linux_dsm_epyc7002/drivers/cpufreq/ia64-acpi-cpufreq.c

353 lines
7.6 KiB
C
Raw Normal View History

/*
* This file provides the ACPI based P-state support. This
* module works with generic cpufreq infrastructure. Most of
* the code is based on i386 version
* (arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c)
*
* Copyright (C) 2005 Intel Corp
* Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/cpufreq.h>
#include <linux/proc_fs.h>
#include <asm/io.h>
#include <linux/uaccess.h>
#include <asm/pal.h>
#include <linux/acpi.h>
#include <acpi/processor.h>
MODULE_AUTHOR("Venkatesh Pallipadi");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
MODULE_LICENSE("GPL");
struct cpufreq_acpi_io {
struct acpi_processor_performance acpi_data;
unsigned int resume;
};
struct cpufreq_acpi_req {
unsigned int cpu;
unsigned int state;
};
static struct cpufreq_acpi_io *acpi_io_data[NR_CPUS];
static struct cpufreq_driver acpi_cpufreq_driver;
static int
processor_set_pstate (
u32 value)
{
s64 retval;
pr_debug("processor_set_pstate\n");
retval = ia64_pal_set_pstate((u64)value);
if (retval) {
pr_debug("Failed to set freq to 0x%x, with error 0x%lx\n",
value, retval);
return -ENODEV;
}
return (int)retval;
}
static int
processor_get_pstate (
u32 *value)
{
u64 pstate_index = 0;
s64 retval;
pr_debug("processor_get_pstate\n");
retval = ia64_pal_get_pstate(&pstate_index,
PAL_GET_PSTATE_TYPE_INSTANT);
*value = (u32) pstate_index;
if (retval)
pr_debug("Failed to get current freq with "
"error 0x%lx, idx 0x%x\n", retval, *value);
return (int)retval;
}
/* To be used only after data->acpi_data is initialized */
static unsigned
extract_clock (
struct cpufreq_acpi_io *data,
unsigned value)
{
unsigned long i;
pr_debug("extract_clock\n");
for (i = 0; i < data->acpi_data.state_count; i++) {
if (value == data->acpi_data.states[i].status)
return data->acpi_data.states[i].core_frequency;
}
return data->acpi_data.states[i-1].core_frequency;
}
static long
processor_get_freq (
void *arg)
{
struct cpufreq_acpi_req *req = arg;
unsigned int cpu = req->cpu;
struct cpufreq_acpi_io *data = acpi_io_data[cpu];
u32 value;
int ret;
pr_debug("processor_get_freq\n");
if (smp_processor_id() != cpu)
return -EAGAIN;
/* processor_get_pstate gets the instantaneous frequency */
ret = processor_get_pstate(&value);
if (ret) {
pr_warn("get performance failed with error %d\n", ret);
return ret;
}
return 1000 * extract_clock(data, value);
}
static long
processor_set_freq (
void *arg)
{
struct cpufreq_acpi_req *req = arg;
unsigned int cpu = req->cpu;
struct cpufreq_acpi_io *data = acpi_io_data[cpu];
int ret, state = req->state;
u32 value;
pr_debug("processor_set_freq\n");
if (smp_processor_id() != cpu)
return -EAGAIN;
if (state == data->acpi_data.state) {
if (unlikely(data->resume)) {
pr_debug("Called after resume, resetting to P%d\n", state);
data->resume = 0;
} else {
pr_debug("Already at target state (P%d)\n", state);
return 0;
}
}
pr_debug("Transitioning from P%d to P%d\n",
data->acpi_data.state, state);
/*
* First we write the target state's 'control' value to the
* control_register.
*/
value = (u32) data->acpi_data.states[state].control;
pr_debug("Transitioning to state: 0x%08x\n", value);
ret = processor_set_pstate(value);
if (ret) {
pr_warn("Transition failed with error %d\n", ret);
return -ENODEV;
}
data->acpi_data.state = state;
return 0;
}
static unsigned int
acpi_cpufreq_get (
unsigned int cpu)
{
struct cpufreq_acpi_req req;
long ret;
req.cpu = cpu;
ret = work_on_cpu(cpu, processor_get_freq, &req);
return ret > 0 ? (unsigned int) ret : 0;
}
static int
acpi_cpufreq_target (
struct cpufreq_policy *policy,
cpufreq: Implement light weight ->target_index() routine Currently, the prototype of cpufreq_drivers target routines is: int target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); And most of the drivers call cpufreq_frequency_table_target() to get a valid index of their frequency table which is closest to the target_freq. And they don't use target_freq and relation after that. So, it makes sense to just do this work in cpufreq core before calling cpufreq_frequency_table_target() and simply pass index instead. But this can be done only with drivers which expose their frequency table with cpufreq core. For others we need to stick with the old prototype of target() until those drivers are converted to expose frequency tables. This patch implements the new light weight prototype for target_index() routine. It looks like this: int target_index(struct cpufreq_policy *policy, unsigned int index); CPUFreq core will call cpufreq_frequency_table_target() before calling this routine and pass index to it. Because CPUFreq core now requires to call routines present in freq_table.c CONFIG_CPU_FREQ_TABLE must be enabled all the time. This also marks target() interface as deprecated. So, that new drivers avoid using it. And Documentation is updated accordingly. It also converts existing .target() to newly defined light weight .target_index() routine for many driver. Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King <linux@arm.linux.org.uk> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rjw@rjwysocki.net>
