linux_dsm_epyc7002/drivers/acpi/processor_perflib.c

811 lines
20 KiB
C
Raw Normal View History

/*
* processor_perflib.c - ACPI Processor P-States Library ($Revision: 71 $)
*
* Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
* Copyright (C) 2004 Dominik Brodowski <linux@brodo.de>
* Copyright (C) 2004 Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
* - Added processor hotplug support
*
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or (at
* your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/cpufreq.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>
ACPI: Clean up inclusions of ACPI header files Replace direct inclusions of <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h>, which are incorrect, with <linux/acpi.h> inclusions and remove some inclusions of those files that aren't necessary. First of all, <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h> should not be included directly from any files that are built for CONFIG_ACPI unset, because that generally leads to build warnings about undefined symbols in !CONFIG_ACPI builds. For CONFIG_ACPI set, <linux/acpi.h> includes those files and for CONFIG_ACPI unset it provides stub ACPI symbols to be used in that case. Second, there are ordering dependencies between those files that always have to be met. Namely, it is required that <acpi/acpi_bus.h> be included prior to <acpi/acpi_drivers.h> so that the acpi_pci_root declarations the latter depends on are always there. And <acpi/acpi.h> which provides basic ACPICA type declarations should always be included prior to any other ACPI headers in CONFIG_ACPI builds. That also is taken care of including <linux/acpi.h> as appropriate. Signed-off-by: Lv Zheng <lv.zheng@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Tony Luck <tony.luck@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> (drivers/pci stuff) Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> (Xen stuff) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-12-03 07:49:16 +07:00
#include <linux/acpi.h>
#include <acpi/processor.h>
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
#endif
#define PREFIX "ACPI: "
#define ACPI_PROCESSOR_CLASS "processor"
#define ACPI_PROCESSOR_FILE_PERFORMANCE "performance"
#define _COMPONENT ACPI_PROCESSOR_COMPONENT
ACPI_MODULE_NAME("processor_perflib");
static DEFINE_MUTEX(performance_mutex);
/*
* _PPC support is implemented as a CPUfreq policy notifier:
* This means each time a CPUfreq driver registered also with
* the ACPI core is asked to change the speed policy, the maximum
* value is adjusted so that it is within the platform limit.
*
* Also, when a new platform limit value is detected, the CPUfreq
* policy is adjusted accordingly.
*/
/* ignore_ppc:
* -1 -> cpufreq low level drivers not initialized -> _PSS, etc. not called yet
* ignore _PPC
* 0 -> cpufreq low level drivers initialized -> consider _PPC values
* 1 -> ignore _PPC totally -> forced by user through boot param
*/
static int ignore_ppc = -1;
module_param(ignore_ppc, int, 0644);
MODULE_PARM_DESC(ignore_ppc, "If the frequency of your machine gets wrongly" \
"limited by BIOS, this should help");
#define PPC_REGISTERED 1
#define PPC_IN_USE 2
static int acpi_processor_ppc_status;
static int acpi_processor_ppc_notifier(struct notifier_block *nb,
unsigned long event, void *data)
{
struct cpufreq_policy *policy = data;
struct acpi_processor *pr;
unsigned int ppc = 0;
if (ignore_ppc < 0)
ignore_ppc = 0;
if (ignore_ppc)
return 0;
if (event != CPUFREQ_ADJUST)
return 0;
mutex_lock(&performance_mutex);
pr = per_cpu(processors, policy->cpu);
if (!pr || !pr->performance)
goto out;
ppc = (unsigned int)pr->performance_platform_limit;
if (ppc >= pr->performance->state_count)
goto out;
cpufreq_verify_within_limits(policy, 0,
pr->performance->states[ppc].
core_frequency * 1000);
out:
mutex_unlock(&performance_mutex);
return 0;
}
static struct notifier_block acpi_ppc_notifier_block = {
.notifier_call = acpi_processor_ppc_notifier,
};
static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
{
acpi_status status = 0;
unsigned long long ppc = 0;
if (!pr)
return -EINVAL;
/*
* _PPC indicates the maximum state currently supported by the platform
* (e.g. 0 = states 0..n; 1 = states 1..n; etc.
