From: "Cédric Le Goater" <clg@redhat.com>
To: John Levon <john.levon@nutanix.com>, qemu-devel@nongnu.org
Cc: "Peter Xu" <peterx@redhat.com>,
qemu-s390x@nongnu.org, "Jason Herne" <jjherne@linux.ibm.com>,
"Tomita Moeko" <tomitamoeko@gmail.com>,
"Markus Armbruster" <armbru@redhat.com>,
"Matthew Rosato" <mjrosato@linux.ibm.com>,
"Eric Farman" <farman@linux.ibm.com>,
"David Hildenbrand" <david@redhat.com>,
"Philippe Mathieu-Daudé" <philmd@linaro.org>,
"Michael S. Tsirkin" <mst@redhat.com>,
"Tony Krowiak" <akrowiak@linux.ibm.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Stefano Garzarella" <sgarzare@redhat.com>,
"Thomas Huth" <thuth@redhat.com>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Halil Pasic" <pasic@linux.ibm.com>,
"John Johnson" <john.g.johnson@oracle.com>,
"Elena Ufimtseva" <elena.ufimtseva@oracle.com>,
"Jagannathan Raman" <jag.raman@oracle.com>
Subject: Re: [PATCH v2 10/15] vfio: add device IO ops vector
Date: Mon, 5 May 2025 14:21:42 +0200 [thread overview]
Message-ID: <d56d6565-0839-4f7d-9100-e1bcf03ebc60@redhat.com> (raw)
In-Reply-To: <20250430194003.2793823-11-john.levon@nutanix.com>
On 4/30/25 21:39, John Levon wrote:
> For vfio-user, device operations such as IRQ handling and region
> read/writes are implemented in userspace over the control socket, not
> ioctl() to the vfio kernel driver; add an ops vector to generalize this,
> and implement vfio_device_io_ops_ioctl for interacting with the kernel
> vfio driver.
>
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/container-base.c | 6 +--
> hw/vfio/device.c | 77 ++++++++++++++++++++++++++++++-----
> hw/vfio/listener.c | 13 +++---
> hw/vfio/pci.c | 10 ++---
> include/hw/vfio/vfio-device.h | 38 +++++++++++++++++
> 5 files changed, 117 insertions(+), 27 deletions(-)
>
> diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
> index 3ff473a45c..1c6ca94b60 100644
> --- a/hw/vfio/container-base.c
> +++ b/hw/vfio/container-base.c
> @@ -198,11 +198,7 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
> feature->flags = VFIO_DEVICE_FEATURE_GET |
> VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;
>
> - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
> - return -errno;
> - }
> -
> - return 0;
> + return vbasedev->io_ops->device_feature(vbasedev, feature);
> }
>
> static int vfio_container_iommu_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
> diff --git a/hw/vfio/device.c b/hw/vfio/device.c
> index 5d837092cb..468fb50eac 100644
> --- a/hw/vfio/device.c
> +++ b/hw/vfio/device.c
> @@ -82,7 +82,7 @@ void vfio_device_irq_disable(VFIODevice *vbasedev, int index)
> .count = 0,
> };
>
> - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
> + vbasedev->io_ops->set_irqs(vbasedev, &irq_set);
> }
>
> void vfio_device_irq_unmask(VFIODevice *vbasedev, int index)
> @@ -95,7 +95,7 @@ void vfio_device_irq_unmask(VFIODevice *vbasedev, int index)
> .count = 1,
> };
>
> - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
> + vbasedev->io_ops->set_irqs(vbasedev, &irq_set);
> }
>
> void vfio_device_irq_mask(VFIODevice *vbasedev, int index)
> @@ -108,7 +108,7 @@ void vfio_device_irq_mask(VFIODevice *vbasedev, int index)
> .count = 1,
> };
>
> - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
> + vbasedev->io_ops->set_irqs(vbasedev, &irq_set);
> }
>
> static inline const char *action_to_str(int action)
> @@ -155,6 +155,7 @@ bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex
> int argsz;
> const char *name;
> int32_t *pfd;
> + int ret;
Why adding a 'ret' variable here ?
The rest looks good.
Thanks,
C.
> argsz = sizeof(*irq_set) + sizeof(*pfd);
>
> @@ -167,7 +168,9 @@ bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex
> pfd = (int32_t *)&irq_set->data;
> *pfd = fd;
>
> - if (!ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
> + ret = vbasedev->io_ops->set_irqs(vbasedev, irq_set);
> +
> + if (!ret) {
> return true;
> }
>
> @@ -188,22 +191,19 @@ bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex
> int vfio_device_get_irq_info(VFIODevice *vbasedev, int index,
> struct vfio_irq_info *info)
> {
> - int ret;
> -
> memset(info, 0, sizeof(*info));
>
> info->argsz = sizeof(*info);
> info->index = index;
>
> - ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
> -
> - return ret < 0 ? -errno : ret;
> + return vbasedev->io_ops->get_irq_info(vbasedev, info);
> }
>
> int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
> struct vfio_region_info **info)
> {
> size_t argsz = sizeof(struct vfio_region_info);
> + int ret;
>
> *info = g_malloc0(argsz);
>
> @@ -211,10 +211,11 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
> retry:
> (*info)->argsz = argsz;
>
> - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
> + ret = vbasedev->io_ops->get_region_info(vbasedev, *info);
> + if (ret != 0) {
> g_free(*info);
> *info = NULL;
> - return -errno;
> + return ret;
> }
>
> if ((*info)->argsz > argsz) {
> @@ -320,11 +321,14 @@ void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
> vbasedev->fd = fd;
> }
>
> +static VFIODeviceIOOps vfio_device_io_ops_ioctl;
> +
> void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
> DeviceState *dev, bool ram_discard)
> {
> vbasedev->type = type;
> vbasedev->ops = ops;
> + vbasedev->io_ops = &vfio_device_io_ops_ioctl;
> vbasedev->dev = dev;
> vbasedev->fd = -1;
>
> @@ -442,3 +446,54 @@ void vfio_device_unprepare(VFIODevice *vbasedev)
> QLIST_REMOVE(vbasedev, global_next);
> vbasedev->bcontainer = NULL;
> }
> +
> +/*
> + * Traditional ioctl() based io
> + */
> +
> +static int vfio_device_io_device_feature(VFIODevice *vbasedev,
> + struct vfio_device_feature *feature)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_device_io_get_region_info(VFIODevice *vbasedev,
> + struct vfio_region_info *info)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_device_io_get_irq_info(VFIODevice *vbasedev,
> + struct vfio_irq_info *info)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_device_io_set_irqs(VFIODevice *vbasedev,
> + struct vfio_irq_set *irqs)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irqs);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static VFIODeviceIOOps vfio_device_io_ops_ioctl = {
> + .device_feature = vfio_device_io_device_feature,
> + .get_region_info = vfio_device_io_get_region_info,
> + .get_irq_info = vfio_device_io_get_irq_info,
> + .set_irqs = vfio_device_io_set_irqs,
> +};
> diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
> index e7ade7d62e..2b93ca55b6 100644
> --- a/hw/vfio/listener.c
> +++ b/hw/vfio/listener.c
> @@ -794,13 +794,17 @@ static void vfio_devices_dma_logging_stop(VFIOContainerBase *bcontainer)
> VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP;
>
> QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
> + int ret;
> +
> if (!vbasedev->dirty_tracking) {
> continue;
> }
>
> - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
> + ret = vbasedev->io_ops->device_feature(vbasedev, feature);
> +
> + if (ret != 0) {
> warn_report("%s: Failed to stop DMA logging, err %d (%s)",
> - vbasedev->name, -errno, strerror(errno));
> + vbasedev->name, -ret, strerror(-ret));
> }
> vbasedev->dirty_tracking = false;
> }
> @@ -901,10 +905,9 @@ static bool vfio_devices_dma_logging_start(VFIOContainerBase *bcontainer,
> continue;
> }
>
> - ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
> + ret = vbasedev->io_ops->device_feature(vbasedev, feature);
> if (ret) {
> - ret = -errno;
> - error_setg_errno(errp, errno, "%s: Failed to start DMA logging",
> + error_setg_errno(errp, -ret, "%s: Failed to start DMA logging",
> vbasedev->name);
> goto out;
> }
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 8455010d62..bbf95215cc 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -381,7 +381,7 @@ static void vfio_msi_interrupt(void *opaque)
> static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
> {
> g_autofree struct vfio_irq_set *irq_set = NULL;
> - int ret = 0, argsz;
> + int argsz;
> int32_t *fd;
>
> argsz = sizeof(*irq_set) + sizeof(*fd);
> @@ -396,9 +396,7 @@ static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
> fd = (int32_t *)&irq_set->data;
> *fd = -1;
>
> - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> -
> - return ret < 0 ? -errno : ret;
> + return vdev->vbasedev.io_ops->set_irqs(&vdev->vbasedev, irq_set);
> }
>
> static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
> @@ -455,11 +453,11 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
> fds[i] = fd;
> }
>
> - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> + ret = vdev->vbasedev.io_ops->set_irqs(&vdev->vbasedev, irq_set);
>
> g_free(irq_set);
>
> - return ret < 0 ? -errno : ret;
> + return ret;
> }
>
> static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,
> diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
> index 5b833868c9..e89ed02c0e 100644
> --- a/include/hw/vfio/vfio-device.h
> +++ b/include/hw/vfio/vfio-device.h
> @@ -41,6 +41,7 @@ enum {
> };
>
> typedef struct VFIODeviceOps VFIODeviceOps;
> +typedef struct VFIODeviceIOOps VFIODeviceIOOps;
> typedef struct VFIOMigration VFIOMigration;
>
> typedef struct IOMMUFDBackend IOMMUFDBackend;
> @@ -66,6 +67,7 @@ typedef struct VFIODevice {
> OnOffAuto migration_multifd_transfer;
> bool migration_events;
> VFIODeviceOps *ops;
> + VFIODeviceIOOps *io_ops;
> unsigned int num_irqs;
> unsigned int num_regions;
> unsigned int flags;
> @@ -141,6 +143,42 @@ typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList;
> extern VFIODeviceList vfio_device_list;
>
> #ifdef CONFIG_LINUX
> +/*
> + * How devices communicate with the server. The default option is through
> + * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote
> + * process.
