vfio: vfio-pci device assignment driver

This adds the core of the QEMU VFIO-based PCI device assignment driver.
To make use of this driver, enable CONFIG_VFIO, CONFIG_VFIO_IOMMU_TYPE1,
and CONFIG_VFIO_PCI in your host Linux kernel config.  Load the vfio-pci
module.  To assign device 0000:05:00.0 to a guest, do the following:

for dev in $(ls /sys/bus/pci/devices/0000:05:00.0/iommu_group/devices); do
    vendor=$(cat /sys/bus/pci/devices/$dev/vendor)
    device=$(cat /sys/bus/pci/devices/$dev/device)
    if [ -e /sys/bus/pci/devices/$dev/driver ]; then
        echo $dev > /sys/bus/pci/devices/$dev/driver/unbind
    fi
    echo $vendor $device > /sys/bus/pci/drivers/vfio-pci/new_id
done

See Documentation/vfio.txt in the Linux kernel tree for further
description of IOMMU groups and VFIO.

Then launch qemu including the option:

-device vfio-pci,host=0000:05:00.0

Legacy PCI interrupts (INTx) currently makes use of a kludge where we
trap BAR accesses and assume the access is in response to an interrupt,
therefore de-asserting and unmasking the interrupt.  It's not quite as
targetted as using the EOI for this, but it's self contained and seems
to work across all architectures.  The side-effect is a significant
performance slow-down for device in INTx mode.  Some devices, like
graphics cards, don't really use their interrupt, so this can be turned
off with the x-intx=off option, which disables INTx alltogether.  This
should be considered an experimental option until we refine this code.
Both MSI and MSI-X are supported and avoid these issues.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

1 files changed, 114 insertions, 0 deletions

diff --git a/hw/vfio_pci_int.h b/hw/vfio_pci_int.h
new file mode 100644
index 0000000000..3812d8d7f1
--- /dev/null
+++ b/hw/vfio_pci_int.h
@@ -0,0 +1,114 @@
+/*
+ * vfio based device assignment support
+ *
+ * Copyright Red Hat, Inc. 2012
+ *
+ * Authors:
+ *  Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#ifndef HW_VFIO_PCI_INT_H
+#define HW_VFIO_PCI_INT_H
+
+#include "qemu-common.h"
+#include "qemu-queue.h"
+#include "pci.h"
+#include "event_notifier.h"
+
+typedef struct VFIOBAR {
+    off_t fd_offset; /* offset of BAR within device fd */
+    int fd; /* device fd, allows us to pass VFIOBAR as opaque data */
+    MemoryRegion mem; /* slow, read/write access */
+    MemoryRegion mmap_mem; /* direct mapped access */
+    void *mmap;
+    size_t size;
+    uint32_t flags; /* VFIO region flags (rd/wr/mmap) */
+    uint8_t nr; /* cache the BAR number for debug */
+} VFIOBAR;
+
+typedef struct VFIOINTx {
+    bool pending; /* interrupt pending */
+    bool kvm_accel; /* set when QEMU bypass through KVM enabled */
+    uint8_t pin; /* which pin to pull for qemu_set_irq */
+    EventNotifier interrupt; /* eventfd triggered on interrupt */
+    EventNotifier unmask; /* eventfd for unmask on QEMU bypass */
+    PCIINTxRoute route; /* routing info for QEMU bypass */
+    bool disabled;
+    char *intx;
+} VFIOINTx;
+
+struct VFIODevice;
+
+typedef struct VFIOMSIVector {
+    EventNotifier interrupt; /* eventfd triggered on interrupt */
+    struct VFIODevice *vdev; /* back pointer to device */
+    int virq; /* KVM irqchip route for QEMU bypass */
+    bool use;
+} VFIOMSIVector;
+
+enum {
+    VFIO_INT_NONE = 0,
+    VFIO_INT_INTx = 1,
+    VFIO_INT_MSI  = 2,
+    VFIO_INT_MSIX = 3,
+};
+
+struct VFIOGroup;
+
+typedef struct VFIOContainer {
+    int fd; /* /dev/vfio/vfio, empowered by the attached groups */
+    struct {
+        /* enable abstraction to support various iommu backends */
+        union {
+            MemoryListener listener; /* Used by type1 iommu */
+        };
+        void (*release)(struct VFIOContainer *);
+    } iommu_data;
+    QLIST_HEAD(, VFIOGroup) group_list;
+    QLIST_ENTRY(VFIOContainer) next;
+} VFIOContainer;
+
+/* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */
+typedef struct VFIOMSIXInfo {
+    uint8_t table_bar;
+    uint8_t pba_bar;
+    uint16_t entries;
+    uint32_t table_offset;
+    uint32_t pba_offset;
+    MemoryRegion mmap_mem;
+    void *mmap;
+} VFIOMSIXInfo;
+
+typedef struct VFIODevice {
+    PCIDevice pdev;
+    int fd;
+    VFIOINTx intx;
+    unsigned int config_size;
+    off_t config_offset; /* Offset of config space region within device fd */
+    unsigned int rom_size;
+    off_t rom_offset; /* Offset of ROM region within device fd */
+    int msi_cap_size;
+    VFIOMSIVector *msi_vectors;
+    VFIOMSIXInfo *msix;
+    int nr_vectors; /* Number of MSI/MSIX vectors currently in use */
+    int interrupt; /* Current interrupt type */
+    VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */
+    PCIHostDeviceAddress host;
+    QLIST_ENTRY(VFIODevice) next;
+    struct VFIOGroup *group;
+    bool reset_works;
+} VFIODevice;
+
+typedef struct VFIOGroup {
+    int fd;
+    int groupid;
+    VFIOContainer *container;
+    QLIST_HEAD(, VFIODevice) device_list;
+    QLIST_ENTRY(VFIOGroup) next;
+    QLIST_ENTRY(VFIOGroup) container_next;
+} VFIOGroup;
+
+#endif /* HW_VFIO_PCI_INT_H */