Re: [Qemu-devel] [PATCH v5 07/10] hw/vfio/platform: add vfio-platform support

[Alexander Graf <agraf@suse.de>]

On 09.08.14 16:25, Eric Auger wrote:
> Minimal VFIO platform implementation supporting
> - register space user mapping,
> - IRQ assignment based on eventfds handled on qemu side.
>
> irqfd kernel acceleration comes in a subsequent patch.
>
> Signed-off-by: Kim Phillips <kim.phillips@linaro.org>
> Signed-off-by: Eric Auger <eric.auger@linaro.org>
>
> ---
>
> v4 -> v5:
> - vfio-plaform.h included first
> - cleanup error handling in *populate*, vfio_get_device,
>    vfio_enable_intp
> - vfio_put_device not called anymore
> - add some includes to follow vfio policy
>
> v3 -> v4:
> [Eric Auger]
> - merge of "vfio: Add initial IRQ support in platform device"
>    to get a full functional patch although perfs are limited.
> - removal of unrealize function since I currently understand
>    it is only used with device hot-plug feature.
>
> v2 -> v3:
> [Eric Auger]
> - further factorization between PCI and platform (VFIORegion,
>    VFIODevice). same level of functionality.
>
> <= v2:
> [Kim Philipps]
> - Initial Creation of the device supporting register space mapping
> ---
>   hw/vfio/Makefile.objs           |   1 +
>   hw/vfio/platform.c              | 517 ++++++++++++++++++++++++++++++++++++++++
>   include/hw/vfio/vfio-platform.h |  77 ++++++
>   3 files changed, 595 insertions(+)
>   create mode 100644 hw/vfio/platform.c
>   create mode 100644 include/hw/vfio/vfio-platform.h
>
> diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
> index e31f30e..c5c76fe 100644
> --- a/hw/vfio/Makefile.objs
> +++ b/hw/vfio/Makefile.objs
> @@ -1,4 +1,5 @@
>   ifeq ($(CONFIG_LINUX), y)
>   obj-$(CONFIG_SOFTMMU) += common.o
>   obj-$(CONFIG_PCI) += pci.o
> +obj-$(CONFIG_SOFTMMU) += platform.o
>   endif
> diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
> new file mode 100644
> index 0000000..f1a1b55
> --- /dev/null
> +++ b/hw/vfio/platform.c
> @@ -0,0 +1,517 @@
> +/*
> + * vfio based device assignment support - platform devices
> + *
> + * Copyright Linaro Limited, 2014
> + *
> + * Authors:
> + *  Kim Phillips <kim.phillips@linaro.org>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2.  See
> + * the COPYING file in the top-level directory.
> + *
> + * Based on vfio based PCI device assignment support:
> + *  Copyright Red Hat, Inc. 2012
> + */
> +
> +#include <linux/vfio.h>
> +#include <sys/ioctl.h>
> +
> +#include "hw/vfio/vfio-platform.h"
> +#include "qemu/error-report.h"
> +#include "qemu/range.h"
> +#include "sysemu/sysemu.h"
> +#include "exec/memory.h"
> +#include "qemu/queue.h"
> +#include "hw/sysbus.h"
> +
> +extern const MemoryRegionOps vfio_region_ops;
> +extern const MemoryListener vfio_memory_listener;
> +extern QLIST_HEAD(, VFIOGroup) group_list;
> +extern QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces;
> +void vfio_put_device(VFIOPlatformDevice *vdev);
> +
> +/*
> + * It is mandatory to pass a VFIOPlatformDevice since VFIODevice
> + * is not a QOM Object and cannot be passed to memory region functions
> +*/
> +static void vfio_map_region(VFIOPlatformDevice *vdev, int nr)
> +{
> +    VFIORegion *region = vdev->regions[nr];
> +    unsigned size = region->size;
> +    char name[64];
> +
> +    if (!size) {
> +        return;
> +    }
> +
> +    snprintf(name, sizeof(name), "VFIO %s region %d",
> +             vdev->vbasedev.name, nr);
> +
> +    /* A "slow" read/write mapping underlies all regions */
> +    memory_region_init_io(&region->mem, OBJECT(vdev), &vfio_region_ops,
> +                          region, name, size);
> +
> +    strncat(name, " mmap", sizeof(name) - strlen(name) - 1);
> +
> +    if (vfio_mmap_region(OBJECT(vdev), region, &region->mem,
> +                         &region->mmap_mem, &region->mmap, size, 0, name)) {
> +        error_report("%s unsupported. Performance may be slow", name);
> +    }
> +}
> +
> +static void print_regions(VFIOPlatformDevice *vdev)
> +{
> +    int i;
> +
> +    DPRINTF("Device \"%s\" counts %d region(s):\n",
> +             vdev->vbasedev.name, vdev->vbasedev.num_regions);
> +
