To prepare for handling page faults in parallel, change the TDP MMU
page fault handler to use atomic operations to set SPTEs so that changes
are not lost if multiple threads attempt to modify the same SPTE.
Reviewed-by: Peter Feiner <pfei...@google.com>
Signed-off-by: Ben Gardon <bgar...@google.com>
---
arch/x86/kvm/mmu/tdp_mmu.c | 38 ++++++++++++++++++++++----------------
1 file changed, 22 insertions(+), 16 deletions(-)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 1380ed313476..7b12a87a4124 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -714,21 +714,18 @@ static int tdp_mmu_map_handle_target_level(struct
kvm_vcpu *vcpu, int write,
int ret = 0;
int make_spte_ret = 0;
- if (unlikely(is_noslot_pfn(pfn))) {
+ if (unlikely(is_noslot_pfn(pfn)))
new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
- trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte);
- } else {
+ else
make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn,
pfn, iter->old_spte, prefault, true,
map_writable, !shadow_accessed_mask,
&new_spte);
- trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
- }
if (new_spte == iter->old_spte)
ret = RET_PF_SPURIOUS;
- else
- tdp_mmu_set_spte(vcpu->kvm, iter, new_spte);
+ else if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte))
+ return RET_PF_RETRY;
/*
* If the page fault was caused by a write but the page is write
@@ -742,8 +739,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu
*vcpu, int write,
}
/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
- if (unlikely(is_mmio_spte(new_spte)))
+ if (unlikely(is_mmio_spte(new_spte))) {
+ trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte);
ret = RET_PF_EMULATE;
+ } else
+ trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
if (!prefault)
@@ -801,7 +801,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32
error_code,
*/
if (is_shadow_present_pte(iter.old_spte) &&
is_large_pte(iter.old_spte)) {
- tdp_mmu_set_spte(vcpu->kvm, &iter, 0);
+ if (!tdp_mmu_set_spte_atomic(vcpu->kvm, &iter, 0))
+ break;
kvm_flush_remote_tlbs_with_address(vcpu->kvm, iter.gfn,
KVM_PAGES_PER_HPAGE(iter.level));
@@ -818,19 +819,24 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32
error_code,
sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level);
child_pt = sp->spt;
- tdp_mmu_link_page(vcpu->kvm, sp, false,
- huge_page_disallowed &&
- req_level >= iter.level);
-
new_spte = make_nonleaf_spte(child_pt,
!shadow_accessed_mask);
- trace_kvm_mmu_get_page(sp, true);
- tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte);
+ if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter,
+ new_spte)) {
+ tdp_mmu_link_page(vcpu->kvm, sp, true,
+ huge_page_disallowed &&
+ req_level >= iter.level);
+
+ trace_kvm_mmu_get_page(sp, true);
+ } else {
+ tdp_mmu_free_sp(sp);
+ break;
+ }
}
}
- if (WARN_ON(iter.level != level)) {
+ if (iter.level != level) {
rcu_read_unlock();
return RET_PF_RETRY;
}
--
2.30.0.284.gd98b1dd5eaa7-goog
