mirror of
https://github.com/torvalds/linux.git
synced 2024-12-22 19:01:37 +00:00
5a0e3ad6af
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
822 lines
20 KiB
C
822 lines
20 KiB
C
/*
|
|
* Kernel-based Virtual Machine - device assignment support
|
|
*
|
|
* Copyright (C) 2006-9 Red Hat, Inc
|
|
*
|
|
* 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 "irq.h"
|
|
|
|
static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
|
|
int assigned_dev_id)
|
|
{
|
|
struct list_head *ptr;
|
|
struct kvm_assigned_dev_kernel *match;
|
|
|
|
list_for_each(ptr, head) {
|
|
match = list_entry(ptr, struct kvm_assigned_dev_kernel, 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 0;
|
|
}
|
|
|
|
return index;
|
|
}
|
|
|
|
static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
|
|
{
|
|
struct kvm_assigned_dev_kernel *assigned_dev;
|
|
struct kvm *kvm;
|
|
int i;
|
|
|
|
assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
|
|
interrupt_work);
|
|
kvm = assigned_dev->kvm;
|
|
|
|
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;
|
|
kvm_set_irq(assigned_dev->kvm,
|
|
assigned_dev->irq_source_id,
|
|
guest_entries[i].vector, 1);
|
|
}
|
|
} else
|
|
kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
|
|
assigned_dev->guest_irq, 1);
|
|
|
|
spin_unlock_irq(&assigned_dev->assigned_dev_lock);
|
|
}
|
|
|
|
static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
|
|
{
|
|
unsigned long flags;
|
|
struct kvm_assigned_dev_kernel *assigned_dev =
|
|
(struct kvm_assigned_dev_kernel *) dev_id;
|
|
|
|
spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
|
|
if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
|
|
int index = find_index_from_host_irq(assigned_dev, irq);
|
|
if (index < 0)
|
|
goto out;
|
|
assigned_dev->guest_msix_entries[index].flags |=
|
|
KVM_ASSIGNED_MSIX_PENDING;
|
|
}
|
|
|
|
schedule_work(&assigned_dev->interrupt_work);
|
|
|
|
if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
|
|
disable_irq_nosync(irq);
|
|
assigned_dev->host_irq_disabled = true;
|
|
}
|
|
|
|
out:
|
|
spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
|
|
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;
|
|
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);
|
|
|
|
/* The guest irq may be shared so this ack may be
|
|
* from another device.
|
|
*/
|
|
spin_lock_irqsave(&dev->assigned_dev_lock, flags);
|
|
if (dev->host_irq_disabled) {
|
|
enable_irq(dev->host_irq);
|
|
dev->host_irq_disabled = false;
|
|
}
|
|
spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
|
|
}
|
|
|
|
static void deassign_guest_irq(struct kvm *kvm,
|
|
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->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)
|
|
{
|
|
/*
|
|
* 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.
|
|
*
|
|
* 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.
|
|
*/
|
|
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);
|
|
|
|
for (i = 0; i < assigned_dev->entries_nr; i++)
|
|
free_irq(assigned_dev->host_msix_entries[i].vector,
|
|
(void *)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 */
|
|
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_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);
|
|
|
|
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 list_head *ptr, *ptr2;
|
|
struct kvm_assigned_dev_kernel *assigned_dev;
|
|
|
|
list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
|
|
assigned_dev = list_entry(ptr,
|
|
struct kvm_assigned_dev_kernel,
|
|
list);
|
|
|
|
kvm_free_assigned_device(kvm, assigned_dev);
|
|
}
|
|
}
|
|
|
|
static int assigned_device_enable_host_intx(struct kvm *kvm,
|
|
struct kvm_assigned_dev_kernel *dev)
|
|
{
|
|
dev->host_irq = dev->dev->irq;
|
|
/* Even though this is PCI, we don't want to use shared
|
|
* interrupts. Sharing host devices with guest-assigned devices
|
|
* on the same interrupt line is not a happy situation: there
|
|
* are going to be long delays in accepting, acking, etc.
