diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 97b63dc1145773e8e3c0a6254570d1529148e8d0..e356d1b7469f7e2fff9e41743926538421e30751 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -861,12 +861,16 @@ the parameter has no effect. crash_kexec_post_notifiers - Run kdump after running panic-notifiers and dumping - kmsg. This only for the users who doubt kdump always - succeeds in any situation. - Note that this also increases risks of kdump failure, - because some panic notifiers can make the crashed - kernel more unstable. + Only jump to kdump kernel after running the panic + notifiers and dumping kmsg. This option increases + the risks of a kdump failure, since some panic + notifiers can make the crashed kernel more unstable. + In configurations where kdump may not be reliable, + running the panic notifiers could allow collecting + more data on dmesg, like stack traces from other CPUS + or extra data dumped by panic_print. Note that some + configurations enable this option unconditionally, + like Hyper-V, PowerPC (fadump) and AMD SEV-SNP. crashkernel=size[KMG][@offset[KMG]] [KNL] Using kexec, Linux can switch to a 'crash kernel' diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index 68b0d2363af820256c70ba2d5284244247ee979f..de68d3a4b54038df1701ea42e6b195795f669243 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -67,6 +67,23 @@ counter (e.g. counter overflow), then -EIO will be returned. }; }; +The host ioctls are issued to a file descriptor of the /dev/sev device. +The ioctl accepts the command ID/input structure documented below. + +:: + + struct sev_issue_cmd { + /* Command ID */ + __u32 cmd; + + /* Command request structure */ + __u64 data; + + /* Firmware error code on failure (see psp-sev.h) */ + __u32 error; + }; + + 2.1 SNP_GET_REPORT ------------------ @@ -124,6 +141,60 @@ be updated with the expected value. See GHCB specification for further detail on how to parse the certificate blob. +2.4 SNP_PLATFORM_STATUS +----------------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (out): struct sev_user_data_snp_status +:Returns (out): 0 on success, -negative on error + +The SNP_PLATFORM_STATUS command is used to query the SNP platform status. The +status includes API major, minor version and more. See the SEV-SNP +specification for further details. + +2.5 SNP_COMMIT +-------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Returns (out): 0 on success, -negative on error + +SNP_COMMIT is used to commit the currently installed firmware using the +SEV-SNP firmware SNP_COMMIT command. This prevents roll-back to a previously +committed firmware version. This will also update the reported TCB to match +that of the currently installed firmware. + +2.6 SNP_SET_CONFIG +------------------ +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (in): struct sev_user_data_snp_config +:Returns (out): 0 on success, -negative on error + +SNP_SET_CONFIG is used to set the system-wide configuration such as +reported TCB version in the attestation report. The command is similar +to SNP_CONFIG command defined in the SEV-SNP spec. The current values of +the firmware parameters affected by this command can be queried via +SNP_PLATFORM_STATUS. + +2.7 SNP_VLEK_LOAD +----------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (in): struct sev_user_data_snp_vlek_load +:Returns (out): 0 on success, -negative on error + +When requesting an attestation report a guest is able to specify whether +it wants SNP firmware to sign the report using either a Versioned Chip +Endorsement Key (VCEK), which is derived from chip-unique secrets, or a +Versioned Loaded Endorsement Key (VLEK) which is obtained from an AMD +Key Derivation Service (KDS) and derived from seeds allocated to +enrolled cloud service providers. + +In the case of VLEK keys, the SNP_VLEK_LOAD SNP command is used to load +them into the system after obtaining them from the KDS, and corresponds +closely to the SNP_VLEK_LOAD firmware command specified in the SEV-SNP +spec. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 17811002a8f7cdf54fb065e2b65a60472f2f6d3e..5866b26781d5aae980780a88d9575e02d0cc1628 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -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 @@ -547,7 +566,7 @@ ioctl is useful if the in-kernel PIC is not used. PPC: ^^^^ -Queues an external interrupt to be injected. This ioctl is overleaded +Queues an external interrupt to be injected. This ioctl is overloaded with 3 different irq values: a) KVM_INTERRUPT_SET @@ -998,7 +1017,7 @@ be set in the flags field of this ioctl: The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag requests KVM to generate the contents of the hypercall page automatically; hypercalls will be intercepted and passed to userspace through KVM_EXIT_XEN. In this -ase, all of the blob size and address fields must be zero. +case, all of the blob size and address fields must be zero. The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates to KVM that userspace will always use the KVM_XEN_HVM_EVTCHN_SEND ioctl to deliver event @@ -1103,7 +1122,7 @@ Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored. :Extended by: KVM_CAP_INTR_SHADOW :Architectures: x86, arm64 :Type: vcpu ioctl -:Parameters: struct kvm_vcpu_event (out) +:Parameters: struct kvm_vcpu_events (out) :Returns: 0 on success, -1 on error X86: @@ -1226,7 +1245,7 @@ directly to the virtual CPU). :Extended by: KVM_CAP_INTR_SHADOW :Architectures: x86, arm64 :Type: vcpu ioctl -:Parameters: struct kvm_vcpu_event (in) +:Parameters: struct kvm_vcpu_events (in) :Returns: 0 on success, -1 on error X86: @@ -3121,7 +3140,7 @@ as follow:: }; An entry with a "page_shift" of 0 is unused. Because the array is -organized in increasing order, a lookup can stop when encoutering +organized in increasing order, a lookup can stop when encountering such an entry. The "slb_enc" field provides the encoding to use in the SLB for the @@ -3428,6 +3447,8 @@ return indicates the attribute is implemented. It does not necessarily indicate that the attribute can be read or written in the device's current state. "addr" is ignored. +.. _KVM_ARM_VCPU_INIT: + 4.82 KVM_ARM_VCPU_INIT ---------------------- @@ -3513,7 +3534,7 @@ Possible features: - KVM_RUN and KVM_GET_REG_LIST are not available; - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access - the scalable archietctural SVE registers + the scalable architectural SVE registers KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or KVM_REG_ARM64_SVE_FFR; @@ -4459,7 +4480,7 @@ This will have undefined effects on the guest if it has not already placed itself in a quiescent state where no vcpu will make MMU enabled memory accesses. -On succsful completion, the pending HPT will become the guest's active +On successful completion, the pending HPT will become the guest's active HPT and the previous HPT will be discarded. On failure, the guest will still be operating on its previous HPT. @@ -5074,7 +5095,7 @@ before the vcpu is fully usable. Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be configured by use of ioctls such as KVM_SET_ONE_REG. The exact configuration -that should be performaned and how to do it are feature-dependent. +that should be performed and how to do it are feature-dependent. Other calls that depend on a particular feature being finalized, such as KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with @@ -5182,6 +5203,24 @@ Valid values for 'action':: #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +Via this API, KVM userspace can also control the behavior of the VM's fixed +counters (if any) by configuring the "action" and "fixed_counter_bitmap" fields. + +Specifically, KVM follows the following pseudo-code when determining whether to +allow the guest FixCtr[i] to count its pre-defined fixed event:: + + FixCtr[i]_is_allowed = (action == ALLOW) && (bitmap & BIT(i)) || + (action == DENY) && !(bitmap & BIT(i)); + FixCtr[i]_is_denied = !FixCtr[i]_is_allowed; + +KVM always consumes fixed_counter_bitmap, it's userspace's responsibility to +ensure fixed_counter_bitmap is set correctly, e.g. if userspace wants to define +a filter that only affects general purpose counters. + +Note, the "events" field also applies to fixed counters' hardcoded event_select +and unit_mask values. "fixed_counter_bitmap" has higher priority than "events" +if there is a contradiction between the two. + 4.121 KVM_PPC_SVM_OFF --------------------- @@ -5533,7 +5572,7 @@ KVM_XEN_ATTR_TYPE_EVTCHN from the guest. A given sending port number may be directed back to a specified vCPU (by APIC ID) / port / priority on the guest, or to trigger events on an eventfd. The vCPU and priority can be changed - by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other + by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but other fields cannot change for a given sending port. A port mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing KVM_XEN_EVTCHN_RESET in the flags field removes all interception of @@ -6128,6 +6167,241 @@ writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG interface. No error will be returned, but the resulting offset will not be applied. +.. _KVM_ARM_GET_REG_WRITABLE_MASKS: + +4.139 KVM_ARM_GET_REG_WRITABLE_MASKS +------------------------------------------- + +:Capability: KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES +:Architectures: arm64 +:Type: vm ioctl +:Parameters: struct reg_mask_range (in/out) +:Returns: 0 on success, < 0 on error + + +:: + + #define KVM_ARM_FEATURE_ID_RANGE 0 + #define KVM_ARM_FEATURE_ID_RANGE_SIZE (3 * 8 * 8) + + struct reg_mask_range { + __u64 addr; /* Pointer to mask array */ + __u32 range; /* Requested range */ + __u32 reserved[13]; + }; + +This ioctl copies the writable masks for a selected range of registers to +userspace. + +The ``addr`` field is a pointer to the destination array where KVM copies +the writable masks. + +The ``range`` field indicates the requested range of registers. +``KVM_CHECK_EXTENSION`` for the ``KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES`` +capability returns the supported ranges, expressed as a set of flags. Each +flag's bit index represents a possible value for the ``range`` field. +All other values are reserved for future use and KVM may return an error. + +The ``reserved[13]`` array is reserved for future use and should be 0, or +KVM may return an error. + +KVM_ARM_FEATURE_ID_RANGE (0) +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The Feature ID range is defined as the AArch64 System register space with +op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, op2=={0-7}. + +The mask returned array pointed to by ``addr`` is indexed by the macro +``ARM64_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)``, allowing userspace +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: A file descriptor 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. + +4.143 KVM_PRE_FAULT_MEMORY +------------------------ + +:Capability: KVM_CAP_PRE_FAULT_MEMORY +:Architectures: none +:Type: vcpu ioctl +:Parameters: struct kvm_pre_fault_memory (in/out) +:Returns: 0 if at least one page is processed, < 0 on error + +Errors: + + ========== =============================================================== + EINVAL The specified `gpa` and `size` were invalid (e.g. not + page aligned, causes an overflow, or size is zero). + ENOENT The specified `gpa` is outside defined memslots. + EINTR An unmasked signal is pending and no page was processed. + EFAULT The parameter address was invalid. + EOPNOTSUPP Mapping memory for a GPA is unsupported by the + hypervisor, and/or for the current vCPU state/mode. + EIO unexpected error conditions (also causes a WARN) + ========== =============================================================== + +:: + + struct kvm_pre_fault_memory { + /* in/out */ + __u64 gpa; + __u64 size; + /* in */ + __u64 flags; + __u64 padding[5]; + }; + +KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory +for the current vCPU state. KVM maps memory as if the vCPU generated a +stage-2 read page fault, e.g. faults in memory as needed, but doesn't break +CoW. However, KVM does not mark any newly created stage-2 PTE as Accessed. + +In the case of confidential VM types where there is an initial set up of +private guest memory before the guest is 'finalized'/measured, this ioctl +should only be issued after completing all the necessary setup to put the +guest into a 'finalized' state so that the above semantics can be reliably +ensured. + +In some cases, multiple vCPUs might share the page tables. In this +case, the ioctl can be called in parallel. + +When the ioctl returns, the input values are updated to point to the +remaining range. If `size` > 0 on return, the caller can just issue +the ioctl again with the same `struct kvm_map_memory` argument. + +Shadow page tables cannot support this ioctl because they +are indexed by virtual address or nested guest physical address. +Calling this ioctl when the guest is using shadow page tables (for +example because it is running a nested guest with nested page tables) +will fail with `EOPNOTSUPP` even if `KVM_CHECK_EXTENSION` reports +the capability to be present. + +`flags` must currently be zero. + + 5. The kvm_run structure ======================== @@ -6760,6 +7034,30 @@ 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 */ @@ -7794,6 +8092,27 @@ 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. ====================== @@ -8310,6 +8629,7 @@ 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. @@ -8353,6 +8673,11 @@ 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 ------------------------- @@ -8532,6 +8857,21 @@ 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 + #define KVM_X86_SEV_VM 2 + #define KVM_X86_SEV_ES_VM 3 + 9. Known KVM API problems ========================= diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst index e84848432158084f789b0c18764afd1f3fb547ac..7f231c724e16756f63b2a38e9e2df6a60727d2ee 100644 --- a/Documentation/virt/kvm/arm/index.rst +++ b/Documentation/virt/kvm/arm/index.rst @@ -11,3 +11,4 @@ ARM hypercalls pvtime ptp_kvm + vcpu-features diff --git a/Documentation/virt/kvm/arm/vcpu-features.rst b/Documentation/virt/kvm/arm/vcpu-features.rst new file mode 100644 index 0000000000000000000000000000000000000000..f7cc6d8d8b74052616acbf0dab3b92ec13badf22 --- /dev/null +++ b/Documentation/virt/kvm/arm/vcpu-features.rst @@ -0,0 +1,48 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============================== +vCPU feature selection on arm64 +=============================== + +KVM/arm64 provides two mechanisms that allow userspace to configure +the CPU features presented to the guest. + +KVM_ARM_VCPU_INIT +================= + +The ``KVM_ARM_VCPU_INIT`` ioctl accepts a bitmap of feature flags +(``struct kvm_vcpu_init::features``). Features enabled by this interface are +*opt-in* and may change/extend UAPI. See :ref:`KVM_ARM_VCPU_INIT` for complete +documentation of the features controlled by the ioctl. + +Otherwise, all CPU features supported by KVM are described by the architected +ID registers. + +The ID Registers +================ + +The Arm architecture specifies a range of *ID Registers* that describe the set +of architectural features supported by the CPU implementation. KVM initializes +the guest's ID registers to the maximum set of CPU features supported by the +system. The ID register values may be VM-scoped in KVM, meaning that the +values could be shared for all vCPUs in a VM. + +KVM allows userspace to *opt-out* of certain CPU features described by the ID +registers by writing values to them via the ``KVM_SET_ONE_REG`` ioctl. The ID +registers are mutable until the VM has started, i.e. userspace has called +``KVM_RUN`` on at least one vCPU in the VM. Userspace can discover what fields +are mutable in the ID registers using the ``KVM_ARM_GET_REG_WRITABLE_MASKS``. +See the :ref:`ioctl documentation ` for more +details. + +Userspace is allowed to *limit* or *mask* CPU features according to the rules +outlined by the architecture in DDI0487J.a D19.1.3 'Principles of the ID +scheme for fields in ID register'. KVM does not allow ID register values that +exceed the capabilities of the system. + +.. warning:: + It is **strongly recommended** that userspace modify the ID register values + before accessing the rest of the vCPU's CPU register state. KVM may use the + ID register values to control feature emulation. Interleaving ID register + modification with other system register accesses may lead to unpredictable + behavior. diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index 995780088eb23142a169542fad4d298b4cbc2cfe..1ddb6a86ce7ff57755349ac1e92ea3826a1dba07 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -46,21 +46,16 @@ SEV hardware uses ASIDs to associate a memory encryption key with a VM. Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value defined in the CPUID 0x8000001f[ecx] field. -SEV Key Management -================== +The KVM_MEMORY_ENCRYPT_OP ioctl +=============================== -The SEV guest key management is handled by a separate processor called the AMD -Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure -key management interface to perform common hypervisor activities such as -encrypting bootstrap code, snapshot, migrating and debugging the guest. For more -information, see the SEV Key Management spec [api-spec]_ - -The main ioctl to access SEV is KVM_MEMORY_ENCRYPT_OP. If the argument -to KVM_MEMORY_ENCRYPT_OP is NULL, the ioctl returns 0 if SEV is enabled -and ``ENOTTY`` if it is disabled (on some older versions of Linux, -the ioctl runs normally even with a NULL argument, and therefore will -likely return ``EFAULT``). If non-NULL, the argument to KVM_MEMORY_ENCRYPT_OP -must be a struct kvm_sev_cmd:: +The main ioctl to access SEV is KVM_MEMORY_ENCRYPT_OP, which operates on +the VM file descriptor. If the argument to KVM_MEMORY_ENCRYPT_OP is NULL, +the ioctl returns 0 if SEV is enabled and ``ENOTTY`` if it is disabled +(on some older versions of Linux, the ioctl tries to run normally even +with a NULL argument, and therefore will likely return ``EFAULT`` instead +of zero if SEV is enabled). If non-NULL, the argument to +KVM_MEMORY_ENCRYPT_OP must be a struct kvm_sev_cmd:: struct kvm_sev_cmd { __u32 id; @@ -81,19 +76,56 @@ are defined in ````. KVM implements the following commands to support common lifecycle events of SEV guests, such as launching, running, snapshotting, migrating and decommissioning. -1. KVM_SEV_INIT ---------------- +1. KVM_SEV_INIT2 +---------------- -The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform +The KVM_SEV_INIT2 command is used by the hypervisor to initialize the SEV platform context. In a typical workflow, this command should be the first command issued. -The firmware can be initialized either by using its own non-volatile storage or -the OS can manage the NV storage for the firmware using the module parameter -``init_ex_path``. If the file specified by ``init_ex_path`` does not exist or -is invalid, the OS will create or override the file with output from PSP. +For this command to be accepted, either KVM_X86_SEV_VM or KVM_X86_SEV_ES_VM +must have been passed to the KVM_CREATE_VM ioctl. A virtual machine created +with those machine types in turn cannot be run until KVM_SEV_INIT2 is invoked. + +Parameters: struct kvm_sev_init (in) Returns: 0 on success, -negative on error +:: + + struct kvm_sev_init { + __u64 vmsa_features; /* initial value of features field in VMSA */ + __u32 flags; /* must be 0 */ + __u16 ghcb_version; /* maximum guest GHCB version allowed */ + __u16 pad1; + __u32 pad2[8]; + }; + +It is an error if the hypervisor does not support any of the bits that +are set in ``flags`` or ``vmsa_features``. ``vmsa_features`` must be +0 for SEV virtual machines, as they do not have a VMSA. + +``ghcb_version`` must be 0 for SEV virtual machines, as they do not issue GHCB +requests. If ``ghcb_version`` is 0 for any other guest type, then the maximum +allowed guest GHCB protocol will default to version 2. + +This command replaces the deprecated KVM_SEV_INIT and KVM_SEV_ES_INIT commands. +The commands did not have any parameters (the ```data``` field was unused) and +only work for the KVM_X86_DEFAULT_VM machine type (0). + +They behave as if: + +* the VM type is KVM_X86_SEV_VM for KVM_SEV_INIT, or KVM_X86_SEV_ES_VM for + KVM_SEV_ES_INIT + +* the ``flags`` and ``vmsa_features`` fields of ``struct kvm_sev_init`` are + set to zero, and ``ghcb_version`` is set to 0 for KVM_SEV_INIT and 1 for + KVM_SEV_ES_INIT. + +If the ``KVM_X86_SEV_VMSA_FEATURES`` attribute does not exist, the hypervisor only +supports KVM_SEV_INIT and KVM_SEV_ES_INIT. In that case, note that KVM_SEV_ES_INIT +might set the debug swap VMSA feature (bit 5) depending on the value of the +``debug_swap`` parameter of ``kvm-amd.ko``. + 2. KVM_SEV_LAUNCH_START ----------------------- @@ -434,13 +466,148 @@ issued by the hypervisor to make the guest ready for execution. Returns: 0 on success, -negative on error +18. KVM_SEV_SNP_LAUNCH_START +---------------------------- + +The KVM_SNP_LAUNCH_START command is used for creating the memory encryption +context for the SEV-SNP guest. It must be called prior to issuing +KVM_SEV_SNP_LAUNCH_UPDATE or KVM_SEV_SNP_LAUNCH_FINISH; + +Parameters (in): struct kvm_sev_snp_launch_start + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_snp_launch_start { + __u64 policy; /* Guest policy to use. */ + __u8 gosvw[16]; /* Guest OS visible workarounds. */ + __u16 flags; /* Must be zero. */ + __u8 pad0[6]; + __u64 pad1[4]; + }; + +See SNP_LAUNCH_START in the SEV-SNP specification [snp-fw-abi]_ for further +details on the input parameters in ``struct kvm_sev_snp_launch_start``. + +19. KVM_SEV_SNP_LAUNCH_UPDATE +----------------------------- + +The KVM_SEV_SNP_LAUNCH_UPDATE command is used for loading userspace-provided +data into a guest GPA range, measuring the contents into the SNP guest context +created by KVM_SEV_SNP_LAUNCH_START, and then encrypting/validating that GPA +range so that it will be immediately readable using the encryption key +associated with the guest context once it is booted, after which point it can +attest the measurement associated with its context before unlocking any +secrets. + +It is required that the GPA ranges initialized by this command have had the +KVM_MEMORY_ATTRIBUTE_PRIVATE attribute set in advance. See the documentation +for KVM_SET_MEMORY_ATTRIBUTES for more details on this aspect. + +Upon success, this command is not guaranteed to have processed the entire +range requested. Instead, the ``gfn_start``, ``uaddr``, and ``len`` fields of +``struct kvm_sev_snp_launch_update`` will be updated to correspond to the +remaining range that has yet to be processed. The caller should continue +calling this command until those fields indicate the entire range has been +processed, e.g. ``len`` is 0, ``gfn_start`` is equal to the last GFN in the +range plus 1, and ``uaddr`` is the last byte of the userspace-provided source +buffer address plus 1. In the case where ``type`` is KVM_SEV_SNP_PAGE_TYPE_ZERO, +``uaddr`` will be ignored completely. + +Parameters (in): struct kvm_sev_snp_launch_update + +Returns: 0 on success, < 0 on error, -EAGAIN if caller should retry + +:: + + struct kvm_sev_snp_launch_update { + __u64 gfn_start; /* Guest page number to load/encrypt data into. */ + __u64 uaddr; /* Userspace address of data to be loaded/encrypted. */ + __u64 len; /* 4k-aligned length in bytes to copy into guest memory.*/ + __u8 type; /* The type of the guest pages being initialized. */ + __u8 pad0; + __u16 flags; /* Must be zero. */ + __u32 pad1; + __u64 pad2[4]; + + }; + +where the allowed values for page_type are #define'd as:: + + KVM_SEV_SNP_PAGE_TYPE_NORMAL + KVM_SEV_SNP_PAGE_TYPE_ZERO + KVM_SEV_SNP_PAGE_TYPE_UNMEASURED + KVM_SEV_SNP_PAGE_TYPE_SECRETS + KVM_SEV_SNP_PAGE_TYPE_CPUID + +See the SEV-SNP spec [snp-fw-abi]_ for further details on how each page type is +used/measured. + +20. KVM_SEV_SNP_LAUNCH_FINISH +----------------------------- + +After completion of the SNP guest launch flow, the KVM_SEV_SNP_LAUNCH_FINISH +command can be issued to make the guest ready for execution. + +Parameters (in): struct kvm_sev_snp_launch_finish + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_snp_launch_finish { + __u64 id_block_uaddr; + __u64 id_auth_uaddr; + __u8 id_block_en; + __u8 auth_key_en; + __u8 vcek_disabled; + __u8 host_data[32]; + __u8 pad0[3]; + __u16 flags; /* Must be zero */ + __u64 pad1[4]; + }; + + +See SNP_LAUNCH_FINISH in the SEV-SNP specification [snp-fw-abi]_ for further +details on the input parameters in ``struct kvm_sev_snp_launch_finish``. + +Device attribute API +==================== + +Attributes of the SEV implementation can be retrieved through the +``KVM_HAS_DEVICE_ATTR`` and ``KVM_GET_DEVICE_ATTR`` ioctls on the ``/dev/kvm`` +device node, using group ``KVM_X86_GRP_SEV``. + +Currently only one attribute is implemented: + +* ``KVM_X86_SEV_VMSA_FEATURES``: return the set of all bits that + are accepted in the ``vmsa_features`` of ``KVM_SEV_INIT2``. + +Firmware Management +=================== + +The SEV guest key management is handled by a separate processor called the AMD +Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure +key management interface to perform common hypervisor activities such as +encrypting bootstrap code, snapshot, migrating and debugging the guest. For more +information, see the SEV Key Management spec [api-spec]_ + +The AMD-SP firmware can be initialized either by using its own non-volatile +storage or the OS can manage the NV storage for the firmware using +parameter ``init_ex_path`` of the ``ccp`` module. If the file specified +by ``init_ex_path`` does not exist or is invalid, the OS will create or +override the file with PSP non-volatile storage. + References ========== -See [white-paper]_, [api-spec]_, [amd-apm]_ and [kvm-forum]_ for more info. +See [white-paper]_, [api-spec]_, [amd-apm]_, [kvm-forum]_, and [snp-fw-abi]_ +for more info. .. [white-paper] https://developer.amd.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf .. [api-spec] https://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf .. [amd-apm] https://support.amd.com/TechDocs/24593.pdf (section 15.34) .. [kvm-forum] https://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf +.. [snp-fw-abi] https://www.amd.com/system/files/TechDocs/56860.pdf diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 81898bb87c5e999375bfd9e23c80f48b976509aa..6c745b7217314207abe8c23686a7c759d6b48e7d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1000,8 +1000,6 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); -#define KVM_ARCH_WANT_MMU_NOTIFIER - void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); @@ -1210,6 +1208,8 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, struct kvm_arm_counter_offset *offset); +int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, + struct reg_mask_range *range); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 196231712b10975b06e929d347525d68364bae57..93f12e30dd0f36b77739d54af2e20c13bd4ec6a9 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -514,6 +514,38 @@ struct kvm_smccc_filter { #define KVM_HYPERCALL_EXIT_SMC (1U << 0) #define KVM_HYPERCALL_EXIT_16BIT (1U << 1) +/* + * Get feature ID registers userspace writable mask. + * + * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model + * Feature Register 2"): + * + * "The Feature ID space is defined as the System register space in + * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, + * op2=={0-7}." + * + * This covers all currently known R/O registers that indicate + * anything useful feature wise, including the ID registers. + * + * If we ever need to introduce a new range, it will be described as + * such in the range field. + */ +#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2) \ + ({ \ + __u64 __op1 = (op1) & 3; \ + __op1 -= (__op1 == 3); \ + (__op1 << 6 | ((crm) & 7) << 3 | (op2)); \ + }) + +#define KVM_ARM_FEATURE_ID_RANGE 0 +#define KVM_ARM_FEATURE_ID_RANGE_SIZE (3 * 8 * 8) + +struct reg_mask_range { + __u64 addr; /* Pointer to mask array */ + __u32 range; /* Requested range */ + __u32 reserved[13]; +}; + #endif #endif /* __ARM_KVM_H__ */ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 52edbd7f6340cdb39d257a4834c4cf7997247231..fc88494beed016814ab644b993ac645510ed0d6d 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -23,7 +23,7 @@ menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM select KVM_GENERIC_HARDWARE_ENABLING - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3100a87944d57084672ed24dbcfae93bf48de464..1908d2db8ba33c941aa167ea7c37ba88dc6ec15e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -510,6 +510,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES: r = kvm_supported_block_sizes(); break; + case KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES: + r = BIT(0); + break; #ifdef CONFIG_VIRT_PLAT_DEV case KVM_CAP_ARM_VIRT_MSI_BYPASS: r = sdev_enable; @@ -1994,6 +1997,13 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return kvm_vm_set_attr(kvm, &attr); } + case KVM_ARM_GET_REG_WRITABLE_MASKS: { + struct reg_mask_range range; + + if (copy_from_user(&range, argp, sizeof(range))) + return -EFAULT; + return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range); + } #ifdef CONFIG_VIRT_PLAT_DEV case KVM_CREATE_SHADOW_DEV: { struct kvm_master_dev_info *mdi; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 8cd4c95759a02df30dabff05317ccbb3c2559eba..6a445cd9fd64fdefe03648dc4113eec184af1cbe 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1407,6 +1407,13 @@ static inline bool is_id_reg(u32 id) sys_reg_CRm(id) < 8); } +static inline bool is_aa32_id_reg(u32 id) +{ + return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 && + sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 && + sys_reg_CRm(id) <= 3); +} + static unsigned int id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { @@ -3723,6 +3730,65 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return write_demux_regids(uindices); } +#define KVM_ARM_FEATURE_ID_RANGE_INDEX(r) \ + KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(r), \ + sys_reg_Op1(r), \ + sys_reg_CRn(r), \ + sys_reg_CRm(r), \ + sys_reg_Op2(r)) + +static bool is_feature_id_reg(u32 encoding) +{ + return (sys_reg_Op0(encoding) == 3 && + (sys_reg_Op1(encoding) < 2 || sys_reg_Op1(encoding) == 3) && + sys_reg_CRn(encoding) == 0 && + sys_reg_CRm(encoding) <= 7); +} + +int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range) +{ + const void *zero_page = page_to_virt(ZERO_PAGE(0)); + u64 __user *masks = (u64 __user *)range->addr; + + /* Only feature id range is supported, reserved[13] must be zero. */ + if (range->range || + memcmp(range->reserved, zero_page, sizeof(range->reserved))) + return -EINVAL; + + /* Wipe the whole thing first */ + if (clear_user(masks, KVM_ARM_FEATURE_ID_RANGE_SIZE * sizeof(__u64))) + return -EFAULT; + + for (int i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { + const struct sys_reg_desc *reg = &sys_reg_descs[i]; + u32 encoding = reg_to_encoding(reg); + u64 val; + + if (!is_feature_id_reg(encoding) || !reg->set_user) + continue; + + /* + * For ID registers, we return the writable mask. Other feature + * registers return a full 64bit mask. That's not necessary + * compliant with a given revision of the architecture, but the + * RES0/RES1 definitions allow us to do that. + */ + if (is_id_reg(encoding)) { + if (!reg->val || + (is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0())) + continue; + val = reg->val; + } else { + val = ~0UL; + } + + if (put_user(val, (masks + KVM_ARM_FEATURE_ID_RANGE_INDEX(encoding)))) + return -EFAULT; + } + + return 0; +} + int __init kvm_sys_reg_table_init(void) { struct sys_reg_params params; diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index d28d70fea012b6cc7b36ae82ee66296bc12645d2..51901b42871fb0cba3261f595f7ae8cf93de551a 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -312,7 +312,6 @@ void kvm_flush_tlb_all(void); void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa); int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write); -#define KVM_ARCH_WANT_MMU_NOTIFIER void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig index e899d96f4da61c923cf879d2a535defdf0061b93..283871e15e41903f34bca545747e8811365f0121 100644 --- a/arch/loongarch/kvm/Kconfig +++ b/arch/loongarch/kvm/Kconfig @@ -30,10 +30,10 @@ config KVM select HAVE_KVM_MSI select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_GENERIC_HARDWARE_ENABLING + select KVM_GENERIC_MMU_NOTIFIER select KVM_MMIO select KVM_XFER_TO_GUEST_WORK select SCHED_INFO - select MMU_NOTIFIER select PREEMPT_NOTIFIERS select KVM_VFIO help diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index d54b2388dfee21e42f8cbe57e3ba873783cc50d6..7fa477a28ee152ad2727d61c10aeec203607b09f 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -698,7 +698,7 @@ static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot, * * There are several ways to safely use this helper: * - * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -879,7 +879,7 @@ static int kvm_map_page(struct kvm_vcpu *vcpu, unsigned long gpa, bool write) /* Check if an invalidation has taken place since we got pfn */ spin_lock(&kvm->mmu_lock); - if (mmu_invalidate_retry_hva(kvm, mmu_seq, hva)) { + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { /* * This can happen when mappings are changed asynchronously, but * also synchronously if a COW is triggered by diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 54a85f1d4f2c8d8822f25974c000d2d7aafc86c0..179f320cc2313b985d3a6d03c6437c85aa69a7dc 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -810,8 +810,6 @@ int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn); pgd_t *kvm_pgd_alloc(void); void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu); -#define KVM_ARCH_WANT_MMU_NOTIFIER - /* Emulation */ enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause); int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out); diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index a8cdba75f98dde949c9cd86ef073027cc49bfad3..c04987d2ed2e3e3c9b56015eaa0be8bd08ed62f2 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -25,7 +25,7 @@ config KVM select HAVE_KVM_EVENTFD select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_MMIO - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER select INTERVAL_TREE select KVM_GENERIC_HARDWARE_ENABLING help diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 14ee0dece8538be1c4c743ebf59c8d808a178b22..4b5c3f2acf78f555c5705bb8dd49766df3c41889 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -62,8 +62,6 @@ #include -#define KVM_ARCH_WANT_MMU_NOTIFIER - #define HPTEG_CACHE_NUM (1 << 15) #define HPTEG_HASH_BITS_PTE 13 #define HPTEG_HASH_BITS_PTE_LONG 12 diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 902611954200df90c43e2b2516ce242006dba09c..b33358ee642440adba4836e3257107af4bf11b06 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -42,7 +42,7 @@ config KVM_BOOK3S_64_HANDLER config KVM_BOOK3S_PR_POSSIBLE bool select KVM_MMIO - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER config KVM_BOOK3S_HV_POSSIBLE bool @@ -85,7 +85,7 @@ config KVM_BOOK3S_64_HV tristate "KVM for POWER7 and later using hypervisor mode in host" depends on KVM_BOOK3S_64 && PPC_POWERNV select KVM_BOOK3S_HV_POSSIBLE - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER select CMA help Support running unmodified book3s_64 guest kernels in @@ -194,7 +194,7 @@ config KVM_E500V2 depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500 guest kernels in virtual machines on E500v2 host processors. @@ -211,7 +211,7 @@ config KVM_E500MC select KVM select KVM_MMIO select KVM_BOOKE_HV - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500MC/E5500/E6500 guest kernels in virtual machines on E500MC/E5500/E6500 host processors. diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 924689fa5efa15dc2c7979ece686308cc2933a56..724cfbebb39e555c5bf9546f4049ab2cd630f74a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -6106,7 +6106,7 @@ static int kvmhv_svm_off(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); int bkt; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6cef200c2404df0a8f9807b5c1decbd3a1bf1efc..d867b209cc959f106199d9d032b6f6c87a5a6710 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -632,13 +632,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif case KVM_CAP_SYNC_MMU: -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - r = hv_enabled; -#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER) + BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER)); r = 1; -#else - r = 0; -#endif break; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_HTAB_FD: diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 459e61ad7d2b68b22403caf3b21eed3e4e159b7f..efad04b22b6a1de511e12846ee7841ce9be14390 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -250,8 +250,6 @@ struct kvm_vcpu_arch { static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -#define KVM_ARCH_WANT_MMU_NOTIFIER - #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index dfc237d7875b53bb2f3e7e716c1b85af8b335458..ae2e05f050ece1eff54c496f8bdf13d168bd5cfa 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -30,7 +30,7 @@ config KVM select KVM_GENERIC_HARDWARE_ENABLING select KVM_MMIO select KVM_XFER_TO_GUEST_WORK - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER select PREEMPT_NOTIFIERS help Support hosting virtualized guest machines. diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 5a83da703e8766199f3123f0c915f8743a5e1847..6a1f36df6a181761d805d99279539874095f096a 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -28,5 +28,7 @@ obj-y += net/ obj-$(CONFIG_KEXEC_FILE) += purgatory/ +obj-y += virt/svm/ + # for cleaning subdir- += boot tools diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 01d61f0609ab4d59694aa296a7a62ceded05d29f..efdb98787ae9eb442b4d0d6ab67312ff73356aa4 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -307,6 +307,10 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) if (result != ES_OK) goto finish; + result = vc_check_opcode_bytes(&ctxt, exit_code); + if (result != ES_OK) + goto finish; + switch (exit_code) { case SVM_EXIT_RDTSC: case SVM_EXIT_RDTSCP: @@ -330,26 +334,6 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } -static void enforce_vmpl0(void) -{ - u64 attrs; - int err; - - /* - * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically - * higher) privilege level. Here, clear the VMPL1 permission mask of the - * GHCB page. If the guest is not running at VMPL0, this will fail. - * - * If the guest is running at VMPL0, it will succeed. Even if that operation - * modifies permission bits, it is still ok to do so currently because Linux - * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks - * changing is a don't-care. - */ - attrs = 1; - if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); -} - /* * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need * guest side implementation for proper functioning of the guest. If any @@ -368,7 +352,7 @@ static void enforce_vmpl0(void) MSR_AMD64_SNP_VMPL_SSS | \ MSR_AMD64_SNP_SECURE_TSC | \ MSR_AMD64_SNP_VMGEXIT_PARAM | \ - MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_VMSA_REG_PROT | \ MSR_AMD64_SNP_RESERVED_BIT13 | \ MSR_AMD64_SNP_RESERVED_BIT15 | \ MSR_AMD64_SNP_RESERVED_MASK) @@ -408,6 +392,85 @@ void snp_check_features(void) } } +/* Search for Confidential Computing blob in the EFI config table. */ +static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp) +{ + unsigned long cfg_table_pa; + unsigned int cfg_table_len; + int ret; + + ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len); + if (ret) + return NULL; + + return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa, + cfg_table_len, + EFI_CC_BLOB_GUID); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the boot kernel + * by firmware/bootloader in the following ways: + * + * - via an entry in the EFI config table + * - via a setup_data structure, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + cc_info = find_cc_blob_efi(bp); + if (cc_info) + goto found_cc_info; + + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + return cc_info; +} + +/* + * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks + * will verify the SNP CPUID/MSR bits. + */ +static bool early_snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + /* + * If a SNP-specific Confidential Computing blob is present, then + * firmware/bootloader have indicated SNP support. Verifying this + * involves CPUID checks which will be more reliable if the SNP + * CPUID table is used. See comments over snp_setup_cpuid_table() for + * more details. + */ + setup_cpuid_table(cc_info); + + /* + * Pass run-time kernel a pointer to CC info via boot_params so EFI + * config table doesn't need to be searched again during early startup + * phase. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + /* * sev_check_cpu_support - Check for SEV support in the CPU capabilities * @@ -458,7 +521,7 @@ void sev_enable(struct boot_params *bp) bp->cc_blob_address = 0; /* - * Do an initial SEV capability check before snp_init() which + * Do an initial SEV capability check before early_snp_init() which * loads the CPUID page and the same checks afterwards are done * without the hypervisor and are trustworthy. * @@ -473,7 +536,7 @@ void sev_enable(struct boot_params *bp) * Setup/preliminary detection of SNP. This will be sanity-checked * against CPUID/MSR values later. */ - snp = snp_init(bp); + snp = early_snp_init(bp); /* Now repeat the checks with the SNP CPUID table. */ @@ -504,7 +567,20 @@ void sev_enable(struct boot_params *bp) if (!(get_hv_features() & GHCB_HV_FT_SNP)) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); - enforce_vmpl0(); + /* + * Enforce running at VMPL0. + * + * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically + * higher) privilege level. Here, clear the VMPL1 permission mask of the + * GHCB page. If the guest is not running at VMPL0, this will fail. + * + * If the guest is running at VMPL0, it will succeed. Even if that operation + * modifies permission bits, it is still ok to do so currently because Linux + * SNP guests running at VMPL0 only run at VMPL0, so VMPL1 or higher + * permission mask changes are a don't-care. + */ + if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); } if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) @@ -530,85 +606,6 @@ u64 sev_get_status(void) return m.q; } -/* Search for Confidential Computing blob in the EFI config table. */ -static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp) -{ - unsigned long cfg_table_pa; - unsigned int cfg_table_len; - int ret; - - ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len); - if (ret) - return NULL; - - return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa, - cfg_table_len, - EFI_CC_BLOB_GUID); -} - -/* - * Initial set up of SNP relies on information provided by the - * Confidential Computing blob, which can be passed to the boot kernel - * by firmware/bootloader in the following ways: - * - * - via an entry in the EFI config table - * - via a setup_data structure, as defined by the Linux Boot Protocol - * - * Scan for the blob in that order. - */ -static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) -{ - struct cc_blob_sev_info *cc_info; - - cc_info = find_cc_blob_efi(bp); - if (cc_info) - goto found_cc_info; - - cc_info = find_cc_blob_setup_data(bp); - if (!cc_info) - return NULL; - -found_cc_info: - if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); - - return cc_info; -} - -/* - * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks - * will verify the SNP CPUID/MSR bits. - */ -bool snp_init(struct boot_params *bp) -{ - struct cc_blob_sev_info *cc_info; - - if (!bp) - return false; - - cc_info = find_cc_blob(bp); - if (!cc_info) - return false; - - /* - * If a SNP-specific Confidential Computing blob is present, then - * firmware/bootloader have indicated SNP support. Verifying this - * involves CPUID checks which will be more reliable if the SNP - * CPUID table is used. See comments over snp_setup_cpuid_table() for - * more details. - */ - setup_cpuid_table(cc_info); - - /* - * Pass run-time kernel a pointer to CC info via boot_params so EFI - * config table doesn't need to be searched again during early startup - * phase. - */ - bp->cc_blob_address = (u32)(unsigned long)cc_info; - - return true; -} - void sev_prep_identity_maps(unsigned long top_level_pgt) { /* diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index ddd4efdc79d66875bb8b17387aaea883c3b621cc..b31ef2424d194b96d07b601d4eeac4b23d637d27 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -20,6 +20,11 @@ enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; u64 cc_mask __ro_after_init; +static struct cc_attr_flags { + __u64 host_sev_snp : 1, + __resv : 63; +} cc_flags; + static bool noinstr intel_cc_platform_has(enum cc_attr attr) { switch (attr) { @@ -93,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_HOST_SEV_SNP: + return cc_flags.host_sev_snp; + default: return false; } @@ -153,6 +161,50 @@ u64 cc_mkdec(u64 val) } EXPORT_SYMBOL_GPL(cc_mkdec); +static void amd_cc_platform_clear(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 0; + break; + default: + break; + } +} + +void cc_platform_clear(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_clear(attr); + break; + default: + break; + } +} + +static void amd_cc_platform_set(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 1; + break; + default: + break; + } +} + +void cc_platform_set(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_set(attr); + break; + default: + break; + } +} + __init void cc_random_init(void) { /* diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 3cbae4c5f3902319cf71f5d4f2c56d0bdc847482..19e9e844c3e1ecc1ce7962f083804e76dda7720e 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -746,12 +746,19 @@ CONFIG_HAVE_KVM_MSI=y CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT=y CONFIG_KVM_VFIO=y CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT=y +CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY=y CONFIG_KVM_COMPAT=y CONFIG_HAVE_KVM_IRQ_BYPASS=y CONFIG_HAVE_KVM_NO_POLL=y CONFIG_KVM_XFER_TO_GUEST_WORK=y CONFIG_HAVE_KVM_PM_NOTIFIER=y CONFIG_KVM_GENERIC_HARDWARE_ENABLING=y +CONFIG_KVM_GENERIC_MMU_NOTIFIER=y +CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES=y +CONFIG_KVM_PRIVATE_MEM=y +CONFIG_KVM_GENERIC_PRIVATE_MEM=y +CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE=y +CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE=y CONFIG_VIRTUALIZATION=y CONFIG_KVM=m CONFIG_KVM_INTEL=m @@ -759,6 +766,7 @@ CONFIG_X86_SGX_KVM=y CONFIG_KVM_AMD=m CONFIG_KVM_AMD_SEV=y CONFIG_KVM_SMM=y +CONFIG_KVM_HYPERV=y # CONFIG_KVM_XEN is not set CONFIG_KVM_EXTERNAL_WRITE_TRACKING=y CONFIG_ARCH_VCPU_STAT=y @@ -7197,6 +7205,7 @@ CONFIG_VIRT_DRIVERS=y CONFIG_VMGENID=y # CONFIG_VBOXGUEST is not set # CONFIG_NITRO_ENCLAVES is not set +CONFIG_TSM_REPORTS=m CONFIG_EFI_SECRET=m CONFIG_SEV_GUEST=m # CONFIG_TDX_GUEST_DRIVER is not set @@ -8285,6 +8294,7 @@ CONFIG_OVERLAY_FS=m # CONFIG_OVERLAY_FS_XINO_AUTO is not set # CONFIG_OVERLAY_FS_METACOPY is not set # CONFIG_OVERLAY_FS_DEBUG is not set + # # Caches # @@ -8349,9 +8359,9 @@ CONFIG_TMPFS_XATTR=y # CONFIG_TMPFS_INODE64 is not set # CONFIG_TMPFS_QUOTA is not set CONFIG_HUGETLBFS=y +# CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON is not set CONFIG_HUGETLB_PAGE=y CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP=y -# CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON is not set CONFIG_HUGETLB_ALLOC_LIMIT=y CONFIG_ARCH_HAS_GIGANTIC_PAGE=y CONFIG_CONFIGFS_FS=y @@ -8437,6 +8447,7 @@ CONFIG_NFS_USE_KERNEL_DNS=y CONFIG_NFS_DEBUG=y # CONFIG_NFS_DISABLE_UDP_SUPPORT is not set # CONFIG_NFS_V4_2_READ_PLUS is not set +CONFIG_ENFS=m CONFIG_NFSD=m # CONFIG_NFSD_V2 is not set CONFIG_NFSD_V3_ACL=y @@ -8453,8 +8464,6 @@ CONFIG_LOCKD_V4=y CONFIG_NFS_ACL_SUPPORT=m CONFIG_NFS_COMMON=y CONFIG_NFS_V4_2_SSC_HELPER=y -CONFIG_ENFS=m -CONFIG_SUNRPC_ENFS=m CONFIG_SUNRPC=m CONFIG_SUNRPC_GSS=m CONFIG_SUNRPC_BACKCHANNEL=y @@ -8464,6 +8473,7 @@ CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA1=y # CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA2 is not set CONFIG_SUNRPC_DEBUG=y CONFIG_SUNRPC_XPRT_RDMA=m +CONFIG_SUNRPC_ENFS=y CONFIG_CEPH_FS=m # CONFIG_CEPH_FSCACHE is not set CONFIG_CEPH_FS_POSIX_ACL=y @@ -9182,6 +9192,10 @@ CONFIG_DEBUG_INFO_COMPRESSED_NONE=y # CONFIG_DEBUG_INFO_COMPRESSED_ZLIB is not set # CONFIG_DEBUG_INFO_SPLIT is not set CONFIG_DEBUG_INFO_BTF=y +CONFIG_PAHOLE_HAS_SPLIT_BTF=y +CONFIG_PAHOLE_HAS_LANG_EXCLUDE=y +CONFIG_DEBUG_INFO_BTF_MODULES=y +# CONFIG_MODULE_ALLOW_BTF_MISMATCH is not set # CONFIG_GDB_SCRIPTS is not set CONFIG_FRAME_WARN=2048 CONFIG_STRIP_ASM_SYMS=y diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1688c2c667fb2cc7c9af853b9f52ab27f1ad92a1..1754fc73bc1731323a00f6ce1ef91fbb05997ee9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -465,11 +465,15 @@ #define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ +#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* HYGON 3rd CSV */ -#define X86_FEATURE_CSV3 (19*32 + 30) /* HYGON 3rd CSV */ +#define X86_FEATURE_CSV3 (19*32+31) /* HYGON 3rd CSV */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 3d4c7338361b516b9e5e048918790b7a8a3e809b..c7f91989a16fb0649fb066a7a1151b08bcbfd526 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -117,6 +117,12 @@ #define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31)) #endif +#ifdef CONFIG_KVM_AMD_SEV +#define DISABLE_SEV_SNP 0 +#else +#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -141,7 +147,7 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 (DISABLE_IBT) -#define DISABLED_MASK19 0 +#define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 #define DISABLED_MASK21 0 #define DISABLED_MASK22 0 diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index e8f58ddd06d97fbce6ef1f701f9f91766ef2847d..2e74a7f0e93575c3aa4180dc9ad4a9728f07700d 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -17,6 +17,7 @@ extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); extern void e820__range_add (u64 start, u64 size, enum e820_type type); extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type); +extern u64 e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern void e820__print_table(char *who); extern int e820__update_table(struct e820_table *table); diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index c7c3074f383b7491fdc9b4468d7dd4bed445551f..270124ea86add3953249372b79a1b27b42db193a 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -180,6 +180,9 @@ extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfe extern u64 xstate_get_guest_group_perm(void); +extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); + + /* KVM specific functions */ extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 2fd52b65deac104c97cd5b4dc30360633b7568aa..3be2451e7bc857683ab4aa9481d010c9a79eb137 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -10,6 +10,7 @@ extern int force_iommu, no_iommu; extern int iommu_detected; extern