diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-08 12:37:56 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-08 12:37:56 -0700 |
commit | 2d3e4866dea96b0506395b47bfefb234f2088dac (patch) | |
tree | d5c7bd97d222bef46f9d73adee8c79dbdb9f82f4 /arch/x86/kvm | |
parent | 9c6ee01ed5bb1ee489d580eaa60d7eb5a8ede336 (diff) | |
parent | 2e5b0bd9cc6172edef502dfae28ae790f74a882e (diff) |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"ARM:
- HYP mode stub supports kexec/kdump on 32-bit
- improved PMU support
- virtual interrupt controller performance improvements
- support for userspace virtual interrupt controller (slower, but
necessary for KVM on the weird Broadcom SoCs used by the Raspberry
Pi 3)
MIPS:
- basic support for hardware virtualization (ImgTec P5600/P6600/I6400
and Cavium Octeon III)
PPC:
- in-kernel acceleration for VFIO
s390:
- support for guests without storage keys
- adapter interruption suppression
x86:
- usual range of nVMX improvements, notably nested EPT support for
accessed and dirty bits
- emulation of CPL3 CPUID faulting
generic:
- first part of VCPU thread request API
- kvm_stat improvements"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
kvm: nVMX: Don't validate disabled secondary controls
KVM: put back #ifndef CONFIG_S390 around kvm_vcpu_kick
Revert "KVM: Support vCPU-based gfn->hva cache"
tools/kvm: fix top level makefile
KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING
KVM: Documentation: remove VM mmap documentation
kvm: nVMX: Remove superfluous VMX instruction fault checks
KVM: x86: fix emulation of RSM and IRET instructions
KVM: mark requests that need synchronization
KVM: return if kvm_vcpu_wake_up() did wake up the VCPU
KVM: add explicit barrier to kvm_vcpu_kick
KVM: perform a wake_up in kvm_make_all_cpus_request
KVM: mark requests that do not need a wakeup
KVM: remove #ifndef CONFIG_S390 around kvm_vcpu_wake_up
KVM: x86: always use kvm_make_request instead of set_bit
KVM: add kvm_{test,clear}_request to replace {test,clear}_bit
s390: kvm: Cpu model support for msa6, msa7 and msa8
KVM: x86: remove irq disablement around KVM_SET_CLOCK/KVM_GET_CLOCK
kvm: better MWAIT emulation for guests
KVM: x86: virtualize cpuid faulting
...
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 12 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/kvm/assigned-dev.c | 1058 | ||||
-rw-r--r-- | arch/x86/kvm/assigned-dev.h | 32 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.h | 11 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 23 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 72 | ||||
-rw-r--r-- | arch/x86/kvm/ioapic.c | 28 | ||||
-rw-r--r-- | arch/x86/kvm/ioapic.h | 16 | ||||
-rw-r--r-- | arch/x86/kvm/iommu.c | 356 | ||||
-rw-r--r-- | arch/x86/kvm/irq.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/irq.h | 32 | ||||
-rw-r--r-- | arch/x86/kvm/irq_comm.c | 50 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 22 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 3 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 54 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 14 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 332 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 256 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 36 |
22 files changed, 446 insertions, 1972 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ab8e32f7b9a8..760433b2574a 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -86,18 +86,6 @@ config KVM_MMU_AUDIT This option adds a R/W kVM module parameter 'mmu_audit', which allows auditing of KVM MMU events at runtime. -config KVM_DEVICE_ASSIGNMENT - bool "KVM legacy PCI device assignment support (DEPRECATED)" - depends on KVM && PCI && IOMMU_API - default n - ---help--- - Provide support for legacy PCI device assignment through KVM. The - kernel now also supports a full featured userspace device driver - framework through VFIO, which supersedes this support and provides - better security. - - If unsure, say N. - # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/vhost/Kconfig diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 3bff20710471..09d4b17be022 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -15,8 +15,6 @@ kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ hyperv.o page_track.o debugfs.o -kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o - kvm-intel-y += vmx.o pmu_intel.o kvm-amd-y += svm.o pmu_amd.o diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c deleted file mode 100644 index 308b8597c691..000000000000 --- a/arch/x86/kvm/assigned-dev.c +++ /dev/null @@ -1,1058 +0,0 @@ -/* - * Kernel-based Virtual Machine - device assignment support - * - * 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. - * - */ - -#include <linux/kvm_host.h> -#include <linux/kvm.h> -#include <linux/uaccess.h> -#include <linux/vmalloc.h> -#include <linux/errno.h> -#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" -#include "assigned-dev.h" -#include "trace/events/kvm.h" - -struct kvm_assigned_dev_kernel { - struct kvm_irq_ack_notifier ack_notifier; - struct list_head list; - int assigned_dev_id; - int host_segnr; - int host_busnr; - int host_devfn; - unsigned int entries_nr; - int host_irq; - bool host_irq_disabled; - bool pci_2_3; - struct msix_entry *host_msix_entries; - int guest_irq; - struct msix_entry *guest_msix_entries; - unsigned long irq_requested_type; - int irq_source_id; - int flags; - struct pci_dev *dev; - struct kvm *kvm; - spinlock_t intx_lock; - spinlock_t intx_mask_lock; - char irq_name[32]; - struct pci_saved_state *pci_saved_state; -}; - -static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, - int assigned_dev_id) -{ - struct kvm_assigned_dev_kernel *match; - - list_for_each_entry(match, head, list) { - if (match->assigned_dev_id == assigned_dev_id) - return match; - } - return NULL; -} - -static int find_index_from_host_irq(struct kvm_assigned_dev_kernel - *assigned_dev, int irq) -{ - int i, index; - struct msix_entry *host_msix_entries; - - host_msix_entries = assigned_dev->host_msix_entries; - - index = -1; - for (i = 0; i < assigned_dev->entries_nr; i++) - if (irq == host_msix_entries[i].vector) { - index = i; - break; - } - if (index < 0) - printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); - - return index; -} - -static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id) -{ - 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); - - return ret; -} - -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, vector, 1, - false); - spin_unlock(&assigned_dev->intx_mask_lock); - } else - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - 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; -} - -/* - * Deliver an IRQ in an atomic context if we can, or return a failure, - * user can retry in a process context. - * Return value: - * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context. - * Other values - No need to retry. - */ -static int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, - int level) -{ - struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; - struct kvm_kernel_irq_routing_entry *e; - int ret = -EINVAL; - int idx; - - trace_kvm_set_irq(irq, level, irq_source_id); - - /* - * Injection into either PIC or IOAPIC might need to scan all CPUs, - * which would need to be retried from thread context; when same GSI - * is connected to both PIC and IOAPIC, we'd have to report a - * partial failure here. - * Since there's no easy way to do this, we only support injecting MSI - * which is limited to 1:1 GSI mapping. - */ - idx = srcu_read_lock(&kvm->irq_srcu); - if (kvm_irq_map_gsi(kvm, entries, irq) > 0) { - e = &entries[0]; - ret = kvm_arch_set_irq_inatomic(e, kvm, irq_source_id, - irq, level); - } - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} - - -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_thread_msi(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - - kvm_assigned_dev_raise_guest_irq(assigned_dev, - assigned_dev->guest_irq); - - return IRQ_HANDLED; -} - -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); - } - - return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED; -} - -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); - } - - return IRQ_HANDLED; -} - -/* Ack the irq line for an assigned device */ -static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) -{ - struct kvm_assigned_dev_kernel *dev = - 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); - - if (reassert) - kvm_set_irq(dev->kvm, dev->irq_source_id, - dev->guest_irq, 1, false); - } - - spin_unlock(&dev->intx_mask_lock); -} - -static void deassign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - 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); - assigned_dev->irq_source_id = -1; - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); -} - -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void deassign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - /* - * 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 - * 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(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, - assigned_dev); - - assigned_dev->entries_nr = 0; - kfree(assigned_dev->host_msix_entries); - kfree(assigned_dev->guest_msix_entries); - pci_disable_msix(assigned_dev->dev); - } else { - /* Deal with MSI and INTx */ - 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); - } - - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); -} - -static int kvm_deassign_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev, - unsigned long irq_requested_type) -{ - unsigned long guest_irq_type, host_irq_type; - - if (!irqchip_in_kernel(kvm)) - return -EINVAL; - /* no irq assignment to deassign */ - if (!assigned_dev->irq_requested_type) - return -ENXIO; - - host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; - guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; - - if (host_irq_type) - deassign_host_irq(kvm, assigned_dev); - if (guest_irq_type) - deassign_guest_irq(kvm, assigned_dev); - - return 0; -} - -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); -} - -static void kvm_free_assigned_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel - *assigned_dev) -{ - kvm_free_assigned_irq(kvm, assigned_dev); - - pci_reset_function(assigned_dev->dev); - 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); - - pci_clear_dev_assigned(assigned_dev->dev); - - pci_release_regions(assigned_dev->dev); - pci_disable_device(assigned_dev->dev); - pci_dev_put(assigned_dev->dev); - - list_del(&assigned_dev->list); - kfree(assigned_dev); -} - -void kvm_free_all_assigned_devices(struct kvm *kvm) -{ - struct kvm_assigned_dev_kernel *assigned_dev, *tmp; - - list_for_each_entry_safe(assigned_dev, tmp, - &kvm->arch.assigned_dev_head, list) { - kvm_free_assigned_device(kvm, assigned_dev); - } -} - -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; - - /* - * 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 (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; -} - -static int assigned_device_enable_host_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int r; - - if (!dev->dev->msi_enabled) { - r = pci_enable_msi(dev->dev); - if (r) - return r; - } - - dev->host_irq = dev->dev->irq; - if (request_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; - } - - return 0; -} - -static int assigned_device_enable_host_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int i, r = -EINVAL; - - /* host_msix_entries and guest_msix_entries should have been - * initialized */ - if (dev->entries_nr == 0) - return r; - - r = pci_enable_msix_exact(dev->dev, - dev->host_msix_entries, dev->entries_nr); - if (r) - return r; - - for (i = 0; i < dev->entries_nr; i++) { - 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) - 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; -} - -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; -} - -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; -} - -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; -} - -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; - - 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); - break; - case KVM_DEV_IRQ_HOST_MSI: - r = assigned_device_enable_host_msi(kvm, dev); - break; - case KVM_DEV_IRQ_HOST_MSIX: - r = assigned_device_enable_host_msix(kvm, dev); - break; - default: - r = -EINVAL; - } - dev->host_irq_disabled = false; - - if (!r) - dev->irq_requested_type |= host_irq_type; - - return r; -} - -static int assign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq, - unsigned long guest_irq_type) -{ - int id; - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) - return r; - - id = kvm_request_irq_source_id(kvm); - if (id < 0) - return id; - - dev->irq_source_id = id; - - switch (guest_irq_type) { - case KVM_DEV_IRQ_GUEST_INTX: - r = assigned_device_enable_guest_intx(kvm, dev, irq); - break; - case KVM_DEV_IRQ_GUEST_MSI: - r = assigned_device_enable_guest_msi(kvm, dev, irq); - break; - case KVM_DEV_IRQ_GUEST_MSIX: - r = assigned_device_enable_guest_msix(kvm, dev, irq); - break; - default: - r = -EINVAL; - } - - if (!r) { - dev->irq_requested_type |= guest_irq_type; - 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); - dev->irq_source_id = -1; - } - - return r; -} - -/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ -static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq *assigned_irq) -{ - int r = -EINVAL; - struct kvm_assigned_dev_kernel *match; - unsigned long host_irq_type, guest_irq_type; - - if (!irqchip_in_kernel(kvm)) - return r; - - mutex_lock(&kvm->lock); - r = -ENODEV; - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); - guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - - r = -EINVAL; - /* can only assign one type at a time */ - if (hweight_long(host_irq_type) > 1) - goto out; - if (hweight_long(guest_irq_type) > 1) - goto out; - if (host_irq_type == 0 && guest_irq_type == 0) - goto out; - - r = 0; - if (host_irq_type) - r = assign_host_irq(kvm, match, host_irq_type); - if (r) - goto out; - - if (guest_irq_type) - r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) -{ - int r = -ENODEV; - struct kvm_assigned_dev_kernel *match; - unsigned long irq_type; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - 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 = d_backing_inode(path.dentry); - - 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, 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); - idx = srcu_read_lock(&kvm->srcu); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (match) { - /* device already assigned */ - r = -EEXIST; - goto out; - } - - match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); - if (match == NULL) { - printk(KERN_INFO "%s: Couldn't allocate memory\n", - __func__); - r = -ENOMEM; - goto out; - } - dev = pci_get_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; - goto out_put; - } - r = pci_request_regions(dev, "kvm_assigned_device"); - if (r) { - printk(KERN_INFO "%s: Could not get access to device regions\n", - __func__); - goto out_disable; - } - - pci_reset_function(dev); - 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->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; - - list_add(&match->list, &kvm->arch.assigned_dev_head); - - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match->dev); - if (r) - goto out_list_del; - -out: - 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: - pci_disable_device(dev); -out_put: - pci_dev_put(dev); -out_free: - kfree(match); - srcu_read_unlock(&kvm->srcu, idx); - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (!match) { - printk(KERN_INFO "%s: device hasn't been assigned before, " - "so cannot be deassigned\n", __func__); - r = -EINVAL; - goto out; - } - - kvm_deassign_device(kvm, match->dev); - - kvm_free_assigned_device(kvm, match); - -out: - mutex_unlock(&kvm->lock); - return r; -} - - -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 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; -} - -static int kvm_vm_ioctl_set_pci_irq_mask(struct k |