> + */
> +struct VFIODeviceIOOps {
> + /**
> + * @device_feature
> + *
> + * Fill in feature info for the given device.
> + */
> + int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *);
> +
> + /**
> + * @get_region_info
> + *
> + * Fill in @info with information on the region given by @info->index.
> + */
> + int (*get_region_info)(VFIODevice *vdev,
> + struct vfio_region_info *info);
> +
> + /**
> + * @get_irq_info
> + *
> + * Fill in @irq with information on the IRQ given by @info->index.
> + */
> + int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq);
> +
> + /**
> + * @set_irqs
> + *
> + * Configure IRQs as defined by @irqs.
> + */
> + int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs);
> +};
> +
> int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
> struct vfio_region_info **info);
> int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type,
next prev parent reply other threads:[~2025-05-05 12:22 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-30 19:39 [PATCH v2 00/15] vfio: preparation for vfio-user John Levon
2025-04-30 19:39 ` [PATCH v2 01/15] vfio: add vfio_prepare_device() John Levon
2025-05-05 8:35 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 02/15] vfio: add vfio_unprepare_device() John Levon
2025-05-05 9:18 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 03/15] vfio: add vfio_attach_device_by_iommu_type() John Levon
2025-04-30 19:39 ` [PATCH v2 04/15] vfio: add vfio_device_get_irq_info() helper John Levon
2025-05-01 11:53 ` Anthony Krowiak
2025-05-05 9:19 ` Cédric Le Goater
2025-05-06 11:38 ` John Levon
2025-05-06 12:27 ` Cédric Le Goater
2025-05-06 12:35 ` John Levon
2025-04-30 19:39 ` [PATCH v2 05/15] vfio: consistently handle return value for helpers John Levon
2025-05-05 9:32 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 06/15] include/qemu: add strread/writeerror() John Levon
2025-05-05 9:37 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 07/15] vfio: add vfio_pci_config_space_read/write() John Levon
2025-05-05 9:45 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 08/15] vfio: add unmap_all flag to DMA unmap callback John Levon
2025-05-05 12:06 ` Cédric Le Goater
2025-05-05 13:26 ` John Levon
2025-05-05 21:05 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 09/15] vfio: implement unmap all for DMA unmap callbacks John Levon
2025-05-05 11:28 ` Cédric Le Goater
2025-05-07 11:47 ` John Levon
2025-04-30 19:39 ` [PATCH v2 10/15] vfio: add device IO ops vector John Levon
2025-05-05 12:21 ` Cédric Le Goater [this message]
2025-05-06 10:01 ` Cédric Le Goater
2025-04-30 19:39 ` [PATCH v2 11/15] vfio: add region info cache John Levon
2025-05-05 12:26 ` Cédric Le Goater
2025-04-30 19:40 ` [PATCH v2 12/15] vfio: add read/write to device IO ops vector John Levon
2025-05-05 12:39 ` Cédric Le Goater
2025-04-30 19:40 ` [PATCH v2 13/15] vfio: add vfio-pci-base class John Levon
2025-05-05 12:42 ` Cédric Le Goater
2025-04-30 19:40 ` [PATCH v2 14/15] vfio/container: pass listener_begin/commit callbacks John Levon
2025-05-05 12:43 ` Cédric Le Goater
2025-04-30 19:40 ` [PATCH v2 15/15] vfio/container: pass MemoryRegion to DMA operations John Levon
2025-05-05 12:46 ` Cédric Le Goater
2025-05-07 13:58 ` John Levon
2025-05-09 10:28 ` Cédric Le Goater
2025-05-05 12:51 ` [PATCH v2 00/15] vfio: preparation for vfio-user Cédric Le Goater
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d56d6565-0839-4f7d-9100-e1bcf03ebc60@redhat.com \
--to=clg@redhat.com \
--cc=akrowiak@linux.ibm.com \
--cc=alex.williamson@redhat.com \
--cc=armbru@redhat.com \
--cc=david@redhat.com \
--cc=elena.ufimtseva@oracle.com \
--cc=farman@linux.ibm.com \
--cc=jag.raman@oracle.com \
--cc=jjherne@linux.ibm.com \
--cc=john.g.johnson@oracle.com \
--cc=john.levon@nutanix.com \
--cc=mjrosato@linux.ibm.com \
--cc=mst@redhat.com \
--cc=pasic@linux.ibm.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=philmd@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=qemu-s390x@nongnu.org \
--cc=sgarzare@redhat.com \
--cc=thuth@redhat.com \
--cc=tomitamoeko@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).