From 45ec431c52f89218ac01d87663e54de30458edf0 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 23 Aug 2009 17:46:21 +0300 Subject: KVM: Don't wrap schedule() with vcpu_put()/vcpu_load() Preemption notifiers will do that for us automatically. Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7495ce347344..22b520b54411 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1689,9 +1689,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) if (signal_pending(current)) break; - vcpu_put(vcpu); schedule(); - vcpu_load(vcpu); } finish_wait(&vcpu->wq, &wait); -- cgit v1.2.3-59-g8ed1b From 1a6e4a8c276e122dbeb6f9c610f29735e4236bfd Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:19 +0300 Subject: KVM: Move irq sharing information to irqchip level This removes assumptions that max GSIs is smaller than number of pins. Sharing is tracked on pin level not GSI level. [avi: no PIC on ia64] Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/irq.h | 1 + include/linux/kvm_host.h | 2 +- virt/kvm/ioapic.h | 1 + virt/kvm/irq_comm.c | 59 +++++++++++++++++++++++++---------------- 5 files changed, 39 insertions(+), 25 deletions(-) (limited to 'virt') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0b113f2b58cf..35d3236c9de4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -410,7 +410,6 @@ struct kvm_arch{ gpa_t ept_identity_map_addr; unsigned long irq_sources_bitmap; - unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; u64 vm_init_tsc; }; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7d6058a2fd38..c025a2362aae 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -71,6 +71,7 @@ struct kvm_pic { int output; /* intr from master PIC */ struct kvm_io_device dev; void (*ack_notifier)(void *opaque, int irq); + unsigned long irq_states[16]; }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b7bbb5ddd7ae..1c7f8c49e4e8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -120,7 +120,7 @@ struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level); + struct kvm *kvm, int irq_source_id, int level); union { struct { unsigned irqchip; diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 7080b713c160..6e461ade6365 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -41,6 +41,7 @@ struct kvm_ioapic { u32 irr; u32 pad; union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS]; + unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 001663ff401a..9783f5c43dae 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -31,20 +31,39 @@ #include "ioapic.h" +static inline int kvm_irq_line_state(unsigned long *irq_state, + int irq_source_id, int level) +{ + /* Logical OR for level trig interrupt */ + if (level) + set_bit(irq_source_id, irq_state); + else + clear_bit(irq_source_id, irq_state); + + return !!(*irq_state); +} + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { #ifdef CONFIG_X86 - return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level); + struct kvm_pic *pic = pic_irqchip(kvm); + level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin], + irq_source_id, level); + return kvm_pic_set_irq(pic, e->irqchip.pin, level); #else return -1; #endif } static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { - return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin], + irq_source_id, level); + + return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level); } inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) @@ -96,10 +115,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, } static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { struct kvm_lapic_irq irq; + if (!level) + return -1; + trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); irq.dest_id = (e->msi.address_lo & @@ -125,34 +147,19 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) { struct kvm_kernel_irq_routing_entry *e; - unsigned long *irq_state, sig_level; int ret = -1; trace_kvm_set_irq(irq, level, irq_source_id); WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - if (irq < KVM_IOAPIC_NUM_PINS) { - irq_state = (unsigned long *)&kvm->arch.irq_states[irq]; - - /* Logical OR for level trig interrupt */ - if (level) - set_bit(irq_source_id, irq_state); - else - clear_bit(irq_source_id, irq_state); - sig_level = !!(*irq_state); - } else if (!level) - return ret; - else /* Deal with MSI/MSI-X */ - sig_level = 1; - /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ list_for_each_entry(e, &kvm->irq_routing, link) if (e->gsi == irq) { - int r = e->set(e, kvm, sig_level); + int r = e->set(e, kvm, irq_source_id, level); if (r < 0) continue; @@ -232,8 +239,14 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); return; } - for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) - clear_bit(irq_source_id, &kvm->arch.irq_states[i]); + for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { + clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); + if (i >= 16) + continue; +#ifdef CONFIG_X86 + clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]); +#endif + } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); mutex_unlock(&kvm->irq_lock); } -- cgit v1.2.3-59-g8ed1b From 46e624b95c36d729bdf24010fff11d16f6fe94fa Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:20 +0300 Subject: KVM: Change irq routing table to use gsi indexed array Use gsi indexed array instead of scanning all entries on each interrupt injection. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 21 ++++++++++-- virt/kvm/irq_comm.c | 88 +++++++++++++++++++++++++++++------------------- virt/kvm/kvm_main.c | 1 - 3 files changed, 71 insertions(+), 39 deletions(-) (limited to 'virt') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1c7f8c49e4e8..f403e66557fb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -128,7 +128,17 @@ struct kvm_kernel_irq_routing_entry { } irqchip; struct msi_msg msi; }; - struct list_head link; + struct hlist_node link; +}; + +struct kvm_irq_routing_table { + struct kvm_kernel_irq_routing_entry *rt_entries; + u32 nr_rt_entries; + /* + * Array indexed by gsi. Each entry contains list of irq chips + * the gsi is connected to. + */ + struct hlist_head map[0]; }; struct kvm { @@ -166,7 +176,7 @@ struct kvm { struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP - struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */ + struct kvm_irq_routing_table *irq_routing; struct hlist_head mask_notifier_list; #endif @@ -390,7 +400,12 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); -int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); +#ifdef __KVM_HAVE_IOAPIC +void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, + union kvm_ioapic_redirect_entry *entry, + unsigned long *deliver_bitmask); +#endif +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 9783f5c43dae..81950f6f6fd9 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -144,10 +144,12 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, * = 0 Interrupt was coalesced (previous irq is still pending) * > 0 Number of CPUs interrupt was delivered to */ -int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) { struct kvm_kernel_irq_routing_entry *e; int ret = -1; + struct kvm_irq_routing_table *irq_rt; + struct hlist_node *n; trace_kvm_set_irq(irq, level, irq_source_id); @@ -157,8 +159,9 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - list_for_each_entry(e, &kvm->irq_routing, link) - if (e->gsi == irq) { + irq_rt = kvm->irq_routing; + if (irq < irq_rt->nr_rt_entries) + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { int r = e->set(e, kvm, irq_source_id, level); if (r < 0) continue; @@ -170,20 +173,23 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { - struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_ack_notifier *kian; struct hlist_node *n; unsigned gsi = pin; + int i; trace_kvm_ack_irq(irqchip, pin); - list_for_each_entry(e, &kvm->irq_routing, link) + for (i = 0; i < kvm->irq_routing->nr_rt_entries; i++) { + struct kvm_kernel_irq_routing_entry *e; + e = &kvm->irq_routing->rt_entries[i]; if (e->type == KVM_IRQ_ROUTING_IRQCHIP && e->irqchip.irqchip == irqchip && e->irqchip.pin == pin) { gsi = e->gsi; break; } + } hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) if (kian->gsi == gsi) @@ -280,26 +286,30 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) kimn->func(kimn, mask); } -static void __kvm_free_irq_routing(struct list_head *irq_routing) -{ - struct kvm_kernel_irq_routing_entry *e, *n; - - list_for_each_entry_safe(e, n, irq_routing, link) - kfree(e); -} - void kvm_free_irq_routing(struct kvm *kvm) { mutex_lock(&kvm->irq_lock); - __kvm_free_irq_routing(&kvm->irq_routing); + kfree(kvm->irq_routing); mutex_unlock(&kvm->irq_lock); } -static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, +static int setup_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; int delta; + struct kvm_kernel_irq_routing_entry *ei; + struct hlist_node *n; + + /* + * Do not allow GSI to be mapped to the same irqchip more than once. + * Allow only one to one mapping between GSI and MSI. + */ + hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) + if (ei->type == KVM_IRQ_ROUTING_MSI || + ue->u.irqchip.irqchip == ei->irqchip.irqchip) + return r; e->gsi = ue->gsi; e->type = ue->type; @@ -332,6 +342,8 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, default: goto out; } + + hlist_add_head(&e->link, &rt->map[e->gsi]); r = 0; out: return r; @@ -343,43 +355,49 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned nr, unsigned flags) { - struct list_head irq_list = LIST_HEAD_INIT(irq_list); - struct list_head tmp = LIST_HEAD_INIT(tmp); - struct kvm_kernel_irq_routing_entry *e = NULL; - unsigned i; + struct kvm_irq_routing_table *new, *old; + u32 i, nr_rt_entries = 0; int r; + for (i = 0; i < nr; ++i) { + if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) + return -EINVAL; + nr_rt_entries = max(nr_rt_entries, ue[i].gsi); + } + + nr_rt_entries += 1; + + new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) + + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), + GFP_KERNEL); + + if (!new) + return -ENOMEM; + + new->rt_entries = (void *)&new->map[nr_rt_entries]; + + new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < nr; ++i) { r = -EINVAL; - if (ue->gsi >= KVM_MAX_IRQ_ROUTES) - goto out; if (ue->flags) goto out; - r = -ENOMEM; - e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - goto out; - r = setup_routing_entry(e, ue); + r = setup_routing_entry(new, &new->rt_entries[i], ue); if (r) goto out; ++ue; - list_add(&e->link, &irq_list); - e = NULL; } mutex_lock(&kvm->irq_lock); - list_splice(&kvm->irq_routing, &tmp); - INIT_LIST_HEAD(&kvm->irq_routing); - list_splice(&irq_list, &kvm->irq_routing); - INIT_LIST_HEAD(&irq_list); - list_splice(&tmp, &irq_list); + old = kvm->irq_routing; + kvm->irq_routing = new; mutex_unlock(&kvm->irq_lock); + new = old; r = 0; out: - kfree(e); - __kvm_free_irq_routing(&irq_list); + kfree(new); return r; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 22b520b54411..3bee94892774 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -957,7 +957,6 @@ static struct kvm *kvm_create_vm(void) if (IS_ERR(kvm)) goto out; #ifdef CONFIG_HAVE_KVM_IRQCHIP - INIT_LIST_HEAD(&kvm->irq_routing); INIT_HLIST_HEAD(&kvm->mask_notifier_list); #endif -- cgit v1.2.3-59-g8ed1b From 3e71f88bc90792a187703860cf22fbed7c12cbd9 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:21 +0300 Subject: KVM: Maintain back mapping from irqchip/pin to gsi Maintain back mapping from irqchip/pin to gsi to speedup interrupt acknowledgment notifications. [avi: build fix on non-x86/ia64] Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm.h | 1 + arch/x86/include/asm/kvm.h | 1 + include/linux/kvm_host.h | 9 +++++++++ virt/kvm/irq_comm.c | 31 ++++++++++++++----------------- 4 files changed, 25 insertions(+), 17 deletions(-) (limited to 'virt') diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index 18a7e49abbc5..bc90c75adf67 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -60,6 +60,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 #define KVM_CONTEXT_SIZE 8*1024 diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 4a5fe914dc59..f02e87a5206f 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -79,6 +79,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f403e66557fb..cc2d7493598b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -131,7 +131,10 @@ struct kvm_kernel_irq_routing_entry { struct hlist_node link; }; +#ifdef __KVM_HAVE_IOAPIC + struct kvm_irq_routing_table { + int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS]; struct kvm_kernel_irq_routing_entry *rt_entries; u32 nr_rt_entries; /* @@ -141,6 +144,12 @@ struct kvm_irq_routing_table { struct hlist_head map[0]; }; +#else + +struct kvm_irq_routing_table {}; + +#endif + struct kvm { spinlock_t mmu_lock; spinlock_t requests_lock; diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 81950f6f6fd9..59cf8dae0062 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -175,25 +175,16 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; struct hlist_node *n; - unsigned gsi = pin; - int i; + int gsi; trace_kvm_ack_irq(irqchip, pin); - for (i = 0; i < kvm->irq_routing->nr_rt_entries; i++) { - struct kvm_kernel_irq_routing_entry *e; - e = &kvm->irq_routing->rt_entries[i]; - if (e->type == KVM_IRQ_ROUTING_IRQCHIP && - e->irqchip.irqchip == irqchip && - e->irqchip.pin == pin) { - gsi = e->gsi; - break; - } - } - - hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) - if (kian->gsi == gsi) - kian->irq_acked(kian); + gsi = kvm->irq_routing->chip[irqchip][pin]; + if (gsi != -1) + hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, + link) + if (kian->gsi == gsi) + kian->irq_acked(kian); } void kvm_register_irq_ack_notifier(struct kvm *kvm, @@ -332,6 +323,9 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, } e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin + delta; + if (e->irqchip.pin >= KVM_IOAPIC_NUM_PINS) + goto out; + rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; @@ -356,7 +350,7 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned flags) { struct kvm_irq_routing_table *new, *old; - u32 i, nr_rt_entries = 0; + u32 i, j, nr_rt_entries = 0; int r; for (i = 0; i < nr; ++i) { @@ -377,6 +371,9 @@ int kvm_set_irq_routing(struct kvm *kvm, new->rt_entries = (void *)&new->map[nr_rt_entries]; new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < 3; i++) + for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++) + new->chip[i][j] = -1; for (i = 0; i < nr; ++i) { r = -EINVAL; -- cgit v1.2.3-59-g8ed1b From e42bba90bfe724e32fc66ab1b6cb283c51d064b1 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:22 +0300 Subject: KVM: Move irq routing data structure to rcu locking Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'virt') diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 59cf8dae0062..fb861dd956fc 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -159,7 +159,8 @@ 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. */ - irq_rt = kvm->irq_routing; + rcu_read_lock(); + irq_rt = rcu_dereference(kvm->irq_routing); if (irq < irq_rt->nr_rt_entries) hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { int r = e->set(e, kvm, irq_source_id, level); @@ -168,6 +169,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) ret = r + ((ret < 0) ? 0 : ret); } + rcu_read_unlock(); return ret; } @@ -179,7 +181,10 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) trace_kvm_ack_irq(irqchip, pin); - gsi = kvm->irq_routing->chip[irqchip][pin]; + rcu_read_lock(); + gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + rcu_read_unlock(); + if (gsi != -1) hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) @@ -279,9 +284,9 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) void kvm_free_irq_routing(struct kvm *kvm) { - mutex_lock(&kvm->irq_lock); + /* Called only during vm destruction. Nobody can use the pointer + at this stage */ kfree(kvm->irq_routing); - mutex_unlock(&kvm->irq_lock); } static int setup_routing_entry(struct kvm_irq_routing_table *rt, @@ -387,8 +392,9 @@ int kvm_set_irq_routing(struct kvm *kvm, mutex_lock(&kvm->irq_lock); old = kvm->irq_routing; - kvm->irq_routing = new; + rcu_assign_pointer(kvm->irq_routing, new); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); new = old; r = 0; -- cgit v1.2.3-59-g8ed1b From 136bdfeee7b5bc986fc94af3a40d7d13ea37bb95 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:23 +0300 Subject: KVM: Move irq ack notifier list to arch independent code Mask irq notifier list is already there. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm_host.h | 1 - arch/x86/include/asm/kvm_host.h | 1 - include/linux/kvm_host.h | 1 + virt/kvm/irq_comm.c | 5 ++--- virt/kvm/kvm_main.c | 1 + 5 files changed, 4 insertions(+), 5 deletions(-) (limited to 'virt') diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index d9b6325a9328..a362e67e0ca6 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -475,7 +475,6 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; int iommu_flags; - struct hlist_head irq_ack_notifier_list; unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 35d3236c9de4..a46e2dd9aca8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -397,7 +397,6 @@ struct kvm_arch{ struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; - struct hlist_head irq_ack_notifier_list; int vapics_in_nmi_mode; unsigned int tss_addr; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cc2d7493598b..4aa5e1d9a797 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -187,6 +187,7 @@ struct kvm { #ifdef CONFIG_HAVE_KVM_IRQCHIP struct kvm_irq_routing_table *irq_routing; struct hlist_head mask_notifier_list; + struct hlist_head irq_ack_notifier_list; #endif #ifdef KVM_ARCH_WANT_MMU_NOTIFIER diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index fb861dd956fc..f01972595938 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -186,8 +186,7 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) rcu_read_unlock(); if (gsi != -1) - hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, - link) + hlist_for_each_entry(kian, n, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) kian->irq_acked(kian); } @@ -196,7 +195,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list); + hlist_add_head(&kian->link, &kvm->irq_ack_notifier_list); mutex_unlock(&kvm->irq_lock); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3bee94892774..6eca153e1a02 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -958,6 +958,7 @@ static struct kvm *kvm_create_vm(void) goto out; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); + INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET -- cgit v1.2.3-59-g8ed1b From 280aa177dcd1edc718d8a92f17f235b783ec6307 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:24 +0300 Subject: KVM: Convert irq notifiers lists to RCU locking Use RCU locking for mask/ack notifiers lists. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'virt') diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index f01972595938..6c946141dbcc 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -183,19 +183,19 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) rcu_read_lock(); gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - rcu_read_unlock(); - if (gsi != -1) - hlist_for_each_entry(kian, n, &kvm->irq_ack_notifier_list, link) + hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + link) if (kian->gsi == gsi) kian->irq_acked(kian); + rcu_read_unlock(); } void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_add_head(&kian->link, &kvm->irq_ack_notifier_list); + hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); mutex_unlock(&kvm->irq_lock); } @@ -203,8 +203,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_del_init(&kian->link); + hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); } int kvm_request_irq_source_id(struct kvm *kvm) @@ -257,7 +258,7 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, { mutex_lock(&kvm->irq_lock); kimn->irq = irq; - hlist_add_head(&kimn->link, &kvm->mask_notifier_list); + hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list); mutex_unlock(&kvm->irq_lock); } @@ -265,8 +266,9 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn) { mutex_lock(&kvm->irq_lock); - hlist_del(&kimn->link); + hlist_del_rcu(&kimn->link); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); } void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) @@ -274,11 +276,11 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) struct kvm_irq_mask_notifier *kimn; struct hlist_node *n; - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - - hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link) + rcu_read_lock(); + hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link) if (kimn->irq == irq) kimn->func(kimn, mask); + rcu_read_unlock(); } void kvm_free_irq_routing(struct kvm *kvm) -- cgit v1.2.3-59-g8ed1b From eba0226bdfffe262e72b8360e4d0d12070e9a0f0 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:25 +0300 Subject: KVM: Move IO APIC to its own lock The allows removal of irq_lock from the injection path. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 7 ++--- arch/x86/kvm/i8259.c | 22 +++++++++---- arch/x86/kvm/lapic.c | 5 +-- arch/x86/kvm/x86.c | 10 ++---- virt/kvm/ioapic.c | 80 ++++++++++++++++++++++++++++++++++++------------ virt/kvm/ioapic.h | 4 +++ virt/kvm/irq_comm.c | 23 ++++++++------ 7 files changed, 100 insertions(+), 51 deletions(-) (limited to 'virt') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 0ad09f05efa9..4a983147f6eb 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -851,8 +851,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -868,9 +867,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index ccc941af4eaf..d057c0cbd245 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -38,7 +38,15 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) s->isr_ack |= (1 << irq); if (s != &s->pics_state->pics[0]) irq += 8; + /* + * We are dropping lock while calling ack notifiers since ack + * notifier callbacks for assigned devices call into PIC recursively. + * Other interrupt may be delivered to PIC while lock is dropped but + * it should be safe since PIC state is already updated at this stage. + */ + spin_unlock(&s->pics_state->lock); kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); + spin_lock(&s->pics_state->lock); } void kvm_pic_clear_isr_ack(struct kvm *kvm) @@ -176,16 +184,18 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) static inline void pic_intack(struct kvm_kpic_state *s, int irq) { s->isr |= 1 << irq; - if (s->auto_eoi) { - if (s->rotate_on_auto_eoi) - s->priority_add = (irq + 1) & 7; - pic_clear_isr(s, irq); - } /* * We don't clear a level sensitive interrupt here */ if (!