On Thu, Apr 14, 2022, Vitaly Kuznetsov wrote:
> @@ -1862,15 +1890,58 @@ void kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
> {
> struct kvm_vcpu_hv_tlb_flush_ring *tlb_flush_ring;
> struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
> + struct kvm_vcpu_hv_tlb_flush_entry *entry;
> + int read_idx, write_idx;
> + u64 address;
> + u32 count;
> + int i, j;
>
> - kvm_vcpu_flush_tlb_guest(vcpu);
> -
> - if (!hv_vcpu)
> + if (!tdp_enabled || !hv_vcpu) {
> + kvm_vcpu_flush_tlb_guest(vcpu);
> return;
> + }
>
> tlb_flush_ring = &hv_vcpu->tlb_flush_ring;
>
> - tlb_flush_ring->read_idx = tlb_flush_ring->write_idx;
> + /*
> + * TLB flush must be performed on the target vCPU so 'read_idx'
> + * (AKA 'tail') cannot change underneath, the compiler is free
> + * to re-read it.
> + */
> + read_idx = tlb_flush_ring->read_idx;
> +
> + /*
> + * 'write_idx' (AKA 'head') can be concurently updated by a different
> + * vCPU so we must be sure it's read once.
> + */
> + write_idx = READ_ONCE(tlb_flush_ring->write_idx);
> +
> + /* Pairs with smp_wmb() in hv_tlb_flush_ring_enqueue() */
> + smp_rmb();
> +
> + for (i = read_idx; i != write_idx; i = (i + 1) % KVM_HV_TLB_FLUSH_RING_SIZE) {
> + entry = &tlb_flush_ring->entries[i];
> +
> + if (entry->flush_all)
> + goto out_flush_all;
> +
> + /*
> + * Lower 12 bits of 'address' encode the number of additional
> + * pages to flush.
> + */
> + address = entry->addr & PAGE_MASK;
> + count = (entry->addr & ~PAGE_MASK) + 1;
> + for (j = 0; j < count; j++)
> + static_call(kvm_x86_flush_tlb_gva)(vcpu, address + j * PAGE_SIZE);
> + }
> + ++vcpu->stat.tlb_flush;
Bumping tlb_flush is inconsistent with how KVM handles INVLPG, and could be wrong
if the ring is empty (might be impossible without a bug?). And if my math is right,
or at least in the ballpark, tlb_flush will be incremented once regardless of whether
the loop flushed 1 page or 64k pages (completely full ring, full count on every one).
I'd prefer to either drop the stat adjustment entirely, or bump invlpg in the loop, e.g.
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 56f06cf85282..5654c9d56289 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1945,10 +1945,11 @@ void kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
for (i = read_idx; i != write_idx; i = (i + 1) % KVM_HV_TLB_FLUSH_RING_SIZE) {
address = tlb_flush_ring->entries[i] & PAGE_MASK;
count = (tlb_flush_ring->entries[i] & ~PAGE_MASK) + 1;
- for (j = 0; j < count; j++)
+ for (j = 0; j < count; j++) {
static_call(kvm_x86_flush_tlb_gva)(vcpu, address + j * PAGE_SIZE);
+ ++vcpu->stat.invlpg;
+ }
}
- ++vcpu->stat.tlb_flush;
out_empty_ring:
tlb_flush_ring->read_idx = write_idx;
> + goto out_empty_ring;
> +
> +out_flush_all:
> + kvm_vcpu_flush_tlb_guest(vcpu);
> +
> +out_empty_ring:
> + tlb_flush_ring->read_idx = write_idx;
> }
>
