summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c43
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c4
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c18
-rw-r--r--arch/x86/kernel/head64.c7
-rw-r--r--arch/x86/kernel/hpet.c27
-rw-r--r--arch/x86/kernel/irq.c19
-rw-r--r--arch/x86/kernel/irqinit.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c10
-rw-r--r--arch/x86/kernel/ksysfs.c4
-rw-r--r--arch/x86/kernel/kvm.c6
-rw-r--r--arch/x86/kernel/reboot.c6
-rw-r--r--arch/x86/kernel/smpboot.c30
13 files changed, 118 insertions, 60 deletions
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index d869c8671e36..0ee83321a313 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -8,20 +8,25 @@
* This file is licensed under GPLv2.
*/
-#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/ktime.h>
#include <linux/math64.h>
#include <linux/percpu.h>
#include <linux/smp.h>
struct aperfmperf_sample {
unsigned int khz;
- unsigned long jiffies;
+ ktime_t time;
u64 aperf;
u64 mperf;
};
static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
+#define APERFMPERF_CACHE_THRESHOLD_MS 10
+#define APERFMPERF_REFRESH_DELAY_MS 20
+#define APERFMPERF_STALE_THRESHOLD_MS 1000
+
/*
* aperfmperf_snapshot_khz()
* On the current CPU, snapshot APERF, MPERF, and jiffies
@@ -33,13 +38,18 @@ static void aperfmperf_snapshot_khz(void *dummy)
u64 aperf, aperf_delta;
u64 mperf, mperf_delta;
struct aperfmperf_sample *s = this_cpu_ptr(&samples);
+ ktime_t now = ktime_get();
+ s64 time_delta = ktime_ms_delta(now, s->time);
+ unsigned long flags;
- /* Don't bother re-computing within 10 ms */
- if (time_before(jiffies, s->jiffies + HZ/100))
+ /* Don't bother re-computing within the cache threshold time. */
+ if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
return;
+ local_irq_save(flags);
rdmsrl(MSR_IA32_APERF, aperf);
rdmsrl(MSR_IA32_MPERF, mperf);
+ local_irq_restore(flags);
aperf_delta = aperf - s->aperf;
mperf_delta = mperf - s->mperf;
@@ -51,22 +61,21 @@ static void aperfmperf_snapshot_khz(void *dummy)
if (mperf_delta == 0)
return;
- /*
- * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then
- * khz = (cpu_khz * aperf_delta) / mperf_delta
- */
- if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta)
- s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
- else /* khz = aperf_delta / (mperf_delta / cpu_khz) */
- s->khz = div64_u64(aperf_delta,
- div64_u64(mperf_delta, cpu_khz));
- s->jiffies = jiffies;
+ s->time = now;
s->aperf = aperf;
s->mperf = mperf;
+
+ /* If the previous iteration was too long ago, discard it. */
+ if (time_delta > APERFMPERF_STALE_THRESHOLD_MS)
+ s->khz = 0;
+ else
+ s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
}
unsigned int arch_freq_get_on_cpu(int cpu)
{
+ unsigned int khz;
+
if (!cpu_khz)
return 0;
@@ -74,6 +83,12 @@ unsigned int arch_freq_get_on_cpu(int cpu)
return 0;
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
+ khz = per_cpu(samples.khz, cpu);
+ if (khz)
+ return khz;
+
+ msleep(APERFMPERF_REFRESH_DELAY_MS);
+ smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
return per_cpu(samples.khz, cpu);
}
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d7cc190ae457..f7370abd33c6 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = {
NULL
};
-static struct attribute_group thermal_attr_group = {
+static const struct attribute_group thermal_attr_group = {
.attrs = thermal_throttle_attrs,
.name = "thermal_throttle"
};
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 9cb98ee103db..86e8f0b2537b 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = {
NULL
};
-static struct attribute_group mc_attr_group = {
+static const struct attribute_group mc_attr_group = {
.attrs = mc_default_attrs,
.name = "microcode",
};
@@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = {
NULL
};
-static struct attribute_group cpu_root_microcode_group = {
+static const struct attribute_group cpu_root_microcode_group = {
.name = "microcode",
.attrs = cpu_root_microcode_attrs,
};
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index c5bb63be4ba1..40d5a8a75212 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask);
}
+static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base,
+ unsigned long size, mtrr_type type)
+{
+ struct set_mtrr_data data = { .smp_reg = reg,
+ .smp_base = base,
+ .smp_size = size,
+ .smp_type = type
+ };
+
+ stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask);
+}
+
