Re: [Qemu-devel] [PATCH qemu v14 17/18] vfio/spapr: Use VFIO_SPAPR_TCE_v2_IOMMU

[David Gibson <david@gibson.dropbear.id.au>]

[-- Attachment #1: Type: text/plain, Size: 9115 bytes --]

On Mon, Mar 21, 2016 at 06:47:05PM +1100, Alexey Kardashevskiy wrote:
> New VFIO_SPAPR_TCE_v2_IOMMU type supports dynamic DMA window management.
> This adds ability to VFIO common code to dynamically allocate/remove
> DMA windows in the host kernel when new VFIO container is added/removed.
> 
> This adds VFIO_IOMMU_SPAPR_TCE_CREATE ioctl to vfio_listener_region_add
> and adds just created IOMMU into the host IOMMU list; the opposite
> action is taken in vfio_listener_region_del.
> 
> When creating a new window, this uses euristic to decide on the TCE table
> levels number.
> 
> This should cause no guest visible change in behavior.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
> Changes:
> v14:
> * new to the series
> 
> ---
> TODO:
> * export levels to PHB
> ---
>  hw/vfio/common.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++++++++---
>  trace-events     |   2 ++
>  2 files changed, 105 insertions(+), 5 deletions(-)
> 
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 4e873b7..421d6eb 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -279,6 +279,14 @@ static int vfio_host_iommu_add(VFIOContainer *container,
>      return 0;
>  }
>  
> +static void vfio_host_iommu_del(VFIOContainer *container, hwaddr min_iova)
> +{
> +    VFIOHostIOMMU *hiommu = vfio_host_iommu_lookup(container, min_iova, 0x1000);

The hard-coded 0x1000 looks dubious..

> +    g_assert(hiommu);
> +    QLIST_REMOVE(hiommu, hiommu_next);
> +}
> +
>  static bool vfio_listener_skipped_section(MemoryRegionSection *section)
>  {
>      return (!memory_region_is_ram(section->mr) &&
> @@ -392,6 +400,61 @@ static void vfio_listener_region_add(MemoryListener *listener,
>      }
>      end = int128_get64(llend);
>  
> +    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {

I think this would be clearer split out into a helper function,
vfio_create_host_window() or something.

> +        unsigned entries, pages;
> +        struct vfio_iommu_spapr_tce_create create = { .argsz = sizeof(create) };
> +
> +        g_assert(section->mr->iommu_ops);
> +        g_assert(memory_region_is_iommu(section->mr));

I don't think you need these asserts.  AFAICT the same logic should
work if a RAM MR was added directly to PCI address space - this would
create the new host window, then the existing code for adding a RAM MR
would map that block of RAM statically into the new window.

> +        trace_vfio_listener_region_add_iommu(iova, end - 1);
> +        /*
> +         * FIXME: For VFIO iommu types which have KVM acceleration to
> +         * avoid bouncing all map/unmaps through qemu this way, this
> +         * would be the right place to wire that up (tell the KVM
> +         * device emulation the VFIO iommu handles to use).
> +         */
> +        create.window_size = memory_region_size(section->mr);
> +        create.page_shift =
> +                ctz64(section->mr->iommu_ops->get_page_sizes(section->mr));

Ah.. except that I guess you'd need to fall back to host page size
here to handle a RAM MR.

> +        /*
> +         * SPAPR host supports multilevel TCE tables, there is some
> +         * euristic to decide how many levels we want for our table:
> +         * 0..64 = 1; 65..4096 = 2; 4097..262144 = 3; 262145.. = 4
> +         */
> +        entries = create.window_size >> create.page_shift;
> +        pages = (entries * sizeof(uint64_t)) / getpagesize();
> +        create.levels = ctz64(pow2ceil(pages) - 1) / 6 + 1;
> +
> +        ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
> +        if (ret) {
> +            error_report("Failed to create a window, ret = %d (%m)", ret);
> +            goto fail;
> +        }
> +
> +        if (create.start_addr != section->offset_within_address_space ||
> +            vfio_host_iommu_lookup(container, create.start_addr,
> +                                   create.start_addr + create.window_size - 1)) {

Under what circumstances can this trigger?  Is the kernel ioctl
allowed to return a different window start address than the one
requested?

