Commit 222f06e7 authored by Chia-I Wu's avatar Chia-I Wu Committed by Paolo Bonzini

KVM: vmx: rewrite the comment in vmx_get_mt_mask

Better reflect the structure of the code and metion why we could not
always honor the guest.
Signed-off-by: default avatarChia-I Wu <olvaffe@gmail.com>
Cc: Gurchetan Singh <gurchetansingh@chromium.org>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent 244c6b6d
...@@ -6898,17 +6898,24 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) ...@@ -6898,17 +6898,24 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
u8 cache; u8 cache;
u64 ipat = 0; u64 ipat = 0;
/* For VT-d and EPT combination /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in
* 1. MMIO: always map as UC * memory aliases with conflicting memory types and sometimes MCEs.
* 2. EPT with VT-d: * We have to be careful as to what are honored and when.
* a. VT-d without snooping control feature: can't guarantee the *
* result, try to trust guest. * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to
* b. VT-d with snooping control feature: snooping control feature of * UC. The effective memory type is UC or WC depending on guest PAT.
* VT-d engine can guarantee the cache correctness. Just set it * This was historically the source of MCEs and we want to be
* to WB to keep consistent with host. So the same as item 3. * conservative.
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep *
* consistent with host MTRR * When there is no need to deal with noncoherent DMA (e.g., no VT-d
* or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The
* EPT memory type is set to WB. The effective memory type is forced
* WB.
*
* Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The
* EPT memory type is used to emulate guest CD/MTRR.
*/ */
if (is_mmio) { if (is_mmio) {
cache = MTRR_TYPE_UNCACHABLE; cache = MTRR_TYPE_UNCACHABLE;
goto exit; goto exit;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment