KVM: x86: drop legacy device assignment

Legacy device assignment has been deprecated since 4.2 (released
1.5 years ago).  VFIO is better and everyone should have switched to it.
If they haven't, this should convince them. :)
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -1326,130 +1326,6 @@ The flags bitmap is defined as:
    /* the host supports the ePAPR idle hcall
    #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
 
-4.48 KVM_ASSIGN_PCI_DEVICE (deprecated)
-
-Capability: none
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_pci_dev (in)
-Returns: 0 on success, -1 on error
-
-Assigns a host PCI device to the VM.
-
-struct kvm_assigned_pci_dev {
-	__u32 assigned_dev_id;
-	__u32 busnr;
-	__u32 devfn;
-	__u32 flags;
-	__u32 segnr;
-	union {
-		__u32 reserved[11];
-	};
-};
-
-The PCI device is specified by the triple segnr, busnr, and devfn.
-Identification in succeeding service requests is done via assigned_dev_id. The
-following flags are specified:
-
-/* Depends on KVM_CAP_IOMMU */
-#define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
-/* The following two depend on KVM_CAP_PCI_2_3 */
-#define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
-#define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
-
-If KVM_DEV_ASSIGN_PCI_2_3 is set, the kernel will manage legacy INTx interrupts
-via the PCI-2.3-compliant device-level mask, thus enable IRQ sharing with other
-assigned devices or host devices. KVM_DEV_ASSIGN_MASK_INTX specifies the
-guest's view on the INTx mask, see KVM_ASSIGN_SET_INTX_MASK for details.
-
-The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
-isolation of the device.  Usages not specifying this flag are deprecated.
-
-Only PCI header type 0 devices with PCI BAR resources are supported by
-device assignment.  The user requesting this ioctl must have read/write
-access to the PCI sysfs resource files associated with the device.
-
-Errors:
-  ENOTTY: kernel does not support this ioctl
-
-  Other error conditions may be defined by individual device types or
-  have their standard meanings.
-
-
-4.49 KVM_DEASSIGN_PCI_DEVICE (deprecated)
-
-Capability: none
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_pci_dev (in)
-Returns: 0 on success, -1 on error
-
-Ends PCI device assignment, releasing all associated resources.
-
-See KVM_ASSIGN_PCI_DEVICE for the data structure. Only assigned_dev_id is
-used in kvm_assigned_pci_dev to identify the device.
-
-Errors:
-  ENOTTY: kernel does not support this ioctl
-
-  Other error conditions may be defined by individual device types or
-  have their standard meanings.
-
-4.50 KVM_ASSIGN_DEV_IRQ (deprecated)
-
-Capability: KVM_CAP_ASSIGN_DEV_IRQ
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_irq (in)
-Returns: 0 on success, -1 on error
-
-Assigns an IRQ to a passed-through device.
-
-struct kvm_assigned_irq {
-	__u32 assigned_dev_id;
-	__u32 host_irq; /* ignored (legacy field) */
-	__u32 guest_irq;
-	__u32 flags;
-	union {
-		__u32 reserved[12];
-	};
-};
-
-The following flags are defined:
-
-#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)
-
-It is not valid to specify multiple types per host or guest IRQ. However, the
-IRQ type of host and guest can differ or can even be null.
-
-Errors:
-  ENOTTY: kernel does not support this ioctl
-
-  Other error conditions may be defined by individual device types or
-  have their standard meanings.
-
-
-4.51 KVM_DEASSIGN_DEV_IRQ (deprecated)
-
-Capability: KVM_CAP_ASSIGN_DEV_IRQ
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_irq (in)
-Returns: 0 on success, -1 on error
-
-Ends an IRQ assignment to a passed-through device.
-
-See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
-by assigned_dev_id, flags must correspond to the IRQ type specified on
-KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
-
-
 4.52 KVM_SET_GSI_ROUTING
 
 Capability: KVM_CAP_IRQ_ROUTING
@@ -1536,52 +1412,6 @@ struct kvm_irq_routing_hv_sint {
 	__u32 sint;
 };
 
-4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated)
-
-Capability: none
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_msix_nr (in)
-Returns: 0 on success, -1 on error
-
-Set the number of MSI-X interrupts for an assigned device. The number is
-reset again by terminating the MSI-X assignment of the device via
-KVM_DEASSIGN_DEV_IRQ. Calling this service more than once at any earlier
-point will fail.
-
-struct kvm_assigned_msix_nr {
-	__u32 assigned_dev_id;
-	__u16 entry_nr;
-	__u16 padding;
-};
-
-#define KVM_MAX_MSIX_PER_DEV		256
-
-
-4.54 KVM_ASSIGN_SET_MSIX_ENTRY (deprecated)
-
-Capability: none
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_msix_entry (in)
-Returns: 0 on success, -1 on error
-
-Specifies the routing of an MSI-X assigned device interrupt to a GSI. Setting
-the GSI vector to zero means disabling the interrupt.
-
-struct kvm_assigned_msix_entry {
-	__u32 assigned_dev_id;
-	__u32 gsi;
-	__u16 entry; /* The index of entry in the MSI-X table */
-	__u16 padding[3];
-};
-
-Errors:
-  ENOTTY: kernel does not support this ioctl
-
-  Other error conditions may be defined by individual device types or
-  have their standard meanings.
-
 
 4.55 KVM_SET_TSC_KHZ
 
@@ -1733,40 +1563,6 @@ should skip processing the bitmap and just invalidate everything.  It must
 be set to the number of set bits in the bitmap.
 
 
-4.61 KVM_ASSIGN_SET_INTX_MASK (deprecated)
-
-Capability: KVM_CAP_PCI_2_3
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_assigned_pci_dev (in)
-Returns: 0 on success, -1 on error
-
-Allows userspace to mask PCI INTx interrupts from the assigned device.  The
-kernel will not deliver INTx interrupts to the guest between setting and
-clearing of KVM_ASSIGN_SET_INTX_MASK via this interface.  This enables use of
-and emulation of PCI 2.3 INTx disable command register behavior.
-
-This may be used for both PCI 2.3 devices supporting INTx disable natively and
-older devices lacking this support. Userspace is responsible for emulating the
-read value of the INTx disable bit in the guest visible PCI command register.
-When modifying the INTx disable state, userspace should precede updating the
-physical device command register by calling this ioctl to inform the kernel of
-the new intended INTx mask state.
-
-Note that the kernel uses the device INTx disable bit to internally manage the
-device interrupt state for PCI 2.3 devices.  Reads of this register may
-therefore not match the expected value.  Writes should always use the guest
-intended INTx disable value rather than attempting to read-copy-update the
-current physical device state.  Races between user and kernel updates to the
-INTx disable bit are handled lazily in the kernel.  It's possible the device
-may generate unintended interrupts, but they will not be injected into the
-guest.
-
-See KVM_ASSIGN_DEV_IRQ for the data structure.  The target device is specified
-by assigned_dev_id.  In the flags field, only KVM_DEV_ASSIGN_MASK_INTX is
-evaluated.
-
-
 4.62 KVM_CREATE_SPAPR_TCE
 
 Capability: KVM_CAP_SPAPR_TCE

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

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
 

arch/x86/kvm/assigned-dev.c

-/*
- * 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 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;
-
-	switch (ioctl) {
-	case KVM_ASSIGN_PCI_DEVICE: {
-		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_assign_device(kvm, &assigned_dev);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_ASSIGN_IRQ: {
-		r = -EOPNOTSUPP;
-		break;
-	}
-	case KVM_ASSIGN_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_assign_irq(kvm, &assigned_irq);
-		if (r)
-			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;
-	}
-	case KVM_DEASSIGN_PCI_DEVICE: {
-		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_deassign_device(kvm, &assigned_dev);
-		if (r)
-			goto out;
-		break;
-	}
-	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;
-	}
-	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;
-}

arch/x86/kvm/assigned-dev.h

-#ifndef ARCH_X86_KVM_ASSIGNED_DEV_H
-#define ARCH_X86_KVM_ASSIGNED_DEV_H
-
-#include <linux/kvm_host.h>
-
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
-int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev);
-int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev);
-
-int kvm_iommu_map_guest(struct kvm *kvm);
-int kvm_iommu_unmap_guest(struct kvm *kvm);
-
-long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-				  unsigned long arg);
-
-void kvm_free_all_assigned_devices(struct kvm *kvm);
-#else
-static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
-{
-	return 0;
-}
-
-static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-						unsigned long arg)
-{
-	return -ENOTTY;
-}
-
-static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
-#endif /* CONFIG_KVM_DEVICE_ASSIGNMENT */
-
-#endif /* ARCH_X86_KVM_ASSIGNED_DEV_H */

arch/x86/kvm/iommu.c

-/*
- * Copyright (c) 2006, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
- * Copyright (C) 2006-2008 Intel Corporation
- * Copyright IBM Corporation, 2008
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- * Author: Allen M. Kay <allen.m.kay@intel.com>
- * Author: Weidong Han <weidong.han@intel.com>
- * Author: Ben-Ami Yassour <benami@il.ibm.com>
- */
-
-#include <linux/list.h>
-#include <linux/kvm_host.h>
-#include <linux/moduleparam.h>
-#include <linux/pci.h>
-#include <linux/stat.h>
-#include <linux/iommu.h>
-#include "assigned-dev.h"
-
-static bool allow_unsafe_assigned_interrupts;
-module_param_named(allow_unsafe_assigned_interrupts,
-		   allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(allow_unsafe_assigned_interrupts,
- "Enable device assignment on platforms without interrupt remapping support.");
-
-static int kvm_iommu_unmap_memslots(struct kvm *kvm);
-static void kvm_iommu_put_pages(struct kvm *kvm,
-				gfn_t base_gfn, unsigned long npages);
-
-static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
-			   unsigned long npages)
-{
-	gfn_t end_gfn;
-	kvm_pfn_t pfn;
-
-	pfn     = gfn_to_pfn_memslot(slot, gfn);
-	end_gfn = gfn + npages;
-	gfn    += 1;
-
-	if (is_error_noslot_pfn(pfn))
-		return pfn;
-
-	while (gfn < end_gfn)
-		gfn_to_pfn_memslot(slot, gfn++);
-
-	return pfn;
-}
-
-static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn,
-		unsigned long npages)
-{
-	unsigned long i;
-
-	for (i = 0; i < npages; ++i)
-		kvm_release_pfn_clean(pfn + i);
-}
-
-int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	gfn_t gfn, end_gfn;
-	kvm_pfn_t pfn;
-	int r = 0;
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int flags;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	gfn     = slot->base_gfn;
-	end_gfn = gfn + slot->npages;
-
-	flags = IOMMU_READ;
-	if (!(slot->flags & KVM_MEM_READONLY))
-		flags |= IOMMU_WRITE;
-	if (!kvm->arch.iommu_noncoherent)
-		flags |= IOMMU_CACHE;
-
-
-	while (gfn < end_gfn) {
-		unsigned long page_size;
-
-		/* Check if already mapped */
-		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
-			gfn += 1;
-			continue;
-		}
-
-		/* Get the page size we could use to map */
-		page_size = kvm_host_page_size(kvm, gfn);
-
-		/* Make sure the page_size does not exceed the memslot */
-		while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
-			page_size >>= 1;
-
-		/* Make sure gfn is aligned to the page size we want to map */
-		while ((gfn << PAGE_SHIFT) & (page_size - 1))
-			page_size >>= 1;
-
-		/* Make sure hva is aligned to the page size we want to map */
-		while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
-			page_size >>= 1;
-
-		/*
-		 * Pin all pages we are about to map in memory. This is
-		 * important because we unmap and unpin in 4kb steps later.
-		 */
-		pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
-		if (is_error_noslot_pfn(pfn)) {
-			gfn += 1;
-			continue;
-		}
-
-		/* Map into IO address space */
-		r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
-			      page_size, flags);
-		if (r) {
-			printk(KERN_ERR "kvm_iommu_map_address:"
-			       "iommu failed to map pfn=%llx\n", pfn);
-			kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
-			goto unmap_pages;
-		}
-
-		gfn += page_size >> PAGE_SHIFT;
-
-		cond_resched();
-	}
-
-	return 0;
-
-unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
-	return r;
-}
-
-static int kvm_iommu_map_memslots(struct kvm *kvm)
-{
-	int idx, r = 0;
-	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
-
-	if (kvm->arch.iommu_noncoherent)
-		kvm_arch_register_noncoherent_dma(kvm);
-
-	idx = srcu_read_lock(&kvm->srcu);
-	slots = kvm_memslots(kvm);
-
-	kvm_for_each_memslot(memslot, slots) {
-		r = kvm_iommu_map_pages(kvm, memslot);
-		if (r)
-			break;
-	}
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return r;
-}
-
-int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
-{
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int r;
-	bool noncoherent;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	if (pdev == NULL)
-		return -ENODEV;
-
-	r = iommu_attach_device(domain, &pdev->dev);
-	if (r) {
-		dev_err(&pdev->dev, "kvm assign device failed ret %d", r);
-		return r;
-	}
-
-	noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
-
-	/* Check if need to update IOMMU page table for guest memory */
-	if (noncoherent != kvm->arch.iommu_noncoherent) {
-		kvm_iommu_unmap_memslots(kvm);
-		kvm->arch.iommu_noncoherent = noncoherent;
-		r = kvm_iommu_map_memslots(kvm);
-		if (r)
-			goto out_unmap;
-	}
-
-	kvm_arch_start_assignment(kvm);
-	pci_set_dev_assigned(pdev);
-
-	dev_info(&pdev->dev, "kvm assign device\n");
-
-	return 0;
-out_unmap:
-	kvm_iommu_unmap_memslots(kvm);
-	return r;
-}
-
-int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
-{
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	if (pdev == NULL)
-		return -ENODEV;
-
-	iommu_detach_device(domain, &pdev->dev);
-
-	pci_clear_dev_assigned(pdev);
-	kvm_arch_end_assignment(kvm);
-
-	dev_info(&pdev->dev, "kvm deassign device\n");
-
-	return 0;
-}
-
-int kvm_iommu_map_guest(struct kvm *kvm)
-{
-	int r;
-
-	if (!iommu_present(&pci_bus_type)) {
-		printk(KERN_ERR "%s: iommu not found\n", __func__);
-		return -ENODEV;
-	}
-
-	mutex_lock(&kvm->slots_lock);
-
-	kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type);
-	if (!kvm->arch.iommu_domain) {
-		r = -ENOMEM;
-		goto out_unlock;
-	}
-
-	if (!allow_unsafe_assigned_interrupts &&
-	    !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
-		printk(KERN_WARNING "%s: No interrupt remapping support,"
-		       " disallowing device assignment."
-		       " Re-enable with \"allow_unsafe_assigned_interrupts=1\""
-		       " module option.\n", __func__);
-		iommu_domain_free(kvm->arch.iommu_domain);
-		kvm->arch.iommu_domain = NULL;
-		r = -EPERM;
-		goto out_unlock;
-	}
-
-	r = kvm_iommu_map_memslots(kvm);
-	if (r)
-		kvm_iommu_unmap_memslots(kvm);
-
-out_unlock:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
-}
-
-static void kvm_iommu_put_pages(struct kvm *kvm,
-				gfn_t base_gfn, unsigned long npages)
-{
-	struct iommu_domain *domain;
-	gfn_t end_gfn, gfn;
-	kvm_pfn_t pfn;
-	u64 phys;
-
-	domain  = kvm->arch.iommu_domain;
-	end_gfn = base_gfn + npages;
-	gfn     = base_gfn;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return;
-
-	while (gfn < end_gfn) {
-		unsigned long unmap_pages;
-		size_t size;
-
-		/* Get physical address */
-		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
-
-		if (!phys) {
-			gfn++;
-			continue;
-		}
-
-		pfn  = phys >> PAGE_SHIFT;
-
-		/* Unmap address from IO address space */
-		size       = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
-		unmap_pages = 1ULL << get_order(size);
-
-		/* Unpin all pages we just unmapped to not leak any memory */
-		kvm_unpin_pages(kvm, pfn, unmap_pages);
-
-		gfn += unmap_pages;
-
-		cond_resched();
-	}
-}
-
-void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	kvm_iommu_put_pages(kvm, slot->base_gfn, slot->npages);
-}
-
-static int kvm_iommu_unmap_memslots(struct kvm *kvm)
-{
-	int idx;
-	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	slots = kvm_memslots(kvm);
-
-	kvm_for_each_memslot(memslot, slots)
-		kvm_iommu_unmap_pages(kvm, memslot);
-
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	if (kvm->arch.iommu_noncoherent)
-		kvm_arch_unregister_noncoherent_dma(kvm);
-
-	return 0;
-}
-
-int kvm_iommu_unmap_guest(struct kvm *kvm)
-{
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	mutex_lock(&kvm->slots_lock);
-	kvm_iommu_unmap_memslots(kvm);
-	kvm->arch.iommu_domain = NULL;
-	kvm->arch.iommu_noncoherent = false;
-	mutex_unlock(&kvm->slots_lock);
-
-	iommu_domain_free(domain);
-	return 0;
-}

