aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/apic/apic.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/apic/apic.c')
-rw-r--r--arch/x86/kernel/apic/apic.c981
1 files changed, 625 insertions, 356 deletions
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3f838d53739..ad28db7e6bd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -24,41 +24,45 @@
#include <linux/ftrace.h>
#include <linux/ioport.h>
#include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/timex.h>
+#include <linux/i8253.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>
+#include <asm/trace/irq_vectors.h>
+#include <asm/irq_remapping.h>
#include <asm/perf_event.h>
#include <asm/x86_init.h>
#include <asm/pgalloc.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/mpspec.h>
-#include <asm/i8253.h>
#include <asm/i8259.h>
#include <asm/proto.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/idle.h>
#include <asm/mtrr.h>
+#include <asm/time.h>
#include <asm/smp.h>
#include <asm/mce.h>
-#include <asm/kvm_para.h>
#include <asm/tsc.h>
+#include <asm/hypervisor.h>
unsigned int num_processors;
-unsigned disabled_cpus __cpuinitdata;
+unsigned disabled_cpus;
/* Processor that is doing the boot up */
unsigned int boot_cpu_physical_apicid = -1U;
+EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
/*
* The highest APIC ID seen during enumeration.
@@ -71,29 +75,30 @@ unsigned int max_physical_apicid;
physid_mask_t phys_cpu_present_map;
/*
+ * Processor to be disabled specified by kernel parameter
+ * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
+ * avoid undefined behaviour caused by sending INIT from AP to BSP.
+ */
+static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
+
+/*
* 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);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(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
+ * On x86_32, the mapping between cpu and logical apicid may vary
+ * depending on apic in use. The following early percpu variable is
+ * used for the mapping. This is where the behaviors of x86_64 and 32
+ * actually diverge. Let's keep it ugly for now.
*/
-static int __init parse_lapic(char *arg)
-{
- force_enable_local_apic = 1;
- return 0;
-}
-early_param("lapic", parse_lapic);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
+
/* Local APIC was disabled by the BIOS and enabled by the kernel */
static int enabled_via_apicbase;
@@ -122,6 +127,29 @@ static inline void imcr_apic_to_pic(void)
}
#endif
+/*
+ * Knob to control our willingness to enable the local APIC.
+ *
+ * +1=force-enable
+ */
+static int force_enable_local_apic __initdata;
+
+/* Control whether x2APIC mode is enabled or not */
+static bool nox2apic __initdata;
+
+/*
+ * APIC command line parameters
+ */
+static int __init parse_lapic(char *arg)
+{
+ if (config_enabled(CONFIG_X86_32) && !arg)
+ force_enable_local_apic = 1;
+ else if (arg && !strncmp(arg, "notscdeadline", 13))
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+ return 0;
+}
+early_param("lapic", parse_lapic);
+
#ifdef CONFIG_X86_64
static int apic_calibrate_pmtmr __initdata;
static __init int setup_apicpmtimer(char *s)
@@ -136,16 +164,25 @@ __setup("apicpmtimer", setup_apicpmtimer);
int x2apic_mode;
#ifdef CONFIG_X86_X2APIC
/* x2apic enabled before OS handover */
-static int x2apic_preenabled;
-static __init int setup_nox2apic(char *str)
+int x2apic_preenabled;
+static int x2apic_disabled;
+static int __init setup_nox2apic(char *str)
{
if (x2apic_enabled()) {
- pr_warning("Bios already enabled x2apic, "
- "can't enforce nox2apic");
- return 0;
- }
+ int apicid = native_apic_msr_read(APIC_ID);
+
+ if (apicid >= 255) {
+ pr_warning("Apicid: %08x, cannot enforce nox2apic\n",
+ apicid);
+ return 0;
+ }
+
+ pr_warning("x2apic already enabled. will disable it\n");
+ } else
+ setup_clear_cpu_cap(X86_FEATURE_X2APIC);
+
+ nox2apic = true;
- setup_clear_cpu_cap(X86_FEATURE_X2APIC);
return 0;
}
early_param("nox2apic", setup_nox2apic);
@@ -154,7 +191,7 @@ early_param("nox2apic", setup_nox2apic);
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;
+static int disable_apic_timer __initdata;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -176,31 +213,10 @@ static struct resource lapic_resource = {
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};
-static unsigned int calibration_result;
+unsigned int lapic_timer_frequency = 0;
-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;
/*
