diff options
36 files changed, 1408 insertions, 534 deletions
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt index 4bc7287806de..978463a7c81e 100644 --- a/Documentation/cpu-freq/core.txt +++ b/Documentation/cpu-freq/core.txt @@ -8,6 +8,8 @@ Dominik Brodowski <linux@brodo.de> David Kimdon <dwhedon@debian.org> + Rafael J. Wysocki <rafael.j.wysocki@intel.com> + Viresh Kumar <viresh.kumar@linaro.org> @@ -36,10 +38,11 @@ speed limits (like LCD drivers on ARM architecture). Additionally, the kernel "constant" loops_per_jiffy is updated on frequency changes here. -Reference counting is done by cpufreq_get_cpu and cpufreq_put_cpu, -which make sure that the cpufreq processor driver is correctly -registered with the core, and will not be unloaded until -cpufreq_put_cpu is called. +Reference counting of the cpufreq policies is done by cpufreq_cpu_get +and cpufreq_cpu_put, which make sure that the cpufreq driver is +correctly registered with the core, and will not be unloaded until +cpufreq_put_cpu is called. That also ensures that the respective cpufreq +policy doesn't get freed while being used. 2. CPUFreq notifiers ==================== @@ -69,18 +72,16 @@ CPUFreq policy notifier is called twice for a policy transition: The phase is specified in the second argument to the notifier. The third argument, a void *pointer, points to a struct cpufreq_policy -consisting of five values: cpu, min, max, policy and max_cpu_freq. min -and max are the lower and upper frequencies (in kHz) of the new -policy, policy the new policy, cpu the number of the affected CPU; and -max_cpu_freq the maximum supported CPU frequency. This value is given -for informational purposes only. +consisting of several values, including min, max (the lower and upper +frequencies (in kHz) of the new policy). 2.2 CPUFreq transition notifiers -------------------------------- -These are notified twice when the CPUfreq driver switches the CPU core -frequency and this change has any external implications. +These are notified twice for each online CPU in the policy, when the +CPUfreq driver switches the CPU core frequency and this change has no +any external implications. The second argument specifies the phase - CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE. @@ -90,6 +91,7 @@ values: cpu - number of the affected CPU old - old frequency new - new frequency +flags - flags of the cpufreq driver 3. CPUFreq Table Generation with Operating Performance Point (OPP) ================================================================== diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt index 772b94fde264..f71e6be26b83 100644 --- a/Documentation/cpu-freq/cpu-drivers.txt +++ b/Documentation/cpu-freq/cpu-drivers.txt @@ -9,6 +9,8 @@ Dominik Brodowski <linux@brodo.de> + Rafael J. Wysocki <rafael.j.wysocki@intel.com> + Viresh Kumar <viresh.kumar@linaro.org> @@ -49,49 +51,65 @@ using cpufreq_register_driver() What shall this struct cpufreq_driver contain? -cpufreq_driver.name - The name of this driver. + .name - The name of this driver. -cpufreq_driver.init - A pointer to the per-CPU initialization - function. + .init - A pointer to the per-policy initialization function. -cpufreq_driver.verify - A pointer to a "verification" function. + .verify - A pointer to a "verification" function. -cpufreq_driver.setpolicy _or_ -cpufreq_driver.target/ -target_index - See below on the differences. + .setpolicy _or_ .fast_switch _or_ .target _or_ .target_index - See + below on the differences. And optionally -cpufreq_driver.exit - A pointer to a per-CPU cleanup - function called during CPU_POST_DEAD - phase of cpu hotplug process. + .flags - Hints for the cpufreq core. -cpufreq_driver.stop_cpu - A pointer to a per-CPU stop function - called during CPU_DOWN_PREPARE phase of - cpu hotplug process. + .driver_data - cpufreq driver specific data. -cpufreq_driver.resume - A pointer to a per-CPU resume function - which is called with interrupts disabled - and _before_ the pre-suspend frequency - and/or policy is restored by a call to - ->target/target_index or ->setpolicy. + .resolve_freq - Returns the most appropriate frequency for a target + frequency. Doesn't change the frequency though. -cpufreq_driver.attr - A pointer to a NULL-terminated list of - "struct freq_attr" which allow to - export values to sysfs. + .get_intermediate and target_intermediate - Used to switch to stable + frequency while changing CPU frequency. -cpufreq_driver.get_intermediate -and target_intermediate Used to switch to stable frequency while - changing CPU frequency. + .get - Returns current frequency of the CPU. + + .bios_limit - Returns HW/BIOS max frequency limitations for the CPU. + + .exit - A pointer to a per-policy cleanup function called during + CPU_POST_DEAD phase of cpu hotplug process. + + .stop_cpu - A pointer to a per-policy stop function called during + CPU_DOWN_PREPARE phase of cpu hotplug process. + + .suspend - A pointer to a per-policy suspend function which is called + with interrupts disabled and _after_ the governor is stopped for the + policy. + + .resume - A pointer to a per-policy resume function which is called + with interrupts disabled and _before_ the governor is started again. + + .ready - A pointer to a per-policy ready function which is called after + the policy is fully initialized. + + .attr - A pointer to a NULL-terminated list of "struct freq_attr" which + allow to export values to sysfs. + + .boost_enabled - If set, boost frequencies are enabled. + + .set_boost - A pointer to a per-policy function to enable/disable boost + frequencies. 1.2 Per-CPU Initialization -------------------------- Whenever a new CPU is registered with the device model, or after the -cpufreq driver registers itself, the per-CPU initialization function -cpufreq_driver.init is called. It takes a struct cpufreq_policy -*policy as argument. What to do now? +cpufreq driver registers itself, the per-policy initialization function +cpufreq_driver.init is called if no cpufreq policy existed for the CPU. +Note that the .init() and .exit() routines are called only once for the +policy and not for each CPU managed by the policy. It takes a struct +cpufreq_policy *policy as argument. What to do now? If necessary, activate the CPUfreq support on your CPU. @@ -117,47 +135,45 @@ policy->governor must contain the "default policy" for cpufreq_driver.setpolicy or cpufreq_driver.target/target_index is called with these values. +policy->cpus Update this with the masks of the + (online + offline) CPUs that do DVFS + along with this CPU (i.e. that share + clock/voltage rails with it). For setting some of these values (cpuinfo.min[max]_freq, policy->min[max]), the frequency table helpers might be helpful. See the section 2 for more information on them. -SMP systems normally have same clock source for a group of cpus. For these the -.init() would be called only once for the first online cpu. Here the .init() -routine must initialize policy->cpus with mask of all possible cpus (Online + -Offline) that share the clock. Then the core would copy this mask onto -policy->related_cpus and will reset policy->cpus to carry only online cpus. - 1.3 verify ------------- +---------- When the user decides a new policy (consisting of "policy,governor,min,max") shall be set, this policy must be validated so that incompatible values can be corrected. For verifying these -values, a frequency table helper and/or the -cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned -int min_freq, unsigned int max_freq) function might be helpful. See -section 2 for details on frequency table helpers. +values cpufreq_verify_within_limits(struct cpufreq_policy *policy, +unsigned int min_freq, unsigned int max_freq) function might be helpful. +See section 2 for details on frequency table helpers. You need to make sure that at least one valid frequency (or operating range) is within policy->min and policy->max. If necessary, increase policy->max first, and only if this is no solution, decrease policy->min. -1.4 target/target_index or setpolicy? ----------------------------- +1.4 target or target_index or setpolicy or fast_switch? +------------------------------------------------------- Most cpufreq drivers or even most cpu frequency scaling algorithms -only allow the CPU to be set to one frequency. For these, you use the -->target/target_index call. +only allow the CPU frequency to be set to predefined fixed values. For +these, you use the ->target(), ->target_index() or ->fast_switch() +callbacks. -Some cpufreq-capable processors switch the frequency between certain -limits on their own. These shall use the ->setpolicy call +Some cpufreq capable processors switch the frequency between certain +limits on their own. These shall use the ->setpolicy() callback. 1.5. target/target_index -------------- +------------------------ The target_index call has two arguments: struct cpufreq_policy *policy, and unsigned int index (into the exposed frequency table). @@ -186,9 +202,20 @@ actual frequency must be determined using the following rules: Here again the frequency table helper might assist you - see section 2 for details. +1.6. fast_switch +---------------- -1.6 setpolicy ---------------- +This function is used for frequency switching from scheduler's context. +Not all drivers are expected to implement it, as sleeping from within +this callback isn't allowed. This callback must be highly optimized to +do switching as fast as possible. + +This function has two arguments: struct cpufreq_policy *policy and +unsigned int target_frequency. + + +1.7 setpolicy +------------- The setpolicy call only takes a struct cpufreq_policy *policy as argument. You need to set the lower limit of the in-processor or @@ -198,7 +225,7 @@ setting when policy->policy is CPUFREQ_POLICY_PERFORMANCE, and a powersaving-oriented setting when CPUFREQ_POLICY_POWERSAVE. Also check the reference implementation in drivers/cpufreq/longrun.c -1.7 get_intermediate and target_intermediate +1.8 get_intermediate and target_intermediate -------------------------------------------- Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset. @@ -222,42 +249,36 @@ failures as core would send notifications for that. As most cpufreq processors only allow for being set to a few specific frequencies, a "frequency table" with some functions might assist in -some work of the processor driver. Such a "frequency table" consists -of an array of struct cpufreq_frequency_table entries, with any value in -"driver_data" you want to use, and the corresponding frequency in -"frequency". At the end of the table, you need to add a -cpufreq_frequency_table entry with frequency set to CPUFREQ_TABLE_END. And -if you want to skip one entry in the table, set the frequency to -CPUFREQ_ENTRY_INVALID. The entries don't need to be in ascending -order. - -By calling cpufreq_table_validate_and_show(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); -the cpuinfo.min_freq and cpuinfo.max_freq values are detected, and -policy->min and policy->max are set to the same values. This is -helpful for the per-CPU initialization stage. - -int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); -assures that at least one valid frequency is within policy->min and -policy->max, and all other criteria are met. This is helpful for the -->verify call. - -int cpufreq_frequency_table_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); - -is the corresponding frequency table helper for the ->target -stage. Just pass the values to this function, and this function -returns the number of the frequency table entry which contains -the frequency the CPU shall be set to. +some work of the processor driver. Such a "frequency table" consists of +an array of struct cpufreq_frequency_table entries, with driver specific +values in "driver_data", the corresponding frequency in "frequency" and +flags set. At the end of the table, you need to add a +cpufreq_frequency_table entry with frequency set to CPUFREQ_TABLE_END. +And if you want to skip one entry in the table, set the frequency to +CPUFREQ_ENTRY_INVALID. The entries don't need to be in sorted in any +particular order, but if they are cpufreq core will do DVFS a bit +quickly for them as search for best match is faster. + +By calling cpufreq_table_validate_and_show(), the cpuinfo.min_freq and +cpuinfo.max_freq values are detected, and policy->min and policy->max +are set to the same values. This is helpful for the per-CPU +initialization stage. + +cpufreq_frequency_table_verify() assures that at least one valid +frequency is within policy->min and policy->max, and all other criteria +are met. This is helpful for the ->verify call. + +cpufreq_frequency_table_target() is the corresponding frequency table +helper for the ->target stage. Just pass the values to this function, +and this function returns the of the frequency table entry which +contains the frequency the CPU shall be set to. The following macros can be used as iterators over cpufreq_frequency_table: cpufreq_for_each_entry(pos, table) - iterates over all entries of frequency table. -cpufreq-for_each_valid_entry(pos, table) - iterates over all entries, +cpufreq_for_each_valid_entry(pos, table) - iterates over all entries, excluding CPUFREQ_ENTRY_INVALID frequencies. Use arguments "pos" - a cpufreq_frequency_table * as a loop cursor and "table" - the cpufreq_frequency_table * you want to iterate over. diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt index 3c355f6ad834..2bbe207354ed 100644 --- a/Documentation/cpu-freq/cpufreq-stats.txt +++ b/Documentation/cpu-freq/cpufreq-stats.txt @@ -34,10 +34,10 @@ cpufreq stats provides following statistics (explained in detail below). - total_trans - trans_table -All the statistics will be from the time the stats driver has been inserted -to the time when a read of a particular statistic is done. Obviously, stats -driver will not have any information about the frequency transitions before -the stats driver insertion. +All the statistics will be from the time the stats driver has been inserted +(or the time the stats were reset) to the time when a read of a particular +statistic is done. Obviously, stats driver will not have any information +about the frequency transitions before the stats driver insertion. -------------------------------------------------------------------------------- <mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # ls -l @@ -110,25 +110,13 @@ Config Main Menu CPU Frequency scaling ---> [*] CPU Frequency scaling [*] CPU frequency translation statistics - [*] CPU frequency translation statistics details "CPU Frequency scaling" (CONFIG_CPU_FREQ) should be enabled to configure cpufreq-stats. "CPU frequency translation statistics" (CONFIG_CPU_FREQ_STAT) provides the -basic statistics which includes time_in_state and total_trans. +statistics which includes time_in_state, total_trans and trans_table. -"CPU frequency translation statistics details" (CONFIG_CPU_FREQ_STAT_DETAILS) -provides fine grained cpufreq stats by trans_table. The reason for having a -separate config option for trans_table is: -- trans_table goes against the traditional /sysfs rule of one value per - interface. It provides a whole bunch of value in a 2 dimensional matrix - form. - -Once these two options are enabled and your CPU supports cpufrequency, you +Once this option is enabled and your CPU supports cpufrequency, you will be able to see the CPU frequency statistics in /sysfs. - - - - diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt index c15aa75f5227..61b3184b6c24 100644 --- a/Documentation/cpu-freq/governors.txt +++ b/Documentation/cpu-freq/governors.txt @@ -10,6 +10,8 @@ Dominik Brodowski <linux@brodo.de> some additions and corrections by Nico Golde <nico@ngolde.de> + Rafael J. Wysocki <rafael.j.wysocki@intel.com> + Viresh Kumar <viresh.kumar@linaro.org> @@ -28,32 +30,27 @@ Contents: 2.3 Userspace 2.4 Ondemand 2.5 Conservative +2.6 Schedutil 3. The Governor Interface in the CPUfreq Core +4. References 1. What Is A CPUFreq Governor? ============================== Most cpufreq drivers (except the intel_pstate and longrun) or even most -cpu frequency scaling algorithms only offer the CPU to be set to one -frequency. In order to offer dynamic frequency scaling, the cpufreq -core must be able to tell these drivers of a "target frequency". So -these specific drivers will be transformed to offer a "->target/target_index" -call instead of the existing "->setpolicy" call. For "longrun", all -stays the same, though. +cpu frequency scaling algorithms only allow the CPU frequency to be set +to predefined fixed values. In order to offer dynamic frequency +scaling, the cpufreq core must be able to tell these drivers of a +"target frequency". So these specific drivers will be transformed to +offer a "->target/target_index/fast_switch()" call instead of the +"->setpolicy()" call. For set_policy drivers, all stays the same, +though. How to decide what frequency within the CPUfreq policy should be used? -That's done using "cpufreq governors". Two are already in this patch --- they're the already existing "powersave" and "performance" which -set the frequency statically to the lowest or highest frequency, -respectively. At least two more such governors will be ready for -addition in the near future, but likely many more as there are various -different theories and models about dynamic frequency scaling -around. Using such a generic interface as cpufreq offers to scaling -governors, these can be tested extensively, and the best one can be -selected for each specific use. +That's done using "cpufreq governors". Basically, it's the following flow graph: @@ -71,7 +68,7 @@ CPU can be set to switch independently | CPU can only be set / the limits of policy->{min,max} / \ / \ - Using the ->setpolicy call, Using the ->target/target_index call, + Using the ->setpolicy call, Using the ->target/target_index/fast_switch call, the limits and the the frequency closest "policy" is set. to target_freq is set. It is assured that it @@ -109,114 +106,159 @@ directory. 2.4 Ondemand ------------ -The CPUfreq governor "ondemand" sets the CPU depending on the -current usage. To do this the CPU must have the capability to -switch the frequency very quickly. There are a number of sysfs file -accessible parameters: - -sampling_rate: measured in uS (10^-6 seconds), this is how often you -want the kernel to look at the CPU usage and to make decisions on -what to do about the frequency. Typically this is set to values of -around '10000' or more. It's default value is (cmp. with users-guide.txt): -transition_latency * 1000 -Be aware that transition latency is in ns and sampling_rate is in us, so you -get the same sysfs value by default. -Sampling rate should always get adjusted considering the transition latency -To set the sampling rate 750 times as high as the transition latency -in the bash (as said, 1000 is default), do: -echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) \ - >ondemand/sampling_rate - -sampling_rate_min: -The sampling rate is limited by the HW transition latency: -transition_latency * 100 -Or by kernel restrictions: -If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed. -If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is used, the -limits depend on the CONFIG_HZ option: -HZ=1000: min=20000us (20ms) -HZ=250: min=80000us (80ms) -HZ=100: min=200000us (200ms) -The highest value of kernel and HW latency restrictions is shown and -used as the minimum sampling rate. - -up_threshold: defines what the average CPU usage between the samplings -of 'sampling_rate' needs to be for the kernel to make a decision on -whether it should increase the frequency. For example when it is set -to its default value of '95' it means that between the checking -intervals the CPU needs to be on average more than 95% in use to then -decide that the CPU frequency needs to be increased. - -ignore_nice_load: this parameter takes a value of '0' or '1'. When -set to '0' (its default), all processes are counted towards the -'cpu utilisation' value. When set to '1', the processes that are -run with a 'nice' value will not count (and thus be ignored) in the -overall usage calculation. This is useful if you are running a CPU -intensive calculation on your laptop that you do not care how long it -takes to complete as you can 'nice' it and prevent it from taking part -in the deciding process of whether to increase your CPU frequency. - -sampling_down_factor: this parameter controls the rate at which the -kernel makes a decision on when to decrease the frequency while running -at top speed. When set to 1 (the default) decisions to reevaluate load -are made at the same interval regardless of current clock speed. But -when set to greater than 1 (e.g. 100) it acts as a multiplier for the -scheduling interval for reevaluating load when the CPU is at its top -speed due to high load. This improves performance by reducing the overhead -of load evaluation and helping the CPU stay at its top speed when truly -busy, rather than shifting back and forth in speed. This tunable has no -effect on behavior at lower speeds/lower CPU loads. - -powersave_bias: this parameter takes a value between 0 to 1000. It -defines the percentage (times 10) value of the target frequency that -will be shaved off of the target. For example, when set to 100 -- 10%, -when ondemand governor would have targeted 1000 MHz, it will target -1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0 -(disabled) by default. -When AMD frequency sensitivity powersave bias driver -- -drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter -defines the workload frequency sensitivity threshold in which a lower -frequency is chosen instead of ondemand governor's original target. -The frequency sensitivity is a hardware reported (on AMD Family 16h -Processors and above) value between 0 to 100% that tells software how -the performance of the workload running on a CPU will change when -frequency changes. A workload with sensitivity of 0% (memory/IO-bound) -will not perform any better on higher core frequency, whereas a -workload with sensitivity of 100% (CPU-bound) will perform better -higher the frequency. When the driver is loaded, this is set to 400 -by default -- for CPUs running workloads with sensitivity value below -40%, a lower frequency is chosen. Unloading the driver or writing 0 -will disable this feature. +The CPUfreq governor "ondemand" sets the CPU frequency depending on the +current system load. Load estimation is triggered by the scheduler +through the update_util_data->func hook; when triggered, cpufreq checks +the CPU-usage statistics over the last period and the governor sets the +CPU accordingly. The CPU must have the capability to switch the +frequency very quickly. + +Sysfs files: + +* sampling_rate: + + Measured in uS (10^-6 seconds), this is how often you want the kernel + to look at the CPU usage and to make decisions on what to do about the + frequency. Typically this is set to values of around '10000' or more. + It's default value is (cmp. with users-guide.txt): transition_latency + * 1000. Be aware that transition latency is in ns and sampling_rate + is in us, so you get the same sysfs value by default. Sampling rate + should always get adjusted considering the transition latency to set + the sampling rate 750 times as high as the transition latency in the + bash (as said, 1000 is default), do: + + $ echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate + +* sampling_rate_min: + + The sampling rate is limited by the HW transition latency: + transition_latency * 100 + + Or by kernel restrictions: + - If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed. + - If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is + used, the limits depend on the CONFIG_HZ option: + HZ=1000: min=20000us (20ms) + HZ=250: min=80000us (80ms) + HZ=100: min=200000us (200ms) + + The highest value of kernel and HW latency restrictions is shown and + used as the minimum sampling rate. + +* up_threshold: + + This defines what the average CPU usage between the samplings of + 'sampling_rate' needs to be for the kernel to make a decision on + whether it should increase the frequency. For example when it is set + to its default value of '95' it means that between the checking + intervals the CPU needs to be on average more than 95% in use to then + decide that the CPU frequency needs to be increased. + +* ignore_nice_load: + + This parameter takes a value of '0' or '1'. When set to '0' (its + default), all processes are counted towards the 'cpu utilisation' + value. When set to '1', the processes that are run with a 'nice' + value will not count (and thus be ignored) in the overall usage + calculation. This is useful if you are running a CPU intensive + calculation on your laptop that you do not care how long it takes to + complete as you can 'nice' it and prevent it from taking part in the + deciding process of whether to increase your CPU frequency. + +* sampling_down_factor: + + This parameter controls the rate at which the kernel makes a decision + on when to decrease the frequency while running at top speed. When set + to 1 (the default) decisions to reevaluate load are made at the same + interval regardless of current clock speed. But when set to greater + than 1 (e.g. 100) it acts as a multiplier for the scheduling interval + for reevaluating load when the CPU is at its top speed due to high + load. This improves performance by reducing the overhead of load + evaluation and helping the CPU stay at its top speed when truly busy, + rather than shifting back and forth in speed. This tunable has no + effect on behavior at lower speeds/lower CPU loads. + +* powersave_bias: + + This parameter takes a value between 0 to 1000. It defines the + percentage (times 10) value of the target frequency that will be + shaved off of the target. For example, when set to 100 -- 10%, when + ondemand governor would have targeted 1000 MHz, it will target + 1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0 + (disabled) by default. + + When AMD frequency sensitivity powersave bias driver -- + drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter + defines the workload frequency sensitivity threshold in which a lower + frequency is chosen instead of ondemand governor's original target. + The frequency sensitivity is a hardware reported (on AMD Family 16h + Processors and above) value between 0 to 100% that tells software how + the performance of the workload running on a CPU will change when + frequency changes. A workload with sensitivity of 0% (memory/IO-bound) + will not perform any better on higher core frequency, whereas a + workload with sensitivity of 100% (CPU-bound) will perform better + higher the frequency. When the driver is loaded, this is set to 400 by + default -- for CPUs running workloads with sensitivity value below + 40%, a lower frequency is chosen. Unloading the driver or writing 0 + will disable this feature. 2.5 Conservative ---------------- The CPUfreq governor "conservative", much like the "ondemand" -governor, sets the CPU depending on the current usage. It differs in -behaviour in that it gracefully increases and decreases the CPU speed -rather than jumping to max speed the moment there is any load on the -CPU. This behaviour more suitable in a battery powered environment. -The governor is tweaked in the same manner as the "ondemand" governor -through sysfs with the addition of: - -freq_step: this describes what percentage steps the cpu freq should be -increased and decreased smoothly by. By default the cpu frequency will -increase in 5% chunks of your maximum cpu frequency. You can change this -value to anywhere between 0 and 100 where '0' will effectively lock your -CPU at a speed regardless of its load whilst '100' will, in theory, make -it behave identically to the "ondemand" governor. - -down_threshold: same as the 'up_threshold' found for the "ondemand" -governor but for the opposite direction. For example when set to its -default value of '20' it means that if the CPU usage needs to be below -20% between samples to have the frequency decreased. - -sampling_down_factor: similar functionality as in "ondemand" governor. -But in "conservative", it controls the rate at which the kernel makes -a decision on when to decrease the frequency while running in any -speed. Load for frequency increase is still evaluated every -sampling rate. +governor, sets the CPU frequency depending on the current usage. It +differs in behaviour in that it gracefully increases and decreases the +CPU speed rather than jumping to max speed the moment there is any load +on the CPU. This behaviour is more suitable in a battery powered +environment. The governor is tweaked in the same manner as the +"ondemand" governor through sysfs with the addition of: + +* freq_step: + + This describes what percentage steps the cpu freq should be increased + and decreased smoothly by. By default the cpu frequency will increase + in 5% chunks of your maximum cpu frequency. You can change this value + to anywhere between 0 and 100 where '0' will effectively lock your CPU + at a speed regardless of its load whilst '100' will, in theory, make + it behave identically to the "ondemand" governor. + +* down_threshold: + + Same as the 'up_threshold' found for the "ondemand" governor but for + the opposite direction. For example when set to its default value of + '20' it means that if the CPU usage needs to be below 20% between + samples to have the frequency decreased. + +* sampling_down_factor: + + Similar functionality as in "ondemand" governor. But in + "conservative", it controls the rate at which the kernel makes a + decision on when to decrease the frequency while running in any speed. + Load for frequency increase is still evaluated every sampling rate. + + +2.6 Schedutil +------------- + +The "schedutil" governor aims at better integration with the Linux +kernel scheduler. Load estimation is achieved through the scheduler's +Per-Entity Load Tracking (PELT) mechanism, which also provides +information about the recent load [1]. This governor currently does +load based DVFS only for tasks managed by CFS. RT and DL scheduler tasks +are always run at the highest frequency. Unlike all the other +governors, the code is located under the kernel/sched/ directory. + +Sysfs files: + +* rate_limit_us: + + This contains a value in microseconds. The governor waits for + rate_limit_us time before reevaluating the load again, after it has + evaluated the load once. + +For an in-depth comparison with the other governors refer to [2]. + 3. The Governor Interface in the CPUfreq Core ============================================= @@ -225,26 +267,10 @@ A new governor must register itself with the CPUfreq core using "cpufreq_register_governor". The struct cpufreq_governor, which has to be passed to that function, must contain the following values: -governor->name - A unique name for this governor -governor->governor - The governor callback function -governor->owner - .THIS_MODULE for the governor module (if - appropriate) - -The governor->governor callback is called with the current (or to-be-set) -cpufreq_policy struct for that CPU, and an unsigned int event. The -following events are currently defined: - -CPUFREQ_GOV_START: This governor shall start its duty for the CPU - policy->cpu -CPUFREQ_GOV_STOP: This governor shall end its duty for the CPU - policy->cpu -CPUFREQ_GOV_LIMITS: The limits for CPU policy->cpu have changed to - policy->min and policy->max. - -If you need other "events" externally of your driver, _only_ use the -cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the -CPUfreq core to ensure proper locking. +governor->name - A unique name for this governor. +governor->owner - .THIS_MODULE for the governor module (if appropriate). +plus a set of hooks to the functions implementing the governor's logic. The CPUfreq governor may call the CPU processor driver using one of these two functions: @@ -258,12 +284,18 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); target_freq must be within policy->min and policy->max, of course. -What's the difference between these two functions? When your governor -still is in a direct code path of a call to governor->governor, the -per-CPU cpufreq lock is still held in the cpufreq core, and there's -no need to lock it again (in fact, this would cause a deadlock). So -use __cpufreq_driver_target only in these cases. In all other cases -(for example, when there's a "daemonized" function that wakes up -every second), use cpufreq_driver_target to lock the cpufreq per-CPU -lock before the command is passed to the cpufreq processor driver. +What's the difference between these two functions? When your governor is +in a direct code path of a call to governor callbacks, like +governor->start(), the policy->rwsem is still held in the cpufreq core, +and there's no need to lock it again (in fact, this would cause a +deadlock). So use __cpufreq_driver_target only in these cases. In all +other cases (for example, when there's a "daemonized" function that +wakes up every second), use cpufreq_driver_target to take policy->rwsem +before the command is passed to the cpufreq driver. + +4. References +============= + +[1] Per-entity load tracking: https://lwn.net/Articles/531853/ +[2] Improvements in CPU frequency management: https://lwn.net/Articles/682391/ diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt index dc024ab4054f..ef1d39247b05 100644 --- a/Documentation/cpu-freq/index.txt +++ b/Documentation/cpu-freq/index.txt @@ -18,16 +18,29 @@ Documents in this directory: ---------------------------- + +amd-powernow.txt - AMD powernow driver specific file. + +boost.txt - Frequency boosting support. + core.txt - General description of the CPUFreq core and - of CPUFreq notifiers + of CPUFreq notifiers. + +cpu-drivers.txt - How to implement a new cpufreq processor driver. -cpu-drivers.txt - How to implement a new cpufreq processor driver +cpufreq-nforce2.txt - nVidia nForce2 platform specific file. + +cpufreq-stats.txt - General description of sysfs cpufreq stats. governors.txt - What are cpufreq governors and how to implement them? index.txt - File index, Mailing list and Links (this document) +intel-pstate.txt - Intel pstate cpufreq driver specific file. + +pcc-cpufreq.txt - PCC cpufreq driver specific file. + user-guide.txt - User Guide to CPUFreq @@ -35,9 +48,7 @@ Mailing List ------------ There is a CPU frequency changing CVS commit and general list where you can report bugs, problems or submit patches. To post a message, -send an email to linux-pm@vger.kernel.org, to subscribe go to -http://vger.kernel.org/vger-lists.html#linux-pm and follow the -instructions there. +send an email to linux-pm@vger.kernel.org. Links ----- @@ -48,7 +59,7 @@ how to access the CVS repository: * http://cvs.arm.linux.org.uk/ the CPUFreq Mailing list: -* http://vger.kernel.org/vger-lists.html#cpufreq +* http://vger.kernel.org/vger-lists.html#linux-pm Clock and voltage scaling for the SA-1100: * http://www.lartmaker.nl/projects/scaling diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index 1953994ef5e6..3fdcdfd968ba 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -85,6 +85,21 @@ Sysfs will show : Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide" to understand ratios. +There is one more sysfs attribute in /sys/devices/system/cpu/intel_pstate/ +that can be used for controlling the operation mode of the driver: + + status: Three settings are possible: + "off" - The driver is not in use at this time. + "active" - The driver works as a P-state governor (default). + "passive" - The driver works as a regular cpufreq one and collaborates + with the generic cpufreq governors (it sets P-states as + requested by those governors). + The current setting is returned by reads from this attribute. Writing one + of the above strings to it changes the operation mode as indicated by that + string, if possible. If HW-managed P-states (HWP) are enabled, it is not + possible to change the driver's operation mode and attempts to write to + this attribute will fail. + cpufreq sysfs for Intel P-State Since this driver registers with cpufreq, cpufreq sysfs is also presented. diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt index 109e97bbab77..107f6fdd7d14 100644 --- a/Documentation/cpu-freq/user-guide.txt +++ b/Documentation/cpu-freq/user-guide.txt @@ -18,7 +18,7 @@ Contents: --------- 1. Supported Architectures and Processors -1.1 ARM +1.1 ARM and ARM64 1.2 x86 1.3 sparc64 1.4 ppc @@ -37,16 +37,10 @@ Contents: 1. Supported Architectures and Processors ========================================= -1.1 ARM -------- - -The following ARM processors are supported by cpufreq: - -ARM Integrator -ARM-SA1100 -ARM-SA1110 -Intel PXA +1.1 ARM and ARM64 +----------------- +Almost all ARM and ARM64 platforms support CPU frequency scaling. 1.2 x86 ------- @@ -69,6 +63,7 @@ Transmeta Crusoe Transmeta Efficeon VIA Cyrix 3 / C3 various processors on some ACPI 2.0-compatible systems [*] +And many more [*] Only if "ACPI Processor Performance States" are available to the ACPI<->BIOS interface. @@ -147,10 +142,19 @@ mounted it at /sys, the cpufreq interface is located in a subdirectory "cpufreq" within the cpu-device directory (e.g. /sys/devices/system/cpu/cpu0/cpufreq/ for the first CPU). +affected_cpus : List of Online CPUs that require software + coordination of frequency. + +cpuinfo_cur_freq : Current frequency of the CPU as obtained from + the hardware, in KHz. This is the frequency + the CPU actually runs at. + cpuinfo_min_freq : this file shows the minimum operating frequency the processor can run at(in kHz) + cpuinfo_max_freq : this file shows the maximum operating frequency the processor can run at(in kHz) + cpuinfo_transition_latency The time it takes on this CPU to switch between two frequencies in nano seconds. If unknown or known to be @@ -163,25 +167,30 @@ cpuinfo_transition_latency The time it takes on this CPU to userspace daemon. Make sure to not switch the frequency too often resulting in performance loss. -scaling_driver : this file shows what cpufreq driver is - used to set the frequency on this CPU + +related_cpus : List of Online + Offline CPUs that need software + coordination of frequency. + +scaling_available_frequencies : List of available frequencies, in KHz. scaling_available_governors : this file shows the CPUfreq governors available in this kernel. You can see the currently activated governor in +scaling_cur_freq : Current frequency of the CPU as determined by + the governor and cpufreq core, in KHz. This is + the frequency the kernel thinks the CPU runs + at. + +scaling_driver : this file shows what cpufreq driver is + used to set the frequency on this CPU + scaling_governor, and by "echoing" the name of another governor you can change it. Please note that some governors won't load - they only work on some specific architectures or processors. -cpuinfo_cur_freq : Current frequency of the CPU as obtained from - the hardware, in KHz. This is the frequency - the CPU actually runs at. - -scaling_available_frequencies : List of available frequencies, in KHz. - scaling_min_freq and scaling_max_freq show the current "policy limits" (in kHz). By echoing new values into these @@ -190,16 +199,11 @@ scaling_max_freq show the current "policy limits" (in first set scaling_max_freq, then scaling_min_freq. -affected_cpus : List of Online CPUs that require software - coordination of frequency. - -related_cpus : List of Online + Offline CPUs that need software - coordination of frequency. - -scaling_cur_freq : Current frequency of the CPU as determined by - the governor and cpufreq core, in KHz. This is - the frequency the kernel thinks the CPU runs - at. +scaling_setspeed This can be read to get the currently programmed + value by the governor. This can be written to + change the current frequency for a group of + CPUs, represented by a policy. This is supported + currently only by the userspace governor. bios_limit : If the BIOS tells the OS to limit a CPU to lower frequencies, the user can read out the diff --git a/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt b/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt new file mode 100644 index 000000000000..ba0e15ad5bd9 --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt @@ -0,0 +1,128 @@ +TI CPUFreq and OPP bindings +================================ + +Certain TI SoCs, like those in the am335x, am437x, am57xx, and dra7xx +families support different OPPs depending on the silicon variant in use. +The ti-cpufreq driver can use revision and an efuse value from the SoC to +provide the OPP framework with supported hardware information. This is +used to determine which OPPs from the operating-points-v2 table get enabled +when it is parsed by the OPP framework. + +Required properties: +-------------------- +In 'cpus' nodes: +- operating-points-v2: Phandle to the operating-points-v2 table to use. + +In 'operating-points-v2' table: +- compatible: Should be + - 'operating-points-v2-ti-cpu' for am335x, am43xx, and dra7xx/am57xx SoCs +- syscon: A phandle pointing to a syscon node representing the control module + register space of the SoC. + +Optional properties: +-------------------- +For each opp entry in 'operating-points-v2' table: +- opp-supported-hw: Two bitfields indicating: + 1. Which revision of the SoC the OPP is supported by + 2. Which eFuse bits indicate this OPP is available + + A bitwise AND is performed against these values and if any bit + matches, the OPP gets enabled. + +Example: +-------- + +/* From arch/arm/boot/dts/am33xx.dtsi */ +cpus { + #address-cells = <1>; + #size-cells = <0>; + cpu@0 { + compatible = "arm,cortex-a8"; + device_type = "cpu"; + reg = <0>; + + operating-points-v2 = <&cpu0_opp_table>; + + clocks = <&dpll_mpu_ck>; + clock-names = "cpu"; + + clock-latency = <300000>; /* From omap-cpufreq driver */ + }; +}; + +/* + * cpu0 has different OPPs depending on SoC revision and some on revisions + * 0x2 and 0x4 have eFuse bits that indicate if they are available or not + */ +cpu0_opp_table: opp-table { + compatible = "operating-points-v2-ti-cpu"; + syscon = <&scm_conf>; + + /* + * The three following nodes are marked with opp-suspend + * because they can not be enabled simultaneously on a + * single SoC. + */ + opp50@300000000 { + opp-hz = /bits/ 64 <300000000>; + opp-microvolt = <950000 931000 969000>; + opp-supported-hw = <0x06 0x0010>; + opp-suspend; + }; + + opp100@275000000 { + opp-hz = /bits/ 64 <275000000>; + opp-microvolt = <1100000 1078000 1122000>; + opp-supported-hw = <0x01 0x00FF>; + opp-suspend; + }; + + opp100@300000000 { + opp-hz = /bits/ 64 <300000000>; + opp-microvolt = <1100000 1078000 1122000>; + opp-supported-hw = <0x06 0x0020>; + opp-suspend; + }; + + opp100@500000000 { + opp-hz = /bits/ 64 <500000000>; + opp-microvolt = <1100000 1078000 1122000>; + opp-supported-hw = <0x01 0xFFFF>; + }; + + opp100@600000000 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <1100000 1078000 1122000>; + opp-supported-hw = <0x06 0x0040>; + }; + + opp120@600000000 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <1200000 1176000 1224000>; + opp-supported-hw = <0x01 0xFFFF>; + }; + + opp120@720000000 { + opp-hz = /bits/ 64 <720000000>; + opp-microvolt = <1200000 1176000 1224000>; + opp-supported-hw = <0x06 0x0080>; + }; + + oppturbo@720000000 { + opp-hz = /bits/ 64 <720000000>; + opp-microvolt = <1260000 1234800 1285200>; + opp-supported-hw = <0x01 0xFFFF>; + }; + + oppturbo@800000000 { + opp-hz = /bits/ 64 <800000000>; + opp-microvolt = <1260000 1234800 1285200>; + opp-supported-hw = <0x06 0x0100>; + }; + + oppnitro@1000000000 { + opp-hz = /bits/ 64 <1000000000>; + opp-microvolt = <1325000 1298500 1351500>; + opp-supported-hw = <0x04 0x0200>; + }; +}; diff --git a/MAINTAINERS b/MAINTAINERS index 107c10e8f2d2..d4ac248ec31b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2692,6 +2692,13 @@ F: drivers/irqchip/irq-brcmstb* F: include/linux/bcm963xx_nvram.h F: include/linux/bcm963xx_tag.h +BROADCOM BMIPS CPUFREQ DRIVER +M: Markus Mayer <mmayer@broadcom.com> +M: bcm-kernel-feedback-list@broadcom.com +L: linux-pm@vger.kernel.org +S: Maintained +F: drivers/cpufreq/bmips-cpufreq.c + BROADCOM TG3 GIGABIT ETHERNET DRIVER M: Siva Reddy Kallam <siva.kallam@broadcom.com> M: Prashant Sreedharan <prashant@broadcom.com> diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 79c415c33f69..809f0bf3042a 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -24,7 +24,7 @@ CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init=/linuxrc mem=256M" CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig index 361686a362f1..69a4bd13eea5 100644 --- a/arch/arm/configs/multi_v5_defconfig +++ b/arch/arm/configs/multi_v5_defconfig @@ -58,7 +58,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_IDLE=y CONFIG_ARM_KIRKWOOD_CPUIDLE=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 028d2b70e3b5..8d7b17f52750 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -132,7 +132,7 @@ CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_KEXEC=y CONFIG_EFI=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig index f7f6039419aa..4b598da0d086 100644 --- a/arch/arm/configs/mvebu_v5_defconfig +++ b/arch/arm/configs/mvebu_v5_defconfig @@ -44,7 +44,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_IDLE=y CONFIG_ARM_KIRKWOOD_CPUIDLE=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index e4314b1227a3..271dc7e78e43 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -97,7 +97,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_CMDLINE="root=/dev/ram0 ro" CONFIG_KEXEC=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index 1b0f8ae36fb3..adeaecd831a4 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -38,7 +38,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_ARM_APPENDED_DTB=y CONFIG_KEXEC=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b3c5bde43d34..e137eedb90d2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1703,6 +1703,8 @@ config CPU_BMIPS select WEAK_ORDERING select CPU_SUPPORTS_HIGHMEM select CPU_HAS_PREFETCH + select CPU_SUPPORTS_CPUFREQ + select MIPS_EXTERNAL_TIMER help Support for BMIPS32/3300/4350/4380 and BMIPS5000 processors. diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig index 4eb5d6e9cf8f..3cefa6bc01dd 100644 --- a/arch/mips/configs/bmips_stb_defconfig +++ b/arch/mips/configs/bmips_stb_defconfig @@ -9,13 +9,20 @@ CONFIG_MIPS_O32_FP64_SUPPORT=y # CONFIG_SWAP is not set CONFIG_NO_HZ=y CONFIG_BLK_DEV_INITRD=y -CONFIG_RD_GZIP=y CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y +CONFIG_BMIPS_CPUFREQ=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=y @@ -24,7 +31,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_CFG80211=y CONFIG_NL80211_TESTMODE=y @@ -34,8 +40,6 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set -CONFIG_PRINTK_TIME=y -CONFIG_BRCMSTB_GISB_ARB=y CONFIG_MTD=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -51,16 +55,15 @@ CONFIG_USB_USBNET=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set -CONFIG_POWER_SUPPLY=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_BRCMSTB=y CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_SUPPLY=y # CONFIG_HWMON is not set CONFIG_USB=y CONFIG_USB_EHCI_HCD=y @@ -82,6 +85,7 @@ CONFIG_CIFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y +CONFIG_PRINTK_TIME=y CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_CMDLINE_BOOL=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index 5da76e0e120f..bed745596d86 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -40,7 +40,6 @@ CONFIG_PM_STD_PARTITION="/dev/hda3" CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_DEBUG=y CONFIG_CPU_FREQ_STAT=m -CONFIG_CPU_FREQ_STAT_DETAILS=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 3ce91a3df27f..1d2d69dd6409 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -62,7 +62,6 @@ CONFIG_MPC8610_HPCD=y CONFIG_GEF_SBC610=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=m -CONFIG_CPU_FREQ_STAT_DETAILS=y CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig index 9bdcf72ec06a..2fce54d9c388 100644 --- a/arch/sh/configs/sh7785lcr_32bit_defconfig +++ b/arch/sh/configs/sh7785lcr_32bit_defconfig @@ -25,7 +25,7 @@ CONFIG_SH_SH7785LCR=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_SH_CPU_FREQ=y CONFIG_HEARTBEAT=y diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index f0b4a981b8d3..18b72eec3507 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -75,10 +75,8 @@ static int acpi_processor_ppc_notifier(struct notifier_block *nb, struct acpi_processor *pr; unsigned int ppc = 0; - if (event == CPUFREQ_START && ignore_ppc <= 0) { + if (ignore_ppc < 0) ignore_ppc = 0; - return 0; - } if (ignore_ppc) return 0; diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index d8b164a7c4e5..4ebae43118ef 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -37,14 +37,6 @@ config CPU_FREQ_STAT If in doubt, say N. -config CPU_FREQ_STAT_DETAILS - bool "CPU frequency transition statistics details" - depends on CPU_FREQ_STAT - help - Show detailed CPU frequency transition table in sysfs. - - If in doubt, say N. - choice prompt "Default CPUFreq governor" default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ @@ -271,6 +263,16 @@ config IA64_ACPI_CPUFREQ endif if MIPS +config BMIPS_CPUFREQ + tristate "BMIPS CPUfreq Driver" + help + This option adds a CPUfreq driver for BMIPS processors with + support for configurable CPU frequency. + + For now, BMIPS5 chips are supported (such as the Broadcom 7425). + + If in doubt, say N. + config LOONGSON2_CPUFREQ tristate "Loongson2 CPUFreq Driver" help @@ -332,7 +334,7 @@ endif config QORIQ_CPUFREQ tristate "CPU frequency scaling driver for Freescale QorIQ SoCs" - depends on OF && COMMON_CLK && (PPC_E500MC || ARM) + depends on OF && COMMON_CLK && (PPC_E500MC || ARM || ARM64) depends on !CPU_THERMAL || THERMAL select CLK_QORIQ help diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 920c469f3953..74fa5c5904d3 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -247,6 +247,17 @@ config ARM_TEGRA124_CPUFREQ help This adds the CPUFreq driver support for Tegra124 SOCs. +config ARM_TI_CPUFREQ + bool "Texas Instruments CPUFreq support" + depends on ARCH_OMAP2PLUS + help + This driver enables valid OPPs on the running platform based on + values contained within the SoC in use. Enable this in order to + use the cpufreq-dt driver on all Texas Instruments platforms that + provide dt based operating-points-v2 tables with opp-supported-hw + data provided. Required for cpufreq support on AM335x, AM437x, + DRA7x, and AM57x platforms. + config ARM_PXA2xx_CPUFREQ tristate "Intel PXA2xx CPUfreq driver" depends on PXA27x || PXA25x @@ -257,7 +268,7 @@ config ARM_PXA2xx_CPUFREQ config ACPI_CPPC_CPUFREQ tristate "CPUFreq driver based on the ACPI CPPC spec" - depends on ACPI + depends on ACPI_PROCESSOR select ACPI_CPPC_LIB default n help diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 1e46c3918e7a..9f5a8045f36d 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ) += spear-cpufreq.o obj-$(CONFIG_ARM_STI_CPUFREQ) += sti-cpufreq.o obj-$(CONFIG_ARM_TEGRA20_CPUFREQ) += tegra20-cpufreq.o obj-$(CONFIG_ARM_TEGRA124_CPUFREQ) += tegra124-cpufreq.o +obj-$(CONFIG_ARM_TI_CPUFREQ) += ti-cpufreq.o obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ) += vexpress-spc-cpufreq.o obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o obj-$(CONFIG_MACH_MVEBU_V7) += mvebu-cpufreq.o @@ -98,6 +99,7 @@ obj-$(CONFIG_POWERNV_CPUFREQ) += powernv-cpufreq.o # Other platform drivers obj-$(CONFIG_AVR32_AT32AP_CPUFREQ) += at32ap-cpufreq.o obj-$(CONFIG_BFIN_CPU_FREQ) += blackfin-cpufreq.o +obj-$(CONFIG_BMIPS_CPUFREQ) += bmips-cpufreq.o obj-$(CONFIG_CRIS_MACH_ARTPEC3) += cris-artpec3-cpufreq.o obj-$(CONFIG_ETRAXFS) += cris-etraxfs-cpufreq.o obj-$(CONFIG_IA64_ACPI_CPUFREQ) += ia64-acpi-cpufreq.o diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c new file mode 100644 index 000000000000..1653151b77df --- /dev/null +++ b/drivers/cpufreq/bmips-cpufreq.c @@ -0,0 +1,188 @@ +/* + * CPU frequency scaling for Broadcom BMIPS SoCs + * + * Copyright (c) 2017 Broadcom + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/cpufreq.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/slab.h> + +/* for mips_hpt_frequency */ +#include <asm/time.h> + +#define BMIPS_CPUFREQ_PREFIX "bmips" +#define BMIPS_CPUFREQ_NAME BMIPS_CPUFREQ_PREFIX "-cpufreq" + +#define TRANSITION_LATENCY (25 * 1000) /* 25 us */ + +#define BMIPS5_CLK_DIV_SET_SHIFT 0x7 +#define BMIPS5_CLK_DIV_SHIFT 0x4 +#define BMIPS5_CLK_DIV_MASK 0xf + +enum bmips_type { + BMIPS5000, + BMIPS5200, +}; + +struct cpufreq_compat { + const char *compatible; + unsigned int bmips_type; + unsigned int clk_mult; + unsigned int max_freqs; +}; + +#define BMIPS(c, t, m, f) { \ + .compatible = c, \ + .bmips_type = (t), \ + .clk_mult = (m), \ + .max_freqs = (f), \ +} + +static struct cpufreq_compat bmips_cpufreq_compat[] = { + BMIPS("brcm,bmips5000", BMIPS5000, 8, 4), + BMIPS("brcm,bmips5200", BMIPS5200, 8, 4), + { } +}; + +static struct cpufreq_compat *priv; + +static int htp_freq_to_cpu_freq(unsigned int clk_mult) +{ + return mips_hpt_frequency * clk_mult / 1000; +} + +static struct cpufreq_frequency_table * +bmips_cpufreq_get_freq_table(const struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *table; + unsigned long cpu_freq; + int i; + + cpu_freq = htp_freq_to_cpu_freq(priv->clk_mult); + + table = kmalloc((priv->max_freqs + 1) * sizeof(*table), GFP_KERNEL); + if (!table) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < priv->max_freqs; i++) { + table[i].frequency = cpu_freq / (1 << i); + table[i].driver_data = i; + } + table[i].frequency = CPUFREQ_TABLE_END; + + return table; +} + +static unsigned int bmips_cpufreq_get(unsigned int cpu) +{ + unsigned int div; + uint32_t mode; + + switch (priv->bmips_type) { + case BMIPS5200: + case BMIPS5000: + mode = read_c0_brcm_mode(); + div = ((mode >> BMIPS5_CLK_DIV_SHIFT) & BMIPS5_CLK_DIV_MASK); + break; + default: + div = 0; + } + + return htp_freq_to_cpu_freq(priv->clk_mult) / (1 << div); +} + +static int bmips_cpufreq_target_index(struct cpufreq_policy *policy, + unsigned int index) +{ + unsigned int div = policy->freq_table[index].driver_data; + + switch (priv->bmips_type) { + case BMIPS5200: + case BMIPS5000: + change_c0_brcm_mode(BMIPS5_CLK_DIV_MASK << BMIPS5_CLK_DIV_SHIFT, + (1 << BMIPS5_CLK_DIV_SET_SHIFT) | + (div << BMIPS5_CLK_DIV_SHIFT)); + break; + default: + return -ENOTSUPP; + } + + return 0; +} + +static int bmips_cpufreq_exit(struct cpufreq_policy *policy) +{ + kfree(policy->freq_table); + + return 0; +} + +static int bmips_cpufreq_init(struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *freq_table; + int ret; + + freq_table = bmips_cpufreq_get_freq_table(policy); + if (IS_ERR(freq_table)) { + ret = PTR_ERR(freq_table); + pr_err("%s: couldn't determine frequency table (%d).\n", + BMIPS_CPUFREQ_NAME, ret); + return ret; + } + + ret = cpufreq_generic_init(policy, freq_table, TRANSITION_LATENCY); + if (ret) + bmips_cpufreq_exit(policy); + else + pr_info("%s: registered\n", BMIPS_CPUFREQ_NAME); + + return ret; +} + +static struct cpufreq_driver bmips_cpufreq_driver = { + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = bmips_cpufreq_target_index, + .get = bmips_cpufreq_get, + .init = bmips_cpufreq_init, + .exit = bmips_cpufreq_exit, + .attr = cpufreq_generic_attr, + .name = BMIPS_CPUFREQ_PREFIX, +}; + +static int __init bmips_cpufreq_probe(void) +{ + struct cpufreq_compat *cc; + struct device_node *np; + + for (cc = bmips_cpufreq_compat; cc->compatible; cc++) { + np = of_find_compatible_node(NULL, "cpu", cc->compatible); + if (np) { + of_node_put(np); + priv = cc; + break; + } + } + + /* We hit the guard element of the array. No compatible CPU found. */ + if (!cc->compatible) + return -ENODEV; + + return cpufreq_register_driver(&bmips_cpufreq_driver); +} +device_initcall(bmips_cpufreq_probe); + +MODULE_AUTHOR("Markus Mayer <mmayer@broadcom.com>"); +MODULE_DESCRIPTION("CPUfreq driver for Broadcom BMIPS SoCs"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index c94360671f41..7281a2c19c36 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -878,7 +878,6 @@ unmap_intr_base: iounmap(priv->avs_intr_base); unmap_base: iounmap(priv->base); - platform_set_drvdata(pdev, NULL); return ret; } @@ -1042,7 +1041,6 @@ static int brcm_avs_cpufreq_remove(struct platform_device *pdev) priv = platform_get_drvdata(pdev); iounmap(priv->base); iounmap(priv->avs_intr_base); - platform_set_drvdata(pdev, NULL); return 0; } diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 7fcaf26e8f81..921b4a6c3d16 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -87,8 +87,6 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "socionext,uniphier-ld11", }, { .compatible = "socionext,uniphier-ld20", }, - { .compatible = "ti,am33xx", }, - { .compatible = "ti,dra7", }, { .compatible = "ti,omap2", }, { .compatible = "ti,omap3", }, { .compatible = "ti,omap4", }, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index cc475eff90b3..80a785ad17e8 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1078,15 +1078,11 @@ err_free_policy: return NULL; } -static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify) +static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy) { struct kobject *kobj; struct completion *cmp; - if (notify) - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_REMOVE_POLICY, policy); - down_write(&policy->rwsem); cpufreq_stats_free_table(policy); kobj = &policy->kobj; @@ -1104,7 +1100,7 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify) pr_debug("wait complete\n"); } -static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify) +static void cpufreq_policy_free(struct cpufreq_policy *policy) { unsigned long flags; int cpu; @@ -1117,7 +1113,7 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify) per_cpu(cpufreq_cpu_data, cpu) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - cpufreq_policy_put_kobj(policy, notify); + cpufreq_policy_put_kobj(policy); free_cpumask_var(policy->real_cpus); free_cpumask_var(policy->related_cpus); free_cpumask_var(policy->cpus); @@ -1170,8 +1166,6 @@ static int cpufreq_online(unsigned int cpu) if (new_policy) { /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); - /* Clear mask of registered CPUs */ - cpumask_clear(policy->real_cpus); } /* @@ -1244,17 +1238,12 @@ static int cpufreq_online(unsigned int cpu) goto out_exit_policy; cpufreq_stats_create_table(policy); - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_CREATE_POLICY, policy); write_lock_irqsave(&cpufreq_driver_lock, flags); list_add(&policy->policy_list, &cpufreq_policy_list); write_unlock_irqrestore(&cpufreq_driver_lock, flags); } - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_START, policy); - ret = cpufreq_init_policy(policy); if (ret) { pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n", @@ -1282,7 +1271,7 @@ out_exit_policy: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); out_free_policy: - cpufreq_policy_free(policy, !new_policy); + cpufreq_policy_free(policy); return ret; } @@ -1403,7 +1392,7 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) remove_cpu_dev_symlink(policy, dev); if (cpumask_empty(policy->real_cpus)) - cpufreq_policy_free(policy, true); + cpufreq_policy_free(policy); } /** diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index ac284e66839c..18abd454da43 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -25,9 +25,7 @@ struct cpufreq_stats { unsigned int last_index; u64 *time_in_state; unsigned int *freq_table; -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS unsigned int *trans_table; -#endif }; static int cpufreq_stats_update(struct cpufreq_stats *stats) @@ -46,9 +44,7 @@ static void cpufreq_stats_clear_table(struct cpufreq_stats *stats) unsigned int count = stats->max_state; memset(stats->time_in_state, 0, count * sizeof(u64)); -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS memset(stats->trans_table, 0, count * count * sizeof(int)); -#endif stats->last_time = get_jiffies_64(); stats->total_trans = 0; } @@ -84,7 +80,6 @@ static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf, return count; } -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { struct cpufreq_stats *stats = policy->stats; @@ -129,7 +124,6 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) return len; } cpufreq_freq_attr_ro(trans_table); -#endif cpufreq_freq_attr_ro(total_trans); cpufreq_freq_attr_ro(time_in_state); @@ -139,9 +133,7 @@ static struct attribute *default_attrs[] = { &total_trans.attr, &time_in_state.attr, &reset.attr, -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS &trans_table.attr, -#endif NULL }; static struct attribute_group stats_attr_group = { @@ -200,9 +192,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) alloc_size = count * sizeof(int) + count * sizeof(u64); -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS alloc_size += count * count * sizeof(int); -#endif /* Allocate memory for time_in_state/freq_table/trans_table in one go */ stats->time_in_state = kzalloc(alloc_size, GFP_KERNEL); @@ -211,9 +201,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) stats->freq_table = (unsigned int *)(stats->time_in_state + count); -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS stats->trans_table = stats->freq_table + count; -#endif stats->max_state = count; @@ -259,8 +247,6 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy, cpufreq_stats_update(stats); stats->last_index = new_index; -#ifdef CONFIG_CPU_FREQ_STAT_DETAILS stats->trans_table[old_index * stats->max_state + new_index]++; -#endif stats->total_trans++; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 50bd6d987fc3..eb0f7fb71685 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -358,6 +358,8 @@ static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; static bool per_cpu_limits __read_mostly; +static bool driver_registered __read_mostly; + #ifdef CONFIG_ACPI static bool acpi_ppc; #endif @@ -394,6 +396,7 @@ static struct perf_limits *limits = &performance_limits; static struct perf_limits *limits = &powersave_limits; #endif +static DEFINE_MUTEX(intel_pstate_driver_lock); static DEFINE_MUTEX(intel_pstate_limits_lock); #ifdef CONFIG_ACPI @@ -538,7 +541,6 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) acpi_processor_unregister_performance(policy->cpu); } - #else static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { @@ -873,7 +875,10 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); hw_min = HWP_LOWEST_PERF(cap); - hw_max = HWP_HIGHEST_PERF(cap); + if (limits->no_turbo) + hw_max = HWP_GUARANTEED_PERF(cap); + else + hw_max = HWP_HIGHEST_PERF(cap); range = hw_max - hw_min; max_perf_pct = perf_limits->max_perf_pct; @@ -887,11 +892,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) adj_range = max_perf_pct * range / 100; max = hw_min + adj_range; - if (limits->no_turbo) { - hw_max = HWP_GUARANTEED_PERF(cap); - if (hw_max < max) - max = hw_max; - } value &= ~HWP_MAX_PERF(~0L); value |= HWP_MAX_PERF(max); @@ -1007,35 +1007,57 @@ static int pid_param_get(void *data, u64 *val) } DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get, pid_param_set, "%llu\n"); +static struct dentry *debugfs_parent; + struct pid_param { char *name; void *value; + struct dentry *dentry; }; static struct pid_param pid_files[] = { - {"sample_rate_ms", &pid_params.sample_rate_ms}, - {"d_gain_pct", &pid_params.d_gain_pct}, - {"i_gain_pct", &pid_params.i_gain_pct}, - {"deadband", &pid_params.deadband}, - {"setpoint", &pid_params.setpoint}, - {"p_gain_pct", &pid_params.p_gain_pct}, - {NULL, NULL} + {"sample_rate_ms", &pid_params.sample_rate_ms, }, + {"d_gain_pct", &pid_params.d_gain_pct, }, + {"i_gain_pct", &pid_params.i_gain_pct, }, + {"deadband", &pid_params.deadband, }, + {"setpoint", &pid_params.setpoint, }, + {"p_gain_pct", &pid_params.p_gain_pct, }, + {NULL, NULL, } }; -static void __init intel_pstate_debug_expose_params(void) +static void intel_pstate_debug_expose_params(void) { - struct dentry *debugfs_parent; - int i = 0; + int i; debugfs_parent = debugfs_create_dir("pstate_snb", NULL); if (IS_ERR_OR_NULL(debugfs_parent)) return; - while (pid_files[i].name) { - debugfs_create_file(pid_files[i].name, 0660, - debugfs_parent, pid_files[i].value, - &fops_pid_param); - i++; + + for (i = 0; pid_files[i].name; i++) { + struct dentry *dentry; + + dentry = debugfs_create_file(pid_files[i].name, 0660, + debugfs_parent, pid_files[i].value, + &fops_pid_param); + if (!IS_ERR(dentry)) + pid_files[i].dentry = dentry; + } +} + +static void intel_pstate_debug_hide_params(void) +{ + int i; + + if (IS_ERR_OR_NULL(debugfs_parent)) + return; + + for (i = 0; pid_files[i].name; i++) { + debugfs_remove(pid_files[i].dentry); + pid_files[i].dentry = NULL; } + + debugfs_remove(debugfs_parent); + debugfs_parent = NULL; } /************************** debugfs end ************************/ @@ -1048,6 +1070,34 @@ static void __init intel_pstate_debug_expose_params(void) return sprintf(buf, "%u\n", limits->object); \ } +static ssize_t intel_pstate_show_status(char *buf); +static int intel_pstate_update_status(const char *buf, size_t size); + +static ssize_t show_status(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + ssize_t ret; + + mutex_lock(&intel_pstate_driver_lock); + ret = intel_pstate_show_status(buf); + mutex_unlock(&intel_pstate_driver_lock); + + return ret; +} + +static ssize_t store_status(struct kobject *a, struct attribute *b, + const char *buf, size_t count) +{ + char *p = memchr(buf, '\n', count); + int ret; + + mutex_lock(&intel_pstate_driver_lock); + ret = intel_pstate_update_status(buf, p ? p - buf : count); + mutex_unlock(&intel_pstate_driver_lock); + + return ret < 0 ? ret : count; +} + static ssize_t show_turbo_pct(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -1055,12 +1105,22 @@ static ssize_t show_turbo_pct(struct kobject *kobj, int total, no_turbo, turbo_pct; uint32_t turbo_fp; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + cpu = all_cpu_data[0]; total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1; turbo_fp = div_fp(no_turbo, total); turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100))); + + mutex_unlock(&intel_pstate_driver_lock); + return sprintf(buf, "%u\n", turbo_pct); } @@ -1070,8 +1130,18 @@ static ssize_t show_num_pstates(struct kobject *kobj, struct cpudata *cpu; int total; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + cpu = all_cpu_data[0]; total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; + + mutex_unlock(&intel_pstate_driver_lock); + return sprintf(buf, "%u\n", total); } @@ -1080,12 +1150,21 @@ static ssize_t show_no_turbo(struct kobject *kobj, { ssize_t ret; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + update_turbo_state(); if (limits->turbo_disabled) ret = sprintf(buf, "%u\n", limits->turbo_disabled); else ret = sprintf(buf, "%u\n", limits->no_turbo); + mutex_unlock(&intel_pstate_driver_lock); + return ret; } @@ -1099,12 +1178,20 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + mutex_lock(&intel_pstate_limits_lock); update_turbo_state(); if (limits->turbo_disabled) { pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); mutex_unlock(&intel_pstate_limits_lock); + mutex_unlock(&intel_pstate_driver_lock); return -EPERM; } @@ -1114,6 +1201,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_driver_lock); + return count; } @@ -1127,6 +1216,13 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + mutex_lock(&intel_pstate_limits_lock); limits->max_sysfs_pct = clamp_t(int, input, 0 , 100); @@ -1142,6 +1238,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_driver_lock); + return count; } @@ -1155,6 +1253,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_driver_lock); + + if (!driver_registered) { + mutex_unlock(&intel_pstate_driver_lock); + return -EAGAIN; + } + mutex_lock(&intel_pstate_limits_lock); limits->min_sysfs_pct = clamp_t(int, input, 0 , 100); @@ -1170,12 +1275,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, intel_pstate_update_policies(); + mutex_unlock(&intel_pstate_driver_lock); + return count; } show_one(max_perf_pct, max_perf_pct); show_one(min_perf_pct, min_perf_pct); +define_one_global_rw(status); define_one_global_rw(no_turbo); define_one_global_rw(max_perf_pct); define_one_global_rw(min_perf_pct); @@ -1183,6 +1291,7 @@ define_one_global_ro(turbo_pct); define_one_global_ro(num_pstates); static struct attribute *intel_pstate_attributes[] = { + &status.attr, &no_turbo.attr, &turbo_pct.attr, &num_pstates.attr, @@ -1364,48 +1473,71 @@ static int core_get_max_pstate_physical(void) return (value >> 8) & 0xFF; } +static int core_get_tdp_ratio(u64 plat_info) +{ + /* Check how many TDP levels present */ + if (plat_info & 0x600000000) { + u64 tdp_ctrl; + u64 tdp_ratio; + int tdp_msr; + int err; + + /* Get the TDP level (0, 1, 2) to get ratios */ + err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl); + if (err) + return err; + + /* TDP MSR are continuous starting at 0x648 */ + tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03); + err = rdmsrl_safe(tdp_msr, &tdp_ratio); + if (err) + return err; + + /* For level 1 and 2, bits[23:16] contain the ratio */ + if (tdp_ctrl & 0x03) + tdp_ratio >>= 16; + + tdp_ratio &= 0xff; /* ratios are only 8 bits long */ + pr_debug("tdp_ratio %x\n", (int)tdp_ratio); + + return (int)tdp_ratio; + } + + return -ENXIO; +} + static int core_get_max_pstate(void) { u64 tar; u64 plat_info; int max_pstate; + int tdp_ratio; int err; rdmsrl(MSR_PLATFORM_INFO, plat_info); max_pstate = (plat_info >> 8) & 0xFF; + tdp_ratio = core_get_tdp_ratio(plat_info); + if (tdp_ratio <= 0) + return max_pstate; + + if (hwp_active) { + /* Turbo activation ratio is not used on HWP platforms */ + return tdp_ratio; + } + err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar); if (!err) { + int tar_levels; + /* Do some sanity checking for safety */ - if (plat_info & 0x600000000) { - u64 tdp_ctrl; - u64 tdp_ratio; - int tdp_msr; - - err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl); - if (err) - goto skip_tar; - - tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3); - err = rdmsrl_safe(tdp_msr, &tdp_ratio); - if (err) - goto skip_tar; - - /* For level 1 and 2, bits[23:16] contain the ratio */ - if (tdp_ctrl) - tdp_ratio >>= 16; - - tdp_ratio &= 0xff; /* ratios are only 8 bits long */ - if (tdp_ratio - 1 == tar) { - max_pstate = tar; - pr_debug("max_pstate=TAC %x\n", max_pstate); - } else { - goto skip_tar; - } + tar_levels = tar & 0xff; + if (tdp_ratio - 1 == tar_levels) { + max_pstate = tar_levels; + pr_debug("max_pstate=TAC %x\n", max_pstate); } } -skip_tar: return max_pstate; } @@ -2072,6 +2204,20 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) static int intel_pstate_verify_policy(struct cpufreq_policy *policy) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; + struct perf_limits *perf_limits; + + if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) + perf_limits = &performance_limits; + else + perf_limits = &powersave_limits; + + update_turbo_state(); + policy->cpuinfo.max_freq = perf_limits->turbo_disabled || + perf_limits->no_turbo ? + cpu->pstate.max_freq : + cpu->pstate.turbo_freq; + cpufreq_verify_within_cpu_limits(policy); if (policy->policy != CPUFREQ_POLICY_POWERSAVE && @@ -2299,6 +2445,111 @@ static struct cpufreq_driver intel_cpufreq = { static struct cpufreq_driver *intel_pstate_driver = &intel_pstate; +static void intel_pstate_driver_cleanup(void) +{ + unsigned int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + if (all_cpu_data[cpu]) { + if (intel_pstate_driver == &intel_pstate) + intel_pstate_clear_update_util_hook(cpu); + + kfree(all_cpu_data[cpu]); + all_cpu_data[cpu] = NULL; + } + } + put_online_cpus(); +} + +static int intel_pstate_register_driver(void) +{ + int ret; + + ret = cpufreq_register_driver(intel_pstate_driver); + if (ret) { + intel_pstate_driver_cleanup(); + return ret; + } + + mutex_lock(&intel_pstate_limits_lock); + driver_registered = true; + mutex_unlock(&intel_pstate_limits_lock); + + if (intel_pstate_driver == &intel_pstate && !hwp_active && + pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) + intel_pstate_debug_expose_params(); + + return 0; +} + +static int intel_pstate_unregister_driver(void) +{ + if (hwp_active) + return -EBUSY; + + if (intel_pstate_driver == &intel_pstate && !hwp_active && + pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) + intel_pstate_debug_hide_params(); + + mutex_lock(&intel_pstate_limits_lock); + driver_registered = false; + mutex_unlock(&intel_pstate_limits_lock); + + cpufreq_unregister_driver(intel_pstate_driver); + intel_pstate_driver_cleanup(); + + return 0; +} + +static ssize_t intel_pstate_show_status(char *buf) +{ + if (!driver_registered) + return sprintf(buf, "off\n"); + + return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ? + "active" : "passive"); +} + +static int intel_pstate_update_status(const char *buf, size_t size) +{ + int ret; + + if (size == 3 && !strncmp(buf, "off", size)) + return driver_registered ? + intel_pstate_unregister_driver() : -EINVAL; + + if (size == 6 && !strncmp(buf, "active", size)) { + if (driver_registered) { + if (intel_pstate_driver == &intel_pstate) + return 0; + + ret = intel_pstate_unregister_driver(); + if (ret) + return ret; + } + + intel_pstate_driver = &intel_pstate; + return intel_pstate_register_driver(); + } + + if (size == 7 && !strncmp(buf, "passive", size)) { + if (driver_registered) { + if (intel_pstate_driver != &intel_pstate) + return 0; + + ret = intel_pstate_unregister_driver(); + if (ret) + return ret; + } + + intel_pstate_driver = &intel_cpufreq; + return intel_pstate_register_driver(); + } + + return -EINVAL; +} + static int no_load __initdata; static int no_hwp __initdata; static int hwp_only __initdata; @@ -2486,9 +2737,9 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = { static int __init intel_pstate_init(void) { - int cpu, rc = 0; const struct x86_cpu_id *id; struct cpu_defaults *cpu_def; + int rc = 0; if (no_load) return -ENODEV; @@ -2520,45 +2771,29 @@ hwp_cpu_matched: if (intel_pstate_platform_pwr_mgmt_exists()) return -ENODEV; + if (!hwp_active && hwp_only) + return -ENOTSUPP; + pr_info("Intel P-state driver initializing\n"); all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus()); if (!all_cpu_data) return -ENOMEM; - if (!hwp_active && hwp_only) - goto out; - intel_pstate_request_control_from_smm(); - rc = cpufreq_register_driver(intel_pstate_driver); - if (rc) - goto out; - - if (intel_pstate_driver == &intel_pstate && !hwp_active && - pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) - intel_pstate_debug_expose_params(); - intel_pstate_sysfs_expose_params(); + mutex_lock(&intel_pstate_driver_lock); + rc = intel_pstate_register_driver(); + mutex_unlock(&intel_pstate_driver_lock); + if (rc) + return rc; + if (hwp_active) pr_info("HWP enabled\n"); - return rc; -out: - get_online_cpus(); - for_each_online_cpu(cpu) { - if (all_cpu_data[cpu]) { - if (intel_pstate_driver == &intel_pstate) - intel_pstate_clear_update_util_hook(cpu); - - kfree(all_cpu_data[cpu]); - } - } - - put_online_cpus(); - vfree(all_cpu_data); - return -ENODEV; + return 0; } device_initcall(intel_pstate_init); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 37671b545880..3ff5160451b4 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -144,6 +144,7 @@ static struct powernv_pstate_info { unsigned int max; unsigned int nominal; unsigned int nr_pstates; + bool wof_enabled; } powernv_pstate_info; /* Use following macros for conversions between pstate_id and index */ @@ -203,6 +204,7 @@ static int init_powernv_pstates(void) const __be32 *pstate_ids, *pstate_freqs; u32 len_ids, len_freqs; u32 pstate_min, pstate_max, pstate_nominal; + u32 pstate_turbo, pstate_ultra_turbo; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { @@ -225,8 +227,29 @@ static int init_powernv_pstates(void) pr_warn("ibm,pstate-nominal not found\n"); return -ENODEV; } + + if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo", + &pstate_ultra_turbo)) { + powernv_pstate_info.wof_enabled = false; + goto next; + } + + if (of_property_read_u32(power_mgt, "ibm,pstate-turbo", + &pstate_turbo)) { + powernv_pstate_info.wof_enabled = false; + goto next; + } + + if (pstate_turbo == pstate_ultra_turbo) + powernv_pstate_info.wof_enabled = false; + else + powernv_pstate_info.wof_enabled = true; + +next: pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min, pstate_nominal, pstate_max); + pr_info("Workload Optimized Frequency is %s in the platform\n", + (powernv_pstate_info.wof_enabled) ? "enabled" : "disabled"); pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { @@ -268,6 +291,13 @@ static int init_powernv_pstates(void) powernv_pstate_info.nominal = i; else if (id == pstate_min) powernv_pstate_info.min = i; + + if (powernv_pstate_info.wof_enabled && id == pstate_turbo) { + int j; + + for (j = i - 1; j >= (int)powernv_pstate_info.max; j--) + powernv_freqs[j].flags = CPUFREQ_BOOST_FREQ; + } } /* End of list marker entry */ @@ -305,9 +335,12 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy, struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq = __ATTR_RO(cpuinfo_nominal_freq); +#define SCALING_BOOST_FREQS_ATTR_INDEX 2 + static struct freq_attr *powernv_cpu_freq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, &cpufreq_freq_attr_cpuinfo_nominal_freq, + &cpufreq_freq_attr_scaling_boost_freqs, NULL, }; @@ -1013,11 +1046,22 @@ static int __init powernv_cpufreq_init(void) register_reboot_notifier(&powernv_cpufreq_reboot_nb); opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb); + if (powernv_pstate_info.wof_enabled) + powernv_cpufreq_driver.boost_enabled = true; + else + powernv_cpu_freq_attr[SCALING_BOOST_FREQS_ATTR_INDEX] = NULL; + rc = cpufreq_register_driver(&powernv_cpufreq_driver); - if (!rc) - return 0; + if (rc) { + pr_info("Failed to register the cpufreq driver (%d)\n", rc); + goto cleanup_notifiers; + } - pr_info("Failed to register the cpufreq driver (%d)\n", rc); + if (powernv_pstate_info.wof_enabled) + cpufreq_enable_boost_support(); + + return 0; +cleanup_notifiers: unregister_all_notifiers(); clean_chip_info(); out: diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c index dc112481a408..eeaa92251512 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c @@ -100,9 +100,6 @@ static int pmi_notifier(struct notifier_block *nb, /* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY * policy events?) */ - if (event == CPUFREQ_START) - return 0; - node = cbe_cpu_to_node(policy->cpu); pr_debug("got notified, event=%lu, node=%u\n", event, node); diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index 53d8c3fb16f6..a6fefac8afe4 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/clk.h> +#include <linux/clk-provider.h> #include <linux/cpufreq.h> #include <linux/cpu_cooling.h> #include <linux/errno.h> @@ -37,53 +38,20 @@ struct cpu_data { struct thermal_cooling_device *cdev; }; +/* + * Don't use cpufreq on this SoC -- used when the SoC would have otherwise + * matched a more generic compatible. + */ +#define SOC_BLACKLIST 1 + /** * struct soc_data - SoC specific data - * @freq_mask: mask the disallowed frequencies - * @flag: unique flags + * @flags: SOC_xxx */ struct soc_data { - u32 freq_mask[4]; - u32 flag; -}; - -#define FREQ_MASK 1 -/* see hardware specification for the allowed frqeuencies */ -static const struct soc_data sdata[] = { - { /* used by p2041 and p3041 */ - .freq_mask = {0x8, 0x8, 0x2, 0x2}, - .flag = FREQ_MASK, - }, - { /* used by p5020 */ - .freq_mask = {0x8, 0x2}, - .flag = FREQ_MASK, - }, - { /* used by p4080, p5040 */ - .freq_mask = {0}, - .flag = 0, - }, + u32 flags; }; -/* - * the minimum allowed core frequency, in Hz - * for chassis v1.0, >= platform frequency - * for chassis v2.0, >= platform frequency / 2 - */ -static u32 min_cpufreq; -static const u32 *fmask; - -#if defined(CONFIG_ARM) -static int get_cpu_physical_id(int cpu) -{ - return topology_core_id(cpu); -} -#else -static int get_cpu_physical_id(int cpu) -{ - return get_hard_smp_processor_id(cpu); -} -#endif - static u32 get_bus_freq(void) { struct device_node *soc; @@ -101,9 +69,10 @@ static u32 get_bus_freq(void) return sysfreq; } -static struct device_node *cpu_to_clk_node(int cpu) +static struct clk *cpu_to_clk(int cpu) { - struct device_node *np, *clk_np; + struct device_node *np; + struct clk *clk; if (!cpu_present(cpu)) return NULL; @@ -112,37 +81,28 @@ static struct device_node *cpu_to_clk_node(int cpu) if (!np) return NULL; - clk_np = of_parse_phandle(np, "clocks", 0); - if (!clk_np) - return NULL; - + clk = of_clk_get(np, 0); of_node_put(np); - - return clk_np; + return clk; } /* traverse cpu nodes to get cpu mask of sharing clock wire */ static void set_affected_cpus(struct cpufreq_policy *policy) { - struct device_node *np, *clk_np; struct cpumask *dstp = policy->cpus; + struct clk *clk; int i; - np = cpu_to_clk_node(policy->cpu); - if (!np) - return; - for_each_present_cpu(i) { - clk_np = cpu_to_clk_node(i); - if (!clk_np) + clk = cpu_to_clk(i); + if (IS_ERR(clk)) { + pr_err("%s: no clock for cpu %d\n", __func__, i); continue; + } - if (clk_np == np) + if (clk_is_match(policy->clk, clk)) cpumask_set_cpu(i, dstp); - - of_node_put(clk_np); } - of_node_put(np); } /* reduce the duplicated frequencies in frequency table */ @@ -198,10 +158,11 @@ static void freq_table_sort(struct cpufreq_frequency_table *freq_table, static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) { - struct device_node *np, *pnode; + struct device_node *np; int i, count, ret; - u32 freq, mask; + u32 freq; struct clk *clk; + const struct clk_hw *hwclk; struct cpufreq_frequency_table *table; struct cpu_data *data; unsigned int cpu = policy->cpu; @@ -221,17 +182,13 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) goto err_nomem2; } - pnode = of_parse_phandle(np, "clocks", 0); - if (!pnode) { - pr_err("%s: could not get clock information\n", __func__); - goto err_nomem2; - } + hwclk = __clk_get_hw(policy->clk); + count = clk_hw_get_num_parents(hwclk); - count = of_property_count_strings(pnode, "clock-names"); data->pclk = kcalloc(count, sizeof(struct clk *), GFP_KERNEL); if (!data->pclk) { pr_err("%s: no memory\n", __func__); - goto err_node; + goto err_nomem2; } table = kcalloc(count + 1, sizeof(*table), GFP_KERNEL); @@ -240,23 +197,11 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) goto err_pclk; } - if (fmask) - mask = fmask[get_cpu_physical_id(cpu)]; - else - mask = 0x0; - for (i = 0; i < count; i++) { - clk = of_clk_get(pnode, i); + clk = clk_hw_get_parent_by_index(hwclk, i)->clk; data->pclk[i] = clk; freq = clk_get_rate(clk); - /* - * the clock is valid if its frequency is not masked - * and large than minimum allowed frequency. - */ - if (freq < min_cpufreq || (mask & (1 << i))) - table[i].frequency = CPUFREQ_ENTRY_INVALID; - else - table[i].frequency = freq / 1000; + table[i].frequency = freq / 1000; table[i].driver_data = i; } freq_table_redup(table, count); @@ -282,7 +227,6 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = u64temp + 1; of_node_put(np); - of_node_put(pnode); return 0; @@ -290,10 +234,7 @@ err_nomem1: kfree(table); err_pclk: kfree(data->pclk); -err_node: - of_node_put(pnode); err_nomem2: - policy->driver_data = NULL; kfree(data); err_np: of_node_put(np); @@ -357,12 +298,25 @@ static struct cpufreq_driver qoriq_cpufreq_driver = { .attr = cpufreq_generic_attr, }; +static const struct soc_data blacklist = { + .flags = SOC_BLACKLIST, +}; + static const struct of_device_id node_matches[] __initconst = { - { .compatible = "fsl,p2041-clockgen", .data = &sdata[0], }, - { .compatible = "fsl,p3041-clockgen", .data = &sdata[0], }, - { .compatible = "fsl,p5020-clockgen", .data = &sdata[1], }, - { .compatible = "fsl,p4080-clockgen", .data = &sdata[2], }, - { .compatible = "fsl,p5040-clockgen", .data = &sdata[2], }, + /* e6500 cannot use cpufreq due to erratum A-008083 */ + { .compatible = "fsl,b4420-clockgen", &blacklist }, + { .compatible = "fsl,b4860-clockgen", &blacklist }, + { .compatible = "fsl,t2080-clockgen", &blacklist }, + { .compatible = "fsl,t4240-clockgen", &blacklist }, + + { .compatible = "fsl,ls1012a-clockgen", }, + { .compatible = "fsl,ls1021a-clockgen", }, + { .compatible = "fsl,ls1043a-clockgen", }, + { .compatible = "fsl,ls1046a-clockgen", }, + { .compatible = "fsl,ls1088a-clockgen", }, + { .compatible = "fsl,ls2080a-clockgen", }, + { .compatible = "fsl,p4080-clockgen", }, + { .compatible = "fsl,qoriq-clockgen-1.0", }, { .compatible = "fsl,qoriq-clockgen-2.0", }, {} }; @@ -380,16 +334,12 @@ static int __init qoriq_cpufreq_init(void) match = of_match_node(node_matches, np); data = match->data; - if (data) { - if (data->flag) - fmask = data->freq_mask; - min_cpufreq = get_bus_freq(); - } else { - min_cpufreq = get_bus_freq() / 2; - } of_node_put(np); + if (data && data->flags & SOC_BLACKLIST) + return -ENODEV; + ret = cpufreq_register_driver(&qoriq_cpufreq_driver); if (!ret) pr_info("Freescale QorIQ CPU frequency scaling driver\n"); diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c index d6d425773fa4..5b2db3c6568f 100644 --- a/drivers/cpufreq/s3c2416-cpufreq.c +++ b/drivers/cpufreq/s3c2416-cpufreq.c @@ -400,7 +400,6 @@ static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy) rate = clk_get_rate(s3c_freq->hclk); if (rate < 133 * 1000 * 1000) { pr_err("cpufreq: HCLK not at 133MHz\n"); - clk_put(s3c_freq->hclk); ret = -EINVAL; goto err_armclk; } diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c new file mode 100644 index 000000000000..a7b5658c0460 --- /dev/null +++ b/drivers/cpufreq/ti-cpufreq.c @@ -0,0 +1,268 @@ +/* + * TI CPUFreq/OPP hw-supported driver + * + * Copyright (C) 2016-2017 Texas Instruments, Inc. + * Dave Gerlach <d-gerlach@ti.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/cpu.h> +#include <linux/io.h> +#include <linux/mfd/syscon.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/pm_opp.h> +#include <linux/regmap.h> +#include <linux/slab.h> + +#define REVISION_MASK 0xF +#define REVISION_SHIFT 28 + +#define AM33XX_800M_ARM_MPU_MAX_FREQ 0x1E2F +#define AM43XX_600M_ARM_MPU_MAX_FREQ 0xFFA + +#define DRA7_EFUSE_HAS_OD_MPU_OPP 11 +#define DRA7_EFUSE_HAS_HIGH_MPU_OPP 15 +#define DRA7_EFUSE_HAS_ALL_MPU_OPP 23 + +#define DRA7_EFUSE_NOM_MPU_OPP BIT(0) +#define DRA7_EFUSE_OD_MPU_OPP BIT(1) +#define DRA7_EFUSE_HIGH_MPU_OPP BIT(2) + +#define VERSION_COUNT 2 + +struct ti_cpufreq_data; + +struct ti_cpufreq_soc_data { + unsigned long (*efuse_xlate)(struct ti_cpufreq_data *opp_data, + unsigned long efuse); + unsigned long efuse_fallback; + unsigned long efuse_offset; + unsigned long efuse_mask; + unsigned long efuse_shift; + unsigned long rev_offset; +}; + +struct ti_cpufreq_data { + struct device *cpu_dev; + struct device_node *opp_node; + struct regmap *syscon; + const struct ti_cpufreq_soc_data *soc_data; +}; + +static unsigned long amx3_efuse_xlate(struct ti_cpufreq_data *opp_data, + unsigned long efuse) +{ + if (!efuse) + efuse = opp_data->soc_data->efuse_fallback; + /* AM335x and AM437x use "OPP disable" bits, so invert */ + return ~efuse; +} + +static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data, + unsigned long efuse) +{ + unsigned long calculated_efuse = DRA7_EFUSE_NOM_MPU_OPP; + + /* + * The efuse on dra7 and am57 parts contains a specific + * value indicating the highest available OPP. + */ + + switch (efuse) { + case DRA7_EFUSE_HAS_ALL_MPU_OPP: + case DRA7_EFUSE_HAS_HIGH_MPU_OPP: + calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP; + case DRA7_EFUSE_HAS_OD_MPU_OPP: + calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP; + } + + return calculated_efuse; +} + +static struct ti_cpufreq_soc_data am3x_soc_data = { + .efuse_xlate = amx3_efuse_xlate, + .efuse_fallback = AM33XX_800M_ARM_MPU_MAX_FREQ, + .efuse_offset = 0x07fc, + .efuse_mask = 0x1fff, + .rev_offset = 0x600, +}; + +static struct ti_cpufreq_soc_data am4x_soc_data = { + .efuse_xlate = amx3_efuse_xlate, + .efuse_fallback = AM43XX_600M_ARM_MPU_MAX_FREQ, + .efuse_offset = 0x0610, + .efuse_mask = 0x3f, + .rev_offset = 0x600, +}; + +static struct ti_cpufreq_soc_data dra7_soc_data = { + .efuse_xlate = dra7_efuse_xlate, + .efuse_offset = 0x020c, + .efuse_mask = 0xf80000, + .efuse_shift = 19, + .rev_offset = 0x204, +}; + +/** + * ti_cpufreq_get_efuse() - Parse and return efuse value present on SoC + * @opp_data: pointer to ti_cpufreq_data context + * @efuse_value: Set to the value parsed from efuse + * + * Returns error code if efuse not read properly. + */ +static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data, + u32 *efuse_value) +{ + struct device *dev = opp_data->cpu_dev; + u32 efuse; + int ret; + + ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset, + &efuse); + if (ret) { + dev_err(dev, + "Failed to read the efuse value from syscon: %d\n", + ret); + return ret; + } + + efuse = (efuse & opp_data->soc_data->efuse_mask); + efuse >>= opp_data->soc_data->efuse_shift; + + *efuse_value = opp_data->soc_data->efuse_xlate(opp_data, efuse); + + return 0; +} + +/** + * ti_cpufreq_get_rev() - Parse and return rev value present on SoC + * @opp_data: pointer to ti_cpufreq_data context + * @revision_value: Set to the value parsed from revision register + * + * Returns error code if revision not read properly. + */ +static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data, + u32 *revision_value) +{ + struct device *dev = opp_data->cpu_dev; + u32 revision; + int ret; + + ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset, + &revision); + if (ret) { + dev_err(dev, + "Failed to read the revision number from syscon: %d\n", + ret); + return ret; + } + + *revision_value = BIT((revision >> REVISION_SHIFT) & REVISION_MASK); + + return 0; +} + +static int ti_cpufreq_setup_syscon_register(struct ti_cpufreq_data *opp_data) +{ + struct device *dev = opp_data->cpu_dev; + struct device_node *np = opp_data->opp_node; + + opp_data->syscon = syscon_regmap_lookup_by_phandle(np, + "syscon"); + if (IS_ERR(opp_data->syscon)) { + dev_err(dev, + "\"syscon\" is missing, cannot use OPPv2 table.\n"); + return PTR_ERR(opp_data->syscon); + } + + return 0; +} + +static const struct of_device_id ti_cpufreq_of_match[] = { + { .compatible = "ti,am33xx", .data = &am3x_soc_data, }, + { .compatible = "ti,am4372", .data = &am4x_soc_data, }, + { .compatible = "ti,dra7", .data = &dra7_soc_data }, + {}, +}; + +static int ti_cpufreq_init(void) +{ + u32 version[VERSION_COUNT]; + struct device_node *np; + const struct of_device_id *match; + struct ti_cpufreq_data *opp_data; + int ret; + + np = of_find_node_by_path("/"); + match = of_match_node(ti_cpufreq_of_match, np); + if (!match) + return -ENODEV; + + opp_data = kzalloc(sizeof(*opp_data), GFP_KERNEL); + if (!opp_data) + return -ENOMEM; + + opp_data->soc_data = match->data; + + opp_data->cpu_dev = get_cpu_device(0); + if (!opp_data->cpu_dev) { + pr_err("%s: Failed to get device for CPU0\n", __func__); + return -ENODEV; + } + + opp_data->opp_node = dev_pm_opp_of_get_opp_desc_node(opp_data->cpu_dev); + if (!opp_data->opp_node) { + dev_info(opp_data->cpu_dev, + "OPP-v2 not supported, cpufreq-dt will attempt to use legacy tables.\n"); + goto register_cpufreq_dt; + } + + ret = ti_cpufreq_setup_syscon_register(opp_data); + if (ret) + goto fail_put_node; + + /* + * OPPs determine whether or not they are supported based on + * two metrics: + * 0 - SoC Revision + * 1 - eFuse value + */ + ret = ti_cpufreq_get_rev(opp_data, &version[0]); + if (ret) + goto fail_put_node; + + ret = ti_cpufreq_get_efuse(opp_data, &version[1]); + if (ret) + goto fail_put_node; + + of_node_put(opp_data->opp_node); + + ret = PTR_ERR_OR_ZERO(dev_pm_opp_set_supported_hw(opp_data->cpu_dev, + version, VERSION_COUNT)); + if (ret) { + dev_err(opp_data->cpu_dev, + "Failed to set supported hardware\n"); + goto fail_put_node; + } + +register_cpufreq_dt: + platform_device_register_simple("cpufreq-dt", -1, NULL, 0); + + return 0; + +fail_put_node: + of_node_put(opp_data->opp_node); + + return ret; +} +device_initcall(ti_cpufreq_init); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7e05c5e4e45c..87165f06a307 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -31,7 +31,7 @@ #define CPUFREQ_ETERNAL (-1) #define CPUFREQ_NAME_LEN 16 -/* Print length for names. Extra 1 space for accomodating '\n' in prints */ +/* Print length for names. Extra 1 space for accommodating '\n' in prints */ #define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) struct cpufreq_governor; @@ -115,7 +115,7 @@ struct cpufreq_policy { * guarantee that frequency can be changed on any CPU sharing the * policy and that the change will affect all of the policy CPUs then. * - fast_switch_enabled is to be set by governors that support fast - * freqnency switching with the help of cpufreq_enable_fast_switch(). + * frequency switching with the help of cpufreq_enable_fast_switch(). */ bool fast_switch_possible; bool fast_switch_enabled; @@ -415,9 +415,6 @@ static inline void cpufreq_resume(void) {} /* Policy Notifiers */ #define CPUFREQ_ADJUST (0) #define CPUFREQ_NOTIFY (1) -#define CPUFREQ_START (2) -#define CPUFREQ_CREATE_POLICY (3) -#define CPUFREQ_REMOVE_POLICY (4) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); |