From: Paolo Bonzini Date: Tue, 6 May 2014 15:20:37 +0000 (+0200) Subject: Merge tag 'kvm-s390-20140506' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms39... X-Git-Tag: next-20140516~30^2~9 X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=2ce316f0b9b2103e27585180b6aa6f17f0175f0e;hp=f14d82e06a008b8977b64866a4907d2e152af939;p=karo-tx-linux.git Merge tag 'kvm-s390-20140506' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into kvm-next 1. Fixes an error return code for the breakpoint setup 2. External interrupt fixes 2.1. Some interrupt conditions like cpu timer or clock comparator stay pending even after the interrupt is injected. If the external new PSW is enabled for interrupts this will result in an endless loop. Usually this indicates a programming error in the guest OS. Lets detect such situations and go to userspace. We will provide a QEMU patch that sets the guest in panicked/crashed state to avoid wasting CPU cycles. 2.2 Resend external interrupts back to the guest if the HW could not do it. - --- diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 545245d7cc63..33574c95220d 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -91,16 +91,21 @@ TRACE_EVENT(kvm_hv_hypercall, /* * Tracepoint for PIO. */ + +#define KVM_PIO_IN 0 +#define KVM_PIO_OUT 1 + TRACE_EVENT(kvm_pio, TP_PROTO(unsigned int rw, unsigned int port, unsigned int size, - unsigned int count), - TP_ARGS(rw, port, size, count), + unsigned int count, void *data), + TP_ARGS(rw, port, size, count, data), TP_STRUCT__entry( __field( unsigned int, rw ) __field( unsigned int, port ) __field( unsigned int, size ) __field( unsigned int, count ) + __field( unsigned int, val ) ), TP_fast_assign( @@ -108,11 +113,18 @@ TRACE_EVENT(kvm_pio, __entry->port = port; __entry->size = size; __entry->count = count; + if (size == 1) + __entry->val = *(unsigned char *)data; + else if (size == 2) + __entry->val = *(unsigned short *)data; + else + __entry->val = *(unsigned int *)data; ), - TP_printk("pio_%s at 0x%x size %d count %d", + TP_printk("pio_%s at 0x%x size %d count %d val 0x%x %s", __entry->rw ? "write" : "read", - __entry->port, __entry->size, __entry->count) + __entry->port, __entry->size, __entry->count, __entry->val, + __entry->count > 1 ? "(...)" : "") ); /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c5582c385bc0..de0931cb3f58 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4480,8 +4480,6 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count, bool in) { - trace_kvm_pio(!in, port, size, count); - vcpu->arch.pio.port = port; vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; @@ -4516,6 +4514,7 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (ret) { data_avail: memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); vcpu->arch.pio.count = 0; return 1; } @@ -4530,6 +4529,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); memcpy(vcpu->arch.pio_data, val, size * count); + trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1e125b055327..970c68197c69 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -370,6 +370,7 @@ struct kvm { struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots *memslots; struct srcu_struct srcu; + struct srcu_struct irq_srcu; #ifdef CONFIG_KVM_APIC_ARCHITECTURE u32 bsp_vcpu_id; #endif diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 912ec5a95e2c..20c3af7692c5 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include "iodev.h" @@ -118,19 +119,22 @@ static void irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) { struct _irqfd_resampler *resampler; + struct kvm *kvm; struct _irqfd *irqfd; + int idx; resampler = container_of(kian, struct _irqfd_resampler, notifier); + kvm = resampler->kvm; - kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); - rcu_read_lock(); + idx = srcu_read_lock(&kvm->irq_srcu); list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) eventfd_signal(irqfd->resamplefd, 1); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } static void @@ -142,7 +146,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd) mutex_lock(&kvm->irqfds.resampler_lock); list_del_rcu(&irqfd->resampler_link); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { list_del(&resampler->link); @@ -221,17 +225,18 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) unsigned long flags = (unsigned long)key; struct kvm_kernel_irq_routing_entry *irq; struct kvm *kvm = irqfd->kvm; + int idx; if (flags & POLLIN) { - rcu_read_lock(); - irq = rcu_dereference(irqfd->irq_entry); + idx = srcu_read_lock(&kvm->irq_srcu); + irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu); /* An event has been signaled, inject an interrupt */ if (irq) kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false); else schedule_work(&irqfd->inject); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } if (flags & POLLHUP) { @@ -363,7 +368,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); mutex_unlock(&kvm->irqfds.resampler_lock); } @@ -465,7 +470,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) * another thread calls kvm_irq_routing_update before * we flush workqueue below (we synchronize with * kvm_irq_routing_update using irqfds.lock). - * It is paired with synchronize_rcu done by caller + * It is paired with synchronize_srcu done by caller * of that function. */ rcu_assign_pointer(irqfd->irq_entry, NULL); @@ -524,7 +529,7 @@ kvm_irqfd_release(struct kvm *kvm) /* * Change irq_routing and irqfd. - * Caller must invoke synchronize_rcu afterwards. + * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards. */ void kvm_irq_routing_update(struct kvm *kvm, struct kvm_irq_routing_table *irq_rt) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index e2e6b4473a96..ced4a542a031 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -163,6 +163,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) struct kvm_kernel_irq_routing_entry *e; int ret = -EINVAL; struct kvm_irq_routing_table *irq_rt; + int idx; trace_kvm_set_irq(irq, level, irq_source_id); @@ -174,8 +175,8 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) * Since there's no easy way to do this, we only support injecting MSI * which is limited to 1:1 GSI mapping. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); if (irq < irq_rt->nr_rt_entries) hlist_for_each_entry(e, &irq_rt->map[irq], link) { if (likely(e->type == KVM_IRQ_ROUTING_MSI)) @@ -184,7 +185,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) ret = -EWOULDBLOCK; break; } - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); return ret; } @@ -253,22 +254,22 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, mutex_lock(&kvm->irq_lock); hlist_del_rcu(&kimn->link); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); } void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask) { struct kvm_irq_mask_notifier *kimn; - int gsi; + int idx, gsi; - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link) if (kimn->irq == gsi) kimn->func(kimn, mask); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 20dc9e4a8f6c..b43c275775cd 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -26,6 +26,7 @@ #include #include +#include #include #include #include "irq.h" @@ -33,19 +34,19 @@ bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; - int gsi; + int gsi, idx; - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) { - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); return true; } - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); return false; } @@ -54,18 +55,18 @@ EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; - int gsi; + int gsi, idx; trace_kvm_ack_irq(irqchip, pin); - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) kian->irq_acked(kian); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } void kvm_register_irq_ack_notifier(struct kvm *kvm, @@ -85,7 +86,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, mutex_lock(&kvm->irq_lock); hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); #ifdef __KVM_HAVE_IOAPIC kvm_vcpu_request_scan_ioapic(kvm); #endif @@ -115,7 +116,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; - int ret = -1, i = 0; + int ret = -1, i = 0, idx; struct kvm_irq_routing_table *irq_rt; trace_kvm_set_irq(irq, level, irq_source_id); @@ -124,12 +125,12 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); if (irq < irq_rt->nr_rt_entries) hlist_for_each_entry(e, &irq_rt->map[irq], link) irq_set[i++] = *e; - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); while(i--) { int r; @@ -226,7 +227,7 @@ int kvm_set_irq_routing(struct kvm *kvm, kvm_irq_routing_update(kvm, new); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu_expedited(&kvm->irq_srcu); new = old; r = 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fa70c6e642b4..95b4c2b3906a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -457,11 +457,11 @@ static struct kvm *kvm_create_vm(unsigned long type) r = kvm_arch_init_vm(kvm, type); if (r) - goto out_err_nodisable; + goto out_err_no_disable; r = hardware_enable_all(); if (r) - goto out_err_nodisable; + goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); @@ -473,10 +473,12 @@ static struct kvm *kvm_create_vm(unsigned long type) r = -ENOMEM; kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) - goto out_err_nosrcu; + goto out_err_no_srcu; kvm_init_memslots_id(kvm); if (init_srcu_struct(&kvm->srcu)) - goto out_err_nosrcu; + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); @@ -505,10 +507,12 @@ static struct kvm *kvm_create_vm(unsigned long type) return kvm; out_err: + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); -out_err_nosrcu: +out_err_no_srcu: hardware_disable_all(); -out_err_nodisable: +out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); kfree(kvm->memslots);