From cf9e4e15e8f6306b2559979269ead7c02e6b2b95 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 11 Feb 2009 16:03:36 +0800 Subject: KVM: Split IOAPIC structure Prepared for reuse ioapic_redir_entry for MSI. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm_types.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2b8318c83e5..b84aca3c4ad 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -40,4 +40,21 @@ typedef unsigned long hfn_t; typedef hfn_t pfn_t; +union kvm_ioapic_redirect_entry { + u64 bits; + struct { + u8 vector; + u8 delivery_mode:3; + u8 dest_mode:1; + u8 delivery_status:1; + u8 polarity:1; + u8 remote_irr:1; + u8 trig_mode:1; + u8 mask:1; + u8 reserve:7; + u8 reserved[4]; + u8 dest_id; + } fields; +}; + #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3-70-g09d2 From 116191b69b608d0f1513e3abe71d6a46800f2bd6 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 11 Feb 2009 16:03:37 +0800 Subject: KVM: Unify the delivery of IOAPIC and MSI interrupts Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 3 ++ virt/kvm/ioapic.c | 91 +++++++++++++++++----------------------------- virt/kvm/irq_comm.c | 95 +++++++++++++++++++++++++++++------------------- 3 files changed, 95 insertions(+), 94 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 894a56e365e..1a2f98fbece 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -352,6 +352,9 @@ 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); +void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, + union kvm_ioapic_redirect_entry *entry, + unsigned long *deliver_bitmask); 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); void kvm_register_irq_ack_notifier(struct kvm *kvm, diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 812801317e3..883fd0dc9b7 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -203,79 +203,56 @@ u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) { - u8 dest = ioapic->redirtbl[irq].fields.dest_id; - u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode; - u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode; - u8 vector = ioapic->redirtbl[irq].fields.vector; - u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode; - u32 deliver_bitmask; + union kvm_ioapic_redirect_entry entry = ioapic->redirtbl[irq]; + unsigned long deliver_bitmask; struct kvm_vcpu *vcpu; int vcpu_id, r = -1; ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", - dest, dest_mode, delivery_mode, vector, trig_mode); + entry.fields.dest, entry.fields.dest_mode, + entry.fields.delivery_mode, entry.fields.vector, + entry.fields.trig_mode); - deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, dest, - dest_mode); + kvm_get_intr_delivery_bitmask(ioapic, &entry, &deliver_bitmask); if (!deliver_bitmask) { ioapic_debug("no target on destination\n"); return 0; } - switch (delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector, - deliver_bitmask); + /* Always delivery PIT interrupt to vcpu 0 */ #ifdef CONFIG_X86 - if (irq == 0) - vcpu = ioapic->kvm->vcpus[0]; + if (irq == 0) + deliver_bitmask = 1; #endif - if (vcpu != NULL) - r = ioapic_inj_irq(ioapic, vcpu, vector, - trig_mode, delivery_mode); - else - ioapic_debug("null lowest prio vcpu: " - "mask=%x vector=%x delivery_mode=%x\n", - deliver_bitmask, vector, IOAPIC_LOWEST_PRIORITY); - break; - case IOAPIC_FIXED: -#ifdef CONFIG_X86 - if (irq == 0) - deliver_bitmask = 1; -#endif - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { + + for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { + if (!(deliver_bitmask & (1 << vcpu_id))) + continue; + deliver_bitmask &= ~(1 << vcpu_id); + vcpu = ioapic->kvm->vcpus[vcpu_id]; + if (vcpu) { + if (entry.fields.delivery_mode == + IOAPIC_LOWEST_PRIORITY || + entry.fields.delivery_mode == IOAPIC_FIXED) { if (r < 0) r = 0; - r += ioapic_inj_irq(ioapic, vcpu, vector, - trig_mode, delivery_mode); - } - } - break; - case IOAPIC_NMI: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - ioapic_inj_nmi(vcpu); + r += ioapic_inj_irq(ioapic, vcpu, + entry.fields.vector, + entry.fields.trig_mode, + entry.fields.delivery_mode); + } else if (entry.fields.delivery_mode == IOAPIC_NMI) { r = 1; - } - else - ioapic_debug("NMI to vcpu %d failed\n", - vcpu->vcpu_id); - } - break; - default: - printk(KERN_WARNING "Unsupported delivery mode %d\n", - delivery_mode); - break; + ioapic_inj_nmi(vcpu); + } else + ioapic_debug("unsupported delivery mode %x!\n", + entry.fields.delivery_mode); + } else + ioapic_debug("null destination vcpu: " + "mask=%x vector=%x delivery_mode=%x\n", + entry.fields.deliver_bitmask, + entry.fields.vector, + entry.fields.delivery_mode); } return r; } diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 864ac5483ba..aec7a0d93a3 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -43,53 +43,74 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } +void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, + union kvm_ioapic_redirect_entry *entry, + unsigned long *deliver_bitmask) +{ + struct kvm_vcpu *vcpu; + + *deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, + entry->fields.dest_id, entry->fields.dest_mode); + switch (entry->fields.delivery_mode) { + case IOAPIC_LOWEST_PRIORITY: + vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, + entry->fields.vector, *deliver_bitmask); + *deliver_bitmask = 1 << vcpu->vcpu_id; + break; + case IOAPIC_FIXED: + case IOAPIC_NMI: + break; + default: + if (printk_ratelimit()) + printk(KERN_INFO "kvm: unsupported delivery mode %d\n", + entry->fields.delivery_mode); + *deliver_bitmask = 0; + } +} + static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level) { int vcpu_id, r = -1; struct kvm_vcpu *vcpu; struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - int dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) - >> MSI_ADDR_DEST_ID_SHIFT; - int vector = (e->msi.data & MSI_DATA_VECTOR_MASK) - >> MSI_DATA_VECTOR_SHIFT; - int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT, - (unsigned long *)&e->msi.address_lo); - int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT, - (unsigned long *)&e->msi.data); - int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT, - (unsigned long *)&e->msi.data); - u32 deliver_bitmask; + union kvm_ioapic_redirect_entry entry; + unsigned long deliver_bitmask; BUG_ON(!ioapic); - deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, - dest_id, dest_mode); - /* IOAPIC delivery mode value is the same as MSI here */ - switch (delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector, - deliver_bitmask); - if (vcpu != NULL) - r = kvm_apic_set_irq(vcpu, vector, trig_mode); - else - printk(KERN_INFO "kvm: null lowest priority vcpu!\n"); - break; - case IOAPIC_FIXED: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, vector, trig_mode); - } + entry.bits = 0; + entry.fields.dest_id = (e->msi.address_lo & + MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; + entry.fields.vector = (e->msi.data & + MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; + entry.fields.dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT, + (unsigned long *)&e->msi.address_lo); + entry.fields.trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT, + (unsigned long *)&e->msi.data); + entry.fields.delivery_mode = test_bit( + MSI_DATA_DELIVERY_MODE_SHIFT, + (unsigned long *)&e->msi.data); + + /* TODO Deal with RH bit of MSI message address */ + + kvm_get_intr_delivery_bitmask(ioapic, &entry, &deliver_bitmask); + + if (!deliver_bitmask) { + printk(KERN_WARNING "kvm: no destination for MSI delivery!"); + return -1; + } + for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { + if (!(deliver_bitmask & (1 << vcpu_id))) + continue; + deliver_bitmask &= ~(1 << vcpu_id); + vcpu = ioapic->kvm->vcpus[vcpu_id]; + if (vcpu) { + if (r < 0) + r = 0; + r += kvm_apic_set_irq(vcpu, entry.fields.vector, + entry.fields.trig_mode); } - break; - default: - break; } return r; } -- cgit v1.2.3-70-g09d2 From c1e01514296e8a4a43ff0c88dcff635cb90feb5f Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 25 Feb 2009 17:22:26 +0800 Subject: KVM: Ioctls for init MSI-X entry Introduce KVM_SET_MSIX_NR and KVM_SET_MSIX_ENTRY two ioctls. This two ioctls are used by userspace to specific guest device MSI-X entry number and correlate MSI-X entry with GSI during the initialization stage. MSI-X should be well initialzed before enabling. Don't support change MSI-X entry number for now. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm.h | 18 ++++++++ include/linux/kvm_host.h | 10 +++++ virt/kvm/kvm_main.c | 104 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 132 insertions(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 8cc137911b3..78cdee8c635 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -487,6 +487,10 @@ struct kvm_irq_routing { #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) #define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ struct kvm_assigned_pci_dev) +#define KVM_ASSIGN_SET_MSIX_NR \ + _IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr) +#define KVM_ASSIGN_SET_MSIX_ENTRY \ + _IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry) /* * ioctls for vcpu fds @@ -607,4 +611,18 @@ struct kvm_assigned_irq { #define KVM_DEV_IRQ_ASSIGN_MSI_ACTION KVM_DEV_IRQ_ASSIGN_ENABLE_MSI #define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI (1 << 0) +struct kvm_assigned_msix_nr { + __u32 assigned_dev_id; + __u16 entry_nr; + __u16 padding; +}; + +#define KVM_MAX_MSIX_PER_DEV 512 +struct kvm_assigned_msix_entry { + __u32 assigned_dev_id; + __u32 gsi; + __u16 entry; /* The index of entry in the MSI-X table */ + __u16 padding[3]; +}; + #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1a2f98fbece..432edc27e82 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -319,6 +319,12 @@ struct kvm_irq_ack_notifier { void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; +struct kvm_guest_msix_entry { + u32 vector; + u16 entry; + u16 flags; +}; + struct kvm_assigned_dev_kernel { struct kvm_irq_ack_notifier ack_notifier; struct work_struct interrupt_work; @@ -326,13 +332,17 @@ struct kvm_assigned_dev_kernel { int assigned_dev_id; int host_busnr; int host_devfn; + unsigned int entries_nr; int host_irq; bool host_irq_disabled; + struct msix_entry *host_msix_entries; int guest_irq; + struct kvm_guest_msix_entry *guest_msix_entries; #define KVM_ASSIGNED_DEV_GUEST_INTX (1 << 0) #define KVM_ASSIGNED_DEV_GUEST_MSI (1 << 1) #define KVM_ASSIGNED_DEV_HOST_INTX (1 << 8) #define KVM_ASSIGNED_DEV_HOST_MSI (1 << 9) +#define KVM_ASSIGNED_DEV_MSIX ((1 << 2) | (1 << 10)) unsigned long irq_requested_type; int irq_source_id; int flags; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4d0dd390aa5..1ceb96901f3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1593,6 +1593,88 @@ 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) { @@ -1917,7 +1999,29 @@ static long kvm_vm_ioctl(struct file *filp, vfree(entries); break; } +#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 +#endif /* KVM_CAP_IRQ_ROUTING */ default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } -- cgit v1.2.3-70-g09d2 From 2350bd1f62c8706c22b8e58c3bfff10806c0a31b Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 25 Feb 2009 17:22:27 +0800 Subject: KVM: Add MSI-X interrupt injection logic We have to handle more than one interrupt with one handler for MSI-X. Avi suggested to use a flag to indicate the pending. So here is it. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 66 +++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 60 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 432edc27e82..3832243625d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -319,6 +319,7 @@ struct kvm_irq_ack_notifier { void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; +#define KVM_ASSIGNED_MSIX_PENDING 0x1 struct kvm_guest_msix_entry { u32 vector; u16 entry; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1ceb96901f3..8bd44d6985c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -95,25 +95,69 @@ static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *h 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 irq, i; assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, interrupt_work); + kvm = assigned_dev->kvm; /* This is taken to safely inject irq inside the guest. When * the interrupt injection (or the ioapic code) uses a * finer-grained lock, update this */ - mutex_lock(&assigned_dev->kvm->lock); - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) { - enable_irq(assigned_dev->host_irq); - assigned_dev->host_irq_disabled = false; + mutex_lock(&kvm->lock); + if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_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); + irq = assigned_dev->host_msix_entries[i].vector; + if (irq != 0) + enable_irq(irq); + assigned_dev->host_irq_disabled = false; + } + } else { + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + if (assigned_dev->irq_requested_type & + KVM_ASSIGNED_DEV_GUEST_MSI) { + enable_irq(assigned_dev->host_irq); + assigned_dev->host_irq_disabled = false; + } } + mutex_unlock(&assigned_dev->kvm->lock); } @@ -122,6 +166,14 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) struct kvm_assigned_dev_kernel *assigned_dev = (struct kvm_assigned_dev_kernel *) dev_id; + if (assigned_dev->irq_requested_type == KVM_ASSIGNED_DEV_MSIX) { + int index = find_index_from_host_irq(assigned_dev, irq); + if (index < 0) + return IRQ_HANDLED; + assigned_dev->guest_msix_entries[index].flags |= + KVM_ASSIGNED_MSIX_PENDING; + } + schedule_work(&assigned_dev->interrupt_work); disable_irq_nosync(irq); -- cgit v1.2.3-70-g09d2 From d510d6cc653bc4b3094ea73afe12600d0ab445b3 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 25 Feb 2009 17:22:28 +0800 Subject: KVM: Enable MSI-X for KVM assigned device This patch finally enable MSI-X. What we need for MSI-X: 1. Intercept one page in MMIO region of device. So that we can get guest desired MSI-X table and set up the real one. Now this have been done by guest, and transfer to kernel using ioctl KVM_SET_MSIX_NR and KVM_SET_MSIX_ENTRY. 2. Information for incoming interrupt. Now one device can have more than one interrupt, and they are all handled by one workqueue structure. So we need to identify them. The previous patch enable gsi_msg_pending_bitmap get this done. 3. Mapping from host IRQ to guest gsi as well as guest gsi to real MSI/MSI-X message address/data. We used same entry number for the host and guest here, so that it's easy to find the correlated guest gsi. What we lack for now: 1. The PCI spec said nothing can existed with MSI-X table in the same page of MMIO region, except pending bits. The patch ignore pending bits as the first step (so they are always 0 - no pending). 2. The PCI spec allowed to change MSI-X table dynamically. That means, the OS can enable MSI-X, then mask one MSI-X entry, modify it, and unmask it. The patch didn't support this, and Linux also don't work in this way. 3. The patch didn't implement MSI-X mask all and mask single entry. I would implement the former in driver/pci/msi.c later. And for single entry, userspace should have reposibility to handle it. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm.h | 1 + include/linux/kvm.h | 8 ++++ virt/kvm/kvm_main.c | 98 +++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 101 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index dc3f6cf1170..125be8b1956 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -16,6 +16,7 @@ #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI #define __KVM_HAVE_GUEST_DEBUG +#define __KVM_HAVE_MSIX /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 78cdee8c635..640835ed270 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -409,6 +409,9 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT #define KVM_CAP_DEVICE_DEASSIGNMENT 27 #endif +#ifdef __KVM_HAVE_MSIX +#define KVM_CAP_DEVICE_MSIX 28 +#endif /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30 @@ -611,6 +614,11 @@ struct kvm_assigned_irq { #define KVM_DEV_IRQ_ASSIGN_MSI_ACTION KVM_DEV_IRQ_ASSIGN_ENABLE_MSI #define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI (1 << 0) +#define KVM_DEV_IRQ_ASSIGN_MSIX_ACTION (KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX |\ + KVM_DEV_IRQ_ASSIGN_MASK_MSIX) +#define KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX (1 << 1) +#define KVM_DEV_IRQ_ASSIGN_MASK_MSIX (1 << 2) + struct kvm_assigned_msix_nr { __u32 assigned_dev_id; __u16 entry_nr; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8bd44d6985c..3bed82754a5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -236,13 +236,33 @@ static void kvm_free_assigned_irq(struct kvm *kvm, * now, the kvm state is still legal for probably we also have to wait * interrupt_work done. */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); + if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_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); - free_irq(assigned_dev->host_irq, (void *)assigned_dev); + for (i = 0; i < assigned_dev->entries_nr; i++) + free_irq(assigned_dev->host_msix_entries[i].vector, + (void *)assigned_dev); - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) - pci_disable_msi(assigned_dev->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_ASSIGNED_DEV_HOST_MSI) + pci_disable_msi(assigned_dev->dev); + } assigned_dev->irq_requested_type = 0; } @@ -373,6 +393,60 @@ static int assigned_device_update_msi(struct kvm *kvm, } #endif +#ifdef __KVM_HAVE_MSIX +static int assigned_device_update_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *adev, + struct kvm_assigned_irq *airq) +{ + /* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ + int i, r; + + adev->ack_notifier.gsi = -1; + + if (irqchip_in_kernel(kvm)) { + if (airq->flags & KVM_DEV_IRQ_ASSIGN_MASK_MSIX) + return -ENOTTY; + + if (!(airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX)) { + /* Guest disable MSI-X */ + kvm_free_assigned_irq(kvm, adev); + if (msi2intx) { + pci_enable_msi(adev->dev); + if (adev->dev->msi_enabled) + return assigned_device_update_msi(kvm, + adev, airq); + } + return assigned_device_update_intx(kvm, adev, airq); + } + + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (adev->entries_nr == 0) + return -EINVAL; + + kvm_free_assigned_irq(kvm, adev); + + r = pci_enable_msix(adev->dev, adev->host_msix_entries, + adev->entries_nr); + if (r) + return r; + + for (i = 0; i < adev->entries_nr; i++) { + r = request_irq((adev->host_msix_entries + i)->vector, + kvm_assigned_dev_intr, 0, + "kvm_assigned_msix_device", + (void *)adev); + if (r) + return r; + } + } + + adev->irq_requested_type |= KVM_ASSIGNED_DEV_MSIX; + + return 0; +} +#endif + static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, struct kvm_assigned_irq *assigned_irq) @@ -417,12 +491,24 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, } } - if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) && + if (match->irq_requested_type & KVM_ASSIGNED_DEV_MSIX) + current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX; + else if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) && (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI)) current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI; changed_flags = assigned_irq->flags ^ current_flags; +#ifdef __KVM_HAVE_MSIX + if (changed_flags & KVM_DEV_IRQ_ASSIGN_MSIX_ACTION) { + r = assigned_device_update_msix(kvm, match, assigned_irq); + if (r) { + printk(KERN_WARNING "kvm: failed to execute " + "MSI-X action!\n"); + goto out_release; + } + } else +#endif if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) || (msi2intx && match->dev->msi_enabled)) { #ifdef CONFIG_X86 -- cgit v1.2.3-70-g09d2 From b95b51d580bff9376850eef29d34c3aa08c26db7 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 26 Feb 2009 13:55:33 +0100 Subject: KVM: declare ioapic functions only on affected hardware Since "KVM: Unify the delivery of IOAPIC and MSI interrupts" I get the following warnings: CC [M] arch/s390/kvm/kvm-s390.o In file included from arch/s390/kvm/kvm-s390.c:22: include/linux/kvm_host.h:357: warning: 'struct kvm_ioapic' declared inside parameter list include/linux/kvm_host.h:357: warning: its scope is only this definition or declaration, which is probably not what you want This patch limits IOAPIC functions for architectures that have one. Signed-off-by: Christian Borntraeger Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3832243625d..3b91ec9982c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -363,9 +363,11 @@ 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); +#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, int irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, -- cgit v1.2.3-70-g09d2 From a53c17d21c46a752f5ac6695376481bc27865b04 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 5 Mar 2009 16:34:49 +0200 Subject: KVM: ioapic/msi interrupt delivery consolidation ioapic_deliver() and kvm_set_msi() have code duplication. Move the code into ioapic_deliver_entry() function and call it from both places. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 +- virt/kvm/ioapic.c | 61 +++++++++++++++++++++++++----------------------- virt/kvm/ioapic.h | 4 ++-- virt/kvm/irq_comm.c | 32 +++---------------------- 4 files changed, 38 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3b91ec9982c..ec9d078b1e8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -364,7 +364,7 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); #ifdef __KVM_HAVE_IOAPIC -void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, +void kvm_get_intr_delivery_bitmask(struct kvm *kvm, union kvm_ioapic_redirect_entry *entry, unsigned long *deliver_bitmask); #endif diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index d4a7948b010..b71c0442cec 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -142,54 +142,57 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) } } -static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) +int ioapic_deliver_entry(struct kvm *kvm, union kvm_ioapic_redirect_entry *e) { - union kvm_ioapic_redirect_entry entry = ioapic->redirtbl[irq]; DECLARE_BITMAP(deliver_bitmask, KVM_MAX_VCPUS); - struct kvm_vcpu *vcpu; - int vcpu_id, r = -1; + int i, r = -1; - ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " - "vector=%x trig_mode=%x\n", - entry.fields.dest, entry.fields.dest_mode, - entry.fields.delivery_mode, entry.fields.vector, - entry.fields.trig_mode); - - /* Always delivery PIT interrupt to vcpu 0 */ -#ifdef CONFIG_X86 - if (irq == 0) { - bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); - __set_bit(0, deliver_bitmask); - } else -#endif - kvm_get_intr_delivery_bitmask(ioapic, &entry, deliver_bitmask); + kvm_get_intr_delivery_bitmask(kvm, e, deliver_bitmask); if (find_first_bit(deliver_bitmask, KVM_MAX_VCPUS) >= KVM_MAX_VCPUS) { ioapic_debug("no target on destination\n"); - return 0; + return r; } - while ((vcpu_id = find_first_bit(deliver_bitmask, KVM_MAX_VCPUS)) + while ((i = find_first_bit(deliver_bitmask, KVM_MAX_VCPUS)) < KVM_MAX_VCPUS) { - __clear_bit(vcpu_id, deliver_bitmask); - vcpu = ioapic->kvm->vcpus[vcpu_id]; + struct kvm_vcpu *vcpu = kvm->vcpus[i]; + __clear_bit(i, deliver_bitmask); if (vcpu) { if (r < 0) r = 0; - r += kvm_apic_set_irq(vcpu, - entry.fields.vector, - entry.fields.trig_mode, - entry.fields.delivery_mode); + r += kvm_apic_set_irq(vcpu, e->fields.vector, + e->fields.delivery_mode, + e->fields.trig_mode); } else ioapic_debug("null destination vcpu: " "mask=%x vector=%x delivery_mode=%x\n", - entry.fields.deliver_bitmask, - entry.fields.vector, - entry.fields.delivery_mode); + e->fields.deliver_bitmask, + e->fields.vector, e->fields.delivery_mode); } return r; } +static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) +{ + union kvm_ioapic_redirect_entry entry = ioapic->redirtbl[irq]; + + ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " + "vector=%x trig_mode=%x\n", + entry.fields.dest, entry.fields.dest_mode, + entry.fields.delivery_mode, entry.fields.vector, + entry.fields.trig_mode); + +#ifdef CONFIG_X86 + /* Always delivery PIT interrupt to vcpu 0 */ + if (irq == 0) { + entry.fields.dest_mode = 0; /* Physical mode. */ + entry.fields.dest_id = ioapic->kvm->vcpus[0]->vcpu_id; + } +#endif + return ioapic_deliver_entry(ioapic->kvm, &entry); +} + int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) { u32 old_irr = ioapic->irr; diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index c8032ab2a4e..bedeea59cc1 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -70,8 +70,8 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); -void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, +void kvm_get_intr_delivery_bitmask(struct kvm *kvm, union kvm_ioapic_redirect_entry *entry, unsigned long *deliver_bitmask); - +int ioapic_deliver_entry(struct kvm *kvm, union kvm_ioapic_redirect_entry *e); #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 325c6685f20..35397a569b2 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -43,12 +43,11 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } -void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, +void kvm_get_intr_delivery_bitmask(struct kvm *kvm, union kvm_ioapic_redirect_entry *entry, unsigned long *deliver_bitmask) { int i; - struct kvm *kvm = ioapic->kvm; struct kvm_vcpu *vcpu; bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); @@ -90,7 +89,7 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, switch (entry->fields.delivery_mode) { case IOAPIC_LOWEST_PRIORITY: /* Select one in deliver_bitmask */ - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, + vcpu = kvm_get_lowest_prio_vcpu(kvm, entry->fields.vector, deliver_bitmask); bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); if (!vcpu) @@ -111,13 +110,7 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level) { - int vcpu_id, r = -1; - struct kvm_vcpu *vcpu; - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); union kvm_ioapic_redirect_entry entry; - DECLARE_BITMAP(deliver_bitmask, KVM_MAX_VCPUS); - - BUG_ON(!ioapic); entry.bits = 0; entry.fields.dest_id = (e->msi.address_lo & @@ -133,26 +126,7 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, (unsigned long *)&e->msi.data); /* TODO Deal with RH bit of MSI message address */ - - kvm_get_intr_delivery_bitmask(ioapic, &entry, deliver_bitmask); - - if (find_first_bit(deliver_bitmask, KVM_MAX_VCPUS) >= KVM_MAX_VCPUS) { - printk(KERN_WARNING "kvm: no destination for MSI delivery!"); - return -1; - } - while ((vcpu_id = find_first_bit(deliver_bitmask, - KVM_MAX_VCPUS)) < KVM_MAX_VCPUS) { - __clear_bit(vcpu_id, deliver_bitmask); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, entry.fields.vector, - entry.fields.dest_mode, - entry.fields.trig_mode); - } - } - return r; + return ioapic_deliver_entry(kvm, &entry); } /* This should be called with the kvm->lock mutex held -- cgit v1.2.3-70-g09d2 From 343f94fe4d16ec898da77720c03da9e09f8523d2 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 5 Mar 2009 16:34:54 +0200 Subject: KVM: consolidate ioapic/ipi interrupt delivery logic Use kvm_apic_match_dest() in kvm_get_intr_delivery_bitmask() instead of duplicating the same code. Use kvm_get_intr_delivery_bitmask() in apic_send_ipi() to figure out ipi destination instead of reimplementing the logic. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 8 ++++++ arch/ia64/kvm/lapic.h | 3 ++ arch/x86/kvm/lapic.c | 69 +++++++++++++++++--------------------------- arch/x86/kvm/lapic.h | 2 ++ include/linux/kvm_host.h | 5 ---- virt/kvm/ioapic.c | 5 +++- virt/kvm/ioapic.h | 10 ++++--- virt/kvm/irq_comm.c | 74 ++++++++++++++---------------------------------- 8 files changed, 70 insertions(+), 106 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 99d6d174d93..8eea9cba7b7 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1852,6 +1852,14 @@ struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, return lvcpu; } +int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, int dest, int dest_mode) +{ + return (dest_mode == 0) ? + kvm_apic_match_physical_addr(target, dest) : + kvm_apic_match_logical_addr(target, dest); +} + static int find_highest_bits(int *dat) { u32 bits, bitnum; diff --git a/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h index cbcfaa6195c..31602e7338d 100644 --- a/arch/ia64/kvm/lapic.h +++ b/arch/ia64/kvm/lapic.h @@ -20,6 +20,9 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); +int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, int dest, int dest_mode); +bool kvm_apic_present(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 dmode, u8 trig); #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a42f968a23e..998862a3c26 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -260,7 +260,7 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) { - return kvm_apic_id(apic) == dest; + return dest == 0xff || kvm_apic_id(apic) == dest; } int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) @@ -289,37 +289,34 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) return result; } -static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, +int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, int dest, int dest_mode) { int result = 0; struct kvm_lapic *target = vcpu->arch.apic; apic_debug("target %p, source %p, dest 0x%x, " - "dest_mode 0x%x, short_hand 0x%x", + "dest_mode 0x%x, short_hand 0x%x\n", target, source, dest, dest_mode, short_hand); ASSERT(!target); switch (short_hand) { case APIC_DEST_NOSHORT: - if (dest_mode == 0) { + if (dest_mode == 0) /* Physical mode. */ - if ((dest == 0xFF) || (dest == kvm_apic_id(target))) - result = 1; - } else + result = kvm_apic_match_physical_addr(target, dest); + else /* Logical mode. */ result = kvm_apic_match_logical_addr(target, dest); break; case APIC_DEST_SELF: - if (target == source) - result = 1; + result = (target == source); break; case APIC_DEST_ALLINC: result = 1; break; case APIC_DEST_ALLBUT: - if (target != source) - result = 1; + result = (target != source); break; default: printk(KERN_WARNING "Bad dest shorthand value %x\n", @@ -492,38 +489,26 @@ static void apic_send_ipi(struct kvm_lapic *apic) unsigned int delivery_mode = icr_low & APIC_MODE_MASK; unsigned int vector = icr_low & APIC_VECTOR_MASK; - struct kvm_vcpu *target; - struct kvm_vcpu *vcpu; - DECLARE_BITMAP(lpr_map, KVM_MAX_VCPUS); + DECLARE_BITMAP(deliver_bitmask, KVM_MAX_VCPUS); int i; - bitmap_zero(lpr_map, KVM_MAX_VCPUS); apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", icr_high, icr_low, short_hand, dest, trig_mode, level, dest_mode, delivery_mode, vector); - for (i = 0; i < KVM_MAX_VCPUS; i++) { - vcpu = apic->vcpu->kvm->vcpus[i]; - if (!vcpu) - continue; - - if (vcpu->arch.apic && - apic_match_dest(vcpu, apic, short_hand, dest, dest_mode)) { - if (delivery_mode == APIC_DM_LOWEST) - __set_bit(vcpu->vcpu_id, lpr_map); - else - __apic_accept_irq(vcpu->arch.apic, delivery_mode, - vector, level, trig_mode); - } - } - - if (delivery_mode == APIC_DM_LOWEST) { - target = kvm_get_lowest_prio_vcpu(vcpu->kvm, vector, lpr_map); - if (target != NULL) - __apic_accept_irq(target->arch.apic, delivery_mode, - vector, level, trig_mode); + kvm_get_intr_delivery_bitmask(apic->vcpu->kvm, apic, dest, dest_mode, + delivery_mode == APIC_DM_LOWEST, short_hand, + deliver_bitmask); + + while ((i = find_first_bit(deliver_bitmask, KVM_MAX_VCPUS)) + < KVM_MAX_VCPUS) { + struct kvm_vcpu *vcpu = apic->vcpu->kvm->vcpus[i]; + __clear_bit(i, deliver_bitmask); + if (vcpu) + __apic_accept_irq(vcpu->arch.apic, delivery_mode, + vector, level, trig_mode); } } @@ -930,16 +915,14 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_reset); -int kvm_lapic_enabled(struct kvm_vcpu *vcpu) +bool kvm_apic_present(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = vcpu->arch.apic; - int ret = 0; - - if (!apic) - return 0; - ret = apic_enabled(apic); + return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic); +} - return ret; +int kvm_lapic_enabled(struct kvm_vcpu *vcpu) +{ + return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_lapic_enabled); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 1b0e3c03cb3..b66dc14a969 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -37,6 +37,8 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu); int kvm_lapic_enabled(struct kvm_vcpu *vcpu); +bool kvm_apic_present(struct kvm_vcpu *vcpu); +bool kvm_lapic_present(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ec9d078b1e8..fb60f31c4fb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -363,11 +363,6 @@ 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); -#ifdef __KVM_HAVE_IOAPIC -void kvm_get_intr_delivery_bitmask(struct kvm *kvm, - union kvm_ioapic_redirect_entry *entry, - unsigned long *deliver_bitmask); -#endif 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); void kvm_register_irq_ack_notifier(struct kvm *kvm, diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index b71c0442cec..43969bbf127 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -147,7 +147,10 @@ int ioapic_deliver_entry(struct kvm *kvm, union kvm_ioapic_redirect_entry *e) DECLARE_BITMAP(deliver_bitmask, KVM_MAX_VCPUS); int i, r = -1; - kvm_get_intr_delivery_bitmask(kvm, e, deliver_bitmask); + kvm_get_intr_delivery_bitmask(kvm, NULL, e->fields.dest_id, + e->fields.dest_mode, + e->fields.delivery_mode == IOAPIC_LOWEST_PRIORITY, + 0, deliver_bitmask); if (find_first_bit(deliver_bitmask, KVM_MAX_VCPUS) >= KVM_MAX_VCPUS) { ioapic_debug("no target on destination\n"); diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index bedeea59cc1..d996c7abc46 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -65,13 +65,15 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) } struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, - unsigned long *bitmap); + unsigned long *bitmap); +int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, int dest, int dest_mode); void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); -void kvm_get_intr_delivery_bitmask(struct kvm *kvm, - union kvm_ioapic_redirect_entry *entry, - unsigned long *deliver_bitmask); +void kvm_get_intr_delivery_bitmask(struct kvm *kvm, struct kvm_lapic *src, + int dest_id, int dest_mode, bool low_prio, int short_hand, + unsigned long *deliver_bitmask); int ioapic_deliver_entry(struct kvm *kvm, union kvm_ioapic_redirect_entry *e); #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 35397a569b2..e43701c0a5c 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -43,67 +43,35 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } -void kvm_get_intr_delivery_bitmask(struct kvm *kvm, - union kvm_ioapic_redirect_entry *entry, - unsigned long *deliver_bitmask) +void kvm_get_intr_delivery_bitmask(struct kvm *kvm, struct kvm_lapic *src, + int dest_id, int dest_mode, bool low_prio, int short_hand, + unsigned long *deliver_bitmask) { int i; struct kvm_vcpu *vcpu; + if (dest_mode == 0 && dest_id == 0xff && low_prio) + printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); + for (i = 0; i < KVM_MAX_VCPUS; i++) { + vcpu = kvm->vcpus[i]; - if (entry->fields.dest_mode == 0) { /* Physical mode. */ - if (entry->fields.dest_id == 0xFF) { /* Broadcast. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i] && kvm->vcpus[i]->arch.apic) - __set_bit(i, deliver_bitmask); - /* Lowest priority shouldn't combine with broadcast */ - if (entry->fields.delivery_mode == - IOAPIC_LOWEST_PRIORITY && printk_ratelimit()) - printk(KERN_INFO "kvm: apic: phys broadcast " - "and lowest prio\n"); - return; - } - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (kvm_apic_match_physical_addr(vcpu->arch.apic, - entry->fields.dest_id)) { - if (vcpu->arch.apic) - __set_bit(i, deliver_bitmask); - break; - } - } - } else if (entry->fields.dest_id != 0) /* Logical mode, MDA non-zero. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (vcpu->arch.apic && - kvm_apic_match_logical_addr(vcpu->arch.apic, - entry->fields.dest_id)) - __set_bit(i, deliver_bitmask); - } + if (!vcpu || !kvm_apic_present(vcpu)) + continue; - switch (entry->fields.delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - /* Select one in deliver_bitmask */ - vcpu = kvm_get_lowest_prio_vcpu(kvm, - entry->fields.vector, deliver_bitmask); - bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); - if (!vcpu) - return; - __set_bit(vcpu->vcpu_id, deliver_bitmask); - break; - case IOAPIC_FIXED: - case IOAPIC_NMI: - break; - default: - if (printk_ratelimit()) - printk(KERN_INFO "kvm: unsupported delivery mode %d\n", - entry->fields.delivery_mode); + if (!kvm_apic_match_dest(vcpu, src, short_hand, dest_id, + dest_mode)) + continue; + + __set_bit(i, deliver_bitmask); + } + + if (low_prio) { + vcpu = kvm_get_lowest_prio_vcpu(kvm, 0, deliver_bitmask); bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); + if (vcpu) + __set_bit(vcpu->vcpu_id, deliver_bitmask); } } -- cgit v1.2.3-70-g09d2 From 58c2dde17d6eb6c8c0566e52d184aa16755d890f Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 5 Mar 2009 16:35:04 +0200 Subject: KVM: APIC: get rid of deliver_bitmask Deliver interrupt during destination matching loop. Signed-off-by: Gleb Natapov Acked-by: Xiantao Zhang Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 33 ++++++++++++---------- arch/ia64/kvm/lapic.h | 4 +-- arch/x86/kvm/lapic.c | 59 +++++++++++---------------------------- arch/x86/kvm/lapic.h | 3 +- include/linux/kvm_types.h | 10 +++++++ virt/kvm/ioapic.c | 57 +++++++++++-------------------------- virt/kvm/ioapic.h | 6 ++-- virt/kvm/irq_comm.c | 71 ++++++++++++++++++++++++++++------------------- 8 files changed, 108 insertions(+), 135 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 1887a93a2bd..acf43ec4270 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -283,6 +283,18 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } +static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector) +{ + struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd); + + if (!test_and_set_bit(vector, &vpd->irr[0])) { + vcpu->arch.irq_new_pending = 1; + kvm_vcpu_kick(vcpu); + return 1; + } + return 0; +} + /* * offset: address offset to IPI space. * value: deliver value. @@ -292,20 +304,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm, { switch (dm) { case SAPIC_FIXED: - kvm_apic_set_irq(vcpu, vector, dm, 0); break; case SAPIC_NMI: - kvm_apic_set_irq(vcpu, 2, dm, 0); + vector = 2; break; case SAPIC_EXTINT: - kvm_apic_set_irq(vcpu, 0, dm, 0); + vector = 0; break; case SAPIC_INIT: case SAPIC_PMI: default: printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n"); - break; + return; } + __apic_accept_irq(vcpu, vector); } static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id, @@ -1813,17 +1825,9 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) put_cpu(); } -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 dmode, u8 trig) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) { - - struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd); - - if (!test_and_set_bit(vec, &vpd->irr[0])) { - vcpu->arch.irq_new_pending = 1; - kvm_vcpu_kick(vcpu); - return 1; - } - return 0; + return __apic_accept_irq(vcpu, irq->vector); } int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) @@ -1844,6 +1848,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, int dest, int dest_mode) { + struct kvm_lapic *target = vcpu->arch.apic; return (dest_mode == 0) ? kvm_apic_match_physical_addr(target, dest) : kvm_apic_match_logical_addr(target, dest); diff --git a/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h index e42109e6ca4..ee541cebcd7 100644 --- a/arch/ia64/kvm/lapic.h +++ b/arch/ia64/kvm/lapic.h @@ -23,7 +23,7 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); -bool kvm_apic_present(struct kvm_vcpu *vcpu); -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 dmode, u8 trig); +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq); +#define kvm_apic_present(x) (true) #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 814466f455d..dd934d27040 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -199,27 +199,12 @@ EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode); -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 dmode, u8 trig) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) { struct kvm_lapic *apic = vcpu->arch.apic; - int lapic_dmode; - switch (dmode) { - case IOAPIC_LOWEST_PRIORITY: - lapic_dmode = APIC_DM_LOWEST; - break; - case IOAPIC_FIXED: - lapic_dmode = APIC_DM_FIXED; - break; - case IOAPIC_NMI: - lapic_dmode = APIC_DM_NMI; - break; - default: - printk(KERN_DEBUG"Ignoring delivery mode %d\n", dmode); - return 0; - break; - } - return __apic_accept_irq(apic, lapic_dmode, vec, 1, trig); + return __apic_accept_irq(apic, irq->delivery_mode, irq->vector, + irq->level, irq->trig_mode); } static inline int apic_find_highest_isr(struct kvm_lapic *apic) @@ -447,36 +432,24 @@ static void apic_send_ipi(struct kvm_lapic *apic) { u32 icr_low = apic_get_reg(apic, APIC_ICR); u32 icr_high = apic_get_reg(apic, APIC_ICR2); + struct kvm_lapic_irq irq; - unsigned int dest = GET_APIC_DEST_FIELD(icr_high); - unsigned int short_hand = icr_low & APIC_SHORT_MASK; - unsigned int trig_mode = icr_low & APIC_INT_LEVELTRIG; - unsigned int level = icr_low & APIC_INT_ASSERT; - unsigned int dest_mode = icr_low & APIC_DEST_MASK; - unsigned int delivery_mode = icr_low & APIC_MODE_MASK; - unsigned int vector = icr_low & APIC_VECTOR_MASK; - - DECLARE_BITMAP(deliver_bitmask, KVM_MAX_VCPUS); - int i; + irq.vector = icr_low & APIC_VECTOR_MASK; + irq.delivery_mode = icr_low & APIC_MODE_MASK; + irq.dest_mode = icr_low & APIC_DEST_MASK; + irq.level = icr_low & APIC_INT_ASSERT; + irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; + irq.shorthand = icr_low & APIC_SHORT_MASK; + irq.dest_id = GET_APIC_DEST_FIELD(icr_high); apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", - icr_high, icr_low, short_hand, dest, - trig_mode, level, dest_mode, delivery_mode, vector); - - kvm_get_intr_delivery_bitmask(apic->vcpu->kvm, apic, dest, dest_mode, - delivery_mode == APIC_DM_LOWEST, short_hand, - deliver_bitmask); - - while ((i = find_first_bit(deliver_bitmask, KVM_MAX_VCPUS)) - < KVM_MAX_VCPUS) { - struct kvm_vcpu *vcpu = apic->vcpu->kvm->vcpus[i]; - __clear_bit(i, deliver_bitmask); - if (vcpu) - __apic_accept_irq(vcpu->arch.apic, delivery_mode, - vector, level, trig_mode); - } + icr_high, icr_low, irq.shorthand, irq.dest, + irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, + irq.vector); + + kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); } static u32 apic_get_tmcct(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index b66dc14a969..a587f8349c4 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -31,14 +31,13 @@ u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 dmode, u8 trig); +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu); int kvm_lapic_enabled(struct kvm_vcpu *vcpu); bool kvm_apic_present(struct kvm_vcpu *vcpu); -bool kvm_lapic_present(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index b84aca3c4ad..fb46efbeabe 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -57,4 +57,14 @@ union kvm_ioapic_redirect_entry { } fields; }; +struct kvm_lapic_irq { + u32 vector; + u32 delivery_mode; + u32 dest_mode; + u32 level; + u32 trig_mode; + u32 shorthand; + u32 dest_id; +}; + #endif /* __KVM_TYPES_H__ */ diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 43969bbf127..1eddae94bab 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -142,58 +142,33 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) } } -int ioapic_deliver_entry(struct kvm *kvm, union kvm_ioapic_redirect_entry *e) -{ - DECLARE_BITMAP(deliver_bitmask, KVM_MAX_VCPUS); - int i, r = -1; - - kvm_get_intr_delivery_bitmask(kvm, NULL, e->fields.dest_id, - e->fields.dest_mode, - e->fields.delivery_mode == IOAPIC_LOWEST_PRIORITY, - 0, deliver_bitmask); - - if (find_first_bit(deliver_bitmask, KVM_MAX_VCPUS) >= KVM_MAX_VCPUS) { - ioapic_debug("no target on destination\n"); - return r; - } - - while ((i = find_first_bit(deliver_bitmask, KVM_MAX_VCPUS)) - < KVM_MAX_VCPUS) { - struct kvm_vcpu *vcpu = kvm->vcpus[i]; - __clear_bit(i, deliver_bitmask); - if (vcpu) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, e->fields.vector, - e->fields.delivery_mode, - e->fields.trig_mode); - } else - ioapic_debug("null destination vcpu: " - "mask=%x vector=%x delivery_mode=%x\n", - e->fields.deliver_bitmask, - e->fields.vector, e->fields.delivery_mode); - } - return r; -} - static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) { - union kvm_ioapic_redirect_entry entry = ioapic->redirtbl[irq]; + union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; + struct kvm_lapic_irq irqe; ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", - entry.fields.dest, entry.fields.dest_mode, - entry.fields.delivery_mode, entry.fields.vector, - entry.fields.trig_mode); + entry->fields.dest, entry->fields.dest_mode, + entry->fields.delivery_mode, entry->fields.vector, + entry->fields.trig_mode); + + irqe.dest_id = entry->fields.dest_id; + irqe.vector = entry->fields.vector; + irqe.dest_mode = entry->fields.dest_mode; + irqe.trig_mode = entry->fields.trig_mode; + irqe.delivery_mode = entry->fields.delivery_mode << 8; + irqe.level = 1; + irqe.shorthand = 0; #ifdef CONFIG_X86 /* Always delivery PIT interrupt to vcpu 0 */ if (irq == 0) { - entry.fields.dest_mode = 0; /* Physical mode. */ - entry.fields.dest_id = ioapic->kvm->vcpus[0]->vcpu_id; + irqe.dest_mode = 0; /* Physical mode. */ + irqe.dest_id = ioapic->kvm->vcpus[0]->vcpu_id; } #endif - return ioapic_deliver_entry(ioapic->kvm, &entry); + return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe); } int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index e7bc92d895f..7080b713c16 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -71,8 +71,6 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); -void kvm_get_intr_delivery_bitmask(struct kvm *kvm, struct kvm_lapic *src, - int dest_id, int dest_mode, bool low_prio, int short_hand, - unsigned long *deliver_bitmask); -int ioapic_deliver_entry(struct kvm *kvm, union kvm_ioapic_redirect_entry *e); +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq); #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index f5e059b67cd..4fa1f604b42 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -22,6 +22,9 @@ #include #include +#ifdef CONFIG_IA64 +#include +#endif #include "irq.h" @@ -43,61 +46,71 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } -void kvm_get_intr_delivery_bitmask(struct kvm *kvm, struct kvm_lapic *src, - int dest_id, int dest_mode, bool low_prio, int short_hand, - unsigned long *deliver_bitmask) +inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) { - int i, lowest = -1; - struct kvm_vcpu *vcpu; +#ifdef CONFIG_IA64 + return irq->delivery_mode == + (IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT); +#else + return irq->delivery_mode == APIC_DM_LOWEST; +#endif +} - if (dest_mode == 0 && dest_id == 0xff && low_prio) +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq) +{ + int i, r = -1; + struct kvm_vcpu *vcpu, *lowest = NULL; + + 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"); - bitmap_zero(deliver_bitmask, KVM_MAX_VCPUS); for (i = 0; i < KVM_MAX_VCPUS; i++) { vcpu = kvm->vcpus[i]; if (!vcpu || !kvm_apic_present(vcpu)) continue; - if (!kvm_apic_match_dest(vcpu, src, short_hand, dest_id, - dest_mode)) + if (!kvm_apic_match_dest(vcpu, src, irq->shorthand, + irq->dest_id, irq->dest_mode)) continue; - if (!low_prio) { - __set_bit(i, deliver_bitmask); + if (!kvm_is_dm_lowest_prio(irq)) { + if (r < 0) + r = 0; + r += kvm_apic_set_irq(vcpu, irq); } else { - if (lowest < 0) - lowest = i; - if (kvm_apic_compare_prio(vcpu, kvm->vcpus[lowest]) < 0) - lowest = i; + if (!lowest) + lowest = vcpu; + else if (kvm_apic_compare_prio(vcpu, lowest) < 0) + lowest = vcpu; } } - if (lowest != -1) - __set_bit(lowest, deliver_bitmask); + if (lowest) + r = kvm_apic_set_irq(lowest, irq); + + return r; } static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level) { - union kvm_ioapic_redirect_entry entry; + struct kvm_lapic_irq irq; - entry.bits = 0; - entry.fields.dest_id = (e->msi.address_lo & + irq.dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; - entry.fields.vector = (e->msi.data & + irq.vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; - entry.fields.dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT, - (unsigned long *)&e->msi.address_lo); - entry.fields.trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT, - (unsigned long *)&e->msi.data); - entry.fields.delivery_mode = test_bit( - MSI_DATA_DELIVERY_MODE_SHIFT, - (unsigned long *)&e->msi.data); + irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; + irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; + irq.delivery_mode = e->msi.data & 0x700; + irq.level = 1; + irq.shorthand = 0; /* TODO Deal with RH bit of MSI message address */ - return ioapic_deliver_entry(kvm, &entry); + return kvm_irq_delivery_to_apic(kvm, NULL, &irq); } /* This should be called with the kvm->lock mutex held -- cgit v1.2.3-70-g09d2 From e56d532f20c890a06bbe7cd479f4201e3a03cd73 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Thu, 12 Mar 2009 21:45:39 +0800 Subject: KVM: Device assignment framework rework After discussion with Marcelo, we decided to rework device assignment framework together. The old problems are kernel logic is unnecessary complex. So Marcelo suggest to split it into a more elegant way: 1. Split host IRQ assign and guest IRQ assign. And userspace determine the combination. Also discard msi2intx parameter, userspace can specific KVM_DEV_IRQ_HOST_MSI | KVM_DEV_IRQ_GUEST_INTX in assigned_irq->flags to enable MSI to INTx convertion. 2. Split assign IRQ and deassign IRQ. Import two new ioctls: KVM_ASSIGN_DEV_IRQ and KVM_DEASSIGN_DEV_IRQ. This patch also fixed the reversed _IOR vs _IOW in definition(by deprecated the old interface). [avi: replace homemade bitcount() by hweight_long()] Signed-off-by: Marcelo Tosatti Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 1 + include/linux/kvm.h | 26 ++- include/linux/kvm_host.h | 5 - virt/kvm/kvm_main.c | 486 +++++++++++++++++++++++++---------------------- 4 files changed, 276 insertions(+), 242 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 43e049a2ccf..41123fc8613 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1026,6 +1026,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_SYNC_MMU: case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: + case KVM_CAP_ASSIGN_DEV_IRQ: r = 1; break; case KVM_CAP_COALESCED_MMIO: diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 640835ed270..644e3a9f47d 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -412,6 +412,7 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_MSIX #define KVM_CAP_DEVICE_MSIX 28 #endif +#define KVM_CAP_ASSIGN_DEV_IRQ 29 /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30 @@ -485,8 +486,10 @@ struct kvm_irq_routing { #define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ struct kvm_assigned_pci_dev) #define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) +/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */ #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ struct kvm_assigned_irq) +#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) #define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ struct kvm_assigned_pci_dev) @@ -494,6 +497,7 @@ struct kvm_irq_routing { _IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr) #define KVM_ASSIGN_SET_MSIX_ENTRY \ _IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry) +#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) /* * ioctls for vcpu fds @@ -584,6 +588,8 @@ struct kvm_debug_guest { #define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) #define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) +#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) + struct kvm_assigned_pci_dev { __u32 assigned_dev_id; __u32 busnr; @@ -594,6 +600,17 @@ struct kvm_assigned_pci_dev { }; }; +#define KVM_DEV_IRQ_HOST_INTX (1 << 0) +#define KVM_DEV_IRQ_HOST_MSI (1 << 1) +#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) + +#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) +#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) +#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) + +#define KVM_DEV_IRQ_HOST_MASK 0x00ff +#define KVM_DEV_IRQ_GUEST_MASK 0xff00 + struct kvm_assigned_irq { __u32 assigned_dev_id; __u32 host_irq; @@ -609,15 +626,6 @@ struct kvm_assigned_irq { }; }; -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) - -#define KVM_DEV_IRQ_ASSIGN_MSI_ACTION KVM_DEV_IRQ_ASSIGN_ENABLE_MSI -#define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI (1 << 0) - -#define KVM_DEV_IRQ_ASSIGN_MSIX_ACTION (KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX |\ - KVM_DEV_IRQ_ASSIGN_MASK_MSIX) -#define KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX (1 << 1) -#define KVM_DEV_IRQ_ASSIGN_MASK_MSIX (1 << 2) struct kvm_assigned_msix_nr { __u32 assigned_dev_id; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fb60f31c4fb..40e49ede8f9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -339,11 +339,6 @@ struct kvm_assigned_dev_kernel { struct msix_entry *host_msix_entries; int guest_irq; struct kvm_guest_msix_entry *guest_msix_entries; -#define KVM_ASSIGNED_DEV_GUEST_INTX (1 << 0) -#define KVM_ASSIGNED_DEV_GUEST_MSI (1 << 1) -#define KVM_ASSIGNED_DEV_HOST_INTX (1 << 8) -#define KVM_ASSIGNED_DEV_HOST_MSI (1 << 9) -#define KVM_ASSIGNED_DEV_MSIX ((1 << 2) | (1 << 10)) unsigned long irq_requested_type; int irq_source_id; int flags; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3bed82754a5..792fb7fae0a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -60,9 +61,6 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int msi2intx = 1; -module_param(msi2intx, bool, 0); - DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); @@ -132,7 +130,7 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) * finer-grained lock, update this */ mutex_lock(&kvm->lock); - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_MSIX) { + 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++) { @@ -152,7 +150,7 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, assigned_dev->guest_irq, 1); if (assigned_dev->irq_requested_type & - KVM_ASSIGNED_DEV_GUEST_MSI) { + KVM_DEV_IRQ_GUEST_MSI) { enable_irq(assigned_dev->host_irq); assigned_dev->host_irq_disabled = false; } @@ -166,7 +164,7 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) struct kvm_assigned_dev_kernel *assigned_dev = (struct kvm_assigned_dev_kernel *) dev_id; - if (assigned_dev->irq_requested_type == KVM_ASSIGNED_DEV_MSIX) { + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { int index = find_index_from_host_irq(assigned_dev, irq); if (index < 0) return IRQ_HANDLED; @@ -204,22 +202,22 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) } } -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) +static void deassign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) { - if (!irqchip_in_kernel(kvm)) - return; - kvm_unregister_irq_ack_notifier(&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); +} - if (!assigned_dev->irq_requested_type) - return; - +/* 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. @@ -236,7 +234,7 @@ static void kvm_free_assigned_irq(struct kvm *kvm, * now, the kvm state is still legal for probably we also have to wait * interrupt_work done. */ - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_MSIX) { + 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-> @@ -259,14 +257,41 @@ static void kvm_free_assigned_irq(struct kvm *kvm, free_irq(assigned_dev->host_irq, (void *)assigned_dev); - if (assigned_dev->irq_requested_type & - KVM_ASSIGNED_DEV_HOST_MSI) + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) pci_disable_msi(assigned_dev->dev); } - assigned_dev->irq_requested_type = 0; + 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 @@ -298,256 +323,244 @@ void kvm_free_all_assigned_devices(struct kvm *kvm) } } -static int assigned_device_update_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) +static int assigned_device_enable_host_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) { - adev->guest_irq = airq->guest_irq; - adev->ack_notifier.gsi = airq->guest_irq; - - if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX) - return 0; - - if (irqchip_in_kernel(kvm)) { - if (!msi2intx && - (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) { - free_irq(adev->host_irq, (void *)adev); - pci_disable_msi(adev->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; +} - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_host_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int r; - if (airq->host_irq) - adev->host_irq = airq->host_irq; - else - adev->host_irq = adev->dev->irq; + if (!dev->dev->msi_enabled) { + r = pci_enable_msi(dev->dev); + if (r) + return r; + } - /* 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(adev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)adev)) - return -EIO; + 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; } - adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX | - KVM_ASSIGNED_DEV_HOST_INTX; return 0; } +#endif -#ifdef CONFIG_X86 -static int assigned_device_update_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_host_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) { - int r; + int i, r = -EINVAL; - adev->guest_irq = airq->guest_irq; - if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) { - /* x86 don't care upper address of guest msi message addr */ - adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI; - adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX; - adev->ack_notifier.gsi = -1; - } else if (msi2intx) { - adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX; - adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI; - adev->ack_notifier.gsi = airq->guest_irq; - } else { - /* - * Guest require to disable device MSI, we disable MSI and - * re-enable INTx by default again. Notice it's only for - * non-msi2intx. - */ - assigned_device_update_intx(kvm, adev, airq); - return 0; - } + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (dev->entries_nr == 0) + return r; - if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) - return 0; + r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + if (r) + return r; - if (irqchip_in_kernel(kvm)) { - if (!msi2intx) { - if (adev->irq_requested_type & - KVM_ASSIGNED_DEV_HOST_INTX) - free_irq(adev->host_irq, (void *)adev); + 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; + } - r = pci_enable_msi(adev->dev); - if (r) - return r; - } + return 0; +} - adev->host_irq = adev->dev->irq; - if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)adev)) - return -EIO; - } +#endif - if (!msi2intx) - adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI; +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; +} - adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI; +#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; 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; + 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 -static int assigned_device_update_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) -{ - /* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ - int i, r; - - adev->ack_notifier.gsi = -1; - - if (irqchip_in_kernel(kvm)) { - if (airq->flags & KVM_DEV_IRQ_ASSIGN_MASK_MSIX) - return -ENOTTY; - - if (!(airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX)) { - /* Guest disable MSI-X */ - kvm_free_assigned_irq(kvm, adev); - if (msi2intx) { - pci_enable_msi(adev->dev); - if (adev->dev->msi_enabled) - return assigned_device_update_msi(kvm, - adev, airq); - } - return assigned_device_update_intx(kvm, adev, airq); - } + case KVM_DEV_IRQ_HOST_MSIX: + r = assigned_device_enable_host_msix(kvm, dev); + break; +#endif + default: + r = -EINVAL; + } - /* host_msix_entries and guest_msix_entries should have been - * initialized */ - if (adev->entries_nr == 0) - return -EINVAL; + if (!r) + dev->irq_requested_type |= host_irq_type; - kvm_free_assigned_irq(kvm, adev); + return r; +} - r = pci_enable_msix(adev->dev, adev->host_msix_entries, - adev->entries_nr); - if (r) - 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; - for (i = 0; i < adev->entries_nr; i++) { - r = request_irq((adev->host_msix_entries + i)->vector, - kvm_assigned_dev_intr, 0, - "kvm_assigned_msix_device", - (void *)adev); - if (r) - return r; - } + 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; } - adev->irq_requested_type |= KVM_ASSIGNED_DEV_MSIX; + 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 0; + return r; } -#endif +/* 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) + struct kvm_assigned_irq *assigned_irq) { - int r = 0; + int r = -EINVAL; struct kvm_assigned_dev_kernel *match; - u32 current_flags = 0, changed_flags; + unsigned long host_irq_type, guest_irq_type; - mutex_lock(&kvm->lock); + 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) { - mutex_unlock(&kvm->lock); - return -EINVAL; - } - - if (!match->irq_requested_type) { - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); - if (irqchip_in_kernel(kvm)) { - /* Register ack nofitier */ - match->ack_notifier.gsi = -1; - match->ack_notifier.irq_acked = - kvm_assigned_dev_ack_irq; - kvm_register_irq_ack_notifier(kvm, - &match->ack_notifier); - - /* Request IRQ source ID */ - r = kvm_request_irq_source_id(kvm); - if (r < 0) - goto out_release; - else - match->irq_source_id = r; - -#ifdef CONFIG_X86 - /* Determine host device irq type, we can know the - * result from dev->msi_enabled */ - if (msi2intx) - pci_enable_msi(match->dev); -#endif - } - } + if (!match) + goto out; - if (match->irq_requested_type & KVM_ASSIGNED_DEV_MSIX) - current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSIX; - else if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) && - (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI)) - current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI; + host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); + guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - changed_flags = assigned_irq->flags ^ current_flags; + 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; -#ifdef __KVM_HAVE_MSIX - if (changed_flags & KVM_DEV_IRQ_ASSIGN_MSIX_ACTION) { - r = assigned_device_update_msix(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to execute " - "MSI-X action!\n"); - goto out_release; - } - } else -#endif - if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) || - (msi2intx && match->dev->msi_enabled)) { -#ifdef CONFIG_X86 - r = assigned_device_update_msi(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to enable " - "MSI device!\n"); - goto out_release; - } -#else - r = -ENOTTY; -#endif - } else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) { - /* Host device IRQ 0 means don't support INTx */ - if (!msi2intx) { - printk(KERN_WARNING - "kvm: wait device to enable MSI!\n"); - r = 0; - } else { - printk(KERN_WARNING - "kvm: failed to enable MSI device!\n"); - r = -ENOTTY; - goto out_release; - } - } else { - /* Non-sharing INTx mode */ - r = assigned_device_update_intx(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to enable " - "INTx device!\n"); - goto out_release; - } - } + 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; -out_release: +} + +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); - kvm_free_assigned_device(kvm, match); return r; } @@ -565,7 +578,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, assigned_dev->assigned_dev_id); if (match) { /* device already assigned */ - r = -EINVAL; + r = -EEXIST; goto out; } @@ -604,6 +617,9 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, match->dev = dev; 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); @@ -2084,6 +2100,11 @@ static long kvm_vm_ioctl(struct file *filp, 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; @@ -2094,6 +2115,18 @@ static long kvm_vm_ioctl(struct file *filp, 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: { @@ -2596,9 +2629,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; -#ifndef CONFIG_X86 - msi2intx = 0; -#endif return 0; -- cgit v1.2.3-70-g09d2 From 78646121e9a2fcf7977cc15966420e572a450bc3 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 23 Mar 2009 12:12:11 +0200 Subject: KVM: Fix interrupt unhalting a vcpu when it shouldn't kvm_vcpu_block() unhalts vpu on an interrupt/timer without checking if interrupt window is actually opened. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 6 ++++++ arch/powerpc/kvm/powerpc.c | 6 ++++++ arch/s390/kvm/interrupt.c | 6 ++++++ arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm.c | 10 ++++++++++ arch/x86/kvm/vmx.c | 8 +++++++- arch/x86/kvm/x86.c | 5 +++++ include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 3 ++- 9 files changed, 44 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index d2a90fd505b..3bf0a345224 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1963,6 +1963,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) return 0; } +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + /* do real check here */ + return 1; +} + int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return vcpu->arch.timer_fired; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9057335fdc6..2cf915e51e7 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -41,6 +41,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) return !!(v->arch.pending_exceptions); } +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + /* do real check here */ + return 1; +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { return !(v->arch.msr & MSR_WE); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 0189356fe20..4ed4c3a1148 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -318,6 +318,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) return rc; } +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + /* do real check here */ + return 1; +} + int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return 0; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 46276273a1a..8351c4d00ac 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -521,7 +521,7 @@ struct kvm_x86_ops { void (*inject_pending_irq)(struct kvm_vcpu *vcpu); void (*inject_pending_vectors)(struct kvm_vcpu *vcpu, struct kvm_run *run); - + int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*get_tdp_level)(void); int (*get_mt_mask_shift)(void); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index aa528dbad07..de741043c5b 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2270,6 +2270,15 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK; } +static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + return (vmcb->save.rflags & X86_EFLAGS_IF) && + !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && + (svm->vcpu.arch.hflags & HF_GIF_MASK); +} + static void svm_intr_assist(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2649,6 +2658,7 @@ static struct kvm_x86_ops svm_x86_ops = { .exception_injected = svm_exception_injected, .inject_pending_irq = svm_intr_assist, .inject_pending_vectors = do_interrupt_requests, + .interrupt_allowed = svm_interrupt_allowed, .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index da6461d5dc8..b9e06b07aca 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2490,6 +2490,12 @@ static void vmx_update_window_states(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_MOV_SS))); } +static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + vmx_update_window_states(vcpu); + return vcpu->arch.interrupt_window_open; +} + static void do_interrupt_requests(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { @@ -3691,7 +3697,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .exception_injected = vmx_exception_injected, .inject_pending_irq = vmx_intr_assist, .inject_pending_vectors = do_interrupt_requests, - + .interrupt_allowed = vmx_interrupt_allowed, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, .get_mt_mask_shift = vmx_get_mt_mask_shift, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8fca7a4e95a..5bbcad34537 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4475,3 +4475,8 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); put_cpu(); } + +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops->interrupt_allowed(vcpu); +} diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 40e49ede8f9..72d56844f38 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -298,6 +298,7 @@ int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); void kvm_arch_check_processor_compat(void *rtn); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); void kvm_free_physmem(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a1a4272fa57..63d5fa2bc84 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1610,7 +1610,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) for (;;) { prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); - if (kvm_cpu_has_interrupt(vcpu) || + if ((kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) || kvm_arch_vcpu_runnable(vcpu)) { set_bit(KVM_REQ_UNHALT, &vcpu->requests); break; -- cgit v1.2.3-70-g09d2 From 2f8b9ee14eb439008e0c5131116ea6baa40dba50 Mon Sep 17 00:00:00 2001 From: nathan binkert Date: Fri, 27 Mar 2009 21:53:05 -0700 Subject: KVM: Make kvm header C++ friendly Two things needed fixing: 1) g++ does not allow a named structure type within an anonymous union and 2) Avoid name clash between two padding fields within the same struct by giving them different names as is done elsewhere in the header. Signed-off-by: Nathan Binkert Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 644e3a9f47d..3db5d8d3748 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -119,7 +119,7 @@ struct kvm_run { __u32 error_code; } ex; /* KVM_EXIT_IO */ - struct kvm_io { + struct { #define KVM_EXIT_IO_IN 0 #define KVM_EXIT_IO_OUT 1 __u8 direction; @@ -224,10 +224,10 @@ struct kvm_interrupt { /* for KVM_GET_DIRTY_LOG */ struct kvm_dirty_log { __u32 slot; - __u32 padding; + __u32 padding1; union { void __user *dirty_bitmap; /* one bit per page */ - __u64 padding; + __u64 padding2; }; }; -- cgit v1.2.3-70-g09d2 From 522c68c4416de3cd3e11a9ff10d58e776a69ae1e Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Mon, 27 Apr 2009 20:35:43 +0800 Subject: KVM: Enable snooping control for supported hardware Memory aliases with different memory type is a problem for guest. For the guest without assigned device, the memory type of guest memory would always been the same as host(WB); but for the assigned device, some part of memory may be used as DMA and then set to uncacheable memory type(UC/WC), which would be a conflict of host memory type then be a potential issue. Snooping control can guarantee the cache correctness of memory go through the DMA engine of VT-d. [avi: fix build on ia64] Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm_host.h | 1 + arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx.c | 19 +++++++++++++++++-- include/linux/kvm_host.h | 3 +++ virt/kvm/iommu.c | 27 ++++++++++++++++++++++++--- 5 files changed, 46 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index 589536fa799..5f43697aed3 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -474,6 +474,7 @@ 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; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8a6f6b643df..253d8f669cf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -393,6 +393,7 @@ struct kvm_arch{ struct list_head active_mmu_pages; struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; + int iommu_flags; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 59b080c262e..e8a5649f9c1 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3581,11 +3581,26 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u64 ret; + /* For VT-d and EPT combination + * 1. MMIO: always map as UC + * 2. EPT with VT-d: + * a. VT-d without snooping control feature: can't guarantee the + * result, try to trust guest. + * b. VT-d with snooping control feature: snooping control feature of + * VT-d engine can guarantee the cache correctness. Just set it + * to WB to keep consistent with host. So the same as item 3. + * 3. EPT without VT-d: always map as WB and set IGMT=1 to keep + * consistent with host MTRR + */ if (is_mmio) ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; + else if (vcpu->kvm->arch.iommu_domain && + !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)) + ret = kvm_get_guest_memory_type(vcpu, gfn) << + VMX_EPT_MT_EPTE_SHIFT; else - ret = (kvm_get_guest_memory_type(vcpu, gfn) << - VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IGMT_BIT; + ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) + | VMX_EPT_IGMT_BIT; return ret; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 72d56844f38..bdce8e1303c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -367,6 +367,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian); int kvm_request_irq_source_id(struct kvm *kvm); void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); +/* For vcpu->arch.iommu_flags */ +#define KVM_IOMMU_CACHE_COHERENCY 0x1 + #ifdef CONFIG_IOMMU_API int kvm_iommu_map_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 4c403750360..15147583abd 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -39,11 +39,16 @@ int kvm_iommu_map_pages(struct kvm *kvm, pfn_t pfn; int i, r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; + int flags; /* check if iommu exists and in use */ if (!domain) return 0; + flags = IOMMU_READ | IOMMU_WRITE; + if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY) + flags |= IOMMU_CACHE; + for (i = 0; i < npages; i++) { /* check if already mapped */ if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) @@ -53,8 +58,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, r = iommu_map_range(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn), - PAGE_SIZE, - IOMMU_READ | IOMMU_WRITE); + PAGE_SIZE, flags); if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%lx\n", pfn); @@ -88,7 +92,7 @@ int kvm_assign_device(struct kvm *kvm, { struct pci_dev *pdev = NULL; struct iommu_domain *domain = kvm->arch.iommu_domain; - int r; + int r, last_flags; /* check if iommu exists and in use */ if (!domain) @@ -107,12 +111,29 @@ int kvm_assign_device(struct kvm *kvm, return r; } + last_flags = kvm->arch.iommu_flags; + if (iommu_domain_has_cap(kvm->arch.iommu_domain, + IOMMU_CAP_CACHE_COHERENCY)) + kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY; + + /* Check if need to update IOMMU page table for guest memory */ + if ((last_flags ^ kvm->arch.iommu_flags) == + KVM_IOMMU_CACHE_COHERENCY) { + kvm_iommu_unmap_memslots(kvm); + r = kvm_iommu_map_memslots(kvm); + if (r) + goto out_unmap; + } + printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n", assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); return 0; +out_unmap: + kvm_iommu_unmap_memslots(kvm); + return r; } int kvm_deassign_device(struct kvm *kvm, -- cgit v1.2.3-70-g09d2 From 32f8840064d88cc3f6e85203aec7b6b57bebcb97 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 7 May 2009 17:55:12 -0300 Subject: KVM: use smp_send_reschedule in kvm_vcpu_kick KVM uses a function call IPI to cause the exit of a guest running on a physical cpu. For virtual interrupt notification there is no need to wait on IPI receival, or to execute any function. This is exactly what the reschedule IPI does, without the overhead of function IPI. So use it instead of smp_call_function_single in kvm_vcpu_kick. Also change the "guest_mode" variable to a bit in vcpu->requests, and use that to collapse multiple IPI's that would be issued between the first one and zeroing of guest mode. This allows kvm_vcpu_kick to called with interrupts disabled. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/ia64/kernel/irq_ia64.c | 3 +++ arch/ia64/kvm/kvm-ia64.c | 22 ++++++++-------------- arch/x86/kernel/smp.c | 3 +++ arch/x86/kvm/x86.c | 36 +++++++++++------------------------- include/linux/kvm_host.h | 2 +- 5 files changed, 26 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index acc4d19ae62..b448197728b 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -610,6 +610,9 @@ static struct irqaction ipi_irqaction = { .name = "IPI" }; +/* + * KVM uses this interrupt to force a cpu out of guest mode + */ static struct irqaction resched_irqaction = { .handler = dummy_handler, .flags = IRQF_DISABLED, diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index be4413e1f43..80c57b0a21c 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -668,7 +668,7 @@ again: host_ctx = kvm_get_host_context(vcpu); guest_ctx = kvm_get_guest_context(vcpu); - vcpu->guest_mode = 1; + clear_bit(KVM_REQ_KICK, &vcpu->requests); r = kvm_vcpu_pre_transition(vcpu); if (r < 0) @@ -685,7 +685,7 @@ again: kvm_vcpu_post_transition(vcpu); vcpu->arch.launched = 1; - vcpu->guest_mode = 0; + set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); /* @@ -1879,24 +1879,18 @@ void kvm_arch_hardware_unsetup(void) { } -static void vcpu_kick_intr(void *info) -{ -#ifdef DEBUG - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; - printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu); -#endif -} - void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int ipi_pcpu = vcpu->cpu; - int cpu = get_cpu(); + int me; + int cpu = vcpu->cpu; if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); - if (vcpu->guest_mode && cpu != ipi_pcpu) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); + me = get_cpu(); + if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu)) + if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)) + smp_send_reschedule(cpu); put_cpu(); } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 13f33ea8cca..3b2e55e8ad2 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -172,6 +172,9 @@ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + /* + * KVM uses this interrupt to force a cpu out of guest mode + */ } void smp_call_function_interrupt(struct pt_regs *regs) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 75927700a26..3c4c327490a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3230,6 +3230,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) local_irq_disable(); + clear_bit(KVM_REQ_KICK, &vcpu->requests); + smp_mb__after_clear_bit(); + if (vcpu->requests || need_resched() || signal_pending(current)) { local_irq_enable(); preempt_enable(); @@ -3237,13 +3240,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - vcpu->guest_mode = 1; - /* - * Make sure that guest_mode assignment won't happen after - * testing the pending IRQ vector bitmap. - */ - smp_wmb(); - if (vcpu->arch.exception.pending) __queue_exception(vcpu); else @@ -3288,7 +3284,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) set_debugreg(vcpu->arch.host_dr6, 6); set_debugreg(vcpu->arch.host_dr7, 7); - vcpu->guest_mode = 0; + set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); ++vcpu->stat.exits; @@ -4571,30 +4567,20 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) || vcpu->arch.nmi_pending; } -static void vcpu_kick_intr(void *info) -{ -#ifdef DEBUG - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; - printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu); -#endif -} - void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int ipi_pcpu = vcpu->cpu; - int cpu; + int me; + int cpu = vcpu->cpu; if (waitqueue_active(&vcpu->wq)) { wake_up_interruptible(&vcpu->wq); ++vcpu->stat.halt_wakeup; } - /* - * We may be called synchronously with irqs disabled in guest mode, - * So need not to call smp_call_function_single() in that case. - */ - cpu = get_cpu(); - if (vcpu->guest_mode && vcpu->cpu != cpu) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); + + me = get_cpu(); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) + if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)) + smp_send_reschedule(cpu); put_cpu(); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bdce8e1303c..16181628419 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -38,6 +38,7 @@ #define KVM_REQ_UNHALT 6 #define KVM_REQ_MMU_SYNC 7 #define KVM_REQ_KVMCLOCK_UPDATE 8 +#define KVM_REQ_KICK 9 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 @@ -72,7 +73,6 @@ struct kvm_vcpu { struct mutex mutex; int cpu; struct kvm_run *run; - int guest_mode; unsigned long requests; unsigned long guest_debug; int fpu_active; -- cgit v1.2.3-70-g09d2 From 547de29e5b1662deb05b5f90917902dc0e9ac182 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 7 May 2009 17:55:13 -0300 Subject: KVM: protect assigned dev workqueue, int handler and irq acker kvm_assigned_dev_ack_irq is vulnerable to a race condition with the interrupt handler function. It does: if (dev->host_irq_disabled) { enable_irq(dev->host_irq); dev->host_irq_disabled = false; } If an interrupt triggers before the host->dev_irq_disabled assignment, it will disable the interrupt and set dev->host_irq_disabled to true. On return to kvm_assigned_dev_ack_irq, dev->host_irq_disabled is set to false, and the next kvm_assigned_dev_ack_irq call will fail to reenable it. Other than that, having the interrupt handler and work handlers run in parallel sounds like asking for trouble (could not spot any obvious problem, but better not have to, its fragile). CC: sheng.yang@intel.com Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 16181628419..aacc5449f58 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -345,6 +345,7 @@ struct kvm_assigned_dev_kernel { int flags; struct pci_dev *dev; struct kvm *kvm; + spinlock_t assigned_dev_lock; }; struct kvm_irq_mask_notifier { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 29c0afb064d..687d113a3e5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -130,6 +131,7 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) * finer-grained lock, update this */ mutex_lock(&kvm->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 = assigned_dev->guest_msix_entries; @@ -156,18 +158,21 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) } } + spin_unlock_irq(&assigned_dev->assigned_dev_lock); mutex_unlock(&assigned_dev->kvm->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) - return IRQ_HANDLED; + goto out; assigned_dev->guest_msix_entries[index].flags |= KVM_ASSIGNED_MSIX_PENDING; } @@ -177,6 +182,8 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) disable_irq_nosync(irq); assigned_dev->host_irq_disabled = true; +out: + spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); return IRQ_HANDLED; } @@ -184,6 +191,7 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) 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; @@ -196,10 +204,12 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) /* 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, @@ -615,6 +625,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, 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; -- cgit v1.2.3-70-g09d2