| Message ID | 20230628022554.1638318-5-longman@redhat.com (mailing list archive) |
|---|---|
| State | Handled Elsewhere, archived |
| Headers | show |
| Series | x86/speculation: Disable IBRS when idle | expand |
Hi, On 6/27/23 19:25, Waiman Long wrote: > Documentation/admin-guide/pm/intel_idle.rst | 17 ++++++++++++++++- > drivers/idle/intel_idle.c | 14 ++++++++++++-- > 2 files changed, 28 insertions(+), 3 deletions(-) > > diff --git a/Documentation/admin-guide/pm/intel_idle.rst b/Documentation/admin-guide/pm/intel_idle.rst > index b799a43da62e..8604e6d1fe2c 100644 > --- a/Documentation/admin-guide/pm/intel_idle.rst > +++ b/Documentation/admin-guide/pm/intel_idle.rst You may take or leave these comments as you choose. > @@ -216,6 +216,21 @@ are ignored). > The idle states disabled this way can be enabled (on a per-CPU basis) from user > space via ``sysfs``. > > +The ``ibrs_off`` module parameter is a boolean flag (default to false). It is (default false). or (defaults to false). Then I think it reads better if the next sentence begins with: "If set," instead of having it in the middle of the sentence. > +used to control if IBRS (Indirect Branch Restricted Speculation) should be > +turned off, if set, when the CPU enters an idle state. This flag will not > +affect CPUs that are using Enhanced IBRS which can remain on with little > +performance impact. > + > +For some CPUs, IBRS will be selected as mitigation for Spectre v2 and Retbleed > +security vulnerabilities by default. Leaving the IBRS mode on while idling may > +have a performance impact on its sibling CPU. The IBRS mode will be turned off > +by default when the CPU enters into a deep idle state, but not in some > +shallower ones. Setting the ``ibrs_off`` module parameter will force the IBRS > +mode to off when the CPU is in any one of the available idle states. This may > +help performance of a sibling CPU at the expense of a slightly higher wakeup > +latency for the idle CPU. thanks.
On 6/27/23 22:58, Randy Dunlap wrote: > Hi, > > On 6/27/23 19:25, Waiman Long wrote: >> Documentation/admin-guide/pm/intel_idle.rst | 17 ++++++++++++++++- >> drivers/idle/intel_idle.c | 14 ++++++++++++-- >> 2 files changed, 28 insertions(+), 3 deletions(-) >> >> diff --git a/Documentation/admin-guide/pm/intel_idle.rst b/Documentation/admin-guide/pm/intel_idle.rst >> index b799a43da62e..8604e6d1fe2c 100644 >> --- a/Documentation/admin-guide/pm/intel_idle.rst >> +++ b/Documentation/admin-guide/pm/intel_idle.rst > You may take or leave these comments as you choose. > >> @@ -216,6 +216,21 @@ are ignored). >> The idle states disabled this way can be enabled (on a per-CPU basis) from user >> space via ``sysfs``. >> >> +The ``ibrs_off`` module parameter is a boolean flag (default to false). It is > (default false). > or > (defaults to false). > > Then I think it reads better if the next sentence begins with: "If set," > instead of having it in the middle of the sentence. > >> +used to control if IBRS (Indirect Branch Restricted Speculation) should be >> +turned off, if set, when the CPU enters an idle state. This flag will not >> +affect CPUs that are using Enhanced IBRS which can remain on with little >> +performance impact. >> + >> +For some CPUs, IBRS will be selected as mitigation for Spectre v2 and Retbleed >> +security vulnerabilities by default. Leaving the IBRS mode on while idling may >> +have a performance impact on its sibling CPU. The IBRS mode will be turned off >> +by default when the CPU enters into a deep idle state, but not in some >> +shallower ones. Setting the ``ibrs_off`` module parameter will force the IBRS >> +mode to off when the CPU is in any one of the available idle states. This may >> +help performance of a sibling CPU at the expense of a slightly higher wakeup >> +latency for the idle CPU. > thanks. Thanks for the suggestion. I will make the change if I have to revise the patch again for any reason. Cheers, Longman
On Tue, Jun 27, 2023 at 10:25:54PM -0400, Waiman Long wrote: > @@ -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 ibrs_off __read_mostly; > > static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; > > @@ -1919,12 +1920,15 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) > } > > if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && > - state->flags & CPUIDLE_FLAG_IBRS) { > + ((state->flags & CPUIDLE_FLAG_IBRS) || ibrs_off)) { > /* > * IBRS mitigation requires that C-states are entered > * with interrupts disabled. > */ > - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); > + if (ibrs_off && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)) > + state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE; > + else > + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); If you're respinning this, you can leave out the else and avoid the indent on the WARN: + if (ibrs_off && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)) + state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE; WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); Same effect, simpler code and all that. > state->enter = intel_idle_ibrs; > return; > }
On 7/3/23 06:32, Peter Zijlstra wrote: > On Tue, Jun 27, 2023 at 10:25:54PM -0400, Waiman Long wrote: > >> @@ -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 ibrs_off __read_mostly; >> >> static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; >> >> @@ -1919,12 +1920,15 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) >> } >> >> if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && >> - state->flags & CPUIDLE_FLAG_IBRS) { >> + ((state->flags & CPUIDLE_FLAG_IBRS) || ibrs_off)) { >> /* >> * IBRS mitigation requires that C-states are entered >> * with interrupts disabled. >> */ >> - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); >> + if (ibrs_off && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)) >> + state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE; >> + else >> + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); > If you're respinning this, you can leave out the else and avoid the > indent on the WARN: > > + if (ibrs_off && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)) > + state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE; > WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); > > Same effect, simpler code and all that. That is true. I can certainly respin that as there is another suggested doc change that is pending. Cheers, Longman
diff --git a/Documentation/admin-guide/pm/intel_idle.rst b/Documentation/admin-guide/pm/intel_idle.rst index b799a43da62e..8604e6d1fe2c 100644 --- a/Documentation/admin-guide/pm/intel_idle.rst +++ b/Documentation/admin-guide/pm/intel_idle.rst @@ -170,7 +170,7 @@ and ``idle=nomwait``. If any of them is present in the kernel command line, the ``MWAIT`` instruction is not allowed to be used, so the initialization of ``intel_idle`` will fail. -Apart from that there are four module parameters recognized by ``intel_idle`` +Apart from that there are five module parameters recognized by ``intel_idle`` itself that can be set via the kernel command line (they cannot be updated via sysfs, so that is the only way to change their values). @@ -216,6 +216,21 @@ are ignored). The idle states disabled this way can be enabled (on a per-CPU basis) from user space via ``sysfs``. +The ``ibrs_off`` module parameter is a boolean flag (default to false). It is +used to control if IBRS (Indirect Branch Restricted Speculation) should be +turned off, if set, when the CPU enters an idle state. This flag will not +affect CPUs that are using Enhanced IBRS which can remain on with little +performance impact. + +For some CPUs, IBRS will be selected as mitigation for Spectre v2 and Retbleed +security vulnerabilities by default. Leaving the IBRS mode on while idling may +have a performance impact on its sibling CPU. The IBRS mode will be turned off +by default when the CPU enters into a deep idle state, but not in some +shallower ones. Setting the ``ibrs_off`` module parameter will force the IBRS +mode to off when the CPU is in any one of the available idle states. This may +help performance of a sibling CPU at the expense of a slightly higher wakeup +latency for the idle CPU. + .. _intel-idle-core-and-package-idle-states: diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index e32ff09051af..14874579b396 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 ibrs_off __read_mostly; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; @@ -1919,12 +1920,15 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) } if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && - state->flags & CPUIDLE_FLAG_IBRS) { + ((state->flags & CPUIDLE_FLAG_IBRS) || ibrs_off)) { /* * IBRS mitigation requires that C-states are entered * with interrupts disabled. */ - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); + if (ibrs_off && (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; return; } @@ -2346,3 +2350,9 @@ 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(ibrs_off, bool, 0444); +MODULE_PARM_DESC(ibrs_off, "Disable IBRS when idle");
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 "ibrs_off" 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 ibrs_off option will likely increase the IRQ response latency as IRQ will now be disabled. When running SPECjbb2015 with cstates set to C1 on a Skylake system. First test when the kernel is booted with: "intel_idle.ibrs_off" max-jOPS = 117828, critical-jOPS = 66047 Then retest when the kernel is booted without the "intel_idle.ibrs_off" added. max-jOPS = 116408, critical-jOPS = 58958 That means booting with "intel_idle.ibrs_off" improves performance by: max-jOPS: 1.2%, which could be considered noise range. critical-jOPS: 12%, which is definitely a solid improvement. The admin-guide/pm/intel_idle.rst file is updated to add a description about the new "ibrs_off" module parameter. Signed-off-by: Waiman Long <longman@redhat.com> --- Documentation/admin-guide/pm/intel_idle.rst | 17 ++++++++++++++++- drivers/idle/intel_idle.c | 14 ++++++++++++-- 2 files changed, 28 insertions(+), 3 deletions(-)