diff options
Diffstat (limited to 'arch/i386/kernel')
-rw-r--r-- | arch/i386/kernel/acpi/boot.c | 19 | ||||
-rw-r--r-- | arch/i386/kernel/acpi/cstate.c | 122 | ||||
-rw-r--r-- | arch/i386/kernel/alternative.c | 4 | ||||
-rw-r--r-- | arch/i386/kernel/apic.c | 18 | ||||
-rw-r--r-- | arch/i386/kernel/apm.c | 37 | ||||
-rw-r--r-- | arch/i386/kernel/cpu/mcheck/therm_throt.c | 21 | ||||
-rw-r--r-- | arch/i386/kernel/i8253.c | 2 | ||||
-rw-r--r-- | arch/i386/kernel/i8259.c | 50 | ||||
-rw-r--r-- | arch/i386/kernel/io_apic.c | 504 | ||||
-rw-r--r-- | arch/i386/kernel/irq.c | 19 | ||||
-rw-r--r-- | arch/i386/kernel/microcode.c | 8 | ||||
-rw-r--r-- | arch/i386/kernel/process.c | 28 | ||||
-rw-r--r-- | arch/i386/kernel/setup.c | 13 | ||||
-rw-r--r-- | arch/i386/kernel/smp.c | 6 | ||||
-rw-r--r-- | arch/i386/kernel/syscall_table.S | 1 | ||||
-rw-r--r-- | arch/i386/kernel/time.c | 10 | ||||
-rw-r--r-- | arch/i386/kernel/time_hpet.c | 4 | ||||
-rw-r--r-- | arch/i386/kernel/tsc.c | 6 | ||||
-rw-r--r-- | arch/i386/kernel/vm86.c | 2 |
19 files changed, 568 insertions, 306 deletions
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 1aaea6ab8c46..ab974ff97073 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -62,8 +62,6 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return #include <mach_mpparse.h> #endif /* CONFIG_X86_LOCAL_APIC */ -static inline int gsi_irq_sharing(int gsi) { return gsi; } - #endif /* X86 */ #define BAD_MADT_ENTRY(entry, end) ( \ @@ -334,7 +332,7 @@ acpi_parse_ioapic(acpi_table_entry_header * header, const unsigned long end) /* * Parse Interrupt Source Override for the ACPI SCI */ -static void acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) +static void acpi_sci_ioapic_setup(u32 bus_irq, u32 gsi, u16 polarity, u16 trigger) { if (trigger == 0) /* compatible SCI trigger is level */ trigger = 3; @@ -354,13 +352,13 @@ static void acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) * If GSI is < 16, this will update its flags, * else it will create a new mp_irqs[] entry. */ - mp_override_legacy_irq(gsi, polarity, trigger, gsi); + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); /* * stash over-ride to indicate we've been here * and for later update of acpi_fadt */ - acpi_sci_override_gsi = gsi; + acpi_sci_override_gsi = bus_irq; return; } @@ -378,7 +376,7 @@ acpi_parse_int_src_ovr(acpi_table_entry_header * header, acpi_table_print_madt_entry(header); if (intsrc->bus_irq == acpi_fadt.sci_int) { - acpi_sci_ioapic_setup(intsrc->global_irq, + acpi_sci_ioapic_setup(intsrc->bus_irq, intsrc->global_irq, intsrc->flags.polarity, intsrc->flags.trigger); return 0; @@ -468,12 +466,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) { -#ifdef CONFIG_X86_IO_APIC - if (use_pci_vector() && !platform_legacy_irq(gsi)) - *irq = IO_APIC_VECTOR(gsi); - else -#endif - *irq = gsi_irq_sharing(gsi); + *irq = gsi; return 0; } @@ -886,7 +879,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) * pretend we got one so we can set the SCI flags. */ if (!acpi_sci_override_gsi) - acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0); + acpi_sci_ioapic_setup(acpi_fadt.sci_int, acpi_fadt.sci_int, 0, 0); /* Fill in identity legacy mapings where no override */ mp_config_acpi_legacy_irqs(); diff --git a/arch/i386/kernel/acpi/cstate.c b/arch/i386/kernel/acpi/cstate.c index 25db49ef1770..20563e52c622 100644 --- a/arch/i386/kernel/acpi/cstate.c +++ b/arch/i386/kernel/acpi/cstate.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/acpi.h> +#include <linux/cpu.h> #include <acpi/processor.h> #include <asm/acpi.h> @@ -41,5 +42,124 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, flags->bm_check = 1; } } - EXPORT_SYMBOL(acpi_processor_power_init_bm_check); + +/* The code below handles cstate entry with monitor-mwait pair on Intel*/ + +struct cstate_entry_s { + struct { + unsigned int eax; + unsigned int ecx; + } states[ACPI_PROCESSOR_MAX_POWER]; +}; +static struct cstate_entry_s *cpu_cstate_entry; /* per CPU ptr */ + +static short mwait_supported[ACPI_PROCESSOR_MAX_POWER]; + +#define MWAIT_SUBSTATE_MASK (0xf) +#define MWAIT_SUBSTATE_SIZE (4) + +#define CPUID_MWAIT_LEAF (5) +#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1) +#define CPUID5_ECX_INTERRUPT_BREAK (0x2) + +#define MWAIT_ECX_INTERRUPT_BREAK (0x1) + +#define NATIVE_CSTATE_BEYOND_HALT (2) + +int acpi_processor_ffh_cstate_probe(unsigned int cpu, + struct acpi_processor_cx *cx, struct acpi_power_register *reg) +{ + struct cstate_entry_s *percpu_entry; + struct cpuinfo_x86 *c = cpu_data + cpu; + + cpumask_t saved_mask; + int retval; + unsigned int eax, ebx, ecx, edx; + unsigned int edx_part; + unsigned int cstate_type; /* C-state type and not ACPI C-state type */ + unsigned int num_cstate_subtype; + + if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF ) + return -1; + + if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT) + return -1; + + percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu); + percpu_entry->states[cx->index].eax = 0; + percpu_entry->states[cx->index].ecx = 0; + + /* Make sure we are running on right CPU */ + saved_mask = current->cpus_allowed; + retval = set_cpus_allowed(current, cpumask_of_cpu(cpu)); + if (retval) + return -1; + + cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + + /* Check whether this particular cx_type (in CST) is supported or not */ + cstate_type = (cx->address >> MWAIT_SUBSTATE_SIZE) + 1; + edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE); + num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK; + + retval = 0; + if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) { + retval = -1; + goto out; + } + + /* mwait ecx extensions INTERRUPT_BREAK should be supported for C2/C3 */ + if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) || + !