*/
status = acpi_evaluate_integer(pr->handle, "_PPC", NULL, &ppc);
if (status != AE_NOT_FOUND)
acpi_processor_ppc_status |= PPC_IN_USE;
if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PPC"));
return -ENODEV;
}
pr_debug("CPU %d: _PPC is %d - frequency %s limited\n", pr->id,
(int)ppc, ppc ? "" : "not");
pr->performance_platform_limit = (int)ppc;
return 0;
}
#define ACPI_PROCESSOR_NOTIFY_PERFORMANCE 0x80
/*
* acpi_processor_ppc_ost: Notify firmware the _PPC evaluation status
* @handle: ACPI processor handle
* @status: the status code of _PPC evaluation
* 0: success. OSPM is now using the performance state specificed.
* 1: failure. OSPM has not changed the number of P-states in use
*/
static void acpi_processor_ppc_ost(acpi_handle handle, int status)
{
if (acpi_has_method(handle, "_OST"))
acpi_evaluate_ost(handle, ACPI_PROCESSOR_NOTIFY_PERFORMANCE,
status, NULL);
}
void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag)
{
int ret;
ACPI: processor_perflib: Do not send _PPC change notification if not ready The following warning was triggered after resumed from S3 - if all the nonboot CPUs were put offline before suspend: [ 1840.329515] unchecked MSR access error: RDMSR from 0x771 at rIP: 0xffffffff86061e3a (native_read_msr+0xa/0x30) [ 1840.329516] Call Trace: [ 1840.329521] __rdmsr_on_cpu+0x33/0x50 [ 1840.329525] generic_exec_single+0x81/0xb0 [ 1840.329527] smp_call_function_single+0xd2/0x100 [ 1840.329530] ? acpi_ds_result_pop+0xdd/0xf2 [ 1840.329532] ? acpi_ds_create_operand+0x215/0x23c [ 1840.329534] rdmsrl_on_cpu+0x57/0x80 [ 1840.329536] ? cpumask_next+0x1b/0x20 [ 1840.329538] ? rdmsrl_on_cpu+0x57/0x80 [ 1840.329541] intel_pstate_update_perf_limits+0xf3/0x220 [ 1840.329544] ? notifier_call_chain+0x4a/0x70 [ 1840.329546] intel_pstate_set_policy+0x4e/0x150 [ 1840.329548] cpufreq_set_policy+0xcd/0x2f0 [ 1840.329550] cpufreq_update_policy+0xb2/0x130 [ 1840.329552] ? cpufreq_update_policy+0x130/0x130 [ 1840.329556] acpi_processor_ppc_has_changed+0x65/0x80 [ 1840.329558] acpi_processor_notify+0x80/0x100 [ 1840.329561] acpi_ev_notify_dispatch+0x44/0x5c [ 1840.329563] acpi_os_execute_deferred+0x14/0x20 [ 1840.329565] process_one_work+0x193/0x3c0 [ 1840.329567] worker_thread+0x35/0x3b0 [ 1840.329569] kthread+0x125/0x140 [ 1840.329571] ? process_one_work+0x3c0/0x3c0 [ 1840.329572] ? kthread_park+0x60/0x60 [ 1840.329575] ? do_syscall_64+0x67/0x180 [ 1840.329577] ret_from_fork+0x25/0x30 [ 1840.329585] unchecked MSR access error: WRMSR to 0x774 (tried to write 0x0000000000000000) at rIP: 0xffffffff86061f78 (native_write_msr+0x8/0x30) [ 1840.329586] Call Trace: [ 1840.329587] __wrmsr_on_cpu+0x37/0x40 [ 1840.329589] generic_exec_single+0x81/0xb0 [ 1840.329592] smp_call_function_single+0xd2/0x100 [ 1840.329594] ? acpi_ds_create_operand+0x215/0x23c [ 1840.329595] ? cpumask_next+0x1b/0x20 [ 1840.329597] wrmsrl_on_cpu+0x57/0x70 [ 1840.329598] ? rdmsrl_on_cpu+0x57/0x80 [ 1840.329599] ? wrmsrl_on_cpu+0x57/0x70 [ 1840.329602] intel_pstate_hwp_set+0xd3/0x150 [ 1840.329604] intel_pstate_set_policy+0x119/0x150 [ 1840.329606] cpufreq_set_policy+0xcd/0x2f0 [ 1840.329607] cpufreq_update_policy+0xb2/0x130 [ 1840.329610] ? cpufreq_update_policy+0x130/0x130 [ 1840.329613] acpi_processor_ppc_has_changed+0x65/0x80 [ 1840.329615] acpi_processor_notify+0x80/0x100 [ 1840.329617] acpi_ev_notify_dispatch+0x44/0x5c [ 1840.329619] acpi_os_execute_deferred+0x14/0x20 [ 1840.329620] process_one_work+0x193/0x3c0 [ 1840.329622] worker_thread+0x35/0x3b0 [ 1840.329624] kthread+0x125/0x140 [ 1840.329625] ? process_one_work+0x3c0/0x3c0 [ 1840.329626] ? kthread_park+0x60/0x60 [ 1840.329628] ? do_syscall_64+0x67/0x180 [ 1840.329631] ret_from_fork+0x25/0x30 This is because if there's only one online CPU, the MSR_PM_ENABLE (package wide)can not be enabled after resumed, due to intel_pstate_hwp_enable() will only be invoked on AP's online process after resumed - if there's no AP online, the HWP remains disabled after resumed (BIOS has disabled it in S3). Then if there comes a _PPC change notification which touches HWP register during this stage, the warning is triggered. Since we don't call acpi_processor_register_performance() when HWP is enabled, the pr->performance will be NULL. When this is NULL we don't need to do _PPC change notification. Reported-by: Doug Smythies <dsmythies@telus.net> Suggested-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Signed-off-by: Yu Chen <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2018-01-29 09:26:46 +07:00
if (ignore_ppc || !pr->performance) {
/*
* Only when it is notification event, the _OST object
* will be evaluated. Otherwise it is skipped.
*/
if (event_flag)
acpi_processor_ppc_ost(pr->handle, 1);
return;
}
ret = acpi_processor_get_platform_limit(pr);
/*
* Only when it is notification event, the _OST object
* will be evaluated. Otherwise it is skipped.
*/
if (event_flag) {
if (ret < 0)
acpi_processor_ppc_ost(pr->handle, 1);
else
acpi_processor_ppc_ost(pr->handle, 0);
}
if (ret >= 0)
cpufreq_update_policy(pr->id);
}
[ACPI/CPUFREQ] Introduce bios_limit per cpu cpufreq sysfs interface This interface is mainly intended (and implemented) for ACPI _PPC BIOS frequency limitations, but other cpufreq drivers can also use it for similar use-cases. Why is this needed: Currently it's not obvious why cpufreq got limited. People see cpufreq/scaling_max_freq reduced, but this could have happened by: - any userspace prog writing to scaling_max_freq - thermal limitations - hardware (_PPC in ACPI case) limitiations Therefore export bios_limit (in kHz) to: - Point the user that it's the BIOS (broken or intended) which limits frequency - Export it as a sysfs interface for userspace progs. While this was a rarely used feature on laptops, there will appear more and more server implemenations providing "Green IT" features like allowing the service processor to limit the frequency. People want to know about HW/BIOS frequency limitations. All ACPI P-state driven cpufreq drivers are covered with this patch: - powernow-k8 - powernow-k7 - acpi-cpufreq Tested with a patched DSDT which limits the first two cores (_PPC returns 1) via _PPC, exposed by bios_limit: # echo 2200000 >cpu2/cpufreq/scaling_max_freq # cat cpu*/cpufreq/scaling_max_freq 2600000 2600000 2200000 2200000 # #scaling_max_freq shows general user/thermal/BIOS limitations # cat cpu*/cpufreq/bios_limit 2600000 2600000 2800000 2800000 # #bios_limit only shows the HW/BIOS limitation CC: Pallipadi Venkatesh <venkatesh.pallipadi@intel.com> CC: Len Brown <lenb@kernel.org> CC: davej@codemonkey.org.uk CC: linux@dominikbrodowski.net Signed-off-by: Thomas Renninger <trenn@suse.de> Signed-off-by: Dave Jones <davej@redhat.com>
2009-11-19 18:31:01 +07:00
int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
{
struct acpi_processor *pr;
pr = per_cpu(processors, cpu);
if (!pr || !pr->performance || !pr->performance->state_count)
return -ENODEV;
*limit = pr->performance->states[pr->performance_platform_limit].
core_frequency * 1000;
return 0;
}
EXPORT_SYMBOL(acpi_processor_get_bios_limit);
void acpi_processor_ppc_init(void)
{
if (!cpufreq_register_notifier
(&acpi_ppc_notifier_block, CPUFREQ_POLICY_NOTIFIER))
acpi_processor_ppc_status |= PPC_REGISTERED;
else
printk(KERN_DEBUG
"Warning: Processor Platform Limit not supported.\n");
}
void acpi_processor_ppc_exit(void)
{
if (acpi_processor_ppc_status & PPC_REGISTERED)
cpufreq_unregister_notifier(&acpi_ppc_notifier_block,
CPUFREQ_POLICY_NOTIFIER);
acpi_processor_ppc_status &= ~PPC_REGISTERED;
}
static int acpi_processor_get_performance_control(struct acpi_processor *pr)
{
int result = 0;
acpi_status status = 0;
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *pct = NULL;
union acpi_object obj = { 0 };
status = acpi_evaluate_object(pr->handle, "_PCT", NULL, &buffer);
if (ACPI_FAILURE(status)) {
ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PCT"));
return -ENODEV;
}
pct = (union acpi_object *)buffer.pointer;
if (!pct || (pct->type != ACPI_TYPE_PACKAGE)
|| (pct->package.count != 2)) {
printk(KERN_ERR PREFIX "Invalid _PCT data\n");
result = -EFAULT;
goto end;
}
/*
* control_register
*/
obj = pct->package.elements[0];
if ((obj.type != ACPI_TYPE_BUFFER)
|| (obj.buffer.length < sizeof(struct acpi_pct_register))
|| (obj.buffer.pointer == NULL)) {
printk(KERN_ERR PREFIX "Invalid _PCT data (control_register)\n");
result = -EFAULT;
goto end;
}
memcpy(&pr->performance->control_register, obj.buffer.pointer,
sizeof(struct acpi_pct_register));
/*
* status_register
*/
obj = pct->package.elements[1];
if ((obj.type != ACPI_TYPE_BUFFER)
|| (obj.buffer.length < sizeof(struct acpi_pct_register))
|| (obj.buffer.pointer == NULL)) {
printk(KERN_ERR PREFIX "Invalid _PCT data (status_register)\n");
result = -EFAULT;
goto end;
}
memcpy(&pr->performance->status_register, obj.buffer.pointer,
sizeof(struct acpi_pct_register));
end:
kfree(buffer.pointer);
return result;
}
#ifdef CONFIG_X86
/*
* Some AMDs have 50MHz frequency multiples, but only provide 100MHz rounding
* in their ACPI data. Calculate the real values and fix up the _PSS data.
*/
static void amd_fixup_frequency(struct acpi_processor_px *px, int i)
{
u32 hi, lo, fid, did;
int index = px->control & 0x00000007;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
return;
if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
|| boot_cpu_data.x86 == 0x11) {
rdmsr(MSR_AMD_PSTATE_DEF_BASE + index, lo, hi);
/*
* MSR C001_0064+:
* Bit 63: PstateEn. Read-write. If set, the P-state is valid.
*/
if (!(hi & BIT(31)))
return;
fid = lo & 0x3f;
did = (lo >> 6) & 7;
if (boot_cpu_data.x86 == 0x10)
px->core_frequency = (100 * (fid + 0x10)) >> did;
else
px->core_frequency = (100 * (fid + 8)) >> did;
}
}
#else
static void amd_fixup_frequency(struct acpi_processor_px *px, int i) {};
#endif
static int acpi_processor_get_performance_states(struct acpi_processor *pr)
{
int result = 0;
acpi_status status = AE_OK;
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
struct acpi_buffer format = { sizeof("NNNNNN"), "NNNNNN" };
struct acpi_buffer state = { 0, NULL };
union acpi_object *pss = NULL;
int i;
int last_invalid = -1;
status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer);
if (ACPI_FAILURE(status)) {
ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PSS"));
return -ENODEV;
}
pss = buffer.pointer;
if (!pss || (pss->type != ACPI_TYPE_PACKAGE)) {
printk(KERN_ERR PREFIX "Invalid _PSS data\n");
result = -EFAULT;
goto end;
}
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found %d performance states\n",
pss->package.count));
pr->performance->state_count = pss->package.count;
pr->performance->states =
kmalloc(sizeof(struct acpi_processor_px) * pss->package.count,
GFP_KERNEL);
if (!pr->performance->states) {
result = -ENOMEM;
goto end;
}
for (i = 0; i < pr->performance->state_count; i++) {
struct acpi_processor_px *px = &(pr->performance->states[i]);
state.length = sizeof(struct acpi_processor_px);
state.pointer = px;
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Extracting state %d\n", i));
status = acpi_extract_package(&(pss->package.elements[i]),
&format, &state);
if (ACPI_FAILURE(status)) {
ACPI_EXCEPTION((AE_INFO, status, "Invalid _PSS data"));
result = -EFAULT;
kfree(pr->performance->states);
goto end;
}
amd_fixup_frequency(px, i);
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"State [%d]: core_frequency[%d] power[%d] transition_latency[%d] bus_master_latency[%d] control[0x%x] status[0x%x]\n",
i,
(u32) px->core_frequency,
(u32) px->power,
(u32) px->transition_latency,
(u32) px->bus_master_latency,
(u32) px->control, (u32) px->status));
/*
* Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
*/
if (!px->core_frequency ||
((u32)(px->core_frequency * 1000) !=
(px->core_frequency * 1000))) {
printk(KERN_ERR FW_BUG PREFIX
"Invalid BIOS _PSS frequency found for processor %d: 0x%llx MHz\n",
pr->id, px->core_frequency);
if (last_invalid == -1)
last_invalid = i;
} else {
if (last_invalid != -1) {
/*
* Copy this valid entry over last_invalid entry
*/
memcpy(&(pr->performance->states[last_invalid]),
px, sizeof(struct acpi_processor_px));
++last_invalid;
}
}
}
if (last_invalid == 0) {
printk(KERN_ERR FW_BUG PREFIX
"No valid BIOS _PSS frequency found for processor %d\n", pr->id);
result = -EFAULT;
kfree(pr->performance->states);
pr->performance->states = NULL;
}
if (last_invalid > 0)
pr->performance->state_count = last_invalid;
end:
kfree(buffer.pointer);
return result;
}
acpi: Export the acpi_processor_get_performance_info The git commit d5aaffa9dd531c978c6f3fea06a2972653bd7fc8 (cpufreq: handle cpufreq being disabled for all exported function) tightens the cpufreq API by returning errors when disable_cpufreq() had been called. The problem we are hitting is that the module xen-acpi-processor which uses the ACPI's functions: acpi_processor_register_performance, acpi_processor_preregister_performance, and acpi_processor_notify_smm fails at acpi_processor_register_performance with -22. Note that earlier during bootup in arch/x86/xen/setup.c there is also an call to cpufreq's API: disable_cpufreq(). This is b/c we want the Linux kernel to parse the ACPI data, but leave the cpufreq decisions to the hypervisor. In v3.9 all the checks that d5aaffa9dd531c978c6f3fea06a2972653bd7fc8 added are now hit and the calls to cpufreq_register_notifier will now fail. This means that acpi_processor_ppc_init ends up printing: "Warning: Processor Platform Limit not supported" and the acpi_processor_ppc_status is not set. The repercussions of that is that the call to acpi_processor_register_performance fails right away at: if (!(acpi_processor_ppc_status & PPC_REGISTERED)) and we don't progress any further on parsing and extracting the _P* objects. The only reason the Xen code called that function was b/c it was exported and the only way to gather the P-states. But we can also just make acpi_processor_get_performance_info be exported and not use acpi_processor_register_performance. This patch does so. Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-03-06 01:42:54 +07:00
int acpi_processor_get_performance_info(struct acpi_processor *pr)
{
int result = 0;
if (!pr || !pr->performance || !pr->handle)
return -EINVAL;
if (!acpi_has_method(pr->handle, "_PCT")) {
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"ACPI-based processor performance control unavailable\n"));
return -ENODEV;
}
result = acpi_processor_get_performance_control(pr);
if (result)
goto update_bios;
result = acpi_processor_get_performance_states(pr);
if (result)
goto update_bios;
/* We need to call _PPC once when cpufreq starts */
if (ignore_ppc != 1)
result = acpi_processor_get_platform_limit(pr);
return result;
/*
* Having _PPC but missing frequencies (_PSS, _PCT) is a very good hint that
* the BIOS is older than the CPU and does not know its frequencies
*/
update_bios:
#ifdef CONFIG_X86
if (acpi_has_method(pr->handle, "_PPC")) {
if(boot_cpu_has(X86_FEATURE_EST))
printk(KERN_WARNING FW_BUG "BIOS needs update for CPU "
"frequency support\n");
}
#endif
return result;
}
acpi: Export the acpi_processor_get_performance_info The git commit d5aaffa9dd531c978c6f3fea06a2972653bd7fc8 (cpufreq: handle cpufreq being disabled for all exported function) tightens the cpufreq API by returning errors when disable_cpufreq() had been called. The problem we are hitting is that the module xen-acpi-processor which uses the ACPI's functions: acpi_processor_register_performance, acpi_processor_preregister_performance, and acpi_processor_notify_smm fails at acpi_processor_register_performance with -22. Note that earlier during bootup in arch/x86/xen/setup.c there is also an call to cpufreq's API: disable_cpufreq(). This is b/c we want the Linux kernel to parse the ACPI data, but leave the cpufreq decisions to the hypervisor. In v3.9 all the checks that d5aaffa9dd531c978c6f3fea06a2972653bd7fc8 added are now hit and the calls to cpufreq_register_notifier will now fail. This means that acpi_processor_ppc_init ends up printing: "Warning: Processor Platform Limit not supported" and the acpi_processor_ppc_status is not set. The repercussions of that is that the call to acpi_processor_register_performance fails right away at: if (!(acpi_processor_ppc_status & PPC_REGISTERED)) and we don't progress any further on parsing and extracting the _P* objects. The only reason the Xen code called that function was b/c it was exported and the only way to gather the P-states. But we can also just make acpi_processor_get_performance_info be exported and not use acpi_processor_register_performance. This patch does so. Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-03-06 01:42:54 +07:00
EXPORT_SYMBOL_GPL(acpi_processor_get_performance_info);
int acpi_processor_pstate_control(void)
{
acpi_status status;
if (!acpi_gbl_FADT.smi_command || !acpi_gbl_FADT.pstate_control)
return 0;
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"Writing pstate_control [0x%x] to smi_command [0x%x]\n",
acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command));
status = acpi_os_write_port(acpi_gbl_FADT.smi_command,
(u32)acpi_gbl_FADT.pstate_control, 8);
if (ACPI_SUCCESS(status))
return 1;
ACPI_EXCEPTION((AE_INFO, status,
"Failed to write pstate_control [0x%x] to smi_command [0x%x]",
acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command));
return -EIO;
}
int acpi_processor_notify_smm(struct module *calling_module)
{
static int is_done = 0;
int result;
if (!(acpi_processor_ppc_status & PPC_REGISTERED))
return -EBUSY;
if (!try_module_get(calling_module))
return -EINVAL;
/* is_done is set to negative if an error occurred,
* and to postitive if _no_ error occurred, but SMM
* was already notified. This avoids double notification
* which might lead to unexpected results...