|
|
*/
|
|
if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
|
|
0, "kvm_assigned_intx_device", (void *)dev))
|
|
return -EIO;
|
|
return 0;
|
|
}
|
|
|
|
#ifdef __KVM_HAVE_MSI
|
|
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_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
|
|
"kvm_assigned_msi_device", (void *)dev)) {
|
|
pci_disable_msi(dev->dev);
|
|
return -EIO;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef __KVM_HAVE_MSIX
|
|
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(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 */
|
|
if (r)
|
|
return r;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
#endif
|
|
|
|
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;
|
|
}
|
|
|
|
#ifdef __KVM_HAVE_MSI
|
|
static int assigned_device_enable_guest_msi(struct kvm *kvm,
|
|
struct kvm_assigned_dev_kernel *dev,
|
|
struct kvm_assigned_irq *irq)
|
|
{
|
|
dev->guest_irq = irq->guest_irq;
|
|
dev->ack_notifier.gsi = -1;
|
|
dev->host_irq_disabled = false;
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef __KVM_HAVE_MSIX
|
|
static int assigned_device_enable_guest_msix(struct kvm *kvm,
|
|
struct kvm_assigned_dev_kernel *dev,
|
|
struct kvm_assigned_irq *irq)
|
|
{
|
|
dev->guest_irq = irq->guest_irq;
|
|
dev->ack_notifier.gsi = -1;
|
|
dev->host_irq_disabled = false;
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
static int assign_host_irq(struct kvm *kvm,
|
|
struct kvm_assigned_dev_kernel *dev,
|
|
__u32 host_irq_type)
|
|
{
|
|
int r = -EEXIST;
|
|
|
|
if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
|
|
return r;
|
|
|
|
switch (host_irq_type) {
|
|
case KVM_DEV_IRQ_HOST_INTX:
|
|
r = assigned_device_enable_host_intx(kvm, dev);
|
|
break;
|
|
#ifdef __KVM_HAVE_MSI
|
|
case KVM_DEV_IRQ_HOST_MSI:
|
|
r = assigned_device_enable_host_msi(kvm, dev);
|
|
break;
|
|
#endif
|
|
#ifdef __KVM_HAVE_MSIX
|
|
case KVM_DEV_IRQ_HOST_MSIX:
|
|
r = assigned_device_enable_host_msix(kvm, dev);
|
|
break;
|
|
#endif
|
|
default:
|
|
r = -EINVAL;
|
|
}
|
|
|
|
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;
|
|
#ifdef __KVM_HAVE_MSI
|
|
case KVM_DEV_IRQ_GUEST_MSI:
|
|
r = assigned_device_enable_guest_msi(kvm, dev, irq);
|
|
break;
|
|
#endif
|
|
#ifdef __KVM_HAVE_MSIX
|
|
case KVM_DEV_IRQ_GUEST_MSIX:
|
|
r = assigned_device_enable_guest_msix(kvm, dev, irq);
|
|
break;
|
|
#endif
|
|
default:
|
|
r = -EINVAL;
|
|
}
|
|
|
|
if (!r) {
|
|
dev->irq_requested_type |= guest_irq_type;
|
|
kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
|
|
} else
|
|
kvm_free_irq_source_id(kvm, dev->irq_source_id);
|
|
|
|
return 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 (!capable(CAP_SYS_RAWIO))
|
|
return -EPERM;
|
|
|
|
if (!irqchip_in_kernel(kvm))
|
|
return r;
|
|
|
|
mutex_lock(&kvm->lock);
|
|
r = -ENODEV;
|
|
match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
|
|
assigned_irq->assigned_dev_id);
|
|
if (!match)
|
|
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;
|
|
|
|
mutex_lock(&kvm->lock);
|
|
|
|
match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
|
|
assigned_irq->assigned_dev_id);
|
|
if (!match)
|
|
goto out;
|
|
|
|
r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
|
|
out:
|
|
mutex_unlock(&kvm->lock);
|
|
return r;
|
|
}
|
|
|
|
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;
|
|
|
|
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;
|
|
}
|
|
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);
|
|
|
|
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);
|
|
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 (r)
|
|
goto out_list_del;
|
|
}
|
|
|
|
out:
|
|
srcu_read_unlock(&kvm->srcu, idx);
|
|
mutex_unlock(&kvm->lock);
|
|
return r;
|
|
out_list_del:
|
|
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;
|
|
}
|
|
|
|
if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
|
|
kvm_deassign_device(kvm, match);
|
|
|
|
kvm_free_assigned_device(kvm, match);
|
|
|
|
out:
|
|
mutex_unlock(&kvm->lock);
|
|
return r;
|
|
}
|
|
|
|
|
|
#ifdef __KVM_HAVE_MSIX
|
|
static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
|
|
struct kvm_assigned_msix_nr *entry_nr)
|
|
{
|
|
int r = 0;
|
|
struct kvm_assigned_dev_kernel *adev;
|
|
|
|
mutex_lock(&kvm->lock);
|
|
|
|
adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
|
|
entry_nr->assigned_dev_id);
|
|
if (!adev) {
|
|
r = -EINVAL;
|
|
goto msix_nr_out;
|
|
}
|
|
|
|
if (adev->entries_nr == 0) {
|
|
adev->entries_nr = entry_nr->entry_nr;
|
|
if (adev->entries_nr == 0 ||
|
|
adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
|
|
r = -EINVAL;
|
|
goto msix_nr_out;
|
|
}
|
|
|
|
adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
|
|
entry_nr->entry_nr,
|
|
GFP_KERNEL);
|
|
if (!adev->host_msix_entries) {
|
|
r = -ENOMEM;
|
|
goto msix_nr_out;
|
|
}
|
|
adev->guest_msix_entries = kzalloc(
|
|
sizeof(struct kvm_guest_msix_entry) *
|
|
entry_nr->entry_nr, GFP_KERNEL);
|
|
if (!adev->guest_msix_entries) {
|
|
kfree(adev->host_msix_entries);
|
|
r = -ENOMEM;
|
|
goto msix_nr_out;
|
|
}
|
|
} else /* Not allowed set MSI-X number twice */
|
|
r = -EINVAL;
|
|
msix_nr_out:
|
|
mutex_unlock(&kvm->lock);
|
|
return r;
|
|
}
|
|
|
|
static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
|
|
struct kvm_assigned_msix_entry *entry)
|
|
{
|
|
int r = 0, i;
|
|
struct kvm_assigned_dev_kernel *adev;
|
|
|
|
mutex_lock(&kvm->lock);
|
|
|
|
adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
|
|
entry->assigned_dev_id);
|
|
|
|
if (!adev) {
|
|
r = -EINVAL;
|
|
goto msix_entry_out;
|
|
}
|
|
|
|
for (i = 0; i < adev->entries_nr; i++)
|
|
if (adev->guest_msix_entries[i].vector == 0 ||
|
|
adev->guest_msix_entries[i].entry == entry->entry) {
|
|
adev->guest_msix_entries[i].entry = entry->entry;
|
|
adev->guest_msix_entries[i].vector = entry->gsi;
|
|
adev->host_msix_entries[i].entry = entry->entry;
|
|
break;
|
|
}
|
|
if (i == adev->entries_nr) {
|
|
r = -ENOSPC;
|
|
goto msix_entry_out;
|
|
}
|
|
|
|
msix_entry_out:
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
return r;
|
|
}
|
|
#endif
|
|
|
|
long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
|
|
unsigned long arg)
|
|
{
|
|
void __user *argp = (void __user *)arg;
|
|
int r = -ENOTTY;
|
|
|
|
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;
|
|
}
|
|
#ifdef KVM_CAP_ASSIGN_DEV_IRQ
|
|
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;
|
|
}
|
|
#endif
|
|
#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
|
|
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;
|
|
}
|
|
#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;
|
|
r = -EFAULT;
|
|
if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
|
|
goto out;
|
|
r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
|
|
if (r)
|
|
goto out;
|
|
break;
|
|
}
|
|
case KVM_ASSIGN_SET_MSIX_ENTRY: {
|
|
struct kvm_assigned_msix_entry entry;
|
|
r = -EFAULT;
|
|
if (copy_from_user(&entry, argp, sizeof entry))
|
|
goto out;
|
|
r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
|
|
if (r)
|
|
goto out;
|
|
break;
|
|
}
|
|
#endif
|
|
}
|
|
out:
|
|
return r;
|
|
}
|
|
|