linux-stable/arch/x86/kernel/apic_64.c

1228 lines
30 KiB
C
Raw Normal View History

/*
* Local APIC handling, local APIC timers
*
* (c) 1999, 2000 Ingo Molnar <mingo@redhat.com>
*
* Fixes
* Maciej W. Rozycki : Bits for genuine 82489DX APICs;
* thanks to Eric Gilmore
* and Rolf G. Tews
* for testing these extensively.
* Maciej W. Rozycki : Various updates and fixes.
* Mikael Pettersson : Power Management for UP-APIC.
* Pavel Machek and
* Mikael Pettersson : PM converted to driver model.
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/bootmem.h>
#include <linux/interrupt.h>
#include <linux/mc146818rtc.h>
#include <linux/kernel_stat.h>
#include <linux/sysdev.h>
#include <linux/module.h>
#include <linux/ioport.h>
#include <linux/clockchips.h>
#include <asm/atomic.h>
#include <asm/smp.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
#include <asm/pgalloc.h>
#include <asm/mach_apic.h>
#include <asm/nmi.h>
#include <asm/idle.h>
#include <asm/proto.h>
#include <asm/timex.h>
#include <asm/hpet.h>
#include <asm/apic.h>
int apic_verbosity;
int disable_apic_timer __cpuinitdata;
static int apic_calibrate_pmtmr __initdata;
/* Local APIC timer works in C2? */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
static struct resource *ioapic_resources;
static struct resource lapic_resource = {
.name = "Local APIC",
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};
static unsigned int calibration_result;
static int lapic_next_event(unsigned long delta,
struct clock_event_device *evt);
static void lapic_timer_setup(enum clock_event_mode mode,
struct clock_event_device *evt);
static void lapic_timer_broadcast(cpumask_t mask);
static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen);
static struct clock_event_device lapic_clockevent = {
.name = "lapic",
.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
.shift = 32,
.set_mode = lapic_timer_setup,
.set_next_event = lapic_next_event,
.broadcast = lapic_timer_broadcast,
.rating = 100,
.irq = -1,
};
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
static int lapic_next_event(unsigned long delta,
struct clock_event_device *evt)
{
apic_write(APIC_TMICT, delta);
return 0;
}
static void lapic_timer_setup(enum clock_event_mode mode,
struct clock_event_device *evt)
{
unsigned long flags;
unsigned int v;
/* Lapic used as dummy for broadcast ? */
if (evt->features & CLOCK_EVT_FEAT_DUMMY)
return;
local_irq_save(flags);
switch (mode) {
case CLOCK_EVT_MODE_PERIODIC:
case CLOCK_EVT_MODE_ONESHOT:
__setup_APIC_LVTT(calibration_result,
mode != CLOCK_EVT_MODE_PERIODIC, 1);
break;
case CLOCK_EVT_MODE_UNUSED:
case CLOCK_EVT_MODE_SHUTDOWN:
v = apic_read(APIC_LVTT);
v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
apic_write(APIC_LVTT, v);
break;
case CLOCK_EVT_MODE_RESUME:
/* Nothing to do here */
break;
}
local_irq_restore(flags);
}
/*
* Local APIC timer broadcast function
*/
static void lapic_timer_broadcast(cpumask_t mask)
{
#ifdef CONFIG_SMP
send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
#endif
}
static void apic_pm_activate(void);
[PATCH] x86-64: safe_apic_wait_icr_idle - x86_64 apic_wait_icr_idle looks like this: static __inline__ void apic_wait_icr_idle(void) { while (apic_read(APIC_ICR) & APIC_ICR_BUSY) cpu_relax(); } The busy loop in this function would not be problematic if the corresponding status bit in the ICR were always updated, but that does not seem to be the case under certain crash scenarios. Kdump uses an IPI to stop the other CPUs in the event of a crash, but when any of the other CPUs are locked-up inside the NMI handler the CPU that sends the IPI will end up looping forever in the ICR check, effectively hard-locking the whole system. Quoting from Intel's "MultiProcessor Specification" (Version 1.4), B-3: "A local APIC unit indicates successful dispatch of an IPI by resetting the Delivery Status bit in the Interrupt Command Register (ICR). The operating system polls the delivery status bit after sending an INIT or STARTUP IPI until the command has been dispatched. A period of 20 microseconds should be sufficient for IPI dispatch to complete under normal operating