x86, apic: move APIC drivers to arch/x86/kernel/apic/*
arch/x86/kernel/ is getting a bit crowded, and the APIC
drivers are scattered into various different files.
Move them to arch/x86/kernel/apic/*, and also remove
the 'gen' prefix from those which had it.
Also move APIC related functionality: the IO-APIC driver,
the NMI and the IPI code.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
new file mode 100644
index 0000000..da20b70
--- /dev/null
+++ b/arch/x86/kernel/apic/Makefile
@@ -0,0 +1,15 @@
+#
+# Makefile for local APIC drivers and for the IO-APIC code
+#
+
+obj-y := apic.o ipi.o nmi.o
+obj-$(CONFIG_X86_IO_APIC) += io_apic.o
+obj-$(CONFIG_SMP) += ipi.o
+
+ifeq ($(CONFIG_X86_64),y)
+obj-y += apic_64.o apic_flat_64.o
+obj-$(CONFIG_X86_X2APIC) += x2apic_cluster.o
+obj-$(CONFIG_X86_X2APIC) += x2apic_phys.o
+obj-$(CONFIG_X86_UV) += x2apic_uv_x.o
+endif
+
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
new file mode 100644
index 0000000..c12823e
--- /dev/null
+++ b/arch/x86/kernel/apic/apic.c
@@ -0,0 +1,2212 @@
+/*
+ * 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.
+ */
+
+#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>
+
+#include <asm/arch_hooks.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>
+
+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;
+
+#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
+
+#ifdef CONFIG_X86_X2APIC
+int x2apic;
+/* x2apic enabled before OS handover */
+static int x2apic_preenabled;
+static int disable_x2apic;
+static __init int setup_nox2apic(char *str)
+{
+ disable_x2apic = 1;
+ 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;
+
+/* 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;
+}
+
+void native_apic_wait_icr_idle(void)
+{
+ while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
+ cpu_relax();
+}
+
+u32 native_safe_apic_wait_icr_idle(void)
+{
+ u32 send_status;
+ int timeout;
+
+ timeout = 0;
+ do {
+ send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
+ if (!send_status)
+ break;
+ udelay(100);
+ } while (timeout++ < 1000);
+
+ return send_status;
+}
+
+void 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_EILVT0;
+ 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, 0xffffffff);
+ 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);
+
+ 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;
+ }
+}
+
+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");
+ 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);
+
+ /* 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);
+ 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;
+ 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);
+
+ 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,
+ &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: %ld\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",
+ (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 (!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 */
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
+ if (maxlvt >= 5) {
+ v = apic_read(APIC_LVTTHMR);
+ apic_write(APIC_LVTTHMR, 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)
+ 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.
+ */
+ reg0 = apic_read(APIC_ID);
+ apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
+ apic_write(APIC_ID, reg0 ^ apic->apic_id_mask);
+ reg1 = apic_read(APIC_ID);
+ apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
+ apic_write(APIC_ID, reg0);
+ if (reg1 != (reg0 ^ apic->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
+
+ preempt_disable();
+
+ /*
+ * Double-check whether this APIC is really registered.
+ * This is meaningless in clustered apic mode, so we skip it.
+ */
+ if (!apic->apic_id_registered())
+ BUG();
+
+ /*
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116). So here it goes...
+ */
+ 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);
+
+ preempt_enable();
+}
+
+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)
+{
+ int msr, msr2;
+
+ if (!cpu_has_x2apic)
+ return;
+
+ rdmsr(MSR_IA32_APICBASE, msr, msr2);
+
+ if (msr & X2APIC_ENABLE) {
+ pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
+ x2apic_preenabled = x2apic = 1;
+ }
+}
+
+void enable_x2apic(void)
+{
+ int msr, msr2;
+
+ if (!x2apic)
+ return;
+
+ rdmsr(MSR_IA32_APICBASE, msr, msr2);
+ if (!(msr & X2APIC_ENABLE)) {
+ pr_info("Enabling x2apic\n");
+ wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
+ }
+}
+
+void __init enable_IR_x2apic(void)
+{
+#ifdef CONFIG_INTR_REMAP
+ int ret;
+ unsigned long flags;
+
+ if (!cpu_has_x2apic)
+ return;
+
+ if (!x2apic_preenabled && disable_x2apic) {
+ pr_info("Skipped enabling x2apic and Interrupt-remapping "
+ "because of nox2apic\n");
+ return;
+ }
+
+ if (x2apic_preenabled && disable_x2apic)
+ panic("Bios already enabled x2apic, can't enforce nox2apic");
+
+ if (!x2apic_preenabled && skip_ioapic_setup) {
+ pr_info("Skipped enabling x2apic and Interrupt-remapping "
+ "because of skipping io-apic setup\n");
+ return;
+ }
+
+ ret = dmar_table_init();
+ if (ret) {
+ pr_info("dmar_table_init() failed with %d:\n", ret);
+
+ if (x2apic_preenabled)
+ panic("x2apic enabled by bios. But IR enabling failed");
+ else
+ pr_info("Not enabling x2apic,Intr-remapping\n");
+ return;
+ }
+
+ local_irq_save(flags);
+ mask_8259A();
+
+ ret = save_mask_IO_APIC_setup();
+ if (ret) {
+ pr_info("Saving IO-APIC state failed: %d\n", ret);
+ goto end;
+ }
+
+ ret = enable_intr_remapping(1);
+
+ if (ret && x2apic_preenabled) {
+ local_irq_restore(flags);
+ panic("x2apic enabled by bios. But IR enabling failed");
+ }
+
+ if (ret)
+ goto end_restore;
+
+ if (!x2apic) {
+ x2apic = 1;
+ enable_x2apic();
+ }
+
+end_restore:
+ if (ret)
+ /*
+ * IR enabling failed
+ */
+ restore_IO_APIC_setup();
+ else
+ reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+
+end:
+ unmask_8259A();
+ local_irq_restore(flags);
+
+ if (!ret) {
+ if (!x2apic_preenabled)
+ pr_info("Enabled x2apic and interrupt-remapping\n");
+ else
+ pr_info("Enabled Interrupt-remapping\n");
+ } else
+ pr_err("Failed to enable Interrupt-remapping and x2apic\n");
+#else
+ if (!cpu_has_x2apic)
+ return;
+
+ if (x2apic_preenabled)
+ panic("x2apic enabled prior OS handover,"
+ " enable CONFIG_INTR_REMAP");
+
+ pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+ " and x2apic\n");
+#endif
+
+ return;
+}
+#endif /* CONFIG_X86_X2APIC */
+
+#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;
+ boot_cpu_physical_apicid = 0;
+ 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)
+{
+ unsigned long phys_addr;
+
+ /*
+ * If no local APIC can be found then go out
+ * : it means there is no mpatable and MADT
+ */
+ if (!smp_found_config)
+ return;
+
+ phys_addr = mp_lapic_addr;
+
+ set_fixmap_nocache(FIX_APIC_BASE, phys_addr);
+ apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
+ APIC_BASE, phys_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)
+{
+#ifdef CONFIG_X86_X2APIC
+ if (x2apic) {
+ boot_cpu_physical_apicid = read_apic_id();
+ return;
+ }
+#endif
+
+ /*
+ * If no local APIC can be found then set up a fake all
+ * zeroes page to simulate the local APIC and another
+ * one for the IO-APIC.
+ */
+ if (!smp_found_config && detect_init_APIC()) {
+ apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
+ apic_phys = __pa(apic_phys);
+ } else
+ apic_phys = mp_lapic_addr;
+
+ set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+ apic_printk(APIC_VERBOSE, "mapped APIC to %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).
+ */
+ if (boot_cpu_physical_apicid == -1U)
+ boot_cpu_physical_apicid = read_apic_id();
+}
+
+/*
+ * 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);
+ clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ 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
+
+ setup_boot_clock();
+#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");
+ outb(0x70, 0x22);
+ outb(0x01, 0x23);
+ }
+#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");
+ outb(0x70, 0x22);
+ outb(0x00, 0x23);
+ 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();
+
+ 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);
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
+ if (maxlvt >= 5)
+ apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
+#endif
+
+ local_irq_save(flags);
+ disable_local_APIC();
+ local_irq_restore(flags);
+ return 0;
+}
+
+static int lapic_resume(struct sys_device *dev)
+{
+ unsigned int l, h;
+ unsigned long flags;
+ int maxlvt;
+
+ if (!apic_pm_state.active)
+ return 0;
+
+ maxlvt = lapic_get_maxlvt();
+
+ local_irq_save(flags);
+
+#ifdef CONFIG_X86_X2APIC
+ if (x2apic)
+ enable_x2apic();
+ else
+#endif
+ {
+ /*
+ * 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);
+ }
+
+ 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);
+
+ local_irq_restore(flags);
+
+ return 0;
+}
+
+/*
+ * 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;
+}
+device_initcall(init_lapic_sysfs);
+
+#else /* CONFIG_PM */
+
+static void apic_pm_activate(void) { }
+
+#endif /* CONFIG_PM */
+
+#ifdef CONFIG_X86_64
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ *
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis. Use available data to take a good guess.
+ * If in doubt, go HPET.
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+ int i, clusters, zeros;
+ unsigned id;
+ u16 *bios_cpu_apicid;
+ DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
+
+ /*
+ * there is not this kind of box with AMD CPU yet.
+ * Some AMD box with quadcore cpu and 8 sockets apicid
+ * will be [4, 0x23] or [8, 0x27] could be thought to
+ * vsmp box still need checking...
+ */
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
+ return 0;
+
+ 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;
+ }
+
+ /* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+ * not guaranteed to be synced between boards
+ */
+ if (is_vsmp_box() && clusters > 1)
+ return 1;
+
+ /*
+ * If clusters > 2, then should be multi-chassis.
+ * May have to revisit this when multi-core + hyperthreaded CPUs come
+ * out, but AFAIK this will work even for them.
+ */
+ return (clusters > 2);
+}
+#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);
+
+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);
diff --git a/arch/x86/kernel/apic/apic_64.c b/arch/x86/kernel/apic/apic_64.c
new file mode 100644
index 0000000..70935dd
--- /dev/null
+++ b/arch/x86/kernel/apic/apic_64.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch probe layer.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/hardirq.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+#include <asm/setup.h>
+
+extern struct apic apic_flat;
+extern struct apic apic_physflat;
+extern struct apic apic_x2xpic_uv_x;
+extern struct apic apic_x2apic_phys;
+extern struct apic apic_x2apic_cluster;
+
+struct apic __read_mostly *apic = &apic_flat;
+EXPORT_SYMBOL_GPL(apic);
+
+static struct apic *apic_probe[] __initdata = {
+#ifdef CONFIG_X86_UV
+ &apic_x2apic_uv_x,
+#endif
+#ifdef CONFIG_X86_X2APIC
+ &apic_x2apic_phys,
+ &apic_x2apic_cluster,
+#endif
+ &apic_physflat,
+ NULL,
+};
+
+/*
+ * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
+ */
+void __init default_setup_apic_routing(void)
+{
+#ifdef CONFIG_X86_X2APIC
+ if (apic == &apic_x2apic_phys || apic == &apic_x2apic_cluster) {
+ if (!intr_remapping_enabled)
+ apic = &apic_flat;
+ }
+#endif
+
+ if (apic == &apic_flat) {
+ if (max_physical_apicid >= 8)
+ apic = &apic_physflat;
+ printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
+ }
+
+ if (x86_quirks->update_apic)
+ x86_quirks->update_apic();
+}
+
+/* Same for both flat and physical. */
+
+void apic_send_IPI_self(int vector)
+{
+ __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
+}
+
+int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ int i;
+
+ for (i = 0; apic_probe[i]; ++i) {
+ if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) {
+ apic = apic_probe[i];
+ printk(KERN_INFO "Setting APIC routing to %s.\n",
+ apic->name);
+ return 1;
+ }
+ }
+ return 0;
+}
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
new file mode 100644
index 0000000..3b00299
--- /dev/null
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -0,0 +1,389 @@
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Flat APIC subarch code.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+#include <linux/errno.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/hardirq.h>
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+
+#ifdef CONFIG_ACPI
+#include <acpi/acpi_bus.h>
+#endif
+
+static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ return 1;
+}
+
+static const struct cpumask *flat_target_cpus(void)
+{
+ return cpu_online_mask;
+}
+
+static void flat_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+ /* Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ cpumask_clear(retmask);
+ cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * 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...
+ */
+static void flat_init_apic_ldr(void)
+{
+ unsigned long val;
+ unsigned long num, id;
+
+ num = smp_processor_id();
+ id = 1UL << num;
+ apic_write(APIC_DFR, APIC_DFR_FLAT);
+ val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+ val |= SET_APIC_LOGICAL_ID(id);
+ apic_write(APIC_LDR, val);
+}
+
+static inline void _flat_send_IPI_mask(unsigned long mask, int vector)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __default_send_IPI_dest_field(mask, vector, apic->dest_logical);
+ local_irq_restore(flags);
+}
+
+static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector)
+{
+ unsigned long mask = cpumask_bits(cpumask)[0];
+
+ _flat_send_IPI_mask(mask, vector);
+}
+
+static void
+ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
+{
+ unsigned long mask = cpumask_bits(cpumask)[0];
+ int cpu = smp_processor_id();
+
+ if (cpu < BITS_PER_LONG)
+ clear_bit(cpu, &mask);
+
+ _flat_send_IPI_mask(mask, vector);
+}
+
+static void flat_send_IPI_allbutself(int vector)
+{
+ int cpu = smp_processor_id();
+#ifdef CONFIG_HOTPLUG_CPU
+ int hotplug = 1;
+#else
+ int hotplug = 0;
+#endif
+ if (hotplug || vector == NMI_VECTOR) {
+ if (!cpumask_equal(cpu_online_mask, cpumask_of(cpu))) {
+ unsigned long mask = cpumask_bits(cpu_online_mask)[0];
+
+ if (cpu < BITS_PER_LONG)
+ clear_bit(cpu, &mask);
+
+ _flat_send_IPI_mask(mask, vector);
+ }
+ } else if (num_online_cpus() > 1) {
+ __default_send_IPI_shortcut(APIC_DEST_ALLBUT,
+ vector, apic->dest_logical);
+ }
+}
+
+static void flat_send_IPI_all(int vector)
+{
+ if (vector == NMI_VECTOR) {
+ flat_send_IPI_mask(cpu_online_mask, vector);
+ } else {
+ __default_send_IPI_shortcut(APIC_DEST_ALLINC,
+ vector, apic->dest_logical);
+ }
+}
+
+static unsigned int flat_get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ id = (((x)>>24) & 0xFFu);
+
+ return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ x = ((id & 0xFFu)<<24);
+ return x;
+}
+
+static unsigned int read_xapic_id(void)
+{
+ unsigned int id;
+
+ id = flat_get_apic_id(apic_read(APIC_ID));
+ return id;
+}
+
+static int flat_apic_id_registered(void)
+{
+ return physid_isset(read_xapic_id(), phys_cpu_present_map);
+}
+
+static unsigned int flat_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+ return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+}
+
+static unsigned int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ unsigned long mask1 = cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+ unsigned long mask2 = cpumask_bits(andmask)[0] & APIC_ALL_CPUS;
+
+ return mask1 & mask2;
+}
+
+static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
+{
+ return hard_smp_processor_id() >> index_msb;
+}
+
+struct apic apic_flat = {
+ .name = "flat",
+ .probe = NULL,
+ .acpi_madt_oem_check = flat_acpi_madt_oem_check,
+ .apic_id_registered = flat_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ .irq_dest_mode = 1, /* logical */
+
+ .target_cpus = flat_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = flat_vector_allocation_domain,
+ .init_apic_ldr = flat_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = flat_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = flat_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFu << 24,
+
+ .cpu_mask_to_apicid = flat_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = flat_send_IPI_mask,
+ .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = flat_send_IPI_allbutself,
+ .send_IPI_all = flat_send_IPI_all,
+ .send_IPI_self = apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .inquire_remote_apic = NULL,
+
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .icr_read = native_apic_icr_read,
+ .icr_write = native_apic_icr_write,
+ .wait_icr_idle = native_apic_wait_icr_idle,
+ .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+};
+
+/*
+ * Physflat mode is used when there are more than 8 CPUs on a AMD system.
+ * We cannot use logical delivery in this case because the mask
+ * overflows, so use physical mode.
+ */
+static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+#ifdef CONFIG_ACPI
+ /*
+ * Quirk: some x86_64 machines can only use physical APIC mode
+ * regardless of how many processors are present (x86_64 ES7000
+ * is an example).
+ */
+ if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+ (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
+ printk(KERN_DEBUG "system APIC only can use physical flat");
+ return 1;
+ }
+#endif
+
+ return 0;
+}
+
+static const struct cpumask *physflat_target_cpus(void)
+{
+ return cpu_online_mask;
+}
+
+static void physflat_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+ cpumask_clear(retmask);
+ cpumask_set_cpu(cpu, retmask);
+}
+
+static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector)
+{
+ default_send_IPI_mask_sequence_phys(cpumask, vector);
+}
+
+static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask,
+ int vector)
+{
+ default_send_IPI_mask_allbutself_phys(cpumask, vector);
+}
+
+static void physflat_send_IPI_allbutself(int vector)
+{
+ default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
+}
+
+static void physflat_send_IPI_all(int vector)
+{
+ physflat_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static unsigned int physflat_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ cpu = cpumask_first(cpumask);
+ if ((unsigned)cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+ else
+ return BAD_APICID;
+}
+
+static unsigned int
+physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+ if (cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+
+ return BAD_APICID;
+}
+
+struct apic apic_physflat = {
+
+ .name = "physical flat",
+ .probe = NULL,
+ .acpi_madt_oem_check = physflat_acpi_madt_oem_check,
+ .apic_id_registered = flat_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 0, /* physical */
+
+ .target_cpus = physflat_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = 0,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = physflat_vector_allocation_domain,
+ /* not needed, but shouldn't hurt: */
+ .init_apic_ldr = flat_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = flat_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = flat_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFu << 24,
+
+ .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = physflat_send_IPI_mask,
+ .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = physflat_send_IPI_allbutself,
+ .send_IPI_all = physflat_send_IPI_all,
+ .send_IPI_self = apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .inquire_remote_apic = NULL,
+
+ .read = native_apic_mem_read,
+ .write = native_apic_mem_write,
+ .icr_read = native_apic_icr_read,
+ .icr_write = native_apic_icr_write,
+ .wait_icr_idle = native_apic_wait_icr_idle,
+ .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
+};
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
new file mode 100644
index 0000000..00e6071
--- /dev/null
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -0,0 +1,4160 @@
+/*
+ * Intel IO-APIC support for multi-Pentium hosts.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ *
+ * Many thanks to Stig Venaas for trying out countless experimental
+ * patches and reporting/debugging problems patiently!
+ *
+ * (c) 1999, Multiple IO-APIC support, developed by
+ * Ken-ichi Yaku <yaku@css1.kbnes.nec.co.jp> and
+ * Hidemi Kishimoto <kisimoto@css1.kbnes.nec.co.jp>,
+ * further tested and cleaned up by Zach Brown <zab@redhat.com>
+ * and 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
+ * Paul Diefenbaugh : Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/mc146818rtc.h>
+#include <linux/compiler.h>
+#include <linux/acpi.h>
+#include <linux/module.h>
+#include <linux/sysdev.h>
+#include <linux/msi.h>
+#include <linux/htirq.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/jiffies.h> /* time_after() */
+#ifdef CONFIG_ACPI
+#include <acpi/acpi_bus.h>
+#endif
+#include <linux/bootmem.h>
+#include <linux/dmar.h>
+#include <linux/hpet.h>
+
+#include <asm/idle.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/desc.h>
+#include <asm/proto.h>
+#include <asm/acpi.h>
+#include <asm/dma.h>
+#include <asm/timer.h>
+#include <asm/i8259.h>
+#include <asm/nmi.h>
+#include <asm/msidef.h>
+#include <asm/hypertransport.h>
+#include <asm/setup.h>
+#include <asm/irq_remapping.h>
+#include <asm/hpet.h>
+#include <asm/uv/uv_hub.h>
+#include <asm/uv/uv_irq.h>
+
+#include <asm/apic.h>
+
+#define __apicdebuginit(type) static type __init
+
+/*
+ * Is the SiS APIC rmw bug present ?
+ * -1 = don't know, 0 = no, 1 = yes
+ */
+int sis_apic_bug = -1;
+
+static DEFINE_SPINLOCK(ioapic_lock);
+static DEFINE_SPINLOCK(vector_lock);
+
+/*
+ * # of IRQ routing registers
+ */
+int nr_ioapic_registers[MAX_IO_APICS];
+
+/* I/O APIC entries */
+struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
+int nr_ioapics;
+
+/* MP IRQ source entries */
+struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
+
+/* # of MP IRQ source entries */
+int mp_irq_entries;
+
+#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
+int mp_bus_id_to_type[MAX_MP_BUSSES];
+#endif
+
+DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
+int skip_ioapic_setup;
+
+void arch_disable_smp_support(void)
+{
+#ifdef CONFIG_PCI
+ noioapicquirk = 1;
+ noioapicreroute = -1;
+#endif
+ skip_ioapic_setup = 1;
+}
+
+static int __init parse_noapic(char *str)
+{
+ /* disable IO-APIC */
+ arch_disable_smp_support();
+ return 0;
+}
+early_param("noapic", parse_noapic);
+
+struct irq_pin_list;
+
+/*
+ * This is performance-critical, we want to do it O(1)
+ *
+ * the indexing order of this array favors 1:1 mappings
+ * between pins and IRQs.
+ */
+
+struct irq_pin_list {
+ int apic, pin;
+ struct irq_pin_list *next;
+};
+
+static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+{
+ struct irq_pin_list *pin;
+ int node;
+
+ node = cpu_to_node(cpu);
+
+ pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
+
+ return pin;
+}
+
+struct irq_cfg {
+ struct irq_pin_list *irq_2_pin;
+ cpumask_var_t domain;
+ cpumask_var_t old_domain;
+ unsigned move_cleanup_count;
+ u8 vector;
+ u8 move_in_progress : 1;
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+ u8 move_desc_pending : 1;
+#endif
+};
+
+/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_cfg irq_cfgx[] = {
+#else
+static struct irq_cfg irq_cfgx[NR_IRQS] = {
+#endif
+ [0] = { .vector = IRQ0_VECTOR, },
+ [1] = { .vector = IRQ1_VECTOR, },
+ [2] = { .vector = IRQ2_VECTOR, },
+ [3] = { .vector = IRQ3_VECTOR, },
+ [4] = { .vector = IRQ4_VECTOR, },
+ [5] = { .vector = IRQ5_VECTOR, },
+ [6] = { .vector = IRQ6_VECTOR, },
+ [7] = { .vector = IRQ7_VECTOR, },
+ [8] = { .vector = IRQ8_VECTOR, },
+ [9] = { .vector = IRQ9_VECTOR, },
+ [10] = { .vector = IRQ10_VECTOR, },
+ [11] = { .vector = IRQ11_VECTOR, },
+ [12] = { .vector = IRQ12_VECTOR, },
+ [13] = { .vector = IRQ13_VECTOR, },
+ [14] = { .vector = IRQ14_VECTOR, },
+ [15] = { .vector = IRQ15_VECTOR, },
+};
+
+int __init arch_early_irq_init(void)
+{
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+ int count;
+ int i;
+
+ cfg = irq_cfgx;
+ count = ARRAY_SIZE(irq_cfgx);
+
+ for (i = 0; i < count; i++) {
+ desc = irq_to_desc(i);
+ desc->chip_data = &cfg[i];
+ alloc_bootmem_cpumask_var(&cfg[i].domain);
+ alloc_bootmem_cpumask_var(&cfg[i].old_domain);
+ if (i < NR_IRQS_LEGACY)
+ cpumask_setall(cfg[i].domain);
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_cfg *irq_cfg(unsigned int irq)
+{
+ struct irq_cfg *cfg = NULL;
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+ if (desc)
+ cfg = desc->chip_data;
+
+ return cfg;
+}
+
+static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+{
+ struct irq_cfg *cfg;
+ int node;
+
+ node = cpu_to_node(cpu);
+
+ cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
+ if (cfg) {
+ if (!alloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
+ kfree(cfg);
+ cfg = NULL;
+ } else if (!alloc_cpumask_var_node(&cfg->old_domain,
+ GFP_ATOMIC, node)) {
+ free_cpumask_var(cfg->domain);
+ kfree(cfg);
+ cfg = NULL;
+ } else {
+ cpumask_clear(cfg->domain);
+ cpumask_clear(cfg->old_domain);
+ }
+ }
+
+ return cfg;
+}
+
+int arch_init_chip_data(struct irq_desc *desc, int cpu)
+{
+ struct irq_cfg *cfg;
+
+ cfg = desc->chip_data;
+ if (!cfg) {
+ desc->chip_data = get_one_free_irq_cfg(cpu);
+ if (!desc->chip_data) {
+ printk(KERN_ERR "can not alloc irq_cfg\n");
+ BUG_ON(1);
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+
+static void
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+{
+ struct irq_pin_list *old_entry, *head, *tail, *entry;
+
+ cfg->irq_2_pin = NULL;
+ old_entry = old_cfg->irq_2_pin;
+ if (!old_entry)
+ return;
+
+ entry = get_one_free_irq_2_pin(cpu);
+ if (!entry)
+ return;
+
+ entry->apic = old_entry->apic;
+ entry->pin = old_entry->pin;
+ head = entry;
+ tail = entry;
+ old_entry = old_entry->next;
+ while (old_entry) {
+ entry = get_one_free_irq_2_pin(cpu);
+ if (!entry) {
+ entry = head;
+ while (entry) {
+ head = entry->next;
+ kfree(entry);
+ entry = head;
+ }
+ /* still use the old one */
+ return;
+ }
+ entry->apic = old_entry->apic;
+ entry->pin = old_entry->pin;
+ tail->next = entry;
+ tail = entry;
+ old_entry = old_entry->next;
+ }
+
+ tail->next = NULL;
+ cfg->irq_2_pin = head;
+}
+
+static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
+{
+ struct irq_pin_list *entry, *next;
+
+ if (old_cfg->irq_2_pin == cfg->irq_2_pin)
+ return;
+
+ entry = old_cfg->irq_2_pin;
+
+ while (entry) {
+ next = entry->next;
+ kfree(entry);
+ entry = next;
+ }
+ old_cfg->irq_2_pin = NULL;
+}
+
+void arch_init_copy_chip_data(struct irq_desc *old_desc,
+ struct irq_desc *desc, int cpu)
+{
+ struct irq_cfg *cfg;
+ struct irq_cfg *old_cfg;
+
+ cfg = get_one_free_irq_cfg(cpu);
+
+ if (!cfg)
+ return;
+
+ desc->chip_data = cfg;
+
+ old_cfg = old_desc->chip_data;
+
+ memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
+
+ init_copy_irq_2_pin(old_cfg, cfg, cpu);
+}
+
+static void free_irq_cfg(struct irq_cfg *old_cfg)
+{
+ kfree(old_cfg);
+}
+
+void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
+{
+ struct irq_cfg *old_cfg, *cfg;
+
+ old_cfg = old_desc->chip_data;
+ cfg = desc->chip_data;
+
+ if (old_cfg == cfg)
+ return;
+
+ if (old_cfg) {
+ free_irq_2_pin(old_cfg, cfg);
+ free_irq_cfg(old_cfg);
+ old_desc->chip_data = NULL;
+ }
+}
+
+static void
+set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg = desc->chip_data;
+
+ if (!cfg->move_in_progress) {
+ /* it means that domain is not changed */
+ if (!cpumask_intersects(desc->affinity, mask))
+ cfg->move_desc_pending = 1;
+ }
+}
+#endif
+
+#else
+static struct irq_cfg *irq_cfg(unsigned int irq)
+{
+ return irq < nr_irqs ? irq_cfgx + irq : NULL;
+}
+
+#endif
+
+#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
+static inline void
+set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+}
+#endif
+
+struct io_apic {
+ unsigned int index;
+ unsigned int unused[3];
+ unsigned int data;
+};
+
+static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
+{
+ return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
+ + (mp_ioapics[idx].apicaddr & ~PAGE_MASK);
+}
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+ struct io_apic __iomem *io_apic = io_apic_base(apic);
+ writel(reg, &io_apic->index);
+ return readl(&io_apic->data);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+ struct io_apic __iomem *io_apic = io_apic_base(apic);
+ writel(reg, &io_apic->index);
+ writel(value, &io_apic->data);
+}
+
+/*
+ * Re-write a value: to be used for read-modify-write
+ * cycles where the read already set up the index register.
+ *
+ * Older SiS APIC requires we rewrite the index register
+ */
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+{
+ struct io_apic __iomem *io_apic = io_apic_base(apic);
+
+ if (sis_apic_bug)
+ writel(reg, &io_apic->index);
+ writel(value, &io_apic->data);
+}
+
+static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
+{
+ struct irq_pin_list *entry;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ entry = cfg->irq_2_pin;
+ for (;;) {
+ unsigned int reg;
+ int pin;
+
+ if (!entry)
+ break;
+ pin = entry->pin;
+ reg = io_apic_read(entry->apic, 0x10 + pin*2);
+ /* Is the remote IRR bit set? */
+ if (reg & IO_APIC_REDIR_REMOTE_IRR) {
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ return true;
+ }
+ if (!entry->next)
+ break;
+ entry = entry->next;
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return false;
+}
+
+union entry_union {
+ struct { u32 w1, w2; };
+ struct IO_APIC_route_entry entry;
+};
+
+static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
+{
+ union entry_union eu;
+ unsigned long flags;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
+ eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ return eu.entry;
+}
+
+/*
+ * When we write a new IO APIC routing entry, we need to write the high
+ * word first! If the mask bit in the low word is clear, we will enable
+ * the interrupt, and we need to make sure the entry is fully populated
+ * before that happens.
+ */
+static void
+__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+{
+ union entry_union eu;
+ eu.entry = e;
+ io_apic_write(apic, 0x11 + 2*pin, eu.w2);
+ io_apic_write(apic, 0x10 + 2*pin, eu.w1);
+}
+
+void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __ioapic_write_entry(apic, pin, e);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+/*
+ * When we mask an IO APIC routing entry, we need to write the low
+ * word first, in order to set the mask bit before we change the
+ * high bits!
+ */
+static void ioapic_mask_entry(int apic, int pin)
+{
+ unsigned long flags;
+ union entry_union eu = { .entry.mask = 1 };
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0x10 + 2*pin, eu.w1);
+ io_apic_write(apic, 0x11 + 2*pin, eu.w2);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+#ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ cpumask_var_t cleanup_mask;
+
+ if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+ unsigned int i;
+ cfg->move_cleanup_count = 0;
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ cfg->move_cleanup_count++;
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+ } else {
+ cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+ apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ free_cpumask_var(cleanup_mask);
+ }
+ cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+ int apic, pin;
+ struct irq_pin_list *entry;
+ u8 vector = cfg->vector;
+
+ entry = cfg->irq_2_pin;
+ for (;;) {
+ unsigned int reg;
+
+ if (!entry)
+ break;
+
+ apic = entry->apic;
+ pin = entry->pin;
+#ifdef CONFIG_INTR_REMAP
+ /*
+ * With interrupt-remapping, destination information comes
+ * from interrupt-remapping table entry.
+ */
+ if (!irq_remapped(irq))
+ io_apic_write(apic, 0x11 + pin*2, dest);
+#else
+ io_apic_write(apic, 0x11 + pin*2, dest);
+#endif
+ reg = io_apic_read(apic, 0x10 + pin*2);
+ reg &= ~IO_APIC_REDIR_VECTOR_MASK;
+ reg |= vector;
+ io_apic_modify(apic, 0x10 + pin*2, reg);
+ if (!entry->next)
+ break;
+ entry = entry->next;
+ }
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ unsigned int irq;
+
+ if (!cpumask_intersects(mask, cpu_online_mask))
+ return BAD_APICID;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
+ return BAD_APICID;
+
+ cpumask_and(desc->affinity, cfg->domain, mask);
+ set_extra_move_desc(desc, mask);
+
+ return apic->cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
+}
+
+static void
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ unsigned int dest;
+ unsigned int irq;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ dest = set_desc_affinity(desc, mask);
+ if (dest != BAD_APICID) {
+ /* Only the high 8 bits are valid. */
+ dest = SET_APIC_LOGICAL_ID(dest);
+ __target_IO_APIC_irq(irq, dest, cfg);
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+
+ set_ioapic_affinity_irq_desc(desc, mask);
+}
+#endif /* CONFIG_SMP */
+
+/*
+ * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
+ * shared ISA-space IRQs, so we have to support them. We are super
+ * fast in the common case, and fast for shared ISA-space IRQs.
+ */
+static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
+{
+ struct irq_pin_list *entry;
+
+ entry = cfg->irq_2_pin;
+ if (!entry) {
+ entry = get_one_free_irq_2_pin(cpu);
+ if (!entry) {
+ printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
+ apic, pin);
+ return;
+ }
+ cfg->irq_2_pin = entry;
+ entry->apic = apic;
+ entry->pin = pin;
+ return;
+ }
+
+ while (entry->next) {
+ /* not again, please */
+ if (entry->apic == apic && entry->pin == pin)
+ return;
+
+ entry = entry->next;
+ }
+
+ entry->next = get_one_free_irq_2_pin(cpu);
+ entry = entry->next;
+ entry->apic = apic;
+ entry->pin = pin;
+}
+
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
+ int oldapic, int oldpin,
+ int newapic, int newpin)
+{
+ struct irq_pin_list *entry = cfg->irq_2_pin;
+ int replaced = 0;
+
+ while (entry) {
+ if (entry->apic == oldapic && entry->pin == oldpin) {
+ entry->apic = newapic;
+ entry->pin = newpin;
+ replaced = 1;
+ /* every one is different, right? */
+ break;
+ }
+ entry = entry->next;
+ }
+
+ /* why? call replace before add? */
+ if (!replaced)
+ add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
+}
+
+static inline void io_apic_modify_irq(struct irq_cfg *cfg,
+ int mask_and, int mask_or,
+ void (*final)(struct irq_pin_list *entry))
+{
+ int pin;
+ struct irq_pin_list *entry;
+
+ for (entry = cfg->irq_2_pin; entry != NULL; entry = entry->next) {
+ unsigned int reg;
+ pin = entry->pin;
+ reg = io_apic_read(entry->apic, 0x10 + pin * 2);
+ reg &= mask_and;
+ reg |= mask_or;
+ io_apic_modify(entry->apic, 0x10 + pin * 2, reg);
+ if (final)
+ final(entry);
+ }
+}
+
+static void __unmask_IO_APIC_irq(struct irq_cfg *cfg)
+{
+ io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
+}
+
+#ifdef CONFIG_X86_64
+static void io_apic_sync(struct irq_pin_list *entry)
+{
+ /*
+ * Synchronize the IO-APIC and the CPU by doing
+ * a dummy read from the IO-APIC
+ */
+ struct io_apic __iomem *io_apic;
+ io_apic = io_apic_base(entry->apic);
+ readl(&io_apic->data);
+}
+
+static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
+{
+ io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+}
+#else /* CONFIG_X86_32 */
+static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
+{
+ io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, NULL);
+}
+
+static void __mask_and_edge_IO_APIC_irq(struct irq_cfg *cfg)
+{
+ io_apic_modify_irq(cfg, ~IO_APIC_REDIR_LEVEL_TRIGGER,
+ IO_APIC_REDIR_MASKED, NULL);
+}
+
+static void __unmask_and_level_IO_APIC_irq(struct irq_cfg *cfg)
+{
+ io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED,
+ IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
+}
+#endif /* CONFIG_X86_32 */
+
+static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
+{
+ struct irq_cfg *cfg = desc->chip_data;
+ unsigned long flags;
+
+ BUG_ON(!cfg);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __mask_IO_APIC_irq(cfg);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
+{
+ struct irq_cfg *cfg = desc->chip_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __unmask_IO_APIC_irq(cfg);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void mask_IO_APIC_irq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ mask_IO_APIC_irq_desc(desc);
+}
+static void unmask_IO_APIC_irq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ unmask_IO_APIC_irq_desc(desc);
+}
+
+static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
+{
+ struct IO_APIC_route_entry entry;
+
+ /* Check delivery_mode to be sure we're not clearing an SMI pin */
+ entry = ioapic_read_entry(apic, pin);
+ if (entry.delivery_mode == dest_SMI)
+ return;
+ /*
+ * Disable it in the IO-APIC irq-routing table:
+ */
+ ioapic_mask_entry(apic, pin);
+}
+
+static void clear_IO_APIC (void)
+{
+ int apic, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+ clear_IO_APIC_pin(apic, pin);
+}
+
+#ifdef CONFIG_X86_32
+/*
+ * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
+ * specific CPU-side IRQs.
+ */
+
+#define MAX_PIRQS 8
+static int pirq_entries[MAX_PIRQS] = {
+ [0 ... MAX_PIRQS - 1] = -1
+};
+
+static int __init ioapic_pirq_setup(char *str)
+{
+ int i, max;
+ int ints[MAX_PIRQS+1];
+
+ get_options(str, ARRAY_SIZE(ints), ints);
+
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "PIRQ redirection, working around broken MP-BIOS.\n");
+ max = MAX_PIRQS;
+ if (ints[0] < MAX_PIRQS)
+ max = ints[0];
+
+ for (i = 0; i < max; i++) {
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "... PIRQ%d -> IRQ %d\n", i, ints[i+1]);
+ /*
+ * PIRQs are mapped upside down, usually.
+ */
+ pirq_entries[MAX_PIRQS-i-1] = ints[i+1];
+ }
+ return 1;
+}
+
+__setup("pirq=", ioapic_pirq_setup);
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_INTR_REMAP
+/* I/O APIC RTE contents at the OS boot up */
+static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
+
+/*
+ * Saves and masks all the unmasked IO-APIC RTE's
+ */
+int save_mask_IO_APIC_setup(void)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+ int apic, pin;
+
+ /*
+ * The number of IO-APIC IRQ registers (== #pins):
+ */
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(apic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+ }
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ early_ioapic_entries[apic] =
+ kzalloc(sizeof(struct IO_APIC_route_entry) *
+ nr_ioapic_registers[apic], GFP_KERNEL);
+ if (!early_ioapic_entries[apic])
+ goto nomem;
+ }
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ struct IO_APIC_route_entry entry;
+
+ entry = early_ioapic_entries[apic][pin] =
+ ioapic_read_entry(apic, pin);
+ if (!entry.mask) {
+ entry.mask = 1;
+ ioapic_write_entry(apic, pin, entry);
+ }
+ }
+
+ return 0;
+
+nomem:
+ while (apic >= 0)
+ kfree(early_ioapic_entries[apic--]);
+ memset(early_ioapic_entries, 0,
+ ARRAY_SIZE(early_ioapic_entries));
+
+ return -ENOMEM;
+}
+
+void restore_IO_APIC_setup(void)
+{
+ int apic, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ if (!early_ioapic_entries[apic])
+ break;
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+ ioapic_write_entry(apic, pin,
+ early_ioapic_entries[apic][pin]);
+ kfree(early_ioapic_entries[apic]);
+ early_ioapic_entries[apic] = NULL;
+ }
+}
+
+void reinit_intr_remapped_IO_APIC(int intr_remapping)
+{
+ /*
+ * for now plain restore of previous settings.
+ * TBD: In the case of OS enabling interrupt-remapping,
+ * IO-APIC RTE's need to be setup to point to interrupt-remapping
+ * table entries. for now, do a plain restore, and wait for
+ * the setup_IO_APIC_irqs() to do proper initialization.
+ */
+ restore_IO_APIC_setup();
+}
+#endif
+
+/*
+ * Find the IRQ entry number of a certain pin.
+ */
+static int find_irq_entry(int apic, int pin, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].irqtype == type &&
+ (mp_irqs[i].dstapic == mp_ioapics[apic].apicid ||
+ mp_irqs[i].dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].dstirq == pin)
+ return i;
+
+ return -1;
+}
+
+/*
+ * Find the pin to which IRQ[irq] (ISA) is connected
+ */
+static int __init find_isa_irq_pin(int irq, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].srcbus;
+
+ if (test_bit(lbus, mp_bus_not_pci) &&
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
+
+ return mp_irqs[i].dstirq;
+ }
+ return -1;
+}
+
+static int __init find_isa_irq_apic(int irq, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].srcbus;
+
+ if (test_bit(lbus, mp_bus_not_pci) &&
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
+ break;
+ }
+ if (i < mp_irq_entries) {
+ int apic;
+ for(apic = 0; apic < nr_ioapics; apic++) {
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic)
+ return apic;
+ }
+ }
+
+ return -1;
+}
+
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+static int pin_2_irq(int idx, int apic, int pin);
+
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
+{
+ int apic, i, best_guess = -1;
+
+ apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+ bus, slot, pin);
+ if (test_bit(bus, mp_bus_not_pci)) {
+ apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+ return -1;
+ }
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].srcbus;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+ mp_irqs[i].dstapic == MP_APIC_ALL)
+ break;
+
+ if (!test_bit(lbus, mp_bus_not_pci) &&
+ !mp_irqs[i].irqtype &&
+ (bus == lbus) &&
+ (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
+
+ if (!(apic || IO_APIC_IRQ(irq)))
+ continue;
+
+ if (pin == (mp_irqs[i].srcbusirq & 3))
+ return irq;
+ /*
+ * Use the first all-but-pin matching entry as a
+ * best-guess fuzzy result for broken mptables.
+ */
+ if (best_guess < 0)
+ best_guess = irq;
+ }
+ }
+ return best_guess;
+}
+
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+
+#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
+/*
+ * EISA Edge/Level control register, ELCR
+ */
+static int EISA_ELCR(unsigned int irq)
+{
+ if (irq < NR_IRQS_LEGACY) {
+ unsigned int port = 0x4d0 + (irq >> 3);
+ return (inb(port) >> (irq & 7)) & 1;
+ }
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "Broken MPtable reports ISA irq %d\n", irq);
+ return 0;
+}
+
+#endif
+
+/* ISA interrupts are always polarity zero edge triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_ISA_trigger(idx) (0)
+#define default_ISA_polarity(idx) (0)
+
+/* EISA interrupts are always polarity zero and can be edge or level
+ * trigger depending on the ELCR value. If an interrupt is listed as
+ * EISA conforming in the MP table, that means its trigger type must
+ * be read in from the ELCR */
+
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
+#define default_EISA_polarity(idx) default_ISA_polarity(idx)
+
+/* PCI interrupts are always polarity one level triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_PCI_trigger(idx) (1)
+#define default_PCI_polarity(idx) (1)
+
+/* MCA interrupts are always polarity zero level triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_MCA_trigger(idx) (1)
+#define default_MCA_polarity(idx) default_ISA_polarity(idx)
+
+static int MPBIOS_polarity(int idx)
+{
+ int bus = mp_irqs[idx].srcbus;
+ int polarity;
+
+ /*
+ * Determine IRQ line polarity (high active or low active):
+ */
+ switch (mp_irqs[idx].irqflag & 3)
+ {
+ case 0: /* conforms, ie. bus-type dependent polarity */
+ if (test_bit(bus, mp_bus_not_pci))
+ polarity = default_ISA_polarity(idx);
+ else
+ polarity = default_PCI_polarity(idx);
+ break;
+ case 1: /* high active */
+ {
+ polarity = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ case 3: /* low active */
+ {
+ polarity = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ }
+ return polarity;
+}
+
+static int MPBIOS_trigger(int idx)
+{
+ int bus = mp_irqs[idx].srcbus;
+ int trigger;
+
+ /*
+ * Determine IRQ trigger mode (edge or level sensitive):
+ */
+ switch ((mp_irqs[idx].irqflag>>2) & 3)
+ {
+ case 0: /* conforms, ie. bus-type dependent */
+ if (test_bit(bus, mp_bus_not_pci))
+ trigger = default_ISA_trigger(idx);
+ else
+ trigger = default_PCI_trigger(idx);
+#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ /* set before the switch */
+ break;
+ }
+ case MP_BUS_EISA: /* EISA pin */
+ {
+ trigger = default_EISA_trigger(idx);
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ /* set before the switch */
+ break;
+ }
+ case MP_BUS_MCA: /* MCA pin */
+ {
+ trigger = default_MCA_trigger(idx);
+ break;
+ }
+ default:
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ }
+#endif
+ break;
+ case 1: /* edge */
+ {
+ trigger = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ case 3: /* level */
+ {
+ trigger = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 0;
+ break;
+ }
+ }
+ return trigger;
+}
+
+static inline int irq_polarity(int idx)
+{
+ return MPBIOS_polarity(idx);
+}
+
+static inline int irq_trigger(int idx)
+{
+ return MPBIOS_trigger(idx);
+}
+
+int (*ioapic_renumber_irq)(int ioapic, int irq);
+static int pin_2_irq(int idx, int apic, int pin)
+{
+ int irq, i;
+ int bus = mp_irqs[idx].srcbus;
+
+ /*
+ * Debugging check, we are in big trouble if this message pops up!
+ */
+ if (mp_irqs[idx].dstirq != pin)
+ printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
+
+ if (test_bit(bus, mp_bus_not_pci)) {
+ irq = mp_irqs[idx].srcbusirq;
+ } else {
+ /*
+ * PCI IRQs are mapped in order
+ */
+ i = irq = 0;
+ while (i < apic)
+ irq += nr_ioapic_registers[i++];
+ irq += pin;
+ /*
+ * For MPS mode, so far only needed by ES7000 platform
+ */
+ if (ioapic_renumber_irq)
+ irq = ioapic_renumber_irq(apic, irq);
+ }
+
+#ifdef CONFIG_X86_32
+ /*
+ * PCI IRQ command line redirection. Yes, limits are hardcoded.
+ */
+ if ((pin >= 16) && (pin <= 23)) {
+ if (pirq_entries[pin-16] != -1) {
+ if (!pirq_entries[pin-16]) {
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "disabling PIRQ%d\n", pin-16);
+ } else {
+ irq = pirq_entries[pin-16];
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "using PIRQ%d -> IRQ %d\n",
+ pin-16, irq);
+ }
+ }
+ }
+#endif
+
+ return irq;
+}
+
+void lock_vector_lock(void)
+{
+ /* Used to the online set of cpus does not change
+ * during assign_irq_vector.
+ */
+ spin_lock(&vector_lock);
+}
+
+void unlock_vector_lock(void)
+{
+ spin_unlock(&vector_lock);
+}
+
+static int
+__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+{
+ /*
+ * NOTE! The local APIC isn't very good at handling
+ * multiple interrupts at the same interrupt level.
+ * As the interrupt level is determined by taking the
+ * vector number and shifting that right by 4, we
+ * want to spread these out a bit so that they don't
+ * all fall in the same interrupt level.
+ *
+ * Also, we've got to be careful not to trash gate
+ * 0x80, because int 0x80 is hm, kind of importantish. ;)
+ */
+ static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+ unsigned int old_vector;
+ int cpu, err;
+ cpumask_var_t tmp_mask;
+
+ if ((cfg->move_in_progress) || cfg->move_cleanup_count)
+ return -EBUSY;
+
+ if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
+ return -ENOMEM;
+
+ old_vector = cfg->vector;
+ if (old_vector) {
+ cpumask_and(tmp_mask, mask, cpu_online_mask);
+ cpumask_and(tmp_mask, cfg->domain, tmp_mask);
+ if (!cpumask_empty(tmp_mask)) {
+ free_cpumask_var(tmp_mask);
+ return 0;
+ }
+ }
+
+ /* Only try and allocate irqs on cpus that are present */
+ err = -ENOSPC;
+ for_each_cpu_and(cpu, mask, cpu_online_mask) {
+ int new_cpu;
+ int vector, offset;
+
+ apic->vector_allocation_domain(cpu, tmp_mask);
+
+ vector = current_vector;
+ offset = current_offset;
+next:
+ vector += 8;
+ if (vector >= first_system_vector) {
+ /* If out of vectors on large boxen, must share them. */
+ offset = (offset + 1) % 8;
+ vector = FIRST_DEVICE_VECTOR + offset;
+ }
+ if (unlikely(current_vector == vector))
+ continue;
+
+ if (test_bit(vector, used_vectors))
+ goto next;
+
+ for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+ if (per_cpu(vector_irq, new_cpu)[vector] != -1)
+ goto next;
+ /* Found one! */
+ current_vector = vector;
+ current_offset = offset;
+ if (old_vector) {
+ cfg->move_in_progress = 1;
+ cpumask_copy(cfg->old_domain, cfg->domain);
+ }
+ for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+ per_cpu(vector_irq, new_cpu)[vector] = irq;
+ cfg->vector = vector;
+ cpumask_copy(cfg->domain, tmp_mask);
+ err = 0;
+ break;
+ }
+ free_cpumask_var(tmp_mask);
+ return err;
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+{
+ int err;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vector_lock, flags);
+ err = __assign_irq_vector(irq, cfg, mask);
+ spin_unlock_irqrestore(&vector_lock, flags);
+ return err;
+}
+
+static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
+{
+ int cpu, vector;
+
+ BUG_ON(!cfg->vector);
+
+ vector = cfg->vector;
+ for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ per_cpu(vector_irq, cpu)[vector] = -1;
+
+ cfg->vector = 0;
+ cpumask_clear(cfg->domain);
+
+ if (likely(!cfg->move_in_progress))
+ return;
+ for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+ vector++) {
+ if (per_cpu(vector_irq, cpu)[vector] != irq)
+ continue;
+ per_cpu(vector_irq, cpu)[vector] = -1;
+ break;
+ }
+ }
+ cfg->move_in_progress = 0;
+}
+
+void __setup_vector_irq(int cpu)
+{
+ /* Initialize vector_irq on a new cpu */
+ /* This function must be called with vector_lock held */
+ int irq, vector;
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+
+ /* Mark the inuse vectors */
+ for_each_irq_desc(irq, desc) {
+ cfg = desc->chip_data;
+ if (!cpumask_test_cpu(cpu, cfg->domain))
+ continue;
+ vector = cfg->vector;
+ per_cpu(vector_irq, cpu)[vector] = irq;
+ }
+ /* Mark the free vectors */
+ for (vector = 0; vector < NR_VECTORS; ++vector) {
+ irq = per_cpu(vector_irq, cpu)[vector];
+ if (irq < 0)
+ continue;
+
+ cfg = irq_cfg(irq);
+ if (!cpumask_test_cpu(cpu, cfg->domain))
+ per_cpu(vector_irq, cpu)[vector] = -1;
+ }
+}
+
+static struct irq_chip ioapic_chip;
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip;
+#endif
+
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
+#ifdef CONFIG_X86_32
+static inline int IO_APIC_irq_trigger(int irq)
+{
+ int apic, idx, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ idx = find_irq_entry(apic, pin, mp_INT);
+ if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
+ return irq_trigger(idx);
+ }
+ }
+ /*
+ * nonexistent IRQs are edge default
+ */
+ return 0;
+}
+#else
+static inline int IO_APIC_irq_trigger(int irq)
+{
+ return 1;
+}
+#endif
+
+static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long trigger)
+{
+
+ if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+ trigger == IOAPIC_LEVEL)
+ desc->status |= IRQ_LEVEL;
+ else
+ desc->status &= ~IRQ_LEVEL;
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ desc->status |= IRQ_MOVE_PCNTXT;
+ if (trigger)
+ set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+ handle_fasteoi_irq,
+ "fasteoi");
+ else
+ set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+ handle_edge_irq, "edge");
+ return;
+ }
+#endif
+ if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+ trigger == IOAPIC_LEVEL)
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_fasteoi_irq,
+ "fasteoi");
+ else
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_edge_irq, "edge");
+}
+
+int setup_ioapic_entry(int apic_id, int irq,
+ struct IO_APIC_route_entry *entry,
+ unsigned int destination, int trigger,
+ int polarity, int vector)
+{
+ /*
+ * add it to the IO-APIC irq-routing table:
+ */
+ memset(entry,0,sizeof(*entry));
+
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled) {
+ struct intel_iommu *iommu = map_ioapic_to_ir(apic_id);
+ struct irte irte;
+ struct IR_IO_APIC_route_entry *ir_entry =
+ (struct IR_IO_APIC_route_entry *) entry;
+ int index;
+
+ if (!iommu)
+ panic("No mapping iommu for ioapic %d\n", apic_id);
+
+ index = alloc_irte(iommu, irq, 1);
+ if (index < 0)
+ panic("Failed to allocate IRTE for ioapic %d\n", apic_id);
+
+ memset(&irte, 0, sizeof(irte));
+
+ irte.present = 1;
+ irte.dst_mode = apic->irq_dest_mode;
+ irte.trigger_mode = trigger;
+ irte.dlvry_mode = apic->irq_delivery_mode;
+ irte.vector = vector;
+ irte.dest_id = IRTE_DEST(destination);
+
+ modify_irte(irq, &irte);
+
+ ir_entry->index2 = (index >> 15) & 0x1;
+ ir_entry->zero = 0;
+ ir_entry->format = 1;
+ ir_entry->index = (index & 0x7fff);
+ } else
+#endif
+ {
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->dest = destination;
+ }
+
+ entry->mask = 0; /* enable IRQ */
+ entry->trigger = trigger;
+ entry->polarity = polarity;
+ entry->vector = vector;
+
+ /* Mask level triggered irqs.
+ * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+ */
+ if (trigger)
+ entry->mask = 1;
+ return 0;
+}
+
+static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc,
+ int trigger, int polarity)
+{
+ struct irq_cfg *cfg;
+ struct IO_APIC_route_entry entry;
+ unsigned int dest;
+
+ if (!IO_APIC_IRQ(irq))
+ return;
+
+ cfg = desc->chip_data;
+
+ if (assign_irq_vector(irq, cfg, apic->target_cpus()))
+ return;
+
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
+
+ apic_printk(APIC_VERBOSE,KERN_DEBUG
+ "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
+ "IRQ %d Mode:%i Active:%i)\n",
+ apic_id, mp_ioapics[apic_id].apicid, pin, cfg->vector,
+ irq, trigger, polarity);
+
+
+ if (setup_ioapic_entry(mp_ioapics[apic_id].apicid, irq, &entry,
+ dest, trigger, polarity, cfg->vector)) {
+ printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
+ mp_ioapics[apic_id].apicid, pin);
+ __clear_irq_vector(irq, cfg);
+ return;
+ }
+
+ ioapic_register_intr(irq, desc, trigger);
+ if (irq < NR_IRQS_LEGACY)
+ disable_8259A_irq(irq);
+
+ ioapic_write_entry(apic_id, pin, entry);
+}
+
+static void __init setup_IO_APIC_irqs(void)
+{
+ int apic_id, pin, idx, irq;
+ int notcon = 0;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ int cpu = boot_cpu_id;
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+
+ for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
+ for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+
+ idx = find_irq_entry(apic_id, pin, mp_INT);
+ if (idx == -1) {
+ if (!notcon) {
+ notcon = 1;
+ apic_printk(APIC_VERBOSE,
+ KERN_DEBUG " %d-%d",
+ mp_ioapics[apic_id].apicid, pin);
+ } else
+ apic_printk(APIC_VERBOSE, " %d-%d",
+ mp_ioapics[apic_id].apicid, pin);
+ continue;
+ }
+ if (notcon) {
+ apic_printk(APIC_VERBOSE,
+ " (apicid-pin) not connected\n");
+ notcon = 0;
+ }
+
+ irq = pin_2_irq(idx, apic_id, pin);
+
+ /*
+ * Skip the timer IRQ if there's a quirk handler
+ * installed and if it returns 1:
+ */
+ if (apic->multi_timer_check &&
+ apic->multi_timer_check(apic_id, irq))
+ continue;
+
+ desc = irq_to_desc_alloc_cpu(irq, cpu);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+ continue;
+ }
+ cfg = desc->chip_data;
+ add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
+
+ setup_IO_APIC_irq(apic_id, pin, irq, desc,
+ irq_trigger(idx), irq_polarity(idx));
+ }
+ }
+
+ if (notcon)
+ apic_printk(APIC_VERBOSE,
+ " (apicid-pin) not connected\n");
+}
+
+/*
+ * Set up the timer pin, possibly with the 8259A-master behind.
+ */
+static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin,
+ int vector)
+{
+ struct IO_APIC_route_entry entry;
+
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ return;
+#endif
+
+ memset(&entry, 0, sizeof(entry));
+
+ /*
+ * We use logical delivery to get the timer IRQ
+ * to the first CPU.
+ */
+ entry.dest_mode = apic->irq_dest_mode;
+ entry.mask = 0; /* don't mask IRQ for edge */
+ entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus());
+ entry.delivery_mode = apic->irq_delivery_mode;
+ entry.polarity = 0;
+ entry.trigger = 0;
+ entry.vector = vector;
+
+ /*
+ * The timer IRQ doesn't have to know that behind the
+ * scene we may have a 8259A-master in AEOI mode ...
+ */
+ set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
+
+ /*
+ * Add it to the IO-APIC irq-routing table:
+ */
+ ioapic_write_entry(apic_id, pin, entry);
+}
+
+
+__apicdebuginit(void) print_IO_APIC(void)
+{
+ int apic, i;
+ union IO_APIC_reg_00 reg_00;
+ union IO_APIC_reg_01 reg_01;
+ union IO_APIC_reg_02 reg_02;
+ union IO_APIC_reg_03 reg_03;
+ unsigned long flags;
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+ unsigned int irq;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+ for (i = 0; i < nr_ioapics; i++)
+ printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
+ mp_ioapics[i].apicid, nr_ioapic_registers[i]);
+
+ /*
+ * We are a bit conservative about what we expect. We have to
+ * know about every hardware change ASAP.
+ */
+ printk(KERN_INFO "testing the IO APIC.......................\n");
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ reg_01.raw = io_apic_read(apic, 1);
+ if (reg_01.bits.version >= 0x10)
+ reg_02.raw = io_apic_read(apic, 2);
+ if (reg_01.bits.version >= 0x20)
+ reg_03.raw = io_apic_read(apic, 3);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ printk("\n");
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
+ printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
+ printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
+ printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
+ printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS);
+
+ printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)®_01);
+ printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries);
+
+ printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ);
+ printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version);
+
+ /*
+ * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02,
+ * but the value of reg_02 is read as the previous read register
+ * value, so ignore it if reg_02 == reg_01.
+ */
+ if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) {
+ printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
+ printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration);
+ }
+
+ /*
+ * Some Intel chipsets with IO APIC VERSION of 0x2? don't have reg_02
+ * or reg_03, but the value of reg_0[23] is read as the previous read
+ * register value, so ignore it if reg_03 == reg_0[12].
+ */
+ if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw &&
+ reg_03.raw != reg_01.raw) {
+ printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw);
+ printk(KERN_DEBUG "....... : Boot DT : %X\n", reg_03.bits.boot_DT);
+ }
+
+ printk(KERN_DEBUG ".... IRQ redirection table:\n");
+
+ printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol"
+ " Stat Dmod Deli Vect: \n");
+
+ for (i = 0; i <= reg_01.bits.entries; i++) {
+ struct IO_APIC_route_entry entry;
+
+ entry = ioapic_read_entry(apic, i);
+
+ printk(KERN_DEBUG " %02x %03X ",
+ i,
+ entry.dest
+ );
+
+ printk("%1d %1d %1d %1d %1d %1d %1d %02X\n",
+ entry.mask,
+ entry.trigger,
+ entry.irr,
+ entry.polarity,
+ entry.delivery_status,
+ entry.dest_mode,
+ entry.delivery_mode,
+ entry.vector
+ );
+ }
+ }
+ printk(KERN_DEBUG "IRQ to pin mappings:\n");
+ for_each_irq_desc(irq, desc) {
+ struct irq_pin_list *entry;
+
+ cfg = desc->chip_data;
+ entry = cfg->irq_2_pin;
+ if (!entry)
+ continue;
+ printk(KERN_DEBUG "IRQ%d ", irq);
+ for (;;) {
+ printk("-> %d:%d", entry->apic, entry->pin);
+ if (!entry->next)
+ break;
+ entry = entry->next;
+ }
+ printk("\n");
+ }
+
+ printk(KERN_INFO ".................................... done.\n");
+
+ return;
+}
+
+__apicdebuginit(void) print_APIC_bitfield(int base)
+{
+ unsigned int v;
+ int i, j;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG);
+ for (i = 0; i < 8; i++) {
+ v = apic_read(base + i*0x10);
+ for (j = 0; j < 32; j++) {
+ if (v & (1<<j))
+ printk("1");
+ else
+ printk("0");
+ }
+ printk("\n");
+ }
+}
+
+__apicdebuginit(void) print_local_APIC(void *dummy)
+{
+ unsigned int v, ver, maxlvt;
+ u64 icr;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
+ smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
+ printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, read_apic_id());
+ v = apic_read(APIC_LVR);
+ printk(KERN_INFO "... APIC VERSION: %08x\n", v);
+ ver = GET_APIC_VERSION(v);
+ maxlvt = lapic_get_maxlvt();
+
+ v = apic_read(APIC_TASKPRI);
+ printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
+
+ if (APIC_INTEGRATED(ver)) { /* !82489DX */
+ if (!APIC_XAPIC(ver)) {
+ v = apic_read(APIC_ARBPRI);
+ printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
+ v & APIC_ARBPRI_MASK);
+ }
+ v = apic_read(APIC_PROCPRI);
+ printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v);
+ }
+
+ /*
+ * Remote read supported only in the 82489DX and local APIC for
+ * Pentium processors.