(ecx & CPUID5_ECX_INTERRUPT_BREAK)) { + retval = -1; + goto out; + } + percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK; + + /* Use the hint in CST */ + percpu_entry->states[cx->index].eax = cx->address; + + if (!mwait_supported[cstate_type]) { + mwait_supported[cstate_type] = 1; + printk(KERN_DEBUG "Monitor-Mwait will be used to enter C-%d " + "state\n", cx->type); + } + +out: + set_cpus_allowed(current, saved_mask); + return retval; +} +EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); + +void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) +{ + unsigned int cpu = smp_processor_id(); + struct cstate_entry_s *percpu_entry; + + percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu); + mwait_idle_with_hints(percpu_entry->states[cx->index].eax, + percpu_entry->states[cx->index].ecx); +} +EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter); + +static int __init ffh_cstate_init(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + if (c->x86_vendor != X86_VENDOR_INTEL) + return -1; + + cpu_cstate_entry = alloc_percpu(struct cstate_entry_s); + return 0; +} + +static void __exit ffh_cstate_exit(void) +{ + if (cpu_cstate_entry) { + free_percpu(cpu_cstate_entry); + cpu_cstate_entry = NULL; + } +} + +arch_initcall(ffh_cstate_init); +__exitcall(ffh_cstate_exit); diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c index 28ab80649764..583c238e17fb 100644 --- a/arch/i386/kernel/alternative.c +++ b/arch/i386/kernel/alternative.c @@ -344,6 +344,7 @@ void alternatives_smp_switch(int smp) void __init alternative_instructions(void) { + unsigned long flags; if (no_replacement) { printk(KERN_INFO "(SMP-)alternatives turned off\n"); free_init_pages("SMP alternatives", @@ -351,6 +352,8 @@ void __init alternative_instructions(void) (unsigned long)__smp_alt_end); return; } + + local_irq_save(flags); apply_alternatives(__alt_instructions, __alt_instructions_end); /* switch to patch-once-at-boottime-only mode and free the @@ -386,4 +389,5 @@ void __init alternative_instructions(void) alternatives_smp_switch(0); } #endif + local_irq_restore(flags); } diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 90faae5c5d30..2fd4b7d927c2 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -1193,11 +1193,11 @@ EXPORT_SYMBOL(switch_ipi_to_APIC_timer); * value into /proc/profile. */ -inline void smp_local_timer_interrupt(struct pt_regs * regs) +inline void smp_local_timer_interrupt(void) { - profile_tick(CPU_PROFILING, regs); + profile_tick(CPU_PROFILING); #ifdef CONFIG_SMP - update_process_times(user_mode_vm(regs)); + update_process_times(user_mode_vm(get_irq_regs())); #endif /* @@ -1223,6 +1223,7 @@ inline void smp_local_timer_interrupt(struct pt_regs * regs) fastcall void smp_apic_timer_interrupt(struct pt_regs *regs) { + struct pt_regs *old_regs = set_irq_regs(regs); int cpu = smp_processor_id(); /* @@ -1241,12 +1242,13 @@ fastcall void smp_apic_timer_interrupt(struct pt_regs *regs) * interrupt lock, which is the WrongThing (tm) to do. */ irq_enter(); - smp_local_timer_interrupt(regs); + smp_local_timer_interrupt(); irq_exit(); + set_irq_regs(old_regs); } #ifndef CONFIG_SMP -static void up_apic_timer_interrupt_call(struct pt_regs *regs) +static void up_apic_timer_interrupt_call(void) { int cpu = smp_processor_id(); @@ -1255,11 +1257,11 @@ static void up_apic_timer_interrupt_call(struct pt_regs *regs) */ per_cpu(irq_stat, cpu).apic_timer_irqs++; - smp_local_timer_interrupt(regs); + smp_local_timer_interrupt(); } #endif -void smp_send_timer_broadcast_ipi(struct pt_regs *regs) +void smp_send_timer_broadcast_ipi(void) { cpumask_t mask; @@ -1272,7 +1274,7 @@ void smp_send_timer_broadcast_ipi(struct pt_regs *regs) * We can directly call the apic timer interrupt handler * in UP case. Minus all irq related functions */ - up_apic_timer_interrupt_call(regs); + up_apic_timer_interrupt_call(); #endif } } diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c index b42f2d914af3..2af65858d322 100644 --- a/arch/i386/kernel/apm.c +++ b/arch/i386/kernel/apm.c @@ -540,11 +540,30 @@ static inline void apm_restore_cpus(cpumask_t mask) * Also, we KNOW that for the non error case of apm_bios_call, there * is no useful data returned in the low order 8 bits of eax. */ -#define APM_DO_CLI \ - if (apm_info.allow_ints) \ - local_irq_enable(); \ - else \ + +static inline unsigned long __apm_irq_save(void) +{ + unsigned long flags; + local_save_flags(flags); + if (apm_info.allow_ints) { + if (irqs_disabled_flags(flags)) + local_irq_enable(); + } else + local_irq_disable(); + + return flags; +} + +#define apm_irq_save(flags) \ + do { flags = __apm_irq_save(); } while (0) + +static inline void apm_irq_restore(unsigned long flags) +{ + if (irqs_disabled_flags(flags)) local_irq_disable(); + else if (irqs_disabled()) + local_irq_enable(); +} #ifdef APM_ZERO_SEGS # define APM_DECL_SEGS \ @@ -596,12 +615,11 @@ static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in, save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; - local_save_flags(flags); - APM_DO_CLI; + apm_irq_save(flags); APM_DO_SAVE_SEGS; apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi); APM_DO_RESTORE_SEGS; - local_irq_restore(flags); + apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); apm_restore_cpus(cpus); @@ -640,12 +658,11 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; - local_save_flags(flags); - APM_DO_CLI; + apm_irq_save(flags); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax); APM_DO_RESTORE_SEGS; - local_irq_restore(flags); + apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); apm_restore_cpus(cpus); diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c index 4f43047de406..2d8703b7ce65 100644 --- a/arch/i386/kernel/cpu/mcheck/therm_throt.c +++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c @@ -110,17 +110,15 @@ int therm_throt_process(int curr) #ifdef CONFIG_SYSFS /* Add/Remove thermal_throttle interface for CPU device */ -static __cpuinit int thermal_throttle_add_dev(struct sys_device * sys_dev) +static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) { - sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group); - return 0; + return sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group); } #ifdef CONFIG_HOTPLUG_CPU -static __cpuinit int thermal_throttle_remove_dev(struct sys_device * sys_dev) +static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev) { - sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); - return 0; + return sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); } /* Mutex protecting device creation against CPU hotplug */ @@ -133,12 +131,14 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb, { unsigned int cpu = (unsigned long)hcpu; struct sys_device *sys_dev; + int err; sys_dev = get_cpu_sysdev(cpu); mutex_lock(&therm_cpu_lock); switch (action) { case CPU_ONLINE: - thermal_throttle_add_dev(sys_dev); + err = thermal_throttle_add_dev(sys_dev); + WARN_ON(err); break; case CPU_DEAD: thermal_throttle_remove_dev(sys_dev); @@ -157,6 +157,7 @@ static struct notifier_block thermal_throttle_cpu_notifier = static __init int thermal_throttle_init_device(void) { unsigned int cpu = 0; + int err; if (!atomic_read(&therm_throt_en)) return 0; @@ -167,8 +168,10 @@ static __init int thermal_throttle_init_device(void) mutex_lock(&therm_cpu_lock); #endif /* connect live CPUs to sysfs */ - for_each_online_cpu(cpu) - thermal_throttle_add_dev(get_cpu_sysdev(cpu)); + for_each_online_cpu(cpu) { + err = thermal_throttle_add_dev(get_cpu_sysdev(cpu)); + WARN_ON(err); + } #ifdef CONFIG_HOTPLUG_CPU mutex_unlock(&therm_cpu_lock); #endif diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c index 477b24daff53..9a0060b92e32 100644 --- a/arch/i386/kernel/i8253.c +++ b/arch/i386/kernel/i8253.c @@ -109,7 +109,7 @@ static struct clocksource clocksource_pit = { static int __init init_pit_clocksource(void) { - if (num_possible_cpus() > 4) /* PIT does not scale! */ + if (num_possible_cpus() > 1) /* PIT does not scale! */ return 0; clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20); diff --git a/arch/i386/kernel/i8259.c b/arch/i386/kernel/i8259.c index ea5f4e7958d8..62996cd17084 100644 --- a/arch/i386/kernel/i8259.c +++ b/arch/i386/kernel/i8259.c @@ -34,35 +34,15 @@ * moves to arch independent land */ -DEFINE_SPINLOCK(i8259A_lock); - -static void end_8259A_irq (unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)) && - irq_desc[irq].action) - enable_8259A_irq(irq); -} - -#define shutdown_8259A_irq disable_8259A_irq - static int i8259A_auto_eoi; - +DEFINE_SPINLOCK(i8259A_lock); static void mask_and_ack_8259A(unsigned int); -unsigned int startup_8259A_irq(unsigned int irq) -{ - enable_8259A_irq(irq); - return 0; /* never anything pending */ -} - -static struct hw_interrupt_type i8259A_irq_type = { - .typename = "XT-PIC", - .startup = startup_8259A_irq, - .shutdown = shutdown_8259A_irq, - .enable = enable_8259A_irq, - .disable = disable_8259A_irq, - .ack = mask_and_ack_8259A, - .end = end_8259A_irq, +static struct irq_chip i8259A_chip = { + .name = "XT-PIC", + .mask = disable_8259A_irq, + .unmask = enable_8259A_irq, + .mask_ack = mask_and_ack_8259A, }; /* @@ -133,7 +113,8 @@ void make_8259A_irq(unsigned int irq) { disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); - irq_desc[irq].chip = &i8259A_irq_type; + set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq, + "XT"); enable_irq(irq); } @@ -327,12 +308,12 @@ void init_8259A(int auto_eoi) outb_p(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */ if (auto_eoi) /* - * in AEOI mode we just have to mask the interrupt + * In AEOI mode we just have to mask the interrupt * when acking. */ - i8259A_irq_type.ack = disable_8259A_irq; + i8259A_chip.mask_ack = disable_8259A_irq; else - i8259A_irq_type.ack = mask_and_ack_8259A; + i8259A_chip.mask_ack = mask_and_ack_8259A; udelay(100); /* wait for 8259A to initialize */ @@ -355,13 +336,13 @@ void init_8259A(int auto_eoi) */ -static irqreturn_t math_error_irq(int cpl, void *dev_id, struct pt_regs *regs) +static irqreturn_t math_error_irq(int cpl, void *dev_id) { extern void math_error(void __user *); outb(0,0xF0); if (ignore_fpu_irq || !boot_cpu_data.hard_math) return IRQ_NONE; - math_error((void __user *)regs->eip); + math_error((void __user *)get_irq_regs()->eip); return IRQ_HANDLED; } @@ -389,12 +370,13 @@ void __init init_ISA_irqs (void) /* * 16 old-style INTA-cycle interrupts: */ - irq_desc[i].chip = &i8259A_irq_type; + set_irq_chip_and_handler_name(i, &i8259A_chip, + handle_level_irq, "XT"); } else { /* * 'high' PCI IRQs filled in on demand */ - irq_desc[i].chip = &no_irq_type; + irq_desc[i].chip = &no_irq_chip; } } } diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index fd0df75cfbda..350192d6ab98 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -31,6 +31,9 @@ #include <linux/acpi.h> #include <linux/module.h> #include <linux/sysdev.h> +#include <linux/pci.h> +#include <linux/msi.h> +#include <linux/htirq.h> #include <asm/io.h> #include <asm/smp.h> @@ -38,6 +41,8 @@ #include <asm/timer.h> #include <asm/i8259.h> #include <asm/nmi.h> +#include <asm/msidef.h> +#include <asm/hypertransport.h> #include <mach_apic.h> #include <mach_apicdef.h> @@ -86,15 +91,6 @@ static struct irq_pin_list { int apic, pin, next; } irq_2_pin[PIN_MAP_SIZE]; -int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1}; -#ifdef CONFIG_PCI_MSI -#define vector_to_irq(vector) \ - (platform_legacy_irq(vector) ? vector : vector_irq[vector]) -#else -#define vector_to_irq(vector) (vector) -#endif - - union entry_union { struct { u32 w1, w2; }; struct IO_APIC_route_entry entry; @@ -280,7 +276,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) break; entry = irq_2_pin + entry->next; } - set_irq_info(irq, cpumask); + set_native_irq_info(irq, cpumask); spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -1181,46 +1177,45 @@ static inline int IO_APIC_irq_trigger(int irq) /* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 }; -int assign_irq_vector(int irq) +static int __assign_irq_vector(int irq) { static int current_vector = FIRST_DEVICE_VECTOR, offset = 0; - unsigned long flags; int vector; - BUG_ON(irq != AUTO_ASSIGN && (unsigned)irq >= NR_IRQ_VECTORS); + BUG_ON((unsigned)irq >= NR_IRQ_VECTORS); - spin_lock_irqsave(&vector_lock, flags); + if (irq_vector[irq] > 0) + return irq_vector[irq]; - if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) { - spin_unlock_irqrestore(&vector_lock, flags); - return IO_APIC_VECTOR(irq); - } -next: current_vector += 8; if (current_vector == SYSCALL_VECTOR) - goto next; + current_vector += 8; if (current_vector >= FIRST_SYSTEM_VECTOR) { offset++; - if (!(offset%8)) { - spin_unlock_irqrestore(&vector_lock, flags); + if (!(offset % 8)) return -ENOSPC; - } current_vector = FIRST_DEVICE_VECTOR + offset; } vector = current_vector; - vector_irq[vector] = irq; - if (irq != AUTO_ASSIGN) - IO_APIC_VECTOR(irq) = vector; + irq_vector[irq] = vector; + + return vector; +} +static int assign_irq_vector(int irq) +{ + unsigned long flags; + int vector; + + spin_lock_irqsave(&vector_lock, flags); + vector = __assign_irq_vector(irq); spin_unlock_irqrestore(&vector_lock, flags); return vector; } - -static struct hw_interrupt_type ioapic_level_type; -static struct hw_interrupt_type ioapic_edge_type; +static struct irq_chip ioapic_chip; #define IOAPIC_AUTO -1 #define IOAPIC_EDGE 0 @@ -1228,16 +1223,14 @@ static struct hw_interrupt_type ioapic_edge_type; static void ioapic_register_intr(int irq, int vector, unsigned long trigger) { - unsigned idx; - - idx = use_pci_vector() && !platform_legacy_irq(irq) ? vector : irq; - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || trigger == IOAPIC_LEVEL) - irq_desc[idx].chip = &ioapic_level_type; + set_irq_chip_and_handler_name(irq, &ioapic_chip, + handle_fasteoi_irq, "fasteoi"); else - irq_desc[idx].chip = &ioapic_edge_type; - set_intr_gate(vector, interrupt[idx]); + set_irq_chip_and_handler_name(irq, &ioapic_chip, + handle_edge_irq, "edge"); + set_intr_gate(vector, interrupt[irq]); } static void __init setup_IO_APIC_irqs(void) @@ -1346,7 +1339,8 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in * The timer IRQ doesn't have to know that behind the * scene we have a 8259A-master in AEOI mode ... */ - irq_desc[0].chip = &ioapic_edge_type; + irq_desc[0].chip = &ioapic_chip; + set_irq_handler(0, handle_edge_irq); /* * Add it to the IO-APIC irq-routing table: @@ -1481,17 +1475,12 @@ void __init print_IO_APIC(void) ); } } - if (use_pci_vector()) - printk(KERN_INFO "Using vector-based indexing\n"); printk(KERN_DEBUG "IRQ to pin mappings:\n"); for (i = 0; i < NR_IRQS; i++) { struct irq_pin_list *entry = irq_2_pin + i; if (entry->pin < 0) continue; - if (use_pci_vector() && !platform_legacy_irq(i)) - printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i)); - else - printk(KERN_DEBUG "IRQ%d ", i); + printk(KERN_DEBUG "IRQ%d ", i); for (;;) { printk("-> %d:%d", entry->apic, entry->pin); if (!entry->next) @@ -1918,6 +1907,8 @@ static int __init timer_irq_works(void) */ /* + * Startup quirk: + * * Starting up a edge-triggered IO-APIC interrupt is * nasty - we need to make sure that we get the edge. * If it is already asserted for some reason, we need @@ -1925,8 +1916,10 @@ static int __init timer_irq_works(void) * * This is not complete - we should be able to fake * an edge even if it isn't on the 8259A... + * + * (We do this for level-triggered IRQs too - it cannot hurt.) */ -static unsigned int startup_edge_ioapic_irq(unsigned int irq) +static unsigned int startup_ioapic_irq(unsigned int irq) { int was_pending = 0; unsigned long flags; @@ -1943,47 +1936,18 @@ static unsigned int startup_edge_ioapic_irq(unsigned int irq) return was_pending; } -/* - * Once we have recorded IRQ_PENDING already, we can mask the - * interrupt for real. This prevents IRQ storms from unhandled - * devices. - */ -static void ack_edge_ioapic_irq(unsigned int irq) +static void ack_ioapic_irq(unsigned int irq) { - move_irq(irq); - if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED)) - == (IRQ_PENDING | IRQ_DISABLED)) - mask_IO_APIC_irq(irq); + move_native_irq(irq); ack_APIC_irq(); } -/* - * Level triggered interrupts can just be masked, - * and shutting down and starting up the interrupt - * is the same as enabling and disabling them -- except - * with a startup need to return a "was pending" value. - * - * Level triggered interrupts are special because we - * do not touch any IO-APIC register while handling - * them. We ack the APIC in the end-IRQ handler, not - * in the start-IRQ-handler. Protection against reentrance - * from the same interrupt is still provided, both by the - * generic IRQ layer and by the fact that an unacked local - * APIC does not accept IRQs. - */ -static unsigned int startup_level_ioapic_irq (unsigned int irq) -{ - unmask_IO_APIC_irq(irq); - - return 0; /* don't check for pending */ -} - -static void end_level_ioapic_irq (unsigned int irq) +static void ack_ioapic_quirk_irq(unsigned int irq) { unsigned long v; int i; - move_irq(irq); + move_native_irq(irq); /* * It appears there is an erratum which affects at least version 0x11 * of I/O APIC (that's the 82093AA and cores integrated into various @@ -2003,7 +1967,7 @@ static void end_level_ioapic_irq (unsigned int irq) * operation to prevent an edge-triggered interrupt escaping meanwhile. * The idea is from Manfred Spraul. --macro */ - i = IO_APIC_VECTOR(irq); + i = irq_vector[irq]; v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1)); @@ -2018,105 +1982,26 @@ static void end_level_ioapic_irq (unsigned int irq) } } -#ifdef CONFIG_PCI_MSI -static unsigned int startup_edge_ioapic_vector(unsigned int vector) -{ - int irq = vector_to_irq(vector); - - return startup_edge_ioapic_irq(irq); -} - -static void ack_edge_ioapic_vector(unsigned int vector) -{ - int irq = vector_to_irq(vector); - - move_native_irq(vector); - ack_edge_ioapic_irq(irq); -} - -static unsigned int startup_level_ioapic_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - return startup_level_ioapic_irq (irq); -} - -static void end_level_ioapic_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - move_native_irq(vector); - end_level_ioapic_irq(irq); -} - -static void mask_IO_APIC_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - mask_IO_APIC_irq(irq); -} - -static void unmask_IO_APIC_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - unmask_IO_APIC_irq(irq); -} - -#ifdef CONFIG_SMP -static void set_ioapic_affinity_vector (unsigned int vector, - cpumask_t cpu_mask) -{ - int irq = vector_to_irq(vector); - - set_native_irq_info(vector, cpu_mask); - set_ioapic_affinity_irq(irq, cpu_mask); -} -#endif -#endif - -static int ioapic_retrigger(unsigned int irq) +static int ioapic_retrigger_irq(unsigned int irq) { - send_IPI_self(IO_APIC_VECTOR(irq)); + send_IPI_self(irq_vector[irq]); return 1; } -/* - * Level and edge triggered IO-APIC interrupts need different handling, - * so we use two separate IRQ descriptors. Edge triggered IRQs can be - * handled with the level-triggered descriptor, but that one has slightly - * more overhead. Level-triggered interrupts cannot be handled with the - * edge-triggered handler, without risking IRQ storms and other ugly - * races. - */ -static struct hw_interrupt_type ioapic_edge_type __read_mostly = { - .typename = "IO-APIC-edge", - .startup = startup_edge_ioapic, - .shutdown = shutdown_edge_ioapic, - .enable = enable_edge_ioapic, - .disable = disable_edge_ioapic, - .ack = ack_edge_ioapic, - .end = end_edge_ioapic, +static struct irq_chip ioapic_chip __read_mostly = { + .name = "IO-APIC", + .startup = startup_ioapic_irq, + .mask = mask_IO_APIC_irq, + .unmask = unmask_IO_APIC_irq, + .ack = ack_ioapic_irq, + .eoi = ack_ioapic_quirk_irq, #ifdef CONFIG_SMP - .set_affinity = set_ioapic_affinity, + .set_affinity = set_ioapic_affinity_irq, #endif - .retrigger = ioapic_retrigger, + .retrigger = ioapic_retrigger_irq, }; -static struct hw_interrupt_type ioapic_level_type __read_mostly = { - .typename = "IO-APIC-level", - .startup = startup_level_ioapic, - .shutdown = shutdown_level_ioapic, - .enable = enable_level_ioapic, - .disable = disable_level_ioapic, - .ack = mask_and_ack_level_ioapic, - .end = end_level_ioapic, -#ifdef CONFIG_SMP - .set_affinity = set_ioapic_affinity, -#endif - .retrigger = ioapic_retrigger, -}; static inline void init_IO_APIC_traps(void) { @@ -2135,12 +2020,7 @@ static inline void init_IO_APIC_traps(void) */ for (irq = 0; irq < NR_IRQS ; irq++) { int tmp = irq; - if (use_pci_vector()) { - if (!platform_legacy_irq(tmp)) - if ((tmp = vector_to_irq(tmp)) == -1) - continue; - } - if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) { + if (IO_APIC_IRQ(tmp) && !irq_vector[tmp]) { /* * Hmm.. We don't have an entry for this, * so default to an old-fashioned 8259 @@ -2150,20 +2030,21 @@ static inline void init_IO_APIC_traps(void) make_8259A_irq(irq); else /* Strange. Oh, well.. */ - irq_desc[irq].chip = &no_irq_type; + irq_desc[irq].chip = &no_irq_chip; } } } -static void enable_lapic_irq (unsigned int