Re: [Qemu-ppc] [PATCH qemu v10 13/14] vfio: spapr: Add SPAPR IOMMU v2 support (DMA memory preregistering)

[Alex Williamson]

On Mon, 2015-07-06 at 12:11 +1000, Alexey Kardashevskiy wrote:
> This makes use of the new "memory registering" feature. The idea is
> to provide the userspace ability to notify the host kernel about pages
> which are going to be used for DMA. Having this information, the host
> kernel can pin them all once per user process, do locked pages
> accounting (once) and not spent time on doing that in real time with
> possible failures which cannot be handled nicely in some cases.
> 
> This adds a guest RAM memory listener which notifies a VFIO container
> about memory which needs to be pinned/unpinned. VFIO MMIO regions
> (i.e. "skip dump" regions) are skipped.
> 
> The feature is only enabled for SPAPR IOMMU v2. The host kernel changes
> are required. Since v2 does not need/support VFIO_IOMMU_ENABLE, this does
> not call it when v2 is detected and enabled.
> 
> This does not change the guest visible interface.
> 
> Signed-off-by: Alexey Kardashevskiy <address@hidden>
> Reviewed-by: David Gibson <address@hidden>
> ---
> Changes:
> v9:
> * since there is no more SPAPR-specific data in container::iommu_data,
> the memory preregistration fields are common and potentially can be used
> by other architectures
> 
> v7:
> * in vfio_spapr_ram_listener_region_del(), do unref() after ioctl()
> * s'ramlistener'register_listener'
> 
> v6:
> * fixed commit log (s/guest/userspace/), added note about no guest visible
> change
> * fixed error checking if ram registration failed
> * added alignment check for section->offset_within_region
> 
> v5:
> * simplified the patch
> * added trace points
> * added round_up() for the size
> * SPAPR IOMMU v2 used
> ---
>  hw/vfio/common.c              | 109 
> ++++++++++++++++++++++++++++++++++++++----
>  include/hw/vfio/vfio-common.h |   3 ++
>  trace-events                  |   1 +
>  3 files changed, 104 insertions(+), 9 deletions(-)
> 
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 8eacfd7..0c7ba8c 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -488,6 +488,76 @@ static void vfio_listener_release(VFIOContainer 
> *container)
>      memory_listener_unregister(&container->iommu_data.type1.listener);
>  }
>  
> +static void vfio_ram_do_region(VFIOContainer *container,
> +                              MemoryRegionSection *section, unsigned long 
> req)
> +{
> +    int ret;
> +    struct vfio_iommu_spapr_register_memory reg = { .argsz = sizeof(reg) };

This function is not as general as the name would imply, it's spapr
specific due to this.  How about vfio_spapr_register_memory() with a
bool parameter toggling register vs unregister so we're not passing an
arbitrary ioctl number?

> +
> +    if (!memory_region_is_ram(section->mr) ||
> +        memory_region_is_skip_dump(section->mr)) {
> +        return;
> +    }
> +
> +    if (unlikely((section->offset_within_region & (getpagesize() - 1)))) {

s/getpagesize()/qemu_real_host_page_size/?

> +        error_report("%s received unaligned region", __func__);
> +        return;
> +    }
> +
> +    reg.vaddr = (__u64) memory_region_get_ram_ptr(section->mr) +
> +        section->offset_within_region;
> +    reg.size = ROUND_UP(int128_get64(section->size), TARGET_PAGE_SIZE);
> +
> +    ret = ioctl(container->fd, req, &reg);
> +    trace_vfio_ram_register(_IOC_NR(req) - VFIO_BASE, reg.vaddr, reg.size,
> +            ret ? -errno : 0);
> +    if (!ret) {
> +        return;
> +    }
> +
> +    /*
> +     * On the initfn path, store the first error in the container so we
> +     * can gracefully fail.  Runtime, there's not much we can do other
> +     * than throw a hardware error.
> +     */
> +    if (!container->iommu_data.ram_reg_initialized) {
> +        if (!container->iommu_data.ram_reg_error) {
> +            container->iommu_data.ram_reg_error = -errno;
> +        }
> +    } else {
> +        hw_error("vfio: RAM registering failed, unable to continue");
> +    }

I'd rather see:

if (ret) {
  if (!container...) {
    ...
  } else {
    ...
  }
}

Exiting early on success and otherwise falling into error handling is a
strange code flow.

