rudy-in
diff --git a/‎Documentation/admin-guide/kernel-parameters.txt
+3-3 b/‎Documentation/admin-guide/kernel-parameters.txt
+3-3
diff --git a/‎Documentation/virt/kvm/api.rst
+207-12 b/‎Documentation/virt/kvm/api.rst
+207-12
diff --git a/‎Documentation/virt/kvm/locking.rst
+3-4 b/‎Documentation/virt/kvm/locking.rst
+3-4
diff --git a/‎arch/arm64/include/asm/esr.h
+15 b/‎arch/arm64/include/asm/esr.h
+15
@@ -3996,9 +3996,9 @@
 			vulnerability. System may allow data leaks with this
 			option.
 
-	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized
-			steal time accounting. steal time is computed, but
-			won't influence scheduler behaviour
+	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES,RISCV] Disable
+			paravirtualized steal time accounting. steal time is
+			computed, but won't influence scheduler behaviour
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
 
@@ -147,10 +147,29 @@ described as 'basic' will be available.
 The new VM has no virtual cpus and no memory.
 You probably want to use 0 as machine type.
 
+X86:
+^^^^
+
+Supported X86 VM types can be queried via KVM_CAP_VM_TYPES.
+
+S390:
+^^^^^
+
 In order to create user controlled virtual machines on S390, check
 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
 privileged user (CAP_SYS_ADMIN).
 
+MIPS:
+^^^^^
+
+To use hardware assisted virtualization on MIPS (VZ ASE) rather than
+the default trap & emulate implementation (which changes the virtual
+memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
+flag KVM_VM_MIPS_VZ.
+
+ARM64:
+^^^^^^
+
 On arm64, the physical address size for a VM (IPA Size limit) is limited
 to 40bits by default. The limit can be configured if the host supports the
 extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
@@ -608,18 +627,6 @@ interrupt number dequeues the interrupt.
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 
-4.17 KVM_DEBUG_GUEST
---------------------
-
-:Capability: basic
-:Architectures: none
-:Type: vcpu ioctl
-:Parameters: none)
-:Returns: -1 on error
-
-Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
-
-
 4.18 KVM_GET_MSRS
 -----------------
 
@@ -6192,6 +6199,130 @@ to know what fields can be changed for the system register described by
 ``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a
 superset of the features supported by the system.
 
+4.140 KVM_SET_USER_MEMORY_REGION2
+---------------------------------
+
+:Capability: KVM_CAP_USER_MEMORY2
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_userspace_memory_region2 (in)
+:Returns: 0 on success, -1 on error
+
+KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that
+allows mapping guest_memfd memory into a guest.  All fields shared with
+KVM_SET_USER_MEMORY_REGION identically.  Userspace can set KVM_MEM_GUEST_MEMFD
+in flags to have KVM bind the memory region to a given guest_memfd range of
+[guest_memfd_offset, guest_memfd_offset + memory_size].  The target guest_memfd
+must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and
+the target range must not be bound to any other memory region.  All standard
+bounds checks apply (use common sense).
+
+::
+
+  struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+  };
+
+A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and
+userspace_addr (shared memory).  However, "valid" for userspace_addr simply
+means that the address itself must be a legal userspace address.  The backing
+mapping for userspace_addr is not required to be valid/populated at the time of
+KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated
+on-demand.
+
+When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes
+userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE
+state.  At VM creation time, all memory is shared, i.e. the PRIVATE attribute
+is '0' for all gfns.  Userspace can control whether memory is shared/private by
+toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed.
+
+4.141 KVM_SET_MEMORY_ATTRIBUTES
+-------------------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_memory_attributes (in)
+:Returns: 0 on success, <0 on error
+
+KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range
+of guest physical memory.
+
+::
+
+  struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+  };
+
+  #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+The address and size must be page aligned.  The supported attributes can be
+retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES.  If
+executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes
+supported by that VM.  If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES
+returns all attributes supported by KVM.  The only attribute defined at this
+time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being
+guest private memory.
+
+Note, there is no "get" API.  Userspace is responsible for explicitly tracking
+the state of a gfn/page as needed.
+
+The "flags" field is reserved for future extensions and must be '0'.
+
+4.142 KVM_CREATE_GUEST_MEMFD
+----------------------------
+
+:Capability: KVM_CAP_GUEST_MEMFD
+:Architectures: none
+:Type: vm ioctl
+:Parameters: struct kvm_create_guest_memfd(in)
+:Returns: 0 on success, <0 on error
+
+KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor
+that refers to it.  guest_memfd files are roughly analogous to files created
+via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage,
+and are automatically released when the last reference is dropped.  Unlike
+"regular" memfd_create() files, guest_memfd files are bound to their owning
+virtual machine (see below), cannot be mapped, read, or written by userspace,
+and cannot be resized  (guest_memfd files do however support PUNCH_HOLE).
+
+::
+
+  struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+  };
+
+Conceptually, the inode backing a guest_memfd file represents physical memory,
+i.e. is coupled to the virtual machine as a thing, not to a "struct kvm".  The
+file itself, which is bound to a "struct kvm", is that instance's view of the
+underlying memory, e.g. effectively provides the translation of guest addresses
+to host memory.  This allows for use cases where multiple KVM structures are
+used to manage a single virtual machine, e.g. when performing intrahost
+migration of a virtual machine.
+
+KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2,
+and more specifically via the guest_memfd and guest_memfd_offset fields in
+"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset
+into the guest_memfd instance.  For a given guest_memfd file, there can be at
+most one mapping per page, i.e. binding multiple memory regions to a single
+guest_memfd range is not allowed (any number of memory regions can be bound to
+a single guest_memfd file, but the bound ranges must not overlap).
+
+See KVM_SET_USER_MEMORY_REGION2 for additional details.
+
 5. The kvm_run structure
 ========================
 