irq) -{ - unsigned long v; +/* + * The local APIC irq-chip implementation: + */ - v = apic_read(APIC_LVT0); - apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED); +static void ack_apic(unsigned int irq) +{ + ack_APIC_irq(); } -static void disable_lapic_irq (unsigned int irq) +static void mask_lapic_irq (unsigned int irq) { unsigned long v; @@ -2171,21 +2052,19 @@ static void disable_lapic_irq (unsigned int irq) apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED); } -static void ack_lapic_irq (unsigned int irq) +static void unmask_lapic_irq (unsigned int irq) { - ack_APIC_irq(); -} + unsigned long v; -static void end_lapic_irq (unsigned int i) { /* nothing */ } + v = apic_read(APIC_LVT0); + apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED); +} -static struct hw_interrupt_type lapic_irq_type __read_mostly = { - .typename = "local-APIC-edge", - .startup = NULL, /* startup_irq() not used for IRQ0 */ - .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ - .enable = enable_lapic_irq, - .disable = disable_lapic_irq, - .ack = ack_lapic_irq, - .end = end_lapic_irq +static struct irq_chip lapic_chip __read_mostly = { + .name = "local-APIC-edge", + .mask = mask_lapic_irq, + .unmask = unmask_lapic_irq, + .eoi = ack_apic, }; static void setup_nmi (void) @@ -2356,7 +2235,8 @@ static inline void check_timer(void) printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); disable_8259A_irq(0); - irq_desc[0].chip = &lapic_irq_type; + set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq, + "fasteio"); apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */ enable_8259A_irq(0); @@ -2531,6 +2411,240 @@ static int __init ioapic_init_sysfs(void) device_initcall(ioapic_init_sysfs); +/* + * Dynamic irq allocate and deallocation + */ +int create_irq(void) +{ + /* Allocate an unused irq */ + int irq, new, vector; + unsigned long flags; + + irq = -ENOSPC; + spin_lock_irqsave(&vector_lock, flags); + for (new = (NR_IRQS - 1); new >= 0; new--) { + if (platform_legacy_irq(new)) + continue; + if (irq_vector[new] != 0) + continue; + vector = __assign_irq_vector(new); + if (likely(vector > 0)) + irq = new; + break; + } + spin_unlock_irqrestore(&vector_lock, flags); + + if (irq >= 0) { + set_intr_gate(vector, interrupt[irq]); + dynamic_irq_init(irq); + } + return irq; +} + +void destroy_irq(unsigned int irq) +{ + unsigned long flags; + + dynamic_irq_cleanup(irq); + + spin_lock_irqsave(&vector_lock, flags); + irq_vector[irq] = 0; + spin_unlock_irqrestore(&vector_lock, flags); +} + +/* + * MSI mesage composition + */ +#ifdef CONFIG_PCI_MSI +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) +{ + int vector; + unsigned dest; + + vector = assign_irq_vector(irq); + if (vector >= 0) { + dest = cpu_mask_to_apicid(TARGET_CPUS); + + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = + MSI_ADDR_BASE_LO | + ((INT_DEST_MODE == 0) ? + MSI_ADDR_DEST_MODE_PHYSICAL: + MSI_ADDR_DEST_MODE_LOGICAL) | + ((INT_DELIVERY_MODE != dest_LowestPrio) ? + MSI_ADDR_REDIRECTION_CPU: + MSI_ADDR_REDIRECTION_LOWPRI) | + MSI_ADDR_DEST_ID(dest); + + msg->data = + MSI_DATA_TRIGGER_EDGE | + MSI_DATA_LEVEL_ASSERT | + ((INT_DELIVERY_MODE != dest_LowestPrio) ? + MSI_DATA_DELIVERY_FIXED: + MSI_DATA_DELIVERY_LOWPRI) | + MSI_DATA_VECTOR(vector); + } + return vector; +} + +#ifdef CONFIG_SMP +static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask) +{ + struct msi_msg msg; + unsigned int dest; + cpumask_t tmp; + int vector; + + cpus_and(tmp, mask, cpu_online_map); + if (cpus_empty(tmp)) + tmp = TARGET_CPUS; + + vector = assign_irq_vector(irq); + if (vector < 0) + return; + + dest = cpu_mask_to_apicid(mask); + + read_msi_msg(irq, &msg); + + msg.data &= ~MSI_DATA_VECTOR_MASK; + msg.data |= MSI_DATA_VECTOR(vector); + msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; + msg.address_lo |= MSI_ADDR_DEST_ID(dest); + + write_msi_msg(irq, &msg); + set_native_irq_info(irq, mask); +} +#endif /* CONFIG_SMP */ + +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip msi_chip = { + .name = "PCI-MSI", + .unmask = unmask_msi_irq, + .mask = mask_msi_irq, + .ack = ack_ioapic_irq, +#ifdef CONFIG_SMP + .set_affinity = set_msi_irq_affinity, +#endif + .retrigger = ioapic_retrigger_irq, +}; + +int arch_setup_msi_irq(unsigned int irq, struct pci_dev *dev) +{ + struct msi_msg msg; + int ret; + ret = msi_compose_msg(dev, irq, &msg); + if (ret < 0) + return ret; + + write_msi_msg(irq, &msg); + + set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, + "edge"); + + return 0; +} + +void arch_teardown_msi_irq(unsigned int irq) +{ + return; +} + +#endif /* CONFIG_PCI_MSI */ + +/* + * Hypertransport interrupt support + */ +#ifdef CONFIG_HT_IRQ + +#ifdef CONFIG_SMP + +static void target_ht_irq(unsigned int irq, unsigned int dest) +{ + u32 low, high; + low = read_ht_irq_low(irq); + high = read_ht_irq_high(irq); + + low &= ~(HT_IRQ_LOW_DEST_ID_MASK); + high &= ~(HT_IRQ_HIGH_DEST_ID_MASK); + + low |= HT_IRQ_LOW_DEST_ID(dest); + high |= HT_IRQ_HIGH_DEST_ID(dest); + + write_ht_irq_low(irq, low); + write_ht_irq_high(irq, high); +} + +static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask) +{ + unsigned int dest; + cpumask_t tmp; + + cpus_and(tmp, mask, cpu_online_map); + if (cpus_empty(tmp)) + tmp = TARGET_CPUS; + + cpus_and(mask, tmp, CPU_MASK_ALL); + + dest = cpu_mask_to_apicid(mask); + + target_ht_irq(irq, dest); + set_native_irq_info(irq, mask); +} +#endif + +static struct irq_chip ht_irq_chip = { + .name = "PCI-HT", + .mask = mask_ht_irq, + .unmask = unmask_ht_irq, + .ack = ack_ioapic_irq, +#ifdef CONFIG_SMP + .set_affinity = set_ht_irq_affinity, +#endif + .retrigger = ioapic_retrigger_irq, +}; + +int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) +{ + int vector; + + vector = assign_irq_vector(irq); + if (vector >= 0) { + u32 low, high; + unsigned dest; + cpumask_t tmp; + + cpus_clear(tmp); + cpu_set(vector >> 8, tmp); + dest = cpu_mask_to_apicid(tmp); + + high = HT_IRQ_HIGH_DEST_ID(dest); + + low = HT_IRQ_LOW_BASE | + HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_VECTOR(vector) | + ((INT_DEST_MODE == 0) ? + HT_IRQ_LOW_DM_PHYSICAL : + HT_IRQ_LOW_DM_LOGICAL) | + HT_IRQ_LOW_RQEOI_EDGE | + ((INT_DELIVERY_MODE != dest_LowestPrio) ? + HT_IRQ_LOW_MT_FIXED : + HT_IRQ_LOW_MT_ARBITRATED) | + HT_IRQ_LOW_IRQ_MASKED; + + write_ht_irq_low(irq, low); + write_ht_irq_high(irq, high); + + set_irq_chip_and_handler_name(irq, &ht_irq_chip, + handle_edge_irq, "edge"); + } + return vector; +} +#endif /* CONFIG_HT_IRQ */ + /* -------------------------------------------------------------------------- ACPI-based IOAPIC Configuration -------------------------------------------------------------------------- */ @@ -2684,7 +2798,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a ioapic_write_entry(ioapic, pin, entry); spin_lock_irqsave(&ioapic_lock, flags); - set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS); + set_native_irq_info(irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); return 0; diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c index 5fe547cd8f9f..3201d421090a 100644 --- a/arch/i386/kernel/irq.c +++ b/arch/i386/kernel/irq.c @@ -53,8 +53,10 @@ static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly; */ fastcall unsigned int do_IRQ(struct pt_regs *regs) { + struct pt_regs *old_regs; /* high bit used in ret_from_ code */ int irq = ~regs->orig_eax; + struct irq_desc *desc = irq_desc + irq; #ifdef CONFIG_4KSTACKS union irq_ctx *curctx, *irqctx; u32 *isp; @@ -66,6 +68,7 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs) BUG(); } + old_regs = set_irq_regs(regs); irq_enter(); #ifdef CONFIG_DEBUG_STACKOVERFLOW /* Debugging check for stack overflow: is there less than 1KB free? */ @@ -110,19 +113,20 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs) (curctx->tinfo.preempt_count & SOFTIRQ_MASK); asm volatile( - " xchgl %%ebx,%%esp \n" - " call __do_IRQ \n" + " xchgl %%ebx,%%esp \n" + " call *%%edi \n" " movl %%ebx,%%esp \n" : "=a" (arg1), "=d" (arg2), "=b" (ebx) - : "0" (irq), "1" (regs), "2" (isp) - : "memory", "cc", "ecx" + : "0" (irq), "1" (desc), "2" (isp), + "D" (desc->handle_irq) + : "memory", "cc" ); } else #endif - __do_IRQ(irq, regs); + desc->handle_irq(irq, desc); irq_exit(); - + set_irq_regs(old_regs); return 1; } @@ -253,7 +257,8 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(j) seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); #endif - seq_printf(p, " %14s", irq_desc[i].chip->typename); + seq_printf(p, " %8s", irq_desc[i].chip->name); + seq_printf(p, "-%-8s", irq_desc[i].name); seq_printf(p, " %s", action->name); for (action=action->next; action; action = action->next) diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index 9b9479768d5e..c4d0291b519f 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -656,14 +656,18 @@ static struct attribute_group mc_attr_group = { static int mc_sysdev_add(struct sys_device *sys_dev) { - int cpu = sys_dev->id; + int err, cpu = sys_dev->id; struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!cpu_online(cpu)) return 0; + pr_debug("Microcode:CPU %d added\n", cpu); memset(uci, 0, sizeof(*uci)); - sysfs_create_group(&sys_dev->kobj, &mc_attr_group); + + err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group); + if (err) + return err; microcode_init_cpu(cpu); return 0; diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index dad02a960e03..57d375900afb 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -236,20 +236,28 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); * We execute MONITOR against need_resched and enter optimized wait state * through MWAIT. Whenever someone changes need_resched, we would be woken * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. */ -static void mwait_idle(void) +void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { - local_irq_enable(); - - while (!need_resched()) { + if (!need_resched()) { __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); - if (need_resched()) - break; - __mwait(0, 0); + if (!need_resched()) + __mwait(eax, ecx); } } +/* Default MONITOR/MWAIT with no hints, used for default C1 state */ +static void mwait_idle(void) +{ + local_irq_enable(); + while (!need_resched()) + mwait_idle_with_hints(0, 0); +} + void __devinit select_idle_routine(const struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_MWAIT)) { @@ -328,6 +336,7 @@ extern void kernel_thread_helper(void); int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) { struct pt_regs regs; + int err; memset(®s, 0, sizeof(regs)); @@ -342,7 +351,10 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); + err = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); + if (err == 0) /* terminate kernel stack */ + task_pt_regs(current)->eip = 0; + return err; } EXPORT_SYMBOL(kernel_thread); diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 000cf03751fe..519e63c3c130 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -1083,16 +1083,15 @@ static unsigned long __init setup_memory(void) void __init zone_sizes_init(void) { + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM - unsigned long max_zone_pfns[MAX_NR_ZONES] = { - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, - max_low_pfn, - highend_pfn}; + max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; add_active_range(0, 0, highend_pfn); #else - unsigned long max_zone_pfns[MAX_NR_ZONES] = { - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, - max_low_pfn}; add_active_range(0, 0, max_low_pfn); #endif diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c index 1b080ab8a49f..31e5c6573aae 100644 --- a/arch/i386/kernel/smp.c +++ b/arch/i386/kernel/smp.c @@ -321,6 +321,7 @@ static inline void leave_mm (unsigned long cpu) fastcall void smp_invalidate_interrupt(struct pt_regs *regs) { + struct pt_regs *old_regs = set_irq_regs(regs); unsigned long cpu; cpu = get_cpu(); @@ -351,6 +352,7 @@ fastcall void smp_invalidate_interrupt(struct pt_regs *regs) smp_mb__after_clear_bit(); out: put_cpu_no_resched(); + set_irq_regs(old_regs); } static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, @@ -605,11 +607,14 @@ void smp_send_stop(void) */ fastcall void smp_reschedule_interrupt(struct pt_regs *regs) { + struct pt_regs *old_regs = set_irq_regs(regs); ack_APIC_irq(); + set_irq_regs(old_regs); } fastcall void smp_call_function_interrupt(struct pt_regs *regs) { + struct pt_regs *old_regs = set_irq_regs(regs); void (*func) (void *info) = call_data->func; void *info = call_data->info; int wait = call_data->wait; @@ -632,6 +637,7 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs) mb(); atomic_inc(&call_data->finished); } + set_irq_regs(old_regs); } /* diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index 7e639f78b0b9..2697e9210e92 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -318,3 +318,4 @@ ENTRY(sys_call_table) .long sys_vmsplice .long sys_move_pages .long sys_getcpu + .long sys_epoll_pwait diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index 58a2d5582419..78af572fd17c 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -161,7 +161,7 @@ EXPORT_SYMBOL(profile_pc); * Time Stamp Counter value at the time of the timer interrupt, so that * we later on can estimate the time of day more exactly. */ -irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +irqreturn_t timer_interrupt(int irq, void *dev_id) { /* * Here we are in the timer irq handler. We just have irqs locally @@ -188,7 +188,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) } #endif - do_timer_interrupt_hook(regs); + do_timer_interrupt_hook(); if (MCA_bus) { @@ -201,15 +201,15 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) high bit of the PPI port B (0x61). Note that some PS/2s, notably the 55SX, work fine if this is removed. */ - irq = inb_p( 0x61 ); /* read the current state */ - outb_p( irq|0x80, 0x61 ); /* reset the IRQ */ + u8 irq_v = inb_p( 0x61 ); /* read the current state */ + outb_p( irq_v|0x80, 0x61 ); /* reset the IRQ */ } write_sequnlock(&xtime_lock); #ifdef CONFIG_X86_LOCAL_APIC if (using_apic_timer) - smp_send_timer_broadcast_ipi(regs); + smp_send_timer_broadcast_ipi(); #endif return IRQ_HANDLED; diff --git a/arch/i386/kernel/time_hpet.c b/arch/i386/kernel/time_hpet.c index 6bf14a4e995e..1a2a979cf6a3 100644 --- a/arch/i386/kernel/time_hpet.c +++ b/arch/i386/kernel/time_hpet.c @@ -441,7 +441,7 @@ int hpet_rtc_dropped_irq(void) return 1; } -irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs) +irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) { struct rtc_time curr_time; unsigned long rtc_int_flag = 0; @@ -480,7 +480,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs) } if (call_rtc_interrupt) { rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8)); - rtc_interrupt(rtc_int_flag, dev_id, regs); + rtc_interrupt(rtc_int_flag, dev_id); } return IRQ_HANDLED; } diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c index b8fa0a8b2e47..fbc95828cd74 100644 --- a/arch/i386/kernel/tsc.c +++ b/arch/i386/kernel/tsc.c @@ -349,8 +349,8 @@ static int tsc_update_callback(void) int change = 0; /* check to see if we should switch to the safe clocksource: */ - if (clocksource_tsc.rating != 50 && check_tsc_unstable()) { - clocksource_tsc.rating = 50; + if (clocksource_tsc.rating != 0 && check_tsc_unstable()) { + clocksource_tsc.rating = 0; clocksource_reselect(); change = 1; } @@ -461,7 +461,7 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.shift); /* lower the rating if we already know its unstable: */ if (check_tsc_unstable()) - clocksource_tsc.rating = 50; + clocksource_tsc.rating = 0; init_timer(&verify_tsc_freq_timer); verify_tsc_freq_timer.function = verify_tsc_freq; diff --git a/arch/i386/kernel/vm86.c b/arch/i386/kernel/vm86.c index 8355d8d87d18..cbcd61d6120b 100644 --- a/arch/i386/kernel/vm86.c +++ b/arch/i386/kernel/vm86.c @@ -714,7 +714,7 @@ static int irqbits; | (1 << SIGUSR1) | (1 << SIGUSR2) | (1 << SIGIO) | (1 << SIGURG) \ | (1 << SIGUNUSED) ) -static irqreturn_t irq_handler(int intno, void *dev_id, struct pt_regs * regs) +static irqreturn_t irq_handler(int intno, void *dev_id) { int irq_bit; unsigned long flags; |