Re: [PATCH v2 16/19] util/vfio-helpers: Introduce qemu_vfio_pci_msix_init_irqs()

[Auger Eric <eric.auger@redhat.com>]

Hi Philippe,

On 10/26/20 11:55 AM, Philippe Mathieu-Daudé wrote:
> qemu_vfio_pci_init_irq() allows us to initialize any type of IRQ,
> but only one. Introduce qemu_vfio_pci_msix_init_irqs() which is
> specific to MSIX IRQ type, and allow us to use multiple IRQs
> (thus passing multiple eventfd notifiers).
> All eventfd notifiers are initialized with the special '-1' value
> meaning "un-assigned".
> 
> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
> ---
>  include/qemu/vfio-helpers.h |  6 +++-
>  util/vfio-helpers.c         | 65 ++++++++++++++++++++++++++++++++++++-
>  util/trace-events           |  1 +
>  3 files changed, 70 insertions(+), 2 deletions(-)
> 
> diff --git a/include/qemu/vfio-helpers.h b/include/qemu/vfio-helpers.h
> index 4b97a904e93..492072cba2f 100644
> --- a/include/qemu/vfio-helpers.h
> +++ b/include/qemu/vfio-helpers.h
> @@ -1,11 +1,13 @@
>  /*
>   * QEMU VFIO helpers
>   *
> - * Copyright 2016 - 2018 Red Hat, Inc.
> + * Copyright 2016 - 2020 Red Hat, Inc.
>   *
>   * Authors:
>   *   Fam Zheng <famz@redhat.com>
> + *   Philippe Mathieu-Daudé <philmd@redhat.com>
>   *
> + * SPDX-License-Identifier: GPL-2.0-or-later
>   * This work is licensed under the terms of the GNU GPL, version 2 or later.
>   * See the COPYING file in the top-level directory.
>   */
> @@ -29,5 +31,7 @@ void qemu_vfio_pci_unmap_bar(QEMUVFIOState *s, int index, void *bar,
>                               uint64_t offset, uint64_t size);
>  int qemu_vfio_pci_init_irq(QEMUVFIOState *s, EventNotifier *e,
>                             int irq_type, Error **errp);
> +int qemu_vfio_pci_msix_init_irqs(QEMUVFIOState *s,
> +                                 unsigned *irq_count, Error **errp);
>  
>  #endif
> diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
> index 874d76c2a2a..d88e2c7dc1f 100644
> --- a/util/vfio-helpers.c
> +++ b/util/vfio-helpers.c
> @@ -1,11 +1,13 @@
>  /*
>   * VFIO utility
>   *
> - * Copyright 2016 - 2018 Red Hat, Inc.
> + * Copyright 2016 - 2020 Red Hat, Inc.
>   *
>   * Authors:
>   *   Fam Zheng <famz@redhat.com>
> + *   Philippe Mathieu-Daudé <philmd@redhat.com>
>   *
> + * SPDX-License-Identifier: GPL-2.0-or-later
>   * This work is licensed under the terms of the GNU GPL, version 2 or later.
>   * See the COPYING file in the top-level directory.
>   */
> @@ -230,6 +232,67 @@ int qemu_vfio_pci_init_irq(QEMUVFIOState *s, EventNotifier *e,
>      return 0;
>  }
>  
> +/**
> + * Initialize device MSIX IRQs and register event notifiers.
> + * @irq_count: pointer to number of MSIX IRQs to initialize
> + *
> + * If the number of IRQs requested exceeds the available on the device,
> + * store the number of available IRQs in @irq_count and return -EOVERFLOW.
> + */
> +int qemu_vfio_pci_msix_init_irqs(QEMUVFIOState *s,
> +                                 unsigned *irq_count, Error **errp)
> +{
> +    int r;
> +    size_t irq_set_size;
> +    struct vfio_irq_set *irq_set;
> +    struct vfio_irq_info irq_info = {
> +        .argsz = sizeof(irq_info),
> +        .index = VFIO_PCI_MSIX_IRQ_INDEX
> +    };
> +
> +    if (ioctl(s->device, VFIO_DEVICE_GET_IRQ_INFO, &irq_info)) {
> +        error_setg_errno(errp, errno, "Failed to get device interrupt info");
> +        return -errno;
> +    }
> +    trace_qemu_vfio_msix_info_irqs(irq_info.count, *irq_count);
> +    if (irq_info.count < *irq_count) {
> +        error_setg(errp, "Not enough device interrupts available");
> +        *irq_count = irq_info.count;
> +        return -EOVERFLOW;
> +    }
> +    if (!(irq_info.flags & VFIO_IRQ_INFO_EVENTFD)) {
> +        error_setg(errp, "Device interrupt doesn't support eventfd");
> +        return -EINVAL;
> +    }
> +
> +    irq_set_size = sizeof(*irq_set) + *irq_count * sizeof(int32_t);
> +    irq_set = g_malloc0(irq_set_size);
> +
> +    /* Get to a known IRQ state */
> +    *irq_set = (struct vfio_irq_set) {
> +        .argsz = irq_set_size,
> +        .flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER,
> +        .index = VFIO_PCI_MSIX_IRQ_INDEX,
> +        .start = 0,
> +        .count = *irq_count,
> +    };
> +
> +    for (unsigned i = 0; i < *irq_count; i++) {
> +        ((int32_t *)&irq_set->data)[i] = -1; /* un-assigned: skip */
> +    }
> +    r = ioctl(s->device, VFIO_DEVICE_SET_IRQS, irq_set);
> +    g_free(irq_set);
> +    if (r < 0) {
> +        error_setg_errno(errp, errno, "Failed to setup device interrupts");
> +        return -errno;
> +    } else if (r > 0) {
Can it happen?

Thanks

Eric
> +        error_setg(errp, "Not enough device interrupts available");
> +        *irq_count = r;
> +        return -EOVERFLOW;
> +    }
> +    return 0;
> +}
> +
>  static int qemu_vfio_pci_read_config(QEMUVFIOState *s, void *buf,
>                                       int size, int ofs)
>  {
> diff --git a/util/trace-events b/util/trace-events
> index 3c36def9f30..ec93578b125 100644
> --- a/util/trace-events
> +++ b/util/trace-events
> @@ -87,6 +87,7 @@ qemu_vfio_do_mapping(void *s, void *host, uint64_t iova, size_t size) "s %p host
>  qemu_vfio_dma_map(void *s, void *host, size_t size, bool temporary, uint64_t *iova) "s %p host %p size 0x%zx temporary %d &iova %p"
>  qemu_vfio_dma_mapped(void *s, void *host, uint64_t iova, size_t size) "s %p host %p <-> iova 0x%"PRIx64" size 0x%zx"
>  qemu_vfio_dma_unmap(void *s, void *host) "s %p host %p"
> +qemu_vfio_msix_info_irqs(uint32_t count, unsigned asked) "msix irqs %"PRIu32" (asked: %u)"
>  qemu_vfio_iommu_iova_pgsizes(uint64_t iova_pgsizes) "iommu page size bitmask: 0x%08"PRIx64
>  qemu_vfio_pci_read_config(void *buf, int ofs, int size, uint64_t region_ofs, uint64_t region_size) "read cfg ptr %p ofs 0x%x size %d (region ofs 0x%"PRIx64" size %"PRId64")"
>  qemu_vfio_pci_write_config(void *buf, int ofs, int size, uint64_t region_ofs, uint64_t region_size) "write cfg ptr %p ofs 0x%x size %d (region ofs 0x%"PRIx64" size %"PRId64")"
>