summaryrefslogtreecommitdiffstats
path: root/arch/i386/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/i386/kernel')
-rw-r--r--arch/i386/kernel/acpi/boot.c23
-rw-r--r--arch/i386/kernel/acpi/earlyquirk.c7
-rw-r--r--arch/i386/kernel/apic.c117
-rw-r--r--arch/i386/kernel/cpu/amd.c34
-rw-r--r--arch/i386/kernel/hpet.c70
-rw-r--r--arch/i386/kernel/i386_ksyms.c2
-rw-r--r--arch/i386/kernel/i8253.c10
-rw-r--r--arch/i386/kernel/io_apic.c2
-rw-r--r--arch/i386/kernel/microcode.c71
-rw-r--r--arch/i386/kernel/nmi.c137
-rw-r--r--arch/i386/kernel/smpboot.c16
-rw-r--r--arch/i386/kernel/tsc.c9
-rw-r--r--arch/i386/kernel/vmi.c40
13 files changed, 414 insertions, 124 deletions
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index e5eb97a910e..9ea5b8ecc7e 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -1072,7 +1072,28 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
"ASUS A7V ACPI BIOS Revision 1007"),
},
},
-
+ {
+ /*
+ * Latest BIOS for IBM 600E (1.16) has bad pcinum
+ * for LPC bridge, which is needed for the PCI
+ * interrupt links to work. DSDT fix is in bug 5966.
+ * 2645, 2646 model numbers are shared with 600/600E/600X
+ */
+ .callback = disable_acpi_irq,
+ .ident = "IBM Thinkpad 600 Series 2645",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
+ DMI_MATCH(DMI_BOARD_NAME, "2645"),
+ },
+ },
+ {
+ .callback = disable_acpi_irq,
+ .ident = "IBM Thinkpad 600 Series 2646",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
+ DMI_MATCH(DMI_BOARD_NAME, "2646"),
+ },
+ },
/*
* Boxes that need ACPI PCI IRQ routing and PCI scan disabled
*/
diff --git a/arch/i386/kernel/acpi/earlyquirk.c b/arch/i386/kernel/acpi/earlyquirk.c
index bf86f7662d8..a7d22d9f3d7 100644
--- a/arch/i386/kernel/acpi/earlyquirk.c
+++ b/arch/i386/kernel/acpi/earlyquirk.c
@@ -14,11 +14,8 @@
#ifdef CONFIG_ACPI
-static int nvidia_hpet_detected __initdata;
-
static int __init nvidia_hpet_check(struct acpi_table_header *header)
{
- nvidia_hpet_detected = 1;
return 0;
}
#endif
@@ -29,9 +26,7 @@ static int __init check_bridge(int vendor, int device)
/* According to Nvidia all timer overrides are bogus unless HPET
is enabled. */
if (!acpi_use_timer_override && vendor == PCI_VENDOR_ID_NVIDIA) {
- nvidia_hpet_detected = 0;
- acpi_table_parse(ACPI_SIG_HPET, nvidia_hpet_check);
- if (nvidia_hpet_detected == 0) {
+ if (acpi_table_parse(ACPI_SIG_HPET, nvidia_hpet_check)) {
acpi_skip_timer_override = 1;
printk(KERN_INFO "Nvidia board "
"detected. Ignoring ACPI "
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 2383bcf18c5..93aa911646a 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -28,6 +28,7 @@
#include <linux/clockchips.h>
#include <linux/acpi_pmtmr.h>
#include <linux/module.h>
+#include <linux/dmi.h>
#include <asm/atomic.h>
#include <asm/smp.h>
@@ -61,6 +62,11 @@ static int enable_local_apic __initdata = 0;
/* Local APIC timer verification ok */
static int local_apic_timer_verify_ok;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
+/* Local APIC timer works in C2 */
+int local_apic_timer_c2_ok;
+EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
/*
* Debug level, exported for io_apic.c
@@ -338,6 +344,23 @@ void __init setup_boot_APIC_clock(void)
void (*real_handler)(struct clock_event_device *dev);
unsigned long deltaj;
long delta, deltapm;
+ int pm_referenced = 0;
+
+ if (boot_cpu_has(X86_FEATURE_LAPIC_TIMER_BROKEN))
+ local_apic_timer_disabled = 1;
+
+ /*
+ * The local apic timer can be disabled via the kernel
+ * commandline or from the test above. 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 (local_apic_timer_disabled) {
+ /* No broadcast on UP ! */
+ if (num_possible_cpus() > 1)
+ setup_APIC_timer();
+ return;
+ }
apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
"calibrating APIC timer ...\n");
@@ -357,7 +380,8 @@ void __init setup_boot_APIC_clock(void)
/* Let the interrupts run */
local_irq_enable();
- while(lapic_cal_loops <= LAPIC_CAL_LOOPS);
+ while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
+ cpu_relax();
local_irq_disable();
@@ -394,6 +418,7 @@ void __init setup_boot_APIC_clock(void)
"%lu (%ld)\n", (unsigned long) res, delta);
delta = (long) res;
}
+ pm_referenced = 1;
}
/* Calculate the scaled math multiplication factor */
@@ -423,69 +448,43 @@ void __init setup_boot_APIC_clock(void)
calibration_result / (1000000 / HZ),
calibration_result % (1000000 / HZ));
-
- apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
-
- /*
- * Setup the apic timer manually
- */
local_apic_timer_verify_ok = 1;
- 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();
+ /* We trust the pm timer based calibration */
+ if (!pm_referenced) {
+ apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
- while(lapic_cal_loops <= LAPIC_CAL_LOOPS);
+ /*
+ * Setup the apic timer manually
+ */
+ levt->event_handler = lapic_cal_handler;
+ lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt);
+ lapic_cal_loops = -1;
- local_irq_disable();
+ /* Let the interrupts run */
+ local_irq_enable();
- /* Stop the lapic timer */
- lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
+ while(lapic_cal_loops <= LAPIC_CAL_LOOPS)
+ cpu_relax();
- local_irq_enable();
+ local_irq_disable();
- /* Jiffies delta */
- deltaj = lapic_cal_j2 - lapic_cal_j1;
- apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
+ /* Stop the lapic timer */
+ lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
- /* Check, if the PM timer is available */
- deltapm = lapic_cal_pm2 - lapic_cal_pm1;
- apic_printk(APIC_VERBOSE, "... PM timer delta = %ld\n", deltapm);
+ local_irq_enable();
- local_apic_timer_verify_ok = 0;
+ /* Jiffies delta */
+ deltaj = lapic_cal_j2 - lapic_cal_j1;
+ apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
- if (deltapm) {
- if (deltapm > (pm_100ms - pm_thresh) &&
- deltapm < (pm_100ms + pm_thresh)) {
- apic_printk(APIC_VERBOSE, "... PM timer result ok\n");
- /* Check, if the jiffies result is consistent */
- if (deltaj < LAPIC_CAL_LOOPS-2 ||
- deltaj > LAPIC_CAL_LOOPS+2) {
- /*
- * Not sure, what we can do about this one.
- * When high resultion timers are active
- * and the lapic timer does not stop in C3
- * we are fine. Otherwise more trouble might
- * be waiting. -- tglx
- */
- printk(KERN_WARNING "Global event device %s "
- "has wrong frequency "
- "(%lu ticks instead of %d)\n",
- global_clock_event->name, deltaj,
- LAPIC_CAL_LOOPS);
- }
- local_apic_timer_verify_ok = 1;
- }
- } else {
/* Check, if the jiffies result is consistent */
- if (deltaj >= LAPIC_CAL_LOOPS-2 &&
- deltaj <= LAPIC_CAL_LOOPS+2) {
+ if (deltaj >= LAPIC_CAL_LOOPS-2 && deltaj <= LAPIC_CAL_LOOPS+2)
apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
- local_apic_timer_verify_ok = 1;
- }
- }
+ else
+ local_apic_timer_verify_ok = 0;
+ } else
+ local_irq_enable();
if (!local_apic_timer_verify_ok) {
printk(KERN_WARNING
@@ -1203,6 +1202,20 @@ static int __init parse_nolapic(char *arg)
}
early_param("nolapic", parse_nolapic);
+static int __init parse_disable_lapic_timer(char *arg)
+{
+ local_apic_timer_disabled = 1;
+ return 0;
+}
+early_param("nolapic_timer", parse_disable_lapic_timer);
+
+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 apic_set_verbosity(char *str)
{
if (strcmp("debug", str) == 0)
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index 41cfea57232..2d47db48297 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -22,6 +22,37 @@
extern void vide(void);