> +    for (i = 0; i < vdev->vbasedev.num_regions; i++) {
> +        DPRINTF("- region %d flags = 0x%lx, size = 0x%lx, "
> +                "fd= %d, offset = 0x%lx\n",
> +                vdev->regions[i]->nr,
> +                (unsigned long)vdev->regions[i]->flags,
> +                (unsigned long)vdev->regions[i]->size,
> +                vdev->regions[i]->vbasedev->fd,
> +                (unsigned long)vdev->regions[i]->fd_offset);
> +    }
> +}
> +
> +static int vfio_populate_regions(VFIODevice *vbasedev)
> +{
> +    struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) };
> +    int i, ret = 0;
> +    VFIOPlatformDevice *vdev =
> +        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
> +
> +    vdev->regions = g_malloc0(sizeof(VFIORegion *) * vbasedev->num_regions);
> +
> +    for (i = 0; i < vbasedev->num_regions; i++) {
> +        vdev->regions[i] = g_malloc0(sizeof(VFIORegion));
> +        reg_info.index = i;
> +        ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, &reg_info);
> +        if (ret) {
> +            error_report("vfio: Error getting region %d info: %m", i);
> +            goto error;
> +        }
> +
> +        vdev->regions[i]->flags = reg_info.flags;
> +        vdev->regions[i]->size = reg_info.size;
> +        vdev->regions[i]->fd_offset = reg_info.offset;
> +        vdev->regions[i]->nr = i;
> +        vdev->regions[i]->vbasedev = vbasedev;
> +    }
> +    print_regions(vdev);
> +error:
> +    return ret;
> +}
> +
> +/* not implemented yet */
> +static int vfio_platform_check_device(VFIODevice *vdev)
> +{
> +    return 0;
> +}
> +
> +/* not implemented yet */
> +static bool vfio_platform_compute_needs_reset(VFIODevice *vdev)
> +{
> +return false;
> +}
> +
> +/* not implemented yet */
> +static int vfio_platform_hot_reset_multi(VFIODevice *vdev)
> +{
> +return 0;
> +}
> +
> +/*
> + * eoi function is called on the first access to any MMIO region
> + * after an IRQ was triggered. It is assumed this access corresponds
> + * to the IRQ status register reset.
> + * With such a mechanism, a single IRQ can be handled at a time since
> + * there is no way to know which IRQ was completed by the guest.
> + * (we would need additional details about the IRQ status register mask)
> + */
> +static void vfio_platform_eoi(VFIODevice *vbasedev)
> +{
> +    VFIOINTp *intp;
> +    VFIOPlatformDevice *vdev =
> +        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
> +
> +    QLIST_FOREACH(intp, &vdev->intp_list, next) {
> +        if (intp->state == VFIO_IRQ_ACTIVE) {
> +            DPRINTF("EOI IRQ #%d fd=%d\n",
> +                    intp->pin, event_notifier_get_fd(&intp->interrupt));
> +            intp->state = VFIO_IRQ_INACTIVE;
> +
> +            /* deassert the virtual IRQ and unmask physical one */
> +            qemu_set_irq(intp->qemuirq, 0);
> +            vfio_unmask_irqindex(vbasedev, intp->pin);
> +
> +            /* a single IRQ can be active at a time */
> +            break;
> +        }
> +    }
> +
> +    /* in case there are pending IRQs, handle them one at a time */
> +    if (!QSIMPLEQ_EMPTY(&vdev->pending_intp_queue)) {
> +        intp = QSIMPLEQ_FIRST(&vdev->pending_intp_queue);
> +        vfio_intp_interrupt(intp);
> +        QSIMPLEQ_REMOVE_HEAD(&vdev->pending_intp_queue, pqnext);
> +    }
> +}
> +
> +/*
> + * enable/disable the fast path mode
> + * fast path = MMIO region is mmaped (no KVM TRAP)
> + * slow path = MMIO region is trapped and region callbacks are called
> + * slow path enables to trap the IRQ status register guest reset
> +*/
> +
> +static void vfio_mmap_set_enabled(VFIOPlatformDevice *vdev, bool enabled)
> +{
> +    VFIORegion *region;
> +    int i;
> +
> +    DPRINTF("fast path = %d\n", enabled);
> +
> +    for (i = 0; i < vdev->vbasedev.num_regions; i++) {
> +        region = vdev->regions[i];
> +
> +        /* register space is unmapped to trap EOI */
> +        memory_region_set_enabled(&region->mmap_mem, enabled);
> +    }
> +}
> +
> +/*
> + * Checks whether the IRQ is still pending. In the negative
> + * the fast path mode (where reg space is mmaped) can be restored.