+ */
+ if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
+ v = apic_read(APIC_RRR);
+ printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_LDR);
+ printk(KERN_DEBUG "... APIC LDR: %08x\n", v);
+ if (!x2apic_enabled()) {
+ v = apic_read(APIC_DFR);
+ printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
+ }
+ v = apic_read(APIC_SPIV);
+ printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
+
+ printk(KERN_DEBUG "... APIC ISR field:\n");
+ print_APIC_bitfield(APIC_ISR);
+ printk(KERN_DEBUG "... APIC TMR field:\n");
+ print_APIC_bitfield(APIC_TMR);
+ printk(KERN_DEBUG "... APIC IRR field:\n");
+ print_APIC_bitfield(APIC_IRR);
+
+ if (APIC_INTEGRATED(ver)) { /* !82489DX */
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
+
+ v = apic_read(APIC_ESR);
+ printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
+ }
+
+ icr = apic_icr_read();
+ printk(KERN_DEBUG "... APIC ICR: %08x\n", (u32)icr);
+ printk(KERN_DEBUG "... APIC ICR2: %08x\n", (u32)(icr >> 32));
+
+ v = apic_read(APIC_LVTT);
+ printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
+
+ if (maxlvt > 3) { /* PC is LVT#4. */
+ v = apic_read(APIC_LVTPC);
+ printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v);
+ }
+ v = apic_read(APIC_LVT0);
+ printk(KERN_DEBUG "... APIC LVT0: %08x\n", v);
+ v = apic_read(APIC_LVT1);
+ printk(KERN_DEBUG "... APIC LVT1: %08x\n", v);
+
+ if (maxlvt > 2) { /* ERR is LVT#3. */
+ v = apic_read(APIC_LVTERR);
+ printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_TMICT);
+ printk(KERN_DEBUG "... APIC TMICT: %08x\n", v);
+ v = apic_read(APIC_TMCCT);
+ printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
+ v = apic_read(APIC_TDCR);
+ printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+ printk("\n");
+}
+
+__apicdebuginit(void) print_all_local_APICs(void)
+{
+ int cpu;
+
+ preempt_disable();
+ for_each_online_cpu(cpu)
+ smp_call_function_single(cpu, print_local_APIC, NULL, 1);
+ preempt_enable();
+}
+
+__apicdebuginit(void) print_PIC(void)
+{
+ unsigned int v;
+ unsigned long flags;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "\nprinting PIC contents\n");
+
+ spin_lock_irqsave(&i8259A_lock, flags);
+
+ v = inb(0xa1) << 8 | inb(0x21);
+ printk(KERN_DEBUG "... PIC IMR: %04x\n", v);
+
+ v = inb(0xa0) << 8 | inb(0x20);
+ printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
+
+ outb(0x0b,0xa0);
+ outb(0x0b,0x20);
+ v = inb(0xa0) << 8 | inb(0x20);
+ outb(0x0a,0xa0);
+ outb(0x0a,0x20);
+
+ spin_unlock_irqrestore(&i8259A_lock, flags);
+
+ printk(KERN_DEBUG "... PIC ISR: %04x\n", v);
+
+ v = inb(0x4d1) << 8 | inb(0x4d0);
+ printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
+}
+
+__apicdebuginit(int) print_all_ICs(void)
+{
+ print_PIC();
+ print_all_local_APICs();
+ print_IO_APIC();
+
+ return 0;
+}
+
+fs_initcall(print_all_ICs);
+
+
+/* Where if anywhere is the i8259 connect in external int mode */
+static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
+
+void __init enable_IO_APIC(void)
+{
+ union IO_APIC_reg_01 reg_01;
+ int i8259_apic, i8259_pin;
+ int apic;
+ unsigned long flags;
+
+ /*
+ * The number of IO-APIC IRQ registers (== #pins):
+ */
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(apic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+ }
+ for(apic = 0; apic < nr_ioapics; apic++) {
+ int pin;
+ /* See if any of the pins is in ExtINT mode */
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ struct IO_APIC_route_entry entry;
+ entry = ioapic_read_entry(apic, pin);
+
+ /* If the interrupt line is enabled and in ExtInt mode
+ * I have found the pin where the i8259 is connected.
+ */
+ if ((entry.mask == 0) && (entry.delivery_mode == dest_ExtINT)) {
+ ioapic_i8259.apic = apic;
+ ioapic_i8259.pin = pin;
+ goto found_i8259;
+ }
+ }
+ }
+ found_i8259:
+ /* Look to see what if the MP table has reported the ExtINT */
+ /* If we could not find the appropriate pin by looking at the ioapic
+ * the i8259 probably is not connected the ioapic but give the
+ * mptable a chance anyway.
+ */
+ i8259_pin = find_isa_irq_pin(0, mp_ExtINT);
+ i8259_apic = find_isa_irq_apic(0, mp_ExtINT);
+ /* Trust the MP table if nothing is setup in the hardware */
+ if ((ioapic_i8259.pin == -1) && (i8259_pin >= 0)) {
+ printk(KERN_WARNING "ExtINT not setup in hardware but reported by MP table\n");
+ ioapic_i8259.pin = i8259_pin;
+ ioapic_i8259.apic = i8259_apic;
+ }
+ /* Complain if the MP table and the hardware disagree */
+ if (((ioapic_i8259.apic != i8259_apic) || (ioapic_i8259.pin != i8259_pin)) &&
+ (i8259_pin >= 0) && (ioapic_i8259.pin >= 0))
+ {
+ printk(KERN_WARNING "ExtINT in hardware and MP table differ\n");
+ }
+
+ /*
+ * Do not trust the IO-APIC being empty at bootup
+ */
+ clear_IO_APIC();
+}
+
+/*
+ * Not an __init, needed by the reboot code
+ */
+void disable_IO_APIC(void)
+{
+ /*
+ * Clear the IO-APIC before rebooting:
+ */
+ clear_IO_APIC();
+
+ /*
+ * If the i8259 is routed through an IOAPIC
+ * Put that IOAPIC in virtual wire mode
+ * so legacy interrupts can be delivered.
+ */
+ if (ioapic_i8259.pin != -1) {
+ struct IO_APIC_route_entry entry;
+
+ memset(&entry, 0, sizeof(entry));
+ entry.mask = 0; /* Enabled */
+ entry.trigger = 0; /* Edge */
+ entry.irr = 0;
+ entry.polarity = 0; /* High */
+ entry.delivery_status = 0;
+ entry.dest_mode = 0; /* Physical */
+ entry.delivery_mode = dest_ExtINT; /* ExtInt */
+ entry.vector = 0;
+ entry.dest = read_apic_id();
+
+ /*
+ * Add it to the IO-APIC irq-routing table:
+ */
+ ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry);
+ }
+
+ disconnect_bsp_APIC(ioapic_i8259.pin != -1);
+}
+
+#ifdef CONFIG_X86_32
+/*
+ * function to set the IO-APIC physical IDs based on the
+ * values stored in the MPC table.
+ *
+ * by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999
+ */
+
+static void __init setup_ioapic_ids_from_mpc(void)
+{
+ union IO_APIC_reg_00 reg_00;
+ physid_mask_t phys_id_present_map;
+ int apic_id;
+ int i;
+ unsigned char old_id;
+ unsigned long flags;
+
+ if (x86_quirks->setup_ioapic_ids && x86_quirks->setup_ioapic_ids())
+ return;
+
+ /*
+ * Don't check I/O APIC IDs for xAPIC systems. They have
+ * no meaning without the serial APIC bus.
+ */
+ if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ || APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+ return;
+ /*
+ * This is broken; anything with a real cpu count has to
+ * circumvent this idiocy regardless.
+ */
+ phys_id_present_map = apic->ioapic_phys_id_map(phys_cpu_present_map);
+
+ /*
+ * Set the IOAPIC ID to the value stored in the MPC table.
+ */
+ for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
+
+ /* Read the register 0 value */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic_id, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ old_id = mp_ioapics[apic_id].apicid;
+
+ if (mp_ioapics[apic_id].apicid >= get_physical_broadcast()) {
+ printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
+ apic_id, mp_ioapics[apic_id].apicid);
+ printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
+ reg_00.bits.ID);
+ mp_ioapics[apic_id].apicid = reg_00.bits.ID;
+ }
+
+ /*
+ * Sanity check, is the ID really free? Every APIC in a
+ * system must have a unique ID or we get lots of nice
+ * 'stuck on smp_invalidate_needed IPI wait' messages.
+ */
+ if (apic->check_apicid_used(phys_id_present_map,
+ mp_ioapics[apic_id].apicid)) {
+ printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
+ apic_id, mp_ioapics[apic_id].apicid);
+ for (i = 0; i < get_physical_broadcast(); i++)
+ if (!physid_isset(i, phys_id_present_map))
+ break;
+ if (i >= get_physical_broadcast())
+ panic("Max APIC ID exceeded!\n");
+ printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
+ i);
+ physid_set(i, phys_id_present_map);
+ mp_ioapics[apic_id].apicid = i;
+ } else {
+ physid_mask_t tmp;
+ tmp = apic->apicid_to_cpu_present(mp_ioapics[apic_id].apicid);
+ apic_printk(APIC_VERBOSE, "Setting %d in the "
+ "phys_id_present_map\n",
+ mp_ioapics[apic_id].apicid);
+ physids_or(phys_id_present_map, phys_id_present_map, tmp);
+ }
+
+
+ /*
+ * We need to adjust the IRQ routing table
+ * if the ID changed.
+ */
+ if (old_id != mp_ioapics[apic_id].apicid)
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].dstapic == old_id)
+ mp_irqs[i].dstapic
+ = mp_ioapics[apic_id].apicid;
+
+ /*
+ * Read the right value from the MPC table and
+ * write it into the ID register.
+ */
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "...changing IO-APIC physical APIC ID to %d ...",
+ mp_ioapics[apic_id].apicid);
+
+ reg_00.bits.ID = mp_ioapics[apic_id].apicid;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic_id, 0, reg_00.raw);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ /*
+ * Sanity check
+ */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic_id, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ if (reg_00.bits.ID != mp_ioapics[apic_id].apicid)
+ printk("could not set ID!\n");
+ else
+ apic_printk(APIC_VERBOSE, " ok.\n");
+ }
+}
+#endif
+
+int no_timer_check __initdata;
+
+static int __init notimercheck(char *s)
+{
+ no_timer_check = 1;
+ return 1;
+}
+__setup("no_timer_check", notimercheck);
+
+/*
+ * There is a nasty bug in some older SMP boards, their mptable lies
+ * about the timer IRQ. We do the following to work around the situation:
+ *
+ * - timer IRQ defaults to IO-APIC IRQ
+ * - if this function detects that timer IRQs are defunct, then we fall
+ * back to ISA timer IRQs
+ */
+static int __init timer_irq_works(void)
+{
+ unsigned long t1 = jiffies;
+ unsigned long flags;
+
+ if (no_timer_check)
+ return 1;
+
+ local_save_flags(flags);
+ local_irq_enable();
+ /* Let ten ticks pass... */
+ mdelay((10 * 1000) / HZ);
+ local_irq_restore(flags);
+
+ /*
+ * Expect a few ticks at least, to be sure some possible
+ * glue logic does not lock up after one or two first
+ * ticks in a non-ExtINT mode. Also the local APIC
+ * might have cached one ExtINT interrupt. Finally, at
+ * least one tick may be lost due to delays.
+ */
+
+ /* jiffies wrap? */
+ if (time_after(jiffies, t1 + 4))
+ return 1;
+ return 0;
+}
+
+/*
+ * In the SMP+IOAPIC case it might happen that there are an unspecified
+ * number of pending IRQ events unhandled. These cases are very rare,
+ * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
+ * better to do it this way as thus we do not have to be aware of
+ * 'pending' interrupts in the IRQ path, except at this point.
+ */
+/*
+ * Edge triggered needs to resend any interrupt
+ * that was delayed but this is now handled in the device
+ * independent code.
+ */
+
+/*
+ * Starting up a edge-triggered IO-APIC interrupt is
+ * nasty - we need to make sure that we get the edge.
+ * If it is already asserted for some reason, we need
+ * return 1 to indicate that is was pending.
+ *
+ * This is not complete - we should be able to fake
+ * an edge even if it isn't on the 8259A...
+ */
+
+static unsigned int startup_ioapic_irq(unsigned int irq)
+{
+ int was_pending = 0;
+ unsigned long flags;
+ struct irq_cfg *cfg;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ if (irq < NR_IRQS_LEGACY) {
+ disable_8259A_irq(irq);
+ if (i8259A_irq_pending(irq))
+ was_pending = 1;
+ }
+ cfg = irq_cfg(irq);
+ __unmask_IO_APIC_irq(cfg);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return was_pending;
+}
+
+#ifdef CONFIG_X86_64
+static int ioapic_retrigger_irq(unsigned int irq)
+{
+
+ struct irq_cfg *cfg = irq_cfg(irq);
+ unsigned long flags;
+
+ spin_lock_irqsave(&vector_lock, flags);
+ apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
+ spin_unlock_irqrestore(&vector_lock, flags);
+
+ return 1;
+}
+#else
+static int ioapic_retrigger_irq(unsigned int irq)
+{
+ apic->send_IPI_self(irq_cfg(irq)->vector);
+
+ return 1;
+}
+#endif
+
+/*
+ * Level and edge triggered IO-APIC interrupts need different handling,
+ * so we use two separate IRQ descriptors. Edge triggered IRQs can be
+ * handled with the level-triggered descriptor, but that one has slightly
+ * more overhead. Level-triggered interrupts cannot be handled with the
+ * edge-triggered handler, without risking IRQ storms and other ugly
+ * races.
+ */
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_INTR_REMAP
+static void ir_irq_migration(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
+
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For edge triggered, irq migration is a simple atomic update(of vector
+ * and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we need to modify the io-apic RTE aswell with the update
+ * vector information, along with modifying IRTE with vector and destination.
+ * So irq migration for level triggered is little bit more complex compared to
+ * edge triggered migration. But the good news is, we use the same algorithm
+ * for level triggered migration as we have today, only difference being,
+ * we now initiate the irq migration from process context instead of the
+ * interrupt context.
+ *
+ * In future, when we do a directed EOI (combined with cpu EOI broadcast
+ * suppression) to the IO-APIC, level triggered irq migration will also be
+ * as simple as edge triggered migration and we can do the irq migration
+ * with a simple atomic update to IO-APIC RTE.
+ */
+static void
+migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ struct irte irte;
+ int modify_ioapic_rte;
+ unsigned int dest;
+ unsigned long flags;
+ unsigned int irq;
+
+ if (!cpumask_intersects(mask, cpu_online_mask))
+ return;
+
+ irq = desc->irq;
+ if (get_irte(irq, &irte))
+ return;
+
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
+ return;
+
+ set_extra_move_desc(desc, mask);
+
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
+
+ modify_ioapic_rte = desc->status & IRQ_LEVEL;
+ if (modify_ioapic_rte) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __target_IO_APIC_irq(irq, dest, cfg);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ }
+
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ /*
+ * Modified the IRTE and flushes the Interrupt entry cache.
+ */
+ modify_irte(irq, &irte);
+
+ if (cfg->move_in_progress)
+ send_cleanup_vector(cfg);
+
+ cpumask_copy(desc->affinity, mask);
+}
+
+static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
+{
+ int ret = -1;
+ struct irq_cfg *cfg = desc->chip_data;
+
+ mask_IO_APIC_irq_desc(desc);
+
+ if (io_apic_level_ack_pending(cfg)) {
+ /*
+ * Interrupt in progress. Migrating irq now will change the
+ * vector information in the IO-APIC RTE and that will confuse
+ * the EOI broadcast performed by cpu.
+ * So, delay the irq migration to the next instance.
+ */
+ schedule_delayed_work(&ir_migration_work, 1);
+ goto unmask;
+ }
+
+ /* everthing is clear. we have right of way */
+ migrate_ioapic_irq_desc(desc, desc->pending_mask);
+
+ ret = 0;
+ desc->status &= ~IRQ_MOVE_PENDING;
+ cpumask_clear(desc->pending_mask);
+
+unmask:
+ unmask_IO_APIC_irq_desc(desc);
+
+ return ret;
+}
+
+static void ir_irq_migration(struct work_struct *work)
+{
+ unsigned int irq;
+ struct irq_desc *desc;
+
+ for_each_irq_desc(irq, desc) {
+ if (desc->status & IRQ_MOVE_PENDING) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->chip->set_affinity ||
+ !(desc->status & IRQ_MOVE_PENDING)) {
+ desc->status &= ~IRQ_MOVE_PENDING;
+ spin_unlock_irqrestore(&desc->lock, flags);
+ continue;
+ }
+
+ desc->chip->set_affinity(irq, desc->pending_mask);
+ spin_unlock_irqrestore(&desc->lock, flags);
+ }
+ }
+}
+
+/*
+ * Migrates the IRQ destination in the process context.
+ */
+static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+ const struct cpumask *mask)
+{
+ if (desc->status & IRQ_LEVEL) {
+ desc->status |= IRQ_MOVE_PENDING;
+ cpumask_copy(desc->pending_mask, mask);
+ migrate_irq_remapped_level_desc(desc);
+ return;
+ }
+
+ migrate_ioapic_irq_desc(desc, mask);
+}
+static void set_ir_ioapic_affinity_irq(unsigned int irq,
+ const struct cpumask *mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ set_ir_ioapic_affinity_irq_desc(desc, mask);
+}
+#endif
+
+asmlinkage void smp_irq_move_cleanup_interrupt(void)
+{
+ unsigned vector, me;
+
+ ack_APIC_irq();
+ exit_idle();
+ irq_enter();
+
+ me = smp_processor_id();
+ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+ unsigned int irq;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ irq = __get_cpu_var(vector_irq)[vector];
+
+ if (irq == -1)
+ continue;
+
+ desc = irq_to_desc(irq);
+ if (!desc)
+ continue;
+
+ cfg = irq_cfg(irq);
+ spin_lock(&desc->lock);
+ if (!cfg->move_cleanup_count)
+ goto unlock;
+
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+ goto unlock;
+
+ __get_cpu_var(vector_irq)[vector] = -1;
+ cfg->move_cleanup_count--;
+unlock:
+ spin_unlock(&desc->lock);
+ }
+
+ irq_exit();
+}
+
+static void irq_complete_move(struct irq_desc **descp)
+{
+ struct irq_desc *desc = *descp;
+ struct irq_cfg *cfg = desc->chip_data;
+ unsigned vector, me;
+
+ if (likely(!cfg->move_in_progress)) {
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+ if (likely(!cfg->move_desc_pending))
+ return;
+
+ /* domain has not changed, but affinity did */
+ me = smp_processor_id();
+ if (cpumask_test_cpu(me, desc->affinity)) {
+ *descp = desc = move_irq_desc(desc, me);
+ /* get the new one */
+ cfg = desc->chip_data;
+ cfg->move_desc_pending = 0;
+ }
+#endif
+ return;
+ }
+
+ vector = ~get_irq_regs()->orig_ax;
+ me = smp_processor_id();
+
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+ *descp = desc = move_irq_desc(desc, me);
+ /* get the new one */
+ cfg = desc->chip_data;
+#endif
+ send_cleanup_vector(cfg);
+ }
+}
+#else
+static inline void irq_complete_move(struct irq_desc **descp) {}
+#endif
+
+#ifdef CONFIG_INTR_REMAP
+static void ack_x2apic_level(unsigned int irq)
+{
+ ack_x2APIC_irq();
+}
+
+static void ack_x2apic_edge(unsigned int irq)
+{
+ ack_x2APIC_irq();
+}
+
+#endif
+
+static void ack_apic_edge(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ irq_complete_move(&desc);
+ move_native_irq(irq);
+ ack_APIC_irq();
+}
+
+atomic_t irq_mis_count;
+
+static void ack_apic_level(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+#ifdef CONFIG_X86_32
+ unsigned long v;
+ int i;
+#endif
+ struct irq_cfg *cfg;
+ int do_unmask_irq = 0;
+
+ irq_complete_move(&desc);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+ /* If we are moving the irq we need to mask it */
+ if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
+ do_unmask_irq = 1;
+ mask_IO_APIC_irq_desc(desc);
+ }
+#endif
+
+#ifdef CONFIG_X86_32
+ /*
+ * It appears there is an erratum which affects at least version 0x11
+ * of I/O APIC (that's the 82093AA and cores integrated into various
+ * chipsets). Under certain conditions a level-triggered interrupt is
+ * erroneously delivered as edge-triggered one but the respective IRR
+ * bit gets set nevertheless. As a result the I/O unit expects an EOI
+ * message but it will never arrive and further interrupts are blocked
+ * from the source. The exact reason is so far unknown, but the
+ * phenomenon was observed when two consecutive interrupt requests
+ * from a given source get delivered to the same CPU and the source is
+ * temporarily disabled in between.
