Convert kvm_zap_gfn_range() from holding mmu_lock for write to holding for
read in TDP MMU and allow zapping of non-leaf SPTEs of level <= 1G.
TLB flushes are executed/requested within tdp_mmu_zap_spte_atomic() guarded
by RCU lock.
GFN zap can be super slow if mmu_lock is held for write when there are
contentions. In worst cases, huge cpu cycles are spent on yielding GFN by
GFN, i.e. the loop of "check and flush tlb -> drop rcu lock ->
drop mmu_lock -> cpu_relax() -> take mmu_lock -> take rcu lock" are entered
for every GFN.
Contentions can either from concurrent zaps holding mmu_lock for write or
from tdp_mmu_map() holding mmu_lock for read.
After converting to hold mmu_lock for read, there will be less contentions
detected and retaking mmu_lock for read is also faster. There's no need to
flush TLB before dropping mmu_lock when there're contentions as SPTEs have
been zapped atomically and TLBs are flushed/flush requested immediately
within RCU lock.
In order to reduce TLB flush count, non-leaf SPTEs not greater than 1G
level are allowed to be zapped if their ranges are fully covered in the
gfn zap range.
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
---
arch/x86/kvm/mmu/mmu.c | 14 +++++++----
arch/x86/kvm/mmu/tdp_mmu.c | 50 ++++++++++++++++++++++++++++++++++++++
arch/x86/kvm/mmu/tdp_mmu.h | 1 +
3 files changed, 60 insertions(+), 5 deletions(-)
@@ -6310,15 +6310,19 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
+ if (flush)
+ kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
+
if (tdp_mmu_enabled) {
+ write_unlock(&kvm->mmu_lock);
+ read_lock(&kvm->mmu_lock);
+
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
- flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
- gfn_end, true, flush);
+ kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start, gfn_end);
+ read_unlock(&kvm->mmu_lock);
+ write_lock(&kvm->mmu_lock);
}
- if (flush)
- kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
-
kvm_mmu_invalidate_end(kvm, 0, -1ul);
write_unlock(&kvm->mmu_lock);
@@ -888,6 +888,56 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
return flush;
}
+static void zap_gfn_range_atomic(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end)
+{
+ struct tdp_iter iter;
+
+ end = min(end, tdp_mmu_max_gfn_exclusive());
+
+ lockdep_assert_held_read(&kvm->mmu_lock);
+
+ rcu_read_lock();
+
+ for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) {
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte))
+ continue;
+
+ /*
+ * As also documented in tdp_mmu_zap_root(),
+ * KVM must be able to zap a 1gb shadow page without
+ * inducing a stall to allow in-place replacement with a 1gb hugepage.
+ */
+ if (iter.gfn < start ||
+ iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end ||
+ iter.level > KVM_MAX_HUGEPAGE_LEVEL)
+ continue;
+
+ /* Note, a successful atomic zap also does a remote TLB flush. */
+ if (tdp_mmu_zap_spte_atomic(kvm, &iter))
+ goto retry;
+ }
+
+ rcu_read_unlock();
+}
+
+/*
+ * Zap all SPTEs for the range of gfns, [start, end), for all roots with
+ * shared mmu lock in atomic way.
+ * TLB flushs are performed within the rcu lock.
+ */
+void kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, gfn_t end)
+{
+ struct kvm_mmu_page *root;
+
+ for_each_valid_tdp_mmu_root_yield_safe(kvm, root, as_id, true)
+ zap_gfn_range_atomic(kvm, root, start, end);
+}
+
void kvm_tdp_mmu_zap_all(struct kvm *kvm)
{
struct kvm_mmu_page *root;
@@ -22,6 +22,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
gfn_t end, bool can_yield, bool flush);
+void kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, gfn_t end);
bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
void kvm_tdp_mmu_zap_all(struct kvm *kvm);
void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);