linux/arch/x86/kernel/apic/apic.c

2338 lines
55 KiB
C
Raw Normal View History

/*
* Local APIC handling, local APIC timers
*
* (c) 1999, 2000, 2009 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.
*/
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
#include <linux/perf_event.h>
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/acpi_pmtmr.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
#include <linux/bootmem.h>
#include <linux/ftrace.h>
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/sysdev.h>
#include <linux/delay.h>
#include <linux/timex.h>
#include <linux/dmar.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/dmi.h>
#include <linux/nmi.h>
#include <linux/smp.h>
#include <linux/mm.h>
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
#include <asm/perf_event.h>
#include <asm/x86_init.h>
#include <asm/pgalloc.h>
#include <asm/atomic.h>
#include <asm/mpspec.h>
#include <asm/i8253.h>
#include <asm/i8259.h>
#include <asm/proto.h>
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/idle.h>
#include <asm/mtrr.h>
#include <asm/smp.h>
#include <asm/mce.h>
#include <asm/kvm_para.h>
unsigned int num_processors;
unsigned disabled_cpus __cpuinitdata;
/* Processor that is doing the boot up */
unsigned int boot_cpu_physical_apicid = -1U;
/*
* The highest APIC ID seen during enumeration.
*
* This determines the messaging protocol we can use: if all APIC IDs
* are in the 0 ... 7 range, then we can use logical addressing which
* has some performance advantages (better broadcasting).
*
* If there's an APIC ID above 8, we use physical addressing.
*/
unsigned int max_physical_apicid;
/*
* Bitmask of physically existing CPUs:
*/
physid_mask_t phys_cpu_present_map;
/*
* Map cpu index to physical APIC ID
*/
DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
#ifdef CONFIG_X86_32
/*
* Knob to control our willingness to enable the local APIC.
*
* +1=force-enable
*/
static int force_enable_local_apic;
/*
* APIC command line parameters
*/
static int __init parse_lapic(char *arg)
{
force_enable_local_apic = 1;
return 0;
}
early_param("lapic", parse_lapic);
/* Local APIC was disabled by the BIOS and enabled by the kernel */
static int enabled_via_apicbase;
/*
* Handle interrupt mode configuration register (IMCR).
* This register controls whether the interrupt signals
* that reach the BSP come from the master PIC or from the
* local APIC. Before entering Symmetric I/O Mode, either
* the BIOS or the operating system must switch out of
* PIC Mode by changing the IMCR.
*/
static inline void imcr_pic_to_apic(void)
{
/* select IMCR register */
outb(0x70, 0x22);
/* NMI and 8259 INTR go through APIC */
outb(0x01, 0x23);
}
static inline void imcr_apic_to_pic(void)
{
/* select IMCR register */
outb(0x70, 0x22);
/* NMI and 8259 INTR go directly to BSP */
outb(0x00, 0x23);
}
#endif
#ifdef CONFIG_X86_64
static int apic_calibrate_pmtmr __initdata;
static __init int setup_apicpmtimer(char *s)
{
apic_calibrate_pmtmr = 1;
notsc_setup(NULL);
return 0;
}
__setup("apicpmtimer", setup_apicpmtimer);
#endif
int x2apic_mode;
#ifdef CONFIG_X86_X2APIC
/* x2apic enabled before OS handover */
static int x2apic_preenabled;
static __init int setup_nox2apic(char *str)
{
if (x2apic_enabled()) {
pr_warning("Bios already enabled x2apic, "
"can't enforce nox2apic");
return 0;
}
setup_clear_cpu_cap(X86_FEATURE_X2APIC);
return 0;
}
early_param("nox2apic", setup_nox2apic);
#endif
unsigned long mp_lapic_addr;
int disable_apic;
/* Disable local APIC timer from the kernel commandline or via dmi quirk */
static int disable_apic_timer __cpuinitdata;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
int first_system_vector = 0xfe;
/*
* Debug level, exported for io_apic.c
*/
unsigned int apic_verbosity;
int pic_mode;
2008-05-19 23:47:03 +08:00
/* Have we found an MP table */
int smp_found_config;
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(const struct cpumask *mask);
static void apic_pm_activate(void);
/*
* The local apic timer can be used for any function which is CPU local.
*/
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 unsigned long apic_phys;
/*
* Get the LAPIC version
*/
static inline int lapic_get_version(void)
{
return GET_APIC_VERSION(apic_read(APIC_LVR));
}
/*
* Check, if the APIC is integrated or a separate chip
*/
static inline int lapic_is_integrated(void)
{
#ifdef CONFIG_X86_64
return 1;
#else
return APIC_INTEGRATED(lapic_get_version());
#endif
}
/*
* Check, whether this is a modern or a first generation APIC
*/
static int modern_apic(void)
{
/* AMD systems use old APIC versions, so check the CPU */
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 >= 0xf)
return 1;
return lapic_get_version() >= 0x14;
}
/*
* right after this call apic become NOOP driven
* so apic->write/read doesn't do anything
*/
void apic_disable(void)
{
pr_info("APIC: switched to apic NOOP\n");
apic = &apic_noop;
}
void native_apic_wait_icr_idle(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>
2007-05-03 01:27:17 +08:00
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
u32 native_safe_apic_wait_icr_idle(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>
2007-05-03 01:27:17 +08:00
{
u32 send_status;
[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>
2007-05-03 01:27:17 +08:00
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 native_apic_icr_write(u32 low, u32 id)
{
apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
apic_write(APIC_ICR, low);
}
u64 native_apic_icr_read(void)
{
u32 icr1, icr2;
icr2 = apic_read(APIC_ICR2);
icr1 = apic_read(APIC_ICR);
return icr1 | ((u64)icr2 << 32);
}
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
void __cpuinit enable_NMI_through_LVT0(void)
{
unsigned int v;
/* unmask and set to NMI */
v = APIC_DM_NMI;
/* Level triggered for 82489DX (32bit mode) */
if (!lapic_is_integrated())
v |= APIC_LVT_LEVEL_TRIGGER;
apic_write(APIC_LVT0, v);
}
#ifdef CONFIG_X86_32
/**
* get_physical_broadcast - Get number of physical broadcast IDs
*/
int get_physical_broadcast(void)
{
return modern_apic() ? 0xff : 0xf;
}
#endif
/**
* lapic_get_maxlvt - get the maximum number of local vector table entries
*/
int lapic_get_maxlvt(void)
{
unsigned int v;
v = apic_read(APIC_LVR);
/*
* - we always have APIC integrated on 64bit mode
* - 82489DXs do not report # of LVT entries
*/
return APIC_INTEGRATED(GET_APIC_VERSION(v)) ? GET_APIC_MAXLVT(v) : 2;
}
/*
* Local APIC timer
*/
/* Clock divisor */
#define APIC_DIVISOR 16
/*
* 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 (!lapic_is_integrated())
lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
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 / APIC_DIVISOR);
}
/*
* Setup extended LVT, AMD specific (K8, family 10h)
*
* Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
* MCE interrupts are supported. Thus MCE offset must be set to 0.
*
* If mask=1, the LVT entry does not generate interrupts while mask=0
* enables the vector. See also the BKDGs.
*/
#define APIC_EILVT_LVTOFF_MCE 0
#define APIC_EILVT_LVTOFF_IBS 1
static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
{
unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
unsigned int v = (mask << 16) | (msg_type << 8) | vector;
apic_write(reg, v);
}
u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
{
setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
return APIC_EILVT_LVTOFF_MCE;
}
u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
{
setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
return APIC_EILVT_LVTOFF_IBS;
}
EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
/*
* Program the next event, relative to now
*/
static int lapic_next_event(unsigned long delta,
struct clock_event_device *evt)
{
apic_write(APIC_TMICT, delta);
return 0;
}
/*
* Setup the lapic timer in periodic or oneshot mode
*/
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);
apic_write(APIC_TMICT, 0);
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(const struct cpumask *mask)
{
#ifdef CONFIG_SMP
apic->send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
#endif
}
/*
* Setup the local APIC timer for this CPU. Copy the initilized values
* of the boot CPU and register the clock event in the framework.
*/
static void __cpuinit setup_APIC_timer(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
if (cpu_has(&current_cpu_data, X86_FEATURE_ARAT)) {
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
/* Make LAPIC timer preferrable over percpu HPET */
lapic_clockevent.rating = 150;
}
memcpy(levt, &lapic_clockevent, sizeof(*levt));
levt->cpumask = cpumask_of(smp_processor_id());
clockevents_register_device(levt);
}
/*
* In this functions we calibrate APIC bus clocks to the external timer.
*
* 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.
*
* This was previously done by reading the PIT/HPET and waiting for a wrap
* around to find out, that a tick has elapsed. I have a box, where the PIT
* readout is broken, so it never gets out of the wait loop again. This was
* also reported by others.
*
* Monitoring the jiffies value is inaccurate and the clockevents
* infrastructure allows us to do a simple substitution of the interrupt
* handler.
*
* The calibration routine also uses the pm_timer when possible, as the PIT
* happens to run way too slow (factor 2.3 on my VAIO CoreDuo, which goes
* back to normal later in the boot process).
*/
#define LAPIC_CAL_LOOPS (HZ/10)
static __initdata int lapic_cal_loops = -1;
static __initdata long lapic_cal_t1, lapic_cal_t2;
static __initdata unsigned long long lapic_cal_tsc1, lapic_cal_tsc2;
static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
/*
* Temporary interrupt handler.
*/
static void __init lapic_cal_handler(struct clock_event_device *dev)
{
unsigned long long tsc = 0;
long tapic = apic_read(APIC_TMCCT);
unsigned long pm = acpi_pm_read_early();
if (cpu_has_tsc)
rdtscll(tsc);
switch (lapic_cal_loops++) {
case 0:
lapic_cal_t1 = tapic;
lapic_cal_tsc1 = tsc;
lapic_cal_pm1 = pm;
lapic_cal_j1 = jiffies;
break;
case LAPIC_CAL_LOOPS:
lapic_cal_t2 = tapic;
lapic_cal_tsc2 = tsc;
if (pm < lapic_cal_pm1)
pm += ACPI_PM_OVRRUN;
lapic_cal_pm2 = pm;
lapic_cal_j2 = jiffies;
break;
}
}
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
static int __init
calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
{
const long pm_100ms = PMTMR_TICKS_PER_SEC / 10;
const long pm_thresh = pm_100ms / 100;
unsigned long mult;
u64 res;
#ifndef CONFIG_X86_PM_TIMER
return -1;
#endif
apic_printk(APIC_VERBOSE, "... PM-Timer delta = %ld\n", deltapm);
/* Check, if the PM timer is available */
if (!deltapm)
return -1;
mult = clocksource_hz2mult(PMTMR_TICKS_PER_SEC, 22);
if (deltapm > (pm_100ms - pm_thresh) &&
deltapm < (pm_100ms + pm_thresh)) {
apic_printk(APIC_VERBOSE, "... PM-Timer result ok\n");
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
return 0;
}
res = (((u64)deltapm) * mult) >> 22;
do_div(res, 1000000);
pr_warning("APIC calibration not consistent "
"with PM-Timer: %ldms instead of 100ms\n",(long)res);
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
/* Correct the lapic counter value */
res = (((u64)(*delta)) * pm_100ms);
do_div(res, deltapm);
pr_info("APIC delta adjusted to PM-Timer: "
"%lu (%ld)\n", (unsigned long)res, *delta);
*delta = (long)res;
/* Correct the tsc counter value */
if (cpu_has_tsc) {
res = (((u64)(*deltatsc)) * pm_100ms);
do_div(res, deltapm);
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
apic_printk(APIC_VERBOSE, "TSC delta adjusted to "
"PM-Timer: %lu (%ld) \n",
(unsigned long)res, *deltatsc);
*deltatsc = (long)res;
}
return 0;
}
static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
void (*real_handler)(struct clock_event_device *dev);
unsigned long deltaj;
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
long delta, deltatsc;
int pm_referenced = 0;
local_irq_disable();
/* Replace the global interrupt handler */
real_handler = global_clock_event->event_handler;
global_clock_event->event_handler = lapic_cal_handler;
/*
* Setup the APIC counter to maximum. There is no way the lapic
* can underflow in the 100ms detection time frame
*/
__setup_APIC_LVTT(0xffffffff, 0, 0);
/* Let the interrupts run */
local_irq_enable();
while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
cpu_relax();
local_irq_disable();
/* Restore the real event handler */
global_clock_event->event_handler = real_handler;
/* Build delta t1-t2 as apic timer counts down */
delta = lapic_cal_t1 - lapic_cal_t2;
apic_printk(APIC_VERBOSE, "... lapic delta = %ld\n", delta);
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
deltatsc = (long)(lapic_cal_tsc2 - lapic_cal_tsc1);
/* we trust the PM based calibration if possible */
pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
&delta, &deltatsc);
/* Calculate the scaled math multiplication factor */
lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
calibration_result);
if (cpu_has_tsc) {
apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
"%ld.%04ld MHz.\n",
x86: fix debug message of CPU clock speed Impact: Fixes incorrect printk LOCAL APIC is corrected by PM-Timer, when SMI occurred while LOCAL APIC is calibrated. In this case, LOCAL APIC debug message(Boot with apic=debug) is displayed correctly, however, CPU clock speed debug message is displayed wrongly . When SMI occured on my machine, which has 1.6GHz CPU, CPU clock speed is displayed 3622.0205 MHz as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773130 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773130) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 3622.0205 MHz. =====> here ..... host bus clock speed is 265.0987 MHz. This patch fixes to displaying CPU clock speed correctly as follow. CPU0: Intel(R) Xeon(R) CPU 5110 @ 1.60GHz stepping 06 Using local APIC timer interrupts. calibrating APIC timer ... ... lapic delta = 3773131 ... PM timer delta = 812434 APIC calibration not consistent with PM Timer: 226ms instead of 100ms APIC delta adjusted to PM-Timer: 1662420 (3773131) TSC delta adjusted to PM-Timer: 159592409 (362220564) ..... delta 1662420 ..... mult: 71411249 ..... calibration result: 265987 ..... CPU clock speed is 1595.0924 MHz. ..... host bus clock speed is 265.0987 MHz. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-01-28 11:51:09 +08:00
(deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ),
(deltatsc / LAPIC_CAL_LOOPS) % (1000000 / HZ));
}
apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
"%u.%04u MHz.\n",
calibration_result / (1000000 / HZ),
calibration_result % (1000000 / HZ));
/*
* Do a sanity check on the APIC calibration result
*/
if (calibration_result < (1000000 / HZ)) {
local_irq_enable();
pr_warning("APIC frequency too slow, disabling apic timer\n");
return -1;
}
levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
/*
* PM timer calibration failed or not turned on
* so lets try APIC timer based calibration
*/
if (!pm_referenced) {
apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
/*
* Setup the apic timer manually
*/
levt->event_handler = lapic_cal_handler;
lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt);
lapic_cal_loops = -1;
/* Let the interrupts run */
local_irq_enable();
while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
cpu_relax();
/* Stop the lapic timer */
lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
/* Jiffies delta */
deltaj = lapic_cal_j2 - lapic_cal_j1;
apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
/* Check, if the jiffies result is consistent */
if (deltaj >= LAPIC_CAL_LOOPS-2 && deltaj <= LAPIC_CAL_LOOPS+2)
apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
else
levt->features |= CLOCK_EVT_FEAT_DUMMY;
} else
local_irq_enable();
if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
pr_warning("APIC timer disabled due to verification failure\n");
return -1;
}
return 0;
}
/*
* Setup the boot APIC
*
* Calibrate and verify the result.
*/
void __init setup_boot_APIC_clock(void)
{
/*
* The local apic timer can be disabled via the kernel
* commandline or from the CPU detection code. 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) {
pr_info("Disabling APIC timer\n");
/* No broadcast on UP ! */
if (num_possible_cpus() > 1) {
lapic_clockevent.mult = 1;
setup_APIC_timer();
}
return;
}
apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
"calibrating APIC timer ...\n");
if (calibrate_APIC_clock()) {
/* No broadcast on UP ! */
if (num_possible_cpus() > 1)
setup_APIC_timer();
return;
}
/*
* 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
pr_warning("APIC timer registered as dummy,"
" due to nmi_watchdog=%d!\n", nmi_watchdog);
/* Setup the lapic or request the broadcast */
setup_APIC_timer();
}
void __cpuinit setup_secondary_APIC_clock(void)
{
setup_APIC_timer();
}
/*
* The guts of the apic timer interrupt
*/
static void local_apic_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) {
pr_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.
*/
inc_irq_stat(apic_timer_irqs);
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 __irq_entry 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();
local_apic_timer_interrupt();
irq_exit();
set_irq_regs(old_regs);
}
int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
/*
* Local APIC start and shutdown
*/
/**
* clear_local_APIC - shutdown the local APIC
*
* This is called, when a CPU is disabled and before rebooting, so the state of
* the local APIC has no dangling leftovers. Also used to cleanout any BIOS
* leftovers during boot.
*/
void clear_local_APIC(void)
{
int maxlvt;
u32 v;
/* APIC hasn't been mapped yet */
if (!x2apic_mode && !apic_phys)
return;
maxlvt = lapic_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);
}
/* lets not touch this if we didn't frob it */
x86, mce: use 64bit machine check code on 32bit The 64bit machine check code is in many ways much better than the 32bit machine check code: it is more specification compliant, is cleaner, only has a single code base versus one per CPU, has better infrastructure for recovery, has a cleaner way to communicate with user space etc. etc. Use the 64bit code for 32bit too. This is the second attempt to do this. There was one a couple of years ago to unify this code for 32bit and 64bit. Back then this ran into some trouble with K7s and was reverted. I believe this time the K7 problems (and some others) are addressed. I went over the old handlers and was very careful to retain all quirks. But of course this needs a lot of testing on old systems. On newer 64bit capable systems I don't expect much problems because they have been already tested with the 64bit kernel. I made this a CONFIG for now that still allows to select the old machine check code. This is mostly to make testing easier, if someone runs into a problem we can ask them to try with the CONFIG switched. The new code is default y for more coverage. Once there is confidence the 64bit code works well on older hardware too the CONFIG_X86_OLD_MCE and the associated code can be easily removed. This causes a behaviour change for 32bit installations. They now have to install the mcelog package to be able to log corrected machine checks. The 64bit machine check code only handles CPUs which support the standard Intel machine check architecture described in the IA32 SDM. The 32bit code has special support for some older CPUs which have non standard machine check architectures, in particular WinChip C3 and Intel P5. I made those a separate CONFIG option and kept them for now. The WinChip variant could be probably removed without too much pain, it doesn't really do anything interesting. P5 is also disabled by default (like it was before) because many motherboards have it miswired, but according to Alan Cox a few embedded setups use that one. Forward ported/heavily changed version of old patch, original patch included review/fixes from Thomas Gleixner, Bert Wesarg. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-04-29 01:07:31 +08:00
#ifdef CONFIG_X86_THERMAL_VECTOR
if (maxlvt >= 5) {
v = apic_read(APIC_LVTTHMR);
apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
}
#endif
#ifdef CONFIG_X86_MCE_INTEL
if (maxlvt >= 6) {
v = apic_read(APIC_LVTCMCI);
if (!(v & APIC_LVT_MASKED))
apic_write(APIC_LVTCMCI, v | APIC_LVT_MASKED);
}
#endif
/*
* 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);
/* Integrated APIC (!82489DX) ? */
if (lapic_is_integrated()) {
if (maxlvt > 3)
/* Clear ESR due to Pentium errata 3AP and 11AP */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
}
/**
* disable_local_APIC - clear and disable the local APIC
*/
void disable_local_APIC(void)
{
unsigned int value;
/* APIC hasn't been mapped yet */
if (!apic_phys)
return;
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);
#ifdef CONFIG_X86_32
/*
* When LAPIC was disabled by the BIOS and enabled by the kernel,
* restore the disabled state.
*/
if (enabled_via_apicbase) {
unsigned int l, h;
rdmsr(MSR_IA32_APICBASE, l, h);
l &= ~MSR_IA32_APICBASE_ENABLE;
wrmsr(MSR_IA32_APICBASE, l, h);
}
#endif
}
/*
* If Linux enabled the LAPIC against the BIOS default disable it down before
* re-entering the BIOS on shutdown. Otherwise the BIOS may get confused and
* not power-off. Additionally clear all LVT entries before disable_local_APIC
* for the case where Linux didn't enable the LAPIC.
*/
void lapic_shutdown(void)
{
unsigned long flags;
if (!cpu_has_apic && !apic_from_smp_config())
return;
local_irq_save(flags);
#ifdef CONFIG_X86_32
if (!enabled_via_apicbase)
clear_local_APIC();
else
#endif
disable_local_APIC();
local_irq_restore(flags);
}
/*
* 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 = lapic_get_maxlvt();
if (reg1 < 0x02 || reg1 == 0xff)
return 0;
/*
* The ID register is read/write in a real APIC.
*/
x64, x2apic/intr-remap: Interrupt-remapping and x2apic support, fix Yinghai Lu wrote: > Setting APIC routing to physical flat > Kernel panic - not syncing: Boot APIC ID in local APIC unexpected (0 vs 4) > Pid: 1, comm: swapper Not tainted 2.6.26-rc9-tip-01763-g74f94b1-dirty #320 > > Call Trace: > [<ffffffff80a21505>] ? set_cpu_sibling_map+0x38c/0x3bd > [<ffffffff80245215>] ? read_xapic_id+0x25/0x3e > [<ffffffff80e5a2c3>] ? verify_local_APIC+0x139/0x1b9 > [<ffffffff80245215>] ? read_xapic_id+0x25/0x3e > [<ffffffff80e589af>] ? native_smp_prepare_cpus+0x224/0x2e9 > [<ffffffff80e4881a>] ? kernel_init+0x64/0x341 > [<ffffffff8022a439>] ? child_rip+0xa/0x11 > [<ffffffff80e487b6>] ? kernel_init+0x0/0x341 > [<ffffffff8022a42f>] ? child_rip+0x0/0x11 > > > guess read_apic_id changing cuase some problem... genapic's read_apic_id() returns the actual apic id extracted from the APIC_ID register. And in some cases like UV, read_apic_id() returns completely different values from APIC ID register. Use the native apic register read, rather than genapic read_apic_id() in verify_local_APIC() And also, lapic_suspend() should also use native apic register read. Reported-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: "akpm@linux-foundation.org" <akpm@linux-foundation.org> Cc: "arjan@linux.intel.com" <arjan@linux.intel.com> Cc: "andi@firstfloor.org" <andi@firstfloor.org> Cc: "ebiederm@xmission.com" <ebiederm@xmission.com> Cc: "jbarnes@virtuousgeek.org" <jbarnes@virtuousgeek.org> Cc: "steiner@sgi.com" <steiner@sgi.com> Cc: "jeremy@goop.org" <jeremy@goop.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-12 05:24:19 +08:00
reg0 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
apic_write(APIC_ID, reg0 ^ apic->apic_id_mask);
x64, x2apic/intr-remap: Interrupt-remapping and x2apic support, fix Yinghai Lu wrote: > Setting APIC routing to physical flat > Kernel panic - not syncing: Boot APIC ID in local APIC unexpected (0 vs 4) > Pid: 1, comm: swapper Not tainted 2.6.26-rc9-tip-01763-g74f94b1-dirty #320 > > Call Trace: > [<ffffffff80a21505>] ? set_cpu_sibling_map+0x38c/0x3bd > [<ffffffff80245215>] ? read_xapic_id+0x25/0x3e > [<ffffffff80e5a2c3>] ? verify_local_APIC+0x139/0x1b9 > [<ffffffff80245215>] ? read_xapic_id+0x25/0x3e > [<ffffffff80e589af>] ? native_smp_prepare_cpus+0x224/0x2e9 > [<ffffffff80e4881a>] ? kernel_init+0x64/0x341 > [<ffffffff8022a439>] ? child_rip+0xa/0x11 > [<ffffffff80e487b6>] ? kernel_init+0x0/0x341 > [<ffffffff8022a42f>] ? child_rip+0x0/0x11 > > > guess read_apic_id changing cuase some problem... genapic's read_apic_id() returns the actual apic id extracted from the APIC_ID register. And in some cases like UV, read_apic_id() returns completely different values from APIC ID register. Use the native apic register read, rather than genapic read_apic_id() in verify_local_APIC() And also, lapic_suspend() should also use native apic register read. Reported-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: "akpm@linux-foundation.org" <akpm@linux-foundation.org> Cc: "arjan@linux.intel.com" <arjan@linux.intel.com> Cc: "andi@firstfloor.org" <andi@firstfloor.org> Cc: "ebiederm@xmission.com" <ebiederm@xmission.com> Cc: "jbarnes@virtuousgeek.org" <jbarnes@virtuousgeek.org> Cc: "steiner@sgi.com" <steiner@sgi.com> Cc: "jeremy@goop.org" <jeremy@goop.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-12 05:24:19 +08:00
reg1 = apic_read(APIC_ID);
apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
apic_write(APIC_ID, reg0);
if (reg1 != (reg0 ^ apic->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;
}
/**
* sync_Arb_IDs - synchronize APIC bus arbitration IDs
*/
void __init sync_Arb_IDs(void)
{
/*
* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 And not
* needed on AMD.
*/
if (modern_apic() || boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
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;
/*
* 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;
#ifdef CONFIG_X86_32
/* This bit is reserved on P4/Xeon and should be cleared */
if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
(boot_cpu_data.x86 == 15))
value &= ~APIC_SPIV_FOCUS_DISABLED;
else
#endif
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;
if (!lapic_is_integrated()) /* 82489DX */
value |= APIC_LVT_LEVEL_TRIGGER;
apic_write(APIC_LVT1, value);
}
static void __cpuinit lapic_setup_esr(void)
{
unsigned int oldvalue, value, maxlvt;
if (!lapic_is_integrated()) {
pr_info("No ESR for 82489DX.\n");
return;
}
if (apic->disable_esr) {
/*
* Something untraceable is creating bad interrupts on
* secondary quads ... for the moment, just leave the
* ESR disabled - we can't do anything useful with the
* errors anyway - mbligh
*/
pr_info("Leaving ESR disabled.\n");
return;
}
maxlvt = lapic_get_maxlvt();
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
oldvalue = apic_read(APIC_ESR);
/* enables sending errors */
value = ERROR_APIC_VECTOR;
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 before enabling "
"vector: 0x%08x after: 0x%08x\n",
oldvalue, value);
}
/**
* setup_local_APIC - setup the local APIC
*/
void __cpuinit setup_local_APIC(void)
{
unsigned int value;
int i, j;
if (disable_apic) {
arch_disable_smp_support();
return;
}
#ifdef CONFIG_X86_32
/* Pound the ESR really hard over the head with a big hammer - mbligh */
if (lapic_is_integrated() && apic->disable_esr) {
apic_write(APIC_ESR, 0);
apic_write(APIC_ESR, 0);
apic_write(APIC_ESR, 0);
apic_write(APIC_ESR, 0);
}
#endif
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
perf_events_lapic_init();
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-29 03:12:16 +08:00
preempt_disable();
/*
* Double-check whether this APIC is really registered.
* This is meaningless in clustered apic mode, so we skip it.
*/
BUG_ON(!apic->apic_id_registered());
/*
* 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...
*/
apic->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;
#ifdef CONFIG_X86_32
/*
* Some unknown Intel IO/APIC (or APIC) errata is biting us with
* certain networking cards. If high frequency interrupts are
* happening on a particular IOAPIC pin, plus the IOAPIC routing
* entry is masked/unmasked at a high rate as well then sooner or
* later IOAPIC line gets 'stuck', no more interrupts are received
* from the device. If focus CPU is disabled then the hang goes
* away, oh well :-(
*
* [ This bug can be reproduced easily with a level-triggered
* PCI Ne2000 networking cards and PII/PIII processors, dual
* BX chipset. ]
*/
/*
* Actually disabling the focus CPU check just makes the hang less
* frequent as it makes the interrupt distributon model be more
* like LRU than MRU (the short-term load is more even across CPUs).
* See also the comment in end_level_ioapic_irq(). --macro
*/
/*
* - enable focus processor (bit==0)
* - 64bit mode always use processor focus
* so no need to set it
*/
value &= ~APIC_SPIV_FOCUS_DISABLED;
#endif
/*
* 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() && (pic_mode || !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;
if (!lapic_is_integrated()) /* 82489DX */
value |= APIC_LVT_LEVEL_TRIGGER;
apic_write(APIC_LVT1, value);
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-29 03:12:16 +08:00
preempt_enable();
#ifdef CONFIG_X86_MCE_INTEL
/* Recheck CMCI information after local APIC is up on CPU #0 */
if (smp_processor_id() == 0)
cmci_recheck();
#endif
}
void __cpuinit end_local_APIC_setup(void)
{
lapic_setup_esr();
#ifdef CONFIG_X86_32
{
unsigned int value;
/* Disable the local apic timer */
value = apic_read(APIC_LVTT);
value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
apic_write(APIC_LVTT, value);
}
#endif
setup_apic_nmi_watchdog(NULL);
apic_pm_activate();
}
#ifdef CONFIG_X86_X2APIC
void check_x2apic(void)
{
if (x2apic_enabled()) {
pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
x2apic_preenabled = x2apic_mode = 1;
}
}
void enable_x2apic(void)
{
int msr, msr2;
if (!x2apic_mode)
return;
rdmsr(MSR_IA32_APICBASE, msr, msr2);
if (!(msr & X2APIC_ENABLE)) {
printk_once(KERN_INFO "Enabling x2apic\n");
wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
}
}
#endif /* CONFIG_X86_X2APIC */
int __init enable_IR(void)
{
#ifdef CONFIG_INTR_REMAP
if (!intr_remapping_supported()) {
pr_debug("intr-remapping not supported\n");
return 0;
}
if (!x2apic_preenabled && skip_ioapic_setup) {
pr_info("Skipped enabling intr-remap because of skipping "
"io-apic setup\n");
return 0;
}
if (enable_intr_remapping(x2apic_supported()))
return 0;
pr_info("Enabled Interrupt-remapping\n");
return 1;
#endif
return 0;
}
void __init enable_IR_x2apic(void)
{
unsigned long flags;
struct IO_APIC_route_entry **ioapic_entries = NULL;
int ret, x2apic_enabled = 0;
int dmar_table_init_ret;
x86, apic: Move dmar_table_init() out of enable_IR() On an x2apic system, we got: [ 1.818072] ------------[ cut here ]------------ [ 1.820376] WARNING: at kernel/lockdep.c:2461 lockdep_trace_alloc+0xa5/0xe9() [ 1.835282] Hardware name: ASSY, [ 1.839006] Modules linked in: [ 1.841253] Pid: 1, comm: swapper Not tainted 2.6.31-rc5-tip-03926-g39aaa80-dirty #510 [ 1.858056] Call Trace: [ 1.859913] [<ffffffff810d13aa>] ? lockdep_trace_alloc+0xa5/0xe9 [ 1.876270] [<ffffffff81093f37>] warn_slowpath_common+0x8d/0xd0 [ 1.879132] [<ffffffff81093fa1>] warn_slowpath_null+0x27/0x3d [ 1.896823] [<ffffffff810d13aa>] lockdep_trace_alloc+0xa5/0xe9 [ 1.900659] [<ffffffff810cf5a0>] ? lock_release_holdtime+0x2f/0x199 [ 1.917188] [<ffffffff81167a3c>] kmem_cache_alloc_notrace+0x42/0x111 [ 1.922320] [<ffffffff8106fe8c>] ? reserve_memtype+0x152/0x518 [ 1.938137] [<ffffffff8106f8b1>] ? pat_pagerange_is_ram+0x4a/0x91 [ 1.941730] [<ffffffff8106fe8c>] reserve_memtype+0x152/0x518 [ 1.958115] [<ffffffff8106ce62>] __ioremap_caller+0x1dd/0x30f [ 1.975507] [<ffffffff81ce2c5c>] ? acpi_os_map_memory+0x2a/0x47 [ 1.978987] [<ffffffff8106d0fd>] ioremap_nocache+0x2a/0x40 [ 2.031400] [<ffffffff810d0364>] ? trace_hardirqs_off+0x20/0x36 [ 2.036096] [<ffffffff81ce2c5c>] acpi_os_map_memory+0x2a/0x47 [ 2.046263] [<ffffffff815cd642>] acpi_tb_verify_table+0x3d/0x85 [ 2.050349] [<ffffffff81d34af7>] ? _spin_unlock_irqrestore+0x50/0x76 [ 