linux-sg2042/arch/x86/kernel/reboot.c

717 lines
18 KiB
C
Raw Normal View History

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/reboot.h>
#include <linux/init.h>
#include <linux/pm.h>
#include <linux/efi.h>
#include <linux/dmi.h>
#include <linux/sched.h>
#include <linux/tboot.h>
#include <linux/delay.h>
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/pgtable.h>
#include <asm/proto.h>
#include <asm/reboot_fixups.h>
#include <asm/reboot.h>
#include <asm/pci_x86.h>
#include <asm/virtext.h>
#include <asm/cpu.h>
#include <asm/nmi.h>
#include <asm/smp.h>
#include <linux/ctype.h>
#include <linux/mc146818rtc.h>
#include <asm/realmode.h>
#include <asm/x86_init.h>
/*
* Power off function, if any
*/
void (*pm_power_off)(void);
EXPORT_SYMBOL(pm_power_off);
static const struct desc_ptr no_idt = {};
/*
* This is set if we need to go through the 'emergency' path.
* When machine_emergency_restart() is called, we may be on
* an inconsistent state and won't be able to do a clean cleanup
*/
static int reboot_emergency;
/* This is set by the PCI code if either type 1 or type 2 PCI is detected */
bool port_cf9_safe = false;
/*
* Reboot options and system auto-detection code provided by
* Dell Inc. so their systems "just work". :-)
*/
/*
* Some machines require the "reboot=b" or "reboot=k" commandline options,
* this quirk makes that automatic.
*/
static int __init set_bios_reboot(const struct dmi_system_id *d)
{
if (reboot_type != BOOT_BIOS) {
reboot_type = BOOT_BIOS;
pr_info("%s series board detected. Selecting %s-method for reboots.\n",
"BIOS", d->ident);
}
return 0;
}
void __noreturn machine_real_restart(unsigned int type)
{
local_irq_disable();
/*
* Write zero to CMOS register number 0x0f, which the BIOS POST
* routine will recognize as telling it to do a proper reboot. (Well
* that's what this book in front of me says -- it may only apply to
* the Phoenix BIOS though, it's not clear). At the same time,
* disable NMIs by setting the top bit in the CMOS address register,
* as we're about to do peculiar things to the CPU. I'm not sure if
* `outb_p' is needed instead of just `outb'. Use it to be on the
* safe side. (Yes, CMOS_WRITE does outb_p's. - Paul G.)
*/
spin_lock(&rtc_lock);
CMOS_WRITE(0x00, 0x8f);
spin_unlock(&rtc_lock);
/*
* Switch back to the initial page table.
*/
#ifdef CONFIG_X86_32
load_cr3(initial_page_table);
#else
write_cr3(real_mode_header->trampoline_pgd);
#endif
/* Jump to the identity-mapped low memory code */
#ifdef CONFIG_X86_32
asm volatile("jmpl *%0" : :
"rm" (real_mode_header->machine_real_restart_asm),
"a" (type));
#else
asm volatile("ljmpl *%0" : :
"m" (real_mode_header->machine_real_restart_asm),
"D" (type));
#endif
unreachable();
}
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(machine_real_restart);
#endif
/*
* Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot
*/
static int __init set_pci_reboot(const struct dmi_system_id *d)
{
if (reboot_type != BOOT_CF9) {
reboot_type = BOOT_CF9;
pr_info("%s series board detected. Selecting %s-method for reboots.\n",
"PCI", d->ident);
}
return 0;
}
static int __init set_kbd_reboot(const struct dmi_system_id *d)
{
if (reboot_type != BOOT_KBD) {
reboot_type = BOOT_KBD;
pr_info("%s series board detected. Selecting %s-method for reboot.\n",
"KBD", d->ident);
}
return 0;
}
/*
* This is a single dmi_table handling all reboot quirks.
