When using initially-all-set, large pages are not write-protected when
dirty logging is enabled on the memslot. Instead they are
write-protected once userspace invoked CLEAR_DIRTY_LOG for the first
time, and only for the specific sub-region of the memslot that userspace
whishes to clear.
Enhance CLEAR_DIRTY_LOG to also try to split large pages prior to
write-protecting to avoid causing write-protection faults on vCPU
threads. This also allows userspace to smear the cost of large page
splitting across multiple ioctls rather than splitting the entire
memslot when not using initially-all-set.
Signed-off-by: David Matlack <dmatlack@xxxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 4 ++++
arch/x86/kvm/mmu/mmu.c | 30 ++++++++++++++++++++++--------
2 files changed, 26 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 432a4df817ec..6b5bf99f57af 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1591,6 +1591,10 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
const struct kvm_memory_slot *memslot,
int start_level);
+void kvm_mmu_try_split_large_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ u64 start, u64 end,
+ int target_level);
void kvm_mmu_slot_try_split_large_pages(struct kvm *kvm,
const struct kvm_memory_slot *memslot,
int target_level);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 6768ef9c0891..4e78ef2dd352 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1448,6 +1448,12 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
gfn_t start = slot->base_gfn + gfn_offset + __ffs(mask);
gfn_t end = slot->base_gfn + gfn_offset + __fls(mask);
+ /*
+ * Try to proactively split any large pages down to 4KB so that
+ * vCPUs don't have to take write-protection faults.
+ */
+ kvm_mmu_try_split_large_pages(kvm, slot, start, end, PG_LEVEL_4K);
+
kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M);
/* Cross two large pages? */
@@ -5880,21 +5886,17 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
}
-void kvm_mmu_slot_try_split_large_pages(struct kvm *kvm,
- const struct kvm_memory_slot *memslot,
- int target_level)
+void kvm_mmu_try_split_large_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ u64 start, u64 end,
+ int target_level)
{
- u64 start, end;
-
if (!is_tdp_mmu_enabled(kvm))
return;
if (mmu_topup_split_caches(kvm))
return;
- start = memslot->base_gfn;
- end = start + memslot->npages;
-
read_lock(&kvm->mmu_lock);
kvm_tdp_mmu_try_split_large_pages(kvm, memslot, start, end, target_level);
read_unlock(&kvm->mmu_lock);
@@ -5902,6 +5904,18 @@ void kvm_mmu_slot_try_split_large_pages(struct kvm *kvm,
mmu_free_split_caches(kvm);
}
+void kvm_mmu_slot_try_split_large_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ int target_level)
+{
+ u64 start, end;
+
+ start = memslot->base_gfn;
+ end = start + memslot->npages;
+
+ kvm_mmu_try_split_large_pages(kvm, memslot, start, end, target_level);
+}
+
static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
struct kvm_rmap_head *rmap_head,
const struct kvm_memory_slot *slot)
--
2.34.0.rc2.393.gf8c9666880-goog
