Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:

 - Only do MSR filtering for MSRs accessed by rdmsr/wrmsr

 - Documentation improvements

 - Prevent module exit until all VMs are freed

 - PMU Virtualization fixes

 - Fix for kvm_irq_delivery_to_apic_fast() NULL-pointer dereferences

 - Other miscellaneous bugfixes

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (42 commits)
  KVM: x86: fix sending PV IPI
  KVM: x86/mmu: do compare-and-exchange of gPTE via the user address
  KVM: x86: Remove redundant vm_entry_controls_clearbit() call
  KVM: x86: cleanup enter_rmode()
  KVM: x86: SVM: fix tsc scaling when the host doesn't support it
  kvm: x86: SVM: remove unused defines
  KVM: x86: SVM: move tsc ratio definitions to svm.h
  KVM: x86: SVM: fix avic spec based definitions again
  KVM: MIPS: remove reference to trap&emulate virtualization
  KVM: x86: document limitations of MSR filtering
  KVM: x86: Only do MSR filtering when access MSR by rdmsr/wrmsr
  KVM: x86/emulator: Emulate RDPID only if it is enabled in guest
  KVM: x86/pmu: Fix and isolate TSX-specific performance event logic
  KVM: x86: mmu: trace kvm_mmu_set_spte after the new SPTE was set
  KVM: x86/svm: Clear reserved bits written to PerfEvtSeln MSRs
  KVM: x86: Trace all APICv inhibit changes and capture overall status
  KVM: x86: Add wrappers for setting/clearing APICv inhibits
  KVM: x86: Make APICv inhibit reasons an enum and cleanup naming
  KVM: X86: Handle implicit supervisor access with SMAP
  KVM: X86: Rename variable smap to not_smap in permission_fault()
  ...

1 files changed, 26 insertions, 46 deletions

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index e7e7876251b3..d71d177ae6b8 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -14,21 +14,24 @@ static bool __read_mostly tdp_mmu_enabled = true;
 module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
 
 /* Initializes the TDP MMU for the VM, if enabled. */
-bool kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
 {
+	struct workqueue_struct *wq;
+
 	if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled))
-		return false;
+		return 0;
+
+	wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
+	if (!wq)
+		return -ENOMEM;
 
 	/* This should not be changed for the lifetime of the VM. */
 	kvm->arch.tdp_mmu_enabled = true;
-
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
 	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
-	kvm->arch.tdp_mmu_zap_wq =
-		alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
-
-	return true;
+	kvm->arch.tdp_mmu_zap_wq = wq;
+	return 1;
 }
 
 /* Arbitrarily returns true so that this may be used in if statements. */
@@ -906,10 +909,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 }
 
 /*
- * Tears down the mappings for the range of gfns, [start, end), and frees the
- * non-root pages mapping GFNs strictly within that range. Returns true if
- * SPTEs have been cleared and a TLB flush is needed before releasing the
- * MMU lock.
+ * Zap leafs SPTEs for the range of gfns, [start, end). Returns true if SPTEs
+ * have been cleared and a TLB flush is needed before releasing the MMU lock.
  *
  * If can_yield is true, will release the MMU lock and reschedule if the
  * scheduler needs the CPU or there is contention on the MMU lock. If this
@@ -917,42 +918,25 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
  * the caller must ensure it does not supply too large a GFN range, or the
  * operation can cause a soft lockup.
  */
-static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield, bool flush)
+static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
+			      gfn_t start, gfn_t end, bool can_yield, bool flush)
 {
-	bool zap_all = (start == 0 && end >= tdp_mmu_max_gfn_host());
 	struct tdp_iter iter;
 
-	/*
-	 * No need to try to step down in the iterator when zapping all SPTEs,
-	 * zapping the top-level non-leaf SPTEs will recurse on their children.
-	 */
-	int min_level = zap_all ? root->role.level : PG_LEVEL_4K;
-
 	end = min(end, tdp_mmu_max_gfn_host());
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	rcu_read_lock();
 
-	for_each_tdp_pte_min_level(iter, root, min_level, start, end) {
+	for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) {
 		if (can_yield &&
 		    tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) {
 			flush = false;
 			continue;
 		}
 
-		if (!is_shadow_present_pte(iter.old_spte))
-			continue;
-
-		/*
-		 * If this is a non-last-level SPTE that covers a larger range
-		 * than should be zapped, continue, and zap the mappings at a
-		 * lower level, except when zapping all SPTEs.
-		 */
-		if (!zap_all &&
-		    (iter.gfn < start ||
-		     iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) &&
+		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
@@ -960,17 +944,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 		flush = true;
 	}
 
-	/*
-	 * Need to flush before releasing RCU.  TODO: do it only if intermediate
-	 * page tables were zapped; there is no need to flush under RCU protection
-	 * if no 'struct kvm_mmu_page' is freed.
-	 */
-	if (flush)
-		kvm_flush_remote_tlbs_with_address(kvm, start, end - start);
-
 	rcu_read_unlock();
 
-	return false;
+	/*
+	 * Because this flow zaps _only_ leaf SPTEs, the caller doesn't need
+	 * to provide RCU protection as no 'struct kvm_mmu_page' will be freed.
+	 */
+	return flush;
 }
 
 /*
@@ -979,13 +959,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
  * SPTEs have been cleared and a TLB flush is needed before releasing the
  * MMU lock.
  */
-bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
-				 gfn_t end, bool can_yield, bool flush)
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
+			   bool can_yield, bool flush)
 {
 	struct kvm_mmu_page *root;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
-		flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
+		flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush);
 
 	return flush;
 }
@@ -1233,8 +1213,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush)
 {
-	return __kvm_tdp_mmu_zap_gfn_range(kvm, range->slot->as_id, range->start,
-					   range->end, range->may_block, flush);
+	return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
+				     range->end, range->may_block, flush);
 }
 
 typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,