*/
static struct dmi_system_id __initdata reboot_dmi_table[] = {
{ /* Handle problems with rebooting on Dell E520's */
.callback = set_bios_reboot,
.ident = "Dell E520",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Dell DM061"),
},
},
{ /* Handle problems with rebooting on Dell 1300's */
.callback = set_bios_reboot,
.ident = "Dell PowerEdge 1300",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1300/"),
},
},
{ /* Handle problems with rebooting on Dell 300's */
.callback = set_bios_reboot,
.ident = "Dell PowerEdge 300",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"),
},
},
{ /* Handle problems with rebooting on Dell Optiplex 745's SFF */
.callback = set_bios_reboot,
.ident = "Dell OptiPlex 745",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
},
},
{ /* Handle problems with rebooting on Dell Optiplex 745's DFF */
.callback = set_bios_reboot,
.ident = "Dell OptiPlex 745",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
DMI_MATCH(DMI_BOARD_NAME, "0MM599"),
},
},
{ /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */
.callback = set_bios_reboot,
.ident = "Dell OptiPlex 745",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
},
},
{ /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
.callback = set_bios_reboot,
.ident = "Dell OptiPlex 330",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
},
},
{ /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */
.callback = set_bios_reboot,
.ident = "Dell OptiPlex 360",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"),
DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
},
},
{ /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G */
.callback = set_bios_reboot,
.ident = "Dell OptiPlex 760",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"),
DMI_MATCH(DMI_BOARD_NAME, "0G919G"),
},
},
{ /* Handle problems with rebooting on Dell 2400's */
.callback = set_bios_reboot,
.ident = "Dell PowerEdge 2400",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"),
},
},
{ /* Handle problems with rebooting on Dell T5400's */
.callback = set_bios_reboot,
.ident = "Dell Precision T5400",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"),
},
},
{ /* Handle problems with rebooting on Dell T7400's */
.callback = set_bios_reboot,
.ident = "Dell Precision T7400",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"),
},
},
{ /* Handle problems with rebooting on HP laptops */
.callback = set_bios_reboot,
.ident = "HP Compaq Laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"),
},
},
{ /* Handle problems with rebooting on Dell XPS710 */
.callback = set_bios_reboot,
.ident = "Dell XPS710",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
},
},
{ /* Handle problems with rebooting on Dell DXP061 */
.callback = set_bios_reboot,
.ident = "Dell DXP061",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
},
},
{ /* Handle problems with rebooting on Sony VGN-Z540N */
.callback = set_bios_reboot,
.ident = "Sony VGN-Z540N",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
},
},
{ /* Handle problems with rebooting on ASUS P4S800 */
.callback = set_bios_reboot,
.ident = "ASUS P4S800",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
{ /* Handle reboot issue on Acer Aspire one */
.callback = set_kbd_reboot,
.ident = "Acer Aspire One A110",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
},
},
{ /* Handle problems with rebooting on Apple MacBook5 */
.callback = set_pci_reboot,
.ident = "Apple MacBook5",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"),
},
},
{ /* Handle problems with rebooting on Apple MacBookPro5 */
.callback = set_pci_reboot,
.ident = "Apple MacBookPro5",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"),
},
},
{ /* Handle problems with rebooting on Apple Macmini3,1 */
.callback = set_pci_reboot,
.ident = "Apple Macmini3,1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"),
},
},
{ /* Handle problems with rebooting on the iMac9,1. */
.callback = set_pci_reboot,
.ident = "Apple iMac9,1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
},
},
{ /* Handle problems with rebooting on the Latitude E6320. */
.callback = set_pci_reboot,
.ident = "Dell Latitude E6320",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
},
},
{ /* Handle problems with rebooting on the Latitude E5420. */
.callback = set_pci_reboot,
.ident = "Dell Latitude E5420",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"),
},
},
{ /* Handle problems with rebooting on the Latitude E6420. */
.callback = set_pci_reboot,
.ident = "Dell Latitude E6420",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
},
},
{ /* Handle problems with rebooting on the OptiPlex 990. */
.callback = set_pci_reboot,
.ident = "Dell OptiPlex 990",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
},
},
{ /* Handle problems with rebooting on the Precision M6600. */
.callback = set_pci_reboot,
.ident = "Dell OptiPlex 990",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
},
},
{ }
};
static int __init reboot_init(void)
{
/*
* Only do the DMI check if reboot_type hasn't been overridden
* on the command line
*/
if (reboot_default)
dmi_check_system(reboot_dmi_table);
return 0;
}
core_initcall(reboot_init);
static inline void kb_wait(void)
{
int i;
for (i = 0; i < 0x10000; i++) {
if ((inb(0x64) & 0x02) == 0)
break;
udelay(2);
}
}
static void vmxoff_nmi(int cpu, struct pt_regs *regs)
{
cpu_emergency_vmxoff();
}
/* Use NMIs as IPIs to tell all CPUs to disable virtualization */
static void emergency_vmx_disable_all(void)
{
/* Just make sure we won't change CPUs while doing this */
local_irq_disable();
/*
* We need to disable VMX on all CPUs before rebooting, otherwise
* we risk hanging up the machine, because the CPU ignore INIT
* signals when VMX is enabled.
*
* We can't take any locks and we may be on an inconsistent
* state, so we use NMIs as IPIs to tell the other CPUs to disable
* VMX and halt.
*
* For safety, we will avoid running the nmi_shootdown_cpus()
* stuff unnecessarily, but we don't have a way to check
* if other CPUs have VMX enabled. So we will call it only if the
* CPU we are running on has VMX enabled.
*
* We will miss cases where VMX is not enabled on all CPUs. This
* shouldn't do much harm because KVM always enable VMX on all
* CPUs anyway. But we can miss it on the small window where KVM
* is still enabling VMX.
*/
if (cpu_has_vmx() && cpu_vmx_enabled()) {
/* Disable VMX on this CPU. */
cpu_vmxoff();
/* Halt and disable VMX on the other CPUs */
nmi_shootdown_cpus(vmxoff_nmi);
}
}
void __attribute__((weak)) mach_reboot_fixups(void)
{
}
x86: Reorder reboot method preferences We have a never ending stream of 'reboot quirks' for new boxes that will not reboot properly under Linux (they will hang on reboot). The reason is widespread 'Windows compatible' assumption of modern x86 hardware, which expects the following reboot sequence: - hitting the ACPI reboot vector (if available) - trying the keyboard controller - hitting the ACPI reboot vector again - then giving the keyboard controller one last go This sequence expectation gets more and more embedded in modern hardware, which often lacks a keyboard controller and may even lock up if the legacy io ports are hit - and which hardware is often not tested with Linux during development. The end result is that reboot works under Windows-alike OSs but not under Linux. Rework our reboot process to meet this hardware externality a little better and match this assumption of newer x86 hardware. In addition to the ACPI,kbd,ACPI,kbd sequence we'll still fall through to attempting a legacy triple fault if nothing else works - and keep trying that and the kbd reset. Signed-off-by: Matthew Garrett <mjg@redhat.com> [ this commit will also save special casing Oaktrail boards ] Acked-by: Alan Cox <alan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Leann Ogasawara <leann.ogasawara@canonical.com> Cc: Dave Jones <davej@redhat.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <1301939705-2404-1-git-send-email-mjg@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-05 01:55:05 +08:00
/*
* Windows compatible x86 hardware expects the following on reboot:
*
* 1) If the FADT has the ACPI reboot register flag set, try it
* 2) If still alive, write to the keyboard controller
* 3) If still alive, write to the ACPI reboot register again
* 4) If still alive, write to the keyboard controller again
*
* If the machine is still alive at this stage, it gives up. We default to
* following the same pattern, except that if we're still alive after (4) we'll
* try to force a triple fault and then cycle between hitting the keyboard
* controller and doing that
*/
static void native_machine_emergency_restart(void)
{
int i;
x86: Reorder reboot method preferences We have a never ending stream of 'reboot quirks' for new boxes that will not reboot properly under Linux (they will hang on reboot). The reason is widespread 'Windows compatible' assumption of modern x86 hardware, which expects the following reboot sequence: - hitting the ACPI reboot vector (if available) - trying the keyboard controller - hitting the ACPI reboot vector again - then giving the keyboard controller one last go This sequence expectation gets more and more embedded in modern hardware, which often lacks a keyboard controller and may even lock up if the legacy io ports are hit - and which hardware is often not tested with Linux during development. The end result is that reboot works under Windows-alike OSs but not under Linux. Rework our reboot process to meet this hardware externality a little better and match this assumption of newer x86 hardware. In addition to the ACPI,kbd,ACPI,kbd sequence we'll still fall through to attempting a legacy triple fault if nothing else works - and keep trying that and the kbd reset. Signed-off-by: Matthew Garrett <mjg@redhat.com> [ this commit will also save special casing Oaktrail boards ] Acked-by: Alan Cox <alan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Leann Ogasawara <leann.ogasawara@canonical.com> Cc: Dave Jones <davej@redhat.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <1301939705-2404-1-git-send-email-mjg@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-05 01:55:05 +08:00
int attempt = 0;
int orig_reboot_type = reboot_type;
unsigned short mode;