__asm__(".align 4\nvide: ret");
+#define ENABLE_C1E_MASK 0x18000000
+#define CPUID_PROCESSOR_SIGNATURE 1
+#define CPUID_XFAM 0x0ff00000
+#define CPUID_XFAM_K8 0x00000000
+#define CPUID_XFAM_10H 0x00100000
+#define CPUID_XFAM_11H 0x00200000
+#define CPUID_XMOD 0x000f0000
+#define CPUID_XMOD_REV_F 0x00040000
+
+/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
+static __cpuinit int amd_apic_timer_broken(void)
+{
+ u32 lo, hi;
+ u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
+ switch (eax & CPUID_XFAM) {
+ case CPUID_XFAM_K8:
+ if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
+ break;
+ case CPUID_XFAM_10H:
+ case CPUID_XFAM_11H:
+ rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
+ if (lo & ENABLE_C1E_MASK)
+ return 1;
+ break;
+ default:
+ /* err on the side of caution */
+ return 1;
+ }
+ return 0;
+}
+
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
{
u32 l, h;
@@ -241,6 +272,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
if (cpuid_eax(0x80000000) >= 0x80000006)
num_cache_leaves = 3;
+
+ if (amd_apic_timer_broken())
+ set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability);
}
static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size)
diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c
index f3ab61ee749..17d73459fc5 100644
--- a/arch/i386/kernel/hpet.c
+++ b/arch/i386/kernel/hpet.c
@@ -3,6 +3,8 @@
#include <linux/errno.h>
#include <linux/hpet.h>
#include <linux/init.h>
+#include <linux/sysdev.h>
+#include <linux/pm.h>
#include <asm/hpet.h>
#include <asm/io.h>
@@ -197,7 +199,7 @@ static int hpet_next_event(unsigned long delta,
cnt += delta;
hpet_writel(cnt, HPET_T0_CMP);
- return ((long)(hpet_readl(HPET_COUNTER) - cnt ) > 0);
+ return ((long)(hpet_readl(HPET_COUNTER) - cnt ) > 0) ? -ETIME : 0;
}
/*
@@ -307,6 +309,7 @@ int __init hpet_enable(void)
out_nohpet:
iounmap(hpet_virt_address);
hpet_virt_address = NULL;
+ boot_hpet_disable = 1;
return 0;
}
@@ -521,3 +524,68 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}
#endif
+
+
+/*
+ * Suspend/resume part
+ */
+
+#ifdef CONFIG_PM
+
+static int hpet_suspend(struct sys_device *sys_device, pm_message_t state)
+{
+ unsigned long cfg = hpet_readl(HPET_CFG);
+
+ cfg &= ~(HPET_CFG_ENABLE|HPET_CFG_LEGACY);
+ hpet_writel(cfg, HPET_CFG);
+
+ return 0;
+}
+
+static int hpet_resume(struct sys_device *sys_device)
+{
+ unsigned int id;
+
+ hpet_start_counter();
+
+ id = hpet_readl(HPET_ID);
+
+ if (id & HPET_ID_LEGSUP)
+ hpet_enable_int();
+
+ return 0;
+}
+
+static struct sysdev_class hpet_class = {
+ set_kset_name("hpet"),
+ .suspend = hpet_suspend,
+ .resume = hpet_resume,
+};
+
+static struct sys_device hpet_device = {
+ .id = 0,
+ .cls = &hpet_class,
+};
+
+
+static __init int hpet_register_sysfs(void)
+{
+ int err;
+
+ if (!is_hpet_capable())
+ return 0;
+
+ err = sysdev_class_register(&hpet_class);
+
+ if (!err) {
+ err = sysdev_register(&hpet_device);
+ if (err)
+ sysdev_class_unregister(&hpet_class);
+ }
+
+ return err;
+}
+
+device_initcall(hpet_register_sysfs);
+
+#endif
diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c
index e3d4b73bfdb..4afe26e8626 100644
--- a/arch/i386/kernel/i386_ksyms.c
+++ b/arch/i386/kernel/i386_ksyms.c
@@ -28,3 +28,5 @@ EXPORT_SYMBOL(__read_lock_failed);
#endif
EXPORT_SYMBOL(csum_partial);
+
+EXPORT_SYMBOL(_proxy_pda);
diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c
index 5cbb776b308..10cef5ca8a5 100644
--- a/arch/i386/kernel/i8253.c
+++ b/arch/i386/kernel/i8253.c
@@ -47,9 +47,17 @@ static void init_pit_timer(enum clock_event_mode mode,
outb(LATCH >> 8 , PIT_CH0); /* MSB */
break;
- case CLOCK_EVT_MODE_ONESHOT:
+ /*
+ * Avoid unnecessary state transitions, as it confuses
+ * Geode / Cyrix based boxen.