@@ -239,7 +255,7 @@ static int modern_apic(void)
* right after this call apic become NOOP driven
* so apic->write/read doesn't do anything
*/
-void apic_disable(void)
+static void __init apic_disable(void)
{
pr_info("APIC: switched to apic NOOP\n");
apic = &apic_noop;
@@ -261,6 +277,7 @@ u32 native_safe_apic_wait_icr_idle(void)
send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
if (!send_status)
break;
+ inc_irq_stat(icr_read_retry_count);
udelay(100);
} while (timeout++ < 1000);
@@ -269,8 +286,12 @@ u32 native_safe_apic_wait_icr_idle(void)
void native_apic_icr_write(u32 low, u32 id)
{
+ unsigned long flags;
+
+ local_irq_save(flags);
apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
apic_write(APIC_ICR, low);
+ local_irq_restore(flags);
}
u64 native_apic_icr_read(void)
@@ -283,23 +304,6 @@ u64 native_apic_icr_read(void)
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
@@ -331,6 +335,7 @@ int lapic_get_maxlvt(void)
/* Clock divisor */
#define APIC_DIVISOR 16
+#define TSC_DIVISOR 32
/*
* This function sets up the local APIC timer, with a timeout of
@@ -349,6 +354,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
lvtt_value = LOCAL_TIMER_VECTOR;
if (!oneshot)
lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+ else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE;
+
if (!lapic_is_integrated())
lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
@@ -357,6 +365,11 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
apic_write(APIC_LVTT, lvtt_value);
+ if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) {
+ printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
+ return;
+ }
+
/*
* Divide PICLK by 16
*/
@@ -400,26 +413,32 @@ static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
{
- unsigned int rsvd; /* 0: uninitialized */
+ unsigned int rsvd, vector;
if (offset >= APIC_EILVT_NR_MAX)
return ~0;
- rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+ rsvd = atomic_read(&eilvt_offsets[offset]);
do {
- if (rsvd &&
- !eilvt_entry_is_changeable(rsvd, new))
+ vector = rsvd & ~APIC_EILVT_MASKED; /* 0: unassigned */
+ if (vector && !eilvt_entry_is_changeable(vector, new))
/* may not change if vectors are different */
return rsvd;
rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
} while (rsvd != new);
+ rsvd &= ~APIC_EILVT_MASKED;
+ if (rsvd && rsvd != vector)
+ pr_info("LVT offset %d assigned for vector 0x%02x\n",
+ offset, rsvd);
+
return new;
}
/*
* If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * enables the vector. See also the BKDGs. Must be called with
+ * preemption disabled.
*/
int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
@@ -432,17 +451,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
reserved = reserve_eilvt_offset(offset, new);
if (reserved != new) {
- pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
- "vector 0x%x was already reserved by another core, "
- "APIC%lX=0x%x\n",
- smp_processor_id(), new, reserved, reg, old);
+ pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+ "vector 0x%x, but the register is already in use for "
+ "vector 0x%x on another cpu\n",
+ smp_processor_id(), reg, offset, new, reserved);
return -EINVAL;
}
if (!eilvt_entry_is_changeable(old, new)) {
- pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
- "register already in use, APIC%lX=0x%x\n",
- smp_processor_id(), new, reg, old);
+ pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+ "vector 0x%x, but the register is already in use for "
+ "vector 0x%x on this cpu\n",
+ smp_processor_id(), reg, offset, new, old);
return -EBUSY;
}
@@ -462,6 +482,16 @@ static int lapic_next_event(unsigned long delta,
return 0;
}
+static int lapic_next_deadline(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ u64 tsc;
+
+ rdtscll(tsc);
+ wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
+ return 0;
+}
+
/*
* Setup the lapic timer in periodic or oneshot mode
*/
@@ -480,7 +510,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
switch (mode) {
case CLOCK_EVT_MODE_PERIODIC:
case CLOCK_EVT_MODE_ONESHOT:
- __setup_APIC_LVTT(calibration_result,
+ __setup_APIC_LVTT(lapic_timer_frequency,
mode != CLOCK_EVT_MODE_PERIODIC, 1);
break;
case CLOCK_EVT_MODE_UNUSED:
@@ -508,15 +538,32 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
#endif
}
+
+/*
+ * 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);
+
/*
* Setup the local APIC timer for this CPU. Copy the initialized values
* of the boot CPU and register the clock event in the framework.