if (reboot_emergency)
emergency_vmx_disable_all();
tboot_shutdown(TB_SHUTDOWN_REBOOT);
/* Tell the BIOS if we want cold or warm reboot */
mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0;
*((unsigned short *)__va(0x472)) = mode;
for (;;) {
/* Could also try the reset bit in the Hammer NB */
switch (reboot_type) {
case BOOT_KBD:
mach_reboot_fixups(); /* For board specific fixups */
for (i = 0; i < 10; i++) {
kb_wait();
udelay(50);
outb(0xfe, 0x64); /* Pulse reset low */
udelay(50);
}
x86: Reorder reboot method preferences We have a never ending stream of 'reboot quirks' for new boxes that will not reboot properly under Linux (they will hang on reboot). The reason is widespread 'Windows compatible' assumption of modern x86 hardware, which expects the following reboot sequence: - hitting the ACPI reboot vector (if available) - trying the keyboard controller - hitting the ACPI reboot vector again - then giving the keyboard controller one last go This sequence expectation gets more and more embedded in modern hardware, which often lacks a keyboard controller and may even lock up if the legacy io ports are hit - and which hardware is often not tested with Linux during development. The end result is that reboot works under Windows-alike OSs but not under Linux. Rework our reboot process to meet this hardware externality a little better and match this assumption of newer x86 hardware. In addition to the ACPI,kbd,ACPI,kbd sequence we'll still fall through to attempting a legacy triple fault if nothing else works - and keep trying that and the kbd reset. Signed-off-by: Matthew Garrett <mjg@redhat.com> [ this commit will also save special casing Oaktrail boards ] Acked-by: Alan Cox <alan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Leann Ogasawara <leann.ogasawara@canonical.com> Cc: Dave Jones <davej@redhat.com> Cc: Len Brown <len.brown@intel.com> LKML-Reference: <1301939705-2404-1-git-send-email-mjg@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-05 01:55:05 +08:00
if (attempt == 0 && orig_reboot_type == BOOT_ACPI) {
attempt = 1;
reboot_type = BOOT_ACPI;
} else {
reboot_type = BOOT_TRIPLE;
}
break;
case BOOT_TRIPLE:
load_idt(&no_idt);
__asm__ __volatile__("int3");
reboot_type = BOOT_KBD;
break;
case BOOT_BIOS:
machine_real_restart(MRR_BIOS);
reboot_type = BOOT_KBD;
break;
case BOOT_ACPI:
acpi_reboot();
reboot_type = BOOT_KBD;
break;
case BOOT_EFI:
efi: Make 'efi_enabled' a function to query EFI facilities Originally 'efi_enabled' indicated whether a kernel was booted from EFI firmware. Over time its semantics have changed, and it now indicates whether or not we are booted on an EFI machine with bit-native firmware, e.g. 64-bit kernel with 64-bit firmware. The immediate motivation for this patch is the bug report at, https://bugs.launchpad.net/ubuntu-cdimage/+bug/1040557 which details how running a platform driver on an EFI machine that is designed to run under BIOS can cause the machine to become bricked. Also, the following report, https://bugzilla.kernel.org/show_bug.cgi?id=47121 details how running said driver can also cause Machine Check Exceptions. Drivers need a new means of detecting whether they're running on an EFI machine, as sadly the expression, if (!efi_enabled) hasn't been a sufficient condition for quite some time. Users actually want to query 'efi_enabled' for different reasons - what they really want access to is the list of available EFI facilities. For instance, the x86 reboot code needs to know whether it can invoke the ResetSystem() function provided by the EFI runtime services, while the ACPI OSL code wants to know whether the EFI config tables were mapped successfully. There are also checks in some of the platform driver code to simply see if they're running on an EFI machine (which would make it a bad idea to do BIOS-y things). This patch is a prereq for the samsung-laptop fix patch. Cc: David Airlie <airlied@linux.ie> Cc: Corentin Chary <corentincj@iksaif.net> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Olof Johansson <olof@lixom.net> Cc: Peter Jones <pjones@redhat.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: Steve Langasek <steve.langasek@canonical.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Konrad Rzeszutek Wilk <konrad@kernel.org> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: <stable@vger.kernel.org> Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-11-14 17:42:35 +08:00
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi.reset_system(reboot_mode == REBOOT_WARM ?