*/
if (is_done > 0) {
module_put(calling_module);
return 0;
} else if (is_done < 0) {
module_put(calling_module);
return is_done;
}
is_done = -EIO;
result = acpi_processor_pstate_control();
if (!result) {
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No SMI port or pstate_control\n"));
module_put(calling_module);
return 0;
}
if (result < 0) {
module_put(calling_module);
return result;
}
/* Success. If there's no _PPC, we need to fear nothing, so
* we can allow the cpufreq driver to be rmmod'ed. */
is_done = 1;
if (!(acpi_processor_ppc_status & PPC_IN_USE))
module_put(calling_module);
return 0;
}
EXPORT_SYMBOL(acpi_processor_notify_smm);
int acpi_processor_get_psd(acpi_handle handle, struct acpi_psd_package *pdomain)
{
int result = 0;
acpi_status status = AE_OK;
struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
struct acpi_buffer format = {sizeof("NNNNN"), "NNNNN"};
struct acpi_buffer state = {0, NULL};
union acpi_object *psd = NULL;
status = acpi_evaluate_object(handle, "_PSD", NULL, &buffer);
if (ACPI_FAILURE(status)) {
return -ENODEV;
}
psd = buffer.pointer;
if (!psd || (psd->type != ACPI_TYPE_PACKAGE)) {
printk(KERN_ERR PREFIX "Invalid _PSD data\n");
result = -EFAULT;
goto end;
}
if (psd->package.count != 1) {
printk(KERN_ERR PREFIX "Invalid _PSD data\n");
result = -EFAULT;
goto end;
}
state.length = sizeof(struct acpi_psd_package);
state.pointer = pdomain;
status = acpi_extract_package(&(psd->package.elements[0]),
&format, &state);
if (ACPI_FAILURE(status)) {
printk(KERN_ERR PREFIX "Invalid _PSD data\n");
result = -EFAULT;
goto end;
}
if (pdomain->num_entries != ACPI_PSD_REV0_ENTRIES) {
printk(KERN_ERR PREFIX "Unknown _PSD:num_entries\n");
result = -EFAULT;
goto end;
}
if (pdomain->revision != ACPI_PSD_REV0_REVISION) {
printk(KERN_ERR PREFIX "Unknown _PSD:revision\n");
result = -EFAULT;
goto end;
}
if (pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ALL &&
pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ANY &&
pdomain->coord_type != DOMAIN_COORD_TYPE_HW_ALL) {
printk(KERN_ERR PREFIX "Invalid _PSD:coord_type\n");
result = -EFAULT;
goto end;
}
end:
kfree(buffer.pointer);
return result;
}
EXPORT_SYMBOL(acpi_processor_get_psd);
int acpi_processor_preregister_performance(
struct acpi_processor_performance __percpu *performance)
{
int count_target;
int retval = 0;
unsigned int i, j;
cpumask_var_t covered_cpus;
struct acpi_processor *pr;
struct acpi_psd_package *pdomain;
struct acpi_processor *match_pr;
struct acpi_psd_package *match_pdomain;
if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
return -ENOMEM;
mutex_lock(&performance_mutex);
/*
* Check if another driver has already registered, and abort before
* changing pr->performance if it has. Check input data as well.
*/
for_each_possible_cpu(i) {
pr = per_cpu(processors, i);
if (!pr) {
/* Look only at processors in ACPI namespace */
continue;
}
if (pr->performance) {
retval = -EBUSY;
goto err_out;
}
if (!performance || !per_cpu_ptr(performance, i)) {
retval = -EINVAL;
goto err_out;
}
}
/* Call _PSD for all CPUs */
for_each_possible_cpu(i) {
pr = per_cpu(processors, i);
if (!pr)
continue;
pr->performance = per_cpu_ptr(performance, i);
cpumask_set_cpu(i, pr->performance->shared_cpu_map);
pdomain = &(pr->performance->domain_info);
if (acpi_processor_get_psd(pr->handle, pdomain)) {
retval = -EINVAL;
continue;
}
}
if (retval)
goto err_ret;
/*
* Now that we have _PSD data from all CPUs, lets setup P-state
* domain info.