+ */
case CLOCK_EVT_MODE_SHUTDOWN:
+ if (evt->mode == CLOCK_EVT_MODE_UNUSED)
+ break;
case CLOCK_EVT_MODE_UNUSED:
+ if (evt->mode == CLOCK_EVT_MODE_SHUTDOWN)
+ break;
+ case CLOCK_EVT_MODE_ONESHOT:
/* One shot setup */
outb_p(0x38, PIT_MODE);
udelay(10);
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index e4408ff4e67..b3ab8ffebd2 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -736,7 +736,7 @@ failed:
return 0;
}
-int __init irqbalance_disable(char *str)
+int __devinit irqbalance_disable(char *str)
{
irqbalance_disabled = 1;
return 1;
diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c
index b8f16633a6e..cbe7ec8dbb9 100644
--- a/arch/i386/kernel/microcode.c
+++ b/arch/i386/kernel/microcode.c
@@ -567,6 +567,53 @@ static int cpu_request_microcode(int cpu)
return error;
}
+static int apply_microcode_on_cpu(int cpu)
+{
+ struct cpuinfo_x86 *c = cpu_data + cpu;
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ cpumask_t old;
+ unsigned int val[2];
+ int err = 0;
+
+ if (!uci->mc)
+ return -EINVAL;
+
+ old = current->cpus_allowed;
+ set_cpus_allowed(current, cpumask_of_cpu(cpu));
+
+ /* Check if the microcode we have in memory matches the CPU */
+ if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
+ cpu_has(c, X86_FEATURE_IA64) || uci->sig != cpuid_eax(0x00000001))
+ err = -EINVAL;
+
+ if (!err && ((c->x86_model >= 5) || (c->x86 > 6))) {
+ /* get processor flags from MSR 0x17 */
+ rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
+ if (uci->pf != (1 << ((val[1] >> 18) & 7)))
+ err = -EINVAL;
+ }
+
+ if (!err) {
+ wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+ /* see notes above for revision 1.07. Apparent chip bug */
+ sync_core();
+ /* get the current revision from MSR 0x8B */
+ rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+ if (uci->rev != val[1])
+ err = -EINVAL;
+ }
+
+ if (!err)
+ apply_microcode(cpu);
+ else
+ printk(KERN_ERR "microcode: Could not apply microcode to CPU%d:"
+ " sig=0x%x, pf=0x%x, rev=0x%x\n",
+ cpu, uci->sig, uci->pf, uci->rev);
+
+ set_cpus_allowed(current, old);
+ return err;
+}
+
static void microcode_init_cpu(int cpu)
{
cpumask_t old;
@@ -577,7 +624,8 @@ static void microcode_init_cpu(int cpu)
set_cpus_allowed(current, cpumask_of_cpu(cpu));
mutex_lock(&microcode_mutex);
collect_cpu_info(cpu);
- if (uci->valid && system_state == SYSTEM_RUNNING)
+ if (uci->valid && system_state == SYSTEM_RUNNING &&
+ !suspend_cpu_hotplug)
cpu_request_microcode(cpu);
mutex_unlock(&microcode_mutex);
set_cpus_allowed(current, old);
@@ -663,13 +711,24 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
return 0;
pr_debug("Microcode:CPU %d added\n", cpu);
- memset(uci, 0, sizeof(*uci));
+ /* If suspend_cpu_hotplug is set, the system is resuming and we should
+ * use the data from before the suspend.
+ */
+ if (suspend_cpu_hotplug) {
+ err = apply_microcode_on_cpu(cpu);
+ if (err)
+ microcode_fini_cpu(cpu);
+ }
+ if (!uci->valid)
+ memset(uci, 0, sizeof(*uci));
err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
if (err)
return err;
- microcode_init_cpu(cpu);
+ if (!uci->valid)
+ microcode_init_cpu(cpu);
+
return 0;
}
@@ -680,7 +739,11 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
if (!cpu_online(cpu))
return 0;
pr_debug("Microcode:CPU %d removed\n", cpu);
- microcode_fini_cpu(cpu);
+ /* If suspend_cpu_hotplug is set, the system is suspending and we should
+ * keep the microcode in memory for the resume.
+ */
+ if (!suspend_cpu_hotplug)
+ microcode_fini_cpu(cpu);
sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
return 0;
}
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 821df34d2b3..a98ba88a8c0 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -122,64 +122,129 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
/* checks for a bit availability (hack for oprofile) */
int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
{
+ int cpu;
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
+ for_each_possible_cpu (cpu) {
+ if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)))
+ return 0;
+ }
+ return 1;
}
/* checks the an msr for availability */
int avail_to_resrv_perfctr_nmi(unsigned int msr)
{
unsigned int counter;
+ int cpu;
counter = nmi_perfctr_msr_to_bit(msr);
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
- return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
+ for_each_possible_cpu (cpu) {
+ if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)))
+ return 0;
+ }
+ return 1;
}
-int reserve_perfctr_nmi(unsigned int msr)
+static int __reserve_perfctr_nmi(int cpu, unsigned int msr)
{
unsigned int counter;
+ if (cpu < 0)
+ cpu = smp_processor_id();
counter = nmi_perfctr_msr_to_bit(msr);
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
- if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner)))
+ if (!test_and_set_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)))
return 1;
return 0;
}
-void release_perfctr_nmi(unsigned int msr)
+static void __release_perfctr_nmi(int cpu, unsigned int msr)
{
unsigned int counter;
+ if (cpu < 0)
+ cpu = smp_processor_id();
counter = nmi_perfctr_msr_to_bit(msr);
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
- clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner));
+ clear_bit(counter, &per_cpu(perfctr_nmi_owner, cpu));
}
-int reserve_evntsel_nmi(unsigned int msr)
+int reserve_perfctr_nmi(unsigned int msr)
+{
+ int cpu, i;
+ for_each_possible_cpu (cpu) {
+ if (!__reserve_perfctr_nmi(cpu, msr)) {
+ for_each_possible_cpu (i) {
+ if (i >= cpu)
+ break;
+ __release_perfctr_nmi(i, msr);
+ }
+ return 0;
+ }
+ }
+ return 1;
+}
+
+void release_perfctr_nmi(unsigned int msr)
+{
+ int cpu;
+ for_each_possible_cpu (cpu) {
+ __release_perfctr_nmi(cpu, msr);
+ }
+}
+
+int __reserve_evntsel_nmi(int cpu, unsigned int msr)
{
unsigned int counter;
+ if (cpu < 0)
+ cpu = smp_processor_id();
counter = nmi_evntsel_msr_to_bit(msr);
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
- if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0]))
+ if (!test_and_set_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]))
return 1;
return 0;
}
-void release_evntsel_nmi(unsigned int msr)
+static void __release_evntsel_nmi(int cpu, unsigned int msr)
{
unsigned int counter;
+ if (cpu < 0)
+ cpu = smp_processor_id();
counter = nmi_evntsel_msr_to_bit(msr);
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
- clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0]);
+ clear_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]);
+}
+
+int reserve_evntsel_nmi(unsigned int msr)
+{
+ int cpu, i;
+ for_each_possible_cpu (cpu) {
+ if (!__reserve_evntsel_nmi(cpu, msr)) {
+ for_each_possible_cpu (i) {
+ if (i >= cpu)
+ break;
+ __release_evntsel_nmi(i, msr);
+ }
+ return 0;
+ }
+ }
+ return 1;
+}
+
+void release_evntsel_nmi(unsigned int msr)
+{
+ int cpu;
+ for_each_possible_cpu (cpu) {
+ __release_evntsel_nmi(cpu, msr);
+ }
}
static __cpuinit inline int nmi_known_cpu(void)
@@ -245,14 +310,6 @@ static int __init check_nmi_watchdog(void)
unsigned int *prev_nmi_count;
int cpu;
- /* Enable NMI watchdog for newer systems.
