This patch enable per-vector mask for assigned devices using MSI-X.
This patch provided two new APIs: one is for guest to specific device's MSI-X
table address in MMIO, the other is for userspace to get information about mask
bit.
All the mask bit operation are kept in kernel, in order to accelerate.
Userspace shouldn't access the device MMIO directly for the information,
instead it should uses provided API to do so.
Signed-off-by: Sheng Yang <sheng@xxxxxxxxxxxxxxx>
---
Documentation/kvm/api.txt | 48 ++++++++
arch/x86/kvm/x86.c | 1 +
include/linux/kvm.h | 22 ++++-
include/linux/kvm_host.h | 4 +
virt/kvm/assigned-dev.c | 286 ++++++++++++++++++++++++++++++++++++++++++++-
5 files changed, 359 insertions(+), 2 deletions(-)
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index b336266..76f800b 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -1085,6 +1085,54 @@ of 4 instructions that make up a hypercall.
If any additional field gets added to this structure later on, a bit for that
additional piece of information will be set in the flags bitmap.
+4.47 KVM_ASSIGN_REG_MSIX_MMIO
+
+Capability: KVM_CAP_DEVICE_MSIX_MASK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_mmio (in)
+Returns: 0 on success, !0 on error
+
+struct kvm_assigned_msix_mmio {
+ /* Assigned device's ID */
+ __u32 assigned_dev_id;
+ /* Must be 0 */
+ __u32 flags;
+ /* MSI-X table MMIO address */
+ __u64 base_addr;
+ /* Maximum entries contained in the table, <= KVM_MAX_MSIX_PER_DEV */
+ __u32 max_entries_nr;
+ /* Must be 0, reserved for future use */
+ __u32 reserved;
+};
+
+This ioctl would enable in-kernel MSI-X emulation, which would handle MSI-X
+mask bit in the kernel.
+
+4.48 KVM_ASSIGN_GET_MSIX_ENTRY
+
+Capability: KVM_CAP_DEVICE_MSIX_MASK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_entry (in and out)
+Returns: 0 on success, !0 on error
+
+struct kvm_assigned_msix_entry {
+ /* Assigned device's ID */
+ __u32 assigned_dev_id;
+ /* Ignored */
+ __u32 gsi;
+ /* The index of entry in the MSI-X table */
+ __u16 entry;
+ /* Querying flags and returning status */
+ __u16 flags;
+ /* Must be 0 */
+ __u16 padding[2];
+};
+
+This ioctl would allow userspace to get the status of one specific MSI-X
+entry. Currently we support mask bit status querying.
+
5. The kvm_run structure
Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f3f86b2..8fd5121 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1926,6 +1926,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
case KVM_CAP_XSAVE:
+ case KVM_CAP_DEVICE_MSIX_MASK:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 919ae53..bfe5707 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -540,6 +540,9 @@ struct kvm_ppc_pvinfo {
#endif
#define KVM_CAP_PPC_GET_PVINFO 57
#define KVM_CAP_PPC_IRQ_LEVEL 58
+#ifdef __KVM_HAVE_MSIX
+#define KVM_CAP_DEVICE_MSIX_MASK 59
+#endif
#ifdef KVM_CAP_IRQ_ROUTING
@@ -671,6 +674,10 @@ struct kvm_clock_data {
#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config)
#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data)
#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data)
+#define KVM_ASSIGN_GET_MSIX_ENTRY _IOWR(KVMIO, 0x7d, \
+ struct kvm_assigned_msix_entry)
+#define KVM_ASSIGN_REG_MSIX_MMIO _IOW(KVMIO, 0x7e, \
+ struct kvm_assigned_msix_mmio)
/* Available with KVM_CAP_PIT_STATE2 */
#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2)
#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2)
@@ -787,11 +794,24 @@ struct kvm_assigned_msix_nr {
};
#define KVM_MAX_MSIX_PER_DEV 256
+
+#define KVM_MSIX_FLAG_MASK (1 << 0)
+#define KVM_MSIX_FLAG_QUERY_MASK (1 << 15)
+
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];
+ __u16 flags;
+ __u16 padding[2];
+};
+
+struct kvm_assigned_msix_mmio {
+ __u32 assigned_dev_id;
+ __u32 flags;
+ __u64 base_addr;
+ __u32 max_entries_nr;
+ __u32 reserved;
};
#endif /* __LINUX_KVM_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e2ecbac..f58aaca 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -464,6 +464,10 @@ struct kvm_assigned_dev_kernel {
struct pci_dev *dev;
struct kvm *kvm;
spinlock_t assigned_dev_lock;
+ DECLARE_BITMAP(msix_mask_bitmap, KVM_MAX_MSIX_PER_DEV);
+ gpa_t msix_mmio_base;
+ struct kvm_io_device msix_mmio_dev;
+ int msix_max_entries_nr;
};
struct kvm_irq_mask_notifier {
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 7c98928..e3b5530 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -232,6 +232,14 @@ static void kvm_free_assigned_device(struct kvm *kvm,
{
kvm_free_assigned_irq(kvm, assigned_dev);
+#ifdef __KVM_HAVE_MSIX
+ if (assigned_dev->msix_mmio_base) {
+ mutex_lock(&kvm->slots_lock);
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+ &assigned_dev->msix_mmio_dev);
+ mutex_unlock(&kvm->slots_lock);
+ }
+#endif
pci_reset_function(assigned_dev->dev);
pci_release_regions(assigned_dev->dev);
@@ -504,7 +512,7 @@ out:
static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
struct kvm_assigned_pci_dev *assigned_dev)
{
- int r = 0, idx;
+ int r = 0, idx, i;
struct kvm_assigned_dev_kernel *match;
struct pci_dev *dev;
@@ -563,6 +571,10 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
list_add(&match->list, &kvm->arch.assigned_dev_head);
+ /* The state after reset of MSI-X table is all masked */
+ for (i = 0; i < KVM_MAX_MSIX_PER_DEV; i++)
+ set_bit(i, match->msix_mask_bitmap);
+
if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
if (!kvm->arch.iommu_domain) {
r = kvm_iommu_map_guest(kvm);
@@ -666,6 +678,43 @@ msix_nr_out:
return r;
}
+static void update_msix_mask(struct kvm_assigned_dev_kernel *adev,
+ int idx, bool new_mask_flag)
+{
+ int irq;
+ bool old_mask_flag, need_flush = false;
+
+ spin_lock_irq(&adev->assigned_dev_lock);
+
+ if (!adev->dev->msix_enabled ||
+ !(adev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX))
+ goto out;
+
+ old_mask_flag = test_bit(adev->guest_msix_entries[idx].entry,
+ adev->msix_mask_bitmap);
+ if (old_mask_flag == new_mask_flag)
+ goto out;
+
+ irq = adev->host_msix_entries[idx].vector;
+ BUG_ON(irq == 0);
+
+ if (new_mask_flag) {
+ set_bit(adev->guest_msix_entries[idx].entry,
+ adev->msix_mask_bitmap);
+ disable_irq_nosync(irq);
+ need_flush = true;
