Contributors: 50
| Author |
Tokens |
Token Proportion |
Commits |
Commit Proportion |
| Thomas Gleixner |
514 |
24.15% |
23 |
18.25% |
| Andi Kleen |
292 |
13.72% |
8 |
6.35% |
| Jacob jun Pan |
251 |
11.80% |
4 |
3.17% |
| Jan Beulich |
164 |
7.71% |
4 |
3.17% |
| Feng Wu |
73 |
3.43% |
2 |
1.59% |
| Suresh B. Siddha |
67 |
3.15% |
3 |
2.38% |
| Andrew Morton |
62 |
2.91% |
6 |
4.76% |
| Ingo Molnar |
50 |
2.35% |
9 |
7.14% |
| Dimitri Sivanich |
49 |
2.30% |
2 |
1.59% |
| Jeremy Fitzhardinge |
49 |
2.30% |
2 |
1.59% |
| Borislav Petkov |
36 |
1.69% |
2 |
1.59% |
| David Howells |
35 |
1.64% |
1 |
0.79% |
| Brian Gerst |
34 |
1.60% |
4 |
3.17% |
| Seiji Aguchi |
30 |
1.41% |
1 |
0.79% |
| Fernando Luis Vázquez Cao |
29 |
1.36% |
2 |
1.59% |
| Hidetoshi Seto |
29 |
1.36% |
5 |
3.97% |
| Vitaly Kuznetsov |
26 |
1.22% |
2 |
1.59% |
| Michael Kelley |
25 |
1.17% |
2 |
1.59% |
| Tomoki Sekiyama |
23 |
1.08% |
1 |
0.79% |
| Rasmus Villemoes |
22 |
1.03% |
1 |
0.79% |
| Peter Zijlstra |
20 |
0.94% |
2 |
1.59% |
| Joe Korty |
20 |
0.94% |
1 |
0.79% |
| Sean Christopherson |
20 |
0.94% |
4 |
3.17% |
| Prarit Bhargava |
18 |
0.85% |
1 |
0.79% |
| Linus Torvalds (pre-git) |
17 |
0.80% |
4 |
3.17% |
| Heiner Kallweit |
15 |
0.70% |
2 |
1.59% |
| Wincy Van |
14 |
0.66% |
1 |
0.79% |
| Arnd Bergmann |
13 |
0.61% |
1 |
0.79% |
| Yang Zhang |
13 |
0.61% |
1 |
0.79% |
| Linus Torvalds |
13 |
0.61% |
2 |
1.59% |
| Ashok Raj |
12 |
0.56% |
1 |
0.79% |
| Paolo Bonzini |
12 |
0.56% |
1 |
0.79% |
| Aravind Gopalakrishnan |
10 |
0.47% |
1 |
0.79% |
| Luis Henriques |
8 |
0.38% |
1 |
0.79% |
| Eric W. Biedermann |
8 |
0.38% |
2 |
1.59% |
| Tejun Heo |
8 |
0.38% |
1 |
0.79% |
| Andrew Lutomirski |
7 |
0.33% |
1 |
0.79% |
| Dave Hansen |
6 |
0.28% |
1 |
0.79% |
| Jaswinder Singh Rajput |
5 |
0.23% |
2 |
1.59% |
| Yinghai Lu |
5 |
0.23% |
2 |
1.59% |
| James Bottomley |
3 |
0.14% |
1 |
0.79% |
| Andres Salomon |
3 |
0.14% |
1 |
0.79% |
| Frédéric Weisbecker |
3 |
0.14% |
1 |
0.79% |
| Yakui Zhao |
3 |
0.14% |
1 |
0.79% |
| Paul Gortmaker |
3 |
0.14% |
1 |
0.79% |
| K. Y. Srinivasan |
2 |
0.09% |
1 |
0.79% |
| Dave Jones |
2 |
0.09% |
1 |
0.79% |
| Mike Travis |
2 |
0.09% |
1 |
0.79% |
| Li Hong |
2 |
0.09% |
1 |
0.79% |
| Cyrill V. Gorcunov |
1 |
0.05% |
1 |
0.79% |
| Total |
2128 |
|
126 |
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Common interrupt code for 32 and 64 bit
*/
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/of.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/ftrace.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/irq.h>
#include <asm/irq_stack.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/irq.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>
#include <asm/desc.h>
#include <asm/traps.h>
#include <asm/thermal.h>
#include <asm/posted_intr.h>
#include <asm/irq_remapping.h>
#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
#endif
DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);
DEFINE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
EXPORT_PER_CPU_SYMBOL(__softirq_pending);
DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
atomic_t irq_err_count;
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
* each architecture has to answer this themselves.