- Probably safe on most older systems too, but let's be careful.
- IBM ThinkPads use INT10 inside SMM and that allows early NMI inside SMM
- which hangs the system. Disable watchdog for all thinkpads */
- if (nmi_watchdog == NMI_DEFAULT && dmi_get_year(DMI_BIOS_DATE) >= 2004 &&
- !dmi_name_in_vendors("ThinkPad"))
- nmi_watchdog = NMI_LOCAL_APIC;
-
if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT))
return 0;
@@ -271,7 +328,7 @@ static int __init check_nmi_watchdog(void)
for_each_possible_cpu(cpu)
prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count;
local_irq_enable();
- mdelay((10*1000)/nmi_hz); // wait 10 ticks
+ mdelay((20*1000)/nmi_hz); // wait 20 ticks
for_each_possible_cpu(cpu) {
#ifdef CONFIG_SMP
@@ -515,10 +572,10 @@ static int setup_k7_watchdog(void)
perfctr_msr = MSR_K7_PERFCTR0;
evntsel_msr = MSR_K7_EVNTSEL0;
- if (!reserve_perfctr_nmi(perfctr_msr))
+ if (!__reserve_perfctr_nmi(-1, perfctr_msr))
goto fail;
- if (!reserve_evntsel_nmi(evntsel_msr))
+ if (!__reserve_evntsel_nmi(-1, evntsel_msr))
goto fail1;
wrmsrl(perfctr_msr, 0UL);
@@ -541,7 +598,7 @@ static int setup_k7_watchdog(void)
wd->check_bit = 1ULL<<63;
return 1;
fail1:
- release_perfctr_nmi(perfctr_msr);
+ __release_perfctr_nmi(-1, perfctr_msr);
fail:
return 0;
}
@@ -552,8 +609,8 @@ static void stop_k7_watchdog(void)
wrmsr(wd->evntsel_msr, 0, 0);
- release_evntsel_nmi(wd->evntsel_msr);
- release_perfctr_nmi(wd->perfctr_msr);
+ __release_evntsel_nmi(-1, wd->evntsel_msr);
+ __release_perfctr_nmi(-1, wd->perfctr_msr);
}
#define P6_EVNTSEL0_ENABLE (1 << 22)
@@ -571,10 +628,10 @@ static int setup_p6_watchdog(void)
perfctr_msr = MSR_P6_PERFCTR0;
evntsel_msr = MSR_P6_EVNTSEL0;
- if (!reserve_perfctr_nmi(perfctr_msr))
+ if (!__reserve_perfctr_nmi(-1, perfctr_msr))
goto fail;
- if (!reserve_evntsel_nmi(evntsel_msr))
+ if (!__reserve_evntsel_nmi(-1, evntsel_msr))
goto fail1;
wrmsrl(perfctr_msr, 0UL);
@@ -598,7 +655,7 @@ static int setup_p6_watchdog(void)
wd->check_bit = 1ULL<<39;
return 1;
fail1:
- release_perfctr_nmi(perfctr_msr);
+ __release_perfctr_nmi(-1, perfctr_msr);
fail:
return 0;
}
@@ -609,8 +666,8 @@ static void stop_p6_watchdog(void)
wrmsr(wd->evntsel_msr, 0, 0);
- release_evntsel_nmi(wd->evntsel_msr);
- release_perfctr_nmi(wd->perfctr_msr);
+ __release_evntsel_nmi(-1, wd->evntsel_msr);
+ __release_perfctr_nmi(-1, wd->perfctr_msr);
}
/* Note that these events don't tick when the CPU idles. This means
@@ -676,10 +733,10 @@ static int setup_p4_watchdog(void)
cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
}
- if (!reserve_perfctr_nmi(perfctr_msr))
+ if (!__reserve_perfctr_nmi(-1, perfctr_msr))
goto fail;
- if (!reserve_evntsel_nmi(evntsel_msr))
+ if (!__reserve_evntsel_nmi(-1, evntsel_msr))
goto fail1;
evntsel = P4_ESCR_EVENT_SELECT(0x3F)
@@ -703,7 +760,7 @@ static int setup_p4_watchdog(void)
wd->check_bit = 1ULL<<39;
return 1;
fail1:
- release_perfctr_nmi(perfctr_msr);
+ __release_perfctr_nmi(-1, perfctr_msr);
fail:
return 0;
}
@@ -715,8 +772,8 @@ static void stop_p4_watchdog(void)
wrmsr(wd->cccr_msr, 0, 0);