*/
-static void __cpuinit setup_APIC_timer(void)
+static void setup_APIC_timer(void)
{
struct clock_event_device *levt = &__get_cpu_var(lapic_events);
- if (cpu_has(&current_cpu_data, X86_FEATURE_ARAT)) {
+ if (this_cpu_has(X86_FEATURE_ARAT)) {
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
/* Make LAPIC timer preferrable over percpu HPET */
lapic_clockevent.rating = 150;
@@ -525,7 +572,15 @@ static void __cpuinit setup_APIC_timer(void)
memcpy(levt, &lapic_clockevent, sizeof(*levt));
levt->cpumask = cpumask_of(smp_processor_id());
- clockevents_register_device(levt);
+ if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
+ levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_DUMMY);
+ levt->set_next_event = lapic_next_deadline;
+ clockevents_config_and_register(levt,
+ (tsc_khz / TSC_DIVISOR) * 1000,
+ 0xF, ~0UL);
+ } else
+ clockevents_register_device(levt);
}
/*
@@ -647,6 +702,30 @@ static int __init calibrate_APIC_clock(void)
long delta, deltatsc;
int pm_referenced = 0;
+ /**
+ * check if lapic timer has already been calibrated by platform
+ * specific routine, such as tsc calibration code. if so, we just fill
+ * in the clockevent structure and return.
+ */
+
+ if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
+ return 0;
+ } else if (lapic_timer_frequency) {
+ apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
+ lapic_timer_frequency);
+ lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+ TICK_NSEC, lapic_clockevent.shift);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+ return 0;
+ }
+
+ apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
+ "calibrating APIC timer ...\n");
+
local_irq_disable();
/* Replace the global interrupt handler */
@@ -684,16 +763,16 @@ static int __init calibrate_APIC_clock(void)
lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
- calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+ lapic_timer_frequency = (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);
+ lapic_timer_frequency);
if (cpu_has_tsc) {
apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -704,13 +783,13 @@ static int __init calibrate_APIC_clock(void)
apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
"%u.%04u MHz.\n",
- calibration_result / (1000000 / HZ),
- calibration_result % (1000000 / HZ));
+ lapic_timer_frequency / (1000000 / HZ),
+ lapic_timer_frequency % (1000000 / HZ));
/*
* Do a sanity check on the APIC calibration result
*/
- if (calibration_result < (1000000 / HZ)) {
+ if (lapic_timer_frequency < (1000000 / HZ)) {
local_irq_enable();
pr_warning("APIC frequency too slow, disabling apic timer\n");
return -1;
@@ -784,9 +863,6 @@ void __init setup_boot_APIC_clock(void)
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)
@@ -799,17 +875,13 @@ void __init setup_boot_APIC_clock(void)
* 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);
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
/* Setup the lapic or request the broadcast */
setup_APIC_timer();
}
-void __cpuinit setup_secondary_APIC_clock(void)
+void setup_secondary_APIC_clock(void)
{
setup_APIC_timer();
}
@@ -856,24 +928,42 @@ static void local_apic_timer_interrupt(void)
* [ 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)
+__visible 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.
+ *
+ * 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.
*/
- ack_APIC_irq();
+ entering_ack_irq();
+ local_apic_timer_interrupt();
+ exiting_irq();
+
+ set_irq_regs(old_regs);
+}
+
+__visible void __irq_entry smp_trace_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.
+ *
* 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();
+ entering_ack_irq();
+ trace_local_timer_entry(LOCAL_TIMER_VECTOR);
local_apic_timer_interrupt();
- irq_exit();
+ trace_local_timer_exit(LOCAL_TIMER_VECTOR);
+ exiting_irq();
set_irq_regs(old_regs);
}
@@ -1154,7 +1244,7 @@ void __init init_bsp_APIC(void)
apic_write(APIC_LVT1, value);
}
-static void __cpuinit lapic_setup_esr(void)
+static void lapic_setup_esr(void)
{
unsigned int oldvalue, value, maxlvt;
@@ -1195,12 +1285,15 @@ static void __cpuinit lapic_setup_esr(void)
oldvalue, value);
}
-
/**
* setup_local_APIC - setup the local APIC
+ *
+ * Used to setup local APIC while initializing BSP or bringin up APs.
+ * Always called with preemption disabled.
*/
-void __cpuinit setup_local_APIC(void)
+void setup_local_APIC(void)
{
+ int cpu = smp_processor_id();
unsigned int value, queued;
int i, j, acked = 0;
unsigned long long tsc = 0, ntsc;
@@ -1210,7 +1303,7 @@ void __cpuinit setup_local_APIC(void)
rdtscll(tsc);
if (disable_apic) {
- arch_disable_smp_support();
+ disable_ioapic_support();
return;
}
@@ -1225,8 +1318,6 @@ void __cpuinit setup_local_APIC(void)
#endif
perf_events_lapic_init();
- preempt_disable();
-
/*
* Double-check whether this APIC is really registered.