EFI_RESET_WARM :
EFI_RESET_COLD,
EFI_SUCCESS, 0, NULL);
reboot_type = BOOT_KBD;
break;
case BOOT_CF9:
port_cf9_safe = true;
/* Fall through */
case BOOT_CF9_COND:
if (port_cf9_safe) {
u8 cf9 = inb(0xcf9) & ~6;
outb(cf9|2, 0xcf9); /* Request hard reset */
udelay(50);
outb(cf9|6, 0xcf9); /* Actually do the reset */
udelay(50);
}
reboot_type = BOOT_KBD;
break;
}
}
}
void native_machine_shutdown(void)
{
/* Stop the cpus and apics */
#ifdef CONFIG_SMP
/*
* Stop all of the others. Also disable the local irq to
* not receive the per-cpu timer interrupt which may trigger
* scheduler's load balance.
*/
x86/reboot: Fix a warning message triggered by stop_other_cpus() When rebooting our 24 CPU Westmere servers with 3.4-rc6, we always see this warning msg: Restarting system. machine restart ------------[ cut here ]------------ WARNING: at arch/x86/kernel/smp.c:125 native_smp_send_reschedule+0x74/0xa7() Hardware name: X8DTN Modules linked in: igb [last unloaded: scsi_wait_scan] Pid: 1, comm: systemd-shutdow Not tainted 3.4.0-rc6+ #22 Call Trace: <IRQ> [<ffffffff8102a41f>] warn_slowpath_common+0x7e/0x96 [<ffffffff8102a44c>] warn_slowpath_null+0x15/0x17 [<ffffffff81018cf7>] native_smp_send_reschedule+0x74/0xa7 [<ffffffff810561c1>] trigger_load_balance+0x279/0x2a6 [<ffffffff81050112>] scheduler_tick+0xe0/0xe9 [<ffffffff81036768>] update_process_times+0x60/0x70 [<ffffffff81062f2f>] tick_sched_timer+0x68/0x92 [<ffffffff81046e33>] __run_hrtimer+0xb3/0x13c [<ffffffff81062ec7>] ? tick_nohz_handler+0xd0/0xd0 [<ffffffff810474f2>] hrtimer_interrupt+0xdb/0x198 [<ffffffff81019a35>] smp_apic_timer_interrupt+0x81/0x94 [<ffffffff81655187>] apic_timer_interrupt+0x67/0x70 <EOI> [<ffffffff8101a3c4>] ? default_send_IPI_mask_allbutself_phys+0xb4/0xc4 [<ffffffff8101c680>] physflat_send_IPI_allbutself+0x12/0x14 [<ffffffff81018db4>] native_nmi_stop_other_cpus+0x8a/0xd6 [<ffffffff810188ba>] native_machine_shutdown+0x50/0x67 [<ffffffff81018926>] machine_shutdown+0xa/0xc [<ffffffff8101897e>] native_machine_restart+0x20/0x32 [<ffffffff810189b0>] machine_restart+0xa/0xc [<ffffffff8103b196>] kernel_restart+0x47/0x4c [<ffffffff8103b2e6>] sys_reboot+0x13e/0x17c [<ffffffff8164e436>] ? _raw_spin_unlock_bh+0x10/0x12 [<ffffffff810fcac9>] ? bdi_queue_work+0xcf/0xd8 [<ffffffff810fe82f>] ? __bdi_start_writeback+0xae/0xb7 [<ffffffff810e0d64>] ? iterate_supers+0xa3/0xb7 [<ffffffff816547a2>] system_call_fastpath+0x16/0x1b ---[ end trace 320af5cb1cb60c5b ]--- The root cause seems to be the default_send_IPI_mask_allbutself_phys() takes quite some time (I measured it could be several ms) to complete sending NMIs to all the other 23 CPUs, and for HZ=250/1000 system, the time is long enough for a timer interrupt to happen, which will in turn trigger to kick load balance to a stopped CPU and cause this warning in native_smp_send_reschedule(). So disabling the local irq before stop_other_cpu() can fix this problem (tested 25 times reboot ok), and it is fine as there should be nobody caring the timer interrupt in such reboot stage. The latest 3.4 kernel slightly changes this behavior by sending REBOOT_VECTOR first and only send NMI_VECTOR if the REBOOT_VCTOR fails, and this patch is still needed to prevent the problem. Signed-off-by: Feng Tang <feng.tang@intel.com> Acked-by: Don Zickus <dzickus@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120530231541.4c13433a@feng-i7 Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-05-30 23:15:41 +08:00