> + * if the IRQ is still pending, we must keep on trapping IRQ status
> + * register reset with mmap disabled (slow path).
> + * the function is called on mmap_timer event.
> + * by construction a single fd is handled at a time. See EOI comment
> + * for additional details.
> + */
> +static void vfio_intp_mmap_enable(void *opaque)
> +{
> +    VFIOINTp *tmp;
> +    VFIOPlatformDevice *vdev = (VFIOPlatformDevice *)opaque;
> +
> +    QLIST_FOREACH(tmp, &vdev->intp_list, next) {
> +        if (tmp->state == VFIO_IRQ_ACTIVE) {
> +            DPRINTF("IRQ #%d still active, stay in slow path\n",
> +                    tmp->pin);
> +            timer_mod(vdev->mmap_timer,
> +                      qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
> +                          vdev->mmap_timeout);
> +            return;
> +        }
> +    }
> +    DPRINTF("no active IRQ, restore fast path\n");
> +    vfio_mmap_set_enabled(vdev, true);
> +}
> +
> +/*
> + * The fd handler
> + */
> +void vfio_intp_interrupt(void *opaque)
> +{
> +    int ret;
> +    VFIOINTp *tmp, *intp = (VFIOINTp *)opaque;
> +    VFIOPlatformDevice *vdev = intp->vdev;
> +    bool one_active_irq = false;
> +
> +    /*
> +     * first check whether there is a pending IRQ
> +     * in the positive the new IRQ cannot be handled until the
> +     * active one is not completed.
> +     * by construction the same IRQ as the pending one cannot hit
> +     * since the physical IRQ was disabled by the VFIO driver
> +     */
> +    QLIST_FOREACH(tmp, &vdev->intp_list, next) {
> +        if (tmp->state == VFIO_IRQ_ACTIVE) {
> +            one_active_irq = true;
> +            break;
> +        }
> +    }
> +    if (one_active_irq) {
> +        /*
> +         * the new IRQ gets a pending status and is pushed in
> +         * the pending queue
> +         */
> +        intp->state = VFIO_IRQ_PENDING;
> +        QSIMPLEQ_INSERT_TAIL(&vdev->pending_intp_queue,
> +                             intp, pqnext);
> +        return;
> +    }
> +
> +    /* no active IRQ, the new IRQ can be forwarded to the guest */
> +    DPRINTF("Handle IRQ #%d (fd = %d)\n",
> +            intp->pin, event_notifier_get_fd(&intp->interrupt));
> +
> +    ret = event_notifier_test_and_clear(&intp->interrupt);
> +    if (!ret) {
> +        DPRINTF("Error when clearing fd=%d\n",
> +                event_notifier_get_fd(&intp->interrupt));
> +    }
> +
> +    intp->state = VFIO_IRQ_ACTIVE;
> +
> +    /* sets slow path */
> +    vfio_mmap_set_enabled(vdev, false);
> +
> +    /* trigger the virtual IRQ */
> +    qemu_set_irq(intp->qemuirq, 1);
> +
> +    /* schedule the mmap timer which will restore mmap path after EOI*/
> +    if (vdev->mmap_timeout) {
> +        timer_mod(vdev->mmap_timer,
> +                  qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
> +                      vdev->mmap_timeout);
> +    }
> +}
> +
> +static int vfio_enable_intp(VFIODevice *vbasedev, unsigned int index)
> +{
> +    struct vfio_irq_set *irq_set;
> +    int32_t *pfd;
> +    int ret, argsz;
> +    int device = vbasedev->fd;
> +    VFIOPlatformDevice *vdev =
> +        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
> +    SysBusDevice *sbdev = SYS_BUS_DEVICE(vdev);
> +    VFIOINTp *intp;
> +
> +    /* allocate and populate a new VFIOINTp structure put in a queue list */
> +    intp = g_malloc0(sizeof(*intp));
> +    intp->vdev = vdev;
> +    intp->pin = index;
> +    intp->state = VFIO_IRQ_INACTIVE;
> +    sysbus_init_irq(sbdev, &intp->qemuirq);
> +
> +    ret = event_notifier_init(&intp->interrupt, 0);
> +    if (ret) {
> +        g_free(intp);
> +        error_report("vfio: Error: event_notifier_init failed ");