* This is meaningless in clustered apic mode, so we skip it.
@@ -1240,6 +1331,30 @@ void __cpuinit setup_local_APIC(void)
*/
apic->init_apic_ldr();
+#ifdef CONFIG_X86_32
+ /*
+ * APIC LDR is initialized. If logical_apicid mapping was
+ * initialized during get_smp_config(), make sure it matches the
+ * actual value.
+ */
+ i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+ WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
+ /* always use the value from LDR */
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+ logical_smp_processor_id();
+
+ /*
+ * Some NUMA implementations (NUMAQ) don't initialize apicid to
+ * node mapping during NUMA init. Now that logical apicid is
+ * guaranteed to be known, give it another chance. This is already
+ * a bit too late - percpu allocation has already happened without
+ * proper NUMA affinity.
+ */
+ if (apic->x86_32_numa_cpu_node)
+ set_apicid_to_node(early_per_cpu(x86_cpu_to_apicid, cpu),
+ apic->x86_32_numa_cpu_node(cpu));
+#endif
+
/*
* Set Task Priority to 'accept all'. We never change this
* later on.
@@ -1278,11 +1393,13 @@ void __cpuinit setup_local_APIC(void)
acked);
break;
}
- if (cpu_has_tsc) {
- rdtscll(ntsc);
- max_loops = (cpu_khz << 10) - (ntsc - tsc);
- } else
- max_loops--;
+ if (queued) {
+ if (cpu_has_tsc) {
+ rdtscll(ntsc);
+ max_loops = (cpu_khz << 10) - (ntsc - tsc);
+ } else
+ max_loops--;
+ }
} while (queued && max_loops > 0);
WARN_ON(max_loops <= 0);
@@ -1342,21 +1459,19 @@ void __cpuinit setup_local_APIC(void)
* 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)) {
+ if (!cpu && (pic_mode || !value)) {
value = APIC_DM_EXTINT;
- apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n",
- smp_processor_id());
+ apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu);
} else {
value = APIC_DM_EXTINT | APIC_LVT_MASKED;
- apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n",
- smp_processor_id());
+ apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n", cpu);
}
apic_write(APIC_LVT0, value);
/*
* only the BP should see the LINT1 NMI signal, obviously.
*/
- if (!smp_processor_id())
+ if (!cpu)
value = APIC_DM_NMI;
else
value = APIC_DM_NMI | APIC_LVT_MASKED;
@@ -1364,16 +1479,14 @@ void __cpuinit setup_local_APIC(void)
value |= APIC_LVT_LEVEL_TRIGGER;
apic_write(APIC_LVT1, value);
- preempt_enable();
-
#ifdef CONFIG_X86_MCE_INTEL
/* Recheck CMCI information after local APIC is up on CPU #0 */
- if (smp_processor_id() == 0)
+ if (!cpu)
cmci_recheck();
#endif
}
-void __cpuinit end_local_APIC_setup(void)
+void end_local_APIC_setup(void)
{
lapic_setup_esr();
@@ -1387,11 +1500,61 @@ void __cpuinit end_local_APIC_setup(void)
}
#endif
- setup_apic_nmi_watchdog(NULL);
apic_pm_activate();
}
+void __init bsp_end_local_APIC_setup(void)
+{
+ end_local_APIC_setup();
+
+ /*
+ * Now that local APIC setup is completed for BP, configure the fault
+ * handling for interrupt remapping.