static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base,
unsigned long size, mtrr_type type)
{
@@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
/* Search for an empty MTRR */
i = mtrr_if->get_free_region(base, size, replace);
if (i >= 0) {
- set_mtrr(i, base, size, type);
+ set_mtrr_cpuslocked(i, base, size, type);
if (likely(replace < 0)) {
mtrr_usage_table[i] = 1;
} else {
@@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
if (increment)
mtrr_usage_table[i]++;
if (unlikely(replace != i)) {
- set_mtrr(replace, 0, 0, 0);
+ set_mtrr_cpuslocked(replace, 0, 0, 0);
mtrr_usage_table[replace] = 0;
}
}
@@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
goto out;
}
if (--mtrr_usage_table[reg] < 1)
- set_mtrr(reg, 0, 0, 0);
+ set_mtrr_cpuslocked(reg, 0, 0, 0);
error = reg;
out:
mutex_unlock(&mtrr_mutex);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 46c3c73e7f43..9ba79543d9ee 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -53,6 +53,7 @@ void __head __startup_64(unsigned long physaddr)
pudval_t *pud;
pmdval_t *pmd, pmd_entry;
int i;
+ unsigned int *next_pgt_ptr;
/* Is the address too large? */
if (physaddr >> MAX_PHYSMEM_BITS)
@@ -91,9 +92,9 @@ void __head __startup_64(unsigned long physaddr)
* creates a bunch of nonsense entries but that is fine --
* it avoids problems around wraparound.
*/
-
- pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
- pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+ next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
+ pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
+ pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 16f82a3aaec7..8ce4212e2b8d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -345,21 +345,10 @@ static int hpet_shutdown(struct clock_event_device *evt, int timer)
return 0;
}
-static int hpet_resume(struct clock_event_device *evt, int timer)
-{
- if (!timer) {
- hpet_enable_legacy_int();
- } else {
- struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-
- irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
- irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
- disable_hardirq(hdev->irq);
- irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
- enable_irq(hdev->irq);
- }
+static int hpet_resume(struct clock_event_device *evt)
+{
+ hpet_enable_legacy_int();
hpet_print_config();
-
return 0;
}
@@ -417,7 +406,7 @@ static int hpet_legacy_set_periodic(struct clock_event_device *evt)
static int hpet_legacy_resume(struct clock_event_device *evt)
{
- return hpet_resume(evt, 0);
+ return hpet_resume(evt);
}
static int hpet_legacy_next_event(unsigned long delta,
@@ -510,8 +499,14 @@ static int hpet_msi_set_periodic(struct clock_event_device *evt)
static int hpet_msi_resume(struct clock_event_device *evt)
{
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+ struct irq_data *data = irq_get_irq_data(hdev->irq);
+ struct msi_msg msg;
- return hpet_resume(evt, hdev->num);
+ /* Restore the MSI msg and unmask the interrupt */
+ irq_chip_compose_msi_msg(data, &msg);
+ hpet_msi_write(hdev, &msg);
+ hpet_msi_unmask(data);
+ return 0;
}
static int hpet_msi_next_event(unsigned long delta,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4aa03c5a14c9..4ed0aba8dbc8 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -155,6 +155,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
seq_puts(p, " Posted-interrupt notification event\n");
+ seq_printf(p, "%*s: ", prec, "NPI");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->kvm_posted_intr_nested_ipis);
+ seq_puts(p, " Nested posted-interrupt event\n");
+
seq_printf(p, "%*s: ", prec, "PIW");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
@@ -313,6 +319,19 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
exiting_irq();
set_irq_regs(old_regs);
}
+
+/*
+ * Handler for POSTED_INTERRUPT_NESTED_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ entering_ack_irq();
+ inc_irq_stat(kvm_posted_intr_nested_ipis);
+ exiting_irq();
+ set_irq_regs(old_regs);
+}
#endif
__visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs)
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 7468c6987547..c7fd18526c3e 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -150,6 +150,8 @@ static void __init apic_intr_init(void)
alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
/* IPI for KVM to deliver interrupt to wake up tasks */
alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
+ /* IPI for KVM to deliver nested posted interrupt */
