KVM: Enable Function Level Reset for assigned device
PATCH 1/1 KVM: Enable Function Level Reset for assigned device
Ideally, every assigned device should in a clear condition before and after assignment, so that the former state of device won't affect later work. Some devices provide a mechanism named Function Level Reset, which is defined in PCI/PCI-e document. We should execute it before and after device assignment.
(But sadly, the feature is new, and most device on the market now don't support it. We are considering using D0/D3hot transmit to emulate it later, but not that elegant and reliable as FLR itself.)
--- arch/x86/kvm/x86.c | 2 +- virt/kvm/kvm_main.c | 5 +++++ 2 files changed, 6 insertions(+), 1 deletions(-)
arch/x86/kvm/x86.c +1 -1
@@ -4148,8 +4148,8 @@ static void kvm_free_vcpus(struct kvm *kvm)void kvm_arch_destroy_vm (struct kvm *kvm) { -kvm_iommu_unmap_guest (kvm);kvm_free_all_assigned_devices (kvm); +kvm_iommu_unmap_guest (kvm);kvm_free_pit (kvm);kfree (kvm->arch.vpic);kfree (kvm->arch.vioapic);
virt/kvm/kvm_main.c +5 -0
@@ -152,6 +152,8 @@ static void kvm_free_assigned_device(struct kvm *kvm,*/ kvm_put_kvm (kvm); +pci_reset_function (assigned_dev->dev); +pci_release_regions (assigned_dev->dev);pci_disable_device (assigned_dev->dev);pci_dev_put (assigned_dev->dev);
@@ -272,6 +274,9 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, r = -EINVAL ; goto out_free; } + +pci_reset_function (dev); +if (pci_enable_device (dev)) {printk (KERN_INFO "%s: Could not enable PCI device\n" , __func__); r = -EBUSY ;
Signature · 1 line
1.5.4.5
PATCH 1/1 KVM: Enable Function Level Reset for assigned device
Ideally, every assigned device should in a clear condition before and after assignment, so that the former state of device won't affect later work. Some devices provide a mechanism named Function Level Reset, which is defined in PCI/PCI-e document. We should execute it before and after device assignment.
(But sadly, the feature is new, and most device on the market now don't support it. We are considering using D0/D3hot transmit to emulate it later, but not that elegant and reliable as FLR itself.)
[Update: Reminded by Xiantao, execute FLR after we ensure that the device can be assigned to the guest.]
--- arch/x86/kvm/x86.c | 2 +- virt/kvm/kvm_main.c | 5 +++++ 2 files changed, 6 insertions(+), 1 deletions(-)
arch/x86/kvm/x86.c +1 -1
@@ -4148,8 +4148,8 @@ static void kvm_free_vcpus(struct kvm *kvm)void kvm_arch_destroy_vm (struct kvm *kvm) { -kvm_iommu_unmap_guest (kvm);kvm_free_all_assigned_devices (kvm); +kvm_iommu_unmap_guest (kvm);kvm_free_pit (kvm);kfree (kvm->arch.vpic);kfree (kvm->arch.vioapic);
virt/kvm/kvm_main.c +5 -0
@@ -152,6 +152,8 @@ static void kvm_free_assigned_device(struct kvm *kvm,*/ kvm_put_kvm (kvm); +pci_reset_function (assigned_dev->dev); +pci_release_regions (assigned_dev->dev);pci_disable_device (assigned_dev->dev);pci_dev_put (assigned_dev->dev);
@@ -283,6 +285,9 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, __func__); goto out_disable; } + +pci_reset_function (dev); + match->assigned_dev_id = assigned_dev->assigned_dev_id; match->host_busnr = assigned_dev->busnr; match->host_devfn = assigned_dev->devfn;
Signature · 1 line
1.5.4.5
Avi Kivity
AppliedQuoted 6 lines · Sheng Yang
Ideally, every assigned device should in a clear condition before and after assignment, so that the former state of device won't affect later work. Some devices provide a mechanism named Function Level Reset, which is defined in PCI/PCI-e document. We should execute it before and after device assignment.
Quoted 8 lines
(But sadly, the feature is new, and most device on the market now don't support it. We are considering using D0/D3hot transmit to emulate it later, but not that elegant and reliable as FLR itself.)
[Update: Reminded by Xiantao, execute FLR after we ensure that the device can be assigned to the guest.]
Applied, thanks.
Signature · 1 line
error compiling committee.c: too many arguments to function