In parallel startup mode the APs are kicked alive by the control CPU quickly after each other and run through the early startup code in parallel. The real-mode startup code is already serialized with a bit-spinlock to protect the real-mode stack. In parallel startup mode the smpboot_control variable obviously cannot contain the Linux CPU number so the APs have to determine their Linux CPU number on their own. This is required to find the CPUs per CPU offset in order to find the idle task stack and other per CPU data. To achieve this, export the cpuid_to_apicid[] array so that each AP can find its own CPU number by searching therein based on its APIC ID. Introduce a flag in the top bits of smpboot_control which indicates that the AP should find its CPU number by reading the APIC ID from the APIC. This is required because CPUID based APIC ID retrieval can only provide the initial APIC ID, which might have been overruled by the firmware. Some AMD APUs come up with APIC ID = initial APIC ID + 0x10, so the APIC ID to CPU number lookup would fail miserably if based on CPUID. Also virtualization can make its own APIC ID assignements. The only requirement is that the APIC IDs are consistent with the APCI/MADT table. For the boot CPU or in case parallel bringup is disabled the control bits are empty and the CPU number is directly available in bit 0-23 of smpboot_control. [ tglx: Initial proof of concept patch with bitlock and APIC ID lookup ] [ dwmw2: Rework and testing, commit message, CPUID 0x1 and CPU0 support ] [ seanc: Fix stray override of initial_gs in common_cpu_up() ] [ Oleksandr Natalenko: reported suspend/resume issue fixed in x86_acpi_suspend_lowlevel ] [ tglx: Make it read the APIC ID from the APIC instead of using CPUID, split the bitlock part out ] Co-developed-by: Thomas Gleixner <tglx@linutronix.de> Co-developed-by: Brian Gerst <brgerst@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Brian Gerst <brgerst@gmail.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Michael Kelley <mikelley@microsoft.com> Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name> Tested-by: Helge Deller <deller@gmx.de> # parisc Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com> # Steam Deck Link: https://lore.kernel.org/r/20230512205257.411554373@linutronix.de
202 lines
5.9 KiB
C
202 lines
5.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* sleep.c - x86-specific ACPI sleep support.
|
|
*
|
|
* Copyright (C) 2001-2003 Patrick Mochel
|
|
* Copyright (C) 2001-2003 Pavel Machek <pavel@ucw.cz>
|
|
*/
|
|
|
|
#include <linux/acpi.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/dmi.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/pgtable.h>
|
|
#include <asm/segment.h>
|
|
#include <asm/desc.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/realmode.h>
|
|
#include <asm/hypervisor.h>
|
|
#include <asm/smp.h>
|
|
|
|
#include <linux/ftrace.h>
|
|
#include "../../realmode/rm/wakeup.h"
|
|
#include "sleep.h"
|
|
|
|
unsigned long acpi_realmode_flags;
|
|
|
|
#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
|
|
static char temp_stack[4096];
|
|
#endif
|
|
|
|
/**
|
|
* acpi_get_wakeup_address - provide physical address for S3 wakeup
|
|
*
|
|
* Returns the physical address where the kernel should be resumed after the
|
|
* system awakes from S3, e.g. for programming into the firmware waking vector.
|
|
*/
|
|
unsigned long acpi_get_wakeup_address(void)
|
|
{
|
|
return ((unsigned long)(real_mode_header->wakeup_start));
|
|
}
|
|
|
|
/**
|
|
* x86_acpi_enter_sleep_state - enter sleep state
|
|
* @state: Sleep state to enter.
|
|
*
|
|
* Wrapper around acpi_enter_sleep_state() to be called by assembly.
|
|
*/
|
|
asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state)
|
|
{
|
|
return acpi_enter_sleep_state(state);
|
|
}
|
|
|
|
/**
|
|
* x86_acpi_suspend_lowlevel - save kernel state
|
|
*
|
|
* Create an identity mapped page table and copy the wakeup routine to
|
|
* low memory.
|
|
*/
|
|
int x86_acpi_suspend_lowlevel(void)
|
|
{
|
|
struct wakeup_header *header =
|
|
(struct wakeup_header *) __va(real_mode_header->wakeup_header);
|
|
|
|
if (header->signature != WAKEUP_HEADER_SIGNATURE) {
|
|
printk(KERN_ERR "wakeup header does not match\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
header->video_mode = saved_video_mode;
|
|
|
|
header->pmode_behavior = 0;
|
|
|
|
#ifndef CONFIG_64BIT
|
|
native_store_gdt((struct desc_ptr *)&header->pmode_gdt);
|
|
|
|
/*
|
|
* We have to check that we can write back the value, and not
|
|
* just read it. At least on 90 nm Pentium M (Family 6, Model
|
|
* 13), reading an invalid MSR is not guaranteed to trap, see
|
|
* Erratum X4 in "Intel Pentium M Processor on 90 nm Process
|
|
* with 2-MB L2 Cache and Intel® Processor A100 and A110 on 90
|
|
* nm process with 512-KB L2 Cache Specification Update".
