Currently, when breaking up the stage-2 table entries, KVM
would flush the entire VM's context using 'vmalls12e1is'
TLBI operation. One of the problematic situation is collapsing
table entries into a hugepage, specifically if the VM is
faulting on many hugepages (say after dirty-logging). This
creates a performance penality for the guest whose pages have
already been faulted earlier as they would have to refill their
TLBs again.
Hence, if the system supports it, use __kvm_tlb_flush_range_vmid_ipa()
to flush only the range of pages governed by the table entry,
while leaving other TLB entries alone. An upcoming patch also
takes advantage of this when breaking up table entries during
the unmap operation.
Signed-off-by: Raghavendra Rao Ananta <rananta@xxxxxxxxxx>
---
arch/arm64/kvm/hyp/pgtable.c | 23 ++++++++++++++++++++---
1 file changed, 20 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index b11cf2c618a6c..0858d1fa85d6b 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -686,6 +686,20 @@ static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_
return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old;
}
+static void kvm_pgtable_stage2_flush_range(struct kvm_s2_mmu *mmu, u64 start, u64 end,
+ u32 level, u32 tlb_level)
+{
+ if (system_supports_tlb_range())
+ kvm_call_hyp(__kvm_tlb_flush_range_vmid_ipa, mmu, start, end, level, tlb_level);
+ else
+ /*
+ * Invalidate the whole stage-2, as we may have numerous leaf
+ * entries below us which would otherwise need invalidating
+ * individually.
+ */
+ kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+}
+
/**
* stage2_try_break_pte() - Invalidates a pte according to the
* 'break-before-make' requirements of the
@@ -721,10 +735,13 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
* Perform the appropriate TLB invalidation based on the evicted pte
* value (if any).
*/
- if (kvm_pte_table(ctx->old, ctx->level))
- kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
- else if (kvm_pte_valid(ctx->old))
+ if (kvm_pte_table(ctx->old, ctx->level)) {
+ u64 end = ctx->addr + kvm_granule_size(ctx->level);
+
+ kvm_pgtable_stage2_flush_range(mmu, ctx->addr, end, ctx->level, 0);
+ } else if (kvm_pte_valid(ctx->old)) {
kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+ }
if (stage2_pte_is_counted(ctx->old))
mm_ops->put_page(ctx->ptep);
--
2.39.1.519.gcb327c4b5f-goog
