Merge remote-tracking branch 'kvm/queue' into HEAD

x86 Xen-for-KVM:

* Allow the Xen runstate information to cross a page boundary

* Allow XEN_RUNSTATE_UPDATE flag behaviour to be configured

* add support for 32-bit guests in SCHEDOP_poll

x86 fixes:

* One-off fixes for various emulation flows (SGX, VMXON, NRIPS=0).

* Reinstate IBPB on emulated VM-Exit that was incorrectly dropped a few
   years back when eliminating unnecessary barriers when switching between
   vmcs01 and vmcs02.

* Clean up the MSR filter docs.

* Clean up vmread_error_trampoline() to make it more obvious that params
  must be passed on the stack, even for x86-64.

* Let userspace set all supported bits in MSR_IA32_FEAT_CTL irrespective
  of the current guest CPUID.

* Fudge around a race with TSC refinement that results in KVM incorrectly
  thinking a guest needs TSC scaling when running on a CPU with a
  constant TSC, but no hardware-enumerated TSC frequency.

* Advertise (on AMD) that the SMM_CTL MSR is not supported

* Remove unnecessary exports

Selftests:

* Fix an inverted check in the access tracking perf test, and restore
  support for asserting that there aren't too many idle pages when
  running on bare metal.

* Fix an ordering issue in the AMX test introduced by recent conversions
  to use kvm_cpu_has(), and harden the code to guard against similar bugs
  in the future.  Anything that tiggers caching of KVM's supported CPUID,
  kvm_cpu_has() in this case, effectively hides opt-in XSAVE features if
  the caching occurs before the test opts in via prctl().

* Fix build errors that occur in certain setups (unsure exactly what is
  unique about the problematic setup) due to glibc overriding
  static_assert() to a variant that requires a custom message.

* Introduce actual atomics for clear/set_bit() in selftests

Documentation:

* Remove deleted ioctls from documentation

* Various fixes

3 files changed, 36 insertions, 65 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1dc501ab874d..f16c4689322b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -50,8 +50,8 @@
 #endif
 
 /*
- * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
- * in kvm, other bits are visible for userspace which are defined in
+ * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally
+ * used in kvm, other bits are visible for userspace which are defined in
  * include/linux/kvm_h.
  */
 #define KVM_MEMSLOT_INVALID	(1UL << 16)
@@ -1262,18 +1262,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
  * kvm_gpc_init - initialize gfn_to_pfn_cache.
  *
  * @gpc:	   struct gfn_to_pfn_cache object.
- *
- * This sets up a gfn_to_pfn_cache by initializing locks.  Note, the cache must
- * be zero-allocated (or zeroed by the caller before init).
- */
-void kvm_gpc_init(struct gfn_to_pfn_cache *gpc);
-
-/**
- * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
- *                    physical address.
- *
  * @kvm:	   pointer to kvm instance.
- * @gpc:	   struct gfn_to_pfn_cache object.
  * @vcpu:	   vCPU to be used for marking pages dirty and to be woken on
  *		   invalidation.
  * @usage:	   indicates if the resulting host physical PFN is used while
@@ -1282,28 +1271,36 @@ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc);
  *		   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).
+ *
+ * This sets up a gfn_to_pfn_cache by initializing locks and assigning the
+ * immutable attributes.  Note, the cache must be zero-allocated (or zeroed by
+ * the caller before init).
+ */
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm,
+		  struct kvm_vcpu *vcpu, enum pfn_cache_usage usage);
+
+/**
+ * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
+ *                    physical address.
+ *
+ * @gpc:	   struct gfn_to_pfn_cache object.
  * @gpa:	   guest physical address to map.
  * @len:	   sanity check; the range being access must fit a single page.
  *
  * @return:	   0 for success.
  *		   -EINVAL for a mapping which would cross a page boundary.
- *                 -EFAULT for an untranslatable guest physical address.
+ *		   -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.  Callers are required to use
- * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before
- * accessing the target page.
+ * This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for
+ * invalidations to be processed.  Callers are required to use kvm_gpc_check()
+ * to ensure that the cache is valid before accessing the target page.
  */
-int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-		     struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
-		     gpa_t gpa, unsigned long len);
+int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len);
 
 /**
- * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache.
+ * kvm_gpc_check - check validity of a gfn_to_pfn_cache.
  *
- * @kvm:	   pointer to kvm instance.
  * @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.
  *
  * @return:	   %true if the cache is still valid and the address matches.
@@ -1316,52 +1313,35 @@ int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
  * Callers in IN_GUEST_MODE may do so without locking, although they should
  * still hold a read lock on kvm->scru for the memslot checks.
  */
-bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-				gpa_t gpa, unsigned long len);
+bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len);
 
 /**
- * kvm_gfn_to_pfn_cache_refresh - update a previously initialized cache.
+ * kvm_gpc_refresh - update a previously initialized cache.
  *
- * @kvm:	   pointer to kvm instance.
  * @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.
  *
  * @return:	   0 for success.
  *		   -EINVAL for a mapping which would cross a page boundary.
- *                 -EFAULT for an untranslatable guest physical address.
+ *		   -EFAULT for an untranslatable guest physical address.
  *
  * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful
- * returm from this function does not mean the page can be immediately
+ * return from this function does not mean the page can be immediately
  * accessed because it may have raced with an invalidation. Callers must
  * still lock and check the cache status, as this function does not return
  * 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);
-
-/**
- * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache.
- *
- * @kvm:	   pointer to kvm instance.
- * @gpc:	   struct gfn_to_pfn_cache object.
- *
- * 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);
+int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len);
 
 /**
  * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache.
  *
- * @kvm:	   pointer to kvm instance.
  * @gpc:	   struct gfn_to_pfn_cache object.
  *
- * This removes a cache from the @kvm's list to be processed on MMU notifier
+ * This removes a cache from the VM's list to be processed on MMU notifier
  * invocation.
  */
-void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
+void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc);
 
 void kvm_sigset_activate(struct kvm_vcpu *vcpu);
 void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 3ca3db020e0e..76de36e56cdf 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -67,6 +67,7 @@ struct gfn_to_pfn_cache {
 	gpa_t gpa;
 	unsigned long uhva;
 	struct kvm_memory_slot *memslot;
+	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
 	struct list_head list;
 	rwlock_t lock;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 820efdf9fef8..20522d4ba1e0 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -86,14 +86,6 @@ struct kvm_debug_guest {
 /* *** End of deprecated interfaces *** */
 
 
-/* for KVM_CREATE_MEMORY_REGION */
-struct kvm_memory_region {
-	__u32 slot;
-	__u32 flags;
-	__u64 guest_phys_addr;
-	__u64 memory_size; /* bytes */
-};
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -104,9 +96,9 @@ struct kvm_userspace_memory_region {
 };
 
 /*
- * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
- * other bits are reserved for kvm internal use which are defined in
- * include/linux/kvm_host.h.
+ * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
+ * userspace, other bits are reserved for kvm internal use which are defined
+ * in include/linux/kvm_host.h.
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
@@ -1272,6 +1264,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1443,17 +1436,11 @@ struct kvm_vfio_spapr_tce {
 };
 
 /*
- * ioctls for VM fds
- */
-#define KVM_SET_MEMORY_REGION     _IOW(KVMIO,  0x40, struct kvm_memory_region)
-/*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.
  */
 #define KVM_CREATE_VCPU           _IO(KVMIO,   0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO,  0x42, struct kvm_dirty_log)
-/* KVM_SET_MEMORY_ALIAS is obsolete: */
-#define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO,  0x43, struct kvm_memory_alias)
 #define KVM_SET_NR_MMU_PAGES      _IO(KVMIO,   0x44)
 #define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)
 #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
@@ -1777,6 +1764,7 @@ struct kvm_xen_hvm_attr {
 	union {
 		__u8 long_mode;
 		__u8 vector;
+		__u8 runstate_update_flag;
 		struct {
 			__u64 gfn;
 		} shared_info;
@@ -1817,6 +1805,8 @@ struct kvm_xen_hvm_attr {
 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
 #define KVM_XEN_ATTR_TYPE_EVTCHN		0x3
 #define KVM_XEN_ATTR_TYPE_XEN_VERSION		0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG	0x5
 
 /* Per-vCPU Xen attributes */
 #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)