summaryrefslogtreecommitdiff
path: root/drivers/cpufreq
AgeCommit message (Collapse)Author
2013-06-05cpufreq: cpufreq-cpu0: use the exact frequency for clk_set_rate()Guennadi Liakhovetski
clk_set_rate() isn't supposed to accept approximate frequencies, instead a supported frequency should be obtained from clk_round_rate() and then used to set the clock. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Shawn Guo <shawn.guo@linaro.org> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-06-05cpufreq: protect 'policy->cpus' from offlining during __gov_queue_work()Michael Wang
Jiri Kosina <jkosina@suse.cz> and Borislav Petkov <bp@alien8.de> reported the warning: [ 51.616759] ------------[ cut here ]------------ [ 51.621460] WARNING: at arch/x86/kernel/smp.c:123 native_smp_send_reschedule+0x58/0x60() [ 51.629638] Modules linked in: ext2 vfat fat loop snd_hda_codec_hdmi usbhid snd_hda_codec_realtek coretemp kvm_intel kvm snd_hda_intel snd_hda_codec crc32_pclmul crc32c_intel ghash_clmulni_intel snd_hwdep snd_pcm aesni_intel sb_edac aes_x86_64 ehci_pci snd_page_alloc glue_helper snd_timer xhci_hcd snd iTCO_wdt iTCO_vendor_support ehci_hcd edac_core lpc_ich acpi_cpufreq lrw gf128mul ablk_helper cryptd mperf usbcore usb_common soundcore mfd_core dcdbas evdev pcspkr processor i2c_i801 button microcode [ 51.675581] CPU: 0 PID: 244 Comm: kworker/1:1 Tainted: G W 3.10.0-rc1+ #10 [ 51.683407] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013 [ 51.690901] Workqueue: events od_dbs_timer [ 51.695069] 0000000000000009 ffff88043a2f5b68 ffffffff8161441c ffff88043a2f5ba8 [ 51.702602] ffffffff8103e540 0000000000000033 0000000000000001 ffff88043d5f8000 [ 51.710136] 00000000ffff0ce1 0000000000000001 ffff88044fc4fc08 ffff88043a2f5bb8 [ 51.717691] Call Trace: [ 51.720191] [<ffffffff8161441c>] dump_stack+0x19/0x1b [ 51.725396] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0 [ 51.731473] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20 [ 51.737378] [<ffffffff81025628>] native_smp_send_reschedule+0x58/0x60 [ 51.744013] [<ffffffff81072cfd>] wake_up_nohz_cpu+0x2d/0xa0 [ 51.749745] [<ffffffff8104f6bf>] add_timer_on+0x8f/0x110 [ 51.755214] [<ffffffff8105f6fe>] __queue_delayed_work+0x16e/0x1a0 [ 51.761470] [<ffffffff8105f251>] ? try_to_grab_pending+0xd1/0x1a0 [ 51.767724] [<ffffffff8105f78a>] mod_delayed_work_on+0x5a/0xa0 [ 51.773719] [<ffffffff814f6b5d>] gov_queue_work+0x4d/0xc0 [ 51.779271] [<ffffffff814f60cb>] od_dbs_timer+0xcb/0x170 [ 51.784734] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540 [ 51.790634] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540 [ 51.796711] [<ffffffff8105ef22>] worker_thread+0x122/0x380 [ 51.802350] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320 [ 51.808264] [<ffffffff8106634a>] kthread+0xea/0xf0 [ 51.813200] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150 [ 51.819644] [<ffffffff81623d5c>] ret_from_fork+0x7c/0xb0 [ 51.918165] nouveau E[ DRM] GPU lockup - switching to software fbcon [ 51.930505] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150 [ 51.936994] ---[ end trace f419538ada83b5c5 ]--- It was caused by the policy->cpus changed during the process of __gov_queue_work(), in other word, cpu offline happened. Use get/put_online_cpus() to prevent the offline from happening while __gov_queue_work() is running. [rjw: The problem has been present since recent commit 031299b (cpufreq: governors: Avoid unnecessary per cpu timer interrupts)] References: https://lkml.org/lkml/2013/6/5/88 Reported-by: Borislav Petkov <bp@alien8.de> Reported-and-tested-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-06-05acpi-cpufreq: set current frequency based on target P-StateRoss Lagerwall
Commit 4b31e774 (Always set P-state on initialization) fixed bug #4634 and caused the driver to always set the target P-State at least once since the initial P-State may not be the desired one. Commit 5a1c0228 (cpufreq: Avoid calling cpufreq driver's target() routine if target_freq == policy->cur) caused a regression in this behavior. This fixes the regression by setting policy->cur based on the CPU's target frequency rather than the CPU's current reported frequency (which may be different). This means that the P-State will be set initially if the CPU's target frequency is different from the governor's target frequency. This fixes an issue where setting the default governor to performance wouldn't correctly enable turbo mode on all cores. Signed-off-by: Ross Lagerwall <rosslagerwall@gmail.com> Reviewed-by: Len Brown <len.brown@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 3.8+ <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-26Merge tag 'pm+acpi-3.10-rc3' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm Pull power management and ACPI fixes from Rafael Wysocki: - Additional CPU ID for the intel_pstate driver from Dirk Brandewie. - More cpufreq fixes related to ARM big.LITTLE support and locking from Viresh Kumar. - VIA C7 cpufreq build fix from Rafał Bilski. - ACPI power management fix making it possible to use device power states regardless of the CONFIG_PM setting from Rafael J Wysocki. - New ACPI video blacklist item from Bastian Triller. * tag 'pm+acpi-3.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: ACPI / video: Add "Asus UL30A" to ACPI video detect blacklist cpufreq: arm_big_little_dt: Instantiate as platform_driver cpufreq: arm_big_little_dt: Register driver only if DT has valid data cpufreq / e_powersaver: Fix linker error when ACPI processor is a module cpufreq / intel_pstate: Add additional supported CPU ID cpufreq: Drop rwsem lock around CPUFREQ_GOV_POLICY_EXIT ACPI / PM: Allow device power states to be used for CONFIG_PM unset
2013-05-22cpufreq: arm_big_little_dt: Instantiate as platform_driverViresh Kumar
As multiplatform build is being adopted by more and more ARM platforms, initcall function should be used very carefully. For example, when both arm_big_little_dt and cpufreq-cpu0 drivers are compiled in, arm_big_little_dt driver may try to register even if we had platform device for cpufreq-cpu0 registered. To eliminate this undesired the effect, the patch changes arm_big_little_dt driver to have it instantiated as a platform_driver. Then it will only run on platforms that create the platform_device "arm-bL-cpufreq-dt". Reported-and-tested-by: Rob Herring <robherring2@gmail.com> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-22cpufreq: arm_big_little_dt: Register driver only if DT has valid dataViresh Kumar
If arm_big_little_dt driver is enabled, then it will always try to register with big LITTLE cpufreq core driver. In case DT doesn't have relevant data for cpu nodes, i.e. operating points aren't present, then we should exit early and shouldn't register with big LITTLE cpufreq core driver. Otherwise we will fail continuously from the driver->init() routine. This patch fixes this issue. Reported-and-tested-by: Jon Medhurst <tixy@linaro.org> Reviewed-by: Jon Medhurst <tixy@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-22cpufreq / e_powersaver: Fix linker error when ACPI processor is a moduleRafał Bilski
on i386: CONFIG_ACPI_PROCESSOR=m CONFIG_X86_E_POWERSAVER=y drivers/built-in.o: In function `eps_cpu_init.part.8': e_powersaver.c:(.text.unlikely+0x2243): undefined reference to `acpi_processor_register_performance' e_powersaver.c:(.text.unlikely+0x22a2): undefined reference to `acpi_processor_unregister_performance' e_powersaver.c:(.text.unlikely+0x246b): undefined reference to `acpi_processor_get_bios_limit' X86_E_POWERSAVER should also depend on ACPI_PROCESSOR. Signed-off-by: Rafal Bilski <rafalbilski@interia.pl> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-21MIPS: Idle: Consolidate all declarations in <asm/idle.h>.Ralf Baechle
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2013-05-21MIPS: Idle: Re-enable irqs at the end of r3081, au1k and loongson2 cpu_wait.Ralf Baechle
Without this, the WARN_ON_ONCE(irqs_disabled()); in the idle loop will be triggered. Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2013-05-21cpufreq / intel_pstate: Add additional supported CPU IDDirk Brandewie
Add CPU ID for Ivybrigde processor. Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-21cpufreq: Drop rwsem lock around CPUFREQ_GOV_POLICY_EXITViresh Kumar
With the rwsem lock around __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT), we get circular dependency when we call sysfs_remove_group(). ====================================================== [ INFO: possible circular locking dependency detected ] 3.9.0-rc7+ #15 Not tainted ------------------------------------------------------- cat/2387 is trying to acquire lock: (&per_cpu(cpu_policy_rwsem, cpu)){+++++.}, at: [<c02f6179>] lock_policy_rwsem_read+0x25/0x34 but task is already holding lock: (s_active#41){++++.+}, at: [<c00f9bf7>] sysfs_read_file+0x4f/0xcc which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (s_active#41){++++.