2.067327] [<ffffffff815ccad6>] acpi_get_table_with_size+0x64/0xd9 [ 2.070860] [<ffffffff81d34af7>] ? _spin_unlock_irqrestore+0x50/0x76 [ 2.088000] [<ffffffff825c88d5>] dmar_table_detect+0x33/0x70 [ 2.092047] [<ffffffff825c8a01>] dmar_table_init+0x43/0x428 [ 2.106854] [<ffffffff825a7537>] enable_IR+0x1c/0x8d [ 2.110256] [<ffffffff825a7624>] enable_IR_x2apic+0x7c/0x19e [ 2.127139] [<ffffffff825a4876>] native_smp_prepare_cpus+0x139/0x3b8 [ 2.145175] [<ffffffff8259678d>] kernel_init+0x71/0x1da [ 2.148913] [<ffffffff8104305a>] child_rip+0xa/0x20 [ 2.152349] [<ffffffff810429fc>] ? restore_args+0x0/0x30 [ 2.167931] [<ffffffff8259671c>] ? kernel_init+0x0/0x1da [ 2.171671] [<ffffffff81043050>] ? child_rip+0x0/0x20 [ 2.187607] ---[ end trace a7919e7f17c0a725 ]--- Venkatesh Pallipadi said: | Looks like the problem started with this commit | | commit ce69a784504222c3ab6f1b3c357d09ec5772127a | Author: Gleb Natapov <gleb@redhat.com> | Date: Mon Jul 20 15:24:17 2009 +0300 | | x86/apic: Enable x2APIC without interrupt remapping under KVM | | Before this commit, dmar_table_init() was getting called | with interrupts enabled and after this commit, it is getting | called with interrupts disabled. so try to move out dmar_table_init out of that function. Analyzed-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Gleb Natapov <gleb@redhat.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com> LKML-Reference: <4A899F3C.2050104@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-18 02:19:40 +08:00
dmar_table_init_ret = dmar_table_init();
if (dmar_table_init_ret && !x2apic_supported())
return;
ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
pr_err("Allocate ioapic_entries failed\n");
goto out;
}
ret = save_IO_APIC_setup(ioapic_entries);
if (ret) {
pr_info("Saving IO-APIC state failed: %d\n", ret);
goto out;
}
local_irq_save(flags);
mask_8259A();
mask_IO_APIC_setup(ioapic_entries);
x86, apic: Move dmar_table_init() out of enable_IR() On an x2apic system, we got: [ 1.818072] ------------[ cut here ]------------ [ 1.820376] WARNING: at kernel/lockdep.c:2461 lockdep_trace_alloc+0xa5/0xe9() [ 1.835282] Hardware name: ASSY, [ 1.839006] Modules linked in: [ 1.841253] Pid: 1, comm: swapper Not tainted 2.6.31-rc5-tip-03926-g39aaa80-dirty #510 [ 1.858056] Call Trace: [ 1.859913] [<ffffffff810d13aa>] ? lockdep_trace_alloc+0xa5/0xe9 [ 1.876270] [<ffffffff81093f37>] warn_slowpath_common+0x8d/0xd0 [ 1.879132] [<ffffffff81093fa1>] warn_slowpath_null+0x27/0x3d [ 1.896823] [<ffffffff810d13aa>] lockdep_trace_alloc+0xa5/0xe9 [ 1.900659] [<ffffffff810cf5a0>] ? lock_release_holdtime+0x2f/0x199 [ 1.917188] [<ffffffff81167a3c>] kmem_cache_alloc_notrace+0x42/0x111 [ 1.922320] [<ffffffff8106fe8c>] ? reserve_memtype+0x152/0x518 [ 1.938137] [<ffffffff8106f8b1>] ? pat_pagerange_is_ram+0x4a/0x91 [ 1.941730] [<ffffffff8106fe8c>] reserve_memtype+0x152/0x518 [ 1.958115] [<ffffffff8106ce62>] __ioremap_caller+0x1dd/0x30f [ 1.975507] [<ffffffff81ce2c5c>] ? acpi_os_map_memory+0x2a/0x47 [ 1.978987] [<ffffffff8106d0fd>] ioremap_nocache+0x2a/0x40 [ 2.031400] [<ffffffff810d0364>] ? trace_hardirqs_off+0x20/0x36 [ 2.036096] [<ffffffff81ce2c5c>] acpi_os_map_memory+0x2a/0x47 [ 2.046263] [<ffffffff815cd642>] acpi_tb_verify_table+0x3d/0x85 [ 2.050349] [<ffffffff81d34af7>] ? _spin_unlock_irqrestore+0x50/0x76 [ 2.067327] [<ffffffff815ccad6>] acpi_get_table_with_size+0x64/0xd9 [ 2.070860] [<ffffffff81d34af7>] ? _spin_unlock_irqrestore+0x50/0x76 [ 2.088000] [<ffffffff825c88d5>] dmar_table_detect+0x33/0x70 [ 2.092047] [<ffffffff825c8a01>] dmar_table_init+0x43/0x428 [ 2.106854] [<ffffffff825a7537>] enable_IR+0x1c/0x8d [ 2.110256] [<ffffffff825a7624>] enable_IR_x2apic+0x7c/0x19e [ 2.127139] [<ffffffff825a4876>] native_smp_prepare_cpus+0x139/0x3b8 [ 2.145175] [<ffffffff8259678d>] kernel_init+0x71/0x1da [ 2.148913] [<ffffffff8104305a>] child_rip+0xa/0x20 [ 2.152349] [<ffffffff810429fc>] ? restore_args+0x0/0x30 [ 2.167931] [<ffffffff8259671c>] ? kernel_init+0x0/0x1da [ 2.171671] [<ffffffff81043050>] ? child_rip+0x0/0x20 [ 2.187607] ---[ end trace a7919e7f17c0a725 ]--- Venkatesh Pallipadi said: | Looks like the problem started with this commit | | commit ce69a784504222c3ab6f1b3c357d09ec5772127a | Author: Gleb Natapov <gleb@redhat.com> | Date: Mon Jul 20 15:24:17 2009 +0300 | | x86/apic: Enable x2APIC without interrupt remapping under KVM | | Before this commit, dmar_table_init() was getting called | with interrupts enabled and after this commit, it is getting | called with interrupts disabled. so try to move out dmar_table_init out of that function. Analyzed-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Gleb Natapov <gleb@redhat.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com> LKML-Reference: <4A899F3C.2050104@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-18 02:19:40 +08:00
if (dmar_table_init_ret)
ret = 0;
else
ret = enable_IR();
if (!ret) {
/* IR is required if there is APIC ID > 255 even when running
* under KVM
*/
if (max_physical_apicid > 255 || !kvm_para_available())
goto nox2apic;
/*
* without IR all CPUs can be addressed by IOAPIC/MSI
* only in physical mode
*/
x2apic_force_phys();
}
x2apic_enabled = 1;
if (x2apic_supported() && !x2apic_mode) {
x2apic_mode = 1;
enable_x2apic();
pr_info("Enabled x2apic\n");
}
nox2apic:
if (!ret) /* IR enabling failed */
restore_IO_APIC_setup(ioapic_entries);
unmask_8259A();
local_irq_restore(flags);
out:
if (ioapic_entries)
free_ioapic_entries(ioapic_entries);
if (x2apic_enabled)
return;
if (x2apic_preenabled)
panic("x2apic: enabled by BIOS but kernel init failed.");
else if (cpu_has_x2apic)
pr_info("Not enabling x2apic, Intr-remapping init failed.\n");
}
#ifdef CONFIG_X86_64
/*
* 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) {
pr_info("No local APIC present\n");
return -1;
}
mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
return 0;
}
#else
/*
* Detect and initialize APIC
*/
static int __init detect_init_APIC(void)
{
u32 h, l, features;
/* Disabled by kernel option? */
if (disable_apic)
return -1;
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
(boot_cpu_data.x86 >= 15))
break;
goto no_apic;
case X86_VENDOR_INTEL:
if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
(boot_cpu_data.x86 == 5 && cpu_has_apic))
break;
goto no_apic;
default:
goto no_apic;
}
if (!cpu_has_apic) {
/*
* Over-ride BIOS and try to enable the local APIC only if
* "lapic" specified.
