'CPUIDLE_FLAG_IBRS' flags.
*/
module_param(force_irq_on, bool, 0444);
+/*
+ * Force the disabling of IBRS when X86_FEATURE_KERNEL_IBRS is on and
+ * CPUIDLE_FLAG_IRQ_ENABLE isn't set.
+ */
+module_param(no_ibrs, bool, 0444);
+MODULE_PARM_DESC(no_ibrs, "Disable IBRS when idle");
--
2.31.1
On Tue, Jun 20, 2023 at 10:06:24AM -0400, Waiman Long wrote:
> Commit bf5835bcdb96 ("intel_idle: Disable IBRS during long idle")
> disables IBRS when the cstate is 6 or lower. However, there are
> some use cases where a customer may want to use max_cstate=1 to
> lower latency.
And then add the WRMSRs to increase latency again...
Since you're mucking about with all this, perhaps see if you can measure
the latency impact of all this.
> Such use cases will suffer from the performance
> degradation caused by the enabling of IBRS in the sibling idle thread.
> Add a "no_ibrs" module parameter to force disable IBRS and the
> CPUIDLE_FLAG_IRQ_ENABLE flag if set.
>
> In the case of a Skylake server with max_cstate=1, this new no_ibrs
> option will increase the IRQ response latency as IRQ will now be
> disabled.
>
> Signed-off-by: Waiman Long <[email protected]>
> ---
> drivers/idle/intel_idle.c | 14 ++++++++++++--
> 1 file changed, 12 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
> index 07fa23707b3c..366dacccc971 100644
> --- a/drivers/idle/intel_idle.c
> +++ b/drivers/idle/intel_idle.c
> @@ -69,6 +69,7 @@ static int max_cstate = CPUIDLE_STATE_MAX - 1;
> static unsigned int disabled_states_mask __read_mostly;
> static unsigned int preferred_states_mask __read_mostly;
> static bool force_irq_on __read_mostly;
> +static bool no_ibrs __read_mostly;
>
> static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
>
> @@ -1907,12 +1908,15 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
> WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
> state->enter = intel_idle_xstate;
> } else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
> - state->flags & CPUIDLE_FLAG_IBRS) {
> + ((state->flags & CPUIDLE_FLAG_IBRS) || no_ibrs)) {
> /*
> * IBRS mitigation requires that C-states are entered
> * with interrupts disabled.
> */
> - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
> + if (no_ibrs && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE))
> + state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE;
> + else
> + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
> state->enter = intel_idle_ibrs;
> } else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) {
> state->enter = intel_idle_irq;
> @@ -2165,3 +2169,9 @@ MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states");
> * 'CPUIDLE_FLAG_INIT_XSTATE' and 'CPUIDLE_FLAG_IBRS' flags.
> */
> module_param(force_irq_on, bool, 0444);
> +/*
> + * Force the disabling of IBRS when X86_FEATURE_KERNEL_IBRS is on and
> + * CPUIDLE_FLAG_IRQ_ENABLE isn't set.
> + */
> +module_param(no_ibrs, bool, 0444);
> +MODULE_PARM_DESC(no_ibrs, "Disable IBRS when idle");
Urgghhh.. the flag is CPUIDLE_FLAG_IBRS, so "no_ibrs" implies clearing
that flag.