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 --- virt/kvm/kvm_main.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4d0dd390aa50..1ceb96901f32 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 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 'virt/kvm/kvm_main.c') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 432edc27e82b..3832243625d4 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 1ceb96901f32..8bd44d6985c7 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 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 'virt/kvm/kvm_main.c') diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index dc3f6cf11704..125be8b19568 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 78cdee8c6355..640835ed2708 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 8bd44d6985c7..3bed82754a5d 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 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 'virt/kvm/kvm_main.c') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 43e049a2ccf4..41123fc8613e 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 640835ed2708..644e3a9f47db 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 fb60f31c4fb3..40e49ede8f91 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 3bed82754a5d..792fb7fae0a3 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 From f00be0cae4e6ad0a8c7be381c6d9be3586800b3e Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 19 Mar 2009 12:20:36 +0200 Subject: KVM: MMU: do not free active mmu pages in free_mmu_pages() free_mmu_pages() should only undo what alloc_mmu_pages() does. Free mmu pages from the generic VM destruction function, kvm_destroy_vm(). Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 8 -------- virt/kvm/kvm_main.c | 2 ++ 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 32cf11e5728a..8aac67cbd92f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2638,14 +2638,6 @@ EXPORT_SYMBOL_GPL(kvm_disable_tdp); static void free_mmu_pages(struct kvm_vcpu *vcpu) { - struct kvm_mmu_page *sp; - - while (!list_empty(&vcpu->kvm->arch.active_mmu_pages)) { - sp = container_of(vcpu->kvm->arch.active_mmu_pages.next, - struct kvm_mmu_page, link); - kvm_mmu_zap_page(vcpu->kvm, sp); - cond_resched(); - } free_page((unsigned long)vcpu->arch.mmu.pae_root); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 792fb7fae0a3..934dd1c9487e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1032,6 +1032,8 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); +#else + kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); mmdrop(mm); -- cgit v1.2.3 From 09cec754885f900f6aab23801878c0cd217ee1d6 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 23 Mar 2009 15:11:44 +0200 Subject: KVM: Timer event should not unconditionally unhalt vcpu. Currently timer events are processed before entering guest mode. Move it to main vcpu event loop since timer events should be processed even while vcpu is halted. Timer may cause interrupt/nmi to be injected and only then vcpu will be unhalted. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 6 ++--- arch/x86/kvm/x86.c | 57 +++++++++++++++++++++++++++++------------------- virt/kvm/kvm_main.c | 5 +++-- 3 files changed, 40 insertions(+), 28 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 4623a90e515a..d2a90fd505b0 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -488,10 +488,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) hrtimer_cancel(p_ht); vcpu->arch.ht_active = 0; - if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) + if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) || + kvm_cpu_has_pending_timer(vcpu)) if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) return -EINTR; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c0ae5e6cba9b..8fca7a4e95a3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3133,9 +3133,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } - clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); - kvm_inject_pending_timer_irqs(vcpu); - preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); @@ -3235,6 +3232,7 @@ out: return r; } + static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -3261,29 +3259,42 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_vcpu_block(vcpu); down_read(&vcpu->kvm->slots_lock); if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + { + switch(vcpu->arch.mp_state) { + case KVM_MP_STATE_HALTED: vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; - if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) - r = -EINTR; + KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_RUNNABLE: + break; + case KVM_MP_STATE_SIPI_RECEIVED: + default: + r = -EINTR; + break; + } + } } - if (r > 0) { - if (dm_request_for_irq_injection(vcpu, kvm_run)) { - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.request_irq_exits; - } - if (signal_pending(current)) { - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.signal_exits; - } - if (need_resched()) { - up_read(&vcpu->kvm->slots_lock); - kvm_resched(vcpu); - down_read(&vcpu->kvm->slots_lock); - } + if (r <= 0) + break; + + clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); + if (kvm_cpu_has_pending_timer(vcpu)) + kvm_inject_pending_timer_irqs(vcpu); + + if (dm_request_for_irq_injection(vcpu, kvm_run)) { + r = -EINTR; + kvm_run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.request_irq_exits; + } + if (signal_pending(current)) { + r = -EINTR; + kvm_run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.signal_exits; + } + if (need_resched()) { + up_read(&vcpu->kvm->slots_lock); + kvm_resched(vcpu); + down_read(&vcpu->kvm->slots_lock); } } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 934dd1c9487e..a1a4272fa57c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1611,11 +1611,12 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_cpu_has_interrupt(vcpu) || - kvm_cpu_has_pending_timer(vcpu) || - kvm_arch_vcpu_runnable(vcpu)) { + kvm_arch_vcpu_runnable(vcpu)) { set_bit(KVM_REQ_UNHALT, &vcpu->requests); break; } + if (kvm_cpu_has_pending_timer(vcpu)) + break; if (signal_pending(current)) break; -- cgit v1.2.3 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 'virt/kvm/kvm_main.c') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index d2a90fd505b0..3bf0a345224a 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 9057335fdc61..2cf915e51e7e 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 0189356fe209..4ed4c3a11485 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 46276273a1a1..8351c4d00ac0 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 aa528dbad070..de741043c5b1 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 da6461d5dc84..b9e06b07aca1 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 8fca7a4e95a3..5bbcad345376 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 40e49ede8f91..72d56844f388 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 a1a4272fa57c..63d5fa2bc84a 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 From 8e1c18157d8772e65247ac55525a05a26b83fffe Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 29 Apr 2009 11:09:04 +0800 Subject: KVM: VMX: Disable VMX when system shutdown Intel TXT(Trusted Execution Technology) required VMX off for all cpu to work when system shutdown. CC: Joseph Cihula Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 63d5fa2bc84a..29c0afb064da 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2391,15 +2391,15 @@ EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot); static int kvm_reboot(struct notifier_block *notifier, unsigned long val, void *v) { - if (val == SYS_RESTART) { - /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - */ - printk(KERN_INFO "kvm: exiting hardware virtualization\n"); - kvm_rebooting = true; - on_each_cpu(hardware_disable, NULL, 1); - } + /* + * Some (well, at least mine) BIOSes hang on reboot if + * in vmx root mode. + * + * And Intel TXT required VMX off for all cpu when system shutdown. + */ + printk(KERN_INFO "kvm: exiting hardware virtualization\n"); + kvm_rebooting = true; + on_each_cpu(hardware_disable, NULL, 1); return NOTIFY_OK; } -- cgit v1.2.3 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 'virt/kvm/kvm_main.c') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 161816284192..aacc5449f586 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 29c0afb064da..687d113a3e5e 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 From b43b1901ad282aeb74161837fb403927102687a1 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 12 May 2009 18:55:44 -0300 Subject: KVM: take mmu_lock when updating a deleted slot kvm_handle_hva relies on mmu_lock protection to safely access the memslot structures. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 687d113a3e5e..5fed9bfc3cf5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1210,8 +1210,10 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_free_physmem_slot(&old, npages ? &new : NULL); /* Slot deletion case: we have to update the current slot */ + spin_lock(&kvm->mmu_lock); if (!npages) *memslot = old; + spin_unlock(&kvm->mmu_lock); #ifdef CONFIG_DMAR /* map the pages in iommu page table */ r = kvm_iommu_map_pages(kvm, base_gfn, npages); -- cgit v1.2.3 From ac04527f7947020c5890090b2ac87af4e98d977e Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 8 Jun 2009 15:52:39 +0300 Subject: KVM: Disable large pages on misaligned memory slots If a slots guest physical address and host virtual address unequal (mod large page size), then we would erronously try to back guest large pages with host large pages. Detect this misalignment and diable large page support for the trouble slot. Cc: stable@kernel.org Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5fed9bfc3cf5..5f865ed4c431 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1086,7 +1086,7 @@ int __kvm_set_memory_region(struct kvm *kvm, { int r; gfn_t base_gfn; - unsigned long npages; + unsigned long npages, ugfn; int largepages; unsigned long i; struct kvm_memory_slot *memslot; @@ -1177,6 +1177,14 @@ int __kvm_set_memory_region(struct kvm *kvm, new.lpage_info[0].write_count = 1; if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE) new.lpage_info[largepages-1].write_count = 1; + ugfn = new.userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, disable large page support for this slot + */ + if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1)) + for (i = 0; i < largepages; ++i) + new.lpage_info[i].write_count = 1; } /* Allocate page dirty bitmap if needed */ -- cgit v1.2.3 From 09f8ca74ae6c2d78b2c7f6c0751ed0cbe815a3d9 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 8 Jun 2009 15:55:21 +0300 Subject: KVM: Prevent overflow in largepages calculation If userspace specifies a memory slot that is larger than 8 petabytes, it could overflow the largepages variable. Cc: stable@kernel.org Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5f865ed4c431..e21194566b71 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1087,8 +1087,7 @@ int __kvm_set_memory_region(struct kvm *kvm, int r; gfn_t base_gfn; unsigned long npages, ugfn; - int largepages; - unsigned long i; + unsigned long largepages, i; struct kvm_memory_slot *memslot; struct kvm_memory_slot old, new; -- cgit v1.2.3 From aee74f3bb3f4fb5dbeae8c1947c6d8ebdc19ee01 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 11 Jun 2009 15:09:00 -0700 Subject: kvm: remove the duplicated cpumask_clear zalloc_cpumask_var already cleared it. Signed-off-by: Yinghai Lu Signed-off-by: Linus Torvalds --- virt/kvm/kvm_main.c | 1 - 1 file changed, 1 deletion(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e21194566b71..764554350ed8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2604,7 +2604,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, r = -ENOMEM; goto out_free_0; } - cpumask_clear(cpus_hardware_enabled); r = kvm_arch_hardware_setup(); if (r < 0) -- cgit v1.2.3