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()
  ...

2 files changed, 48 insertions, 23 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9536ffa0473b..3f9b22c4983a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -148,6 +148,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQUEST_MASK           GENMASK(7,0)
 #define KVM_REQUEST_NO_WAKEUP      BIT(8)
 #define KVM_REQUEST_WAIT           BIT(9)
+#define KVM_REQUEST_NO_ACTION      BIT(10)
 /*
  * Architecture-independent vcpu->requests bit members
  * Bits 4-7 are reserved for more arch-independent bits.
@@ -156,9 +157,18 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_VM_DEAD           (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_UNBLOCK           2
 #define KVM_REQ_UNHALT            3
-#define KVM_REQ_GPC_INVALIDATE    (5 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQUEST_ARCH_BASE     8
 
+/*
+ * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to
+ * OUTSIDE_GUEST_MODE.  KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick"
+ * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing
+ * on.  A kick only guarantees that the vCPU is on its way out, e.g. a previous
+ * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no
+ * guarantee the vCPU received an IPI and has actually exited guest mode.
+ */
+#define KVM_REQ_OUTSIDE_GUEST_MODE	(KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+
 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
 	BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \
 	(unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \
@@ -1221,27 +1231,27 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
  * @gpc:	   struct gfn_to_pfn_cache object.
  * @vcpu:	   vCPU to be used for marking pages dirty and to be woken on
  *		   invalidation.
- * @guest_uses_pa: indicates that the resulting host physical PFN is used while
- *		   @vcpu is IN_GUEST_MODE so invalidations should wake it.
- * @kernel_map:    requests a kernel virtual mapping (kmap / memremap).
+ * @usage:	   indicates if the resulting host physical PFN is used while
+ *		   the @vcpu is IN_GUEST_MODE (in which case invalidation of 
+ *		   the cache from MMU notifiers---but not for KVM memslot
+ *		   changes!---will also force @vcpu to exit the guest and
+ *		   refresh the cache); and/or if the PFN used directly
+ *		   by KVM (and thus needs a kernel virtual mapping).
  * @gpa:	   guest physical address to map.
  * @len:	   sanity check; the range being access must fit a single page.
- * @dirty:         mark the cache dirty immediately.
  *
  * @return:	   0 for success.
  *		   -EINVAL for a mapping which would cross a page boundary.
  *                 -EFAULT for an untranslatable guest physical address.
  *
  * This primes a gfn_to_pfn_cache and links it into the @kvm's list for
- * invalidations to be processed. Invalidation callbacks to @vcpu using
- * %KVM_REQ_GPC_INVALIDATE will occur only for MMU notifiers, not for KVM
- * memslot changes. Callers are required to use kvm_gfn_to_pfn_cache_check()
- * to ensure that the cache is valid before accessing the target page.
+ * invalidations to be processed.  Callers are required to use
+ * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before
+ * accessing the target page.
  */
 int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-			      struct kvm_vcpu *vcpu, bool guest_uses_pa,
-			      bool kernel_map, gpa_t gpa, unsigned long len,
-			      bool dirty);
+			      struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
+			      gpa_t gpa, unsigned long len);
 
 /**
  * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache.
@@ -1250,7 +1260,6 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
  * @gpc:	   struct gfn_to_pfn_cache object.
  * @gpa:	   current guest physical address to map.
  * @len:	   sanity check; the range being access must fit a single page.
- * @dirty:         mark the cache dirty immediately.
  *
  * @return:	   %true if the cache is still valid and the address matches.
  *		   %false if the cache is not valid.
@@ -1272,7 +1281,6 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
  * @gpc:	   struct gfn_to_pfn_cache object.
  * @gpa:	   updated guest physical address to map.
  * @len:	   sanity check; the range being access must fit a single page.
- * @dirty:         mark the cache dirty immediately.
  *
  * @return:	   0 for success.
  *		   -EINVAL for a mapping which would cross a page boundary.
@@ -1285,7 +1293,7 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
  * with the lock still held to permit access.
  */
 int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-				 gpa_t gpa, unsigned long len, bool dirty);
+				 gpa_t gpa, unsigned long len);
 
 /**
  * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache.
@@ -1293,10 +1301,9 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
  * @kvm:	   pointer to kvm instance.
  * @gpc:	   struct gfn_to_pfn_cache object.
  *
- * This unmaps the referenced page and marks it dirty, if appropriate. The
- * cache is left in the invalid state but at least the mapping from GPA to
- * userspace HVA will remain cached and can be reused on a subsequent
- * refresh.
+ * This unmaps the referenced page. The cache is left in the invalid state
+ * but at least the mapping from GPA to userspace HVA will remain cached
+ * and can be reused on a subsequent refresh.
  */
 void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
 
@@ -1984,7 +1991,7 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
-static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
+static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu)
 {
 	/*
 	 * Ensure the rest of the request is published to kvm_check_request's
@@ -1994,6 +2001,19 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 	set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
 }
 
+static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Request that don't require vCPU action should never be logged in
+	 * vcpu->requests.  The vCPU won't clear the request, so it will stay
+	 * logged indefinitely and prevent the vCPU from entering the guest.
+	 */
+	BUILD_BUG_ON(!__builtin_constant_p(req) ||
+		     (req & KVM_REQUEST_NO_ACTION));
+
+	__kvm_make_request(req, vcpu);
+}
+
 static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
 {
 	return READ_ONCE(vcpu->requests);
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index dceac12c1ce5..ac1ebb37a0ff 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -18,6 +18,7 @@ struct kvm_memslots;
 
 enum kvm_mr_change;
 
+#include <linux/bits.h>
 #include <linux/types.h>
 #include <linux/spinlock_types.h>
 
@@ -46,6 +47,12 @@ typedef u64            hfn_t;
 
 typedef hfn_t kvm_pfn_t;
 
+enum pfn_cache_usage {
+	KVM_GUEST_USES_PFN = BIT(0),
+	KVM_HOST_USES_PFN  = BIT(1),
+	KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN,
+};
+
 struct gfn_to_hva_cache {
 	u64 generation;
 	gpa_t gpa;
@@ -64,11 +71,9 @@ struct gfn_to_pfn_cache {
 	rwlock_t lock;
 	void *khva;
 	kvm_pfn_t pfn;
+	enum pfn_cache_usage usage;
 	bool active;
 	bool valid;
-	bool dirty;
-	bool kernel_map;
-	bool guest_uses_pa;
 };
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE