summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/irq.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/irq.c')
-rw-r--r--arch/x86/kernel/irq.c406
1 files changed, 228 insertions, 178 deletions
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4ed0aba8dbc8..86f4e574de02 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Common interrupt code for 32 and 64 bit
*/
@@ -10,27 +11,35 @@
#include <linux/ftrace.h>
#include <linux/delay.h>
#include <linux/export.h>
+#include <linux/irq.h>
+#include <linux/kvm_types.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(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
+DEFINE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+EXPORT_PER_CPU_SYMBOL(__softirq_pending);
-atomic_t irq_err_count;
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
-/* Function pointer for generic interrupt vector handling */
-void (*x86_platform_ipi_callback)(void) = NULL;
+atomic_t irq_err_count;
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
@@ -50,7 +59,7 @@ void ack_bad_irq(unsigned int irq)
* completely.
* But only ack when the APIC is enabled -AK
*/
- ack_APIC_irq();
+ apic_eoi();
}
#define irq_stats(x) (&per_cpu(irq_stat, x))
@@ -87,13 +96,13 @@ int arch_show_interrupts(struct seq_file *p, int prec)
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
seq_puts(p, " APIC ICR read retries\n");
-#endif
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)
@@ -136,8 +145,8 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
seq_puts(p, " Machine check polls\n");
#endif
-#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
- if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) {
+#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 ",
@@ -145,11 +154,27 @@ int arch_show_interrupts(struct seq_file *p, int prec)
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
-#ifdef CONFIG_HAVE_KVM
+#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);
@@ -167,6 +192,13 @@ int arch_show_interrupts(struct seq_file *p, int prec)
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;
}
@@ -183,9 +215,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
sum += irq_stats(cpu)->apic_perf_irqs;
sum += irq_stats(cpu)->apic_irq_work_irqs;
sum += irq_stats(cpu)->icr_read_retry_count;
-#endif
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;
@@ -196,6 +228,13 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
#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);
@@ -209,78 +248,108 @@ u64 arch_irq_stat(void)
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);
+}
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
+static struct irq_desc *reevaluate_vector(int vector)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
- struct irq_desc * desc;
- /* high bit used in ret_from_ code */
- unsigned vector = ~regs->orig_ax;
+ struct irq_desc *desc = __this_cpu_read(vector_irq[vector]);
+
+ if (!IS_ERR_OR_NULL(desc))
+ return desc;
+
+ if (desc == VECTOR_UNUSED)
+ pr_emerg_ratelimited("No irq handler for %d.%u\n", smp_processor_id(), vector);
+ else
+ __this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+ return NULL;
+}
+
+static __always_inline bool call_irq_handler(int vector, struct pt_regs *regs)
+{
+ struct irq_desc *desc = __this_cpu_read(vector_irq[vector]);
+
+ if (likely(!IS_ERR_OR_NULL(desc))) {
+ handle_irq(desc, regs);
+ return true;
+ }
/*
- * NB: Unlike exception entries, IRQ entries do not reliably
- * handle context tracking in the low-level entry code. This is
- * because syscall entries execute briefly with IRQs on before
- * updating context tracking state, so we can take an IRQ from
- * kernel mode with CONTEXT_USER. The low-level entry code only
- * updates the context if we came from user mode, so we won't
- * switch to CONTEXT_KERNEL. We'll fix that once the syscall
- * code is cleaned up enough that we can cleanly defer enabling
- * IRQs.
+ * Reevaluate with vector_lock held to prevent a race against
+ * request_irq() setting up the vector:
+ *
+ * CPU0 CPU1
+ * interrupt is raised in APIC IRR
+ * but not handled
+ * free_irq()
+ * per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN;
+ *
+ * request_irq() common_interrupt()
+ * d = this_cpu_read(vector_irq[vector]);
+ *
+ * per_cpu(vector_irq, CPU1)[vector] = desc;
+ *
+ * if (d == VECTOR_SHUTDOWN)
+ * this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+ *
+ * This requires that the same vector on the same target CPU is
+ * handed out or that a spurious interrupt hits that CPU/vector.
*/
+ lock_vector_lock();
+ desc = reevaluate_vector(vector);
+ unlock_vector_lock();
- entering_irq();
-
- /* entering_irq() tells RCU that we're not quiescent. Check it. */
- RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
+ if (!desc)
+ return false;
- desc = __this_cpu_read(vector_irq[vector]);
+ handle_irq(desc, regs);
+ return true;
+}
- if (!handle_irq(desc, regs)) {
- ack_APIC_irq();
+/*
+ * 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);
- if (desc != VECTOR_RETRIGGERED) {
- pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
- __func__, smp_processor_id(),
- vector);
- } else {
- __this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
- }
- }
+ /* entry code tells RCU that we're not quiescent. Check it. */
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
- exiting_irq();
+ if (unlikely(!call_irq_handler(vector, regs)))
+ apic_eoi();
set_irq_regs(old_regs);
- return 1;
}
+#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.
*/
-void __smp_x86_platform_ipi(void)
+DEFINE_IDTENTRY_SYSVEC(sysvec_x86_platform_ipi)
{
- inc_irq_stat(x86_platform_ipis);
+ 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();
-}
-
-__visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- entering_ack_irq();
- __smp_x86_platform_ipi();
- exiting_irq();
+ trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
set_irq_regs(old_regs);
}
+#endif
-#ifdef CONFIG_HAVE_KVM
+#if IS_ENABLED(CONFIG_KVM)
static void dummy_handler(void) {}
static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
@@ -288,170 +357,132 @@ void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
{
if (handler)
kvm_posted_intr_wakeup_handler = handler;
- else
+ else {
kvm_posted_intr_wakeup_handler = dummy_handler;
+ synchronize_rcu();
+ }
}
-EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
+EXPORT_SYMBOL_FOR_KVM(kvm_set_posted_intr_wakeup_handler);
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
-__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_ipi)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- entering_ack_irq();
+ apic_eoi();
inc_irq_stat(kvm_posted_intr_ipis);
- exiting_irq();
- set_irq_regs(old_regs);
}
/*
* Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
*/
-__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_posted_intr_wakeup_ipi)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- entering_ack_irq();
+ apic_eoi();
inc_irq_stat(kvm_posted_intr_wakeup_ipis);
kvm_posted_intr_wakeup_handler();
- 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)
+DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- entering_ack_irq();
+ apic_eoi();
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)
+#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)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
+ u32 destination;
+ u32 apic_id;
- entering_ack_irq();
- trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR);
- __smp_x86_platform_ipi();
- trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
- exiting_irq();
- set_irq_regs(old_regs);
+ 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);
}
-EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
+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;
-#ifdef CONFIG_HOTPLUG_CPU
+ 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;
+}
-/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
- * below, which is protected by stop_machine(). Putting them on the stack
- * results in a stack frame overflow. Dynamically allocating could result in a
- * failure so declare these two cpumasks as global.
+/*
+ * Performance data shows that 3 is good enough to harvest 90+% of the benefit
+ * on high IRQ rate workload.
*/
-static struct cpumask affinity_new, online_new;
+#define MAX_POSTED_MSI_COALESCING_LOOP 3
/*
- * This cpu is going to be removed and its vectors migrated to the remaining
- * online cpus. Check to see if there are enough vectors in the remaining cpus.
- * This function is protected by stop_machine().
+ * For MSIs that are delivered as posted interrupts, the CPU notifications
+ * can be coalesced if the MSIs arrive in high frequency bursts.
*/
-int check_irq_vectors_for_cpu_disable(void)
+DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
{
- unsigned int this_cpu, vector, this_count, count;
- struct irq_desc *desc;
- struct irq_data *data;
- int cpu;
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ struct pi_desc *pid;
+ int i = 0;
- this_cpu = smp_processor_id();
- cpumask_copy(&online_new, cpu_online_mask);
- cpumask_clear_cpu(this_cpu, &online_new);
+ pid = this_cpu_ptr(&posted_msi_pi_desc);
- this_count = 0;
- for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
- desc = __this_cpu_read(vector_irq[vector]);
- if (IS_ERR_OR_NULL(desc))
- continue;
- /*
- * Protect against concurrent action removal, affinity
- * changes etc.
- */
- raw_spin_lock(&desc->lock);
- data = irq_desc_get_irq_data(desc);
- cpumask_copy(&affinity_new,
- irq_data_get_affinity_mask(data));
- cpumask_clear_cpu(this_cpu, &affinity_new);
-
- /* Do not count inactive or per-cpu irqs. */
- if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) {
- raw_spin_unlock(&desc->lock);
- continue;
- }
+ inc_irq_stat(posted_msi_notification_count);
+ irq_enter();
- raw_spin_unlock(&desc->lock);
- /*
- * A single irq may be mapped to multiple cpu's
- * vector_irq[] (for example IOAPIC cluster mode). In
- * this case we have two possibilities:
- *
- * 1) the resulting affinity mask is empty; that is
- * this the down'd cpu is the last cpu in the irq's
- * affinity mask, or
- *
- * 2) the resulting affinity mask is no longer a
- * subset of the online cpus but the affinity mask is
- * not zero; that is the down'd cpu is the last online
- * cpu in a user set affinity mask.
- */
- if (cpumask_empty(&affinity_new) ||
- !cpumask_subset(&affinity_new, &online_new))
- this_count++;
+ /*
+ * 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;
}
- /* No need to check any further. */
- if (!this_count)
- return 0;
- count = 0;
- for_each_online_cpu(cpu) {
- if (cpu == this_cpu)
- continue;
- /*
- * We scan from FIRST_EXTERNAL_VECTOR to first system
- * vector. If the vector is marked in the used vectors
- * bitmap or an irq is assigned to it, we don't count
- * it as available.
- *
- * As this is an inaccurate snapshot anyway, we can do
- * this w/o holding vector_lock.
- */
- for (vector = FIRST_EXTERNAL_VECTOR;
- vector < first_system_vector; vector++) {
- if (!test_bit(vector, used_vectors) &&
- IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) {
- if (++count == this_count)
- return 0;
- }
- }
- }
+ /*
+ * Clear outstanding notification bit to allow new IRQ notifications,
+ * do this last to maximize the window of interrupt coalescing.
+ */
+ pi_clear_on(pid);
- if (count < this_count) {
- pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n",
- this_cpu, this_count, count);
- return -ERANGE;
- }
- return 0;
+ /*
+ * 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 irr, vector;
+ unsigned int vector;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
@@ -459,7 +490,7 @@ void fixup_irqs(void)
irq_migrate_all_off_this_cpu();
/*
- * We can remove mdelay() and then send spuriuous interrupts to
+ * 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...).
@@ -478,8 +509,7 @@ void fixup_irqs(void)
if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
continue;
- irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
- if (irr & (1 << (vector % 32))) {
+ if (is_vector_pending(vector)) {
desc = __this_cpu_read(vector_irq[vector]);
raw_spin_lock(&desc->lock);
@@ -496,3 +526,23 @@ void fixup_irqs(void)
}
}
#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