+ *
+ * A workaround is to simulate an EOI message manually. We achieve it
+ * by setting the trigger mode to edge and then to level when the edge
+ * trigger mode gets detected in the TMR of a local APIC for a
+ * level-triggered interrupt. We mask the source for the time of the
+ * operation to prevent an edge-triggered interrupt escaping meanwhile.
+ * The idea is from Manfred Spraul. --macro
+ */
+ cfg = desc->chip_data;
+ i = cfg->vector;
+
+ v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
+#endif
+
+ /*
+ * We must acknowledge the irq before we move it or the acknowledge will
+ * not propagate properly.
+ */
+ ack_APIC_irq();
+
+ /* Now we can move and renable the irq */
+ if (unlikely(do_unmask_irq)) {
+ /* Only migrate the irq if the ack has been received.
+ *
+ * On rare occasions the broadcast level triggered ack gets
+ * delayed going to ioapics, and if we reprogram the
+ * vector while Remote IRR is still set the irq will never
+ * fire again.
+ *
+ * To prevent this scenario we read the Remote IRR bit
+ * of the ioapic. This has two effects.
+ * - On any sane system the read of the ioapic will
+ * flush writes (and acks) going to the ioapic from
+ * this cpu.
+ * - We get to see if the ACK has actually been delivered.
+ *
+ * Based on failed experiments of reprogramming the
+ * ioapic entry from outside of irq context starting
+ * with masking the ioapic entry and then polling until
+ * Remote IRR was clear before reprogramming the
+ * ioapic I don't trust the Remote IRR bit to be
+ * completey accurate.
+ *
+ * However there appears to be no other way to plug
+ * this race, so if the Remote IRR bit is not
+ * accurate and is causing problems then it is a hardware bug
+ * and you can go talk to the chipset vendor about it.
+ */
+ cfg = desc->chip_data;
+ if (!io_apic_level_ack_pending(cfg))
+ move_masked_irq(irq);
+ unmask_IO_APIC_irq_desc(desc);
+ }
+
+#ifdef CONFIG_X86_32
+ if (!(v & (1 << (i & 0x1f)))) {
+ atomic_inc(&irq_mis_count);
+ spin_lock(&ioapic_lock);
+ __mask_and_edge_IO_APIC_irq(cfg);
+ __unmask_and_level_IO_APIC_irq(cfg);
+ spin_unlock(&ioapic_lock);
+ }
+#endif
+}
+
+static struct irq_chip ioapic_chip __read_mostly = {
+ .name = "IO-APIC",
+ .startup = startup_ioapic_irq,
+ .mask = mask_IO_APIC_irq,
+ .unmask = unmask_IO_APIC_irq,
+ .ack = ack_apic_edge,
+ .eoi = ack_apic_level,
+#ifdef CONFIG_SMP
+ .set_affinity = set_ioapic_affinity_irq,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip __read_mostly = {
+ .name = "IR-IO-APIC",
+ .startup = startup_ioapic_irq,
+ .mask = mask_IO_APIC_irq,
+ .unmask = unmask_IO_APIC_irq,
+ .ack = ack_x2apic_edge,
+ .eoi = ack_x2apic_level,
+#ifdef CONFIG_SMP
+ .set_affinity = set_ir_ioapic_affinity_irq,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+#endif
+
+static inline void init_IO_APIC_traps(void)
+{
+ int irq;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+
+ /*
+ * NOTE! The local APIC isn't very good at handling
+ * multiple interrupts at the same interrupt level.
+ * As the interrupt level is determined by taking the
+ * vector number and shifting that right by 4, we
+ * want to spread these out a bit so that they don't
+ * all fall in the same interrupt level.
+ *
+ * Also, we've got to be careful not to trash gate
+ * 0x80, because int 0x80 is hm, kind of importantish. ;)
+ */
+ for_each_irq_desc(irq, desc) {
+ cfg = desc->chip_data;
+ if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
+ /*
+ * Hmm.. We don't have an entry for this,
+ * so default to an old-fashioned 8259
+ * interrupt if we can..
+ */
+ if (irq < NR_IRQS_LEGACY)
+ make_8259A_irq(irq);
+ else
+ /* Strange. Oh, well.. */
+ desc->chip = &no_irq_chip;
+ }
+ }
+}
+
+/*
+ * The local APIC irq-chip implementation:
+ */
+
+static void mask_lapic_irq(unsigned int irq)
+{
+ unsigned long v;
+
+ v = apic_read(APIC_LVT0);
+ apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
+}
+
+static void unmask_lapic_irq(unsigned int irq)
+{
+ unsigned long v;
+
+ v = apic_read(APIC_LVT0);
+ apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
+}
+
+static void ack_lapic_irq(unsigned int irq)
+{
+ ack_APIC_irq();
+}
+
+static struct irq_chip lapic_chip __read_mostly = {
+ .name = "local-APIC",
+ .mask = mask_lapic_irq,
+ .unmask = unmask_lapic_irq,
+ .ack = ack_lapic_irq,
+};
+
+static void lapic_register_intr(int irq, struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_LEVEL;
+ set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+ "edge");
+}
+
+static void __init setup_nmi(void)
+{
+ /*
+ * Dirty trick to enable the NMI watchdog ...
+ * We put the 8259A master into AEOI mode and
+ * unmask on all local APICs LVT0 as NMI.
+ *
+ * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
+ * is from Maciej W. Rozycki - so we do not have to EOI from
+ * the NMI handler or the timer interrupt.
+ */
+ apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
+
+ enable_NMI_through_LVT0();
+
+ apic_printk(APIC_VERBOSE, " done.\n");
+}
+
+/*
+ * This looks a bit hackish but it's about the only one way of sending
+ * a few INTA cycles to 8259As and any associated glue logic. ICR does
+ * not support the ExtINT mode, unfortunately. We need to send these
+ * cycles as some i82489DX-based boards have glue logic that keeps the
+ * 8259A interrupt line asserted until INTA. --macro
+ */
+static inline void __init unlock_ExtINT_logic(void)
+{
+ int apic, pin, i;
+ struct IO_APIC_route_entry entry0, entry1;
+ unsigned char save_control, save_freq_select;
+
+ pin = find_isa_irq_pin(8, mp_INT);
+ if (pin == -1) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ apic = find_isa_irq_apic(8, mp_INT);
+ if (apic == -1) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ entry0 = ioapic_read_entry(apic, pin);
+ clear_IO_APIC_pin(apic, pin);
+
+ memset(&entry1, 0, sizeof(entry1));
+
+ entry1.dest_mode = 0; /* physical delivery */
+ entry1.mask = 0; /* unmask IRQ now */
+ entry1.dest = hard_smp_processor_id();
+ entry1.delivery_mode = dest_ExtINT;
+ entry1.polarity = entry0.polarity;
+ entry1.trigger = 0;
+ entry1.vector = 0;
+
+ ioapic_write_entry(apic, pin, entry1);
+
+ save_control = CMOS_READ(RTC_CONTROL);
+ save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+ CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6,
+ RTC_FREQ_SELECT);
+ CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL);
+
+ i = 100;
+ while (i-- > 0) {
+ mdelay(10);
+ if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF)
+ i -= 10;
+ }
+
+ CMOS_WRITE(save_control, RTC_CONTROL);
+ CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+ clear_IO_APIC_pin(apic, pin);
+
+ ioapic_write_entry(apic, pin, entry0);
+}
+
+static int disable_timer_pin_1 __initdata;
+/* Actually the next is obsolete, but keep it for paranoid reasons -AK */
+static int __init disable_timer_pin_setup(char *arg)
+{
+ disable_timer_pin_1 = 1;
+ return 0;
+}
+early_param("disable_timer_pin_1", disable_timer_pin_setup);
+
+int timer_through_8259 __initdata;
+
+/*
+ * This code may look a bit paranoid, but it's supposed to cooperate with
+ * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
+ * is so screwy. Thanks to Brian Perkins for testing/hacking this beast
+ * fanatically on his truly buggy board.
+ *
+ * FIXME: really need to revamp this for all platforms.
+ */
+static inline void __init check_timer(void)
+{
+ struct irq_desc *desc = irq_to_desc(0);
+ struct irq_cfg *cfg = desc->chip_data;
+ int cpu = boot_cpu_id;
+ int apic1, pin1, apic2, pin2;
+ unsigned long flags;
+ int no_pin1 = 0;
+
+ local_irq_save(flags);
+
+ /*
+ * get/set the timer IRQ vector:
+ */
+ disable_8259A_irq(0);
+ assign_irq_vector(0, cfg, apic->target_cpus());
+
+ /*
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC. Also
+ * timer interrupts need to be acknowledged manually in
+ * the 8259A for the i82489DX when using the NMI
+ * watchdog as that APIC treats NMIs as level-triggered.
+ * The AEOI mode will finish them in the 8259A
+ * automatically.
+ */
+ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ init_8259A(1);
+#ifdef CONFIG_X86_32
+ {
+ unsigned int ver;
+
+ ver = apic_read(APIC_LVR);
+ ver = GET_APIC_VERSION(ver);
+ timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+ }
+#endif
+
+ pin1 = find_isa_irq_pin(0, mp_INT);
+ apic1 = find_isa_irq_apic(0, mp_INT);
+ pin2 = ioapic_i8259.pin;
+ apic2 = ioapic_i8259.apic;
+
+ apic_printk(APIC_QUIET, KERN_INFO "..TIMER: vector=0x%02X "
+ "apic1=%d pin1=%d apic2=%d pin2=%d\n",
+ cfg->vector, apic1, pin1, apic2, pin2);
+
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ panic("BIOS bug: timer not connected to IO-APIC");
+#endif
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
+ if (pin1 != -1) {
+ /*
+ * Ok, does IRQ0 through the IOAPIC work?
+ */
+ if (no_pin1) {
+ add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ } else {
+ /* for edge trigger, setup_IO_APIC_irq already
+ * leave it unmasked.
+ * so only need to unmask if it is level-trigger
+ * do we really have level trigger timer?
+ */
+ int idx;
+ idx = find_irq_entry(apic1, pin1, mp_INT);
+ if (idx != -1 && irq_trigger(idx))
+ unmask_IO_APIC_irq_desc(desc);
+ }
+ if (timer_irq_works()) {
+ if (nmi_watchdog == NMI_IO_APIC) {
+ setup_nmi();
+ enable_8259A_irq(0);
+ }
+ if (disable_timer_pin_1 > 0)
+ clear_IO_APIC_pin(0, pin1);
+ goto out;
+ }
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ panic("timer doesn't work through Interrupt-remapped IO-APIC");
+#endif
+ local_irq_disable();
+ clear_IO_APIC_pin(apic1, pin1);
+ if (!no_pin1)
+ apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
+
+ apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer "
+ "(IRQ0) through the 8259A ...\n");
+ apic_printk(APIC_QUIET, KERN_INFO
+ "..... (found apic %d pin %d) ...\n", apic2, pin2);
+ /*
+ * legacy devices should be connected to IO APIC #0
+ */
+ replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ enable_8259A_irq(0);
+ if (timer_irq_works()) {
+ apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
+ timer_through_8259 = 1;
+ if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
+ setup_nmi();
+ enable_8259A_irq(0);
+ }
+ goto out;
+ }
+ /*
+ * Cleanup, just in case ...
+ */
+ local_irq_disable();
+ disable_8259A_irq(0);
+ clear_IO_APIC_pin(apic2, pin2);
+ apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
+ }
+
+ if (nmi_watchdog == NMI_IO_APIC) {
+ apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work "
+ "through the IO-APIC - disabling NMI Watchdog!\n");
+ nmi_watchdog = NMI_NONE;
+ }
+#ifdef CONFIG_X86_32
+ timer_ack = 0;
+#endif
+
+ apic_printk(APIC_QUIET, KERN_INFO
+ "...trying to set up timer as Virtual Wire IRQ...\n");
+
+ lapic_register_intr(0, desc);
+ apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
+ enable_8259A_irq(0);
+
+ if (timer_irq_works()) {
+ apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
+ goto out;
+ }
+ local_irq_disable();
+ disable_8259A_irq(0);
+ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
+ apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
+
+ apic_printk(APIC_QUIET, KERN_INFO
+ "...trying to set up timer as ExtINT IRQ...\n");
+
+ init_8259A(0);
+ make_8259A_irq(0);
+ apic_write(APIC_LVT0, APIC_DM_EXTINT);
+
+ unlock_ExtINT_logic();
+
+ if (timer_irq_works()) {
+ apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
+ goto out;
+ }
+ local_irq_disable();
+ apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n");
+ panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a "
+ "report. Then try booting with the 'noapic' option.\n");
+out:
+ local_irq_restore(flags);
+}
+
+/*
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices. However there may be an I/O APIC pin available for
+ * this interrupt regardless. The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A. In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table. With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default. We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor. Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now. No actual device should request
+ * it anyway. --macro
+ */
+#define PIC_IRQS (1 << PIC_CASCADE_IR)
+
+void __init setup_IO_APIC(void)
+{
+
+ /*
+ * calling enable_IO_APIC() is moved to setup_local_APIC for BP
+ */
+
+ io_apic_irqs = ~PIC_IRQS;
+
+ apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
+ /*
+ * Set up IO-APIC IRQ routing.
+ */
+#ifdef CONFIG_X86_32
+ if (!acpi_ioapic)
+ setup_ioapic_ids_from_mpc();
+#endif
+ sync_Arb_IDs();
+ setup_IO_APIC_irqs();
+ init_IO_APIC_traps();
+ check_timer();
+}
+
+/*
+ * Called after all the initialization is done. If we didnt find any
+ * APIC bugs then we can allow the modify fast path
+ */
+
+static int __init io_apic_bug_finalize(void)
+{
+ if (sis_apic_bug == -1)
+ sis_apic_bug = 0;
+ return 0;
+}
+
+late_initcall(io_apic_bug_finalize);
+
+struct sysfs_ioapic_data {
+ struct sys_device dev;
+ struct IO_APIC_route_entry entry[0];
+};
+static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+
+static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
+{
+ struct IO_APIC_route_entry *entry;
+ struct sysfs_ioapic_data *data;
+ int i;
+
+ data = container_of(dev, struct sysfs_ioapic_data, dev);
+ entry = data->entry;
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ )
+ *entry = ioapic_read_entry(dev->id, i);
+
+ return 0;
+}
+
+static int ioapic_resume(struct sys_device *dev)
+{
+ struct IO_APIC_route_entry *entry;
+ struct sysfs_ioapic_data *data;
+ unsigned long flags;
+ union IO_APIC_reg_00 reg_00;
+ int i;
+
+ data = container_of(dev, struct sysfs_ioapic_data, dev);
+ entry = data->entry;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(dev->id, 0);
+ if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].apicid;
+ io_apic_write(dev->id, 0, reg_00.raw);
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
+ ioapic_write_entry(dev->id, i, entry[i]);
+
+ return 0;
+}
+
+static struct sysdev_class ioapic_sysdev_class = {
+ .name = "ioapic",
+ .suspend = ioapic_suspend,
+ .resume = ioapic_resume,
+};
+
+static int __init ioapic_init_sysfs(void)
+{
+ struct sys_device * dev;
+ int i, size, error;
+
+ error = sysdev_class_register(&ioapic_sysdev_class);
+ if (error)
+ return error;
+
+ for (i = 0; i < nr_ioapics; i++ ) {
+ size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ * sizeof(struct IO_APIC_route_entry);
+ mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
+ if (!mp_ioapic_data[i]) {
+ printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
+ continue;
+ }
+ dev = &mp_ioapic_data[i]->dev;
+ dev->id = i;
+ dev->cls = &ioapic_sysdev_class;
+ error = sysdev_register(dev);
+ if (error) {
+ kfree(mp_ioapic_data[i]);
+ mp_ioapic_data[i] = NULL;
+ printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
+ continue;
+ }
+ }
+
+ return 0;
+}
+
+device_initcall(ioapic_init_sysfs);
+
+static int nr_irqs_gsi = NR_IRQS_LEGACY;
+/*
+ * Dynamic irq allocate and deallocation
+ */
+unsigned int create_irq_nr(unsigned int irq_want)
+{
+ /* Allocate an unused irq */
+ unsigned int irq;
+ unsigned int new;
+ unsigned long flags;
+ struct irq_cfg *cfg_new = NULL;
+ int cpu = boot_cpu_id;
+ struct irq_desc *desc_new = NULL;
+
+ irq = 0;
+ if (irq_want < nr_irqs_gsi)
+ irq_want = nr_irqs_gsi;
+
+ spin_lock_irqsave(&vector_lock, flags);
+ for (new = irq_want; new < nr_irqs; new++) {
+ desc_new = irq_to_desc_alloc_cpu(new, cpu);
+ if (!desc_new) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", new);
+ continue;
+ }
+ cfg_new = desc_new->chip_data;
+
+ if (cfg_new->vector != 0)
+ continue;
+ if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
+ irq = new;
+ break;
+ }
+ spin_unlock_irqrestore(&vector_lock, flags);
+
+ if (irq > 0) {
+ dynamic_irq_init(irq);
+ /* restore it, in case dynamic_irq_init clear it */
+ if (desc_new)
+ desc_new->chip_data = cfg_new;
+ }
+ return irq;
+}
+
+int create_irq(void)
+{
+ unsigned int irq_want;
+ int irq;
+
+ irq_want = nr_irqs_gsi;
+ irq = create_irq_nr(irq_want);
+
+ if (irq == 0)
+ irq = -1;
+
+ return irq;
+}
+
+void destroy_irq(unsigned int irq)
+{
+ unsigned long flags;
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+
+ /* store it, in case dynamic_irq_cleanup clear it */
+ desc = irq_to_desc(irq);
+ cfg = desc->chip_data;
+ dynamic_irq_cleanup(irq);
+ /* connect back irq_cfg */
+ if (desc)
+ desc->chip_data = cfg;
+
+#ifdef CONFIG_INTR_REMAP
+ free_irte(irq);
+#endif
+ spin_lock_irqsave(&vector_lock, flags);
+ __clear_irq_vector(irq, cfg);
+ spin_unlock_irqrestore(&vector_lock, flags);
+}
+
+/*
+ * MSI message composition
+ */
+#ifdef CONFIG_PCI_MSI
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
+{
+ struct irq_cfg *cfg;
+ int err;
+ unsigned dest;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ cfg = irq_cfg(irq);
+ err = assign_irq_vector(irq, cfg, apic->target_cpus());
+ if (err)
+ return err;
+
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ struct irte irte;
+ int ir_index;
+ u16 sub_handle;
+
+ ir_index = map_irq_to_irte_handle(irq, &sub_handle);
+ BUG_ON(ir_index == -1);
+
+ memset (&irte, 0, sizeof(irte));
+
+ irte.present = 1;
+ irte.dst_mode = apic->irq_dest_mode;
+ irte.trigger_mode = 0; /* edge */
+ irte.dlvry_mode = apic->irq_delivery_mode;
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ modify_irte(irq, &irte);
+
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->data = sub_handle;
+ msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+ MSI_ADDR_IR_SHV |
+ MSI_ADDR_IR_INDEX1(ir_index) |
+ MSI_ADDR_IR_INDEX2(ir_index);
+ } else
+#endif
+ {
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->address_lo =
+ MSI_ADDR_BASE_LO |
+ ((apic->irq_dest_mode == 0) ?
+ MSI_ADDR_DEST_MODE_PHYSICAL:
+ MSI_ADDR_DEST_MODE_LOGICAL) |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_ADDR_REDIRECTION_CPU:
+ MSI_ADDR_REDIRECTION_LOWPRI) |
+ MSI_ADDR_DEST_ID(dest);
+
+ msg->data =
+ MSI_DATA_TRIGGER_EDGE |
+ MSI_DATA_LEVEL_ASSERT |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_DATA_DELIVERY_FIXED:
+ MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_VECTOR(cfg->vector);
+ }
+ return err;
+}
+
+#ifdef CONFIG_SMP
+static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_cfg *cfg;
+ struct msi_msg msg;
+ unsigned int dest;
+
+ dest = set_desc_affinity(desc, mask);
+ if (dest == BAD_APICID)
+ return;
+
+ cfg = desc->chip_data;
+
+ read_msi_msg_desc(desc, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(cfg->vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+ write_msi_msg_desc(desc, &msg);
+}
+#ifdef CONFIG_INTR_REMAP
+/*
+ * Migrate the MSI irq to another cpumask. This migration is
+ * done in the process context using interrupt-remapping hardware.