wrmsr(wd->evntsel_msr, 0, 0);
- release_evntsel_nmi(wd->evntsel_msr);
- release_perfctr_nmi(wd->perfctr_msr);
+ __release_evntsel_nmi(-1, wd->evntsel_msr);
+ __release_perfctr_nmi(-1, wd->perfctr_msr);
}
#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
@@ -744,10 +801,10 @@ static int setup_intel_arch_watchdog(void)
perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;
- if (!reserve_perfctr_nmi(perfctr_msr))
+ if (!__reserve_perfctr_nmi(-1, perfctr_msr))
goto fail;
- if (!reserve_evntsel_nmi(evntsel_msr))
+ if (!__reserve_evntsel_nmi(-1, evntsel_msr))
goto fail1;
wrmsrl(perfctr_msr, 0UL);
@@ -772,7 +829,7 @@ static int setup_intel_arch_watchdog(void)
wd->check_bit = 1ULL << (eax.split.bit_width - 1);
return 1;
fail1:
- release_perfctr_nmi(perfctr_msr);
+ __release_perfctr_nmi(-1, perfctr_msr);
fail:
return 0;
}
@@ -795,8 +852,8 @@ static void stop_intel_arch_watchdog(void)
return;
wrmsr(wd->evntsel_msr, 0, 0);
- release_evntsel_nmi(wd->evntsel_msr);
- release_perfctr_nmi(wd->perfctr_msr);
+ __release_evntsel_nmi(-1, wd->evntsel_msr);
+ __release_perfctr_nmi(-1, wd->perfctr_msr);
}
void setup_apic_nmi_watchdog (void *unused)
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 9b0dd2744c8..4ff55e67557 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -45,6 +45,7 @@
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/percpu.h>
+#include <linux/nmi.h>
#include <linux/delay.h>
#include <linux/mc146818rtc.h>
@@ -1278,8 +1279,9 @@ void __cpu_die(unsigned int cpu)
int __cpuinit __cpu_up(unsigned int cpu)
{
+ unsigned long flags;
#ifdef CONFIG_HOTPLUG_CPU
- int ret=0;
+ int ret = 0;
/*
* We do warm boot only on cpus that had booted earlier
@@ -1297,23 +1299,25 @@ int __cpuinit __cpu_up(unsigned int cpu)
/* In case one didn't come up */
if (!cpu_isset(cpu, cpu_callin_map)) {
printk(KERN_DEBUG "skipping cpu%d, didn't come online\n", cpu);
- local_irq_enable();
return -EIO;
}
- local_irq_enable();
-
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
/* Unleash the CPU! */
cpu_set(cpu, smp_commenced_mask);
/*
- * Check TSC synchronization with the AP:
+ * Check TSC synchronization with the AP (keep irqs disabled
+ * while doing so):
*/
+ local_irq_save(flags);
check_tsc_sync_source(cpu);
+ local_irq_restore(flags);
- while (!cpu_isset(cpu, cpu_online_map))
+ while (!cpu_isset(cpu, cpu_online_map)) {
cpu_relax();
+ touch_nmi_watchdog();
+ }
#ifdef CONFIG_X86_GENERICARCH
if (num_online_cpus() > 8 && genapic == &apic_default)
diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c
index 602660df455..6cb8f533673 100644
--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -18,6 +18,8 @@
#include "mach_timer.h"
+static int tsc_enabled;
+
/*
* On some systems the TSC frequency does not
* change with the cpu frequency. So we need
@@ -105,7 +107,7 @@ unsigned long long sched_clock(void)
/*
* Fall back to jiffies if there's no TSC available:
*/
- if (unlikely(tsc_disable))
+ if (unlikely(!tsc_enabled))
/* No locking but a rare wrong value is not a big deal: */