int iommu_merge; extern int panic_on_overflow; +extern bool amd_iommu_snp_en; #ifdef CONFIG_SWIOTLB extern bool x86_swiotlb_enable; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index fd830075fc50438cddfe8272df7b0f77438af500..b58afab82ee5a240f0440477c89fba40d2e6ceea 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -120,6 +120,7 @@ KVM_X86_OP(enter_smm) KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) #endif +KVM_X86_OP_OPTIONAL(dev_get_attr) KVM_X86_OP_OPTIONAL(mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) @@ -127,7 +128,7 @@ KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) -KVM_X86_OP(can_emulate_instruction) +KVM_X86_OP(check_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) KVM_X86_OP_OPTIONAL(migrate_timers) @@ -141,6 +142,10 @@ KVM_X86_OP_OPTIONAL(control_pre_system_reset) KVM_X86_OP_OPTIONAL(control_post_system_reset) KVM_X86_OP_OPTIONAL(get_hygon_coco_extension) KVM_X86_OP_OPTIONAL(enable_hygon_coco_extension) +KVM_X86_OP_OPTIONAL(alloc_apic_backing_page) +KVM_X86_OP_OPTIONAL_RET0(gmem_prepare) +KVM_X86_OP_OPTIONAL_RET0(private_max_mapping_level) +KVM_X86_OP_OPTIONAL(gmem_invalidate) #undef KVM_X86_OP #undef KVM_X86_OP_OPTIONAL diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 48b48408a8f2a8db9b8039b3b9a24ca756dd965a..7564906e1c96738cdb161178494e59b5cb01a8e9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -113,6 +113,8 @@ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HV_TLB_FLUSH \ KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \ + KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -203,6 +205,7 @@ enum exit_fastpath_completion { EXIT_FASTPATH_NONE, EXIT_FASTPATH_REENTER_GUEST, EXIT_FASTPATH_EXIT_HANDLED, + EXIT_FASTPATH_EXIT_USERSPACE, }; typedef enum exit_fastpath_completion fastpath_t; @@ -246,28 +249,31 @@ enum x86_intercept_stage; KVM_GUESTDBG_INJECT_DB | \ KVM_GUESTDBG_BLOCKIRQ) +#define PFERR_PRESENT_MASK BIT(0) +#define PFERR_WRITE_MASK BIT(1) +#define PFERR_USER_MASK BIT(2) +#define PFERR_RSVD_MASK BIT(3) +#define PFERR_FETCH_MASK BIT(4) +#define PFERR_PK_MASK BIT(5) +#define PFERR_SGX_MASK BIT(15) +#define PFERR_GUEST_RMP_MASK BIT_ULL(31) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(32) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(33) +#define PFERR_GUEST_ENC_MASK BIT_ULL(34) +#define PFERR_GUEST_SIZEM_MASK BIT_ULL(35) +#define PFERR_GUEST_VMPL_MASK BIT_ULL(36) -#define PFERR_PRESENT_BIT 0 -#define PFERR_WRITE_BIT 1 -#define PFERR_USER_BIT 2 -#define PFERR_RSVD_BIT 3 -#define PFERR_FETCH_BIT 4 -#define PFERR_PK_BIT 5 -#define PFERR_SGX_BIT 15 -#define PFERR_GUEST_FINAL_BIT 32 -#define PFERR_GUEST_PAGE_BIT 33 -#define PFERR_IMPLICIT_ACCESS_BIT 48 - -#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT) -#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT) -#define PFERR_USER_MASK BIT(PFERR_USER_BIT) -#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT) -#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT) -#define PFERR_PK_MASK BIT(PFERR_PK_BIT) -#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT) -#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT) -#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT) -#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT) +/* + * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks + * when emulating instructions that triggers implicit access. + */ +#define PFERR_IMPLICIT_ACCESS BIT_ULL(48) +/* + * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred + * when the guest was accessing private memory. + */ +#define PFERR_PRIVATE_ACCESS BIT_ULL(49) +#define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ PFERR_WRITE_MASK | \ @@ -680,6 +686,7 @@ struct kvm_hypervisor_cpuid { u32 limit; }; +#ifdef CONFIG_KVM_XEN /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; @@ -702,6 +709,7 @@ struct kvm_vcpu_xen { struct timer_list poll_timer; struct kvm_hypervisor_cpuid cpuid; }; +#endif struct kvm_queued_exception { bool pending; @@ -929,10 +937,13 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; +#ifdef CONFIG_KVM_HYPERV bool hyperv_enabled; struct kvm_vcpu_hv *hyperv; +#endif +#ifdef CONFIG_KVM_XEN struct kvm_vcpu_xen xen; - +#endif cpumask_var_t wbinvd_dirty_mask; unsigned long last_retry_eip; @@ -1086,6 +1097,7 @@ enum hv_tsc_page_status { HV_TSC_PAGE_BROKEN, }; +#ifdef CONFIG_KVM_HYPERV /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; @@ -1119,6 +1131,7 @@ struct kvm_hv { struct hv_partition_assist_pg *hv_pa_pg; struct kvm_hv_syndbg hv_syndbg; }; +#endif struct msr_bitmap_range { u32 flags; @@ -1127,6 +1140,7 @@ struct msr_bitmap_range { unsigned long *bitmap; }; +#ifdef CONFIG_KVM_XEN /* Xen emulation context */ struct kvm_xen { struct mutex xen_lock; @@ -1138,6 +1152,7 @@ struct kvm_xen { struct idr evtchn_ports; unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; }; +#endif enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, @@ -1251,6 +1266,10 @@ struct kvm_arch { unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; u8 mmu_valid_gen; + u8 vm_type; + bool has_private_mem; + bool has_protected_state; + bool pre_fault_allowed; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; @@ -1338,8 +1357,13 @@ struct kvm_arch { /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; +#ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; +#endif + +#ifdef CONFIG_KVM_XEN struct kvm_xen xen; +#endif bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; @@ -1746,6 +1770,7 @@ struct kvm_x86_ops { void (*enable_smi_window)(struct kvm_vcpu *vcpu); #endif + int (*dev_get_attr)(u32 group, u64 attr, u64 *val); int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); @@ -1755,8 +1780,8 @@ struct kvm_x86_ops { int (*get_msr_feature)(struct kvm_msr_entry *entry); - bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len); + int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); @@ -1782,6 +1807,10 @@ struct kvm_x86_ops { int (*control_post_system_reset)(struct kvm *kvm); int (*get_hygon_coco_extension)(struct kvm *kvm); int (*enable_hygon_coco_extension)(struct kvm *kvm, u32 arg); + void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); + int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); + void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); + int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn); }; struct kvm_x86_nested_ops { @@ -1819,6 +1848,7 @@ struct kvm_arch_async_pf { gfn_t gfn; unsigned long cr3; bool direct_map; + u64 error_code; }; extern u32 __read_mostly kvm_nr_uret_msrs; @@ -1869,6 +1899,9 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot); + void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -1887,6 +1920,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -2107,6 +2141,15 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); + +#ifdef CONFIG_KVM_PRIVATE_MEM +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) +#else +#define kvm_arch_has_private_mem(kvm) false +#endif + +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) + static inline u16 kvm_read_ldt(void) { u16 ldt; @@ -2154,16 +2197,15 @@ enum { #define HF_SMM_MASK (1 << 1) #define HF_SMM_INSIDE_NMI_MASK (1 << 2) -# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE -# define KVM_ADDRESS_SPACE_NUM 2 +# define KVM_MAX_NR_ADDRESS_SPACES 2 +/* SMM is currently unsupported for guests with private memory. */ +# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) #else # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) #endif -#define KVM_ARCH_WANT_MMU_NOTIFIER - int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 9816db501ea462c2108b1414ce3a7f67da6f968e..0291a14674412acde0ebd1330d4fd96c09686281 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -20,8 +20,10 @@ struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); +void __init mem_encrypt_setup_arch(void); #else static inline void mem_encrypt_init(void) { } +static inline void __init mem_encrypt_setup_arch(void) { } #endif #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -44,7 +46,6 @@ void __init sme_map_bootdata(char *real_mode_data); void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sev_setup_arch(void); void sme_encrypt_kernel(struct boot_params *bp); void sme_enable(struct boot_params *bp); @@ -79,7 +80,6 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { } static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sev_setup_arch(void) { } static inline void sme_encrypt_kernel(struct boot_params *bp) { } static inline void sme_enable(struct boot_params *bp) { } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9860a3cb69d099a71a6bc041dd409c580495112e..fee89c98df719c09b3d74743732130ea5add2089 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -617,36 +617,51 @@ #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) - -#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_AMD64_RMP_CFG 0xc0010136 +#define MSR_AMD64_SEG_RMP_ENABLED_BIT 0 +#define MSR_AMD64_SEG_RMP_ENABLED BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT) +#define MSR_AMD64_RMP_SEGMENT_SHIFT(x) (((x) & GENMASK_ULL(13, 8)) >> 8) /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 @@ -734,8 +749,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index b463fcbd4b9070b005a7b187f0b62c2046163a18..8647cc05e2f497d7eebbaec1bbd1eacc21ee2c8f 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -54,8 +54,18 @@ (((unsigned long)fn) << 32)) /* AP Reset Hold */ -#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 -#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 +#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS 12 +#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK GENMASK_ULL(51, 0) + +/* Preferred GHCB GPA Request */ +#define GHCB_MSR_PREF_GPA_REQ 0x010 +#define GHCB_MSR_GPA_VALUE_POS 12 +#define GHCB_MSR_GPA_VALUE_MASK GENMASK_ULL(51, 0) + +#define GHCB_MSR_PREF_GPA_RESP 0x011 +#define GHCB_MSR_PREF_GPA_NONE 0xfffffffffffff /* GHCB GPA Register */ #define GHCB_MSR_REG_GPA_REQ 0x012 @@ -91,14 +101,22 @@ enum psc_op { /* GHCBData[11:0] */ \ GHCB_MSR_PSC_REQ) +#define GHCB_MSR_PSC_REQ_TO_GFN(msr) (((msr) & GENMASK_ULL(51, 12)) >> 12) +#define GHCB_MSR_PSC_REQ_TO_OP(msr) (((msr) & GENMASK_ULL(55, 52)) >> 52) + #define GHCB_MSR_PSC_RESP 0x015 #define GHCB_MSR_PSC_RESP_VAL(val) \ /* GHCBData[63:32] */ \ (((u64)(val) & GENMASK_ULL(63, 32)) >> 32) +/* Set highest bit as a generic error response */ +#define GHCB_MSR_PSC_RESP_ERROR (BIT_ULL(63) | GHCB_MSR_PSC_RESP) + /* GHCB Hypervisor Feature Request/Response */ #define GHCB_MSR_HV_FT_REQ 0x080 #define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_POS 12 +#define GHCB_MSR_HV_FT_MASK GENMASK_ULL(51, 0) #define GHCB_MSR_HV_FT_RESP_VAL(v) \ /* GHCBData[63:12] */ \ (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) @@ -111,8 +129,19 @@ enum psc_op { * The VMGEXIT_PSC_MAX_ENTRY determines the size of the PSC structure, which * is a local stack variable in set_pages_state(). Do not increase this value * without evaluating the impact to stack usage. + * + * Use VMGEXIT_PSC_MAX_COUNT in cases where the actual GHCB-defined max value + * is needed, such as when processing GHCB requests on the hypervisor side. */ #define VMGEXIT_PSC_MAX_ENTRY 64 +#define VMGEXIT_PSC_MAX_COUNT 253 + +#define VMGEXIT_PSC_ERROR_GENERIC (0x100UL << 32) +#define VMGEXIT_PSC_ERROR_INVALID_HDR ((1UL << 32) | 1) +#define VMGEXIT_PSC_ERROR_INVALID_ENTRY ((1UL << 32) | 2) + +#define VMGEXIT_PSC_OP_PRIVATE 1 +#define VMGEXIT_PSC_OP_SHARED 2 struct psc_hdr { u16 cur_entry; diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 75a5388d40681e8690192224ba3e83a803484649..58bc5ee152a6f24b0f1287e4816eec13b062b0c5 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -87,9 +87,26 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs); /* Software defined (when rFlags.CF = 1) */ #define PVALIDATE_FAIL_NOUPDATE 255 +/* RMUPDATE detected 4K page and 2MB page overlap. */ +#define RMPUPDATE_FAIL_OVERLAP 4 + +/* PSMASH failed due to concurrent access by another CPU */ +#define PSMASH_FAIL_INUSE 3 + /* RMP page size */ #define RMP_PG_SIZE_4K 0 #define RMP_PG_SIZE_2M 1 +#define RMP_TO_PG_LEVEL(level) (((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M) +#define PG_LEVEL_TO_RMP(level) (((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M) + +struct rmp_state { + u64 gpa; + u8 assigned; + u8 pagesize; + u8 immutable; + u8 rsvd; + u32 asid; +} __packed; #define RMPADJUST_VMSA_PAGE_BIT BIT(16) @@ -101,6 +118,54 @@ struct snp_req_data { unsigned int data_npages; }; +#define MAX_AUTHTAG_LEN 32 + +/* See SNP spec SNP_GUEST_REQUEST section for the structure */ +enum msg_type { + SNP_MSG_TYPE_INVALID = 0, + SNP_MSG_CPUID_REQ, + SNP_MSG_CPUID_RSP, + SNP_MSG_KEY_REQ, + SNP_MSG_KEY_RSP, + SNP_MSG_REPORT_REQ, + SNP_MSG_REPORT_RSP, + SNP_MSG_EXPORT_REQ, + SNP_MSG_EXPORT_RSP, + SNP_MSG_IMPORT_REQ, + SNP_MSG_IMPORT_RSP, + SNP_MSG_ABSORB_REQ, + SNP_MSG_ABSORB_RSP, + SNP_MSG_VMRK_REQ, + SNP_MSG_VMRK_RSP, + + SNP_MSG_TYPE_MAX +}; + +enum aead_algo { + SNP_AEAD_INVALID, + SNP_AEAD_AES_256_GCM, +}; + +struct snp_guest_msg_hdr { + u8 authtag[MAX_AUTHTAG_LEN]; + u64 msg_seqno; + u8 rsvd1[8]; + u8 algo; + u8 hdr_version; + u16 hdr_sz; + u8 msg_type; + u8 msg_version; + u16 msg_sz; + u32 rsvd2; + u8 msg_vmpck; + u8 rsvd3[35]; +} __packed; + +struct snp_guest_msg { + struct snp_guest_msg_hdr hdr; + u8 payload[4000]; +} __packed; + struct sev_guest_platform_data { u64 secrets_gpa; }; @@ -125,7 +190,7 @@ struct secrets_os_area { #define VMPCK_KEY_LEN 32 /* See the SNP spec version 0.9 for secrets page format */ -struct snp_secrets_page_layout { +struct snp_secrets_page { u32 version; u32 imien : 1, rsvd1 : 31; @@ -213,6 +278,7 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); u64 sev_get_status(void); +void sev_show_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } @@ -241,6 +307,35 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } +static inline void sev_show_status(void) { } +#endif + +#ifdef CONFIG_KVM_AMD_SEV +bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); +void snp_dump_hva_rmpentry(unsigned long address); +int psmash(u64 pfn); +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable); +int rmp_make_shared(u64 pfn, enum pg_level level); +void snp_leak_pages(u64 pfn, unsigned int npages); +void kdump_sev_callback(void); +void snp_fixup_e820_tables(void); +#else +static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } +static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } +static inline void snp_dump_hva_rmpentry(unsigned long address) {} +static inline int psmash(u64 pfn) { return -ENODEV; } +static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, + bool immutable) +{ + return -ENODEV; +} +static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } +static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} +static inline void kdump_sev_callback(void) { } +static inline void snp_fixup_e820_tables(void) {} #endif #endif diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 3ac0ffc4f3e202b18fab10ee6ecacb6b1ea11a91..85ae25d82ef61f8f60cba3dd743c73adfba792e0 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -289,7 +289,10 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_ #define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) -#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5) +#define SVM_SEV_FEAT_SNP_ACTIVE BIT(0) +#define SVM_SEV_FEAT_RESTRICTED_INJECTION BIT(3) +#define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4) +#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5) struct vmcb_seg { u16 selector; diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h index afa524325e558d281e9be0feb1b91cd3a7a488bc..a23a7b707b64e17077a83eae8ae23e4f3cd24a5b 100644 --- a/arch/x86/include/asm/trap_pf.h +++ b/arch/x86/include/asm/trap_pf.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_TRAP_PF_H #define _ASM_X86_TRAP_PF_H +#include + /* * Page fault error code bits: * @@ -13,16 +15,18 @@ * bit 5 == 1: protection keys block access * bit 6 == 1: shadow stack access fault * bit 15 == 1: SGX MMU page-fault + * bit 31 == 1: fault was due to RMP violation */ enum x86_pf_error_code { - X86_PF_PROT = 1 << 0, - X86_PF_WRITE = 1 << 1, - X86_PF_USER = 1 << 2, - X86_PF_RSVD = 1 << 3, - X86_PF_INSTR = 1 << 4, - X86_PF_PK = 1 << 5, - X86_PF_SHSTK = 1 << 6, - X86_PF_SGX = 1 << 15, + X86_PF_PROT = BIT(0), + X86_PF_WRITE = BIT(1), + X86_PF_USER = BIT(2), + X86_PF_RSVD = BIT(3), + X86_PF_INSTR = BIT(4), + X86_PF_PK = BIT(5), + X86_PF_SHSTK = BIT(6), + X86_PF_SGX = BIT(15), + X86_PF_RMP = BIT(31), }; #endif /* _ASM_X86_TRAP_PF_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 1a6a1f98794967d260e2898b0dbb62f830d45664..71c7081071754e4079dc9744c744f39f9fd9d1c3 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -457,8 +457,13 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 -/* attributes for system fd (group 0) */ -#define KVM_X86_XCOMP_GUEST_SUPP 0 +/* vendor-independent attributes for system fd (group 0) */ +#define KVM_X86_GRP_SYSTEM 0 +# define KVM_X86_XCOMP_GUEST_SUPP 0 + +/* vendor-specific groups and attributes for system fd */ +#define KVM_X86_GRP_SEV 1 +# define KVM_X86_SEV_VMSA_FEATURES 0 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -529,6 +534,349 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#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; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + struct { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + /* Second time is the charm; improved versions of the above ioctls. */ + KVM_SEV_INIT2, + + /* SNP-specific commands */ + KVM_SEV_SNP_LAUNCH_START = 100, + KVM_SEV_SNP_LAUNCH_UPDATE, + KVM_SEV_SNP_LAUNCH_FINISH, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_init { + __u64 vmsa_features; + __u32 flags; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_snp_launch_start { + __u64 policy; + __u8 gosvw[16]; + __u16 flags; + __u8 pad0[6]; + __u64 pad1[4]; +}; + +/* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 +#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 +#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 +#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5 +#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6 + +struct kvm_sev_snp_launch_update { + __u64 gfn_start; + __u64 uaddr; + __u64 len; + __u8 type; + __u8 pad0; + __u16 flags; + __u32 pad1; + __u64 pad2[4]; +}; + +#define KVM_SEV_SNP_ID_BLOCK_SIZE 96 +#define KVM_SEV_SNP_ID_AUTH_SIZE 4096 +#define KVM_SEV_SNP_FINISH_DATA_SIZE 32 + +struct kvm_sev_snp_launch_finish { + __u64 id_block_uaddr; + __u64 id_auth_uaddr; + __u8 id_block_en; + __u8 auth_key_en; + __u8 vcek_disabled; + __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE]; + __u8 pad0[3]; + __u16 flags; + __u64 pad1[4]; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -562,4 +910,10 @@ struct kvm_pmu_event_filter { /* x86-specific KVM_EXIT_HYPERCALL flags. */ #define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_X86_DEFAULT_VM 0 +#define KVM_X86_SW_PROTECTED_VM 1 +#define KVM_X86_SEV_VM 2 +#define KVM_X86_SEV_ES_VM 3 +#define KVM_X86_SNP_VM 4 + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 251e23fc1a7fdbcc44820d7e54d724c5e4c4125d..5ec679834b7a41c2c57b17dedf6e7f8c9a6044bd 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_X86_64 # include @@ -472,6 +473,28 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c) #endif } +static void bsp_determine_snp(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM + cc_vendor = CC_VENDOR_AMD; + + if (cpu_has(c, X86_FEATURE_SEV_SNP)) { + /* + * RMP table entry format is not architectural and is defined by the + * per-processor PPR. Restrict SNP support on the known CPU models + * for which the RMP table entry format is currently defined for. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + c->x86 >= 0x19 && snp_probe_rmptable_info()) { + cc_platform_set(CC_ATTR_HOST_SEV_SNP); + } else { + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + } + } +#endif +} + static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -590,6 +613,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) break; } + bsp_determine_snp(c); return; warn: @@ -608,8 +632,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) * SME feature (set in scattered.c). * If the kernel has not enabled SME via any means then * don't advertise the SME feature. - * For SEV: If BIOS has not enabled SEV then don't advertise the - * SEV and SEV_ES feature (set in scattered.c). + * For SEV: If BIOS has not enabled SEV then don't advertise SEV and + * any additional functionality based on it. * * In all cases, since support for SME and SEV requires long mode, * don't advertise the feature under CONFIG_X86_32. @@ -644,6 +668,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) clear_sev: setup_clear_cpu_cap(X86_FEATURE_SEV); setup_clear_cpu_cap(X86_FEATURE_SEV_ES); + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); } } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8bb0d2bd8f2c17f4ad04404aa4e2883f03108747..47e5b5eec312b8ac276ed582a632aedc8dfaef5b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1390,8 +1390,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) /* * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature * flag and protect from vendor-specific bugs via the whitelist. + * + * Don't use AutoIBRS when SNP is enabled because it degrades host + * userspace indirect branch performance. */ - if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || + (cpu_has(c, X86_FEATURE_AUTOIBRS) && + !cpu_feature_enabled(X86_FEATURE_SEV_SNP))) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 2d6aa5d2e3d77ec49fd725e180fffe1df3c5987d..cb6372df1614e533b9e7f938f1389f4587b53a3b 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -108,6 +108,9 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return; + rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c92d88680dbf16ba25826fb7d26b48bcfb72c695..64ae3a1e5c309795841e0a23a2cf260b7d93ca16 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -40,6 +40,7 @@ #include #include #include +#include /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -59,6 +60,8 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_emergency_stop_pt(); + kdump_sev_callback(); + disable_local_APIC(); } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b66f540de054a72403dbe3b4a837d6b1e280610d..8e346410dd3627d417ca02532dd573a2caf70701 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -28,18 +28,13 @@ * the first 128 E820 memory entries in boot_params.e820_table and the remaining * (if any) entries of the SETUP_E820_EXT nodes. We use this to: * - * - inform the user about the firmware's notion of memory layout - * via /sys/firmware/memmap - * * - the hibernation code uses it to generate a kernel-independent CRC32 * checksum of the physical memory layout of a system. * * - 'e820_table_kexec': a slightly modified (by the kernel) firmware version * passed to us by the bootloader - the major difference between - * e820_table_firmware[] and this one is that, the latter marks the setup_data - * list created by the EFI boot stub as reserved, so that kexec can reuse the - * setup_data information in the second kernel. Besides, e820_table_kexec[] - * might also be modified by the kexec itself to fake a mptable. + * e820_table_firmware[] and this one is that e820_table_kexec[] + * might be modified by the kexec itself to fake an mptable. * We use this to: * * - kexec, which is a bootloader in disguise, uses the original E820 @@ -47,6 +42,11 @@ * can have a restricted E820 map while the kexec()-ed kexec-kernel * can have access to full memory - etc. * + * Export the memory layout via /sys/firmware/memmap. kexec-tools uses + * the entries to create an E820 table for the kexec kernel. + * + * kexec_file_load in-kernel code uses the table for the kexec kernel. + * * - 'e820_table': this is the main E820 table that is massaged by the * low level x86 platform code, or modified by boot parameters, before * passed on to higher level MM layers. @@ -532,9 +532,10 @@ u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum return __e820__range_update(e820_table, start, size, old_type, new_type); } -static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) +u64 __init e820__range_update_table(struct e820_table *t, u64 start, u64 size, + enum e820_type old_type, enum e820_type new_type) { - return __e820__range_update(e820_table_kexec, start, size, old_type, new_type); + return __e820__range_update(t, start, size, old_type, new_type); } /* Remove a range of memory from the E820 table: */ @@ -806,7 +807,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) addr = memblock_phys_alloc(size, align); if (addr) { - e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_kexec, addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); e820__update_table_kexec(); } @@ -1016,17 +1017,6 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - /* - * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by - * kexec and do not need to be reserved. - */ - if (data->type != SETUP_EFI && - data->type != SETUP_IMA && - data->type != SETUP_RNG_SEED) - e820__range_update_kexec(pa_data, - sizeof(*data) + data->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT) { len += data->len; early_memunmap(data, sizeof(*data)); @@ -1038,12 +1028,9 @@ void __init e820__reserve_setup_data(void) indirect = (struct setup_indirect *)data->data; - if (indirect->type != SETUP_INDIRECT) { + if (indirect->type != SETUP_INDIRECT) e820__range_update(indirect->addr, indirect->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(indirect->addr, indirect->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - } } pa_data = pa_next; @@ -1051,7 +1038,6 @@ void __init e820__reserve_setup_data(void) } e820__update_table(e820_table); - e820__update_table(e820_table_kexec); pr_info("extended physical RAM map:\n"); e820__print_table("reserve setup_data"); @@ -1192,9 +1178,9 @@ void __init e820__reserve_resources(void) res++; } - /* Expose the bootloader-provided memory layout to the sysfs. */ - for (i = 0; i < e820_table_firmware->nr_entries; i++) { - struct e820_entry *entry = e820_table_firmware->entries + i; + /* Expose the kexec e820 table to the sysfs. */ + for (i = 0; i < e820_table_kexec->nr_entries; i++) { + struct e820_entry *entry = e820_table_kexec->entries + i; firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry)); } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c1ebfe4b4a8db733b5600c06e60e932dd8fb9709..31521e00682a17c76d8ad2c16df4e18cfbed5c8d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1003,6 +1003,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) return __raw_xsave_addr(xsave, xfeature_nr); } +EXPORT_SYMBOL_GPL(get_xsave_addr); #ifdef CONFIG_ARCH_HAS_PKEYS diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 544224611e23c56dccff92b210c7f94004afa274..f2611145f3caa31a6334e4dd37786085c9cd3e88 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -54,8 +54,6 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); -extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); - static inline u64 xfeatures_mask_supervisor(void) { return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bd33c4f7c125c89080da3dc296fc889ad8831b34..feb3bc061c165e6c16973b44ce851c857227db06 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,8 +1119,8 @@ void __init setup_arch(char **cmdline_p) * Needs to run after memblock setup because it needs the physical * memory size. */ - sev_setup_arch(); cc_random_init(); + mem_encrypt_setup_arch(); efi_fake_memmap(); efi_find_mirror(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index acbec4de3ec31ace1761ecb48138e5056a4e0501..7f0147017026a2c94fa680e24cce1d08e7cf9972 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -10,11 +10,15 @@ */ #ifndef __BOOT_COMPRESSED -#define error(v) pr_err(v) -#define has_cpuflag(f) boot_cpu_has(f) +#define error(v) pr_err(v) +#define has_cpuflag(f) boot_cpu_has(f) +#define sev_printk(fmt, ...) printk(fmt, ##__VA_ARGS__) +#define sev_printk_rtl(fmt, ...) printk_ratelimited(fmt, ##__VA_ARGS__) #else #undef WARN #define WARN(condition, format...) (!!(condition)) +#define sev_printk(fmt, ...) +#define sev_printk_rtl(fmt, ...) #endif /* I/O parameters for CPUID-related helpers */ @@ -570,6 +574,7 @@ void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); + u16 opcode = *(unsigned short *)regs->ip; struct cpuid_leaf leaf; int ret; @@ -577,6 +582,10 @@ void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) if (exit_code != SVM_EXIT_CPUID) goto fail; + /* Is it really a CPUID insn? */ + if (opcode != 0xa20f) + goto fail; + leaf.fn = fn; leaf.subfn = subfn; @@ -1167,3 +1176,94 @@ static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) out: return ret; } + +static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, + unsigned long exit_code) +{ + unsigned int opcode = (unsigned int)ctxt->insn.opcode.value; + u8 modrm = ctxt->insn.modrm.value; + + switch (exit_code) { + + case SVM_EXIT_IOIO: + case SVM_EXIT_NPF: + /* handled separately */ + return ES_OK; + + case SVM_EXIT_CPUID: + if (opcode == 0xa20f) + return ES_OK; + break; + + case SVM_EXIT_INVD: + if (opcode == 0x080f) + return ES_OK; + break; + + case SVM_EXIT_MONITOR: + /* MONITOR and MONITORX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa)) + return ES_OK; + break; + + case SVM_EXIT_MWAIT: + /* MWAIT and MWAITX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb)) + return ES_OK; + break; + + case SVM_EXIT_MSR: + /* RDMSR */ + if (opcode == 0x320f || + /* WRMSR */ + opcode == 0x300f) + return ES_OK; + break; + + case SVM_EXIT_RDPMC: + if (opcode == 0x330f) + return ES_OK; + break; + + case SVM_EXIT_RDTSC: + if (opcode == 0x310f) + return ES_OK; + break; + + case SVM_EXIT_RDTSCP: + if (opcode == 0x010f && modrm == 0xf9) + return ES_OK; + break; + + case SVM_EXIT_READ_DR7: + if (opcode == 0x210f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_VMMCALL: + if (opcode == 0x010f && modrm == 0xd9) + return ES_OK; + + break; + + case SVM_EXIT_WRITE_DR7: + if (opcode == 0x230f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_WBINVD: + if (opcode == 0x90f) + return ES_OK; + break; + + default: + break; + } + + sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n", + opcode, exit_code, ctxt->regs->ip); + + return ES_UNSUPPORTED; +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 614335589d527f3e42b28b76e1babd5de6e54c92..1f918fb46c7081250a404bbc4aa7f53707d16693 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -62,6 +62,25 @@ #define AP_INIT_CR0_DEFAULT 0x60000010 #define AP_INIT_MXCSR_DEFAULT 0x1f80 +static const char * const sev_status_feat_names[] = { + [MSR_AMD64_SEV_ENABLED_BIT] = "SEV", + [MSR_AMD64_SEV_ES_ENABLED_BIT] = "SEV-ES", + [MSR_AMD64_SEV_SNP_ENABLED_BIT] = "SEV-SNP", + [MSR_AMD64_SNP_VTOM_BIT] = "vTom", + [MSR_AMD64_SNP_REFLECT_VC_BIT] = "ReflectVC", + [MSR_AMD64_SNP_RESTRICTED_INJ_BIT] = "RI", + [MSR_AMD64_SNP_ALT_INJ_BIT] = "AI", + [MSR_AMD64_SNP_DEBUG_SWAP_BIT] = "DebugSwap", + [MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT] = "NoHostIBS", + [MSR_AMD64_SNP_BTB_ISOLATION_BIT] = "BTBIsol", + [MSR_AMD64_SNP_VMPL_SSS_BIT] = "VmplSSS", + [MSR_AMD64_SNP_SECURE_TSC_BIT] = "SecureTSC", + [MSR_AMD64_SNP_VMGEXIT_PARAM_BIT] = "VMGExitParam", + [MSR_AMD64_SNP_IBS_VIRT_BIT] = "IBSVirt", + [MSR_AMD64_SNP_VMSA_REG_PROT_BIT] = "VMSARegProt", + [MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt", +}; + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -630,7 +649,7 @@ static u64 __init get_secrets_page(void) static u64 __init get_snp_jump_table_addr(void) { - struct snp_secrets_page_layout *layout; + struct snp_secrets_page *secrets; void __iomem *mem; u64 pa, addr; @@ -644,9 +663,9 @@ static u64 __init get_snp_jump_table_addr(void) return 0; } - layout = (__force struct snp_secrets_page_layout *)mem; + secrets = (__force struct snp_secrets_page *)mem; - addr = layout->os_area.ap_jump_table_pa; + addr = secrets->os_area.ap_jump_table_pa; iounmap(mem); return addr; @@ -1741,7 +1760,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) { - enum es_result result; + enum es_result result = vc_check_opcode_bytes(ctxt, exit_code); + + if (result != ES_OK) + return result; switch (exit_code) { case SVM_EXIT_READ_DR7: @@ -2274,3 +2296,19 @@ static int __init snp_init_platform_device(void) return 0; } device_initcall(snp_init_platform_device); + +void sev_show_status(void) +{ + int i; + + pr_info("Status: "); + for (i = 0; i < MSR_AMD64_SNP_RESV_BIT; i++) { + if (sev_status & BIT_ULL(i)) { + if (!sev_status_feat_names[i]) + continue; + + pr_cont("%s ", sev_status_feat_names[i]); + } + } + pr_cont("\n"); +} diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index d926a24c9632720c22d6ca89b957a29a3a817195..e103c1c247ba92e6d6b494427b6639b4ae9c5ddf 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -24,7 +24,7 @@ config KVM depends on HIGH_RES_TIMERS depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS - select MMU_NOTIFIER + select KVM_GENERIC_MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_PFNCACHE select HAVE_KVM_IRQFD @@ -49,6 +49,7 @@ config KVM select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM select KVM_GENERIC_HARDWARE_ENABLING + select KVM_GENERIC_PRE_FAULT_MEMORY help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent @@ -77,6 +78,18 @@ config KVM_WERROR If in doubt, say "N". +config KVM_SW_PROTECTED_VM + bool "Enable support for KVM software-protected VMs" + depends on EXPERT + depends on X86_64 + select KVM_GENERIC_PRIVATE_MEM + help + Enable support for KVM software-protected VMs. Currently "protected" + means the VM can be backed with memory provided by + KVM_CREATE_GUEST_MEMFD. + + If unsure, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL @@ -114,9 +127,15 @@ config KVM_AMD_SEV bool "AMD Secure Encrypted Virtualization (SEV) support" depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) + select ARCH_HAS_CC_PLATFORM + select KVM_GENERIC_PRIVATE_MEM + select HAVE_KVM_ARCH_GMEM_PREPARE + select HAVE_KVM_ARCH_GMEM_INVALIDATE help - Provides support for launching Encrypted VMs (SEV) and Encrypted VMs - with Encrypted State (SEV-ES) on AMD processors. + Provides support for launching encrypted VMs which use Secure + Encrypted Virtualization (SEV), Secure Encrypted Virtualization with + Encrypted State (SEV-ES), and Secure Encrypted Virtualization with + Secure Nested Paging (SEV-SNP) technologies on AMD processors. config KVM_SMM bool "System Management Mode emulation" @@ -129,6 +148,20 @@ config KVM_SMM If unsure, say Y. +config KVM_HYPERV + bool "Support for Microsoft Hyper-V emulation" + depends on KVM + default y + help + Provides KVM support for emulating Microsoft Hyper-V. This allows KVM + to expose a subset of the paravirtualized interfaces defined in the + Hyper-V Hypervisor Top-Level Functional Specification (TLFS): + https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs + These interfaces are required for the correct and performant functioning + of Windows and Hyper-V guests on KVM. + + If unsure, say "Y". + config KVM_XEN bool "Support for Xen hypercall interface" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 97d585ec0baddab7337804707cbdaae26ff90ab2..a3e7c1bc7b809ba406c8feb08cb3f28196a60789 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -11,29 +11,28 @@ include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ + debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o -ifdef CONFIG_HYPERV -kvm-y += kvm_onhyperv.o -endif - kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o +kvm-$(CONFIG_KVM_HYPERV) += hyperv.o kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/hyperv.o vmx/nested.o vmx/posted_intr.o + vmx/nested.o vmx/posted_intr.o + kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o +kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o -ifdef CONFIG_HYPERV -kvm-intel-y += vmx/vmx_onhyperv.o -endif +kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o -kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ - svm/sev.o svm/hyperv.o +kvm-amd-$(CONFIG_KVM_AMD_SEV) += svm/sev.o +kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o ifdef CONFIG_HYPERV +kvm-y += kvm_onhyperv.o +kvm-intel-y += vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm_onhyperv.o endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 8291df97109e6a3596f7796633c11503211923b3..20b52e69eb93a02c11ce9ff2107747fba16a8ef8 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -335,11 +335,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) { +#ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, KVM_CPUID_INDEX_NOT_SIGNIFICANT); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; +#else + return false; +#endif } static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) @@ -455,11 +459,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, return 0; } +#ifdef CONFIG_KVM_HYPERV if (kvm_cpuid_has_hyperv(e2, nent)) { r = kvm_hv_vcpu_init(vcpu); if (r) return r; } +#endif r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -470,7 +476,9 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_nent = nent; vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); +#ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); +#endif kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -775,7 +783,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); kvm_cpu_cap_mask(CPUID_8000_001F_EAX, - 0 /* SME */ | F(SEV) | 0 /* VM_PAGE_FLUSH */ | F(SEV_ES) | + 0 /* SME */ | 0 /* SEV */ | 0 /* VM_PAGE_FLUSH */ | 0 /* SEV_ES */ | F(SME_COHERENT)); kvm_cpu_cap_mask(CPUID_8000_0021_EAX, diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index ee8c4c3496edd050d651f0f1d1863f2c569b040e..42026b3f3ff34ddd7088dcbd3c88e022c720f38e 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) mutex_lock(&kvm->slots_lock); write_lock(&kvm->mmu_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { int bkt; slots = __kvm_memslots(kvm, i); diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index f83b8db72b118cabc6278195d2f6fb99048af34a..a643e11c894d8e3f09370d35bdd5c351b176d28d 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -24,6 +24,8 @@ #include #include "x86.h" +#ifdef CONFIG_KVM_HYPERV + /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -237,5 +239,61 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) } int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock) {} +static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {} +static inline void kvm_hv_init_vm(struct kvm *kvm) {} +static inline void kvm_hv_destroy_vm(struct kvm *kvm) {} +static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {} +static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + return HV_STATUS_ACCESS_DENIED; +} +static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {} +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {} +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {} +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {} +#endif /* CONFIG_KVM_HYPERV */ -#endif +#endif /* __ARCH_X86_KVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index b2c397dd2bc6620c54f045e7d503a326fedf81b4..ad9ca8a60144c773dd2ab7de10af67a436f790cb 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; +#ifdef CONFIG_KVM_XEN if (kvm_xen_has_interrupt(v)) return v->kvm->arch.xen.upcall_vector; +#endif if (irqchip_split(v->kvm)) { int vector = v->arch.pending_external_vector; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 16d076a1b91acc65aed41eed3536bad1744a8a1f..68f3f6c26046936601cb0e0a9383c8946ccad8ce 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } - +#ifdef CONFIG_KVM_HYPERV static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); } +#endif int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, int r; switch (e->type) { +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: return kvm_hv_set_sint(e, kvm, irq_source_id, level, line_status); +#endif case KVM_IRQ_ROUTING_MSI: if (kvm_msi_route_invalid(kvm, e)) @@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm, if (kvm_msi_route_invalid(kvm, e)) return -EINVAL; break; +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#endif #ifdef CONFIG_KVM_XEN case KVM_IRQ_ROUTING_XEN_EVTCHN: return kvm_xen_setup_evtchn(kvm, e, ue); @@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, void kvm_arch_irq_routing_update(struct kvm *kvm) { +#ifdef CONFIG_KVM_HYPERV kvm_hv_irq_routing_update(kvm); +#endif } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 66c7f2367bb34eecaa6a222644ee0ceb67956ffe..9a45d9d696efdbe67bef1897fbee68a8cdd12d8a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2862,7 +2862,10 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) vcpu->arch.apic = apic; - apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (kvm_x86_ops.alloc_apic_backing_page) + apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu); + else + apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index ade33a54306d2bbb431c84d913519c57b624e660..44e35527bae796ba4588a7b959ed5fe79e01f518 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -128,6 +128,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) + kvm_mmu_free_obsolete_roots(vcpu); + if (likely(vcpu->arch.mmu->root.hpa != INVALID_PAGE)) return 0; @@ -215,7 +218,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, */ u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; - int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1; + int index = (pfec | (not_smap ? PFERR_RSVD_MASK : 0)) >> 1; u32 errcode = PFERR_PRESENT_MASK; bool fault; @@ -236,8 +239,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ - offset = (pfec & ~1) + - ((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT)); + offset = (pfec & ~1) | ((pte_access & PT_USER_MASK) ? PFERR_RSVD_MASK : 0); pkru_bits &= mmu->pkru_mask >> offset; errcode |= -pkru_bits & PFERR_PK_MASK; @@ -247,8 +249,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } -void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); - int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); int kvm_mmu_post_init_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4431158309ae44b3634deb1b6a4ed45b62483323..a4494bafa32d6d31e6c9e87ebcf9cc69f06e2840 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -795,16 +795,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } +/* + * The most significant bit in disallow_lpage tracks whether or not memory + * attributes are mixed, i.e. not identical for all gfns at the current level. + * The lower order bits are used to refcount other cases where a hugepage is + * disallowed, e.g. if KVM has shadow a page table at the gfn. + */ +#define KVM_LPAGE_MIXED_FLAG BIT(31) + static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; - int i; + int old, i; for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); + + old = linfo->disallow_lpage; linfo->disallow_lpage += count; - WARN_ON_ONCE(linfo->disallow_lpage < 0); + WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG); } } @@ -3056,7 +3066,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3137,9 +3147,9 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3151,6 +3161,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, break; } + if (is_private) + return max_level; + if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; @@ -3158,6 +3171,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3178,8 +3201,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level); + fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -3318,7 +3342,7 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, return RET_PF_CONTINUE; } -static bool page_fault_can_be_fast(struct kvm_page_fault *fault) +static bool page_fault_can_be_fast(struct kvm *kvm, struct kvm_page_fault *fault) { /* * Page faults with reserved bits set, i.e. faults on MMIO SPTEs, only @@ -3329,6 +3353,26 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault) if (fault->rsvd) return false; + /* + * For hardware-protected VMs, certain conditions like attempting to + * perform a write to a page which is not in the state that the guest + * expects it to be in can result in a nested/extended #PF. In this + * case, the below code might misconstrue this situation as being the + * result of a write-protected access, and treat it as a spurious case + * rather than taking any action to satisfy the real source of the #PF + * such as generating a KVM_EXIT_MEMORY_FAULT. This can lead to the + * guest spinning on a #PF indefinitely, so don't attempt the fast path + * in this case. + * + * Note that the kvm_mem_is_private() check might race with an + * attribute update, but this will either result in the guest spinning + * on RET_PF_SPURIOUS until the update completes, or an actual spurious + * case might go down the slow path. Either case will resolve itself. + */ + if (kvm->arch.has_private_mem && + fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) + return false; + /* * #PF can be fast if: * @@ -3429,7 +3473,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) u64 *sptep = NULL; uint retry_count = 0; - if (!page_fault_can_be_fast(fault)) + if (!page_fault_can_be_fast(vcpu->kvm, fault)) return ret; walk_shadow_page_lockless_begin(vcpu); @@ -3731,7 +3775,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) kvm_page_track_write_tracking_enabled(kvm)) goto out_success; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(slot, bkt, slots) { /* @@ -4218,24 +4262,28 @@ static u32 alloc_apf_token(struct kvm_vcpu *vcpu) return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; } -static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - gfn_t gfn) +static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { struct kvm_arch_async_pf arch; arch.token = alloc_apf_token(vcpu); - arch.gfn = gfn; + arch.gfn = fault->gfn; + arch.error_code = fault->error_code; arch.direct_map = vcpu->arch.mmu->root_role.direct; arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); - return kvm_setup_async_pf(vcpu, cr2_or_gpa, - kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, fault->addr, + kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch); } void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { int r; + if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS)) + return; + if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) || work->wakeup_all) return; @@ -4248,7 +4296,84 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; - kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); + r = kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, + true, NULL, NULL); + + /* + * Account fixed page faults, otherwise they'll never be counted, but + * ignore stats for all other return times. Page-ready "faults" aren't + * truly spurious and never trigger emulation + */ + if (r == RET_PF_FIXED) + vcpu->stat.pf_fixed++; +} + +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, + u8 max_level, int gmem_order) +{ + u8 req_max_level; + + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + max_level = min(kvm_max_level_for_order(gmem_order), max_level); + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + req_max_level = static_call(kvm_x86_private_max_mapping_level)(kvm, pfn); + if (req_max_level) + max_level = min(max_level, req_max_level); + + return max_level; +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn, + fault->max_level, max_order); + + return RET_PF_CONTINUE; } static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -4283,6 +4408,9 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -4296,7 +4424,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return RET_PF_RETRY; - } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) { + } else if (kvm_arch_setup_async_pf(vcpu, fault)) { return RET_PF_RETRY; } } @@ -4317,9 +4445,24 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, { int ret; + /* + * Note that the mmu_invalidate_seq also serves to detect a concurrent + * change in attributes. is_page_fault_stale() will detect an + * invalidation relate to fault->fn and resume the guest without + * installing a mapping in the page tables. + */ fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); + /* + * Now that we have a snapshot of mmu_invalidate_seq we can check for a + * private vs. shared mismatch. + */ + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + ret = __kvm_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; @@ -4358,7 +4501,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); + mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -4425,6 +4568,9 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, return -EFAULT; #endif + /* Ensure the above sanity check also covers KVM-defined flags. */ + BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK)); + vcpu->arch.l1tf_flush_l1d = true; if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); @@ -4518,6 +4664,84 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return direct_page_fault(vcpu, fault); } +static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, + u8 *level) +{ + int r; + + /* + * Restrict to TDP page fault, since that's the only case where the MMU + * is indexed by GPA. + */ + if (vcpu->arch.mmu->page_fault != kvm_tdp_page_fault) + return -EOPNOTSUPP; + + do { + if (signal_pending(current)) + return -EINTR; + cond_resched(); + r = kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level); + } while (r == RET_PF_RETRY); + + if (r < 0) + return r; + + switch (r) { + case RET_PF_FIXED: + case RET_PF_SPURIOUS: + return 0; + + case RET_PF_EMULATE: + return -ENOENT; + + case RET_PF_RETRY: + case RET_PF_CONTINUE: + case RET_PF_INVALID: + default: + WARN_ONCE(1, "could not fix page fault during prefault"); + return -EIO; + } +} + +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + u64 error_code = PFERR_GUEST_FINAL_MASK; + u8 level = PG_LEVEL_4K; + u64 end; + int r; + + if (!vcpu->kvm->arch.pre_fault_allowed) + return -EOPNOTSUPP; + + /* + * reload is efficient when called repeatedly, so we can do it on + * every iteration. + */ + r = kvm_mmu_reload(vcpu); + if (r) + return r; + + if (kvm_arch_has_private_mem(vcpu->kvm) && + kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa))) + error_code |= PFERR_PRIVATE_ACCESS; + + /* + * Shadow paging uses GVA for kvm page fault, so restrict to + * two-dimensional paging. + */ + r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level); + if (r < 0) + return r; + + /* + * If the mapping that covers range->gpa can use a huge page, it + * may start below it or end after range->gpa + range->size. + */ + end = (range->gpa & KVM_HPAGE_MASK(level)) + KVM_HPAGE_SIZE(level); + return min(range->size, end - range->gpa); +} + static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; @@ -5555,6 +5779,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu); __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } +EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots); static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) @@ -5710,20 +5935,23 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->root_role.direct; - /* - * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP - * checks when emulating instructions that triggers implicit access. - * WARN if hardware generates a fault with an error code that collides - * with the KVM-defined value. Clear the flag and continue on, i.e. - * don't terminate the VM, as KVM can't possibly be relying on a flag - * that KVM doesn't know about. - */ - if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS)) - error_code &= ~PFERR_IMPLICIT_ACCESS; - if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; + /* + * Except for reserved faults (emulated MMIO is shared-only), set the + * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's + * current attributes, which are the source of truth for such VMs. Note, + * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't + * currently supported nested virtualization (among many other things) + * for software-protected VMs. + */ + if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && + !(error_code & PFERR_RSVD_MASK) && + vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM && + kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa))) + error_code |= PFERR_PRIVATE_ACCESS; + r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); @@ -5732,15 +5960,22 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err } if (r == RET_PF_INVALID) { - r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), false, - &emulation_type); + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false, + &emulation_type, NULL); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; } if (r < 0) return r; + + if (r == RET_PF_FIXED) + vcpu->stat.pf_fixed++; + else if (r == RET_PF_EMULATE) + vcpu->stat.pf_emulate++; + else if (r == RET_PF_SPURIOUS) + vcpu->stat.pf_spurious++; + if (r != RET_PF_EMULATE) return 1; @@ -6224,7 +6459,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (!kvm_memslots_have_rmaps(kvm)) return flush; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { @@ -6256,7 +6491,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); - kvm_mmu_invalidate_begin(kvm, 0, -1ul); + kvm_mmu_invalidate_begin(kvm); + + kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); @@ -6266,7 +6503,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); - kvm_mmu_invalidate_end(kvm, 0, -1ul); + kvm_mmu_invalidate_end(kvm); write_unlock(&kvm->mmu_lock); } @@ -6612,6 +6849,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, return need_tlb_flush; } +EXPORT_SYMBOL_GPL(kvm_zap_gfn_range); static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -6719,7 +6957,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * modifier prior to checking for a wrap of the MMIO generation so * that a wrap in any address space is detected. */ - gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1); /* * The very rare case: if the MMIO generation number has wrapped, @@ -7170,3 +7408,207 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) if (kvm->arch.nx_huge_page_recovery_thread) kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + struct kvm_memory_slot *slot = range->slot; + int level; + + /* + * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only + * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM + * can simply ignore such slots. But if userspace is making memory + * PRIVATE, then KVM must prevent the guest from accessing the memory + * as shared. And if userspace is making memory SHARED and this point + * is reached, then at least one page within the range was previously + * PRIVATE, i.e. the slot's possible hugepage ranges are changing. + * Zapping SPTEs in this case ensures KVM will reassess whether or not + * a hugepage can be used for affected ranges. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + if (WARN_ON_ONCE(range->end <= range->start)) + return false; + + /* + * If the head and tail pages of the range currently allow a hugepage, + * i.e. reside fully in the slot and don't have mixed attributes, then + * add each corresponding hugepage range to the ongoing invalidation, + * e.g. to prevent KVM from creating a hugepage in response to a fault + * for a gfn whose attributes aren't changing. Note, only the range + * of gfns whose attributes are being modified needs to be explicitly + * unmapped, as that will unmap any existing hugepages. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t start = gfn_round_for_level(range->start, level); + gfn_t end = gfn_round_for_level(range->end - 1, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + + if ((start != range->start || start + nr_pages > range->end) && + start >= slot->base_gfn && + start + nr_pages <= slot->base_gfn + slot->npages && + !hugepage_test_mixed(slot, start, level)) + kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages); + + if (end == start) + continue; + + if ((end + nr_pages) > range->end && + (end + nr_pages) <= (slot->base_gfn + slot->npages) && + !hugepage_test_mixed(slot, end, level)) + kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages); + } + + /* Unmap the old attribute page. */ + if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) + range->attr_filter = KVM_FILTER_SHARED; + else + range->attr_filter = KVM_FILTER_PRIVATE; + + return kvm_unmap_gfn_range(kvm, range); +} + + + +static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, int level, unsigned long attrs) +{ + const unsigned long start = gfn; + const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); + + if (level == PG_LEVEL_2M) + return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs); + + for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { + if (hugepage_test_mixed(slot, gfn, level - 1) || + attrs != kvm_get_memory_attributes(kvm, gfn)) + return false; + } + return true; +} + +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + unsigned long attrs = range->arg.attributes; + struct kvm_memory_slot *slot = range->slot; + int level; + + lockdep_assert_held_write(&kvm->mmu_lock); + lockdep_assert_held(&kvm->slots_lock); + + /* + * Calculate which ranges can be mapped with hugepages even if the slot + * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over + * a range that has PRIVATE GFNs, and conversely converting a range to + * SHARED may now allow hugepages. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + /* + * The sequence matters here: upper levels consume the result of lower + * level's scanning. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn = gfn_round_for_level(range->start, level); + + /* Process the head page if it straddles the range. */ + if (gfn != range->start || gfn + nr_pages > range->end) { + /* + * Skip mixed tracking if the aligned gfn isn't covered + * by the memslot, KVM can't use a hugepage due to the + * misaligned address regardless of memory attributes. + */ + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + gfn += nr_pages; + } + + /* + * Pages entirely covered by the range are guaranteed to have + * only the attributes which were just set. + */ + for ( ; gfn + nr_pages <= range->end; gfn += nr_pages) + hugepage_clear_mixed(slot, gfn, level); + + /* + * Process the last tail page if it straddles the range and is + * contained by the memslot. Like the head page, KVM can't + * create a hugepage if the slot size is misaligned. + */ + if (gfn < range->end && + (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } + return false; +} + +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + int level; + + if (!kvm_arch_has_private_mem(kvm)) + return; + + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + /* + * Don't bother tracking mixed attributes for pages that can't + * be huge due to alignment, i.e. process only pages that are + * entirely contained by the memslot. + */ + gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level); + gfn_t start = gfn_round_for_level(slot->base_gfn, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn; + + if (start < slot->base_gfn) + start += nr_pages; + + /* + * Unlike setting attributes, every potential hugepage needs to + * be manually checked as the attributes may already be mixed. + */ + for (gfn = start; gfn < end; gfn += nr_pages) { + unsigned long attrs = kvm_get_memory_attributes(kvm, gfn); + + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } +} +#endif diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 68f8564d85a99b6577a41a03a4dc33284bea1073..0ead070b9cc8eaf1ceda02940d10218b49125c42 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -190,7 +190,7 @@ static inline bool is_nx_huge_page_enabled(struct kvm *kvm) struct kvm_page_fault { /* arguments to kvm_mmu_do_page_fault. */ const gpa_t addr; - const u32 error_code; + const u64 error_code; const bool prefetch; /* Derived from error_code. */ @@ -202,6 +202,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /* @@ -279,7 +280,8 @@ enum { }; static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - u32 err, bool prefetch, int *emulation_type) + u64 err, bool prefetch, + int *emulation_type, u8 *level) { struct kvm_page_fault fault = { .addr = cr2_or_gpa, @@ -297,6 +299,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, + .is_private = err & PFERR_PRIVATE_ACCESS, }; int r; @@ -320,20 +323,9 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (fault.write_fault_to_shadow_pgtable && emulation_type) *emulation_type |= EMULTYPE_WRITE_PF_TO_SP; + if (level) + *level = fault.goal_level; - /* - * Similar to above, prefetch faults aren't truly spurious, and the - * async #PF path doesn't do emulation. Do count faults that are fixed - * by the async #PF handler though, otherwise they'll never be counted. - */ - if (r == RET_PF_FIXED) - vcpu->stat.pf_fixed++; - else if (prefetch) - ; - else if (r == RET_PF_EMULATE) - vcpu->stat.pf_emulate++; - else if (r == RET_PF_SPURIOUS) - vcpu->stat.pf_spurious++; return r; } diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index ae86820cef697a8c3ba224ab5c5eb7b8eea0afe1..195d98bc8de85e4e377bc084ea3d14e1bab126ce 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -260,7 +260,7 @@ TRACE_EVENT( TP_STRUCT__entry( __field(int, vcpu_id) __field(gpa_t, cr2_or_gpa) - __field(u32, error_code) + __field(u64, error_code) __field(u64 *, sptep) __field(u64, old_spte) __field(u64, new_spte) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 4b74ea91f4e6bb6ea3cea52be67eaeed049c506e..65fd245a9953ce5b1096f6041033c718daf1e899 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1199,6 +1199,12 @@ bool avic_hardware_setup(void) return false; } + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) { + pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n"); + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { pr_info("AVIC enabled\n"); } else if (force_avic) { diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h index 02f4784b5d446b2f0a86604b589c85981b13e5d1..d3f8bfc05832ee0a2249cbaeed22f081027a9a2e 100644 --- a/arch/x86/kvm/svm/hyperv.h +++ b/arch/x86/kvm/svm/hyperv.h @@ -11,6 +11,7 @@ #include "../hyperv.h" #include "svm.h" +#ifdef CONFIG_KVM_HYPERV static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) } void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {} +static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_KVM_HYPERV */ #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index f5850f12bf80d25bcc910fc91112606e3f0f974c..4ea01ab7ef61e5e6fc19d1145e7d6ba265266d6a 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1183,7 +1183,7 @@ int svm_allocate_nested(struct vcpu_svm *svm) if (svm->nested.initialized) return 0; - vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb02_page = snp_safe_alloc_page(&svm->vcpu); if (!vmcb02_page) return -ENOMEM; svm->nested.vmcb02.ptr = page_address(vmcb02_page); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 63611572ae100368f2062545032975039cbc59ae..37483bc8c2b6d6aa83ad6ec58f751b98411ffd55 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -19,12 +19,15 @@ #include #include #include +#include #include #include #include +#include #include #include +#include #include "mmu.h" #include "x86.h" @@ -35,22 +38,12 @@ #include "csv.h" -#ifndef CONFIG_KVM_AMD_SEV -/* - * When this config is not defined, SEV feature is not supported and APIs in - * this file are not used but this file still gets compiled into the KVM AMD - * module. - * - * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum - * misc_res_type {} defined in linux/misc_cgroup.h. - * - * Below macros allow compilation to succeed. - */ -#define MISC_CG_RES_SEV MISC_CG_RES_TYPES -#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES -#endif +#define GHCB_VERSION_MAX 2ULL +#define GHCB_VERSION_DEFAULT 2ULL +#define GHCB_VERSION_MIN 1ULL + +#define GHCB_HV_FT_SUPPORTED (GHCB_HV_FT_SNP | GHCB_HV_FT_SNP_AP_CREATION) -#ifdef CONFIG_KVM_AMD_SEV /* enable/disable SEV support */ static bool sev_enabled = true; module_param_named(sev, sev_enabled, bool, 0444); @@ -59,14 +52,35 @@ module_param_named(sev, sev_enabled, bool, 0444); static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); +/* enable/disable SEV-SNP support */ +static bool sev_snp_enabled = true; +module_param_named(sev_snp, sev_snp_enabled, bool, 0444); + /* enable/disable SEV-ES DebugSwap support */ -static bool sev_es_debug_swap_enabled = false; +static bool sev_es_debug_swap_enabled = true; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); -#else -#define sev_enabled false -#define sev_es_enabled false -#define sev_es_debug_swap_enabled false -#endif /* CONFIG_KVM_AMD_SEV */ +static u64 sev_supported_vmsa_features; + +#define AP_RESET_HOLD_NONE 0 +#define AP_RESET_HOLD_NAE_EVENT 1 +#define AP_RESET_HOLD_MSR_PROTO 2 + +/* As defined by SEV-SNP Firmware ABI, under "Guest Policy". */ +#define SNP_POLICY_MASK_API_MINOR GENMASK_ULL(7, 0) +#define SNP_POLICY_MASK_API_MAJOR GENMASK_ULL(15, 8) +#define SNP_POLICY_MASK_SMT BIT_ULL(16) +#define SNP_POLICY_MASK_RSVD_MBO BIT_ULL(17) +#define SNP_POLICY_MASK_DEBUG BIT_ULL(19) +#define SNP_POLICY_MASK_SINGLE_SOCKET BIT_ULL(20) + +#define SNP_POLICY_MASK_VALID (SNP_POLICY_MASK_API_MINOR | \ + SNP_POLICY_MASK_API_MAJOR | \ + SNP_POLICY_MASK_SMT | \ + SNP_POLICY_MASK_RSVD_MBO | \ + SNP_POLICY_MASK_DEBUG | \ + SNP_POLICY_MASK_SINGLE_SOCKET) + +#define INITIAL_VMSA_GPA 0xFFFFFFFFF000 static u8 sev_enc_bit; static DECLARE_RWSEM(sev_deactivate_lock); @@ -78,6 +92,8 @@ static unsigned int nr_asids; static unsigned long *sev_asid_bitmap; static unsigned long *sev_reclaim_asid_bitmap; +static int snp_decommission_context(struct kvm *kvm); + struct enc_region { struct list_head list; unsigned long npages; @@ -104,19 +120,32 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) down_write(&sev_deactivate_lock); wbinvd_on_all_cpus(); - ret = sev_guest_df_flush(&error); + + if (sev_snp_enabled) + ret = sev_do_cmd(SEV_CMD_SNP_DF_FLUSH, NULL, &error); + else + ret = sev_guest_df_flush(&error); up_write(&sev_deactivate_lock); if (ret) - pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); + pr_err("SEV%s: DF_FLUSH failed, ret=%d, error=%#x\n", + sev_snp_enabled ? "-SNP" : "", ret, error); return ret; } static inline bool is_mirroring_enc_context(struct kvm *kvm) { - return !!to_kvm_svm(kvm)->sev_info.enc_context_owner; + return !!to_kvm_sev_info(kvm)->enc_context_owner; +} + +static bool sev_vcpu_has_debug_swap(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm); + + return sev->vmsa_features & SVM_SEV_FEAT_DEBUG_SWAP; } /* Must be called with the sev_bitmap_lock held */ @@ -248,9 +277,7 @@ static int sev_asid_new(struct kvm_sev_info *sev) static unsigned int sev_get_asid(struct kvm *kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - return sev->asid; + return to_kvm_sev_info(kvm)->asid; } static void sev_asid_free(struct kvm_sev_info *sev) @@ -303,6 +330,53 @@ static void sev_decommission(unsigned int handle) sev_guest_decommission(&decommission, NULL); } +/* + * Transition a page to hypervisor-owned/shared state in the RMP table. This + * should not fail under normal conditions, but leak the page should that + * happen since it will no longer be usable by the host due to RMP protections. + */ +static int kvm_rmp_make_shared(struct kvm *kvm, u64 pfn, enum pg_level level) +{ + if (KVM_BUG_ON(rmp_make_shared(pfn, level), kvm)) { + snp_leak_pages(pfn, page_level_size(level) >> PAGE_SHIFT); + return -EIO; + } + + return 0; +} + +/* + * Certain page-states, such as Pre-Guest and Firmware pages (as documented + * in Chapter 5 of the SEV-SNP Firmware ABI under "Page States") cannot be + * directly transitioned back to normal/hypervisor-owned state via RMPUPDATE + * unless they are reclaimed first. + * + * Until they are reclaimed and subsequently transitioned via RMPUPDATE, they + * might not be usable by the host due to being set as immutable or still + * being associated with a guest ASID. + * + * Bug the VM and leak the page if reclaim fails, or if the RMP entry can't be + * converted back to shared, as the page is no longer usable due to RMP + * protections, and it's infeasible for the guest to continue on. + */ +static int snp_page_reclaim(struct kvm *kvm, u64 pfn) +{ + struct sev_data_snp_page_reclaim data = {0}; + int fw_err, rc; + + data.paddr = __sme_set(pfn << PAGE_SHIFT); + rc = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &fw_err); + if (KVM_BUG(rc, kvm, "Failed to reclaim PFN %llx, rc %d fw_err %d", pfn, rc, fw_err)) { + snp_leak_pages(pfn, 1); + return -EIO; + } + + if (kvm_rmp_make_shared(kvm, pfn, PG_LEVEL_4K)) + return -EIO; + + return rc; +} + static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) { struct sev_data_deactivate deactivate; @@ -320,20 +394,120 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_decommission(handle); } -static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +/* + * This sets up bounce buffers/firmware pages to handle SNP Guest Request + * messages (e.g. attestation requests). See "SNP Guest Request" in the GHCB + * 2.0 specification for more details. + * + * Technically, when an SNP Guest Request is issued, the guest will provide its + * own request/response pages, which could in theory be passed along directly + * to firmware rather than using bounce pages. However, these pages would need + * special care: + * + * - Both pages are from shared guest memory, so they need to be protected + * from migration/etc. occurring while firmware reads/writes to them. At a + * minimum, this requires elevating the ref counts and potentially needing + * an explicit pinning of the memory. This places additional restrictions + * on what type of memory backends userspace can use for shared guest + * memory since there is some reliance on using refcounted pages. + * + * - The response page needs to be switched to Firmware-owned[1] state + * before the firmware can write to it, which can lead to potential + * host RMP #PFs if the guest is misbehaved and hands the host a + * guest page that KVM might write to for other reasons (e.g. virtio + * buffers/etc.). + * + * Both of these issues can be avoided completely by using separately-allocated + * bounce pages for both the request/response pages and passing those to + * firmware instead. So that's what is being set up here. + * + * Guest requests rely on message sequence numbers to ensure requests are + * issued to firmware in the order the guest issues them, so concurrent guest + * requests generally shouldn't happen. But a misbehaved guest could issue + * concurrent guest requests in theory, so a mutex is used to serialize + * access to the bounce buffers. + * + * [1] See the "Page States" section of the SEV-SNP Firmware ABI for more + * details on Firmware-owned pages, along with "RMP and VMPL Access Checks" + * in the APM for details on the related RMP restrictions. + */ +static int snp_guest_req_init(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct page *req_page; + + req_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!req_page) + return -ENOMEM; + + sev->guest_resp_buf = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!sev->guest_resp_buf) { + __free_page(req_page); + return -EIO; + } + + sev->guest_req_buf = page_address(req_page); + mutex_init(&sev->guest_req_mutex); + + return 0; +} + +static void snp_guest_req_cleanup(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + + if (sev->guest_resp_buf) + snp_free_firmware_page(sev->guest_resp_buf); + + if (sev->guest_req_buf) + __free_page(virt_to_page(sev->guest_req_buf)); + + sev->guest_req_buf = NULL; + sev->guest_resp_buf = NULL; +} + +static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, + struct kvm_sev_init *data, + unsigned long vm_type) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct sev_platform_init_args init_args = {0}; int asid, ret; + bool es_active = vm_type != KVM_X86_SEV_VM; + u64 valid_vmsa_features = es_active ? sev_supported_vmsa_features : 0; if (kvm->created_vcpus) return -EINVAL; ret = -EBUSY; + if (data->flags) + return -EINVAL; + + if (data->vmsa_features & ~valid_vmsa_features) + return -EINVAL; + + if (data->ghcb_version > GHCB_VERSION_MAX || (!es_active && data->ghcb_version)) + return -EINVAL; + if (unlikely(sev->active)) return ret; sev->active = true; - sev->es_active = argp->id == KVM_SEV_ES_INIT; + sev->es_active = es_active; + sev->vmsa_features = data->vmsa_features; + sev->ghcb_version = data->ghcb_version; + + /* + * Currently KVM supports the full range of mandatory features defined + * by version 2 of the GHCB protocol, so default to that for SEV-ES + * guests created via KVM_SEV_INIT2. + */ + if (sev->es_active && !sev->ghcb_version) + sev->ghcb_version = GHCB_VERSION_DEFAULT; + + if (vm_type == KVM_X86_SNP_VM) + sev->vmsa_features |= SVM_SEV_FEAT_SNP_ACTIVE; + #ifdef CONFIG_KVM_SUPPORTS_CSV_REUSE_ASID /* Try reuse ASID iff userid array is available for HYGON CSV guests */ @@ -378,26 +552,78 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_no_asid; sev->asid = asid; - ret = sev_platform_init(&argp->error); + init_args.probe = false; + ret = sev_platform_init(&init_args); if (ret) goto e_free; + /* This needs to happen after SEV/SNP firmware initialization. */ + if (vm_type == KVM_X86_SNP_VM) { + ret = snp_guest_req_init(kvm); + if (ret) + goto e_free; + } + INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); + sev->need_init = false; kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); return 0; e_free: + argp->error = init_args.error; sev_asid_free(sev); sev->asid = 0; e_no_asid: + sev->vmsa_features = 0; sev->es_active = false; sev->active = false; return ret; } +static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_init data = { + .vmsa_features = 0, + .ghcb_version = 0, + }; + unsigned long vm_type; + + if (kvm->arch.vm_type != KVM_X86_DEFAULT_VM) + return -EINVAL; + + vm_type = (argp->id == KVM_SEV_INIT ? KVM_X86_SEV_VM : KVM_X86_SEV_ES_VM); + + /* + * KVM_SEV_ES_INIT has been deprecated by KVM_SEV_INIT2, so it will + * continue to only ever support the minimal GHCB protocol version. + */ + if (vm_type == KVM_X86_SEV_ES_VM) + data.ghcb_version = GHCB_VERSION_MIN; + + return __sev_guest_init(kvm, argp, &data, vm_type); +} + +static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_init data; + + if (!to_kvm_sev_info(kvm)->need_init) + return -EINVAL; + + if (kvm->arch.vm_type != KVM_X86_SEV_VM && + kvm->arch.vm_type != KVM_X86_SEV_ES_VM && + kvm->arch.vm_type != KVM_X86_SNP_VM) + return -EINVAL; + + if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data))) + return -EFAULT; + + return __sev_guest_init(kvm, argp, &data, kvm->arch.vm_type); +} + static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { unsigned int asid = sev_get_asid(kvm); @@ -429,14 +655,14 @@ static int __sev_issue_cmd(int fd, int id, void *data, int *error) static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); return __sev_issue_cmd(sev->fd, id, data, error); } static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); struct sev_data_launch_start start; struct kvm_sev_launch_start params; void *dh_blob, *session_blob; @@ -446,7 +672,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; memset(&start, 0, sizeof(start)); @@ -490,7 +716,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* return handle to userspace */ params.handle = start.handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) { sev_unbind_asid(kvm, start.handle); ret = -EFAULT; goto e_free_session; @@ -510,7 +736,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, unsigned long ulen, unsigned long *n, unsigned int flags) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); unsigned long npages, size; int npinned; unsigned long locked, lock_limit; @@ -572,11 +798,9 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, static void sev_unpin_memory(struct kvm *kvm, struct page **pages, unsigned long npages) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - unpin_user_pages(pages, npages); kvfree(pages); - sev->pages_locked -= npages; + to_kvm_sev_info(kvm)->pages_locked -= npages; } static void sev_clflush_pages(struct page *pages[], unsigned long npages) @@ -620,7 +844,6 @@ static unsigned long get_num_contig_pages(unsigned long idx, static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_launch_update_data params; struct sev_data_launch_update_data data; struct page **inpages; @@ -629,7 +852,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; vaddr = params.uaddr; @@ -648,7 +871,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) sev_clflush_pages(inpages, npages); data.reserved = 0; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { int offset, len; @@ -687,7 +910,13 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_es_sync_vmsa(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm); struct sev_es_save_area *save = svm->sev_es.vmsa; + struct xregs_state *xsave; + const u8 *s; + u8 *d; + int i; /* Check some debug related fields before encrypting the VMSA */ if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1)) @@ -728,10 +957,44 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - if (sev_es_debug_swap_enabled) { - save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; - pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. " - "This will not work starting with Linux 6.10\n"); + save->sev_features = sev->vmsa_features; + + /* + * Skip FPU and AVX setup with KVM_SEV_ES_INIT to avoid + * breaking older measurements. + */ + if (vcpu->kvm->arch.vm_type != KVM_X86_DEFAULT_VM) { + xsave = &vcpu->arch.guest_fpu.fpstate->regs.xsave; + save->x87_dp = xsave->i387.rdp; + save->mxcsr = xsave->i387.mxcsr; + save->x87_ftw = xsave->i387.twd; + save->x87_fsw = xsave->i387.swd; + save->x87_fcw = xsave->i387.cwd; + save->x87_fop = xsave->i387.fop; + save->x87_ds = 0; + save->x87_cs = 0; + save->x87_rip = xsave->i387.rip; + + for (i = 0; i < 8; i++) { + /* + * The format of the x87 save area is undocumented and + * definitely not what you would expect. It consists of + * an 8*8 bytes area with bytes 0-7, and an 8*2 bytes + * area with bytes 8-9 of each register. + */ + d = save->fpreg_x87 + i * 8; + s = ((u8 *)xsave->i387.st_space) + i * 16; + memcpy(d, s, 8); + save->fpreg_x87[64 + i * 2] = s[8]; + save->fpreg_x87[64 + i * 2 + 1] = s[9]; + } + memcpy(save->fpreg_xmm, xsave->i387.xmm_space, 256); + + s = get_xsave_addr(xsave, XFEATURE_YMM); + if (s) + memcpy(save->fpreg_ymm, s, 256); + else + memset(save->fpreg_ymm, 0, 256); } pr_debug("Virtual Machine Save Area (VMSA):\n"); @@ -765,13 +1028,20 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE); vmsa.reserved = 0; - vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.handle = to_kvm_sev_info(kvm)->handle; vmsa.address = __sme_pa(svm->sev_es.vmsa); vmsa.len = PAGE_SIZE; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); if (ret) return ret; + /* + * SEV-ES guests maintain an encrypted version of their FPU + * state which is restored and saved on VMRUN and VMEXIT. + * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't + * do xsave/xrstor on it. + */ + fpstate_set_confidential(&vcpu->arch.guest_fpu); vcpu->arch.guest_state_protected = true; /* @@ -785,6 +1055,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, csv2_sync_reset_vmsa(svm); } + + /* + * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it + * only after setting guest_state_protected because KVM_SET_MSRS allows + * dynamic toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); return 0; } @@ -814,8 +1092,7 @@ static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { - void __user *measure = (void __user *)(uintptr_t)argp->data; - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + void __user *measure = u64_to_user_ptr(argp->data); struct sev_data_launch_measure data; struct kvm_sev_launch_measure params; void __user *p = NULL; @@ -834,7 +1111,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - p = (void __user *)(uintptr_t)params.uaddr; + p = u64_to_user_ptr(params.uaddr); if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) return -EINVAL; @@ -848,7 +1125,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) } cmd: - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, &data, &argp->error); /* @@ -876,19 +1153,17 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_finish data; if (!sev_guest(kvm)) return -ENOTTY; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, &data, &argp->error); } static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_guest_status params; struct sev_data_guest_status data; int ret; @@ -898,7 +1173,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) memset(&data, 0, sizeof(data)); - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, &data, &argp->error); if (ret) return ret; @@ -907,7 +1182,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) params.state = data.state; params.handle = data.handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) ret = -EFAULT; return ret; @@ -917,11 +1192,10 @@ static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, unsigned long dst, int size, int *error, bool enc) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_dbg data; data.reserved = 0; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; data.dst_addr = dst; data.src_addr = src; data.len = size; @@ -1072,7 +1346,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) + if (copy_from_user(&debug, u64_to_user_ptr(argp->data), sizeof(debug))) return -EFAULT; if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) @@ -1145,7 +1419,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_secret data; struct kvm_sev_launch_secret params; struct page **pages; @@ -1156,7 +1429,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, FOLL_WRITE); @@ -1201,7 +1474,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) data.hdr_address = __psp_pa(hdr); data.hdr_len = params.hdr_len; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, &data, &argp->error); kfree(hdr); @@ -1220,8 +1493,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) { - void __user *report = (void __user *)(uintptr_t)argp->data; - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + void __user *report = u64_to_user_ptr(argp->data); struct sev_data_attestation_report data; struct kvm_sev_attestation_report params; void __user *p; @@ -1231,7 +1503,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; memset(&data, 0, sizeof(data)); @@ -1240,7 +1512,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - p = (void __user *)(uintptr_t)params.uaddr; + p = u64_to_user_ptr(params.uaddr); if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) return -EINVAL; @@ -1254,7 +1526,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) memcpy(data.mnonce, params.mnonce, sizeof(params.mnonce)); } cmd: - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, &data, &argp->error); /* * If we query the session length, FW responded with expected data. @@ -1284,16 +1556,15 @@ static int __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, struct kvm_sev_send_start *params) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_send_start data; int ret; memset(&data, 0, sizeof(data)); - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); params->session_len = data.session_len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, params, + if (copy_to_user(u64_to_user_ptr(argp->data), params, sizeof(struct kvm_sev_send_start))) ret = -EFAULT; @@ -1302,7 +1573,6 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_send_start data; struct kvm_sev_send_start params; void *amd_certs, *session_data; @@ -1312,7 +1582,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_send_start))) return -EFAULT; @@ -1363,11 +1633,11 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) data.amd_certs_len = params.amd_certs_len; data.session_address = __psp_pa(session_data); data.session_len = params.session_len; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); - if (!ret && copy_to_user((void __user *)(uintptr_t)params.session_uaddr, + if (!ret && copy_to_user(u64_to_user_ptr(params.session_uaddr), session_data, params.session_len)) { ret = -EFAULT; goto e_free_amd_cert; @@ -1375,7 +1645,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) params.policy = data.policy; params.session_len = data.session_len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(struct kvm_sev_send_start))) ret = -EFAULT; @@ -1395,18 +1665,17 @@ static int __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, struct kvm_sev_send_update_data *params) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_send_update_data data; int ret; memset(&data, 0, sizeof(data)); - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); params->hdr_len = data.hdr_len; params->trans_len = data.trans_len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, params, + if (copy_to_user(u64_to_user_ptr(argp->data), params, sizeof(struct kvm_sev_send_update_data))) ret = -EFAULT; @@ -1415,7 +1684,6 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_send_update_data data; struct kvm_sev_send_update_data params; void *hdr, *trans_data; @@ -1426,7 +1694,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_send_update_data))) return -EFAULT; @@ -1469,7 +1737,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; data.guest_address |= sev_me_mask; data.guest_len = params.guest_len; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); @@ -1477,14 +1745,14 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_free_trans_data; /* copy transport buffer to user space */ - if (copy_to_user((void __user *)(uintptr_t)params.trans_uaddr, + if (copy_to_user(u64_to_user_ptr(params.trans_uaddr), trans_data, params.trans_len)) { ret = -EFAULT; goto e_free_trans_data; } /* Copy packet header to userspace. */ - if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, + if (copy_to_user(u64_to_user_ptr(params.hdr_uaddr), hdr, params.hdr_len)) ret = -EFAULT; @@ -1500,31 +1768,29 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_send_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_send_finish data; if (!sev_guest(kvm)) return -ENOTTY; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; return sev_issue_cmd(kvm, SEV_CMD_SEND_FINISH, &data, &argp->error); } static int sev_send_cancel(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_send_cancel data; if (!sev_guest(kvm)) return -ENOTTY; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; return sev_issue_cmd(kvm, SEV_CMD_SEND_CANCEL, &data, &argp->error); } static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); struct sev_data_receive_start start; struct kvm_sev_receive_start params; int *error = &argp->error; @@ -1536,7 +1802,7 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) return -ENOTTY; /* Get parameter from the userspace */ - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_receive_start))) return -EFAULT; @@ -1578,7 +1844,7 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) } params.handle = start.handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(struct kvm_sev_receive_start))) { ret = -EFAULT; sev_unbind_asid(kvm, start.handle); @@ -1598,7 +1864,6 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_receive_update_data params; struct sev_data_receive_update_data data; void *hdr = NULL, *trans = NULL; @@ -1609,7 +1874,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -EINVAL; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(struct kvm_sev_receive_update_data))) return -EFAULT; @@ -1658,7 +1923,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; data.guest_address |= sev_me_mask; data.guest_len = params.guest_len; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; ret = sev_issue_cmd(kvm, SEV_CMD_RECEIVE_UPDATE_DATA, &data, &argp->error); @@ -1675,13 +1940,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_receive_finish data; if (!sev_guest(kvm)) return -ENOTTY; - data.handle = sev->handle; + data.handle = to_kvm_sev_info(kvm)->handle; return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } @@ -1701,8 +1965,8 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id) static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; - struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + struct kvm_sev_info *dst_sev = to_kvm_sev_info(dst_kvm); + struct kvm_sev_info *src_sev = to_kvm_sev_info(src_kvm); int r = -EBUSY; if (dst_kvm == src_kvm) @@ -1736,8 +2000,8 @@ static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; - struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + struct kvm_sev_info *dst_sev = to_kvm_sev_info(dst_kvm); + struct kvm_sev_info *src_sev = to_kvm_sev_info(src_kvm); mutex_unlock(&dst_kvm->lock); mutex_unlock(&src_kvm->lock); @@ -1811,8 +2075,8 @@ static void sev_unlock_vcpus_for_migration(struct kvm *kvm) static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *dst = &to_kvm_svm(dst_kvm)->sev_info; - struct kvm_sev_info *src = &to_kvm_svm(src_kvm)->sev_info; + struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm); + struct kvm_sev_info *src = to_kvm_sev_info(src_kvm); struct kvm_vcpu *dst_vcpu, *src_vcpu; struct vcpu_svm *dst_svm, *src_svm; struct kvm_sev_info *mirror; @@ -1824,6 +2088,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) dst->pages_locked = src->pages_locked; dst->enc_context_owner = src->enc_context_owner; dst->es_active = src->es_active; + dst->vmsa_features = src->vmsa_features; src->asid = 0; src->active = false; @@ -1851,8 +2116,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) * and add the new mirror to the list. */ if (is_mirroring_enc_context(dst_kvm)) { - struct kvm_sev_info *owner_sev_info = - &to_kvm_svm(dst->enc_context_owner)->sev_info; + struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(dst->enc_context_owner); list_del(&src->mirror_entry); list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms); @@ -1911,7 +2175,7 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) { - struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = to_kvm_sev_info(kvm); struct kvm_sev_info *src_sev, *cg_cleanup_sev; struct fd f = fdget(source_fd); struct kvm *source_kvm; @@ -1931,12 +2195,13 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) if (ret) goto out_fput; - if (sev_guest(kvm) || !sev_guest(source_kvm)) { + if (kvm->arch.vm_type != source_kvm->arch.vm_type || + sev_guest(kvm) || !sev_guest(source_kvm)) { ret = -EINVAL; goto out_unlock; } - src_sev = &to_kvm_svm(source_kvm)->sev_info; + src_sev = to_kvm_sev_info(source_kvm); dst_sev->misc_cg = get_current_misc_cg(); cg_cleanup_sev = dst_sev; @@ -1980,152 +2245,594 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) return ret; } -int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) +int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { - struct kvm_sev_cmd sev_cmd; - int r; - - if (!sev_enabled) - return -ENOTTY; + if (group != KVM_X86_GRP_SEV) + return -ENXIO; - if (!argp) + switch (attr) { + case KVM_X86_SEV_VMSA_FEATURES: + *val = sev_supported_vmsa_features; return 0; - if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) - return -EFAULT; - - mutex_lock(&kvm->lock); - - /* Only the enc_context_owner handles some memory enc operations. */ - if (is_mirroring_enc_context(kvm) && - !is_cmd_allowed_from_mirror(sev_cmd.id)) { - r = -EINVAL; - goto out; + default: + return -ENXIO; } +} - switch (sev_cmd.id) { - case KVM_SEV_ES_INIT: - if (!sev_es_enabled) { - r = -ENOTTY; - goto out; - } - fallthrough; - case KVM_SEV_INIT: - r = sev_guest_init(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_START: - r = sev_launch_start(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_UPDATE_DATA: - r = sev_launch_update_data(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_UPDATE_VMSA: - r = sev_launch_update_vmsa(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_MEASURE: - r = sev_launch_measure(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_FINISH: - r = sev_launch_finish(kvm, &sev_cmd); - break; - case KVM_SEV_GUEST_STATUS: - r = sev_guest_status(kvm, &sev_cmd); - break; - case KVM_SEV_DBG_DECRYPT: - r = sev_dbg_crypt(kvm, &sev_cmd, true); - break; - case KVM_SEV_DBG_ENCRYPT: - r = sev_dbg_crypt(kvm, &sev_cmd, false); - break; - case KVM_SEV_LAUNCH_SECRET: - r = sev_launch_secret(kvm, &sev_cmd); - break; - case KVM_SEV_GET_ATTESTATION_REPORT: - r = sev_get_attestation_report(kvm, &sev_cmd); - break; - case KVM_SEV_SEND_START: - r = sev_send_start(kvm, &sev_cmd); - break; - case KVM_SEV_SEND_UPDATE_DATA: - r = sev_send_update_data(kvm, &sev_cmd); - break; - case KVM_SEV_SEND_FINISH: - r = sev_send_finish(kvm, &sev_cmd); - break; - case KVM_SEV_SEND_CANCEL: - r = sev_send_cancel(kvm, &sev_cmd); - break; - case KVM_SEV_RECEIVE_START: - r = sev_receive_start(kvm, &sev_cmd); - break; - case KVM_SEV_RECEIVE_UPDATE_DATA: - r = sev_receive_update_data(kvm, &sev_cmd); - break; - case KVM_SEV_RECEIVE_FINISH: - r = sev_receive_finish(kvm, &sev_cmd); - break; - default: - r = -EINVAL; - goto out; +/* + * The guest context contains all the information, keys and metadata + * associated with the guest that the firmware tracks to implement SEV + * and SNP features. The firmware stores the guest context in hypervisor + * provide page via the SNP_GCTX_CREATE command. + */ +static void *snp_context_create(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct sev_data_snp_addr data = {}; + void *context; + int rc; + + /* Allocate memory for context page */ + context = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT); + if (!context) + return NULL; + + data.address = __psp_pa(context); + rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_GCTX_CREATE, &data, &argp->error); + if (rc) { + pr_warn("Failed to create SEV-SNP context, rc %d fw_error %d", + rc, argp->error); + snp_free_firmware_page(context); + return NULL; } - if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) - r = -EFAULT; + return context; +} -out: - mutex_unlock(&kvm->lock); - return r; +static int snp_bind_asid(struct kvm *kvm, int *error) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct sev_data_snp_activate data = {0}; + + data.gctx_paddr = __psp_pa(sev->snp_context); + data.asid = sev_get_asid(kvm); + return sev_issue_cmd(kvm, SEV_CMD_SNP_ACTIVATE, &data, error); } -int sev_mem_enc_register_region(struct kvm *kvm, - struct kvm_enc_region *range) +static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct enc_region *region; - int ret = 0; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct sev_data_snp_launch_start start = {0}; + struct kvm_sev_snp_launch_start params; + int rc; - if (!sev_guest(kvm)) + if (!sev_snp_guest(kvm)) return -ENOTTY; - /* If kvm is mirroring encryption context it isn't responsible for it */ - if (is_mirroring_enc_context(kvm)) + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) + return -EFAULT; + + /* Don't allow userspace to allocate memory for more than 1 SNP context. */ + if (sev->snp_context) return -EINVAL; - if (range->addr > ULONG_MAX || range->size > ULONG_MAX) + if (params.flags) return -EINVAL; - region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); - if (!region) - return -ENOMEM; + if (params.policy & ~SNP_POLICY_MASK_VALID) + return -EINVAL; - mutex_lock(&kvm->lock); - region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, - FOLL_WRITE | FOLL_LONGTERM); - if (IS_ERR(region->pages)) { - ret = PTR_ERR(region->pages); - mutex_unlock(&kvm->lock); - goto e_free; + /* Check for policy bits that must be set */ + if (!(params.policy & SNP_POLICY_MASK_RSVD_MBO) || + !(params.policy & SNP_POLICY_MASK_SMT)) + return -EINVAL; + + if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET) + return -EINVAL; + + sev->snp_context = snp_context_create(kvm, argp); + if (!sev->snp_context) + return -ENOTTY; + + start.gctx_paddr = __psp_pa(sev->snp_context); + start.policy = params.policy; + memcpy(start.gosvw, params.gosvw, sizeof(params.gosvw)); + rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_START, &start, &argp->error); + if (rc) { + pr_debug("%s: SEV_CMD_SNP_LAUNCH_START firmware command failed, rc %d\n", + __func__, rc); + goto e_free_context; } - /* - * The guest may change the memory encryption attribute from C=0 -> C=1 - * or vice versa for this memory range. Lets make sure caches are - * flushed to ensure that guest data gets written into memory with - * correct C-bit. Note, this must be done before dropping kvm->lock, - * as region and its array of pages can be freed by a different task - * once kvm->lock is released. - */ - sev_clflush_pages(region->pages, region->npages); + sev->fd = argp->sev_fd; + rc = snp_bind_asid(kvm, &argp->error); + if (rc) { + pr_debug("%s: Failed to bind ASID to SEV-SNP context, rc %d\n", + __func__, rc); + goto e_free_context; + } - region->uaddr = range->addr; - region->size = range->size; + return 0; - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); +e_free_context: + snp_decommission_context(kvm); - return ret; + return rc; +} -e_free: +struct sev_gmem_populate_args { + __u8 type; + int sev_fd; + int fw_error; +}; + +static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pfn, + void __user *src, int order, void *opaque) +{ + struct sev_gmem_populate_args *sev_populate_args = opaque; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + int n_private = 0, ret, i; + int npages = (1 << order); + gfn_t gfn; + + if (WARN_ON_ONCE(sev_populate_args->type != KVM_SEV_SNP_PAGE_TYPE_ZERO && !src)) + return -EINVAL; + + for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) { + struct sev_data_snp_launch_update fw_args = {0}; + bool assigned = false; + int level; + + ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level); + if (ret || assigned) { + pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n", + __func__, gfn, ret, assigned); + ret = ret ? -EINVAL : -EEXIST; + goto err; + } + + if (src) { + void *vaddr = kmap_local_pfn(pfn + i); + + if (copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE)) { + ret = -EFAULT; + goto err; + } + kunmap_local(vaddr); + } + + ret = rmp_make_private(pfn + i, gfn << PAGE_SHIFT, PG_LEVEL_4K, + sev_get_asid(kvm), true); + if (ret) + goto err; + + n_private++; + + fw_args.gctx_paddr = __psp_pa(sev->snp_context); + fw_args.address = __sme_set(pfn_to_hpa(pfn + i)); + fw_args.page_size = PG_LEVEL_TO_RMP(PG_LEVEL_4K); + fw_args.page_type = sev_populate_args->type; + + ret = __sev_issue_cmd(sev_populate_args->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE, + &fw_args, &sev_populate_args->fw_error); + if (ret) + goto fw_err; + } + + return 0; + +fw_err: + /* + * If the firmware command failed handle the reclaim and cleanup of that + * PFN specially vs. prior pages which can be cleaned up below without + * needing to reclaim in advance. + * + * Additionally, when invalid CPUID function entries are detected, + * firmware writes the expected values into the page and leaves it + * unencrypted so it can be used for debugging and error-reporting. + * + * Copy this page back into the source buffer so userspace can use this + * information to provide information on which CPUID leaves/fields + * failed CPUID validation. + */ + if (!snp_page_reclaim(kvm, pfn + i) && + sev_populate_args->type == KVM_SEV_SNP_PAGE_TYPE_CPUID && + sev_populate_args->fw_error == SEV_RET_INVALID_PARAM) { + void *vaddr = kmap_local_pfn(pfn + i); + + if (copy_to_user(src + i * PAGE_SIZE, vaddr, PAGE_SIZE)) + pr_debug("Failed to write CPUID page back to userspace\n"); + + kunmap_local(vaddr); + } + + /* pfn + i is hypervisor-owned now, so skip below cleanup for it. */ + n_private--; + +err: + pr_debug("%s: exiting with error ret %d (fw_error %d), restoring %d gmem PFNs to shared.