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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - GICv4.1 support

   - 32bit host removal

  PPC:
   - secure (encrypted) using under the Protected Execution Framework
     ultravisor

  s390:
   - allow disabling GISA (hardware interrupt injection) and protected
     VMs/ultravisor support.

  x86:
   - New dirty bitmap flag that sets all bits in the bitmap when dirty
     page logging is enabled; this is faster because it doesn't require
     bulk modification of the page tables.

   - Initial work on making nested SVM event injection more similar to
     VMX, and less buggy.

   - Various cleanups to MMU code (though the big ones and related
     optimizations were delayed to 5.8). Instead of using cr3 in
     function names which occasionally means eptp, KVM too has
     standardized on "pgd".

   - A large refactoring of CPUID features, which now use an array that
     parallels the core x86_features.

   - Some removal of pointer chasing from kvm_x86_ops, which will also
     be switched to static calls as soon as they are available.

   - New Tigerlake CPUID features.

   - More bugfixes, optimizations and cleanups.

  Generic:
   - selftests: cleanups, new MMU notifier stress test, steal-time test

   - CSV output for kvm_stat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
  x86/kvm: fix a missing-prototypes "vmread_error"
  KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
  KVM: VMX: Add a trampoline to fix VMREAD error handling
  KVM: SVM: Annotate svm_x86_ops as __initdata
  KVM: VMX: Annotate vmx_x86_ops as __initdata
  KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
  KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
  KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
  KVM: VMX: Configure runtime hooks using vmx_x86_ops
  KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
  KVM: x86: Move init-only kvm_x86_ops to separate struct
  KVM: Pass kvm_init()'s opaque param to additional arch funcs
  s390/gmap: return proper error code on ksm unsharing
  KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
  KVM: Fix out of range accesses to memslots
  KVM: X86: Micro-optimize IPI fastpath delay
  KVM: X86: Delay read msr data iff writes ICR MSR
  KVM: PPC: Book3S HV: Add a capability for enabling secure guests
  KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
  KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
  ...

3 files changed, 88 insertions, 33 deletions

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 63457908c9c4..69f4164d6477 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -231,6 +231,9 @@ struct vgic_dist {
 	/* distributor enabled */
 	bool			enabled;
 
+	/* Wants SGIs without active state */
+	bool			nassgireq;
+
 	struct vgic_irq		*spis;
 
 	struct vgic_io_device	dist_iodev;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bcb9b2ac0791..6d58beb65454 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -360,6 +360,10 @@ static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *mem
 	return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap);
 }
 
+#ifndef KVM_DIRTY_LOG_MANUAL_CAPS
+#define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE
+#endif
+
 struct kvm_s390_adapter_int {
 	u64 ind_addr;
 	u64 summary_addr;
@@ -431,11 +435,11 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
  */
 struct kvm_memslots {
 	u64 generation;
-	struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM];
 	/* The mapping table from slot id to the index in memslots[]. */
 	short id_to_index[KVM_MEM_SLOTS_NUM];
 	atomic_t lru_slot;
 	int used_slots;
+	struct kvm_memory_slot memslots[];
 };
 
 struct kvm {
@@ -493,7 +497,7 @@ struct kvm {
 #endif
 	long tlbs_dirty;
 	struct list_head devices;
-	bool manual_dirty_log_protect;
+	u64 manual_dirty_log_protect;
 	struct dentry *debugfs_dentry;
 	struct kvm_stat_data **debugfs_stat_data;
 	struct srcu_struct srcu;
@@ -527,6 +531,11 @@ struct kvm {
 #define vcpu_err(vcpu, fmt, ...)					\
 	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
+static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm)
+{
+	return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET);
+}
+
 static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
 {
 	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
@@ -572,10 +581,11 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
 	return vcpu->vcpu_idx;
 }
 
-#define kvm_for_each_memslot(memslot, slots)	\
-	for (memslot = &slots->memslots[0];	\
-	      memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
-		memslot++)
+#define kvm_for_each_memslot(memslot, slots)				\
+	for (memslot = &slots->memslots[0];				\
+	     memslot < slots->memslots + slots->used_slots; memslot++)	\
+		if (WARN_ON_ONCE(!memslot->npages)) {			\
+		} else
 
 void kvm_vcpu_destroy(struct kvm_vcpu *vcpu);
 
@@ -635,12 +645,15 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu)
 	return __kvm_memslots(vcpu->kvm, as_id);
 }
 
-static inline struct kvm_memory_slot *
-id_to_memslot(struct kvm_memslots *slots, int id)
+static inline
+struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id)
 {
 	int index = slots->id_to_index[id];
 	struct kvm_memory_slot *slot;
 
+	if (index < 0)
+		return NULL;
+
 	slot = &slots->memslots[index];
 
 	WARN_ON(slot->id != id);
@@ -669,10 +682,7 @@ int kvm_set_memory_region(struct kvm *kvm,
 			  const struct kvm_userspace_memory_region *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
 			    const struct kvm_userspace_memory_region *mem);
-void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
-			   struct kvm_memory_slot *dont);
-int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
-			    unsigned long npages);
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
@@ -680,11 +690,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				enum kvm_mr_change change);
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change);
-bool kvm_largepages_enabled(void);
-void kvm_disable_largepages(void);
 /* flush all memory translations */
 void kvm_arch_flush_shadow_all(struct kvm *kvm);
 /* flush memory translations pointing to 'slot' */
@@ -704,7 +712,6 @@ void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
 
-kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
 kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
 kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 		      bool *writable);
@@ -819,23 +826,20 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 
-int kvm_get_dirty_log(struct kvm *kvm,
-			struct kvm_dirty_log *log, int *is_dirty);
-
-int kvm_get_dirty_log_protect(struct kvm *kvm,
-			      struct kvm_dirty_log *log, bool *flush);
-int kvm_clear_dirty_log_protect(struct kvm *kvm,
-				struct kvm_clear_dirty_log *log, bool *flush);
-
 void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 					struct kvm_memory_slot *slot,
 					gfn_t gfn_offset,
 					unsigned long mask);
-
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-				struct kvm_dirty_log *log);
-int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
-				  struct kvm_clear_dirty_log *log);
+void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot);
+
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
+					struct kvm_memory_slot *memslot);
+#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log);
+int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
+		      int *is_dirty, struct kvm_memory_slot **memslot);
+#endif
 
 int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 			bool line_status);
@@ -882,9 +886,9 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu);
 
 int kvm_arch_hardware_enable(void);
 void kvm_arch_hardware_disable(void);
-int kvm_arch_hardware_setup(void);
+int kvm_arch_hardware_setup(void *opaque);
 void kvm_arch_hardware_unsetup(void);
-int kvm_arch_check_processor_compat(void);
+int kvm_arch_check_processor_compat(void *opaque);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
@@ -1018,6 +1022,8 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
  * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
  * gfn_to_memslot() itself isn't here as an inline because that would
  * bloat other code too much.
+ *
+ * IMPORTANT: Slots are sorted from highest GFN to lowest GFN!
  */
 static inline struct kvm_memory_slot *
 search_memslots(struct kvm_memslots *slots, gfn_t gfn)
@@ -1026,6 +1032,9 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn)
 	int slot = atomic_read(&slots->lru_slot);
 	struct kvm_memory_slot *memslots = slots->memslots;
 
+	if (unlikely(!slots->used_slots))
+		return NULL;
+
 	if (gfn >= memslots[slot].base_gfn &&
 	    gfn < memslots[slot].base_gfn + memslots[slot].npages)
 		return &memslots[slot];
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 4b95f9a31a2f..428c7dde6b4b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -474,12 +474,17 @@ struct kvm_s390_mem_op {
 	__u32 size;		/* amount of bytes */
 	__u32 op;		/* type of operation */
 	__u64 buf;		/* buffer in userspace */
-	__u8 ar;		/* the access register number */
-	__u8 reserved[31];	/* should be set to 0 */
+	union {
+		__u8 ar;	/* the access register number */
+		__u32 sida_offset; /* offset into the sida */
+		__u8 reserved[32]; /* should be set to 0 */
+	};
 };
 /* types for kvm_s390_mem_op->op */
 #define KVM_S390_MEMOP_LOGICAL_READ	0
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
+#define KVM_S390_MEMOP_SIDA_READ	2
+#define KVM_S390_MEMOP_SIDA_WRITE	3
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
@@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
 #define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1478,6 +1485,39 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
+struct kvm_s390_pv_sec_parm {
+	__u64 origin;
+	__u64 length;
+};
+
+struct kvm_s390_pv_unp {
+	__u64 addr;
+	__u64 size;
+	__u64 tweak;
+};
+
+enum pv_cmd_id {
+	KVM_PV_ENABLE,
+	KVM_PV_DISABLE,
+	KVM_PV_SET_SEC_PARMS,
+	KVM_PV_UNPACK,
+	KVM_PV_VERIFY,
+	KVM_PV_PREP_RESET,
+	KVM_PV_UNSHARE_ALL,
+};
+
+struct kvm_pv_cmd {
+	__u32 cmd;	/* Command to be executed */
+	__u16 rc;	/* Ultravisor return code */
+	__u16 rrc;	/* Ultravisor return reason code */
+	__u64 data;	/* Data or address */
+	__u32 flags;    /* flags for future extensions. Must be 0 for now */
+	__u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
+
 #endif /* __LINUX_KVM_H */