*/
for_each_possible_cpu(i) {
pr = per_cpu(processors, i);
if (!pr)
continue;
if (cpumask_test_cpu(i, covered_cpus))
continue;
pdomain = &(pr->performance->domain_info);
cpumask_set_cpu(i, pr->performance->shared_cpu_map);
cpumask_set_cpu(i, covered_cpus);
if (pdomain->num_processors <= 1)
continue;
/* Validate the Domain info */
count_target = pdomain->num_processors;
if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ALL;
else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
pr->performance->shared_type = CPUFREQ_SHARED_TYPE_HW;
else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ANY;
for_each_possible_cpu(j) {
if (i == j)
continue;
match_pr = per_cpu(processors, j);
if (!match_pr)
continue;
match_pdomain = &(match_pr->performance->domain_info);
if (match_pdomain->domain != pdomain->domain)
continue;
/* Here i and j are in the same domain */
if (match_pdomain->num_processors != count_target) {
retval = -EINVAL;
goto err_ret;
}
if (pdomain->coord_type != match_pdomain->coord_type) {
retval = -EINVAL;
goto err_ret;
}
cpumask_set_cpu(j, covered_cpus);
cpumask_set_cpu(j, pr->performance->shared_cpu_map);
}
for_each_possible_cpu(j) {
if (i == j)
continue;
match_pr = per_cpu(processors, j);
if (!match_pr)
continue;
match_pdomain = &(match_pr->performance->domain_info);
if (match_pdomain->domain != pdomain->domain)
continue;
match_pr->performance->shared_type =
pr->performance->shared_type;
cpumask_copy(match_pr->performance->shared_cpu_map,
pr->performance->shared_cpu_map);
}
}
err_ret:
for_each_possible_cpu(i) {
pr = per_cpu(processors, i);
if (!pr || !pr->performance)
continue;
/* Assume no coordination on any error parsing domain info */
if (retval) {
cpumask_clear(pr->performance->shared_cpu_map);
cpumask_set_cpu(i, pr->performance->shared_cpu_map);
pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ALL;
}
pr->performance = NULL; /* Will be set for real in register */
}
err_out:
mutex_unlock(&performance_mutex);
free_cpumask_var(covered_cpus);
return retval;
}
EXPORT_SYMBOL(acpi_processor_preregister_performance);
int
acpi_processor_register_performance(struct acpi_processor_performance
*performance, unsigned int cpu)
{
struct acpi_processor *pr;
if (!(acpi_processor_ppc_status & PPC_REGISTERED))
return -EINVAL;
mutex_lock(&performance_mutex);
pr = per_cpu(processors, cpu);
if (!pr) {
mutex_unlock(&performance_mutex);
return -ENODEV;
}
if (pr->performance) {
mutex_unlock(&performance_mutex);
return -EBUSY;
}
WARN_ON(!performance);
pr->performance = performance;
if (acpi_processor_get_performance_info(pr)) {
pr->performance = NULL;
mutex_unlock(&performance_mutex);
return -EIO;
}
mutex_unlock(&performance_mutex);
return 0;
}
EXPORT_SYMBOL(acpi_processor_register_performance);
void acpi_processor_unregister_performance(unsigned int cpu)
{
struct acpi_processor *pr;
mutex_lock(&performance_mutex);
pr = per_cpu(processors, cpu);
if (!pr) {
mutex_unlock(&performance_mutex);
return;
}
if (pr->performance)
kfree(pr->performance->states);
pr->performance = NULL;
mutex_unlock(&performance_mutex);
return;
}
EXPORT_SYMBOL(acpi_processor_unregister_performance);