return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
@@ -283,6 +285,7 @@ void mark_tsc_unstable(void)
{
if (!tsc_unstable) {
tsc_unstable = 1;
+ tsc_enabled = 0;
/* Can be called before registration */
if (clocksource_tsc.mult)
clocksource_change_rating(&clocksource_tsc, 0);
@@ -383,7 +386,9 @@ void __init tsc_init(void)
if (check_tsc_unstable()) {
clocksource_tsc.rating = 0;
clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
- }
+ } else
+ tsc_enabled = 1;
+
clocksource_register(&clocksource_tsc);
return;
diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c
index fbf45fa0832..edc339fa503 100644
--- a/arch/i386/kernel/vmi.c
+++ b/arch/i386/kernel/vmi.c
@@ -23,7 +23,6 @@
*/
#include <linux/module.h>
-#include <linux/license.h>
#include <linux/cpu.h>
#include <linux/bootmem.h>
#include <linux/mm.h>
@@ -48,7 +47,6 @@ typedef u64 __attribute__((regparm(2))) (VROMLONGFUNC)(int);
(((VROMLONGFUNC *)(rom->func)) (arg))
static struct vrom_header *vmi_rom;
-static int license_gplok;
static int disable_pge;
static int disable_pse;
static int disable_sep;
@@ -71,6 +69,7 @@ struct {
void (*flush_tlb)(int);
void (*set_initial_ap_state)(int, int);
void (*halt)(void);
+ void (*set_lazy_mode)(int mode);
} vmi_ops;
/* XXX move this to alternative.h */
@@ -576,6 +575,26 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
}
#endif
+static void vmi_set_lazy_mode(int mode)
+{
+ static DEFINE_PER_CPU(int, lazy_mode);
+
+ if (!vmi_ops.set_lazy_mode)
+ return;
+
+ /* Modes should never nest or overlap */
+ BUG_ON(__get_cpu_var(lazy_mode) && !(mode == PARAVIRT_LAZY_NONE ||
+ mode == PARAVIRT_LAZY_FLUSH));
+
+ if (mode == PARAVIRT_LAZY_FLUSH) {
+ vmi_ops.set_lazy_mode(0);
+ vmi_ops.set_lazy_mode(__get_cpu_var(lazy_mode));
+ } else {
+ vmi_ops.set_lazy_mode(mode);
+ __get_cpu_var(lazy_mode) = mode;
+ }
+}
+
static inline int __init check_vmi_rom(struct vrom_header *rom)
{
struct pci_header *pci;
@@ -629,13 +648,14 @@ static inline int __init check_vmi_rom(struct vrom_header *rom)
rom->api_version_maj, rom->api_version_min,
pci->rom_version_maj, pci->rom_version_min);
- license_gplok = license_is_gpl_compatible(license);
- if (!license_gplok) {
- printk(KERN_WARNING "VMI: ROM license '%s' taints kernel... "
- "inlining disabled\n",
- license);
- add_taint(TAINT_PROPRIETARY_MODULE);
- }
+ /* Don't allow BSD/MIT here for now because we don't want to end up
+ with any binary only shim layers */
+ if (strcmp(license, "GPL") && strcmp(license, "GPL v2")) {
+ printk(KERN_WARNING "VMI: Non GPL license `%s' found for ROM. Not used.\n",
+ license);
+ return 0;
+ }
+
return 1;
}
@@ -805,7 +825,7 @@ static inline int __init activate_vmi(void)
para_wrap(load_esp0, vmi_load_esp0, set_kernel_stack, UpdateKernelStack);
para_fill(set_iopl_mask, SetIOPLMask);
para_fill(io_delay, IODelay);
- para_fill(set_lazy_mode, SetLazyMode);
+ para_wrap(set_lazy_mode, vmi_set_lazy_mode, set_lazy_mode, SetLazyMode);
/* user and kernel flush are just handled with different flags to FlushTLB */
para_wrap(flush_tlb_user, vmi_flush_tlb_user, flush_tlb, FlushTLB);