diff options
55 files changed, 2274 insertions, 218 deletions
diff --git a/Documentation/admin-guide/acpi/cppc_sysfs.rst b/Documentation/admin-guide/acpi/cppc_sysfs.rst index fccf22114e85..e53d76365aa7 100644 --- a/Documentation/admin-guide/acpi/cppc_sysfs.rst +++ b/Documentation/admin-guide/acpi/cppc_sysfs.rst @@ -4,6 +4,8 @@ Collaborative Processor Performance Control (CPPC) ================================================== +.. _cppc_sysfs: + CPPC ==== diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f8a663f47a27..49f495c9a7f8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -225,14 +225,23 @@ For broken nForce2 BIOS resulting in XT-PIC timer. acpi_sleep= [HW,ACPI] Sleep options - Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, - old_ordering, nonvs, sci_force_enable, nobl } + Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, + s4_nohwsig, old_ordering, nonvs, + sci_force_enable, nobl } See Documentation/power/video.rst for information on s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. + s4_hwsig causes the kernel to check the ACPI hardware + signature during resume from hibernation, and gracefully + refuse to resume if it has changed. This complies with + the ACPI specification but not with reality, since + Windows does not do this and many laptops do change it + on docking. So the default behaviour is to allow resume + and simply warn when the signature changes, unless the + s4_hwsig option is enabled. s4_nohwsig prevents ACPI hardware signature from being - used during resume from hibernation. + used (or even warned about) during resume. old_ordering causes the ACPI 1.0 ordering of the _PTS control method, with respect to putting devices into low power states, to be enforced (the ACPI 2.0 ordering diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst new file mode 100644 index 000000000000..2f066df4ee9c --- /dev/null +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -0,0 +1,382 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +=============================================== +``amd-pstate`` CPU Performance Scaling Driver +=============================================== + +:Copyright: |copy| 2021 Advanced Micro Devices, Inc. + +:Author: Huang Rui <ray.huang@amd.com> + + +Introduction +=================== + +``amd-pstate`` is the AMD CPU performance scaling driver that introduces a +new CPU frequency control mechanism on modern AMD APU and CPU series in +Linux kernel. The new mechanism is based on Collaborative Processor +Performance Control (CPPC) which provides finer grain frequency management +than legacy ACPI hardware P-States. Current AMD CPU/APU platforms are using +the ACPI P-states driver to manage CPU frequency and clocks with switching +only in 3 P-states. CPPC replaces the ACPI P-states controls, allows a +flexible, low-latency interface for the Linux kernel to directly +communicate the performance hints to hardware. + +``amd-pstate`` leverages the Linux kernel governors such as ``schedutil``, +``ondemand``, etc. to manage the performance hints which are provided by +CPPC hardware functionality that internally follows the hardware +specification (for details refer to AMD64 Architecture Programmer's Manual +Volume 2: System Programming [1]_). Currently ``amd-pstate`` supports basic +frequency control function according to kernel governors on some of the +Zen2 and Zen3 processors, and we will implement more AMD specific functions +in future after we verify them on the hardware and SBIOS. + + +AMD CPPC Overview +======================= + +Collaborative Processor Performance Control (CPPC) interface enumerates a +continuous, abstract, and unit-less performance value in a scale that is +not tied to a specific performance state / frequency. This is an ACPI +standard [2]_ which software can specify application performance goals and +hints as a relative target to the infrastructure limits. AMD processors +provides the low latency register model (MSR) instead of AML code +interpreter for performance adjustments. ``amd-pstate`` will initialize a +``struct cpufreq_driver`` instance ``amd_pstate_driver`` with the callbacks +to manage each performance update behavior. :: + + Highest Perf ------>+-----------------------+ +-----------------------+ + | | | | + | | | | + | | Max Perf ---->| | + | | | | + | | | | + Nominal Perf ------>+-----------------------+ +-----------------------+ + | | | | + | | | | + | | | | + | | | | + | | | | + | | | | + | | Desired Perf ---->| | + | | | | + | | | | + | | | | + | | | | + | | | | + | | | | + | | | | + | | | | + | | | | + Lowest non- | | | | + linear perf ------>+-----------------------+ +-----------------------+ + | | | | + | | Lowest perf ---->| | + | | | | + Lowest perf ------>+-----------------------+ +-----------------------+ + | | | | + | | | | + | | | | + 0 ------>+-----------------------+ +-----------------------+ + + AMD P-States Performance Scale + + +.. _perf_cap: + +AMD CPPC Performance Capability +-------------------------------- + +Highest Performance (RO) +......................... + +It is the absolute maximum performance an individual processor may reach, +assuming ideal conditions. This performance level may not be sustainable +for long durations and may only be achievable if other platform components +are in a specific state; for example, it may require other processors be in +an idle state. This would be equivalent to the highest frequencies +supported by the processor. + +Nominal (Guaranteed) Performance (RO) +...................................... + +It is the maximum sustained performance level of the processor, assuming +ideal operating conditions. In absence of an external constraint (power, +thermal, etc.) this is the performance level the processor is expected to +be able to maintain continuously. All cores/processors are expected to be +able to sustain their nominal performance state simultaneously. + +Lowest non-linear Performance (RO) +................................... + +It is the lowest performance level at which nonlinear power savings are +achieved, for example, due to the combined effects of voltage and frequency +scaling. Above this threshold, lower performance levels should be generally +more energy efficient than higher performance levels. This register +effectively conveys the most efficient performance level to ``amd-pstate``. + +Lowest Performance (RO) +........................ + +It is the absolute lowest performance level of the processor. Selecting a +performance level lower than the lowest nonlinear performance level may +cause an efficiency penalty but should reduce the instantaneous power +consumption of the processor. + +AMD CPPC Performance Control +------------------------------ + +``amd-pstate`` passes performance goals through these registers. The +register drives the behavior of the desired performance target. + +Minimum requested performance (RW) +................................... + +``amd-pstate`` specifies the minimum allowed performance level. + +Maximum requested performance (RW) +................................... + +``amd-pstate`` specifies a limit the maximum performance that is expected +to be supplied by the hardware. + +Desired performance target (RW) +................................... + +``amd-pstate`` specifies a desired target in the CPPC performance scale as +a relative number. This can be expressed as percentage of nominal +performance (infrastructure max). Below the nominal sustained performance +level, desired performance expresses the average performance level of the +processor subject to hardware. Above the nominal performance level, +processor must provide at least nominal performance requested and go higher +if current operating conditions allow. + +Energy Performance Preference (EPP) (RW) +......................................... + +Provides a hint to the hardware if software wants to bias toward performance +(0x0) or energy efficiency (0xff). + + +Key Governors Support +======================= + +``amd-pstate`` can be used with all the (generic) scaling governors listed +by the ``scaling_available_governors`` policy attribute in ``sysfs``. Then, +it is responsible for the configuration of policy objects corresponding to +CPUs and provides the ``CPUFreq`` core (and the scaling governors attached +to the policy objects) with accurate information on the maximum and minimum +operating frequencies supported by the hardware. Users can check the +``scaling_cur_freq`` information comes from the ``CPUFreq`` core. + +``amd-pstate`` mainly supports ``schedutil`` and ``ondemand`` for dynamic +frequency control. It is to fine tune the processor configuration on +``amd-pstate`` to the ``schedutil`` with CPU CFS scheduler. ``amd-pstate`` +registers adjust_perf callback to implement the CPPC similar performance +update behavior. It is initialized by ``sugov_start`` and then populate the +CPU's update_util_data pointer to assign ``sugov_update_single_perf`` as +the utilization update callback function in CPU scheduler. CPU scheduler +will call ``cpufreq_update_util`` and assign the target performance +according to the ``struct sugov_cpu`` that utilization update belongs to. +Then ``amd-pstate`` updates the desired performance according to the CPU +scheduler assigned. + + +Processor Support +======================= + +The ``amd-pstate`` initialization will fail if the _CPC in ACPI SBIOS is +not existed at the detected processor, and it uses ``acpi_cpc_valid`` to +check the _CPC existence. All Zen based processors support legacy ACPI +hardware P-States function, so while the ``amd-pstate`` fails to be +initialized, the kernel will fall back to initialize ``acpi-cpufreq`` +driver. + +There are two types of hardware implementations for ``amd-pstate``: one is +`Full MSR Support <perf_cap_>`_ and another is `Shared Memory Support +<perf_cap_>`_. It can use :c:macro:`X86_FEATURE_CPPC` feature flag (for +details refer to Processor Programming Reference (PPR) for AMD Family +19h Model 51h, Revision A1 Processors [3]_) to indicate the different +types. ``amd-pstate`` is to register different ``static_call`` instances +for different hardware implementations. + +Currently, some of Zen2 and Zen3 processors support ``amd-pstate``. In the +future, it will be supported on more and more AMD processors. + +Full MSR Support +----------------- + +Some new Zen3 processors such as Cezanne provide the MSR registers directly +while the :c:macro:`X86_FEATURE_CPPC` CPU feature flag is set. +``amd-pstate`` can handle the MSR register to implement the fast switch +function in ``CPUFreq`` that can shrink latency of frequency control on the +interrupt context. The functions with ``pstate_xxx`` prefix represent the +operations of MSR registers. + +Shared Memory Support +---------------------- + +If :c:macro:`X86_FEATURE_CPPC` CPU feature flag is not set, that means the +processor supports shared memory solution. In this case, ``amd-pstate`` +uses the ``cppc_acpi`` helper methods to implement the callback functions +that defined on ``static_call``. The functions with ``cppc_xxx`` prefix +represent the operations of acpi cppc helpers for shared memory solution. + + +AMD P-States and ACPI hardware P-States always can be supported in one +processor. But AMD P-States has the higher priority and if it is enabled +with :c:macro:`MSR_AMD_CPPC_ENABLE` or ``cppc_set_enable``, it will respond +to the request from AMD P-States. + + +User Space Interface in ``sysfs`` +================================== + +``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to +control its functionality at the system level. They located in the +``/sys/devices/system/cpu/cpufreq/policyX/`` directory and affect all CPUs. :: + + root@hr-test1:/home/ray# ls /sys/devices/system/cpu/cpufreq/policy0/*amd* + /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_highest_perf + /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_lowest_nonlinear_freq + /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_max_freq + + +``amd_pstate_highest_perf / amd_pstate_max_freq`` + +Maximum CPPC performance and CPU frequency that the driver is allowed to +set in percent of the maximum supported CPPC performance level (the highest +performance supported in `AMD CPPC Performance Capability <perf_cap_>`_). +In some of ASICs, the highest CPPC performance is not the one in the _CPC +table, so we need to expose it to sysfs. If boost is not active but +supported, this maximum frequency will be larger than the one in +``cpuinfo``. +This attribute is read-only. + +``amd_pstate_lowest_nonlinear_freq`` + +The lowest non-linear CPPC CPU frequency that the driver is allowed to set +in percent of the maximum supported CPPC performance level (Please see the +lowest non-linear performance in `AMD CPPC Performance Capability +<perf_cap_>`_). +This attribute is read-only. + +For other performance and frequency values, we can read them back from +``/sys/devices/system/cpu/cpuX/acpi_cppc/``, see :ref:`cppc_sysfs`. + + +``amd-pstate`` vs ``acpi-cpufreq`` +====================================== + +On majority of AMD platforms supported by ``acpi-cpufreq``, the ACPI tables +provided by the platform firmware used for CPU performance scaling, but +only provides 3 P-states on AMD processors. +However, on modern AMD APU and CPU series, it provides the collaborative +processor performance control according to ACPI protocol and customize this +for AMD platforms. That is fine-grain and continuous frequency range +instead of the legacy hardware P-states. ``amd-pstate`` is the kernel +module which supports the new AMD P-States mechanism on most of future AMD +platforms. The AMD P-States mechanism will be the more performance and energy +efficiency frequency management method on AMD processors. + +Kernel Module Options for ``amd-pstate`` +========================================= + +``shared_mem`` +Use a module param (shared_mem) to enable related processors manually with +**amd_pstate.shared_mem=1**. +Due to the performance issue on the processors with `Shared Memory Support +<perf_cap_>`_, so we disable it for the moment and will enable this by default +once we address performance issue on this solution. + +The way to check whether current processor is `Full MSR Support <perf_cap_>`_ +or `Shared Memory Support <perf_cap_>`_ : :: + + ray@hr-test1:~$ lscpu | grep cppc + Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm + +If CPU Flags have cppc, then this processor supports `Full MSR Support +<perf_cap_>`_. Otherwise it supports `Shared Memory Support <perf_cap_>`_. + + +``cpupower`` tool support for ``amd-pstate`` +=============================================== + +``amd-pstate`` is supported on ``cpupower`` tool that can be used to dump the frequency +information. And it is in progress to support more and more operations for new +``amd-pstate`` module with this tool. :: + + root@hr-test1:/home/ray# cpupower frequency-info + analyzing CPU 0: + driver: amd-pstate + CPUs which run at the same hardware frequency: 0 + CPUs which need to have their frequency coordinated by software: 0 + maximum transition latency: 131 us + hardware limits: 400 MHz - 4.68 GHz + available cpufreq governors: ondemand conservative powersave userspace performance schedutil + current policy: frequency should be within 400 MHz and 4.68 GHz. + The governor "schedutil" may decide which speed to use + within this range. + current CPU frequency: Unable to call hardware + current CPU frequency: 4.02 GHz (asserted by call to kernel) + boost state support: + Supported: yes + Active: yes + AMD PSTATE Highest Performance: 166. Maximum Frequency: 4.68 GHz. + AMD PSTATE Nominal Performance: 117. Nominal Frequency: 3.30 GHz. + AMD PSTATE Lowest Non-linear Performance: 39. Lowest Non-linear Frequency: 1.10 GHz. + AMD PSTATE Lowest Performance: 15. Lowest Frequency: 400 MHz. + + +Diagnostics and Tuning +======================= + +Trace Events +-------------- + +There are two static trace events that can be used for ``amd-pstate`` +diagnostics. One of them is the cpu_frequency trace event generally used +by ``CPUFreq``, and the other one is the ``amd_pstate_perf`` trace event +specific to ``amd-pstate``. The following sequence of shell commands can +be used to enable them and see their output (if the kernel is generally +configured to support event tracing). :: + + root@hr-test1:/home/ray# cd /sys/kernel/tracing/ + root@hr-test1:/sys/kernel/tracing# echo 1 > events/amd_cpu/enable + root@hr-test1:/sys/kernel/tracing# cat trace + # tracer: nop + # + # entries-in-buffer/entries-written: 47827/42233061 #P:2 + # + # _-----=> irqs-off + # / _----=> need-resched + # | / _---=> hardirq/softirq + # || / _--=> preempt-depth + # ||| / delay + # TASK-PID CPU# |||| TIMESTAMP FUNCTION + # | | | |||| | | + <idle>-0 [015] dN... 4995.979886: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=15 changed=false fast_switch=true + <idle>-0 [007] d.h.. 4995.979893: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=7 changed=false fast_switch=true + cat-2161 [000] d.... 4995.980841: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=0 changed=false fast_switch=true + sshd-2125 [004] d.s.. 4995.980968: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=4 changed=false fast_switch=true + <idle>-0 [007] d.s.. 4995.980968: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=7 changed=false fast_switch=true + <idle>-0 [003] d.s.. 4995.980971: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=3 changed=false fast_switch=true + <idle>-0 [011] d.s.. 4995.980996: amd_pstate_perf: amd_min_perf=85 amd_des_perf=85 amd_max_perf=166 cpu_id=11 changed=false fast_switch=true + +The cpu_frequency trace event will be triggered either by the ``schedutil`` scaling +governor (for the policies it is attached to), or by the ``CPUFreq`` core (for the +policies with other scaling governors). + + +Reference +=========== + +.. [1] AMD64 Architecture Programmer's Manual Volume 2: System Programming, + https://www.amd.com/system/files/TechDocs/24593.pdf + +.. [2] Advanced Configuration and Power Interface Specification, + https://uefi.org/sites/default/files/resources/ACPI_Spec_6_4_Jan22.pdf + +.. [3] Processor Programming Reference (PPR) for AMD Family 19h Model 51h, Revision A1 Processors + https://www.amd.com/system/files/TechDocs/56569-A1-PUB.zip diff --git a/Documentation/admin-guide/pm/working-state.rst b/Documentation/admin-guide/pm/working-state.rst index f40994c422dc..5d2757e2de65 100644 --- a/Documentation/admin-guide/pm/working-state.rst +++ b/Documentation/admin-guide/pm/working-state.rst @@ -11,6 +11,7 @@ Working-State Power Management intel_idle cpufreq intel_pstate + amd-pstate cpufreq_drivers intel_epb intel-speed-select diff --git a/Documentation/power/opp.rst b/Documentation/power/opp.rst index e3cc4f349ea8..a7c03c470980 100644 --- a/Documentation/power/opp.rst +++ b/Documentation/power/opp.rst @@ -48,9 +48,9 @@ We can represent these as three OPPs as the following {Hz, uV} tuples: OPP library provides a set of helper functions to organize and query the OPP information. The library is located in drivers/opp/ directory and the header is located in include/linux/pm_opp.h. OPP library can be enabled by enabling -CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on -CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to -optionally boot at a certain OPP without needing cpufreq. +CONFIG_PM_OPP from power management menuconfig menu. Certain SoCs such as Texas +Instrument's OMAP framework allows to optionally boot at a certain OPP without +needing cpufreq. Typical usage of the OPP library is as follows:: @@ -75,8 +75,8 @@ operations until that OPP could be re-enabled if possible. OPP library facilitates this concept in its implementation. The following operational functions operate only on available opps: -opp_find_freq_{ceil, floor}, dev_pm_opp_get_voltage, dev_pm_opp_get_freq, -dev_pm_opp_get_opp_count +dev_pm_opp_find_freq_{ceil, floor}, dev_pm_opp_get_voltage, dev_pm_opp_get_freq, +dev_pm_opp_get_opp_count. dev_pm_opp_find_freq_exact is meant to be used to find the opp pointer which can then be used for dev_pm_opp_enable/disable functions to make an @@ -103,7 +103,7 @@ dev_pm_opp_add The OPP is defined using the frequency and voltage. Once added, the OPP is assumed to be available and control of its availability can be done with the dev_pm_opp_enable/disable functions. OPP library - internally stores and manages this information in the opp struct. + internally stores and manages this information in the dev_pm_opp struct. This function may be used by SoC framework to define a optimal list as per the demands of SoC usage environment. @@ -247,7 +247,7 @@ dev_pm_opp_disable 5. OPP Data Retrieval Functions =============================== Since OPP library abstracts away the OPP information, a set of functions to pull -information from the OPP structure is necessary. Once an OPP pointer is +information from the dev_pm_opp structure is necessary. Once an OPP pointer is retrieved using the search functions, the following functions can be used by SoC framework to retrieve the information represented inside the OPP layer. diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index d6bf84f061f4..65b86e487afe 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -265,6 +265,10 @@ defined in include/linux/pm.h: RPM_SUSPENDED, which means that each device is initially regarded by the PM core as 'suspended', regardless of its real hardware status + `enum rpm_status last_status;` + - the last runtime PM status of the device captured before disabling runtime + PM for it (invalid initially and when disable_depth is 0) + `unsigned int runtime_auto;` - if set, indicates that the user space has allowed the device driver to power manage the device at run time via the /sys/devices/.../power/control @@ -333,10 +337,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: `int pm_runtime_resume(struct device *dev);` - execute the subsystem-level resume callback for the device; returns 0 on - success, 1 if the device's runtime PM status was already 'active' or - error code on failure, where -EAGAIN means it may be safe to attempt to - resume the device again in future, but 'power.runtime_error' should be - checked additionally, and -EACCES means that 'power.disable_depth' is + success, 1 if the device's runtime PM status is already 'active' (also if + 'power.disable_depth' is nonzero, but the status was 'active' when it was + changing from 0 to 1) or error code on failure, where -EAGAIN means it may + be safe to attempt to resume the device again in future, but + 'power.runtime_error' should be checked additionally, and -EACCES means + that the callback could not be run, because 'power.disable_depth' was different from 0 `int pm_runtime_resume_and_get(struct device *dev);` diff --git a/MAINTAINERS b/MAINTAINERS index aeb2863450cb..198c6d0080f8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -994,6 +994,13 @@ S: Supported T: git https://gitlab.freedesktop.org/agd5f/linux.git F: drivers/gpu/drm/amd/pm/ +AMD PSTATE DRIVER +M: Huang Rui <ray.huang@amd.com> +L: linux-pm@vger.kernel.org +S: Supported +F: Documentation/admin-guide/pm/amd-pstate.rst +F: drivers/cpufreq/amd-pstate* + AMD PTDMA DRIVER M: Sanjay R Mehta <sanju.mehta@amd.com> L: dmaengine@vger.kernel.org diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 470299ee2fba..c7d2510e5a78 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -23,7 +23,7 @@ /* Replace task scheduler's default thermal pressure API */ #define arch_scale_thermal_pressure topology_get_thermal_pressure -#define arch_set_thermal_pressure topology_set_thermal_pressure +#define arch_update_thermal_pressure topology_update_thermal_pressure #else diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index ec2db3419c41..f386b90a79c8 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -32,7 +32,7 @@ void update_freq_counters_refs(void); /* Replace task scheduler's default thermal pressure API */ #define arch_scale_thermal_pressure topology_get_thermal_pressure -#define arch_set_thermal_pressure topology_set_thermal_pressure +#define arch_update_thermal_pressure topology_update_thermal_pressure #include <asm-generic/topology.h> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d5b5f2ab87a0..18de5f76f198 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -315,6 +315,7 @@ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 01e2650b9585..3faf0f97edb1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -486,6 +486,23 @@ #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +/* AMD Collaborative Processor Performance Control MSRs */ +#define MSR_AMD_CPPC_CAP1 0xc00102b0 +#define MSR_AMD_CPPC_ENABLE 0xc00102b1 +#define MSR_AMD_CPPC_CAP2 0xc00102b2 +#define MSR_AMD_CPPC_REQ 0xc00102b3 +#define MSR_AMD_CPPC_STATUS 0xc00102b4 + +#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff) +#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff) +#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff) +#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff) + +#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0) +#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8) +#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16) +#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24) + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index cc164777e661..2f0b6be8eaab 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -221,7 +221,7 @@ static inline void arch_set_max_freq_ratio(bool turbo_disabled) } #endif -#ifdef CONFIG_ACPI_CPPC_LIB +#if defined(CONFIG_ACPI_CPPC_LIB) && defined(CONFIG_SMP) void init_freq_invariance_cppc(void); #define init_freq_invariance_cppc init_freq_invariance_cppc #endif diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 3f85fcae450c..1e97f944b47d 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -139,8 +139,10 @@ static int __init acpi_sleep_setup(char *str) if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; #ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_hwsig", 8) == 0) + acpi_check_s4_hw_signature(1); if (strncmp(str, "s4_nohwsig", 10) == 0) - acpi_no_s4_hw_signature(); + acpi_check_s4_hw_signature(0); #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index f4dd73396f28..fbaf12e43f41 100644 --- a/arch/x86/kernel/cpu/intel_epb.c +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -16,6 +16,7 @@ #include <linux/syscore_ops.h> #include <linux/pm.h> +#include <asm/cpu_device_id.