@@ -6824,6 +6955,30 @@ array field represents return values. The userspace should update the return
 values of SBI call before resuming the VCPU. For more details on RISC-V SBI
 spec refer, https://github.com/riscv/riscv-sbi-doc.
 
+::
+
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+  #define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
+
+KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that
+could not be resolved by KVM.  The 'gpa' and 'size' (in bytes) describe the
+guest physical address range [gpa, gpa + size) of the fault.  The 'flags' field
+describes properties of the faulting access that are likely pertinent:
+
+ - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred
+   on a private memory access.  When clear, indicates the fault occurred on a
+   shared access.
+
+Note!  KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it
+accompanies a return code of '-1', not '0'!  errno will always be set to EFAULT
+or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume
+kvm_run.exit_reason is stale/undefined for all other error numbers.
+
 ::
 
     /* KVM_EXIT_NOTIFY */
@@ -7858,6 +8013,27 @@ This capability is aimed to mitigate the threat that malicious VMs can
 cause CPU stuck (due to event windows don't open up) and make the CPU
 unavailable to host or other VMs.
 
+7.34 KVM_CAP_MEMORY_FAULT_INFO
+------------------------------
+
+:Architectures: x86
+:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP.
+
+The presence of this capability indicates that KVM_RUN will fill
+kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if
+there is a valid memslot but no backing VMA for the corresponding host virtual
+address.
+
+The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns
+an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set
+to KVM_EXIT_MEMORY_FAULT.
+
+Note: Userspaces which attempt to resolve memory faults so that they can retry
+KVM_RUN are encouraged to guard against repeatedly receiving the same
+error/annotated fault.
+
+See KVM_EXIT_MEMORY_FAULT for more information.
+
 8. Other capabilities.
 ======================
 
@@ -8374,6 +8550,7 @@ PVHVM guests. Valid flags are::
   #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)
 
 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
 ioctl is available, for the guest to set its hypercall page.
@@ -8417,6 +8594,11 @@ behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless
 specifically enabled (by the guest making the hypercall, causing the VMM
 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute).
 
+The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports
+clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be
+done when the KVM_CAP_XEN_HVM ioctl sets the
+KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag.
+
 8.31 KVM_CAP_PPC_MULTITCE
 -------------------------
 
@@ -8596,6 +8778,19 @@ block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
 64-bit bitmap (each bit describing a block size). The default value is
 0, to disable the eager page splitting.
 
+8.41 KVM_CAP_VM_TYPES
+---------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: system ioctl
+
+This capability returns a bitmap of support VM types.  The 1-setting of bit @n
+means the VM type with value @n is supported.  Possible values of @n are::
+
+  #define KVM_X86_DEFAULT_VM	0
+  #define KVM_X86_SW_PROTECTED_VM	1
+
 9. Known KVM API problems
 =========================
 
 
@@ -43,10 +43,9 @@ On x86:
 
 - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
 
-- kvm->arch.mmu_lock is an rwlock.  kvm->arch.tdp_mmu_pages_lock and
-  kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
-  cannot be taken without already holding kvm->arch.mmu_lock (typically with
-  ``read_lock`` for the TDP MMU, thus the need for additional spinlocks).
+- kvm->arch.mmu_lock is an rwlock; critical sections for
+  kvm->arch.tdp_mmu_pages_lock and kvm->arch.mmu_unsync_pages_lock must
+  also take kvm->arch.mmu_lock
 
 Everything else is a leaf: no other lock is taken inside the critical
 sections.
 
@@ -392,6 +392,21 @@ static inline bool esr_is_data_abort(unsigned long esr)
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
+static inline bool esr_fsc_is_translation_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT;
+}
+
+static inline bool esr_fsc_is_permission_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM;
+}
+
+static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS;
+}
+
 const char *esr_get_class_string(unsigned long esr);
 #endif /* __ASSEMBLY */