conditions. If the IPI is not successfully dispatched, the operating system can abort the command. Alternatively, the operating system can retry the IPI by writing the lower 32-bit double word of the ICR. This “time-out” mechanism can be implemented through an external interrupt, if interrupts are enabled on the processor, or through execution of an instruction or time-stamp counter spin loop." Intel's documentation suggests the implementation of a time-out mechanism, which, by the way, is already being open-coded in some parts of the kernel that tinker with ICR. Create a apic_wait_icr_idle replacement that implements the time-out mechanism and that can be used to solve the aforementioned problem. AK: moved both functions out of line AK: Added improved loop from Keith Owens Signed-off-by: Fernando Luis Vazquez Cao <fernando@oss.ntt.co.jp> Signed-off-by: Andi Kleen <ak@suse.de>
2007-05-02 17:27:17 +00:00
void apic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
unsigned int safe_apic_wait_icr_idle(void)
{
unsigned int send_status;
int timeout;
timeout = 0;
do {
send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
if (!send_status)
break;
udelay(100);
} while (timeout++ < 1000);
return send_status;
}
void enable_NMI_through_LVT0 (void * dummy)
{
unsigned int v;
/* unmask and set to NMI */
v = APIC_DM_NMI;
apic_write(APIC_LVT0, v);
}
int get_maxlvt(void)
{
unsigned int v, maxlvt;
v = apic_read(APIC_LVR);
maxlvt = GET_APIC_MAXLVT(v);
return maxlvt;
}
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
* each architecture has to answer this themselves.
*/
void ack_bad_irq(unsigned int irq)
{
printk("unexpected IRQ trap at vector %02x\n", irq);
/*
* Currently unexpected vectors happen only on SMP and APIC.
* We _must_ ack these because every local APIC has only N
* irq slots per priority level, and a 'hanging, unacked' IRQ
* holds up an irq slot - in excessive cases (when multiple
* unexpected vectors occur) that might lock up the APIC
* completely.
* But don't ack when the APIC is disabled. -AK
*/
if (!disable_apic)
ack_APIC_irq();
}
void clear_local_APIC(void)
{
int maxlvt;
unsigned int v;
maxlvt = get_maxlvt();
/*
* Masking an LVT entry can trigger a local APIC error
* if the vector is zero. Mask LVTERR first to prevent this.
*/
if (maxlvt >= 3) {
v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
}
/*
* Careful: we have to set masks only first to deassert
* any level-triggered sources.
*/
v = apic_read(APIC_LVTT);
apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
v = apic_read(APIC_LVT0);
apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
v = apic_read(APIC_LVT1);
apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
if (maxlvt >= 4) {
v = apic_read(APIC_LVTPC);
apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
}
/*
* Clean APIC state for other OSs:
*/
apic_write(APIC_LVTT, APIC_LVT_MASKED);
apic_write(APIC_LVT0, APIC_LVT_MASKED);
apic_write(APIC_LVT1, APIC_LVT_MASKED);
if (maxlvt >= 3)
apic_write(APIC_LVTERR, APIC_LVT_MASKED);
if (maxlvt >= 4)
apic_write(APIC_LVTPC, APIC_LVT_MASKED);
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
void disconnect_bsp_APIC(int virt_wire_setup)
{
/* Go back to Virtual Wire compatibility mode */
unsigned long value;
/* For the spurious interrupt use vector F, and enable it */
value = apic_read(APIC_SPIV);
value &= ~APIC_VECTOR_MASK;
value |= APIC_SPIV_APIC_ENABLED;
value |= 0xf;
apic_write(APIC_SPIV, value);
if (!virt_wire_setup) {
/*
* For LVT0 make it edge triggered, active high,
* external and enabled
*/
value = apic_read(APIC_LVT0);
value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED );
value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
apic_write(APIC_LVT0, value);
} else {
/* Disable LVT0 */
apic_write(APIC_LVT0, APIC_LVT_MASKED);
}
/* For LVT1 make it edge triggered, active high, nmi and enabled */
value = apic_read(APIC_LVT1);
value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
apic_write(APIC_LVT1, value);
}
void disable_local_APIC(void)
{
unsigned int value;
clear_local_APIC();
/*
* Disable APIC (implies clearing of registers
* for 82489DX!).
*/
value = apic_read(APIC_SPIV);
value &= ~APIC_SPIV_APIC_ENABLED;
apic_write(APIC_SPIV, value);
}
/*
* This is to verify that we're looking at a real local APIC.
* Check these against your board if the CPUs aren't getting
* started for no apparent reason.
*/
int __init verify_local_APIC(void)
{
unsigned int reg0, reg1;
/*
* The version register is read-only in a real APIC.
*/
reg0 = apic_read(APIC_LVR);
apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
reg1 = apic_read(APIC_LVR);
apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);
/*
* The two version reads above should print the same
* numbers. If the second one is different, then we
* poke at a non-APIC.
*/
if (reg1 != reg0)
return 0;
/*
* Check if the version looks reasonably.
*/
reg1 = GET_APIC_VERSION(reg0);
if (reg1 == 0x00 || reg1 == 0xff)
return 0;
reg1 = get_maxlvt();
if (reg1 < 0x02 || reg1 == 0xff)
return 0;
/*
* The ID register is read/write in a real APIC.
*/
reg0 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
reg1 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
apic_write(APIC_ID, reg0);
if (reg1 != (reg0 ^ APIC_ID_MASK))
return 0;
/*
* The next two are just to see if we have sane values.
* They're only really relevant if we're in Virtual Wire
* compatibility mode, but most boxes are anymore.
*/
reg0 = apic_read(APIC_LVT0);
apic_printk(APIC_DEBUG,"Getting LVT0: %x\n", reg0);
reg1 = apic_read(APIC_LVT1);
apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1);
return 1;
}
void __init sync_Arb_IDs(void)
{
/* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
if (ver >= 0x14) /* P4 or higher */
return;
/*
* Wait for idle.
*/
apic_wait_icr_idle();
apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
apic_write(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
| APIC_DM_INIT);
}
/*
* An initial setup of the virtual wire mode.
*/
void __init init_bsp_APIC(void)
{
unsigned int value;
/*
* Don't do the setup now if we have a SMP BIOS as the
* through-I/O-APIC virtual wire mode might be active.
*/
if (smp_found_config || !cpu_has_apic)
return;
value = apic_read(APIC_LVR);
/*
* Do not trust the local APIC being empty at bootup.
*/
clear_local_APIC();
/*
* Enable APIC.
*/
value = apic_read(APIC_SPIV);
value &= ~APIC_VECTOR_MASK;
value |= APIC_SPIV_APIC_ENABLED;
value |= APIC_SPIV_FOCUS_DISABLED;
value |= SPURIOUS_APIC_VECTOR;
apic_write(APIC_SPIV, value);
/*
* Set up the virtual wire mode.
*/
apic_write(APIC_LVT0, APIC_DM_EXTINT);
value = APIC_DM_NMI;
apic_write(APIC_LVT1, value);
}
void __cpuinit setup_local_APIC (void)
{
unsigned int value, maxlvt;
int i, j;
value = apic_read(APIC_LVR);
BUILD_BUG_ON((SPURIOUS_APIC_VECTOR & 0x0f) != 0x0f);
/*
* Double-check whether this APIC is really registered.
* This is meaningless in clustered apic mode, so we skip it.
*/
if (!apic_id_registered())
BUG();
/*
* Intel recommends to set DFR, LDR and TPR before enabling
* an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
* document number 292116). So here it goes...
*/
init_apic_ldr();
/*
* Set Task Priority to 'accept all'. We never change this
* later on.
*/
value = apic_read(APIC_TASKPRI);
value &= ~APIC_TPRI_MASK;
apic_write(APIC_TASKPRI, value);
/*
* After a crash, we no longer service the interrupts and a pending
* interrupt from previous kernel might still have ISR bit set.
*
* Most probably by now CPU has serviced that pending interrupt and
* it might not have done the ack_APIC_irq() because it thought,
* interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it
* does not clear the ISR bit and cpu thinks it has already serivced
* the interrupt. Hence a vector might get locked. It was noticed
* for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
*/
for (i = APIC_ISR_NR - 1; i >= 0; i--) {
value = apic_read(APIC_ISR + i*0x10);
for (j = 31; j >= 0; j--) {
if (value & (1<<j))
ack_APIC_irq();
}
}
/*
* Now that we are all set up, enable the APIC
*/
value = apic_read(APIC_SPIV);
value &= ~APIC_VECTOR_MASK;
/*
* Enable APIC
*/
value |= APIC_SPIV_APIC_ENABLED;
/* We always use processor focus */
/*
* Set spurious IRQ vector
*/
value |= SPURIOUS_APIC_VECTOR;
apic_write(APIC_SPIV, value);
/*
* Set up LVT0, LVT1:
*
* set up through-local-APIC on the BP's LINT0. This is not
* strictly necessary in pure symmetric-IO mode, but sometimes
* we delegate interrupts to the 8259A.
*/
/*
* TODO: set up through-local-APIC from through-I/O-APIC? --macro
*/
value = apic_read(APIC_LVT0) & APIC_LVT_MASKED;
if (!smp_processor_id() && !value) {
value = APIC_DM_EXTINT;
apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n",
smp_processor_id());
} else {
value = APIC_DM_EXTINT | APIC_LVT_MASKED;
apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n",
smp_processor_id());
}
apic_write(APIC_LVT0, value);
/*
* only the BP should see the LINT1 NMI signal, obviously.
*/
if (!smp_processor_id())
value = APIC_DM_NMI;
else
value = APIC_DM_NMI | APIC_LVT_MASKED;
apic_write(APIC_LVT1, value);
{
unsigned oldvalue;
maxlvt = get_maxlvt();
oldvalue = apic_read(APIC_ESR);
value = ERROR_APIC_VECTOR; // enables sending errors
apic_write(APIC_LVTERR, value);
/*
* spec says clear errors after enabling vector.
*/
if (maxlvt > 3)
apic_write(APIC_ESR, 0);
value = apic_read(APIC_ESR);
if (value != oldvalue)
apic_printk(APIC_VERBOSE,
"ESR value after enabling vector: %08x, after %08x\n",
oldvalue, value);
}
nmi_watchdog_default();
setup_apic_nmi_watchdog(NULL);
apic_pm_activate();
}
#ifdef CONFIG_PM
static struct {
/* 'active' is true if the local APIC was enabled by us and
not the BIOS; this signifies that we are also responsible
for disabling it before entering apm/acpi suspend */
int active;
/* r/w apic fields */
unsigned int apic_id;
unsigned int apic_taskpri;
unsigned int apic_ldr;
unsigned int apic_dfr;
unsigned int apic_spiv;
unsigned int apic_lvtt;
unsigned int apic_lvtpc;
unsigned int apic_lvt0;
unsigned int apic_lvt1;
unsigned int apic_lvterr;
unsigned int apic_tmict;
unsigned int apic_tdcr;
unsigned int apic_thmr;
} apic_pm_state;
static int lapic_suspend(struct sys_device *dev, pm_message_t state)
{
unsigned long flags;
int maxlvt;
if (!apic_pm_state.active)
return 0;
maxlvt = get_maxlvt();
apic_pm_state.apic_id = apic_read(APIC_ID);
apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
apic_pm_state.apic_ldr = apic_read(APIC_LDR);
apic_pm_state.apic_dfr = apic_read(APIC_DFR);
apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
if (maxlvt >= 4)
apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
#ifdef CONFIG_X86_MCE_INTEL
if (maxlvt >= 5)
apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
#endif
local_irq_save(flags);
disable_local_APIC();
local_irq_restore(flags);
return 0;
}
static int lapic_resume(struct sys_device *dev)
{
unsigned int l, h;
unsigned long flags;