*/
void ack_bad_irq(unsigned int irq)
{
if (printk_ratelimit())
pr_err("unexpected IRQ trap at vector %02x\n", irq);
/*
* Currently unexpected vectors happen only on SMP and APIC.
* We _must_ ack these because every local APIC has only N
* irq slots per priority level, and a 'hanging, unacked' IRQ
* holds up an irq slot - in excessive cases (when multiple
* unexpected vectors occur) that might lock up the APIC
* completely.
* But only ack when the APIC is enabled -AK
*/
apic_eoi();
}
#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
* /proc/interrupts printing for arch specific interrupts
*/
int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
seq_printf(p, "%*s: ", prec, "NMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->__nmi_count);
seq_puts(p, " Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
seq_printf(p, "%*s: ", prec, "LOC");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
seq_puts(p, " Local timer interrupts\n");
seq_printf(p, "%*s: ", prec, "SPU");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
seq_puts(p, " Spurious interrupts\n");
seq_printf(p, "%*s: ", prec, "PMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
seq_puts(p, " Performance monitoring interrupts\n");
seq_printf(p, "%*s: ", prec, "IWI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
seq_puts(p, " IRQ work interrupts\n");
seq_printf(p, "%*s: ", prec, "RTR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
seq_puts(p, " APIC ICR read retries\n");
if (x86_platform_ipi_callback) {
seq_printf(p, "%*s: ", prec, "PLT");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis);
seq_puts(p, " Platform interrupts\n");
}
#endif
#ifdef CONFIG_SMP
seq_printf(p, "%*s: ", prec, "RES");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
seq_puts(p, " Rescheduling interrupts\n");
seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
seq_puts(p, " Function call interrupts\n");
seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
seq_puts(p, " TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
seq_printf(p, "%*s: ", prec, "TRM");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
seq_puts(p, " Thermal event interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
seq_printf(p, "%*s: ", prec, "THR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
seq_puts(p, " Threshold APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_AMD
seq_printf(p, "%*s: ", prec, "DFR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
seq_puts(p, " Deferred Error APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE
seq_printf(p, "%*s: ", prec, "MCE");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(mce_exception_count, j));
seq_puts(p, " Machine check exceptions\n");
seq_printf(p, "%*s: ", prec, "MCP");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
seq_puts(p, " Machine check polls\n");
#endif
#ifdef CONFIG_X86_HV_CALLBACK_VECTOR
if (test_bit(HYPERVISOR_CALLBACK_VECTOR, system_vectors)) {
seq_printf(p, "%*s: ", prec, "HYP");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
irq_stats(j)->irq_hv_callback_count);
seq_puts(p, " Hypervisor callback interrupts\n");
}
#endif
#if IS_ENABLED(CONFIG_HYPERV)
if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) {
seq_printf(p, "%*s: ", prec, "HRE");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
irq_stats(j)->irq_hv_reenlightenment_count);
seq_puts(p, " Hyper-V reenlightenment interrupts\n");
}
if (test_bit(HYPERV_STIMER0_VECTOR, system_vectors)) {
seq_printf(p, "%*s: ", prec, "HVS");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
irq_stats(j)->hyperv_stimer0_count);
seq_puts(p, " Hyper-V stimer0 interrupts\n");
}
#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
#if IS_ENABLED(CONFIG_KVM)
seq_printf(p, "%*s: ", prec, "PIN");
for_each_online_cpu(j)
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 ",
irq_stats(j)->kvm_posted_intr_wakeup_ipis);
seq_puts(p, " Posted-interrupt wakeup event\n");
#endif
#ifdef CONFIG_X86_POSTED_MSI
seq_printf(p, "%*s: ", prec, "PMN");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
irq_stats(j)->posted_msi_notification_count);
seq_puts(p, " Posted MSI notification event\n");
#endif
return 0;
}
/*
* /proc/stat helpers
*/
u64 arch_irq_stat_cpu(unsigned int cpu)
{
u64 sum = irq_stats(cpu)->__nmi_count;
#ifdef CONFIG_X86_LOCAL_APIC
sum += irq_stats(cpu)->apic_timer_irqs;
sum += irq_stats(cpu)->irq_spurious_count;
sum += irq_stats(cpu)->apic_perf_irqs;
sum += irq_stats(cpu)->apic_irq_work_irqs;
sum += irq_stats(cpu)->icr_read_retry_count;
if (x86_platform_ipi_callback)
sum += irq_stats(cpu)->x86_platform_ipis;
#endif
#ifdef CONFIG_SMP
sum += irq_stats(cpu)->irq_resched_count;
sum += irq_stats(cpu)->irq_call_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
sum += irq_stats(cpu)->irq_thermal_count;
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
sum += irq_stats(cpu)->irq_threshold_count;
#endif
#ifdef CONFIG_X86_HV_CALLBACK_VECTOR
sum += irq_stats(cpu)->irq_hv_callback_count;
#endif
#if IS_ENABLED(CONFIG_HYPERV)
sum += irq_stats(cpu)->irq_hv_reenlightenment_count;
sum += irq_stats(cpu)->hyperv_stimer0_count;
#endif
#ifdef CONFIG_X86_MCE
sum += per_cpu(mce_exception_count, cpu);
sum += per_cpu(mce_poll_count, cpu);
#endif
return sum;
}
u64 arch_irq_stat(void)
{
u64 sum = atomic_read(&irq_err_count);
return sum;
}
static __always_inline void handle_irq(struct irq_desc *desc,
struct pt_regs *regs)
{
if (IS_ENABLED(CONFIG_X86_64))
generic_handle_irq_desc(desc);
else
__handle_irq(desc, regs);
}
static __always_inline int call_irq_handler(int vector, struct pt_regs *regs)
{
struct irq_desc *desc;
int ret = 0;
desc = __this_cpu_read(vector_irq[vector]);
if (likely(!IS_ERR_OR_NULL(desc))) {
handle_irq(desc, regs);
} else {
ret = -EINVAL;
if (desc == VECTOR_UNUSED) {
pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n",
__func__, smp_processor_id(),
vector);
} else {
__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
}
}
return ret;
}
/*
* common_interrupt() handles all normal device IRQ's (the special SMP
* cross-CPU interrupts have their own entry points).
*/
DEFINE_IDTENTRY_IRQ(common_interrupt)
{
struct pt_regs *old_regs = set_irq_regs(regs);
/* entry code tells RCU that we're not quiescent. Check it. */
RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
if (unlikely(call_irq_handler(vector, regs)))
apic_eoi();
set_irq_regs(old_regs);
}
#ifdef CONFIG_X86_LOCAL_APIC
/* Function pointer for generic interrupt vector handling */
void (*x86_platform_ipi_callback)(void) = NULL;
/*
* Handler for X86_PLATFORM_IPI_VECTOR.
*/
DEFINE_IDTENTRY_SYSVEC(sysvec_x86_platform_ipi)
{
struct pt_regs *old_regs = set_irq_regs(regs);
apic_eoi();
trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR);
inc_irq_stat(x86_platform_ipis);
if (x86_platform_ipi_callback)
x86_platform_ipi_callback();
trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
set_irq_regs(old_regs);
}
#endif
#if IS_ENABLED(CONFIG_KVM)
static void dummy_handler(void) {}
static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
{
if (handler)
kvm_posted_intr_wakeup_handler = handler;
else {
kvm_posted_intr_wakeup_handler = dummy_handler;
synchronize_rcu();
}
}
EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_ipi)
{
apic_eoi();
inc_irq_stat(kvm_posted_intr_ipis);
}
/*
* Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
*/
DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_posted_intr_wakeup_ipi)
{
apic_eoi();
inc_irq_stat(kvm_posted_intr_wakeup_ipis);
kvm_posted_intr_wakeup_handler();
}
/*
* Handler for POSTED_INTERRUPT_NESTED_VECTOR.
*/
DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi)
{
apic_eoi();
inc_irq_stat(kvm_posted_intr_nested_ipis);
}
#endif
#ifdef CONFIG_X86_POSTED_MSI
/* Posted Interrupt Descriptors for coalesced MSIs to be posted */
DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc);
void intel_posted_msi_init(void)
{
u32 destination;
u32 apic_id;
this_cpu_write(posted_msi_pi_desc.nv, POSTED_MSI_NOTIFICATION_VECTOR);
/*
* APIC destination ID is stored in bit 8:15 while in XAPIC mode.
* VT-d spec. CH 9.11
*/
apic_id = this_cpu_read(x86_cpu_to_apicid);
destination = x2apic_enabled() ? apic_id : apic_id << 8;
this_cpu_write(posted_msi_pi_desc.ndst, destination);
}
static __always_inline bool handle_pending_pir(unsigned long *pir, struct pt_regs *regs)
{
unsigned long pir_copy[NR_PIR_WORDS];
int vec = FIRST_EXTERNAL_VECTOR;
if (!pi_harvest_pir(pir, pir_copy))
return false;
for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
call_irq_handler(vec, regs);
return true;
}
/*
* Performance data shows that 3 is good enough to harvest 90+% of the benefit
* on high IRQ rate workload.
*/
#define MAX_POSTED_MSI_COALESCING_LOOP 3
/*
* For MSIs that are delivered as posted interrupts, the CPU notifications
* can be coalesced if the MSIs arrive in high frequency bursts.
*/
DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
{
struct pt_regs *old_regs = set_irq_regs(regs);
struct pi_desc *pid;
int i = 0;
pid = this_cpu_ptr(&posted_msi_pi_desc);
inc_irq_stat(posted_msi_notification_count);
irq_enter();
/*
* Max coalescing count includes the extra round of handle_pending_pir
* after clearing the outstanding notification bit. Hence, at most
* MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here.
*/
while (++i < MAX_POSTED_MSI_COALESCING_LOOP) {
if (!handle_pending_pir(pid->pir, regs))
break;
}
/*
* Clear outstanding notification bit to allow new IRQ notifications,
* do this last to maximize the window of interrupt coalescing.
*/
pi_clear_on(pid);
/*
* There could be a race of PI notification and the clearing of ON bit,
* process PIR bits one last time such that handling the new interrupts
* are not delayed until the next IRQ.
*/
handle_pending_pir(pid->pir, regs);
apic_eoi();
irq_exit();
set_irq_regs(old_regs);
}
#endif /* X86_POSTED_MSI */
#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
unsigned int vector;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
irq_migrate_all_off_this_cpu();
/*
* We can remove mdelay() and then send spurious interrupts to
* new cpu targets for all the irqs that were handled previously by
* this cpu. While it works, I have seen spurious interrupt messages
* (nothing wrong but still...).
*
* So for now, retain mdelay(1) and check the IRR and then send those
* interrupts to new targets as this cpu is already offlined...
*/
mdelay(1);
/*
* We can walk the vector array of this cpu without holding
* vector_lock because the cpu is already marked !online, so
* nothing else will touch it.
*/
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
continue;
if (is_vector_pending(vector)) {
desc = __this_cpu_read(vector_irq[vector]);
raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
chip = irq_data_get_irq_chip(data);
if (chip->irq_retrigger) {
chip->irq_retrigger(data);
__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
}
raw_spin_unlock(&desc->lock);
}
if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED)
__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
}
}
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
static void smp_thermal_vector(void)
{
if (x86_thermal_enabled())
intel_thermal_interrupt();
else
pr_err("CPU%d: Unexpected LVT thermal interrupt!\n",
smp_processor_id());
}
DEFINE_IDTENTRY_SYSVEC(sysvec_thermal)
{
trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
inc_irq_stat(irq_thermal_count);
smp_thermal_vector();
trace_thermal_apic_exit(THERMAL_APIC_VECTOR);
apic_eoi();
}
#endif