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

Pull kvm updates from Paolo Bonzini:
 "Generic:

   - Use memdup_array_user() to harden against overflow.

   - Unconditionally advertise KVM_CAP_DEVICE_CTRL for all
     architectures.

   - Clean up Kconfigs that all KVM architectures were selecting

   - New functionality around "guest_memfd", a new userspace API that
     creates an anonymous file and returns a file descriptor that refers
     to it. guest_memfd files are bound to their owning virtual machine,
     cannot be mapped, read, or written by userspace, and cannot be
     resized. guest_memfd files do however support PUNCH_HOLE, which can
     be used to switch a memory area between guest_memfd and regular
     anonymous memory.

   - New ioctl KVM_SET_MEMORY_ATTRIBUTES allowing userspace to specify
     per-page attributes for a given page of guest memory; right now the
     only attribute is whether the guest expects to access memory via
     guest_memfd or not, which in Confidential SVMs backed by SEV-SNP,
     TDX or ARM64 pKVM is checked by firmware or hypervisor that
     guarantees confidentiality (AMD PSP, Intel TDX module, or EL2 in
     the case of pKVM).

  x86:

   - Support for "software-protected VMs" that can use the new
     guest_memfd and page attributes infrastructure. This is mostly
     useful for testing, since there is no pKVM-like infrastructure to
     provide a meaningfully reduced TCB.

   - Fix a relatively benign off-by-one error when splitting huge pages
     during CLEAR_DIRTY_LOG.

   - Fix a bug where KVM could incorrectly test-and-clear dirty bits in
     non-leaf TDP MMU SPTEs if a racing thread replaces a huge SPTE with
     a non-huge SPTE.

   - Use more generic lockdep assertions in paths that don't actually
     care about whether the caller is a reader or a writer.

   - let Xen guests opt out of having PV clock reported as "based on a
     stable TSC", because some of them don't expect the "TSC stable" bit
     (added to the pvclock ABI by KVM, but never set by Xen) to be set.

   - Revert a bogus, made-up nested SVM consistency check for
     TLB_CONTROL.

   - Advertise flush-by-ASID support for nSVM unconditionally, as KVM
     always flushes on nested transitions, i.e. always satisfies flush
     requests. This allows running bleeding edge versions of VMware
     Workstation on top of KVM.

   - Sanity check that the CPU supports flush-by-ASID when enabling SEV
     support.

   - On AMD machines with vNMI, always rely on hardware instead of
     intercepting IRET in some cases to detect unmasking of NMIs

   - Support for virtualizing Linear Address Masking (LAM)

   - Fix a variety of vPMU bugs where KVM fail to stop/reset counters
     and other state prior to refreshing the vPMU model.

   - Fix a double-overflow PMU bug by tracking emulated counter events
     using a dedicated field instead of snapshotting the "previous"
     counter. If the hardware PMC count triggers overflow that is
     recognized in the same VM-Exit that KVM manually bumps an event
     count, KVM would pend PMIs for both the hardware-triggered overflow
     and for KVM-triggered overflow.

   - Turn off KVM_WERROR by default for all configs so that it's not
     inadvertantly enabled by non-KVM developers, which can be
     problematic for subsystems that require no regressions for W=1
     builds.

   - Advertise all of the host-supported CPUID bits that enumerate
     IA32_SPEC_CTRL "features".

   - Don't force a masterclock update when a vCPU synchronizes to the
     current TSC generation, as updating the masterclock can cause
     kvmclock's time to "jump" unexpectedly, e.g. when userspace
     hotplugs a pre-created vCPU.

   - Use RIP-relative address to read kvm_rebooting in the VM-Enter
     fault paths, partly as a super minor optimization, but mostly to
     make KVM play nice with position independent executable builds.

   - Guard KVM-on-HyperV's range-based TLB flush hooks with an #ifdef on
     CONFIG_HYPERV as a minor optimization, and to self-document the
     code.

   - Add CONFIG_KVM_HYPERV to allow disabling KVM support for HyperV
     "emulation" at build time.

  ARM64:

   - LPA2 support, adding 52bit IPA/PA capability for 4kB and 16kB base
     granule sizes. Branch shared with the arm64 tree.

   - Large Fine-Grained Trap rework, bringing some sanity to the
     feature, although there is more to come. This comes with a prefix
     branch shared with the arm64 tree.

   - Some additional Nested Virtualization groundwork, mostly
     introducing the NV2 VNCR support and retargetting the NV support to
     that version of the architecture.

   - A small set of vgic fixes and associated cleanups.

  Loongarch:

   - Optimization for memslot hugepage checking

   - Cleanup and fix some HW/SW timer issues

   - Add LSX/LASX (128bit/256bit SIMD) support

  RISC-V:

   - KVM_GET_REG_LIST improvement for vector registers

   - Generate ISA extension reg_list using macros in get-reg-list
     selftest

   - Support for reporting steal time along with selftest

  s390:

   - Bugfixes

  Selftests:

   - Fix an annoying goof where the NX hugepage test prints out garbage
     instead of the magic token needed to run the test.

   - Fix build errors when a header is delete/moved due to a missing
     flag in the Makefile.

   - Detect if KVM bugged/killed a selftest's VM and print out a helpful
     message instead of complaining that a random ioctl() failed.

   - Annotate the guest printf/assert helpers with __printf(), and fix
     the various bugs that were lurking due to lack of said annotation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (185 commits)
  x86/kvm: Do not try to disable kvmclock if it was not enabled
  KVM: x86: add missing "depends on KVM"
  KVM: fix direction of dependency on MMU notifiers
  KVM: introduce CONFIG_KVM_COMMON
  KVM: arm64: Add missing memory barriers when switching to pKVM's hyp pgd
  KVM: arm64: vgic-its: Avoid potential UAF in LPI translation cache
  RISC-V: KVM: selftests: Add get-reg-list test for STA registers
  RISC-V: KVM: selftests: Add steal_time test support
  RISC-V: KVM: selftests: Add guest_sbi_probe_extension
  RISC-V: KVM: selftests: Move sbi_ecall to processor.c
  RISC-V: KVM: Implement SBI STA extension
  RISC-V: KVM: Add support for SBI STA registers
  RISC-V: KVM: Add support for SBI extension registers
  RISC-V: KVM: Add SBI STA info to vcpu_arch
  RISC-V: KVM: Add steal-update vcpu request
  RISC-V: KVM: Add SBI STA extension skeleton
  RISC-V: paravirt: Implement steal-time support
  RISC-V: Add SBI STA extension definitions
  RISC-V: paravirt: Add skeleton for pv-time support
  RISC-V: KVM: Fix indentation in kvm_riscv_vcpu_set_reg_csr()
  ...

6 files changed, 199 insertions, 152 deletions

diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 5deaddbd7927..93a5f16d03f3 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -15,13 +15,13 @@ struct inode;
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
-int anon_inode_getfd_secure(const char *name,
+int anon_inode_create_getfd(const char *name,
 			    const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4944136efaa2..7e7fd25b09b3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -80,8 +80,8 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM	1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES	1
 #endif
 
 /*
@@ -253,9 +253,10 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
+	unsigned long attributes;
 };
 
 struct kvm_gfn_range {
@@ -588,8 +589,20 @@ struct kvm_memory_slot {
 	u32 flags;
 	short id;
 	u16 as_id;
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	struct {
+		struct file __rcu *file;
+		pgoff_t pgoff;
+	} gmem;
+#endif
 };
 
+static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+{
+	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
 static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
 {
 	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -677,13 +690,29 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
 #endif
 
+/*
+ * Arch code must define kvm_arch_has_private_mem if support for private memory
+ * is enabled.
+ */
+#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -721,9 +750,9 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	unsigned long nr_memslot_pages;
 	/* The two memslot sets - active and inactive (per address space) */
-	struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+	struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
 	/* The current active memslot set for each address space */
-	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
 	struct xarray vcpu_array;
 	/*
 	 * Protected by slots_lock, but can be read outside if an
@@ -753,7 +782,7 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
-#ifdef CONFIG_HAVE_KVM_EVENTFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -761,8 +790,8 @@ struct kvm {
 		struct list_head  resampler_list;
 		struct mutex      resampler_lock;
 	} irqfds;
-	struct list_head ioeventfds;
 #endif
+	struct list_head ioeventfds;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	refcount_t users_count;
@@ -778,17 +807,16 @@ struct kvm {
 	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
-	unsigned long mmu_invalidate_range_start;
-	unsigned long mmu_invalidate_range_end;
+	gfn_t mmu_invalidate_range_start;
+	gfn_t mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -807,6 +835,10 @@ struct kvm {
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
 #endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	struct xarray mem_attr_array;
+#endif
 	char stats_id[KVM_STATS_NAME_SIZE];
 };
 
@@ -965,7 +997,7 @@ static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 }
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -989,7 +1021,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+	as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
@@ -1146,9 +1178,9 @@ enum kvm_mr_change {
 };
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+			  const struct kvm_userspace_memory_region2 *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+			    const struct kvm_userspace_memory_region2 *mem);
 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,
@@ -1392,10 +1424,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1947,7 +1979,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -1970,9 +2002,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 	return 0;
 }
 
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 					   unsigned long mmu_seq,
-					   unsigned long hva)
+					   gfn_t gfn)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
@@ -1981,10 +2013,20 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
 	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_invalidate_in_progress) &&
-	    hva >= kvm->mmu_invalidate_range_start &&
-	    hva < kvm->mmu_invalidate_range_end)
-		return 1;
+	if (unlikely(kvm->mmu_invalidate_in_progress)) {
+		/*
+		 * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+		 * but before updating the range is a KVM bug.
+		 */
+		if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+				 kvm->mmu_invalidate_range_end == INVALID_GPA))
+			return 1;
+
+		if (gfn >= kvm->mmu_invalidate_range_start &&
+		    gfn < kvm->mmu_invalidate_range_end)
+			return 1;
+	}
+
 	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
@@ -2013,12 +2055,10 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 
-#ifdef CONFIG_HAVE_KVM_EVENTFD
-
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 bool kvm_notify_irqfd_resampler(struct kvm *kvm,
@@ -2039,31 +2079,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif
-
-#else
-
-static inline void kvm_eventfd_init(struct kvm *kvm) {}
-
-static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
-{
-	return -EINVAL;
-}
-
-static inline void kvm_irqfd_release(struct kvm *kvm) {}
-
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm)
-{
-}
-#endif
-
-static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_HAVE_KVM_EVENTFD */
+#endif /* CONFIG_HAVE_KVM_IRQCHIP */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
@@ -2318,4 +2334,57 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 /* Max number of entries allowed for each kvm dirty ring */
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						 gpa_t gpa, gpa_t size,
+						 bool is_write, bool is_exec,
+						 bool is_private)
+{
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+	vcpu->run->memory_fault.gpa = gpa;
+	vcpu->run->memory_fault.size = size;
+
+	/* RWX flags are not (yet) defined or communicated to userspace. */
+	vcpu->run->memory_fault.flags = 0;
+	if (is_private)
+		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
+}
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+	return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return false;
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+#else
+static inline int kvm_gmem_get_pfn(struct kvm *kvm,
+				   struct kvm_memory_slot *slot, gfn_t gfn,
+				   kvm_pfn_t *pfn, int *max_order)
+{
+	KVM_BUG_ON(1, kvm);
+	return -EIO;
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 6f4737d5046a..9d1f7835d8c1 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -6,6 +6,7 @@
 struct kvm;
 struct kvm_async_pf;
 struct kvm_device_ops;
+struct kvm_gfn_range;
 struct kvm_interrupt;
 struct kvm_irq_routing_table;
 struct kvm_memory_slot;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 06142ff7f9ce..2df35e65557d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -206,6 +206,7 @@ enum mapping_flags {
 	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
 	AS_STABLE_WRITES,	/* must wait for writeback before modifying
 				   folio contents */
+	AS_UNMOVABLE,		/* The mapping cannot be moved, ever */
 };
 
 /**
@@ -306,6 +307,22 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping)
 	clear_bit(AS_STABLE_WRITES, &mapping->flags);
 }
 
+static inline void mapping_set_unmovable(struct address_space *mapping)
+{
+	/*
+	 * It's expected unmovable mappings are also unevictable. Compaction
+	 * migrate scanner (isolate_migratepages_block()) relies on this to
+	 * reduce page locking.
+	 */
+	set_bit(AS_UNEVICTABLE, &mapping->flags);
+	set_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
+static inline bool mapping_unmovable(struct address_space *mapping)
+{
+	return test_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 3bd31ea23fee..011fba6b5552 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -62,7 +62,7 @@ TRACE_EVENT(kvm_vcpu_wakeup,
 		  __entry->valid ? "valid" : "invalid")
 );
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -82,7 +82,7 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 #if defined(__KVM_HAVE_IOAPIC)
 #define kvm_deliver_mode		\
@@ -170,7 +170,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #endif /* defined(__KVM_HAVE_IOAPIC) */
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 
 #ifdef kvm_irqchips
 #define kvm_ack_irq_string "irqchip %s pin %u"
@@ -197,7 +197,7 @@ TRACE_EVENT(kvm_ack_irq,
 	TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm)
 );
 
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 211b86de35ac..c3308536482b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -95,6 +25,19 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+};
+
 /*
  * 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
@@ -102,6 +45,7 @@ struct kvm_userspace_memory_region {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -265,6 +209,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -518,6 +463,13 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -945,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1201,6 +1150,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1291,6 +1245,7 @@ struct kvm_x86_mce {
 #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)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1483,6 +1438,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
@@ -1507,20 +1464,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1537,9 +1482,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1592,8 +1534,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
@@ -2267,4 +2207,24 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */