Re: [Qemu-ppc] [RFC PATCH qemu v2 1/5] vfio: Switch from TARGET_PAGE_MASK to qemu_real_host_page_mask

[Alex Williamson]

On Tue, 2015-07-14 at 00:56 +1000, Alexey Kardashevskiy wrote:
> These started switching from TARGET_PAGE_MASK (hardcoded as 4K) to
> a real host page size:
> 4e51361d7 "cpu-all: complete "real" host page size API" and
> f7ceed190 "vfio: cpu: Use "real" page size API"
> 
> This finished the transition by:
> - %s/TARGET_PAGE_MASK/qemu_real_host_page_mask/
> - %s/TARGET_PAGE_ALIGN/REAL_HOST_PAGE_ALIGN/
> - removing bitfield length for offsets in VFIOQuirk::data as
> qemu_real_host_page_mask is not a macro

Can we assume that none of the changes to quirks have actually been
tested?  I don't really support them being bundled in here since they
really aren't related to what you're doing.  For DMA we generally want
to be host IOMMU page aligned, which we can generally assume is the same
as host page aligned, but quirks are simply I/O regions, so I think they
ought to continue to be target page aligned.

> This keeps using TARGET_PAGE_MASK for IOMMU regions though as it is
> the minimum page size which IOMMU regions may be using and at the moment
> memory regions do not carry the actual page size.
> 
> Signed-off-by: Alexey Kardashevskiy <address@hidden>
> ---
> 
> In reality DMA windows are always a lot bigger than a single 4K page
> and aligned to 32/64MB, may be only use here qemu_real_host_page_mask?

I don't understand what this is asking either.  While the bulk of memory
is going to be mapped in larger chunks, we do occasionally see 4k
mappings on x86, particularly in some of the legacy low memory areas.