+}: [<c0055a79>] lock_acquire+0x61/0xbc [<c00fabf1>] sysfs_addrm_finish+0xc1/0x128 [<c00f9819>] sysfs_hash_and_remove+0x35/0x64 [<c00fbe6f>] remove_files.isra.0+0x1b/0x24 [<c00fbea5>] sysfs_remove_group+0x2d/0xa8 [<c02f9a0b>] cpufreq_governor_interactive+0x13b/0x35c [<c02f61df>] __cpufreq_governor+0x2b/0x8c [<c02f6579>] __cpufreq_set_policy+0xa9/0xf8 [<c02f6b75>] store_scaling_governor+0x61/0x100 [<c02f6f4d>] store+0x39/0x60 [<c00f9b81>] sysfs_write_file+0xed/0x114 [<c00b3fd1>] vfs_write+0x65/0xd8 [<c00b424b>] sys_write+0x2f/0x50 [<c000cdc1>] ret_fast_syscall+0x1/0x52 -> #0 (&per_cpu(cpu_policy_rwsem, cpu)){+++++.}: [<c0055253>] __lock_acquire+0xef3/0x13dc [<c0055a79>] lock_acquire+0x61/0xbc [<c03ee1f5>] down_read+0x25/0x30 [<c02f6179>] lock_policy_rwsem_read+0x25/0x34 [<c02f6edd>] show+0x21/0x58 [<c00f9c0f>] sysfs_read_file+0x67/0xcc [<c00b40a7>] vfs_read+0x63/0xd8 [<c00b41fb>] sys_read+0x2f/0x50 [<c000cdc1>] ret_fast_syscall+0x1/0x52 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(s_active#41); lock(&per_cpu(cpu_policy_rwsem, cpu)); lock(s_active#41); lock(&per_cpu(cpu_policy_rwsem, cpu)); *** DEADLOCK *** 2 locks held by cat/2387: #0: (&buffer->mutex){+.+.+.}, at: [<c00f9bcd>] sysfs_read_file+0x25/0xcc #1: (s_active#41){++++.+}, at: [<c00f9bf7>] sysfs_read_file+0x4f/0xcc stack backtrace: [<c0011d55>] (unwind_backtrace+0x1/0x9c) from [<c03e9a09>] (print_circular_bug+0x19d/0x1e8) [<c03e9a09>] (print_circular_bug+0x19d/0x1e8) from [<c0055253>] (__lock_acquire+0xef3/0x13dc) [<c0055253>] (__lock_acquire+0xef3/0x13dc) from [<c0055a79>] (lock_acquire+0x61/0xbc) [<c0055a79>] (lock_acquire+0x61/0xbc) from [<c03ee1f5>] (down_read+0x25/0x30) [<c03ee1f5>] (down_read+0x25/0x30) from [<c02f6179>] (lock_policy_rwsem_read+0x25/0x34) [<c02f6179>] (lock_policy_rwsem_read+0x25/0x34) from [<c02f6edd>] (show+0x21/0x58) [<c02f6edd>] (show+0x21/0x58) from [<c00f9c0f>] (sysfs_read_file+0x67/0xcc) [<c00f9c0f>] (sysfs_read_file+0x67/0xcc) from [<c00b40a7>] (vfs_read+0x63/0xd8) [<c00b40a7>] (vfs_read+0x63/0xd8) from [<c00b41fb>] (sys_read+0x2f/0x50) [<c00b41fb>] (sys_read+0x2f/0x50) from [<c000cdc1>] (ret_fast_syscall+0x1/0x52) This lock isn't required while calling __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT). Remove it. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-15cpufreq: Preserve sysfs files across suspend/resumeSrivatsa S. Bhat
The file permissions of cpufreq per-cpu sysfs files are not preserved across suspend/resume because we internally go through the CPU Hotplug path which reinitializes the file permissions on CPU online. But the user is not supposed to know that we are using CPU hotplug internally within suspend/resume (IOW, the kernel should not silently wreck the user-set file permissions across a suspend cycle). Therefore, we need to preserve the file permissions as they are across suspend/resume. The simplest way to achieve that is to just not touch the sysfs files at all - ie., just ignore the CPU hotplug notifications in the suspend/resume path (_FROZEN) in the cpufreq hotplug callback. Reported-by: Robert Jarzmik <robert.jarzmik@intel.com> Reported-by: Durgadoss R <durgadoss.r@intel.com> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-13cpufreq / intel_pstate: use vzalloc() instead of vmalloc()/memset(0)Wei Yongjun
Use vzalloc() instead of vmalloc() and memset(0). Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-13cpufreq, ondemand: Remove leftover debug lineBorislav Petkov
I don't see how the virtual address of the tuners pointer would be of any help to anyone so remove it. Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq / kirkwood: don't check resource with devm_ioremap_resourceWolfram Sang
devm_ioremap_resource does sanity checks on the given resource. No need to duplicate this in the driver. Signed-off-by: Wolfram Sang <wsa@the-dreams.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq / intel_pstate: remove #ifdef MODULE compile fenceDirk Brandewie
The driver can no longer be built as a module remove the compile fence around cpufreq tracing call. Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq / intel_pstate: Remove idle mode PIDDirk Brandewie
Remove dead code from the driver. Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq / intel_pstate: fix ffmpeg regressionDirk Brandewie
The ffmpeg benchmark in the phoronix test suite has threads on multiple cores that rely on the progress on of threads on other cores and ping pong back and forth fast enough to make the core appear less busy than it "should" be. If the core has been at minimum p-state for a while bump the pstate up to kick the core to see if it is in this ping pong state. If the core is truly idle the p-state will be reduced at the next sample time. If the core makes more progress it will send more work to the thread bringing both threads out of the ping pong scenario and the p-state will be selected normally. This fixes a performance regression of approximately 30% Cc: 3.9+ <stable@vger.kernel.org> Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq / intel_pstate: use lowest requested max performanceDirk Brandewie