int maxlvt;
if (!apic_pm_state.active)
return 0;
maxlvt = get_maxlvt();
local_irq_save(flags);
rdmsr(MSR_IA32_APICBASE, l, h);
l &= ~MSR_IA32_APICBASE_BASE;
l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
wrmsr(MSR_IA32_APICBASE, l, h);
apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
apic_write(APIC_ID, apic_pm_state.apic_id);
apic_write(APIC_DFR, apic_pm_state.apic_dfr);
apic_write(APIC_LDR, apic_pm_state.apic_ldr);
apic_write(APIC_TASKPRI, apic_pm_state.apic_taskpri);
apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
#ifdef CONFIG_X86_MCE_INTEL
if (maxlvt >= 5)
apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
#endif
if (maxlvt >= 4)
apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
apic_write(APIC_TMICT, apic_pm_state.apic_tmict);
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
local_irq_restore(flags);
return 0;
}
static struct sysdev_class lapic_sysclass = {
set_kset_name("lapic"),
.resume = lapic_resume,
.suspend = lapic_suspend,
};
static struct sys_device device_lapic = {
.id = 0,
.cls = &lapic_sysclass,
};
static void __cpuinit apic_pm_activate(void)
{
apic_pm_state.active = 1;
}
static int __init init_lapic_sysfs(void)
{
int error;
if (!cpu_has_apic)
return 0;
/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
error = sysdev_class_register(&lapic_sysclass);
if (!error)
error = sysdev_register(&device_lapic);
return error;
}
device_initcall(init_lapic_sysfs);
#else /* CONFIG_PM */
static void apic_pm_activate(void) { }
#endif /* CONFIG_PM */
static int __init apic_set_verbosity(char *str)
{
if (str == NULL) {
skip_ioapic_setup = 0;
ioapic_force = 1;
return 0;
}
if (strcmp("debug", str) == 0)
apic_verbosity = APIC_DEBUG;
else if (strcmp("verbose", str) == 0)
apic_verbosity = APIC_VERBOSE;
else {
printk(KERN_WARNING "APIC Verbosity level %s not recognised"
" use apic=verbose or apic=debug\n", str);
return -EINVAL;
}
return 0;
}
early_param("apic", apic_set_verbosity);
/*
* Detect and enable local APICs on non-SMP boards.
* Original code written by Keir Fraser.
* On AMD64 we trust the BIOS - if it says no APIC it is likely
* not correctly set up (usually the APIC timer won't work etc.)
*/
static int __init detect_init_APIC (void)
{
if (!cpu_has_apic) {
printk(KERN_INFO "No local APIC present\n");
return -1;
}
mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
boot_cpu_id = 0;
return 0;
}
#ifdef CONFIG_X86_IO_APIC
static struct resource * __init ioapic_setup_resources(void)
{
#define IOAPIC_RESOURCE_NAME_SIZE 11
unsigned long n;
struct resource *res;
char *mem;
int i;
if (nr_ioapics <= 0)
return NULL;
n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
n *= nr_ioapics;
mem = alloc_bootmem(n);
res = (void *)mem;
if (mem != NULL) {
memset(mem, 0, n);
mem += sizeof(struct resource) * nr_ioapics;
for (i = 0; i < nr_ioapics; i++) {
res[i].name = mem;
res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
sprintf(mem, "IOAPIC %u", i);
mem += IOAPIC_RESOURCE_NAME_SIZE;
}
}
ioapic_resources = res;
return res;
}
static int __init ioapic_insert_resources(void)
{
int i;
struct resource *r = ioapic_resources;
if (!r) {
printk("IO APIC resources could be not be allocated.\n");
return -1;
}
for (i = 0; i < nr_ioapics; i++) {
insert_resource(&iomem_resource, r);
r++;
}
return 0;
}
/* Insert the IO APIC resources after PCI initialization has occured to handle
* IO APICS that are mapped in on a BAR in PCI space. */
late_initcall(ioapic_insert_resources);
#endif
void __init init_apic_mappings(void)
{
unsigned long apic_phys;
/*
* If no local APIC can be found then set up a fake all
* zeroes page to simulate the local APIC and another
* one for the IO-APIC.