\n", + __func__, ret, sev_populate_args->fw_error, n_private); + for (i = 0; i < n_private; i++) + kvm_rmp_make_shared(kvm, pfn + i, PG_LEVEL_4K); + + return ret; +} + +static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct sev_gmem_populate_args sev_populate_args = {0}; + struct kvm_sev_snp_launch_update params; + struct kvm_memory_slot *memslot; + long npages, count; + void __user *src; + int ret = 0; + + if (!sev_snp_guest(kvm) || !sev->snp_context) + return -EINVAL; + + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) + return -EFAULT; + + pr_debug("%s: GFN start 0x%llx length 0x%llx type %d flags %d\n", __func__, + params.gfn_start, params.len, params.type, params.flags); + + if (!PAGE_ALIGNED(params.len) || params.flags || + (params.type != KVM_SEV_SNP_PAGE_TYPE_NORMAL && + params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO && + params.type != KVM_SEV_SNP_PAGE_TYPE_UNMEASURED && + params.type != KVM_SEV_SNP_PAGE_TYPE_SECRETS && + params.type != KVM_SEV_SNP_PAGE_TYPE_CPUID)) + return -EINVAL; + + npages = params.len / PAGE_SIZE; + + /* + * For each GFN that's being prepared as part of the initial guest + * state, the following pre-conditions are verified: + * + * 1) The backing memslot is a valid private memslot. + * 2) The GFN has been set to private via KVM_SET_MEMORY_ATTRIBUTES + * beforehand. + * 3) The PFN of the guest_memfd has not already been set to private + * in the RMP table. + * + * The KVM MMU relies on kvm->mmu_invalidate_seq to retry nested page + * faults if there's a race between a fault and an attribute update via + * KVM_SET_MEMORY_ATTRIBUTES, and a similar approach could be utilized + * here. However, kvm->slots_lock guards against both this as well as + * concurrent memslot updates occurring while these checks are being + * performed, so use that here to make it easier to reason about the + * initial expected state and better guard against unexpected + * situations. + */ + mutex_lock(&kvm->slots_lock); + + memslot = gfn_to_memslot(kvm, params.gfn_start); + if (!kvm_slot_can_be_private(memslot)) { + ret = -EINVAL; + goto out; + } + + sev_populate_args.sev_fd = argp->sev_fd; + sev_populate_args.type = params.type; + src = params.type == KVM_SEV_SNP_PAGE_TYPE_ZERO ? NULL : u64_to_user_ptr(params.uaddr); + + count = kvm_gmem_populate(kvm, params.gfn_start, src, npages, + sev_gmem_post_populate, &sev_populate_args); + if (count < 0) { + argp->error = sev_populate_args.fw_error; + pr_debug("%s: kvm_gmem_populate failed, ret %ld (fw_error %d)\n", + __func__, count, argp->error); + ret = -EIO; + } else { + params.gfn_start += count; + params.len -= count * PAGE_SIZE; + if (params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO) + params.uaddr += count * PAGE_SIZE; + + ret = 0; + if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) + ret = -EFAULT; + } + +out: + mutex_unlock(&kvm->slots_lock); + + return ret; +} + +static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct sev_data_snp_launch_update data = {}; + struct kvm_vcpu *vcpu; + unsigned long i; + int ret; + + data.gctx_paddr = __psp_pa(sev->snp_context); + data.page_type = SNP_PAGE_TYPE_VMSA; + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vcpu_svm *svm = to_svm(vcpu); + u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT; + + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; + + /* Transition the VMSA page to a firmware state. */ + ret = rmp_make_private(pfn, INITIAL_VMSA_GPA, PG_LEVEL_4K, sev->asid, true); + if (ret) + return ret; + + /* Issue the SNP command to encrypt the VMSA */ + data.address = __sme_pa(svm->sev_es.vmsa); + ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE, + &data, &argp->error); + if (ret) { + snp_page_reclaim(kvm, pfn); + + return ret; + } + + svm->vcpu.arch.guest_state_protected = true; + /* + * SEV-ES (and thus SNP) guest mandates LBR Virtualization to + * be _always_ ON. Enable it only after setting + * guest_state_protected because KVM_SET_MSRS allows dynamic + * toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); + } + + return 0; +} + +static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct kvm_sev_snp_launch_finish params; + struct sev_data_snp_launch_finish *data; + void *id_block = NULL, *id_auth = NULL; + int ret; + + if (!sev_snp_guest(kvm)) + return -ENOTTY; + + if (!sev->snp_context) + return -EINVAL; + + if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) + return -EFAULT; + + if (params.flags) + return -EINVAL; + + /* Measure all vCPUs using LAUNCH_UPDATE before finalizing the launch flow. */ + ret = snp_launch_update_vmsa(kvm, argp); + if (ret) + return ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + if (params.id_block_en) { + id_block = psp_copy_user_blob(params.id_block_uaddr, KVM_SEV_SNP_ID_BLOCK_SIZE); + if (IS_ERR(id_block)) { + ret = PTR_ERR(id_block); + goto e_free; + } + + data->id_block_en = 1; + data->id_block_paddr = __sme_pa(id_block); + + id_auth = psp_copy_user_blob(params.id_auth_uaddr, KVM_SEV_SNP_ID_AUTH_SIZE); + if (IS_ERR(id_auth)) { + ret = PTR_ERR(id_auth); + goto e_free_id_block; + } + + data->id_auth_paddr = __sme_pa(id_auth); + + if (params.auth_key_en) + data->auth_key_en = 1; + } + + data->vcek_disabled = params.vcek_disabled; + + memcpy(data->host_data, params.host_data, KVM_SEV_SNP_FINISH_DATA_SIZE); + data->gctx_paddr = __psp_pa(sev->snp_context); + ret = sev_issue_cmd(kvm, SEV_CMD_SNP_LAUNCH_FINISH, data, &argp->error); + + /* + * Now that there will be no more SNP_LAUNCH_UPDATE ioctls, private pages + * can be given to the guest simply by marking the RMP entry as private. + * This can happen on first access and also with KVM_PRE_FAULT_MEMORY. + */ + if (!ret) + kvm->arch.pre_fault_allowed = true; + + kfree(id_auth); + +e_free_id_block: + kfree(id_block); + +e_free: + kfree(data); + + return ret; +} + +int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) +{ + struct kvm_sev_cmd sev_cmd; + int r; + + if (!sev_enabled) + return -ENOTTY; + + if (!argp) + return 0; + + if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) + return -EFAULT; + + mutex_lock(&kvm->lock); + + /* Only the enc_context_owner handles some memory enc operations. */ + if (is_mirroring_enc_context(kvm) && + !is_cmd_allowed_from_mirror(sev_cmd.id)) { + r = -EINVAL; + goto out; + } + + /* + * Once KVM_SEV_INIT2 initializes a KVM instance as an SNP guest, only + * allow the use of SNP-specific commands. + */ + if (sev_snp_guest(kvm) && sev_cmd.id < KVM_SEV_SNP_LAUNCH_START) { + r = -EPERM; + goto out; + } + + switch (sev_cmd.id) { + case KVM_SEV_ES_INIT: + if (!sev_es_enabled) { + r = -ENOTTY; + goto out; + } + fallthrough; + case KVM_SEV_INIT: + r = sev_guest_init(kvm, &sev_cmd); + break; + case KVM_SEV_INIT2: + r = sev_guest_init2(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_START: + r = sev_launch_start(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_DATA: + r = sev_launch_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_VMSA: + r = sev_launch_update_vmsa(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_MEASURE: + r = sev_launch_measure(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_FINISH: + r = sev_launch_finish(kvm, &sev_cmd); + break; + case KVM_SEV_GUEST_STATUS: + r = sev_guest_status(kvm, &sev_cmd); + break; + case KVM_SEV_DBG_DECRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, true); + break; + case KVM_SEV_DBG_ENCRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, false); + break; + case KVM_SEV_LAUNCH_SECRET: + r = sev_launch_secret(kvm, &sev_cmd); + break; + case KVM_SEV_GET_ATTESTATION_REPORT: + r = sev_get_attestation_report(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_START: + r = sev_send_start(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_UPDATE_DATA: + r = sev_send_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_FINISH: + r = sev_send_finish(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_CANCEL: + r = sev_send_cancel(kvm, &sev_cmd); + break; + case KVM_SEV_RECEIVE_START: + r = sev_receive_start(kvm, &sev_cmd); + break; + case KVM_SEV_RECEIVE_UPDATE_DATA: + r = sev_receive_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_RECEIVE_FINISH: + r = sev_receive_finish(kvm, &sev_cmd); + break; + case KVM_SEV_SNP_LAUNCH_START: + r = snp_launch_start(kvm, &sev_cmd); + break; + case KVM_SEV_SNP_LAUNCH_UPDATE: + r = snp_launch_update(kvm, &sev_cmd); + break; + case KVM_SEV_SNP_LAUNCH_FINISH: + r = snp_launch_finish(kvm, &sev_cmd); + break; + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + +int sev_mem_enc_register_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct enc_region *region; + int ret = 0; + + if (!sev_guest(kvm)) + return -ENOTTY; + + /* If kvm is mirroring encryption context it isn't responsible for it */ + if (is_mirroring_enc_context(kvm)) + return -EINVAL; + + if (range->addr > ULONG_MAX || range->size > ULONG_MAX) + return -EINVAL; + + region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); + if (!region) + return -ENOMEM; + + mutex_lock(&kvm->lock); + region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, + FOLL_WRITE | FOLL_LONGTERM); + if (IS_ERR(region->pages)) { + ret = PTR_ERR(region->pages); + mutex_unlock(&kvm->lock); + goto e_free; + } + + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. + */ + sev_clflush_pages(region->pages, region->npages); + + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + + return ret; + +e_free: kfree(region); return ret; } @@ -2133,7 +2840,7 @@ int sev_mem_enc_register_region(struct kvm *kvm, static struct enc_region * find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); struct list_head *head = &sev->regions_list; struct enc_region *i; @@ -2230,9 +2937,9 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) * The mirror kvm holds an enc_context_owner ref so its asid can't * disappear until we're done with it */ - source_sev = &to_kvm_svm(source_kvm)->sev_info; + source_sev = to_kvm_sev_info(source_kvm); kvm_get_kvm(source_kvm); - mirror_sev = &to_kvm_svm(kvm)->sev_info; + mirror_sev = to_kvm_sev_info(kvm); list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms); /* Set enc_context_owner and copy its encryption context over */ @@ -2241,6 +2948,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) mirror_sev->asid = source_sev->asid; mirror_sev->fd = source_sev->fd; mirror_sev->es_active = source_sev->es_active; + mirror_sev->need_init = false; mirror_sev->handle = source_sev->handle; INIT_LIST_HEAD(&mirror_sev->regions_list); INIT_LIST_HEAD(&mirror_sev->mirror_vms); @@ -2259,9 +2967,34 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) return ret; } +static int snp_decommission_context(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct sev_data_snp_addr data = {}; + int ret; + + /* If context is not created then do nothing */ + if (!sev->snp_context) + return 0; + + /* Do the decommision, which will unbind the ASID from the SNP context */ + data.address = __sme_pa(sev->snp_context); + down_write(&sev_deactivate_lock); + ret = sev_do_cmd(SEV_CMD_SNP_DECOMMISSION, &data, NULL); + up_write(&sev_deactivate_lock); + + if (WARN_ONCE(ret, "Failed to release guest context, ret %d", ret)) + return ret; + + snp_free_firmware_page(sev->snp_context); + sev->snp_context = NULL; + + return 0; +} + void sev_vm_destroy(struct kvm *kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); struct list_head *head = &sev->regions_list; struct list_head *pos, *q; @@ -2300,16 +3033,36 @@ void sev_vm_destroy(struct kvm *kvm) } } - sev_unbind_asid(kvm, sev->handle); + if (sev_snp_guest(kvm)) { + snp_guest_req_cleanup(kvm); + + /* + * Decomission handles unbinding of the ASID. If it fails for + * some unexpected reason, just leak the ASID. + */ + if (snp_decommission_context(kvm)) + return; + } else { + sev_unbind_asid(kvm, sev->handle); + } + sev_asid_free(sev); } void __init sev_set_cpu_caps(void) { - if (!sev_enabled) - kvm_cpu_cap_clear(X86_FEATURE_SEV); - if (!sev_es_enabled) - kvm_cpu_cap_clear(X86_FEATURE_SEV_ES); + if (sev_enabled) { + kvm_cpu_cap_set(X86_FEATURE_SEV); + kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_VM); + } + if (sev_es_enabled) { + kvm_cpu_cap_set(X86_FEATURE_SEV_ES); + kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM); + } + if (sev_snp_enabled) { + kvm_cpu_cap_set(X86_FEATURE_SEV_SNP); + kvm_caps.supported_vm_types |= BIT(KVM_X86_SNP_VM); + } } #ifdef CONFIG_HYGON_CSV @@ -2330,8 +3083,8 @@ void sev_install_hooks(void) void __init sev_hardware_setup(void) { -#ifdef CONFIG_KVM_AMD_SEV unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count; + bool sev_snp_supported = false; bool sev_es_supported = false; bool sev_supported = false; @@ -2405,6 +3158,12 @@ void __init sev_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; + if (!lbrv) { + WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), + "LBRV must be present for SEV-ES support"); + goto out; + } + if (is_x86_vendor_hygon() && hygon_csv_build >= 1810) { /* * Ths ASIDs from 1 to max_sev_asid are available for hygon @@ -2420,6 +3179,7 @@ void __init sev_hardware_setup(void) } WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)); sev_es_supported = true; + sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP); out: if (boot_cpu_has(X86_FEATURE_SEV)) @@ -2437,13 +3197,23 @@ void __init sev_hardware_setup(void) 1 : (min_sev_asid > 1 ? 1 : 0), (is_x86_vendor_hygon() && hygon_csv_build >= 1810) ? max_sev_asid : min_sev_asid - 1); + if (boot_cpu_has(X86_FEATURE_SEV_SNP)) + pr_info("SEV-SNP %s (ASIDs %u - %u)\n", + sev_snp_supported ? "enabled" : "disabled", + min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); sev_enabled = sev_supported; sev_es_enabled = sev_es_supported; + sev_snp_enabled = sev_snp_supported; + if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) || !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP)) sev_es_debug_swap_enabled = false; + + sev_supported_vmsa_features = 0; + if (sev_es_debug_swap_enabled) + sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP; #ifdef CONFIG_HYGON_CSV /* Setup resources which are necessary for HYGON CSV */ if (is_x86_vendor_hygon()) { @@ -2456,7 +3226,6 @@ void __init sev_hardware_setup(void) if (sev_enabled) csv_hardware_setup(max_sev_asid); } -#endif #endif } @@ -2533,7 +3302,13 @@ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) void sev_guest_memory_reclaimed(struct kvm *kvm) { - if (!sev_guest(kvm)) + /* + * With SNP+gmem, private/encrypted memory is unreachable via the + * hva-based mmu notifiers, so these events are only actually + * pertaining to shared pages where there is no need to perform + * the WBINVD to flush associated caches. + */ + if (!sev_guest(kvm) || sev_snp_guest(kvm)) return; wbinvd_on_all_cpus(); @@ -2548,6 +3323,18 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); + /* + * If it's an SNP guest, then the VMSA was marked in the RMP table as + * a guest-owned page. Transition the page to hypervisor state before + * releasing it back to the system. + */ + if (sev_snp_guest(vcpu->kvm)) { + u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT; + + if (kvm_rmp_make_shared(vcpu->kvm, pfn, PG_LEVEL_4K)) + goto skip_vmsa_free; + } + if (vcpu->arch.guest_state_protected) sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); @@ -2556,6 +3343,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) if (svm->sev_es.ghcb) kvm_vcpu_unmap(vcpu, &svm->sev_es.ghcb_map, false); +skip_vmsa_free: if (svm->sev_es.ghcb_sa_free) kvfree(svm->sev_es.ghcb_sa); @@ -2754,10 +3542,31 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; + case SVM_VMGEXIT_AP_CREATION: + if (!sev_snp_guest(vcpu->kvm)) + goto vmgexit_err; + if (lower_32_bits(control->exit_info_1) != SVM_VMGEXIT_AP_DESTROY) + if (!kvm_ghcb_rax_is_valid(svm)) + goto vmgexit_err; + break; case SVM_VMGEXIT_NMI_COMPLETE: case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: + case SVM_VMGEXIT_HV_FEATURES: + case SVM_VMGEXIT_TERM_REQUEST: + break; + case SVM_VMGEXIT_PSC: + if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_VMGEXIT_GUEST_REQUEST: + case SVM_VMGEXIT_EXT_GUEST_REQUEST: + if (!sev_snp_guest(vcpu->kvm) || + !PAGE_ALIGNED(control->exit_info_1) || + !PAGE_ALIGNED(control->exit_info_2) || + control->exit_info_1 == control->exit_info_2) + goto vmgexit_err; break; default: reason = GHCB_ERR_INVALID_EVENT; @@ -2788,6 +3597,9 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) void sev_es_unmap_ghcb(struct vcpu_svm *svm) { + /* Clear any indication that the vCPU is in a type of AP Reset Hold */ + svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NONE; + if (!svm->sev_es.ghcb) return; @@ -2818,10 +3630,19 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) svm->sev_es.ghcb = NULL; } -void pre_sev_run(struct vcpu_svm *svm, int cpu) +int pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - unsigned int asid = sev_get_asid(svm->vcpu.kvm); + struct kvm *kvm = svm->vcpu.kvm; + unsigned int asid = sev_get_asid(kvm); + + /* + * Reject KVM_RUN if userspace attempts to run the vCPU with an invalid + * VMSA, e.g. if userspace forces the vCPU to be RUNNABLE after an SNP + * AP Destroy event. + */ + if (sev_es_guest(kvm) && !VALID_PAGE(svm->vmcb->control.vmsa_pa)) + return -EINVAL; /* Assign the asid allocated with this SEV guest */ svm->asid = asid; @@ -2841,11 +3662,12 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) */ if (sd->sev_vmcbs[asid] == svm->vmcb && svm->vcpu.arch.last_vmentry_cpu == cpu) - return; + return 0; sd->sev_vmcbs[asid] = svm->vmcb; svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; vmcb_mark_dirty(svm->vmcb, VMCB_ASID); + return 0; } #define GHCB_SCRATCH_AREA_LIMIT (16ULL * PAGE_SIZE) @@ -2912,48 +3734,561 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) } /* - * The scratch area is outside the GHCB. The operation will - * dictate whether the buffer needs to be synced before running - * the vCPU next time (i.e. a read was requested so the data - * must be written back to the guest memory). + * The scratch area is outside the GHCB. The operation will + * dictate whether the buffer needs to be synced before running + * the vCPU next time (i.e. a read was requested so the data + * must be written back to the guest memory). + */ + svm->sev_es.ghcb_sa_sync = sync; + svm->sev_es.ghcb_sa_free = true; + } + + svm->sev_es.ghcb_sa = scratch_va; + svm->sev_es.ghcb_sa_len = len; + + return 0; + +e_scratch: + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return 1; +} + +static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, + unsigned int pos) +{ + svm->vmcb->control.ghcb_gpa &= ~(mask << pos); + svm->vmcb->control.ghcb_gpa |= (value & mask) << pos; +} + +static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos) +{ + return (svm->vmcb->control.ghcb_gpa >> pos) & mask; +} + +static void set_ghcb_msr(struct vcpu_svm *svm, u64 value) +{ + svm->vmcb->control.ghcb_gpa = value; +} + +static int snp_rmptable_psmash(kvm_pfn_t pfn) +{ + int ret; + + pfn = pfn & ~(KVM_PAGES_PER_HPAGE(PG_LEVEL_2M) - 1); + + /* + * PSMASH_FAIL_INUSE indicates another processor is modifying the + * entry, so retry until that's no longer the case. + */ + do { + ret = psmash(pfn); + } while (ret == PSMASH_FAIL_INUSE); + + return ret; +} + +static int snp_complete_psc_msr(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (vcpu->run->hypercall.ret) + set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR); + else + set_ghcb_msr(svm, GHCB_MSR_PSC_RESP); + + return 1; /* resume guest */ +} + +static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr) +{ + u64 gpa = gfn_to_gpa(GHCB_MSR_PSC_REQ_TO_GFN(ghcb_msr)); + u8 op = GHCB_MSR_PSC_REQ_TO_OP(ghcb_msr); + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (op != SNP_PAGE_STATE_PRIVATE && op != SNP_PAGE_STATE_SHARED) { + set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR); + return 1; /* resume guest */ + } + + if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) { + set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR); + return 1; /* resume guest */ + } + + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + vcpu->run->hypercall.args[0] = gpa; + vcpu->run->hypercall.args[1] = 1; + vcpu->run->hypercall.args[2] = (op == SNP_PAGE_STATE_PRIVATE) + ? KVM_MAP_GPA_RANGE_ENCRYPTED + : KVM_MAP_GPA_RANGE_DECRYPTED; + vcpu->run->hypercall.args[2] |= KVM_MAP_GPA_RANGE_PAGE_SZ_4K; + + vcpu->arch.complete_userspace_io = snp_complete_psc_msr; + + return 0; /* forward request to userspace */ +} + +struct psc_buffer { + struct psc_hdr hdr; + struct psc_entry entries[]; +} __packed; + +static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc); + +static void snp_complete_psc(struct vcpu_svm *svm, u64 psc_ret) +{ + svm->sev_es.psc_inflight = 0; + svm->sev_es.psc_idx = 0; + svm->sev_es.psc_2m = false; + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, psc_ret); +} + +static void __snp_complete_one_psc(struct vcpu_svm *svm) +{ + struct psc_buffer *psc = svm->sev_es.ghcb_sa; + struct psc_entry *entries = psc->entries; + struct psc_hdr *hdr = &psc->hdr; + __u16 idx; + + /* + * Everything in-flight has been processed successfully. Update the + * corresponding entries in the guest's PSC buffer and zero out the + * count of in-flight PSC entries. + */ + for (idx = svm->sev_es.psc_idx; svm->sev_es.psc_inflight; + svm->sev_es.psc_inflight--, idx++) { + struct psc_entry *entry = &entries[idx]; + + entry->cur_page = entry->pagesize ? 512 : 1; + } + + hdr->cur_entry = idx; +} + +static int snp_complete_one_psc(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct psc_buffer *psc = svm->sev_es.ghcb_sa; + + if (vcpu->run->hypercall.ret) { + snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC); + return 1; /* resume guest */ + } + + __snp_complete_one_psc(svm); + + /* Handle the next range (if any). */ + return snp_begin_psc(svm, psc); +} + +static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc) +{ + struct psc_entry *entries = psc->entries; + struct kvm_vcpu *vcpu = &svm->vcpu; + struct psc_hdr *hdr = &psc->hdr; + struct psc_entry entry_start; + u16 idx, idx_start, idx_end; + int npages; + bool huge; + u64 gfn; + + if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) { + snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC); + return 1; + } + +next_range: + /* There should be no other PSCs in-flight at this point. */ + if (WARN_ON_ONCE(svm->sev_es.psc_inflight)) { + snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC); + return 1; + } + + /* + * The PSC descriptor buffer can be modified by a misbehaved guest after + * validation, so take care to only use validated copies of values used + * for things like array indexing. + */ + idx_start = hdr->cur_entry; + idx_end = hdr->end_entry; + + if (idx_end >= VMGEXIT_PSC_MAX_COUNT) { + snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_HDR); + return 1; + } + + /* Find the start of the next range which needs processing. */ + for (idx = idx_start; idx <= idx_end; idx++, hdr->cur_entry++) { + entry_start = entries[idx]; + + gfn = entry_start.gfn; + huge = entry_start.pagesize; + npages = huge ? 512 : 1; + + if (entry_start.cur_page > npages || !IS_ALIGNED(gfn, npages)) { + snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_ENTRY); + return 1; + } + + if (entry_start.cur_page) { + /* + * If this is a partially-completed 2M range, force 4K handling + * for the remaining pages since they're effectively split at + * this point. Subsequent code should ensure this doesn't get + * combined with adjacent PSC entries where 2M handling is still + * possible. + */ + npages -= entry_start.cur_page; + gfn += entry_start.cur_page; + huge = false; + } + + if (npages) + break; + } + + if (idx > idx_end) { + /* Nothing more to process. */ + snp_complete_psc(svm, 0); + return 1; + } + + svm->sev_es.psc_2m = huge; + svm->sev_es.psc_idx = idx; + svm->sev_es.psc_inflight = 1; + + /* + * Find all subsequent PSC entries that contain adjacent GPA + * ranges/operations and can be combined into a single + * KVM_HC_MAP_GPA_RANGE exit. + */ + while (++idx <= idx_end) { + struct psc_entry entry = entries[idx]; + + if (entry.operation != entry_start.operation || + entry.gfn != entry_start.gfn + npages || + entry.cur_page || !!entry.pagesize != huge) + break; + + svm->sev_es.psc_inflight++; + npages += huge ? 512 : 1; + } + + switch (entry_start.operation) { + case VMGEXIT_PSC_OP_PRIVATE: + case VMGEXIT_PSC_OP_SHARED: + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + vcpu->run->hypercall.args[0] = gfn_to_gpa(gfn); + vcpu->run->hypercall.args[1] = npages; + vcpu->run->hypercall.args[2] = entry_start.operation == VMGEXIT_PSC_OP_PRIVATE + ? KVM_MAP_GPA_RANGE_ENCRYPTED + : KVM_MAP_GPA_RANGE_DECRYPTED; + vcpu->run->hypercall.args[2] |= entry_start.pagesize + ? KVM_MAP_GPA_RANGE_PAGE_SZ_2M + : KVM_MAP_GPA_RANGE_PAGE_SZ_4K; + vcpu->arch.complete_userspace_io = snp_complete_one_psc; + return 0; /* forward request to userspace */ + default: + /* + * Only shared/private PSC operations are currently supported, so if the + * entire range consists of unsupported operations (e.g. SMASH/UNSMASH), + * then consider the entire range completed and avoid exiting to + * userspace. In theory snp_complete_psc() can always be called directly + * at this point to complete the current range and start the next one, + * but that could lead to unexpected levels of recursion. + */ + __snp_complete_one_psc(svm); + goto next_range; + } + + unreachable(); +} + +static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + WARN_ON(!mutex_is_locked(&svm->sev_es.snp_vmsa_mutex)); + + /* Mark the vCPU as offline and not runnable */ + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + + /* Clear use of the VMSA */ + svm->vmcb->control.vmsa_pa = INVALID_PAGE; + + if (VALID_PAGE(svm->sev_es.snp_vmsa_gpa)) { + gfn_t gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa); + struct kvm_memory_slot *slot; + kvm_pfn_t pfn; + + slot = gfn_to_memslot(vcpu->kvm, gfn); + if (!slot) + return -EINVAL; + + /* + * The new VMSA will be private memory guest memory, so + * retrieve the PFN from the gmem backend. + */ + if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, NULL)) + return -EINVAL; + + /* + * From this point forward, the VMSA will always be a + * guest-mapped page rather than the initial one allocated + * by KVM in svm->sev_es.vmsa. In theory, svm->sev_es.vmsa + * could be free'd and cleaned up here, but that involves + * cleanups like wbinvd_on_all_cpus() which would ideally + * be handled during teardown rather than guest boot. + * Deferring that also allows the existing logic for SEV-ES + * VMSAs to be re-used with minimal SNP-specific changes. + */ + svm->sev_es.snp_has_guest_vmsa = true; + + /* Use the new VMSA */ + svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn); + + /* Mark the vCPU as runnable */ + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + + svm->sev_es.snp_vmsa_gpa = INVALID_PAGE; + + /* + * gmem pages aren't currently migratable, but if this ever + * changes then care should be taken to ensure + * svm->sev_es.vmsa is pinned through some other means. + */ + kvm_release_pfn_clean(pfn); + } + + /* + * When replacing the VMSA during SEV-SNP AP creation, + * mark the VMCB dirty so that full state is always reloaded. + */ + vmcb_mark_all_dirty(svm->vmcb); + + return 0; +} + +/* + * Invoked as part of svm_vcpu_reset() processing of an init event. + */ +void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + if (!sev_snp_guest(vcpu->kvm)) + return; + + mutex_lock(&svm->sev_es.snp_vmsa_mutex); + + if (!svm->sev_es.snp_ap_waiting_for_reset) + goto unlock; + + svm->sev_es.snp_ap_waiting_for_reset = false; + + ret = __sev_snp_update_protected_guest_state(vcpu); + if (ret) + vcpu_unimpl(vcpu, "snp: AP state update on init failed\n"); + +unlock: + mutex_unlock(&svm->sev_es.snp_vmsa_mutex); +} + +static int sev_snp_ap_creation(struct vcpu_svm *svm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm); + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_vcpu *target_vcpu; + struct vcpu_svm *target_svm; + unsigned int request; + unsigned int apic_id; + int ret; + + request = lower_32_bits(svm->vmcb->control.exit_info_1); + apic_id = upper_32_bits(svm->vmcb->control.exit_info_1); + + /* Validate the APIC ID */ + target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, apic_id); + if (!target_vcpu) { + vcpu_unimpl(vcpu, "vmgexit: invalid AP APIC ID [%#x] from guest\n", + apic_id); + return -EINVAL; + } + + ret = 0; + + target_svm = to_svm(target_vcpu); + + mutex_lock(&target_svm->sev_es.snp_vmsa_mutex); + + switch (request) { + case SVM_VMGEXIT_AP_CREATE_ON_INIT: + case SVM_VMGEXIT_AP_CREATE: + if (vcpu->arch.regs[VCPU_REGS_RAX] != sev->vmsa_features) { + vcpu_unimpl(vcpu, "vmgexit: mismatched AP sev_features [%#lx] != [%#llx] from guest\n", + vcpu->arch.regs[VCPU_REGS_RAX], sev->vmsa_features); + ret = -EINVAL; + goto out; + } + + if (!page_address_valid(vcpu, svm->vmcb->control.exit_info_2)) { + vcpu_unimpl(vcpu, "vmgexit: invalid AP VMSA address [%#llx] from guest\n", + svm->vmcb->control.exit_info_2); + ret = -EINVAL; + goto out; + } + + /* + * Malicious guest can RMPADJUST a large page into VMSA which + * will hit the SNP erratum where the CPU will incorrectly signal + * an RMP violation #PF if a hugepage collides with the RMP entry + * of VMSA page, reject the AP CREATE request if VMSA address from + * guest is 2M aligned. */ - svm->sev_es.ghcb_sa_sync = sync; - svm->sev_es.ghcb_sa_free = true; + if (IS_ALIGNED(svm->vmcb->control.exit_info_2, PMD_SIZE)) { + vcpu_unimpl(vcpu, + "vmgexit: AP VMSA address [%llx] from guest is unsafe as it is 2M aligned\n", + svm->vmcb->control.exit_info_2); + ret = -EINVAL; + goto out; + } + + target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2; + break; + case SVM_VMGEXIT_AP_DESTROY: + target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE; + break; + default: + vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n", + request); + ret = -EINVAL; + goto out; } - svm->sev_es.ghcb_sa = scratch_va; - svm->sev_es.ghcb_sa_len = len; + target_svm->sev_es.snp_ap_waiting_for_reset = true; - return 0; + /* + * Unless Creation is deferred until INIT, signal the vCPU to update + * its state. + */ + if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) + kvm_make_request_and_kick(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu); -e_scratch: - ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); - ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); +out: + mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex); - return 1; + return ret; } -static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, - unsigned int pos) +static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa) { - svm->vmcb->control.ghcb_gpa &= ~(mask << pos); - svm->vmcb->control.ghcb_gpa |= (value & mask) << pos; -} + struct sev_data_snp_guest_request data = {0}; + struct kvm *kvm = svm->vcpu.kvm; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + sev_ret_code fw_err = 0; + int ret; -static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos) -{ - return (svm->vmcb->control.ghcb_gpa >> pos) & mask; + if (!sev_snp_guest(kvm)) + return -EINVAL; + + mutex_lock(&sev->guest_req_mutex); + + if (kvm_read_guest(kvm, req_gpa, sev->guest_req_buf, PAGE_SIZE)) { + ret = -EIO; + goto out_unlock; + } + + data.gctx_paddr = __psp_pa(sev->snp_context); + data.req_paddr = __psp_pa(sev->guest_req_buf); + data.res_paddr = __psp_pa(sev->guest_resp_buf); + + /* + * Firmware failures are propagated on to guest, but any other failure + * condition along the way should be reported to userspace. E.g. if + * the PSP is dead and commands are timing out. + */ + ret = sev_issue_cmd(kvm, SEV_CMD_SNP_GUEST_REQUEST, &data, &fw_err); + if (ret && !fw_err) + goto out_unlock; + + if (kvm_write_guest(kvm, resp_gpa, sev->guest_resp_buf, PAGE_SIZE)) { + ret = -EIO; + goto out_unlock; + } + + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, SNP_GUEST_ERR(0, fw_err)); + + ret = 1; /* resume guest */ + +out_unlock: + mutex_unlock(&sev->guest_req_mutex); + return ret; } -static void set_ghcb_msr(struct vcpu_svm *svm, u64 value) +static int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa) { - svm->vmcb->control.ghcb_gpa = value; + struct kvm *kvm = svm->vcpu.kvm; + u8 msg_type; + + if (!sev_snp_guest(kvm)) + return -EINVAL; + + if (kvm_read_guest(kvm, req_gpa + offsetof(struct snp_guest_msg_hdr, msg_type), + &msg_type, 1)) + return -EIO; + + /* + * As per GHCB spec, requests of type MSG_REPORT_REQ also allow for + * additional certificate data to be provided alongside the attestation + * report via the guest-provided data pages indicated by RAX/RBX. The + * certificate data is optional and requires additional KVM enablement + * to provide an interface for userspace to provide it, but KVM still + * needs to be able to handle extended guest requests either way. So + * provide a stub implementation that will always return an empty + * certificate table in the guest-provided data pages. + */ + if (msg_type == SNP_MSG_REPORT_REQ) { + struct kvm_vcpu *vcpu = &svm->vcpu; + u64 data_npages; + gpa_t data_gpa; + + if (!kvm_ghcb_rax_is_valid(svm) || !kvm_ghcb_rbx_is_valid(svm)) + goto request_invalid; + + data_gpa = vcpu->arch.regs[VCPU_REGS_RAX]; + data_npages = vcpu->arch.regs[VCPU_REGS_RBX]; + + if (!PAGE_ALIGNED(data_gpa)) + goto request_invalid; + + /* + * As per GHCB spec (see "SNP Extended Guest Request"), the + * certificate table is terminated by 24-bytes of zeroes. + */ + if (data_npages && kvm_clear_guest(kvm, data_gpa, 24)) + return -EIO; + } + + return snp_handle_guest_req(svm, req_gpa, resp_gpa); + +request_invalid: + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT); + return 1; /* resume guest */ } static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm); u64 ghcb_info; int ret = 1; @@ -2964,7 +4299,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) switch (ghcb_info) { case GHCB_MSR_SEV_INFO_REQ: - set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version, GHCB_VERSION_MIN, sev_enc_bit)); break; @@ -3006,6 +4341,60 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_INFO_POS); break; } + case GHCB_MSR_AP_RESET_HOLD_REQ: + svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_MSR_PROTO; + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + + /* + * Preset the result to a non-SIPI return and then only set + * the result to non-zero when delivering a SIPI. + */ + set_ghcb_msr_bits(svm, 0, + GHCB_MSR_AP_RESET_HOLD_RESULT_MASK, + GHCB_MSR_AP_RESET_HOLD_RESULT_POS); + + set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP, + GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + case GHCB_MSR_HV_FT_REQ: + set_ghcb_msr_bits(svm, GHCB_HV_FT_SUPPORTED, + GHCB_MSR_HV_FT_MASK, GHCB_MSR_HV_FT_POS); + set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP, + GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS); + break; + case GHCB_MSR_PREF_GPA_REQ: + if (!sev_snp_guest(vcpu->kvm)) + goto out_terminate; + + set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_NONE, GHCB_MSR_GPA_VALUE_MASK, + GHCB_MSR_GPA_VALUE_POS); + set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_RESP, GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + case GHCB_MSR_REG_GPA_REQ: { + u64 gfn; + + if (!sev_snp_guest(vcpu->kvm)) + goto out_terminate; + + gfn = get_ghcb_msr_bits(svm, GHCB_MSR_GPA_VALUE_MASK, + GHCB_MSR_GPA_VALUE_POS); + + svm->sev_es.ghcb_registered_gpa = gfn_to_gpa(gfn); + + set_ghcb_msr_bits(svm, gfn, GHCB_MSR_GPA_VALUE_MASK, + GHCB_MSR_GPA_VALUE_POS); + set_ghcb_msr_bits(svm, GHCB_MSR_REG_GPA_RESP, GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + } + case GHCB_MSR_PSC_REQ: + if (!sev_snp_guest(vcpu->kvm)) + goto out_terminate; + + ret = snp_begin_psc_msr(svm, control->ghcb_gpa); + break; case GHCB_MSR_TERM_REQ: { u64 reason_set, reason_code; @@ -3018,12 +4407,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); - vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; - vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM; - vcpu->run->system_event.ndata = 1; - vcpu->run->system_event.data[0] = control->ghcb_gpa; - - return 0; + goto out_terminate; } default: /* Error, keep GHCB MSR value as-is */ @@ -3034,6 +4418,14 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) control->ghcb_gpa, ret); return ret; + +out_terminate: + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = control->ghcb_gpa; + + return 0; } int sev_handle_vmgexit(struct kvm_vcpu *vcpu) @@ -3069,6 +4461,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb); sev_es_sync_from_ghcb(svm); + + /* SEV-SNP guest requires that the GHCB GPA must be registered */ + if (sev_snp_guest(svm->vcpu.kvm) && !ghcb_gpa_is_registered(svm, ghcb_gpa)) { + vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB GPA [%#llx] is not registered.\n", ghcb_gpa); + return -EINVAL; + } + ret = sev_es_validate_vmgexit(svm); if (ret) return ret; @@ -3105,10 +4504,11 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = 1; break; case SVM_VMGEXIT_AP_HLT_LOOP: + svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NAE_EVENT; ret = kvm_emulate_ap_reset_hold(vcpu); break; case SVM_VMGEXIT_AP_JUMP_TABLE: { - struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm); switch (control->exit_info_1) { case 0: @@ -3129,6 +4529,41 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = 1; break; } + case SVM_VMGEXIT_HV_FEATURES: + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_HV_FT_SUPPORTED); + + ret = 1; + break; + case SVM_VMGEXIT_TERM_REQUEST: + pr_info("SEV-ES guest requested termination: reason %#llx info %#llx\n", + control->exit_info_1, control->exit_info_2); + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = control->ghcb_gpa; + break; + case SVM_VMGEXIT_PSC: + ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); + if (ret) + break; + + ret = snp_begin_psc(svm, svm->sev_es.ghcb_sa); + break; + case SVM_VMGEXIT_AP_CREATION: + ret = sev_snp_ap_creation(svm); + if (ret) { + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT); + } + + ret = 1; + break; + case SVM_VMGEXIT_GUEST_REQUEST: + ret = snp_handle_guest_req(svm, control->exit_info_1, control->exit_info_2); + break; + case SVM_VMGEXIT_EXT_GUEST_REQUEST: + ret = snp_handle_ext_guest_req(svm, control->exit_info_1, control->exit_info_2); + break; case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", @@ -3214,7 +4649,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; /* * An SEV-ES guest requires a VMSA area that is a separate from the @@ -3223,7 +4657,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) * the VMSA will be NULL if this vCPU is the destination for intrahost * migration, and will be copied later. */ - if (svm->sev_es.vmsa) + if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa) svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ @@ -3243,7 +4677,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) svm_set_intercept(svm, TRAP_CR8_WRITE); vmcb->control.intercepts[INTERCEPT_DR] = 0; - if (!sev_es_debug_swap_enabled) { + if (!sev_vcpu_has_debug_swap(svm)) { vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); recalc_intercepts(svm); @@ -3266,10 +4700,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) @@ -3289,17 +4719,24 @@ void sev_init_vmcb(struct vcpu_svm *svm) void sev_es_vcpu_reset(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm); + /* * Set the GHCB MSR value as per the GHCB specification when emulating * vCPU RESET for an SEV-ES guest. */ - set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version, GHCB_VERSION_MIN, sev_enc_bit)); + + mutex_init(&svm->sev_es.snp_vmsa_mutex); } -void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) +void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa) { + struct kvm *kvm = svm->vcpu.kvm; + /* * All host state for SEV-ES guests is categorized into three swap types * based on how it is handled by hardware during a world switch: @@ -3323,10 +4760,15 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) /* * If DebugSwap is enabled, debug registers are loaded but NOT saved by - * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both - * saves and loads debug registers (Type-A). + * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does + * not save or load debug registers. Sadly, on CPUs without + * ALLOWED_SEV_FEATURES, KVM can't prevent SNP guests from enabling + * DebugSwap on secondary vCPUs without KVM's knowledge via "AP Create". + * Save all registers if DebugSwap is supported to prevent host state + * from being clobbered by a misbehaving guest. */ - if (sev_es_debug_swap_enabled) { + if (sev_vcpu_has_debug_swap(svm) || + (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) { hostsa->dr0 = native_get_debugreg(0); hostsa->dr1 = native_get_debugreg(1); hostsa->dr2 = native_get_debugreg(2); @@ -3348,13 +4790,329 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) return; } + /* Subsequent SIPI */ + switch (svm->sev_es.ap_reset_hold_type) { + case AP_RESET_HOLD_NAE_EVENT: + /* + * Return from an AP Reset Hold VMGEXIT, where the guest will + * set the CS and RIP. Set SW_EXIT_INFO_2 to a non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); + break; + case AP_RESET_HOLD_MSR_PROTO: + /* + * Return from an AP Reset Hold VMGEXIT, where the guest will + * set the CS and RIP. Set GHCB data field to a non-zero value. + */ + set_ghcb_msr_bits(svm, 1, + GHCB_MSR_AP_RESET_HOLD_RESULT_MASK, + GHCB_MSR_AP_RESET_HOLD_RESULT_POS); + + set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP, + GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + default: + break; + } +} + +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) +{ + unsigned long pfn; + struct page *p; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + /* - * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where - * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a - * non-zero value. + * Allocate an SNP-safe page to workaround the SNP erratum where + * the CPU will incorrectly signal an RMP violation #PF if a + * hugepage (2MB or 1GB) collides with the RMP entry of a + * 2MB-aligned VMCB, VMSA, or AVIC backing page. + * + * Allocate one extra page, choose a page which is not + * 2MB-aligned, and free the other. */ - if (!svm->sev_es.ghcb) + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + pfn = page_to_pfn(p); + if (IS_ALIGNED(pfn, PTRS_PER_PMD)) + __free_page(p++); + else + __free_page(p + 1); + + return p; +} + +void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) +{ + struct kvm_memory_slot *slot; + struct kvm *kvm = vcpu->kvm; + int order, rmp_level, ret; + bool assigned; + kvm_pfn_t pfn; + gfn_t gfn; + + gfn = gpa >> PAGE_SHIFT; + + /* + * The only time RMP faults occur for shared pages is when the guest is + * triggering an RMP fault for an implicit page-state change from + * shared->private. Implicit page-state changes are forwarded to + * userspace via KVM_EXIT_MEMORY_FAULT events, however, so RMP faults + * for shared pages should not end up here. + */ + if (!kvm_mem_is_private(kvm, gfn)) { + pr_warn_ratelimited("SEV: Unexpected RMP fault for non-private GPA 0x%llx\n", + gpa); + return; + } + + slot = gfn_to_memslot(kvm, gfn); + if (!kvm_slot_can_be_private(slot)) { + pr_warn_ratelimited("SEV: Unexpected RMP fault, non-private slot for GPA 0x%llx\n", + gpa); + return; + } + + ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &order); + if (ret) { + pr_warn_ratelimited("SEV: Unexpected RMP fault, no backing page for private GPA 0x%llx\n", + gpa); + return; + } + + ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level); + if (ret || !assigned) { + pr_warn_ratelimited("SEV: Unexpected RMP fault, no assigned RMP entry found for GPA 0x%llx PFN 0x%llx error %d\n", + gpa, pfn, ret); + goto out_no_trace; + } + + /* + * There are 2 cases where a PSMASH may be needed to resolve an #NPF + * with PFERR_GUEST_RMP_BIT set: + * + * 1) RMPADJUST/PVALIDATE can trigger an #NPF with PFERR_GUEST_SIZEM + * bit set if the guest issues them with a smaller granularity than + * what is indicated by the page-size bit in the 2MB RMP entry for + * the PFN that backs the GPA. + * + * 2) Guest access via NPT can trigger an #NPF if the NPT mapping is + * smaller than what is indicated by the 2MB RMP entry for the PFN + * that backs the GPA. + * + * In both these cases, the corresponding 2M RMP entry needs to + * be PSMASH'd to 512 4K RMP entries. If the RMP entry is already + * split into 4K RMP entries, then this is likely a spurious case which + * can occur when there are concurrent accesses by the guest to a 2MB + * GPA range that is backed by a 2MB-aligned PFN who's RMP entry is in + * the process of being PMASH'd into 4K entries. These cases should + * resolve automatically on subsequent accesses, so just ignore them + * here. + */ + if (rmp_level == PG_LEVEL_4K) + goto out; + + ret = snp_rmptable_psmash(pfn); + if (ret) { + /* + * Look it up again. If it's 4K now then the PSMASH may have + * raced with another process and the issue has already resolved + * itself. + */ + if (!snp_lookup_rmpentry(pfn, &assigned, &rmp_level) && + assigned && rmp_level == PG_LEVEL_4K) + goto out; + + pr_warn_ratelimited("SEV: Unable to split RMP entry for GPA 0x%llx PFN 0x%llx ret %d\n", + gpa, pfn, ret); + } + + kvm_zap_gfn_range(kvm, gfn, gfn + PTRS_PER_PMD); +out: + trace_kvm_rmp_fault(vcpu, gpa, pfn, error_code, rmp_level, ret); +out_no_trace: + put_page(pfn_to_page(pfn)); +} + +static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end) +{ + kvm_pfn_t pfn = start; + + while (pfn < end) { + int ret, rmp_level; + bool assigned; + + ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level); + if (ret) { + pr_warn_ratelimited("SEV: Failed to retrieve RMP entry: PFN 0x%llx GFN start 0x%llx GFN end 0x%llx RMP level %d error %d\n", + pfn, start, end, rmp_level, ret); + return false; + } + + if (assigned) { + pr_debug("%s: overlap detected, PFN 0x%llx start 0x%llx end 0x%llx RMP level %d\n", + __func__, pfn, start, end, rmp_level); + return false; + } + + pfn++; + } + + return true; +} + +static u8 max_level_for_order(int order) +{ + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static bool is_large_rmp_possible(struct kvm *kvm, kvm_pfn_t pfn, int order) +{ + kvm_pfn_t pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD); + + /* + * If this is a large folio, and the entire 2M range containing the + * PFN is currently shared, then the entire 2M-aligned range can be + * set to private via a single 2M RMP entry. + */ + if (max_level_for_order(order) > PG_LEVEL_4K && + is_pfn_range_shared(pfn_aligned, pfn_aligned + PTRS_PER_PMD)) + return true; + + return false; +} + +int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + kvm_pfn_t pfn_aligned; + gfn_t gfn_aligned; + int level, rc; + bool assigned; + + if (!sev_snp_guest(kvm)) + return 0; + + rc = snp_lookup_rmpentry(pfn, &assigned, &level); + if (rc) { + pr_err_ratelimited("SEV: Failed to look up RMP entry: GFN %llx PFN %llx error %d\n", + gfn, pfn, rc); + return -ENOENT; + } + + if (assigned) { + pr_debug("%s: already assigned: gfn %llx pfn %llx max_order %d level %d\n", + __func__, gfn, pfn, max_order, level); + return 0; + } + + if (is_large_rmp_possible(kvm, pfn, max_order)) { + level = PG_LEVEL_2M; + pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD); + gfn_aligned = ALIGN_DOWN(gfn, PTRS_PER_PMD); + } else { + level = PG_LEVEL_4K; + pfn_aligned = pfn; + gfn_aligned = gfn; + } + + rc = rmp_make_private(pfn_aligned, gfn_to_gpa(gfn_aligned), level, sev->asid, false); + if (rc) { + pr_err_ratelimited("SEV: Failed to update RMP entry: GFN %llx PFN %llx level %d error %d\n", + gfn, pfn, level, rc); + return -EINVAL; + } + + pr_debug("%s: updated: gfn %llx pfn %llx pfn_aligned %llx max_order %d level %d\n", + __func__, gfn, pfn, pfn_aligned, max_order, level); + + return 0; +} + +void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) +{ + kvm_pfn_t pfn; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return; - ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); + pr_debug("%s: PFN start 0x%llx PFN end 0x%llx\n", __func__, start, end); + + for (pfn = start; pfn < end;) { + bool use_2m_update = false; + int rc, rmp_level; + bool assigned; + + rc = snp_lookup_rmpentry(pfn, &assigned, &rmp_level); + if (rc || !assigned) + goto next_pfn; + + use_2m_update = IS_ALIGNED(pfn, PTRS_PER_PMD) && + end >= (pfn + PTRS_PER_PMD) && + rmp_level > PG_LEVEL_4K; + + /* + * If an unaligned PFN corresponds to a 2M region assigned as a + * large page in the RMP table, PSMASH the region into individual + * 4K RMP entries before attempting to convert a 4K sub-page. + */ + if (!use_2m_update && rmp_level > PG_LEVEL_4K) { + /* + * This shouldn't fail, but if it does, report it, but + * still try to update RMP entry to shared and pray this + * was a spurious error that can be addressed later. + */ + rc = snp_rmptable_psmash(pfn); + WARN_ONCE(rc, "SEV: Failed to PSMASH RMP entry for PFN 0x%llx error %d\n", + pfn, rc); + } + + rc = rmp_make_shared(pfn, use_2m_update ? PG_LEVEL_2M : PG_LEVEL_4K); + if (WARN_ONCE(rc, "SEV: Failed to update RMP entry for PFN 0x%llx error %d\n", + pfn, rc)) + goto next_pfn; + + /* + * SEV-ES avoids host/guest cache coherency issues through + * WBINVD hooks issued via MMU notifiers during run-time, and + * KVM's VM destroy path at shutdown. Those MMU notifier events + * don't cover gmem since there is no requirement to map pages + * to a HVA in order to use them for a running guest. While the + * shutdown path would still likely cover things for SNP guests, + * userspace may also free gmem pages during run-time via + * hole-punching operations on the guest_memfd, so flush the + * cache entries for these pages before free'ing them back to + * the host. + */ + clflush_cache_range(__va(pfn_to_hpa(pfn)), + use_2m_update ? PMD_SIZE : PAGE_SIZE); +next_pfn: + pfn += use_2m_update ? PTRS_PER_PMD : 1; + cond_resched(); + } +} + +int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +{ + int level, rc; + bool assigned; + + if (!sev_snp_guest(kvm)) + return 0; + + rc = snp_lookup_rmpentry(pfn, &assigned, &level); + if (rc || !assigned) + return PG_LEVEL_4K; + + return level; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1f9490aa840971aad035f455116e5a9c7fb45624..9d4daf8c70556813c6e29e316b5a6f72e905be3a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -219,7 +220,7 @@ int vgif = true; module_param(vgif, int, 0444); /* enable/disable LBR virtualization */ -static int lbrv = true; +int lbrv = true; module_param(lbrv, int, 0444); static int tsc_scaling = true; @@ -380,8 +381,8 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK; } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len); +static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, bool commit_side_effects) @@ -407,7 +408,7 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, * right thing and treats "can't emulate" as outright failure * for EMULTYPE_SKIP. */ - if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0)) + if (svm_check_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0) != X86EMUL_CONTINUE) return 0; if (unlikely(!commit_side_effects)) @@ -737,7 +738,7 @@ static int svm_cpu_init(int cpu) int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); + sd->save_area = snp_safe_alloc_page(NULL); if (!sd->save_area) return ret; @@ -1024,7 +1025,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } -static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1034,6 +1035,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + if (sev_es_guest(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); @@ -1043,6 +1047,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); @@ -1447,6 +1453,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; + if (init_event) + sev_snp_init_protected_guest_state(vcpu); + init_vmcb(vcpu); if (!init_event) @@ -1470,7 +1479,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); err = -ENOMEM; - vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb01_page = snp_safe_alloc_page(vcpu); if (!vmcb01_page) goto out; @@ -1479,7 +1488,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) * SEV-ES guests require a separate VMSA page used to contain * the encrypted register state of the guest. */ - vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmsa_page = snp_safe_alloc_page(vcpu); if (!vmsa_page) goto error_free_vmcb_page; @@ -1487,14 +1496,6 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) if (csv2_setup_reset_vmsa(svm)) goto error_free_vmsa_page; } - - /* - * SEV-ES guests maintain an encrypted version of their FPU - * state which is restored and saved on VMRUN and VMEXIT. - * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't - * do xsave/xrstor on it. - */ - fpstate_set_confidential(&vcpu->arch.guest_fpu); } err = avic_init_vcpu(svm); @@ -1580,7 +1581,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) struct sev_es_save_area *hostsa; hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - sev_es_prepare_switch_to_guest(hostsa); + sev_es_prepare_switch_to_guest(svm, hostsa); } if (tsc_scaling) @@ -2108,15 +2109,33 @@ static int pf_interception(struct kvm_vcpu *vcpu) static int npf_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + int rc; u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; + /* + * WARN if hardware generates a fault with an error code that collides + * with KVM-defined sythentic flags. Clear the flags and continue on, + * i.e. don't terminate the VM, as KVM can't possibly be relying on a + * flag that KVM doesn't know about. + */ + if (WARN_ON_ONCE(error_code & PFERR_SYNTHETIC_MASK)) + error_code &= ~PFERR_SYNTHETIC_MASK; + + if (sev_snp_guest(vcpu->kvm) && (error_code & PFERR_GUEST_ENC_MASK)) + error_code |= PFERR_PRIVATE_ACCESS; + trace_kvm_page_fault(vcpu, fault_address, error_code); - return kvm_mmu_page_fault(vcpu, fault_address, error_code, - static_cpu_has(X86_FEATURE_DECODEASSISTS) ? - svm->vmcb->control.insn_bytes : NULL, - svm->vmcb->control.insn_len); + rc = kvm_mmu_page_fault(vcpu, fault_address, error_code, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, + svm->vmcb->control.insn_len); + + if (rc > 0 && error_code & PFERR_GUEST_RMP_MASK) + sev_handle_rmp_fault(vcpu, fault_address, error_code); + + return rc; } static int db_interception(struct kvm_vcpu *vcpu) @@ -2881,10 +2900,24 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) return 0; } +static bool +sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + return sev_es_guest(vcpu->kvm) && + vcpu->arch.guest_state_protected && + svm_msrpm_offset(msr_info->index) != MSR_INVALID && + !msr_write_intercepted(vcpu, msr_info->index); +} + static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); + if (sev_es_prevent_msr_access(vcpu, msr_info)) { + msr_info->data = 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + } + switch (msr_info->index) { case MSR_AMD64_TSC_RATIO: if (!msr_info->host_initiated && @@ -3047,6 +3080,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u32 ecx = msr->index; u64 data = msr->data; + + if (sev_es_prevent_msr_access(vcpu, msr)) + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + switch (ecx) { case MSR_AMD64_TSC_RATIO: @@ -3413,7 +3450,9 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, +#ifdef CONFIG_KVM_AMD_SEV [SVM_EXIT_VMGEXIT] = sev_handle_vmgexit, +#endif }; static void dump_vmcb(struct kvm_vcpu *vcpu) @@ -3637,7 +3676,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return svm_invoke_exit_handler(vcpu, exit_code); } -static void pre_svm_run(struct kvm_vcpu *vcpu) +static int pre_svm_run(struct kvm_vcpu *vcpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); @@ -3659,6 +3698,8 @@ static void pre_svm_run(struct kvm_vcpu *vcpu) /* FIXME: handle wraparound of asid_generation */ if (svm->current_vmcb->asid_generation != sd->asid_generation) new_asid(svm, sd); + + return 0; } static void svm_inject_nmi(struct kvm_vcpu *vcpu) @@ -4198,6 +4239,9 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) { + if (to_kvm_sev_info(vcpu->kvm)->need_init) + return -EINVAL; + return 1; } @@ -4266,7 +4310,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) smp_send_reschedule(vcpu->cpu); } - pre_svm_run(vcpu); + if (pre_svm_run(vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; + vcpu->run->fail_entry.hardware_entry_failure_reason = SVM_EXIT_ERR; + vcpu->run->fail_entry.cpu = vcpu->cpu; + return EXIT_FASTPATH_EXIT_USERSPACE; + } sync_lapic_to_cr8(vcpu); @@ -4848,15 +4897,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } #endif -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; u64 error_code; /* Emulation is always possible when KVM has access to all guest state. */ if (!sev_guest(vcpu->kvm)) - return true; + return X86EMUL_CONTINUE; /* #UD and #GP should never be intercepted for SEV guests. */ WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | @@ -4868,14 +4917,14 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * to guest register state. */ if (sev_es_guest(vcpu->kvm)) - return false; + return X86EMUL_RETRY_INSTR; /* * Emulation is possible if the instruction is already decoded, e.g. * when completing I/O after returning from userspace. */ if (emul_type & EMULTYPE_NO_DECODE) - return true; + return X86EMUL_CONTINUE; /* * Emulation is possible for SEV guests if and only if a prefilled @@ -4901,9 +4950,11 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * success (and in practice it will work the vast majority of the time). */ if (unlikely(!insn)) { - if (!(emul_type & EMULTYPE_SKIP)) - kvm_queue_exception(vcpu, UD_VECTOR); - return false; + if (emul_type & EMULTYPE_SKIP) + return X86EMUL_RETRY_INSTR; + + kvm_queue_exception(vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; } /* @@ -4914,7 +4965,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * table used to translate CS:RIP resides in emulated MMIO. */ if (likely(insn_len)) - return true; + return X86EMUL_CONTINUE; /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. @@ -4972,6 +5023,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, kvm_inject_gp(vcpu, 0); else kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return X86EMUL_PROPAGATE_FAULT; } resume_guest: @@ -4989,7 +5041,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * doesn't explicitly define "ignored", i.e. doing nothing and letting * the guest spin is technically "ignoring" the access. */ - return false; + return X86EMUL_RETRY_INSTR; } static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) @@ -5015,6 +5067,18 @@ static void svm_vm_destroy(struct kvm *kvm) static int svm_vm_init(struct kvm *kvm) { + int type = kvm->arch.vm_type; + + if (type != KVM_X86_DEFAULT_VM && + type != KVM_X86_SW_PROTECTED_VM) { + kvm->arch.has_protected_state = + (type == KVM_X86_SEV_ES_VM || type == KVM_X86_SNP_VM); + to_kvm_sev_info(kvm)->need_init = true; + + kvm->arch.has_private_mem = (type == KVM_X86_SNP_VM); + kvm->arch.pre_fault_allowed = !kvm->arch.has_private_mem; + } + if (!pause_filter_count || !pause_filter_thresh) kvm->arch.pause_in_guest = true; @@ -5027,6 +5091,16 @@ static int svm_vm_init(struct kvm *kvm) return 0; } +static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu) +{ + struct page *page = snp_safe_alloc_page(vcpu); + + if (!page) + return NULL; + + return page_address(page); +} + static struct kvm_x86_ops svm_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -5143,6 +5217,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_smi_window = svm_enable_smi_window, #endif +#ifdef CONFIG_KVM_AMD_SEV + .dev_get_attr = sev_dev_get_attr, .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, .mem_enc_unregister_region = sev_mem_enc_unregister_region, @@ -5150,8 +5226,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, - - .can_emulate_instruction = svm_can_emulate_instruction, +#endif + .check_emulate_instruction = svm_check_emulate_instruction, .apic_init_signal_blocked = svm_apic_init_signal_blocked, @@ -5160,6 +5236,11 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, .vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons, + .alloc_apic_backing_page = svm_alloc_apic_backing_page, + + .gmem_prepare = sev_gmem_prepare, + .gmem_invalidate = sev_gmem_invalidate, + .private_max_mapping_level = sev_private_max_mapping_level, }; /* @@ -5390,6 +5471,12 @@ static __init int svm_hardware_setup(void) nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5443,14 +5530,6 @@ static __init int svm_hardware_setup(void) svm_x86_ops.set_vnmi_pending = NULL; } - - if (lbrv) { - if (!boot_cpu_has(X86_FEATURE_LBRV)) - lbrv = false; - else - pr_info("LBR virtualization supported\n"); - } - if (!enable_pmu) pr_info("PMU virtualization is disabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 1108dd91b10755250a55a3fe2e9d46350765d456..3c54702c747b03c9dbb6e31daebfff725ed0f5ee 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -32,7 +32,7 @@ #define GUEST_PAT_WB_ATTR 0x0606060606060606 -#define MAX_DIRECT_ACCESS_MSRS 47 +#define MAX_DIRECT_ACCESS_MSRS 48 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -41,6 +41,7 @@ extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; extern bool vnmi; +extern int lbrv; /* * Clean bits in VMCB. @@ -81,17 +82,24 @@ enum { struct kvm_sev_info { bool active; /* SEV enabled guest */ bool es_active; /* SEV-ES enabled guest */ + bool need_init; /* waiting for SEV_INIT2 */ unsigned int asid; /* ASID used for this guest */ unsigned int handle; /* SEV firmware handle */ int fd; /* SEV device fd */ unsigned long pages_locked; /* Number of pages locked */ struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ + u64 vmsa_features; + u16 ghcb_version; /* Highest guest GHCB protocol version allowed */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct list_head mirror_vms; /* List of VMs mirroring */ struct list_head mirror_entry; /* Use as a list entry of mirrors */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ atomic_t migration_in_progress; + void *snp_context; /* SNP guest context page */ + void *guest_req_buf; /* Bounce buffer for SNP Guest Request input */ + void *guest_resp_buf; /* Bounce buffer for SNP Guest Request output */ + struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */ }; struct kvm_svm { @@ -197,6 +205,7 @@ struct vcpu_sev_es_state { u8 valid_bitmap[16]; struct kvm_host_map ghcb_map; bool received_first_sipi; + unsigned int ap_reset_hold_type; /* SEV-ES scratch area support */ u64 sw_scratch; @@ -205,12 +214,24 @@ struct vcpu_sev_es_state { bool ghcb_sa_sync; bool ghcb_sa_free; + #ifdef CONFIG_HYGON_CSV /* migrated ghcb mapping state for HYGON CSV2 */ bool receiver_ghcb_map_fail; /* CSV2 reboot vmsa */ struct vmcb_save_area *reset_vmsa; #endif + /* SNP Page-State-Change buffer entries currently being processed */ + u16 psc_idx; + u16 psc_inflight; + bool psc_2m; + + u64 ghcb_registered_gpa; + + struct mutex snp_vmsa_mutex; /* Used to handle concurrent updates of VMSA. */ + gpa_t snp_vmsa_gpa; + bool snp_ap_waiting_for_reset; + bool snp_has_guest_vmsa; }; struct vcpu_svm { @@ -325,26 +346,39 @@ static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) return container_of(kvm, struct kvm_svm, kvm); } -static __always_inline bool sev_guest(struct kvm *kvm) +static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - return sev->active; -#else - return false; -#endif + return &to_kvm_svm(kvm)->sev_info; } +#ifdef CONFIG_KVM_AMD_SEV +static __always_inline bool sev_guest(struct kvm *kvm) +{ + return to_kvm_sev_info(kvm)->active; +} static __always_inline bool sev_es_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); return sev->es_active && !WARN_ON_ONCE(!sev->active); +} + +static __always_inline bool sev_snp_guest(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + + return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) && + !WARN_ON_ONCE(!sev_es_guest(kvm)); +} #else - return false; +#define sev_guest(kvm) false +#define sev_es_guest(kvm) false +#define sev_snp_guest(kvm) false #endif + +static inline bool ghcb_gpa_is_registered(struct vcpu_svm *svm, u64 val) +{ + return svm->sev_es.ghcb_registered_gpa == val; } static inline void vmcb_mark_all_dirty(struct vmcb *vmcb) @@ -550,6 +584,7 @@ u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); void svm_vcpu_free_msrpm(u32 *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu); int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -671,13 +706,16 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu); /* sev.c */ -#define GHCB_VERSION_MAX 1ULL -#define GHCB_VERSION_MIN 1ULL - - -extern unsigned int max_sev_asid; +int pre_sev_run(struct vcpu_svm *svm, int cpu); +void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); +int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); +void sev_es_vcpu_reset(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); +void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); -void sev_vm_destroy(struct kvm *kvm); +#ifdef CONFIG_KVM_AMD_SEV int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp); int sev_mem_enc_register_region(struct kvm *kvm, struct kvm_enc_region *range); @@ -686,21 +724,49 @@ int sev_mem_enc_unregister_region(struct kvm *kvm, int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); void sev_guest_memory_reclaimed(struct kvm *kvm); +int sev_handle_vmgexit(struct kvm_vcpu *vcpu); -void pre_sev_run(struct vcpu_svm *svm, int cpu); +/* These symbols are used in common code and are stubbed below. */ +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); +void sev_free_vcpu(struct kvm_vcpu *vcpu); +void sev_vm_destroy(struct kvm *kvm); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); -void sev_init_vmcb(struct vcpu_svm *svm); -void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); -void sev_free_vcpu(struct kvm_vcpu *vcpu); -int sev_handle_vmgexit(struct kvm_vcpu *vcpu); -int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); -void sev_es_vcpu_reset(struct vcpu_svm *svm); -void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); -void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); -void sev_es_unmap_ghcb(struct vcpu_svm *svm); +int sev_dev_get_attr(u32 group, u64 attr, u64 *val); +extern unsigned int max_sev_asid; +void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code); +void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu); +int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); +void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); +int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn); +#else +static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) { + return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); +} + +static inline void sev_free_vcpu(struct kvm_vcpu *vcpu) {} +static inline void sev_vm_destroy(struct kvm *kvm) {} +static inline void __init sev_set_cpu_caps(void) {} +static inline void __init sev_hardware_setup(void) {} +static inline void sev_hardware_unsetup(void) {} +static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; } +static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; } +#define max_sev_asid 0 +static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {} +static inline void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) {} +static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order) +{ + return 0; +} +static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {} +static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +{ + return 0; +} + +#endif /* vmenter.S */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b82e6ed4f024174658114321d85a60529a3df119..5c1cd6520224a843ed1e3b98e56e46c952ab5b19 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1831,6 +1831,37 @@ TRACE_EVENT(kvm_vmgexit_msr_protocol_exit, __entry->vcpu_id, __entry->ghcb_gpa, __entry->result) ); +/* + * Tracepoint for #NPFs due to RMP faults. + */ +TRACE_EVENT(kvm_rmp_fault, + TP_PROTO(struct kvm_vcpu *vcpu, u64 gpa, u64 pfn, u64 error_code, + int rmp_level, int psmash_ret), + TP_ARGS(vcpu, gpa, pfn, error_code, rmp_level, psmash_ret), + + TP_STRUCT__entry( + __field(unsigned int, vcpu_id) + __field(u64, gpa) + __field(u64, pfn) + __field(u64, error_code) + __field(int, rmp_level) + __field(int, psmash_ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->gpa = gpa; + __entry->pfn = pfn; + __entry->error_code = error_code; + __entry->rmp_level = rmp_level; + __entry->psmash_ret = psmash_ret; + ), + + TP_printk("vcpu %u gpa %016llx pfn 0x%llx error_code 0x%llx rmp_level %d psmash_ret %d", + __entry->vcpu_id, __entry->gpa, __entry->pfn, + __entry->error_code, __entry->rmp_level, __entry->psmash_ret) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index de13dc14fe1d2ff792b903d46e3be73799ac07c5..fab6a1ad98dc188c2b0f662bef9c4fd5e4bdbb8d 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,314 +13,6 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) -#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ - {EVMCS1_OFFSET(name), clean_field} - -const struct evmcs_field vmcs_field_to_evmcs_1[] = { - /* 64 bit rw */ - EVMCS1_FIELD(GUEST_RIP, guest_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_RSP, guest_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR0, host_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR3, host_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR4, host_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_RIP, host_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), - EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(TSC_OFFSET, tsc_offset, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR0, guest_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR3, guest_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR4, guest_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_DR7, guest_dr7, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_RSP, host_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(EPT_POINTER, ept_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), - EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - /* - * Not used by KVM: - * - * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x0000682A, guest_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1A, host_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - */ - - /* 64 bit read only */ - EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - /* - * Not defined in KVM: - * - * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - */ - EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* - * No mask defined in the spec as Hyper-V doesn't currently support - * these. Future proof by resetting the whole clean field mask on - * access. - */ - EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 32 bit rw */ - EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), - EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), - EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), - EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, - vm_entry_exception_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - - /* 32 bit read only */ - EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* No mask defined in the spec (not used) */ - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 16 bit rw */ - EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), -}; -const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); - u64 nested_get_evmptr(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 9401dbfaea7cef7a3418b71d6a9269d70e1383eb..ad04a3044316a3d41d519cc43d4f8946cf98fc19 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -2,178 +2,12 @@ #ifndef __KVM_X86_VMX_HYPERV_H #define __KVM_X86_VMX_HYPERV_H -#include - -#include -#include -#include - -#include "../hyperv.h" - -#include "capabilities.h" -#include "vmcs.h" +#include #include "vmcs12.h" -#define KVM_EVMCS_VERSION 1 - -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_ENABLE_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - -struct evmcs_field { - u16 offset; - u16 clean_field; -}; - -extern const struct evmcs_field vmcs_field_to_evmcs_1[]; -extern const unsigned int nr_evmcs_1_fields; - -static __always_inline int evmcs_field_offset(unsigned long field, - u16 *clean_field) -{ - unsigned int index = ROL16(field, 6); - const struct evmcs_field *evmcs_field; - - if (unlikely(index >= nr_evmcs_1_fields)) - return -ENOENT; - - evmcs_field = &vmcs_field_to_evmcs_1[index]; - - /* - * Use offset=0 to detect holes in eVMCS. This offset belongs to - * 'revision_id' but this field has no encoding and is supposed to - * be accessed directly. - */ - if (unlikely(!evmcs_field->offset)) - return -ENOENT; - - if (clean_field) - *clean_field = evmcs_field->clean_field; - - return evmcs_field->offset; -} - -static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, - unsigned long field, u16 offset) -{ - /* - * vmcs12_read_any() doesn't care whether the supplied structure - * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes - * the exact offset of the required field, use it for convenience - * here. - */ - return vmcs12_read_any((void *)evmcs, field, offset); -} - #define EVMPTR_INVALID (-1ULL) #define EVMPTR_MAP_PENDING (-2ULL) -static inline bool evmptr_is_valid(u64 evmptr) -{ - return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; -} - enum nested_evmptrld_status { EVMPTRLD_DISABLED, EVMPTRLD_SUCCEEDED, @@ -181,6 +15,12 @@ enum nested_evmptrld_status { EVMPTRLD_ERROR, }; +#ifdef CONFIG_KVM_HYPERV +static inline bool evmptr_is_valid(u64 evmptr) +{ + return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; +} + u64 nested_get_evmptr(struct kvm_vcpu *vcpu); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, @@ -189,5 +29,11 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * int nested_evmcs_check_controls(struct vmcs12 *vmcs12); bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else +static inline bool evmptr_is_valid(u64 evmptr) +{ + return false; +} +#endif #endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.c b/arch/x86/kvm/vmx/hyperv_evmcs.c new file mode 100644 index 0000000000000000000000000000000000000000..904bfcd1519b0b8b723ce4675a2489161e641b73 --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common code for working with Enlightened VMCS which is + * used both by Hyper-V on KVM and KVM on Hyper-V. + */ + +#include "hyperv_evmcs.h" + +#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) +#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ + {EVMCS1_OFFSET(name), clean_field} + +const struct evmcs_field vmcs_field_to_evmcs_1[] = { + /* 64 bit rw */ + EVMCS1_FIELD(GUEST_RIP, guest_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_RSP, guest_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR0, host_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR3, host_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR4, host_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_RIP, host_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), + EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(TSC_OFFSET, tsc_offset, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR0, guest_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR3, guest_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR4, guest_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_DR7, guest_dr7, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_RSP, host_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(EPT_POINTER, ept_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), + EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + /* + * Not used by KVM: + * + * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x0000682A, guest_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1A, host_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + */ + + /* 64 bit read only */ + EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + /* + * Not defined in KVM: + * + * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + */ + EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* + * No mask defined in the spec as Hyper-V doesn't currently support + * these. Future proof by resetting the whole clean field mask on + * access. + */ + EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 32 bit rw */ + EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), + EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), + EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), + EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, + vm_entry_exception_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + + /* 32 bit read only */ + EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* No mask defined in the spec (not used) */ + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 16 bit rw */ + EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), +}; +const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h new file mode 100644 index 0000000000000000000000000000000000000000..a543fccfc5747a50b709b9d582f502dd6a6a09dc --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains common definitions for working with Enlightened VMCS which + * are used both by Hyper-V on KVM and KVM on Hyper-V. + */ +#ifndef __KVM_X86_VMX_HYPERV_EVMCS_H +#define __KVM_X86_VMX_HYPERV_EVMCS_H + +#include + +#include "capabilities.h" +#include "vmcs12.h" + +#define KVM_EVMCS_VERSION 1 + +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + +struct evmcs_field { + u16 offset; + u16 clean_field; +}; + +extern const struct evmcs_field vmcs_field_to_evmcs_1[]; +extern const unsigned int nr_evmcs_1_fields; + +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) +{ + const struct evmcs_field *evmcs_field; + unsigned int index = ROL16(field, 6); + + if (unlikely(index >= nr_evmcs_1_fields)) + return -ENOENT; + + evmcs_field = &vmcs_field_to_evmcs_1[index]; + + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + + if (clean_field) + *clean_field = evmcs_field->clean_field; + + return evmcs_field->offset; +} + +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 4872ac288f51431bf7f75e6ca7140f2ae287f88f..c4ffe1b52921d7c3ec0046d917eaff76654c1321 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -227,6 +227,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -242,6 +243,34 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) hv_vcpu->nested.vm_id = 0; hv_vcpu->nested.vp_id = 0; } +#endif +} + +static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) +{ +#ifdef CONFIG_KVM_HYPERV + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * When Enlightened VMEntry is enabled on the calling CPU we treat + * memory area pointer by vmptr as Enlightened VMCS (as there's no good + * way to distinguish it from VMCS12) and we must not corrupt it by + * writing to the non-existent 'launch_state' field. The area doesn't + * have to be the currently active EVMCS on the calling CPU and there's + * nothing KVM has to do to transition it from 'active' to 'non-active' + * state. It is possible that the area will stay mapped as + * vmx->nested.hv_evmcs but this shouldn't be a problem. + */ + if (!guest_cpuid_has_evmcs(vcpu) || + !evmptr_is_valid(nested_get_evmptr(vcpu))) + return false; + + if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) + nested_release_evmcs(vcpu); + + return true; +#else + return false; +#endif } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -1582,6 +1611,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); @@ -1822,10 +1852,14 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields */ return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; @@ -1996,6 +2030,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } /* @@ -2005,6 +2042,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( struct kvm_vcpu *vcpu, bool from_launch) { +#ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; @@ -2086,6 +2124,9 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( } return EVMPTRLD_SUCCEEDED; +#else + return EVMPTRLD_DISABLED; +#endif } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) @@ -2903,8 +2944,10 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; +#ifdef CONFIG_KVM_HYPERV if (guest_cpuid_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); +#endif return 0; } @@ -3176,6 +3219,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3203,6 +3247,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) return true; } +#endif static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { @@ -3294,6 +3339,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV /* * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory @@ -3310,6 +3356,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } +#endif if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -4779,6 +4826,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map @@ -4788,6 +4836,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, */ (void)nested_get_evmcs_page(vcpu); } +#endif /* Service pending TLB flush requests for L2 before switching to L1. */ kvm_service_local_tlb_flush_requests(vcpu); @@ -5340,18 +5389,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); - /* - * When Enlightened VMEntry is enabled on the calling CPU we treat - * memory area pointer by vmptr as Enlightened VMCS (as there's no good - * way to distinguish it from VMCS12) and we must not corrupt it by - * writing to the non-existent 'launch_state' field. The area doesn't - * have to be the currently active EVMCS on the calling CPU and there's - * nothing KVM has to do to transition it from 'active' to 'non-active' - * state. It is possible that the area will stay mapped as - * vmx->nested.hv_evmcs but this shouldn't be a problem. - */ - if (likely(!guest_cpuid_has_evmcs(vcpu) || - !evmptr_is_valid(nested_get_evmptr(vcpu)))) { + if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -5368,8 +5406,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { - nested_release_evmcs(vcpu); } return nested_vmx_succeed(vcpu); @@ -6266,11 +6302,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, * Handle L2's bus locks in L0 directly. */ return true; +#ifdef CONFIG_KVM_HYPERV case EXIT_REASON_VMCALL: /* Hyper-V L2 TLB flush hypercall is handled by L0 */ return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && nested_evmcs_l2_tlb_flush_enabled(vcpu) && kvm_hv_is_tlb_flush_hcall(vcpu); +#endif default: break; } @@ -7154,7 +7192,9 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .set_state = vmx_set_nested_state, .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, +#ifdef CONFIG_KVM_HYPERV .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, +#endif }; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index b4b9d51438c6b3e263ce80722ae69eadc26f1fb9..b0f2e26c1aeae6b66a7af5477df8ab5c808981c1 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -3,6 +3,7 @@ #define __KVM_X86_VMX_NESTED_H #include "kvm_cache_regs.h" +#include "hyperv.h" #include "vmcs12.h" #include "vmx.h" diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ef4e2a832b5cd44a71c1eee17271482d7d802083..3837305902a9abe0d84d57b2fcf1b111801c5696 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1670,8 +1670,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1682,9 +1682,9 @@ static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, */ if (to_vmx(vcpu)->exit_reason.enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } - return true; + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -2068,6 +2068,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; +#ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V @@ -2078,6 +2079,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); +#endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) @@ -5814,7 +5816,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) + if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -6782,10 +6784,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; /* - * Grab the memslot so that the hva lookup for the mmu_notifier retry - * is guaranteed to use the same memslot as the pfn lookup, i.e. rely - * on the pfn lookup's validation of the memslot to ensure a valid hva - * is used for the retry check. + * Explicitly grab the memslot using KVM's internal slot ID to ensure + * KVM doesn't unintentionally grab a userspace memslot. It _should_ + * be impossible for userspace to create a memslot for the APIC when + * APICv is enabled, but paranoia won't hurt in this case. */ slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -6810,8 +6812,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; read_lock(&vcpu->kvm->mmu_lock); - if (mmu_invalidate_retry_hva(kvm, mmu_seq, - gfn_to_hva_memslot(slot, gfn))) { + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); read_unlock(&vcpu->kvm->mmu_lock); goto out; @@ -8443,7 +8444,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .enable_smi_window = vmx_enable_smi_window, #endif - .can_emulate_instruction = vmx_can_emulate_instruction, + .check_emulate_instruction = vmx_check_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, .migrate_timers = vmx_migrate_timers, diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index 11541d272dbd8c0982bf8a15635fefd8cb4650d1..eb48153bfd73c0d4a62420b21184712ec840e426 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -4,11 +4,12 @@ #define __ARCH_X86_KVM_VMX_ONHYPERV_H__ #include +#include #include #include "capabilities.h" -#include "hyperv.h" +#include "hyperv_evmcs.h" #include "vmcs12.h" #define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8b0af52b60ff8ad239e9841930be15a9763242b8..c8fbdca0af88f13410159f058403e942b68672d7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1555,6 +1555,8 @@ static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, @@ -1572,6 +1574,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, @@ -2234,31 +2237,34 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); u64 data; - fastpath_t ret = EXIT_FASTPATH_NONE; + fastpath_t ret; + bool handled; kvm_vcpu_srcu_read_lock(vcpu); switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_EXIT_HANDLED; - } + handled = !handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); break; case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_tscdeadline(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_REENTER_GUEST; - } + handled = !handle_fastpath_set_tscdeadline(vcpu, data); break; default: + handled = false; break; } - if (ret != EXIT_FASTPATH_NONE) + if (handled) { + if (!kvm_skip_emulated_instruction(vcpu)) + ret = EXIT_FASTPATH_EXIT_USERSPACE; + else + ret = EXIT_FASTPATH_REENTER_GUEST; trace_kvm_msr_write(msr, data); + } else { + ret = EXIT_FASTPATH_NONE; + } kvm_vcpu_srcu_read_unlock(vcpu); @@ -3153,7 +3159,8 @@ u64 get_kvmclock_ns(struct kvm *kvm) static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, struct gfn_to_pfn_cache *gpc, - unsigned int offset) + unsigned int offset, + bool force_tsc_unstable) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; @@ -3190,6 +3197,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, } memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); + + if (force_tsc_unstable) + guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT; + smp_wmb(); guest_hv_clock->version = ++vcpu->hv_clock.version; @@ -3210,6 +3221,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) u64 tsc_timestamp, host_tsc; u8 pvclock_flags; bool use_master_clock; +#ifdef CONFIG_KVM_XEN + /* + * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless + * explicitly told to use TSC as its clocksource Xen will not set this bit. + * This default behaviour led to bugs in some guest kernels which cause + * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. + */ + bool xen_pvclock_tsc_unstable = + ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; +#endif kernel_ns = 0; host_tsc = 0; @@ -3288,12 +3309,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time.active) - kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); + kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false); +#ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, - offsetof(struct compat_vcpu_info, time)); + offsetof(struct compat_vcpu_info, time), + xen_pvclock_tsc_unstable); if (vcpu->xen.vcpu_time_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0, + xen_pvclock_tsc_unstable); +#endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -3997,6 +4022,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * the need to ignore the workaround. */ break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4009,6 +4035,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -4354,6 +4381,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ msr_info->data = 0x20000000; break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4367,6 +4395,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -4504,6 +4533,7 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +#ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { @@ -4524,6 +4554,17 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, return 0; } +#endif + +static bool kvm_is_vm_type_supported(unsigned long type) +{ + return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); +} + +static inline u64 kvm_sync_valid_fields(struct kvm *kvm) +{ + return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS; +} int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { @@ -4550,9 +4591,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: @@ -4562,6 +4605,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: +#endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -4570,8 +4614,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ASYNC_PF_INT: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: - case KVM_CAP_READONLY_MEM: - case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: @@ -4602,8 +4644,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: + case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; + case KVM_CAP_PRE_FAULT_MEMORY: + r = tdp_enabled; + break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; @@ -4615,14 +4661,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; break; #endif case KVM_CAP_SYNC_REGS: - r = KVM_SYNC_X86_VALID_FIELDS; + r = kvm_sync_valid_fields(kvm); break; case KVM_CAP_ADJUST_CLOCK: r = KVM_CLOCK_VALID_FLAGS; @@ -4681,12 +4728,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; +#endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; @@ -4715,6 +4764,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; + case KVM_CAP_VM_TYPES: + r = kvm_caps.supported_vm_types; + break; case KVM_CAP_SEV_ES_GHCB: r = 0; @@ -4738,52 +4790,53 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) if (is_x86_vendor_hygon() && kvm_x86_ops.get_hygon_coco_extension) r = static_call(kvm_x86_get_hygon_coco_extension)(kvm); break; + case KVM_CAP_READONLY_MEM: + r = kvm ? kvm_arch_has_readonly_mem(kvm) : 1; + break; default: break; } return r; } -static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) +static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val) { - void __user *uaddr = (void __user*)(unsigned long)attr->addr; - - if ((u64)(unsigned long)uaddr != attr->addr) - return ERR_PTR_USR(-EFAULT); - return uaddr; -} - -static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) -{ - u64 __user *uaddr = kvm_get_attr_addr(attr); - - if (attr->group) + if (attr->group) { + if (kvm_x86_ops.dev_get_attr) + return static_call(kvm_x86_dev_get_attr)(attr->group, attr->attr, val); return -ENXIO; - - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); + } switch (attr->attr) { case KVM_X86_XCOMP_GUEST_SUPP: - if (put_user(kvm_caps.supported_xcr0, uaddr)) - return -EFAULT; + *val = kvm_caps.supported_xcr0; return 0; default: return -ENXIO; } } +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = u64_to_user_ptr(attr->addr); + int r; + u64 val; + + r = __kvm_x86_dev_get_attr(attr, &val); + if (r < 0) + return r; + + if (put_user(val, uaddr)) + return -EFAULT; + + return 0; +} + static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) { - if (attr->group) - return -ENXIO; + u64 val; - switch (attr->attr) { - case KVM_X86_XCOMP_GUEST_SUPP: - return 0; - default: - return -ENXIO; - } + return __kvm_x86_dev_get_attr(attr, &val); } long kvm_arch_dev_ioctl(struct file *filp, @@ -4871,9 +4924,11 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; +#endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; @@ -5458,21 +5513,30 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, - struct kvm_debugregs *dbgregs) +static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) { unsigned long val; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; + return 0; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (dbgregs->flags) return -EINVAL; @@ -5491,8 +5555,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, } -static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, - u8 *state, unsigned int size) +static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) { /* * Only copy state for features that are enabled for the guest. The @@ -5510,14 +5574,15 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, XFEATURE_MASK_FPSSE; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, supported_xcr0, vcpu->arch.pkru); + return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) +static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) { return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, sizeof(guest_xsave->region)); @@ -5527,7 +5592,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, @@ -5535,18 +5600,23 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, &vcpu->arch.pkru); } -static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, - struct kvm_xcrs *guest_xcrs) +static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; - return; + return 0; } guest_xcrs->nr_xcrs = 1; guest_xcrs->flags = 0; guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; + return 0; } static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, @@ -5554,6 +5624,10 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, { int i, r = 0; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; @@ -5606,12 +5680,9 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = kvm_get_attr_addr(attr); + u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); - switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = -EFAULT; @@ -5629,13 +5700,10 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = kvm_get_attr_addr(attr); + u64 __user *uaddr = u64_to_user_ptr(attr->addr); struct kvm *kvm = vcpu->kvm; int r; - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); - switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { u64 offset, tsc, ns; @@ -5699,14 +5767,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { - int r; - uint16_t vmcs_version; - void __user *user_ptr; - if (cap->flags) return -EINVAL; switch (cap->cap) { +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; @@ -5718,16 +5783,22 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops.nested_ops->enable_evmcs) - return -ENOTTY; - r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); - if (!r) { - user_ptr = (void __user *)(uintptr_t)cap->args[0]; - if (copy_to_user(user_ptr, &vmcs_version, - sizeof(vmcs_version))) - r = -EFAULT; + { + int r; + uint16_t vmcs_version; + void __user *user_ptr; + + if (!kvm_x86_ops.nested_ops->enable_evmcs) + return -ENOTTY; + r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); + if (!r) { + user_ptr = (void __user *)(uintptr_t)cap->args[0]; + if (copy_to_user(user_ptr, &vmcs_version, + sizeof(vmcs_version))) + r = -EFAULT; + } + return r; } - return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; @@ -5736,6 +5807,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); +#endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; @@ -5939,7 +6011,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_GET_DEBUGREGS: { struct kvm_debugregs dbgregs; - kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, &dbgregs, @@ -5969,7 +6043,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!u.xsave) break; - kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) @@ -5998,7 +6074,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!u.xsave) break; - kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xsave, size)) @@ -6014,7 +6092,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!u.xcrs) break; - kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xcrs, @@ -6130,9 +6210,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; +#endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; @@ -6156,6 +6238,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_GET_SREGS2: { + r = -EINVAL; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + goto out; + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); r = -ENOMEM; if (!u.sregs2) @@ -6168,6 +6255,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_SREGS2: { + r = -EINVAL; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + goto out; + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); if (IS_ERR(u.sregs2)) { r = PTR_ERR(u.sregs2); @@ -7198,6 +7290,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; @@ -7207,6 +7300,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } +#endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; @@ -7618,11 +7712,11 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); -static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { - return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, - insn, insn_len); + return static_call(kvm_x86_check_emulate_instruction)(vcpu, emul_type, + insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) @@ -7632,8 +7726,10 @@ int handle_ud(struct kvm_vcpu *vcpu) int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; + int r; - if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) + r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); + if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && @@ -9035,7 +9131,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); + if (r != X86EMUL_CONTINUE) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -9655,6 +9752,8 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (r) goto out_free_percpu; + kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); + if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; @@ -9700,6 +9799,9 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_register_perf_callbacks(ops->handle_intel_pt_intr); + if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled) + kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM); + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; @@ -10621,19 +10723,20 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - u64 eoi_exit_bitmap[4]; - if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; +#ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { + u64 eoi_exit_bitmap[4]; + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } - +#endif static_call_cond(kvm_x86_load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } @@ -10724,9 +10827,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); +#endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -10779,6 +10884,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; @@ -10809,6 +10915,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); +#endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) @@ -10818,6 +10925,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) static_call(kvm_x86_update_cpu_dirty_logging)(vcpu); + + if (kvm_check_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) { + kvm_vcpu_reset(vcpu, true); + if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) { + r = 1; + goto out; + } + } } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || @@ -11035,6 +11150,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); + if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) + return 0; + r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath); #ifdef CONFIG_ARCH_VCPU_STAT vcpu->stat.utime = current->utime; @@ -11133,6 +11251,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -11274,6 +11393,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; + u64 sync_valid_fields; int r; vcpu_load(vcpu); @@ -11315,8 +11435,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } - if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) || - (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) { + sync_valid_fields = kvm_sync_valid_fields(vcpu->kvm); + if ((kvm_run->kvm_valid_regs & ~sync_valid_fields) || + (kvm_run->kvm_dirty_regs & ~sync_valid_fields)) { r = -EINVAL; goto out; } @@ -11374,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) out: kvm_put_guest_fpu(vcpu); - if (kvm_run->kvm_valid_regs) + if (kvm_run->kvm_valid_regs && likely(!vcpu->arch.guest_state_protected)) store_regs(vcpu); post_kvm_run_save(vcpu); kvm_vcpu_srcu_read_unlock(vcpu); @@ -11422,6 +11543,10 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __get_regs(vcpu, regs); vcpu_put(vcpu); @@ -11463,6 +11588,10 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __set_regs(vcpu, regs); vcpu_put(vcpu); @@ -11535,6 +11664,10 @@ static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __get_sregs(vcpu, sregs); vcpu_put(vcpu); @@ -11815,6 +11948,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { int ret; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); ret = __set_sregs(vcpu, sregs); vcpu_put(vcpu); @@ -11932,7 +12069,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); @@ -11955,7 +12092,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); @@ -12499,9 +12636,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) int ret; unsigned long flags; - if (type) + if (!kvm_is_vm_type_supported(type)) return -EINVAL; + kvm->arch.vm_type = type; + kvm->arch.has_private_mem = + (type == KVM_X86_SW_PROTECTED_VM); + /* Decided by the vendor code for other VM types. */ + kvm->arch.pre_fault_allowed = + type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM; + ret = kvm_page_track_init(kvm); if (ret) goto out; @@ -12641,8 +12785,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, hva = slot->userspace_addr; } - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m; + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; @@ -12792,6 +12936,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + kvm_mmu_init_memslot_memory_attributes(kvm, slot); +#endif + if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; @@ -13044,6 +13192,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_PMI, vcpu)) return true; + if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) + return true; + if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) @@ -13480,6 +13631,19 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order) +{ + return static_call(kvm_x86_gmem_prepare)(kvm, pfn, gfn, max_order); +} +#endif + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) +{ + static_call_cond(kvm_x86_gmem_invalidate)(start, end); +} +#endif int kvm_spec_ctrl_test_value(u64 value) { @@ -13884,6 +14048,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 53e883721e7167dfe2875412987a5254b3b0c83c..5252850b46182a27ccdad0c1d5717e970dc80c66 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -24,6 +24,8 @@ struct kvm_caps { bool has_bus_lock_exit; /* notify VM exit supported? */ bool has_notify_vmexit; + /* bit mask of VM types */ + u32 supported_vm_types; u64 supported_mce_cap; u64 supported_xcr0; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 0ea6016ad132a227c70a1a3e0c03b84ebc604ab4..1ee3c764084cbdd6b8a613fe682c12f4f93f44c3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1113,7 +1113,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) { /* Only some feature flags need to be *enabled* by userspace */ u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + u32 old_flags; if (xhc->flags & ~permitted_flags) return -EINVAL; @@ -1134,9 +1136,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) else if (!xhc->msr && kvm->arch.xen_hvm_config.msr) static_branch_slow_dec_deferred(&kvm_xen_enabled); + old_flags = kvm->arch.xen_hvm_config.flags; memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); mutex_unlock(&kvm->arch.xen.xen_lock); + + if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + return 0; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e568b64a2b6b822373b5168f6e3812d642e5bcdc..cb1f8b73ee9a1b455a5fdfbb9584c662aecf7a82 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -34,6 +34,7 @@ #include /* kvm_handle_async_pf */ #include /* fixup_vdso_exception() */ #include +#include /* snp_dump_hva_rmpentry() */ #define CREATE_TRACE_POINTS #include @@ -547,6 +548,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : + (error_code & X86_PF_RMP) ? "RMP violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { @@ -579,6 +581,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad } dump_pagetable(address); + + if (error_code & X86_PF_RMP) + snp_dump_hva_rmpentry(address); } static noinline void diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 050f77087d8f5c1de542fb0b2f4fe9bf0dcc7622..064cd8bbdbdd0df01e1ff1f84a3f5e95aa28779d 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -12,9 +12,12 @@ #include #include #include +#include #include +#include + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { @@ -43,43 +46,50 @@ bool force_dma_unencrypted(struct device *dev) static void print_mem_encrypt_feature_info(void) { - pr_info("Memory Encryption Features active:"); - - if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { - pr_cont(" Intel TDX\n"); - return; - } + pr_info("Memory Encryption Features active: "); if (is_x86_vendor_hygon()) { print_hygon_cc_feature_info(); return; } - pr_cont(" AMD"); + switch (cc_vendor) { + case CC_VENDOR_INTEL: + pr_cont("Intel TDX\n"); + break; + case CC_VENDOR_AMD: + pr_cont("AMD"); - /* Secure Memory Encryption */ - if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { + /* Secure Memory Encryption */ + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { /* * SME is mutually exclusive with any of the SEV * features below. - */ - pr_cont(" SME\n"); - return; - } + */ + pr_cont(" SME\n"); + return; + } - /* Secure Encrypted Virtualization */ - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - pr_cont(" SEV"); + /* Secure Encrypted Virtualization */ + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + pr_cont(" SEV"); + + /* Encrypted Register State */ + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + pr_cont(" SEV-ES"); - /* Encrypted Register State */ - if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) - pr_cont(" SEV-ES"); + /* Secure Nested Paging */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_cont(" SEV-SNP"); - /* Secure Nested Paging */ - if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) - pr_cont(" SEV-SNP"); + pr_cont("\n"); - pr_cont("\n"); + sev_show_status(); + + break; + default: + pr_cont("Unknown\n"); + } } /* Architecture __weak replacement functions */ @@ -93,3 +103,43 @@ void __init mem_encrypt_init(void) print_mem_encrypt_feature_info(); } + +void __init mem_encrypt_setup_arch(void) +{ + phys_addr_t total_mem = memblock_phys_mem_size(); + unsigned long size; + + /* + * Do RMP table fixups after the e820 tables have been setup by + * e820__memory_setup(). + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + snp_fixup_e820_tables(); + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * For SEV and TDX, all DMA has to occur via shared/unencrypted pages. + * Kernel uses SWIOTLB to make this happen without changing device + * drivers. However, depending on the workload being run, the + * default 64MB of SWIOTLB may not be enough and SWIOTLB may + * run out of buffers for DMA, resulting in I/O errors and/or + * performance degradation especially with high I/O workloads. + * + * Adjust the default size of SWIOTLB using a percentage of guest + * memory for SWIOTLB buffers. Also, as the SWIOTLB bounce buffer + * memory is allocated from low memory, ensure that the adjusted size + * is within the limits of low available memory. + * + * The percentage of guest memory used here for SWIOTLB buffers + * is more of an approximation of the static adjustment which + * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% + */ + size = total_mem * 6 / 100; + size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); + swiotlb_adjust_size(size); + + /* Set restricted memory access for virtio. */ + virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc); +} diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index f7d88ad030b9b6a6b3e1be331eda06cc2bd3d916..cd5dbe951688dea950a72ba3732f05783646a1d6 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include @@ -217,40 +216,6 @@ void __init sme_map_bootdata(char *real_mode_data) __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true); } -void __init sev_setup_arch(void) -{ - phys_addr_t total_mem = memblock_phys_mem_size(); - unsigned long size; - - if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - return; - - /* - * For SEV, all DMA has to occur via shared/unencrypted pages. - * SEV uses SWIOTLB to make this happen without changing device - * drivers. However, depending on the workload being run, the - * default 64MB of SWIOTLB may not be enough and SWIOTLB may - * run out of buffers for DMA, resulting in I/O errors and/or - * performance degradation especially with high I/O workloads. - * - * Adjust the default size of SWIOTLB for SEV guests using - * a percentage of guest memory for SWIOTLB buffers. - * Also, as the SWIOTLB bounce buffer memory is allocated - * from low memory, ensure that the adjusted size is within - * the limits of low available memory. - * - * The percentage of guest memory used here for SWIOTLB buffers - * is more of an approximation of the static adjustment which - * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% - */ - size = total_mem * 6 / 100; - size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); - swiotlb_adjust_size(size); - - /* Set restricted memory access for virtio. */ - virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc); -} - static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) { unsigned long pfn = 0; diff --git a/arch/x86/virt/svm/Makefile b/arch/x86/virt/svm/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..ef2a31bdcc7044d093283393d7f5bbe88054efd8 --- /dev/null +++ b/arch/x86/virt/svm/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KVM_AMD_SEV) += sev.o diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c new file mode 100644 index 0000000000000000000000000000000000000000..fc473ca12c44df51b12ef1b57bfe198a42c8786c --- /dev/null +++ b/arch/x86/virt/svm/sev.c @@ -0,0 +1,1071 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD SVM-SEV Host Support. + * + * Copyright (C) 2023 Advanced Micro Devices, Inc. + * + * Author: Ashish Kalra + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * The RMP entry information as returned by the RMPREAD instruction. + */ +struct rmpentry { + u64 gpa; + u8 assigned :1, + rsvd1 :7; + u8 pagesize :1, + hpage_region_status :1, + rsvd2 :6; + u8 immutable :1, + rsvd3 :7; + u8 rsvd4; + u32 asid; +} __packed; + +/* + * The raw RMP entry format is not architectural. The format is defined in PPR + * Family 19h Model 01h, Rev B1 processor. This format represents the actual + * entry in the RMP table memory. The bitfield definitions are used for machines + * without the RMPREAD instruction (Zen3 and Zen4), otherwise the "hi" and "lo" + * fields are only used for dumping the raw data. + */ +struct rmpentry_raw { + union { + struct { + u64 assigned : 1, + pagesize : 1, + immutable : 1, + rsvd1 : 9, + gpa : 39, + asid : 10, + vmsa : 1, + validated : 1, + rsvd2 : 1; + }; + u64 lo; + }; + u64 hi; +} __packed; + +/* + * The first 16KB from the RMP_BASE is used by the processor for the + * bookkeeping, the range needs to be added during the RMP entry lookup. + */ +#define RMPTABLE_CPU_BOOKKEEPING_SZ 0x4000 + +/* + * For a non-segmented RMP table, use the maximum physical addressing as the + * segment size in order to always arrive at index 0 in the table. + */ +#define RMPTABLE_NON_SEGMENTED_SHIFT 52 + +struct rmp_segment_desc { + struct rmpentry_raw *rmp_entry; + u64 max_index; + u64 size; +}; + +/* + * Segmented RMP Table support. + * - The segment size is used for two purposes: + * - Identify the amount of memory covered by an RMP segment + * - Quickly locate an RMP segment table entry for a physical address + * + * - The RMP segment table contains pointers to an RMP table that covers + * a specific portion of memory. There can be up to 512 8-byte entries, + * one pages worth. + */ +#define RST_ENTRY_MAPPED_SIZE(x) ((x) & GENMASK_ULL(19, 0)) +#define RST_ENTRY_SEGMENT_BASE(x) ((x) & GENMASK_ULL(51, 20)) + +#define RST_SIZE SZ_4K +static struct rmp_segment_desc **rmp_segment_table __ro_after_init; +static unsigned int rst_max_index __ro_after_init = 512; + +static unsigned int rmp_segment_shift; +static u64 rmp_segment_size; +static u64 rmp_segment_mask; + +#define RST_ENTRY_INDEX(x) ((x) >> rmp_segment_shift) +#define RMP_ENTRY_INDEX(x) ((u64)(PHYS_PFN((x) & rmp_segment_mask))) + +static u64 rmp_cfg; + +/* Mask to apply to a PFN to get the first PFN of a 2MB page */ +#define PFN_PMD_MASK GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT) + +static u64 probed_rmp_base, probed_rmp_size; + +static LIST_HEAD(snp_leaked_pages_list); +static DEFINE_SPINLOCK(snp_leaked_pages_list_lock); + +static unsigned long snp_nr_leaked_pages; + +#undef pr_fmt +#define pr_fmt(fmt) "SEV-SNP: " fmt + +static int __mfd_enable(unsigned int cpu) +{ + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + rdmsrl(MSR_AMD64_SYSCFG, val); + + val |= MSR_AMD64_SYSCFG_MFDM; + + wrmsrl(MSR_AMD64_SYSCFG, val); + + return 0; +} + +static __init void mfd_enable(void *arg) +{ + __mfd_enable(smp_processor_id()); +} + +static int __snp_enable(unsigned int cpu) +{ + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + rdmsrl(MSR_AMD64_SYSCFG, val); + + val |= MSR_AMD64_SYSCFG_SNP_EN; + val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN; + + wrmsrl(MSR_AMD64_SYSCFG, val); + + return 0; +} + +static __init void snp_enable(void *arg) +{ + __snp_enable(smp_processor_id()); +} + +static void __init __snp_fixup_e820_tables(u64 pa) +{ + if (IS_ALIGNED(pa, PMD_SIZE)) + return; + + /* + * Handle cases where the RMP table placement by the BIOS is not + * 2M aligned and the kexec kernel could try to allocate + * from within that chunk which then causes a fatal RMP fault. + * + * The e820_table needs to be updated as it is converted to + * kernel memory resources and used by KEXEC_FILE_LOAD syscall + * to load kexec segments. + * + * The e820_table_firmware needs to be updated as it is exposed + * to sysfs and used by the KEXEC_LOAD syscall to load kexec + * segments. + * + * The e820_table_kexec needs to be updated as it passed to + * the kexec-ed kernel. + */ + pa = ALIGN_DOWN(pa, PMD_SIZE); + if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) { + pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa); + e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + if (!memblock_is_region_reserved(pa, PMD_SIZE)) + memblock_reserve(pa, PMD_SIZE); + } +} + +static void __init fixup_e820_tables_for_segmented_rmp(void) +{ + u64 pa, *rst, size, mapped_size; + unsigned int i; + + __snp_fixup_e820_tables(probed_rmp_base); + + pa = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + + __snp_fixup_e820_tables(pa + RST_SIZE); + + rst = early_memremap(pa, RST_SIZE); + if (!rst) + return; + + for (i = 0; i < rst_max_index; i++) { + pa = RST_ENTRY_SEGMENT_BASE(rst[i]); + mapped_size = RST_ENTRY_MAPPED_SIZE(rst[i]); + if (!mapped_size) + continue; + + __snp_fixup_e820_tables(pa); + + /* + * Mapped size in GB. Mapped size is allowed to exceed + * the segment coverage size, but gets reduced to the + * segment coverage size. + */ + mapped_size <<= 30; + if (mapped_size > rmp_segment_size) + mapped_size = rmp_segment_size; + + /* Calculate the RMP segment size (16 bytes/page mapped) */ + size = PHYS_PFN(mapped_size) << 4; + + __snp_fixup_e820_tables(pa + size); + } + + early_memunmap(rst, RST_SIZE); +} + +static void __init fixup_e820_tables_for_contiguous_rmp(void) +{ + __snp_fixup_e820_tables(probed_rmp_base); + __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size); +} + +void __init snp_fixup_e820_tables(void) +{ + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) { + fixup_e820_tables_for_segmented_rmp(); + } else { + fixup_e820_tables_for_contiguous_rmp(); + } +} + +static bool __init clear_rmptable_bookkeeping(void) +{ + void *bk; + + bk = memremap(probed_rmp_base, RMPTABLE_CPU_BOOKKEEPING_SZ, MEMREMAP_WB); + if (!bk) { + pr_err("Failed to map RMP bookkeeping area\n"); + return false; + } + + memset(bk, 0, RMPTABLE_CPU_BOOKKEEPING_SZ); + + memunmap(bk); + + return true; +} + +static bool __init alloc_rmp_segment_desc(u64 segment_pa, u64 segment_size, u64 pa) +{ + u64 rst_index, rmp_segment_size_max; + struct rmp_segment_desc *desc; + void *rmp_segment; + + /* Calculate the maximum size an RMP can be (16 bytes/page mapped) */ + rmp_segment_size_max = PHYS_PFN(rmp_segment_size) << 4; + + /* Validate the RMP segment size */ + if (segment_size > rmp_segment_size_max) { + pr_err("Invalid RMP size 0x%llx for configured segment size 0x%llx\n", + segment_size, rmp_segment_size_max); + return false; + } + + /* Validate the RMP segment table index */ + rst_index = RST_ENTRY_INDEX(pa); + if (rst_index >= rst_max_index) { + pr_err("Invalid RMP segment base address 0x%llx for configured segment size 0x%llx\n", + pa, rmp_segment_size); + return false; + } + + if (rmp_segment_table[rst_index]) { + pr_err("RMP segment descriptor already exists at index %llu\n", rst_index); + return false; + } + + rmp_segment = memremap(segment_pa, segment_size, MEMREMAP_WB); + if (!rmp_segment) { + pr_err("Failed to map RMP segment addr 0x%llx size 0x%llx\n", + segment_pa, segment_size); + return false; + } + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) { + memunmap(rmp_segment); + return false; + } + + desc->rmp_entry = rmp_segment; + desc->max_index = segment_size / sizeof(*desc->rmp_entry); + desc->size = segment_size; + + rmp_segment_table[rst_index] = desc; + + return true; +} + +static void __init free_rmp_segment_table(void) +{ + unsigned int i; + + for (i = 0; i < rst_max_index; i++) { + struct rmp_segment_desc *desc; + + desc = rmp_segment_table[i]; + if (!desc) + continue; + + memunmap(desc->rmp_entry); + + kfree(desc); + } + + free_page((unsigned long)rmp_segment_table); + + rmp_segment_table = NULL; +} + +/* Allocate the table used to index into the RMP segments */ +static bool __init alloc_rmp_segment_table(void) +{ + struct page *page; + + page = alloc_page(__GFP_ZERO); + if (!page) + return false; + + rmp_segment_table = page_address(page); + + return true; +} + +static bool __init setup_contiguous_rmptable(void) +{ + u64 max_rmp_pfn, calc_rmp_sz, rmptable_segment, rmptable_size, rmp_end; + + if (!probed_rmp_size) + return false; + + rmp_end = probed_rmp_base + probed_rmp_size - 1; + + /* + * Calculate the amount of memory that must be reserved by the BIOS to + * address the whole RAM, including the bookkeeping area. The RMP itself + * must also be covered. + */ + max_rmp_pfn = max_pfn; + if (PFN_UP(rmp_end) > max_pfn) + max_rmp_pfn = PFN_UP(rmp_end); + + calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ; + if (calc_rmp_sz > probed_rmp_size) { + pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + calc_rmp_sz, probed_rmp_size); + return false; + } + + if (!alloc_rmp_segment_table()) + return false; + + /* Map only the RMP entries */ + rmptable_segment = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; + + if (!alloc_rmp_segment_desc(rmptable_segment, rmptable_size, 0)) { + free_rmp_segment_table(); + return false; + } + + return true; +} + +static bool __init setup_segmented_rmptable(void) +{ + u64 rst_pa, *rst, pa, ram_pa_end, ram_pa_max; + unsigned int i, max_index; + + if (!probed_rmp_base) + return false; + + if (!alloc_rmp_segment_table()) + return false; + + rst_pa = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + rst = memremap(rst_pa, RST_SIZE, MEMREMAP_WB); + if (!rst) { + pr_err("Failed to map RMP segment table addr 0x%llx\n", rst_pa); + goto e_free; + } + + pr_info("Segmented RMP using %lluGB segments\n", rmp_segment_size >> 30); + + ram_pa_max = max_pfn << PAGE_SHIFT; + + max_index = 0; + ram_pa_end = 0; + for (i = 0; i < rst_max_index; i++) { + u64 rmp_segment, rmp_size, mapped_size; + + mapped_size = RST_ENTRY_MAPPED_SIZE(rst[i]); + if (!mapped_size) + continue; + + max_index = i; + + /* + * Mapped size in GB. Mapped size is allowed to exceed the + * segment coverage size, but gets reduced to the segment + * coverage size. + */ + mapped_size <<= 30; + if (mapped_size > rmp_segment_size) { + pr_info("RMP segment %u mapped size (0x%llx) reduced to 0x%llx\n", + i, mapped_size, rmp_segment_size); + mapped_size = rmp_segment_size; + } + + rmp_segment = RST_ENTRY_SEGMENT_BASE(rst[i]); + + /* Calculate the RMP segment size (16 bytes/page mapped) */ + rmp_size = PHYS_PFN(mapped_size) << 4; + + pa = (u64)i << rmp_segment_shift; + + /* + * Some segments may be for MMIO mapped above system RAM. These + * segments are used for Trusted I/O. + */ + if (pa < ram_pa_max) + ram_pa_end = pa + mapped_size; + + if (!alloc_rmp_segment_desc(rmp_segment, rmp_size, pa)) + goto e_unmap; + + pr_info("RMP segment %u physical address [0x%llx - 0x%llx] covering [0x%llx - 0x%llx]\n", + i, rmp_segment, rmp_segment + rmp_size - 1, pa, pa + mapped_size - 1); + } + + if (ram_pa_max > ram_pa_end) { + pr_err("Segmented RMP does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + ram_pa_max, ram_pa_end); + goto e_unmap; + } + + /* Adjust the maximum index based on the found segments */ + rst_max_index = max_index + 1; + + memunmap(rst); + + return true; + +e_unmap: + memunmap(rst); + +e_free: + free_rmp_segment_table(); + + return false; +} + +static bool __init setup_rmptable(void) +{ + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) { + return setup_segmented_rmptable(); + } else { + return setup_contiguous_rmptable(); + } +} + +/* + * Do the necessary preparations which are verified by the firmware as + * described in the SNP_INIT_EX firmware command description in the SNP + * firmware ABI spec. + */ +int __init snp_rmptable_init(void) +{ + unsigned int i; + u64 val; + + if (WARN_ON_ONCE(!cc_platform_has(CC_ATTR_HOST_SEV_SNP))) + return -ENOSYS; + + if (WARN_ON_ONCE(!amd_iommu_snp_en)) + return -ENOSYS; + + if (!setup_rmptable()) + return -ENOSYS; + + /* + * Check if SEV-SNP is already enabled, this can happen in case of + * kexec boot. + */ + rdmsrl(MSR_AMD64_SYSCFG, val); + if (val & MSR_AMD64_SYSCFG_SNP_EN) + goto skip_enable; + + /* Zero out the RMP bookkeeping area */ + if (!clear_rmptable_bookkeeping()) { + free_rmp_segment_table(); + return -ENOSYS; + } + + /* Zero out the RMP entries */ + for (i = 0; i < rst_max_index; i++) { + struct rmp_segment_desc *desc; + + desc = rmp_segment_table[i]; + if (!desc) + continue; + + memset(desc->rmp_entry, 0, desc->size); + } + + /* Flush the caches to ensure that data is written before SNP is enabled. */ + wbinvd_on_all_cpus(); + + /* MtrrFixDramModEn must be enabled on all the CPUs prior to enabling SNP. */ + on_each_cpu(mfd_enable, NULL, 1); + + on_each_cpu(snp_enable, NULL, 1); + +skip_enable: + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL); + + /* + * Setting crash_kexec_post_notifiers to 'true' to ensure that SNP panic + * notifier is invoked to do SNP IOMMU shutdown before kdump. + */ + crash_kexec_post_notifiers = true; + + return 0; +} + +static void set_rmp_segment_info(unsigned int segment_shift) +{ + rmp_segment_shift = segment_shift; + rmp_segment_size = 1ULL << rmp_segment_shift; + rmp_segment_mask = rmp_segment_size - 1; +} + +#define RMP_ADDR_MASK GENMASK_ULL(51, 13) + +static bool probe_contiguous_rmptable_info(void) +{ + u64 rmp_sz, rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + + if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + if (rmp_base > rmp_end) { + pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); + return false; + } + + rmp_sz = rmp_end - rmp_base + 1; + + /* Treat the contiguous RMP table as a single segment */ + rst_max_index = 1; + + set_rmp_segment_info(RMPTABLE_NON_SEGMENTED_SHIFT); + + probed_rmp_base = rmp_base; + probed_rmp_size = rmp_sz; + + pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", + rmp_base, rmp_end); + + return true; +} + +static bool probe_segmented_rmptable_info(void) +{ + unsigned int eax, ebx, segment_shift, segment_shift_min, segment_shift_max; + u64 rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + if (!(rmp_base & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + WARN_ONCE(rmp_end & RMP_ADDR_MASK, + "Segmented RMP enabled but RMP_END MSR is non-zero\n"); + + /* Obtain the min and max supported RMP segment size */ + eax = cpuid_eax(0x80000025); + segment_shift_min = eax & GENMASK(5, 0); + segment_shift_max = (eax & GENMASK(11, 6)) >> 6; + + /* Verify the segment size is within the supported limits */ + segment_shift = MSR_AMD64_RMP_SEGMENT_SHIFT(rmp_cfg); + if (segment_shift > segment_shift_max || segment_shift < segment_shift_min) { + pr_err("RMP segment size (%u) is not within advertised bounds (min=%u, max=%u)\n", + segment_shift, segment_shift_min, segment_shift_max); + return false; + } + + /* Override the max supported RST index if a hardware limit exists */ + ebx = cpuid_ebx(0x80000025); + if (ebx & BIT(10)) + rst_max_index = ebx & GENMASK(9, 0); + + set_rmp_segment_info(segment_shift); + + probed_rmp_base = rmp_base; + probed_rmp_size = 0; + + pr_info("Segmented RMP base table physical range [0x%016llx - 0x%016llx]\n", + rmp_base, rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ + RST_SIZE); + + return true; +} + +bool snp_probe_rmptable_info(void) +{ + if (cpu_feature_enabled(X86_FEATURE_SEGMENTED_RMP)) + rdmsrl(MSR_AMD64_RMP_CFG, rmp_cfg); + + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) + return probe_segmented_rmptable_info(); + else + return probe_contiguous_rmptable_info(); +} + +/* + * About the array_index_nospec() usage below: + * + * This function can get called by exported functions like + * snp_lookup_rmpentry(), which is used by the KVM #PF handler, among + * others, and since the @pfn passed in cannot always be trusted, + * speculation should be stopped as a protective measure. + */ +static struct rmpentry_raw *get_raw_rmpentry(u64 pfn) +{ + u64 paddr, rst_index, segment_index; + struct rmp_segment_desc *desc; + + if (!rmp_segment_table) + return ERR_PTR(-ENODEV); + + paddr = pfn << PAGE_SHIFT; + + rst_index = RST_ENTRY_INDEX(paddr); + if (unlikely(rst_index >= rst_max_index)) + return ERR_PTR(-EFAULT); + + rst_index = array_index_nospec(rst_index, rst_max_index); + + desc = rmp_segment_table[rst_index]; + if (unlikely(!desc)) + return ERR_PTR(-EFAULT); + + segment_index = RMP_ENTRY_INDEX(paddr); + if (unlikely(segment_index >= desc->max_index)) + return ERR_PTR(-EFAULT); + + segment_index = array_index_nospec(segment_index, desc->max_index); + + return desc->rmp_entry + segment_index; +} + +static int get_rmpentry(u64 pfn, struct rmpentry *e) +{ + struct rmpentry_raw *e_raw; + + if (cpu_feature_enabled(X86_FEATURE_RMPREAD)) { + int ret; + + /* Binutils version 2.44 supports the RMPREAD mnemonic. */ + asm volatile(".byte 0xf2, 0x0f, 0x01, 0xfd" + : "=a" (ret) + : "a" (pfn << PAGE_SHIFT), "c" (e) + : "memory", "cc"); + + return ret; + } + + e_raw = get_raw_rmpentry(pfn); + if (IS_ERR(e_raw)) + return PTR_ERR(e_raw); + + /* + * Map the raw RMP table entry onto the RMPREAD output format. + * The 2MB region status indicator (hpage_region_status field) is not + * calculated, since the overhead could be significant and the field + * is not used. + */ + memset(e, 0, sizeof(*e)); + e->gpa = e_raw->gpa << PAGE_SHIFT; + e->asid = e_raw->asid; + e->assigned = e_raw->assigned; + e->pagesize = e_raw->pagesize; + e->immutable = e_raw->immutable; + + return 0; +} + +static int __snp_lookup_rmpentry(u64 pfn, struct rmpentry *e, int *level) +{ + struct rmpentry e_large; + int ret; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + ret = get_rmpentry(pfn, e); + if (ret) + return ret; + + /* + * Find the authoritative RMP entry for a PFN. This can be either a 4K + * RMP entry or a special large RMP entry that is authoritative for a + * whole 2M area. + */ + ret = get_rmpentry(pfn & PFN_PMD_MASK, &e_large); + if (ret) + return ret; + + *level = RMP_TO_PG_LEVEL(e_large.pagesize); + + return 0; +} + +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) +{ + struct rmpentry e; + int ret; + + ret = __snp_lookup_rmpentry(pfn, &e, level); + if (ret) + return ret; + + *assigned = !!e.assigned; + return 0; +} +EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); + +/* + * Dump the raw RMP entry for a particular PFN. These bits are documented in the + * PPR for a particular CPU model and provide useful information about how a + * particular PFN is being utilized by the kernel/firmware at the time certain + * unexpected events occur, such as RMP faults. + */ +static void dump_rmpentry(u64 pfn) +{ + struct rmpentry_raw *e_raw; + u64 pfn_i, pfn_end; + struct rmpentry e; + int level, ret; + + ret = __snp_lookup_rmpentry(pfn, &e, &level); + if (ret) { + pr_err("Failed to read RMP entry for PFN 0x%llx, error %d\n", + pfn, ret); + return; + } + + if (e.assigned) { + e_raw = get_raw_rmpentry(pfn); + if (IS_ERR(e_raw)) { + pr_err("Failed to read RMP contents for PFN 0x%llx, error %ld\n", + pfn, PTR_ERR(e_raw)); + return; + } + + pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n", + pfn, e_raw->lo, e_raw->hi); + return; + } + + /* + * If the RMP entry for a particular PFN is not in an assigned state, + * then it is sometimes useful to get an idea of whether or not any RMP + * entries for other PFNs within the same 2MB region are assigned, since + * those too can affect the ability to access a particular PFN in + * certain situations, such as when the PFN is being accessed via a 2MB + * mapping in the host page table. + */ + pfn_i = ALIGN_DOWN(pfn, PTRS_PER_PMD); + pfn_end = pfn_i + PTRS_PER_PMD; + + pr_info("PFN 0x%llx unassigned, dumping non-zero entries in 2M PFN region: [0x%llx - 0x%llx]\n", + pfn, pfn_i, pfn_end); + + while (pfn_i < pfn_end) { + e_raw = get_raw_rmpentry(pfn_i); + if (IS_ERR(e_raw)) { + pr_err("Error %ld reading RMP contents for PFN 0x%llx\n", + PTR_ERR(e_raw), pfn_i); + pfn_i++; + continue; + } + + if (e_raw->lo || e_raw->hi) + pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e_raw->lo, e_raw->hi); + pfn_i++; + } +} + +void snp_dump_hva_rmpentry(unsigned long hva) +{ + unsigned long paddr; + unsigned int level; + pgd_t *pgd; + pte_t *pte; + + pgd = __va(read_cr3_pa()); + pgd += pgd_index(hva); + pte = lookup_address_in_pgd(pgd, hva, &level); + + if (!pte) { + pr_err("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva); + return; + } + + paddr = PFN_PHYS(pte_pfn(*pte)) | (hva & ~page_level_mask(level)); + dump_rmpentry(PHYS_PFN(paddr)); +} + +/* + * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the + * Validated bit. + */ +int psmash(u64 pfn) +{ + unsigned long paddr = pfn << PAGE_SHIFT; + int ret; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + if (!pfn_valid(pfn)) + return -EINVAL; + + /* Binutils version 2.36 supports the PSMASH mnemonic. */ + asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF" + : "=a" (ret) + : "a" (paddr) + : "memory", "cc"); + + return ret; +} +EXPORT_SYMBOL_GPL(psmash); + +/* + * If the kernel uses a 2MB or larger directmap mapping to write to an address, + * and that mapping contains any 4KB pages that are set to private in the RMP + * table, an RMP #PF will trigger and cause a host crash. Hypervisor code that + * owns the PFNs being transitioned will never attempt such a write, but other + * kernel tasks writing to other PFNs in the range may trigger these checks + * inadvertently due a large directmap mapping that happens to overlap such a + * PFN. + * + * Prevent this by splitting any 2MB+ mappings that might end up containing a + * mix of private/shared PFNs as a result of a subsequent RMPUPDATE for the + * PFN/rmp_level passed in. + * + * Note that there is no attempt here to scan all the RMP entries for the 2MB + * physical range, since it would only be worthwhile in determining if a + * subsequent RMPUPDATE for a 4KB PFN would result in all the entries being of + * the same shared/private state, thus avoiding the need to split the mapping. + * But that would mean the entries are currently in a mixed state, and so the + * mapping would have already been split as a result of prior transitions. + * And since the 4K split is only done if the mapping is 2MB+, and there isn't + * currently a mechanism in place to restore 2MB+ mappings, such a check would + * not provide any usable benefit. + * + * More specifics on how these checks are carried out can be found in APM + * Volume 2, "RMP and VMPL Access Checks". + */ +static int adjust_direct_map(u64 pfn, int rmp_level) +{ + unsigned long vaddr; + unsigned int level; + int npages, ret; + pte_t *pte; + + /* + * pfn_to_kaddr() will return a vaddr only within the direct + * map range. + */ + vaddr = (unsigned long)pfn_to_kaddr(pfn); + + /* Only 4KB/2MB RMP entries are supported by current hardware. */ + if (WARN_ON_ONCE(rmp_level > PG_LEVEL_2M)) + return -EINVAL; + + if (!pfn_valid(pfn)) + return -EINVAL; + + if (rmp_level == PG_LEVEL_2M && + (!IS_ALIGNED(pfn, PTRS_PER_PMD) || !pfn_valid(pfn + PTRS_PER_PMD - 1))) + return -EINVAL; + + /* + * If an entire 2MB physical range is being transitioned, then there is + * no risk of RMP #PFs due to write accesses from overlapping mappings, + * since even accesses from 1GB mappings will be treated as 2MB accesses + * as far as RMP table checks are concerned. + */ + if (rmp_level == PG_LEVEL_2M) + return 0; + + pte = lookup_address(vaddr, &level); + if (!pte || pte_none(*pte)) + return 0; + + if (level == PG_LEVEL_4K) + return 0; + + npages = page_level_size(rmp_level) / PAGE_SIZE; + ret = set_memory_4k(vaddr, npages); + if (ret) + pr_warn("Failed to split direct map for PFN 0x%llx, ret: %d\n", + pfn, ret); + + return ret; +} + +/* + * It is expected that those operations are seldom enough so that no mutual + * exclusion of updaters is needed and thus the overlap error condition below + * should happen very rarely and would get resolved relatively quickly by + * the firmware. + * + * If not, one could consider introducing a mutex or so here to sync concurrent + * RMP updates and thus diminish the amount of cases where firmware needs to + * lock 2M ranges to protect against concurrent updates. + * + * The optimal solution would be range locking to avoid locking disjoint + * regions unnecessarily but there's no support for that yet. + */ +static int rmpupdate(u64 pfn, struct rmp_state *state) +{ + unsigned long paddr = pfn << PAGE_SHIFT; + int ret, level; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + level = RMP_TO_PG_LEVEL(state->pagesize); + + if (adjust_direct_map(pfn, level)) + return -EFAULT; + + do { + /* Binutils version 2.36 supports the RMPUPDATE mnemonic. */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE" + : "=a" (ret) + : "a" (paddr), "c" ((unsigned long)state) + : "memory", "cc"); + } while (ret == RMPUPDATE_FAIL_OVERLAP); + + if (ret) { + pr_err("RMPUPDATE failed for PFN %llx, pg_level: %d, ret: %d\n", + pfn, level, ret); + dump_rmpentry(pfn); + dump_stack(); + return -EFAULT; + } + + return 0; +} + +/* Transition a page to guest-owned/private state in the RMP table. */ +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable) +{ + struct rmp_state state; + + memset(&state, 0, sizeof(state)); + state.assigned = 1; + state.asid = asid; + state.immutable = immutable; + state.gpa = gpa; + state.pagesize = PG_LEVEL_TO_RMP(level); + + return rmpupdate(pfn, &state); +} +EXPORT_SYMBOL_GPL(rmp_make_private); + +/* Transition a page to hypervisor-owned/shared state in the RMP table. */ +int rmp_make_shared(u64 pfn, enum pg_level level) +{ + struct rmp_state state; + + memset(&state, 0, sizeof(state)); + state.pagesize = PG_LEVEL_TO_RMP(level); + + return rmpupdate(pfn, &state); +} +EXPORT_SYMBOL_GPL(rmp_make_shared); + +void snp_leak_pages(u64 pfn, unsigned int npages) +{ + struct page *page = pfn_to_page(pfn); + + pr_warn("Leaking PFN range 0x%llx-0x%llx\n", pfn, pfn + npages); + + spin_lock(&snp_leaked_pages_list_lock); + while (npages--) { + + /* + * Reuse the page's buddy list for chaining into the leaked + * pages list. This page should not be on a free list currently + * and is also unsafe to be added to a free list. + */ + if (likely(!PageCompound(page)) || + + /* + * Skip inserting tail pages of compound page as + * page->buddy_list of tail pages is not usable. + */ + (PageHead(page) && compound_nr(page) <= npages)) + list_add_tail(&page->buddy_list, &snp_leaked_pages_list); + + dump_rmpentry(pfn); + snp_nr_leaked_pages++; + pfn++; + page++; + } + spin_unlock(&snp_leaked_pages_list_lock); +} +EXPORT_SYMBOL_GPL(snp_leak_pages); + +void kdump_sev_callback(void) +{ + /* + * Do wbinvd() on remote CPUs when SNP is enabled in order to + * safely do SNP_SHUTDOWN on the local CPU. + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + wbinvd(); +} diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig index 7d2c386127d33a00bab307aacc3a845641ca473f..506536b9a98914b770f0036b149e3cecb3c01c4e 100644 --- a/drivers/crypto/ccp/Kconfig +++ b/drivers/crypto/ccp/Kconfig @@ -38,7 +38,7 @@ config CRYPTO_DEV_CCP_CRYPTO config CRYPTO_DEV_SP_PSP bool "Platform Security Processor (PSP) device" default y - depends on CRYPTO_DEV_CCP_DD && X86_64 + depends on CRYPTO_DEV_CCP_DD && X86_64 && AMD_IOMMU help Provide support for the AMD Platform Security Processor (PSP). The PSP is a dedicated processor that provides support for key diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 947dc26e139cb6103f2aa0e95b6c25bf29240508..f570791f86330ce8c8d2de4225baa7f81660a9b0 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -21,14 +21,18 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include +#include +#include #include "psp-dev.h" #include "sev-dev.h" @@ -40,6 +44,19 @@ #define SEV_FW_FILE "amd/sev.fw" #define SEV_FW_NAME_SIZE 64 +/* Minimum firmware version required for the SEV-SNP support */ +#define SNP_MIN_API_MAJOR 1 +#define SNP_MIN_API_MINOR 51 + +/* + * Maximum number of firmware-writable buffers that might be specified + * in the parameters of a legacy SEV command buffer. + */ +#define CMD_BUF_FW_WRITABLE_MAX 2 + +/* Leave room in the descriptor array for an end-of-list indicator. */ +#define CMD_BUF_DESC_MAX (CMD_BUF_FW_WRITABLE_MAX + 1) + static DEFINE_MUTEX(sev_cmd_mutex); static struct sev_misc_dev *misc_dev; @@ -71,9 +88,14 @@ static int psp_timeout; * The TMR is a 1MB area that must be 1MB aligned. Use the page allocator * to allocate the memory, which will return aligned memory for the specified * allocation order. + * + * When SEV-SNP is enabled the TMR needs to be 2MB aligned and 2MB sized. */ -#define SEV_ES_TMR_SIZE (1024 * 1024) +#define SEV_TMR_SIZE (1024 * 1024) +#define SNP_TMR_SIZE (2 * 1024 * 1024) + static void *sev_es_tmr; +static size_t sev_es_tmr_size = SEV_TMR_SIZE; /* INIT_EX NV Storage: * The NV Storage is a 32Kb area and must be 4Kb page aligned. Use the page @@ -83,6 +105,13 @@ static void *sev_es_tmr; #define NV_LENGTH (32 * 1024) static void *sev_init_ex_buffer; +/* + * SEV_DATA_RANGE_LIST: + * Array containing range of pages that firmware transitions to HV-fixed + * page state. + */ +struct sev_data_range_list *snp_range_list; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -119,6 +148,25 @@ static int sev_wait_cmd_ioc(struct sev_device *sev, { int ret; + /* + * If invoked during panic handling, local interrupts are disabled, + * so the PSP command completion interrupt can't be used. Poll for + * PSP command completion instead. + */ + if (irqs_disabled()) { + unsigned long timeout_usecs = (timeout * USEC_PER_SEC) / 10; + + /* Poll for SEV command completion: */ + while (timeout_usecs--) { + *reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg); + if (*reg & PSP_CMDRESP_RESP) + return 0; + + udelay(10); + } + return -ETIMEDOUT; + } + ret = wait_event_timeout(sev->int_queue, sev->int_rcvd, timeout * HZ); if (!ret) @@ -146,6 +194,8 @@ static int sev_cmd_buffer_len(int cmd) switch (cmd) { case SEV_CMD_INIT: return sizeof(struct sev_data_init); case SEV_CMD_INIT_EX: return sizeof(struct sev_data_init_ex); + case SEV_CMD_SNP_SHUTDOWN_EX: return sizeof(struct sev_data_snp_shutdown_ex); + case SEV_CMD_SNP_INIT_EX: return sizeof(struct sev_data_snp_init_ex); case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); @@ -174,23 +224,27 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_GET_ID: return sizeof(struct sev_data_get_id); case SEV_CMD_ATTESTATION_REPORT: return sizeof(struct sev_data_attestation_report); case SEV_CMD_SEND_CANCEL: return sizeof(struct sev_data_send_cancel); + case SEV_CMD_SNP_GCTX_CREATE: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_LAUNCH_START: return sizeof(struct sev_data_snp_launch_start); + case SEV_CMD_SNP_LAUNCH_UPDATE: return sizeof(struct sev_data_snp_launch_update); + case SEV_CMD_SNP_ACTIVATE: return sizeof(struct sev_data_snp_activate); + case SEV_CMD_SNP_DECOMMISSION: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_PAGE_RECLAIM: return sizeof(struct sev_data_snp_page_reclaim); + case SEV_CMD_SNP_GUEST_STATUS: return sizeof(struct sev_data_snp_guest_status); + case SEV_CMD_SNP_LAUNCH_FINISH: return sizeof(struct sev_data_snp_launch_finish); + case SEV_CMD_SNP_DBG_DECRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_DBG_ENCRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_PAGE_UNSMASH: return sizeof(struct sev_data_snp_page_unsmash); + case SEV_CMD_SNP_PLATFORM_STATUS: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request); + case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config); + case SEV_CMD_SNP_COMMIT: return sizeof(struct sev_data_snp_commit); default: return 0; } return 0; } -static void *sev_fw_alloc(unsigned long len) -{ - struct page *page; - - page = alloc_pages(GFP_KERNEL, get_order(len)); - if (!page) - return NULL; - - return page_address(page); -} - static struct file *open_file_as_root(const char *filename, int flags, umode_t mode) { struct file *fp; @@ -321,12 +375,484 @@ static int sev_write_init_ex_file_if_required(int cmd_id) return sev_write_init_ex_file(); } +/* + * snp_reclaim_pages() needs __sev_do_cmd_locked(), and __sev_do_cmd_locked() + * needs snp_reclaim_pages(), so a forward declaration is needed. + */ +static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret); + +static int snp_reclaim_pages(unsigned long paddr, unsigned int npages, bool locked) +{ + int ret, err, i; + + paddr = __sme_clr(ALIGN_DOWN(paddr, PAGE_SIZE)); + + for (i = 0; i < npages; i++, paddr += PAGE_SIZE) { + struct sev_data_snp_page_reclaim data = {0}; + + data.paddr = paddr; + + if (locked) + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + else + ret = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + + if (ret) + goto cleanup; + + ret = rmp_make_shared(__phys_to_pfn(paddr), PG_LEVEL_4K); + if (ret) + goto cleanup; + } + + return 0; + +cleanup: + /* + * If there was a failure reclaiming the page then it is no longer safe + * to release it back to the system; leak it instead. + */ + snp_leak_pages(__phys_to_pfn(paddr), npages - i); + return ret; +} + +static int rmp_mark_pages_firmware(unsigned long paddr, unsigned int npages, bool locked) +{ + unsigned long pfn = __sme_clr(paddr) >> PAGE_SHIFT; + int rc, i; + + for (i = 0; i < npages; i++, pfn++) { + rc = rmp_make_private(pfn, 0, PG_LEVEL_4K, 0, true); + if (rc) + goto cleanup; + } + + return 0; + +cleanup: + /* + * Try unrolling the firmware state changes by + * reclaiming the pages which were already changed to the + * firmware state. + */ + snp_reclaim_pages(paddr, i, locked); + + return rc; +} + +static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order, bool locked) +{ + unsigned long npages = 1ul << order, paddr; + struct sev_device *sev; + struct page *page; + + if (!psp_master || !psp_master->sev_data) + return NULL; + + page = alloc_pages(gfp_mask, order); + if (!page) + return NULL; + + /* If SEV-SNP is initialized then add the page in RMP table. */ + sev = psp_master->sev_data; + if (!sev->snp_initialized) + return page; + + paddr = __pa((unsigned long)page_address(page)); + if (rmp_mark_pages_firmware(paddr, npages, locked)) + return NULL; + + return page; +} + +void *snp_alloc_firmware_page(gfp_t gfp_mask) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(gfp_mask, 0, false); + + return page ? page_address(page) : NULL; +} +EXPORT_SYMBOL_GPL(snp_alloc_firmware_page); + +static void __snp_free_firmware_pages(struct page *page, int order, bool locked) +{ + struct sev_device *sev = psp_master->sev_data; + unsigned long paddr, npages = 1ul << order; + + if (!page) + return; + + paddr = __pa((unsigned long)page_address(page)); + if (sev->snp_initialized && + snp_reclaim_pages(paddr, npages, locked)) + return; + + __free_pages(page, order); +} + +void snp_free_firmware_page(void *addr) +{ + if (!addr) + return; + + __snp_free_firmware_pages(virt_to_page(addr), 0, false); +} +EXPORT_SYMBOL_GPL(snp_free_firmware_page); + +static void *sev_fw_alloc(unsigned long len) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len), true); + if (!page) + return NULL; + + return page_address(page); +} + +/** + * struct cmd_buf_desc - descriptors for managing legacy SEV command address + * parameters corresponding to buffers that may be written to by firmware. + * + * @paddr_ptr: pointer to the address parameter in the command buffer which may + * need to be saved/restored depending on whether a bounce buffer + * is used. In the case of a bounce buffer, the command buffer + * needs to be updated with the address of the new bounce buffer + * snp_map_cmd_buf_desc() has allocated specifically for it. Must + * be NULL if this descriptor is only an end-of-list indicator. + * + * @paddr_orig: storage for the original address parameter, which can be used to + * restore the original value in @paddr_ptr in cases where it is + * replaced with the address of a bounce buffer. + * + * @len: length of buffer located at the address originally stored at @paddr_ptr + * + * @guest_owned: true if the address corresponds to guest-owned pages, in which + * case bounce buffers are not needed. + */ +struct cmd_buf_desc { + u64 *paddr_ptr; + u64 paddr_orig; + u32 len; + bool guest_owned; +}; + +/* + * If a legacy SEV command parameter is a memory address, those pages in + * turn need to be transitioned to/from firmware-owned before/after + * executing the firmware command. + * + * Additionally, in cases where those pages are not guest-owned, a bounce + * buffer is needed in place of the original memory address parameter. + * + * A set of descriptors are used to keep track of this handling, and + * initialized here based on the specific commands being executed. + */ +static void snp_populate_cmd_buf_desc_list(int cmd, void *cmd_buf, + struct cmd_buf_desc *desc_list) +{ + switch (cmd) { + case SEV_CMD_PDH_CERT_EXPORT: { + struct sev_data_pdh_cert_export *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->pdh_cert_address; + desc_list[0].len = data->pdh_cert_len; + desc_list[1].paddr_ptr = &data->cert_chain_address; + desc_list[1].len = data->cert_chain_len; + break; + } + case SEV_CMD_GET_ID: { + struct sev_data_get_id *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_PEK_CSR: { + struct sev_data_pek_csr *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_DATA: { + struct sev_data_launch_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_UPDATE_VMSA: { + struct sev_data_launch_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_MEASURE: { + struct sev_data_launch_measure *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_SECRET: { + struct sev_data_launch_secret *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_DECRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_ENCRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_ATTESTATION_REPORT: { + struct sev_data_attestation_report *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_SEND_START: { + struct sev_data_send_start *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->session_address; + desc_list[0].len = data->session_len; + break; + } + case SEV_CMD_SEND_UPDATE_DATA: { + struct sev_data_send_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_SEND_UPDATE_VMSA: { + struct sev_data_send_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_RECEIVE_UPDATE_DATA: { + struct sev_data_receive_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_RECEIVE_UPDATE_VMSA: { + struct sev_data_receive_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + default: + break; + } +} + +static int snp_map_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + /* Allocate a bounce buffer if this isn't a guest owned page. */ + if (!desc->guest_owned) { + struct page *page; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(desc->len)); + if (!page) { + pr_warn("Failed to allocate bounce buffer for SEV legacy command.\n"); + return -ENOMEM; + } + + desc->paddr_orig = *desc->paddr_ptr; + *desc->paddr_ptr = __psp_pa(page_to_virt(page)); + } + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffer to firmware-owned. */ + if (rmp_mark_pages_firmware(*desc->paddr_ptr, npages, true)) { + pr_warn("Error moving pages to firmware-owned state for SEV legacy command.\n"); + return -EFAULT; + } + + return 0; +} + +static int snp_unmap_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffers back to hypervisor-owned. */ + if (snp_reclaim_pages(*desc->paddr_ptr, npages, true)) { + pr_warn("Failed to reclaim firmware-owned pages while issuing SEV legacy command.\n"); + return -EFAULT; + } + + /* Copy data from bounce buffer and then free it. */ + if (!desc->guest_owned) { + void *bounce_buf = __va(__sme_clr(*desc->paddr_ptr)); + void *dst_buf = __va(__sme_clr(desc->paddr_orig)); + + memcpy(dst_buf, bounce_buf, desc->len); + __free_pages(virt_to_page(bounce_buf), get_order(desc->len)); + + /* Restore the original address in the command buffer. */ + *desc->paddr_ptr = desc->paddr_orig; + } + + return 0; +} + +static int snp_map_cmd_buf_desc_list(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + int i; + + snp_populate_cmd_buf_desc_list(cmd, cmd_buf, desc_list); + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_map_cmd_buf_desc(desc)) + goto err_unmap; + } + + return 0; + +err_unmap: + for (i--; i >= 0; i--) + snp_unmap_cmd_buf_desc(&desc_list[i]); + + return -EFAULT; +} + +static int snp_unmap_cmd_buf_desc_list(struct cmd_buf_desc *desc_list) +{ + int i, ret = 0; + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_unmap_cmd_buf_desc(&desc_list[i])) + ret = -EFAULT; + } + + return ret; +} + +static bool sev_cmd_buf_writable(int cmd) +{ + switch (cmd) { + case SEV_CMD_PLATFORM_STATUS: + case SEV_CMD_GUEST_STATUS: + case SEV_CMD_LAUNCH_START: + case SEV_CMD_RECEIVE_START: + case SEV_CMD_LAUNCH_MEASURE: + case SEV_CMD_SEND_START: + case SEV_CMD_SEND_UPDATE_DATA: + case SEV_CMD_SEND_UPDATE_VMSA: + case SEV_CMD_PEK_CSR: + case SEV_CMD_PDH_CERT_EXPORT: + case SEV_CMD_GET_ID: + case SEV_CMD_ATTESTATION_REPORT: + return true; + default: + return false; + } +} + +/* After SNP is INIT'ed, the behavior of legacy SEV commands is changed. */ +static bool snp_legacy_handling_needed(int cmd) +{ + struct sev_device *sev = psp_master->sev_data; + + return cmd < SEV_CMD_SNP_INIT && sev->snp_initialized; +} + +static int snp_prep_cmd_buf(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + if (snp_map_cmd_buf_desc_list(cmd, cmd_buf, desc_list)) + return -EFAULT; + + /* + * Before command execution, the command buffer needs to be put into + * the firmware-owned state. + */ + if (sev_cmd_buf_writable(cmd)) { + if (rmp_mark_pages_firmware(__pa(cmd_buf), 1, true)) + return -EFAULT; + } + + return 0; +} + +static int snp_reclaim_cmd_buf(int cmd, void *cmd_buf) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + /* + * After command completion, the command buffer needs to be put back + * into the hypervisor-owned state. + */ + if (sev_cmd_buf_writable(cmd)) + if (snp_reclaim_pages(__pa(cmd_buf), 1, true)) + return -EFAULT; + + return 0; +} + static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) { + struct cmd_buf_desc desc_list[CMD_BUF_DESC_MAX] = {0}; struct psp_device *psp = psp_master; struct sev_device *sev; unsigned int phys_lsb, phys_msb; unsigned int reg, ret = 0; + void *cmd_buf; int buf_len; if (!psp || !psp->sev_data) @@ -346,12 +872,47 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) * work for some memory, e.g. vmalloc'd addresses, and @data may not be * physically contiguous. */ - if (data) - memcpy(sev->cmd_buf, data, buf_len); + if (data) { + /* + * Commands are generally issued one at a time and require the + * sev_cmd_mutex, but there could be recursive firmware requests + * due to SEV_CMD_SNP_PAGE_RECLAIM needing to be issued while + * preparing buffers for another command. This is the only known + * case of nesting in the current code, so exactly one + * additional command buffer is available for that purpose. + */ + if (!sev->cmd_buf_active) { + cmd_buf = sev->cmd_buf; + sev->cmd_buf_active = true; + } else if (!sev->cmd_buf_backup_active) { + cmd_buf = sev->cmd_buf_backup; + sev->cmd_buf_backup_active = true; + } else { + dev_err(sev->dev, + "SEV: too many firmware commands in progress, no command buffers available.