arch/x86/kvm/x86.c

@@ -27,7 +27,6 @@
 #include "kvm_cache_regs.h"
 #include "x86.h"
 #include "cpuid.h"
-#include "assigned-dev.h"
 #include "pmu.h"
 #include "hyperv.h"
 
@@ -2675,10 +2674,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
-	case KVM_CAP_ASSIGN_DEV_IRQ:
-	case KVM_CAP_PCI_2_3:
-#endif
 		r = 1;
 		break;
 	case KVM_CAP_ADJUST_CLOCK:
@@ -2713,11 +2708,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PV_MMU:	/* obsolete */
 		r = 0;
 		break;
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
-	case KVM_CAP_IOMMU:
-		r = iommu_present(&pci_bus_type);
-		break;
-#endif
 	case KVM_CAP_MCE:
 		r = KVM_MAX_MCE_BANKS;
 		break;
@@ -4230,7 +4220,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		break;
 	}
 	default:
-		r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
+		r = -ENOTTY;
 	}
 out:
 	return r;
@@ -8068,7 +8058,6 @@ void kvm_arch_sync_events(struct kvm *kvm)
 {
 	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
 	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
-	kvm_free_all_assigned_devices(kvm);
 	kvm_free_pit(kvm);
 }
 
@@ -8152,7 +8141,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 	if (kvm_x86_ops->vm_destroy)
 		kvm_x86_ops->vm_destroy(kvm);
-	kvm_iommu_unmap_guest(kvm);
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);

include/linux/kvm_host.h

@@ -877,22 +877,6 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
-int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
-void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
-#else
-static inline int kvm_iommu_map_pages(struct kvm *kvm,
-				      struct kvm_memory_slot *slot)
-{
-	return 0;
-}
-
-static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
-					 struct kvm_memory_slot *slot)
-{
-}
-#endif
-
 /*
  * search_memslots() and __gfn_to_memslot() are here because they are
  * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.

virt/kvm/kvm_main.c

@@ -1019,8 +1019,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 		old_memslots = install_new_memslots(kvm, as_id, slots);
 
-		/* slot was deleted or moved, clear iommu mapping */
-		kvm_iommu_unmap_pages(kvm, &old);
 		/* From this point no new shadow pages pointing to a deleted,
 		 * or moved, memslot will be created.
 		 *
@@ -1055,21 +1053,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_free_memslot(kvm, &old, &new);
 	kvfree(old_memslots);
-
-	/*
-	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
-	 * un-mapped and re-mapped if their base changes.  Since base change
-	 * unmapping is handled above with slot deletion, mapping alone is
-	 * needed here.  Anything else the iommu might care about for existing
-	 * slots (size changes, userspace addr changes and read-only flag
-	 * changes) is disallowed above, so any other attribute changes getting
-	 * here can be skipped.
-	 */
-	if (as_id == 0 && (change == KVM_MR_CREATE || change == KVM_MR_MOVE)) {
-		r = kvm_iommu_map_pages(kvm, &new);
-		return r;
-	}
-
 	return 0;
 
 out_slots: