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

Pull kvm updates from Paolo Bonzini:
 "Quite a large pull request due to a selftest API overhaul and some
  patches that had come in too late for 5.19.

  ARM:

   - Unwinder implementations for both nVHE modes (classic and
     protected), complete with an overflow stack

   - Rework of the sysreg access from userspace, with a complete rewrite
     of the vgic-v3 view to allign with the rest of the infrastructure

   - Disagregation of the vcpu flags in separate sets to better track
     their use model.

   - A fix for the GICv2-on-v3 selftest

   - A small set of cosmetic fixes

  RISC-V:

   - Track ISA extensions used by Guest using bitmap

   - Added system instruction emulation framework

   - Added CSR emulation framework

   - Added gfp_custom flag in struct kvm_mmu_memory_cache

   - Added G-stage ioremap() and iounmap() functions

   - Added support for Svpbmt inside Guest

  s390:

   - add an interface to provide a hypervisor dump for secure guests

   - improve selftests to use TAP interface

   - enable interpretive execution of zPCI instructions (for PCI
     passthrough)

   - First part of deferred teardown

   - CPU Topology

   - PV attestation

   - Minor fixes

  x86:

   - Permit guests to ignore single-bit ECC errors

   - Intel IPI virtualization

   - Allow getting/setting pending triple fault with
     KVM_GET/SET_VCPU_EVENTS

   - PEBS virtualization

   - Simplify PMU emulation by just using PERF_TYPE_RAW events

   - More accurate event reinjection on SVM (avoid retrying
     instructions)

   - Allow getting/setting the state of the speaker port data bit

   - Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
     are inconsistent

   - "Notify" VM exit (detect microarchitectural hangs) for Intel

   - Use try_cmpxchg64 instead of cmpxchg64

   - Ignore benign host accesses to PMU MSRs when PMU is disabled

   - Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

   - Allow NX huge page mitigation to be disabled on a per-vm basis

   - Port eager page splitting to shadow MMU as well

   - Enable CMCI capability by default and handle injected UCNA errors

   - Expose pid of vcpu threads in debugfs

   - x2AVIC support for AMD

   - cleanup PIO emulation

   - Fixes for LLDT/LTR emulation

   - Don't require refcounted "struct page" to create huge SPTEs

   - Miscellaneous cleanups:
      - MCE MSR emulation
      - Use separate namespaces for guest PTEs and shadow PTEs bitmasks
      - PIO emulation
      - Reorganize rmap API, mostly around rmap destruction
      - Do not workaround very old KVM bugs for L0 that runs with nesting enabled
      - new selftests API for CPUID

  Generic:

   - Fix races in gfn->pfn cache refresh; do not pin pages tracked by
     the cache

   - new selftests API using struct kvm_vcpu instead of a (vm, id)
     tuple"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
  selftests: kvm: set rax before vmcall
  selftests: KVM: Add exponent check for boolean stats
  selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
  selftests: KVM: Check stat name before other fields
  KVM: x86/mmu: remove unused variable
  RISC-V: KVM: Add support for Svpbmt inside Guest/VM
  RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
  RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
  KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
  RISC-V: KVM: Add extensible CSR emulation framework
  RISC-V: KVM: Add extensible system instruction emulation framework
  RISC-V: KVM: Factor-out instruction emulation into separate sources
  RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
  RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
  RISC-V: KVM: Fix variable spelling mistake
  RISC-V: KVM: Improve ISA extension by using a bitmap
  KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
  KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
  KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
  KVM: x86: Do not block APIC write for non ICR registers
  ...

7 files changed, 142 insertions, 19 deletions

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 2d8f2e90edc2..4df9e73a8bb5 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -364,7 +364,7 @@ struct vgic_cpu {
 extern struct static_key_false vgic_v2_cpuif_trap;
 extern struct static_key_false vgic_v3_cpuif_trap;
 
-int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
+int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr);
 void kvm_vgic_early_init(struct kvm *kvm);
 int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
 int kvm_vgic_create(struct kvm *kvm, u32 type);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 90a45ef7203b..1c480b1821e1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -907,11 +907,6 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 	return NULL;
 }
 
-static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
-{
-	return vcpu->vcpu_idx;
-}
-
 void kvm_destroy_vcpus(struct kvm *kvm);
 
 void vcpu_load(struct kvm_vcpu *vcpu);
@@ -1139,7 +1134,6 @@ unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
 				      bool *writable);
 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(struct kvm *kvm, gfn_t gfn);
 kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
@@ -1231,7 +1225,6 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
 kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
 kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
@@ -1358,6 +1351,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
+int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min);
 int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc);
 void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
@@ -1436,6 +1430,8 @@ int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state);
 
 #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
 void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry);
+#else
+static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {}
 #endif
 
 int kvm_arch_hardware_enable(void);
@@ -1572,8 +1568,8 @@ void kvm_arch_sync_events(struct kvm *kvm);
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 
-bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
-bool kvm_is_zone_device_pfn(kvm_pfn_t pfn);
+struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn);
+bool kvm_is_zone_device_page(struct page *page);
 
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
@@ -1719,12 +1715,6 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn)
 	return (hpa_t)pfn << PAGE_SHIFT;
 }
 
-static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu,
-						gpa_t gpa)
-{
-	return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa));
-}
-
 static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
 {
 	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index ac1ebb37a0ff..3ca3db020e0e 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -19,6 +19,7 @@ struct kvm_memslots;
 enum kvm_mr_change;
 
 #include <linux/bits.h>
+#include <linux/mutex.h>
 #include <linux/types.h>
 #include <linux/spinlock_types.h>
 
@@ -69,6 +70,7 @@ struct gfn_to_pfn_cache {
 	struct kvm_vcpu *vcpu;
 	struct list_head list;
 	rwlock_t lock;
+	struct mutex refresh_lock;
 	void *khva;
 	kvm_pfn_t pfn;
 	enum pfn_cache_usage usage;
@@ -83,12 +85,17 @@ struct gfn_to_pfn_cache {
  * MMU flows is problematic, as is triggering reclaim, I/O, etc... while
  * holding MMU locks.  Note, these caches act more like prefetch buffers than
  * classical caches, i.e. objects are not returned to the cache on being freed.
+ *
+ * The @capacity field and @objects array are lazily initialized when the cache
+ * is topped up (__kvm_mmu_topup_memory_cache()).
  */
 struct kvm_mmu_memory_cache {
 	int nobjs;
 	gfp_t gfp_zero;
+	gfp_t gfp_custom;
 	struct kmem_cache *kmem_cache;
-	void *objects[KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE];
+	int capacity;
+	void **objects;
 };
 #endif
 
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 00ed419dd464..f054d0360a75 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -24,7 +24,8 @@ struct user_struct {
 	kuid_t uid;
 
 #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
-    defined(CONFIG_NET) || defined(CONFIG_IO_URING)
+	defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
+	defined(CONFIG_VFIO_PCI_ZDEV_KVM)
 	atomic_long_t locked_vm;
 #endif
 #ifdef CONFIG_WATCH_QUEUE
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 23c176d4b073..d5d9e17f0156 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -206,15 +206,25 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev)
 }
 #endif
 
-#ifdef CONFIG_S390
+#ifdef CONFIG_VFIO_PCI_ZDEV_KVM
 extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 				       struct vfio_info_cap *caps);
+int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev);
+void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev);
 #else
 static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 					      struct vfio_info_cap *caps)
 {
 	return -ENODEV;
 }
+
+static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
+{
+	return 0;
+}
+
+static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
+{}
 #endif
 
 /* Will be exported for vfio pci drivers usage */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index cb6e3846d27b..eed0315a77a6 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -270,6 +270,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
 #define KVM_EXIT_RISCV_SBI        35
+#define KVM_EXIT_RISCV_CSR        36
+#define KVM_EXIT_NOTIFY           37
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -496,6 +498,18 @@ struct kvm_run {
 			unsigned long args[6];
 			unsigned long ret[2];
 		} riscv_sbi;
+		/* KVM_EXIT_RISCV_CSR */
+		struct {
+			unsigned long csr_num;
+			unsigned long new_value;
+			unsigned long write_mask;
+			unsigned long ret_value;
+		} riscv_csr;
+		/* KVM_EXIT_NOTIFY */
+		struct {
+#define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
+			__u32 flags;
+		} notify;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1157,6 +1171,12 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_TSC_CONTROL 214
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216
+#define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
+#define KVM_CAP_X86_NOTIFY_VMEXIT 219
+#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
+#define KVM_CAP_S390_ZPCI_OP 221
+#define KVM_CAP_S390_CPU_TOPOLOGY 222
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1660,6 +1680,55 @@ struct kvm_s390_pv_unp {
 	__u64 tweak;
 };
 
+enum pv_cmd_dmp_id {
+	KVM_PV_DUMP_INIT,
+	KVM_PV_DUMP_CONFIG_STOR_STATE,
+	KVM_PV_DUMP_COMPLETE,
+	KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+	__u64 subcmd;
+	__u64 buff_addr;
+	__u64 buff_len;
+	__u64 gaddr;		/* For dump storage state */
+	__u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+	KVM_PV_INFO_VM,
+	KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+	__u64 dump_cpu_buffer_len;
+	__u64 dump_config_mem_buffer_per_1m;
+	__u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+	__u64 inst_calls_list[4];
+	__u64 max_cpus;
+	__u64 max_guests;
+	__u64 max_guest_addr;
+	__u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+	__u32 id;
+	__u32 len_max;
+	__u32 len_written;
+	__u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+	struct kvm_s390_pv_info_header header;
+	union {
+		struct kvm_s390_pv_info_dump dump;
+		struct kvm_s390_pv_info_vm vm;
+	};
+};
+
 enum pv_cmd_id {
 	KVM_PV_ENABLE,
 	KVM_PV_DISABLE,
@@ -1668,6 +1737,8 @@ enum pv_cmd_id {
 	KVM_PV_VERIFY,
 	KVM_PV_PREP_RESET,
 	KVM_PV_UNSHARE_ALL,
+	KVM_PV_INFO,
+	KVM_PV_DUMP,
 };
 
 struct kvm_pv_cmd {
@@ -2119,4 +2190,41 @@ struct kvm_stats_desc {
 /* Available with KVM_CAP_XSAVE2 */
 #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 
+/* Available with KVM_CAP_S390_PROTECTED_DUMP */
+#define KVM_S390_PV_CPU_COMMAND	_IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED		(1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER		(1ULL << 1)
+
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP         _IOW(KVMIO,  0xd1, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+	/* in */
+	__u32 fh;               /* target device */
+	__u8  op;               /* operation to perform */
+	__u8  pad[3];
+	union {
+		/* for KVM_S390_ZPCIOP_REG_AEN */
+		struct {
+			__u64 ibv;      /* Guest addr of interrupt bit vector */
+			__u64 sb;       /* Guest addr of summary bit */
+			__u32 flags;
+			__u32 noi;      /* Number of interrupts */
+			__u8 isc;       /* Guest interrupt subclass */
+			__u8 sbo;       /* Offset of guest summary bit vector */
+			__u16 pad;
+		} reg_aen;
+		__u64 reserved[8];
+	} u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN                0
+#define KVM_S390_ZPCIOP_DEREG_AEN      1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
+
 #endif /* __LINUX_KVM_H */
diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h
index b4309397b6b2..77f2aff1f27e 100644
--- a/include/uapi/linux/vfio_zdev.h
+++ b/include/uapi/linux/vfio_zdev.h
@@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base {
 	__u16 fmb_length;	/* Measurement Block Length (in bytes) */
 	__u8 pft;		/* PCI Function Type */
 	__u8 gid;		/* PCI function group ID */
+	/* End of version 1 */
+	__u32 fh;		/* PCI function handle */
+	/* End of version 2 */
 };
 
 /**
@@ -47,6 +50,10 @@ struct vfio_device_info_cap_zpci_group {
 	__u16 noi;		/* Maximum number of MSIs */
 	__u16 maxstbl;		/* Maximum Store Block Length */
 	__u8 version;		/* Supported PCI Version */
+	/* End of version 1 */
+	__u8 reserved;
+	__u16 imaxstbl;		/* Maximum Interpreted Store Block Length */
+	/* End of version 2 */
 };
 
 /**