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -58,6 +59,22 @@ static DEFINE_PER_CPU(u8, saved_epb); #define EPB_SAVED 0x10ULL #define MAX_EPB EPB_MASK +enum energy_perf_value_index { + EPB_INDEX_PERFORMANCE, + EPB_INDEX_BALANCE_PERFORMANCE, + EPB_INDEX_NORMAL, + EPB_INDEX_BALANCE_POWERSAVE, + EPB_INDEX_POWERSAVE, +}; + +static u8 energ_perf_values[] = { + [EPB_INDEX_PERFORMANCE] = ENERGY_PERF_BIAS_PERFORMANCE, + [EPB_INDEX_BALANCE_PERFORMANCE] = ENERGY_PERF_BIAS_BALANCE_PERFORMANCE, + [EPB_INDEX_NORMAL] = ENERGY_PERF_BIAS_NORMAL, + [EPB_INDEX_BALANCE_POWERSAVE] = ENERGY_PERF_BIAS_BALANCE_POWERSAVE, + [EPB_INDEX_POWERSAVE] = ENERGY_PERF_BIAS_POWERSAVE, +}; + static int intel_epb_save(void) { u64 epb; @@ -90,7 +107,7 @@ static void intel_epb_restore(void) */ val = epb & EPB_MASK; if (val == ENERGY_PERF_BIAS_PERFORMANCE) { - val = ENERGY_PERF_BIAS_NORMAL; + val = energ_perf_values[EPB_INDEX_NORMAL]; pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); } } @@ -103,18 +120,11 @@ static struct syscore_ops intel_epb_syscore_ops = { }; static const char * const energy_perf_strings[] = { - "performance", - "balance-performance", - "normal", - "balance-power", - "power" -}; -static const u8 energ_perf_values[] = { - ENERGY_PERF_BIAS_PERFORMANCE, - ENERGY_PERF_BIAS_BALANCE_PERFORMANCE, - ENERGY_PERF_BIAS_NORMAL, - ENERGY_PERF_BIAS_BALANCE_POWERSAVE, - ENERGY_PERF_BIAS_POWERSAVE + [EPB_INDEX_PERFORMANCE] = "performance", + [EPB_INDEX_BALANCE_PERFORMANCE] = "balance-performance", + [EPB_INDEX_NORMAL] = "normal", + [EPB_INDEX_BALANCE_POWERSAVE] = "balance-power", + [EPB_INDEX_POWERSAVE] = "power", }; static ssize_t energy_perf_bias_show(struct device *dev, @@ -193,13 +203,22 @@ static int intel_epb_offline(unsigned int cpu) return 0; } +static const struct x86_cpu_id intel_epb_normal[] = { + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 7), + {} +}; + static __init int intel_epb_init(void) { + const struct x86_cpu_id *id = x86_match_cpu(intel_epb_normal); int ret; if (!boot_cpu_has(X86_FEATURE_EPB)) return -ENODEV; + if (id) + energ_perf_values[EPB_INDEX_NORMAL] = id->driver_data; + ret = cpuhp_setup_state(CPUHP_AP_X86_INTEL_EPB_ONLINE, "x86/intel/epb:online", intel_epb_online, intel_epb_offline); diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index e9ac5ea1dfc9..a9d2de403c0c 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -118,6 +118,8 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr); */ #define NUM_RETRIES 500ULL +#define OVER_16BTS_MASK ~0xFFFFULL + #define define_one_cppc_ro(_name) \ static struct kobj_attribute _name = \ __ATTR(_name, 0444, show_##_name, NULL) @@ -412,7 +414,7 @@ bool acpi_cpc_valid(void) struct cpc_desc *cpc_ptr; int cpu; - for_each_possible_cpu(cpu) { + for_each_present_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); if (!cpc_ptr) return false; @@ -730,9 +732,26 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) goto out_free; cpc_ptr->cpc_regs[i-2].sys_mem_vaddr = addr; } + } else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { + if (gas_t->access_width < 1 || gas_t->access_width > 3) { + /* + * 1 = 8-bit, 2 = 16-bit, and 3 = 32-bit. + * SystemIO doesn't implement 64-bit + * registers. + */ + pr_debug("Invalid access width %d for SystemIO register\n", + gas_t->access_width); + goto out_free; + } + if (gas_t->address & OVER_16BTS_MASK) { + /* SystemIO registers use 16-bit integer addresses */ + pr_debug("Invalid IO port %llu for SystemIO register\n", + gas_t->address); + goto out_free; + } } else { if (gas_t->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE || !cpc_ffh_supported()) { - /* Support only PCC ,SYS MEM and FFH type regs */ + /* Support only PCC, SystemMemory, SystemIO, and FFH type regs. */ pr_debug("Unsupported register type: %d\n", gas_t->space_id); goto out_free; } @@ -907,7 +926,21 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } *val = 0; - if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { + u32 width = 8 << (reg->access_width - 1); + acpi_status status; + + status = acpi_os_read_port((acpi_io_address)reg->address, + (u32 *)val, width); + if (ACPI_FAILURE(status)) { + pr_debug("Error: Failed to read SystemIO port %llx\n", + reg->address); + return -EFAULT; + } + + return 0; + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; @@ -946,7 +979,20 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; - if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { + u32 width = 8 << (reg->access_width - 1); + acpi_status status; + + status = acpi_os_write_port((acpi_io_address)reg->address, + (u32)val, width); + if (ACPI_FAILURE(status)) { + pr_debug("Error: Failed to write SystemIO port %llx\n", + reg->address); + return -EFAULT; + } + + return 0; + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; @@ -1214,6 +1260,51 @@ out_err: EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs); /** + * cppc_set_enable - Set to enable CPPC on the processor by writing the + * Continuous Performance Control package EnableRegister field. + * @cpu: CPU for which to enable CPPC register. + * @enable: 0 - disable, 1 - enable CPPC feature on the processor. + * + * Return: 0 for success, -ERRNO or -EIO otherwise. + */ +int cppc_set_enable(int cpu, bool enable) +{ + int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); + struct cpc_register_resource *enable_reg; + struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu); + struct cppc_pcc_data *pcc_ss_data = NULL; + int ret = -EINVAL; + + if (!cpc_desc) { + pr_debug("No CPC descriptor for CPU:%d\n", cpu); + return -EINVAL; + } + + enable_reg = &cpc_desc->cpc_regs[ENABLE]; + + if (CPC_IN_PCC(enable_reg)) { + + if (pcc_ss_id < 0) + return -EIO; + + ret = cpc_write(cpu, enable_reg, enable); + if (ret) + return ret; + + pcc_ss_data = pcc_data[pcc_ss_id]; + + down_write(&pcc_ss_data->pcc_lock); + /* after writing CPC, transfer the ownership of PCC to platfrom */ + ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE); + up_write(&pcc_ss_data->pcc_lock); + return ret; + } + + return cpc_write(cpu, enable_reg, enable); +} +EXPORT_SYMBOL_GPL(cppc_set_enable); + +/** * cppc_set_perf - Set a CPU's performance controls. * @cpu: CPU for which to set performance controls. * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4b8454f26ca1..a60ff5dfed3a 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -874,11 +874,11 @@ static inline void acpi_sleep_syscore_init(void) {} #ifdef CONFIG_HIBERNATION static unsigned long s4_hardware_signature; static struct acpi_table_facs *facs; -static bool nosigcheck; +static int sigcheck = -1; /* Default behaviour is just to warn */ -void __init acpi_no_s4_hw_signature(void) +void __init acpi_check_s4_hw_signature(int check) { - nosigcheck = true; + sigcheck = check; } static int acpi_hibernation_begin(pm_message_t stage) @@ -1004,12 +1004,28 @@ static void acpi_sleep_hibernate_setup(void) hibernation_set_ops(old_suspend_ordering ? &acpi_hibernation_ops_old : &acpi_hibernation_ops); sleep_states[ACPI_STATE_S4] = 1; - if (nosigcheck) + if (!sigcheck) return; acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs); - if (facs) + if (facs) { + /* + * s4_hardware_signature is the local variable which is just + * used to warn about mismatch after we're attempting to + * resume (in violation of the ACPI specification.) + */ s4_hardware_signature = facs->hardware_signature; + + if (sigcheck > 0) { + /* + * If we're actually obeying the ACPI specification + * then the signature is written out as part of the + * swsusp header, in order to allow the boot kernel + * to gracefully decline to resume. + */ + swsusp_hardware_signature = facs->hardware_signature; + } + } } #else /* !CONFIG_HIBERNATION */ static inline void acpi_sleep_hibernate_setup(void) {} diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index ff16a36a908b..976154140f0b 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -22,6 +22,7 @@ static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; +static DEFINE_PER_CPU(u32, freq_factor) = 1; static bool supports_scale_freq_counters(const struct cpumask *cpus) { @@ -155,15 +156,49 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity) DEFINE_PER_CPU(unsigned long, thermal_pressure); -void topology_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure) +/** + * topology_update_thermal_pressure() - Update thermal pressure for CPUs + * @cpus : The related CPUs for which capacity has been reduced + * @capped_freq : The maximum allowed frequency that CPUs can run at + * + * Update the value of thermal pressure for all @cpus in the mask. The + * cpumask should include all (online+offline) affected CPUs, to avoid + * operating on stale data when hot-plug is used for some CPUs. The + * @capped_freq reflects the currently allowed max CPUs frequency due to + * thermal capping. It might be also a boost frequency value, which is bigger + * than the internal 'freq_factor' max frequency. In such case the pressure + * value should simply be removed, since this is an indication that there is + * no thermal throttling. The @capped_freq must be provided in kHz. + */ +void topology_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_freq) { + unsigned long max_capacity, capacity, th_pressure; + u32 max_freq; int cpu; + cpu = cpumask_first(cpus); + max_capacity = arch_scale_cpu_capacity(cpu); + max_freq = per_cpu(freq_factor, cpu); + + /* Convert to MHz scale which is used in 'freq_factor' */ + capped_freq /= 1000; + + /* + * Handle properly the boost frequencies, which should simply clean + * the thermal pressure value. + */ + if (max_freq <= capped_freq) + capacity = max_capacity; + else + capacity = mult_frac(max_capacity, capped_freq, max_freq); + + th_pressure = max_capacity - capacity; + for_each_cpu(cpu, cpus) WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure); } -EXPORT_SYMBOL_GPL(topology_set_thermal_pressure); +EXPORT_SYMBOL_GPL(topology_update_thermal_pressure); static ssize_t cpu_capacity_show(struct device *dev, struct device_attribute *attr, @@ -217,7 +252,6 @@ static void update_topology_flags_workfn(struct work_struct *work) update_topology = 0; } -static DEFINE_PER_CPU(u32, freq_factor) = 1; static u32 *raw_capacity; static int free_raw_capacity(void) diff --git a/drivers/base/core.c b/drivers/base/core.c index fd034d742447..b191bd17de89 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -485,8 +485,7 @@ static void device_link_release_fn(struct work_struct *work) /* Ensure that all references to the link object have been dropped. */ device_link_synchronize_removal(); - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); + pm_runtime_release_supplier(link, true); put_device(link->consumer); put_device(link->supplier); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index d504cd4ab3cb..2f3cce17219b 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -305,19 +305,40 @@ static int rpm_get_suppliers(struct device *dev) return 0; } +/** + * pm_runtime_release_supplier - Drop references to device link's supplier. + * @link: Target device link. + * @check_idle: Whether or not to check if the supplier device is idle. + * + * Drop all runtime PM references associated with @link to its supplier device + * and if @check_idle is set, check if that device is idle (and so it can be + * suspended). + */ +void pm_runtime_release_supplier(struct device_link *link, bool check_idle) +{ + struct device *supplier = link->supplier; + + /* + * The additional power.usage_count check is a safety net in case + * the rpm_active refcount becomes saturated, in which case + * refcount_dec_not_one() would return true forever, but it is not + * strictly necessary. + */ + while (refcount_dec_not_one(&link->rpm_active) && + atomic_read(&supplier->power.usage_count) > 0) + pm_runtime_put_noidle(supplier); + + if (check_idle) + pm_request_idle(supplier); +} + static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, - device_links_read_lock_held()) { - - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put_noidle(link->supplier); - - if (try_to_suspend) - pm_request_idle(link->supplier); - } + device_links_read_lock_held()) + pm_runtime_release_supplier(link, try_to_suspend); } static void rpm_put_suppliers(struct device *dev) @@ -742,13 +763,15 @@ static int rpm_resume(struct device *dev, int rpmflags) trace_rpm_resume_rcuidle(dev, rpmflags); repeat: - if (dev->power.runtime_error) + if (dev->power.runtime_error) { retval = -EINVAL; - else if (dev->power.disable_depth == 1 && dev->power.is_suspended - && dev->power.runtime_status == RPM_ACTIVE) - retval = 1; - else if (dev->power.disable_depth > 0) - retval = -EACCES; + } else if (dev->power.disable_depth > 0) { + if (dev->power.runtime_status == RPM_ACTIVE && + dev->power.last_status == RPM_ACTIVE) + retval = 1; + else + retval = -EACCES; + } if (retval) goto out; @@ -1410,8 +1433,10 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); - if (!dev->power.disable_depth++) + if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); + dev->power.last_status = dev->power.runtime_status; + } out: spin_unlock_irq(&dev->power.lock); @@ -1428,23 +1453,23 @@ void pm_runtime_enable(struct device *dev) spin_lock_irqsave(&dev->power.lock, flags); - if (dev->power.disable_depth > 0) { - dev->power.disable_depth--; - - /* About to enable runtime pm, set accounting_timestamp to now */ - if (!dev->power.disable_depth) - dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); - } else { + if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); + goto out; } - WARN(!dev->power.disable_depth && - dev->power.runtime_status == RPM_SUSPENDED && - !dev->power.ignore_children && - atomic_read(&dev->power.child_count) > 0, - "Enabling runtime PM for inactive device (%s) with active children\n", - dev_name(dev)); + if (--dev->power.disable_depth > 0) + goto out; + + dev->power.last_status = RPM_INVALID; + dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); + + if (dev->power.runtime_status == RPM_SUSPENDED && + !dev->power.ignore_children && + atomic_read(&dev->power.child_count) > 0) + dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); +out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); @@ -1640,6 +1665,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; + dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; @@ -1722,8 +1748,6 @@ void pm_runtime_get_suppliers(struct device *dev) void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; - unsigned long flags; - bool put; int idx; idx = device_links_read_lock(); @@ -1731,11 +1755,17 @@ void pm_runtime_put_suppliers(struct device *dev) list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->supplier_preactivated) { + bool put; + link->supplier_preactivated = false; - spin_lock_irqsave(&dev->power.lock, flags); + + spin_lock_irq(&dev->power.lock); + put = pm_runtime_status_suspended(dev) && refcount_dec_not_one(&link->rpm_active); - spin_unlock_irqrestore(&dev->power.lock, flags); + + spin_unlock_irq(&dev->power.lock); + if (put) pm_runtime_put(link->supplier); } @@ -1772,9 +1802,7 @@ void pm_runtime_drop_link(struct device_link *link) return; pm_runtime_drop_link_count(link->consumer); - - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); + pm_runtime_release_supplier(link, true); } static bool pm_runtime_need_not_resume(struct device *dev) diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 92701a18bdd9..55516043b656 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -34,6 +34,23 @@ config X86_PCC_CPUFREQ If in doubt, say N. +config X86_AMD_PSTATE + tristate "AMD Processor P-State driver" + depends on X86 && ACPI + select ACPI_PROCESSOR + select ACPI_CPPC_LIB if X86_64 + select CPU_FREQ_GOV_SCHEDUTIL if SMP + help + This driver adds a CPUFreq driver which utilizes a fine grain + processor performance frequency control range instead of legacy + performance levels. _CPC needs to be present in the ACPI tables + of the system. + + For details, take a look at: + <file:Documentation/admin-guide/pm/amd-pstate.rst>. + + If in doubt, say N. + config X86_ACPI_CPUFREQ tristate "ACPI Processor P-States driver" depends on ACPI_PROCESSOR diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 48ee5859030c..285de70af877 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -17,6 +17,10 @@ obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET) += cpufreq_governor_attr_set.o obj-$(CONFIG_CPUFREQ_DT) += cpufreq-dt.o obj-$(CONFIG_CPUFREQ_DT_PLATDEV) += cpufreq-dt-platdev.o +# Traces +CFLAGS_amd-pstate-trace.o := -I$(src) +amd_pstate-y := amd-pstate.o amd-pstate-trace.o + ################################################################################## # x86 drivers. # Link order matters. K8 is preferred to ACPI because of firmware bugs in early @@ -25,6 +29,7 @@ obj-$(CONFIG_CPUFREQ_DT_PLATDEV) += cpufreq-dt-platdev.o # speedstep-* is preferred over p4-clockmod. obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_AMD_PSTATE) += amd_pstate.o obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o obj-$(CONFIG_X86_PCC_CPUFREQ) += pcc-cpufreq.o obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o diff --git a/drivers/cpufreq/amd-pstate-trace.c b/drivers/cpufreq/amd-pstate-trace.c new file mode 100644 index 000000000000..891b696dcd69 --- /dev/null +++ b/drivers/cpufreq/amd-pstate-trace.c @@ -0,0 +1,2 @@ +#define CREATE_TRACE_POINTS +#include "amd-pstate-trace.h" diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h new file mode 100644 index 000000000000..647505957d4f --- /dev/null +++ b/drivers/cpufreq/amd-pstate-trace.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * amd-pstate-trace.h - AMD Processor P-state Frequency Driver Tracer + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. All Rights Reserved. + * + * Author: Huang Rui <ray.huang@amd.com> + */ + +#if !defined(_AMD_PSTATE_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _AMD_PSTATE_TRACE_H + +#include <linux/cpufreq.h> +#include <linux/tracepoint.h> +#include <linux/trace_events.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM amd_cpu + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE amd-pstate-trace + +#define TPS(x) tracepoint_string(x) + +TRACE_EVENT(amd_pstate_perf, + + TP_PROTO(unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity, + unsigned int cpu_id, + bool changed, + bool fast_switch + ), + + TP_ARGS(min_perf, + target_perf, + capacity, + cpu_id, + changed, + fast_switch + ), + + TP_STRUCT__entry( + __field(unsigned long, min_perf) + __field(unsigned long, target_perf) + __field(unsigned long, capacity) + __field(unsigned int, cpu_id) + __field(bool, changed) + __field(bool, fast_switch) + ), + + TP_fast_assign( + __entry->min_perf = min_perf; + __entry->target_perf = target_perf; + __entry->capacity = capacity; + __entry->cpu_id = cpu_id; + __entry->changed = changed; + __entry->fast_switch = fast_switch; + ), + + TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu cpu_id=%u changed=%s fast_switch=%s", + (unsigned long)__entry->min_perf, + (unsigned long)__entry->target_perf, + (unsigned long)__entry->capacity, + (unsigned int)__entry->cpu_id, + (__entry->changed) ? "true" : "false", + (__entry->fast_switch) ? "true" : "false" + ) +); + +#endif /* _AMD_PSTATE_TRACE_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . + +#include <trace/define_trace.h> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c new file mode 100644 index 000000000000..9ce75ed11f8e --- /dev/null +++ b/drivers/cpufreq/amd-pstate.c @@ -0,0 +1,645 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * amd-pstate.c - AMD Processor P-state Frequency Driver + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. All Rights Reserved. + * + * Author: Huang Rui <ray.huang@amd.com> + * + * AMD P-State introduces a new CPU performance scaling design for AMD + * processors using the ACPI Collaborative Performance and Power Control (CPPC) + * feature which works with the AMD SMU firmware providing a finer grained + * frequency control range. It is to replace the legacy ACPI P-States control, + * allows a flexible, low-latency interface for the Linux kernel to directly + * communicate the performance hints to hardware. + * + * AMD P-State is supported on recent AMD Zen base CPU series include some of + * Zen2 and Zen3 processors. _CPC needs to be present in the ACPI tables of AMD + * P-State supported system. And there are two types of hardware implementations + * for AMD P-State: 1) Full MSR Solution and 2) Shared Memory Solution. + * X86_FEATURE_CPPC CPU feature flag is used to distinguish the different types. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/sched.h> +#include <linux/cpufreq.h> +#include <linux/compiler.h> +#include <linux/dmi.h> +#include <linux/slab.h> +#include <linux/acpi.h> +#include <linux/io.h> +#include <linux/delay.h> +#include <linux/uaccess.h> +#include <linux/static_call.h> + +#include <acpi/processor.h> +#include <acpi/cppc_acpi.h> + +#include <asm/msr.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> +#include <asm/cpu_device_id.h> +#include "amd-pstate-trace.h" + +#define AMD_PSTATE_TRANSITION_LATENCY 0x20000 +#define AMD_PSTATE_TRANSITION_DELAY 500 + +/* + * TODO: We need more time to fine tune processors with shared memory solution + * with community together. + * + * There are some performance drops on the CPU benchmarks which reports from + * Suse. We are co-working with them to fine tune the shared memory solution. So + * we disable it by default to go acpi-cpufreq on these processors and add a + * module parameter to be able to enable it manually for debugging. + */ +static bool shared_mem = false; +module_param(shared_mem, bool, 0444); +MODULE_PARM_DESC(shared_mem, + "enable amd-pstate on processors with shared memory solution (false = disabled (default), true = enabled)"); + +static struct cpufreq_driver amd_pstate_driver; + +/** + * struct amd_cpudata - private CPU data for AMD P-State + * @cpu: CPU number + * @req: constraint request to apply + * @cppc_req_cached: cached performance request hints + * @highest_perf: the maximum performance an individual processor may reach, + * assuming ideal conditions + * @nominal_perf: the maximum sustained performance level of the processor, + * assuming ideal operating conditions + * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power + * savings are achieved + * @lowest_perf: the absolute lowest performance level of the processor + * @max_freq: the frequency that mapped to highest_perf + * @min_freq: the frequency that mapped to lowest_perf + * @nominal_freq: the frequency that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf + * @boost_supported: check whether the Processor or SBIOS supports boost mode + * + * The amd_cpudata is key private data for each CPU thread in AMD P-State, and + * represents all the attributes and goals that AMD P-State requests at runtime. + */ +struct amd_cpudata { + int cpu; + + struct freq_qos_request req[2]; + u64 cppc_req_cached; + + u32 highest_perf; + u32 nominal_perf; + u32 lowest_nonlinear_perf; + u32 lowest_perf; + + u32 max_freq; + u32 min_freq; + u32 nominal_freq; + u32 lowest_nonlinear_freq; + + bool boost_supported; +}; + +static inline int pstate_enable(bool enable) +{ + return wrmsrl_safe(MSR_AMD_CPPC_ENABLE, enable); +} + +static int cppc_enable(bool enable) +{ + int cpu, ret = 0; + + for_each_present_cpu(cpu) { + ret = cppc_set_enable(cpu, enable); + if (ret) + return ret; + } + + return ret; +} + +DEFINE_STATIC_CALL(amd_pstate_enable, pstate_enable); + +static inline int amd_pstate_enable(bool enable) +{ + return static_call(amd_pstate_enable)(enable); +} + +static int pstate_init_perf(struct amd_cpudata *cpudata) +{ + u64 cap1; + + int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, + &cap1); + if (ret) + return ret; + + /* + * TODO: Introduce AMD specific power feature. + * + * CPPC entry doesn't indicate the highest performance in some ASICs. + */ + WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf()); + + WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); + WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); + WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); + + return 0; +} + +static int cppc_init_perf(struct amd_cpudata *cpudata) +{ + struct cppc_perf_caps cppc_perf; + + int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf()); + + WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); + WRITE_ONCE(cpudata->lowest_nonlinear_perf, + cppc_perf.lowest_nonlinear_perf); + WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); + + return 0; +} + +DEFINE_STATIC_CALL(amd_pstate_init_perf, pstate_init_perf); + +static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata) +{ + return static_call(amd_pstate_init_perf)(cpudata); +} + +static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, bool fast_switch) +{ + if (fast_switch) + wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached)); + else + wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, + READ_ONCE(cpudata->cppc_req_cached)); +} + +static void cppc_update_perf(struct amd_cpudata *cpudata, + u32 min_perf, u32 des_perf, + u32 max_perf, bool fast_switch) +{ + struct cppc_perf_ctrls perf_ctrls; + + perf_ctrls.max_perf = max_perf; + perf_ctrls.min_perf = min_perf; + perf_ctrls.desired_perf = des_perf; + + cppc_set_perf(cpudata->cpu, &perf_ctrls); +} + +DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf); + +static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, + u32 min_perf, u32 des_perf, + u32 max_perf, bool fast_switch) +{ + static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, + max_perf, fast_switch); +} + +static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, bool fast_switch) +{ + u64 prev = READ_ONCE(cpudata->cppc_req_cached); + u64 value = prev; + + value &= ~AMD_CPPC_MIN_PERF(~0L); + value |= AMD_CPPC_MIN_PERF(min_perf); + + value &= ~AMD_CPPC_DES_PERF(~0L); + value |= AMD_CPPC_DES_PERF(des_perf); + + value &= ~AMD_CPPC_MAX_PERF(~0L); + value |= AMD_CPPC_MAX_PERF(max_perf); + + trace_amd_pstate_perf(min_perf, des_perf, max_perf, + cpudata->cpu, (value != prev), fast_switch); + + if (value == prev) + return; + + WRITE_ONCE(cpudata->cppc_req_cached, value); + + amd_pstate_update_perf(cpudata, min_perf, des_perf, + max_perf, fast_switch); +} + +static int amd_pstate_verify(struct cpufreq_policy_data *policy) +{ + cpufreq_verify_within_cpu_limits(policy); + + return 0; +} + +static int amd_pstate_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + struct cpufreq_freqs freqs; + struct amd_cpudata *cpudata = policy->driver_data; + unsigned long max_perf, min_perf, des_perf, cap_perf; + + if (!cpudata->max_freq) + return -ENODEV; + + cap_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + max_perf = cap_perf; + + freqs.old = policy->cur; + freqs.new = target_freq; + + des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf, + cpudata->max_freq); + + cpufreq_freq_transition_begin(policy, &freqs); + amd_pstate_update(cpudata, min_perf, des_perf, + max_perf, false); + cpufreq_freq_transition_end(policy, &freqs, false); + + return 0; +} + +static void amd_pstate_adjust_perf(unsigned int cpu, + unsigned long _min_perf, + unsigned long target_perf, + unsigned long capacity) +{ + unsigned long max_perf, min_perf, des_perf, + cap_perf, lowest_nonlinear_perf; + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct amd_cpudata *cpudata = policy->driver_data; + + cap_perf = READ_ONCE(cpudata->highest_perf); + lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + + des_perf = cap_perf; + if (target_perf < capacity) + des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); + + min_perf = READ_ONCE(cpudata->highest_perf); + if (_min_perf < capacity) + min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); + + if (min_perf < lowest_nonlinear_perf) + min_perf = lowest_nonlinear_perf; + + max_perf = cap_perf; + if (max_perf < min_perf) + max_perf = min_perf; + + des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); + + amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true); +} + +static int amd_get_min_freq(struct amd_cpudata *cpudata) +{ + struct cppc_perf_caps cppc_perf; + + int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + /* Switch to khz */ + return cppc_perf.lowest_freq * 1000; +} + +static int amd_get_max_freq(struct amd_cpudata *cpudata) +{ + struct cppc_perf_caps cppc_perf; + u32 max_perf, max_freq, nominal_freq, nominal_perf; + u64 boost_ratio; + + int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + nominal_freq = cppc_perf.nominal_freq; + nominal_perf = READ_ONCE(cpudata->nominal_perf); + max_perf = READ_ONCE(cpudata->highest_perf); + + boost_ratio = div_u64(max_perf << SCHED_CAPACITY_SHIFT, + nominal_perf); + + max_freq = nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT; + + /* Switch to khz */ + return max_freq * 1000; +} + +static int amd_get_nominal_freq(struct amd_cpudata *cpudata) +{ + struct cppc_perf_caps cppc_perf; + + int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + /* Switch to khz */ + return cppc_perf.nominal_freq * 1000; +} + +static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata) +{ + struct cppc_perf_caps cppc_perf; + u32 lowest_nonlinear_freq, lowest_nonlinear_perf, + nominal_freq, nominal_perf; + u64 lowest_nonlinear_ratio; + + int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + nominal_freq = cppc_perf.nominal_freq; + nominal_perf = READ_ONCE(cpudata->nominal_perf); + + lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf; + + lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, + nominal_perf); + + lowest_nonlinear_freq = nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT; + + /* Switch to khz */ + return lowest_nonlinear_freq * 1000; +} + +static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) +{ + struct amd_cpudata *cpudata = policy->driver_data; + int ret; + + if (!cpudata->boost_supported) { + pr_err("Boost mode is not supported by this processor or SBIOS\n"); + return -EINVAL; + } + + if (state) + policy->cpuinfo.max_freq = cpudata->max_freq; + else + policy->cpuinfo.max_freq = cpudata->nominal_freq; + + policy->max = policy->cpuinfo.max_freq; + + ret = freq_qos_update_request(&cpudata->req[1], + policy->cpuinfo.max_freq); + if (ret < 0) + return ret; + + return 0; +} + +static void amd_pstate_boost_init(struct amd_cpudata *cpudata) +{ + u32 highest_perf, nominal_perf; + + highest_perf = READ_ONCE(cpudata->highest_perf); + nominal_perf = READ_ONCE(cpudata->nominal_perf); + + if (highest_perf <= nominal_perf) + return; + + cpudata->boost_supported = true; + amd_pstate_driver.boost_enabled = true; +} + +static int amd_pstate_cpu_init(struct cpufreq_policy *policy) +{ + int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + struct device *dev; + struct amd_cpudata *cpudata; + + dev = get_cpu_device(policy->cpu); + if (!dev) + return -ENODEV; + + cpudata = kzalloc(sizeof(*cpudata), GFP_KERNEL); + if (!cpudata) + return -ENOMEM; + + cpudata->cpu = policy->cpu; + + ret = amd_pstate_init_perf(cpudata); + if (ret) + goto free_cpudata1; + + min_freq = amd_get_min_freq(cpudata); + max_freq = amd_get_max_freq(cpudata); + nominal_freq = amd_get_nominal_freq(cpudata); + lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); + + if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { + dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", + min_freq, max_freq); + ret = -EINVAL; + goto free_cpudata1; + } + + policy->cpuinfo.transition_latency = AMD_PSTATE_TRANSITION_LATENCY; + policy->transition_delay_us = AMD_PSTATE_TRANSITION_DELAY; + + policy->min = min_freq; + policy->max = max_freq; + + policy->cpuinfo.min_freq = min_freq; + policy->cpuinfo.max_freq = max_freq; + + /* It will be updated by governor */ + policy->cur = policy->cpuinfo.min_freq; + + if (boot_cpu_has(X86_FEATURE_CPPC)) + policy->fast_switch_possible = true; + + ret = freq_qos_add_request(&policy->constraints, &cpudata->req[0], + FREQ_QOS_MIN, policy->cpuinfo.min_freq); + if (ret < 0) { + dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret); + goto free_cpudata1; + } + + ret = freq_qos_add_request(&policy->constraints, &cpudata->req[1], + FREQ_QOS_MAX, policy->cpuinfo.max_freq); + if (ret < 0) { + dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret); + goto free_cpudata2; + } + + /* Initial processor data capability frequencies */ + cpudata->max_freq = max_freq; + cpudata->min_freq = min_freq; + cpudata->nominal_freq = nominal_freq; + cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; + + policy->driver_data = cpudata; + + amd_pstate_boost_init(cpudata); + + return 0; + +free_cpudata2: + freq_qos_remove_request(&cpudata->req[0]); +free_cpudata1: + kfree(cpudata); + return ret; +} + +static int amd_pstate_cpu_exit(struct cpufreq_policy *policy) +{ + struct amd_cpudata *cpudata; + + cpudata = policy->driver_data; + + freq_qos_remove_request(&cpudata->req[1]); + freq_qos_remove_request(&cpudata->req[0]); + kfree(cpudata); + + return 0; +} + +/* Sysfs attributes */ + +/* + * This frequency is to indicate the maximum hardware frequency. + * If boost is not active but supported, the frequency will be larger than the + * one in cpuinfo. + */ +static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy, + char *buf) +{ + int max_freq; + struct amd_cpudata *cpudata; + + cpudata = policy->driver_data; + + max_freq = amd_get_max_freq(cpudata); + if (max_freq < 0) + return max_freq; + + return sprintf(&buf[0], "%u\n", max_freq); +} + +static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *policy, + char *buf) +{ + int freq; + struct amd_cpudata *cpudata; + + cpudata = policy->driver_data; + + freq = amd_get_lowest_nonlinear_freq(cpudata); + if (freq < 0) + return freq; + + return sprintf(&buf[0], "%u\n", freq); +} + +/* + * In some of ASICs, the highest_perf is not the one in the _CPC table, so we + * need to expose it to sysfs. + */ +static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, + char *buf) +{ + u32 perf; + struct amd_cpudata *cpudata = policy->driver_data; + + perf = READ_ONCE(cpudata->highest_perf); + + return sprintf(&buf[0], "%u\n", perf); +} + +cpufreq_freq_attr_ro(amd_pstate_max_freq); +cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); + +cpufreq_freq_attr_ro(amd_pstate_highest_perf); + +static struct freq_attr *amd_pstate_attr[] = { + &amd_pstate_max_freq, + &amd_pstate_lowest_nonlinear_freq, + &amd_pstate_highest_perf, + NULL, +}; + +static struct cpufreq_driver amd_pstate_driver = { + .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS, + .verify = amd_pstate_verify, + .target = amd_pstate_target, + .init = amd_pstate_cpu_init, + .exit = amd_pstate_cpu_exit, + .set_boost = amd_pstate_set_boost, + .name = "amd-pstate", + .attr = amd_pstate_attr, +}; + +static int __init amd_pstate_init(void) +{ + int ret; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return -ENODEV; + + if (!acpi_cpc_valid()) { + pr_debug("the _CPC object is not present in SBIOS\n"); + return -ENODEV; + } + + /* don't keep reloading if cpufreq_driver exists */ + if (cpufreq_get_current_driver()) + return -EEXIST; + + /* capability check */ + if (boot_cpu_has(X86_FEATURE_CPPC)) { + pr_debug("AMD CPPC MSR based functionality is supported\n"); + amd_pstate_driver.adjust_perf = amd_pstate_adjust_perf; + } else if (shared_mem) { + static_call_update(amd_pstate_enable, cppc_enable); + static_call_update(amd_pstate_init_perf, cppc_init_perf); + static_call_update(amd_pstate_update_perf, cppc_update_perf); + } else { + pr_info("This processor supports shared memory solution, you can enable it with amd_pstate.shared_mem=1\n"); + return -ENODEV; + } + + /* enable amd pstate feature */ + ret = amd_pstate_enable(true); + if (ret) { + pr_err("failed to enable amd-pstate with return %d\n", ret); + return ret; + } + + ret = cpufreq_register_driver(&amd_pstate_driver); + if (ret) + pr_err("failed to register amd_pstate_driver with return %d\n", + ret); + + return ret; +} + +static void __exit amd_pstate_exit(void) +{ + cpufreq_unregister_driver(&amd_pstate_driver); + + amd_pstate_enable(false); +} + +module_init(amd_pstate_init); +module_exit(amd_pstate_exit); + +MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>"); +MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 096c3848fa41..b8d95536ee22 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -924,7 +924,7 @@ cpufreq_freq_attr_rw(scaling_max_freq); cpufreq_freq_attr_rw(scaling_governor); cpufreq_freq_attr_rw(scaling_setspeed); -static struct attribute *default_attrs[] = { +static struct attribute *cpufreq_attrs[] = { &cpuinfo_min_freq.attr, &cpuinfo_max_freq.attr, &cpuinfo_transition_latency.attr, @@ -938,6 +938,7 @@ static struct attribute *default_attrs[] = { &scaling_setspeed.attr, NULL }; +ATTRIBUTE_GROUPS(cpufreq); #define to_policy(k) container_of(k, struct cpufreq_policy, kobj) #define to_attr(a) container_of(a, struct freq_attr, attr) @@ -1000,7 +1001,7 @@ static const struct sysfs_ops sysfs_ops = { static struct kobj_type ktype_cpufreq = { .sysfs_ops = &sysfs_ops, - .default_attrs = default_attrs, + .default_groups = cpufreq_groups, .release = cpufreq_sysfs_release, }; @@ -1403,7 +1404,7 @@ static int cpufreq_online(unsigned int cpu) ret = freq_qos_add_request(&policy->constraints, policy->min_freq_req, FREQ_QOS_MIN, - policy->min); + FREQ_QOS_MIN_DEFAULT_VALUE); if (ret < 0) { /* * So we don't call freq_qos_remove_request() for an @@ -1423,7 +1424,7 @@ static int cpufreq_online(unsigned int cpu) ret = freq_qos_add_request(&policy->constraints, policy->max_freq_req, FREQ_QOS_MAX, - policy->max); + FREQ_QOS_MAX_DEFAULT_VALUE); if (ret < 0) { policy->max_freq_req = NULL; goto out_destroy_policy; diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 0879ec3c170c..08515f7e515f 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -257,7 +257,7 @@ gov_attr_rw(ignore_nice_load); gov_attr_rw(down_threshold); gov_attr_rw(freq_step); -static struct attribute *cs_attributes[] = { +static struct attribute *cs_attrs[] = { &sampling_rate.attr, &sampling_down_factor.attr, &up_threshold.attr, @@ -266,6 +266,7 @@ static struct attribute *cs_attributes[] = { &freq_step.attr, NULL }; +ATTRIBUTE_GROUPS(cs); /************************** sysfs end ************************/ @@ -315,7 +316,7 @@ static void cs_start(struct cpufreq_policy *policy) static struct dbs_governor cs_governor = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"), - .kobj_type = { .default_attrs = cs_attributes }, + .kobj_type = { .default_groups = cs_groups }, .gov_dbs_update = cs_dbs_update, .alloc = cs_alloc, .free = cs_free, diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 3b8f924771b4..6a41ea4729b8 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -328,7 +328,7 @@ gov_attr_rw(sampling_down_factor); gov_attr_rw(ignore_nice_load); gov_attr_rw(powersave_bias); -static struct attribute *od_attributes[] = { +static struct attribute *od_attrs[] = { &sampling_rate.attr, &up_threshold.attr, &sampling_down_factor.attr, @@ -337,6 +337,7 @@ static struct attribute *od_attributes[] = { &io_is_busy.attr, NULL }; +ATTRIBUTE_GROUPS(od); /************************** sysfs end ************************/ @@ -401,7 +402,7 @@ static struct od_ops od_ops = { static struct dbs_governor od_dbs_gov = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("ondemand"), - .kobj_type = { .default_attrs = od_attributes }, + .kobj_type = { .default_groups = od_groups }, .gov_dbs_update = od_dbs_update, .alloc = od_alloc, .free = od_free, diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index dec2a5649ac1..bc7f7e6759bd 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -664,19 +664,29 @@ static int intel_pstate_set_epb(int cpu, s16 pref) * 3 balance_power * 4 power */ + +enum energy_perf_value_index { + EPP_INDEX_DEFAULT = 0, + EPP_INDEX_PERFORMANCE, + EPP_INDEX_BALANCE_PERFORMANCE, + EPP_INDEX_BALANCE_POWERSAVE, + EPP_INDEX_POWERSAVE, +}; + static const char * const energy_perf_strings[] = { - "default", - "performance", - "balance_performance", - "balance_power", - "power", + [EPP_INDEX_DEFAULT] = "default", + [EPP_INDEX_PERFORMANCE] = "performance", + [EPP_INDEX_BALANCE_PERFORMANCE] = "balance_performance", + [EPP_INDEX_BALANCE_POWERSAVE] = "balance_power", + [EPP_INDEX_POWERSAVE] = "power", NULL }; -static const unsigned int epp_values[] = { - HWP_EPP_PERFORMANCE, - HWP_EPP_BALANCE_PERFORMANCE, - HWP_EPP_BALANCE_POWERSAVE, - HWP_EPP_POWERSAVE +static unsigned int epp_values[] = { + [EPP_INDEX_DEFAULT] = 0, /* Unused index */ + [EPP_INDEX_PERFORMANCE] = HWP_EPP_PERFORMANCE, + [EPP_INDEX_BALANCE_PERFORMANCE] = HWP_EPP_BALANCE_PERFORMANCE, + [EPP_INDEX_BALANCE_POWERSAVE] = HWP_EPP_BALANCE_POWERSAVE, + [EPP_INDEX_POWERSAVE] = HWP_EPP_POWERSAVE, }; static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw_epp) @@ -690,14 +700,14 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw return epp; if (boot_cpu_has(X86_FEATURE_HWP_EPP)) { - if (epp == HWP_EPP_PERFORMANCE) - return 1; - if (epp == HWP_EPP_BALANCE_PERFORMANCE) - return 2; - if (epp == HWP_EPP_BALANCE_POWERSAVE) - return 3; - if (epp == HWP_EPP_POWERSAVE) - return 4; + if (epp == epp_values[EPP_INDEX_PERFORMANCE]) + return EPP_INDEX_PERFORMANCE; + if (epp == epp_values[EPP_INDEX_BALANCE_PERFORMANCE]) + return EPP_INDEX_BALANCE_PERFORMANCE; + if (epp == epp_values[EPP_INDEX_BALANCE_POWERSAVE]) + return EPP_INDEX_BALANCE_POWERSAVE; + if (epp == epp_values[EPP_INDEX_POWERSAVE]) + return EPP_INDEX_POWERSAVE; *raw_epp = epp; return 0; } else if (boot_cpu_has(X86_FEATURE_EPB)) { @@ -757,7 +767,7 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, if (use_raw) epp = raw_epp; else if (epp == -EINVAL) - epp = epp_values[pref_index - 1]; + epp = epp_values[pref_index]; /* * To avoid confusion, refuse to set EPP to any values different @@ -843,7 +853,7 @@ static ssize_t store_energy_performance_preference( * upfront. */ if (!raw) - epp = ret ? epp_values[ret - 1] : cpu->epp_default; + epp = ret ? epp_values[ret] : cpu->epp_default; if (cpu->epp_cached != epp) { int err; @@ -1124,19 +1134,22 @@ static void intel_pstate_update_policies(void) cpufreq_update_policy(cpu); } +static void __intel_pstate_update_max_freq(struct cpudata *cpudata, + struct cpufreq_policy *policy) +{ + policy->cpuinfo.max_freq = global.turbo_disabled_mf ? + cpudata->pstate.max_freq : cpudata->pstate.turbo_freq; + refresh_frequency_limits(policy); +} + static void intel_pstate_update_max_freq(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); - struct cpudata *cpudata; if (!policy) return; - cpudata = all_cpu_data[cpu]; - policy->cpuinfo.max_freq = global.turbo_disabled_mf ? - cpudata->pstate.max_freq : cpudata->pstate.turbo_freq; - - refresh_frequency_limits(policy); + __intel_pstate_update_max_freq(all_cpu_data[cpu], policy); cpufreq_cpu_release(policy); } @@ -1584,8 +1597,15 @@ static void intel_pstate_notify_work(struct work_struct *work) { struct cpudata *cpudata = container_of(to_delayed_work(work), struct cpudata, hwp_notify_work); + struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpudata->cpu); + + if (policy) { + intel_pstate_get_hwp_cap(cpudata); + __intel_pstate_update_max_freq(cpudata, policy); + + cpufreq_cpu_release(policy); + } - cpufreq_update_policy(cpudata->cpu); wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } @@ -1679,10 +1699,18 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); - if (cpudata->epp_default == -EINVAL) - cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); intel_pstate_enable_hwp_interrupt(cpudata); + + if (cpudata->epp_default >= 0) + return; + + if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE) { + cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); + } else { + cpudata->epp_default = epp_values[EPP_INDEX_BALANCE_PERFORMANCE]; + intel_pstate_set_epp(cpudata, cpudata->epp_default); + } } static int atom_get_min_pstate(void) @@ -2486,18 +2514,14 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu, * HWP needs some special consideration, because HWP_REQUEST uses * abstract values to represent performance rather than pure ratios. */ - if (hwp_active) { - intel_pstate_get_hwp_cap(cpu); + if (hwp_active && cpu->pstate.scaling != perf_ctl_scaling) { + int scaling = cpu->pstate.scaling; + int freq; - if (cpu->pstate.scaling != perf_ctl_scaling) { - int scaling = cpu->pstate.scaling; - int freq; - - freq = max_policy_perf * perf_ctl_scaling; - max_policy_perf = DIV_ROUND_UP(freq, scaling); - freq = min_policy_perf * perf_ctl_scaling; - min_policy_perf = DIV_ROUND_UP(freq, scaling); - } + freq = max_policy_perf * perf_ctl_scaling; + max_policy_perf = DIV_ROUND_UP(freq, scaling); + freq = min_policy_perf * perf_ctl_scaling; + min_policy_perf = DIV_ROUND_UP(freq, scaling); } pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n", @@ -3349,6 +3373,16 @@ static bool intel_pstate_hwp_is_enabled(void) return !!(value & 0x1); } +static const struct x86_cpu_id intel_epp_balance_perf[] = { + /* + * Set EPP value as 102, this is the max suggested EPP + * which can result in one core turbo frequency for + * AlderLake Mobile CPUs. + */ + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 102), + {} +}; + static int __init intel_pstate_init(void) { static struct cpudata **_all_cpu_data; @@ -3438,6 +3472,13 @@ hwp_cpu_matched: intel_pstate_sysfs_expose_params(); + if (hwp_active) { + const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf); + + if (id) + epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data; + } + mutex_lock(&intel_pstate_driver_lock); rc = intel_pstate_register_driver(default_driver); mutex_unlock(&intel_pstate_driver_lock); diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index 8ddbd0c5ce37..0a94c56ddad2 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -36,6 +36,8 @@ enum { struct mtk_cpufreq_data { struct cpufreq_frequency_table *table; void __iomem *reg_bases[REG_ARRAY_SIZE]; + struct resource *res; + void __iomem *base; int nr_opp; }; @@ -156,6 +158,7 @@ static int mtk_cpu_resources_init(struct platform_device *pdev, { struct mtk_cpufreq_data *data; struct device *dev = &pdev->dev; + struct resource *res; void __iomem *base; int ret, i; int index; @@ -170,9 +173,26 @@ static int mtk_cpu_resources_init(struct platform_device *pdev, if (index < 0) return index; - base = devm_platform_ioremap_resource(pdev, index); - if (IS_ERR(base)) - return PTR_ERR(base); + res = platform_get_resource(pdev, IORESOURCE_MEM, index); + if (!res) { + dev_err(dev, "failed to get mem resource %d\n", index); + return -ENODEV; + } + + if (!request_mem_region(res->start, resource_size(res), res->name)) { + dev_err(dev, "failed to request resource %pR\n", res); + return -EBUSY; + } + + base = ioremap(res->start, resource_size(res)); + if (!base) { + dev_err(dev, "failed to map resource %pR\n", res); + ret = -ENOMEM; + goto release_region; + } + + data->base = base; + data->res = res; for (i = REG_FREQ_LUT_TABLE; i < REG_ARRAY_SIZE; i++) data->reg_bases[i] = base + offsets[i]; @@ -187,6 +207,9 @@ static int mtk_cpu_resources_init(struct platform_device *pdev, policy->driver_data = data; return 0; +release_region: + release_mem_region(res->start, resource_size(res)); + return ret; } static int mtk_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) @@ -233,9 +256,13 @@ static int mtk_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) static int mtk_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) { struct mtk_cpufreq_data *data = policy->driver_data; + struct resource *res = data->res; + void __iomem *base = data->base; /* HW should be in paused state now */ writel_relaxed(0x0, data->reg_bases[REG_FREQ_ENABLE]); + iounmap(base); + release_mem_region(res->start, resource_size(res)); return 0; } diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index a2be0df7e174..05f3d7876e44 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -46,6 +46,7 @@ struct qcom_cpufreq_data { */ struct mutex throttle_lock; int throttle_irq; + char irq_name[15]; bool cancel_throttle; struct delayed_work throttle_work; struct cpufreq_policy *policy; @@ -275,10 +276,10 @@ static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) { - unsigned long max_capacity, capacity, freq_hz, throttled_freq; struct cpufreq_policy *policy = data->policy; int cpu = cpumask_first(policy->cpus); struct device *dev = get_cpu_device(cpu); + unsigned long freq_hz, throttled_freq; struct dev_pm_opp *opp; unsigned int freq; @@ -295,16 +296,8 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) throttled_freq = freq_hz / HZ_PER_KHZ; - /* Update thermal pressure */ - - max_capacity = arch_scale_cpu_capacity(cpu); - capacity = mult_frac(max_capacity, throttled_freq, policy->cpuinfo.max_freq); - - /* Don't pass boost capacity to scheduler */ - if (capacity > max_capacity) - capacity = max_capacity; - - arch_set_thermal_pressure(policy->cpus, max_capacity - capacity); + /* Update thermal pressure (the boost frequencies are accepted) */ + arch_update_thermal_pressure(policy->related_cpus, throttled_freq); /* * In the unlikely case policy is unregistered do not enable @@ -342,9 +335,9 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data) /* Disable interrupt and enable polling */ disable_irq_nosync(c_data->throttle_irq); - qcom_lmh_dcvs_notify(c_data); + schedule_delayed_work(&c_data->throttle_work, 0); - return 0; + return IRQ_HANDLED; } static const struct qcom_cpufreq_soc_data qcom_soc_data = { @@ -375,16 +368,17 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) { struct qcom_cpufreq_data *data = policy->driver_data; struct platform_device *pdev = cpufreq_get_driver_data(); - char irq_name[15]; int ret; /* * Look for LMh interrupt. If no interrupt line is specified / * if there is an error, allow cpufreq to be enabled as usual. */ - data->throttle_irq = platform_get_irq(pdev, index); - if (data->throttle_irq <= 0) - return data->throttle_irq == -EPROBE_DEFER ? -EPROBE_DEFER : 0; + data->throttle_irq = platform_get_irq_optional(pdev, index); + if (data->throttle_irq == -ENXIO) + return 0; + if (data->throttle_irq < 0) + return data->throttle_irq; data->cancel_throttle = false; data->policy = policy; @@ -392,14 +386,19 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) mutex_init(&data->throttle_lock); INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll); - snprintf(irq_name, sizeof(irq_name), "dcvsh-irq-%u", policy->cpu); + snprintf(data->irq_name, sizeof(data->irq_name), "dcvsh-irq-%u", policy->cpu); ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq, - IRQF_ONESHOT, irq_name, data); + IRQF_ONESHOT, data->irq_name, data); if (ret) { - dev_err(&pdev->dev, "Error registering %s: %d\n", irq_name, ret); + dev_err(&pdev->dev, "Error registering %s: %d\n", data->irq_name, ret); return 0; } + ret = irq_set_affinity_hint(data->throttle_irq, policy->cpus); + if (ret) + dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n", + data->irq_name, data->throttle_irq); + return 0; } diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 2e5670446991..c4922684f305 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -34,7 +34,7 @@ * 1) Energy break even point * 2) Performance impact * 3) Latency tolerance (from pmqos infrastructure) - * These these three factors are treated independently. + * These three factors are treated independently. * * Energy break even point * ----------------------- diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 469e18547d06..2b496a53cbca 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -335,6 +335,7 @@ static struct attribute *cpuidle_state_default_attrs[] = { &attr_default_status.attr, NULL }; +ATTRIBUTE_GROUPS(cpuidle_state_default); struct cpuidle_state_kobj { struct cpuidle_state *state; @@ -448,7 +449,7 @@ static void cpuidle_state_sysfs_release(struct kobject *kobj) static struct kobj_type ktype_state_cpuidle = { .sysfs_ops = &cpuidle_state_sysfs_ops, - .default_attrs = cpuidle_state_default_attrs, + .default_groups = cpuidle_state_default_groups, .release = cpuidle_state_sysfs_release, }; @@ -505,7 +506,7 @@ error_state: } /** - * cpuidle_remove_driver_sysfs - removes the cpuidle states sysfs attributes + * cpuidle_remove_state_sysfs - removes the cpuidle states sysfs attributes * @device: the target device */ static void cpuidle_remove_state_sysfs(struct cpuidle_device *device) @@ -591,10 +592,11 @@ static struct attribute *cpuidle_driver_default_attrs[] = { &attr_driver_name.attr, NULL }; +ATTRIBUTE_GROUPS(cpuidle_driver_default); static struct kobj_type ktype_driver_cpuidle = { .sysfs_ops = &cpuidle_driver_sysfs_ops, - .default_attrs = cpuidle_driver_default_attrs, + .default_groups = cpuidle_driver_default_groups, .release = cpuidle_driver_sysfs_release, }; diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index e87d01c0b76a..87eb2b837e68 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -132,6 +132,15 @@ config ARM_RK3399_DMC_DEVFREQ It sets the frequency for the memory controller and reads the usage counts from hardware. +config ARM_SUN8I_A33_MBUS_DEVFREQ + tristate "sun8i/sun50i MBUS DEVFREQ Driver" + depends on ARCH_SUNXI || COMPILE_TEST + depends on COMMON_CLK + select DEVFREQ_GOV_SIMPLE_ONDEMAND + help + This adds the DEVFREQ driver for the MBUS controller in some + Allwinner sun8i (A33 through H3) and sun50i (A64 and H5) SoCs. + source "drivers/devfreq/event/Kconfig" endif # PM_DEVFREQ diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile index a16333ea7034..0b6be92a25d9 100644 --- a/drivers/devfreq/Makefile +++ b/drivers/devfreq/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_ARM_EXYNOS_BUS_DEVFREQ) += exynos-bus.o obj-$(CONFIG_ARM_IMX_BUS_DEVFREQ) += imx-bus.o obj-$(CONFIG_ARM_IMX8M_DDRC_DEVFREQ) += imx8m-ddrc.o obj-$(CONFIG_ARM_RK3399_DMC_DEVFREQ) += rk3399_dmc.o +obj-$(CONFIG_ARM_SUN8I_A33_MBUS_DEVFREQ) += sun8i-a33-mbus.o obj-$(CONFIG_ARM_TEGRA_DEVFREQ) += tegra30-devfreq.o # DEVFREQ Event Drivers diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 7906220d025c..a525a609dfc6 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -382,8 +382,8 @@ static int devfreq_set_target(struct devfreq *devfreq, unsigned long new_freq, devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); if (devfreq_update_status(devfreq, new_freq)) - dev_err(&devfreq->dev, - "Couldn't update frequency transition information.\n"); + dev_warn(&devfreq->dev, + "Couldn't update frequency transition information.\n"); devfreq->previous_freq = new_freq; diff --git a/drivers/devfreq/sun8i-a33-mbus.c b/drivers/devfreq/sun8i-a33-mbus.c new file mode 100644 index 000000000000..13d32213139f --- /dev/null +++ b/drivers/devfreq/sun8i-a33-mbus.c @@ -0,0 +1,511 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Copyright (C) 2020-2021 Samuel Holland <samuel@sholland.org> +// + +#include <linux/clk.h> +#include <linux/devfreq.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/property.h> + +#define MBUS_CR 0x0000 +#define MBUS_CR_GET_DRAM_TYPE(x) (((x) >> 16) & 0x7) +#define MBUS_CR_DRAM_TYPE_DDR2 2 +#define MBUS_CR_DRAM_TYPE_DDR3 3 +#define MBUS_CR_DRAM_TYPE_DDR4 4 +#define MBUS_CR_DRAM_TYPE_LPDDR2 6 +#define MBUS_CR_DRAM_TYPE_LPDDR3 7 + +#define MBUS_TMR 0x000c +#define MBUS_TMR_PERIOD(x) ((x) - 1) + +#define MBUS_PMU_CFG 0x009c +#define MBUS_PMU_CFG_PERIOD(x) (((x) - 1) << 16) +#define MBUS_PMU_CFG_UNIT (0x3 << 1) +#define MBUS_PMU_CFG_UNIT_B (0x0 << 1) +#define MBUS_PMU_CFG_UNIT_KB (0x1 << 1) +#define MBUS_PMU_CFG_UNIT_MB (0x2 << 1) +#define MBUS_PMU_CFG_ENABLE (0x1 << 0) + +#define MBUS_PMU_BWCR(n) (0x00a0 + (0x04 * (n))) + +#define MBUS_TOTAL_BWCR MBUS_PMU_BWCR(5) +#define MBUS_TOTAL_BWCR_H616 MBUS_PMU_BWCR(13) + +#define MBUS_MDFSCR 0x0100 +#define MBUS_MDFSCR_BUFFER_TIMING (0x1 << 15) +#define MBUS_MDFSCR_PAD_HOLD (0x1 << 13) +#define MBUS_MDFSCR_BYPASS (0x1 << 4) +#define MBUS_MDFSCR_MODE (0x1 << 1) +#define MBUS_MDFSCR_MODE_DFS (0x0 << 1) +#define MBUS_MDFSCR_MODE_CFS (0x1 << 1) +#define MBUS_MDFSCR_START (0x1 << 0) + +#define MBUS_MDFSMRMR 0x0108 + +#define DRAM_PWRCTL 0x0004 +#define DRAM_PWRCTL_SELFREF_EN (0x1 << 0) + +#define DRAM_RFSHTMG 0x0090 +#define DRAM_RFSHTMG_TREFI(x) ((x) << 16) +#define DRAM_RFSHTMG_TRFC(x) ((x) << 0) + +#define DRAM_VTFCR 0x00b8 +#define DRAM_VTFCR_VTF_ENABLE (0x3 << 8) + +#define DRAM_ODTMAP 0x0120 + +#define DRAM_DX_MAX 4 + +#define DRAM_DXnGCR0(n) (0x0344 + 0x80 * (n)) +#define DRAM_DXnGCR0_DXODT (0x3 << 4) +#define DRAM_DXnGCR0_DXODT_DYNAMIC (0x0 << 4) +#define DRAM_DXnGCR0_DXODT_ENABLED (0x1 << 4) +#define DRAM_DXnGCR0_DXODT_DISABLED (0x2 << 4) +#define DRAM_DXnGCR0_DXEN (0x1 << 0) + +struct sun8i_a33_mbus_variant { + u32 min_dram_divider; + u32 max_dram_divider; + u32 odt_freq_mhz; +}; + +struct sun8i_a33_mbus { + const struct sun8i_a33_mbus_variant *variant; + void __iomem *reg_dram; + void __iomem *reg_mbus; + struct clk *clk_bus; + struct clk *clk_dram; + struct clk *clk_mbus; + struct devfreq *devfreq_dram; + struct devfreq_simple_ondemand_data gov_data; + struct devfreq_dev_profile profile; + u32 data_width; + u32 nominal_bw; + u32 odtmap; + u32 tREFI_ns; + u32 tRFC_ns; + unsigned long freq_table[]; +}; + +/* + * The unit for this value is (MBUS clock cycles / MBUS_TMR_PERIOD). When + * MBUS_TMR_PERIOD is programmed to match the MBUS clock frequency in MHz, as + * it is during DRAM init and during probe, the resulting unit is microseconds. + */ +static int pmu_period = 50000; +module_param(pmu_period, int, 0644); +MODULE_PARM_DESC(pmu_period, "Bandwidth measurement period (microseconds)"); + +static u32 sun8i_a33_mbus_get_peak_bw(struct sun8i_a33_mbus *priv) +{ + /* Returns the peak transfer (in KiB) during any single PMU period. */ + return readl_relaxed(priv->reg_mbus + MBUS_TOTAL_BWCR); +} + +static void sun8i_a33_mbus_restart_pmu_counters(struct sun8i_a33_mbus *priv) +{ + u32 pmu_cfg = MBUS_PMU_CFG_PERIOD(pmu_period) | MBUS_PMU_CFG_UNIT_KB; + + /* All PMU counters are cleared on a disable->enable transition. */ + writel_relaxed(pmu_cfg, + priv->reg_mbus + MBUS_PMU_CFG); + writel_relaxed(pmu_cfg | MBUS_PMU_CFG_ENABLE, + priv->reg_mbus + MBUS_PMU_CFG); + +} + +static void sun8i_a33_mbus_update_nominal_bw(struct sun8i_a33_mbus *priv, + u32 ddr_freq_mhz) +{ + /* + * Nominal bandwidth (KiB per PMU period): + * + * DDR transfers microseconds KiB + * ------------- * ------------ * -------- + * microsecond PMU period transfer + */ + priv->nominal_bw = ddr_freq_mhz * pmu_period * priv->data_width / 1024; +} + +static int sun8i_a33_mbus_set_dram_freq(struct sun8i_a33_mbus *priv, + unsigned long freq) +{ + u32 ddr_freq_mhz = freq / USEC_PER_SEC; /* DDR */ + u32 dram_freq_mhz = ddr_freq_mhz / 2; /* SDR */ + u32 mctl_freq_mhz = dram_freq_mhz / 2; /* HDR */ + u32 dxodt, mdfscr, pwrctl, vtfcr; + u32 i, tREFI_32ck, tRFC_ck; + int ret; + + /* The rate change is not effective until the MDFS process runs. */ + ret = clk_set_rate(priv->clk_dram, freq); + if (ret) + return ret; + + /* Disable automatic self-refesh and VTF before starting MDFS. */ + pwrctl = readl_relaxed(priv->reg_dram + DRAM_PWRCTL) & + ~DRAM_PWRCTL_SELFREF_EN; + writel_relaxed(pwrctl, priv->reg_dram + DRAM_PWRCTL); + vtfcr = readl_relaxed(priv->reg_dram + DRAM_VTFCR); + writel_relaxed(vtfcr & ~DRAM_VTFCR_VTF_ENABLE, + priv->reg_dram + DRAM_VTFCR); + + /* Set up MDFS and enable double buffering for timing registers. */ + mdfscr = MBUS_MDFSCR_MODE_DFS | + MBUS_MDFSCR_BYPASS | + MBUS_MDFSCR_PAD_HOLD | + MBUS_MDFSCR_BUFFER_TIMING; + writel(mdfscr, priv->reg_mbus + MBUS_MDFSCR); + + /* Update the buffered copy of RFSHTMG. */ + tREFI_32ck = priv->tREFI_ns * mctl_freq_mhz / 1000 / 32; + tRFC_ck = DIV_ROUND_UP(priv->tRFC_ns * mctl_freq_mhz, 1000); + writel(DRAM_RFSHTMG_TREFI(tREFI_32ck) | DRAM_RFSHTMG_TRFC(tRFC_ck), + priv->reg_dram + DRAM_RFSHTMG); + + /* Enable ODT if needed, or disable it to save power. */ + if (priv->odtmap && dram_freq_mhz > priv->variant->odt_freq_mhz) { + dxodt = DRAM_DXnGCR0_DXODT_DYNAMIC; + writel(priv->odtmap, priv->reg_dram + DRAM_ODTMAP); + } else { + dxodt = DRAM_DXnGCR0_DXODT_DISABLED; + writel(0, priv->reg_dram + DRAM_ODTMAP); + } + for (i = 0; i < DRAM_DX_MAX; ++i) { + void __iomem *reg = priv->reg_dram + DRAM_DXnGCR0(i); + + writel((readl(reg) & ~DRAM_DXnGCR0_DXODT) | dxodt, reg); + } + + dev_dbg(priv->devfreq_dram->dev.parent, + "Setting DRAM to %u MHz, tREFI=%u, tRFC=%u, ODT=%s\n", + dram_freq_mhz, tREFI_32ck, tRFC_ck, + dxodt == DRAM_DXnGCR0_DXODT_DYNAMIC ? "dynamic" : "disabled"); + + /* Trigger hardware MDFS. */ + writel(mdfscr | MBUS_MDFSCR_START, priv->reg_mbus + MBUS_MDFSCR); + ret = readl_poll_timeout_atomic(priv->reg_mbus + MBUS_MDFSCR, mdfscr, + !