> +}
> +
> +static void vfio_ram_listener_region_add(MemoryListener *listener,
> +                                         MemoryRegionSection *section)
> +{
> +    VFIOContainer *container = container_of(listener, VFIOContainer,
> +                                            iommu_data.register_listener);
> +    memory_region_ref(section->mr);
> +    vfio_ram_do_region(container, section, VFIO_IOMMU_SPAPR_REGISTER_MEMORY);

vfio_spapr_register_memory(container, section, true);

> +}
> +
> +static void vfio_ram_listener_region_del(MemoryListener *listener,
> +                                         MemoryRegionSection *section)
> +{
> +    VFIOContainer *container = container_of(listener, VFIOContainer,
> +                                            iommu_data.register_listener);
> +    vfio_ram_do_region(container, section, 
> VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY);

vfio_spapr_register_memory(container, section, false);

> +    memory_region_unref(section->mr);
> +}
> +
> +static const MemoryListener vfio_ram_memory_listener = {
> +    .region_add = vfio_ram_listener_region_add,
> +    .region_del = vfio_ram_listener_region_del,
> +};

These are all spapr specific, please reflect that in the name;
vfio_spapr_v2_memory_listener, vfio_spapr_v2_listener_add/del.

Actually, can't we determine what type of IOMMU we have and make the
existing MemoryListener handle either type1 or spapr or spapr-v2?

> +
> +static void vfio_spapr_listener_release_v2(VFIOContainer *container)
> +{
> +    memory_listener_unregister(&container->iommu_data.register_listener);
> +    vfio_listener_release(container);
> +}
> +
>  int vfio_mmap_region(Object *obj, VFIORegion *region,
>                       MemoryRegion *mem, MemoryRegion *submem,
>                       void **map, size_t size, off_t offset,
> @@ -698,14 +768,18 @@ static int vfio_connect_container(VFIOGroup *group, 
> AddressSpace *as)
>  
>          container->iommu_data.type1.initialized = true;
>  
> -    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) {
> +    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) ||
> +               ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) {
> +        bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU);
> +
>          ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
>          if (ret) {
>              error_report("vfio: failed to set group container: %m");
>              ret = -errno;
>              goto free_container_exit;
>          }
> -        ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU);
> +        ret = ioctl(fd, VFIO_SET_IOMMU,
> +                v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU);
>          if (ret) {
>              error_report("vfio: failed to set iommu for container: %m");
>              ret = -errno;
> @@ -717,19 +791,36 @@ static int vfio_connect_container(VFIOGroup *group, 
> AddressSpace *as)
>           * when container fd is closed so we do not call it explicitly
>           * in this file.
>           */
> -        ret = ioctl(fd, VFIO_IOMMU_ENABLE);
> -        if (ret) {
> -            error_report("vfio: failed to enable container: %m");
> -            ret = -errno;
> -            goto free_container_exit;
> +        if (!v2) {
> +            ret = ioctl(fd, VFIO_IOMMU_ENABLE);
> +            if (ret) {
> +                error_report("vfio: failed to enable container: %m");
> +                ret = -errno;
> +                goto free_container_exit;
> +            }
>          }
>  
>          container->iommu_data.type1.listener = vfio_memory_listener;
> -        container->iommu_data.release = vfio_listener_release;
> -
>          memory_listener_register(&container->iommu_data.type1.listener,
>                                   container->space->as);
>  
> +        if (!v2) {
> +            container->iommu_data.release = vfio_listener_release;
> +        } else {
> +            container->iommu_data.release = vfio_spapr_listener_release_v2;
> +            container->iommu_data.register_listener =
> +                    vfio_ram_memory_listener;
> +            
> memory_listener_register(&container->iommu_data.register_listener,
> +                                     &address_space_memory);
> +
> +            if (container->iommu_data.ram_reg_error) {
> +                error_report("vfio: RAM memory listener initialization 
> failed for container");
> +                goto listener_release_exit;
> +            }
> +
> +            container->iommu_data.ram_reg_initialized = true;
> +        }
> +
>      } else {
>          error_report("vfio: No available IOMMU models");
>          ret = -EINVAL;
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index 59a321d..b132248 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -79,6 +79,9 @@ typedef struct VFIOContainer {
>              VFIOType1 type1;
>          };
>          void (*release)(struct VFIOContainer *);
> +        MemoryListener register_listener;
> +        int ram_reg_error;
> +        bool ram_reg_initialized;

Isn't this exactly what the union above is for?

>      } iommu_data;
>      QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
>      QLIST_HEAD(, VFIOGroup) group_list;
> diff --git a/trace-events b/trace-events
> index a994019..b300e94 100644
> --- a/trace-events
> +++ b/trace-events
> @@ -1584,6 +1584,7 @@ vfio_disconnect_container(int fd) "close 
> container->fd=%d"
>  vfio_put_group(int fd) "close group->fd=%d"
>  vfio_get_device(const char * name, unsigned int flags, unsigned int 
> num_regions, unsigned int num_irqs) "Device %s flags: %u, regions: %u, irqs: 
> %u"
>  vfio_put_base_device(int fd) "close vdev->fd=%d"
> +vfio_ram_register(int req, uint64_t va, uint64_t size, int ret) "req=%d 
> va=%"PRIx64" size=%"PRIx64" ret=%d"
>  
>  # hw/vfio/platform.c
>  vfio_platform_populate_regions(int region_index, unsigned long flag, 
> unsigned long size, int fd, unsigned long offset) "- region %d flags = 0x%lx, 
> size = 0x%lx, fd= %d, offset = 0x%lx"