\n"); + return -EBUSY; + } + + memcpy(cmd_buf, data, buf_len); + + /* + * The behavior of the SEV-legacy commands is altered when the + * SNP firmware is in the INIT state. + */ + ret = snp_prep_cmd_buf(cmd, cmd_buf, desc_list); + if (ret) { + dev_err(sev->dev, + "SEV: failed to prepare buffer for legacy command 0x%x. Error: %d\n", + cmd, ret); + return ret; + } + } else { + cmd_buf = sev->cmd_buf; + } /* Get the physical address of the command buffer */ - phys_lsb = data ? lower_32_bits(__psp_pa(sev->cmd_buf)) : 0; - phys_msb = data ? upper_32_bits(__psp_pa(sev->cmd_buf)) : 0; + phys_lsb = data ? lower_32_bits(__psp_pa(cmd_buf)) : 0; + phys_msb = data ? upper_32_bits(__psp_pa(cmd_buf)) : 0; dev_dbg(sev->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", cmd, phys_msb, phys_lsb, psp_timeout); @@ -364,7 +925,18 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) sev->int_rcvd = 0; - reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd) | SEV_CMDRESP_IOC; + reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd); + + /* + * If invoked during panic handling, local interrupts are disabled so + * the PSP command completion interrupt can't be used. + * sev_wait_cmd_ioc() already checks for interrupts disabled and + * polls for PSP command completion. Ensure we do not request an + * interrupt from the PSP if irqs disabled. + */ + if (!irqs_disabled()) + reg |= SEV_CMDRESP_IOC; + iowrite32(reg, sev->io_regs + sev->vdata->cmdresp_reg); /* wait for command completion */ @@ -392,20 +964,41 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) ret = sev_write_init_ex_file_if_required(cmd); } - print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, - buf_len, false); - /* * Copy potential output from the PSP back to data. Do this even on * failure in case the caller wants to glean something from the error. */ - if (data) - memcpy(data, sev->cmd_buf, buf_len); + if (data) { + int ret_reclaim; + /* + * Restore the page state after the command completes. + */ + ret_reclaim = snp_reclaim_cmd_buf(cmd, cmd_buf); + if (ret_reclaim) { + dev_err(sev->dev, + "SEV: failed to reclaim buffer for legacy command %#x. Error: %d\n", + cmd, ret_reclaim); + return ret_reclaim; + } + + memcpy(data, cmd_buf, buf_len); + + if (sev->cmd_buf_backup_active) + sev->cmd_buf_backup_active = false; + else + sev->cmd_buf_active = false; + + if (snp_unmap_cmd_buf_desc_list(desc_list)) + return -EFAULT; + } + + print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, + buf_len, false); return ret; } -static int sev_do_cmd(int cmd, void *data, int *psp_ret) +int sev_do_cmd(int cmd, void *data, int *psp_ret) { int rc; int mutex_enabled = READ_ONCE(hygon_psp_hooks.psp_mutex_enabled); @@ -425,76 +1018,269 @@ static int sev_do_cmd(int cmd, void *data, int *psp_ret) return rc; } +EXPORT_SYMBOL_GPL(sev_do_cmd); + +static int __sev_init_locked(int *error) +{ + struct sev_data_init data; + + memset(&data, 0, sizeof(data)); + if (sev_es_tmr) { + /* + * Do not include the encryption mask on the physical + * address of the TMR (firmware should clear it anyway). + */ + data.tmr_address = __pa(sev_es_tmr); + + data.flags |= SEV_INIT_FLAGS_SEV_ES; + data.tmr_len = sev_es_tmr_size; + } + + return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error); +} + +static int __sev_init_ex_locked(int *error) +{ + struct sev_data_init_ex data; + + memset(&data, 0, sizeof(data)); + data.length = sizeof(data); + data.nv_address = __psp_pa(sev_init_ex_buffer); + data.nv_len = NV_LENGTH; + + if (sev_es_tmr) { + /* + * Do not include the encryption mask on the physical + * address of the TMR (firmware should clear it anyway). + */ + data.tmr_address = __pa(sev_es_tmr); + + data.flags |= SEV_INIT_FLAGS_SEV_ES; + data.tmr_len = sev_es_tmr_size; + } + + return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error); +} + +static inline int __sev_do_init_locked(int *psp_ret) +{ + if (sev_init_ex_buffer) + return __sev_init_ex_locked(psp_ret); + else + return __sev_init_locked(psp_ret); +} + +static void snp_set_hsave_pa(void *arg) +{ + wrmsrl(MSR_VM_HSAVE_PA, 0); +} + +static int snp_filter_reserved_mem_regions(struct resource *rs, void *arg) +{ + struct sev_data_range_list *range_list = arg; + struct sev_data_range *range = &range_list->ranges[range_list->num_elements]; + size_t size; + + /* + * Ensure the list of HV_FIXED pages that will be passed to firmware + * do not exceed the page-sized argument buffer. + */ + if ((range_list->num_elements * sizeof(struct sev_data_range) + + sizeof(struct sev_data_range_list)) > PAGE_SIZE) + return -E2BIG; + + switch (rs->desc) { + case E820_TYPE_RESERVED: + case E820_TYPE_PMEM: + case E820_TYPE_ACPI: + range->base = rs->start & PAGE_MASK; + size = PAGE_ALIGN((rs->end + 1) - rs->start); + range->page_count = size >> PAGE_SHIFT; + range_list->num_elements++; + break; + default: + break; + } + + return 0; +} + +static int __sev_snp_init_locked(int *error) +{ + struct psp_device *psp = psp_master; + struct sev_data_snp_init_ex data; + struct sev_device *sev; + void *arg = &data; + int cmd, rc = 0; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + sev = psp->sev_data; + + if (sev->snp_initialized) + return 0; + + if (!sev_version_greater_or_equal(SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR)) { + dev_dbg(sev->dev, "SEV-SNP support requires firmware version >= %d:%d\n", + SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR); + return 0; + } + + /* SNP_INIT requires MSR_VM_HSAVE_PA to be cleared on all CPUs. */ + on_each_cpu(snp_set_hsave_pa, NULL, 1); + + /* + * Starting in SNP firmware v1.52, the SNP_INIT_EX command takes a list + * of system physical address ranges to convert into HV-fixed page + * states during the RMP initialization. For instance, the memory that + * UEFI reserves should be included in the that list. This allows system + * components that occasionally write to memory (e.g. logging to UEFI + * reserved regions) to not fail due to RMP initialization and SNP + * enablement. + * + */ + if (sev_version_greater_or_equal(SNP_MIN_API_MAJOR, 52)) { + /* + * Firmware checks that the pages containing the ranges enumerated + * in the RANGES structure are either in the default page state or in the + * firmware page state. + */ + snp_range_list = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!snp_range_list) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX range list memory allocation failed\n"); + return -ENOMEM; + } + + /* + * Retrieve all reserved memory regions from the e820 memory map + * to be setup as HV-fixed pages. + */ + rc = walk_iomem_res_desc(IORES_DESC_NONE, IORESOURCE_MEM, 0, ~0, + snp_range_list, snp_filter_reserved_mem_regions); + if (rc) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX walk_iomem_res_desc failed rc = %d\n", rc); + return rc; + } + + memset(&data, 0, sizeof(data)); + data.init_rmp = 1; + data.list_paddr_en = 1; + data.list_paddr = __psp_pa(snp_range_list); + cmd = SEV_CMD_SNP_INIT_EX; + } else { + cmd = SEV_CMD_SNP_INIT; + arg = NULL; + } + + /* + * The following sequence must be issued before launching the first SNP + * guest to ensure all dirty cache lines are flushed, including from + * updates to the RMP table itself via the RMPUPDATE instruction: + * + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_INIT[_EX] firmware command + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_DF_FLUSH firmware command + */ + wbinvd_on_all_cpus(); + + rc = __sev_do_cmd_locked(cmd, arg, error); + if (rc) + return rc; + + /* Prepare for first SNP guest launch after INIT. */ + wbinvd_on_all_cpus(); + rc = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, error); + if (rc) + return rc; + + sev->snp_initialized = true; + dev_dbg(sev->dev, "SEV-SNP firmware initialized\n"); + + sev_es_tmr_size = SNP_TMR_SIZE; + + return rc; +} -static int __sev_init_locked(int *error) +static void __sev_platform_init_handle_tmr(struct sev_device *sev) { - struct sev_data_init data; + if (sev_es_tmr) + return; - memset(&data, 0, sizeof(data)); + /* Obtain the TMR memory area for SEV-ES use */ + sev_es_tmr = sev_fw_alloc(sev_es_tmr_size); if (sev_es_tmr) { - /* - * Do not include the encryption mask on the physical - * address of the TMR (firmware should clear it anyway). - */ - data.tmr_address = __pa(sev_es_tmr); - - data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + /* Must flush the cache before giving it to the firmware */ + if (!sev->snp_initialized) + clflush_cache_range(sev_es_tmr, sev_es_tmr_size); + } else { + dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n"); } - - return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error); } -static int __sev_init_ex_locked(int *error) +/* + * If an init_ex_path is provided allocate a buffer for the file and + * read in the contents. Additionally, if SNP is initialized, convert + * the buffer pages to firmware pages. + */ +static int __sev_platform_init_handle_init_ex_path(struct sev_device *sev) { - struct sev_data_init_ex data; + struct page *page; + int rc; - memset(&data, 0, sizeof(data)); - data.length = sizeof(data); - data.nv_address = __psp_pa(sev_init_ex_buffer); - data.nv_len = NV_LENGTH; + if (!init_ex_path) + return 0; - if (sev_es_tmr) { - /* - * Do not include the encryption mask on the physical - * address of the TMR (firmware should clear it anyway). - */ - data.tmr_address = __pa(sev_es_tmr); + if (sev_init_ex_buffer) + return 0; - data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + page = alloc_pages(GFP_KERNEL, get_order(NV_LENGTH)); + if (!page) { + dev_err(sev->dev, "SEV: INIT_EX NV memory allocation failed\n"); + return -ENOMEM; } - return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error); -} + sev_init_ex_buffer = page_address(page); -static inline int __sev_do_init_locked(int *psp_ret) -{ - if (sev_init_ex_buffer) - return __sev_init_ex_locked(psp_ret); - else - return __sev_init_locked(psp_ret); + rc = sev_read_init_ex_file(); + if (rc) + return rc; + + /* If SEV-SNP is initialized, transition to firmware page. */ + if (sev->snp_initialized) { + unsigned long npages; + + npages = 1UL << get_order(NV_LENGTH); + if (rmp_mark_pages_firmware(__pa(sev_init_ex_buffer), npages, false)) { + dev_err(sev->dev, "SEV: INIT_EX NV memory page state change failed.\n"); + return -ENOMEM; + } + } + + return 0; } static int __sev_platform_init_locked(int *error) { - int rc = 0, psp_ret = SEV_RET_NO_FW_CALL; - struct psp_device *psp = psp_master; + int rc, psp_ret = SEV_RET_NO_FW_CALL; struct sev_device *sev; - if (!psp || !psp->sev_data) + if (!psp_master || !psp_master->sev_data) return -ENODEV; - sev = psp->sev_data; + sev = psp_master->sev_data; if (sev->state == SEV_STATE_INIT) return 0; - if (sev_init_ex_buffer) { - rc = sev_read_init_ex_file(); - if (rc) - return rc; - } + __sev_platform_init_handle_tmr(sev); + + rc = __sev_platform_init_handle_init_ex_path(sev); + if (rc) + return rc; rc = __sev_do_init_locked(&psp_ret); if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) { @@ -536,7 +1322,41 @@ static int __sev_platform_init_locked(int *error) return 0; } -int sev_platform_init(int *error) +static int _sev_platform_init_locked(struct sev_platform_init_args *args) +{ + struct sev_device *sev; + int rc; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + sev = psp_master->sev_data; + + if (sev->state == SEV_STATE_INIT) + return 0; + + /* + * Legacy guests cannot be running while SNP_INIT(_EX) is executing, + * so perform SEV-SNP initialization at probe time. + */ + rc = __sev_snp_init_locked(&args->error); + if (rc && rc != -ENODEV) { + /* + * Don't abort the probe if SNP INIT failed, + * continue to initialize the legacy SEV firmware. + */ + dev_err(sev->dev, "SEV-SNP: failed to INIT rc %d, error %#x\n", + rc, args->error); + } + + /* Defer legacy SEV/SEV-ES support if allowed by caller/module. */ + if (args->probe && !psp_init_on_probe) + return 0; + + return __sev_platform_init_locked(&args->error); +} + +int sev_platform_init(struct sev_platform_init_args *args) { int rc; int mutex_enabled = READ_ONCE(hygon_psp_hooks.psp_mutex_enabled); @@ -548,7 +1368,7 @@ int sev_platform_init(int *error) } else { mutex_lock(&sev_cmd_mutex); } - rc = __sev_platform_init_locked(error); + rc = _sev_platform_init_locked(args); if (is_vendor_hygon() && mutex_enabled) psp_mutex_unlock(&hygon_psp_hooks.psp_misc->data_pg_aligned->mb_mutex); else @@ -586,27 +1406,6 @@ static int __sev_platform_shutdown_locked(int *error) return ret; } -static int sev_platform_shutdown(int *error) -{ - int rc; - int mutex_enabled = READ_ONCE(hygon_psp_hooks.psp_mutex_enabled); - - if (is_vendor_hygon() && mutex_enabled) { - if (psp_mutex_lock_timeout(&hygon_psp_hooks.psp_misc->data_pg_aligned->mb_mutex, - PSP_MUTEX_TIMEOUT) != 1) - return -EBUSY; - } else { - mutex_lock(&sev_cmd_mutex); - } - rc = __sev_platform_shutdown_locked(NULL); - if (is_vendor_hygon() && mutex_enabled) - psp_mutex_unlock(&hygon_psp_hooks.psp_misc->data_pg_aligned->mb_mutex); - else - mutex_unlock(&sev_cmd_mutex); - - return rc; -} - static int sev_get_platform_state(int *state, int *error) { struct sev_user_data_status data; @@ -901,6 +1700,78 @@ static int sev_update_firmware(struct device *dev) return ret; } +static int __sev_snp_shutdown_locked(int *error, bool panic) +{ + struct psp_device *psp = psp_master; + struct sev_device *sev; + struct sev_data_snp_shutdown_ex data; + int ret; + + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (!sev->snp_initialized) + return 0; + + memset(&data, 0, sizeof(data)); + data.len = sizeof(data); + data.iommu_snp_shutdown = 1; + + /* + * If invoked during panic handling, local interrupts are disabled + * and all CPUs are stopped, so wbinvd_on_all_cpus() can't be called. + * In that case, a wbinvd() is done on remote CPUs via the NMI + * callback, so only a local wbinvd() is needed here. + */ + if (!panic) + wbinvd_on_all_cpus(); + else + wbinvd(); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, error); + /* SHUTDOWN may require DF_FLUSH */ + if (*error == SEV_RET_DFFLUSH_REQUIRED) { + ret = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, NULL); + if (ret) { + dev_err(sev->dev, "SEV-SNP DF_FLUSH failed\n"); + return ret; + } + /* reissue the shutdown command */ + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, + error); + } + if (ret) { + dev_err(sev->dev, "SEV-SNP firmware shutdown failed\n"); + return ret; + } + + /* + * SNP_SHUTDOWN_EX with IOMMU_SNP_SHUTDOWN set to 1 disables SNP + * enforcement by the IOMMU and also transitions all pages + * associated with the IOMMU to the Reclaim state. + * Firmware was transitioning the IOMMU pages to Hypervisor state + * before version 1.53. But, accounting for the number of assigned + * 4kB pages in a 2M page was done incorrectly by not transitioning + * to the Reclaim state. This resulted in RMP #PF when later accessing + * the 2M page containing those pages during kexec boot. Hence, the + * firmware now transitions these pages to Reclaim state and hypervisor + * needs to transition these pages to shared state. SNP Firmware + * version 1.53 and above are needed for kexec boot. + */ + ret = amd_iommu_snp_disable(); + if (ret) { + dev_err(sev->dev, "SNP IOMMU shutdown failed\n"); + return ret; + } + + sev->snp_initialized = false; + dev_dbg(sev->dev, "SEV-SNP firmware shutdown\n"); + + return ret; +} + static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; @@ -1143,6 +2014,118 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) return ret; } +static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_addr buf; + struct page *status_page; + void *data; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + status_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!status_page) + return -ENOMEM; + + data = page_address(status_page); + + /* + * Firmware expects status page to be in firmware-owned state, otherwise + * it will report firmware error code INVALID_PAGE_STATE (0x1A). + */ + if (rmp_mark_pages_firmware(__pa(data), 1, true)) { + ret = -EFAULT; + goto cleanup; + } + + buf.address = __psp_pa(data); + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error); + + /* + * Status page will be transitioned to Reclaim state upon success, or + * left in Firmware state in failure. Use snp_reclaim_pages() to + * transition either case back to Hypervisor-owned state. + */ + if (snp_reclaim_pages(__pa(data), 1, true)) + return -EFAULT; + + if (ret) + goto cleanup; + + if (copy_to_user((void __user *)argp->data, data, + sizeof(struct sev_user_data_snp_status))) + ret = -EFAULT; + +cleanup: + __free_pages(status_page, 0); + return ret; +} + +static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_commit buf; + + if (!sev->snp_initialized) + return -EINVAL; + + buf.len = sizeof(buf); + + return __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error); +} + +static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_config config; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&config, (void __user *)argp->data, sizeof(config))) + return -EFAULT; + + return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); +} + +static int sev_ioctl_do_snp_vlek_load(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_vlek_load input; + void *blob; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&input, u64_to_user_ptr(argp->data), sizeof(input))) + return -EFAULT; + + if (input.len != sizeof(input) || input.vlek_wrapped_version != 0) + return -EINVAL; + + blob = psp_copy_user_blob(input.vlek_wrapped_address, + sizeof(struct sev_user_data_snp_wrapped_vlek_hashstick)); + if (IS_ERR(blob)) + return PTR_ERR(blob); + + input.vlek_wrapped_address = __psp_pa(blob); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_VLEK_LOAD, &input, &argp->error); + + kfree(blob); + + return ret; +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -1201,6 +2184,18 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SEV_GET_ID2: ret = sev_ioctl_do_get_id2(&input); break; + case SNP_PLATFORM_STATUS: + ret = sev_ioctl_do_snp_platform_status(&input); + break; + case SNP_COMMIT: + ret = sev_ioctl_do_snp_commit(&input); + break; + case SNP_SET_CONFIG: + ret = sev_ioctl_do_snp_set_config(&input, writable); + break; + case SNP_VLEK_LOAD: + ret = sev_ioctl_do_snp_vlek_load(&input, writable); + break; default: ret = -EINVAL; goto out; @@ -1344,10 +2339,12 @@ int sev_dev_init(struct psp_device *psp) if (!sev) goto e_err; - sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0); + sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 1); if (!sev->cmd_buf) goto e_sev; + sev->cmd_buf_backup = (uint8_t *)sev->cmd_buf + PAGE_SIZE; + psp->sev_data = sev; sev->dev = dev; @@ -1386,24 +2383,51 @@ int sev_dev_init(struct psp_device *psp) return ret; } -static void sev_firmware_shutdown(struct sev_device *sev) +static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) { - sev_platform_shutdown(NULL); + int error; + + __sev_platform_shutdown_locked(NULL); if (sev_es_tmr) { - /* The TMR area was encrypted, flush it from the cache */ - wbinvd_on_all_cpus(); + /* + * The TMR area was encrypted, flush it from the cache. + * + * If invoked during panic handling, local interrupts are + * disabled and all CPUs are stopped, so wbinvd_on_all_cpus() + * can't be used. In that case, wbinvd() is done on remote CPUs + * via the NMI callback, and done for this CPU later during + * SNP shutdown, so wbinvd_on_all_cpus() can be skipped. + */ + if (!panic) + wbinvd_on_all_cpus(); - free_pages((unsigned long)sev_es_tmr, - get_order(SEV_ES_TMR_SIZE)); + __snp_free_firmware_pages(virt_to_page(sev_es_tmr), + get_order(sev_es_tmr_size), + true); sev_es_tmr = NULL; } if (sev_init_ex_buffer) { - free_pages((unsigned long)sev_init_ex_buffer, - get_order(NV_LENGTH)); + __snp_free_firmware_pages(virt_to_page(sev_init_ex_buffer), + get_order(NV_LENGTH), + true); sev_init_ex_buffer = NULL; } + + if (snp_range_list) { + kfree(snp_range_list); + snp_range_list = NULL; + } + + __sev_snp_shutdown_locked(&error, panic); +} + +static void sev_firmware_shutdown(struct sev_device *sev) +{ + mutex_lock(&sev_cmd_mutex); + __sev_firmware_shutdown(sev, false); + mutex_unlock(&sev_cmd_mutex); } void sev_dev_destroy(struct psp_device *psp) @@ -1421,6 +2445,29 @@ void sev_dev_destroy(struct psp_device *psp) psp_clear_sev_irq_handler(psp); } +static int snp_shutdown_on_panic(struct notifier_block *nb, + unsigned long reason, void *arg) +{ + struct sev_device *sev = psp_master->sev_data; + + /* + * If sev_cmd_mutex is already acquired, then it's likely + * another PSP command is in flight and issuing a shutdown + * would fail in unexpected ways. Rather than create even + * more confusion during a panic, just bail out here. + */ + if (mutex_is_locked(&sev_cmd_mutex)) + return NOTIFY_DONE; + + __sev_firmware_shutdown(sev, true); + + return NOTIFY_DONE; +} + +static struct notifier_block snp_panic_notifier = { + .notifier_call = snp_shutdown_on_panic, +}; + int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd, void *data, int *error) { @@ -1436,6 +2483,7 @@ void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; int error, rc; + struct sev_platform_init_args args = {0}; if (!sev) return; @@ -1448,40 +2496,22 @@ void sev_pci_init(void) if (sev_update_firmware(sev->dev) == 0) sev_get_api_version(); - /* If an init_ex_path is provided rely on INIT_EX for PSP initialization - * instead of INIT. - */ - if (init_ex_path) { - sev_init_ex_buffer = sev_fw_alloc(NV_LENGTH); - if (!sev_init_ex_buffer) { - dev_err(sev->dev, - "SEV: INIT_EX NV memory allocation failed\n"); - goto err; - } - } - - /* Obtain the TMR memory area for SEV-ES use */ - sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); - if (sev_es_tmr) - /* Must flush the cache before giving it to the firmware */ - clflush_cache_range(sev_es_tmr, SEV_ES_TMR_SIZE); - else - dev_warn(sev->dev, - "SEV: TMR allocation failed, SEV-ES support unavailable\n"); - - if (!psp_init_on_probe) - return; - /* Set SMR for HYGON CSV3 */ if (is_vendor_hygon() && boot_cpu_has(X86_FEATURE_CSV3)) csv_platform_cmd_set_secure_memory_region(sev, &error); /* Initialize the platform */ - rc = sev_platform_init(&error); + args.probe = true; + rc = sev_platform_init(&args); if (rc) dev_err(sev->dev, "SEV: failed to INIT error %#x, rc %d\n", - error, rc); + args.error, rc); + dev_info(sev->dev, "SEV%s API:%d.%d build:%d\n", sev->snp_initialized ? + "-SNP" : "", sev->api_major, sev->api_minor, sev->build); + + atomic_notifier_chain_register(&panic_notifier_list, + &snp_panic_notifier); return; err: @@ -1498,4 +2528,7 @@ void sev_pci_exit(void) return; sev_firmware_shutdown(sev); + + atomic_notifier_chain_unregister(&panic_notifier_list, + &snp_panic_notifier); } diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h index 388d85415bf5ebe73618599ce959ffb463919005..e85c8bb7bbb8b74a1940285b46a8cedfedcb428c 100644 --- a/drivers/crypto/ccp/sev-dev.h +++ b/drivers/crypto/ccp/sev-dev.h @@ -54,9 +54,14 @@ struct sev_device { u8 build; void *cmd_buf; + void *cmd_buf_backup; + bool cmd_buf_active; + bool cmd_buf_backup_active; /* Management of the Hygon RING BUFFER mode */ struct csv_ringbuffer_queue ring_buffer[CSV_COMMAND_PRIORITY_NUM]; + + bool snp_initialized; }; int sev_dev_init(struct psp_device *psp); diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index e2857109e966015e94efb919f28723c8ed151fa4..188cfbfa094e95f8292fb1d8579928adc6e3c704 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -87,9 +87,19 @@ static inline bool is_rd890_iommu(struct pci_dev *pdev) (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); } -static inline bool iommu_feature(struct amd_iommu *iommu, u64 mask) +static inline bool check_feature(u64 mask) { - return !!(iommu->features & mask); + return (amd_iommu_efr & mask); +} + +static inline bool check_feature2(u64 mask) +{ + return (amd_iommu_efr2 & mask); +} + +static inline int check_feature_gpt_level(void) +{ + return ((amd_iommu_efr >> FEATURE_GATS_SHIFT) & FEATURE_GATS_MASK); } static inline u64 iommu_virt_to_phys(void *vaddr) @@ -146,8 +156,4 @@ void amd_iommu_domain_set_pgtable(struct protection_domain *domain, u64 *root, int mode); struct dev_table_entry *get_dev_table(struct amd_iommu *iommu); -extern u64 amd_iommu_efr; -extern u64 amd_iommu_efr2; - -extern bool amd_iommu_snp_en; #endif diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index dec4e5c2b66b8236fcd6faeb8497fdc9b42dfe20..13a747106c11a3eec3208cbfba4fad07ca89823d 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -906,6 +906,10 @@ extern bool amd_iommu_force_isolation; /* Max levels of glxval supported */ extern int amd_iommu_max_glx_val; +/* Global EFR and EFR2 registers */ +extern u64 amd_iommu_efr; +extern u64 amd_iommu_efr2; + /* * This function flushes all internal caches of * the IOMMU used by this driver. diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 4beddd8cc42014cfa4dceba9d93a63034568bf84..caa547c5c7d411950901387d57e90fe4e056feb4 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -30,6 +30,7 @@ #include #include #include +#include #include @@ -272,7 +273,7 @@ int amd_iommu_get_num_iommus(void) * Iterate through all the IOMMUs to get common EFR * masks among all IOMMUs and warn if found inconsistency. */ -static void get_global_efr(void) +static __init void get_global_efr(void) { struct amd_iommu *iommu; @@ -304,16 +305,6 @@ static void get_global_efr(void) pr_info("Using global IVHD EFR:%#llx, EFR2:%#llx\n", amd_iommu_efr, amd_iommu_efr2); } -static bool check_feature_on_all_iommus(u64 mask) -{ - return !!(amd_iommu_efr & mask); -} - -static inline int check_feature_gpt_level(void) -{ - return ((amd_iommu_efr >> FEATURE_GATS_SHIFT) & FEATURE_GATS_MASK); -} - /* * For IVHD type 0x11/0x40, EFR is also available via IVHD. * Default to IVHD EFR since it is available sooner @@ -399,7 +390,7 @@ static void iommu_set_cwwb_range(struct amd_iommu *iommu) u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem); u64 entry = start & PM_ADDR_MASK; - if (!check_feature_on_all_iommus(FEATURE_SNP)) + if (!check_feature(FEATURE_SNP)) return; /* Note: @@ -869,7 +860,7 @@ static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, void *buf = (void *)__get_free_pages(gfp, order); if (buf && - check_feature_on_all_iommus(FEATURE_SNP) && + check_feature(FEATURE_SNP) && set_memory_4k((unsigned long)buf, (1 << order))) { free_pages((unsigned long)buf, order); buf = NULL; @@ -1048,7 +1039,7 @@ static void iommu_enable_xt(struct amd_iommu *iommu) static void iommu_enable_gt(struct amd_iommu *iommu) { - if (!iommu_feature(iommu, FEATURE_GT)) + if (!check_feature(FEATURE_GT)) return; iommu_feature_enable(iommu, CONTROL_GT_EN); @@ -1996,7 +1987,7 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu) u64 val; struct pci_dev *pdev = iommu->dev; - if (!iommu_feature(iommu, FEATURE_PC)) + if (!check_feature(FEATURE_PC)) return; amd_iommu_pc_present = true; @@ -2023,8 +2014,7 @@ static ssize_t amd_iommu_show_features(struct device *dev, struct device_attribute *attr, char *buf) { - struct amd_iommu *iommu = dev_to_amd_iommu(dev); - return sysfs_emit(buf, "%llx:%llx\n", iommu->features2, iommu->features); + return sysfs_emit(buf, "%llx:%llx\n", amd_iommu_efr, amd_iommu_efr2); } static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL); @@ -2060,9 +2050,9 @@ static void __init late_iommu_features_init(struct amd_iommu *iommu) features = readq(iommu->mmio_base + MMIO_EXT_FEATURES); features2 = readq(iommu->mmio_base + MMIO_EXT_FEATURES2); - if (!iommu->features) { - iommu->features = features; - iommu->features2 = features2; + if (!amd_iommu_efr) { + amd_iommu_efr = features; + amd_iommu_efr2 = features2; return; } @@ -2070,12 +2060,12 @@ static void __init late_iommu_features_init(struct amd_iommu *iommu) * Sanity check and warn if EFR values from * IVHD and MMIO conflict. */ - if (features != iommu->features || - features2 != iommu->features2) { + if (features != amd_iommu_efr || + features2 != amd_iommu_efr2) { pr_warn(FW_WARN "EFR mismatch. Use IVHD EFR (%#llx : %#llx), EFR2 (%#llx : %#llx).\n", - features, iommu->features, - features2, iommu->features2); + features, amd_iommu_efr, + features2, amd_iommu_efr2); } } @@ -2104,12 +2094,12 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) late_iommu_features_init(iommu); - if (iommu_feature(iommu, FEATURE_GT)) { + if (check_feature(FEATURE_GT)) { int glxval; u32 max_pasid; u64 pasmax; - pasmax = iommu->features & FEATURE_PASID_MASK; + pasmax = amd_iommu_efr & FEATURE_PASID_MASK; pasmax >>= FEATURE_PASID_SHIFT; max_pasid = (1 << (pasmax + 1)) - 1; @@ -2117,7 +2107,7 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) BUG_ON(amd_iommu_max_pasid & ~PASID_MASK); - glxval = iommu->features & FEATURE_GLXVAL_MASK; + glxval = amd_iommu_efr & FEATURE_GLXVAL_MASK; glxval >>= FEATURE_GLXVAL_SHIFT; if (amd_iommu_max_glx_val == -1) @@ -2126,13 +2116,13 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval); } - if (iommu_feature(iommu, FEATURE_GT) && - iommu_feature(iommu, FEATURE_PPR)) { + if (check_feature(FEATURE_GT) && + check_feature(FEATURE_PPR)) { iommu->is_iommu_v2 = true; amd_iommu_v2_present = true; } - if (iommu_feature(iommu, FEATURE_PPR) && alloc_ppr_log(iommu)) + if (check_feature(FEATURE_PPR) && alloc_ppr_log(iommu)) return -ENOMEM; if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) { @@ -2144,8 +2134,8 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) init_iommu_perf_ctr(iommu); if (amd_iommu_pgtable == AMD_IOMMU_V2) { - if (!iommu_feature(iommu, FEATURE_GIOSUP) || - !iommu_feature(iommu, FEATURE_GT)) { + if (!check_feature(FEATURE_GIOSUP) || + !check_feature(FEATURE_GT)) { pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n"); amd_iommu_pgtable = AMD_IOMMU_V1; } else if (iommu_default_passthrough()) { @@ -2198,35 +2188,29 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) static void print_iommu_info(void) { + int i; static const char * const feat_str[] = { "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", "IA", "GA", "HE", "PC" }; - struct amd_iommu *iommu; - - for_each_iommu(iommu) { - struct pci_dev *pdev = iommu->dev; - int i; - - pci_info(pdev, "Found IOMMU cap 0x%x\n", iommu->cap_ptr); - if (iommu->cap & (1 << IOMMU_CAP_EFR)) { - pr_info("Extended features (%#llx, %#llx):", iommu->features, iommu->features2); + if (amd_iommu_efr) { + pr_info("Extended features (%#llx, %#llx):", amd_iommu_efr, amd_iommu_efr2); - for (i = 0; i < ARRAY_SIZE(feat_str); ++i) { - if (iommu_feature(iommu, (1ULL << i))) - pr_cont(" %s", feat_str[i]); - } + for (i = 0; i < ARRAY_SIZE(feat_str); ++i) { + if (check_feature(1ULL << i)) + pr_cont(" %s", feat_str[i]); + } - if (iommu->features & FEATURE_GAM_VAPIC) - pr_cont(" GA_vAPIC"); + if (check_feature(FEATURE_GAM_VAPIC)) + pr_cont(" GA_vAPIC"); - if (iommu->features & FEATURE_SNP) - pr_cont(" SNP"); + if (check_feature(FEATURE_SNP)) + pr_cont(" SNP"); - pr_cont("\n"); - } + pr_cont("\n"); } + if (irq_remapping_enabled) { pr_info("Interrupt remapping enabled\n"); if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) @@ -2924,7 +2908,7 @@ static void enable_iommus_vapic(void) } if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) && - !check_feature_on_all_iommus(FEATURE_GAM_VAPIC)) { + !check_feature(FEATURE_GAM_VAPIC)) { amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA; return; } @@ -3275,6 +3259,47 @@ static bool __init detect_ivrs(void) return true; } +static __init void iommu_snp_enable(void) +{ +#ifdef CONFIG_KVM_AMD_SEV + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return; + /* + * The SNP support requires that IOMMU must be enabled, and is + * configured with V1 page table (DTE[Mode] = 0 is not supported). + */ + if (no_iommu || iommu_default_passthrough()) { + pr_warn("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n"); + goto disable_snp; + } + + if (amd_iommu_pgtable != AMD_IOMMU_V1) { + pr_warn("SNP: IOMMU is configured with V2 page table mode, SNP cannot be supported.\n"); + goto disable_snp; + } + + amd_iommu_snp_en = check_feature(FEATURE_SNP); + if (!amd_iommu_snp_en) { + pr_warn("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n"); + goto disable_snp; + } + + /* + * Enable host SNP support once SNP support is checked on IOMMU. + */ + if (snp_rmptable_init()) { + pr_warn("SNP: RMP initialization failed, SNP cannot be supported.\n"); + goto disable_snp; + } + + pr_info("IOMMU SNP support enabled.\n"); + return; + +disable_snp: + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); +#endif +} + /**************************************************************************** * * AMD IOMMU Initialization State Machine @@ -3310,6 +3335,7 @@ static int __init state_next(void) break; case IOMMU_ENABLED: register_syscore_ops(&amd_iommu_syscore_ops); + iommu_snp_enable(); ret = amd_iommu_init_pci(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; break; @@ -3365,6 +3391,19 @@ static int __init iommu_go_to_state(enum iommu_init_state state) ret = state_next(); } + /* + * SNP platform initilazation requires IOMMUs to be fully configured. + * If the SNP support on IOMMUs has NOT been checked, simply mark SNP + * as unsupported. If the SNP support on IOMMUs has been checked and + * host SNP support enabled but RMP enforcement has not been enabled + * in IOMMUs, then the system is in a half-baked state, but can limp + * along as all memory should be Hypervisor-Owned in the RMP. WARN, + * but leave SNP as "supported" to avoid confusing the kernel. + */ + if (ret && cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !WARN_ON_ONCE(amd_iommu_snp_en)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + return ret; } @@ -3468,25 +3507,28 @@ static bool amd_iommu_sme_check(void) * IOMMUs * ****************************************************************************/ -int __init amd_iommu_detect(void) +void __init amd_iommu_detect(void) { int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return -ENODEV; + goto disable_snp; if (!amd_iommu_sme_check()) - return -ENODEV; + goto disable_snp; ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); if (ret) - return ret; + goto disable_snp; amd_iommu_detected = true; iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; + return; - return 1; +disable_snp: + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); } /**************************************************************************** @@ -3822,40 +3864,85 @@ int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true); } -#ifdef CONFIG_AMD_MEM_ENCRYPT -int amd_iommu_snp_enable(void) +#ifdef CONFIG_KVM_AMD_SEV +static int iommu_page_make_shared(void *page) { - /* - * The SNP support requires that IOMMU must be enabled, and is - * not configured in the passthrough mode. - */ - if (no_iommu || iommu_default_passthrough()) { - pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported"); - return -EINVAL; + unsigned long paddr, pfn; + + paddr = iommu_virt_to_phys(page); + /* Cbit maybe set in the paddr */ + pfn = __sme_clr(paddr) >> PAGE_SHIFT; + + if (!(pfn % PTRS_PER_PMD)) { + int ret, level; + bool assigned; + + ret = snp_lookup_rmpentry(pfn, &assigned, &level); + if (ret) { + pr_warn("IOMMU PFN %lx RMP lookup failed, ret %d\n", pfn, ret); + return ret; + } + + if (!assigned) { + pr_warn("IOMMU PFN %lx not assigned in RMP table\n", pfn); + return -EINVAL; + } + + if (level > PG_LEVEL_4K) { + ret = psmash(pfn); + if (!ret) + goto done; + + pr_warn("PSMASH failed for IOMMU PFN %lx huge RMP entry, ret: %d, level: %d\n", + pfn, ret, level); + return ret; + } } - /* - * Prevent enabling SNP after IOMMU_ENABLED state because this process - * affect how IOMMU driver sets up data structures and configures - * IOMMU hardware. - */ - if (init_state > IOMMU_ENABLED) { - pr_err("SNP: Too late to enable SNP for IOMMU.\n"); - return -EINVAL; +done: + return rmp_make_shared(pfn, PG_LEVEL_4K); +} + +static int iommu_make_shared(void *va, size_t size) +{ + void *page; + int ret; + + if (!va) + return 0; + + for (page = va; page < (va + size); page += PAGE_SIZE) { + ret = iommu_page_make_shared(page); + if (ret) + return ret; } - amd_iommu_snp_en = check_feature_on_all_iommus(FEATURE_SNP); + return 0; +} + +int amd_iommu_snp_disable(void) +{ + struct amd_iommu *iommu; + int ret; + if (!amd_iommu_snp_en) - return -EINVAL; + return 0; - pr_info("SNP enabled\n"); + for_each_iommu(iommu) { + ret = iommu_make_shared(iommu->evt_buf, EVT_BUFFER_SIZE); + if (ret) + return ret; - /* Enforce IOMMU v1 pagetable when SNP is enabled. */ - if (amd_iommu_pgtable != AMD_IOMMU_V1) { - pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n"); - amd_iommu_pgtable = AMD_IOMMU_V1; + ret = iommu_make_shared(iommu->ppr_log, PPR_LOG_SIZE); + if (ret) + return ret; + + ret = iommu_make_shared((void *)iommu->cmd_sem, PAGE_SIZE); + if (ret) + return ret; } return 0; } +EXPORT_SYMBOL_GPL(amd_iommu_snp_disable); #endif diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 41557c5e158b2281d63ec448b577d17011617d9e..9b9f1820ea3edfd8fc3db03418d5a0ab028b3724 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1298,7 +1298,7 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu) void iommu_flush_all_caches(struct amd_iommu *iommu) { - if (iommu_feature(iommu, FEATURE_IA)) { + if (check_feature(FEATURE_IA)) { amd_iommu_flush_all(iommu); } else { amd_iommu_flush_dte_all(iommu); @@ -1606,7 +1606,7 @@ static void set_dte_entry(struct amd_iommu *iommu, u16 devid, flags |= DTE_FLAG_IOTLB; if (ppr) { - if (iommu_feature(iommu, FEATURE_EPHSUP)) + if (check_feature(FEATURE_EPHSUP)) pte_root |= 1ULL << DEV_ENTRY_PPR; } diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig index da2d7ca531f0fb7cdcc7fbd9a1d660bb72ac950d..1cffc72c41cb1461020dff76db8b84ffb7527795 100644 --- a/drivers/virt/coco/sev-guest/Kconfig +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -5,6 +5,7 @@ config SEV_GUEST select CRYPTO select CRYPTO_AEAD2 select CRYPTO_GCM + select TSM_REPORTS help SEV-SNP firmware provides the guest a mechanism to communicate with the PSP without risk from a malicious hypervisor who wishes to read, diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index 5bee58ef5f1e3977da39335bce6865d926dc381e..ed1f4ae30e0b8b3c4a6d46498fcb01ef2c5f8051 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -16,17 +16,19 @@ #include #include #include +#include #include #include #include +#include +#include +#include #include #include #include #include -#include "sev-guest.h" - #define DEVICE_NAME "sev-guest" #define AAD_LEN 48 #define MSG_HDR_VER 1 @@ -55,7 +57,7 @@ struct snp_guest_dev { */ struct snp_guest_msg secret_request, secret_response; - struct snp_secrets_page_layout *layout; + struct snp_secrets_page *secrets; struct snp_req_data input; union { struct snp_report_req report; @@ -475,6 +477,11 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, return 0; } +struct snp_req_resp { + sockptr_t req_data; + sockptr_t resp_data; +}; + static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) { struct snp_guest_crypto *crypto = snp_dev->crypto; @@ -555,22 +562,25 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque return rc; } -static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg, + struct snp_req_resp *io) + { struct snp_ext_report_req *req = &snp_dev->req.ext_report; struct snp_guest_crypto *crypto = snp_dev->crypto; struct snp_report_resp *resp; int ret, npages = 0, resp_len; + sockptr_t certs_address; lockdep_assert_held(&snp_cmd_mutex); - if (!arg->req_data || !arg->resp_data) + if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data)) return -EINVAL; - if (copy_from_user(req, (void __user *)arg->req_data, sizeof(*req))) + if (copy_from_sockptr(req, io->req_data, sizeof(*req))) return -EFAULT; - /* userspace does not want certificate data */ + /* caller does not want certificate data */ if (!req->certs_len || !req->certs_address) goto cmd; @@ -578,8 +588,13 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques !IS_ALIGNED(req->certs_len, PAGE_SIZE)) return -EINVAL; - if (!access_ok((const void __user *)req->certs_address, req->certs_len)) - return -EFAULT; + if (sockptr_is_kernel(io->resp_data)) { + certs_address = KERNEL_SOCKPTR((void *)req->certs_address); + } else { + certs_address = USER_SOCKPTR((void __user *)req->certs_address); + if (!access_ok(certs_address.user, req->certs_len)) + return -EFAULT; + } /* * Initialize the intermediate buffer with all zeros. This buffer @@ -609,21 +624,19 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) { req->certs_len = snp_dev->input.data_npages << PAGE_SHIFT; - if (copy_to_user((void __user *)arg->req_data, req, sizeof(*req))) + if (copy_to_sockptr(io->req_data, req, sizeof(*req))) ret = -EFAULT; } if (ret) goto e_free; - if (npages && - copy_to_user((void __user *)req->certs_address, snp_dev->certs_data, - req->certs_len)) { + if (npages && copy_to_sockptr(certs_address, snp_dev->certs_data, req->certs_len)) { ret = -EFAULT; goto e_free; } - if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp))) + if (copy_to_sockptr(io->resp_data, resp, sizeof(*resp))) ret = -EFAULT; e_free: @@ -636,6 +649,7 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long struct snp_guest_dev *snp_dev = to_snp_dev(file); void __user *argp = (void __user *)arg; struct snp_guest_request_ioctl input; + struct snp_req_resp io; int ret = -ENOTTY; if (copy_from_user(&input, argp, sizeof(input))) @@ -664,7 +678,14 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long ret = get_derived_key(snp_dev, &input); break; case SNP_GET_EXT_REPORT: - ret = get_ext_report(snp_dev, &input); + /* + * As get_ext_report() may be called from the ioctl() path and a + * kernel internal path (configfs-tsm), decorate the passed + * buffers as user pointers. + */ + io.req_data = USER_SOCKPTR((void __user *)input.req_data); + io.resp_data = USER_SOCKPTR((void __user *)input.resp_data); + ret = get_ext_report(snp_dev, &input, &io); break; default: break; @@ -720,26 +741,26 @@ static const struct file_operations snp_guest_fops = { .unlocked_ioctl = snp_guest_ioctl, }; -static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno) +static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) { u8 *key = NULL; switch (id) { case 0: - *seqno = &layout->os_area.msg_seqno_0; - key = layout->vmpck0; + *seqno = &secrets->os_area.msg_seqno_0; + key = secrets->vmpck0; break; case 1: - *seqno = &layout->os_area.msg_seqno_1; - key = layout->vmpck1; + *seqno = &secrets->os_area.msg_seqno_1; + key = secrets->vmpck1; break; case 2: - *seqno = &layout->os_area.msg_seqno_2; - key = layout->vmpck2; + *seqno = &secrets->os_area.msg_seqno_2; + key = secrets->vmpck2; break; case 3: - *seqno = &layout->os_area.msg_seqno_3; - key = layout->vmpck3; + *seqno = &secrets->os_area.msg_seqno_3; + key = secrets->vmpck3; break; default: break; @@ -748,10 +769,134 @@ static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno return key; } +struct snp_msg_report_resp_hdr { + u32 status; + u32 report_size; + u8 rsvd[24]; +}; + +struct snp_msg_cert_entry { + guid_t guid; + u32 offset; + u32 length; +}; + +static int sev_report_new(struct tsm_report *report, void *data) +{ + struct snp_msg_cert_entry *cert_table; + struct tsm_desc *desc = &report->desc; + struct snp_guest_dev *snp_dev = data; + struct snp_msg_report_resp_hdr hdr; + const u32 report_size = SZ_4K; + const u32 ext_size = SEV_FW_BLOB_MAX_SIZE; + u32 certs_size, i, size = report_size + ext_size; + int ret; + + if (desc->inblob_len != SNP_REPORT_USER_DATA_SIZE) + return -EINVAL; + + void *buf __free(kvfree) = kvzalloc(size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + guard(mutex)(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (is_vmpck_empty(snp_dev)) { + dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n"); + return -ENOTTY; + } + + cert_table = buf + report_size; + struct snp_ext_report_req ext_req = { + .data = { .vmpl = desc->privlevel }, + .certs_address = (__u64)cert_table, + .certs_len = ext_size, + }; + memcpy(&ext_req.data.user_data, desc->inblob, desc->inblob_len); + + struct snp_guest_request_ioctl input = { + .msg_version = 1, + .req_data = (__u64)&ext_req, + .resp_data = (__u64)buf, + .exitinfo2 = 0xff, + }; + struct snp_req_resp io = { + .req_data = KERNEL_SOCKPTR(&ext_req), + .resp_data = KERNEL_SOCKPTR(buf), + }; + + ret = get_ext_report(snp_dev, &input, &io); + if (ret) + return ret; + + memcpy(&hdr, buf, sizeof(hdr)); + if (hdr.status == SEV_RET_INVALID_PARAM) + return -EINVAL; + if (hdr.status == SEV_RET_INVALID_KEY) + return -EINVAL; + if (hdr.status) + return -ENXIO; + if ((hdr.report_size + sizeof(hdr)) > report_size) + return -ENOMEM; + + void *rbuf __free(kvfree) = kvzalloc(hdr.report_size, GFP_KERNEL); + if (!rbuf) + return -ENOMEM; + + memcpy(rbuf, buf + sizeof(hdr), hdr.report_size); + report->outblob = no_free_ptr(rbuf); + report->outblob_len = hdr.report_size; + + certs_size = 0; + for (i = 0; i < ext_size / sizeof(struct snp_msg_cert_entry); i++) { + struct snp_msg_cert_entry *ent = &cert_table[i]; + + if (guid_is_null(&ent->guid) && !ent->offset && !ent->length) + break; + certs_size = max(certs_size, ent->offset + ent->length); + } + + /* Suspicious that the response populated entries without populating size */ + if (!certs_size && i) + dev_warn_ratelimited(snp_dev->dev, "certificate slots conveyed without size\n"); + + /* No certs to report */ + if (!certs_size) + return 0; + + /* Suspicious that the certificate blob size contract was violated + */ + if (certs_size > ext_size) { + dev_warn_ratelimited(snp_dev->dev, "certificate data truncated\n"); + certs_size = ext_size; + } + + void *cbuf __free(kvfree) = kvzalloc(certs_size, GFP_KERNEL); + if (!cbuf) + return -ENOMEM; + + memcpy(cbuf, cert_table, certs_size); + report->auxblob = no_free_ptr(cbuf); + report->auxblob_len = certs_size; + + return 0; +} + +static const struct tsm_ops sev_tsm_ops = { + .name = KBUILD_MODNAME, + .report_new = sev_report_new, +}; + +static void unregister_sev_tsm(void *data) +{ + tsm_unregister(&sev_tsm_ops); +} + static int __init sev_guest_probe(struct platform_device *pdev) { - struct snp_secrets_page_layout *layout; struct sev_guest_platform_data *data; + struct snp_secrets_page *secrets; struct device *dev = &pdev->dev; struct snp_guest_dev *snp_dev; struct miscdevice *misc; @@ -769,7 +914,7 @@ static int __init sev_guest_probe(struct platform_device *pdev) if (!mapping) return -ENODEV; - layout = (__force void *)mapping; + secrets = (__force void *)mapping; ret = -ENOMEM; snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); @@ -777,7 +922,7 @@ static int __init sev_guest_probe(struct platform_device *pdev) goto e_unmap; ret = -EINVAL; - snp_dev->vmpck = get_vmpck(vmpck_id, layout, &snp_dev->os_area_msg_seqno); + snp_dev->vmpck = get_vmpck(vmpck_id, secrets, &snp_dev->os_area_msg_seqno); if (!snp_dev->vmpck) { dev_err(dev, "invalid vmpck id %d\n", vmpck_id); goto e_unmap; @@ -791,7 +936,7 @@ static int __init sev_guest_probe(struct platform_device *pdev) platform_set_drvdata(pdev, snp_dev); snp_dev->dev = dev; - snp_dev->layout = layout; + snp_dev->secrets = secrets; /* Allocate the shared page used for the request and response message. */ snp_dev->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); @@ -821,6 +966,14 @@ static int __init sev_guest_probe(struct platform_device *pdev) snp_dev->input.resp_gpa = __pa(snp_dev->response); snp_dev->input.data_gpa = __pa(snp_dev->certs_data); + ret = tsm_register(&sev_tsm_ops, snp_dev, &tsm_report_extra_type); + if (ret) + goto e_free_cert_data; + + ret = devm_add_action_or_reset(&pdev->dev, unregister_sev_tsm, NULL); + if (ret) + goto e_free_cert_data; + ret = misc_register(misc); if (ret) goto e_free_cert_data; diff --git a/drivers/virt/coco/sev-guest/sev-guest.h b/drivers/virt/coco/sev-guest/sev-guest.h deleted file mode 100644 index 21bda26fdb953e88115a06e463ebe375f23427d0..0000000000000000000000000000000000000000 --- a/drivers/virt/coco/sev-guest/sev-guest.