(mdfscr & MBUS_MDFSCR_START), 10, 1000); + if (ret) + return ret; + + /* Disable double buffering. */ + writel(0, priv->reg_mbus + MBUS_MDFSCR); + + /* Restore VTF configuration. */ + writel_relaxed(vtfcr, priv->reg_dram + DRAM_VTFCR); + + /* Enable automatic self-refresh at the lowest frequency only. */ + if (freq == priv->freq_table[0]) + pwrctl |= DRAM_PWRCTL_SELFREF_EN; + writel_relaxed(pwrctl, priv->reg_dram + DRAM_PWRCTL); + + sun8i_a33_mbus_restart_pmu_counters(priv); + sun8i_a33_mbus_update_nominal_bw(priv, ddr_freq_mhz); + + return 0; +} + +static int sun8i_a33_mbus_set_dram_target(struct device *dev, + unsigned long *freq, u32 flags) +{ + struct sun8i_a33_mbus *priv = dev_get_drvdata(dev); + struct devfreq *devfreq = priv->devfreq_dram; + struct dev_pm_opp *opp; + int ret; + + opp = devfreq_recommended_opp(dev, freq, flags); + if (IS_ERR(opp)) + return PTR_ERR(opp); + + dev_pm_opp_put(opp); + + if (*freq == devfreq->previous_freq) + return 0; + + ret = sun8i_a33_mbus_set_dram_freq(priv, *freq); + if (ret) { + dev_warn(dev, "failed to set DRAM frequency: %d\n", ret); + *freq = devfreq->previous_freq; + } + + return ret; +} + +static int sun8i_a33_mbus_get_dram_status(struct device *dev, + struct devfreq_dev_status *stat) +{ + struct sun8i_a33_mbus *priv = dev_get_drvdata(dev); + + stat->busy_time = sun8i_a33_mbus_get_peak_bw(priv); + stat->total_time = priv->nominal_bw; + stat->current_frequency = priv->devfreq_dram->previous_freq; + + sun8i_a33_mbus_restart_pmu_counters(priv); + + dev_dbg(dev, "Using %lu/%lu (%lu%%) at %lu MHz\n", + stat->busy_time, stat->total_time, + DIV_ROUND_CLOSEST(stat->busy_time * 100, stat->total_time), + stat->current_frequency / USEC_PER_SEC); + + return 0; +} + +static int sun8i_a33_mbus_hw_init(struct device *dev, + struct sun8i_a33_mbus *priv, + unsigned long ddr_freq) +{ + u32 i, mbus_cr, mbus_freq_mhz; + + /* Choose tREFI and tRFC to match the configured DRAM type. */ + mbus_cr = readl_relaxed(priv->reg_mbus + MBUS_CR); + switch (MBUS_CR_GET_DRAM_TYPE(mbus_cr)) { + case MBUS_CR_DRAM_TYPE_DDR2: + case MBUS_CR_DRAM_TYPE_DDR3: + case MBUS_CR_DRAM_TYPE_DDR4: + priv->tREFI_ns = 7800; + priv->tRFC_ns = 350; + break; + case MBUS_CR_DRAM_TYPE_LPDDR2: + case MBUS_CR_DRAM_TYPE_LPDDR3: + priv->tREFI_ns = 3900; + priv->tRFC_ns = 210; + break; + default: + return -EINVAL; + } + + /* Save ODTMAP so it can be restored when raising the frequency. */ + priv->odtmap = readl_relaxed(priv->reg_dram + DRAM_ODTMAP); + + /* Compute the DRAM data bus width by counting enabled DATx8 blocks. */ + for (i = 0; i < DRAM_DX_MAX; ++i) { + void __iomem *reg = priv->reg_dram + DRAM_DXnGCR0(i); + + if (!(readl_relaxed(reg) & DRAM_DXnGCR0_DXEN)) + break; + } + priv->data_width = i; + + dev_dbg(dev, "Detected %u-bit %sDDRx with%s ODT\n", + priv->data_width * 8, + MBUS_CR_GET_DRAM_TYPE(mbus_cr) > 4 ? "LP" : "", + priv->odtmap ? "" : "out"); + + /* Program MBUS_TMR such that the PMU period unit is microseconds. */ + mbus_freq_mhz = clk_get_rate(priv->clk_mbus) / USEC_PER_SEC; + writel_relaxed(MBUS_TMR_PERIOD(mbus_freq_mhz), + priv->reg_mbus + MBUS_TMR); + + /* "Master Ready Mask Register" bits must be set or MDFS will block. */ + writel_relaxed(0xffffffff, priv->reg_mbus + MBUS_MDFSMRMR); + + sun8i_a33_mbus_restart_pmu_counters(priv); + sun8i_a33_mbus_update_nominal_bw(priv, ddr_freq / USEC_PER_SEC); + + return 0; +} + +static int __maybe_unused sun8i_a33_mbus_suspend(struct device *dev) +{ + struct sun8i_a33_mbus *priv = dev_get_drvdata(dev); + + clk_disable_unprepare(priv->clk_bus); + + return 0; +} + +static int __maybe_unused sun8i_a33_mbus_resume(struct device *dev) +{ + struct sun8i_a33_mbus *priv = dev_get_drvdata(dev); + + return clk_prepare_enable(priv->clk_bus); +} + +static int sun8i_a33_mbus_probe(struct platform_device *pdev) +{ + const struct sun8i_a33_mbus_variant *variant; + struct device *dev = &pdev->dev; + struct sun8i_a33_mbus *priv; + unsigned long base_freq; + unsigned int max_state; + const char *err; + int i, ret; + + variant = device_get_match_data(dev); + if (!variant) + return -EINVAL; + + max_state = variant->max_dram_divider - variant->min_dram_divider + 1; + + priv = devm_kzalloc(dev, struct_size(priv, freq_table, max_state), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + platform_set_drvdata(pdev, priv); + + priv->variant = variant; + + priv->reg_dram = devm_platform_ioremap_resource_byname(pdev, "dram"); + if (IS_ERR(priv->reg_dram)) + return PTR_ERR(priv->reg_dram); + + priv->reg_mbus = devm_platform_ioremap_resource_byname(pdev, "mbus"); + if (IS_ERR(priv->reg_mbus)) + return PTR_ERR(priv->reg_mbus); + + priv->clk_bus = devm_clk_get(dev, "bus"); + if (IS_ERR(priv->clk_bus)) + return dev_err_probe(dev, PTR_ERR(priv->clk_bus), + "failed to get bus clock\n"); + + priv->clk_dram = devm_clk_get(dev, "dram"); + if (IS_ERR(priv->clk_dram)) + return dev_err_probe(dev, PTR_ERR(priv->clk_dram), + "failed to get dram clock\n"); + + priv->clk_mbus = devm_clk_get(dev, "mbus"); + if (IS_ERR(priv->clk_mbus)) + return dev_err_probe(dev, PTR_ERR(priv->clk_mbus), + "failed to get mbus clock\n"); + + ret = clk_prepare_enable(priv->clk_bus); + if (ret) + return dev_err_probe(dev, ret, + "failed to enable bus clock\n"); + + /* Lock the DRAM clock rate to keep priv->nominal_bw in sync. */ + ret = clk_rate_exclusive_get(priv->clk_dram); + if (ret) { + err = "failed to lock dram clock rate\n"; + goto err_disable_bus; + } + + /* Lock the MBUS clock rate to keep MBUS_TMR_PERIOD in sync. */ + ret = clk_rate_exclusive_get(priv->clk_mbus); + if (ret) { + err = "failed to lock mbus clock rate\n"; + goto err_unlock_dram; + } + + priv->gov_data.upthreshold = 10; + priv->gov_data.downdifferential = 5; + + priv->profile.initial_freq = clk_get_rate(priv->clk_dram); + priv->profile.polling_ms = 1000; + priv->profile.target = sun8i_a33_mbus_set_dram_target; + priv->profile.get_dev_status = sun8i_a33_mbus_get_dram_status; + priv->profile.freq_table = priv->freq_table; + priv->profile.max_state = max_state; + + ret = devm_pm_opp_set_clkname(dev, "dram"); + if (ret) { + err = "failed to add OPP table\n"; + goto err_unlock_mbus; + } + + base_freq = clk_get_rate(clk_get_parent(priv->clk_dram)); + for (i = 0; i < max_state; ++i) { + unsigned int div = variant->max_dram_divider - i; + + priv->freq_table[i] = base_freq / div; + + ret = dev_pm_opp_add(dev, priv->freq_table[i], 0); + if (ret) { + err = "failed to add OPPs\n"; + goto err_remove_opps; + } + } + + ret = sun8i_a33_mbus_hw_init(dev, priv, priv->profile.initial_freq); + if (ret) { + err = "failed to init hardware\n"; + goto err_remove_opps; + } + + priv->devfreq_dram = devfreq_add_device(dev, &priv->profile, + DEVFREQ_GOV_SIMPLE_ONDEMAND, + &priv->gov_data); + if (IS_ERR(priv->devfreq_dram)) { + ret = PTR_ERR(priv->devfreq_dram); + err = "failed to add devfreq device\n"; + goto err_remove_opps; + } + + /* + * This must be set manually after registering the devfreq device, + * because there is no way to select a dynamic OPP as the suspend OPP. + */ + priv->devfreq_dram->suspend_freq = priv->freq_table[0]; + + return 0; + +err_remove_opps: + dev_pm_opp_remove_all_dynamic(dev); +err_unlock_mbus: + clk_rate_exclusive_put(priv->clk_mbus); +err_unlock_dram: + clk_rate_exclusive_put(priv->clk_dram); +err_disable_bus: + clk_disable_unprepare(priv->clk_bus); + + return dev_err_probe(dev, ret, err); +} + +static int sun8i_a33_mbus_remove(struct platform_device *pdev) +{ + struct sun8i_a33_mbus *priv = platform_get_drvdata(pdev); + unsigned long initial_freq = priv->profile.initial_freq; + struct device *dev = &pdev->dev; + int ret; + + devfreq_remove_device(priv->devfreq_dram); + + ret = sun8i_a33_mbus_set_dram_freq(priv, initial_freq); + if (ret) + dev_warn(dev, "failed to restore DRAM frequency: %d\n", ret); + + dev_pm_opp_remove_all_dynamic(dev); + clk_rate_exclusive_put(priv->clk_mbus); + clk_rate_exclusive_put(priv->clk_dram); + clk_disable_unprepare(priv->clk_bus); + + return 0; +} + +static const struct sun8i_a33_mbus_variant sun50i_a64_mbus = { + .min_dram_divider = 1, + .max_dram_divider = 4, + .odt_freq_mhz = 400, +}; + +static const struct of_device_id sun8i_a33_mbus_of_match[] = { + { .compatible = "allwinner,sun50i-a64-mbus", .data = &sun50i_a64_mbus }, + { .compatible = "allwinner,sun50i-h5-mbus", .data = &sun50i_a64_mbus }, + { }, +}; +MODULE_DEVICE_TABLE(of, sun8i_a33_mbus_of_match); + +static SIMPLE_DEV_PM_OPS(sun8i_a33_mbus_pm_ops, + sun8i_a33_mbus_suspend, sun8i_a33_mbus_resume); + +static struct platform_driver sun8i_a33_mbus_driver = { + .probe = sun8i_a33_mbus_probe, + .remove = sun8i_a33_mbus_remove, + .driver = { + .name = "sun8i-a33-mbus", + .of_match_table = sun8i_a33_mbus_of_match, + .pm = pm_ptr(&sun8i_a33_mbus_pm_ops), + }, +}; +module_platform_driver(sun8i_a33_mbus_driver); + +MODULE_AUTHOR("Samuel Holland <samuel@sholland.org>"); +MODULE_DESCRIPTION("Allwinner sun8i/sun50i MBUS DEVFREQ Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 80a2c270d502..bb612fce7ead 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -1103,17 +1103,17 @@ static int jz4740_mmc_remove(struct platform_device *pdev) return 0; } -static int __maybe_unused jz4740_mmc_suspend(struct device *dev) +static int jz4740_mmc_suspend(struct device *dev) { return pinctrl_pm_select_sleep_state(dev); } -static int __maybe_unused jz4740_mmc_resume(struct device *dev) +static int jz4740_mmc_resume(struct device *dev) { return pinctrl_select_default_state(dev); } -static SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend, +DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend, jz4740_mmc_resume); static struct platform_driver jz4740_mmc_driver = { @@ -1123,7 +1123,7 @@ static struct platform_driver jz4740_mmc_driver = { .name = "jz4740-mmc", .probe_type = PROBE_PREFER_ASYNCHRONOUS, .of_match_table = of_match_ptr(jz4740_mmc_of_match), - .pm = pm_ptr(&jz4740_mmc_pm_ops), + .pm = pm_sleep_ptr(&jz4740_mmc_pm_ops), }, }; diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 2fe6fcdbb1b3..98c218bd6669 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -1183,7 +1183,6 @@ static int mxcmci_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP static int mxcmci_suspend(struct device *dev) { struct mmc_host *mmc = dev_get_drvdata(dev); @@ -1210,9 +1209,8 @@ static int mxcmci_resume(struct device *dev) return ret; } -#endif -static SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume); +DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume); static struct platform_driver mxcmci_driver = { .probe = mxcmci_probe, @@ -1220,7 +1218,7 @@ static struct platform_driver mxcmci_driver = { .driver = { .name = DRIVER_NAME, .probe_type = PROBE_PREFER_ASYNCHRONOUS, - .pm = &mxcmci_pm_ops, + .pm = pm_sleep_ptr(&mxcmci_pm_ops), .of_match_table = mxcmci_of_match, } }; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7161a5b1c701..19e2621e0645 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5460,7 +5460,9 @@ static struct pci_driver rtl8169_pci_driver = { .probe = rtl_init_one, .remove = rtl_remove_one, .shutdown = rtl_shutdown, - .driver.pm = pm_ptr(&rtl8169_pm_ops), +#ifdef CONFIG_PM + .driver.pm = &rtl8169_pm_ops, +#endif }; module_pci_driver(rtl8169_pci_driver); diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index 2a5c1829aab7..8cb45f2d3d78 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -382,7 +382,7 @@ void dtpm_unregister(struct dtpm *dtpm) { powercap_unregister_zone(pct, &dtpm->zone); - pr_info("Unregistered dtpm node '%s'\n", dtpm->zone.name); + pr_debug("Unregistered dtpm node '%s'\n", dtpm->zone.name); } /** @@ -453,8 +453,8 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) dtpm->power_limit = dtpm->power_max; } - pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n", - dtpm->zone.name, dtpm->power_min, dtpm->power_max); + pr_debug("Registered dtpm node '%s' / %llu-%llu uW, \n", + dtpm->zone.name, dtpm->power_min, dtpm->power_max); mutex_unlock(&dtpm_lock); diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c index 6e1a0043c411..a20bf12f3ce3 100644 --- a/drivers/powercap/idle_inject.c +++ b/drivers/powercap/idle_inject.c @@ -12,7 +12,7 @@ * * All of the kthreads used for idle injection are created at init time. * - * Next, the users of the the idle injection framework provide a cpumask via + * Next, the users of the idle injection framework provide a cpumask via * its register function. The kthreads will be synchronized with respect to * this cpumask. * diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 7c0099e7a6d7..07611a00b78f 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -61,6 +61,20 @@ #define PERF_STATUS_THROTTLE_TIME_MASK 0xffffffff #define PP_POLICY_MASK 0x1F +/* + * SPR has different