KVM: x86/mmu: Atomically clear SPTE dirty state in the clear-dirty-log flow

Optimize the clearing of dirty state in TDP MMU SPTEs by doing an
atomic-AND (on SPTEs that have volatile bits) instead of the full XCHG
that currently ends up being invoked (see kvm_tdp_mmu_write_spte()).
Clearing _only_ the bit in question will allow KVM to skip the many
irrelevant checks in __handle_changed_spte() by avoiding any collateral
damage due to the XCHG writing all SPTE bits, e.g. the XCHG could race
with fast_page_fault() setting the W-bit and the CPU setting the D-bit,
and thus incorrectly drop the CPU's D-bit update.

Link: https://lore.kernel.org/all/Y9hXmz%2FnDOr1hQal@google.com
Signed-off-by: Vipin Sharma <vipinsh@google.com>
Reviewed-by: David Matlack <dmatlack@google.com>
[sean: split the switch to atomic-AND to a separate patch]
Link: https://lore.kernel.org/r/20230321220021.2119033-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index c11c5d0..fae5595 100644 (file)
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -58,6 +58,20 @@ static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
        return old_spte;
 }
 
+static inline u64 tdp_mmu_clear_spte_bits(tdp_ptep_t sptep, u64 old_spte,
+                                         u64 mask, int level)
+{
+       atomic64_t *sptep_atomic;
+
+       if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level)) {
+               sptep_atomic = (atomic64_t *)rcu_dereference(sptep);
+               return (u64)atomic64_fetch_and(~mask, sptep_atomic);
+       }
+
+       __kvm_tdp_mmu_write_spte(sptep, old_spte & ~mask);
+       return old_spte;
+}
+
 /*
  * A TDP iterator performs a pre-order walk over a TDP paging structure.
  */

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index b32c9ba..a70cc1d 100644 (file)
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -770,13 +770,6 @@ static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm,
        _tdp_mmu_set_spte(kvm, iter, new_spte, false, true);
 }
 
-static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
-                                                struct tdp_iter *iter,
-                                                u64 new_spte)
-{
-       _tdp_mmu_set_spte(kvm, iter, new_spte, true, false);
-}
-
 #define tdp_root_for_each_pte(_iter, _root, _start, _end) \
        for_each_tdp_pte(_iter, _root, _start, _end)
 
@@ -1692,7 +1685,14 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
                if (!(iter.old_spte & dbit))
                        continue;
 
-               tdp_mmu_set_spte_no_dirty_log(kvm, &iter, iter.old_spte & ~dbit);
+               iter.old_spte = tdp_mmu_clear_spte_bits(iter.sptep,
+                                                       iter.old_spte, dbit,
+                                                       iter.level);
+
+               __handle_changed_spte(kvm, iter.as_id, iter.gfn, iter.old_spte,
+                                     iter.old_spte & ~dbit, iter.level, false);
+               handle_changed_spte_acc_track(iter.old_spte, iter.old_spte & ~dbit,
+                                             iter.level);
        }
 
        rcu_read_unlock();