+ */
+static void
+ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_cfg *cfg = desc->chip_data;
+ unsigned int dest;
+ struct irte irte;
+
+ if (get_irte(irq, &irte))
+ return;
+
+ dest = set_desc_affinity(desc, mask);
+ if (dest == BAD_APICID)
+ return;
+
+ irte.vector = cfg->vector;
+ irte.dest_id = IRTE_DEST(dest);
+
+ /*
+ * atomically update the IRTE with the new destination and vector.
+ */
+ modify_irte(irq, &irte);
+
+ /*
+ * After this point, all the interrupts will start arriving
+ * at the new destination. So, time to cleanup the previous
+ * vector allocation.
+ */
+ if (cfg->move_in_progress)
+ send_cleanup_vector(cfg);
+}
+
+#endif
+#endif /* CONFIG_SMP */
+
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip msi_chip = {
+ .name = "PCI-MSI",
+ .unmask = unmask_msi_irq,
+ .mask = mask_msi_irq,
+ .ack = ack_apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = set_msi_irq_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip msi_ir_chip = {
+ .name = "IR-PCI-MSI",
+ .unmask = unmask_msi_irq,
+ .mask = mask_msi_irq,
+ .ack = ack_x2apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = ir_set_msi_irq_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+/*
+ * Map the PCI dev to the corresponding remapping hardware unit
+ * and allocate 'nvec' consecutive interrupt-remapping table entries
+ * in it.
+ */
+static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
+{
+ struct intel_iommu *iommu;
+ int index;
+
+ iommu = map_dev_to_ir(dev);
+ if (!iommu) {
+ printk(KERN_ERR
+ "Unable to map PCI %s to iommu\n", pci_name(dev));
+ return -ENOENT;
+ }
+
+ index = alloc_irte(iommu, irq, nvec);
+ if (index < 0) {
+ printk(KERN_ERR
+ "Unable to allocate %d IRTE for PCI %s\n", nvec,
+ pci_name(dev));
+ return -ENOSPC;
+ }
+ return index;
+}
+#endif
+
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+{
+ int ret;
+ struct msi_msg msg;
+
+ ret = msi_compose_msg(dev, irq, &msg);
+ if (ret < 0)
+ return ret;
+
+ set_irq_msi(irq, msidesc);
+ write_msi_msg(irq, &msg);
+
+#ifdef CONFIG_INTR_REMAP
+ if (irq_remapped(irq)) {
+ struct irq_desc *desc = irq_to_desc(irq);
+ /*
+ * irq migration in process context
+ */
+ desc->status |= IRQ_MOVE_PCNTXT;
+ set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
+ } else
+#endif
+ set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+
+ dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
+
+ return 0;
+}
+
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ unsigned int irq;
+ int ret, sub_handle;
+ struct msi_desc *msidesc;
+ unsigned int irq_want;
+
+#ifdef CONFIG_INTR_REMAP
+ struct intel_iommu *iommu = 0;
+ int index = 0;
+#endif
+
+ irq_want = nr_irqs_gsi;
+ sub_handle = 0;
+ list_for_each_entry(msidesc, &dev->msi_list, list) {
+ irq = create_irq_nr(irq_want);
+ if (irq == 0)
+ return -1;
+ irq_want = irq + 1;
+#ifdef CONFIG_INTR_REMAP
+ if (!intr_remapping_enabled)
+ goto no_ir;
+
+ if (!sub_handle) {
+ /*
+ * allocate the consecutive block of IRTE's
+ * for 'nvec'
+ */
+ index = msi_alloc_irte(dev, irq, nvec);
+ if (index < 0) {
+ ret = index;
+ goto error;
+ }
+ } else {
+ iommu = map_dev_to_ir(dev);
+ if (!iommu) {
+ ret = -ENOENT;
+ goto error;
+ }
+ /*
+ * setup the mapping between the irq and the IRTE
+ * base index, the sub_handle pointing to the
+ * appropriate interrupt remap table entry.
+ */
+ set_irte_irq(irq, iommu, index, sub_handle);
+ }
+no_ir:
+#endif
+ ret = setup_msi_irq(dev, msidesc, irq);
+ if (ret < 0)
+ goto error;
+ sub_handle++;
+ }
+ return 0;
+
+error:
+ destroy_irq(irq);
+ return ret;
+}
+
+void arch_teardown_msi_irq(unsigned int irq)
+{
+ destroy_irq(irq);
+}
+
+#ifdef CONFIG_DMAR
+#ifdef CONFIG_SMP
+static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_cfg *cfg;
+ struct msi_msg msg;
+ unsigned int dest;
+
+ dest = set_desc_affinity(desc, mask);
+ if (dest == BAD_APICID)
+ return;
+
+ cfg = desc->chip_data;
+
+ dmar_msi_read(irq, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(cfg->vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+ dmar_msi_write(irq, &msg);
+}
+
+#endif /* CONFIG_SMP */
+
+struct irq_chip dmar_msi_type = {
+ .name = "DMAR_MSI",
+ .unmask = dmar_msi_unmask,
+ .mask = dmar_msi_mask,
+ .ack = ack_apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = dmar_msi_set_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_dmar_msi(unsigned int irq)
+{
+ int ret;
+ struct msi_msg msg;
+
+ ret = msi_compose_msg(NULL, irq, &msg);
+ if (ret < 0)
+ return ret;
+ dmar_msi_write(irq, &msg);
+ set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+ "edge");
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_HPET_TIMER
+
+#ifdef CONFIG_SMP
+static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_cfg *cfg;
+ struct msi_msg msg;
+ unsigned int dest;
+
+ dest = set_desc_affinity(desc, mask);
+ if (dest == BAD_APICID)
+ return;
+
+ cfg = desc->chip_data;
+
+ hpet_msi_read(irq, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(cfg->vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+ hpet_msi_write(irq, &msg);
+}
+
+#endif /* CONFIG_SMP */
+
+struct irq_chip hpet_msi_type = {
+ .name = "HPET_MSI",
+ .unmask = hpet_msi_unmask,
+ .mask = hpet_msi_mask,
+ .ack = ack_apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = hpet_msi_set_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_hpet_msi(unsigned int irq)
+{
+ int ret;
+ struct msi_msg msg;
+
+ ret = msi_compose_msg(NULL, irq, &msg);
+ if (ret < 0)
+ return ret;
+
+ hpet_msi_write(irq, &msg);
+ set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq,
+ "edge");
+
+ return 0;
+}
+#endif
+
+#endif /* CONFIG_PCI_MSI */
+/*
+ * Hypertransport interrupt support
+ */
+#ifdef CONFIG_HT_IRQ
+
+#ifdef CONFIG_SMP
+
+static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
+{
+ struct ht_irq_msg msg;
+ fetch_ht_irq_msg(irq, &msg);
+
+ msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
+ msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+
+ msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
+ msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
+
+ write_ht_irq_msg(irq, &msg);
+}
+
+static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_cfg *cfg;
+ unsigned int dest;
+
+ dest = set_desc_affinity(desc, mask);
+ if (dest == BAD_APICID)
+ return;
+
+ cfg = desc->chip_data;
+
+ target_ht_irq(irq, dest, cfg->vector);
+}
+
+#endif
+
+static struct irq_chip ht_irq_chip = {
+ .name = "PCI-HT",
+ .mask = mask_ht_irq,
+ .unmask = unmask_ht_irq,
+ .ack = ack_apic_edge,
+#ifdef CONFIG_SMP
+ .set_affinity = set_ht_irq_affinity,
+#endif
+ .retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+{
+ struct irq_cfg *cfg;
+ int err;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ cfg = irq_cfg(irq);
+ err = assign_irq_vector(irq, cfg, apic->target_cpus());
+ if (!err) {
+ struct ht_irq_msg msg;
+ unsigned dest;
+
+ dest = apic->cpu_mask_to_apicid_and(cfg->domain,
+ apic->target_cpus());
+
+ msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+
+ msg.address_lo =
+ HT_IRQ_LOW_BASE |
+ HT_IRQ_LOW_DEST_ID(dest) |
+ HT_IRQ_LOW_VECTOR(cfg->vector) |
+ ((apic->irq_dest_mode == 0) ?
+ HT_IRQ_LOW_DM_PHYSICAL :
+ HT_IRQ_LOW_DM_LOGICAL) |
+ HT_IRQ_LOW_RQEOI_EDGE |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ HT_IRQ_LOW_MT_FIXED :
+ HT_IRQ_LOW_MT_ARBITRATED) |
+ HT_IRQ_LOW_IRQ_MASKED;
+
+ write_ht_irq_msg(irq, &msg);
+
+ set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+ handle_edge_irq, "edge");
+
+ dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
+ }
+ return err;
+}
+#endif /* CONFIG_HT_IRQ */
+
+#ifdef CONFIG_X86_UV
+/*
+ * Re-target the irq to the specified CPU and enable the specified MMR located
+ * on the specified blade to allow the sending of MSIs to the specified CPU.
+ */
+int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
+ unsigned long mmr_offset)
+{
+ const struct cpumask *eligible_cpu = cpumask_of(cpu);
+ struct irq_cfg *cfg;
+ int mmr_pnode;
+ unsigned long mmr_value;
+ struct uv_IO_APIC_route_entry *entry;
+ unsigned long flags;
+ int err;
+
+ cfg = irq_cfg(irq);
+
+ err = assign_irq_vector(irq, cfg, eligible_cpu);
+ if (err != 0)
+ return err;
+
+ spin_lock_irqsave(&vector_lock, flags);
+ set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
+ irq_name);
+ spin_unlock_irqrestore(&vector_lock, flags);
+
+ mmr_value = 0;
+ entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+ BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
+ entry->vector = cfg->vector;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->polarity = 0;
+ entry->trigger = 0;
+ entry->mask = 0;
+ entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
+
+ mmr_pnode = uv_blade_to_pnode(mmr_blade);
+ uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+
+ return irq;
+}
+
+/*
+ * Disable the specified MMR located on the specified blade so that MSIs are
+ * longer allowed to be sent.
+ */
+void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset)
+{
+ unsigned long mmr_value;
+ struct uv_IO_APIC_route_entry *entry;
+ int mmr_pnode;
+
+ mmr_value = 0;
+ entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+ BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
+ entry->mask = 1;
+
+ mmr_pnode = uv_blade_to_pnode(mmr_blade);
+ uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+}
+#endif /* CONFIG_X86_64 */
+
+int __init io_apic_get_redir_entries (int ioapic)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(ioapic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return reg_01.bits.entries;
+}
+
+void __init probe_nr_irqs_gsi(void)
+{
+ int nr = 0;
+
+ nr = acpi_probe_gsi();
+ if (nr > nr_irqs_gsi) {
+ nr_irqs_gsi = nr;
+ } else {
+ /* for acpi=off or acpi is not compiled in */
+ int idx;
+
+ nr = 0;
+ for (idx = 0; idx < nr_ioapics; idx++)
+ nr += io_apic_get_redir_entries(idx) + 1;
+
+ if (nr > nr_irqs_gsi)
+ nr_irqs_gsi = nr;
+ }
+
+ printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
+}
+
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+ int nr;
+
+ if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
+ nr_irqs = NR_VECTORS * nr_cpu_ids;
+
+ nr = nr_irqs_gsi + 8 * nr_cpu_ids;
+#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
+ /*
+ * for MSI and HT dyn irq
+ */
+ nr += nr_irqs_gsi * 16;
+#endif
+ if (nr < nr_irqs)
+ nr_irqs = nr;
+
+ return 0;
+}
+#endif
+
+/* --------------------------------------------------------------------------
+ ACPI-based IOAPIC Configuration
+ -------------------------------------------------------------------------- */
+
+#ifdef CONFIG_ACPI
+
+#ifdef CONFIG_X86_32
+int __init io_apic_get_unique_id(int ioapic, int apic_id)
+{
+ union IO_APIC_reg_00 reg_00;
+ static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
+ physid_mask_t tmp;
+ unsigned long flags;
+ int i = 0;
+
+ /*
+ * The P4 platform supports up to 256 APIC IDs on two separate APIC
+ * buses (one for LAPICs, one for IOAPICs), where predecessors only
+ * supports up to 16 on one shared APIC bus.
+ *
+ * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
+ * advantage of new APIC bus architecture.
+ */
+
+ if (physids_empty(apic_id_map))
+ apic_id_map = apic->ioapic_phys_id_map(phys_cpu_present_map);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(ioapic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ if (apic_id >= get_physical_broadcast()) {
+ printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
+ "%d\n", ioapic, apic_id, reg_00.bits.ID);
+ apic_id = reg_00.bits.ID;
+ }
+
+ /*
+ * Every APIC in a system must have a unique ID or we get lots of nice
+ * 'stuck on smp_invalidate_needed IPI wait' messages.
+ */
+ if (apic->check_apicid_used(apic_id_map, apic_id)) {
+
+ for (i = 0; i < get_physical_broadcast(); i++) {
+ if (!apic->check_apicid_used(apic_id_map, i))
+ break;
+ }
+
+ if (i == get_physical_broadcast())
+ panic("Max apic_id exceeded!\n");
+
+ printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, "
+ "trying %d\n", ioapic, apic_id, i);
+
+ apic_id = i;
+ }
+
+ tmp = apic->apicid_to_cpu_present(apic_id);
+ physids_or(apic_id_map, apic_id_map, tmp);
+
+ if (reg_00.bits.ID != apic_id) {
+ reg_00.bits.ID = apic_id;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(ioapic, 0, reg_00.raw);
+ reg_00.raw = io_apic_read(ioapic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ /* Sanity check */
+ if (reg_00.bits.ID != apic_id) {
+ printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic);
+ return -1;
+ }
+ }
+
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id);
+
+ return apic_id;
+}
+
+int __init io_apic_get_version(int ioapic)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(ioapic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return reg_01.bits.version;
+}
+#endif
+
+int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
+{
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ int cpu = boot_cpu_id;
+
+ if (!IO_APIC_IRQ(irq)) {
+ apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+ ioapic);
+ return -EINVAL;
+ }
+
+ desc = irq_to_desc_alloc_cpu(irq, cpu);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc %d\n", irq);
+ return 0;
+ }
+
+ /*
+ * IRQs < 16 are already in the irq_2_pin[] map
+ */
+ if (irq >= NR_IRQS_LEGACY) {
+ cfg = desc->chip_data;
+ add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
+ }
+
+ setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);
+
+ return 0;
+}
+
+
+int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
+{
+ int i;
+
+ if (skip_ioapic_setup)
+ return -1;
+
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].irqtype == mp_INT &&
+ mp_irqs[i].srcbusirq == bus_irq)
+ break;
+ if (i >= mp_irq_entries)
+ return -1;
+
+ *trigger = irq_trigger(i);
+ *polarity = irq_polarity(i);
+ return 0;
+}
+
+#endif /* CONFIG_ACPI */
+
+/*
+ * This function currently is only a helper for the i386 smp boot process where
+ * we need to reprogram the ioredtbls to cater for the cpus which have come online
+ * so mask in all cases should simply be apic->target_cpus()
+ */
+#ifdef CONFIG_SMP
+void __init setup_ioapic_dest(void)
+{
+ int pin, ioapic, irq, irq_entry;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ const struct cpumask *mask;
+
+ if (skip_ioapic_setup == 1)
+ return;
+
+ for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
+ for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+ irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+ if (irq_entry == -1)
+ continue;
+ irq = pin_2_irq(irq_entry, ioapic, pin);
+
+ /* setup_IO_APIC_irqs could fail to get vector for some device
+ * when you have too many devices, because at that time only boot
+ * cpu is online.
+ */
+ desc = irq_to_desc(irq);
+ cfg = desc->chip_data;
+ if (!cfg->vector) {
+ setup_IO_APIC_irq(ioapic, pin, irq, desc,
+ irq_trigger(irq_entry),
+ irq_polarity(irq_entry));
+ continue;
+
+ }
+
+ /*
+ * Honour affinities which have been set in early boot
+ */
+ if (desc->status &
+ (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+ mask = desc->affinity;
+ else
+ mask = apic->target_cpus();
+
+#ifdef CONFIG_INTR_REMAP
+ if (intr_remapping_enabled)
+ set_ir_ioapic_affinity_irq_desc(desc, mask);
+ else
+#endif
+ set_ioapic_affinity_irq_desc(desc, mask);
+ }
+
+ }
+}
+#endif
+
+#define IOAPIC_RESOURCE_NAME_SIZE 11
+
+static struct resource *ioapic_resources;
+
+static struct resource * __init ioapic_setup_resources(void)
+{
+ unsigned long n;
+ struct resource *res;
+ char *mem;
+ int i;
+
+ if (nr_ioapics <= 0)
+ return NULL;
+
+ n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
+ n *= nr_ioapics;
+
+ mem = alloc_bootmem(n);
+ res = (void *)mem;
+
+ if (mem != NULL) {
+ mem += sizeof(struct resource) * nr_ioapics;
+
+ for (i = 0; i < nr_ioapics; i++) {
+ res[i].name = mem;
+ res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ sprintf(mem, "IOAPIC %u", i);
+ mem += IOAPIC_RESOURCE_NAME_SIZE;
+ }
+ }
+
+ ioapic_resources = res;
+
+ return res;
+}
+
+void __init ioapic_init_mappings(void)
+{
+ unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
+ struct resource *ioapic_res;
+ int i;
+
+ ioapic_res = ioapic_setup_resources();
+ for (i = 0; i < nr_ioapics; i++) {
+ if (smp_found_config) {
+ ioapic_phys = mp_ioapics[i].apicaddr;
+#ifdef CONFIG_X86_32
+ if (!ioapic_phys) {
+ printk(KERN_ERR
+ "WARNING: bogus zero IO-APIC "
+ "address found in MPTABLE, "
+ "disabling IO/APIC support!\n");
+ smp_found_config = 0;
+ skip_ioapic_setup = 1;
+ goto fake_ioapic_page;
+ }
+#endif
+ } else {
+#ifdef CONFIG_X86_32
+fake_ioapic_page:
+#endif
+ ioapic_phys = (unsigned long)
+ alloc_bootmem_pages(PAGE_SIZE);
+ ioapic_phys = __pa(ioapic_phys);
+ }
+ set_fixmap_nocache(idx, ioapic_phys);
+ apic_printk(APIC_VERBOSE,
+ "mapped IOAPIC to %08lx (%08lx)\n",
+ __fix_to_virt(idx), ioapic_phys);
+ idx++;
+
+ if (ioapic_res != NULL) {
+ ioapic_res->start = ioapic_phys;
+ ioapic_res->end = ioapic_phys + (4 * 1024) - 1;
+ ioapic_res++;
+ }
+ }
+}
+
+static int __init ioapic_insert_resources(void)
+{
+ int i;
+ struct resource *r = ioapic_resources;
+
+ if (!r) {
+ printk(KERN_ERR
+ "IO APIC resources could be not be allocated.\n");
+ return -1;
+ }
+
+ for (i = 0; i < nr_ioapics; i++) {
+ insert_resource(&iomem_resource, r);
+ r++;
+ }
+
+ return 0;
+}
+
+/* Insert the IO APIC resources after PCI initialization has occured to handle
+ * IO APICS that are mapped in on a BAR in PCI space. */
+late_initcall(ioapic_insert_resources);
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
new file mode 100644
index 0000000..dbf5445
--- /dev/null
+++ b/arch/x86/kernel/apic/ipi.c
@@ -0,0 +1,164 @@
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/cache.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/apic.h>
+#include <asm/proto.h>
+#include <asm/ipi.h>
+
+void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector)
+{
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ /*
+ * Hack. The clustered APIC addressing mode doesn't allow us to send
+ * to an arbitrary mask, so I do a unicast to each CPU instead.
+ * - mbligh
+ */
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
+ query_cpu), vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
+
+void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
+ int vector)
+{
+ unsigned int this_cpu = smp_processor_id();
+ unsigned int query_cpu;
+ unsigned long flags;
+
+ /* See Hack comment above */
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu == this_cpu)
+ continue;
+ __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
+ query_cpu), vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
+
+void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+ int vector)
+{
+ unsigned long flags;
+ unsigned int query_cpu;
+
+ /*
+ * Hack. The clustered APIC addressing mode doesn't allow us to send
+ * to an arbitrary mask, so I do a unicasts to each CPU instead. This
+ * should be modified to do 1 message per cluster ID - mbligh
+ */
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask)
+ __default_send_IPI_dest_field(
+ apic->cpu_to_logical_apicid(query_cpu), vector,
+ apic->dest_logical);
+ local_irq_restore(flags);
+}
+
+void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+ int vector)
+{
+ unsigned long flags;
+ unsigned int query_cpu;
+ unsigned int this_cpu = smp_processor_id();
+
+ /* See Hack comment above */
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu == this_cpu)
+ continue;
+ __default_send_IPI_dest_field(
+ apic->cpu_to_logical_apicid(query_cpu), vector,
+ apic->dest_logical);
+ }
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_X86_32
+
+/*
+ * This is only used on smaller machines.