(s->elcr & (1 << irq))) s->irr &= ~(1 << irq); + + if (s->auto_eoi) { + if (s->rotate_on_auto_eoi) + s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); + } + } int kvm_pic_read_irq(struct kvm *kvm) @@ -294,9 +304,9 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) priority = get_priority(s, s->isr); if (priority != 8) { irq = (priority + s->priority_add) & 7; - pic_clear_isr(s, irq); if (cmd == 5) s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); pic_update_irq(s->pics_state); } break; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 23c217692ea9..df8bcb0f66d8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -471,11 +471,8 @@ static void apic_set_eoi(struct kvm_lapic *apic) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; - if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) { - mutex_lock(&apic->vcpu->kvm->irq_lock); + if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); - mutex_unlock(&apic->vcpu->kvm->irq_lock); - } } static void apic_send_ipi(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1687d12b122a..fdf989f17a61 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2038,9 +2038,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2070,11 +2068,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: - mutex_lock(&kvm->irq_lock); - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - mutex_unlock(&kvm->irq_lock); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 9fe140bb38ec..38a2d20b89de 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -182,6 +182,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) union kvm_ioapic_redirect_entry entry; int ret = 1; + mutex_lock(&ioapic->lock); if (irq >= 0 && irq < IOAPIC_NUM_PINS) { entry = ioapic->redirtbl[irq]; level ^= entry.fields.polarity; @@ -198,34 +199,51 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) } trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); } + mutex_unlock(&ioapic->lock); + return ret; } -static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin, - int trigger_mode) +static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, + int trigger_mode) { - union kvm_ioapic_redirect_entry *ent; + int i; + + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; - ent = &ioapic->redirtbl[pin]; + if (ent->fields.vector != vector) + continue; - kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin); + /* + * We are dropping lock while calling ack notifiers because ack + * notifier callbacks for assigned devices call into IOAPIC + * recursively. Since remote_irr is cleared only after call + * to notifiers if the same vector will be delivered while lock + * is dropped it will be put into irr and will be delivered + * after ack notifier returns. + */ + mutex_unlock(&ioapic->lock); + kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); + mutex_lock(&ioapic->lock); + + if (trigger_mode != IOAPIC_LEVEL_TRIG) + continue; - if (trigger_mode == IOAPIC_LEVEL_TRIG) { ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << pin))) - ioapic_service(ioapic, pin); + if (!ent->fields.mask && (ioapic->irr & (1 << i))) + ioapic_service(ioapic, i); } } void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; - int i; - for (i = 0; i < IOAPIC_NUM_PINS; i++) - if (ioapic->redirtbl[i].fields.vector == vector) - __kvm_ioapic_update_eoi(ioapic, i, trigger_mode); + mutex_lock(&ioapic->lock); + __kvm_ioapic_update_eoi(ioapic, vector, trigger_mode); + mutex_unlock(&ioapic->lock); } static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev) @@ -250,8 +268,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, ioapic_debug("addr %lx\n", (unsigned long)addr); ASSERT(!(addr & 0xf)); /* check alignment */ - mutex_lock(&ioapic->kvm->irq_lock); addr &= 0xff; + mutex_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: result = ioapic->ioregsel; @@ -265,6 +283,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, result = 0; break; } + mutex_unlock(&ioapic->lock); + switch (len) { case 8: *(u64 *) val = result; @@ -277,7 +297,6 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, default: printk(KERN_WARNING "ioapic: wrong length %d\n", len); } - mutex_unlock(&ioapic->kvm->irq_lock); return 0; } @@ -293,15 +312,15 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, (void*)addr, len, val); ASSERT(!(addr & 0xf)); /* check alignment */ - mutex_lock(&ioapic->kvm->irq_lock); if (len == 4 || len == 8) data = *(u32 *) val; else { printk(KERN_WARNING "ioapic: Unsupported size %d\n", len); - goto unlock; + return 0; } addr &= 0xff; + mutex_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: ioapic->ioregsel = data; @@ -312,15 +331,14 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, break; #ifdef CONFIG_IA64 case IOAPIC_REG_EOI: - kvm_ioapic_update_eoi(ioapic->kvm, data, IOAPIC_LEVEL_TRIG); + __kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG); break; #endif default: break; } -unlock: - mutex_unlock(&ioapic->kvm->irq_lock); + mutex_unlock(&ioapic->lock); return 0; } @@ -349,6 +367,7 @@ int kvm_ioapic_init(struct kvm *kvm) ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); if (!ioapic) return -ENOMEM; + mutex_init(&ioapic->lock); kvm->arch.vioapic = ioapic; kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); @@ -360,3 +379,26 @@ int kvm_ioapic_init(struct kvm *kvm) return ret; } +int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +{ + struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + if (!ioapic) + return -EINVAL; + + mutex_lock(&ioapic->lock); + memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&ioapic->lock); + return 0; +} + +int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +{ + struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + if (!ioapic) + return -EINVAL; + + mutex_lock(&ioapic->lock); + memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&ioapic->lock); + return 0; +} diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 6e461ade6365..419c43b667ab 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -45,6 +45,7 @@ struct kvm_ioapic { struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); + struct mutex lock; }; #ifdef DEBUG @@ -74,4 +75,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq); +int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); + #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 6c946141dbcc..fadf4408a820 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -146,8 +146,8 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, */ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) { - struct kvm_kernel_irq_routing_entry *e; - int ret = -1; + struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; + int ret = -1, i = 0; struct kvm_irq_routing_table *irq_rt; struct hlist_node *n; @@ -162,14 +162,19 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) rcu_read_lock(); irq_rt = rcu_dereference(kvm->irq_routing); if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { - int r = e->set(e, kvm, irq_source_id, level); - if (r < 0) - continue; - - ret = r + ((ret < 0) ? 0 : ret); - } + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) + irq_set[i++] = *e; rcu_read_unlock(); + + while(i--) { + int r; + r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level); + if (r < 0) + continue; + + ret = r + ((ret < 0) ? 0 : ret); + } + return ret; } -- cgit v1.2.3-59-g8ed1b From 680b3648ba89c44ac8d0316f78a0d6e147b88809 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:26 +0300 Subject: KVM: Drop kvm->irq_lock lock from irq injection path The only thing it protects now is interrupt injection into lapic and this can work lockless. Even now with kvm->irq_lock in place access to lapic is not entirely serialized since vcpu access doesn't take kvm->irq_lock. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 2 -- arch/x86/kvm/i8254.c | 2 -- arch/x86/kvm/lapic.c | 2 -- arch/x86/kvm/x86.c | 2 -- virt/kvm/eventfd.c | 2 -- virt/kvm/irq_comm.c | 6 +----- virt/kvm/kvm_main.c | 2 -- 7 files changed, 1 insertion(+), 17 deletions(-) (limited to 'virt') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 4a983147f6eb..f534e0f6bb0d 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -982,10 +982,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 144e7f60b5e2..fab7440c9bb2 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -688,10 +688,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm) struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - mutex_unlock(&kvm->irq_lock); /* * Provides NMI watchdog support via Virtual Wire mode. diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index df8bcb0f66d8..8787637b1a9c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -501,9 +501,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); - mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); - mutex_unlock(&apic->vcpu->kvm->irq_lock); } static u32 apic_get_tmcct(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fdf989f17a61..5beb4c16caab 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2286,10 +2286,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index bb4ebd89b9ff..30f70fd511c4 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -61,10 +61,8 @@ irqfd_inject(struct work_struct *work) struct _irqfd *irqfd = container_of(work, struct _irqfd, inject); struct kvm *kvm = irqfd->kvm; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); - mutex_unlock(&kvm->irq_lock); } /* diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index fadf4408a820..15a83b93566d 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -82,8 +82,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, int i, r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - if (irq->dest_mode == 0 && irq->dest_id == 0xff && kvm_is_dm_lowest_prio(irq)) printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); @@ -138,7 +136,7 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq); } -/* This should be called with the kvm->irq_lock mutex held +/* * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) * = 0 Interrupt was coalesced (previous irq is still pending) @@ -153,8 +151,6 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) trace_kvm_set_irq(irq, level, irq_source_id); - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6eca153e1a02..c12c95b1b641 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -137,7 +137,6 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) interrupt_work); kvm = assigned_dev->kvm; - mutex_lock(&kvm->irq_lock); spin_lock_irq(&assigned_dev->assigned_dev_lock); if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { struct kvm_guest_msix_entry *guest_entries = @@ -156,7 +155,6 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) assigned_dev->guest_irq, 1); spin_unlock_irq(&assigned_dev->assigned_dev_lock); - mutex_unlock(&assigned_dev->kvm->irq_lock); } static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) -- cgit v1.2.3-59-g8ed1b From bfd99ff5d483b11c32bca49fbff7a5ac59038b0a Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 26 Aug 2009 14:57:50 +0300 Subject: KVM: Move assigned device code to own file Signed-off-by: Avi Kivity --- arch/ia64/kvm/Makefile | 2 +- arch/x86/kvm/Makefile | 3 +- include/linux/kvm_host.h | 17 + virt/kvm/assigned-dev.c | 818 +++++++++++++++++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 798 +-------------------------------------------- 5 files changed, 840 insertions(+), 798 deletions(-) create mode 100644 virt/kvm/assigned-dev.c (limited to 'virt') diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile index 0bb99b732908..1089b3e918ac 100644 --- a/arch/ia64/kvm/Makefile +++ b/arch/ia64/kvm/Makefile @@ -49,7 +49,7 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/ EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o) + coalesced_mmio.o irq_comm.o assigned-dev.o) ifeq ($(CONFIG_IOMMU_API),y) common-objs += $(addprefix ../../../virt/kvm/, iommu.o) diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 0e7fe78d0f74..31a7035c4bd9 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -6,7 +6,8 @@ CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o) + coalesced_mmio.o irq_comm.o eventfd.o \ + assigned-dev.o) kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4aa5e1d9a797..c0a1cc35f080 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -577,4 +577,21 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id; } #endif + +#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT + +long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg); + +#else + +static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + #endif + +#endif + diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c new file mode 100644 index 000000000000..fd9c097b760a --- /dev/null +++ b/virt/kvm/assigned-dev.c @@ -0,0 +1,818 @@ +/* + * Kernel-based Virtual Machine - device assignment support + * + * Copyright (C) 2006-9 Red Hat, Inc + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "irq.h" + +static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, + int assigned_dev_id) +{ + struct list_head *ptr; + struct kvm_assigned_dev_kernel *match; + + list_for_each(ptr, head) { + match = list_entry(ptr, struct kvm_assigned_dev_kernel, list); + if (match->assigned_dev_id == assigned_dev_id) + return match; + } + return NULL; +} + +static int find_index_from_host_irq(struct kvm_assigned_dev_kernel + *assigned_dev, int irq) +{ + int i, index; + struct msix_entry *host_msix_entries; + + host_msix_entries = assigned_dev->host_msix_entries; + + index = -1; + for (i = 0; i < assigned_dev->entries_nr; i++) + if (irq == host_msix_entries[i].vector) { + index = i; + break; + } + if (index < 0) { + printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); + return 0; + } + + return index; +} + +static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) +{ + struct kvm_assigned_dev_kernel *assigned_dev; + struct kvm *kvm; + int i; + + assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, + interrupt_work); + kvm = assigned_dev->kvm; + + spin_lock_irq(&assigned_dev->assigned_dev_lock); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + struct kvm_guest_msix_entry *guest_entries = + assigned_dev->guest_msix_entries; + for (i = 0; i < assigned_dev->entries_nr; i++) { + if (!(guest_entries[i].flags & + KVM_ASSIGNED_MSIX_PENDING)) + continue; + guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; + kvm_set_irq(assigned_dev->kvm, + assigned_dev->irq_source_id, + guest_entries[i].vector, 1); + } + } else + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + + spin_unlock_irq(&assigned_dev->assigned_dev_lock); +} + +static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) +{ + unsigned long flags; + struct kvm_assigned_dev_kernel *assigned_dev = + (struct kvm_assigned_dev_kernel *) dev_id; + + spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int index = find_index_from_host_irq(assigned_dev, irq); + if (index < 0) + goto out; + assigned_dev->guest_msix_entries[index].flags |= + KVM_ASSIGNED_MSIX_PENDING; + } + + schedule_work(&assigned_dev->interrupt_work); + + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { + disable_irq_nosync(irq); + assigned_dev->host_irq_disabled = true; + } + +out: + spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); + return IRQ_HANDLED; +} + +/* Ack the irq line for an assigned device */ +static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) +{ + struct kvm_assigned_dev_kernel *dev; + unsigned long flags; + + if (kian->gsi == -1) + return; + + dev = container_of(kian, struct kvm_assigned_dev_kernel, + ack_notifier); + + kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); + + /* The guest irq may be shared so this ack may be + * from another device. + */ + spin_lock_irqsave(&dev->assigned_dev_lock, flags); + if (dev->host_irq_disabled) { + enable_irq(dev->host_irq); + dev->host_irq_disabled = false; + } + spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); +} + +static void deassign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); + assigned_dev->ack_notifier.gsi = -1; + + if (assigned_dev->irq_source_id != -1) + kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); + assigned_dev->irq_source_id = -1; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); +} + +/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ +static void deassign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + /* + * In kvm_free_device_irq, cancel_work_sync return true if: + * 1. work is scheduled, and then cancelled. + * 2. work callback is executed. + * + * The first one ensured that the irq is disabled and no more events + * would happen. But for the second one, the irq may be enabled (e.g. + * for MSI). So we disable irq here to prevent further events. + * + * Notice this maybe result in nested disable if the interrupt type is + * INTx, but it's OK for we are going to free it. + * + * If this function is a part of VM destroy, please ensure that till + * now, the kvm state is still legal for probably we also have to wait + * interrupt_work done. + */ + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int i; + for (i = 0; i < assigned_dev->entries_nr; i++) + disable_irq_nosync(assigned_dev-> + host_msix_entries[i].vector); + + cancel_work_sync(&assigned_dev->interrupt_work); + + for (i = 0; i < assigned_dev->entries_nr; i++) + free_irq(assigned_dev->host_msix_entries[i].vector, + (void *)assigned_dev); + + assigned_dev->entries_nr = 0; + kfree(assigned_dev->host_msix_entries); + kfree(assigned_dev->guest_msix_entries); + pci_disable_msix(assigned_dev->dev); + } else { + /* Deal with MSI and INTx */ + disable_irq_nosync(assigned_dev->host_irq); + cancel_work_sync(&assigned_dev->interrupt_work); + + free_irq(assigned_dev->host_irq, (void *)assigned_dev); + + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) + pci_disable_msi(assigned_dev->dev); + } + + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); +} + +static int kvm_deassign_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev, + unsigned long irq_requested_type) +{ + unsigned long guest_irq_type, host_irq_type; + + if (!irqchip_in_kernel(kvm)) + return -EINVAL; + /* no irq assignment to deassign */ + if (!assigned_dev->irq_requested_type) + return -ENXIO; + + host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; + guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; + + if (host_irq_type) + deassign_host_irq(kvm, assigned_dev); + if (guest_irq_type) + deassign_guest_irq(kvm, assigned_dev); + + return 0; +} + +static void kvm_free_assigned_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); +} + +static void kvm_free_assigned_device(struct kvm *kvm, + struct kvm_assigned_dev_kernel + *assigned_dev) +{ + kvm_free_assigned_irq(kvm, assigned_dev); + + pci_reset_function(assigned_dev->dev); + + pci_release_regions(assigned_dev->dev); + pci_disable_device(assigned_dev->dev); + pci_dev_put(assigned_dev->dev); + + list_del(&assigned_dev->list); + kfree(assigned_dev); +} + +void kvm_free_all_assigned_devices(struct kvm *kvm) +{ + struct list_head *ptr, *ptr2; + struct kvm_assigned_dev_kernel *assigned_dev; + + list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) { + assigned_dev = list_entry(ptr, + struct kvm_assigned_dev_kernel, + list); + + kvm_free_assigned_device(kvm, assigned_dev); + } +} + +static int assigned_device_enable_host_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + dev->host_irq = dev->dev->irq; + /* Even though this is PCI, we don't want to use shared + * interrupts. Sharing host devices with guest-assigned devices + * on the same interrupt line is not a happy situation: there + * are going to be long delays in accepting, acking, etc. + */ + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, + 0, "kvm_assigned_intx_device", (void *)dev)) + return -EIO; + return 0; +} + +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_host_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int r; + + if (!dev->dev->msi_enabled) { + r = pci_enable_msi(dev->dev); + if (r) + return r; + } + + dev->host_irq = dev->dev->irq; + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, + "kvm_assigned_msi_device", (void *)dev)) { + pci_disable_msi(dev->dev); + return -EIO; + } + + return 0; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_host_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int i, r = -EINVAL; + + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (dev->entries_nr == 0) + return r; + + r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + if (r) + return r; + + for (i = 0; i < dev->entries_nr; i++) { + r = request_irq(dev->host_msix_entries[i].vector, + kvm_assigned_dev_intr, 0, + "kvm_assigned_msix_device", + (void *)dev); + /* FIXME: free requested_irq's on failure */ + if (r) + return r; + } + + return 0; +} + +#endif + +static int assigned_device_enable_guest_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = irq->guest_irq; + return 0; +} + +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_guest_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + dev->host_irq_disabled = false; + return 0; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_guest_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + dev->host_irq_disabled = false; + return 0; +} +#endif + +static int assign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + __u32 host_irq_type) +{ + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) + return r; + + switch (host_irq_type) { + case KVM_DEV_IRQ_HOST_INTX: + r = assigned_device_enable_host_intx(kvm, dev); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_HOST_MSI: + r = assigned_device_enable_host_msi(kvm, dev); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_HOST_MSIX: + r = assigned_device_enable_host_msix(kvm, dev); + break; +#endif + default: + r = -EINVAL; + } + + if (!r) + dev->irq_requested_type |= host_irq_type; + + return r; +} + +static int assign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq, + unsigned long guest_irq_type) +{ + int id; + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) + return r; + + id = kvm_request_irq_source_id(kvm); + if (id < 0) + return id; + + dev->irq_source_id = id; + + switch (guest_irq_type) { + case KVM_DEV_IRQ_GUEST_INTX: + r = assigned_device_enable_guest_intx(kvm, dev, irq); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_GUEST_MSI: + r = assigned_device_enable_guest_msi(kvm, dev, irq); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_GUEST_MSIX: + r = assigned_device_enable_guest_msix(kvm, dev, irq); + break; +#endif + default: + r = -EINVAL; + } + + if (!r) { + dev->irq_requested_type |= guest_irq_type; + kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); + } else + kvm_free_irq_source_id(kvm, dev->irq_source_id); + + return r; +} + +/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ +static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, + struct kvm_assigned_irq *assigned_irq) +{ + int r = -EINVAL; + struct kvm_assigned_dev_kernel *match; + unsigned long host_irq_type, guest_irq_type; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + if (!irqchip_in_kernel(kvm)) + return r; + + mutex_lock(&kvm->lock); + r = -ENODEV; + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); + guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); + + r = -EINVAL; + /* can only assign one type at a time */ + if (hweight_long(host_irq_type) > 1) + goto out; + if (hweight_long(guest_irq_type) > 1) + goto out; + if (host_irq_type == 0 && guest_irq_type == 0) + goto out; + + r = 0; + if (host_irq_type) + r = assign_host_irq(kvm, match, host_irq_type); + if (r) + goto out; + + if (guest_irq_type) + r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, + struct kvm_assigned_irq + *assigned_irq) +{ + int r = -ENODEV; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + r = kvm_deassign_irq(kvm, match, assigned_irq->flags); +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_assign_device(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + struct pci_dev *dev; + + down_read(&kvm->slots_lock); + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (match) { + /* device already assigned */ + r = -EEXIST; + goto out; + } + + match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); + if (match == NULL) { + printk(KERN_INFO "%s: Couldn't allocate memory\n", + __func__); + r = -ENOMEM; + goto out; + } + dev = pci_get_bus_and_slot(assigned_dev->busnr, + assigned_dev->devfn); + if (!dev) { + printk(KERN_INFO "%s: host device not found\n", __func__); + r = -EINVAL; + goto out_free; + } + if (pci_enable_device(dev)) { + printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); + r = -EBUSY; + goto out_put; + } + r = pci_request_regions(dev, "kvm_assigned_device"); + if (r) { + printk(KERN_INFO "%s: Could not get access to device regions\n", + __func__); + goto out_disable; + } + + pci_reset_function(dev); + + match->assigned_dev_id = assigned_dev->assigned_dev_id; + match->host_busnr = assigned_dev->busnr; + match->host_devfn = assigned_dev->devfn; + match->flags = assigned_dev->flags; + match->dev = dev; + spin_lock_init(&match->assigned_dev_lock); + match->irq_source_id = -1; + match->kvm = kvm; + match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; + INIT_WORK(&match->interrupt_work, + kvm_assigned_dev_interrupt_work_handler); + + list_add(&match->list, &kvm->arch.assigned_dev_head); + + if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { + if (!kvm->arch.iommu_domain) { + r = kvm_iommu_map_guest(kvm); + if (r) + goto out_list_del; + } + r = kvm_assign_device(kvm, match); + if (r) + goto out_list_del; + } + +out: + mutex_unlock(&kvm->lock); + up_read(&kvm->slots_lock); + return r; +out_list_del: + list_del(&match->list); + pci_release_regions(dev); +out_disable: + pci_disable_device(dev); +out_put: + pci_dev_put(dev); +out_free: + kfree(match); + mutex_unlock(&kvm->lock); + up_read(&kvm->slots_lock); + return r; +} + +static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (!match) { + printk(KERN_INFO "%s: device hasn't been assigned before, " + "so cannot be deassigned\n", __func__); + r = -EINVAL; + goto out; + } + + if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) + kvm_deassign_device(kvm, match); + + kvm_free_assigned_device(kvm, match); + +out: + mutex_unlock(&kvm->lock); + return r; +} + + +#ifdef __KVM_HAVE_MSIX +static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, + struct kvm_assigned_msix_nr *entry_nr) +{ + int r = 0; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry_nr->assigned_dev_id); + if (!adev) { + r = -EINVAL; + goto msix_nr_out; + } + + if (adev->entries_nr == 0) { + adev->entries_nr = entry_nr->entry_nr; + if (adev->entries_nr == 0 || + adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { + r = -EINVAL; + goto msix_nr_out; + } + + adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * + entry_nr->entry_nr, + GFP_KERNEL); + if (!adev->host_msix_entries) { + r = -ENOMEM; + goto msix_nr_out; + } + adev->guest_msix_entries = kzalloc( + sizeof(struct kvm_guest_msix_entry) * + entry_nr->entry_nr, GFP_KERNEL); + if (!adev->guest_msix_entries) { + kfree(adev->host_msix_entries); + r = -ENOMEM; + goto msix_nr_out; + } + } else /* Not allowed set MSI-X number twice */ + r = -EINVAL; +msix_nr_out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, + struct kvm_assigned_msix_entry *entry) +{ + int r = 0, i; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry->assigned_dev_id); + + if (!adev) { + r = -EINVAL; + goto msix_entry_out; + } + + for (i = 0; i < adev->entries_nr; i++) + if (adev->guest_msix_entries[i].vector == 0 || + adev->guest_msix_entries[i].entry == entry->entry) { + adev->guest_msix_entries[i].entry = entry->entry; + adev->guest_msix_entries[i].vector = entry->gsi; + adev->host_msix_entries[i].entry = entry->entry; + break; + } + if (i == adev->entries_nr) { + r = -ENOSPC; + goto msix_entry_out; + } + +msix_entry_out: + mutex_unlock(&kvm->lock); + + return r; +} +#endif + +long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + int r = -ENOTTY; + + switch (ioctl) { + case KVM_ASSIGN_PCI_DEVICE: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); + if (r) + goto out; + break; + } + case KVM_ASSIGN_IRQ: { + r = -EOPNOTSUPP; + break; + } +#ifdef KVM_CAP_ASSIGN_DEV_IRQ + case KVM_ASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } + case KVM_DEASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } +#endif +#ifdef KVM_CAP_DEVICE_DEASSIGNMENT + case KVM_DEASSIGN_PCI_DEVICE: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); + if (r) + goto out; + break; + } +#endif +#ifdef KVM_CAP_IRQ_ROUTING + case KVM_SET_GSI_ROUTING: { + struct kvm_irq_routing routing; + struct kvm_irq_routing __user *urouting; + struct kvm_irq_routing_entry *entries; + + r = -EFAULT; + if (copy_from_user(&routing, argp, sizeof(routing))) + goto out; + r = -EINVAL; + if (routing.nr >= KVM_MAX_IRQ_ROUTES) + goto out; + if (routing.flags) + goto out; + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + r = kvm_set_irq_routing(kvm, entries, routing.nr, + routing.flags); + out_free_irq_routing: + vfree(entries); + break; + } +#endif /* KVM_CAP_IRQ_ROUTING */ +#ifdef __KVM_HAVE_MSIX + case KVM_ASSIGN_SET_MSIX_NR: { + struct kvm_assigned_msix_nr entry_nr; + r = -EFAULT; + if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) + goto out; + r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); + if (r) + goto out; + break; + } + case KVM_ASSIGN_SET_MSIX_ENTRY: { + struct kvm_assigned_msix_entry entry; + r = -EFAULT; + if (copy_from_user(&entry, argp, sizeof entry)) + goto out; + r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); + if (r) + goto out; + break; + } +#endif + } +out: + return r; +} + diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c12c95b1b641..38e4d2c34ac1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -53,12 +53,6 @@ #include "coalesced_mmio.h" #endif -#ifdef KVM_CAP_DEVICE_ASSIGNMENT -#include -#include -#include "irq.h" -#endif - #define CREATE_TRACE_POINTS #include @@ -90,608 +84,6 @@ static bool kvm_rebooting; static bool largepages_enabled = true; -#ifdef KVM_CAP_DEVICE_ASSIGNMENT -static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, - int assigned_dev_id) -{ - struct list_head *ptr; - struct kvm_assigned_dev_kernel *match; - - list_for_each(ptr, head) { - match = list_entry(ptr, struct kvm_assigned_dev_kernel, list); - if (match->assigned_dev_id == assigned_dev_id) - return match; - } - return NULL; -} - -static int find_index_from_host_irq(struct kvm_assigned_dev_kernel - *assigned_dev, int irq) -{ - int i, index; - struct msix_entry *host_msix_entries; - - host_msix_entries = assigned_dev->host_msix_entries; - - index = -1; - for (i = 0; i < assigned_dev->entries_nr; i++) - if (irq == host_msix_entries[i].vector) { - index = i; - break; - } - if (index < 0) { - printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); - return 0; - } - - return index; -} - -static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) -{ - struct kvm_assigned_dev_kernel *assigned_dev; - struct kvm *kvm; - int i; - - assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, - interrupt_work); - kvm = assigned_dev->kvm; - - spin_lock_irq(&assigned_dev->assigned_dev_lock); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - struct kvm_guest_msix_entry *guest_entries = - assigned_dev->guest_msix_entries; - for (i = 0; i < assigned_dev->entries_nr; i++) { - if (!(guest_entries[i].flags & - KVM_ASSIGNED_MSIX_PENDING)) - continue; - guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; - kvm_set_irq(assigned_dev->kvm, - assigned_dev->irq_source_id, - guest_entries[i].vector, 1); - } - } else - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - - spin_unlock_irq(&assigned_dev->assigned_dev_lock); -} - -static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) -{ - unsigned long flags; - struct kvm_assigned_dev_kernel *assigned_dev = - (struct kvm_assigned_dev_kernel *) dev_id; - - spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int index = find_index_from_host_irq(assigned_dev, irq); - if (index < 0) - goto out; - assigned_dev->guest_msix_entries[index].flags |= - KVM_ASSIGNED_MSIX_PENDING; - } - - schedule_work(&assigned_dev->interrupt_work); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { - disable_irq_nosync(irq); - assigned_dev->host_irq_disabled = true; - } - -out: - spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); - return IRQ_HANDLED; -} - -/* Ack the irq line for an assigned device */ -static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) -{ - struct kvm_assigned_dev_kernel *dev; - unsigned long flags; - - if (kian->gsi == -1) - return; - - dev = container_of(kian, struct kvm_assigned_dev_kernel, - ack_notifier); - - kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); - - /* The guest irq may be shared so this ack may be - * from another device. - */ - spin_lock_irqsave(&dev->assigned_dev_lock, flags); - if (dev->host_irq_disabled) { - enable_irq(dev->host_irq); - dev->host_irq_disabled = false; - } - spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); -} - -static void deassign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); - assigned_dev->ack_notifier.gsi = -1; - - if (assigned_dev->irq_source_id != -1) - kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); - assigned_dev->irq_source_id = -1; - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); -} - -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void deassign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - /* - * In kvm_free_device_irq, cancel_work_sync return true if: - * 1. work is scheduled, and then cancelled. - * 2. work callback is executed. - * - * The first one ensured that the irq is disabled and no more events - * would happen. But for the second one, the irq may be enabled (e.g. - * for MSI). So we disable irq here to prevent further events. - * - * Notice this maybe result in nested disable if the interrupt type is - * INTx, but it's OK for we are going to free it. - * - * If this function is a part of VM destroy, please ensure that till - * now, the kvm state is still legal for probably we also have to wait - * interrupt_work done. - */ - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int i; - for (i = 0; i < assigned_dev->entries_nr; i++) - disable_irq_nosync(assigned_dev-> - host_msix_entries[i].vector); - - cancel_work_sync(&assigned_dev->interrupt_work); - - for (i = 0; i < assigned_dev->entries_nr; i++) - free_irq(assigned_dev->host_msix_entries[i].vector, - (void *)assigned_dev); - - assigned_dev->entries_nr = 0; - kfree(assigned_dev->host_msix_entries); - kfree(assigned_dev->guest_msix_entries); - pci_disable_msix(assigned_dev->dev); - } else { - /* Deal with MSI and INTx */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); - - free_irq(assigned_dev->host_irq, (void *)assigned_dev); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) - pci_disable_msi(assigned_dev->dev); - } - - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); -} - -static int kvm_deassign_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev, - unsigned long irq_requested_type) -{ - unsigned long guest_irq_type, host_irq_type; - - if (!irqchip_in_kernel(kvm)) - return -EINVAL; - /* no irq assignment to deassign */ - if (!assigned_dev->irq_requested_type) - return -ENXIO; - - host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; - guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; - - if (host_irq_type) - deassign_host_irq(kvm, assigned_dev); - if (guest_irq_type) - deassign_guest_irq(kvm, assigned_dev); - - return 0; -} - -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); -} - -static void kvm_free_assigned_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel - *assigned_dev) -{ - kvm_free_assigned_irq(kvm, assigned_dev); - - pci_reset_function(assigned_dev->dev); - - pci_release_regions(assigned_dev->dev); - pci_disable_device(assigned_dev->dev); - pci_dev_put(assigned_dev->dev); - - list_del(&assigned_dev->list); - kfree(assigned_dev); -} - -void kvm_free_all_assigned_devices(struct kvm *kvm) -{ - struct list_head *ptr, *ptr2; - struct kvm_assigned_dev_kernel *assigned_dev; - - list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) { - assigned_dev = list_entry(ptr, - struct kvm_assigned_dev_kernel, - list); - - kvm_free_assigned_device(kvm, assigned_dev); - } -} - -static int assigned_device_enable_host_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - dev->host_irq = dev->dev->irq; - /* Even though this is PCI, we don't want to use shared - * interrupts. Sharing host devices with guest-assigned devices - * on the same interrupt line is not a happy situation: there - * are going to be long delays in accepting, acking, etc. - */ - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)dev)) - return -EIO; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_host_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int r; - - if (!dev->dev->msi_enabled) { - r = pci_enable_msi(dev->dev); - if (r) - return r; - } - - dev->host_irq = dev->dev->irq; - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)dev)) { - pci_disable_msi(dev->dev); - return -EIO; - } - - return 0; -} -#endif - -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_host_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int i, r = -EINVAL; - - /* host_msix_entries and guest_msix_entries should have been - * initialized */ - if (dev->entries_nr == 0) - return r; - - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); - if (r) - return r; - - for (i = 0; i < dev->entries_nr; i++) { - r = request_irq(dev->host_msix_entries[i].vector, - kvm_assigned_dev_intr, 0, - "kvm_assigned_msix_device", - (void *)dev); - /* FIXME: free requested_irq's on failure */ - if (r) - return r; - } - - return 0; -} - -#endif - -static int assigned_device_enable_guest_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = irq->guest_irq; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_guest_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; - return 0; -} -#endif -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_guest_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; - return 0; -} -#endif - -static int assign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - __u32 host_irq_type) -{ - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) - return r; - - switch (host_irq_type) { - case KVM_DEV_IRQ_HOST_INTX: - r = assigned_device_enable_host_intx(kvm, dev); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_HOST_MSI: - r = assigned_device_enable_host_msi(kvm, dev); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_HOST_MSIX: - r = assigned_device_enable_host_msix(kvm, dev); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) - dev->irq_requested_type |= host_irq_type; - - return r; -} - -static int assign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq, - unsigned long guest_irq_type) -{ - int id; - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) - return r; - - id = kvm_request_irq_source_id(kvm); - if (id < 0) - return id; - - dev->irq_source_id = id; - - switch (guest_irq_type) { - case KVM_DEV_IRQ_GUEST_INTX: - r = assigned_device_enable_guest_intx(kvm, dev, irq); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_GUEST_MSI: - r = assigned_device_enable_guest_msi(kvm, dev, irq); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_GUEST_MSIX: - r = assigned_device_enable_guest_msix(kvm, dev, irq); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) { - dev->irq_requested_type |= guest_irq_type; - kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); - } else - kvm_free_irq_source_id(kvm, dev->irq_source_id); - - return r; -} - -/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ -static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq *assigned_irq) -{ - int r = -EINVAL; - struct kvm_assigned_dev_kernel *match; - unsigned long host_irq_type, guest_irq_type; - - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - - if (!irqchip_in_kernel(kvm)) - return r; - - mutex_lock(&kvm->lock); - r = -ENODEV; - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); - guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - - r = -EINVAL; - /* can only assign one type at a time */ - if (hweight_long(host_irq_type) > 1) - goto out; - if (hweight_long(guest_irq_type) > 1) - goto out; - if (host_irq_type == 0 && guest_irq_type == 0) - goto out; - - r = 0; - if (host_irq_type) - r = assign_host_irq(kvm, match, host_irq_type); - if (r) - goto out; - - if (guest_irq_type) - r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) -{ - int r = -ENODEV; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - r = kvm_deassign_irq(kvm, match, assigned_irq->flags); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_assign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - struct pci_dev *dev; - - down_read(&kvm->slots_lock); - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (match) { - /* device already assigned */ - r = -EEXIST; - goto out; - } - - match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); - if (match == NULL) { - printk(KERN_INFO "%s: Couldn't allocate memory\n", - __func__); - r = -ENOMEM; - goto out; - } - dev = pci_get_bus_and_slot(assigned_dev->busnr, - assigned_dev->devfn); - if (!dev) { - printk(KERN_INFO "%s: host device not found\n", __func__); - r = -EINVAL; - goto out_free; - } - if (pci_enable_device(dev)) { - printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); - r = -EBUSY; - goto out_put; - } - r = pci_request_regions(dev, "kvm_assigned_device"); - if (r) { - printk(KERN_INFO "%s: Could not get access to device regions\n", - __func__); - goto out_disable; - } - - pci_reset_function(dev); - - match->assigned_dev_id = assigned_dev->assigned_dev_id; - match->host_busnr = assigned_dev->busnr; - match->host_devfn = assigned_dev->devfn; - match->flags = assigned_dev->flags; - match->dev = dev; - spin_lock_init(&match->assigned_dev_lock); - match->irq_source_id = -1; - match->kvm = kvm; - match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); - - list_add(&match->list, &kvm->arch.assigned_dev_head); - - if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match); - if (r) - goto out_list_del; - } - -out: - mutex_unlock(&kvm->lock); - up_read(&kvm->slots_lock); - return r; -out_list_del: - list_del(&match->list); - pci_release_regions(dev); -out_disable: - pci_disable_device(dev); -out_put: - pci_dev_put(dev); -out_free: - kfree(match); - mutex_unlock(&kvm->lock); - up_read(&kvm->slots_lock); - return r; -} -#endif - -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT -static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (!match) { - printk(KERN_INFO "%s: device hasn't been assigned before, " - "so cannot be deassigned\n", __func__); - r = -EINVAL; - goto out; - } - - if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) - kvm_deassign_device(kvm, match); - - kvm_free_assigned_device(kvm, match); - -out: - mutex_unlock(&kvm->lock); - return r; -} -#endif - inline int kvm_is_mmio_pfn(pfn_t pfn) { if (pfn_valid(pfn)) { @@ -1824,88 +1216,6 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } -#ifdef __KVM_HAVE_MSIX -static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, - struct kvm_assigned_msix_nr *entry_nr) -{ - int r = 0; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry_nr->assigned_dev_id); - if (!adev) { - r = -EINVAL; - goto msix_nr_out; - } - - if (adev->entries_nr == 0) { - adev->entries_nr = entry_nr->entry_nr; - if (adev->entries_nr == 0 || - adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { - r = -EINVAL; - goto msix_nr_out; - } - - adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * - entry_nr->entry_nr, - GFP_KERNEL); - if (!adev->host_msix_entries) { - r = -ENOMEM; - goto msix_nr_out; - } - adev->guest_msix_entries = kzalloc( - sizeof(struct kvm_guest_msix_entry) * - entry_nr->entry_nr, GFP_KERNEL); - if (!adev->guest_msix_entries) { - kfree(adev->host_msix_entries); - r = -ENOMEM; - goto msix_nr_out; - } - } else /* Not allowed set MSI-X number twice */ - r = -EINVAL; -msix_nr_out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, - struct kvm_assigned_msix_entry *entry) -{ - int r = 0, i; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry->assigned_dev_id); - - if (!adev) { - r = -EINVAL; - goto msix_entry_out; - } - - for (i = 0; i < adev->entries_nr; i++) - if (adev->guest_msix_entries[i].vector == 0 || - adev->guest_msix_entries[i].entry == entry->entry) { - adev->guest_msix_entries[i].entry = entry->entry; - adev->guest_msix_entries[i].vector = entry->gsi; - adev->host_msix_entries[i].entry = entry->entry; - break; - } - if (i == adev->entries_nr) { - r = -ENOSPC; - goto msix_entry_out; - } - -msix_entry_out: - mutex_unlock(&kvm->lock); - - return r; -} -#endif - static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2163,112 +1473,6 @@ static long kvm_vm_ioctl(struct file *filp, r = 0; break; } -#endif -#ifdef KVM_CAP_DEVICE_ASSIGNMENT - case KVM_ASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } - case KVM_ASSIGN_IRQ: { - r = -EOPNOTSUPP; - break; - } -#ifdef KVM_CAP_ASSIGN_DEV_IRQ - case KVM_ASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } - case KVM_DEASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } -#endif -#endif -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT - case KVM_DEASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } -#endif -#ifdef KVM_CAP_IRQ_ROUTING - case KVM_SET_GSI_ROUTING: { - struct kvm_irq_routing routing; - struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; - - r = -EFAULT; - if (copy_from_user(&routing, argp, sizeof(routing))) - goto out; - r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) - goto out; - if (routing.flags) - goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; - r = kvm_set_irq_routing(kvm, entries, routing.nr, - routing.flags); - out_free_irq_routing: - vfree(entries); - break; - } -#endif /* KVM_CAP_IRQ_ROUTING */ -#ifdef __KVM_HAVE_MSIX - case KVM_ASSIGN_SET_MSIX_NR: { - struct kvm_assigned_msix_nr entry_nr; - r = -EFAULT; - if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) - goto out; - r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); - if (r) - goto out; - break; - } - case KVM_ASSIGN_SET_MSIX_ENTRY: { - struct kvm_assigned_msix_entry entry; - r = -EFAULT; - if (copy_from_user(&entry, argp, sizeof entry)) - goto out; - r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); - if (r) - goto out; - break; - } #endif case KVM_IRQFD: { struct kvm_irqfd data; @@ -2301,6 +1505,8 @@ static long kvm_vm_ioctl(struct file *filp, #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); + if (r == -ENOTTY) + r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } out: return r; -- cgit v1.2.3-59-g8ed1b From 10474ae8945ce08622fd1f3464e55bd817bf2376 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 15 Sep 2009 11:37:46 +0200 Subject: KVM: Activate Virtualization On Demand X86 CPUs need to have some magic happening to enable the virtualization extensions on them. This magic can result in unpleasant results for users, like blocking other VMMs from working (vmx) or using invalid TLB entries (svm). Currently KVM activates virtualization when the respective kernel module is loaded. This blocks us from autoloading KVM modules without breaking other VMMs. To circumvent this problem at least a bit, this patch introduces on demand activation of virtualization. This means, that instead virtualization is enabled on creation of the first virtual machine and disabled on destruction of the last one. So using this, KVM can be easily autoloaded, while keeping other hypervisors usable. Signed-off-by: Alexander Graf Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 8 ++-- arch/powerpc/kvm/powerpc.c | 3 +- arch/s390/kvm/kvm-s390.c | 3 +- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm.c | 13 ++++-- arch/x86/kvm/vmx.c | 11 +++-- arch/x86/kvm/x86.c | 4 +- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 90 +++++++++++++++++++++++++++++++++++------ 9 files changed, 108 insertions(+), 28 deletions(-) (limited to 'virt') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index f6471c882667..5fdeec5fddcf 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -124,7 +124,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler) static DEFINE_SPINLOCK(vp_lock); -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { long status; long tmp_base; @@ -137,7 +137,7 @@ void kvm_arch_hardware_enable(void *garbage) slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT); local_irq_restore(saved_psr); if (slot < 0) - return; + return -EINVAL; spin_lock(&vp_lock); status = ia64_pal_vp_init_env(kvm_vsa_base ? @@ -145,7 +145,7 @@ void kvm_arch_hardware_enable(void *garbage) __pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base); if (status != 0) { printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n"); - return ; + return -EINVAL; } if (!kvm_vsa_base) { @@ -154,6 +154,8 @@ void kvm_arch_hardware_enable(void *garbage) } spin_unlock(&vp_lock); ia64_ptr_entry(0x3, slot); + + return 0; } void kvm_arch_hardware_disable(void *garbage) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 95af62217b6b..5902bbc2411e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -78,8 +78,9 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { + return 0; } void kvm_arch_hardware_disable(void *garbage) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 00e2ce8e91f5..544505893c9f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -74,9 +74,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { static unsigned long long *facilities; /* Section: not file related */ -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { /* every s390 is virtualization enabled ;-) */ + return 0; } void kvm_arch_hardware_disable(void *garbage) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a46e2dd9aca8..295c7c4d9c90 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -459,7 +459,7 @@ struct descriptor_table { struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ - void (*hardware_enable)(void *dummy); /* __init */ + int (*hardware_enable)(void *dummy); void (*hardware_disable)(void *dummy); void (*check_processor_compatibility)(void *rtn); int (*hardware_setup)(void); /* __init */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f54c4f9d2865..59fe4d54da11 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -316,7 +316,7 @@ static void svm_hardware_disable(void *garbage) cpu_svm_disable(); } -static void svm_hardware_enable(void *garbage) +static int svm_hardware_enable(void *garbage) { struct svm_cpu_data *svm_data; @@ -325,16 +325,20 @@ static void svm_hardware_enable(void *garbage) struct desc_struct *gdt; int me = raw_smp_processor_id(); + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) + return -EBUSY; + if (!has_svm()) { printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); - return; + return -EINVAL; } svm_data = per_cpu(svm_data, me); if (!svm_data) { printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", me); - return; + return -EINVAL; } svm_data->asid_generation = 1; @@ -345,11 +349,12 @@ static void svm_hardware_enable(void *garbage) gdt = (struct desc_struct *)gdt_descr.base; svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); - rdmsrl(MSR_EFER, efer); wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); + + return 0; } static void svm_cpu_uninit(int cpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 73cb5dd960cf..a187570e4837 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1138,12 +1138,15 @@ static __init int vmx_disabled_by_bios(void) /* locked but not enabled */ } -static void hardware_enable(void *garbage) +static int hardware_enable(void *garbage) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); u64 old; + if (read_cr4() & X86_CR4_VMXE) + return -EBUSY; + INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); if ((old & (FEATURE_CONTROL_LOCKED | @@ -1158,6 +1161,10 @@ static void hardware_enable(void *garbage) asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) : "memory", "cc"); + + ept_sync_global(); + + return 0; } static void vmclear_local_vcpus(void) @@ -4040,8 +4047,6 @@ static int __init vmx_init(void) if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); - ept_sync_global(); - return 0; out3: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 829e3063e2ab..3d83de8bcbf4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4691,9 +4691,9 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) return kvm_x86_ops->vcpu_reset(vcpu); } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { - kvm_x86_ops->hardware_enable(garbage); + return kvm_x86_ops->hardware_enable(garbage); } void kvm_arch_hardware_disable(void *garbage) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c0a1cc35f080..b985a29d8175 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -345,7 +345,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu); -void kvm_arch_hardware_enable(void *garbage); +int kvm_arch_hardware_enable(void *garbage); void kvm_arch_hardware_disable(void *garbage); int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 38e4d2c34ac1..70c8cbea0a99 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -69,6 +69,8 @@ DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; +static int kvm_usage_count = 0; +static atomic_t hardware_enable_failed; struct kmem_cache *kvm_vcpu_cache; EXPORT_SYMBOL_GPL(kvm_vcpu_cache); @@ -79,6 +81,8 @@ struct dentry *kvm_debugfs_dir; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); +static int hardware_enable_all(void); +static void hardware_disable_all(void); static bool kvm_rebooting; @@ -339,6 +343,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { static struct kvm *kvm_create_vm(void) { + int r = 0; struct kvm *kvm = kvm_arch_create_vm(); #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET struct page *page; @@ -346,6 +351,11 @@ static struct kvm *kvm_create_vm(void) if (IS_ERR(kvm)) goto out; + + r = hardware_enable_all(); + if (r) + goto out_err_nodisable; + #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); @@ -354,8 +364,8 @@ static struct kvm *kvm_create_vm(void) #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { - kfree(kvm); - return ERR_PTR(-ENOMEM); + r = -ENOMEM; + goto out_err; } kvm->coalesced_mmio_ring = (struct kvm_coalesced_mmio_ring *)page_address(page); @@ -363,15 +373,13 @@ static struct kvm *kvm_create_vm(void) #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) { - int err; kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; - err = mmu_notifier_register(&kvm->mmu_notifier, current->mm); - if (err) { + r = mmu_notifier_register(&kvm->mmu_notifier, current->mm); + if (r) { #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET put_page(page); #endif - kfree(kvm); - return ERR_PTR(err); + goto out_err; } } #endif @@ -395,6 +403,12 @@ static struct kvm *kvm_create_vm(void) #endif out: return kvm; + +out_err: + hardware_disable_all(); +out_err_nodisable: + kfree(kvm); + return ERR_PTR(r); } /* @@ -453,6 +467,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); + hardware_disable_all(); mmdrop(mm); } @@ -1644,11 +1659,21 @@ static struct miscdevice kvm_dev = { static void hardware_enable(void *junk) { int cpu = raw_smp_processor_id(); + int