> +        return ret;
> +    }
> +
> +    /* build the irq_set to be passed to the vfio kernel driver */
> +    argsz = sizeof(*irq_set) + sizeof(*pfd);
> +
> +    irq_set = g_malloc0(argsz);
> +    irq_set->argsz = argsz;
> +    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
> +    irq_set->index = index;
> +    irq_set->start = 0;
> +    irq_set->count = 1;
> +    pfd = (int32_t *)&irq_set->data;
> +
> +    *pfd = event_notifier_get_fd(&intp->interrupt);
> +
> +    DPRINTF("register fd=%d/irq index=%d to kernel\n", *pfd, index);
> +
> +    qemu_set_fd_handler(*pfd, vfio_intp_interrupt, NULL, intp);
> +
> +    /*
> +     * pass the index/fd binding to the kernel driver so that it
> +     * triggers this fd on HW IRQ
> +     */
> +    ret = ioctl(device, VFIO_DEVICE_SET_IRQS, irq_set);
> +    g_free(irq_set);
> +    if (ret) {
> +        error_report("vfio: Error: Failed to pass IRQ fd to the driver: %m");
> +        qemu_set_fd_handler(*pfd, NULL, NULL, NULL);
> +        event_notifier_cleanup(&intp->interrupt);
> +        return -errno;
> +    }
> +
> +    /* store the new intp in qlist */
> +    QLIST_INSERT_HEAD(&vdev->intp_list, intp, next);
> +    return 0;
> +}
> +
> +static int vfio_populate_interrupts(VFIODevice *vbasedev)
> +{
> +    struct vfio_irq_info irq = { .argsz = sizeof(irq) };
> +    int i, ret;
> +    VFIOPlatformDevice *vdev =
> +        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
> +
> +    vdev->mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
> +                                    vfio_intp_mmap_enable, vdev);
> +
> +    QSIMPLEQ_INIT(&vdev->pending_intp_queue);
> +
> +    for (i = 0; i < vbasedev->num_irqs; i++) {
> +        irq.index = i;
> +
> +        DPRINTF("Retrieve IRQ info from vfio platform driver ...\n");
> +
> +        ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq);
> +        if (ret) {
> +            /* This can fail for an old kernel or legacy PCI dev */
> +            error_printf("vfio: error getting device %s irq info",
> +                         vbasedev->name);
> +        } else {
> +            DPRINTF("- IRQ index %d: count %d, flags=0x%x\n",
> +                    irq.index, irq.count, irq.flags);
> +
> +            ret = vfio_enable_intp(vbasedev, irq.index);
> +            if (ret) {
> +                error_report("vfio: Error setting IRQ %d up", i);
> +                return ret;
> +            }
> +        }
> +    }
> +    return 0;
> +}
> +
> +static VFIODeviceOps vfio_platform_ops = {
> +    .vfio_compute_needs_reset = vfio_platform_compute_needs_reset,
> +    .vfio_hot_reset_multi = vfio_platform_hot_reset_multi,
> +    .vfio_eoi = vfio_platform_eoi,
> +    .vfio_check_device = vfio_platform_check_device,
> +    .vfio_populate_regions = vfio_populate_regions,
> +    .vfio_populate_interrupts = vfio_populate_interrupts,
> +};
> +
> +static int vfio_base_device_init(VFIODevice *vbasedev)
> +{
> +    VFIOGroup *group;
> +    VFIODevice *vbasedev_iter;
> +    char path[PATH_MAX], iommu_group_path[PATH_MAX], *group_name;
> +    ssize_t len;
> +    struct stat st;
> +    int groupid;
> +    int ret;
> +
> +    /* name must be set prior to the call */
> +    if (!vbasedev->name) {
> +        return -EINVAL;
> +    }
> +
> +    /* Check that the host device exists */
> +    snprintf(path, sizeof(path), "/sys/bus/platform/devices/%s/",
> +             vbasedev->name);
> +
> +    if (stat(path, &st) < 0) {
> +        error_report("vfio: error: no such host device: %s", path);
> +        return -errno;
> +    }
> +
> +    strncat(path, "iommu_group", sizeof(path) - strlen(path) - 1);
> +    len = readlink(path, iommu_group_path, sizeof(path));
