From 6e218d21acef34b2db633c16cc6a7ebf5ba8c74d Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Wed, 7 Nov 2018 11:13:46 -0500 Subject: [PATCH 01/17] cpufreq: s3c24xx: Change to use DEFINE_SHOW_ATTRIBUTE macro Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code. Signed-off-by: Yangtao Li Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/s3c24xx-cpufreq-debugfs.c | 46 +++-------------------- 1 file changed, 6 insertions(+), 40 deletions(-) diff --git a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c index 4d976e8dbb2f..0df87b6480fe 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c +++ b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c @@ -63,18 +63,7 @@ static int board_show(struct seq_file *seq, void *p) return 0; } -static int fops_board_open(struct inode *inode, struct file *file) -{ - return single_open(file, board_show, NULL); -} - -static const struct file_operations fops_board = { - .open = fops_board_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; +DEFINE_SHOW_ATTRIBUTE(board); static int info_show(struct seq_file *seq, void *p) { @@ -105,18 +94,7 @@ static int info_show(struct seq_file *seq, void *p) return 0; } -static int fops_info_open(struct inode *inode, struct file *file) -{ - return single_open(file, info_show, NULL); -} - -static const struct file_operations fops_info = { - .open = fops_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; +DEFINE_SHOW_ATTRIBUTE(info); static int io_show(struct seq_file *seq, void *p) { @@ -162,19 +140,7 @@ static int io_show(struct seq_file *seq, void *p) return 0; } -static int fops_io_open(struct inode *inode, struct file *file) -{ - return single_open(file, io_show, NULL); -} - -static const struct file_operations fops_io = { - .open = fops_io_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - +DEFINE_SHOW_ATTRIBUTE(io); static int __init s3c_freq_debugfs_init(void) { @@ -185,13 +151,13 @@ static int __init s3c_freq_debugfs_init(void) } dbgfs_file_io = debugfs_create_file("io-timing", S_IRUGO, dbgfs_root, - NULL, &fops_io); + NULL, &io_fops); dbgfs_file_info = debugfs_create_file("info", S_IRUGO, dbgfs_root, - NULL, &fops_info); + NULL, &info_fops); dbgfs_file_board = debugfs_create_file("board", S_IRUGO, dbgfs_root, - NULL, &fops_board); + NULL, &board_fops); return 0; } From af3b7379e2d709f2d7c6966b8a6f5ec6bd134241 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Fri, 16 Nov 2018 14:24:19 -0800 Subject: [PATCH 02/17] cpufreq: intel_pstate: Force HWP min perf before offline Force HWP Request MAX = HWP Request MIN = HWP Capability MIN and EPP to 0xFF. In this way the performance limits on the offlined CPU will not influence performance limits on its sibling CPU, which is still online. If the sibling CPU is calling for higher performance, it will impact the max core performance. Here core performance will follow higher of the performance requests from each sibling. Reported-and-tested-by: Chen Yu Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 9578312e43f2..106402b89961 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -830,6 +830,28 @@ skip_epp: wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } +static void intel_pstate_hwp_force_min_perf(int cpu) +{ + u64 value; + int min_perf; + + value = all_cpu_data[cpu]->hwp_req_cached; + value &= ~GENMASK_ULL(31, 0); + min_perf = HWP_LOWEST_PERF(all_cpu_data[cpu]->hwp_cap_cached); + + /* Set hwp_max = hwp_min */ + value |= HWP_MAX_PERF(min_perf); + value |= HWP_MIN_PERF(min_perf); + + /* Set EPP/EPB to min */ + if (static_cpu_has(X86_FEATURE_HWP_EPP)) + value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE); + else + intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE); + + wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); +} + static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) { struct cpudata *cpu_data = all_cpu_data[policy->cpu]; @@ -2084,10 +2106,12 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) pr_debug("CPU %d exiting\n", policy->cpu); intel_pstate_clear_update_util_hook(policy->cpu); - if (hwp_active) + if (hwp_active) { intel_pstate_hwp_save_state(policy); - else + intel_pstate_hwp_force_min_perf(policy->cpu); + } else { intel_cpufreq_stop_cpu(policy); + } } static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) From 60935c17e26ac2cfc4095bed02a6b4135c3e6d4a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Fri, 16 Nov 2018 14:24:20 -0800 Subject: [PATCH 03/17] Documentation: intel_pstate: Clarify coordination of P-State limits Explain influence of per-core P-states and hyper threading on the effective performance. Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- Documentation/admin-guide/pm/intel_pstate.rst | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index ac6f5c597a56..ec0f7c111f65 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -495,7 +495,15 @@ on the following rules, regardless of the current operation mode of the driver: 2. Each individual CPU is affected by its own per-policy limits (that is, it cannot be requested to run faster than its own per-policy maximum and it - cannot be requested to run slower than its own per-policy minimum). + cannot be requested to run slower than its own per-policy minimum). The + effective performance depends on whether the platform supports per core + P-states, hyper-threading is enabled and on current performance requests + from other CPUs. When platform doesn't support per core P-states, the + effective performance can be more than the policy limits set on a CPU, if + other CPUs are requesting higher performance at that moment. Even with per + core P-states support, when hyper-threading is enabled, if the sibling CPU + is requesting higher performance, the other siblings will get higher + performance than their policy limits. 3. The global and per-policy limits can be set independently. From 3be466d681a92300908c51888f75cf298e040558 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 20 Nov 2018 11:05:30 -0500 Subject: [PATCH 04/17] cpufreq: powernv: add of_node_put() The of_find_node_by_path() returns a node pointer with refcount incremented,but there is the lack of use of the of_node_put() when done.Add the missing of_node_put() to release the refcount. Signed-off-by: Yangtao Li Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/powernv-cpufreq.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index bf6519cf64bc..7e7ad3879c4e 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -253,18 +253,18 @@ static int init_powernv_pstates(void) if (of_property_read_u32(power_mgt, "ibm,pstate-min", &pstate_min)) { pr_warn("ibm,pstate-min node not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-max", &pstate_max)) { pr_warn("ibm,pstate-max node not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-nominal", &pstate_nominal)) { pr_warn("ibm,pstate-nominal not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo", @@ -293,14 +293,14 @@ next: pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { pr_warn("ibm,pstate-ids not found\n"); - return -ENODEV; + goto out; } pstate_freqs = of_get_property(power_mgt, "ibm,pstate-frequencies-mhz", &len_freqs); if (!pstate_freqs) { pr_warn("ibm,pstate-frequencies-mhz not found\n"); - return -ENODEV; + goto out; } if (len_ids != len_freqs) { @@ -311,7 +311,7 @@ next: nr_pstates = min(len_ids, len_freqs) / sizeof(u32); if (!nr_pstates) { pr_warn("No PStates found\n"); - return -ENODEV; + goto out; } powernv_pstate_info.nr_pstates = nr_pstates; @@ -352,7 +352,12 @@ next: /* End of list marker entry */ powernv_freqs[i].frequency = CPUFREQ_TABLE_END; + + of_node_put(power_mgt); return 0; +out: + of_node_put(power_mgt); + return -ENODEV; } /* Returns the CPU frequency corresponding to the pstate_id. */ From 0dc0eb78155bcc997932b7f19151ae3dd2748096 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Fri, 23 Nov 2018 08:33:40 -0500 Subject: [PATCH 05/17] cpufreq: pmac64: add of_node_put() of_find_node_by_path() acquires a reference to the node returned by it and that reference needs to be dropped by its caller. g5_neo2_cpufreq_init() doesn't do that, so fix it. Signed-off-by: Yangtao Li Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/pmac64-cpufreq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c index be623dd7b9f2..1d32a863332d 100644 --- a/drivers/cpufreq/pmac64-cpufreq.c +++ b/drivers/cpufreq/pmac64-cpufreq.c @@ -411,6 +411,7 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpunode) pfunc_set_vdnap0 = pmf_find_function(root, "set-vdnap0"); pfunc_vdnap0_complete = pmf_find_function(root, "slewing-done"); + of_node_put(root); if (pfunc_set_vdnap0 == NULL || pfunc_vdnap0_complete == NULL) { pr_err("Can't find required platform function\n"); From 58ad4e619747f6b2711396ad068af84185afb74d Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Mon, 26 Nov 2018 02:59:45 +0000 Subject: [PATCH 06/17] cpufreq: imx6q: remove unused code In voltage scale down path, the return value is NOT used at all, remove them to simplify the code. Signed-off-by: Anson Huang Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/imx6q-cpufreq.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index d8c3595e9023..8cb9683f94d3 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -177,22 +177,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) /* scaling down? scale voltage after frequency */ if (new_freq < old_freq) { ret = regulator_set_voltage_tol(arm_reg, volt, 0); - if (ret) { + if (ret) dev_warn(cpu_dev, "failed to scale vddarm down: %d\n", ret); - ret = 0; - } ret = regulator_set_voltage_tol(soc_reg, imx6_soc_volt[index], 0); - if (ret) { + if (ret) dev_warn(cpu_dev, "failed to scale vddsoc down: %d\n", ret); - ret = 0; - } if (!IS_ERR(pu_reg)) { ret = regulator_set_voltage_tol(pu_reg, imx6_soc_volt[index], 0); - if (ret) { + if (ret) dev_warn(cpu_dev, "failed to scale vddpu down: %d\n", ret); - ret = 0; - } } } From cccf6ae52d35f77fc8e8792d29b877024fdbe392 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Mon, 26 Nov 2018 02:59:48 +0000 Subject: [PATCH 07/17] cpufreq: imx6q: save one condition block for normal case of nvmem read Put return value checks of calling imx6ul_opp_check_speed_grading() into one block to save one condition block for normal case. Signed-off-by: Anson Huang Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/imx6q-cpufreq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 8cb9683f94d3..9fedf627e000 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -405,9 +405,10 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) if (of_machine_is_compatible("fsl,imx6ul") || of_machine_is_compatible("fsl,imx6ull")) { ret = imx6ul_opp_check_speed_grading(cpu_dev); - if (ret == -EPROBE_DEFER) - return ret; if (ret) { + if (ret == -EPROBE_DEFER) + return ret; + dev_err(cpu_dev, "failed to read ocotp: %d\n", ret); return ret; From aa5eee355b466cb33f97f79bed9740a472c4ab73 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 29 Nov 2018 22:22:04 +0100 Subject: [PATCH 08/17] Documentation: admin-guide: PM: Add cpuidle document Important information is missing from user/admin cpuidle documentation available today, so add a new user/admin document for cpuidle containing current and comprehensive information to admin-guide and drop the old .txt documents it is replacing. Signed-off-by: Rafael J. Wysocki Reviewed-by: Viresh Kumar Reviewed-by: Ulf Hansson --- Documentation/admin-guide/pm/cpuidle.rst | 614 ++++++++++++++++++ .../admin-guide/pm/working-state.rst | 1 + Documentation/cpuidle/core.txt | 23 - Documentation/cpuidle/sysfs.txt | 98 --- 4 files changed, 615 insertions(+), 121 deletions(-) create mode 100644 Documentation/admin-guide/pm/cpuidle.rst delete mode 100644 Documentation/cpuidle/core.txt delete mode 100644 Documentation/cpuidle/sysfs.txt diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst new file mode 100644 index 000000000000..80b4f26547ac --- /dev/null +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -0,0 +1,614 @@ +.. |struct cpuidle_state| replace:: :c:type:`struct cpuidle_state ` +.. |cpufreq| replace:: :doc:`CPU Performance Scaling ` + +======================== +CPU Idle Time Management +======================== + +:: + + Copyright (c) 2018 Intel Corp., Rafael J. Wysocki + +Concepts +======== + +Modern processors are generally able to enter states in which the execution of +a program is suspended and instructions belonging to it are not fetched from +memory or executed. Those states are the *idle* states of the processor. + +Since part of the processor hardware is not used in idle states, entering them +generally allows power drawn by the processor to be reduced and, in consequence, +it is an opportunity to save energy. + +CPU idle time management is an energy-efficiency feature concerned about using +the idle states of processors for this purpose. + +Logical CPUs +------------ + +CPU idle time management operates on CPUs as seen by the *CPU scheduler* (that +is the part of the kernel responsible for the distribution of computational +work in the system). In its view, CPUs are *logical* units. That is, they need +not be separate physical entities and may just be interfaces appearing to +software as individual single-core processors. In other words, a CPU is an +entity which appears to be fetching instructions that belong to one sequence +(program) from memory and executing them, but it need not work this way +physically. Generally, three different cases can be consider here. + +First, if the whole processor can only follow one sequence of instructions (one +program) at a time, it is a CPU. In that case, if the hardware is asked to +enter an idle state, that applies to the processor as a whole. + +Second, if the processor is multi-core, each core in it is able to follow at +least one program at a time. The cores need not be entirely independent of each +other (for example, they may share caches), but still most of the time they +work physically in parallel with each other, so if each of them executes only +one program, those programs run mostly independently of each other at the same +time. The entire cores are CPUs in that case and if the hardware is asked to +enter an idle state, that applies to the core that asked for it in the first +place, but it also may apply to a larger unit (say a "package" or a "cluster") +that the core belongs to (in fact, it may apply to an entire hierarchy of larger +units containing the core). Namely, if all of the cores in the larger unit +except for one have been put into idle states at the "core level" and the +remaining core asks the processor to enter an idle state, that may trigger it +to put the whole larger unit into an idle state which also will affect the +other cores in that unit. + +Finally, each core in a multi-core processor may be able to follow more than one +program in the same time frame (that is, each core may be able to fetch +instructions from multiple locations in memory and execute them in the same time +frame, but not necessarily entirely in parallel with each other). In that case +the cores present themselves to software as "bundles" each consisting of +multiple individual single-core "processors", referred to as *hardware threads* +(or hyper-threads specifically on Intel hardware), that each can follow one +sequence of instructions. Then, the hardware threads are CPUs from the CPU idle +time management perspective and if the processor is asked to enter an idle state +by one of them, the hardware thread (or CPU) that asked for it is stopped, but +nothing more happens, unless all of the other hardware threads within the same +core also have asked the processor to enter an idle state. In that situation, +the core may be put into an idle state individually or a larger unit containing +it may be put into an idle state as a whole (if the other cores within the +larger unit are in idle states already). + +Idle CPUs +--------- + +Logical CPUs, simply referred to as "CPUs" in what follows, are regarded as +*idle* by the Linux kernel when there are no tasks to run on them except for the +special "idle" task. + +Tasks are the CPU scheduler's representation of work. Each task consists of a +sequence of instructions to execute, or code, data to be manipulated while +running that code, and some context information that needs to be loaded into the +processor every time the task's code is run by a CPU. The CPU scheduler +distributes work by assigning tasks to run to the CPUs present in the system. + +Tasks can be in various states. In particular, they are *runnable* if there are +no specific conditions preventing their code from being run by a CPU as long as +there is a CPU available for that (for example, they are not waiting for any +events to occur or similar). When a task becomes runnable, the CPU scheduler +assigns it to one of the available CPUs to run and if there are no more runnable +tasks assigned to it, the CPU will load the given task's context and run its +code (from the instruction following the last one executed so far, possibly by +another CPU). [If there are multiple runnable tasks assigned to one CPU +simultaneously, they will be subject to prioritization and time sharing in order +to allow them to make some progress over time.] + +The special "idle" task becomes runnable if there are no other runnable tasks +assigned to the given CPU and the CPU is then regarded as idle. In other words, +in Linux idle CPUs run the code of the "idle" task called *the idle loop*. That +code may cause the processor to be put into one of its idle states, if they are +supported, in order to save energy, but if the processor does not support any +idle states, or there is not enough time to spend in an idle state before the +next wakeup event, or there are strict latency constraints preventing any of the +available idle states from being used, the CPU will simply execute more or less +useless instructions in a loop until it is assigned a new task to run. + + +.. _idle-loop: + +The Idle Loop +============= + +The idle loop code takes two major steps in every iteration of it. First, it +calls into a code module referred to as the *governor* that belongs to the CPU +idle time management subsystem called ``CPUIdle`` to select an idle state for +the CPU to ask the hardware to enter. Second, it invokes another code module +from the ``CPUIdle`` subsystem, called the *driver*, to actually ask the +processor hardware to enter the idle state selected by the governor. + +The role of the governor is to find an idle state most suitable for the +conditions at hand. For this purpose, idle states that the hardware can be +asked to enter by logical CPUs are represented in an abstract way independent of +the platform or the processor architecture and organized in a one-dimensional +(linear) array. That array has to be prepared and supplied by the ``CPUIdle`` +driver matching the platform the kernel is running on at the initialization +time. This allows ``CPUIdle`` governors to be independent of the underlying +hardware and to work with any platforms that the Linux kernel can run on. + +Each idle state present in that array is characterized by two parameters to be +taken into account by the governor, the *target residency* and the (worst-case) +*exit latency*. The target residency is the minimum time the hardware must +spend in the given state, including the time needed to enter it (which may be +substantial), in order to save more energy than it would save by entering one of +the shallower idle states instead. [The "depth" of an idle state roughly +corresponds to the power drawn by the processor in that state.] The exit +latency, in turn, is the maximum time it will take a CPU asking the processor +hardware to enter an idle state to start executing the first instruction after a +wakeup from that state. Note that in general the exit latency also must cover +the time needed to enter the given state in case the wakeup occurs when the +hardware is entering it and it must be entered completely to be exited in an +ordered manner. + +There are two types of information that can influence the governor's decisions. +First of all, the governor knows the time until the closest timer event. That +time is known exactly, because the kernel programs timers and it knows exactly +when they will trigger, and it is the maximum time the hardware that the given +CPU depends on can spend in an idle state, including the time necessary to enter +and exit it. However, the CPU may be woken up by a non-timer event at any time +(in particular, before the closest timer triggers) and it generally is not known +when that may happen. The governor can only see how much time the CPU actually +was idle after it has been woken up (that time will be referred to as the *idle +duration* from now on) and it can use that information somehow along with the +time until the closest timer to estimate the idle duration in future. How the +governor uses that information depends on what algorithm is implemented by it +and that is the primary reason for having more than one governor in the +``CPUIdle`` subsystem. + +There are two ``CPUIdle`` governors available, ``menu`` and ``ladder``. Which +of them is used depends on the configuration of the kernel and in particular on +whether or not the scheduler tick can be `stopped by the idle +loop `_. It is possible to change the governor at run time +if the ``cpuidle_sysfs_switch`` command line parameter has been passed to the +kernel, but that is not safe in general, so it should not be done on production +systems (that may change in the future, though). The name of the ``CPUIdle`` +governor currently used by the kernel can be read from the +:file:`current_governor_ro` (or :file:`current_governor` if +``cpuidle_sysfs_switch`` is present in the kernel command line) file under +:file:`/sys/devices/system/cpu/cpuidle/` in ``sysfs``. + +Which ``CPUIdle`` driver is used, on the other hand, usually depends on the +platform the kernel is running on, but there are platforms with more than one +matching driver. For example, there are two drivers that can work with the +majority of Intel platforms, ``intel_idle`` and ``acpi_idle``, one with +hardcoded idle states information and the other able to read that information +from the system's ACPI tables, respectively. Still, even in those cases, the +driver chosen at the system initialization time cannot be replaced later, so the +decision on which one of them to use has to be made early (on Intel platforms +the ``acpi_idle`` driver will be used if ``intel_idle`` is disabled for some +reason or if it does not recognize the processor). The name of the ``CPUIdle`` +driver currently used by the kernel can be read from the :file:`current_driver` +file under :file:`/sys/devices/system/cpu/cpuidle/` in ``sysfs``. + + +.. _idle-cpus-and-tick: + +Idle CPUs and The Scheduler Tick +================================ + +The scheduler tick is a timer that triggers periodically in order to implement +the time sharing strategy of the CPU scheduler. Of course, if there are +multiple runnable tasks assigned to one CPU at the same time, the only way to +allow them to make reasonable progress in a given time frame is to make them +share the available CPU time. Namely, in rough approximation, each task is +given a slice of the CPU time to run its code, subject to the scheduling class, +prioritization and so on and when that time slice is used up, the CPU should be +switched over to running (the code of) another task. The currently running task +may not want to give the CPU away voluntarily, however, and the scheduler tick +is there to make the switch happen regardless. That is not the only role of the +tick, but it is the primary reason for using it. + +The scheduler tick is problematic from the CPU idle time management perspective, +because it triggers periodically and relatively often (depending on the kernel +configuration, the length of the tick period is between 1 ms and 10 ms). +Thus, if the tick is allowed to trigger on idle CPUs, it will not make sense +for them to ask the hardware to enter idle states with target residencies above +the tick period length. Moreover, in that case the idle duration of any CPU +will never exceed the tick period length and the energy used for entering and +exiting idle states due to the tick wakeups on idle CPUs will be wasted. + +Fortunately, it is not really necessary to allow the tick to trigger on idle +CPUs, because (by definition) they have no tasks to run except for the special +"idle" one. In other words, from the CPU scheduler perspective, the only user +of the CPU time on them is the idle loop. Since the time of an idle CPU need +not be shared between multiple runnable tasks, the primary reason for using the +tick goes away if the given CPU is idle. Consequently, it is possible to stop +the scheduler tick entirely on idle CPUs in principle, even though that may not +always be worth the effort. + +Whether or not it makes sense to stop the scheduler tick in the idle loop +depends on what is expected by the governor. First, if there is another +(non-tick) timer due to trigger within the tick range, stopping the tick clearly +would be a waste of time, even though the timer hardware may not need to be +reprogrammed in that case. Second, if the governor is expecting a non-timer +wakeup within the tick range, stopping the tick is not necessary and it may even +be harmful. Namely, in that case the governor will select an idle state with +the target residency within the time until the expected wakeup, so that state is +going to be relatively shallow. The governor really cannot select a deep idle +state then, as that would contradict its own expectation of a wakeup in short +order. Now, if the wakeup really occurs shortly, stopping the tick would be a +waste of time and in this case the timer hardware would need to be reprogrammed, +which is expensive. On the other hand, if the tick is stopped and the wakeup +does not occur any time soon, the hardware may spend indefinite amount of time +in the shallow idle state selected by the governor, which will be a waste of +energy. Hence, if the governor is expecting a wakeup of any kind within the +tick range, it is better to allow the tick trigger. Otherwise, however, the +governor will select a relatively deep idle state, so the tick should be stopped +so that it does not wake up the CPU too early. + +In any case, the governor knows what it is expecting and the decision on whether +or not to stop the scheduler tick belongs to it. Still, if the tick has been +stopped already (in one of the previous iterations of the loop), it is better +to leave it as is and the governor needs to take that into account. + +The kernel can be configured to disable stopping the scheduler tick in the idle +loop altogether. That can be done through the build-time configuration of it +(by unsetting the ``CONFIG_NO_HZ_IDLE`` configuration option) or by passing +``nohz=off`` to it in the command line. In both cases, as the stopping of the +scheduler tick is disabled, the governor's decisions regarding it are simply +ignored by the idle loop code and the tick is never stopped. + +The systems that run kernels configured to allow the scheduler tick to be +stopped on idle CPUs are referred to as *tickless* systems and they are +generally regarded as more energy-efficient than the systems running kernels in +which the tick cannot be stopped. If the given system is tickless, it will use +the ``menu`` governor by default and if it is not tickless, the default +``CPUIdle`` governor on it will be ``ladder``. + + +The ``menu`` Governor +===================== + +The ``menu`` governor is the default ``CPUIdle`` governor for tickless systems. +It is quite complex, but the basic principle of its design is straightforward. +Namely, when invoked to select an idle state for a CPU (i.e. an idle state that +the CPU will ask the processor hardware to enter), it attempts to predict the +idle duration and uses the predicted value for idle state selection. + +It first obtains the time until the closest timer event with the assumption +that the scheduler tick will be stopped. That time, referred to as the *sleep +length* in what follows, is the upper bound on the time before the next CPU +wakeup. It is used to determine the sleep length range, which in turn is needed +to get the sleep length correction factor. + +The ``menu`` governor maintains two arrays of sleep length correction factors. +One of them is used when tasks previously running on the given CPU are waiting +for some I/O operations to complete and the other one is used when that is not +the case. Each array contains several correction factor values that correspond +to different sleep length ranges organized so that each range represented in the +array is approximately 10 times wider than the previous one. + +The correction factor for the given sleep length range (determined before +selecting the idle state for the CPU) is updated after the CPU has been woken +up and the closer the sleep length is to the observed idle duration, the closer +to 1 the correction factor becomes (it must fall between 0 and 1 inclusive). +The sleep length is multiplied by the correction factor for the range that it +falls into to obtain the first approximation of the predicted idle duration. + +Next, the governor uses a simple pattern recognition algorithm to refine its +idle duration prediction. Namely, it saves the last 8 observed idle duration +values and, when predicting the idle duration next time, it computes the average +and variance of them. If the variance is small (smaller than 400 square +milliseconds) or it is small relative to the average (the average is greater +that 6 times the standard deviation), the average is regarded as the "typical +interval" value. Otherwise, the longest of the saved observed idle duration +values is discarded and the computation is repeated for the remaining ones. +Again, if the variance of them is small (in the above sense), the average is +taken as the "typical interval" value and so on, until either the "typical +interval" is determined or too many data points are disregarded, in which case +the "typical interval" is assumed to equal "infinity" (the maximum unsigned +integer value). The "typical interval" computed this way is compared with the +sleep length multiplied by the correction factor and the minimum of the two is +taken as the predicted idle duration. + +Then, the governor computes an extra latency limit to help "interactive" +workloads. It uses the observation that if the exit latency of the selected +idle state is comparable with the predicted idle duration, the total time spent +in that state probably will be very short and the amount of energy to save by +entering it will be relatively small, so likely it is better to avoid the +overhead related to entering that state and exiting it. Thus selecting a +shallower state is likely to be a better option then. The first approximation +of the extra latency limit is the predicted idle duration itself which +additionally is divided by a value depending on