Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 58 insertions, 81 deletions

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 04c1f0957f..36539c1b36 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -495,8 +495,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		 * impact the guest since both the former and current SPTEs
 		 * are nonpresent.
 		 */
-		if (WARN_ON_ONCE(!is_mmio_spte(old_spte) &&
-				 !is_mmio_spte(new_spte) &&
+		if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) &&
+				 !is_mmio_spte(kvm, new_spte) &&
 				 !is_removed_spte(new_spte)))
 			pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
 			       "should not be replaced with another,\n"
@@ -530,6 +530,31 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		kvm_set_pfn_accessed(spte_to_pfn(old_spte));
 }
 
+static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte)
+{
+	u64 *sptep = rcu_dereference(iter->sptep);
+
+	/*
+	 * The caller is responsible for ensuring the old SPTE is not a REMOVED
+	 * SPTE.  KVM should never attempt to zap or manipulate a REMOVED SPTE,
+	 * and pre-checking before inserting a new SPTE is advantageous as it
+	 * avoids unnecessary work.
+	 */
+	WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+
+	/*
+	 * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
+	 * does not hold the mmu_lock.  On failure, i.e. if a different logical
+	 * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
+	 * the current value, so the caller operates on fresh data, e.g. if it
+	 * retries tdp_mmu_set_spte_atomic()
+	 */
+	if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
+		return -EBUSY;
+
+	return 0;
+}
+
 /*
  * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically
  * and handle the associated bookkeeping.  Do not mark the page dirty
@@ -551,27 +576,13 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm,
 					  struct tdp_iter *iter,
 					  u64 new_spte)
 {
-	u64 *sptep = rcu_dereference(iter->sptep);
-
-	/*
-	 * The caller is responsible for ensuring the old SPTE is not a REMOVED
-	 * SPTE.  KVM should never attempt to zap or manipulate a REMOVED SPTE,
-	 * and pre-checking before inserting a new SPTE is advantageous as it
-	 * avoids unnecessary work.
-	 */
-	WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+	int ret;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	/*
-	 * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
-	 * does not hold the mmu_lock.  On failure, i.e. if a different logical
-	 * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
-	 * the current value, so the caller operates on fresh data, e.g. if it
-	 * retries tdp_mmu_set_spte_atomic()
-	 */
-	if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
-		return -EBUSY;
+	ret = __tdp_mmu_set_spte_atomic(iter, new_spte);
+	if (ret)
+		return ret;
 
 	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
 			    new_spte, iter->level, true);
@@ -584,13 +595,17 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 {
 	int ret;
 
+	lockdep_assert_held_read(&kvm->mmu_lock);
+
 	/*
-	 * Freeze the SPTE by setting it to a special,
-	 * non-present value. This will stop other threads from
-	 * immediately installing a present entry in its place
-	 * before the TLBs are flushed.
+	 * Freeze the SPTE by setting it to a special, non-present value. This
+	 * will stop other threads from immediately installing a present entry
+	 * in its place before the TLBs are flushed.
+	 *
+	 * Delay processing of the zapped SPTE until after TLBs are flushed and
+	 * the REMOVED_SPTE is replaced (see below).
 	 */
-	ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE);
+	ret = __tdp_mmu_set_spte_atomic(iter, REMOVED_SPTE);
 	if (ret)
 		return ret;
 
@@ -599,11 +614,19 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	/*
 	 * No other thread can overwrite the removed SPTE as they must either
 	 * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not
-	 * overwrite the special removed SPTE value. No bookkeeping is needed
-	 * here since the SPTE is going from non-present to non-present.  Use
-	 * the raw write helper to avoid an unnecessary check on volatile bits.
+	 * overwrite the special removed SPTE value. Use the raw write helper to
+	 * avoid an unnecessary check on volatile bits.
 	 */
-	__kvm_tdp_mmu_write_spte(iter->sptep, 0);
+	__kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
+
+	/*
+	 * Process the zapped SPTE after flushing TLBs, and after replacing
+	 * REMOVED_SPTE with 0. This minimizes the amount of time vCPUs are
+	 * blocked by the REMOVED_SPTE and reduces contention on the child
+	 * SPTEs.
+	 */
+	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+			    SHADOW_NONPRESENT_VALUE, iter->level, true);
 
 	return 0;
 }
@@ -740,8 +763,8 @@ retry:
 			continue;
 
 		if (!shared)
-			tdp_mmu_iter_set_spte(kvm, &iter, 0);
-		else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+			tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
+		else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE))
 			goto retry;
 	}
 }
@@ -808,8 +831,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
 		return false;
 
-	tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
-			 sp->gfn, sp->role.level + 1);
+	tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte,
+			 SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1);
 
 	return true;
 }
@@ -843,7 +866,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		tdp_mmu_iter_set_spte(kvm, &iter, 0);
+		tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
 
 		/*
 		 * Zappings SPTEs in invalid roots doesn't require a TLB flush,
@@ -1028,7 +1051,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 	}
 
 	/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
-	if (unlikely(is_mmio_spte(new_spte))) {
+	if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) {
 		vcpu->stat.pf_mmio_spte_created++;
 		trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
 				     new_spte);
@@ -1258,52 +1281,6 @@ bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return kvm_tdp_mmu_handle_gfn(kvm, range, test_age_gfn);
 }
 
-static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
-			 struct kvm_gfn_range *range)
-{
-	u64 new_spte;
-
-	/* Huge pages aren't expected to be modified without first being zapped. */
-	WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end);
-
-	if (iter->level != PG_LEVEL_4K ||
-	    !is_shadow_present_pte(iter->old_spte))
-		return false;
-
-	/*
-	 * Note, when changing a read-only SPTE, it's not strictly necessary to
-	 * zero the SPTE before setting the new PFN, but doing so preserves the
-	 * invariant that the PFN of a present * leaf SPTE can never change.
-	 * See handle_changed_spte().
-	 */
-	tdp_mmu_iter_set_spte(kvm, iter, 0);
-
-	if (!pte_write(range->arg.pte)) {
-		new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
-								  pte_pfn(range->arg.pte));
-
-		tdp_mmu_iter_set_spte(kvm, iter, new_spte);
-	}
-
-	return true;
-}
-
-/*
- * Handle the changed_pte MMU notifier for the TDP MMU.
- * data is a pointer to the new pte_t mapping the HVA specified by the MMU
- * notifier.
- * Returns non-zero if a flush is needed before releasing the MMU lock.
- */
-bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	/*
-	 * No need to handle the remote TLB flush under RCU protection, the
-	 * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a
-	 * shadow page. See the WARN on pfn_changed in handle_changed_spte().
-	 */
-	return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn);
-}
-
 /*
  * Remove write access from all SPTEs at or above min_level that map GFNs
  * [start, end). Returns true if an SPTE has been changed and the TLBs need to