+ */
+ irq_remap_enable_fault_handling();
+
+}
+
#ifdef CONFIG_X86_X2APIC
+/*
+ * Need to disable xapic and x2apic at the same time and then enable xapic mode
+ */
+static inline void __disable_x2apic(u64 msr)
+{
+ wrmsrl(MSR_IA32_APICBASE,
+ msr & ~(X2APIC_ENABLE | XAPIC_ENABLE));
+ wrmsrl(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE);
+}
+
+static __init void disable_x2apic(void)
+{
+ u64 msr;
+
+ if (!cpu_has_x2apic)
+ return;
+
+ rdmsrl(MSR_IA32_APICBASE, msr);
+ if (msr & X2APIC_ENABLE) {
+ u32 x2apic_id = read_apic_id();
+
+ if (x2apic_id >= 255)
+ panic("Cannot disable x2apic, id: %08x\n", x2apic_id);
+
+ pr_info("Disabling x2apic\n");
+ __disable_x2apic(msr);
+
+ if (nox2apic) {
+ clear_cpu_cap(&cpu_data(0), X86_FEATURE_X2APIC);
+ setup_clear_cpu_cap(X86_FEATURE_X2APIC);
+ }
+
+ x2apic_disabled = 1;
+ x2apic_mode = 0;
+
+ register_lapic_address(mp_lapic_addr);
+ }
+}
+
void check_x2apic(void)
{
if (x2apic_enabled()) {
@@ -1402,82 +1565,87 @@ void check_x2apic(void)
void enable_x2apic(void)
{
- int msr, msr2;
+ u64 msr;
+
+ rdmsrl(MSR_IA32_APICBASE, msr);
+ if (x2apic_disabled) {
+ __disable_x2apic(msr);
+ return;
+ }
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);
+ wrmsrl(MSR_IA32_APICBASE, msr | X2APIC_ENABLE);
}
}
#endif /* CONFIG_X86_X2APIC */
int __init enable_IR(void)
{
-#ifdef CONFIG_INTR_REMAP
- if (!intr_remapping_supported()) {
+#ifdef CONFIG_IRQ_REMAP
+ if (!irq_remapping_supported()) {
pr_debug("intr-remapping not supported\n");
- return 0;
+ return -1;
}
if (!x2apic_preenabled && skip_ioapic_setup) {
pr_info("Skipped enabling intr-remap because of skipping "
"io-apic setup\n");
- return 0;
+ return -1;
}
- if (enable_intr_remapping(x2apic_supported()))
- return 0;
-
- pr_info("Enabled Interrupt-remapping\n");
-
- return 1;
-
+ return irq_remapping_enable();
#endif
- return 0;
+ return -1;
}
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;
+ int hardware_init_ret;
- dmar_table_init_ret = dmar_table_init();
- if (dmar_table_init_ret && !x2apic_supported())
- return;
+ /* Make sure irq_remap_ops are initialized */
+ setup_irq_remapping_ops();
- ioapic_entries = alloc_ioapic_entries();
- if (!ioapic_entries) {
- pr_err("Allocate ioapic_entries failed\n");
- goto out;
- }
+ hardware_init_ret = irq_remapping_prepare();
+ if (hardware_init_ret && !x2apic_supported())
+ return;
- ret = save_IO_APIC_setup(ioapic_entries);
+ ret = save_ioapic_entries();
if (ret) {
pr_info("Saving IO-APIC state failed: %d\n", ret);
- goto out;
+ return;
}
local_irq_save(flags);
legacy_pic->mask_all();
- mask_IO_APIC_setup(ioapic_entries);
+ mask_ioapic_entries();
- if (dmar_table_init_ret)
- ret = 0;
+ if (x2apic_preenabled && nox2apic)
+ disable_x2apic();
+
+ if (hardware_init_ret)
+ ret = -1;
else
ret = enable_IR();
- if (!ret) {
+ if (!x2apic_supported())
+ goto skip_x2apic;
+
+ if (ret < 0) {
/* IR is required if there is APIC ID > 255 even when running
* under KVM
*/
- if (max_physical_apicid > 255 || !kvm_para_available())
- goto nox2apic;
+ if (max_physical_apicid > 255 ||
+ !hypervisor_x2apic_available()) {
+ if (x2apic_preenabled)
+ disable_x2apic();
+ goto skip_x2apic;
+ }
/*
* without IR all CPUs can be addressed by IOAPIC/MSI
* only in physical mode
@@ -1485,6 +1653,11 @@ void __init enable_IR_x2apic(void)
x2apic_force_phys();
}
+ if (ret == IRQ_REMAP_XAPIC_MODE) {
+ pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n");
+ goto skip_x2apic;
+ }
+
x2apic_enabled = 1;
if (x2apic_supported() && !x2apic_mode) {
@@ -1493,23 +1666,11 @@ void __init enable_IR_x2apic(void)
pr_info("Enabled x2apic\n");
}
-nox2apic:
- if (!ret) /* IR enabling failed */
- restore_IO_APIC_setup(ioapic_entries);
+skip_x2apic:
+ if (ret < 0) /* IR enabling failed */
+ restore_ioapic_entries();
legacy_pic->restore_mask();
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
@@ -1530,13 +1691,64 @@ static int __init detect_init_APIC(void)
return 0;
}
#else
+
+static int __init apic_verify(void)
+{
+ u32 features, h, l;
+
+ /*
+ * 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 */
+ if (boot_cpu_data.x86 >= 6) {
+ 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");
+ return 0;
+}
+
+int __init apic_force_enable(unsigned long addr)
+{
+ u32 h, l;
+
+ if (disable_apic)
+ 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.
+ */
+ if (boot_cpu_data.x86 >= 6) {
+ 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 | addr;
+ wrmsr(MSR_IA32_APICBASE, l, h);
+ enabled_via_apicbase = 1;
+ }
+ }
+ return apic_verify();
+}
+
/*
* Detect and initialize APIC
*/
static int __init detect_init_APIC(void)
{
- u32 h, l, features;
-
/* Disabled by kernel option? */
if (disable_apic)
return -1;
@@ -1566,38 +1778,12 @@ static int __init detect_init_APIC(void)
"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;
+ if (apic_force_enable(APIC_DEFAULT_PHYS_BASE))
+ return -1;
+ } else {
+ if (apic_verify())
+ 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();
@@ -1609,28 +1795,6 @@ no_apic:
}
#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
*/
@@ -1656,10 +1820,7 @@ void __init init_apic_mappings(void)
* acpi_register_lapic_address()
*/
if (!acpi_lapic && !smp_found_config)
- set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
-
- apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
- APIC_BASE, apic_phys);
+ register_lapic_address(apic_phys);
}
/*
@@ -1681,11 +1842,27 @@ void __init init_apic_mappings(void)
}
}
+void __init register_lapic_address(unsigned long address)
+{
+ mp_lapic_addr = address;
+
+ if (!x2apic_mode) {
+ set_fixmap_nocache(FIX_APIC_BASE, address);
+ apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
+ APIC_BASE, mp_lapic_addr);
+ }
+ if (boot_cpu_physical_apicid == -1U) {
+ boot_cpu_physical_apicid = read_apic_id();
+ apic_version[boot_cpu_physical_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 apic_version[MAX_LOCAL_APIC];
int __init APIC_init_uniprocessor(void)
{
@@ -1743,24 +1920,17 @@ int __init APIC_init_uniprocessor(void)
enable_IO_APIC();
#endif
- end_local_APIC_setup();
+ bsp_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;
}
@@ -1771,12 +1941,10 @@ int __init APIC_init_uniprocessor(void)
/*
* This interrupt should _never_ happen with our APIC/SMP architecture
*/
-void smp_spurious_interrupt(struct pt_regs *regs)
+static inline void __smp_spurious_interrupt(void)
{
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...
@@ -1791,39 +1959,78 @@ void smp_spurious_interrupt(struct pt_regs *regs)
/* 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();
+}
+
+__visible void smp_spurious_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ __smp_spurious_interrupt();
+ exiting_irq();
+}
+
+__visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
+ __smp_spurious_interrupt();
+ trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR);
+ exiting_irq();
}
/*
* This interrupt should never happen with our APIC/SMP architecture
*/
-void smp_error_interrupt(struct pt_regs *regs)
+static inline void __smp_error_interrupt(struct pt_regs *regs)
{
- u32 v, v1;
+ u32 v;
+ u32 i = 0;
+ static const char * const error_interrupt_reason[] = {
+ "Send CS error", /* APIC Error Bit 0 */
+ "Receive CS error", /* APIC Error Bit 1 */
+ "Send accept error", /* APIC Error Bit 2 */
+ "Receive accept error", /* APIC Error Bit 3 */
+ "Redirectable IPI", /* APIC Error Bit 4 */
+ "Send illegal vector", /* APIC Error Bit 5 */
+ "Received illegal vector", /* APIC Error Bit 6 */
+ "Illegal register address", /* APIC Error Bit 7 */
+ };
- exit_idle();
- irq_enter();
/* First tickle the hardware, only then report what went on. -- REW */
+ if (lapic_get_maxlvt() > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
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();
+ apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x",
+ smp_processor_id(), v);
+
+ v &= 0xff;
+ while (v) {
+ if (v & 0x1)
+ apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
+ i++;
+ v >>= 1;
+ }
+
+ apic_printk(APIC_DEBUG, KERN_CONT "\n");
+
+}
+
+__visible void smp_error_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ __smp_error_interrupt(regs);
+ exiting_irq();
+}
+
+__visible void smp_trace_error_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ trace_error_apic_entry(ERROR_APIC_VECTOR);
+ __smp_error_interrupt(regs);
+ trace_error_apic_exit(ERROR_APIC_VECTOR);
+ exiting_irq();
}
/**
@@ -1915,23 +2122,62 @@ void disconnect_bsp_APIC(int virt_wire_setup)
apic_write(APIC_LVT1, value);
}
-void __cpuinit generic_processor_info(int apicid, int version)
+int generic_processor_info(int apicid, int version)
{
- int cpu;
+ int cpu, max = nr_cpu_ids;
+ bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
+ phys_cpu_present_map);
/*
- * Validate version
+ * boot_cpu_physical_apicid is designed to have the apicid
+ * returned by read_apic_id(), i.e, the apicid of the
+ * currently booting-up processor. However, on some platforms,
+ * it is temporarily modified by the apicid reported as BSP
+ * through MP table. Concretely:
+ *
+ * - arch/x86/kernel/mpparse.c: MP_processor_info()
+ * - arch/x86/mm/amdtopology.c: amd_numa_init()
+ *
+ * This function is executed with the modified
+ * boot_cpu_physical_apicid. So, disabled_cpu_apicid kernel
+ * parameter doesn't work to disable APs on kdump 2nd kernel.
