diff options
Diffstat (limited to 'virt/kvm/assigned-dev.c')
| -rw-r--r-- | virt/kvm/assigned-dev.c | 522 |
1 files changed, 364 insertions, 158 deletions
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index f73de631e3e..bf06577fea5 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -1,7 +1,7 @@ /* * Kernel-based Virtual Machine - device assignment support * - * Copyright (C) 2006-9 Red Hat, Inc + * Copyright (C) 2010 Red Hat, Inc. and/or its affiliates. * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -16,6 +16,9 @@ #include <linux/spinlock.h> #include <linux/pci.h> #include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/fs.h> #include "irq.h" static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, @@ -46,101 +49,161 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel index = i; break; } - if (index < 0) { + 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) +static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id) { - struct kvm_assigned_dev_kernel *assigned_dev; - struct kvm *kvm; - int i; + struct kvm_assigned_dev_kernel *assigned_dev = dev_id; + int ret; + + spin_lock(&assigned_dev->intx_lock); + if (pci_check_and_mask_intx(assigned_dev->dev)) { + assigned_dev->host_irq_disabled = true; + ret = IRQ_WAKE_THREAD; + } else + ret = IRQ_NONE; + spin_unlock(&assigned_dev->intx_lock); - assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, - interrupt_work); - kvm = assigned_dev->kvm; + return ret; +} - spin_lock_irq(&assigned_dev->assigned_dev_lock); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - struct kvm_guest_msix_entry *guest_entries = - assigned_dev->guest_msix_entries; - for (i = 0; i < assigned_dev->entries_nr; i++) { - if (!(guest_entries[i].flags & - KVM_ASSIGNED_MSIX_PENDING)) - continue; - guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; +static void +kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev, + int vector) +{ + if (unlikely(assigned_dev->irq_requested_type & + KVM_DEV_IRQ_GUEST_INTX)) { + spin_lock(&assigned_dev->intx_mask_lock); + if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) kvm_set_irq(assigned_dev->kvm, - assigned_dev->irq_source_id, - guest_entries[i].vector, 1); - } + assigned_dev->irq_source_id, vector, 1, + false); + spin_unlock(&assigned_dev->intx_mask_lock); } else kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); + vector, 1, false); +} + +static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id) +{ + struct kvm_assigned_dev_kernel *assigned_dev = dev_id; + + if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) { + spin_lock_irq(&assigned_dev->intx_lock); + disable_irq_nosync(irq); + assigned_dev->host_irq_disabled = true; + spin_unlock_irq(&assigned_dev->intx_lock); + } + + kvm_assigned_dev_raise_guest_irq(assigned_dev, + assigned_dev->guest_irq); + + return IRQ_HANDLED; +} - spin_unlock_irq(&assigned_dev->assigned_dev_lock); +#ifdef __KVM_HAVE_MSI +static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id) +{ + struct kvm_assigned_dev_kernel *assigned_dev = dev_id; + int ret = kvm_set_irq_inatomic(assigned_dev->kvm, + assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED; } -static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) +static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id) { - unsigned long flags; - struct kvm_assigned_dev_kernel *assigned_dev = - (struct kvm_assigned_dev_kernel *) dev_id; + struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int index = find_index_from_host_irq(assigned_dev, irq); - if (index < 0) - goto out; - assigned_dev->guest_msix_entries[index].flags |= - KVM_ASSIGNED_MSIX_PENDING; + kvm_assigned_dev_raise_guest_irq(assigned_dev, + assigned_dev->guest_irq); + + return IRQ_HANDLED; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id) +{ + struct kvm_assigned_dev_kernel *assigned_dev = dev_id; + int index = find_index_from_host_irq(assigned_dev, irq); + u32 vector; + int ret = 0; + + if (index >= 0) { + vector = assigned_dev->guest_msix_entries[index].vector; + ret = kvm_set_irq_inatomic(assigned_dev->kvm, + assigned_dev->irq_source_id, + vector, 1); } - schedule_work(&assigned_dev->interrupt_work); + return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED; +} - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { - disable_irq_nosync(irq); - assigned_dev->host_irq_disabled = true; +static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id) +{ + struct kvm_assigned_dev_kernel *assigned_dev = dev_id; + int index = find_index_from_host_irq(assigned_dev, irq); + u32 vector; + + if (index >= 0) { + vector = assigned_dev->guest_msix_entries[index].vector; + kvm_assigned_dev_raise_guest_irq(assigned_dev, vector); } -out: - spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); return IRQ_HANDLED; } +#endif /* Ack the irq line for an assigned device */ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) { - struct kvm_assigned_dev_kernel *dev; - unsigned long flags; - - if (kian->gsi == -1) - return; - - dev = container_of(kian, struct kvm_assigned_dev_kernel, - ack_notifier); - - kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); + struct kvm_assigned_dev_kernel *dev = + container_of(kian, struct kvm_assigned_dev_kernel, + ack_notifier); + + kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false); + + spin_lock(&dev->intx_mask_lock); + + if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) { + bool reassert = false; + + spin_lock_irq(&dev->intx_lock); + /* + * The guest IRQ may be shared so this ack can come from an + * IRQ for another guest device. + */ + if (dev->host_irq_disabled) { + if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) + enable_irq(dev->host_irq); + else if (!pci_check_and_unmask_intx(dev->dev)) + reassert = true; + dev->host_irq_disabled = reassert; + } + spin_unlock_irq(&dev->intx_lock); - /* 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; + if (reassert) + kvm_set_irq(dev->kvm, dev->irq_source_id, + dev->guest_irq, 1, false); } - spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); + + spin_unlock(&dev->intx_mask_lock); } static void deassign_guest_irq(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev) { - kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); - assigned_dev->ack_notifier.gsi = -1; + if (assigned_dev->ack_notifier.gsi != -1) + kvm_unregister_irq_ack_notifier(kvm, + &assigned_dev->ack_notifier); + + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 0, false); if (assigned_dev->irq_source_id != -1) kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); @@ -153,32 +216,23 @@ static void deassign_host_irq(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev) { /* - * In kvm_free_device_irq, cancel_work_sync return true if: - * 1. work is scheduled, and then cancelled. - * 2. work callback is executed. - * - * The first one ensured that the irq is disabled and no more events - * would happen. But for the second one, the irq may be enabled (e.g. - * for MSI). So we disable irq here to prevent further events. + * We disable irq here to prevent further events. * * Notice this maybe result in nested disable if the interrupt type is * INTx, but it's OK for we are going to free it. * * If this function is a part of VM destroy, please ensure that till * now, the kvm state is still legal for probably we also have to wait - * interrupt_work done. + * on a currently running IRQ handler. */ if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { int i; for (i = 0; i < assigned_dev->entries_nr; i++) - disable_irq_nosync(assigned_dev-> - host_msix_entries[i].vector); - - cancel_work_sync(&assigned_dev->interrupt_work); + disable_irq(assigned_dev->host_msix_entries[i].vector); for (i = 0; i < assigned_dev->entries_nr; i++) free_irq(assigned_dev->host_msix_entries[i].vector, - (void *)assigned_dev); + assigned_dev); assigned_dev->entries_nr = 0; kfree(assigned_dev->host_msix_entries); @@ -186,10 +240,17 @@ static void deassign_host_irq(struct kvm *kvm, pci_disable_msix(assigned_dev->dev); } else { /* Deal with MSI and INTx */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); - - free_irq(assigned_dev->host_irq, (void *)assigned_dev); + if ((assigned_dev->irq_requested_type & + KVM_DEV_IRQ_HOST_INTX) && + (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) { + spin_lock_irq(&assigned_dev->intx_lock); + pci_intx(assigned_dev->dev, false); + spin_unlock_irq(&assigned_dev->intx_lock); + synchronize_irq(assigned_dev->host_irq); + } else + disable_irq(assigned_dev->host_irq); + + free_irq(assigned_dev->host_irq, assigned_dev); if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) pci_disable_msi(assigned_dev->dev); @@ -234,6 +295,14 @@ static void kvm_free_assigned_device(struct kvm *kvm, kvm_free_assigned_irq(kvm, assigned_dev); pci_reset_function(assigned_dev->dev); + if (pci_load_and_free_saved_state(assigned_dev->dev, + &assigned_dev->pci_saved_state)) + printk(KERN_INFO "%s: Couldn't reload %s saved state\n", + __func__, dev_name(&assigned_dev->dev->dev)); + else + pci_restore_state(assigned_dev->dev); + + assigned_dev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED; pci_release_regions(assigned_dev->dev); pci_disable_device(assigned_dev->dev); @@ -260,15 +329,34 @@ void kvm_free_all_assigned_devices(struct kvm *kvm) static int assigned_device_enable_host_intx(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { + irq_handler_t irq_handler; + unsigned long flags; + 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. + + /* + * We can only share the IRQ line with other host devices if we are + * able to disable the IRQ source at device-level - independently of + * the guest driver. Otherwise host devices may suffer from unbounded + * IRQ latencies when the guest keeps the line asserted. */ - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)dev)) + if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) { + irq_handler = kvm_assigned_dev_intx; + flags = IRQF_SHARED; + } else { + irq_handler = NULL; + flags = IRQF_ONESHOT; + } + if (request_threaded_irq(dev->host_irq, irq_handler, + kvm_assigned_dev_thread_intx, flags, + dev->irq_name, dev)) return -EIO; + + if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) { + spin_lock_irq(&dev->intx_lock); + pci_intx(dev->dev, true); + spin_unlock_irq(&dev->intx_lock); + } return 0; } @@ -285,8 +373,9 @@ static int assigned_device_enable_host_msi(struct kvm *kvm, } dev->host_irq = dev->dev->irq; - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)dev)) { + if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi, + kvm_assigned_dev_thread_msi, 0, + dev->irq_name, dev)) { pci_disable_msi(dev->dev); return -EIO; } @@ -306,21 +395,26 @@ static int assigned_device_enable_host_msix(struct kvm *kvm, if (dev->entries_nr == 0) return r; - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + r = pci_enable_msix_exact(dev->dev, + dev->host_msix_entries, dev->entries_nr); if (r) return r; for (i = 0; i < dev->entries_nr; i++) { - r = request_irq(dev->host_msix_entries[i].vector, - kvm_assigned_dev_intr, 0, - "kvm_assigned_msix_device", - (void *)dev); - /* FIXME: free requested_irq's on failure */ + r = request_threaded_irq(dev->host_msix_entries[i].vector, + kvm_assigned_dev_msix, + kvm_assigned_dev_thread_msix, + 0, dev->irq_name, dev); if (r) - return r; + goto err; } return 0; +err: + for (i -= 1; i >= 0; i--) + free_irq(dev->host_msix_entries[i].vector, dev); + pci_disable_msix(dev->dev); + return r; } #endif @@ -341,7 +435,6 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm, { dev->guest_irq = irq->guest_irq; dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; return 0; } #endif @@ -353,7 +446,6 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm, { dev->guest_irq = irq->guest_irq; dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; return 0; } #endif @@ -367,6 +459,9 @@ static int assign_host_irq(struct kvm *kvm, if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) return r; + snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s", + pci_name(dev->dev)); + switch (host_irq_type) { case KVM_DEV_IRQ_HOST_INTX: r = assigned_device_enable_host_intx(kvm, dev); @@ -384,6 +479,7 @@ static int assign_host_irq(struct kvm *kvm, default: r = -EINVAL; } + dev->host_irq_disabled = false; if (!r) dev->irq_requested_type |= host_irq_type; @@ -428,7 +524,8 @@ static int assign_guest_irq(struct kvm *kvm, if (!r) { dev->irq_requested_type |= guest_irq_type; - kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); + if (dev->ack_notifier.gsi != -1) + kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); } else kvm_free_irq_source_id(kvm, dev->irq_source_id); @@ -443,9 +540,6 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, struct kvm_assigned_dev_kernel *match; unsigned long host_irq_type, guest_irq_type; - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - if (!irqchip_in_kernel(kvm)) return r; @@ -487,6 +581,7 @@ static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, { int r = -ENODEV; struct kvm_assigned_dev_kernel *match; + unsigned long irq_type; mutex_lock(&kvm->lock); @@ -495,21 +590,86 @@ static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, if (!match) goto out; - r = kvm_deassign_irq(kvm, match, assigned_irq->flags); + irq_type = assigned_irq->flags & (KVM_DEV_IRQ_HOST_MASK | + KVM_DEV_IRQ_GUEST_MASK); + r = kvm_deassign_irq(kvm, match, irq_type); out: mutex_unlock(&kvm->lock); return r; } +/* + * We want to test whether the caller has been granted permissions to + * use this device. To be able to configure and control the device, + * the user needs access to PCI configuration space and BAR resources. + * These are accessed through PCI sysfs. PCI config space is often + * passed to the process calling this ioctl via file descriptor, so we + * can't rely on access to that file. We can check for permissions + * on each of the BAR resource files, which is a pretty clear + * indicator that the user has been granted access to the device. + */ +static int probe_sysfs_permissions(struct pci_dev *dev) +{ +#ifdef CONFIG_SYSFS + int i; + bool bar_found = false; + + for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) { + char *kpath, *syspath; + struct path path; + struct inode *inode; + int r; + + if (!pci_resource_len(dev, i)) + continue; + + kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); + if (!kpath) + return -ENOMEM; + + /* Per sysfs-rules, sysfs is always at /sys */ + syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i); + kfree(kpath); + if (!syspath) + return -ENOMEM; + + r = kern_path(syspath, LOOKUP_FOLLOW, &path); + kfree(syspath); + if (r) + return r; + + inode = path.dentry->d_inode; + + r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS); + path_put(&path); + if (r) + return r; + + bar_found = true; + } + + /* If no resources, probably something special */ + if (!bar_found) + return -EPERM; + + return 0; +#else + return -EINVAL; /* No way to control the device without sysfs */ +#endif +} + static int kvm_vm_ioctl_assign_device(struct kvm *kvm, struct kvm_assigned_pci_dev *assigned_dev) { - int r = 0; + int r = 0, idx; struct kvm_assigned_dev_kernel *match; struct pci_dev *dev; + if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)) + return -EINVAL; + mutex_lock(&kvm->lock); - down_read(&kvm->slots_lock); + idx = srcu_read_lock(&kvm->srcu); match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, assigned_dev->assigned_dev_id); @@ -526,13 +686,25 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, r = -ENOMEM; goto out; } - dev = pci_get_bus_and_slot(assigned_dev->busnr, + dev = pci_get_domain_bus_and_slot(assigned_dev->segnr, + assigned_dev->busnr, assigned_dev->devfn); if (!dev) { printk(KERN_INFO "%s: host device not found\n", __func__); r = -EINVAL; goto out_free; } + + /* Don't allow bridges to be assigned */ + if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL) { + r = -EPERM; + goto out_put; + } + + r = probe_sysfs_permissions(dev); + if (r) + goto out_put; + if (pci_enable_device(dev)) { printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); r = -EBUSY; @@ -546,37 +718,46 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, } pci_reset_function(dev); + pci_save_state(dev); + match->pci_saved_state = pci_store_saved_state(dev); + if (!match->pci_saved_state) + printk(KERN_DEBUG "%s: Couldn't store %s saved state\n", + __func__, dev_name(&dev->dev)); + + if (!pci_intx_mask_supported(dev)) + assigned_dev->flags &= ~KVM_DEV_ASSIGN_PCI_2_3; match->assigned_dev_id = assigned_dev->assigned_dev_id; + match->host_segnr = assigned_dev->segnr; match->host_busnr = assigned_dev->busnr; match->host_devfn = assigned_dev->devfn; match->flags = assigned_dev->flags; match->dev = dev; - spin_lock_init(&match->assigned_dev_lock); + spin_lock_init(&match->intx_lock); + spin_lock_init(&match->intx_mask_lock); match->irq_source_id = -1; match->kvm = kvm; match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); list_add(&match->list, &kvm->arch.assigned_dev_head); - if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match); + if (!kvm->arch.iommu_domain) { + r = kvm_iommu_map_guest(kvm); if (r) goto out_list_del; } + r = kvm_assign_device(kvm, match); + if (r) + goto out_list_del; out: - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); return r; out_list_del: + if (pci_load_and_free_saved_state(dev, &match->pci_saved_state)) + printk(KERN_INFO "%s: Couldn't reload %s saved state\n", + __func__, dev_name(&dev->dev)); list_del(&match->list); pci_release_regions(dev); out_disable: @@ -585,7 +766,7 @@ out_put: pci_dev_put(dev); out_free: kfree(match); - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); return r; } @@ -607,8 +788,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, goto out; } - if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) - kvm_deassign_device(kvm, match); + kvm_deassign_device(kvm, match); kvm_free_assigned_device(kvm, match); @@ -637,7 +817,7 @@ static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, 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) { + adev->entries_nr > KVM_MAX_MSIX_PER_DEV) { r = -EINVAL; goto msix_nr_out; } @@ -649,9 +829,9 @@ static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, r = -ENOMEM; goto msix_nr_out; } - adev->guest_msix_entries = kzalloc( - sizeof(struct kvm_guest_msix_entry) * - entry_nr->entry_nr, GFP_KERNEL); + adev->guest_msix_entries = + kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr, + GFP_KERNEL); if (!adev->guest_msix_entries) { kfree(adev->host_msix_entries); r = -ENOMEM; @@ -700,11 +880,60 @@ msix_entry_out: } #endif +static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (!match) { + r = -ENODEV; + goto out; + } + + spin_lock(&match->intx_mask_lock); + + match->flags &= ~KVM_DEV_ASSIGN_MASK_INTX; + match->flags |= assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX; + + if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { + if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) { + kvm_set_irq(match->kvm, match->irq_source_id, + match->guest_irq, 0, false); + /* + * Masking at hardware-level is performed on demand, + * i.e. when an IRQ actually arrives at the host. + */ + } else if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) { + /* + * Unmask the IRQ line if required. Unmasking at + * device level will be performed by user space. + */ + spin_lock_irq(&match->intx_lock); + if (match->host_irq_disabled) { + enable_irq(match->host_irq); + match->host_irq_disabled = false; + } + spin_unlock_irq(&match->intx_lock); + } + } + + spin_unlock(&match->intx_mask_lock); + +out: + mutex_unlock(&kvm->lock); + return r; +} + long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; - int r = -ENOTTY; + int r; switch (ioctl) { case KVM_ASSIGN_PCI_DEVICE: { @@ -722,7 +951,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, r = -EOPNOTSUPP; break; } -#ifdef KVM_CAP_ASSIGN_DEV_IRQ case KVM_ASSIGN_DEV_IRQ: { struct kvm_assigned_irq assigned_irq; @@ -745,8 +973,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#endif -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT case KVM_DEASSIGN_PCI_DEVICE: { struct kvm_assigned_pci_dev assigned_dev; @@ -758,37 +984,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#endif -#ifdef KVM_CAP_IRQ_ROUTING - case KVM_SET_GSI_ROUTING: { - struct kvm_irq_routing routing; - struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; - - r = -EFAULT; - if (copy_from_user(&routing, argp, sizeof(routing))) - goto out; - r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) - goto out; - if (routing.flags) - goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; - r = kvm_set_irq_routing(kvm, entries, routing.nr, - routing.flags); - out_free_irq_routing: - vfree(entries); - break; - } -#endif /* KVM_CAP_IRQ_ROUTING */ #ifdef __KVM_HAVE_MSIX case KVM_ASSIGN_SET_MSIX_NR: { struct kvm_assigned_msix_nr entry_nr; @@ -811,8 +1006,19 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, break; } #endif + case KVM_ASSIGN_SET_INTX_MASK: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_set_pci_irq_mask(kvm, &assigned_dev); + break; + } + default: + r = -ENOTTY; + break; } out: return r; } - |