There are two ways that the maximum p-state can be clamped, via a policy change and via the sysfs file. The acpi-thermal driver adjusts the p-state policy in response to thermal events. These changes override the users settings at the moment. Use the lowest of the two requested values this ensures that we will not exceed the requested pstate from either mechanism. Reported-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Cc: 3.9+ <stable@vger.kernel.org> Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq / intel_pstate: remove idle time and duration from sample and ↵Dirk Brandewie
calculations Idle time is taken into account in the APERF/MPERF ratio calculation there is no reason for the driver to track it seperately. This reduces the work in the driver and makes the code more readable. Removal of the tracking of sample duration removes the possibility of the divide by zero exception when the duration is sub 1us References: https://bugzilla.kernel.org/show_bug.cgi?id=56691 Reported-by: Mike Lothian <mike@fireburn.co.uk> Cc: 3.9+ <stable@vger.kernel.org> Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: Fix incorrect dependecies for ARM SA11xx driversAlexander Shiyan
Kconfig dependecies for ARM SA11xx drivers are incorrect, so fix them. [rjw: Changelog] Signed-off-by: Alexander Shiyan <shc_work@mail.ru> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: ARM big LITTLE: Fix Kconfig entriesViresh Kumar
This fixes usage of "depends on" and "select" options in Kconfig for ARM big LITTLE cpufreq driver. Otherwise we get these warnings: warning: (ARM_DT_BL_CPUFREQ) selects ARM_BIG_LITTLE_CPUFREQ which has unmet direct dependencies (ARCH_HAS_CPUFREQ && CPU_FREQ && ARM && ARM_CPU_TOPOLOGY) Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: cpufreq-cpu0: Free parent node for error casesViresh Kumar
We are freeing parent node in success cases but not in failure cases. Let's do it. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Shawn Guo <shawn.guo@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: cpufreq-cpu0: defer probe when regulator is not readyNishanth Menon
With commit 1e4b545, regulator_get will now return -EPROBE_DEFER when the cpu0-supply node is present, but the regulator is not yet registered. It is possible for this to occur when the regulator registration by itself might be defered due to some dependent interface not yet instantiated. For example: an regulator which uses I2C and GPIO might need both systems available before proceeding, in this case, the regulator might defer it's registration. However, the cpufreq-cpu0 driver assumes that any un-successful return result is equivalent of failure. When the regulator_get returns failure other than -EPROBE_DEFER, it makes sense to assume that supply node is not present and proceed with the assumption that only clock control is necessary in the platform. With this change, we can now handle the following conditions: a) cpu0-supply binding is not present, regulator_get will return appropriate error result, resulting in cpufreq-cpu0 driver controlling just the clock. b) cpu0-supply binding is present, regulator_get returns -EPROBE_DEFER, we retry resulting in cpufreq-cpu0 driver registering later once the regulator is available. c) cpu0-supply binding is present, regulator_get returns -EPROBE_DEFER, however, regulator never registers, we retry until cpufreq-cpu0 driver fails to register pointing at device tree information bug. However, in this case, the fact that cpufreq-cpu0 operates with clock only when the DT binding clearly indicates need of a supply is a bug of it's own. d) cpu0-supply gets an regulator at probe - cpufreq-cpu0 driver controls both the clock and regulator Signed-off-by: Nishanth Menon <nm@ti.com> Acked-by: Shawn Guo <shawn.guo@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: Issue CPUFREQ_GOV_POLICY_EXIT notifier before dropping policy refcountViresh Kumar
We must call __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT) before calling cpufreq_cpu_put(data), so that policy kobject have valid fields. Otherwise, removing last online cpu of policy->cpus causes this crash for ondemand/conservative governor. [<c00fb076>] (sysfs_find_dirent+0xe/0xa8) from [<c00fb1bd>] (sysfs_get_dirent+0x21/0x58) [<c00fb1bd>] (sysfs_get_dirent+0x21/0x58) from [<c00fc259>] (sysfs_remove_group+0x85/0xbc) [<c00fc259>] (sysfs_remove_group+0x85/0xbc) from [<c02faad9>] (cpufreq_governor_dbs+0x369/0x4a0) [<c02faad9>] (cpufreq_governor_dbs+0x369/0x4a0) from [<c02f66d7>] (__cpufreq_governor+0x2b/0x8c) [<c02f66d7>] (__cpufreq_governor+0x2b/0x8c) from [<c02f6893>] (__cpufreq_remove_dev.isra.12+0x15b/0x250) [<c02f6893>] (__cpufreq_remove_dev.isra.12+0x15b/0x250) from [<c03e91c7>] (cpufreq_cpu_callback+0x2f/0x3c) [<c03e91c7>] (cpufreq_cpu_callback+0x2f/0x3c) from [<c0036fe1>] (notifier_call_chain+0x45/0x54) [<c0036fe1>] (notifier_call_chain+0x45/0x54) from [<c001e611>] (__cpu_notify+0x1d/0x34) [<c001e611>] (__cpu_notify+0x1d/0x34) from [<c03e5833>] (_cpu_down+0x63/0x1ac) [<c03e5833>] (_cpu_down+0x63/0x1ac) from [<c03e5997>] (cpu_down+0x1b/0x30) [<c03e5997>] (cpu_down+0x1b/0x30) from [<c03e60eb>] (store_online+0x27/0x54) [<c03e60eb>] (store_online+0x27/0x54) from [<c0295629>] (dev_attr_store+0x11/0x18) [<c0295629>] (dev_attr_store+0x11/0x18) from [<c00f9edd>] (sysfs_write_file+0xed/0x114) [<c00f9edd>] (sysfs_write_file+0xed/0x114) from [<c00b42a9>] (vfs_write+0x65/0xd8) [<c00b42a9>] (vfs_write+0x65/0xd8) from [<c00b4523>] (sys_write+0x2f/0x50) [<c00b4523>] (sys_write+0x2f/0x50) from [<c000cdc1>] (ret_fast_syscall+0x1/0x52) Of course this only impacted drivers which have have_governor_per_policy set to true. i.e. big LITTLE cpufreq driver. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: governors: Fix CPUFREQ_GOV_POLICY_{INIT|EXIT} notifiersViresh Kumar
There are two types of INIT/EXIT activities that we need to do for governors: - Done only once per governor (doesn't depend how many instances of the governor there are). eg: cpufreq_register_notifier() for conservative governor. - Done per governor instance, eg: sysfs_{create|remove}_group(). There were some corner cases where current code isn't able to handle them separately and so failing for some test cases. We use two separate variables now for keeping track of above two requirements. - governor->initialized for first one - dbs_data->usage_count for per governor instance Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: ARM big LITTLE: Improve print messageViresh Kumar
The message printed at the end of driver->init() doesn't include the "cpufreq" string at all and so is difficult to find in dmesg. Add function name to that message to clearly state where the message is coming from. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: ARM big LITTLE: Move cpu_to_cluster() to arm_big_little.hViresh Kumar
The cpu_to_cluster() function may be used by glue drivers, so it's better to keep it in arm_big_little.h. [rjw: Changelog] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: ARM big LITTLE DT: Return CPUFREQ_ETERNAL if clock-latency isn't foundViresh Kumar
If "/cpus" node isn't present or "clock-latency" isn't defined we are returning error currently. Let's return CPUFREQ_ETERNAL instead, so that we don't fail. Flag appropriate messages to user in such cases. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: ARM big LITTLE DT: Return correct transition latencyViresh Kumar
By mistake we are returning zero for successful call to dt_get_transition_latency(), whereas we should return transition_latency. Fix that. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-12cpufreq: ARM big LITTLE: Select PM_OPPViresh Kumar
The ARM big LITTLE cpufreq driver uses the OPP layer for its functionality. Select it in Kconfig. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-28Merge branch 'pm-cpufreq'Rafael J. Wysocki
* pm-cpufreq: cpufreq: Revert incorrect commit 5800043
2013-04-28cpufreq: Revert incorrect commit 5800043Rafael J. Wysocki
Commit 5800043 (cpufreq: convert cpufreq_driver to using RCU) causes the following call trace to be spit on boot: BUG: sleeping function called from invalid context at /scratch/rafael/work/linux-pm/mm/slab.c:3179 in_atomic(): 0, irqs_disabled(): 0, pid: 292, name: systemd-udevd 2 locks held by systemd-udevd/292: #0: (subsys mutex){+.+.+.}, at: [<ffffffff8146851a>] subsys_interface_register+0x4a/0xe0 #1: (rcu_read_lock){.+.+.+}, at: [<ffffffff81538210>] cpufreq_add_dev_interface+0x60/0x5e0 Pid: 292, comm: systemd-udevd Not tainted 3.9.0-rc8+ #323 Call Trace: [<ffffffff81072c90>] __might_sleep+0x140/0x1f0 [<ffffffff811581c2>] kmem_cache_alloc+0x42/0x2b0 [<ffffffff811e7179>] sysfs_new_dirent+0x59/0x130 [<ffffffff811e63cb>] sysfs_add_file_mode+0x6b/0x110 [<ffffffff81538210>] ? cpufreq_add_dev_interface+0x60/0x5e0 [<ffffffff810a3254>] ? __lock_is_held+0x54/0x80 [<ffffffff811e647d>] sysfs_add_file+0xd/0x10 [<ffffffff811e6541>] sysfs_create_file+0x21/0x30 [<ffffffff81538280>] cpufreq_add_dev_interface+0xd0/0x5e0 [<ffffffff81538210>] ? cpufreq_add_dev_interface+0x60/0x5e0 [<ffffffffa000337f>] ? acpi_processor_get_platform_limit+0x32/0xbb [processor] [<ffffffffa022f540>] ? do_drv_write+0x70/0x70 [acpi_cpufreq] [<ffffffff810a3254>] ? __lock_is_held+0x54/0x80 [<ffffffff8106c97e>] ? up_read+0x1e/0x40 [<ffffffff8106e632>] ? __blocking_notifier_call_chain+0x72/0xc0 [<ffffffff81538dbd>] cpufreq_add_dev+0x62d/0xae0 [<ffffffff815389b8>] ? cpufreq_add_dev+0x228/0xae0 [<ffffffff81468569>] subsys_interface_register+0x99/0xe0 [<ffffffffa014d000>] ? 0xffffffffa014cfff [<ffffffff81535d5d>] cpufreq_register_driver+0x9d/0x200 [<ffffffffa014d000>] ? 0xffffffffa014cfff [<ffffffffa014d0e9>] acpi_cpufreq_init+0xe9/0x1000 [acpi_cpufreq] [<ffffffff810002fa>] do_one_initcall+0x11a/0x170 [<ffffffff810b4b87>] load_module+0x1cf7/0x2920 [<ffffffff81322580>] ? ddebug_proc_open+0xb0/0xb0 [<ffffffff816baee0>] ? retint_restore_args+0xe/0xe [<ffffffff810b5887>] sys_init_module+0xd7/0x120 [<ffffffff816bb6d2>] system_call_fastpath+0x16/0x1b which is quite obvious, because that commit put (multiple instances of) sysfs_create_file() under rcu_read_lock()/rcu_read_unlock(), although sysfs_create_file() may cause memory to be allocated with GFP_KERNEL and that may sleep, which is not permitted in RCU read critical section. Revert the buggy commit altogether along with some changes on top of it. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-28Merge branch 'pm-cpufreq'Rafael J. Wysocki
* pm-cpufreq: (57 commits) cpufreq: MAINTAINERS: Add co-maintainer cpufreq: pxa2xx: initialize variables ARM: S5pv210: compiling issue, ARM_S5PV210_CPUFREQ needs CONFIG_CPU_FREQ_TABLE=y cpufreq: cpu0: Put cpu parent node after using it cpufreq: ARM big LITTLE: Adapt to latest cpufreq updates cpufreq: ARM big LITTLE: put DT nodes after using them cpufreq: Don't call __cpufreq_governor() for drivers without target() cpufreq: exynos5440: Protect OPP search calls with RCU lock cpufreq: dbx500: Round to closest available freq cpufreq: Call __cpufreq_governor() with correct policy->cpus mask cpufreq / intel_pstate: Optimize intel_pstate_set_policy cpufreq: OMAP: instantiate omap-cpufreq as a platform_driver arm: exynos: Enable OPP library support for exynos5440 cpufreq: exynos: Remove error return even if no soc is found cpufreq: exynos: Add cpufreq driver for exynos5440 cpufreq: AMD "frequency sensitivity feedback" powersave bias for ondemand governor cpufreq: ondemand: allow custom powersave_bias_target handler to be registered cpufreq: convert cpufreq_driver to using RCU cpufreq: powerpc/platforms/cell: move cpufreq driver to drivers/cpufreq cpufreq: sparc: move cpufreq driver to drivers/cpufreq ... Conflicts: MAINTAINERS (with commit a8e39c3 from pm-cpuidle) drivers/cpufreq/cpufreq_governor.h (with commit beb0ff3)
2013-04-25cpufreq: pxa2xx: initialize variablesArnd Bergmann
gcc-3.8 correctly found that the variables set by find_freq_tables() are not initialized if this function is called on something other than a pxa2xx or pxa3xx: pxa2xx-cpufreq.c: In function 'pxa_verify_policy': pxa2xx-cpufreq.c:272:6: warning: 'pxa_freqs_table' may be used uninitialized in this function [-Wmaybe-uninitialized] pxa2xx-cpufreq.c: In function 'pxa_set_target': pxa2xx-cpufreq.c:345:23: warning: 'pxa_freq_settings' may be used uninitialized in this function [-Wmaybe-uninitialized] Rather than adding a bogus initialization that would let us get a little further before crashing, add an explicit BUG(). We know that this code is designed to run on only these cpus, so this will fix the build warning and give a more helpful diagnostic if the code ever changes to run on other machines. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-24ARM: S5pv210: compiling issue, ARM_S5PV210_CPUFREQ needs CONFIG_CPU_FREQ_TABLE=yChen Gang
