diff options
27 files changed, 831 insertions, 431 deletions
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt index 29b3f9ffc66..ce0666e5103 100644 --- a/Documentation/cpu-freq/core.txt +++ b/Documentation/cpu-freq/core.txt @@ -24,7 +24,7 @@ Contents: 1. General Information ======================= -The CPUFreq core code is located in linux/kernel/cpufreq.c. This +The CPUFreq core code is located in drivers/cpufreq/cpufreq.c. This cpufreq code offers a standardized interface for the CPUFreq architecture drivers (those pieces of code that do actual frequency transitions), as well as to "notifiers". These are device diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 031029e89fd..64ce44da593 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -259,3 +259,25 @@ Why: The new layer 3 independant connection tracking replaces the old Who: Patrick McHardy <kaber@trash.net> --------------------------- + +What: ACPI hooks (X86_SPEEDSTEP_CENTRINO_ACPI) in speedstep-centrino driver +When: December 2006 +Why: Speedstep-centrino driver with ACPI hooks and acpi-cpufreq driver are + functionally very much similar. They talk to ACPI in same way. Only + difference between them is the way they do frequency transitions. + One uses MSRs and the other one uses IO ports. Functionaliy of + speedstep_centrino with ACPI hooks is now merged into acpi-cpufreq. + That means one common driver will support all Intel Enhanced Speedstep + capable CPUs. That means less confusion over name of + speedstep-centrino driver (with that driver supposed to be used on + non-centrino platforms). That means less duplication of code and + less maintenance effort and no possibility of these two drivers + going out of sync. + Current users of speedstep_centrino with ACPI hooks are requested to + switch over to acpi-cpufreq driver. speedstep-centrino will continue + to work using older non-ACPI static table based scheme even after this + date. + +Who: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + +--------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index b2024938adc..8d1695811cf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -740,7 +740,7 @@ P: Dave Jones M: davej@codemonkey.org.uk L: cpufreq@lists.linux.org.uk W: http://www.codemonkey.org.uk/projects/cpufreq/ -T: git kernel.org/pub/scm/linux/kernel/davej/cpufreq.git +T: git kernel.org/pub/scm/linux/kernel/git/davej/cpufreq.git S: Maintained CPUID/MSR DRIVER diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index ccc1edff5c9..5299c5bf445 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -17,6 +17,7 @@ config X86_ACPI_CPUFREQ help This driver adds a CPUFreq driver which utilizes the ACPI Processor Performance States. + This driver also supports Intel Enhanced Speedstep. For details, take a look at <file:Documentation/cpu-freq/>. @@ -121,11 +122,14 @@ config X86_SPEEDSTEP_CENTRINO If in doubt, say N. config X86_SPEEDSTEP_CENTRINO_ACPI - bool "Use ACPI tables to decode valid frequency/voltage pairs" + bool "Use ACPI tables to decode valid frequency/voltage (deprecated)" depends on X86_SPEEDSTEP_CENTRINO && ACPI_PROCESSOR depends on !(X86_SPEEDSTEP_CENTRINO = y && ACPI_PROCESSOR = m) default y help + This is deprecated and this functionality is now merged into + acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of + speedstep_centrino. Use primarily the information provided in the BIOS ACPI tables to determine valid CPU frequency and voltage pairings. It is required for the driver to work on non-Banias CPUs. diff --git a/arch/i386/kernel/cpu/cpufreq/Makefile b/arch/i386/kernel/cpu/cpufreq/Makefile index 2e894f1c891..8de3abe322a 100644 --- a/arch/i386/kernel/cpu/cpufreq/Makefile +++ b/arch/i386/kernel/cpu/cpufreq/Makefile @@ -7,9 +7,9 @@ obj-$(CONFIG_SC520_CPUFREQ) += sc520_freq.o obj-$(CONFIG_X86_LONGRUN) += longrun.o obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o obj-$(CONFIG_X86_SPEEDSTEP_ICH) += speedstep-ich.o -obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o obj-$(CONFIG_X86_SPEEDSTEP_SMI) += speedstep-smi.o obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 57c880bf0bd..18f4715c655 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -1,9 +1,10 @@ /* - * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.3 $) + * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $) * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de> + * Copyright (C) 2006 Denis Sadykov <denis.m.sadykov@intel.com> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -27,202 +28,387 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/smp.h> +#include <linux/sched.h> #include <linux/cpufreq.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> #include <linux/compiler.h> -#include <linux/sched.h> /* current */ #include <linux/dmi.h> -#include <asm/io.h> -#include <asm/delay.h> -#include <asm/uaccess.h> #include <linux/acpi.h> #include <acpi/processor.h> +#include <asm/io.h> +#include <asm/msr.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> +#include <asm/delay.h> +#include <asm/uaccess.h> + #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); +enum { + UNDEFINED_CAPABLE = 0, + SYSTEM_INTEL_MSR_CAPABLE, + SYSTEM_IO_CAPABLE, +}; + +#define INTEL_MSR_RANGE (0xffff) +#define CPUID_6_ECX_APERFMPERF_CAPABILITY (0x1) -struct cpufreq_acpi_io { - struct acpi_processor_performance *acpi_data; - struct cpufreq_frequency_table *freq_table; - unsigned int resume; +struct acpi_cpufreq_data { + struct acpi_processor_performance *acpi_data; + struct cpufreq_frequency_table *freq_table; + unsigned int max_freq; + unsigned int resume; + unsigned int cpu_feature; }; -static struct cpufreq_acpi_io *acpi_io_data[NR_CPUS]; -static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; +static struct acpi_cpufreq_data *drv_data[NR_CPUS]; +static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; static struct cpufreq_driver acpi_cpufreq_driver; static unsigned int acpi_pstate_strict; -static int -acpi_processor_write_port( - u16 port, - u8 bit_width, - u32 value) +static int check_est_cpu(unsigned int cpuid) +{ + struct cpuinfo_x86 *cpu = &cpu_data[cpuid]; + + if (cpu->x86_vendor != X86_VENDOR_INTEL || + !cpu_has(cpu, X86_FEATURE_EST)) + return 0; + + return 1; +} + +static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data) +{ + struct acpi_processor_performance *perf; + int i; + + perf = data->acpi_data; + + for (i=0; i<perf->state_count; i++) { + if (value == perf->states[i].status) + return data->freq_table[i].frequency; + } + return 0; +} + +static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data) { - if (bit_width <= 8) { + int i; + struct acpi_processor_performance *perf; + + msr &= INTEL_MSR_RANGE; + perf = data->acpi_data; + + for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { + if (msr == perf->states[data->freq_table[i].index].status) + return data->freq_table[i].frequency; + } + return data->freq_table[0].frequency; +} + +static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data) +{ + switch (data->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + return extract_msr(val, data); + case SYSTEM_IO_CAPABLE: + return extract_io(val, data); + default: + return 0; + } +} + +static void wrport(u16 port, u8 bit_width, u32 value) +{ + if (bit_width <= 8) outb(value, port); - } else if (bit_width <= 16) { + else if (bit_width <= 16) outw(value, port); - } else if (bit_width <= 32) { + else if (bit_width <= 32) outl(value, port); - } else { - return -ENODEV; - } - return 0; } -static int -acpi_processor_read_port( - u16 port, - u8 bit_width, - u32 *ret) +static void rdport(u16 port, u8 bit_width, u32 * ret) { *ret = 0; - if (bit_width <= 8) { + if (bit_width <= 8) *ret = inb(port); - } else if (bit_width <= 16) { + else if (bit_width <= 16) *ret = inw(port); - } else if (bit_width <= 32) { + else if (bit_width <= 32) *ret = inl(port); - } else { - return -ENODEV; +} + +struct msr_addr { + u32 reg; +}; + +struct io_addr { + u16 port; + u8 bit_width; +}; + +typedef union { + struct msr_addr msr; + struct io_addr io; +} drv_addr_union; + +struct drv_cmd { + unsigned int type; + cpumask_t mask; + drv_addr_union addr; + u32 val; +}; + +static void do_drv_read(struct drv_cmd *cmd) +{ + u32 h; + + switch (cmd->type) { + case SYSTEM_INTEL_MSR_CAPABLE: + rdmsr(cmd->addr.msr.reg, cmd->val, h); + break; + case SYSTEM_IO_CAPABLE: + rdport(cmd->addr.io.port, cmd->addr.io.bit_width, &cmd->val); + break; + default: + break; } - return 0; } -static int -acpi_processor_set_performance ( - struct cpufreq_acpi_io *data, - unsigned int cpu, - int state) +static void do_drv_write(struct drv_cmd *cmd) { - u16 port = 0; - u8 bit_width = 0; - int i = 0; - int ret = 0; - u32 value = 0; - int retval; - struct acpi_processor_performance *perf; - - dprintk("acpi_processor_set_performance\n"); - - retval = 0; - perf = data->acpi_data; - if (state == perf->state) { - if (unlikely(data->resume)) { - dprintk("Called after resume, resetting to P%d\n", state); - data->resume = 0; - } else { - dprintk("Already at target state (P%d)\n", state); - return (retval); - } + u32 h = 0; + + switch (cmd->type) { + case SYSTEM_INTEL_MSR_CAPABLE: + wrmsr(cmd->addr.msr.reg, cmd->val, h); + break; + case SYSTEM_IO_CAPABLE: + wrport(cmd->addr.io.port, cmd->addr.io.bit_width, cmd->val); + break; + default: + break; } +} - dprintk("Transitioning from P%d to P%d\n", perf->state, state); +static void drv_read(struct drv_cmd *cmd) +{ + cpumask_t saved_mask = current->cpus_allowed; + cmd->val = 0; - /* - * First we write the target state's 'control' value to the - * control_register. - */ + set_cpus_allowed(current, cmd->mask); + do_drv_read(cmd); + set_cpus_allowed(current, saved_mask); +} + +static void drv_write(struct drv_cmd *cmd) +{ + cpumask_t saved_mask = current->cpus_allowed; + unsigned int i; + + for_each_cpu_mask(i, cmd->mask) { + set_cpus_allowed(current, cpumask_of_cpu(i)); + do_drv_write(cmd); + } + + set_cpus_allowed(current, saved_mask); + return; +} + +static u32 get_cur_val(cpumask_t mask) +{ + struct acpi_processor_performance *perf; + struct drv_cmd cmd; + + if (unlikely(cpus_empty(mask))) + return 0; + + switch (drv_data[first_cpu(mask)]->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + cmd.type = SYSTEM_INTEL_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; + break; + case SYSTEM_IO_CAPABLE: + cmd.type = SYSTEM_IO_CAPABLE; + perf = drv_data[first_cpu(mask)]->acpi_data; + cmd.addr.io.port = perf->control_register.address; + cmd.addr.io.bit_width = perf->control_register.bit_width; + break; + default: + return 0; + } + + cmd.mask = mask; - port = perf->control_register.address; - bit_width = perf->control_register.bit_width; - value = (u32) perf->states[state].control; + drv_read(&cmd); - dprintk("Writing 0x%08x to port 0x%04x\n", value, port); + dprintk("get_cur_val = %u\n", cmd.val); - ret = acpi_processor_write_port(port, bit_width, value); - if (ret) { - dprintk("Invalid port width 0x%04x\n", bit_width); - return (ret); + return cmd.val; +} + +/* + * Return the measured active (C0) frequency on this CPU since last call + * to this function. + * Input: cpu number + * Return: Average CPU frequency in terms of max frequency (zero on error) + * + * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance + * over a period of time, while CPU is in C0 state. + * IA32_MPERF counts at the rate of max advertised frequency + * IA32_APERF counts at the rate of actual CPU frequency + * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and + * no meaning should be associated with absolute values of these MSRs. + */ +static unsigned int get_measured_perf(unsigned int cpu) +{ + union { + struct { + u32 lo; + u32 hi; + } split; + u64 whole; + } aperf_cur, mperf_cur; + + cpumask_t saved_mask; + unsigned int perf_percent; + unsigned int retval; + + saved_mask = current->cpus_allowed; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + if (get_cpu() != cpu) { + /* We were not able to run on requested processor */ + put_cpu(); + return 0; } + rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi); + rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi); + + wrmsr(MSR_IA32_APERF, 0,0); + wrmsr(MSR_IA32_MPERF, 0,0); + +#ifdef __i386__ /* - * Assume the write went through when acpi_pstate_strict is not used. - * As read status_register is an expensive operation and there - * are no specific error cases where an IO port write will fail. + * We dont want to do 64 bit divide with 32 bit kernel + * Get an approximate value. Return failure in case we cannot get + * an approximate value. */ - if (acpi_pstate_strict) { - /* Then we read the 'status_register' and compare the value - * with the target state's 'status' to make sure the - * transition was successful. - * Note that we'll poll for up to 1ms (100 cycles of 10us) - * before giving up. - */ - - port = perf->status_register.address; - bit_width = perf->status_register.bit_width; - - dprintk("Looking for 0x%08x from port 0x%04x\n", - (u32) perf->states[state].status, port); - - for (i = 0; i < 100; i++) { - ret = acpi_processor_read_port(port, bit_width, &value); - if (ret) { - dprintk("Invalid port width 0x%04x\n", bit_width); - return (ret); - } - if (value == (u32) perf->states[state].status) - break; - udelay(10); - } - } else { - value = (u32) perf->states[state].status; + if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) { + int shift_count; + u32 h; + + h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi); + shift_count = fls(h); + + aperf_cur.whole >>= shift_count; + mperf_cur.whole >>= shift_count; + } + + if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) { + int shift_count = 7; + aperf_cur.split.lo >>= shift_count; + mperf_cur.split.lo >>= shift_count; + } + + if (aperf_cur.split.lo && mperf_cur.split.lo) + perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo; + else + perf_percent = 0; + +#else + if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) { + int shift_count = 7; + aperf_cur.whole >>= shift_count; + mperf_cur.whole >>= shift_count; } - if (unlikely(value != (u32) perf->states[state].status)) { - printk(KERN_WARNING "acpi-cpufreq: Transition failed\n"); - retval = -ENODEV; - return (retval); + if (aperf_cur.whole && mperf_cur.whole) + perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole; + else + perf_percent = 0; + +#endif + + retval = drv_data[cpu]->max_freq * perf_percent / 100; + + put_cpu(); + set_cpus_allowed(current, saved_mask); + + dprintk("cpu %d: performance percent %d\n", cpu, perf_percent); + return retval; +} + +static unsigned int get_cur_freq_on_cpu(unsigned int cpu) +{ + struct acpi_cpufreq_data *data = drv_data[cpu]; + unsigned int freq; + + dprintk("get_cur_freq_on_cpu (%d)\n", cpu); + + if (unlikely(data == NULL || + data->acpi_data == NULL || data->freq_table == NULL)) { + return 0; } - dprintk("Transition successful after %d microseconds\n", i * 10); + freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data); + dprintk("cur freq = %u\n", freq); - perf->state = state; - return (retval); + return freq; } +static unsigned int check_freqs(cpumask_t mask, unsigned int freq, + struct acpi_cpufreq_data *data) +{ + unsigned int cur_freq; + unsigned int i; + + for (i=0; i<100; i++) { + cur_freq = extract_freq(get_cur_val(mask), data); + if (cur_freq == freq) + return 1; + udelay(10); + } + return 0; +} -static int -acpi_cpufreq_target ( - struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) +static int acpi_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, unsigned int relation) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; struct acpi_processor_performance *perf; struct cpufreq_freqs freqs; cpumask_t online_policy_cpus; - cpumask_t saved_mask; - cpumask_t set_mask; - cpumask_t covered_cpus; - unsigned int cur_state = 0; + struct drv_cmd cmd; + unsigned int msr; unsigned int next_state = 0; - unsigned int result = 0; - unsigned int j; - unsigned int tmp; + unsigned int next_perf_state = 0; + unsigned int i; + int result = 0; - dprintk("acpi_cpufreq_setpolicy\n"); + dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu); - result = cpufreq_frequency_table_target(policy, - data->freq_table, - target_freq, - relation, - &next_state); - if (unlikely(result)) - return (result); + if (unlikely(data == NULL || + data->acpi_data == NULL || data->freq_table == NULL)) { + return -ENODEV; + } perf = data->acpi_data; - cur_state = perf->state; - freqs.old = data->freq_table[cur_state].frequency; - freqs.new = data->freq_table[next_state].frequency; + result = cpufreq_frequency_table_target(policy, + data->freq_table, + target_freq, + relation, &next_state); + if (unlikely(result)) + return -ENODEV; #ifdef CONFIG_HOTPLUG_CPU /* cpufreq holds the hotplug lock, so we are safe from