+ *
+ * Since fixing handling of boot_cpu_physical_apicid requires
+ * another discussion and tests on each platform, we leave it
+ * for now and here we use read_apic_id() directly in this
+ * function, generic_processor_info().
*/
- 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;
+ if (disabled_cpu_apicid != BAD_APICID &&
+ disabled_cpu_apicid != read_apic_id() &&
+ disabled_cpu_apicid == apicid) {
+ int thiscpu = num_processors + disabled_cpus;
+
+ pr_warning("APIC: Disabling requested cpu."
+ " Processor %d/0x%x ignored.\n",
+ thiscpu, apicid);
+
+ disabled_cpus++;
+ return -ENODEV;
+ }
+
+ /*
+ * If boot cpu has not been detected yet, then only allow upto
+ * nr_cpu_ids - 1 processors and keep one slot free for boot cpu
+ */
+ if (!boot_cpu_detected && num_processors >= nr_cpu_ids - 1 &&
+ apicid != boot_cpu_physical_apicid) {
+ int thiscpu = max + disabled_cpus - 1;
+
+ pr_warning(
+ "ACPI: NR_CPUS/possible_cpus limit of %i almost"
+ " reached. Keeping one slot for boot cpu."
+ " Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
+
+ disabled_cpus++;
+ return -ENODEV;
}
- apic_version[apicid] = version;
if (num_processors >= nr_cpu_ids) {
- int max = nr_cpu_ids;
int thiscpu = max + disabled_cpus;
pr_warning(
@@ -1939,26 +2185,38 @@ void __cpuinit generic_processor_info(int apicid, int version)
" Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
disabled_cpus++;
- return;
+ return -EINVAL;
}
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.
+ * boot_cpu_init() already hold bit 0 in cpu_present_mask
+ * for BSP.
*/
cpu = 0;
+ } else
+ cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+ /*
+ * Validate version
+ */
+ if (version == 0x0) {
+ pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
+ cpu, apicid);
+ version = 0x10;
+ }
+ apic_version[apicid] = version;
+
+ if (version != apic_version[boot_cpu_physical_apicid]) {
+ pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
+ apic_version[boot_cpu_physical_apicid], cpu, version);
}
+
+ physid_set(apicid, phys_cpu_present_map);
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
@@ -1966,9 +2224,14 @@ void __cpuinit generic_processor_info(int apicid, int version)
early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
-
+#ifdef CONFIG_X86_32
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+ apic->x86_32_early_logical_apicid(cpu);
+#endif
set_cpu_possible(cpu, true);
set_cpu_present(cpu, true);
+
+ return cpu;
}
int hard_smp_processor_id(void)
@@ -1986,16 +2249,41 @@ void default_init_apic_ldr(void)
apic_write(APIC_LDR, val);
}
-#ifdef CONFIG_X86_32
-int default_apicid_to_node(int logical_apicid)
+int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask,
+ unsigned int *apicid)
{
-#ifdef CONFIG_SMP
- return apicid_2_node[hard_smp_processor_id()];
-#else
- return 0;
-#endif
+ unsigned int cpu;
+
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+
+ if (likely(cpu < nr_cpu_ids)) {
+ *apicid = per_cpu(x86_cpu_to_apicid, cpu);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+/*
+ * Override the generic EOI implementation with an optimized version.
+ * Only called during early boot when only one CPU is active and with
+ * interrupts disabled, so we know this does not race with actual APIC driver
+ * use.
