When KVM needs to coalesce the normal page mappings into a block mapping,
we currently invalidate the old table entry first followed by invalidation
of TLB, then unmap the page mappings, and install the block entry at last.
It will cost a long time to unmap the numerous page mappings, which means
there will be a long period when the table entry can be found invalid.
If other vCPUs access any guest page within the block range and find the
table entry invalid, they will all exit from guest with a translation fault
which is not necessary. And KVM will make efforts to handle these faults,
especially when performing CMOs by block range.
So let's quickly install the block entry at first to ensure uninterrupted
memory access of the other vCPUs, and then unmap the page mappings after
installation. This will reduce most of the time when the table entry is
invalid, and avoid most of the unnecessary translation faults.
Signed-off-by: Yanan Wang <wangyanan55@xxxxxxxxxx>
---
arch/arm64/kvm/hyp/pgtable.c | 26 ++++++++++++--------------
1 file changed, 12 insertions(+), 14 deletions(-)
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 78a560446f80..308c36b9cd21 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -434,6 +434,7 @@ struct stage2_map_data {
kvm_pte_t attr;
kvm_pte_t *anchor;
+ kvm_pte_t *follow;
struct kvm_s2_mmu *mmu;
struct kvm_mmu_memory_cache *memcache;
@@ -553,15 +554,14 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
if (!kvm_block_mapping_supported(addr, end, data->phys, level))
return 0;
- kvm_set_invalid_pte(ptep);
-
/*
- * Invalidate the whole stage-2, as we may have numerous leaf
- * entries below us which would otherwise need invalidating
- * individually.
+ * If we need to coalesce existing table entries into a block here,
+ * then install the block entry first and the sub-level page mappings
+ * will be unmapped later.
*/
- kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu);
data->anchor = ptep;
+ data->follow = kvm_pte_follow(*ptep);
+ stage2_coalesce_tables_into_block(addr, level, ptep, data);
return 0;
}
@@ -614,20 +614,18 @@ static int stage2_map_walk_table_post(u64 addr, u64 end, u32 level,
kvm_pte_t *ptep,
struct stage2_map_data *data)
{
- int ret = 0;
-
if (!data->anchor)
return 0;
- free_page((unsigned long)kvm_pte_follow(*ptep));
- put_page(virt_to_page(ptep));
-
- if (data->anchor == ptep) {
+ if (data->anchor != ptep) {
+ free_page((unsigned long)kvm_pte_follow(*ptep));
+ put_page(virt_to_page(ptep));
+ } else {
+ free_page((unsigned long)data->follow);
data->anchor = NULL;
- ret = stage2_map_walk_leaf(addr, end, level, ptep, data);
}
- return ret;
+ return 0;
}
/*
--
2.23.0