here on */ @@ -231,106 +417,84 @@ acpi_cpufreq_target ( online_policy_cpus = policy->cpus; #endif - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + next_perf_state = data->freq_table[next_state].index; + if (perf->state == next_perf_state) { + if (unlikely(data->resume)) { + dprintk("Called after resume, resetting to P%d\n", + next_perf_state); + data->resume = 0; + } else { + dprintk("Already at target state (P%d)\n", + next_perf_state); + return 0; + } } - /* - * We need to call driver->target() on all or any CPU in - * policy->cpus, depending on policy->shared_type. - */ - saved_mask = current->cpus_allowed; - cpus_clear(covered_cpus); - for_each_cpu_mask(j, online_policy_cpus) { - /* - * Support for SMP systems. - * Make sure we are running on CPU that wants to change freq - */ - cpus_clear(set_mask); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - cpus_or(set_mask, set_mask, online_policy_cpus); - else - cpu_set(j, set_mask); - - set_cpus_allowed(current, set_mask); - if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) { - dprintk("couldn't limit to CPUs in this domain\n"); - result = -EAGAIN; - break; - } + switch (data->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + cmd.type = SYSTEM_INTEL_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_IA32_PERF_CTL; + msr = + (u32) perf->states[next_perf_state]. + control & INTEL_MSR_RANGE; + cmd.val = (cmd.val & ~INTEL_MSR_RANGE) | msr; + break; + case SYSTEM_IO_CAPABLE: + cmd.type = SYSTEM_IO_CAPABLE; + cmd.addr.io.port = perf->control_register.address; + cmd.addr.io.bit_width = perf->control_register.bit_width; + cmd.val = (u32) perf->states[next_perf_state].control; + break; + default: + return -ENODEV; + } - result = acpi_processor_set_performance (data, j, next_state); - if (result) { - result = -EAGAIN; - break; - } + cpus_clear(cmd.mask); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - break; - - cpu_set(j, covered_cpus); - } + if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY) + cmd.mask = online_policy_cpus; + else + cpu_set(policy->cpu, cmd.mask); - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + freqs.old = data->freq_table[perf->state].frequency; + freqs.new = data->freq_table[next_perf_state].frequency; + for_each_cpu_mask(i, cmd.mask) { + freqs.cpu = i; + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } - if (unlikely(result)) { - /* - * We have failed halfway through the frequency change. - * We have sent callbacks to online_policy_cpus and - * acpi_processor_set_performance() has been called on - * coverd_cpus. Best effort undo.. - */ - - if (!cpus_empty(covered_cpus)) { - for_each_cpu_mask(j, covered_cpus) { - policy->cpu = j; - acpi_processor_set_performance (data, - j, - cur_state); - } - } + drv_write(&cmd); - tmp = freqs.new; - freqs.new = freqs.old; - freqs.old = tmp; - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + if (acpi_pstate_strict) { + if (!check_freqs(cmd.mask, freqs.new, data)) { + dprintk("acpi_cpufreq_target failed (%d)\n", + policy->cpu); + return -EAGAIN; } } - set_cpus_allowed(current, saved_mask); - return (result); -} + for_each_cpu_mask(i, cmd.mask) { + freqs.cpu = i; + cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + } + perf->state = next_perf_state; + return result; +} -static int -acpi_cpufreq_verify ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_verify(struct cpufreq_policy *policy) { - unsigned int result = 0; - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_verify\n"); - result = cpufreq_frequency_table_verify(policy, - data->freq_table); - - return (result); + return cpufreq_frequency_table_verify(policy, data->freq_table); } - static unsigned long -acpi_cpufreq_guess_freq ( - struct cpufreq_acpi_io *data, - unsigned int cpu) +acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu) { - struct acpi_processor_performance *perf = data->acpi_data; + struct acpi_processor_performance *perf = data->acpi_data; if (cpu_khz) { /* search the closest match to cpu_khz */ @@ -338,16 +502,16 @@ acpi_cpufreq_guess_freq ( unsigned long freq; unsigned long freqn = perf->states[0].core_frequency * 1000; - for (i = 0; i < (perf->state_count - 1); i++) { + for (i=0; i<(perf->state_count-1); i++) { freq = freqn; freqn = perf->states[i+1].core_frequency * 1000; if ((2 * cpu_khz) > (freqn + freq)) { perf->state = i; - return (freq); + return freq; } } - perf->state = perf->state_count - 1; - return (freqn); + perf->state = perf->state_count-1; + return freqn; } else { /* assume CPU is at P0... */ perf->state = 0; @@ -355,7 +519,6 @@ acpi_cpufreq_guess_freq ( } } - /* * acpi_cpufreq_early_init - initialize ACPI P-States library * @@ -364,30 +527,34 @@ acpi_cpufreq_guess_freq ( * do _PDC and _PSD and find out the processor dependency for the * actual init that will happen later... */ -static int acpi_cpufreq_early_init_acpi(void) +static int acpi_cpufreq_early_init(void) { - struct acpi_processor_performance *data; - unsigned int i, j; + struct acpi_processor_performance *data; + cpumask_t covered; + unsigned int i, j; dprintk("acpi_cpufreq_early_init\n"); for_each_possible_cpu(i) { - data = kzalloc(sizeof(struct acpi_processor_performance), - GFP_KERNEL); + data = kzalloc(sizeof(struct acpi_processor_performance), + GFP_KERNEL); if (!data) { - for_each_possible_cpu(j) { + for_each_cpu_mask(j, covered) { kfree(acpi_perf_data[j]); acpi_perf_data[j] = NULL; } - return (-ENOMEM); + return -ENOMEM; } acpi_perf_data[i] = data; + cpu_set(i, covered); } /* Do initialization in ACPI core */ - return acpi_processor_preregister_performance(acpi_perf_data); + acpi_processor_preregister_performance(acpi_perf_data); + return 0; } +#ifdef CONFIG_SMP /* * Some BIOSes do SW_ANY coordination internally, either set it up in hw * or do it in BIOS firmware and won't inform about it to OS. If not @@ -414,39 +581,42 @@ static struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; +#endif -static int -acpi_cpufreq_cpu_init ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) { - unsigned int i; - unsigned int cpu = policy->cpu; - struct cpufreq_acpi_io *data; - unsigned int result = 0; + unsigned int i; + unsigned int valid_states = 0; + unsigned int cpu = policy->cpu; + struct acpi_cpufreq_data *data; + unsigned int result = 0; struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; - struct acpi_processor_performance *perf; + struct acpi_processor_performance *perf; dprintk("acpi_cpufreq_cpu_init\n"); if (!acpi_perf_data[cpu]) - return (-ENODEV); + return -ENODEV; - data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); + data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL); if (!data) - return (-ENOMEM); + return -ENOMEM; data->acpi_data = acpi_perf_data[cpu]; - acpi_io_data[cpu] = data; + drv_data[cpu] = data; - result = acpi_processor_register_performance(data->acpi_data, cpu); + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) + acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; + result = acpi_processor_register_performance(data->acpi_data, cpu); if (result) goto err_free; perf = data->acpi_data; policy->shared_type = perf->shared_type; + /* - * Will let policy->cpus know about dependency only when software + * Will let policy->cpus know about dependency only when software * coordination is required. */ if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL || @@ -462,10 +632,6 @@ acpi_cpufreq_cpu_init ( } #endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { - acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; - } - /* capability check */ if (perf->state_count <= 1) { dprintk("No P-States\n"); @@ -473,17 +639,33 @@ acpi_cpufreq_cpu_init ( goto err_unreg; } - if ((perf->control_register.space_id != ACPI_ADR_SPACE_SYSTEM_IO) || - (perf->status_register.space_id != ACPI_ADR_SPACE_SYSTEM_IO)) { - dprintk("Unsupported address space [%d, %d]\n", - (u32) (perf->control_register.space_id), - (u32) (perf->status_register.space_id)); + if (perf->control_register.space_id != perf->status_register.space_id) { + result = -ENODEV; + goto err_unreg; + } + + switch (perf->control_register.space_id) { + case ACPI_ADR_SPACE_SYSTEM_IO: + dprintk("SYSTEM IO addr space\n"); + data->cpu_feature = SYSTEM_IO_CAPABLE; + break; + case ACPI_ADR_SPACE_FIXED_HARDWARE: + dprintk("HARDWARE addr space\n"); + if (!check_est_cpu(cpu)) { + result = -ENODEV; + goto