+ alloc_intr_gate(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi);
#endif
/* IPI vectors for APIC spurious and error interrupts */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6b877807598b..f0153714ddac 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -457,6 +457,8 @@ static int arch_copy_kprobe(struct kprobe *p)
int arch_prepare_kprobe(struct kprobe *p)
{
+ int ret;
+
if (alternatives_text_reserved(p->addr, p->addr))
return -EINVAL;
@@ -467,7 +469,13 @@ int arch_prepare_kprobe(struct kprobe *p)
if (!p->ainsn.insn)
return -ENOMEM;
- return arch_copy_kprobe(p);
+ ret = arch_copy_kprobe(p);
+ if (ret) {
+ free_insn_slot(p->ainsn.insn, 0);
+ p->ainsn.insn = NULL;
+ }
+
+ return ret;
}
void arch_arm_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index 4afc67f5facc..06e1ff5562c0 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = {
NULL,
};
-static struct attribute_group boot_params_attr_group = {
+static const struct attribute_group boot_params_attr_group = {
.attrs = boot_params_version_attrs,
.bin_attrs = boot_params_data_attrs,
};
@@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = {
NULL,
};
-static struct attribute_group setup_data_attr_group = {
+static const struct attribute_group setup_data_attr_group = {
.attrs = setup_data_type_attrs,
.bin_attrs = setup_data_data_attrs,
};
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 71c17a5be983..d04e30e3c0ff 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
if (hlist_unhashed(&n.link))
break;
+ rcu_irq_exit();
+
if (!n.halted) {
local_irq_enable();
schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
/*
* We cannot reschedule. So halt.
*/
- rcu_irq_exit();
native_safe_halt();
local_irq_disable();
- rcu_irq_enter();
}
+
+ rcu_irq_enter();
}
if (!n.halted)
finish_swait(&n.wq, &wait);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 67393fc88353..a56bf6051f4e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -471,12 +471,12 @@ static int __init reboot_init(void)
/*
* The DMI quirks table takes precedence. If no quirks entry
- * matches and the ACPI Hardware Reduced bit is set, force EFI
- * reboot.
+ * matches and the ACPI Hardware Reduced bit is set and EFI
+ * runtime services are enabled, force EFI reboot.
*/
rv = dmi_check_system(reboot_dmi_table);
- if (!rv && efi_reboot_required())
+ if (!rv && efi_reboot_required() && !efi_runtime_disabled())
reboot_type = BOOT_EFI;
return 0;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b474c8de7fba..54b9e89d4d6b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
* Returns zero if CPU booted OK, else error code from
* ->wakeup_secondary_cpu.
*/
-static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
+ int *cpu0_nmi_registered)
{
volatile u32 *trampoline_status =
(volatile u32 *) __va(real_mode_header->trampoline_status);
@@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
unsigned long start_ip = real_mode_header->trampoline_start;
unsigned long boot_error = 0;
- int cpu0_nmi_registered = 0;
unsigned long timeout;
idle->thread.sp = (unsigned long)task_pt_regs(idle);
@@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
else
boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
- &cpu0_nmi_registered);
+ cpu0_nmi_registered);
if (!boot_error) {
/*
@@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
*/
smpboot_restore_warm_reset_vector();
}
- /*
- * Clean up the nmi handler. Do this after the callin and callout sync
- * to avoid impact of possible long unregister time.
- */
- if (cpu0_nmi_registered)
- unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
return boot_error;
}
@@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int apicid = apic->cpu_present_to_apicid(cpu);
+ int cpu0_nmi_registered = 0;
unsigned long flags;
- int err;
+ int err, ret = 0;
WARN_ON(irqs_disabled());
@@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
common_cpu_up(cpu, tidle);
- err = do_boot_cpu(apicid, cpu, tidle);
+ err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
if (err) {
pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
- return -EIO;
+ ret = -EIO;
+ goto unreg_nmi;
}
/*
@@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
touch_nmi_watchdog();
}
- return 0;
+unreg_nmi:
+ /*
+ * Clean up the nmi handler. Do this after the callin and callout sync
+ * to avoid impact of possible long unregister time.
+ */
+ if (cpu0_nmi_registered)
+ unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+
+ return ret;
}
/**