alistair23-linux/drivers/platform/x86/intel_turbo_max_3.c
Srinivas Pandruvada 5520437beb platform/x86: intel_turbo_max_3: Add Skylake platform
Ev Kontsevoy reported that he can't see the presence of
"/proc/sys/kernel/sched_itmt_enabled" on i9-7900x with Asrock x299
Taichi system even if he enabled "Turbo 3.0" in the BIOS.

The problem is that even if one core max is 200MHz more than others, the
current implementation couldn't enumerate that with the way the system
is configured.

The system by default configured for legacy mode (no HWP or speed shift
technology), in this mode only way we can enumerate via the mail box
interface as implemented in this driver. We were planing to only use
this driver for Broadwell, but we need to extend this because some
Skylake system has same issue as Braodwell systems.

On this system BIOS allows to change to HWP mode, where we expect that
we can enumerate favored core with ACPI-CPPC. But on this system the
core priority is 0xff for all cores in CPPC object. So this is not an
option.

Hence this change allows Skylake systems to be enumerate favored core
similar to Broadwell in legacy mode.

Reported-and-tested-by: Ev Kontsevoy <ev@kontsevoy.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
2017-10-27 20:54:01 +03:00

153 lines
4 KiB
C

/*
* Intel Turbo Boost Max Technology 3.0 legacy (non HWP) enumeration driver
* Copyright (c) 2017, Intel Corporation.
* All rights reserved.
*
* Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope 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.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/topology.h>
#include <linux/workqueue.h>
#include <linux/cpuhotplug.h>
#include <linux/cpufeature.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#define MSR_OC_MAILBOX 0x150
#define MSR_OC_MAILBOX_CMD_OFFSET 32
#define MSR_OC_MAILBOX_RSP_OFFSET 32
#define MSR_OC_MAILBOX_BUSY_BIT 63
#define OC_MAILBOX_FC_CONTROL_CMD 0x1C
/*
* Typical latency to get mail box response is ~3us, It takes +3 us to
* process reading mailbox after issuing mailbox write on a Broadwell 3.4 GHz
* system. So for most of the time, the first mailbox read should have the
* response, but to avoid some boundary cases retry twice.
*/
#define OC_MAILBOX_RETRY_COUNT 2
static int get_oc_core_priority(unsigned int cpu)
{
u64 value, cmd = OC_MAILBOX_FC_CONTROL_CMD;
int ret, i;
/* Issue favored core read command */
value = cmd << MSR_OC_MAILBOX_CMD_OFFSET;
/* Set the busy bit to indicate OS is trying to issue command */
value |= BIT_ULL(MSR_OC_MAILBOX_BUSY_BIT);
ret = wrmsrl_safe(MSR_OC_MAILBOX, value);
if (ret) {
pr_debug("cpu %d OC mailbox write failed\n", cpu);
return ret;
}
for (i = 0; i < OC_MAILBOX_RETRY_COUNT; ++i) {
ret = rdmsrl_safe(MSR_OC_MAILBOX, &value);
if (ret) {
pr_debug("cpu %d OC mailbox read failed\n", cpu);
break;
}
if (value & BIT_ULL(MSR_OC_MAILBOX_BUSY_BIT)) {
pr_debug("cpu %d OC mailbox still processing\n", cpu);
ret = -EBUSY;
continue;
}
if ((value >> MSR_OC_MAILBOX_RSP_OFFSET) & 0xff) {
pr_debug("cpu %d OC mailbox cmd failed\n", cpu);
ret = -ENXIO;
break;
}
ret = value & 0xff;
pr_debug("cpu %d max_ratio %d\n", cpu, ret);
break;
}
return ret;
}
/*
* The work item is needed to avoid CPU hotplug locking issues. The function
* itmt_legacy_set_priority() is called from CPU online callback, so can't
* call sched_set_itmt_support() from there as this function will aquire
* hotplug locks in its path.
*/
static void itmt_legacy_work_fn(struct work_struct *work)
{
sched_set_itmt_support();
}
static DECLARE_WORK(sched_itmt_work, itmt_legacy_work_fn);
static int itmt_legacy_cpu_online(unsigned int cpu)
{
static u32 max_highest_perf = 0, min_highest_perf = U32_MAX;
int priority;
priority = get_oc_core_priority(cpu);
if (priority < 0)
return 0;
sched_set_itmt_core_prio(priority, cpu);
/* Enable ITMT feature when a core with different priority is found */
if (max_highest_perf <= min_highest_perf) {
if (priority > max_highest_perf)
max_highest_perf = priority;
if (priority < min_highest_perf)
min_highest_perf = priority;
if (max_highest_perf > min_highest_perf)
schedule_work(&sched_itmt_work);
}
return 0;
}
#define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
static const struct x86_cpu_id itmt_legacy_cpu_ids[] = {
ICPU(INTEL_FAM6_BROADWELL_X),
ICPU(INTEL_FAM6_SKYLAKE_X),
{}
};
static int __init itmt_legacy_init(void)
{
const struct x86_cpu_id *id;
int ret;
id = x86_match_cpu(itmt_legacy_cpu_ids);
if (!id)
return -ENODEV;
if (boot_cpu_has(X86_FEATURE_HWP))
return -ENODEV;
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
"platform/x86/turbo_max_3:online",
itmt_legacy_cpu_online, NULL);
if (ret < 0)
return ret;
return 0;
}
late_initcall(itmt_legacy_init)