*/
if (!force_enable_local_apic) {
pr_info("Local APIC disabled by BIOS -- "
"you can enable it with \"lapic\"\n");
return -1;
}
/*
* Some BIOSes disable the local APIC in the APIC_BASE
* MSR. This can only be done in software for Intel P6 or later
* and AMD K7 (Model > 1) or later.
*/
rdmsr(MSR_IA32_APICBASE, l, h);
if (!(l & MSR_IA32_APICBASE_ENABLE)) {
pr_info("Local APIC disabled by BIOS -- reenabling.\n");
l &= ~MSR_IA32_APICBASE_BASE;
l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
wrmsr(MSR_IA32_APICBASE, l, h);
enabled_via_apicbase = 1;
}
}
/*
* The APIC feature bit should now be enabled
* in `cpuid'
*/
features = cpuid_edx(1);
if (!(features & (1 << X86_FEATURE_APIC))) {
pr_warning("Could not enable APIC!\n");
return -1;
}
set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
/* The BIOS may have set up the APIC at some other address */
rdmsr(MSR_IA32_APICBASE, l, h);
if (l & MSR_IA32_APICBASE_ENABLE)
mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
pr_info("Found and enabled local APIC!\n");
apic_pm_activate();
return 0;
no_apic:
pr_info("No local APIC present or hardware disabled\n");
return -1;
}
#endif
#ifdef CONFIG_X86_64
void __init early_init_lapic_mapping(void)
{
/*
* If no local APIC can be found then go out
* : it means there is no mpatable and MADT
*/
if (!smp_found_config)
return;
set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr);
apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
APIC_BASE, mp_lapic_addr);
/*
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
boot_cpu_physical_apicid = read_apic_id();
}
#endif
/**
* init_apic_mappings - initialize APIC mappings
*/
void __init init_apic_mappings(void)
{
unsigned int new_apicid;
if (x2apic_mode) {
boot_cpu_physical_apicid = read_apic_id();
return;
}
/* If no local APIC can be found return early */
if (!smp_found_config && detect_init_APIC()) {
/* lets NOP'ify apic operations */
pr_info("APIC: disable apic facility\n");
apic_disable();
} else {
apic_phys = mp_lapic_addr;
/*
* acpi lapic path already maps that address in
* acpi_register_lapic_address()
*/
if (!acpi_lapic)
set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
APIC_BASE, apic_phys);
}
/*
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
new_apicid = read_apic_id();
if (boot_cpu_physical_apicid != new_apicid) {
boot_cpu_physical_apicid = new_apicid;
/*
* yeah -- we lie about apic_version
* in case if apic was disabled via boot option
* but it's not a problem for SMP compiled kernel
* since smp_sanity_check is prepared for such a case
* and disable smp mode
*/
apic_version[new_apicid] =
GET_APIC_VERSION(apic_read(APIC_LVR));
}
}
/*
* This initializes the IO-APIC and APIC hardware if this is
* a UP kernel.
*/
int apic_version[MAX_APICS];
int __init APIC_init_uniprocessor(void)
{
if (disable_apic) {
pr_info("Apic disabled\n");
return -1;
}
#ifdef CONFIG_X86_64
if (!cpu_has_apic) {
disable_apic = 1;
pr_info("Apic disabled by BIOS\n");
return -1;
}
#else
if (!smp_found_config && !cpu_has_apic)
return -1;
/*
* Complain if the BIOS pretends there is one.
*/
if (!cpu_has_apic &&
APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
boot_cpu_physical_apicid);
return -1;
}
#endif
enable_IR_x2apic();
#ifdef CONFIG_X86_64
default_setup_apic_routing();
#endif
verify_local_APIC();
connect_bsp_APIC();
#ifdef CONFIG_X86_64
apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid));
#else
/*
* Hack: In case of kdump, after a crash, kernel might be booting
* on a cpu with non-zero lapic id. But boot_cpu_physical_apicid
* might be zero if read from MP tables. Get it from LAPIC.
*/
# ifdef CONFIG_CRASH_DUMP
boot_cpu_physical_apicid = read_apic_id();
# endif
#endif
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
setup_local_APIC();
#ifdef CONFIG_X86_IO_APIC
/*
* Now enable IO-APICs, actually call clear_IO_APIC
* We need clear_IO_APIC before enabling error vector
*/
if (!skip_ioapic_setup && nr_ioapics)
enable_IO_APIC();
#endif
end_local_APIC_setup();
#ifdef CONFIG_X86_IO_APIC
if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
setup_IO_APIC();
else {
nr_ioapics = 0;
localise_nmi_watchdog();
}
#else
localise_nmi_watchdog();
#endif
x86_init.timers.setup_percpu_clockev();
#ifdef CONFIG_X86_64
check_nmi_watchdog();
#endif
return 0;
}
/*
* Local APIC interrupts
*/
/*
* This interrupt should _never_ happen with our APIC/SMP architecture
*/
void smp_spurious_interrupt(struct pt_regs *regs)
{
u32 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();
inc_irq_stat(irq_spurious_count);
/* see sw-dev-man vol 3, chapter 7.4.13.5 */
pr_info("spurious APIC interrupt on CPU#%d, "
"should never happen.\n", smp_processor_id());
irq_exit();
}
/*
* This interrupt should never happen with our APIC/SMP architecture
*/
void smp_error_interrupt(struct pt_regs *regs)
{
u32 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
*/
pr_debug("APIC error on CPU%d: %02x(%02x)\n",
smp_processor_id(), v , v1);
irq_exit();
}
/**
* connect_bsp_APIC - attach the APIC to the interrupt system
*/
void __init connect_bsp_APIC(void)
{
#ifdef CONFIG_X86_32
if (pic_mode) {
/*
* Do not trust the local APIC being empty at bootup.
*/
clear_local_APIC();
/*
* PIC mode, enable APIC mode in the IMCR, i.e. connect BSP's
* local APIC to INT and NMI lines.
*/
apic_printk(APIC_VERBOSE, "leaving PIC mode, "
"enabling APIC mode.\n");
imcr_pic_to_apic();
}
#endif
if (apic->enable_apic_mode)
apic->enable_apic_mode();
}
/**
* disconnect_bsp_APIC - detach the APIC from the interrupt system
* @virt_wire_setup: indicates, whether virtual wire mode is selected
*
* Virtual wire mode is necessary to deliver legacy interrupts even when the
* APIC is disabled.
*/
void disconnect_bsp_APIC(int virt_wire_setup)
{
unsigned int value;
#ifdef CONFIG_X86_32
if (pic_mode) {
/*
* Put the board back into PIC mode (has an effect only on
* certain older boards). Note that APIC interrupts, including
* IPIs, won't work beyond this point! The only exception are
* INIT IPIs.
*/
apic_printk(APIC_VERBOSE, "disabling APIC mode, "
"entering PIC mode.\n");
imcr_apic_to_pic();
return;
}
#endif
/* Go back to Virtual Wire compatibility mode */
/* 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 __cpuinit generic_processor_info(int apicid, int version)
{
int cpu;
/*
* Validate version
*/
if (version == 0x0) {
pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
"fixing up to 0x10. (tell your hw vendor)\n",
version);
version = 0x10;
}
apic_version[apicid] = version;
if (num_processors >= nr_cpu_ids) {
int max = nr_cpu_ids;
int thiscpu = max + disabled_cpus;
pr_warning(
"ACPI: NR_CPUS/possible_cpus limit of %i reached."
" Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
disabled_cpus++;
return;
}
num_processors++;
cpu = cpumask_next_zero(-1, cpu_present_mask);
if (version != apic_version[boot_cpu_physical_apicid])
WARN_ONCE(1,
"ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
apic_version[boot_cpu_physical_apicid], cpu, version);
physid_set(apicid, phys_cpu_present_map);
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
* in same order as logical cpu numbers. Hence the first
* entry is BSP, and so on.
*/
cpu = 0;
}
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
#ifdef CONFIG_X86_32
/*
* Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
* but we need to work other dependencies like SMP_SUSPEND etc
* before this can be done without some confusion.
* if (CPU_HOTPLUG_ENABLED || num_processors > 8)
* - Ashok Raj <ashok.raj@intel.com>
*/
if (max_physical_apicid >= 8) {
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_INTEL:
if (!APIC_XAPIC(version)) {
def_to_bigsmp = 0;
break;
}
/* If P4 and above fall through */
case X86_VENDOR_AMD:
def_to_bigsmp = 1;
}
}
#endif
#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
set_cpu_possible(cpu, true);
set_cpu_present(cpu, true);
}
int hard_smp_processor_id(void)
{
return read_apic_id();
}
void default_init_apic_ldr(void)
{
unsigned long val;
apic_write(APIC_DFR, APIC_DFR_VALUE);
val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
apic_write(APIC_LDR, val);
}
#ifdef CONFIG_X86_32
int default_apicid_to_node(int logical_apicid)
{
#ifdef CONFIG_SMP
return apicid_2_node[hard_smp_processor_id()];
#else
return 0;
#endif
}
#endif
/*
* Power management
*/
#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 = lapic_get_maxlvt();
x64, x2apic/intr-remap: Interrupt-remapping and x2apic support, fix Yinghai Lu wrote: > Setting APIC routing to physical flat > Kernel panic - not syncing: Boot APIC ID in local APIC unexpected (0 vs 4) > Pid: 1, comm: swapper Not tainted 2.6.26-rc9-tip-01763-g74f94b1-dirty #320 > > Call Trace: > [<ffffffff80a21505>] ? set_cpu_sibling_map+0x38c/0x3bd > [<ffffffff80245215>] ? read_xapic_id+0x25/0x3e > [<ffffffff80e5a2c3>] ? verify_local_APIC+0x139/0x1b9 > [<ffffffff80245215>] ? read_xapic_id+0x25/0x3e > [<ffffffff80e589af>] ? native_smp_prepare_cpus+0x224/0x2e9 > [<ffffffff80e4881a>] ? kernel_init+0x64/0x341 > [<ffffffff8022a439>] ? child_rip+0xa/0x11 > [<ffffffff80e487b6>] ? kernel_init+0x0/0x341 > [<ffffffff8022a42f>] ? child_rip+0x0/0x11 > > > guess read_apic_id changing cuase some problem... genapic's read_apic_id() returns the actual apic id extracted from the APIC_ID register. And in some cases like UV, read_apic_id() returns completely different values from APIC ID register. Use the native apic register read, rather than genapic read_apic_id() in verify_local_APIC() And also, lapic_suspend() should also use native apic register read. Reported-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: "akpm@linux-foundation.org" <akpm@linux-foundation.org> Cc: "arjan@linux.intel.com" <arjan@linux.intel.com> Cc: "andi@firstfloor.org" <andi@firstfloor.org> Cc: "ebiederm@xmission.com" <ebiederm@xmission.com> Cc: "jbarnes@virtuousgeek.org" <jbarnes@virtuousgeek.org> Cc: "steiner@sgi.com" <steiner@sgi.com> Cc: "jeremy@goop.org" <jeremy@goop.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-12 05:24:19 +08:00
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);
x86, mce: use 64bit machine check code on 32bit The 64bit machine check code is in many ways much better than the 32bit machine check code: it is more specification compliant, is cleaner, only has a single code base versus one per CPU, has better infrastructure for recovery, has a cleaner way to communicate with user space etc. etc. Use the 64bit code for 32bit too. This is the second attempt to do this. There was one a couple of years ago to unify this code for 32bit and 64bit. Back then this ran into some trouble with K7s and was reverted. I believe this time the K7 problems (and some others) are addressed. I went over the old handlers and was very careful to retain all quirks. But of course this needs a lot of testing on old systems. On newer 64bit capable systems I don't expect much problems because they have been already tested with the 64bit kernel. I made this a CONFIG for now that still allows to select the old machine check code. This is mostly to make testing easier, if someone runs into a problem we can ask them to try with the CONFIG switched. The new code is default y for more coverage. Once there is confidence the 64bit code works well on older hardware too the CONFIG_X86_OLD_MCE and the associated code can be easily removed. This causes a behaviour change for 32bit installations. They now have to install the mcelog package to be able to log corrected machine checks. The 64bit machine check code only handles CPUs which support the standard Intel machine check architecture described in the IA32 SDM. The 32bit code has special support for some older CPUs which have non standard machine check architectures, in particular WinChip C3 and Intel P5. I made those a separate CONFIG option and kept them for now. The WinChip variant could be probably removed without too much pain, it doesn't really do anything interesting. P5 is also disabled by default (like it was before) because many motherboards have it miswired, but according to Alan Cox a few embedded setups use that one. Forward ported/heavily changed version of old patch, original patch included review/fixes from Thomas Gleixner, Bert Wesarg. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-04-29 01:07:31 +08:00
#ifdef CONFIG_X86_THERMAL_VECTOR
if (maxlvt >= 5)
apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
#endif
local_irq_save(flags);
disable_local_APIC();
if (intr_remapping_enabled)
disable_intr_remapping();
local_irq_restore(flags);
return 0;
}
static int lapic_resume(struct sys_device *dev)
{
unsigned int l, h;
unsigned long flags;
int maxlvt;
int ret = 0;
struct IO_APIC_route_entry **ioapic_entries = NULL;
if (!apic_pm_state.active)
return 0;
local_irq_save(flags);
if (intr_remapping_enabled) {
ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
WARN(1, "Alloc ioapic_entries in lapic resume failed.");
ret = -ENOMEM;
goto restore;
}
ret = save_IO_APIC_setup(ioapic_entries);
if (ret) {
WARN(1, "Saving IO-APIC state failed: %d\n", ret);
free_ioapic_entries(ioapic_entries);
goto restore;
}
mask_IO_APIC_setup(ioapic_entries);
mask_8259A();
}
if (x2apic_mode)
enable_x2apic();
else {
/*
* Make sure the APICBASE points to the right address
*
* FIXME! This will be wrong if we ever support suspend on
* SMP! We'll need to do this as part of the CPU restore!