|
|
*/
|
|
if (!rdmsr_safe(MSR_EFER,
|
|
&header->pmode_efer_low,
|
|
&header->pmode_efer_high) &&
|
|
!wrmsr_safe(MSR_EFER,
|
|
header->pmode_efer_low,
|
|
header->pmode_efer_high))
|
|
header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER);
|
|
#endif /* !CONFIG_64BIT */
|
|
|
|
header->pmode_cr0 = read_cr0();
|
|
if (__this_cpu_read(cpu_info.cpuid_level) >= 0) {
|
|
header->pmode_cr4 = __read_cr4();
|
|
header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4);
|
|
}
|
|
if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
|
|
&header->pmode_misc_en_low,
|
|
&header->pmode_misc_en_high) &&
|
|
!wrmsr_safe(MSR_IA32_MISC_ENABLE,
|
|
header->pmode_misc_en_low,
|
|
header->pmode_misc_en_high))
|
|
header->pmode_behavior |=
|
|
(1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE);
|
|
header->realmode_flags = acpi_realmode_flags;
|
|
header->real_magic = 0x12345678;
|
|
|
|
#ifndef CONFIG_64BIT
|
|
header->pmode_entry = (u32)&wakeup_pmode_return;
|
|
header->pmode_cr3 = (u32)__pa_symbol(initial_page_table);
|
|
saved_magic = 0x12345678;
|
|
#else /* CONFIG_64BIT */
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* As each CPU starts up, it will find its own stack pointer
|
|
* from its current_task->thread.sp. Typically that will be
|
|
* the idle thread for a newly-started AP, or even the boot
|
|
* CPU which will find it set to &init_task in the static
|
|
* per-cpu data.
|
|
*
|
|
* Make the resuming CPU use the temporary stack at startup
|
|
* by setting current->thread.sp to point to that. The true
|
|
* %rsp will be restored with the rest of the CPU context,
|
|
* by do_suspend_lowlevel(). And unwinders don't care about
|
|
* the abuse of ->thread.sp because it's a dead variable
|
|
* while the thread is running on the CPU anyway; the true
|
|
* value is in the actual %rsp register.
|
|
*/
|
|
current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
|
|
/*
|
|
* Ensure the CPU knows which one it is when it comes back, if
|
|
* it isn't in parallel mode and expected to work that out for
|
|
* itself.
|
|
*/
|
|
if (!(smpboot_control & STARTUP_PARALLEL_MASK))
|
|
smpboot_control = smp_processor_id();
|
|
#endif
|
|
initial_code = (unsigned long)wakeup_long64;
|
|
saved_magic = 0x123456789abcdef0L;
|
|
#endif /* CONFIG_64BIT */
|
|
|
|
/*
|
|
* Pause/unpause graph tracing around do_suspend_lowlevel as it has
|
|
* inconsistent call/return info after it jumps to the wakeup vector.
|
|
*/
|
|
pause_graph_tracing();
|
|
do_suspend_lowlevel();
|
|
unpause_graph_tracing();
|
|
return 0;
|
|
}
|
|
|
|
static int __init acpi_sleep_setup(char *str)
|
|
{
|
|
while ((str != NULL) && (*str != '\0')) {
|
|
if (strncmp(str, "s3_bios", 7) == 0)
|
|
acpi_realmode_flags |= 1;
|
|
if (strncmp(str, "s3_mode", 7) == 0)
|
|
acpi_realmode_flags |= 2;
|
|
if (strncmp(str, "s3_beep", 7) == 0)
|
|
acpi_realmode_flags |= 4;
|
|
#ifdef CONFIG_HIBERNATION
|
|
if (strncmp(str, "s4_hwsig", 8) == 0)
|
|
acpi_check_s4_hw_signature = 1;
|
|
if (strncmp(str, "s4_nohwsig", 10) == 0)
|
|
acpi_check_s4_hw_signature = 0;
|
|
#endif
|
|
if (strncmp(str, "nonvs", 5) == 0)
|
|
acpi_nvs_nosave();
|
|
if (strncmp(str, "nonvs_s3", 8) == 0)
|
|
acpi_nvs_nosave_s3();
|
|
if (strncmp(str, "old_ordering", 12) == 0)
|
|
acpi_old_suspend_ordering();
|
|
if (strncmp(str, "nobl", 4) == 0)
|
|
acpi_sleep_no_blacklist();
|
|
str = strchr(str, ',');
|
|
if (str != NULL)
|
|
str += strspn(str, ", \t");
|
|
}
|
|
return 1;
|
|
}
|
|
|
|
__setup("acpi_sleep=", acpi_sleep_setup);
|
|
|
|
#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HYPERVISOR_GUEST)
|
|
static int __init init_s4_sigcheck(void)
|
|
{
|
|
/*
|
|
* If running on a hypervisor, honour the ACPI specification
|
|
* by default and trigger a clean reboot when the hardware
|
|
* signature in FACS is changed after hibernation.
|
|
*/
|
|
if (acpi_check_s4_hw_signature == -1 &&
|
|
!hypervisor_is_type(X86_HYPER_NATIVE))
|
|
acpi_check_s4_hw_signature = 1;
|
|
|
|
return 0;
|
|
}
|
|
/* This must happen before acpi_init() which is a subsys initcall */
|
|
arch_initcall(init_s4_sigcheck);
|
|
#endif
|