+ } else {
+ clear_bit(adev->guest_msix_entries[idx].entry,
+ adev->msix_mask_bitmap);
+ enable_irq(irq);
+ }
+out:
+ spin_unlock_irq(&adev->assigned_dev_lock);
+
+ if (need_flush)
+ flush_work(&adev->interrupt_work);
+}
+
static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
struct kvm_assigned_msix_entry *entry)
{
@@ -700,6 +749,211 @@ msix_entry_out:
return r;
}
+
+static int kvm_vm_ioctl_get_msix_entry(struct kvm *kvm,
+ struct kvm_assigned_msix_entry *entry)
+{
+ int r = 0;
+ 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 out;
+ }
+
+ if (entry->entry >= adev->msix_max_entries_nr) {
+ r = -ENOSPC;
+ goto out;
+ }
+
+ if (entry->flags & KVM_MSIX_FLAG_QUERY_MASK) {
+ if (test_bit(entry->entry, adev->msix_mask_bitmap))
+ entry->flags |= KVM_MSIX_FLAG_MASK;
+ else
+ entry->flags &= ~KVM_MSIX_FLAG_MASK;
+ }
+
+out:
+ mutex_unlock(&kvm->lock);
+
+ return r;
+}
+
+static bool msix_mmio_in_range(struct kvm_assigned_dev_kernel *adev,
+ gpa_t addr, int len)
+{
+ gpa_t start, end;
+
+ BUG_ON(adev->msix_mmio_base == 0);
+ start = adev->msix_mmio_base;
+ end = adev->msix_mmio_base + PCI_MSIX_ENTRY_SIZE *
+ adev->msix_max_entries_nr;
+ if (addr >= start && addr + len <= end)
+ return true;
+
+ return false;
+}
+
+static int msix_get_enabled_idx(struct kvm_assigned_dev_kernel *adev,
+ gpa_t addr, int len)
+{
+ int i, index = (addr - adev->msix_mmio_base) / PCI_MSIX_ENTRY_SIZE;
+
+ for (i = 0; i < adev->entries_nr; i++)
+ if (adev->guest_msix_entries[i].entry == index)
+ return i;
+
+ return -EINVAL;
+}
+
+static int msix_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
+ void *val)
+{
+ struct kvm_assigned_dev_kernel *adev =
+ container_of(this, struct kvm_assigned_dev_kernel,
+ msix_mmio_dev);
+ int idx, r = 0;
+ u32 entry[4];
+ struct kvm_kernel_irq_routing_entry e;
+
+ mutex_lock(&adev->kvm->lock);
+ if (!msix_mmio_in_range(adev, addr, len)) {
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+ if ((addr & 0x3) || len != 4)
+ goto out;
+
+ idx = msix_get_enabled_idx(adev, addr, len);
+ if (idx < 0) {
+ idx = (addr - adev->msix_mmio_base) / PCI_MSIX_ENTRY_SIZE;
+ if ((addr % PCI_MSIX_ENTRY_SIZE) ==
+ PCI_MSIX_ENTRY_VECTOR_CTRL)
+ *(unsigned long *)val =
+ test_bit(idx, adev->msix_mask_bitmap) ?
+ PCI_MSIX_ENTRY_CTRL_MASKBIT : 0;
+ else
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+
+ r = kvm_get_irq_routing_entry(adev->kvm,
+ adev->guest_msix_entries[idx].vector, &e);
+ if (r || e.type != KVM_IRQ_ROUTING_MSI) {
+ printk(KERN_WARNING "KVM: Wrong MSI-X routing entry! "
+ "idx %d, addr 0x%llx, len %d\n", idx, addr, len);
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+ entry[0] = e.msi.address_lo;
+ entry[1] = e.msi.address_hi;
+ entry[2] = e.msi.data;
+ entry[3] = test_bit(adev->guest_msix_entries[idx].entry,
+ adev->msix_mask_bitmap);
+ memcpy(val, &entry[addr % PCI_MSIX_ENTRY_SIZE / sizeof *entry], len);
+
+out:
+ mutex_unlock(&adev->kvm->lock);
+ return r;
+}
+
+static int msix_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
+ const void *val)
+{
+ struct kvm_assigned_dev_kernel *adev =
+ container_of(this, struct kvm_assigned_dev_kernel,
+ msix_mmio_dev);
+ int idx, r = 0;
+ unsigned long new_val = *(unsigned long *)val;
+
+ mutex_lock(&adev->kvm->lock);
+ if (!msix_mmio_in_range(adev, addr, len)) {
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+ if ((addr & 0x3) || len != 4)
+ goto out;
+
+ idx = msix_get_enabled_idx(adev, addr, len);
+ if (idx < 0) {
+ idx = (addr - adev->msix_mmio_base) / PCI_MSIX_ENTRY_SIZE;
+ if (((addr % PCI_MSIX_ENTRY_SIZE) ==
+ PCI_MSIX_ENTRY_VECTOR_CTRL)) {
+ if (new_val & ~PCI_MSIX_ENTRY_CTRL_MASKBIT)
+ goto out;
+ if (new_val & PCI_MSIX_ENTRY_CTRL_MASKBIT)
+ set_bit(idx, adev->msix_mask_bitmap);
+ else
+ clear_bit(idx, adev->msix_mask_bitmap);
+ } else
+ /* Userspace would handle other MMIO writing */
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+ if (addr % PCI_MSIX_ENTRY_SIZE != PCI_MSIX_ENTRY_VECTOR_CTRL) {
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+ if (new_val & ~PCI_MSIX_ENTRY_CTRL_MASKBIT)
+ goto out;
+ update_msix_mask(adev, idx, !!(new_val & PCI_MSIX_ENTRY_CTRL_MASKBIT));
+out:
+ mutex_unlock(&adev->kvm->lock);
+
+ return r;
+}
+
+static const struct kvm_io_device_ops msix_mmio_ops = {
+ .read = msix_mmio_read,
+ .write = msix_mmio_write,
+};
+
+static int kvm_vm_ioctl_register_msix_mmio(struct kvm *kvm,
+ struct kvm_assigned_msix_mmio *msix_mmio)
+{
+ int r = 0;
+ struct kvm_assigned_dev_kernel *adev;
+
+ mutex_lock(&kvm->lock);
+ adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ msix_mmio->assigned_dev_id);
+ if (!adev) {
+ r = -EINVAL;
+ goto out;
+ }
+ if (msix_mmio->base_addr == 0) {
+ r = -EINVAL;
+ goto out;
+ }
+ if (msix_mmio->max_entries_nr == 0 ||
+ msix_mmio->max_entries_nr > KVM_MAX_MSIX_PER_DEV) {
+ r = -EINVAL;
+ goto out;
+ }
+
+ mutex_lock(&kvm->slots_lock);
+ if (adev->msix_mmio_base == 0) {
+ kvm_iodevice_init(&adev->msix_mmio_dev, &msix_mmio_ops);
+ r = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS,
+ &adev->msix_mmio_dev);
+ if (r)
+ goto out2;
+ }
+
+ adev->msix_mmio_base = msix_mmio->base_addr;
+ adev->msix_max_entries_nr = msix_mmio->max_entries_nr;
+out2:
+ mutex_unlock(&kvm->slots_lock);
+out:
+ mutex_unlock(&kvm->lock);
+
+ return r;
+}
#endif
long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
@@ -812,6 +1066,36 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
goto out;
break;
}
+ case KVM_ASSIGN_GET_MSIX_ENTRY: {
+ struct kvm_assigned_msix_entry entry;
+ r = -EFAULT;
+ if (copy_from_user(&entry, argp, sizeof entry))
+ goto out;
+ r = kvm_vm_ioctl_get_msix_entry(kvm, &entry);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &entry, sizeof entry))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_ASSIGN_REG_MSIX_MMIO: {
+ struct kvm_assigned_msix_mmio msix_mmio;
+
+ r = -EFAULT;
+ if (copy_from_user(&msix_mmio, argp, sizeof(msix_mmio)))
+ goto out;
+
+ r = -EINVAL;
+ if (msix_mmio.flags != 0 || msix_mmio.reserved != 0)
+ goto out;
+
+ r = kvm_vm_ioctl_register_msix_mmio(kvm, &msix_mmio);
+ if (r)
+ goto out;
+ break;
+ }
#endif
}
out:
--
1.7.0.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