*/
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);
}
maxlvt = lapic_get_maxlvt();
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);
#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(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);
if (intr_remapping_enabled) {
reenable_intr_remapping(x2apic_mode);
unmask_8259A();
restore_IO_APIC_setup(ioapic_entries);
free_ioapic_entries(ioapic_entries);
}
restore:
local_irq_restore(flags);
return ret;
}
/*
* This device has no shutdown method - fully functioning local APICs
* are needed on every CPU up until machine_halt/restart/poweroff.
*/
static struct sysdev_class lapic_sysclass = {
.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;
}
/* local apic needs to resume before other devices access its registers. */
core_initcall(init_lapic_sysfs);
#else /* CONFIG_PM */
static void apic_pm_activate(void) { }
#endif /* CONFIG_PM */
#ifdef CONFIG_X86_64
static int __cpuinit apic_cluster_num(void)
{
int i, clusters, zeros;
unsigned id;
u16 *bios_cpu_apicid;
DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
x86: cleanup early per cpu variables/accesses v4 * Introduce a new PER_CPU macro called "EARLY_PER_CPU". This is used by some per_cpu variables that are initialized and accessed before there are per_cpu areas allocated. ["Early" in respect to per_cpu variables is "earlier than the per_cpu areas have been setup".] This patchset adds these new macros: DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) EXPORT_EARLY_PER_CPU_SYMBOL(_name) DECLARE_EARLY_PER_CPU(_type, _name) early_per_cpu_ptr(_name) early_per_cpu_map(_name, _idx) early_per_cpu(_name, _cpu) The DEFINE macro defines the per_cpu variable as well as the early map and pointer. It also initializes the per_cpu variable and map elements to "_initvalue". The early_* macros provide access to the initial map (usually setup during system init) and the early pointer. This pointer is initialized to point to the early map but is then NULL'ed when the actual per_cpu areas are setup. After that the per_cpu variable is the correct access to the variable. The early_per_cpu() macro is not very efficient but does show how to access the variable if you have a function that can be called both "early" and "late". It tests the early ptr to be NULL, and if not then it's still valid. Otherwise, the per_cpu variable is used instead: #define early_per_cpu(_name, _cpu) \ (early_per_cpu_ptr(_name) ? \ early_per_cpu_ptr(_name)[_cpu] : \ per_cpu(_name, _cpu)) A better method is to actually check the pointer manually. In the case below, numa_set_node can be called both "early" and "late": void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); if (cpu_to_node_map) cpu_to_node_map[cpu] = node; else per_cpu(x86_cpu_to_node_map, cpu) = node; } * Add a flag "arch_provides_topology_pointers" that indicates pointers to topology cpumask_t maps are available. Otherwise, use the function returning the cpumask_t value. This is useful if cpumask_t set size is very large to avoid copying data on to/off of the stack. * The coverage of CONFIG_DEBUG_PER_CPU_MAPS has been increased while the non-debug case has been optimized a bit. * Remove an unreferenced compiler warning in drivers/base/topology.c * Clean up #ifdef in setup.c For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:21:12 +08:00
bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
for (i = 0; i < nr_cpu_ids; i++) {
/* are we being called early in kernel startup? */
if (bios_cpu_apicid) {
id = bios_cpu_apicid[i];
} else if (i < nr_cpu_ids) {
if (cpu_present(i))
id = per_cpu(x86_bios_cpu_apicid, i);
else
continue;
} else
break;
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
* x86_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;
}
return clusters;
}
static int __cpuinitdata multi_checked;
static int __cpuinitdata multi;
static int __cpuinit set_multi(const struct dmi_system_id *d)
{
if (multi)
return 0;
pr_info("APIC: %s detected, Multi Chassis\n", d->ident);
multi = 1;
return 0;
}
static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
{
.callback = set_multi,
.ident = "IBM System Summit2",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
},
},
{}
};
static void __cpuinit dmi_check_multi(void)
{
if (multi_checked)
return;
dmi_check_system(multi_dmi_table);
multi_checked = 1;
}
/*
* 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 DMI to check them
*/
__cpuinit int apic_is_clustered_box(void)
{
dmi_check_multi();
if (multi)
return 1;
if (!is_vsmp_box())
return 0;
/*
* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
* not guaranteed to be synced between boards
*/
if (apic_cluster_num() > 1)
return 1;
return 0;
}
#endif
/*
* APIC command line parameters
*/
static int __init setup_disableapic(char *arg)
{
disable_apic = 1;
setup_clear_cpu_cap(X86_FEATURE_APIC);
return 0;
}
early_param("disableapic", setup_disableapic);
/* same as disableapic, for compatibility */
static int __init setup_nolapic(char *arg)
{
return setup_disableapic(arg);
}
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 int __init parse_disable_apic_timer(char *arg)
{
disable_apic_timer = 1;
return 0;
}
early_param("noapictimer", parse_disable_apic_timer);
static int __init parse_nolapic_timer(char *arg)
{
disable_apic_timer = 1;
return 0;
}
early_param("nolapic_timer", parse_nolapic_timer);
static int __init apic_set_verbosity(char *arg)
{
if (!arg) {
#ifdef CONFIG_X86_64
skip_ioapic_setup = 0;
return 0;
#endif
return -EINVAL;
}
if (strcmp("debug", arg) == 0)
apic_verbosity = APIC_DEBUG;
else if (strcmp("verbose", arg) == 0)
apic_verbosity = APIC_VERBOSE;
else {
pr_warning("APIC Verbosity level %s not recognised"
" use apic=verbose or apic=debug\n", arg);
return -EINVAL;
}
return 0;
}
early_param("apic", apic_set_verbosity);
x86: insert_resorce for lapic addr after e820_reserve_resources when comparing the e820 direct from BIOS, and the one by kexec: BIOS-provided physical RAM map: - BIOS-e820: 0000000000000000 - 0000000000097400 (usable) + BIOS-e820: 0000000000000100 - 0000000000097400 (usable) BIOS-e820: 0000000000097400 - 00000000000a0000 (reserved) BIOS-e820: 00000000000e6000 - 0000000000100000 (reserved) BIOS-e820: 0000000000100000 - 00000000dffa0000 (usable) - BIOS-e820: 00000000dffae000 - 00000000dffb0000 type 9 + BIOS-e820: 00000000dffae000 - 00000000dffb0000 (reserved) BIOS-e820: 00000000dffb0000 - 00000000dffbe000 (ACPI data) BIOS-e820: 00000000dffbe000 - 00000000dfff0000 (ACPI NVS) BIOS-e820: 00000000dfff0000 - 00000000e0000000 (reserved) BIOS-e820: 00000000fec00000 - 00000000fec01000 (reserved) - BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved) =======> that is the local apic address... somewhere we lost it BIOS-e820: 00000000ff700000 - 0000000100000000 (reserved) BIOS-e820: 0000000100000000 - 0000004020000000 (usable) found one entry about reserved is missing for the kernel by kexec. it turns out init_apic_mappings is called before e820_reserve_resources in setup_arch. but e820_reserve_resources is using request_resource. it will not handle the conflicts. there are three ways to fix it: 1. change request_resource in e820_reserve_resources to to insert_resource 2. move init_apic_mappings after e820_reserve_resources 3. use late_initcall to insert lapic resource. this patch is using method 3, that is less intrusive. in later version could consider to use method 1. before patch fed20000-ffffffff : PCI Bus #00 fee00000-fee00fff : Local APIC fefff000-feffffff : pnp 00:09 ff700000-ffffffff : reserved with patch will get map in first kernel fed20000-ffffffff : PCI Bus #00 fee00000-fee00fff : Local APIC fee00000-fee00fff : reserved fefff000-feffffff : pnp 00:09 ff700000-ffffffff : reserved Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-23 05:37:26 +08:00
static int __init lapic_insert_resource(void)
{
if (!apic_phys)
return -1;
/* 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);
return 0;
}
/*
* need call insert after e820_reserve_resources()
* that is using request_resource
*/
late_initcall(lapic_insert_resource);