layout for Psys Domain PowerLimit registers. + * There are 17 bits of PL1 and PL2 instead of 15 bits. + * The Enable bits and TimeWindow bits are also shifted as a result. + */ +#define PSYS_POWER_LIMIT1_MASK 0x1FFFF +#define PSYS_POWER_LIMIT1_ENABLE BIT(17) + +#define PSYS_POWER_LIMIT2_MASK (0x1FFFFULL<<32) +#define PSYS_POWER_LIMIT2_ENABLE BIT_ULL(49) + +#define PSYS_TIME_WINDOW1_MASK (0x7FULL<<19) +#define PSYS_TIME_WINDOW2_MASK (0x7FULL<<51) + /* Non HW constants */ #define RAPL_PRIMITIVE_DERIVED BIT(1) /* not from raw data */ #define RAPL_PRIMITIVE_DUMMY BIT(2) @@ -97,6 +111,7 @@ struct rapl_defaults { bool to_raw); unsigned int dram_domain_energy_unit; unsigned int psys_domain_energy_unit; + bool spr_psys_bits; }; static struct rapl_defaults *rapl_defaults; @@ -669,12 +684,51 @@ static struct rapl_primitive_info rpi[] = { RAPL_DOMAIN_REG_PERF, TIME_UNIT, 0), PRIMITIVE_INFO_INIT(PRIORITY_LEVEL, PP_POLICY_MASK, 0, RAPL_DOMAIN_REG_POLICY, ARBITRARY_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_POWER_LIMIT1, PSYS_POWER_LIMIT1_MASK, 0, + RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_POWER_LIMIT2, PSYS_POWER_LIMIT2_MASK, 32, + RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_PL1_ENABLE, PSYS_POWER_LIMIT1_ENABLE, 17, + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_PL2_ENABLE, PSYS_POWER_LIMIT2_ENABLE, 49, + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_TIME_WINDOW1, PSYS_TIME_WINDOW1_MASK, 19, + RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_TIME_WINDOW2, PSYS_TIME_WINDOW2_MASK, 51, + RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0), /* non-hardware */ PRIMITIVE_INFO_INIT(AVERAGE_POWER, 0, 0, 0, POWER_UNIT, RAPL_PRIMITIVE_DERIVED), {NULL, 0, 0, 0}, }; +static enum rapl_primitives +prim_fixups(struct rapl_domain *rd, enum rapl_primitives prim) +{ + if (!rapl_defaults->spr_psys_bits) + return prim; + + if (rd->id != RAPL_DOMAIN_PLATFORM) + return prim; + + switch (prim) { + case POWER_LIMIT1: + return PSYS_POWER_LIMIT1; + case POWER_LIMIT2: + return PSYS_POWER_LIMIT2; + case PL1_ENABLE: + return PSYS_PL1_ENABLE; + case PL2_ENABLE: + return PSYS_PL2_ENABLE; + case TIME_WINDOW1: + return PSYS_TIME_WINDOW1; + case TIME_WINDOW2: + return PSYS_TIME_WINDOW2; + default: + return prim; + } +} + /* Read primitive data based on its related struct rapl_primitive_info. * if xlate flag is set, return translated data based on data units, i.e. * time, energy, and power. @@ -692,7 +746,8 @@ static int rapl_read_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, bool xlate, u64 *data) { u64 value; - struct rapl_primitive_info *rp = &rpi[prim]; + enum rapl_primitives prim_fixed = prim_fixups(rd, prim); + struct rapl_primitive_info *rp = &rpi[prim_fixed]; struct reg_action ra; int cpu; @@ -738,7 +793,8 @@ static int rapl_write_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, unsigned long long value) { - struct rapl_primitive_info *rp = &rpi[prim]; + enum rapl_primitives prim_fixed = prim_fixups(rd, prim); + struct rapl_primitive_info *rp = &rpi[prim_fixed]; int cpu; u64 bits; struct reg_action ra; @@ -981,6 +1037,7 @@ static const struct rapl_defaults rapl_defaults_spr_server = { .compute_time_window = rapl_compute_time_window_core, .dram_domain_energy_unit = 15300, .psys_domain_energy_unit = 1000000000, + .spr_psys_bits = true, }; static const struct rapl_defaults rapl_defaults_byt = { diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index 43b1ae8a7789..0bfb8eebd126 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -462,7 +462,6 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; struct cpumask *cpus; unsigned int frequency; - unsigned long max_capacity, capacity; int ret; /* Request state should be less than max_level */ @@ -479,10 +478,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, if (ret >= 0) { cpufreq_cdev->cpufreq_state = state; cpus = cpufreq_cdev->policy->related_cpus; - max_capacity = arch_scale_cpu_capacity(cpumask_first(cpus)); - capacity = frequency * max_capacity; - capacity /= cpufreq_cdev->policy->cpuinfo.max_freq; - arch_set_thermal_pressure(cpus, max_capacity - capacity); + arch_update_thermal_pressure(cpus, frequency); ret = 0; } diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index bc159a9b4a73..92b7ea8d8f5e 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -138,6 +138,7 @@ extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf); extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf); extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs); extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); +extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); extern bool acpi_cpc_valid(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); @@ -162,6 +163,10 @@ static inline int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) { return -ENOTSUPP; } +static inline int cppc_set_enable(int cpu, bool enable) +{ + return -ENOTSUPP; +} static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps) { return -ENOTSUPP; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 93eaba2485e3..eaeb4b9255bc 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -506,7 +506,7 @@ acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -void __init acpi_no_s4_hw_signature(void); +void __init acpi_check_s4_hw_signature(int check); #endif #ifdef CONFIG_PM_SLEEP diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index b97cea83b25e..cce6136b300a 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -56,8 +56,8 @@ static inline unsigned long topology_get_thermal_pressure(int cpu) return per_cpu(thermal_pressure, cpu); } -void topology_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure); +void topology_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_freq); struct cpu_topology { int thread_id; diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 2890f6370eb9..d37e5d06a357 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -70,6 +70,4 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); -int dtpm_register_cpu(struct dtpm *parent); - #endif diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 93780834fc8f..9f4b6f5b822f 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -58,6 +58,12 @@ enum rapl_primitives { THROTTLED_TIME, PRIORITY_LEVEL, + PSYS_POWER_LIMIT1, + PSYS_POWER_LIMIT2, + PSYS_PL1_ENABLE, + PSYS_PL2_ENABLE, + PSYS_TIME_WINDOW1, + PSYS_TIME_WINDOW2, /* below are not raw primitive data */ AVERAGE_POWER, NR_RAPL_PRIMITIVES, diff --git a/include/linux/pm.h b/include/linux/pm.h index 1d8209c09686..e1e9402180b9 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -300,47 +300,59 @@ struct dev_pm_ops { int (*runtime_idle)(struct device *dev); }; +#define SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend = pm_sleep_ptr(suspend_fn), \ + .resume = pm_sleep_ptr(resume_fn), \ + .freeze = pm_sleep_ptr(suspend_fn), \ + .thaw = pm_sleep_ptr(resume_fn), \ + .poweroff = pm_sleep_ptr(suspend_fn), \ + .restore = pm_sleep_ptr(resume_fn), + +#define LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_late = pm_sleep_ptr(suspend_fn), \ + .resume_early = pm_sleep_ptr(resume_fn), \ + .freeze_late = pm_sleep_ptr(suspend_fn), \ + .thaw_early = pm_sleep_ptr(resume_fn), \ + .poweroff_late = pm_sleep_ptr(suspend_fn), \ + .restore_early = pm_sleep_ptr(resume_fn), + +#define NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_noirq = pm_sleep_ptr(suspend_fn), \ + .resume_noirq = pm_sleep_ptr(resume_fn), \ + .freeze_noirq = pm_sleep_ptr(suspend_fn), \ + .thaw_noirq = pm_sleep_ptr(resume_fn), \ + .poweroff_noirq = pm_sleep_ptr(suspend_fn), \ + .restore_noirq = pm_sleep_ptr(resume_fn), + +#define RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + .runtime_suspend = suspend_fn, \ + .runtime_resume = resume_fn, \ + .runtime_idle = idle_fn, + #ifdef CONFIG_PM_SLEEP #define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend = suspend_fn, \ - .resume = resume_fn, \ - .freeze = suspend_fn, \ - .thaw = resume_fn, \ - .poweroff = suspend_fn, \ - .restore = resume_fn, + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM_SLEEP #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend_late = suspend_fn, \ - .resume_early = resume_fn, \ - .freeze_late = suspend_fn, \ - .thaw_early = resume_fn, \ - .poweroff_late = suspend_fn, \ - .restore_early = resume_fn, + LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM_SLEEP #define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend_noirq = suspend_fn, \ - .resume_noirq = resume_fn, \ - .freeze_noirq = suspend_fn, \ - .thaw_noirq = resume_fn, \ - .poweroff_noirq = suspend_fn, \ - .restore_noirq = resume_fn, + NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ - .runtime_suspend = suspend_fn, \ - .runtime_resume = resume_fn, \ - .runtime_idle = idle_fn, + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #else #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #endif @@ -349,9 +361,9 @@ struct dev_pm_ops { * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. */ -#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops __maybe_unused name = { \ - SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ +#define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +static const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } /* @@ -367,17 +379,27 @@ const struct dev_pm_ops __maybe_unused name = { \ * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). */ +#define DEFINE_UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ +static const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ +} + +/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ +#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +const struct dev_pm_ops __maybe_unused name = { \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ +} + +/* Deprecated. Use DEFINE_UNIVERSAL_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } -#ifdef CONFIG_PM -#define pm_ptr(_ptr) (_ptr) -#else -#define pm_ptr(_ptr) NULL -#endif +#define pm_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM), (_ptr)) +#define pm_sleep_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM_SLEEP), (_ptr)) /* * PM_EVENT_ messages @@ -499,6 +521,7 @@ const struct dev_pm_ops __maybe_unused name = { \ */ enum rpm_status { + RPM_INVALID = -1, RPM_ACTIVE = 0, RPM_RESUMING, RPM_SUSPENDED, @@ -612,6 +635,7 @@ struct dev_pm_info { unsigned int links_count; enum rpm_request request; enum rpm_status runtime_status; + enum rpm_status last_status; int runtime_error; int autosuspend_delay; u64 last_busy; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index eddd66d426ca..016de5776b6d 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -58,6 +58,7 @@ extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); +extern void pm_runtime_release_supplier(struct device_link *link, bool check_idle); extern int devm_pm_runtime_enable(struct device *dev); @@ -283,6 +284,8 @@ static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} +static inline void pm_runtime_release_supplier(struct device_link *link, + bool check_idle) {} #endif /* !CONFIG_PM */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index c07bfa2d80f2..8054641c0a7b 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -266,10 +266,10 @@ unsigned long arch_scale_thermal_pressure(int cpu) } #endif -#ifndef arch_set_thermal_pressure +#ifndef arch_update_thermal_pressure static __always_inline -void arch_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure) +void arch_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_frequency) { } #endif diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8af13ba60c7e..5785d909c321 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -446,6 +446,7 @@ extern unsigned long get_safe_page(gfp_t gfp_mask); extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); +extern u32 swsusp_hardware_signature; extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); diff --git a/init/Kconfig b/init/Kconfig index 03e1b863f5ce..ec589e5c1b8c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -550,7 +550,7 @@ config SCHED_THERMAL_PRESSURE i.e. put less load on throttled CPUs than on non/less throttled ones. This requires the architecture to implement - arch_set_thermal_pressure() and arch_scale_thermal_pressure(). + arch_update_thermal_pressure() and arch_scale_thermal_pressure(). config BSD_PROCESS_ACCT bool "BSD Process Accounting" diff --git a/kernel/power/power.h b/kernel/power/power.h index 326f8d032eb5..b4f433943209 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -170,6 +170,7 @@ extern int swsusp_swap_in_use(void); #define SF_PLATFORM_MODE 1 #define SF_NOCOMPRESS_MODE 2 #define SF_CRC32_MODE 4 +#define SF_HW_SIG 8 /* kernel/power/hibernate.c */ extern int swsusp_check(void); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index ff326c2cb77b..ad10359030a4 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -36,6 +36,8 @@ #define HIBERNATE_SIG "S1SUSPEND" +u32 swsusp_hardware_signature; + /* * When reading an {un,}compressed image, we may restore pages in place, * in which case some architectures need these pages cleaning before they @@ -104,7 +106,8 @@ struct swap_map_handle { struct swsusp_header { char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) - - sizeof(u32)]; + sizeof(u32) - sizeof(u32)]; + u32 hw_sig; u32 crc32; sector_t image; unsigned int flags; /* Flags to pass to the "boot" kernel */ @@ -312,7 +315,6 @@ static int hib_wait_io(struct hib_bio_batch *hb) /* * Saving part */ - static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) { int error; @@ -324,6 +326,10 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10); memcpy(swsusp_header->sig, HIBERNATE_SIG, 10); swsusp_header->image = handle->first_sector; + if (swsusp_hardware_signature) { + swsusp_header->hw_sig = swsusp_hardware_signature; + flags |= SF_HW_SIG; + } swsusp_header->flags = flags; if (flags & SF_CRC32_MODE) swsusp_header->crc32 = handle->crc32; @@ -1537,6 +1543,12 @@ int swsusp_check(void) } else { error = -EINVAL; } + if (!error && swsusp_header->flags & SF_HW_SIG && + swsusp_header->hw_sig != swsusp_hardware_signature) { + pr_info("Suspend image hardware signature mismatch (%08x now %08x); aborting resume.\n", + swsusp_header->hw_sig, swsusp_hardware_signature); + error = -EINVAL; + } put: if (error) |