*/
if (!smp_found_config && detect_init_APIC()) {
apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
apic_phys = __pa(apic_phys);
} else
apic_phys = mp_lapic_addr;
set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
APIC_BASE, apic_phys);
/* Put local APIC into the resource map. */
lapic_resource.start = apic_phys;
lapic_resource.end = lapic_resource.start + PAGE_SIZE - 1;
insert_resource(&iomem_resource, &lapic_resource);
/*
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID));
{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
int i;
struct resource *ioapic_res;
ioapic_res = ioapic_setup_resources();
for (i = 0; i < nr_ioapics; i++) {
if (smp_found_config) {
ioapic_phys = mp_ioapics[i].mpc_apicaddr;
} else {
ioapic_phys = (unsigned long)
alloc_bootmem_pages(PAGE_SIZE);
ioapic_phys = __pa(ioapic_phys);
}
set_fixmap_nocache(idx, ioapic_phys);
apic_printk(APIC_VERBOSE,
"mapped IOAPIC to %016lx (%016lx)\n",
__fix_to_virt(idx), ioapic_phys);
idx++;
if (ioapic_res != NULL) {
ioapic_res->start = ioapic_phys;
ioapic_res->end = ioapic_phys + (4 * 1024) - 1;
ioapic_res++;
}
}
}
}
/*
* This function sets up the local APIC timer, with a timeout of
* 'clocks' APIC bus clock. During calibration we actually call
* this function twice on the boot CPU, once with a bogus timeout
* value, second time for real. The other (noncalibrating) CPUs
* call this function only once, with the real, calibrated value.
*
* We do reads before writes even if unnecessary, to get around the
* P5 APIC double write bug.
*/
static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
{
unsigned int lvtt_value, tmp_value;
lvtt_value = LOCAL_TIMER_VECTOR;
if (!oneshot)
lvtt_value |= APIC_LVT_TIMER_PERIODIC;
if (!irqen)
lvtt_value |= APIC_LVT_MASKED;
apic_write(APIC_LVTT, lvtt_value);
/*
* Divide PICLK by 16
*/
tmp_value = apic_read(APIC_TDCR);
apic_write(APIC_TDCR, (tmp_value
& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
| APIC_TDR_DIV_16);
if (!oneshot)
apic_write(APIC_TMICT, clocks);
}
static void setup_APIC_timer(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
memcpy(levt, &lapic_clockevent, sizeof(*levt));
levt->cpumask = cpumask_of_cpu(smp_processor_id());
clockevents_register_device(levt);
}
/*
* In this function we calibrate APIC bus clocks to the external
* timer. Unfortunately we cannot use jiffies and the timer irq
* to calibrate, since some later bootup code depends on getting
* the first irq? Ugh.
*
* We want to do the calibration only once since we
* want to have local timer irqs syncron. CPUs connected
* by the same APIC bus have the very same bus frequency.
* And we want to have irqs off anyways, no accidental
* APIC irq that way.
*/
#define TICK_COUNT 100000000
static void __init calibrate_APIC_clock(void)
{
unsigned apic, apic_start;
unsigned long tsc, tsc_start;
int result;
local_irq_disable();
/*
* Put whatever arbitrary (but long enough) timeout
* value into the APIC clock, we just want to get the
* counter running for calibration.
*
* No interrupt enable !