the number of tasks that +previously ran on the given CPU and now they are waiting for I/O operations to +complete. The result of that division is compared with the latency limit coming +from the power management quality of service, or `PM QoS `_, +framework and the minimum of the two is taken as the limit for the idle states' +exit latency. + +Now, the governor is ready to walk the list of idle states and choose one of +them. For this purpose, it compares the target residency of each state with +the predicted idle duration and the exit latency of it with the computed latency +limit. It selects the state with the target residency closest to the predicted +idle duration, but still below it, and exit latency that does not exceed the +limit. + +In the final step the governor may still need to refine the idle state selection +if it has not decided to `stop the scheduler tick `_. That +happens if the idle duration predicted by it is less than the tick period and +the tick has not been stopped already (in a previous iteration of the idle +loop). Then, the sleep length used in the previous computations may not reflect +the real time until the closest timer event and if it really is greater than +that time, the governor may need to select a shallower state with a suitable +target residency. + + +.. _idle-states-representation: + +Representation of Idle States +============================= + +For the CPU idle time management purposes all of the physical idle states +supported by the processor have to be represented as a one-dimensional array of +|struct cpuidle_state| objects each allowing an individual (logical) CPU to ask +the processor hardware to enter an idle state of certain properties. If there +is a hierarchy of units in the processor, one |struct cpuidle_state| object can +cover a combination of idle states supported by the units at different levels of +the hierarchy. In that case, the `target residency and exit latency parameters +of it `_, must reflect the properties of the idle state at the +deepest level (i.e. the idle state of the unit containing all of the other +units). + +For example, take a processor with two cores in a larger unit referred to as +a "module" and suppose that asking the hardware to enter a specific idle state +(say "X") at the "core" level by one core will trigger the module to try to +enter a specific idle state of its own (say "MX") if the other core is in idle +state "X" already. In other words, asking for idle state "X" at the "core" +level gives the hardware a license to go as deep as to idle state "MX" at the +"module" level, but there is no guarantee that this is going to happen (the core +asking for idle state "X" may just end up in that state by itself instead). +Then, the target residency of the |struct cpuidle_state| object representing +idle state "X" must reflect the minimum time to spend in idle state "MX" of +the module (including the time needed to enter it), because that is the minimum +time the CPU needs to be idle to save any energy in case the hardware enters +that state. Analogously, the exit latency parameter of that object must cover +the exit time of idle state "MX" of the module (and usually its entry time too), +because that is the maximum delay between a wakeup signal and the time the CPU +will start to execute the first new instruction (assuming that both cores in the +module will always be ready to execute instructions as soon as the module +becomes operational as a whole). + +There are processors without direct coordination between different levels of the +hierarchy of units inside them, however. In those cases asking for an idle +state at the "core" level does not automatically affect the "module" level, for +example, in any way and the ``CPUIdle`` driver is responsible for the entire +handling of the hierarchy. Then, the definition of the idle state objects is +entirely up to the driver, but still the physical properties of the idle state +that the processor hardware finally goes into must always follow the parameters +used by the governor for idle state selection (for instance, the actual exit +latency of that idle state must not exceed the exit latency parameter of the +idle state object selected by the governor). + +In addition to the target residency and exit latency idle state parameters +discussed above, the objects representing idle states each contain a few other +parameters describing the idle state and a pointer to the function to run in +order to ask the hardware to enter that state. Also, for each +|struct cpuidle_state| object, there is a corresponding +:c:type:`struct cpuidle_state_usage ` one containing usage +statistics of the given idle state. That information is exposed by the kernel +via ``sysfs``. + +For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpuidle/` +directory in ``sysfs``, where the number ```` is assigned to the given +CPU at the initialization time. That directory contains a set of subdirectories +called :file:`state0`, :file:`state1` and so on, up to the number of idle state +objects defined for the given CPU minus one. Each of these directories +corresponds to one idle state object and the larger the number in its name, the +deeper the (effective) idle state represented by it. Each of them contains +a number of files (attributes) representing the properties of the idle state +object corresponding to it, as follows: + +``desc`` + Description of the idle state. + +``disable`` + Whether or not this idle state is disabled. + +``latency`` + Exit latency of the idle state in microseconds. + +``name`` + Name of the idle state. + +``power`` + Power drawn by hardware in this idle state in milliwatts (if specified, + 0 otherwise). + +``residency`` + Target residency of the idle state in microseconds. + +``time`` + Total time spent in this idle state by the given CPU (as measured by the + kernel) in microseconds. + +``usage`` + Total number of times the hardware has been asked by the given CPU to + enter this idle state. + +The :file:`desc` and :file:`name` files both contain strings. The difference +between them is that the name is expected to be more concise, while the +description may be longer and it may contain white space or special characters. +The other files listed above contain integer numbers. + +The :file:`disable` attribute is the only writeable one. If it contains 1, the +given idle state is disabled for this particular CPU, which means that the +governor will never select it for this particular CPU and the ``CPUIdle`` +driver will never ask the hardware to enter it for that CPU as a result. +However, disabling an idle state for one CPU does not prevent it from being +asked for by the other CPUs, so it must be disabled for all of them in order to +never be asked for by any of them. [Note that, due to the way the ``ladder`` +governor is implemented, disabling an idle state prevents that governor from +selecting any idle states deeper than the disabled one too.] + +If the :file:`disable` attribute contains 0, the given idle state is enabled for +this particular CPU, but it still may be disabled for some or all of the other +CPUs in the system at the same time. Writing 1 to it causes the idle state to +be disabled for this particular CPU and writing 0 to it allows the governor to +take it into consideration for the given CPU and the driver to ask for it, +unless that state was disabled globally in the driver (in which case it cannot +be used at all). + +The :file:`power` attribute is not defined very well, especially for idle state +objects representing combinations of idle states at different levels of the +hierarchy of units in the processor, and it generally is hard to obtain idle +state power numbers for complex hardware, so :file:`power` often contains 0 (not +available) and if it contains a nonzero number, that number may not be very +accurate and it should not be relied on for anything meaningful. + +The number in the :file:`time` file generally may be greater than the total time +really spent by the given CPU in the given idle state, because it is measured by +the kernel and it may not cover the cases in which the hardware refused to enter +this idle state and entered a shallower one instead of it (or even it did not +enter any idle state at all). The kernel can only measure the time span between +asking the hardware to enter an idle state and the subsequent wakeup of the CPU +and it cannot say what really happened in the meantime at the hardware level. +Moreover, if the idle state object in question represents a combination of idle +states at different levels of the hierarchy of units in the processor, +the kernel can never say how deep the hardware went down the hierarchy in any +particular case. For these reasons, the only reliable way to find out how +much time has been spent by the hardware in different idle states supported by +it is to use idle state residency counters in the hardware, if available. + + +.. _cpu-pm-qos: + +Power Management Quality of Service for CPUs +============================================ + +The power management quality of service (PM QoS) framework in the Linux kernel +allows kernel code and user space processes to set constraints on various +energy-efficiency features of the kernel to prevent performance from dropping +below a required level. The PM QoS constraints can be set globally, in +predefined categories referred to as PM QoS classes, or against individual +devices. + +CPU idle time management can be affected by PM QoS in two ways, through the +global constraint in the ``PM_QOS_CPU_DMA_LATENCY`` class and through the +resume latency constraints for individual CPUs. Kernel code (e.g. device +drivers) can set both of them with the help of special internal interfaces +provided by the PM QoS framework. User space can modify the former by opening +the :file:`cpu_dma_latency` special device file under :file:`/dev/` and writing +a binary value (interpreted as a signed 32-bit integer) to it. In turn, the +resume latency constraint for a CPU can be modified by user space by writing a +string (representing a signed 32-bit integer) to the +:file:`power/pm_qos_resume_latency_us` file under +:file:`/sys/devices/system/cpu/cpu/` in ``sysfs``, where the CPU number +```` is allocated at the system initialization time. Negative values +will be rejected in both cases and, also in both cases, the written integer +number will be interpreted as a requested PM QoS constraint in microseconds. + +The requested value is not automatically applied as a new constraint, however, +as it may be less restrictive (greater in this particular case) than another +constraint previously requested by someone else. For this reason, the PM QoS +framework maintains a list of requests that have been made so far in each +global class and for each device, aggregates them and applies the effective +(minimum in this particular case) value as the new constraint. + +In fact, opening the :file:`cpu_dma_latency` special device file causes a new +PM QoS request to be created and added to the priority list of requests in the +``PM_QOS_CPU_DMA_LATENCY`` class and the file descriptor coming from the +"open" operation represents that request. If that file descriptor is then +used for writing, the number written to it will be associated with the PM QoS +request represented by it as a new requested constraint value. Next, the +priority list mechanism will be used to determine the new effective value of +the entire list of requests and that effective value will be set as a new +constraint. Thus setting a new requested constraint value will only change the +real constraint if the effective "list" value is affected by it. In particular, +for the ``PM_QOS_CPU_DMA_LATENCY`` class it only affects the real constraint if +it is the minimum of the requested constraints in the list. The process holding +a file descriptor obtained by opening the :file:`cpu_dma_latency` special device +file controls the PM QoS request associated with that file descriptor, but it +controls this particular PM QoS request only. + +Closing the :file:`cpu_dma_latency` special device file or, more precisely, the +file descriptor obtained while opening it, causes the PM QoS request associated +with that file descriptor to be removed from the ``PM_QOS_CPU_DMA_LATENCY`` +class priority list and destroyed. If that happens, the priority list mechanism +will be used, again, to determine the new effective value for the whole list +and that value will become the new real constraint. + +In turn, for each CPU there is only one resume latency PM QoS request +associated with the :file:`power/pm_qos_resume_latency_us` file under +:file:`/sys/devices/system/cpu/cpu/` in ``sysfs`` and writing to it causes +this single PM QoS request to be updated regardless of which user space +process does that. In other words, this PM QoS request is shared by the entire +user space, so access to the file associated with it needs to be arbitrated +to avoid confusion. [Arguably, the only legitimate use of this mechanism in +practice is to pin a process to the CPU in question and let it use the +``sysfs`` interface to control the resume latency constraint for it.] It +still only is a request, however. It is a member of a priority list used to +determine the effective value to be set as the resume latency constraint for the +CPU in question every time the list of requests is updated this way or another +(there may be other requests coming from kernel code in that list). + +CPU idle time governors are expected to regard the minimum of the global +effective ``PM_QOS_CPU_DMA_LATENCY`` class constraint and the effective +resume latency constraint for the given CPU as the upper limit for the exit +latency of the idle states they can select for that CPU. They should never +select any idle states with exit latency beyond that limit. + + +Idle States Control Via Kernel Command Line +=========================================== + +In addition to the ``sysfs`` interface allowing individual idle states to be +`disabled for individual CPUs `_, there are kernel +command line parameters affecting CPU idle time management. + +The ``cpuidle.off=1`` kernel command line option can be used to disable the +CPU idle time management entirely. It does not prevent the idle loop from +running on idle CPUs, but it prevents the CPU idle time governors and drivers +from being invoked. If it is added to the kernel command line, the idle loop +will ask the hardware to enter idle states on idle CPUs via the CPU architecture +support code that is expected to provide a default mechanism for this purpose. +That default mechanism usually is the least common denominator for all of the +processors implementing the architecture (i.e. CPU instruction set) in question, +however, so it is rather crude and not very energy-efficient. For this reason, +it is not recommended for production use. + +The other kernel command line parameters controlling CPU idle time management +described below are only relevant for the *x86* architecture and some of +them affect Intel processors only. + +The *x86* architecture support code recognizes three kernel command line +options related to CPU idle time management: ``idle=poll``, ``idle=halt``, +and ``idle=nomwait``. The first two of them disable the ``acpi_idle`` and +``intel_idle`` drivers altogether, which effectively causes the entire +``CPUIdle`` subsystem to be disabled and makes the idle loop invoke the +architecture support code to deal with idle CPUs. How it does that depends on +which of the two parameters is added to the kernel command line. In the +``idle=halt`` case, the architecture support code will use the ``HLT`` +instruction of the CPUs (which, as a rule, suspends the execution of the program +and causes the hardware to attempt to enter the shallowest available idle state) +for this purpose, and if ``idle=poll`` is used, idle CPUs will execute a +more or less ``lightweight'' sequence of instructions in a tight loop. [Note +that using ``idle=poll`` is somewhat drastic in many cases, as preventing idle +CPUs from saving almost any energy at all may not be the only effect of it. +For example, on Intel hardware it effectively prevents CPUs from using +P-states (see |cpufreq|) that require any number of CPUs in a package to be +idle, so it very well may hurt single-thread computations performance as well as +energy-efficiency. Thus using it for performance reasons may not be a good idea +at all.] + +The ``idle=nomwait`` option disables the ``intel_idle`` driver and causes +``acpi_idle`` to be used (as long as all of the information needed by it is +there in the system's ACPI tables), but it is not allowed to use the +``MWAIT`` instruction of the CPUs to ask the hardware to enter idle states. + +In addition to the architecture-level kernel command line options affecting CPU +idle time management, there are parameters affecting individual ``CPUIdle`` +drivers that can be passed to them via the kernel command line. Specifically, +the ``intel_idle.max_cstate=`` and ``processor.max_cstate=`` parameters, +where ```` is an idle state index also used in the name of the given +state's directory in ``sysfs`` (see +`Representation of Idle States `_), causes the +``intel_idle`` and ``acpi_idle`` drivers, respectively, to discard all of the +idle states deeper than idle state ````. In that case, they will never ask +for any of those idle states or expose them to the governor. [The behavior of +the two drivers is different for ```` equal to ``0``. Adding +``intel_idle.max_cstate=0`` to the kernel command line disables the +``intel_idle`` driver and allows ``acpi_idle`` to be used, whereas +``processor.max_cstate=0`` is equivalent to ``processor.max_cstate=1``. +Also, the ``acpi_idle`` driver is part of the ``processor`` kernel module that +can be loaded separately and ``max_cstate=`` can be passed to it as a module +parameter when it is loaded.] diff --git a/Documentation/admin-guide/pm/working-state.rst b/Documentation/admin-guide/pm/working-state.rst index fa01bf083dfe..b6cef9b5e961 100644 --- a/Documentation/admin-guide/pm/working-state.rst +++ b/Documentation/admin-guide/pm/working-state.rst @@ -5,5 +5,6 @@ Working-State Power Management .. toctree:: :maxdepth: 2 + cpuidle cpufreq intel_pstate diff --git a/Documentation/cpuidle/core.txt b/Documentation/cpuidle/core.txt deleted file mode 100644 index 63ecc5dc9d8a..000000000000 --- a/Documentation/cpuidle/core.txt +++ /dev/null @@ -1,23 +0,0 @@ - - Supporting multiple CPU idle levels in kernel - - cpuidle - -General Information: - -Various CPUs today support multiple idle levels that are differentiated -by varying exit latencies and power consumption during idle. -cpuidle is a generic in-kernel infrastructure that separates -idle policy (governor) from idle mechanism (driver) and provides a -standardized infrastructure to support independent development of -governors and drivers. - -cpuidle resides under drivers/cpuidle. - -Boot options: -"cpuidle_sysfs_switch" -enables current_governor interface in /sys/devices/system/cpu/cpuidle/, -which can be used to switch governors at run time. This boot option -is meant for developer testing only. In normal usage, kernel picks the -best governor based on governor ratings. -SEE ALSO: sysfs.txt in this directory. diff --git a/Documentation/cpuidle/sysfs.txt b/Documentation/cpuidle/sysfs.txt deleted file mode 100644 index d1587f434e7b..000000000000 --- a/Documentation/cpuidle/sysfs.txt +++ /dev/null @@ -1,98 +0,0 @@ - - - Supporting multiple CPU idle levels in kernel - - cpuidle sysfs - -System global cpuidle related information and tunables are under -/sys/devices/system/cpu/cpuidle - -The current interfaces in this directory has self-explanatory names: -* current_driver -* current_governor_ro - -With cpuidle_sysfs_switch boot option (meant for developer testing) -following objects are visible instead. -* current_driver -* available_governors -* current_governor -In this case users can switch the governor at run time by writing -to current_governor. - - -Per logical CPU specific cpuidle information are under -/sys/devices/system/cpu/cpuX/cpuidle -for each online cpu X - --------------------------------------------------------------------------------- -# ls -lR /sys/devices/system/cpu/cpu0/cpuidle/ -/sys/devices/system/cpu/cpu0/cpuidle/: -total 0 -drwxr-xr-x 2 root root 0 Feb 8 10:42 state0 -drwxr-xr-x 2 root root 0 Feb 8 10:42 state1 -drwxr-xr-x 2 root root 0 Feb 8 10:42 state2 -drwxr-xr-x 2 root root 0 Feb 8 10:42 state3 - -/sys/devices/system/cpu/cpu0/cpuidle/state0: -total 0 --r--r--r-- 1 root root 4096 Feb 8 10:42 desc --rw-r--r-- 1 root root 4096 Feb 8 10:42 disable --r--r--r-- 1 root root 4096 Feb 8 10:42 latency --r--r--r-- 1 root root 4096 Feb 8 10:42 name --r--r--r-- 1 root root 4096 Feb 8 10:42 power --r--r--r-- 1 root root 4096 Feb 8 10:42 residency --r--r--r-- 1 root root 4096 Feb 8 10:42 time --r--r--r-- 1 root root 4096 Feb 8 10:42 usage - -/sys/devices/system/cpu/cpu0/cpuidle/state1: -total 0 --r--r--r-- 1 root root 4096 Feb 8 10:42 desc --rw-r--r-- 1 root root 4096 Feb 8 10:42 disable --r--r--r-- 1 root root 4096 Feb 8 10:42 latency --r--r--r-- 1 root root 4096 Feb 8 10:42 name --r--r--r-- 1 root root 4096 Feb 8 10:42 power --r--r--r-- 1 root root 4096 Feb 8 10:42 residency --r--r--r-- 1 root root 4096 Feb 8 10:42 time --r--r--r-- 1 root root 4096 Feb 8 10:42 usage - -/sys/devices/system/cpu/cpu0/cpuidle/state2: -total 0 --r--r--r-- 1 root root 4096 Feb 8 10:42 desc --rw-r--r-- 1 root root 4096 Feb 8 10:42 disable --r--r--r-- 1 root root 4096 Feb 8 10:42 latency --r--r--r-- 1 root root 4096 Feb 8 10:42 name --r--r--r-- 1 root root 4096 Feb 8 10:42 power --r--r--r-- 1 root root 4096 Feb 8 10:42 residency --r--r--r-- 1 root root 4096 Feb 8 10:42 time --r--r--r-- 1 root root 4096 Feb 8 10:42 usage - -/sys/devices/system/cpu/cpu0/cpuidle/state3: -total 0 --r--r--r-- 1 root root 4096 Feb 8 10:42 desc --rw-r--r-- 1 root root 4096 Feb 8 10:42 disable --r--r--r-- 1 root root 4096 Feb 8 10:42 latency --r--r--r-- 1 root root 4096 Feb 8 10:42 name --r--r--r-- 1 root root 4096 Feb 8 10:42 power --r--r--r-- 1 root root 4096 Feb 8 10:42 residency --r--r--r-- 1 root root 4096 Feb 8 10:42 time --r--r--r-- 1 root root 4096 Feb 8 10:42 usage --------------------------------------------------------------------------------- - - -* desc : Small description about the idle state (string) -* disable : Option to disable this idle state (bool) -> see note below -* latency : Latency to exit out of this idle state (in microseconds) -* residency : Time after which a state becomes more effecient than any - shallower state (in microseconds) -* name : Name of the idle state (string) -* power : Power consumed while in this idle state (in milliwatts) -* time : Total time spent in this idle state (in microseconds) -* usage : Number of times this state was entered (count) - -Note: -The behavior and the effect of the disable variable depends on the -implementation of a particular governor. In the ladder governor, for -example, it is not coherent, i.e. if one is disabling a light state, -then all deeper states are disabled as well, but the disable variable -does not reflect it. Likewise, if one enables a deep state but a lighter -state still is disabled, then this has no effect. From 108c35a908d484df094f46a1e9d961d732737013 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 3 Dec 2018 11:29:29 +0100 Subject: [PATCH 09/17] sched/cpufreq: Add the SPDX tags The SPDX tags are not present in cpufreq.c and cpufreq_schedutil.c. Add them and remove the license descriptions Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- kernel/sched/cpufreq.c | 5 +---- kernel/sched/cpufreq_schedutil.c | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index 5e54cbcae673..22bd8980f32f 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Scheduler code and data structures related to cpufreq. * * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki - * - * 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. */ #include "sched.h" diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3fffad3bc8a8..626ddd4ffa43 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * CPUFreq governor based on scheduler-provided CPU utilization data. * * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki - * - * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt From 800fb34a99ce7d22dca839c90f869c7a12b50f70 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 3 Dec 2018 13:32:53 +0100 Subject: [PATCH 10/17] cpuidle: poll_state: Disregard disable idle states When computing the limit of time to spend in the loop in poll_idle(), use the target residency of the first enabled idle state deeper than state 0 instead of always using the target residency of state 1. This helps when state 1 is disabled for diagnostics, for instance. Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/poll_state.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 85792d371add..b17d153e724f 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -20,8 +20,17 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, local_irq_enable(); if (!current_set_polling_and_test()) { - u64 limit = (u64)drv->states[1].target_residency * NSEC_PER_USEC; unsigned int loop_count = 0; + u64 limit = TICK_USEC; + int i; + + for (i = 1; i < drv->state_count; i++) { + if (drv->states[i].disabled || dev->states_usage[i].disable) + continue; + + limit = (u64)drv->states[i].target_residency * NSEC_PER_USEC; + break; + } while (!need_resched()) { cpu_relax(); From 61cb5758d3c46bc1ba87694fefc0d9653613ce6b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 5 Dec 2018 23:45:34 +0100 Subject: [PATCH 11/17] cpuidle: Add cpuidle.governor= command line parameter Add cpuidle.governor= command line parameter to allow the default cpuidle governor to be replaced. That is useful, for example, if someone running a tickful kernel wants to use the menu governor on it. Signed-off-by: Rafael J. Wysocki --- Documentation/admin-guide/kernel-parameters.txt | 3 +++ Documentation/admin-guide/pm/cpuidle.rst | 7 +++++++ drivers/cpuidle/cpuidle.c | 1 + drivers/cpuidle/cpuidle.h | 1 + drivers/cpuidle/governor.c | 9 +++++++-- 5 files changed, 19 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 19f4423e70d9..60fb9913af48 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -674,6 +674,9 @@ cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system + cpuidle.governor= + [CPU_IDLE] Name of the cpuidle governor to use. + cpufreq.off=1 [CPU_FREQ] disable the cpufreq sub-system diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 80b4f26547ac..9a34484fd6e4 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -566,6 +566,13 @@ processors implementing the architecture (i.e. CPU instruction set) in question, however, so it is rather crude and not very energy-efficient. For this reason, it is not recommended for production use. +The ``cpuidle.governor=`` kernel command line switch allows the ``CPUIdle`` +governor to use to be specified. It has to be appended with a string matching +the name of an available governor (e.g. ``cpuidle.governor=menu``) and that +governor will be used instead of the default one. It is possible to force +the ``menu`` governor to be used on the systems that use the ``ladder`` governor +by default this way, for example. + The other kernel command line parameters controlling CPU idle time management described below are only relevant for the *x86* architecture and some of them affect Intel processors only. diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 4a97446f66d8..f7c58043e50f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -702,4 +702,5 @@ static int __init cpuidle_init(void) } module_param(off, int, 0444); +module_param_string(governor, param_governor, CPUIDLE_NAME_LEN, 0444); core_initcall(cpuidle_init); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index 2965ab32a583..d6613101af92 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/drivers/cpuidle/cpuidle.h @@ -7,6 +7,7 @@ #define __DRIVER_CPUIDLE_H /* For internal use only */ +extern char param_governor[]; extern struct cpuidle_governor *cpuidle_curr_governor; extern struct list_head cpuidle_governors; extern struct list_head cpuidle_detected_devices; diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index 9fed1b829292..bb93e5cf6a4a 100644 --- a/drivers/cpuidle/governor.c +++ b/drivers/cpuidle/governor.c @@ -11,10 +11,13 @@ #include #include #include +#include #include #include "cpuidle.h" +char param_governor[CPUIDLE_NAME_LEN]; + LIST_HEAD(cpuidle_governors); struct cpuidle_governor *cpuidle_curr_governor; @@ -86,9 +89,11 @@ int cpuidle_register_governor(struct cpuidle_governor *gov) mutex_lock(&cpuidle_lock); if (__cpuidle_find_governor(gov->name) == NULL) { ret = 0; - list_add_tail(&gov->governor_list, &cpuidle_governors); if (!cpuidle_curr_governor || - cpuidle_curr_governor->rating < gov->rating) + !strncasecmp(param_governor, gov->name, CPUIDLE_NAME_LEN) || + (cpuidle_curr_governor->rating < gov->rating && + strncasecmp(param_governor, cpuidle_curr_governor->name, + CPUIDLE_NAME_LEN))) cpuidle_switch_governor(gov); } mutex_unlock(&cpuidle_lock); From 9456823c842f346c74265fcd98d008d87a7eb6f5 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Mon, 10 Dec 2018 11:26:41 -0500 Subject: [PATCH 12/17] cpuidle: big.LITTLE: fix refcount leak of_find_node_by_path() acquires a reference to the node returned by it and that reference needs to be dropped by its caller. bl_idle_init() doesn't do that, so fix it. Signed-off-by: Yangtao Li Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle-big_little.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c index db2ede565f1a..b44476a1b7ad 100644 --- a/drivers/cpuidle/cpuidle-big_little.c +++ b/drivers/cpuidle/cpuidle-big_little.c @@ -167,6 +167,7 @@ static int __init bl_idle_init(void) { int ret; struct device_node *root = of_find_node_by_path("/"); + const struct of_device_id *match_id; if (!root) return -ENODEV; @@ -174,7 +175,11 @@ static int __init bl_idle_init(void) /* * Initialize the driver just for a compliant set of machines */ - if (!of_match_node(compatible_machine_match, root)) + match_id = of_match_node(compatible_machine_match, root); + + of_node_put(root); + + if (!match_id) return -ENODEV; if (!mcpm_is_available()) From df3e1c83a3a7bd65dac951c117cc9c796acd96b0 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Wed, 5 Dec 2018 10:44:49 -0500 Subject: [PATCH 13/17] cpufreq: ia64: Remove unused header files seq_file.h does not need to be included, so remove it. Moreover deleted a line of meaningless return and some useless blank lines. In a function whose return type is void, returning on the last line is not required. Signed-off-by: Yangtao Li Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/ia64-acpi-cpufreq.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c index dd5440d3372d..80c5bf590acb 100644 --- a/drivers/cpufreq/ia64-acpi-cpufreq.c +++ b/drivers/cpufreq/ia64-acpi-cpufreq.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -28,7 +27,6 @@ MODULE_AUTHOR("Venkatesh Pallipadi"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); - struct cpufreq_acpi_io { struct acpi_processor_performance acpi_data; unsigned int resume; @@ -348,10 +346,7 @@ acpi_cpufreq_exit (void) pr_debug("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); - return; } - late_initcall(acpi_cpufreq_init); module_exit(acpi_cpufreq_exit); - From a67d5849c9f1ff6b2afa0704b68ba5e192a3cb32 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Wed, 5 Dec 2018 10:57:51 -0500 Subject: [PATCH 14/17] cpufreq: nforce2: Remove meaningless return Delete a line of meaningless return and some useless blank lines. In a function whose return type is void, returning on the last line is not required. Signed-off-by: Yangtao Li Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq-nforce2.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index dbf82f36d270..33c309a08c64 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -123,8 +123,6 @@ static void nforce2_write_pll(int pll) /* Now write the value in all 64 registers */ for (temp = 0; temp <= 0x3f; temp++) pci_write_config_dword(nforce2_dev, NFORCE2_PLLREG, pll); - - return; } /** @@ -438,4 +436,3 @@ static void __exit nforce2_exit(void) module_init(nforce2_init); module_exit(nforce2_exit); - From 04dab58a39d402162a7effe7278df8cd41557252 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 10 Dec 2018 12:30:23 +0100 Subject: [PATCH 15/17] cpuidle: Add 'above' and 'below' idle state metrics Add two new metrics for CPU idle states, "above" and "below", to count the number of times the given state had been asked for (or entered from the kernel's perspective), but the observed idle duration turned out to be too short or too long for it (respectively). These metrics help to estimate the quality of the CPU idle governor in use. Signed-off-by: Rafael J. Wysocki --- .../ABI/testing/sysfs-devices-system-cpu | 7 +++++ Documentation/admin-guide/pm/cpuidle.rst | 10 ++++++ drivers/cpuidle/cpuidle.c | 31 ++++++++++++++++++- drivers/cpuidle/sysfs.c | 6 ++++ include/linux/cpuidle.h | 2 ++ 5 files changed, 55 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 73318225a368..9605dbd4b5b5 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -145,6 +145,8 @@ What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/name /sys/devices/system/cpu/cpuX/cpuidle/stateN/power /sys/devices/system/cpu/cpuX/cpuidle/stateN/time /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage + /sys/devices/system/cpu/cpuX/cpuidle/stateN/above + /sys/devices/system/cpu/cpuX/cpuidle/stateN/below Date: September 2007 KernelVersion: v2.6.24 Contact: Linux power management list @@ -166,6 +168,11 @@ Description: usage: (RO) Number of times this state was entered (a count). + above: (RO) Number of times this state was entered, but the + observed CPU idle duration was too short for it (a count). + + below: (RO) Number of times this state was entered, but the + observed CPU idle duration was too long for it (a count). What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc Date: February 2008 diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 9a34484fd6e4..106379e2619f 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -398,6 +398,16 @@ deeper the (effective) idle state represented by it. Each of them contains a number of files (attributes) representing the properties of the idle state object corresponding to it, as follows: +``above`` + Total number of times this idle state had been asked for, but the + observed idle duration was certainly too short to match its target + residency. + +``below`` + Total number of times this idle state had been asked for, but cerainly + a deeper idle state would have been a better match for the observed idle + duration. + ``desc`` Description of the idle state. diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index f7c58043e50f..7f108309e871 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -202,7 +202,6 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, struct cpuidle_state *target_state = &drv->states[index]; bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); ktime_t time_start, time_end; - s64 diff; /* * Tell the time framework to switch to a broadcast timer because our @@ -248,6 +247,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, local_irq_enable(); if (entered_state >= 0) { + s64 diff, delay = drv->states[entered_state].exit_latency; + int i; + /* * Update cpuidle counters * This can be moved to within driver enter routine, @@ -260,6 +262,33 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, dev->last_residency = (int)diff; dev->states_usage[entered_state].time += dev->last_residency; dev->states_usage[entered_state].usage++; + + if (diff < drv->states[entered_state].target_residency) { + for (i = entered_state - 1; i >= 0; i--) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + /* Shallower states are enabled, so update. */ + dev->states_usage[entered_state].above++; + break; + } + } else if (diff > delay) { + for (i = entered_state + 1; i < drv->state_count; i++) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + /* + * Update if a deeper state would have been a + * better match for the observed idle duration. + */ + if (diff - delay >= drv->states[i].target_residency) + dev->states_usage[entered_state].below++; + + break; + } + } } else { dev->last_residency = 0; } diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index e754c7aae7f7..eb20adb5de23 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -301,6 +301,8 @@ define_show_state_str_function(name) define_show_state_str_function(desc) define_show_state_ull_function(disable) define_store_state_ull_function(disable) +define_show_state_ull_function(above) +define_show_state_ull_function(below) define_one_state_ro(name, show_state_name); define_one_state_ro(desc, show_state_desc); @@ -310,6 +312,8 @@ define_one_state_ro(power, show_state_power_usage); define_one_state_ro(usage, show_state_usage); define_one_state_ro(time, show_state_time); define_one_state_rw(disable, show_state_disable, store_state_disable); +define_one_state_ro(above, show_state_above); +define_one_state_ro(below, show_state_below); static struct attribute *cpuidle_state_default_attrs[] = { &attr_name.attr, @@ -320,6 +324,8 @@ static struct attribute *cpuidle_state_default_attrs[] = { &attr_usage.attr, &attr_time.attr, &attr_disable.attr, + &attr_above.attr, + &attr_below.attr, NULL }; diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index faed7a8977e8..4dff74f48d4b 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -33,6 +33,8 @@ struct cpuidle_state_usage { unsigned long long disable; unsigned long long usage; unsigned long long time; /* in US */ + unsigned long long above; /* Number of times it's been too deep */ + unsigned long long below; /* Number of times it's been too shallow */ #ifdef CONFIG_SUSPEND unsigned long long s2idle_usage; unsigned long long s2idle_time; /* in US */ From 0a3b0c7f979563c97a136c51e43ef724121e83ed Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Fri, 14 Dec 2018 09:40:23 +0530 Subject: [PATCH 16/17] dt-bindings: cpufreq: Introduce QCOM cpufreq firmware bindings Add QCOM cpufreq firmware device bindings for Qualcomm Technology Inc's SoCs. This is required for managing the cpu frequency transitions which are controlled by the hardware engine. Signed-off-by: Taniya Das Reviewed-by: Stephen Boyd Acked-by: Viresh Kumar Tested-by: Amit Kucheria Reviewed-by: Rob Herring Signed-off-by: Rafael J. Wysocki --- .../bindings/cpufreq/cpufreq-qcom-hw.txt | 172 ++++++++++++++++++ 1 file changed, 172 insertions(+) create mode 100644 Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.txt diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.txt new file mode 100644 index 000000000000..33856947c561 --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.txt @@ -0,0 +1,172 @@ +Qualcomm Technologies, Inc. CPUFREQ Bindings + +CPUFREQ HW is a hardware engine used by some Qualcomm Technologies, Inc. (QTI) +SoCs to manage frequency in hardware. It is capable of controlling frequency +for multiple clusters. + +Properties: +- compatible + Usage: required + Value type: + Definition: must be "qcom,cpufreq-hw". + +- clocks + Usage: required + Value type: From common clock binding. + Definition: clock handle for XO clock and GPLL0 clock. + +- clock-names + Usage: required + Value type: From common clock binding. + Definition: must be "xo", "alternate". + +- reg + Usage: required + Value type: + Definition: Addresses and sizes for the memory of the HW bases in + each frequency domain. +- reg-names + Usage: Optional + Value type: + Definition: Frequency domain name i.e. + "freq-domain0", "freq-domain1". + +- #freq-domain-cells: + Usage: required. + Definition: Number of cells in a freqency domain specifier. + +* Property qcom,freq-domain +Devices supporting freq-domain must set their "qcom,freq-domain" property with +phandle to a cpufreq_hw followed by the Domain ID(0/1) in the CPU DT node. + + +Example: + +Example 1: Dual-cluster, Quad-core per cluster. CPUs within a cluster switch +DCVS state together. + +/ { + cpus { + #address-cells = <2>; + #size-cells = <0>; + + CPU0: cpu@0 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x0>; + enable-method = "psci"; + next-level-cache = <&L2_0>; + qcom,freq-domain = <&cpufreq_hw 0>; + L2_0: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + L3_0: l3-cache { + compatible = "cache"; + }; + }; + }; + + CPU1: cpu@100 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x100>; + enable-method = "psci"; + next-level-cache = <&L2_100>; + qcom,freq-domain = <&cpufreq_hw 0>; + L2_100: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + + CPU2: cpu@200 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x200>; + enable-method = "psci"; + next-level-cache = <&L2_200>; + qcom,freq-domain = <&cpufreq_hw 0>; + L2_200: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + + CPU3: cpu@300 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x300>; + enable-method = "psci"; + next-level-cache = <&L2_300>; + qcom,freq-domain = <&cpufreq_hw 0>; + L2_300: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + + CPU4: cpu@400 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x400>; + enable-method = "psci"; + next-level-cache = <&L2_400>; + qcom,freq-domain = <&cpufreq_hw 1>; + L2_400: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + + CPU5: cpu@500 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x500>; + enable-method = "psci"; + next-level-cache = <&L2_500>; + qcom,freq-domain = <&cpufreq_hw 1>; + L2_500: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + + CPU6: cpu@600 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x600>; + enable-method = "psci"; + next-level-cache = <&L2_600>; + qcom,freq-domain = <&cpufreq_hw 1>; + L2_600: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + + CPU7: cpu@700 { + device_type = "cpu"; + compatible = "qcom,kryo385"; + reg = <0x0 0x700>; + enable-method = "psci"; + next-level-cache = <&L2_700>; + qcom,freq-domain = <&cpufreq_hw 1>; + L2_700: l2-cache { + compatible = "cache"; + next-level-cache = <&L3_0>; + }; + }; + }; + + soc { + cpufreq_hw: cpufreq@17d43000 { + compatible = "qcom,cpufreq-hw"; + reg = <0x17d43000 0x1400>, <0x17d45800 0x1400>; + reg-names = "freq-domain0", "freq-domain1"; + + clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GPLL0>; + clock-names = "xo", "alternate"; + + #freq-domain-cells = <1>; + }; +} From 2849dd8bc72b62a315854863c84c523176bd55ce Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Fri, 14 Dec 2018 09:40:24 +0530 Subject: [PATCH 17/17] cpufreq: qcom-hw: Add support for QCOM cpufreq HW driver The CPUfreq HW present in some QCOM chipsets offloads the steps necessary for changing the frequency of CPUs. The driver implements the cpufreq driver interface for this hardware engine. Signed-off-by: Saravana Kannan Signed-off-by: Taniya Das Reviewed-by: Stephen Boyd Tested-by: Stephen Boyd Acked-by: Viresh Kumar Tested-by: Amit Kucheria Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/Kconfig.arm | 11 ++ drivers/cpufreq/Makefile | 1 + drivers/cpufreq/qcom-cpufreq-hw.c | 308 ++++++++++++++++++++++++++++++ 3 files changed, 320 insertions(+) create mode 100644 drivers/cpufreq/qcom-cpufreq-hw.c diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 4e1131ef85ae..688f10227793 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -114,6 +114,17 @@ config ARM_QCOM_CPUFREQ_KRYO If in doubt, say N. +config ARM_QCOM_CPUFREQ_HW + tristate "QCOM CPUFreq HW driver" + depends on ARCH_QCOM || COMPILE_TEST + help + Support for the CPUFreq HW driver. + Some QCOM chipsets have a HW engine to offload the steps + necessary for changing the frequency of the CPUs. Firmware loaded + in this engine exposes a programming interface to the OS. + The driver implements the cpufreq interface for this HW engine. + Say Y if you want to support CPUFreq HW. + config ARM_S3C_CPUFREQ bool help diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index d5ee4562ed06..08c071be2491 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -61,6 +61,7 @@ obj-$(CONFIG_MACH_MVEBU_V7) += mvebu-cpufreq.o obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ) += omap-cpufreq.o obj-$(CONFIG_ARM_PXA2xx_CPUFREQ) += pxa2xx-cpufreq.o obj-$(CONFIG_PXA3xx) += pxa3xx-cpufreq.o +obj-$(CONFIG_ARM_QCOM_CPUFREQ_HW) += qcom-cpufreq-hw.o obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO) += qcom-cpufreq-kryo.o obj-$(CONFIG_ARM_S3C2410_CPUFREQ) += s3c2410-cpufreq.o obj-$(CONFIG_ARM_S3C2412_CPUFREQ) += s3c2412-cpufreq.o diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c new file mode 100644 index 000000000000..d83939a1b3d4 --- /dev/null +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define LUT_MAX_ENTRIES 40U +#define LUT_SRC GENMASK(31, 30) +#define LUT_L_VAL GENMASK(7, 0) +#define LUT_CORE_COUNT GENMASK(18, 16) +#define LUT_ROW_SIZE 32 +#define CLK_HW_DIV 2 + +/* Register offsets */ +#define REG_ENABLE 0x0 +#define REG_LUT_TABLE 0x110 +#define REG_PERF_STATE 0x920 + +static unsigned long cpu_hw_rate, xo_rate; +static struct platform_device *global_pdev; + +static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy, + unsigned int index) +{ + void __iomem *perf_state_reg = policy->driver_data; + + writel_relaxed(index, perf_state_reg); + + return 0; +} + +static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +{ + void __iomem *perf_state_reg; + struct cpufreq_policy *policy; + unsigned int index; + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) + return 0; + + perf_state_reg = policy->driver_data; + + index = readl_relaxed(perf_state_reg); + index = min(index, LUT_MAX_ENTRIES - 1); + + return policy->freq_table[index].frequency; +} + +static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + void __iomem *perf_state_reg = policy->driver_data; + int index; + + index = policy->cached_resolved_idx; + if (index < 0) + return 0; + + writel_relaxed(index, perf_state_reg); + + return policy->freq_table[index].frequency; +} + +static int qcom_cpufreq_hw_read_lut(struct device *dev, + struct cpufreq_policy *policy, + void __iomem *base) +{ + u32 data, src, lval, i, core_count, prev_cc = 0, prev_freq = 0, freq; + unsigned int max_cores = cpumask_weight(policy->cpus); + struct cpufreq_frequency_table *table; + + table = kcalloc(LUT_MAX_ENTRIES + 1, sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + for (i = 0; i < LUT_MAX_ENTRIES; i++) { + data = readl_relaxed(base + REG_LUT_TABLE + i * LUT_ROW_SIZE); + src = FIELD_GET(LUT_SRC, data); + lval = FIELD_GET(LUT_L_VAL, data); + core_count = FIELD_GET(LUT_CORE_COUNT, data); + + if (src) + freq = xo_rate * lval / 1000; + else + freq = cpu_hw_rate / 1000; + + /* Ignore boosts in the middle of the table */ + if (core_count != max_cores) { + table[i].frequency = CPUFREQ_ENTRY_INVALID; + } else { + table[i].frequency = freq; + dev_dbg(dev, "index=%d freq=%d, core_count %d\n", i, + freq, core_count); + } + + /* + * Two of the same frequencies with the same core counts means + * end of table + */ + if (i > 0 && prev_freq == freq && prev_cc == core_count) { + struct cpufreq_frequency_table *prev = &table[i - 1]; + + /* + * Only treat the last frequency that might be a boost + * as the boost frequency + */ + if (prev_cc != max_cores) { + prev->frequency = prev_freq; + prev->flags = CPUFREQ_BOOST_FREQ; + } + + break; + } + + prev_cc = core_count; + prev_freq = freq; + } + + table[i].frequency = CPUFREQ_TABLE_END; + policy->freq_table = table; + + return 0; +} + +static void qcom_get_related_cpus(int index, struct cpumask *m) +{ + struct device_node *cpu_np; + struct of_phandle_args args; + int cpu, ret; + + for_each_possible_cpu(cpu) { + cpu_np = of_cpu_device_node_get(cpu); + if (!cpu_np) + continue; + + ret = of_parse_phandle_with_args(cpu_np, "qcom,freq-domain", + "#freq-domain-cells", 0, + &args); + of_node_put(cpu_np); + if (ret < 0) + continue; + + if (index == args.args[0]) + cpumask_set_cpu(cpu, m); + } +} + +static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) +{ + struct device *dev = &global_pdev->dev; + struct of_phandle_args args; + struct device_node *cpu_np; + struct resource *res; + void __iomem *base; + int ret, index; + + cpu_np = of_cpu_device_node_get(policy->cpu); + if (!cpu_np) + return -EINVAL; + + ret = of_parse_phandle_with_args(cpu_np, "qcom,freq-domain", + "#freq-domain-cells", 0, &args); + of_node_put(cpu_np); + if (ret) + return ret; + + index = args.args[0]; + + res = platform_get_resource(global_pdev, IORESOURCE_MEM, index); + if (!res) + return -ENODEV; + + base = devm_ioremap(dev, res->start, resource_size(res)); + if (!base) + return -ENOMEM; + + /* HW should be in enabled state to proceed */ + if (!(readl_relaxed(base + REG_ENABLE) & 0x1)) { + dev_err(dev, "Domain-%d cpufreq hardware not enabled\n", index); + ret = -ENODEV; + goto error; + } + + qcom_get_related_cpus(index, policy->cpus); + if (!cpumask_weight(policy->cpus)) { + dev_err(dev, "Domain-%d failed to get related CPUs\n", index); + ret = -ENOENT; + goto error; + } + + policy->driver_data = base + REG_PERF_STATE; + + ret = qcom_cpufreq_hw_read_lut(dev, policy, base); + if (ret) { + dev_err(dev, "Domain-%d failed to read LUT\n", index); + goto error; + } + + policy->fast_switch_possible = true; + + return 0; +error: + devm_iounmap(dev, base); + return ret; +} + +static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) +{ + void __iomem *base = policy->driver_data - REG_PERF_STATE; + + kfree(policy->freq_table); + devm_iounmap(&global_pdev->dev, base); + + return 0; +} + +static struct freq_attr *qcom_cpufreq_hw_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + &cpufreq_freq_attr_scaling_boost_freqs, + NULL +}; + +static struct cpufreq_driver cpufreq_qcom_hw_driver = { + .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_HAVE_GOVERNOR_PER_POLICY, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = qcom_cpufreq_hw_target_index, + .get = qcom_cpufreq_hw_get, + .init = qcom_cpufreq_hw_cpu_init, + .exit = qcom_cpufreq_hw_cpu_exit, + .fast_switch = qcom_cpufreq_hw_fast_switch, + .name = "qcom-cpufreq-hw", + .attr = qcom_cpufreq_hw_attr, +}; + +static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) +{ + struct clk *clk; + int ret; + + clk = clk_get(&pdev->dev, "xo"); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + xo_rate = clk_get_rate(clk); + clk_put(clk); + + clk = clk_get(&pdev->dev, "alternate"); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + cpu_hw_rate = clk_get_rate(clk) / CLK_HW_DIV; + clk_put(clk); + + global_pdev = pdev; + + ret = cpufreq_register_driver(&cpufreq_qcom_hw_driver); + if (ret) + dev_err(&pdev->dev, "CPUFreq HW driver failed to register\n"); + else + dev_dbg(&pdev->dev, "QCOM CPUFreq HW driver initialized\n"); + + return ret; +} + +static int qcom_cpufreq_hw_driver_remove(struct platform_device *pdev) +{ + return cpufreq_unregister_driver(&cpufreq_qcom_hw_driver); +} + +static const struct of_device_id qcom_cpufreq_hw_match[] = { + { .compatible = "qcom,cpufreq-hw" }, + {} +}; +MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match); + +static struct platform_driver qcom_cpufreq_hw_driver = { + .probe = qcom_cpufreq_hw_driver_probe, + .remove = qcom_cpufreq_hw_driver_remove, + .driver = { + .name = "qcom-cpufreq-hw", + .of_match_table = qcom_cpufreq_hw_match, + }, +}; + +static int __init qcom_cpufreq_hw_init(void) +{ + return platform_driver_register(&qcom_cpufreq_hw_driver); +} +subsys_initcall(qcom_cpufreq_hw_init); + +static void __exit qcom_cpufreq_hw_exit(void) +{ + platform_driver_unregister(&qcom_cpufreq_hw_driver); +} +module_exit(qcom_cpufreq_hw_exit); + +MODULE_DESCRIPTION("QCOM CPUFREQ HW Driver"); +MODULE_LICENSE("GPL v2");