> +    if (len <= 0 || len >= sizeof(path)) {
> +        error_report("vfio: error no iommu_group for device");
> +        return len < 0 ? -errno : ENAMETOOLONG;
> +    }
> +
> +    iommu_group_path[len] = 0;
> +    group_name = basename(iommu_group_path);
> +
> +    if (sscanf(group_name, "%d", &groupid) != 1) {
> +        error_report("vfio: error reading %s: %m", path);
> +        return -errno;
> +    }
> +
> +    DPRINTF("%s(%s) group %d\n", __func__, vbasedev->name, groupid);
> +
> +    group = vfio_get_group(groupid, &address_space_memory);
> +    if (!group) {
> +        error_report("vfio: failed to get group %d", groupid);
> +        return -ENOENT;
> +    }
> +
> +    snprintf(path, sizeof(path), "%s", vbasedev->name);
> +
> +    QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
> +        if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) {
> +            error_report("vfio: error: device %s is already attached", path);
> +            vfio_put_group(group);
> +            return -EBUSY;
> +        }
> +    }
> +    ret = vfio_get_device(group, path, vbasedev);
> +    if (ret) {
> +        error_report("vfio: failed to get device %s", path);
> +        vfio_put_group(group);
> +    }
> + return ret;
> +}
> +
> +void vfio_put_device(VFIOPlatformDevice *vdev)
> +{
> +    unsigned int i;
> +    VFIODevice *vbasedev = &vdev->vbasedev;
> +
> +    for (i = 0; i < vbasedev->num_regions; i++) {
> +            g_free(vdev->regions[i]);
> +    }
> +    g_free(vdev->regions);
> +    g_free(vdev->vbasedev.name);
> +    vfio_put_base_device(&vdev->vbasedev);
> +}
> +
> +static void vfio_platform_realize(DeviceState *dev, Error **errp)
> +{
> +    VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev);
> +    SysBusDevice *sbdev = SYS_BUS_DEVICE(dev);
> +    VFIODevice *vbasedev = &vdev->vbasedev;
> +    int i, ret;
> +
> +    vbasedev->type = VFIO_DEVICE_TYPE_PLATFORM;
> +    vbasedev->ops = &vfio_platform_ops;
> +
> +    DPRINTF("vfio device %s, compat = %s\n", vbasedev->name, vdev->compat);
> +
> +    ret = vfio_base_device_init(vbasedev);
> +    if (ret) {
> +        return;
> +    }
> +
> +    for (i = 0; i < vbasedev->num_regions; i++) {
> +        vfio_map_region(vdev, i);
> +        sysbus_init_mmio(sbdev, &vdev->regions[i]->mem);
> +    }
> +}
> +
> +static const VMStateDescription vfio_platform_vmstate = {
> +    .name = TYPE_VFIO_PLATFORM,
> +    .unmigratable = 1,
> +};
> +
> +static Property vfio_platform_dev_properties[] = {
> +    DEFINE_PROP_STRING("vfio_device", VFIOPlatformDevice, vbasedev.name),
> +    DEFINE_PROP_STRING("compat", VFIOPlatformDevice, compat),
> +    DEFINE_PROP_UINT32("mmap-timeout-ms", VFIOPlatformDevice,
> +                       mmap_timeout, 1100),
> +    DEFINE_PROP_BOOL("irqfd", VFIOPlatformDevice, irqfd_allowed, true),
> +    DEFINE_PROP_END_OF_LIST(),
> +};
> +
> +static void vfio_platform_class_init(ObjectClass *klass, void *data)
> +{
> +    DeviceClass *dc = DEVICE_CLASS(klass);
> +
> +    dc->realize = vfio_platform_realize;
> +    dc->props = vfio_platform_dev_properties;
> +    dc->vmsd = &vfio_platform_vmstate;
> +    dc->desc = "VFIO-based platform device assignment";
> +    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
> +}
> +
> +static const TypeInfo vfio_platform_dev_info = {
> +    .name = TYPE_VFIO_PLATFORM,
> +    .parent = TYPE_SYS_BUS_DEVICE,
> +    .instance_size = sizeof(VFIOPlatformDevice),
> +    .class_init = vfio_platform_class_init,
> +    .class_size = sizeof(VFIOPlatformDeviceClass),

This should be an abstract class. People must never instantiate a 
generic "vfio-platform" device. Only "vfio-xgmac", "vfio-etsec", etc 
devices should be exposed to the user.


Alex