For arm S5pv210 with allmodconfig, ARM_S5PV210_CPUFREQ need CONFIG_CPU_FREQ_TABLE=y, or will cause compiling issue. The related operation: + arm-linux-gnu-ld -EL -p --no-undefined -X --build-id -X -o .tmp_vmlinux1 -T /root/linux-next/arch/arm/kernel/vmlinux.lds arch/arm/kernel/head.o init/built-in.o --start-group usr/built-in.o arch/arm/nwfpe/built-in.o arch/arm/vfp/built-in.o arch/arm/kernel/built-in.o arch/arm/mm/built-in.o arch/arm/common/built-in.o arch/arm/net/built-in.o arch/arm/crypto/built-in.o arch/arm/mach-s5pv210/built-in.o arch/arm/plat-samsung/built-in.o kernel/built-in.o mm/built-in.o fs/built-in.o ipc/built-in.o security/built-in.o crypto/built-in.o block/built-in.o arch/arm/lib/lib.a lib/lib.a arch/arm/lib/built-in.o lib/built-in.o drivers/built-in.o sound/built-in.o firmware/built-in.o net/built-in.o --end-group The related errors: drivers/built-in.o: In function `s5pv210_target': drivers/cpufreq/s5pv210-cpufreq.c:225: undefined reference to `cpufreq_frequency_table_target' drivers/cpufreq/s5pv210-cpufreq.c:237: undefined reference to `cpufreq_frequency_table_target' drivers/built-in.o: In function `s5pv210_verify_speed': drivers/cpufreq/s5pv210-cpufreq.c:182: undefined reference to `cpufreq_frequency_table_verify' drivers/built-in.o: In function `s5pv210_cpu_init': drivers/cpufreq/s5pv210-cpufreq.c:556: undefined reference to `cpufreq_frequency_table_get_attr' drivers/cpufreq/s5pv210-cpufreq.c:560: undefined reference to `cpufreq_frequency_table_cpuinfo' make: *** [vmlinux] Error 1 Signed-off-by: Chen Gang <gang.chen@asianux.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-21cpufreq: cpu0: Put cpu parent node after using itViresh Kumar
Parent node must be put after using it to balance its usage count. This was missing in cpufreq-cpu0 driver. Fix it. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Shawn Guo <shawn.guo@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-21cpufreq: ARM big LITTLE: Adapt to latest cpufreq updatesViresh Kumar
This driver isn't updated to work with latest cpufreq core updates that happened recently. Fix them. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-21cpufreq: ARM big LITTLE: put DT nodes after using themViresh Kumar
DT nodes should be put using of_node_put() to balance their usage counts. This is not done properly in ARM's big LITTLE driver. Fix it. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-21cpufreq: Don't call __cpufreq_governor() for drivers without target()Viresh Kumar
Some cpufreq drivers implement their own governor and so don't need us to call generic governors interface via __cpufreq_governor(). Few recent commits haven't obeyed this law well and we saw some regressions. This patch is an attempt to fix the above issue. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Reported-and-tested-by: Sedat Dilek <sedat.dilek@gmail.com> Tested-by: Dirk Brandewie <dirk.brandewie@gmail.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-21cpufreq: exynos5440: Protect OPP search calls with RCU lockAmit Daniel Kachhap
As per the OPP library documentation(Documentation/power/opp.txt) all OPP find/get calls should be protected by RCU locks. Signed-off-by: Amit Daniel Kachhap <amit.daniel@samsung.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-11cpufreq: dbx500: Round to closest available freqMats Fagerstrom
When reading the cpu speed, round it to the closest available frequency from the table. Signed-off-by: Mats Fagerstrom <mats.fagerstrom@stericsson.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org> Acked-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-11cpufreq: Call __cpufreq_governor() with correct policy->cpus maskViresh Kumar
__cpufreq_governor() must be called with a correct policy->cpus mask. In __cpufreq_remove_dev() we initially clear policy->cpus with cpumask_clear_cpu() and then call __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT). If the governor is doing some per-cpu stuff in EXIT callback, this can create uncertain behavior. Generic governors in drivers/cpufreq/ doesn't do any per-cpu stuff in EXIT callback and so we don't face any issues currently. But its better to keep the code clean, so we don't face any issues in future. Now, we call cpumask_clear_cpu() only when multiple cpus are managed by policy. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq / intel_pstate: Optimize intel_pstate_set_policySrinivas Pandruvada
This function is called quite often from other subsystems. Removed unused call to intel_pstate_get_min_max(). Also when "policy->policy == CPUFREQ_POLICY_PERFORMANCE", then no need to do calculations as the limits will be forced anyway. Also corrected filename in the header. Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq: OMAP: instantiate omap-cpufreq as a platform_driverNishanth Menon
As multi-platform build is being adopted by more and more ARM platforms, initcall function should be used very carefully. For example, when CONFIG_ARM_OMAP2PLUS_CPUFREQ is built in the kernel, omap_cpufreq_init() will be called on all the platforms to initialize omap-cpufreq driver. Further, on OMAP, we now use Soc generic cpufreq-cpu0 driver using device tree entries. To allow cpufreq-cpu0 and omap-cpufreq drivers to co-exist for OMAP in a single image, we need to ensure the following: 1. With device tree boot, we use cpufreq-cpu0 2. With non device tree boot, we use omap-cpufreq In the case of (1), we will have cpu OPPs and regulator registered as part of the device tree nodes, to ensure that omap-cpufreq and cpufreq-cpu0 don't conflict in managing the frequency of the same CPU, we should not permit omap-cpufreq to be probed. In the case of (2), we will not have the cpufreq-cpu0 device, hence only omap-cpufreq will be active. To eliminate this undesired these effects, we change omap-cpufreq driver to have it instantiated as a platform_driver and register "omap-cpufreq" device only when booted without device tree nodes on OMAP platforms. This allows the following: a) Will only run on platforms that create the platform_device "omap-cpufreq". b) Since the platform_device is registered only when device tree nodes are *not* populated, omap-cpufreq driver does not conflict with the usage of cpufreq-cpu0 driver which is used on OMAP platforms when device tree nodes are present. Inspired by commit 5553f9e26f6f49a93ba732fd222eac6973a4cf35 (cpufreq: instantiate cpufreq-cpu0 as a platform_driver) [robherring2@gmail.com: reported conflict of omap-cpufreq vs other driver in an non-device tree supported boot] Reported-by: Rob Herring <robherring2@gmail.com> Signed-off-by: Nishanth Menon <nm@ti.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Kevin Hilman <khilman@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq: exynos: Remove error return even if no soc is foundAmit Daniel Kachhap
This patch helps to have single binary for exynos5440 and previous exynos soc's. This change is needed for adding exynos5440 cpufreq driver which does not uses exynos-cpufreq common file and adds it own driver. Signed-off-by: Amit Daniel Kachhap <amit.daniel@samsung.com> Acked-by: Kukjin Kim <kgene.kim@samsung.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq: exynos: Add cpufreq driver for exynos5440Amit Daniel Kachhap
This patch adds dvfs support for exynos5440 SOC. This soc has 4 cores and they scale at same frequency. The nature of exynos5440 clock controller is different from previous exynos controllers so not using the common exynos cpufreq framework. The major difference being interrupt notification for frequency change. Also, OPP library is used for device tree parsing to get different parameters like frequency, voltage etc. Since the opp library sorts the frequency table in ascending order so they are again re-arranged in descending order. This will have one-to-one mapping with the clock controller state management logic. Signed-off-by: Amit Daniel Kachhap <amit.daniel@samsung.com> Acked-by: Kukjin Kim <kgene.kim@samsung.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq: AMD "frequency sensitivity feedback" powersave bias for ondemand ↵Jacob Shin
governor Future AMD processors, starting with Family 16h, can provide software with feedback on how the workload may respond to frequency change -- memory-bound workloads will not benefit from higher frequency, where as compute-bound workloads will. This patch enables this "frequency sensitivity feedback" to aid the ondemand governor to make better frequency change decisions by hooking into the powersave bias. Signed-off-by: Jacob Shin <jacob.shin@amd.com> Acked-by: Thomas Renninger <trenn@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq: ondemand: allow custom powersave_bias_target handler to be registeredJacob Shin
This allows for another [arch specific] driver to hook into existing powersave bias function of the ondemand governor. i.e. This allows AMD specific powersave bias function (in a separate AMD specific driver) to aid ondemand governor's frequency transition decisions. Signed-off-by: Jacob Shin <jacob.shin@amd.com> Acked-by: Thomas Renninger <trenn@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10cpufreq: convert cpufreq_driver to using RCUNathan Zimmer
We eventually would like to remove the rwlock cpufreq_driver_lock or convert it back to a spinlock and protect the read sections with RCU. The first step in that direction is to make cpufreq_driver use RCU. I don't see an easy wasy to protect the cpufreq_cpu_data structure with RCU, so I am leaving it with the rwlock for now since under certain configs __cpufreq_cpu_get is a hot spot with 256+ cores. [rjw: Subject, changelog, white space] Signed-off-by: Nathan Zimmer <nzimmer@sgi.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>