+ */
+void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
+{
+ unsigned long mask = cpumask_bits(cpumask)[0];
+ unsigned long flags;
+
+ local_irq_save(flags);
+ WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]);
+ __default_send_IPI_dest_field(mask, vector, apic->dest_logical);
+ local_irq_restore(flags);
+}
+
+void default_send_IPI_allbutself(int vector)
+{
+ /*
+ * if there are no other CPUs in the system then we get an APIC send
+ * error if we try to broadcast, thus avoid sending IPIs in this case.
+ */
+ if (!(num_online_cpus() > 1))
+ return;
+
+ __default_local_send_IPI_allbutself(vector);
+}
+
+void default_send_IPI_all(int vector)
+{
+ __default_local_send_IPI_all(vector);
+}
+
+void default_send_IPI_self(int vector)
+{
+ __default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical);
+}
+
+/* must come after the send_IPI functions above for inlining */
+static int convert_apicid_to_cpu(int apic_id)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
+ return i;
+ }
+ return -1;
+}
+
+int safe_smp_processor_id(void)
+{
+ int apicid, cpuid;
+
+ if (!boot_cpu_has(X86_FEATURE_APIC))
+ return 0;
+
+ apicid = hard_smp_processor_id();
+ if (apicid == BAD_APICID)
+ return 0;
+
+ cpuid = convert_apicid_to_cpu(apicid);
+
+ return cpuid >= 0 ? cpuid : 0;
+}
+#endif
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
new file mode 100644
index 0000000..bdfad80
--- /dev/null
+++ b/arch/x86/kernel/apic/nmi.c
@@ -0,0 +1,564 @@
+/*
+ * NMI watchdog support on APIC systems
+ *
+ * Started by Ingo Molnar <mingo@redhat.com>
+ *
+ * Fixes:
+ * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog.
+ * Mikael Pettersson : Power Management for local APIC NMI watchdog.
+ * Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog.
+ * Pavel Machek and
+ * Mikael Pettersson : PM converted to driver model. Disable/enable API.
+ */
+
+#include <asm/apic.h>
+
+#include <linux/nmi.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/sysdev.h>
+#include <linux/sysctl.h>
+#include <linux/percpu.h>
+#include <linux/kprobes.h>
+#include <linux/cpumask.h>
+#include <linux/kernel_stat.h>
+#include <linux/kdebug.h>
+#include <linux/smp.h>
+
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
+#include <asm/proto.h>
+#include <asm/timer.h>
+
+#include <asm/mce.h>
+
+#include <asm/mach_traps.h>
+
+int unknown_nmi_panic;
+int nmi_watchdog_enabled;
+
+static cpumask_t backtrace_mask = CPU_MASK_NONE;
+
+/* nmi_active:
+ * >0: the lapic NMI watchdog is active, but can be disabled
+ * <0: the lapic NMI watchdog has not been set up, and cannot
+ * be enabled
+ * 0: the lapic NMI watchdog is disabled, but can be enabled
+ */
+atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
+
+unsigned int nmi_watchdog = NMI_NONE;
+EXPORT_SYMBOL(nmi_watchdog);
+
+static int panic_on_timeout;
+
+static unsigned int nmi_hz = HZ;
+static DEFINE_PER_CPU(short, wd_enabled);
+static int endflag __initdata;
+
+static inline unsigned int get_nmi_count(int cpu)
+{
+ return per_cpu(irq_stat, cpu).__nmi_count;
+}
+
+static inline int mce_in_progress(void)
+{
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+ return atomic_read(&mce_entry) > 0;
+#endif
+ return 0;
+}
+
+/*
+ * Take the local apic timer and PIT/HPET into account. We don't
+ * know which one is active, when we have highres/dyntick on
+ */
+static inline unsigned int get_timer_irqs(int cpu)
+{
+ return per_cpu(irq_stat, cpu).apic_timer_irqs +
+ per_cpu(irq_stat, cpu).irq0_irqs;
+}
+
+#ifdef CONFIG_SMP
+/*
+ * The performance counters used by NMI_LOCAL_APIC don't trigger when
+ * the CPU is idle. To make sure the NMI watchdog really ticks on all
+ * CPUs during the test make them busy.
+ */
+static __init void nmi_cpu_busy(void *data)
+{
+ local_irq_enable_in_hardirq();
+ /*
+ * Intentionally don't use cpu_relax here. This is
+ * to make sure that the performance counter really ticks,
+ * even if there is a simulator or similar that catches the
+ * pause instruction. On a real HT machine this is fine because
+ * all other CPUs are busy with "useless" delay loops and don't
+ * care if they get somewhat less cycles.
+ */
+ while (endflag == 0)
+ mb();
+}
+#endif
+
+static void report_broken_nmi(int cpu, int *prev_nmi_count)
+{
+ printk(KERN_CONT "\n");
+
+ printk(KERN_WARNING
+ "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
+ cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
+
+ printk(KERN_WARNING
+ "Please report this to bugzilla.kernel.org,\n");
+ printk(KERN_WARNING
+ "and attach the output of the 'dmesg' command.\n");
+
+ per_cpu(wd_enabled, cpu) = 0;
+ atomic_dec(&nmi_active);
+}
+
+static void __acpi_nmi_disable(void *__unused)
+{
+ apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+}
+
+int __init check_nmi_watchdog(void)
+{
+ unsigned int *prev_nmi_count;
+ int cpu;
+
+ if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
+ return 0;
+
+ prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
+ if (!prev_nmi_count)
+ goto error;
+
+ printk(KERN_INFO "Testing NMI watchdog ... ");
+
+#ifdef CONFIG_SMP
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
+#endif
+
+ for_each_possible_cpu(cpu)
+ prev_nmi_count[cpu] = get_nmi_count(cpu);
+ local_irq_enable();
+ mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
+
+ for_each_online_cpu(cpu) {
+ if (!per_cpu(wd_enabled, cpu))
+ continue;
+ if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
+ report_broken_nmi(cpu, prev_nmi_count);
+ }
+ endflag = 1;
+ if (!atomic_read(&nmi_active)) {
+ kfree(prev_nmi_count);
+ atomic_set(&nmi_active, -1);
+ goto error;
+ }
+ printk("OK.\n");
+
+ /*
+ * now that we know it works we can reduce NMI frequency to
+ * something more reasonable; makes a difference in some configs
+ */
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ nmi_hz = lapic_adjust_nmi_hz(1);
+
+ kfree(prev_nmi_count);
+ return 0;
+error:
+ if (nmi_watchdog == NMI_IO_APIC) {
+ if (!timer_through_8259)
+ disable_8259A_irq(0);
+ on_each_cpu(__acpi_nmi_disable, NULL, 1);
+ }
+
+#ifdef CONFIG_X86_32
+ timer_ack = 0;
+#endif
+ return -1;
+}
+
+static int __init setup_nmi_watchdog(char *str)
+{
+ unsigned int nmi;
+
+ if (!strncmp(str, "panic", 5)) {
+ panic_on_timeout = 1;
+ str = strchr(str, ',');
+ if (!str)
+ return 1;
+ ++str;
+ }
+
+ if (!strncmp(str, "lapic", 5))
+ nmi_watchdog = NMI_LOCAL_APIC;
+ else if (!strncmp(str, "ioapic", 6))
+ nmi_watchdog = NMI_IO_APIC;
+ else {
+ get_option(&str, &nmi);
+ if (nmi >= NMI_INVALID)
+ return 0;
+ nmi_watchdog = nmi;
+ }
+
+ return 1;
+}
+__setup("nmi_watchdog=", setup_nmi_watchdog);
+
+/*
+ * Suspend/resume support
+ */
+#ifdef CONFIG_PM
+
+static int nmi_pm_active; /* nmi_active before suspend */
+
+static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
+{
+ /* only CPU0 goes here, other CPUs should be offline */
+ nmi_pm_active = atomic_read(&nmi_active);
+ stop_apic_nmi_watchdog(NULL);
+ BUG_ON(atomic_read(&nmi_active) != 0);
+ return 0;
+}
+
+static int lapic_nmi_resume(struct sys_device *dev)
+{
+ /* only CPU0 goes here, other CPUs should be offline */
+ if (nmi_pm_active > 0) {
+ setup_apic_nmi_watchdog(NULL);
+ touch_nmi_watchdog();
+ }
+ return 0;
+}
+
+static struct sysdev_class nmi_sysclass = {
+ .name = "lapic_nmi",
+ .resume = lapic_nmi_resume,
+ .suspend = lapic_nmi_suspend,
+};
+
+static struct sys_device device_lapic_nmi = {
+ .id = 0,
+ .cls = &nmi_sysclass,
+};
+
+static int __init init_lapic_nmi_sysfs(void)
+{
+ int error;
+
+ /*
+ * should really be a BUG_ON but b/c this is an
+ * init call, it just doesn't work. -dcz
+ */
+ if (nmi_watchdog != NMI_LOCAL_APIC)
+ return 0;
+
+ if (atomic_read(&nmi_active) < 0)
+ return 0;
+
+ error = sysdev_class_register(&nmi_sysclass);
+ if (!error)
+ error = sysdev_register(&device_lapic_nmi);
+ return error;
+}
+
+/* must come after the local APIC's device_initcall() */
+late_initcall(init_lapic_nmi_sysfs);
+
+#endif /* CONFIG_PM */
+
+static void __acpi_nmi_enable(void *__unused)
+{
+ apic_write(APIC_LVT0, APIC_DM_NMI);
+}
+
+/*
+ * Enable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_enable(void)
+{
+ if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+ on_each_cpu(__acpi_nmi_enable, NULL, 1);
+}
+
+/*
+ * Disable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_disable(void)
+{
+ if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+ on_each_cpu(__acpi_nmi_disable, NULL, 1);
+}
+
+/*
+ * This function is called as soon the LAPIC NMI watchdog driver has everything
+ * in place and it's ready to check if the NMIs belong to the NMI watchdog
+ */
+void cpu_nmi_set_wd_enabled(void)
+{
+ __get_cpu_var(wd_enabled) = 1;
+}
+
+void setup_apic_nmi_watchdog(void *unused)
+{
+ if (__get_cpu_var(wd_enabled))
+ return;
+
+ /* cheap hack to support suspend/resume */
+ /* if cpu0 is not active neither should the other cpus */
+ if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
+ return;
+
+ switch (nmi_watchdog) {
+ case NMI_LOCAL_APIC:
+ if (lapic_watchdog_init(nmi_hz) < 0) {
+ __get_cpu_var(wd_enabled) = 0;
+ return;
+ }
+ /* FALL THROUGH */
+ case NMI_IO_APIC:
+ __get_cpu_var(wd_enabled) = 1;
+ atomic_inc(&nmi_active);
+ }
+}
+
+void stop_apic_nmi_watchdog(void *unused)
+{
+ /* only support LOCAL and IO APICs for now */
+ if (!nmi_watchdog_active())
+ return;
+ if (__get_cpu_var(wd_enabled) == 0)
+ return;
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ lapic_watchdog_stop();
+ else
+ __acpi_nmi_disable(NULL);
+ __get_cpu_var(wd_enabled) = 0;
+ atomic_dec(&nmi_active);
+}
+
+/*
+ * the best way to detect whether a CPU has a 'hard lockup' problem
+ * is to check it's local APIC timer IRQ counts. If they are not
+ * changing then that CPU has some problem.
+ *
+ * as these watchdog NMI IRQs are generated on every CPU, we only
+ * have to check the current processor.
+ *
+ * since NMIs don't listen to _any_ locks, we have to be extremely
+ * careful not to rely on unsafe variables. The printk might lock
+ * up though, so we have to break up any console locks first ...
+ * [when there will be more tty-related locks, break them up here too!]
+ */
+
+static DEFINE_PER_CPU(unsigned, last_irq_sum);
+static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(int, nmi_touch);
+
+void touch_nmi_watchdog(void)
+{
+ if (nmi_watchdog_active()) {
+ unsigned cpu;
+
+ /*
+ * Tell other CPUs to reset their alert counters. We cannot
+ * do it ourselves because the alert count increase is not
+ * atomic.
+ */
+ for_each_present_cpu(cpu) {
+ if (per_cpu(nmi_touch, cpu) != 1)
+ per_cpu(nmi_touch, cpu) = 1;
+ }
+ }
+
+ /*
+ * Tickle the softlockup detector too:
+ */
+ touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+notrace __kprobes int
+nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
+{
+ /*
+ * Since current_thread_info()-> is always on the stack, and we
+ * always switch the stack NMI-atomically, it's safe to use
+ * smp_processor_id().
+ */
+ unsigned int sum;
+ int touched = 0;
+ int cpu = smp_processor_id();
+ int rc = 0;
+
+ /* check for other users first */
+ if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
+ == NOTIFY_STOP) {
+ rc = 1;
+ touched = 1;
+ }
+
+ sum = get_timer_irqs(cpu);
+
+ if (__get_cpu_var(nmi_touch)) {
+ __get_cpu_var(nmi_touch) = 0;
+ touched = 1;
+ }
+
+ if (cpu_isset(cpu, backtrace_mask)) {
+ static DEFINE_SPINLOCK(lock); /* Serialise the printks */
+
+ spin_lock(&lock);
+ printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+ dump_stack();
+ spin_unlock(&lock);
+ cpu_clear(cpu, backtrace_mask);
+ }
+
+ /* Could check oops_in_progress here too, but it's safer not to */
+ if (mce_in_progress())
+ touched = 1;
+
+ /* if the none of the timers isn't firing, this cpu isn't doing much */
+ if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+ /*
+ * Ayiee, looks like this CPU is stuck ...
+ * wait a few IRQs (5 seconds) before doing the oops ...
+ */
+ local_inc(&__get_cpu_var(alert_counter));
+ if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
+ /*
+ * die_nmi will return ONLY if NOTIFY_STOP happens..
+ */
+ die_nmi("BUG: NMI Watchdog detected LOCKUP",
+ regs, panic_on_timeout);
+ } else {
+ __get_cpu_var(last_irq_sum) = sum;
+ local_set(&__get_cpu_var(alert_counter), 0);
+ }
+
+ /* see if the nmi watchdog went off */
+ if (!__get_cpu_var(wd_enabled))
+ return rc;
+ switch (nmi_watchdog) {
+ case NMI_LOCAL_APIC:
+ rc |= lapic_wd_event(nmi_hz);
+ break;
+ case NMI_IO_APIC:
+ /*
+ * don't know how to accurately check for this.
+ * just assume it was a watchdog timer interrupt
+ * This matches the old behaviour.
+ */
+ rc = 1;
+ break;
+ }
+ return rc;
+}
+
+#ifdef CONFIG_SYSCTL
+
+static void enable_ioapic_nmi_watchdog_single(void *unused)
+{
+ __get_cpu_var(wd_enabled) = 1;
+ atomic_inc(&nmi_active);
+ __acpi_nmi_enable(NULL);
+}
+
+static void enable_ioapic_nmi_watchdog(void)
+{
+ on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
+ touch_nmi_watchdog();
+}
+
+static void disable_ioapic_nmi_watchdog(void)
+{
+ on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
+}
+
+static int __init setup_unknown_nmi_panic(char *str)
+{
+ unknown_nmi_panic = 1;
+ return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
+
+static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
+{
+ unsigned char reason = get_nmi_reason();
+ char buf[64];
+
+ sprintf(buf, "NMI received for unknown reason %02x\n", reason);
+ die_nmi(buf, regs, 1); /* Always panic here */
+ return 0;
+}
+
+/*
+ * proc handler for /proc/sys/kernel/nmi
+ */
+int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
+ void __user *buffer, size_t *length, loff_t *ppos)
+{
+ int old_state;
+
+ nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
+ old_state = nmi_watchdog_enabled;
+ proc_dointvec(table, write, file, buffer, length, ppos);
+ if (!!old_state == !!nmi_watchdog_enabled)
+ return 0;
+
+ if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
+ printk(KERN_WARNING
+ "NMI watchdog is permanently disabled\n");
+ return -EIO;
+ }
+
+ if (nmi_watchdog == NMI_LOCAL_APIC) {
+ if (nmi_watchdog_enabled)
+ enable_lapic_nmi_watchdog();
+ else
+ disable_lapic_nmi_watchdog();
+ } else if (nmi_watchdog == NMI_IO_APIC) {
+ if (nmi_watchdog_enabled)
+ enable_ioapic_nmi_watchdog();
+ else
+ disable_ioapic_nmi_watchdog();
+ } else {
+ printk(KERN_WARNING
+ "NMI watchdog doesn't know what hardware to touch\n");
+ return -EIO;
+ }
+ return 0;
+}
+
+#endif /* CONFIG_SYSCTL */
+
+int do_nmi_callback(struct pt_regs *regs, int cpu)
+{
+#ifdef CONFIG_SYSCTL
+ if (unknown_nmi_panic)
+ return unknown_nmi_panic_callback(regs, cpu);
+#endif
+ return 0;
+}
+
+void __trigger_all_cpu_backtrace(void)
+{
+ int i;
+
+ backtrace_mask = cpu_online_map;
+ /* Wait for up to 10 seconds for all CPUs to do the backtrace */
+ for (i = 0; i < 10 * 1000; i++) {
+ if (cpus_empty(backtrace_mask))
+ break;
+ mdelay(1);
+ }
+}
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
new file mode 100644
index 0000000..4e39d9a
--- /dev/null
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -0,0 +1,243 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+
+DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+
+static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ if (cpu_has_x2apic)
+ return 1;
+
+ return 0;
+}
+
+/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
+
+static const struct cpumask *x2apic_target_cpus(void)
+{
+ return cpumask_of(0);
+}
+
+/*
+ * for now each logical cpu is in its own vector allocation domain.
+ */
+static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+ cpumask_clear(retmask);
+ cpumask_set_cpu(cpu, retmask);
+}
+
+static void
+ __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
+{
+ unsigned long cfg;
+
+ cfg = __prepare_ICR(0, vector, dest);
+
+ /*
+ * send the IPI.
+ */
+ native_x2apic_icr_write(cfg, apicid);
+}
+
+/*
+ * for now, we send the IPI's one by one in the cpumask.
+ * TBD: Based on the cpu mask, we can send the IPI's to the cluster group
+ * at once. We have 16 cpu's in a cluster. This will minimize IPI register
+ * writes.
+ */
+static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ __x2apic_send_IPI_dest(
+ per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+ vector, apic->dest_logical);
+ }
+ local_irq_restore(flags);
+}
+
+static void
+ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
+{
+ unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu == this_cpu)
+ continue;
+ __x2apic_send_IPI_dest(
+ per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+ vector, apic->dest_logical);
+ }
+ local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+ unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ for_each_online_cpu(query_cpu) {
+ if (query_cpu == this_cpu)
+ continue;
+ __x2apic_send_IPI_dest(
+ per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+ vector, apic->dest_logical);
+ }
+ local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+ x2apic_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int x2apic_apic_id_registered(void)
+{
+ return 1;
+}
+
+static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+ /*
+ * We're using fixed IRQ delivery, can only return one logical APIC ID.
+ * May as well be the first.
+ */
+ int cpu = cpumask_first(cpumask);
+
+ if ((unsigned)cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_logical_apicid, cpu);
+ else
+ return BAD_APICID;
+}
+
+static unsigned int
+x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one logical APIC ID.
+ * May as well be the first.
+ */
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+
+ if (cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_logical_apicid, cpu);
+
+ return BAD_APICID;
+}
+
+static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ id = x;
+ return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ x = id;
+ return x;
+}
+
+static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb)
+{
+ return current_cpu_data.initial_apicid >> index_msb;
+}
+
+static void x2apic_send_IPI_self(int vector)
+{
+ apic_write(APIC_SELF_IPI, vector);
+}
+
+static void init_x2apic_ldr(void)
+{
+ int cpu = smp_processor_id();
+
+ per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR);
+}
+
+struct apic apic_x2apic_cluster = {
+
+ .name = "cluster x2apic",
+ .probe = NULL,
+ .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+ .apic_id_registered = x2apic_apic_id_registered,
+
+ .irq_delivery_mode = dest_LowestPrio,
+ .irq_dest_mode = 1, /* logical */
+
+ .target_cpus = x2apic_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = x2apic_vector_allocation_domain,
+ .init_apic_ldr = init_x2apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = x2apic_cluster_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = x2apic_cluster_phys_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFFFFFFFu,
+
+ .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = x2apic_send_IPI_mask,
+ .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+ .send_IPI_all = x2apic_send_IPI_all,
+ .send_IPI_self = x2apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .inquire_remote_apic = NULL,
+
+ .read = native_apic_msr_read,
+ .write = native_apic_msr_write,
+ .icr_read = native_x2apic_icr_read,
+ .icr_write = native_x2apic_icr_write,
+ .wait_icr_idle = native_x2apic_wait_icr_idle,
+ .safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle,
+};
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
new file mode 100644
index 0000000..d2d52eb
--- /dev/null
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -0,0 +1,229 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+
+static int x2apic_phys;
+
+static int set_x2apic_phys_mode(char *arg)
+{
+ x2apic_phys = 1;
+ return 0;
+}
+early_param("x2apic_phys", set_x2apic_phys_mode);
+
+static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ if (cpu_has_x2apic && x2apic_phys)
+ return 1;
+
+ return 0;
+}
+
+/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
+
+static const struct cpumask *x2apic_target_cpus(void)
+{
+ return cpumask_of(0);
+}
+
+static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+ cpumask_clear(retmask);
+ cpumask_set_cpu(cpu, retmask);
+}
+
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+ unsigned int dest)
+{
+ unsigned long cfg;
+
+ cfg = __prepare_ICR(0, vector, dest);
+
+ /*
+ * send the IPI.
+ */
+ native_x2apic_icr_write(cfg, apicid);
+}
+
+static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
+ vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
+
+static void
+ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
+{
+ unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ for_each_cpu(query_cpu, mask) {
+ if (query_cpu != this_cpu)
+ __x2apic_send_IPI_dest(
+ per_cpu(x86_cpu_to_apicid, query_cpu),
+ vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_allbutself(int vector)
+{
+ unsigned long this_cpu = smp_processor_id();
+ unsigned long query_cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ for_each_online_cpu(query_cpu) {
+ if (query_cpu == this_cpu)
+ continue;
+ __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
+ vector, APIC_DEST_PHYSICAL);
+ }
+ local_irq_restore(flags);
+}
+
+static void x2apic_send_IPI_all(int vector)
+{
+ x2apic_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int x2apic_apic_id_registered(void)
+{
+ return 1;
+}
+
+static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ int cpu = cpumask_first(cpumask);
+
+ if ((unsigned)cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+ else
+ return BAD_APICID;
+}
+
+static unsigned int
+x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+
+ if (cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+
+ return BAD_APICID;
+}
+
+static unsigned int x2apic_phys_get_apic_id(unsigned long x)
+{
+ return x;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ return id;
+}
+
+static int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
+{
+ return current_cpu_data.initial_apicid >> index_msb;
+}
+
+static void x2apic_send_IPI_self(int vector)
+{
+ apic_write(APIC_SELF_IPI, vector);
+}
+
+static void init_x2apic_ldr(void)
+{
+}
+
+struct apic apic_x2apic_phys = {
+
+ .name = "physical x2apic",
+ .probe = NULL,
+ .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+ .apic_id_registered = x2apic_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 0, /* physical */
+
+ .target_cpus = x2apic_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = 0,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = x2apic_vector_allocation_domain,
+ .init_apic_ldr = init_x2apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = x2apic_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = x2apic_phys_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFFFFFFFu,
+
+ .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = x2apic_send_IPI_mask,
+ .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+ .send_IPI_all = x2apic_send_IPI_all,
+ .send_IPI_self = x2apic_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .inquire_remote_apic = NULL,
+
+ .read = native_apic_msr_read,
+ .write = native_apic_msr_write,
+ .icr_read = native_x2apic_icr_read,
+ .icr_write = native_x2apic_icr_write,
+ .wait_icr_idle = native_x2apic_wait_icr_idle,
+ .safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle,
+};
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
new file mode 100644
index 0000000..20b4ad0
--- /dev/null
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -0,0 +1,643 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV APIC functions (note: not an Intel compatible APIC)
+ *
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/timer.h>
+#include <linux/proc_fs.h>
+#include <asm/current.h>
+#include <asm/smp.h>
+#include <asm/apic.h>
+#include <asm/ipi.h>
+#include <asm/pgtable.h>
+#include <asm/uv/uv.h>
+#include <asm/uv/uv_mmrs.h>
+#include <asm/uv/uv_hub.h>
+#include <asm/uv/bios.h>
+
+DEFINE_PER_CPU(int, x2apic_extra_bits);
+
+static enum uv_system_type uv_system_type;
+
+static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+ if (!strcmp(oem_id, "SGI")) {
+ if (!strcmp(oem_table_id, "UVL"))
+ uv_system_type = UV_LEGACY_APIC;
+ else if (!strcmp(oem_table_id, "UVX"))
+ uv_system_type = UV_X2APIC;
+ else if (!strcmp(oem_table_id, "UVH")) {
+ uv_system_type = UV_NON_UNIQUE_APIC;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+enum uv_system_type get_uv_system_type(void)
+{
+ return uv_system_type;
+}
+
+int is_uv_system(void)
+{
+ return uv_system_type != UV_NONE;
+}
+EXPORT_SYMBOL_GPL(is_uv_system);
+
+DEFINE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
+EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info);
+
+struct uv_blade_info *uv_blade_info;
+EXPORT_SYMBOL_GPL(uv_blade_info);
+
+short *uv_node_to_blade;
+EXPORT_SYMBOL_GPL(uv_node_to_blade);
+
+short *uv_cpu_to_blade;
+EXPORT_SYMBOL_GPL(uv_cpu_to_blade);
+
+short uv_possible_blades;
+EXPORT_SYMBOL_GPL(uv_possible_blades);
+
+unsigned long sn_rtc_cycles_per_second;
+EXPORT_SYMBOL(sn_rtc_cycles_per_second);
+
+/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
+
+static const struct cpumask *uv_target_cpus(void)
+{
+ return cpumask_of(0);
+}
+
+static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+ cpumask_clear(retmask);
+ cpumask_set_cpu(cpu, retmask);
+}
+
+int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip)
+{
+ unsigned long val;
+ int pnode;
+
+ pnode = uv_apicid_to_pnode(phys_apicid);
+ val = (1UL << UVH_IPI_INT_SEND_SHFT) |
+ (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
+ (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
+ APIC_DM_INIT;
+ uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+ mdelay(10);
+
+ val = (1UL << UVH_IPI_INT_SEND_SHFT) |
+ (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
+ (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
+ APIC_DM_STARTUP;
+ uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+ return 0;
+}
+
+static void uv_send_IPI_one(int cpu, int vector)
+{
+ unsigned long val, apicid;
+ int pnode;
+
+ apicid = per_cpu(x86_cpu_to_apicid, cpu);
+ pnode = uv_apicid_to_pnode(apicid);
+
+ val = (1UL << UVH_IPI_INT_SEND_SHFT) |
+ (apicid << UVH_IPI_INT_APIC_ID_SHFT) |
+ (vector << UVH_IPI_INT_VECTOR_SHFT);
+
+ uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+}
+
+static void uv_send_IPI_mask(const struct cpumask *mask, int vector)
+{
+ unsigned int cpu;
+
+ for_each_cpu(cpu, mask)
+ uv_send_IPI_one(cpu, vector);
+}
+
+static void uv_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
+{
+ unsigned int this_cpu = smp_processor_id();
+ unsigned int cpu;
+
+ for_each_cpu(cpu, mask) {
+ if (cpu != this_cpu)
+ uv_send_IPI_one(cpu, vector);
+ }
+}
+
+static void uv_send_IPI_allbutself(int vector)
+{
+ unsigned int this_cpu = smp_processor_id();
+ unsigned int cpu;
+
+ for_each_online_cpu(cpu) {
+ if (cpu != this_cpu)
+ uv_send_IPI_one(cpu, vector);
+ }
+}
+
+static void uv_send_IPI_all(int vector)
+{
+ uv_send_IPI_mask(cpu_online_mask, vector);
+}
+
+static int uv_apic_id_registered(void)
+{
+ return 1;
+}
+
+static void uv_init_apic_ldr(void)
+{
+}
+
+static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ int cpu = cpumask_first(cpumask);
+
+ if ((unsigned)cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+ else
+ return BAD_APICID;
+}
+
+static unsigned int
+uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask)
+{
+ int cpu;
+
+ /*
+ * We're using fixed IRQ delivery, can only return one phys APIC ID.
+ * May as well be the first.
+ */
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+ if (cpu < nr_cpu_ids)
+ return per_cpu(x86_cpu_to_apicid, cpu);
+
+ return BAD_APICID;
+}
+
+static unsigned int x2apic_get_apic_id(unsigned long x)
+{
+ unsigned int id;
+
+ WARN_ON(preemptible() && num_online_cpus() > 1);
+ id = x | __get_cpu_var(x2apic_extra_bits);
+
+ return id;
+}
+
+static unsigned long set_apic_id(unsigned int id)
+{
+ unsigned long x;
+
+ /* maskout x2apic_extra_bits ? */
+ x = id;
+ return x;
+}
+
+static unsigned int uv_read_apic_id(void)
+{
+
+ return x2apic_get_apic_id(apic_read(APIC_ID));
+}
+
+static int uv_phys_pkg_id(int initial_apicid, int index_msb)
+{
+ return uv_read_apic_id() >> index_msb;
+}
+
+static void uv_send_IPI_self(int vector)
+{
+ apic_write(APIC_SELF_IPI, vector);
+}
+
+struct apic apic_x2apic_uv_x = {
+
+ .name = "UV large system",
+ .probe = NULL,
+ .acpi_madt_oem_check = uv_acpi_madt_oem_check,
+ .apic_id_registered = uv_apic_id_registered,
+
+ .irq_delivery_mode = dest_Fixed,
+ .irq_dest_mode = 1, /* logical */
+
+ .target_cpus = uv_target_cpus,
+ .disable_esr = 0,
+ .dest_logical = APIC_DEST_LOGICAL,
+ .check_apicid_used = NULL,
+ .check_apicid_present = NULL,
+
+ .vector_allocation_domain = uv_vector_allocation_domain,
+ .init_apic_ldr = uv_init_apic_ldr,
+
+ .ioapic_phys_id_map = NULL,
+ .setup_apic_routing = NULL,
+ .multi_timer_check = NULL,
+ .apicid_to_node = NULL,
+ .cpu_to_logical_apicid = NULL,
+ .cpu_present_to_apicid = default_cpu_present_to_apicid,
+ .apicid_to_cpu_present = NULL,
+ .setup_portio_remap = NULL,
+ .check_phys_apicid_present = default_check_phys_apicid_present,
+ .enable_apic_mode = NULL,
+ .phys_pkg_id = uv_phys_pkg_id,
+ .mps_oem_check = NULL,
+
+ .get_apic_id = x2apic_get_apic_id,
+ .set_apic_id = set_apic_id,
+ .apic_id_mask = 0xFFFFFFFFu,
+
+ .cpu_mask_to_apicid = uv_cpu_mask_to_apicid,
+ .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and,
+
+ .send_IPI_mask = uv_send_IPI_mask,
+ .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself,
+ .send_IPI_allbutself = uv_send_IPI_allbutself,
+ .send_IPI_all = uv_send_IPI_all,
+ .send_IPI_self = uv_send_IPI_self,
+
+ .wakeup_cpu = NULL,
+ .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
+ .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
+ .wait_for_init_deassert = NULL,
+ .smp_callin_clear_local_apic = NULL,
+ .inquire_remote_apic = NULL,
+
+ .read = native_apic_msr_read,
+ .write = native_apic_msr_write,
+ .icr_read = native_x2apic_icr_read,
+ .icr_write = native_x2apic_icr_write,
+ .wait_icr_idle = native_x2apic_wait_icr_idle,
+ .safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle,
+};
+
+static __cpuinit void set_x2apic_extra_bits(int pnode)
+{
+ __get_cpu_var(x2apic_extra_bits) = (pnode << 6);
+}
+
+/*
+ * Called on boot cpu.
+ */
+static __init int boot_pnode_to_blade(int pnode)
+{
+ int blade;
+
+ for (blade = 0; blade < uv_num_possible_blades(); blade++)
+ if (pnode == uv_blade_info[blade].pnode)
+ return blade;
+ BUG();
+}
+
+struct redir_addr {
+ unsigned long redirect;
+ unsigned long alias;
+};
+
+#define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
+
+static __initdata struct redir_addr redir_addrs[] = {
+ {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_SI_ALIAS0_OVERLAY_CONFIG},
+ {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_SI_ALIAS1_OVERLAY_CONFIG},
+ {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_SI_ALIAS2_OVERLAY_CONFIG},
+};
+
+static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
+{
+ union uvh_si_alias0_overlay_config_u alias;
+ union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
+ alias.v = uv_read_local_mmr(redir_addrs[i].alias);
+ if (alias.s.base == 0) {
+ *size = (1UL << alias.s.m_alias);
+ redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
+ *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
+ return;
+ }
+ }
+ BUG();
+}
+
+static __init void map_low_mmrs(void)
+{
+ init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE);
+ init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE);
+}
+
+enum map_type {map_wb, map_uc};
+
+static __init void map_high(char *id, unsigned long base, int shift,
+ int max_pnode, enum map_type map_type)
+{
+ unsigned long bytes, paddr;
+
+ paddr = base << shift;
+ bytes = (1UL << shift) * (max_pnode + 1);
+ printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr,
+ paddr + bytes);
+ if (map_type == map_uc)
+ init_extra_mapping_uc(paddr, bytes);
+ else
+ init_extra_mapping_wb(paddr, bytes);
+
+}
+static __init void map_gru_high(int max_pnode)
+{
+ union uvh_rh_gam_gru_overlay_config_mmr_u gru;
+ int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+ gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
+ if (gru.s.enable)
+ map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
+}
+
+static __init void map_config_high(int max_pnode)
+{
+ union uvh_rh_gam_cfg_overlay_config_mmr_u cfg;
+ int shift = UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+ cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR);
+ if (cfg.s.enable)
+ map_high("CONFIG", cfg.s.base, shift, max_pnode, map_uc);
+}
+
+static __init void map_mmr_high(int max_pnode)
+{
+ union uvh_rh_gam_mmr_overlay_config_mmr_u mmr;
+ int shift = UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+ mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR);
+ if (mmr.s.enable)
+ map_high("MMR", mmr.s.base, shift, max_pnode, map_uc);
+}
+
+static __init void map_mmioh_high(int max_pnode)
+{
+ union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
+ int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+
+ mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
+ if (mmioh.s.enable)
+ map_high("MMIOH", mmioh.s.base, shift, max_pnode, map_uc);
+}
+
+static __init void uv_rtc_init(void)
+{
+ long status;
+ u64 ticks_per_sec;
+
+ status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK,
+ &ticks_per_sec);
+ if (status != BIOS_STATUS_SUCCESS || ticks_per_sec < 100000) {
+ printk(KERN_WARNING
+ "unable to determine platform RTC clock frequency, "
+ "guessing.\n");
+ /* BIOS gives wrong value for clock freq. so guess */
+ sn_rtc_cycles_per_second = 1000000000000UL / 30000UL;
+ } else
+ sn_rtc_cycles_per_second = ticks_per_sec;
+}
+
+/*
+ * percpu heartbeat timer
+ */
+static void uv_heartbeat(unsigned long ignored)
+{
+ struct timer_list *timer = &uv_hub_info->scir.timer;
+ unsigned char bits = uv_hub_info->scir.state;
+
+ /* flip heartbeat bit */
+ bits ^= SCIR_CPU_HEARTBEAT;
+
+ /* is this cpu idle? */
+ if (idle_cpu(raw_smp_processor_id()))
+ bits &= ~SCIR_CPU_ACTIVITY;
+ else
+ bits |= SCIR_CPU_ACTIVITY;
+
+ /* update system controller interface reg */
+ uv_set_scir_bits(bits);
+
+ /* enable next timer period */
+ mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
+}
+
+static void __cpuinit uv_heartbeat_enable(int cpu)
+{
+ if (!uv_cpu_hub_info(cpu)->scir.enabled) {
+ struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
+
+ uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
+ setup_timer(timer, uv_heartbeat, cpu);
+ timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
+ add_timer_on(timer, cpu);
+ uv_cpu_hub_info(cpu)->scir.enabled = 1;
+ }
+
+ /* check boot cpu */
+ if (!uv_cpu_hub_info(0)->scir.enabled)
+ uv_heartbeat_enable(0);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __cpuinit uv_heartbeat_disable(int cpu)
+{
+ if (uv_cpu_hub_info(cpu)->scir.enabled) {
+ uv_cpu_hub_info(cpu)->scir.enabled = 0;
+ del_timer(&uv_cpu_hub_info(cpu)->scir.timer);
+ }
+ uv_set_cpu_scir_bits(cpu, 0xff);
+}
+
+/*
+ * cpu hotplug notifier
+ */
+static __cpuinit int uv_scir_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ uv_heartbeat_enable(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ uv_heartbeat_disable(cpu);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static __init void uv_scir_register_cpu_notifier(void)
+{
+ hotcpu_notifier(uv_scir_cpu_notify, 0);
+}
+
+#else /* !CONFIG_HOTPLUG_CPU */
+
+static __init void uv_scir_register_cpu_notifier(void)
+{
+}
+
+static __init int uv_init_heartbeat(void)
+{
+ int cpu;
+
+ if (is_uv_system())
+ for_each_online_cpu(cpu)
+ uv_heartbeat_enable(cpu);
+ return 0;
+}
+
+late_initcall(uv_init_heartbeat);
+
+#endif /* !CONFIG_HOTPLUG_CPU */
+
+/*
+ * Called on each cpu to initialize the per_cpu UV data area.
+ * ZZZ hotplug not supported yet
+ */
+void __cpuinit uv_cpu_init(void)
+{
+ /* CPU 0 initilization will be done via uv_system_init. */
+ if (!uv_blade_info)
+ return;
+
+ uv_blade_info[uv_numa_blade_id()].nr_online_cpus++;
+
+ if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
+ set_x2apic_extra_bits(uv_hub_info->pnode);
+}
+
+
+void __init uv_system_init(void)
+{
+ union uvh_si_addr_map_config_u m_n_config;
+ union uvh_node_id_u node_id;
+ unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
+ int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+ int max_pnode = 0;
+ unsigned long mmr_base, present;
+
+ map_low_mmrs();
+
+ m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
+ m_val = m_n_config.s.m_skt;
+ n_val = m_n_config.s.n_skt;
+ mmr_base =
+ uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
+ ~UV_MMR_ENABLE;
+ printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
+
+ for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
+ uv_possible_blades +=
+ hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
+ printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
+
+ bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
+ uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+
+ get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
+
+ bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
+ uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
+ memset(uv_node_to_blade, 255, bytes);
+
+ bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
+ uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
+ memset(uv_cpu_to_blade, 255, bytes);
+
+ blade = 0;
+ for (i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) {
+ present = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
+ for (j = 0; j < 64; j++) {
+ if (!test_bit(j, &present))
+ continue;
+ uv_blade_info[blade].pnode = (i * 64 + j);
+ uv_blade_info[blade].nr_possible_cpus = 0;
+ uv_blade_info[blade].nr_online_cpus = 0;
+ blade++;
+ }
+ }
+
+ node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+ gnode_upper = (((unsigned long)node_id.s.node_id) &
+ ~((1 << n_val) - 1)) << m_val;
+
+ uv_bios_init();
+ uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
+ &sn_coherency_id, &sn_region_size);
+ uv_rtc_init();
+
+ for_each_present_cpu(cpu) {
+ nid = cpu_to_node(cpu);
+ pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu));
+ blade = boot_pnode_to_blade(pnode);
+ lcpu = uv_blade_info[blade].nr_possible_cpus;
+ uv_blade_info[blade].nr_possible_cpus++;
+
+ uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
+ uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
+ uv_cpu_hub_info(cpu)->m_val = m_val;
+ uv_cpu_hub_info(cpu)->n_val = m_val;
+ uv_cpu_hub_info(cpu)->numa_blade_id = blade;
+ uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
+ uv_cpu_hub_info(cpu)->pnode = pnode;
+ uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1;
+ uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
+ uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
+ uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
+ uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
+ uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
+ uv_node_to_blade[nid] = blade;
+ uv_cpu_to_blade[cpu] = blade;
+ max_pnode = max(pnode, max_pnode);
+
+ printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, "
+ "lcpu %d, blade %d\n",
+ cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid,
+ lcpu, blade);
+ }
+
+ map_gru_high(max_pnode);
+ map_mmr_high(max_pnode);
+ map_config_high(max_pnode);
+ map_mmioh_high(max_pnode);
+
+ uv_cpu_init();
+ uv_scir_register_cpu_notifier();
+ proc_mkdir("sgi_uv", NULL);
+}