r; if (cpumask_test_cpu(cpu, cpus_hardware_enabled)) return; + cpumask_set_cpu(cpu, cpus_hardware_enabled); - kvm_arch_hardware_enable(NULL); + + r = kvm_arch_hardware_enable(NULL); + + if (r) { + cpumask_clear_cpu(cpu, cpus_hardware_enabled); + atomic_inc(&hardware_enable_failed); + printk(KERN_INFO "kvm: enabling virtualization on " + "CPU%d failed\n", cpu); + } } static void hardware_disable(void *junk) @@ -1661,11 +1686,52 @@ static void hardware_disable(void *junk) kvm_arch_hardware_disable(NULL); } +static void hardware_disable_all_nolock(void) +{ + BUG_ON(!kvm_usage_count); + + kvm_usage_count--; + if (!kvm_usage_count) + on_each_cpu(hardware_disable, NULL, 1); +} + +static void hardware_disable_all(void) +{ + spin_lock(&kvm_lock); + hardware_disable_all_nolock(); + spin_unlock(&kvm_lock); +} + +static int hardware_enable_all(void) +{ + int r = 0; + + spin_lock(&kvm_lock); + + kvm_usage_count++; + if (kvm_usage_count == 1) { + atomic_set(&hardware_enable_failed, 0); + on_each_cpu(hardware_enable, NULL, 1); + + if (atomic_read(&hardware_enable_failed)) { + hardware_disable_all_nolock(); + r = -EBUSY; + } + } + + spin_unlock(&kvm_lock); + + return r; +} + static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, void *v) { int cpu = (long)v; + if (!kvm_usage_count) + return NOTIFY_OK; + val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: @@ -1868,13 +1934,15 @@ static void kvm_exit_debug(void) static int kvm_suspend(struct sys_device *dev, pm_message_t state) { - hardware_disable(NULL); + if (kvm_usage_count) + hardware_disable(NULL); return 0; } static int kvm_resume(struct sys_device *dev) { - hardware_enable(NULL); + if (kvm_usage_count) + hardware_enable(NULL); return 0; } @@ -1949,7 +2017,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, goto out_free_1; } - on_each_cpu(hardware_enable, NULL, 1); r = register_cpu_notifier(&kvm_cpu_notifier); if (r) goto out_free_2; @@ -1999,7 +2066,6 @@ out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); out_free_2: - on_each_cpu(hardware_disable, NULL, 1); out_free_1: kvm_arch_hardware_unsetup(); out_free_0a: -- cgit v1.2.3-59-g8ed1b From 0c6ddcebd8303ada6faefa6f72ac18b6230320c4 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 25 Sep 2009 09:33:38 +0200 Subject: KVM: fix lock imbalance in kvm_*_irq_source_id() Stanse found 2 lock imbalances in kvm_request_irq_source_id and kvm_free_irq_source_id. They omit to unlock kvm->irq_lock on fail paths. Fix that by adding unlock labels at the end of the functions and jump there from the fail paths. Signed-off-by: Jiri Slaby Cc: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'virt') diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 15a83b93566d..00c68d298579 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -220,11 +220,13 @@ int kvm_request_irq_source_id(struct kvm *kvm) if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); - return -EFAULT; + irq_source_id = -EFAULT; + goto unlock; } ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); set_bit(irq_source_id, bitmap); +unlock: mutex_unlock(&kvm->irq_lock); return irq_source_id; @@ -240,7 +242,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) if (irq_source_id < 0 || irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); - return; + goto unlock; } for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); @@ -251,6 +253,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) #endif } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); +unlock: mutex_unlock(&kvm->irq_lock); } -- cgit v1.2.3-59-g8ed1b From d255f4f2bac81eb798fcf76938147f1f6c756ae2 Mon Sep 17 00:00:00 2001 From: "Zhai, Edwin" Date: Fri, 9 Oct 2009 18:03:20 +0800 Subject: KVM: introduce kvm_vcpu_on_spin Introduce kvm_vcpu_on_spin, to be used by VMX/SVM to yield processing once the cpu detects pause-based looping. Signed-off-by: "Zhai, Edwin" Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'virt') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b985a29d8175..bd5a616d9373 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -286,6 +286,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 70c8cbea0a99..cac69c4415df 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1108,6 +1108,21 @@ void kvm_resched(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_resched); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu) +{ + ktime_t expires; + DEFINE_WAIT(wait); + + prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + + /* Sleep for 100 us, and hope lock-holder got scheduled */ + expires = ktime_add_ns(ktime_get(), 100000UL); + schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); + + finish_wait(&vcpu->wq, &wait); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); + static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vma->vm_file->private_data; -- cgit v1.2.3-59-g8ed1b From cd5a2685de4a642fd0bd763e8c19711ef08dbe27 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Sat, 17 Oct 2009 22:47:23 -0300 Subject: KVM: fix irq_source_id size verification find_first_zero_bit works with bit numbers, not bytes. Fixes https://sourceforge.net/tracker/?func=detail&aid=2847560&group_id=180599&atid=893831 Reported-by: "Xu, Jiajun" Cc: stable@kernel.org Signed-off-by: Marcelo Tosatti --- virt/kvm/irq_comm.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'virt') diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 00c68d298579..0d454d352717 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -215,10 +215,9 @@ int kvm_request_irq_source_id(struct kvm *kvm) int irq_source_id; mutex_lock(&kvm->irq_lock); - irq_source_id = find_first_zero_bit(bitmap, - sizeof(kvm->arch.irq_sources_bitmap)); + irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); - if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + if (irq_source_id >= BITS_PER_LONG) { printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); irq_source_id = -EFAULT; goto unlock; @@ -240,7 +239,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || - irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + irq_source_id >= BITS_PER_LONG) { printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); goto unlock; } -- cgit v1.2.3-59-g8ed1b From 6ff5894cdfe7103083bd15b31002434ccd351039 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Oct 2009 14:19:27 +0200 Subject: KVM: Enable 32bit dirty log pointers on 64bit host With big endian userspace, we can't quite figure out if a pointer is 32 bit (shifted >> 32) or 64 bit when we read a 64 bit pointer. This is what happens with dirty logging. To get the pointer interpreted correctly, we thus need Arnd's patch to implement a compat layer for the ioctl: A better way to do this is to add a separate compat_ioctl() method that converts this for you. Based on initial patch from Arnd Bergmann. Signed-off-by: Arnd Bergmann Signed-off-by: Alexander Graf Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cac69c4415df..bd44fb48ac43 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -1542,6 +1543,52 @@ out: return r; } +#ifdef CONFIG_COMPAT +struct compat_kvm_dirty_log { + __u32 slot; + __u32 padding1; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +static long kvm_vm_compat_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + int r; + + if (kvm->mm != current->mm) + return -EIO; + switch (ioctl) { + case KVM_GET_DIRTY_LOG: { + struct compat_kvm_dirty_log compat_log; + struct kvm_dirty_log log; + + r = -EFAULT; + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + goto out; + log.slot = compat_log.slot; + log.padding1 = compat_log.padding1; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_get_dirty_log(kvm, &log); + if (r) + goto out; + break; + } + default: + r = kvm_vm_ioctl(filp, ioctl, arg); + } + +out: + return r; +} +#endif + static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page[1]; @@ -1576,7 +1623,9 @@ static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma) static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, - .compat_ioctl = kvm_vm_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = kvm_vm_compat_ioctl, +#endif .mmap = kvm_vm_mmap, }; -- cgit v1.2.3-59-g8ed1b From e50212bb51356f0df48d6cce0aae5acf41df336d Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 29 Oct 2009 13:44:17 -0200 Subject: KVM: only clear irq_source_id if irqchip is present Otherwise kvm might attempt to dereference a NULL pointer. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 0d454d352717..9b077342ab54 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -243,6 +243,10 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); goto unlock; } + clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); + if (!irqchip_in_kernel(kvm)) + goto unlock; + for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); if (i >= 16) @@ -251,7 +255,6 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]); #endif } - clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); unlock: mutex_unlock(&kvm->irq_lock); } -- cgit v1.2.3-59-g8ed1b From a9c7399d6cda0a092b347f8ee49bbe44f6e1fe66 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 4 Nov 2009 11:54:59 +0200 Subject: KVM: Allow internal errors reported to userspace to carry extra data Usually userspace will freeze the guest so we can inspect it, but some internal state is not available. Add extra data to internal error reporting so we can expose it to the debugger. Extra data is specific to the suberror. Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 1 + arch/x86/kvm/vmx.c | 1 + include/linux/kvm.h | 4 ++++ virt/kvm/kvm_main.c | 1 + 4 files changed, 7 insertions(+) (limited to 'virt') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a9024797b21f..4c3e5b2314cb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2800,6 +2800,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) case EMULATE_FAIL: vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; default: BUG(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c9cc9596e1a6..c0e66dd58a47 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3352,6 +3352,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) kvm_report_emulation_failure(vcpu, "emulation failure"); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; ret = 0; goto out; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ca62b8e056f9..172639e94392 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -251,6 +251,9 @@ struct kvm_run { } dcr; struct { __u32 suberror; + /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */ + __u32 ndata; + __u64 data[16]; } internal; /* Fix the size of the union. */ char padding[256]; @@ -484,6 +487,7 @@ struct kvm_ioeventfd { #define KVM_CAP_XEN_HVM 38 #endif #define KVM_CAP_ADJUST_CLOCK 39 +#define KVM_CAP_INTERNAL_ERROR_DATA 40 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index bd44fb48ac43..f92ba138007a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1653,6 +1653,7 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) #ifdef CONFIG_KVM_APIC_ARCHITECTURE case KVM_CAP_SET_BOOT_CPU_ID: #endif + case KVM_CAP_INTERNAL_ERROR_DATA: return 1; #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQ_ROUTING: -- cgit v1.2.3-59-g8ed1b