local_irq_disable();
stop_other_cpus();
#endif
lapic_shutdown();
#ifdef CONFIG_X86_IO_APIC
disable_IO_APIC();
#endif
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
#ifdef CONFIG_X86_64
x86_platform.iommu_shutdown();
#endif
}
static void __machine_emergency_restart(int emergency)
{
reboot_emergency = emergency;
machine_ops.emergency_restart();
}
static void native_machine_restart(char *__unused)
{
pr_notice("machine restart\n");
if (!reboot_force)
machine_shutdown();
__machine_emergency_restart(0);
}
static void native_machine_halt(void)
{
/* Stop other cpus and apics */
machine_shutdown();
tboot_shutdown(TB_SHUTDOWN_HALT);
stop_this_cpu(NULL);
}
static void native_machine_power_off(void)
{
[PATCH] i386/x86-64: Don't IPI to offline cpus on shutdown So why are we calling smp_send_stop from machine_halt? We don't. Looking more closely at the bug report the problem here is that halt -p is called which triggers not a halt but an attempt to power off. machine_power_off calls machine_shutdown which calls smp_send_stop. If pm_power_off is set we should never make it out machine_power_off to the call of do_exit. So pm_power_off must not be set in this case. When pm_power_off is not set we expect machine_power_off to devolve into machine_halt. So how do we fix this? Playing too much with smp_send_stop is dangerous because it must also be safe to be called from panic. It looks like the obviously correct fix is to only call machine_shutdown when pm_power_off is defined. Doing that will make Andi's assumption about not scheduling true and generally simplify what must be supported. This turns machine_power_off into a noop like machine_halt when pm_power_off is not defined. If the expected behavior is that sys_reboot(LINUX_REBOOT_CMD_POWER_OFF) becomes sys_reboot(LINUX_REBOOT_CMD_HALT) if pm_power_off is NULL this is not quite a comprehensive fix as we pass a different parameter to the reboot notifier and we set system_state to a different value before calling device_shutdown(). Unfortunately any fix more comprehensive I can think of is not obviously correct. The core problem is that there is no architecture independent way to detect if machine_power will become a noop, without calling it. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-12 05:43:12 +08:00
if (pm_power_off) {
if (!reboot_force)
machine_shutdown();
pm_power_off();
[PATCH] i386/x86-64: Don't IPI to offline cpus on shutdown So why are we calling smp_send_stop from machine_halt? We don't. Looking more closely at the bug report the problem here is that halt -p is called which triggers not a halt but an attempt to power off. machine_power_off calls machine_shutdown which calls smp_send_stop. If pm_power_off is set we should never make it out machine_power_off to the call of do_exit. So pm_power_off must not be set in this case. When pm_power_off is not set we expect machine_power_off to devolve into machine_halt. So how do we fix this? Playing too much with smp_send_stop is dangerous because it must also be safe to be called from panic. It looks like the obviously correct fix is to only call machine_shutdown when pm_power_off is defined. Doing that will make Andi's assumption about not scheduling true and generally simplify what must be supported. This turns machine_power_off into