Remove the 'preferred_cstates' module parameter as it is not really useful.
The parameter currently only affects Alder Lake, where it controls C1/C1E
preference, with C1E being the default. The parameter does not support any
other platform. For example, Meteor Lake has a similar C1/C1E limitation,
but the parameter does not support Meteor Lake. This indicates that the
parameter is not very useful.
Generally, independent C1 and C1E are important for server platforms where
low latency is key. However, they are not as important for client platforms,
like Alder Lake, where C1E providing better energy savings is generally
preferred.
The parameter was originally introduced for Sapphire Rapids Xeon:
da0e58c038e6 intel_idle: add 'preferred_cstates' module argument
Later it was added to Alder Lake:
d1cf8bbfed1ed ("intel_idle: Add AlderLake support")
But it was removed from Sapphire Rapids when firmware fixed the C1/C1E
limitation:
1548fac47a114 ("intel_idle: make SPR C1 and C1E be independent")
So Alder Lake is the only platform left where this parameter has any effect.
Remove this parameter to simplify the driver and reduce maintenance burden.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/20251215111300.132803-1-dedekind1@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git a36dc37b5672
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Release-Acked-by: Oleksii Kurochko <oleksii.kurochko@gmail.com>
Clearwater Forest (CWF) SoC has the same C-states as Sierra Forest (SRF)
SoC. Add CWF support by re-using the SRF C-states table.
Note: it is expected that CWF C-states will have same or very similar
characteristics as SRF C-states (latency and target residency).
However, there is a possibility that the characteristics will end up
being different enough when the CWF platform development is finished.
In that case, a separate CWF C-states table will be created and populated
with the CWF-specific characteristics (latency and target residency).
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/20241203130306.1559024-1-artem.bityutskiy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git eeed4bfbe9b9
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
Add Granite Rapids Xeon C-states, which are C1, C1E, C6, and C6P.
Comparing to previous Xeon Generations (e.g., Emerald Rapids), C6
requests end up only in core C6 state, and no package C-state promotion
takes place even if all cores in the package are in core C6.
C6P requests also end up in core C6, but if all cores have requested
C6P, the SoC will enter the package C6 state.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/20240806160310.3719205-1-artem.bityutskiy@linux.intel.com
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 370406bf5738
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
Add Sierra Forest SoC C-states, which are C1, C1E, C6S, and C6SP.
Sierra Forest SoC is built with modules, each module includes 4 cores
(Crestmont microarchitecture). There is one L2 cache per module, shared
between the 4 cores.
There is no core C6 state, but there is C6S state, which has module scope:
when all 4 cores request C6S, the entire module (4 cores + L2 cache)
enters the low power state.
C6SP state has package scope - when all modules in the package enter C6S,
the package enters the power state mode.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 92813fd5b156
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
Add Intel Grand Ridge SoC C-states, which are C1, C1E, and C6S.
The Grand Ridge SoC is built with modules, each module includes 4 cores
(Crestmont microarchitecture). There is one L2 cache per module, shared
between the 4 cores.
There is no core C6 state, but there is C6S state, which has module
scope: when all 4 cores request C6S, the entire module (4 cores + L2
cache) enters the low power state.
Package C6 is not supported by Grand Ridge SoC.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git ac89d11b93cc
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
Emerald Rapids (EMR) is the next Intel Xeon processor after Sapphire
Rapids (SPR).
EMR C-states are the same as SPR C-states, and we expect that EMR
C-state characteristics (latency and target residency) will be the
same as in SPR. Therefore, add EMR support by using SPR C-states table.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 74528edfbc66
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
This patch partially reverts the changes made by the following commit:
da0e58c038e6 intel_idle: add 'preferred_cstates' module argument
As that commit describes, on early Sapphire Rapids Xeon platforms the C1 and
C1E states were mutually exclusive, so that users could only have either C1 and
C6, or C1E and C6.
However, Intel firmware engineers managed to remove this limitation and make C1
and C1E to be completely independent, just like on previous Xeon platforms.
Therefore, this patch:
* Removes commentary describing the old, and now non-existing SPR C1E
limitation.
* Marks SPR C1E as available by default.
* Removes the 'preferred_cstates' parameter handling for SPR. Both C1 and
C1E will be available regardless of 'preferred_cstates' value.
We expect that all SPR systems are shipping with new firmware, which includes
the C1/C1E improvement.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 1548fac47a11
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Release-acked-by: Henry Wang <Henry.Wang@arm.com>
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Add a Sapphire Rapids Xeon C6 optimization, similar to what we have for Sky Lake
Xeon: if package C6 is disabled, adjust C6 exit latency and target residency to
match core C6 values, instead of using the default package C6 values.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 3a9cf77b60dc
Make sure a contradictory "preferred-cstates" wouldn't cause bypassing
of the added logic.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Release-acked-by: Henry Wang <Henry.Wang@arm.com>
On Sapphire Rapids Xeon (SPR) the C1 and C1E states are basically mutually
exclusive - only one of them can be enabled. By default, 'intel_idle' driver
enables C1 and disables C1E. However, some users prefer to use C1E instead of
C1, because it saves more energy.
This patch adds a new module parameter ('preferred_cstates') for enabling C1E
and disabling C1. Here is the idea behind it.
1. This option has effect only for "mutually exclusive" C-states like C1 and
C1E on SPR.
2. It does not have any effect on independent C-states, which do not require
other C-states to be disabled (most states on most platforms as of today).
3. For mutually exclusive C-states, the 'intel_idle' driver always has a
reasonable default, such as enabling C1 on SPR by default. On other
platforms, the default may be different.
4. Users can override the default using the 'preferred_cstates' parameter.
5. The parameter accepts the preferred C-states bit-mask, similarly to the
existing 'states_off' parameter.
6. This parameter is not limited to C1/C1E, and leaves room for supporting
other mutually exclusive C-states, if they come in the future.
Today 'intel_idle' can only be compiled-in, which means that on SPR, in order
to disable C1 and enable C1E, users should boot with the following kernel
argument: intel_idle.preferred_cstates=4
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git da0e58c038e6
Enable C1E (if requested) not only on the BSP's socket / package. Alter
command line option to fit our model, and extend it to also accept
string form arguments.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Release-acked-by: Henry Wang <Henry.Wang@arm.com>
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>
Origin: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 9edf3c0ffef0
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Enable local interrupts before requesting C1 on the last two generations
of Intel Xeon platforms: Sky Lake, Cascade Lake, Cooper Lake, Ice Lake.
This decreases average C1 interrupt latency by about 5-10%, as measured
with the 'wult' tool.
The '->enter()' function of the driver enters C-states with local
interrupts disabled by executing the 'monitor' and 'mwait' pair of
instructions. If an interrupt happens, the CPU exits the C-state and
continues executing instructions after 'mwait'. It does not jump to
the interrupt handler, because local interrupts are disabled. The
cpuidle subsystem enables interrupts a bit later, after doing some
housekeeping.
With this patch, we enable local interrupts before requesting C1. In
this case, if the CPU wakes up because of an interrupt, it will jump
to the interrupt handler right away. The cpuidle housekeeping will be
done after the pending interrupt(s) are handled.
Enabling interrupts before entering a C-state has measurable impact
for faster C-states, like C1. Deeper, but slower C-states like C6 do
not really benefit from this sort of change, because their latency is
a lot higher comparing to the delay added by cpuidle housekeeping.
This change was also tested with cyclictest and dbench. In case of Ice
Lake, the average cyclictest latency decreased by 5.1%, and the average
'dbench' throughput increased by about 0.8%. Both tests were run for 4
hours with only C1 enabled (all other idle states, including 'POLL',
were disabled). CPU frequency was pinned to HFM, and uncore frequency
was pinned to the maximum value. The other platforms had similar
single-digit percentage improvements.
It is worth noting that this patch affects 'cpuidle' statistics a tiny
bit. Before this patch, C1 residency did not include the interrupt
handling time, but with this patch, it will include it. This is similar
to what happens in case of the 'POLL' state, which also runs with
interrupts enabled.
Suggested-by: Len Brown <len.brown@intel.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
[Linux commit: c227233ad64c77e57db738ab0e46439db71822a3]
We don't have a pointer into cpuidle_state_table[] readily available.
To compensate, propagate the flag into struct acpi_processor_cx.
Unlike Linux we want to
- disable IRQs again after MWAITing, as subsequently invoked functions
assume so,
- avoid enabling IRQs if cstate_restore_tsc() is not a no-op, to avoid
interfering with, in particular, the time rendezvous.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
x86/mwait-idle: add SnowRidge C-state table
Add C-state table for the SnowRidge SoC which is found on Intel Jacobsville
platforms.
The following has been changed.
1. C1E latency changed from 10us to 15us. It was measured using the
open source "wult" tool (the "nic" method, 15us is the 99.99th
percentile).
2. C1E power break even changed from 20us to 25us, which may result
in less C1E residency in some workloads.
3. C6 latency changed from 50us to 130us. Measured the same way as C1E.
The C6 C-state is supported only by some SnowRidge revisions, so add a C-state
table commentary about this.
On SnowRidge, C6 support is enumerated via the usual mechanism: "mwait" leaf of
the "cpuid" instruction. The 'intel_idle' driver does check this leaf, so even
though C6 is present in the table, the driver will only use it if the CPU does
support it.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
[Linux commit: 9cf93f056f783f986c19f40d5304d1bcffa0fc0d]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
This patch adds Icelake Xeon D support to the intel_idle driver.
Since Icelake D and Icelake SP C-state characteristics the same,
we use Icelake SP C-states table for Icelake D as well.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Acked-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
[Linux commit: 22141d5f411895bb1b0df2a6b05f702e11e63918]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Change IceLake Xeon C6 latency from 128 us to 170 us. The latency
was measured with the "wult" tool and corresponds to the 99.99th
percentile when measuring with the "nic" method. Note, the 128 us
figure correspond to the median latency, but in intel_idle we use
the "worst case" latency figure instead.
C6 target residency was increased from 384 us to 600 us, which may
result in less C6 residency in some workloads. This value was tested
and compared to values 384, and 1000. Value 600 is a reasonable
tradeoff between power and performance.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Acked-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
[Linux commit: d484b8bfc6fa71a088e4ac85d9ce11aa0385867e]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Artem Bityutskiy