*/
__setup_APIC_LVTT(250000000, 0, 0);
apic_start = apic_read(APIC_TMCCT);
#ifdef CONFIG_X86_PM_TIMER
if (apic_calibrate_pmtmr && pmtmr_ioport) {
pmtimer_wait(5000); /* 5ms wait */
apic = apic_read(APIC_TMCCT);
result = (apic_start - apic) * 1000L / 5;
} else
#endif
{
rdtscll(tsc_start);
do {
apic = apic_read(APIC_TMCCT);
rdtscll(tsc);
} while ((tsc - tsc_start) < TICK_COUNT &&
(apic_start - apic) < TICK_COUNT);
result = (apic_start - apic) * 1000L * tsc_khz /
(tsc - tsc_start);
}
local_irq_enable();
printk(KERN_DEBUG "APIC timer calibration result %d\n", result);
printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
result / 1000 / 1000, result / 1000 % 1000);
/* Calculate the scaled math multiplication factor */
lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
calibration_result = result / HZ;
}
void __init setup_boot_APIC_clock (void)
{
/*
* The local apic timer can be disabled via the kernel commandline.
* Register the lapic timer as a dummy clock event source on SMP
* systems, so the broadcast mechanism is used. On UP systems simply
* ignore it.
*/
if (disable_apic_timer) {
printk(KERN_INFO "Disabling APIC timer\n");
/* No broadcast on UP ! */
if (num_possible_cpus() > 1)
setup_APIC_timer();
return;
}
printk(KERN_INFO "Using local APIC timer interrupts.\n");
calibrate_APIC_clock();
/*
* If nmi_watchdog is set to IO_APIC, we need the
* PIT/HPET going. Otherwise register lapic as a dummy
* device.
*/
if (nmi_watchdog != NMI_IO_APIC)
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
else
printk(KERN_WARNING "APIC timer registered as dummy,"
" due to nmi_watchdog=1!\n");
setup_APIC_timer();
}
void __cpuinit setup_secondary_APIC_clock(void)
{
setup_APIC_timer();
}
int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
unsigned char msg_type, unsigned char mask)
{
unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
unsigned int v = (mask << 16) | (msg_type << 8) | vector;
apic_write(reg, v);
}
/*
* Local timer interrupt handler. It does both profiling and
* process statistics/rescheduling.
*
* We do profiling in every local tick, statistics/rescheduling
* happen only every 'profiling multiplier' ticks. The default
* multiplier is 1 and it can be changed by writing the new multiplier
* value into /proc/profile.
*/
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 13:55:46 +00:00
void smp_local_timer_interrupt(void)
{
int cpu = smp_processor_id();
struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
/*
* Normally we should not be here till LAPIC has been initialized but
* in some cases like kdump, its possible that there is a pending LAPIC
* timer interrupt from previous kernel's context and is delivered in
* new kernel the moment interrupts are enabled.
*
* Interrupts are enabled early and LAPIC is setup much later, hence
* its possible that when we get here evt->event_handler is NULL.
* Check for event_handler being NULL and discard the interrupt as
* spurious.
*/
if (!evt->event_handler) {
printk(KERN_WARNING
"Spurious LAPIC timer interrupt on cpu %d\n", cpu);
/* Switch it off */
lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
return;
}
/*
* the NMI deadlock-detector uses this.
*/
add_pda(apic_timer_irqs, 1);
evt->event_handler(evt);
}
/*
* Local APIC timer interrupt. This is the most natural way for doing
* local interrupts, but local timer interrupts can be emulated by
* broadcast interrupts too. [in case the hw doesn't support APIC timers]
*
* [ if a single-CPU system runs an SMP kernel then we call the local
* interrupt as well. Thus we cannot inline the local irq ... ]
*/
void smp_apic_timer_interrupt(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
/*
* NOTE! We'd better ACK the irq immediately,
* because timer handling can be slow.
*/
ack_APIC_irq();
/*
* update_process_times() expects us to have done irq_enter().
* Besides, if we don't timer interrupts ignore the global
* interrupt lock, which is the WrongThing (tm) to do.
*/
exit_idle();
irq_enter();
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 13:55:46 +00:00
smp_local_timer_interrupt();
irq_exit();
set_irq_regs(old_regs);
}
/*
* apic_is_clustered_box() -- Check if we can expect good TSC
*
* Thus far, the major user of this is IBM's Summit2 series:
*
* Clustered boxes may have unsynced TSC problems if they are
* multi-chassis. Use available data to take a good guess.
* If in doubt, go HPET.
*/
__cpuinit int apic_is_clustered_box(void)
{
int i, clusters, zeros;
unsigned id;
DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
for (i = 0; i < NR_CPUS; i++) {
id = bios_cpu_apicid[i];
if (id != BAD_APICID)
__set_bit(APIC_CLUSTERID(id), clustermap);
}
/* Problem: Partially populated chassis may not have CPUs in some of
* the APIC clusters they have been allocated. Only present CPUs have
* bios_cpu_apicid entries, thus causing zeroes in the bitmap. Since
* clusters are allocated sequentially, count zeros only if they are
* bounded by ones.
*/
clusters = 0;
zeros = 0;
for (i = 0; i < NUM_APIC_CLUSTERS; i++) {
if (test_bit(i, clustermap)) {
clusters += 1 + zeros;
zeros = 0;
} else
++zeros;
}
/*
* If clusters > 2, then should be multi-chassis.
* May have to revisit this when multi-core + hyperthreaded CPUs come
* out, but AFAIK this will work even for them.
*/
return (clusters > 2);
}
/*
* This interrupt should _never_ happen with our APIC/SMP architecture
*/
asmlinkage void smp_spurious_interrupt(void)
{
unsigned int v;
exit_idle();
irq_enter();
/*
* Check if this really is a spurious interrupt and ACK it
* if it is a vectored one. Just in case...
* Spurious interrupts should not be ACKed.
*/
v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
ack_APIC_irq();
irq_exit();
}
/*
* This interrupt should never happen with our APIC/SMP architecture
*/
asmlinkage void smp_error_interrupt(void)
{
unsigned int v, v1;
exit_idle();
irq_enter();
/* First tickle the hardware, only then report what went on. -- REW */
v = apic_read(APIC_ESR);
apic_write(APIC_ESR, 0);
v1 = apic_read(APIC_ESR);
ack_APIC_irq();
atomic_inc(&irq_err_count);
/* Here is what the APIC error bits mean:
0: Send CS error
1: Receive CS error
2: Send accept error
3: Receive accept error
4: Reserved
5: Send illegal vector
6: Received illegal vector
7: Illegal register address
*/
printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
smp_processor_id(), v , v1);
irq_exit();
}
int disable_apic;
/*
* This initializes the IO-APIC and APIC hardware if this is
* a UP kernel.
*/
int __init APIC_init_uniprocessor (void)
{
if (disable_apic) {
printk(KERN_INFO "Apic disabled\n");
return -1;
}
if (!cpu_has_apic) {
disable_apic = 1;
printk(KERN_INFO "Apic disabled by BIOS\n");
return -1;
}
verify_local_APIC();
phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id));
setup_local_APIC();
if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
setup_IO_APIC();
else
nr_ioapics = 0;
setup_boot_APIC_clock();
check_nmi_watchdog();
return 0;
}
static __init int setup_disableapic(char *str)
{
disable_apic = 1;
clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
return 0;
}
early_param("disableapic", setup_disableapic);
/* same as disableapic, for compatibility */
static __init int setup_nolapic(char *str)
{
return setup_disableapic(str);
}
early_param("nolapic", setup_nolapic);
static int __init parse_lapic_timer_c2_ok(char *arg)
{
local_apic_timer_c2_ok = 1;
return 0;
}
early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
static __init int setup_noapictimer(char *str)
{
if (str[0] != ' ' && str[0] != 0)
return 0;
disable_apic_timer = 1;
return 1;
}
__setup("noapictimer", setup_noapictimer);
static __init int setup_apicpmtimer(char *s)
{
apic_calibrate_pmtmr = 1;
notsc_setup(NULL);
return 0;
}
__setup("apicpmtimer", setup_apicpmtimer);