+ */
+void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v))
+{
+ struct apic **drv;
+
+ for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+ /* Should happen once for each apic */
+ WARN_ON((*drv)->eoi_write == eoi_write);
+ (*drv)->eoi_write = eoi_write;
+ }
}
-#endif
/*
* Power management
@@ -2025,7 +2313,7 @@ static struct {
unsigned int apic_thmr;
} apic_pm_state;
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
+static int lapic_suspend(void)
{
unsigned long flags;
int maxlvt;
@@ -2056,43 +2344,31 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
local_irq_save(flags);
disable_local_APIC();
- if (intr_remapping_enabled)
- disable_intr_remapping();
+ irq_remapping_disable();
local_irq_restore(flags);
return 0;
}
-static int lapic_resume(struct sys_device *dev)
+static void lapic_resume(void)
{
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;
+ return;
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);
- legacy_pic->mask_all();
- }
+ /*
+ * IO-APIC and PIC have their own resume routines.
+ * We just mask them here to make sure the interrupt
+ * subsystem is completely quiet while we enable x2apic
+ * and interrupt-remapping.
+ */
+ mask_ioapic_entries();
+ legacy_pic->mask_all();
if (x2apic_mode)
enable_x2apic();
@@ -2103,10 +2379,12 @@ static int lapic_resume(struct sys_device *dev)
* 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);
+ if (boot_cpu_data.x86 >= 6) {
+ 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();
@@ -2118,7 +2396,7 @@ static int lapic_resume(struct sys_device *dev)
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 defined(CONFIG_X86_MCE_INTEL)
if (maxlvt >= 5)
apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
#endif
@@ -2133,16 +2411,9 @@ static int lapic_resume(struct sys_device *dev)
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
- if (intr_remapping_enabled) {
- reenable_intr_remapping(x2apic_mode);
- legacy_pic->restore_mask();
- restore_IO_APIC_setup(ioapic_entries);
- free_ioapic_entries(ioapic_entries);
- }
-restore:
- local_irq_restore(flags);
+ irq_remapping_reenable(x2apic_mode);
- return ret;
+ local_irq_restore(flags);
}
/*
@@ -2150,34 +2421,23 @@ restore:
* are needed on every CPU up until machine_halt/restart/poweroff.
*/
-static struct sysdev_class lapic_sysclass = {
- .name = "lapic",
+static struct syscore_ops lapic_syscore_ops = {
.resume = lapic_resume,
.suspend = lapic_suspend,
};
-static struct sys_device device_lapic = {
- .id = 0,
- .cls = &lapic_sysclass,
-};
-
-static void __cpuinit apic_pm_activate(void)
+static void 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? */
+ if (cpu_has_apic)
+ register_syscore_ops(&lapic_syscore_ops);
- error = sysdev_class_register(&lapic_sysclass);
- if (!error)
- error = sysdev_register(&device_lapic);
- return error;
+ return 0;
}
/* local apic needs to resume before other devices access its registers. */
@@ -2191,7 +2451,7 @@ static void apic_pm_activate(void) { }
#ifdef CONFIG_X86_64
-static int __cpuinit apic_cluster_num(void)
+static int apic_cluster_num(void)
{
int i, clusters, zeros;
unsigned id;
@@ -2236,10 +2496,10 @@ static int __cpuinit apic_cluster_num(void)
return clusters;
}
-static int __cpuinitdata multi_checked;
-static int __cpuinitdata multi;
+static int multi_checked;
+static int multi;
-static int __cpuinit set_multi(const struct dmi_system_id *d)
+static int set_multi(const struct dmi_system_id *d)
{
if (multi)
return 0;
@@ -2248,7 +2508,7 @@ static int __cpuinit set_multi(const struct dmi_system_id *d)
return 0;
}
-static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+static const struct dmi_system_id multi_dmi_table[] = {
{
.callback = set_multi,
.ident = "IBM System Summit2",
@@ -2260,7 +2520,7 @@ static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
{}
};
-static void __cpuinit dmi_check_multi(void)
+static void dmi_check_multi(void)
{
if (multi_checked)
return;
@@ -2277,7 +2537,7 @@ static void __cpuinit dmi_check_multi(void)
* multi-chassis.
* Use DMI to check them
*/
-__cpuinit int apic_is_clustered_box(void)
+int apic_is_clustered_box(void)
{
dmi_check_multi();
if (multi)
@@ -2378,3 +2638,12 @@ static int __init lapic_insert_resource(void)
* that is using request_resource
*/
late_initcall(lapic_insert_resource);
+
+static int __init apic_set_disabled_cpu_apicid(char *arg)
+{
+ if (!arg || !get_option(&arg, &disabled_cpu_apicid))
+ return -EINVAL;
+
+ return 0;
+}
+early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-05 08:19:54 +0000