--- zzzz-none-000/linux-3.10.107/arch/x86/kernel/irq.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/x86/kernel/irq.c 2021-02-04 17:41:59.000000000 +0000 @@ -17,6 +17,16 @@ #include #include #include +#include + +#define CREATE_TRACE_POINTS +#include + +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); atomic_t irq_err_count; @@ -55,77 +65,104 @@ seq_printf(p, "%*s: ", prec, "NMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->__nmi_count); - seq_printf(p, " Non-maskable interrupts\n"); + 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_printf(p, " Local timer interrupts\n"); + 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_printf(p, " Spurious interrupts\n"); + 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_printf(p, " Performance monitoring interrupts\n"); + 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_printf(p, " IRQ work interrupts\n"); + 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_printf(p, " APIC ICR read retries\n"); + 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_printf(p, " Platform interrupts\n"); + seq_puts(p, " Platform interrupts\n"); } #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_printf(p, " Rescheduling interrupts\n"); + 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 - irq_stats(j)->irq_tlb_count); - seq_printf(p, " Function call interrupts\n"); + 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_printf(p, " TLB shootdowns\n"); + 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_printf(p, " Thermal event interrupts\n"); + 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_printf(p, " Threshold APIC interrupts\n"); + 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_printf(p, " Machine check exceptions\n"); + 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_printf(p, " Machine check polls\n"); + seq_puts(p, " Machine check polls\n"); +#endif +#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) + if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_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 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 + 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, "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 return 0; } @@ -174,28 +211,45 @@ * SMP cross-CPU interrupts have their own specific * handlers). */ -unsigned int __irq_entry do_IRQ(struct pt_regs *regs) +__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) { 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; - unsigned irq; - irq_enter(); - exit_idle(); + /* + * 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. + */ + + 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"); - irq = __this_cpu_read(vector_irq[vector]); + desc = __this_cpu_read(vector_irq[vector]); - if (!handle_irq(irq, regs)) { + if (!handle_irq(desc, regs)) { ack_APIC_irq(); - if (printk_ratelimit()) - pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n", - __func__, smp_processor_id(), vector, irq); + 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); + } } - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); return 1; @@ -204,51 +258,174 @@ /* * Handler for X86_PLATFORM_IPI_VECTOR. */ -void smp_x86_platform_ipi(struct pt_regs *regs) +void __smp_x86_platform_ipi(void) { - struct pt_regs *old_regs = set_irq_regs(regs); - - ack_APIC_irq(); - - irq_enter(); - - exit_idle(); - inc_irq_stat(x86_platform_ipis); if (x86_platform_ipi_callback) x86_platform_ipi_callback(); +} - irq_exit(); +__visible void 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(); set_irq_regs(old_regs); } #ifdef CONFIG_HAVE_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; +} +EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); + /* * Handler for POSTED_INTERRUPT_VECTOR. */ -void smp_kvm_posted_intr_ipi(struct pt_regs *regs) +__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - ack_APIC_irq(); - - irq_enter(); - - exit_idle(); - + entering_ack_irq(); inc_irq_stat(kvm_posted_intr_ipis); + exiting_irq(); + set_irq_regs(old_regs); +} - irq_exit(); +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + entering_ack_irq(); + inc_irq_stat(kvm_posted_intr_wakeup_ipis); + kvm_posted_intr_wakeup_handler(); + exiting_irq(); set_irq_regs(old_regs); } #endif +__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + 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); +} + EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU + +/* 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. + */ +static struct cpumask affinity_new, online_new; + +/* + * 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(). + */ +int check_irq_vectors_for_cpu_disable(void) +{ + unsigned int this_cpu, vector, this_count, count; + struct irq_desc *desc; + struct irq_data *data; + int cpu; + + this_cpu = smp_processor_id(); + cpumask_copy(&online_new, cpu_online_mask); + cpumask_clear_cpu(this_cpu, &online_new); + + 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; + } + + 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++; + } + + 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])) + count++; + } + } + + 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; +} + /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { @@ -257,6 +434,7 @@ struct irq_desc *desc; struct irq_data *data; struct irq_chip *chip; + int ret; for_each_irq_desc(irq, desc) { int break_affinity = 0; @@ -272,7 +450,7 @@ raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); - affinity = data->affinity; + affinity = irq_data_get_affinity_mask(data); if (!irq_has_action(irq) || irqd_is_per_cpu(data) || cpumask_subset(affinity, cpu_online_mask)) { raw_spin_unlock(&desc->lock); @@ -284,7 +462,7 @@ * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -292,13 +470,26 @@ } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); - if (chip->irq_set_affinity) - chip->irq_set_affinity(data, affinity, true); - else if (!(warned++)) - set_affinity = 0; + if (chip->irq_set_affinity) { + ret = chip->irq_set_affinity(data, affinity, true); + if (ret == -ENOSPC) + pr_crit("IRQ %d set affinity failed because there are no available vectors. The device assigned to this IRQ is unstable.\n", irq); + } else { + if (!(warned++)) + set_affinity = 0; + } /* * We unmask if the irq was not marked masked by the @@ -328,25 +519,32 @@ */ 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++) { unsigned int irr; - if (__this_cpu_read(vector_irq[vector]) < 0) + 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))) { - irq = __this_cpu_read(vector_irq[vector]); + desc = __this_cpu_read(vector_irq[vector]); - desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); - raw_spin_lock(&desc->lock); - if (chip->irq_retrigger) + if (chip->irq_retrigger) { chip->irq_retrigger(data); + __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); + } raw_spin_unlock(&desc->lock); } - __this_cpu_write(vector_irq[vector], -1); + if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED) + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } #endif