The second check looks very strange - if it returns true doesn't that
mean you *do* have host window which can accomodate this guest region,
which is what you want?

> +            struct vfio_iommu_spapr_tce_remove remove = {
> +                .argsz = sizeof(remove),
> +                .start_addr = create.start_addr
> +            };
> +            error_report("Host doesn't support DMA window at %"HWADDR_PRIx", must be %"PRIx64,
> +                         section->offset_within_address_space,
> +                         create.start_addr);
> +            ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
> +            ret = -EINVAL;
> +            goto fail;
> +        }
> +        trace_vfio_spapr_create_window(create.page_shift,
> +                                       create.window_size,
> +                                       create.start_addr);
> +
> +        vfio_host_iommu_add(container, create.start_addr,
> +                            create.start_addr + create.window_size - 1,
> +                            1ULL << create.page_shift);
> +    }
> +
>      if (!vfio_host_iommu_lookup(container, iova, end - 1)) {
>          error_report("vfio: IOMMU container %p can't map guest IOVA region"
>                       " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx,
> @@ -525,6 +588,22 @@ static void vfio_listener_region_del(MemoryListener *listener,
>                       container, iova, end - iova, ret);
>      }
>  
> +    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
> +        struct vfio_iommu_spapr_tce_remove remove = {
> +            .argsz = sizeof(remove),
> +            .start_addr = section->offset_within_address_space,
> +        };
> +        ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
> +        if (ret) {
> +            error_report("Failed to remove window at %"PRIx64,
> +                         remove.start_addr);
> +        }
> +
> +        vfio_host_iommu_del(container, section->offset_within_address_space);
> +
> +        trace_vfio_spapr_remove_window(remove.start_addr);
> +    }
> +
>      if (iommu && iommu->iommu_ops && iommu->iommu_ops->vfio_stop) {
>          iommu->iommu_ops->vfio_stop(section->mr);
>      }
> @@ -928,11 +1007,30 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
>              goto listener_release_exit;
>          }
>  
> -        /* The default table uses 4K pages */
> -        vfio_host_iommu_add(container, info.dma32_window_start,
> -                            info.dma32_window_start +
> -                            info.dma32_window_size - 1,
> -                            0x1000);
> +        if (v2) {
> +            /*
> +             * There is a default window in just created container.
> +             * To make region_add/del simpler, we better remove this
> +             * window now and let those iommu_listener callbacks
> +             * create/remove them when needed.
> +             */
> +            struct vfio_iommu_spapr_tce_remove remove = {
> +                .argsz = sizeof(remove),
> +                .start_addr = info.dma32_window_start,
> +            };
> +            ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
> +            if (ret) {
> +                error_report("vfio: VFIO_IOMMU_SPAPR_TCE_REMOVE failed: %m");
> +                ret = -errno;
> +                goto free_container_exit;
> +            }
> +        } else {
> +            /* The default table uses 4K pages */
> +            vfio_host_iommu_add(container, info.dma32_window_start,
> +                                info.dma32_window_start +
> +                                info.dma32_window_size - 1,
> +                                0x1000);
> +        }
>      } else {
>          error_report("vfio: No available IOMMU models");
>          ret = -EINVAL;
> diff --git a/trace-events b/trace-events
> index cc619e1..f2b75a3 100644
> --- a/trace-events
> +++ b/trace-events
> @@ -1736,6 +1736,8 @@ vfio_region_finalize(const char *name, int index) "Device %s, region %d"
>  vfio_region_mmaps_set_enabled(const char *name, bool enabled) "Region %s mmaps enabled: %d"
>  vfio_ram_register(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d"
>  vfio_ram_unregister(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d"
> +vfio_spapr_create_window(int ps, uint64_t ws, uint64_t off) "pageshift=0x%x winsize=0x%"PRIx64" offset=0x%"PRIx64
> +vfio_spapr_remove_window(uint64_t off) "offset=%"PRIx64
>  
>  # hw/vfio/platform.c
>  vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d"

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]