> ---
>  hw/vfio/common.c | 26 ++++++++++++++++----------
>  hw/vfio/pci.c    | 30 +++++++++++++++---------------
>  2 files changed, 31 insertions(+), 25 deletions(-)
> 
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 85ee9b0..d115ec9 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -321,6 +321,9 @@ static void vfio_listener_region_add(MemoryListener 
> *listener,
>      Int128 llend;
>      void *vaddr;
>      int ret;
> +    const bool is_iommu = memory_region_is_iommu(section->mr);
> +    const hwaddr page_mask =
> +        is_iommu ? TARGET_PAGE_MASK : qemu_real_host_page_mask;
>  
>      if (vfio_listener_skipped_section(section)) {
>          trace_vfio_listener_region_add_skip(
> @@ -330,16 +333,16 @@ static void vfio_listener_region_add(MemoryListener 
> *listener,
>          return;
>      }
>  
> -    if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) 
> !=
> -                 (section->offset_within_region & ~TARGET_PAGE_MASK))) {
> +    if (unlikely((section->offset_within_address_space & ~page_mask) !=
> +                 (section->offset_within_region & ~page_mask))) {
>          error_report("%s received unaligned region", __func__);
>          return;
>      }
>  
> -    iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
> +    iova = ROUND_UP(section->offset_within_address_space, ~page_mask + 1);
>      llend = int128_make64(section->offset_within_address_space);
>      llend = int128_add(llend, section->size);
> -    llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK));
> +    llend = int128_and(llend, int128_exts64(page_mask));
>  
>      if (int128_ge(int128_make64(iova), llend)) {
>          return;
> @@ -347,7 +350,7 @@ static void vfio_listener_region_add(MemoryListener 
> *listener,
>  
>      memory_region_ref(section->mr);
>  
> -    if (memory_region_is_iommu(section->mr)) {
> +    if (is_iommu) {
>          VFIOGuestIOMMU *giommu;
>  
>          trace_vfio_listener_region_add_iommu(iova,
> @@ -423,6 +426,9 @@ static void vfio_listener_region_del(MemoryListener 
> *listener,
>                                              iommu_data.type1.listener);
>      hwaddr iova, end;
>      int ret;
> +    const bool is_iommu = memory_region_is_iommu(section->mr);
> +    const hwaddr page_mask =
> +        is_iommu ? TARGET_PAGE_MASK : qemu_real_host_page_mask;
>  
>      if (vfio_listener_skipped_section(section)) {
>          trace_vfio_listener_region_del_skip(
> @@ -432,13 +438,13 @@ static void vfio_listener_region_del(MemoryListener 
> *listener,
>          return;
>      }
>  
> -    if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) 
> !=
> -                 (section->offset_within_region & ~TARGET_PAGE_MASK))) {
> +    if (unlikely((section->offset_within_address_space & ~page_mask) !=
> +                 (section->offset_within_region & ~page_mask))) {
>          error_report("%s received unaligned region", __func__);
>          return;
>      }
>  
> -    if (memory_region_is_iommu(section->mr)) {
> +    if (is_iommu) {
>          VFIOGuestIOMMU *giommu;
>  
>          QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
> @@ -459,9 +465,9 @@ static void vfio_listener_region_del(MemoryListener 
> *listener,
>           */
>      }
>  
> -    iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
> +    iova = REAL_HOST_PAGE_ALIGN(section->offset_within_address_space);
>      end = (section->offset_within_address_space + 
> int128_get64(section->size)) &
> -          TARGET_PAGE_MASK;
> +          page_mask;
>  
>      if (iova >= end) {
>          return;
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 2ed877f..7694afe 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -50,16 +50,16 @@ typedef struct VFIOQuirk {
>      struct VFIOPCIDevice *vdev;
>      QLIST_ENTRY(VFIOQuirk) next;
>      struct {
> -        uint32_t base_offset:TARGET_PAGE_BITS;
> -        uint32_t address_offset:TARGET_PAGE_BITS;
> +        uint32_t base_offset;
> +        uint32_t address_offset;
>          uint32_t address_size:3;
>          uint32_t bar:3;
>  
>          uint32_t address_match;
>          uint32_t address_mask;
>  
> -        uint32_t address_val:TARGET_PAGE_BITS;
> -        uint32_t data_offset:TARGET_PAGE_BITS;
> +        uint32_t address_val;
> +        uint32_t data_offset;
>          uint32_t data_size:3;
>  
>          uint8_t flags;
> @@ -1319,8 +1319,8 @@ static uint64_t vfio_generic_quirk_read(void *opaque,
>  {
>      VFIOQuirk *quirk = opaque;
>      VFIOPCIDevice *vdev = quirk->vdev;
> -    hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK;
> -    hwaddr offset = quirk->data.address_match & ~TARGET_PAGE_MASK;
> +    hwaddr base = quirk->data.address_match & qemu_real_host_page_mask;
> +    hwaddr offset = quirk->data.address_match & ~qemu_real_host_page_mask;
>      uint64_t data;
>  
>      if (vfio_flags_enabled(quirk->data.flags, quirk->data.read_flags) &&
> @@ -1349,8 +1349,8 @@ static void vfio_generic_quirk_write(void *opaque, 
> hwaddr addr,
>  {
>      VFIOQuirk *quirk = opaque;
>      VFIOPCIDevice *vdev = quirk->vdev;
> -    hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK;
> -    hwaddr offset = quirk->data.address_match & ~TARGET_PAGE_MASK;
> +    hwaddr base = quirk->data.address_match & qemu_real_host_page_mask;
> +    hwaddr offset = quirk->data.address_match & ~qemu_real_host_page_mask;
>  
>      if (vfio_flags_enabled(quirk->data.flags, quirk->data.write_flags) &&
>          ranges_overlap(addr, size, offset, quirk->data.address_mask + 1)) {
> @@ -1650,9 +1650,9 @@ static void 
> vfio_probe_ati_bar2_4000_quirk(VFIOPCIDevice *vdev, int nr)
>  
>      memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_quirk, 
> quirk,
>                            "vfio-ati-bar2-4000-quirk",
> -                          TARGET_PAGE_ALIGN(quirk->data.address_mask + 1));
> +                          REAL_HOST_PAGE_ALIGN(quirk->data.address_mask + 
> 1));
>      memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem,
> -                          quirk->data.address_match & TARGET_PAGE_MASK,
> +                          quirk->data.address_match & 
> qemu_real_host_page_mask,
>                            &quirk->mem, 1);
>  
>      QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);
> @@ -1888,7 +1888,7 @@ static void vfio_nvidia_88000_quirk_write(void *opaque, 
> hwaddr addr,
>      VFIOQuirk *quirk = opaque;
>      VFIOPCIDevice *vdev = quirk->vdev;
>      PCIDevice *pdev = &vdev->pdev;
> -    hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK;
> +    hwaddr base = quirk->data.address_match & qemu_real_host_page_mask;
>  
>      vfio_generic_quirk_write(opaque, addr, data, size);
>  
> @@ -1943,9 +1943,9 @@ static void 
> vfio_probe_nvidia_bar0_88000_quirk(VFIOPCIDevice *vdev, int nr)
>  
>      memory_region_init_io(&quirk->mem, OBJECT(vdev), 
> &vfio_nvidia_88000_quirk,
>                            quirk, "vfio-nvidia-bar0-88000-quirk",
> -                          TARGET_PAGE_ALIGN(quirk->data.address_mask + 1));
> +                          REAL_HOST_PAGE_ALIGN(quirk->data.address_mask + 
> 1));
>      memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem,
> -                          quirk->data.address_match & TARGET_PAGE_MASK,
> +                          quirk->data.address_match & 
> qemu_real_host_page_mask,
>                            &quirk->mem, 1);
>  
>      QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);
> @@ -1980,9 +1980,9 @@ static void 
> vfio_probe_nvidia_bar0_1800_quirk(VFIOPCIDevice *vdev, int nr)
>  
>      memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_quirk, 
> quirk,
>                            "vfio-nvidia-bar0-1800-quirk",
> -                          TARGET_PAGE_ALIGN(quirk->data.address_mask + 1));
> +                          REAL_HOST_PAGE_ALIGN(quirk->data.address_mask + 
> 1));
>      memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem,
> -                          quirk->data.address_match & TARGET_PAGE_MASK,
> +                          quirk->data.address_match & 
> qemu_real_host_page_mask,
>                            &quirk->mem, 1);
>  
>      QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);