[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [RFC PATCH 4/8] exec: introduce address_space_get_iotlb
From: |
Peter Xu |
Subject: |
Re: [Qemu-devel] [RFC PATCH 4/8] exec: introduce address_space_get_iotlb_entry() |
Date: |
Mon, 28 Mar 2016 10:18:00 +0800 |
User-agent: |
Mutt/1.5.24 (2015-08-30) |
On Fri, Mar 25, 2016 at 10:13:25AM +0800, Jason Wang wrote:
> This patch introduces a helper to query the iotlb entry for a
> possible iova. This will be used by later device IOTLB API to enable
> the capability for a dataplane (e.g vhost) to query the IOTLB.
>
> Cc: Paolo Bonzini <address@hidden>
> Cc: Peter Crosthwaite <address@hidden>
> Cc: Richard Henderson <address@hidden>
> Signed-off-by: Jason Wang <address@hidden>
> ---
> exec.c | 30 ++++++++++++++++++++++++++++++
> include/exec/memory.h | 7 +++++++
> 2 files changed, 37 insertions(+)
>
> diff --git a/exec.c b/exec.c
> index f398d21..31fac9f 100644
> --- a/exec.c
> +++ b/exec.c
> @@ -411,6 +411,36 @@ address_space_translate_internal(AddressSpaceDispatch
> *d, hwaddr addr, hwaddr *x
> }
>
> /* Called from RCU critical section */
> +IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr,
> + bool is_write)
> +{
> + IOMMUTLBEntry iotlb = {0};
> + MemoryRegionSection *section;
> + MemoryRegion *mr;
> + hwaddr plen;
> +
> + for (;;) {
> + AddressSpaceDispatch *d = atomic_rcu_read(&as->dispatch);
> + section = address_space_translate_internal(d, addr, &addr, &plen,
> true);
> + mr = section->mr;
> +
> + if (!mr->iommu_ops) {
> + break;
> + }
> +
> + iotlb = mr->iommu_ops->translate(mr, addr, is_write);
> + if (!(iotlb.perm & (1 << is_write))) {
> + iotlb.target_as = NULL;
> + break;
> + }
Here, do we still need something like:
addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
| (addr & iotlb.addr_mask));
Just as address_space_translate() does? Now "addr" should be the
offset in memory region "mr", while we need it to be the offset in
address space if there are more loops, right?
Also, not sure whether we can abstract a shared function out of this
function and address_space_translate().
Thanks.
-- peterx
- [Qemu-devel] [RFC PATCH 0/8] virtio/vhost DMAR support, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 2/8] intel_iommu: name vtd address space with devfn, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 3/8] intel_iommu: allocate new key when creating new address space, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 1/8] virtio: convert to use DMA api, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 4/8] exec: introduce address_space_get_iotlb_entry(), Jason Wang, 2016/03/24
- Re: [Qemu-devel] [RFC PATCH 4/8] exec: introduce address_space_get_iotlb_entry(),
Peter Xu <=
- [Qemu-devel] [RFC PATCH 5/8] virtio-pci: address space translation service (ATS) support, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 6/8] intel_iommu: support device iotlb descriptor, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 7/8] memory: handle alias for iommu notifier, Jason Wang, 2016/03/24
- [Qemu-devel] [RFC PATCH 8/8] vhost_net: device IOTLB support, Jason Wang, 2016/03/24