err_unreg; + } + data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; + break; + default: + dprintk("Unknown addr space %d\n", + (u32) (perf->control_register.space_id)); result = -ENODEV; goto err_unreg; } - /* alloc freq_table */ - data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * (perf->state_count + 1), GFP_KERNEL); + data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * + (perf->state_count+1), GFP_KERNEL); if (!data->freq_table) { result = -ENOMEM; goto err_unreg; @@ -492,129 +674,140 @@ acpi_cpufreq_cpu_init ( /* detect transition latency */ policy->cpuinfo.transition_latency = 0; for (i=0; i<perf->state_count; i++) { - if ((perf->states[i].transition_latency * 1000) > policy->cpuinfo.transition_latency) - policy->cpuinfo.transition_latency = perf->states[i].transition_latency * 1000; + if ((perf->states[i].transition_latency * 1000) > + policy->cpuinfo.transition_latency) + policy->cpuinfo.transition_latency = + perf->states[i].transition_latency * 1000; } policy->governor = CPUFREQ_DEFAULT_GOVERNOR; - /* The current speed is unknown and not detectable by ACPI... */ - policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu); - + data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ - for (i=0; i<=perf->state_count; i++) - { - data->freq_table[i].index = i; - if (i<perf->state_count) - data->freq_table[i].frequency = perf->states[i].core_frequency * 1000; - else - data->freq_table[i].frequency = CPUFREQ_TABLE_END; + for (i=0; i<perf->state_count; i++) { + if (i>0 && perf->states[i].core_frequency == + perf->states[i-1].core_frequency) + continue; + + data->freq_table[valid_states].index = i; + data->freq_table[valid_states].frequency = + perf->states[i].core_frequency * 1000; + valid_states++; } + data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END; result = cpufreq_frequency_table_cpuinfo(policy, data->freq_table); - if (result) { + if (result) goto err_freqfree; + + switch (data->cpu_feature) { + case ACPI_ADR_SPACE_SYSTEM_IO: + /* Current speed is unknown and not detectable by IO port */ + policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu); + break; + case ACPI_ADR_SPACE_FIXED_HARDWARE: + acpi_cpufreq_driver.get = get_cur_freq_on_cpu; + get_cur_freq_on_cpu(cpu); + break; + default: + break; } /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); - printk(KERN_INFO "acpi-cpufreq: CPU%u - ACPI performance management activated.\n", - cpu); + /* Check for APERF/MPERF support in hardware */ + if (c->x86_vendor == X86_VENDOR_INTEL && c->cpuid_level >= 6) { + unsigned int ecx; + ecx = cpuid_ecx(6); + if (ecx & CPUID_6_ECX_APERFMPERF_CAPABILITY) + acpi_cpufreq_driver.getavg = get_measured_perf; + } + + dprintk("CPU%u - ACPI performance management activated.\n", cpu); for (i = 0; i < perf->state_count; i++) dprintk(" %cP%d: %d MHz, %d mW, %d uS\n", - (i == perf->state?'*':' '), i, + (i == perf->state ? '*' : ' '), i, (u32) perf->states[i].core_frequency, (u32) perf->states[i].power, (u32) perf->states[i].transition_latency); cpufreq_frequency_table_get_attr(data->freq_table, policy->cpu); - + /* * the first call to ->target() should result in us actually * writing something to the appropriate registers. */ data->resume = 1; - - return (result); - err_freqfree: + return result; + +err_freqfree: kfree(data->freq_table); - err_unreg: +err_unreg: acpi_processor_unregister_performance(perf, cpu); - err_free: +err_free: kfree(data); - acpi_io_data[cpu] = NULL; + drv_data[cpu] = NULL; - return (result); + return result; } - -static int -acpi_cpufreq_cpu_exit ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_cpu_exit\n"); if (data) { cpufreq_frequency_table_put_attr(policy->cpu); - acpi_io_data[policy->cpu] = NULL; - acpi_processor_unregister_performance(data->acpi_data, policy->cpu); + drv_data[policy->cpu] = NULL; + acpi_processor_unregister_performance(data->acpi_data, + policy->cpu); kfree(data); } - return (0); + return 0; } -static int -acpi_cpufreq_resume ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_resume\n"); data->resume = 1; - return (0); + return 0; } - -static struct freq_attr* acpi_cpufreq_attr[] = { +static struct freq_attr *acpi_cpufreq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; static struct cpufreq_driver acpi_cpufreq_driver = { - .verify = acpi_cpufreq_verify, - .target = acpi_cpufreq_target, - .init = acpi_cpufreq_cpu_init, - .exit = acpi_cpufreq_cpu_exit, - .resume = acpi_cpufreq_resume, - .name = "acpi-cpufreq", - .owner = THIS_MODULE, - .attr = acpi_cpufreq_attr, + .verify = acpi_cpufreq_verify, + .target = acpi_cpufreq_target, + .init = acpi_cpufreq_cpu_init, + .exit = acpi_cpufreq_cpu_exit, + .resume = acpi_cpufreq_resume, + .name = "acpi-cpufreq", + .owner = THIS_MODULE, + .attr = acpi_cpufreq_attr, }; - -static int __init -acpi_cpufreq_init (void) +static int __init acpi_cpufreq_init(void) { dprintk("acpi_cpufreq_init\n"); - acpi_cpufreq_early_init_acpi(); + acpi_cpufreq_early_init(); return cpufreq_register_driver(&acpi_cpufreq_driver); } - -static void __exit -acpi_cpufreq_exit (void) +static void __exit acpi_cpufreq_exit(void) { - unsigned int i; + unsigned int i; dprintk("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); @@ -627,7 +820,9 @@ acpi_cpufreq_exit (void) } module_param(acpi_pstate_strict, uint, 0644); -MODULE_PARM_DESC(acpi_pstate_strict, "value 0 or non-zero. non-zero -> strict ACPI checks are performed during frequency changes."); +MODULE_PARM_DESC(acpi_pstate_strict, + "value 0 or non-zero. non-zero -> strict ACPI checks are " + "performed during frequency changes."); late_initcall(acpi_cpufreq_init); module_exit(acpi_cpufreq_exit); diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c index 92afa3bc84f..6667e9cceb9 100644 --- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c @@ -447,7 +447,6 @@ static int __init cpufreq_gx_init(void) int ret; struct gxfreq_params *params; struct pci_dev *gx_pci; - u32 class_rev; /* Test if we have the right hardware */ if ((gx_pci = gx_detect_chipset()) == NULL) @@ -472,8 +471,7 @@ static int __init cpufreq_gx_init(void) pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2)); pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration)); pci_read_config_byte(params->cs55x0, PCI_MODOFF, &(params->off_duration)); - pci_read_config_dword(params->cs55x0, PCI_CLASS_REVISION, &class_rev); - params->pci_rev = class_rev && 0xff; + pci_read_config_byte(params->cs55x0, PCI_REVISION_ID, ¶ms->pci_rev); if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { kfree(params); diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index 7233abe5d69..c548daad347 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -410,7 +410,7 @@ static int __init longhaul_get_ranges(void) maxmult=longhaul_get_cpu_mult(); /* Starting with the 1.2GHz parts, theres a 200MHz bus. */ - if ((cpu_khz/1000) > 1200) + if ((cpu_khz/maxmult) > 13400) fsb = 200; else fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB]; @@ -583,6 +583,10 @@ static int enable_arbiter_disable(void) if (dev == NULL) { reg = 0x76; dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_862X_0, NULL); + /* Find CN400 V-Link host bridge */ + if (dev == NULL) + dev = pci_find_device(PCI_VENDOR_ID_VIA, 0x7259, NULL); + } if (dev != NULL) { /* Enable access to port 0x22 */ @@ -734,7 +738,7 @@ print_support_type: return 0; err_acpi: - printk(KERN_ERR PFX "No ACPI support. No VT8601 or VT8623 northbridge. Aborting.\n"); + printk(KERN_ERR PFX "No ACPI support. Unsupported northbridge. Aborting.\n"); return -ENODEV; } diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index 304d2eaa4a1..bec50170b75 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -163,29 +163,27 @@ static int cpufreq_p4_verify(struct cpufreq_policy *policy) static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { - if ((c->x86 == 0x06) && (c->x86_model == 0x09)) { - /* Pentium M (Banias) */ - printk(KERN_WARNING PFX "Warning: Pentium M detected. " - "The speedstep_centrino module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); - } - - if ((c->x86 == 0x06) && (c->x86_model == 0x0D)) { - /* Pentium M (Dothan) */ - printk(KERN_WARNING PFX "Warning: Pentium M detected. " - "The speedstep_centrino module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); - /* on P-4s, the TSC runs with constant frequency independent whether - * throttling is active or not. */ - p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + if (c->x86 == 0x06) { + if (cpu_has(c, X86_FEATURE_EST)) + printk(KERN_WARNING PFX "Warning: EST-capable CPU detected. " + "The acpi-cpufreq module offers voltage scaling" + " in addition of frequency scaling. You should use " + "that instead of p4-clockmod, if possible.