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
  ...

4 files changed, 26 insertions, 18 deletions

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 */