2013-10-25 21:15:48 +07:00
unsigned int index)
{
struct cpufreq_acpi_req req;
req.cpu = policy->cpu;
req.state = index;
return work_on_cpu(req.cpu, processor_set_freq, &req);
}
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;
struct cpufreq_frequency_table *freq_table;
pr_debug("acpi_cpufreq_cpu_init\n");
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return (-ENOMEM);
acpi_io_data[cpu] = data;
result = acpi_processor_register_performance(&data->acpi_data, cpu);
if (result)
goto err_free;
/* capability check */
if (data->acpi_data.state_count <= 1) {
pr_debug("No P-States\n");
result = -ENODEV;
goto err_unreg;
}
if ((data->acpi_data.control_register.space_id !=
ACPI_ADR_SPACE_FIXED_HARDWARE) ||
(data->acpi_data.status_register.space_id !=
ACPI_ADR_SPACE_FIXED_HARDWARE)) {
pr_debug("Unsupported address space [%d, %d]\n",
(u32) (data->acpi_data.control_register.space_id),
(u32) (data->acpi_data.status_register.space_id));
result = -ENODEV;
goto err_unreg;
}
/* alloc freq_table */
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:03:40 +07:00
freq_table = kcalloc(data->acpi_data.state_count + 1,
sizeof(*freq_table),
GFP_KERNEL);
if (!freq_table) {
result = -ENOMEM;
goto err_unreg;
}
/* detect transition latency */
policy->cpuinfo.transition_latency = 0;
for (i=0; i<data->acpi_data.state_count; i++) {
if ((data->acpi_data.states[i].transition_latency * 1000) >
policy->cpuinfo.transition_latency) {
policy->cpuinfo.transition_latency =
data->acpi_data.states[i].transition_latency * 1000;
}
}
/* table init */
for (i = 0; i <= data->acpi_data.state_count; i++)
{
if (i < data->acpi_data.state_count) {
freq_table[i].frequency =
data->acpi_data.states[i].core_frequency * 1000;
} else {
freq_table[i].frequency = CPUFREQ_TABLE_END;
}
}
policy->freq_table = freq_table;
/* notify BIOS that we exist */
acpi_processor_notify_smm(THIS_MODULE);
pr_info("CPU%u - ACPI performance management activated\n", cpu);
for (i = 0; i < data->acpi_data.state_count; i++)
pr_debug(" %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n",
(i == data->acpi_data.state?'*':' '), i,
(u32) data->acpi_data.states[i].core_frequency,
(u32) data->acpi_data.states[i].power,
(u32) data->acpi_data.states[i].transition_latency,
(u32) data->acpi_data.states[i].bus_master_latency,
(u32) data->acpi_data.states[i].status,
(u32) data->acpi_data.states[i].control);
/* the first call to ->target() should result in us actually
* writing something to the appropriate registers. */
data->resume = 1;
return (result);
err_unreg:
acpi_processor_unregister_performance(cpu);
err_free:
kfree(data);
acpi_io_data[cpu] = NULL;
return (result);
}
static int
acpi_cpufreq_cpu_exit (
struct cpufreq_policy *policy)
{
struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu];
pr_debug("acpi_cpufreq_cpu_exit\n");
if (data) {
acpi_io_data[policy->cpu] = NULL;
acpi_processor_unregister_performance(policy->cpu);
kfree(policy->freq_table);
kfree(data);
}
return (0);
}
static struct cpufreq_driver acpi_cpufreq_driver = {
.verify = cpufreq_generic_frequency_table_verify,
cpufreq: Implement light weight ->target_index() routine Currently, the prototype of cpufreq_drivers target routines is: int target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); And most of the drivers call cpufreq_frequency_table_target() to get a valid index of their frequency table which is closest to the target_freq. And they don't use target_freq and relation after that. So, it makes sense to just do this work in cpufreq core before calling cpufreq_frequency_table_target() and simply pass index instead. But this can be done only with drivers which expose their frequency table with cpufreq core. For others we need to stick with the old prototype of target() until those drivers are converted to expose frequency tables. This patch implements the new light weight prototype for target_index() routine. It looks like this: int target_index(struct cpufreq_policy *policy, unsigned int index); CPUFreq core will call cpufreq_frequency_table_target() before calling this routine and pass index to it. Because CPUFreq core now requires to call routines present in freq_table.c CONFIG_CPU_FREQ_TABLE must be enabled all the time. This also marks target() interface as deprecated. So, that new drivers avoid using it. And Documentation is updated accordingly. It also converts existing .target() to newly defined light weight .target_index() routine for many driver. Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King <linux@arm.linux.org.uk> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rjw@rjwysocki.net>
2013-10-25 21:15:48 +07:00
.target_index = acpi_cpufreq_target,
.get = acpi_cpufreq_get,
.init = acpi_cpufreq_cpu_init,
.exit = acpi_cpufreq_cpu_exit,
.name = "acpi-cpufreq",
.attr = cpufreq_generic_attr,
};
static int __init
acpi_cpufreq_init (void)
{
pr_debug("acpi_cpufreq_init\n");
return cpufreq_register_driver(&acpi_cpufreq_driver);
}
static void __exit
acpi_cpufreq_exit (void)
{
pr_debug("acpi_cpufreq_exit\n");
cpufreq_unregister_driver(&acpi_cpufreq_driver);
}
late_initcall(acpi_cpufreq_init);
module_exit(acpi_cpufreq_exit);