\n"); + switch (c->x86_model) { + case 0x0E: /* Core */ + case 0x0F: /* Core Duo */ + p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; + return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PCORE); + case 0x0D: /* Pentium M (Dothan) */ + p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; + /* fall through */ + case 0x09: /* Pentium M (Banias) */ + return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + } } if (c->x86 != 0xF) { - printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. Please send an e-mail to <linux@brodo.de>\n"); + printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. Please send an e-mail to <cpufreq@lists.linux.org.uk>\n"); return 0; } diff --git a/arch/i386/kernel/cpu/cpufreq/sc520_freq.c b/arch/i386/kernel/cpu/cpufreq/sc520_freq.c index ef457d50f4a..b8fb4b521c6 100644 --- a/arch/i386/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/i386/kernel/cpu/cpufreq/sc520_freq.c @@ -153,6 +153,7 @@ static struct cpufreq_driver sc520_freq_driver = { static int __init sc520_freq_init(void) { struct cpuinfo_x86 *c = cpu_data; + int err; /* Test if we have the right hardware */ if(c->x86_vendor != X86_VENDOR_AMD || @@ -166,7 +167,11 @@ static int __init sc520_freq_init(void) return -ENOMEM; } - return cpufreq_register_driver(&sc520_freq_driver); + err = cpufreq_register_driver(&sc520_freq_driver); + if (err) + iounmap(cpuctl); + + return err; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index e8993baf3d1..5113e923163 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -36,6 +36,7 @@ #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg) +#define INTEL_MSR_RANGE (0xffff) struct cpu_id { @@ -379,6 +380,7 @@ static int centrino_cpu_early_init_acpi(void) } +#ifdef CONFIG_SMP /* * Some BIOSes do SW_ANY coordination internally, either set it up in hw * or do it in BIOS firmware and won't inform about it to OS. If not @@ -392,7 +394,6 @@ static int sw_any_bug_found(struct dmi_system_id *d) return 0; } - static struct dmi_system_id sw_any_bug_dmi_table[] = { { .callback = sw_any_bug_found, @@ -405,7 +406,7 @@ static struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; - +#endif /* * centrino_cpu_init_acpi - register with ACPI P-States library @@ -463,8 +464,9 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } for (i=0; i<p->state_count; i++) { - if (p->states[i].control != p->states[i].status) { - dprintk("Different control (%llu) and status values (%llu)\n", + if ((p->states[i].control & INTEL_MSR_RANGE) != + (p->states[i].status & INTEL_MSR_RANGE)) { + dprintk("Different MSR bits in control (%llu) and status (%llu)\n", p->states[i].control, p->states[i].status); result = -EINVAL; goto err_unreg; @@ -500,7 +502,7 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } for (i=0; i<p->state_count; i++) { - centrino_model[cpu]->op_points[i].index = p->states[i].control; + centrino_model[cpu]->op_points[i].index = p->states[i].control & INTEL_MSR_RANGE; centrino_model[cpu]->op_points[i].frequency = p->states[i].core_frequency * 1000; dprintk("adding state %i with frequency %u and control value %04x\n", i, centrino_model[cpu]->op_points[i].frequency, centrino_model[cpu]->op_points[i].index); @@ -531,6 +533,9 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); + printk("speedstep-centrino with X86_SPEEDSTEP_CENTRINO_ACPI" + "config is deprecated.\n " + "Use X86_ACPI_CPUFREQ (acpi-cpufreq instead.\n" ); return 0; diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c index 4f46cac155c..d59277c0091 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c @@ -123,6 +123,36 @@ static unsigned int pentiumM_get_frequency(void) return (msr_tmp * 100 * 1000); } +static unsigned int pentium_core_get_frequency(void) +{ + u32 fsb = 0; + u32 msr_lo, msr_tmp; + + rdmsr(MSR_FSB_FREQ, msr_lo, msr_tmp); + /* see table B-2 of 25366920.pdf */ + switch (msr_lo & 0x07) { + case 5: + fsb = 100000; + break; + case 1: + fsb = 133333; + break; + case 3: + fsb = 166667; + break; + default: + printk(KERN_ERR "PCORE - MSR_FSB_FREQ undefined value"); + } + + rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); + dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + + msr_tmp = (msr_lo >> 22) & 0x1f; + dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * fsb)); + + return (msr_tmp * fsb); +} + static unsigned int pentium4_get_frequency(void) { @@ -174,6 +204,8 @@ static unsigned int pentium4_get_frequency(void) unsigned int speedstep_get_processor_frequency(unsigned int processor) { switch (processor) { + case SPEEDSTEP_PROCESSOR_PCORE: + return pentium_core_get_frequency(); case SPEEDSTEP_PROCESSOR_PM: return pentiumM_get_frequency(); case SPEEDSTEP_PROCESSOR_P4D: diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h index b735429c50b..b11bcc608ca 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h @@ -22,6 +22,7 @@ * the speedstep_get_processor_frequency() call. */ #define SPEEDSTEP_PROCESSOR_PM 0xFFFFFF03 /* Pentium M */ #define SPEEDSTEP_PROCESSOR_P4D 0xFFFFFF04 /* desktop P4 */ +#define SPEEDSTEP_PROCESSOR_PCORE 0xFFFFFF05 /* Core */ /* speedstep states -- only two of them */ diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c index c28333d5364..ff0d8980611 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c @@ -360,9 +360,6 @@ static int __init speedstep_init(void) case SPEEDSTEP_PROCESSOR_PIII_C: case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: break; - case SPEEDSTEP_PROCESSOR_P4M: - printk(KERN_INFO "speedstep-smi: you're trying to use this cpufreq driver on a Pentium 4-based CPU. Most likely it will not work.\n"); - break; default: speedstep_processor = 0; } diff --git a/arch/x86_64/kernel/cpufreq/Kconfig b/arch/x86_64/kernel/cpufreq/Kconfig index 81f1562e539..3abcfa3e1ed 100644 --- a/arch/x86_64/kernel/cpufreq/Kconfig +++ b/arch/x86_64/kernel/cpufreq/Kconfig @@ -27,10 +27,13 @@ config X86_POWERNOW_K8_ACPI default y config X86_SPEEDSTEP_CENTRINO - tristate "Intel Enhanced SpeedStep" + tristate "Intel Enhanced SpeedStep (deprecated)" select CPU_FREQ_TABLE depends on ACPI_PROCESSOR help + This is deprecated and this functionality is now merged into + acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of + speedstep_centrino. This adds the CPUFreq driver for Enhanced SpeedStep enabled mobile CPUs. This means Intel Pentium M (Centrino) CPUs or 64bit enabled Intel Xeons. @@ -50,6 +53,7 @@ config X86_ACPI_CPUFREQ help This driver adds a CPUFreq driver which utilizes the ACPI Processor Performance States. + This driver also supports Intel Enhanced Speedstep. For details, take a look at <file:Documentation/cpu-freq/>. diff --git a/arch/x86_64/kernel/cpufreq/Makefile b/arch/x86_64/kernel/cpufreq/Makefile index d8b59387922..753ce1dd418 100644 --- a/arch/x86_64/kernel/cpufreq/Makefile +++ b/arch/x86_64/kernel/cpufreq/Makefile @@ -5,8 +5,8 @@ SRCDIR := ../../../i386/kernel/cpu/cpufreq obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o -obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 47ab42db122..9fb2edf3661 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -29,7 +29,8 @@ #include <linux/completion.h> #include <linux/mutex.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "cpufreq-core", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \ + "cpufreq-core", msg) /** * The "cpufreq driver" - the arch- or hardware-dependent low @@ -151,7 +152,8 @@ static void cpufreq_debug_disable_ratelimit(void) spin_unlock_irqrestore(&disable_ratelimit_lock, flags); } -void cpufreq_debug_printk(unsigned int type, const char *prefix, const char *fmt, ...) +void cpufreq_debug_printk(unsigned int type, const char *prefix, + const char *fmt, ...) { char s[256]; va_list args; @@ -161,7 +163,8 @@ void cpufreq_debug_printk(unsigned int type, const char *prefix, const char *fmt WARN_ON(!prefix); if (type & debug) { spin_lock_irqsave(&disable_ratelimit_lock, flags); - if (!disable_ratelimit && debug_ratelimit && !printk_ratelimit()) { + if (!disable_ratelimit && debug_ratelimit + && !printk_ratelimit()) { spin_unlock_irqrestore(&disable_ratelimit_lock, flags); return; } @@ -182,10 +185,12 @@ EXPORT_SYMBOL(cpufreq_debug_printk); module_param(debug, uint, 0644); -MODULE_PARM_DESC(debug, "CPUfreq debugging: add 1 to debug core, 2 to debug drivers, and 4 to debug governors."); +MODULE_PARM_DESC(debug, "CPUfreq debugging: add 1 to debug core," + " 2 to debug drivers, and 4 to debug governors."); module_param(debug_ratelimit, uint, 0644); -MODULE_PARM_DESC(debug_ratelimit, "CPUfreq debugging: set to 0 to disable ratelimiting."); +MODULE_PARM_DESC(debug_ratelimit, "CPUfreq debugging:" + " set to 0 to disable ratelimiting."); #else /* !CONFIG_CPU_FREQ_DEBUG */ @@ -219,17 +224,23 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) if (!l_p_j_ref_freq) { l_p_j_ref = loops_per_jiffy; l_p_j_ref_freq = ci->old; - dprintk("saving %lu as reference value for loops_per_jiffy; freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq); + dprintk("saving %lu as reference value for loops_per_jiffy;" + "freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq); } if ((val == CPUFREQ_PRECHANGE && ci->old < ci->new) || (val == CPUFREQ_POSTCHANGE && ci->old > ci->new) || (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) { - loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, ci->new); - dprintk("scaling loops_per_jiffy to %lu for frequency %u kHz\n", loops_per_jiffy, ci->new); + loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, + ci->new); + dprintk("scaling loops_per_jiffy to %lu" + "for frequency %u kHz\n", loops_per_jiffy, ci->new); } } #else -static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) { return; } +static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) +{ + return; +} #endif @@ -316,7 +327,8 @@ static int cpufreq_parse_governor (char *str_governor, unsigned int *policy, if (!strnicmp(str_governor, "performance", CPUFREQ_NAME_LEN)) { *policy = CPUFREQ_POLICY_PERFORMANCE; err = 0; - } else if (!strnicmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) { + } else if (!strnicmp(str_governor, "powersave", + CPUFREQ_NAME_LEN)) { *policy = CPUFREQ_POLICY_POWERSAVE; err = 0; } @@ -328,7 +340,8 @@ static int cpufreq_parse_governor (char *str_governor, unsigned int *policy, t = __find_governor(str_governor); if (t == NULL) { - char *name = kasprintf(GFP_KERNEL, "cpufreq_%s", str_governor); + char *name = kasprintf(GFP_KERNEL, "cpufreq_%s", + str_governor); if (name) { int ret; @@ -361,7 +374,8 @@ extern struct sysdev_class cpu_sysdev_class; /** - * cpufreq_per_cpu_attr_read() / show_##file_name() - print out cpufreq information + * cpufreq_per_cpu_attr_read() / show_##file_name() - + * print out cpufreq information * * Write out information from cpufreq_driver->policy[cpu]; object must be * "unsigned int". @@ -380,7 +394,8 @@ show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); show_one(scaling_cur_freq, cur); -static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_policy *policy); +static int __cpufreq_set_policy(struct cpufreq_policy *data, + struct cpufreq_policy *policy); /** * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access @@ -416,7 +431,8 @@ store_one(scaling_max_freq,max); /** * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware */ -static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy, char *buf) +static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy, + char *buf) { unsigned int cur_freq = cpufreq_get(policy->cpu); if (!cur_freq) @@ -428,7 +444,8 @@ static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy, char *buf) /** * show_scaling_governor - show the current policy for the specified CPU */ -static ssize_t show_scaling_governor (struct cpufreq_policy * policy, char *buf) +static ssize_t show_scaling_governor (struct cpufreq_policy * policy, + char *buf) { if(policy->policy == CPUFREQ_POLICY_POWERSAVE) return sprintf(buf, "powersave\n"); @@ -458,7 +475,8 @@ static ssize_t store_scaling_governor (struct cpufreq_policy * policy, if (ret != 1) return -EINVAL; - if (cpufreq_parse_governor(str_governor, &new_policy.policy, &new_policy.governor)) + if (cpufreq_parse_governor(str_governor, &new_policy.policy, + &new_policy.governor)) return -EINVAL; lock_cpu_hotplug(); @@ -474,7 +492,10 @@ static ssize_t store_scaling_governor (struct cpufreq_policy * policy, unlock_cpu_hotplug(); - return ret ? ret : count; + if (ret) + return ret; + else + return count; } /** @@ -488,7 +509,7 @@ static ssize_t show_scaling_driver (struct cpufreq_policy * policy, char *buf) /** * show_scaling_available_governors - show the available CPUfreq governors */ -static ssize_t show_scaling_available_governors (struct cpufreq_policy * policy, +static ssize_t show_scaling_available_governors (struct cpufreq_policy *policy, char *buf) { ssize_t i = 0; @@ -574,7 +595,11 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf) policy = cpufreq_cpu_get(policy->cpu); if (!policy) return -EINVAL; - ret = fattr->show ? fattr->show(policy,buf) : -EIO; + if (fattr->show) + ret = fattr->show(policy, buf); + else + ret = -EIO; + cpufreq_cpu_put(policy); return ret; } @@ -588,7 +613,11 @@ static ssize_t store(struct kobject * kobj, struct attribute * attr, policy = cpufreq_cpu_get(policy->cpu); if (!policy) return -EINVAL; - ret = fattr->store ? fattr->store(policy,buf,count) : -EIO; + if (fattr->store) + ret = fattr->store(policy, buf, count); + else + ret = -EIO; + cpufreq_cpu_put(policy); return ret; } @@ -913,7 +942,8 @@ static void handle_update(struct work_struct *work) * We adjust to current frequency first, and need to clean up later. So either call * to cpufreq_update_policy() or schedule handle_update()). */ -static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigned int new_freq) +static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, + unsigned int new_freq) { struct cpufreq_freqs freqs; @@ -938,16 +968,16 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigne unsigned int cpufreq_quick_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret = 0; + unsigned int ret_freq = 0; if (policy) { mutex_lock(&policy->lock); - ret = policy->cur; + ret_freq = policy->cur; mutex_unlock(&policy->lock); cpufreq_cpu_put(policy); } - return (ret); + return (ret_freq); } EXPORT_SYMBOL(cpufreq_quick_get); @@ -961,7 +991,7 @@ EXPORT_SYMBOL(cpufreq_quick_get); unsigned int cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret = 0; + unsigned int ret_freq = 0; if (!policy) return 0; @@ -971,12 +1001,14 @@ unsigned int cpufreq_get(unsigned int cpu) mutex_lock(&policy->lock); - ret = cpufreq_driver->get(cpu); + ret_freq = cpufreq_driver->get(cpu); - if (ret && policy->cur && !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - /* verify no discrepancy between actual and saved value exists */ - if (unlikely(ret != policy->cur)) { - cpufreq_out_of_sync(cpu, policy->cur, ret); + if (ret_freq && policy->cur && + !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { + /* verify no discrepancy between actual and + saved value exists */ + if (unlikely(ret_freq != policy->cur)) { + cpufreq_out_of_sync(cpu, policy->cur, ret_freq); schedule_work(&policy->update); } } @@ -986,7 +1018,7 @@ unsigned int cpufreq_get(unsigned int cpu) out: cpufreq_cpu_put(policy); - return (ret); + return (ret_freq); } EXPORT_SYMBOL(cpufreq_get); @@ -998,7 +1030,7 @@ EXPORT_SYMBOL(cpufreq_get); static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg) { int cpu = sysdev->id; - unsigned int ret = 0; + int ret = 0; unsigned int cur_freq = 0; struct cpufreq_policy *cpu_policy; @@ -1080,7 +1112,7 @@ out: static int cpufreq_resume(struct sys_device * sysdev) { int cpu = sysdev->id; - unsigned int ret = 0; + int ret = 0; struct cpufreq_policy *cpu_policy; dprintk("resuming cpu %u\n", cpu); @@ -1276,22 +1308,45 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, } EXPORT_SYMBOL_GPL(cpufreq_driver_target); +int cpufreq_driver_getavg(struct cpufreq_policy *policy) +{ + int ret = 0; + + policy = cpufreq_cpu_get(policy->cpu); + if (!policy) + return -EINVAL; + + mutex_lock(&policy->lock); + + if (cpu_online(policy->cpu) && cpufreq_driver->getavg) + ret = cpufreq_driver->getavg(policy->cpu); + + mutex_unlock(&policy->lock); + + cpufreq_cpu_put(policy); + return ret; +} +EXPORT_SYMBOL_GPL(cpufreq_driver_getavg); + /* * Locking: Must be called with the lock_cpu_hotplug() lock held * when "event" is CPUFREQ_GOV_LIMITS */ -static int __cpufreq_governor(struct cpufreq_policy *policy, unsigned int event) +static int __cpufreq_governor(struct cpufreq_policy *policy, + unsigned int event) { int ret; if (!try_module_get(policy->governor->owner)) return -EINVAL; - dprintk("__cpufreq_governor for CPU %u, event %u\n", policy->cpu, event); + dprintk("__cpufreq_governor for CPU %u, event %u\n", + policy->cpu, event); ret = policy->governor->governor(policy, event); - /* we keep one module reference alive for each CPU governed by this CPU */ + /* we keep one module reference alive for + each CPU governed by this CPU */ if ((event != CPUFREQ_GOV_START) || ret) module_put(policy->governor->owner); if ((event == CPUFREQ_GOV_STOP) && !ret) @@ -1367,9 +1422,12 @@ EXPORT_SYMBOL(cpufreq_get_policy); /* + * data : current policy. + * policy : policy to be set. * Locking: Must be called with the lock_cpu_hotplug() lock held */ -static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_policy *policy) +static int __cpufreq_set_policy(struct cpufreq_policy *data, + struct cpufreq_policy *policy) { int ret = 0; @@ -1377,7 +1435,8 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli dprintk("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu, policy->min, policy->max); - memcpy(&policy->cpuinfo, &data->cpuinfo, sizeof(struct cpufreq_cpuinfo)); + memcpy(&policy->cpuinfo, &data->cpuinfo, + sizeof(struct cpufreq_cpuinfo)); if (policy->min > data->min && policy->min > policy->max) { ret = -EINVAL; @@ -1410,7 +1469,8 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli data->min = policy->min; data->max = policy->max; - dprintk("new min and max freqs are %u - %u kHz\n", data->min, data->max); + dprintk("new min and max freqs are %u - %u kHz\n", + data->min, data->max); if (cpufreq_driver->setpolicy) { data->policy = policy->policy; @@ -1431,10 +1491,12 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli data->governor = policy->governor; if (__cpufreq_governor(data, CPUFREQ_GOV_START)) { /* new governor failed, so re-start old one */ - dprintk("starting governor %s failed\n", data->governor->name); + dprintk("starting governor %s failed\n", + data->governor->name); if (old_gov) { data->governor = old_gov; - __cpufreq_governor(data, CPUFREQ_GOV_START); + __cpufreq_governor(data, + CPUFREQ_GOV_START); } ret = -EINVAL; goto error_out; @@ -1524,7 +1586,8 @@ int cpufreq_update_policy(unsigned int cpu) data->cur = policy.cur; } else { if (data->cur != policy.cur) - cpufreq_out_of_sync(cpu, data->cur, policy.cur); + cpufreq_out_of_sync(cpu, data->cur, + policy.cur); } } @@ -1626,8 +1689,10 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) /* if all ->init() calls failed, unregister */ if (ret) { - dprintk("no CPU initialized for driver %s\n", driver_data->name); - sysdev_driver_unregister(&cpu_sysdev_class, &cpufreq_sysdev_driver); + dprintk("no CPU initialized for driver %s\n", + driver_data->name); + sysdev_driver_unregister(&cpu_sysdev_class, + &cpufreq_sysdev_driver); spin_lock_irqsave(&cpufreq_driver_lock, flags); cpufreq_driver = NULL; diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 5ef5ede5b88..eef0270c6f3 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -44,15 +44,17 @@ * latency of the processor. The governor will work on any processor with * transition latency <= 10mS, using appropriate sampling * rate. - * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL) - * this governor will not work. + * For CPUs with transition latency > 10mS (mostly drivers + * with CPUFREQ_ETERNAL), this governor will not work. * All times here are in uS. */ static unsigned int def_sampling_rate; #define MIN_SAMPLING_RATE_RATIO (2) /* for correct statistics, we need at least 10 ticks between each measure */ -#define MIN_STAT_SAMPLING_RATE (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) -#define MIN_SAMPLING_RATE (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) +#define MIN_STAT_SAMPLING_RATE \ + (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) +#define MIN_SAMPLING_RATE \ + (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) #define MAX_SAMPLING_RATE (500 * def_sampling_rate) #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (1000) #define DEF_SAMPLING_DOWN_FACTOR (1) @@ -103,11 +105,16 @@ static struct dbs_tuners dbs_tuners_ins = { static inline unsigned int get_cpu_idle_time(unsigned int cpu) { - return kstat_cpu(cpu).cpustat.idle + + unsigned int add_nice = 0, ret; + + if (dbs_tuners_ins.ignore_nice) + add_nice = kstat_cpu(cpu).cpustat.nice; + + ret = kstat_cpu(cpu).cpustat.idle + kstat_cpu(cpu).cpustat.iowait + - ( dbs_tuners_ins.ignore_nice ? - kstat_cpu(cpu).cpustat.nice : - 0); + add_nice; + + return ret; } /************************** sysfs interface ************************/ @@ -452,6 +459,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int cpu = policy->cpu; struct cpu_dbs_info_s *this_dbs_info; unsigned int j; + int rc; this_dbs_info = &per_cpu(cpu_dbs_info, cpu); @@ -468,6 +476,13 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, break; mutex_lock(&dbs_mutex); + + rc = sysfs_create_group(&policy->kobj, &dbs_attr_group); + if (rc) { + mutex_unlock(&dbs_mutex); + return rc; + } + for_each_cpu_mask(j, policy->cpus) { struct cpu_dbs_info_s *j_dbs_info; j_dbs_info = &per_cpu(cpu_dbs_info, j); @@ -480,7 +495,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, this_dbs_info->enable = 1; this_dbs_info->down_skip = 0; this_dbs_info->requested_freq = policy->cur; - sysfs_create_group(&policy->kobj, &dbs_attr_group); + dbs_enable++; /* * Start the timerschedule work, when this governor diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index e1cc5113c2a..f697449327c 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -41,8 +41,10 @@ static unsigned int def_sampling_rate; #define MIN_SAMPLING_RATE_RATIO (2) /* for correct statistics, we need at least 10 ticks between each measure */ -#define MIN_STAT_SAMPLING_RATE (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) -#define MIN_SAMPLING_RATE (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) +#define MIN_STAT_SAMPLING_RATE \ + (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) +#define MIN_SAMPLING_RATE \ + (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) #define MAX_SAMPLING_RATE (500 * def_sampling_rate) #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (1000) #define TRANSITION_LATENCY_LIMIT (10 * 1000) @@ -206,7 +208,8 @@ static ssize_t store_sampling_rate(struct cpufreq_policy *unused, ret = sscanf(buf, "%u", &input); mutex_lock(&dbs_mutex); - if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) { + if (ret != 1 || input > MAX_SAMPLING_RATE + || input < MIN_SAMPLING_RATE) { mutex_unlock(&dbs_mutex); return -EINVAL; } @@ -397,8 +400,15 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) * policy. To be safe, we focus 10 points under the threshold. */ if (load < (dbs_tuners_ins.up_threshold - 10)) { - unsigned int freq_next = (policy->cur * load) / + unsigned int freq_next, freq_cur; + + freq_cur = cpufreq_driver_getavg(policy); + if (!freq_cur) + freq_cur = policy->cur; + + freq_next = (freq_cur * load) / (dbs_tuners_ins.up_threshold - 10); + if (!dbs_tuners_ins.powersave_bias) { __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L); @@ -472,6 +482,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int cpu = policy->cpu; struct cpu_dbs_info_s *this_dbs_info; unsigned int j; + int rc; this_dbs_info = &per_cpu(cpu_dbs_info, cpu); @@ -494,12 +505,23 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, if (dbs_enable == 1) { kondemand_wq = create_workqueue("kondemand"); if (!kondemand_wq) { - printk(KERN_ERR "Creation of kondemand failed\n"); + printk(KERN_ERR + "Creation of kondemand failed\n"); dbs_enable--; mutex_unlock(&dbs_mutex); return -ENOSPC; } } + + rc = sysfs_create_group(&policy->kobj, &dbs_attr_group); + if (rc) { + if (dbs_enable == 1) + destroy_workqueue(kondemand_wq); + dbs_enable--; + mutex_unlock(&dbs_mutex); + return rc; + } + for_each_cpu_mask(j, policy->cpus) { struct cpu_dbs_info_s *j_dbs_info; j_dbs_info = &per_cpu(cpu_dbs_info, j); @@ -509,7 +531,6 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, j_dbs_info->prev_cpu_wall = get_jiffies_64(); } this_dbs_info->enable = 1; - sysfs_create_group(&policy->kobj, &dbs_attr_group); /* * Start the timerschedule work, when this governor * is used for first time diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index de91e3371ef..e8e1451ef1c 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -15,7 +15,8 @@ #include <linux/cpufreq.h> #include <linux/init.