a noop like machine_halt when pm_power_off is not defined. If the expected behavior is that sys_reboot(LINUX_REBOOT_CMD_POWER_OFF) becomes sys_reboot(LINUX_REBOOT_CMD_HALT) if pm_power_off is NULL this is not quite a comprehensive fix as we pass a different parameter to the reboot notifier and we set system_state to a different value before calling device_shutdown(). Unfortunately any fix more comprehensive I can think of is not obviously correct. The core problem is that there is no architecture independent way to detect if machine_power will become a noop, without calling it. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-12 05:43:12 +08:00
}
/* A fallback in case there is no PM info available */
tboot_shutdown(TB_SHUTDOWN_HALT);
}
struct machine_ops machine_ops = {
.power_off = native_machine_power_off,
.shutdown = native_machine_shutdown,
.emergency_restart = native_machine_emergency_restart,
.restart = native_machine_restart,
.halt = native_machine_halt,
#ifdef CONFIG_KEXEC
.crash_shutdown = native_machine_crash_shutdown,
#endif
};
void machine_power_off(void)
{
machine_ops.power_off();
}
void machine_shutdown(void)
{
machine_ops.shutdown();
}
void machine_emergency_restart(void)
{
__machine_emergency_restart(1);
}
void machine_restart(char *cmd)
{
machine_ops.restart(cmd);
}
void machine_halt(void)
{
machine_ops.halt();
}
#ifdef CONFIG_KEXEC
void machine_crash_shutdown(struct pt_regs *regs)
{
machine_ops.crash_shutdown(regs);
}
#endif
#if defined(CONFIG_SMP)
/* This keeps a track of which one is crashing cpu. */
static int crashing_cpu;
static nmi_shootdown_cb shootdown_callback;
static atomic_t waiting_for_crash_ipi;
static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
{
int cpu;
cpu = raw_smp_processor_id();
/*
* Don't do anything if this handler is invoked on crashing cpu.
* Otherwise, system will completely hang. Crashing cpu can get
* an NMI if system was initially booted with nmi_watchdog parameter.
*/
if (cpu == crashing_cpu)
return NMI_HANDLED;
local_irq_disable();
shootdown_callback(cpu, regs);
atomic_dec(&waiting_for_crash_ipi);
/* Assume hlt works */
halt();
for (;;)
cpu_relax();
return NMI_HANDLED;
}
static void smp_send_nmi_allbutself(void)
{
apic->send_IPI_allbutself(NMI_VECTOR);
}
/*
* Halt all other CPUs, calling the specified function on each of them
*
* This function can be used to halt all other CPUs on crash
* or emergency reboot time. The function passed as parameter
* will be called inside a NMI handler on all CPUs.
*/
void nmi_shootdown_cpus(nmi_shootdown_cb callback)
{
unsigned long msecs;
local_irq_disable();
/* Make a note of crashing cpu. Will be used in NMI callback. */
crashing_cpu = safe_smp_processor_id();
shootdown_callback = callback;
atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
/* Would it be better to replace the trap vector here? */
if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
NMI_FLAG_FIRST, "crash"))
return; /* Return what? */
/*
* Ensure the new callback function is set before sending
* out the NMI
*/
wmb();
smp_send_nmi_allbutself();
msecs = 1000; /* Wait at most a second for the other cpus to stop */
while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
mdelay(1);
msecs--;
}
/* Leave the nmi callback set */
}
#else /* !CONFIG_SMP */
void nmi_shootdown_cpus(nmi_shootdown_cb callback)
{
/* No other CPUs to shoot down */
}
#endif