diff options
Diffstat (limited to 'arch/x86/kernel/reboot.c')
| -rw-r--r-- | arch/x86/kernel/reboot.c | 830 |
1 files changed, 552 insertions, 278 deletions
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 484c4a80d38..52b1157c53e 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,25 +1,33 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> -#include <linux/init.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> -#ifdef CONFIG_X86_32 -# include <linux/dmi.h> -# include <linux/ctype.h> -# include <linux/mc146818rtc.h> -# include <asm/pgtable.h> -#else -# include <asm/iommu.h> -#endif +#include <linux/ctype.h> +#include <linux/mc146818rtc.h> +#include <asm/realmode.h> +#include <asm/x86_init.h> /* * Power off function, if any @@ -27,98 +35,181 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -static long no_idt[3]; -static int reboot_mode; -enum reboot_type reboot_type = BOOT_KBD; -int reboot_force; +static const struct desc_ptr no_idt = {}; -#if defined(CONFIG_X86_32) && defined(CONFIG_SMP) -static int reboot_cpu = -1; -#endif - -/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] - warm Don't set the cold reboot flag - cold Set the cold reboot flag - bios Reboot by jumping through the BIOS (only for X86_32) - smp Reboot by executing reset on BSP or other CPU (only for X86_32) - triple Force a triple fault (init) - kbd Use the keyboard controller. cold reset (default) - acpi Use the RESET_REG in the FADT - efi Use efi reset_system runtime service - force Avoid anything that could hang. +/* + * 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 __init reboot_setup(char *str) -{ - for (;;) { - switch (*str) { - case 'w': - reboot_mode = 0x1234; - break; - - case 'c': - reboot_mode = 0; - break; - -#ifdef CONFIG_X86_32 -#ifdef CONFIG_SMP - case 's': - if (isdigit(*(str+1))) { - reboot_cpu = (int) (*(str+1) - '0'); - if (isdigit(*(str+2))) - reboot_cpu = reboot_cpu*10 + (int)(*(str+2) - '0'); - } - /* we will leave sorting out the final value - when we are ready to reboot, since we might not - have set up boot_cpu_id or smp_num_cpu */ - break; -#endif /* CONFIG_SMP */ +static int reboot_emergency; - case 'b': -#endif - case 'a': - case 'k': - case 't': - case 'e': - reboot_type = *str; - break; +/* This is set by the PCI code if either type 1 or type 2 PCI is detected */ +bool port_cf9_safe = false; - case 'f': - reboot_force = 1; - break; - } - - str = strchr(str, ','); - if (str) - str++; - else - break; - } - return 1; -} - -__setup("reboot=", reboot_setup); - - -#ifdef CONFIG_X86_32 /* * Reboot options and system auto-detection code provided by * Dell Inc. so their systems "just work". :-) */ /* - * Some machines require the "reboot=b" commandline option, + * 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; - printk(KERN_INFO "%s series board detected. Selecting BIOS-method for reboots.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboots.\n", + d->ident, "BIOS"); + } + 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_FORCE) { + reboot_type = BOOT_CF9_FORCE; + pr_info("%s series board detected. Selecting %s-method for reboots.\n", + d->ident, "PCI"); + } + 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", + d->ident, "KBD"); } return 0; } +/* + * This is a single dmi_table handling all reboot quirks. + */ static struct dmi_system_id __initdata reboot_dmi_table[] = { + + /* Acer */ + { /* 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"), + }, + }, + + /* Apple */ + { /* 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"), + }, + }, + + /* ASUS */ + { /* 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"), + }, + }, + + /* Certec */ + { /* Handle problems with rebooting on Certec BPC600 */ + .callback = set_pci_reboot, + .ident = "Certec BPC600", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Certec"), + DMI_MATCH(DMI_PRODUCT_NAME, "BPC600"), + }, + }, + + /* Dell */ + { /* 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 Dell E520's */ .callback = set_bios_reboot, .ident = "Dell E520", @@ -127,32 +218,65 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell DM061"), }, }, - { /* Handle problems with rebooting on Dell 1300's */ + { /* Handle problems with rebooting on the Latitude E5410. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E5410", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"), + }, + }, + { /* 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 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 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 Dell Optiplex 330 with 0KP561 */ .callback = set_bios_reboot, - .ident = "Dell PowerEdge 1300", + .ident = "Dell OptiPlex 330", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1300/"), + 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 300's */ + { /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */ .callback = set_bios_reboot, - .ident = "Dell PowerEdge 300", + .ident = "Dell OptiPlex 360", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"), + 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 745's SFF*/ + { /* 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"), - DMI_MATCH(DMI_BOARD_NAME, "0WF810"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 745's DFF*/ + { /* Handle problems with rebooting on Dell Optiplex 745's DFF */ .callback = set_bios_reboot, .ident = "Dell OptiPlex 745", .matches = { @@ -161,7 +285,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0MM599"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */ + { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */ .callback = set_bios_reboot, .ident = "Dell OptiPlex 745", .matches = { @@ -170,6 +294,39 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0KW626"), }, }, + { /* 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 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 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 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 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", @@ -178,6 +335,48 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"), }, }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Handle problems with rebooting on the Precision M6600. */ + .callback = set_pci_reboot, + .ident = "Dell Precision M6600", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), + }, + }, + { /* 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 Dell XPS710 */ + .callback = set_bios_reboot, + .ident = "Dell XPS710", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), + }, + }, + + /* Hewlett-Packard */ { /* Handle problems with rebooting on HP laptops */ .callback = set_bios_reboot, .ident = "HP Compaq Laptop", @@ -186,275 +385,254 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"), }, }, + + /* Sony */ + { /* 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"), + }, + }, + { } }; static int __init reboot_init(void) { - dmi_check_system(reboot_dmi_table); + /* + * 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); -/* The following code and data reboots the machine by switching to real - mode and jumping to the BIOS reset entry point, as if the CPU has - really been reset. The previous version asked the keyboard - controller to pulse the CPU reset line, which is more thorough, but - doesn't work with at least one type of 486 motherboard. It is easy - to stop this code working; hence the copious comments. */ -static unsigned long long -real_mode_gdt_entries [3] = +static inline void kb_wait(void) { - 0x0000000000000000ULL, /* Null descriptor */ - 0x00009a000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */ - 0x000092000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */ -}; + int i; -static struct desc_ptr -real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries }, -real_mode_idt = { 0x3ff, 0 }; - -/* This is 16-bit protected mode code to disable paging and the cache, - switch to real mode and jump to the BIOS reset code. - - The instruction that switches to real mode by writing to CR0 must be - followed immediately by a far jump instruction, which set CS to a - valid value for real mode, and flushes the prefetch queue to avoid - running instructions that have already been decoded in protected - mode. - - Clears all the flags except ET, especially PG (paging), PE - (protected-mode enable) and TS (task switch for coprocessor state - save). Flushes the TLB after paging has been disabled. Sets CD and - NW, to disable the cache on a 486, and invalidates the cache. This - is more like the state of a 486 after reset. I don't know if - something else should be done for other chips. - - More could be done here to set up the registers as if a CPU reset had - occurred; hopefully real BIOSs don't assume much. */ -static unsigned char real_mode_switch [] = -{ - 0x66, 0x0f, 0x20, 0xc0, /* movl %cr0,%eax */ - 0x66, 0x83, 0xe0, 0x11, /* andl $0x00000011,%eax */ - 0x66, 0x0d, 0x00, 0x00, 0x00, 0x60, /* orl $0x60000000,%eax */ - 0x66, 0x0f, 0x22, 0xc0, /* movl %eax,%cr0 */ - 0x66, 0x0f, 0x22, 0xd8, /* movl %eax,%cr3 */ - 0x66, 0x0f, 0x20, 0xc3, /* movl %cr0,%ebx */ - 0x66, 0x81, 0xe3, 0x00, 0x00, 0x00, 0x60, /* andl $0x60000000,%ebx */ - 0x74, 0x02, /* jz f */ - 0x0f, 0x09, /* wbinvd */ - 0x24, 0x10, /* f: andb $0x10,al */ - 0x66, 0x0f, 0x22, 0xc0 /* movl %eax,%cr0 */ -}; -static unsigned char jump_to_bios [] = + for (i = 0; i < 0x10000; i++) { + if ((inb(0x64) & 0x02) == 0) + break; + udelay(2); + } +} + +static void vmxoff_nmi(int cpu, struct pt_regs *regs) { - 0xea, 0x00, 0x00, 0xff, 0xff /* ljmp $0xffff,$0x0000 */ -}; + cpu_emergency_vmxoff(); +} -/* - * Switch to real mode and then execute the code - * specified by the code and length parameters. - * We assume that length will aways be less that 100! - */ -void machine_real_restart(unsigned char *code, int length) +/* 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(); - /* 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); - - /* Remap the kernel at virtual address zero, as well as offset zero - from the kernel segment. This assumes the kernel segment starts at - virtual address PAGE_OFFSET. */ - memcpy(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS, - sizeof(swapper_pg_dir [0]) * KERNEL_PGD_PTRS); - /* - * Use `swapper_pg_dir' as our page directory. + * 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. */ - load_cr3(swapper_pg_dir); - - /* Write 0x1234 to absolute memory location 0x472. The BIOS reads - this on booting to tell it to "Bypass memory test (also warm - boot)". This seems like a fairly standard thing that gets set by - REBOOT.COM programs, and the previous reset routine did this - too. */ - *((unsigned short *)0x472) = reboot_mode; - - /* For the switch to real mode, copy some code to low memory. It has - to be in the first 64k because it is running in 16-bit mode, and it - has to have the same physical and virtual address, because it turns - off paging. Copy it near the end of the first page, out of the way - of BIOS variables. */ - memcpy((void *)(0x1000 - sizeof(real_mode_switch) - 100), - real_mode_switch, sizeof (real_mode_switch)); - memcpy((void *)(0x1000 - 100), code, length); - - /* Set up the IDT for real mode. */ - load_idt(&real_mode_idt); - - /* Set up a GDT from which we can load segment descriptors for real - mode. The GDT is not used in real mode; it is just needed here to - prepare the descriptors. */ - load_gdt(&real_mode_gdt); - - /* Load the data segment registers, and thus the descriptors ready for - real mode. The base address of each segment is 0x100, 16 times the - selector value being loaded here. This is so that the segment - registers don't have to be reloaded after switching to real mode: - the values are consistent for real mode operation already. */ - __asm__ __volatile__ ("movl $0x0010,%%eax\n" - "\tmovl %%eax,%%ds\n" - "\tmovl %%eax,%%es\n" - "\tmovl %%eax,%%fs\n" - "\tmovl %%eax,%%gs\n" - "\tmovl %%eax,%%ss" : : : "eax"); - - /* Jump to the 16-bit code that we copied earlier. It disables paging - and the cache, switches to real mode, and jumps to the BIOS reset - entry point. */ - __asm__ __volatile__ ("ljmp $0x0008,%0" - : - : "i" ((void *)(0x1000 - sizeof (real_mode_switch) - 100))); -} -#ifdef CONFIG_APM_MODULE -EXPORT_SYMBOL(machine_real_restart); -#endif - -#endif /* CONFIG_X86_32 */ + if (cpu_has_vmx() && cpu_vmx_enabled()) { + /* Disable VMX on this CPU. */ + cpu_vmxoff(); -static inline void kb_wait(void) -{ - int i; + /* Halt and disable VMX on the other CPUs */ + nmi_shootdown_cpus(vmxoff_nmi); - for (i = 0; i < 0x10000; i++) { - if ((inb(0x64) & 0x02) == 0) - break; - udelay(2); } } + void __attribute__((weak)) mach_reboot_fixups(void) { } +/* + * To the best of our knowledge 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 + * 5) If still alive, call the EFI runtime service to reboot + * 6) If no EFI runtime service, call the BIOS to do a reboot + * + * We default to following the same pattern. We also have + * two other reboot methods: 'triple fault' and 'PCI', which + * can be triggered via the reboot= kernel boot option or + * via quirks. + * + * This means that this function can never return, it can misbehave + * by not rebooting properly and hanging. + */ static void native_machine_emergency_restart(void) { int i; + 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 */ - *((unsigned short *)__va(0x472)) = reboot_mode; + 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_ACPI: + acpi_reboot(); + reboot_type = BOOT_KBD; + break; + case BOOT_KBD: - mach_reboot_fixups(); /* for board specific fixups */ + mach_reboot_fixups(); /* For board specific fixups */ for (i = 0; i < 10; i++) { kb_wait(); udelay(50); - outb(0xfe, 0x64); /* pulse reset low */ + outb(0xfe, 0x64); /* Pulse reset low */ udelay(50); } + if (attempt == 0 && orig_reboot_type == BOOT_ACPI) { + attempt = 1; + reboot_type = BOOT_ACPI; + } else { + reboot_type = BOOT_EFI; + } + break; - case BOOT_TRIPLE: - load_idt((const struct desc_ptr *)&no_idt); - __asm__ __volatile__("int3"); - - reboot_type = BOOT_KBD; + case BOOT_EFI: + 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_BIOS; break; -#ifdef CONFIG_X86_32 case BOOT_BIOS: - machine_real_restart(jump_to_bios, sizeof(jump_to_bios)); + machine_real_restart(MRR_BIOS); - reboot_type = BOOT_KBD; + /* We're probably dead after this, but... */ + reboot_type = BOOT_CF9_SAFE; break; -#endif - case BOOT_ACPI: - acpi_reboot(); - reboot_type = BOOT_KBD; - break; + case BOOT_CF9_FORCE: + port_cf9_safe = true; + /* Fall through */ + case BOOT_CF9_SAFE: + if (port_cf9_safe) { + u8 reboot_code = reboot_mode == REBOOT_WARM ? 0x06 : 0x0E; + u8 cf9 = inb(0xcf9) & ~reboot_code; + outb(cf9|2, 0xcf9); /* Request hard reset */ + udelay(50); + /* Actually do the reset */ + outb(cf9|reboot_code, 0xcf9); + udelay(50); + } + reboot_type = BOOT_TRIPLE; + break; - case BOOT_EFI: - if (efi_enabled) - efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD, - EFI_SUCCESS, 0, NULL); + case BOOT_TRIPLE: + load_idt(&no_idt); + __asm__ __volatile__("int3"); + /* We're probably dead after this, but... */ reboot_type = BOOT_KBD; break; } } } -static void native_machine_shutdown(void) +void native_machine_shutdown(void) { /* Stop the cpus and apics */ -#ifdef CONFIG_SMP - int reboot_cpu_id; - - /* The boot cpu is always logical cpu 0 */ - reboot_cpu_id = 0; - -#ifdef CONFIG_X86_32 - /* See if there has been given a command line override */ - if ((reboot_cpu != -1) && (reboot_cpu < NR_CPUS) && - cpu_isset(reboot_cpu, cpu_online_map)) - reboot_cpu_id = reboot_cpu; +#ifdef CONFIG_X86_IO_APIC + /* + * Disabling IO APIC before local APIC is a workaround for + * erratum AVR31 in "Intel Atom Processor C2000 Product Family + * Specification Update". In this situation, interrupts that target + * a Logical Processor whose Local APIC is either in the process of + * being hardware disabled or software disabled are neither delivered + * nor discarded. When this erratum occurs, the processor may hang. + * + * Even without the erratum, it still makes sense to quiet IO APIC + * before disabling Local APIC. + */ + disable_IO_APIC(); #endif - /* Make certain the cpu I'm about to reboot on is online */ - if (!cpu_isset(reboot_cpu_id, cpu_online_map)) - reboot_cpu_id = smp_processor_id(); - - /* Make certain I only run on the appropriate processor */ - set_cpus_allowed(current, cpumask_of_cpu(reboot_cpu_id)); - - /* O.K Now that I'm on the appropriate processor, - * stop all of the others. +#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. */ - smp_send_stop(); + 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 - pci_iommu_shutdown(); + 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) { - printk("machine restart\n"); + pr_notice("machine restart\n"); if (!reboot_force) machine_shutdown(); - machine_emergency_restart(); + __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) @@ -464,6 +642,8 @@ static void native_machine_power_off(void) machine_shutdown(); pm_power_off(); } + /* A fallback in case there is no PM info available */ + tboot_shutdown(TB_SHUTDOWN_HALT); } struct machine_ops machine_ops = { @@ -471,7 +651,10 @@ struct machine_ops machine_ops = { .shutdown = native_machine_shutdown, .emergency_restart = native_machine_emergency_restart, .restart = native_machine_restart, - .halt = native_machine_halt + .halt = native_machine_halt, +#ifdef CONFIG_KEXEC + .crash_shutdown = native_machine_crash_shutdown, +#endif }; void machine_power_off(void) @@ -486,7 +669,7 @@ void machine_shutdown(void) void machine_emergency_restart(void) { - machine_ops.emergency_restart(); + __machine_emergency_restart(1); } void machine_restart(char *cmd) @@ -499,3 +682,94 @@ 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 |