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg) static int cpufreq_governor_performance(struct cpufreq_policy *policy, @@ -24,8 +25,10 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy, switch (event) { case CPUFREQ_GOV_START: case CPUFREQ_GOV_LIMITS: - dprintk("setting to %u kHz because of event %u\n", policy->max, event); - __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); + dprintk("setting to %u kHz because of event %u\n", + policy->max, event); + __cpufreq_driver_target(policy, policy->max, + CPUFREQ_RELATION_H); break; default: break; diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index 0a2596044e6..13fe06b94b0 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -15,7 +15,8 @@ #include <linux/cpufreq.h> #include <linux/init.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg) static int cpufreq_governor_powersave(struct cpufreq_policy *policy, unsigned int event) @@ -23,8 +24,10 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy, switch (event) { case CPUFREQ_GOV_START: case CPUFREQ_GOV_LIMITS: - dprintk("setting to %u kHz because of event %u\n", policy->min, event); - __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); + dprintk("setting to %u kHz because of event %u\n", + policy->min, event); + __cpufreq_driver_target(policy, policy->min, + CPUFREQ_RELATION_L); break; default: break; diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index c2ecc599dc5..6742b1adf2c 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -351,8 +351,8 @@ __init cpufreq_stats_init(void) register_hotcpu_notifier(&cpufreq_stat_cpu_notifier); for_each_online_cpu(cpu) { - cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, CPU_ONLINE, - (void *)(long)cpu); + cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, + CPU_ONLINE, (void *)(long)cpu); } return 0; } @@ -368,14 +368,15 @@ __exit cpufreq_stats_exit(void) unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier); lock_cpu_hotplug(); for_each_online_cpu(cpu) { - cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, CPU_DEAD, - (void *)(long)cpu); + cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, + CPU_DEAD, (void *)(long)cpu); } unlock_cpu_hotplug(); } MODULE_AUTHOR ("Zou Nan hai <nanhai.zou@intel.com>"); -MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats through sysfs filesystem"); +MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats" + "through sysfs filesystem"); MODULE_LICENSE ("GPL"); module_init(cpufreq_stats_init); diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c index a06c204589c..2a4eb0bfaf3 100644 --- a/drivers/cpufreq/cpufreq_userspace.c +++ b/drivers/cpufreq/cpufreq_userspace.c @@ -131,19 +131,26 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, unsigned int event) { unsigned int cpu = policy->cpu; + int rc = 0; + switch (event) { case CPUFREQ_GOV_START: if (!cpu_online(cpu)) return -EINVAL; BUG_ON(!policy->cur); mutex_lock(&userspace_mutex); + rc = sysfs_create_file (&policy->kobj, + &freq_attr_scaling_setspeed.attr); + if (rc) + goto start_out; + cpu_is_managed[cpu] = 1; cpu_min_freq[cpu] = policy->min; cpu_max_freq[cpu] = policy->max; cpu_cur_freq[cpu] = policy->cur; cpu_set_freq[cpu] = policy->cur; - sysfs_create_file (&policy->kobj, &freq_attr_scaling_setspeed.attr); dprintk("managing cpu %u started (%u - %u kHz, currently %u kHz)\n", cpu, cpu_min_freq[cpu], cpu_max_freq[cpu], cpu_cur_freq[cpu]); +start_out: mutex_unlock(&userspace_mutex); break; case CPUFREQ_GOV_STOP: @@ -180,7 +187,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, mutex_unlock(&userspace_mutex); break; } - return 0; + return rc; } diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 551f4ccf87f..e7490925fdc 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -9,7 +9,8 @@ #include <linux/init.h> #include <linux/cpufreq.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg) /********************************************************************* * FREQUENCY TABLE HELPERS * @@ -29,7 +30,8 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, continue; } - dprintk("table entry %u: %u kHz, %u index\n", i, freq, table[i].index); + dprintk("table entry %u: %u kHz, %u index\n", + i, freq, table[i].index); if (freq < min_freq) min_freq = freq; if (freq > max_freq) @@ -54,13 +56,14 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, unsigned int i; unsigned int count = 0; - dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n", policy->min, policy->max, policy->cpu); + dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n", + policy->min, policy->max, policy->cpu); if (!cpu_online(policy->cpu)) return -EINVAL; - cpufreq_verify_within_limits(policy, - policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); + cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, + policy->cpuinfo.max_freq); for (i=0; (table[i].frequency != CPUFREQ_TABLE_END); i++) { unsigned int freq = table[i].frequency; @@ -75,10 +78,11 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, if (!count) policy->max = next_larger; - cpufreq_verify_within_limits(policy, - policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); + cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, + policy->cpuinfo.max_freq); - dprintk("verification lead to (%u - %u kHz) for cpu %u\n", policy->min, policy->max, policy->cpu); + dprintk("verification lead to (%u - %u kHz) for cpu %u\n", + policy->min, policy->max, policy->cpu); return 0; } @@ -101,7 +105,8 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, }; unsigned int i; - dprintk("request for target %u kHz (relation: %u) for cpu %u\n", target_freq, relation, policy->cpu); + dprintk("request for target %u kHz (relation: %u) for cpu %u\n", + target_freq, relation, policy->cpu); switch (relation) { case CPUFREQ_RELATION_H: @@ -192,7 +197,10 @@ static ssize_t show_available_freqs (struct cpufreq_policy *policy, char *buf) } struct freq_attr cpufreq_freq_attr_scaling_available_freqs = { - .attr = { .name = "scaling_available_frequencies", .mode = 0444, .owner=THIS_MODULE }, + .attr = { .name = "scaling_available_frequencies", + .mode = 0444, + .owner=THIS_MODULE + }, .show = show_available_freqs, }; EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs); diff --git a/include/asm-i386/msr.h b/include/asm-i386/msr.h index 5679d499307..609a3899475 100644 --- a/include/asm-i386/msr.h +++ b/include/asm-i386/msr.h @@ -100,6 +100,8 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val) #define MSR_P6_PERFCTR0 0xc1 #define MSR_P6_PERFCTR1 0xc2 +#define MSR_FSB_FREQ 0xcd + #define MSR_IA32_BBL_CR_CTL 0x119 @@ -130,6 +132,9 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val) #define MSR_IA32_PERF_STATUS 0x198 #define MSR_IA32_PERF_CTL 0x199 +#define MSR_IA32_MPERF 0xE7 +#define MSR_IA32_APERF 0xE8 + #define MSR_IA32_THERM_CONTROL 0x19a #define MSR_IA32_THERM_INTERRUPT 0x19b #define MSR_IA32_THERM_STATUS 0x19c diff --git a/include/asm-x86_64/msr.h b/include/asm-x86_64/msr.h index 952783d35c7..3227bc93d69 100644 --- a/include/asm-x86_64/msr.h +++ b/include/asm-x86_64/msr.h @@ -189,6 +189,7 @@ static inline unsigned int cpuid_edx(unsigned int op) #define MSR_IA32_PERFCTR0 0xc1 #define MSR_IA32_PERFCTR1 0xc2 +#define MSR_FSB_FREQ 0xcd #define MSR_MTRRcap 0x0fe #define MSR_IA32_BBL_CR_CTL 0x119 @@ -311,6 +312,9 @@ static inline unsigned int cpuid_edx(unsigned int op) #define MSR_IA32_PERF_STATUS 0x198 #define MSR_IA32_PERF_CTL 0x199 +#define MSR_IA32_MPERF 0xE7 +#define MSR_IA32_APERF 0xE8 + #define MSR_IA32_THERM_CONTROL 0x19a #define MSR_IA32_THERM_INTERRUPT 0x19b #define MSR_IA32_THERM_STATUS 0x19c diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4ea39fee99c..7f008f6bfdc 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -172,6 +172,8 @@ extern int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); +extern int cpufreq_driver_getavg(struct cpufreq_policy *policy); + int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); @@ -204,6 +206,7 @@ struct cpufreq_driver { unsigned int (*get) (unsigned int cpu); /* optional */ + unsigned int (*getavg) (unsigned int cpu); int (*exit) (struct cpufreq_policy *policy); int (*suspend) (struct cpufreq_policy *policy, pm_message_t pmsg); int (*resume) (struct cpufreq_policy *policy); |