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2021 Advanced Micro Devices, Inc. - * - * Author: Brijesh Singh - * - * SEV-SNP API spec is available at https://developer.amd.com/sev - */ - -#ifndef __VIRT_SEVGUEST_H__ -#define __VIRT_SEVGUEST_H__ - -#include - -#define MAX_AUTHTAG_LEN 32 - -/* See SNP spec SNP_GUEST_REQUEST section for the structure */ -enum msg_type { - SNP_MSG_TYPE_INVALID = 0, - SNP_MSG_CPUID_REQ, - SNP_MSG_CPUID_RSP, - SNP_MSG_KEY_REQ, - SNP_MSG_KEY_RSP, - SNP_MSG_REPORT_REQ, - SNP_MSG_REPORT_RSP, - SNP_MSG_EXPORT_REQ, - SNP_MSG_EXPORT_RSP, - SNP_MSG_IMPORT_REQ, - SNP_MSG_IMPORT_RSP, - SNP_MSG_ABSORB_REQ, - SNP_MSG_ABSORB_RSP, - SNP_MSG_VMRK_REQ, - SNP_MSG_VMRK_RSP, - - SNP_MSG_TYPE_MAX -}; - -enum aead_algo { - SNP_AEAD_INVALID, - SNP_AEAD_AES_256_GCM, -}; - -struct snp_guest_msg_hdr { - u8 authtag[MAX_AUTHTAG_LEN]; - u64 msg_seqno; - u8 rsvd1[8]; - u8 algo; - u8 hdr_version; - u16 hdr_sz; - u8 msg_type; - u8 msg_version; - u16 msg_sz; - u32 rsvd2; - u8 msg_vmpck; - u8 rsvd3[35]; -} __packed; - -struct snp_guest_msg { - struct snp_guest_msg_hdr hdr; - u8 payload[4000]; -} __packed; - -#endif /* __VIRT_SEVGUEST_H__ */ diff --git a/fs/aio.c b/fs/aio.c index c3614193d749349f281ecca7e37667a80f126f20..ab28da0c85e5f2534548235c2cf28748f79c321f 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -266,7 +266,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) return ERR_CAST(inode); inode->i_mapping->a_ops = &aio_ctx_aops; - inode->i_mapping->private_data = ctx; + inode->i_mapping->i_private_data = ctx; inode->i_size = PAGE_SIZE * nr_pages; file = alloc_file_pseudo(inode, aio_mnt, "[aio]", @@ -316,10 +316,10 @@ static void put_aio_ring_file(struct kioctx *ctx) /* Prevent further access to the kioctx from migratepages */ i_mapping = aio_ring_file->f_mapping; - spin_lock(&i_mapping->private_lock); - i_mapping->private_data = NULL; + spin_lock(&i_mapping->i_private_lock); + i_mapping->i_private_data = NULL; ctx->aio_ring_file = NULL; - spin_unlock(&i_mapping->private_lock); + spin_unlock(&i_mapping->i_private_lock); fput(aio_ring_file); } @@ -422,9 +422,9 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, rc = 0; - /* mapping->private_lock here protects against the kioctx teardown. */ - spin_lock(&mapping->private_lock); - ctx = mapping->private_data; + /* mapping->i_private_lock here protects against the kioctx teardown. */ + spin_lock(&mapping->i_private_lock); + ctx = mapping->i_private_data; if (!ctx) { rc = -EINVAL; goto out; @@ -476,7 +476,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, out_unlock: mutex_unlock(&ctx->ring_lock); out: - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return rc; } #else diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 24192a7667edf766e6932e12459c93379875e7e5..8dd436ee985b3b03b31c995ff3e0dd8fc3241369 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -79,7 +79,7 @@ static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, - bool secure) + bool make_inode) { struct inode *inode; struct file *file; @@ -87,7 +87,7 @@ static struct file *__anon_inode_getfile(const char *name, if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); - if (secure) { + if (make_inode) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); @@ -149,13 +149,10 @@ struct file *anon_inode_getfile(const char *name, EXPORT_SYMBOL_GPL(anon_inode_getfile); /** - * anon_inode_getfile_secure - Like anon_inode_getfile(), but creates a new + * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the - * inode_init_security_anon() LSM hook. This - * allows for both the inode to have its own - * security context and for the LSM to enforce - * policy on the inode's creation. + * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file @@ -164,11 +161,21 @@ EXPORT_SYMBOL_GPL(anon_inode_getfile); * @context_inode: * [in] the logical relationship with the new inode (optional) * + * Create a new anonymous inode and file pair. This can be done for two + * reasons: + * + * - for the inode to have its own security context, so that LSMs can enforce + * policy on the inode's creation; + * + * - if the caller needs a unique inode, for example in order to customize + * the size returned by fstat() + * * The LSM may use @context_inode in inode_init_security_anon(), but a - * reference to it is not held. Returns the newly created file* or an error - * pointer. See the anon_inode_getfile() documentation for more information. + * reference to it is not held. + * + * Returns the newly created file* or an error pointer. */ -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) @@ -176,12 +183,13 @@ struct file *anon_inode_getfile_secure(const char *name, return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } +EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, - bool secure) + bool make_inode) { int error, fd; struct file *file; @@ -192,7 +200,7 @@ static int __anon_inode_getfd(const char *name, fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, - secure); + make_inode); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; @@ -231,10 +239,9 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops, EXPORT_SYMBOL_GPL(anon_inode_getfd); /** - * anon_inode_getfd_secure - Like anon_inode_getfd(), but creates a new + * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls - * the inode_init_security_anon() LSM hook. This allows the inode to have its - * own security context and for a LSM to reject creation of the inode. + * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file @@ -243,16 +250,26 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd); * @context_inode: * [in] the logical relationship with the new inode (optional) * + * Create a new anonymous inode and file pair. This can be done for two + * reasons: + * + * - for the inode to have its own security context, so that LSMs can enforce + * policy on the inode's creation; + * + * - if the caller needs a unique inode, for example in order to customize + * the size returned by fstat() + * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. + * + * Returns a newly created file descriptor or an error code. */ -int anon_inode_getfd_secure(const char *name, const struct file_operations *fops, +int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } -EXPORT_SYMBOL_GPL(anon_inode_getfd_secure); static int __init anon_inode_init(void) { diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a8de5b5df86fd40465b4027c14c4f0e20d4c5d8c..95e1af0003f4ab1cca57e1731ff98f5537c76749 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -866,7 +866,7 @@ static int attach_extent_buffer_page(struct extent_buffer *eb, * will not race with any other ebs. */ if (page->mapping) - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); if (fs_info->nodesize >= PAGE_SIZE) { if (!PagePrivate(page)) @@ -1732,16 +1732,16 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) * Take private lock to ensure the subpage won't be detached * in the meantime. */ - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) { - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); break; } spin_lock_irqsave(&subpage->lock, flags); if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset, subpage->bitmaps)) { spin_unlock_irqrestore(&subpage->lock, flags); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); bit_start++; continue; } @@ -1755,7 +1755,7 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) */ eb = find_extent_buffer_nolock(fs_info, start); spin_unlock_irqrestore(&subpage->lock, flags); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); /* * The eb has already reached 0 refs thus find_extent_buffer() @@ -1807,9 +1807,9 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx) if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) return submit_eb_subpage(page, wbc); - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (!PagePrivate(page)) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return 0; } @@ -1820,16 +1820,16 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx) * crashing the machine for something we can survive anyway. */ if (WARN_ON(!eb)) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return 0; } if (eb == ctx->eb) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return 0; } ret = atomic_inc_not_zero(&eb->refs); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); if (!ret) return 0; @@ -3262,7 +3262,7 @@ static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page) { struct btrfs_subpage *subpage; - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); if (PagePrivate(page)) { subpage = (struct btrfs_subpage *)page->private; @@ -3285,14 +3285,14 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag /* * For mapped eb, we're going to change the page private, which should - * be done under the private_lock. + * be done under the i_private_lock. */ if (mapped) - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) { if (mapped) - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return; } @@ -3316,7 +3316,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag detach_page_private(page); } if (mapped) - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return; } @@ -3339,7 +3339,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag if (!page_range_has_eb(fs_info, page)) btrfs_detach_subpage(fs_info, page); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); } /* Release all pages attached to the extent buffer */ @@ -3714,7 +3714,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, /* * Preallocate page->private for subpage case, so that we won't - * allocate memory with private_lock nor page lock hold. + * allocate memory with i_private_lock nor page lock hold. * * The memory will be freed by attach_extent_buffer_page() or freed * manually if we exit earlier. @@ -3735,10 +3735,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, goto free_eb; } - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); exists = grab_extent_buffer(fs_info, p); if (exists) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); unlock_page(p); put_page(p); mark_extent_buffer_accessed(exists, p); @@ -3758,7 +3758,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, * Thus needs no special handling in error path. */ btrfs_page_inc_eb_refs(fs_info, p); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len)); eb->pages[i] = p; @@ -4776,12 +4776,12 @@ static int try_release_subpage_extent_buffer(struct page *page) * Finally to check if we have cleared page private, as if we have * released all ebs in the page, the page private should be cleared now. */ - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) ret = 1; else ret = 0; - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return ret; } @@ -4797,9 +4797,9 @@ int try_release_extent_buffer(struct page *page) * We need to make sure nobody is changing page->private, as we rely on * page->private as the pointer to extent buffer. */ - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) { - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return 1; } @@ -4814,10 +4814,10 @@ int try_release_extent_buffer(struct page *page) spin_lock(&eb->refs_lock); if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return 0; } - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); /* * If tree ref isn't set then we know the ref on this eb is a real ref, diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index b98d42ca55647f0aa3e5668bca9bc7723bc4d608..4fe2f14f5de6bf9ad1ffd8e485792a7b4fa91a6f 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -200,7 +200,7 @@ void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, return; ASSERT(PagePrivate(page) && page->mapping); - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); subpage = (struct btrfs_subpage *)page->private; atomic_inc(&subpage->eb_refs); @@ -215,7 +215,7 @@ void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, return; ASSERT(PagePrivate(page) && page->mapping); - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); subpage = (struct btrfs_subpage *)page->private; ASSERT(atomic_read(&subpage->eb_refs)); diff --git a/fs/buffer.c b/fs/buffer.c index 4b86e971efd8a18c01e4a202931cdb47c11c1daf..10c175c387e5b930698e195e8a7788df7e43ba07 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -180,11 +180,11 @@ EXPORT_SYMBOL(end_buffer_write_sync); * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's - * private_lock. + * i_private_lock. * - * Hack idea: for the blockdev mapping, private_lock contention + * Hack idea: for the blockdev mapping, i_private_lock contention * may be quite high. This code could TryLock the page, and if that - * succeeds, there is no need to take private_lock. + * succeeds, there is no need to take i_private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) @@ -204,7 +204,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) if (IS_ERR(folio)) goto out; - spin_lock(&bd_mapping->private_lock); + spin_lock(&bd_mapping->i_private_lock); head = folio_buffers(folio); if (!head) goto out_unlock; @@ -236,7 +236,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) 1 << bd_inode->i_blkbits); } out_unlock: - spin_unlock(&bd_mapping->private_lock); + spin_unlock(&bd_mapping->i_private_lock); folio_put(folio); out: return ret; @@ -473,25 +473,25 @@ EXPORT_SYMBOL(mark_buffer_async_write); * * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the - * management of a list of dependent buffers at ->i_mapping->private_list. + * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. - * So the locking for private_list is via the private_lock in the address_space + * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, - * mapping->private_lock does *not* protect mapping->private_list! In fact, - * mapping->private_list will always be protected by the backing blockdev's - * ->private_lock. + * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, + * mapping->i_private_list will always be protected by the backing blockdev's + * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's - * ->private_list must be from the same address_space: the blockdev's. + * ->i_private_list must be from the same address_space: the blockdev's. * - * address_spaces which do not place buffers at ->private_list via these - * utility functions are free to use private_lock and private_list for - * whatever they want. The only requirement is that list_empty(private_list) + * address_spaces which do not place buffers at ->i_private_list via these + * utility functions are free to use i_private_lock and i_private_list for + * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The @@ -514,7 +514,7 @@ EXPORT_SYMBOL(mark_buffer_async_write); */ /* - * The buffer's backing address_space's private_lock must be held + * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { @@ -525,7 +525,7 @@ static void __remove_assoc_queue(struct buffer_head *bh) int inode_has_buffers(struct inode *inode) { - return !list_empty(&inode->i_data.private_list); + return !list_empty(&inode->i_data.i_private_list); } /* @@ -567,7 +567,7 @@ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * - * Starts I/O against the buffers at mapping->private_list, and waits upon + * Starts I/O against the buffers at mapping->i_private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). @@ -576,13 +576,13 @@ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) */ int sync_mapping_buffers(struct address_space *mapping) { - struct address_space *buffer_mapping = mapping->private_data; + struct address_space *buffer_mapping = mapping->i_private_data; - if (buffer_mapping == NULL || list_empty(&mapping->private_list)) + if (buffer_mapping == NULL || list_empty(&mapping->i_private_list)) return 0; - return fsync_buffers_list(&buffer_mapping->private_lock, - &mapping->private_list); + return fsync_buffers_list(&buffer_mapping->i_private_lock, + &mapping->i_private_list); } EXPORT_SYMBOL(sync_mapping_buffers); @@ -679,17 +679,17 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); - if (!mapping->private_data) { - mapping->private_data = buffer_mapping; + if (!mapping->i_private_data) { + mapping->i_private_data = buffer_mapping; } else { - BUG_ON(mapping->private_data != buffer_mapping); + BUG_ON(mapping->i_private_data != buffer_mapping); } if (!bh->b_assoc_map) { - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); list_move_tail(&bh->b_assoc_buffers, - &mapping->private_list); + &mapping->i_private_list); bh->b_assoc_map = mapping; - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); @@ -712,7 +712,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean * page on the dirty page list. * - * We use private_lock to lock against try_to_free_buffers while using the + * We use i_private_lock to lock against try_to_free_buffers while using the * page's buffer list. Also use this to protect against clean buffers being * added to the page after it was set dirty. * @@ -724,7 +724,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) struct buffer_head *head; bool newly_dirty; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; @@ -740,7 +740,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) */ folio_memcg_lock(folio); newly_dirty = !folio_test_set_dirty(folio); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); @@ -833,7 +833,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, - &mapping->private_list); + &mapping->i_private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); @@ -857,7 +857,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * - * NOTE: we take the inode's blockdev's mapping's private_lock. Which + * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ @@ -865,13 +865,13 @@ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; - struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->private_data; + struct list_head *list = &mapping->i_private_list; + struct address_space *buffer_mapping = mapping->i_private_data; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); @@ -888,10 +888,10 @@ int remove_inode_buffers(struct inode *inode) if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; - struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->private_data; + struct list_head *list = &mapping->i_private_list; + struct address_space *buffer_mapping = mapping->i_private_data; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { @@ -900,7 +900,7 @@ int remove_inode_buffers(struct inode *inode) } __remove_assoc_queue(bh); } - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } return ret; } @@ -1076,11 +1076,11 @@ grow_dev_page(struct block_device *bdev, sector_t block, * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ - spin_lock(&inode->i_mapping->private_lock); + spin_lock(&inode->i_mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, (sector_t)index << sizebits, size); - spin_unlock(&inode->i_mapping->private_lock); + spin_unlock(&inode->i_mapping->i_private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; failed: @@ -1180,7 +1180,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, * and then attach the address_space's inode to its superblock's dirty * inode list. * - * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->private_lock, + * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) @@ -1258,10 +1258,10 @@ void __bforget(struct buffer_head *bh) if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_folio->mapping; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } __brelse(bh); } @@ -1637,7 +1637,7 @@ EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt - * block_dirty_folio() via private_lock. try_to_free_buffers + * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *folio_create_empty_buffers(struct folio *folio, @@ -1654,7 +1654,7 @@ struct buffer_head *folio_create_empty_buffers(struct folio *folio, } while (bh); tail->b_this_page = head; - spin_lock(&folio->mapping->private_lock); + spin_lock(&folio->mapping->i_private_lock); if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { @@ -1666,7 +1666,7 @@ struct buffer_head *folio_create_empty_buffers(struct folio *folio, } while (bh != head); } folio_attach_private(folio, head); - spin_unlock(&folio->mapping->private_lock); + spin_unlock(&folio->mapping->i_private_lock); return head; } @@ -1720,7 +1720,7 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) if (!folio_buffers(folio)) continue; /* - * We use folio lock instead of bd_mapping->private_lock + * We use folio lock instead of bd_mapping->i_private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ @@ -2892,7 +2892,7 @@ EXPORT_SYMBOL(sync_dirty_buffer); * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either - * locking the folio or by holding its mapping's private_lock. + * locking the folio or by holding its mapping's i_private_lock. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio @@ -2903,7 +2903,7 @@ EXPORT_SYMBOL(sync_dirty_buffer); * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with - * private_lock. + * i_private_lock. * * try_to_free_buffers() is non-blocking. */ @@ -2955,7 +2955,7 @@ bool try_to_free_buffers(struct folio *folio) goto out; } - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); ret = drop_buffers(folio, &buffers_to_free); /* @@ -2968,13 +2968,13 @@ bool try_to_free_buffers(struct folio *folio) * the folio's buffers clean. We discover that here and clean * the folio also. * - * private_lock must be held over this entire operation in order + * i_private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) folio_cancel_dirty(folio); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 045a7213d6b61bd58d4f4c9fd4cae07a2f8e0f5f..b020c59ae858ca20227bd5e494ed32d447771b6c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1307,7 +1307,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode, * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). * - * ext4 never places buffers on inode->i_mapping->private_list. metadata + * ext4 never places buffers on inode->i_mapping->i_private_list. metadata * buffers are managed internally. */ static int ext4_write_end(struct file *file, @@ -3304,7 +3304,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) } /* Any metadata buffers to write? */ - if (!list_empty(&inode->i_mapping->private_list)) + if (!list_empty(&inode->i_mapping->i_private_list)) return true; return inode->i_state & I_DIRTY_DATASYNC; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 4f8f2b148652001737ac7ce5aed26cde9b0182d3..1f4acdd24f6f9598c466aff8055788e1b3e1fa13 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1254,7 +1254,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, mapping->host = s->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index f4c066aa24b963cca1760ccb476a7b065c033627..5ac6d3c6c20499da424a8aa0f989b28e50018bf2 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -117,7 +117,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping->host = sb->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; spin_lock_init(&sdp->sd_log_lock); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index fb0d3db162c20fba4dbc4b955cfaa086f6379b7a..4a0a5beac8c72d4cf44ff4aa03d98960003587ed 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -721,7 +721,7 @@ static void hugetlbfs_evict_inode(struct inode *inode) * at inode creation time. If this is a device special inode, * i_mapping may not point to the original address space. */ - resv_map = (struct resv_map *)(&inode->i_data)->private_data; + resv_map = (struct resv_map *)(&inode->i_data)->i_private_data; /* Only regular and link inodes have associated reserve maps */ if (resv_map) resv_map_release(&resv_map->refs); @@ -993,7 +993,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, inode->i_mode = S_IFDIR | ctx->mode; inode->i_uid = ctx->uid; inode->i_gid = ctx->gid; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ @@ -1037,8 +1037,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); - inode->i_mapping->private_data = resv_map; + simple_inode_init_ts(inode); + inode->i_mapping->i_private_data = resv_map; info->seals = F_SEAL_SEAL; switch (mode & S_IFMT) { default: @@ -1080,7 +1080,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev); if (!inode) return -ENOSPC; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_instantiate(dentry, inode); dget(dentry);/* Extra count - pin the dentry in core */ return 0; @@ -1112,7 +1112,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0); if (!inode) return -ENOSPC; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_tmpfile(file, inode); return finish_open_simple(file, 0); } @@ -1134,7 +1134,7 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap, } else iput(inode); } - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return error; } diff --git a/fs/inode.c b/fs/inode.c index ad7445342ee9f7dd26bae2cd68c5b9c56fef87d4..5d5efeadb8c1ee3105926b829a937620974b667c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -209,7 +209,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, @@ -398,8 +398,8 @@ static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); - INIT_LIST_HEAD(&mapping->private_list); - spin_lock_init(&mapping->private_lock); + INIT_LIST_HEAD(&mapping->i_private_list); + spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } @@ -658,7 +658,7 @@ void clear_inode(struct inode *inode) * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); - BUG_ON(!list_empty(&inode->i_data.private_list)); + BUG_ON(!list_empty(&inode->i_data.i_private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6bc36cef14cdb6ba2b42690221b7bf8a38fd879b..cf1ce670dddfc8dc29d9964405f1ab2f78735aa6 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -192,13 +192,13 @@ static struct nfs_page *nfs_folio_find_private_request(struct folio *folio) if (!folio_test_private(folio)) return NULL; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); req = nfs_folio_private_request(folio); if (req) { WARN_ON_ONCE(req->wb_head != req); kref_get(&req->wb_kref); } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return req; } @@ -769,13 +769,13 @@ static void nfs_inode_add_request(struct nfs_page *req) * Swap-space should not get truncated. Hence no need to plug the race * with invalidate/truncate. */ - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (likely(!folio_test_swapcache(folio))) { set_bit(PG_MAPPED, &req->wb_flags); folio_set_private(folio); folio->private = req; } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); atomic_long_inc(&nfsi->nrequests); /* this a head request for a page group - mark it as having an * extra reference so sub groups can follow suit. @@ -796,13 +796,13 @@ static void nfs_inode_remove_request(struct nfs_page *req) struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio_file_mapping(folio); - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (likely(folio && !folio_test_swapcache(folio))) { folio->private = NULL; folio_clear_private(folio); clear_bit(PG_MAPPED, &req->wb_head->wb_flags); } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 5f2d73f36e0d2f74682d6d91d44386aa4fe54f6e..00c85a14d049dfc35c396a5b4e42d59ff9809be3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -214,7 +214,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping, /* * The page may not be locked, eg if called from try_to_unmap_one() */ - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; @@ -230,7 +230,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping, } else if (ret) { nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits); } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 4e158bce419295d84b3d71a64d2c9a3df4949314..2695e7e51b78e886a53418169dfdb1d92f0d3358 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -1707,7 +1707,7 @@ const struct address_space_operations ntfs_mst_aops = { * * If the page does not have buffers, we create them and set them uptodate. * The page may not be locked which is why we need to handle the buffers under - * the mapping->private_lock. Once the buffers are marked dirty we no longer + * the mapping->i_private_lock. Once the buffers are marked dirty we no longer * need the lock since try_to_free_buffers() does not free dirty buffers. */ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { @@ -1719,11 +1719,11 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { BUG_ON(!PageUptodate(page)); end = ofs + ni->itype.index.block_size; bh_size = VFS_I(ni)->i_sb->s_blocksize; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (unlikely(!page_has_buffers(page))) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); bh = head = alloc_page_buffers(page, bh_size, true); - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (likely(!page_has_buffers(page))) { struct buffer_head *tail; @@ -1747,7 +1747,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { break; set_buffer_dirty(bh); } while ((bh = bh->b_this_page) != head); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); filemap_dirty_folio(mapping, page_folio(page)); if (unlikely(buffers_to_free)) { do { diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d616b7777eef8ccaef7c8761c3473b1077488262..eb46803cd512a5c128fd4f54f3c49d87b8863586 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1083,7 +1083,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new, { int fd; - fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new, + fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; @@ -2280,7 +2280,8 @@ static int new_userfaultfd(int flags) /* prevent the mm struct to be freed */ mmgrab(ctx->mm); - fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx, + /* Create a new inode so that the LSM can block the creation. */ + fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (fd < 0) { mmdrop(ctx->mm); diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 99a5201d9e625796f762b35beb32b1b523497019..9787442f0e9dc31ac312b40062eb5f5b197cb9af 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -31,7 +31,7 @@ struct amd_iommu_pi_data { struct task_struct; struct pci_dev; -extern int amd_iommu_detect(void); +extern void amd_iommu_detect(void); /** * amd_iommu_init_device() - Init device for use with IOMMUv2 driver @@ -155,7 +155,7 @@ extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev, amd_iommu_invalidate_ctx cb); #else /* CONFIG_AMD_IOMMU */ -static inline int amd_iommu_detect(void) { return -ENODEV; } +static inline void amd_iommu_detect(void) { } #endif /* CONFIG_AMD_IOMMU */ @@ -205,8 +205,10 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value); struct amd_iommu *get_amd_iommu(unsigned int idx); -#ifdef CONFIG_AMD_MEM_ENCRYPT -int amd_iommu_snp_enable(void); +#ifdef CONFIG_KVM_AMD_SEV +int amd_iommu_snp_disable(void); +#else +static inline int amd_iommu_snp_disable(void) { return 0; } #endif #endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 5deaddbd79278fb9954833da36a3c5444d4c6ead..93a5f16d03f3f38612d37f0bcef56e6948912413 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/cc_platform.h b/include/linux/cc_platform.h index cb0d6cd1c12f24e1dd8681b5f9f0302675bec7d5..60693a1458946223f791aae517210cb67ba13050 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -90,6 +90,14 @@ enum cc_attr { * Examples include TDX Guest. */ CC_ATTR_HOTPLUG_DISABLED, + + /** + * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. + * + * The host kernel is running with the necessary features + * enabled to run SEV-SNP guests. + */ + CC_ATTR_HOST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM @@ -107,10 +115,14 @@ enum cc_attr { * * FALSE - Specified Confidential Computing attribute is not active */ bool cc_platform_has(enum cc_attr attr); +void cc_platform_set(enum cc_attr attr); +void cc_platform_clear(enum cc_attr attr); #else /* !CONFIG_ARCH_HAS_CC_PLATFORM */ static inline bool cc_platform_has(enum cc_attr attr) { return false; } +static inline void cc_platform_set(enum cc_attr attr) { } +static inline void cc_platform_clear(enum cc_attr attr) { } #endif /* CONFIG_ARCH_HAS_CC_PLATFORM */ diff --git a/include/linux/fs.h b/include/linux/fs.h index b6ccdceb4f94519da99068fa3a71628275952e69..d0f68f78bce60c270db6512ee53945a0cf70313f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -489,9 +489,9 @@ extern const struct address_space_operations empty_aops; * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. - * @private_lock: For use by the owner of the address_space. - * @private_list: For use by the owner of the address_space. - * @private_data: For use by the owner of the address_space. + * @i_private_lock: For use by the owner of the address_space. + * @i_private_list: For use by the owner of the address_space. + * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; @@ -509,10 +509,7 @@ struct address_space { const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; - spinlock_t private_lock; - struct list_head private_list; struct rw_semaphore i_mmap_rwsem; - void *private_data; KABI_RESERVE(1) KABI_RESERVE(2) @@ -521,6 +518,9 @@ struct address_space { KABI_RESERVE(5) KABI_RESERVE(6) KABI_RESERVE(7) + spinlock_t i_private_lock; + struct list_head i_private_list; + void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fa0542624f42866495ff32d37ca4ae8d192e4baa..2a00169edac647b2adada6d0ce7083255a02100e 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 /* @@ -254,9 +254,15 @@ 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; +}; + +enum kvm_gfn_range_filter { + KVM_FILTER_SHARED = BIT(0), + KVM_FILTER_PRIVATE = BIT(1), }; struct kvm_gfn_range { @@ -264,6 +270,7 @@ struct kvm_gfn_range { gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; + enum kvm_gfn_range_filter attr_filter; bool may_block; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); @@ -611,8 +618,20 @@ 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; @@ -711,13 +730,36 @@ 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 + +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; @@ -773,9 +815,9 @@ 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 @@ -835,12 +877,12 @@ struct kvm { 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; @@ -858,6 +900,10 @@ 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]; #ifdef CONFIG_ARM64_HDBSS @@ -1075,7 +1121,7 @@ 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)); @@ -1232,9 +1278,9 @@ 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, @@ -1461,7 +1507,16 @@ bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); -void kvm_vcpu_kick(struct kvm_vcpu *vcpu); + +#ifndef CONFIG_S390 +void __kvm_vcpu_kick(struct kvm_vcpu *vcpu, bool wait); + +static inline void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +{ + __kvm_vcpu_kick(vcpu, false); +} +#endif + int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); @@ -1478,10 +1533,10 @@ 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); @@ -2096,7 +2151,7 @@ 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)) @@ -2119,9 +2174,9 @@ 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); /* @@ -2130,10 +2185,20 @@ 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; @@ -2240,6 +2305,14 @@ static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) __kvm_make_request(req, vcpu); } +#ifndef CONFIG_S390 +static inline void kvm_make_request_and_kick(int req, struct kvm_vcpu *vcpu) +{ + kvm_make_request(req, vcpu); + __kvm_vcpu_kick(vcpu, req & KVM_REQUEST_WAIT); +} +#endif + static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); @@ -2472,4 +2545,99 @@ 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 mask, 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 */ + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +/** + * kvm_gmem_populate() - Populate/prepare a GPA range with guest data + * + * @kvm: KVM instance + * @gfn: starting GFN to be populated + * @src: userspace-provided buffer containing data to copy into GFN range + * (passed to @post_populate, and incremented on each iteration + * if not NULL) + * @npages: number of pages to copy from userspace-buffer + * @post_populate: callback to issue for each gmem page that backs the GPA + * range + * @opaque: opaque data to pass to @post_populate callback + * + * This is primarily intended for cases where a gmem-backed GPA range needs + * to be initialized with userspace-provided data prior to being mapped into + * the guest as a private page. This should be called with the slots->lock + * held so that caller-enforced invariants regarding the expected memory + * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. + * + * Returns the number of pages that were populated. + */ +typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + void __user *src, int order, void *opaque); + +long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque); +#endif + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + #endif diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 6f4737d5046a41181401c1be7a663f0d7eb76a95..9d1f7835d8c13917ad171297752e072c04bec1b3 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 62471227394703272275126bc07dceb35008274d..991ebed90aa15dd553a88075143ccad2467a6166 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -316,6 +316,22 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping) clear_bit(AS_STABLE_WRITES, &mapping->flags); } +static inline void mapping_set_inaccessible(struct address_space *mapping) +{ + /* + * It's expected inaccessible 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_INACCESSIBLE, &mapping->flags); +} + +static inline bool mapping_inaccessible(struct address_space *mapping) +{ + return test_bit(AS_INACCESSIBLE, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index a2a4e975fb0cbc437620cec29b8c10777c569cf2..c5be91a544b5dde9f3746423e3172e76cee28f3e 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -79,6 +79,36 @@ enum sev_cmd { SEV_CMD_DBG_DECRYPT = 0x060, SEV_CMD_DBG_ENCRYPT = 0x061, + /* SNP specific commands */ + SEV_CMD_SNP_INIT = 0x081, + SEV_CMD_SNP_SHUTDOWN = 0x082, + SEV_CMD_SNP_PLATFORM_STATUS = 0x083, + SEV_CMD_SNP_DF_FLUSH = 0x084, + SEV_CMD_SNP_INIT_EX = 0x085, + SEV_CMD_SNP_SHUTDOWN_EX = 0x086, + SEV_CMD_SNP_DECOMMISSION = 0x090, + SEV_CMD_SNP_ACTIVATE = 0x091, + SEV_CMD_SNP_GUEST_STATUS = 0x092, + SEV_CMD_SNP_GCTX_CREATE = 0x093, + SEV_CMD_SNP_GUEST_REQUEST = 0x094, + SEV_CMD_SNP_ACTIVATE_EX = 0x095, + SEV_CMD_SNP_LAUNCH_START = 0x0A0, + SEV_CMD_SNP_LAUNCH_UPDATE = 0x0A1, + SEV_CMD_SNP_LAUNCH_FINISH = 0x0A2, + SEV_CMD_SNP_DBG_DECRYPT = 0x0B0, + SEV_CMD_SNP_DBG_ENCRYPT = 0x0B1, + SEV_CMD_SNP_PAGE_SWAP_OUT = 0x0C0, + SEV_CMD_SNP_PAGE_SWAP_IN = 0x0C1, + SEV_CMD_SNP_PAGE_MOVE = 0x0C2, + SEV_CMD_SNP_PAGE_MD_INIT = 0x0C3, + SEV_CMD_SNP_PAGE_SET_STATE = 0x0C6, + SEV_CMD_SNP_PAGE_RECLAIM = 0x0C7, + SEV_CMD_SNP_PAGE_UNSMASH = 0x0C8, + SEV_CMD_SNP_CONFIG = 0x0C9, + SEV_CMD_SNP_DOWNLOAD_FIRMWARE_EX = 0x0CA, + SEV_CMD_SNP_COMMIT = 0x0CB, + SEV_CMD_SNP_VLEK_LOAD = 0x0CD, + SEV_CMD_MAX, }; @@ -525,12 +555,273 @@ struct sev_data_attestation_report { u32 len; /* In/Out */ } __packed; +/** + * struct sev_data_snp_download_firmware - SNP_DOWNLOAD_FIRMWARE command params + * + * @address: physical address of firmware image + * @len: length of the firmware image + */ +struct sev_data_snp_download_firmware { + u64 address; /* In */ + u32 len; /* In */ +} __packed; + +/** + * struct sev_data_snp_activate - SNP_ACTIVATE command params + * + * @gctx_paddr: system physical address guest context page + * @asid: ASID to bind to the guest + */ +struct sev_data_snp_activate { + u64 gctx_paddr; /* In */ + u32 asid; /* In */ +} __packed; + +/** + * struct sev_data_snp_addr - generic SNP command params + * + * @address: physical address of generic data param + */ +struct sev_data_snp_addr { + u64 address; /* In/Out */ +} __packed; + +/** + * struct sev_data_snp_launch_start - SNP_LAUNCH_START command params + * + * @gctx_paddr: system physical address of guest context page + * @policy: guest policy + * @ma_gctx_paddr: system physical address of migration agent + * @ma_en: the guest is associated with a migration agent + * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the + * purpose of guest-assisted migration. + * @rsvd: reserved + * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest + * @gosvw: guest OS-visible workarounds, as defined by hypervisor + */ +struct sev_data_snp_launch_start { + u64 gctx_paddr; /* In */ + u64 policy; /* In */ + u64 ma_gctx_paddr; /* In */ + u32 ma_en:1; /* In */ + u32 imi_en:1; /* In */ + u32 rsvd:30; + u32 desired_tsc_khz; /* In */ + u8 gosvw[16]; /* In */ +} __packed; + +/* SNP support page type */ +enum { + SNP_PAGE_TYPE_NORMAL = 0x1, + SNP_PAGE_TYPE_VMSA = 0x2, + SNP_PAGE_TYPE_ZERO = 0x3, + SNP_PAGE_TYPE_UNMEASURED = 0x4, + SNP_PAGE_TYPE_SECRET = 0x5, + SNP_PAGE_TYPE_CPUID = 0x6, + + SNP_PAGE_TYPE_MAX +}; + +/** + * struct sev_data_snp_launch_update - SNP_LAUNCH_UPDATE command params + * + * @gctx_paddr: system physical address of guest context page + * @page_size: page size 0 indicates 4K and 1 indicates 2MB page + * @page_type: encoded page type + * @imi_page: indicates that this page is part of the IMI (Incoming Migration + * Image) of the guest + * @rsvd: reserved + * @rsvd2: reserved + * @address: system physical address of destination page to encrypt + * @rsvd3: reserved + * @vmpl1_perms: VMPL permission mask for VMPL1 + * @vmpl2_perms: VMPL permission mask for VMPL2 + * @vmpl3_perms: VMPL permission mask for VMPL3 + * @rsvd4: reserved + */ +struct sev_data_snp_launch_update { + u64 gctx_paddr; /* In */ + u32 page_size:1; /* In */ + u32 page_type:3; /* In */ + u32 imi_page:1; /* In */ + u32 rsvd:27; + u32 rsvd2; + u64 address; /* In */ + u32 rsvd3:8; + u32 vmpl1_perms:8; /* In */ + u32 vmpl2_perms:8; /* In */ + u32 vmpl3_perms:8; /* In */ + u32 rsvd4; +} __packed; + +/** + * struct sev_data_snp_launch_finish - SNP_LAUNCH_FINISH command params + * + * @gctx_paddr: system physical address of guest context page + * @id_block_paddr: system physical address of ID block + * @id_auth_paddr: system physical address of ID block authentication structure + * @id_block_en: indicates whether ID block is present + * @auth_key_en: indicates whether author key is present in authentication structure + * @vcek_disabled: indicates whether use of VCEK is allowed for attestation reports + * @rsvd: reserved + * @host_data: host-supplied data for guest, not interpreted by firmware + */ +struct sev_data_snp_launch_finish { + u64 gctx_paddr; + u64 id_block_paddr; + u64 id_auth_paddr; + u8 id_block_en:1; + u8 auth_key_en:1; + u8 vcek_disabled:1; + u64 rsvd:61; + u8 host_data[32]; +} __packed; + +/** + * struct sev_data_snp_guest_status - SNP_GUEST_STATUS command params + * + * @gctx_paddr: system physical address of guest context page + * @address: system physical address of guest status page + */ +struct sev_data_snp_guest_status { + u64 gctx_paddr; + u64 address; +} __packed; + +/** + * struct sev_data_snp_page_reclaim - SNP_PAGE_RECLAIM command params + * + * @paddr: system physical address of page to be claimed. The 0th bit in the + * address indicates the page size. 0h indicates 4KB and 1h indicates + * 2MB page. + */ +struct sev_data_snp_page_reclaim { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_page_unsmash - SNP_PAGE_UNSMASH command params + * + * @paddr: system physical address of page to be unsmashed. The 0th bit in the + * address indicates the page size. 0h indicates 4 KB and 1h indicates + * 2 MB page. + */ +struct sev_data_snp_page_unsmash { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters + * + * @gctx_paddr: system physical address of guest context page + * @src_addr: source address of data to operate on + * @dst_addr: destination address of data to operate on + */ +struct sev_data_snp_dbg { + u64 gctx_paddr; /* In */ + u64 src_addr; /* In */ + u64 dst_addr; /* In */ +} __packed; + +/** + * struct sev_data_snp_guest_request - SNP_GUEST_REQUEST command params + * + * @gctx_paddr: system physical address of guest context page + * @req_paddr: system physical address of request page + * @res_paddr: system physical address of response page + */ +struct sev_data_snp_guest_request { + u64 gctx_paddr; /* In */ + u64 req_paddr; /* In */ + u64 res_paddr; /* In */ +} __packed; + +/** + * struct sev_data_snp_init_ex - SNP_INIT_EX structure + * + * @init_rmp: indicate that the RMP should be initialized. + * @list_paddr_en: indicate that list_paddr is valid + * @rsvd: reserved + * @rsvd1: reserved + * @list_paddr: system physical address of range list + * @rsvd2: reserved + */ +struct sev_data_snp_init_ex { + u32 init_rmp:1; + u32 list_paddr_en:1; + u32 rsvd:30; + u32 rsvd1; + u64 list_paddr; + u8 rsvd2[48]; +} __packed; + +/** + * struct sev_data_range - RANGE structure + * + * @base: system physical address of first byte of range + * @page_count: number of 4KB pages in this range + * @rsvd: reserved + */ +struct sev_data_range { + u64 base; + u32 page_count; + u32 rsvd; +} __packed; + +/** + * struct sev_data_range_list - RANGE_LIST structure + * + * @num_elements: number of elements in RANGE_ARRAY + * @rsvd: reserved + * @ranges: array of num_elements of type RANGE + */ +struct sev_data_range_list { + u32 num_elements; + u32 rsvd; + struct sev_data_range ranges[]; +} __packed; + +/** + * struct sev_data_snp_shutdown_ex - SNP_SHUTDOWN_EX structure + * + * @len: length of the command buffer read by the PSP + * @iommu_snp_shutdown: Disable enforcement of SNP in the IOMMU + * @rsvd1: reserved + */ +struct sev_data_snp_shutdown_ex { + u32 len; + u32 iommu_snp_shutdown:1; + u32 rsvd1:31; +} __packed; + +/** + * struct sev_platform_init_args + * + * @error: SEV firmware error code + * @probe: True if this is being called as part of CCP module probe, which + * will defer SEV_INIT/SEV_INIT_EX firmware initialization until needed + * unless psp_init_on_probe module param is set + */ +struct sev_platform_init_args { + int error; + bool probe; +}; + +/** + * struct sev_data_snp_commit - SNP_COMMIT structure + * + * @len: length of the command buffer read by the PSP + */ +struct sev_data_snp_commit { + u32 len; +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** * sev_platform_init - perform SEV INIT command * - * @error: SEV command return code + * @args: struct sev_platform_init_args to pass in arguments * * Returns: * 0 if the SEV successfully processed the command @@ -539,7 +830,7 @@ struct sev_data_attestation_report { * -%ETIMEDOUT if the SEV command timed out * -%EIO if the SEV returned a non-zero return code */ -int sev_platform_init(int *error); +int sev_platform_init(struct sev_platform_init_args *args); /** * sev_platform_status - perform SEV PLATFORM_STATUS command @@ -639,14 +930,32 @@ int sev_guest_df_flush(int *error); */ int sev_guest_decommission(struct sev_data_decommission *data, int *error); +/** + * sev_do_cmd - issue an SEV or an SEV-SNP command + * + * @cmd: SEV or SEV-SNP firmware command to issue + * @data: arguments for firmware command + * @psp_ret: SEV command return code + * + * Returns: + * 0 if the SEV device successfully processed the command + * -%ENODEV if the PSP device is not available + * -%ENOTSUPP if PSP device does not support SEV + * -%ETIMEDOUT if the SEV command timed out + * -%EIO if PSP device returned a non-zero return code + */ +int sev_do_cmd(int cmd, void *data, int *psp_ret); + void *psp_copy_user_blob(u64 uaddr, u32 len); +void *snp_alloc_firmware_page(gfp_t mask); +void snp_free_firmware_page(void *addr); #else /* !CONFIG_CRYPTO_DEV_SP_PSP */ static inline int sev_platform_status(struct sev_user_data_status *status, int *error) { return -ENODEV; } -static inline int sev_platform_init(int *error) { return -ENODEV; } +static inline int sev_platform_init(struct sev_platform_init_args *args) { return -ENODEV; } static inline int sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENODEV; } @@ -654,6 +963,9 @@ sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENO static inline int sev_guest_decommission(struct sev_data_decommission *data, int *error) { return -ENODEV; } +static inline int +sev_do_cmd(int cmd, void *data, int *psp_ret) { return -ENODEV; } + static inline int sev_guest_activate(struct sev_data_activate *data, int *error) { return -ENODEV; } @@ -664,6 +976,13 @@ sev_issue_cmd_external_user(struct file *filep, unsigned int id, void *data, int static inline void *psp_copy_user_blob(u64 __user uaddr, u32 len) { return ERR_PTR(-EINVAL); } +static inline void *snp_alloc_firmware_page(gfp_t mask) +{ + return NULL; +} + +static inline void snp_free_firmware_page(void *addr) { } + #endif /* CONFIG_CRYPTO_DEV_SP_PSP */ #endif /* __PSP_SEV_H__ */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d55699e1386dbc640ada1540aefae2e9ac900818..ba46bc9b387099103f3ba2a44329e859efc0300e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -95,6 +95,19 @@ 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 +115,7 @@ 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 +279,7 @@ 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 +533,13 @@ 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]; }; @@ -1206,6 +1228,13 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_COUNTER_OFFSET 227 #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 +#define KVM_CAP_PRE_FAULT_MEMORY 236 #define KVM_CAP_SEV_ES_GHCB 500 #define KVM_CAP_HYGON_COCO_EXT 501 @@ -1289,39 +1318,6 @@ struct kvm_irq_routing { #endif -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#ifdef KVM_CAP_XEN_HVM -#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) -#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) -#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#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) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1532,8 +1528,10 @@ struct kvm_numa_info { 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) -#define KVM_LOAD_USER_DATA _IOW(KVMIO, 0x49, struct kvm_user_data) +#define KVM_LOAD_USER_DATA _IOW(KVMIO, 0x43, struct kvm_user_data) #define KVM_CAP_ARM_TMM 300 /* FIXME: Large number to prevent conflicts */ @@ -1640,6 +1638,7 @@ struct kvm_s390_ucas_mapping { #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) /* Available with KVM_CAP_COUNTER_OFFSET */ #define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) +#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO, 0xb6, struct reg_mask_range) /* ioctl for SW vcpu init*/ #define KVM_SW64_VCPU_INIT _IO(KVMIO, 0xba) @@ -1872,58 +1871,6 @@ struct kvm_pv_cmd { #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) -struct kvm_xen_hvm_attr { - __u16 type; - __u16 pad[3]; - union { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } u; -}; - - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 -#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 -#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) @@ -1934,225 +1881,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } u; -}; - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - /* Available with KVM_CAP_ARM_USER_IRQ */ /* Bits for run->s.regs.device_irq_level */ @@ -2160,16 +1888,6 @@ struct kvm_assigned_msix_entry { #define KVM_ARM_DEV_EL1_PTIMER (1 << 1) #define KVM_ARM_DEV_PMU (1 << 2) -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#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) @@ -2386,6 +2104,18 @@ struct kvm_csv_init { #define KVM_CONTROL_PRE_SYSTEM_RESET _IO(KVMIO, 0xe8) #define KVM_CONTROL_POST_SYSTEM_RESET _IO(KVMIO, 0xe9) +/* 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) + /* CSV3 command */ enum csv3_cmd_id { KVM_CSV3_NR_MIN = 0xc0, @@ -2457,4 +2187,21 @@ struct kvm_csv3_handle_memory { /* get tmi version */ #define KVM_GET_TMI_VERSION _IOR(KVMIO, 0xd2, u64) +#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]; +}; + +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 1c9da485318f93fe50e11a47f284d8fe81106066..24922758435d03b827af9caf7ce244f3a257c8df 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -28,6 +28,10 @@ enum { SEV_PEK_CERT_IMPORT, SEV_GET_ID, /* This command is deprecated, use SEV_GET_ID2 */ SEV_GET_ID2, + SNP_PLATFORM_STATUS, + SNP_COMMIT, + SNP_SET_CONFIG, + SNP_VLEK_LOAD, SEV_MAX, }; @@ -68,6 +72,20 @@ typedef enum { SEV_RET_INVALID_PARAM, SEV_RET_RESOURCE_LIMIT, SEV_RET_SECURE_DATA_INVALID, + SEV_RET_INVALID_PAGE_SIZE = 0x0019, + SEV_RET_INVALID_PAGE_STATE = 0x001A, + SEV_RET_INVALID_MDATA_ENTRY = 0x001B, + SEV_RET_INVALID_PAGE_OWNER = 0x001C, + SEV_RET_AEAD_OFLOW = 0x001D, + SEV_RET_EXIT_RING_BUFFER = 0x001F, + SEV_RET_RMP_INIT_REQUIRED = 0x0020, + SEV_RET_BAD_SVN = 0x0021, + SEV_RET_BAD_VERSION = 0x0022, + SEV_RET_SHUTDOWN_REQUIRED = 0x0023, + SEV_RET_UPDATE_FAILED = 0x0024, + SEV_RET_RESTORE_REQUIRED = 0x0025, + SEV_RET_RMP_INITIALIZATION_FAILED = 0x0026, + SEV_RET_INVALID_KEY = 0x0027, SEV_RET_MAX, } sev_ret_code; @@ -154,6 +172,82 @@ struct sev_user_data_get_id2 { __u32 length; /* In/Out */ } __packed; +/** + * struct sev_user_data_snp_status - SNP status + * + * @api_major: API major version + * @api_minor: API minor version + * @state: current platform state + * @is_rmp_initialized: whether RMP is initialized or not + * @rsvd: reserved + * @build_id: firmware build id for the API version + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @vlek_en: VLEK (Version Loaded Endorsement Key) hashstick is loaded + * @rsvd1: reserved + * @guest_count: the number of guest currently managed by the firmware + * @current_tcb_version: current TCB version + * @reported_tcb_version: reported TCB version + */ +struct sev_user_data_snp_status { + __u8 api_major; /* Out */ + __u8 api_minor; /* Out */ + __u8 state; /* Out */ + __u8 is_rmp_initialized:1; /* Out */ + __u8 rsvd:7; + __u32 build_id; /* Out */ + __u32 mask_chip_id:1; /* Out */ + __u32 mask_chip_key:1; /* Out */ + __u32 vlek_en:1; /* Out */ + __u32 rsvd1:29; + __u32 guest_count; /* Out */ + __u64 current_tcb_version; /* Out */ + __u64 reported_tcb_version; /* Out */ +} __packed; + +/** + * struct sev_user_data_snp_config - system wide configuration value for SNP. + * + * @reported_tcb: the TCB version to report in the guest attestation report. + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @rsvd: reserved + * @rsvd1: reserved + */ +struct sev_user_data_snp_config { + __u64 reported_tcb ; /* In */ + __u32 mask_chip_id:1; /* In */ + __u32 mask_chip_key:1; /* In */ + __u32 rsvd:30; /* In */ + __u8 rsvd1[52]; +} __packed; + +/** + * struct sev_data_snp_vlek_load - SNP_VLEK_LOAD structure + * + * @len: length of the command buffer read by the PSP + * @vlek_wrapped_version: version of wrapped VLEK hashstick (Must be 0h) + * @rsvd: reserved + * @vlek_wrapped_address: address of a wrapped VLEK hashstick + * (struct sev_user_data_snp_wrapped_vlek_hashstick) + */ +struct sev_user_data_snp_vlek_load { + __u32 len; /* In */ + __u8 vlek_wrapped_version; /* In */ + __u8 rsvd[3]; /* In */ + __u64 vlek_wrapped_address; /* In */ +} __packed; + +/** + * struct sev_user_data_snp_vlek_wrapped_vlek_hashstick - Wrapped VLEK data + * + * @data: Opaque data provided by AMD KDS (as described in SEV-SNP Firmware ABI + * 1.54, SNP_VLEK_LOAD) + */ +struct sev_user_data_snp_wrapped_vlek_hashstick { + __u8 data[432]; /* In */ +} __packed; + /** * struct sev_issue_cmd - SEV ioctl parameters * diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 2aa39112cf8dd37e3ee265f6128973c8698145df..fcdfea767fca88d7db4672e5566ce05826e9237c 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -14,9 +14,11 @@ #include +#define SNP_REPORT_USER_DATA_SIZE 64 + struct snp_report_req { /* user data that should be included in the report */ - __u8 user_data[64]; + __u8 user_data[SNP_REPORT_USER_DATA_SIZE]; /* The vmpl level to be included in the report */ __u32 vmpl; @@ -87,6 +89,9 @@ struct snp_ext_report_req { #define SNP_GUEST_FW_ERR_MASK GENMASK_ULL(31, 0) #define SNP_GUEST_VMM_ERR_SHIFT 32 #define SNP_GUEST_VMM_ERR(x) (((u64)x) << SNP_GUEST_VMM_ERR_SHIFT) +#define SNP_GUEST_FW_ERR(x) ((x) & SNP_GUEST_FW_ERR_MASK) +#define SNP_GUEST_ERR(vmm_err, fw_err) (SNP_GUEST_VMM_ERR(vmm_err) | \ + SNP_GUEST_FW_ERR(fw_err)) #define SNP_GUEST_VMM_ERR_INVALID_LEN 1 #define SNP_GUEST_VMM_ERR_BUSY 2 diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 8b15e9dc340fc50cc4a6aa4d5bfc3329d3e34855..83e9998955cdbdffe762b50b822188d80d7bf3ef 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3961,7 +3961,8 @@ static int io_uring_install_fd(struct file *file) */ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) { - return anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx, + /* Create a new inode so that the LSM can block the creation. */ + return anon_inode_create_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC, NULL); } diff --git a/mm/compaction.c b/mm/compaction.c index ed0baf7404c8b8e54624a3ed70fe42532e5b0ed0..54e96ccbd558b4b0178b2051949f66e43c0f1416 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -938,6 +938,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* Time to isolate some pages for migration */ for (; low_pfn < end_pfn; low_pfn++) { + bool is_dirty, is_unevictable; if (skip_on_failure && low_pfn >= next_skip_pfn) { /* @@ -1153,8 +1154,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (!folio_test_lru(folio)) goto isolate_fail_put; + is_unevictable = folio_test_unevictable(folio); + /* Compaction might skip unevictable pages but CMA takes them */ - if (!(mode & ISOLATE_UNEVICTABLE) && folio_test_unevictable(folio)) + if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable) goto isolate_fail_put; /* @@ -1166,26 +1169,42 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio)) goto isolate_fail_put; - if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_dirty(folio)) { - bool migrate_dirty; + is_dirty = folio_test_dirty(folio); + + if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) || + (mapping && is_unevictable)) { + bool migrate_dirty = true; + bool is_inaccessible; /* * Only folios without mappings or that have - * a ->migrate_folio callback are possible to - * migrate without blocking. However, we may - * be racing with truncation, which can free - * the mapping. Truncation holds the folio lock - * until after the folio is removed from the page - * cache so holding it ourselves is sufficient. + * a ->migrate_folio callback are possible to migrate + * without blocking. + * + * Folios from inaccessible mappings are not migratable. + * + * However, we can be racing with truncation, which can + * free the mapping that we need to check. Truncation + * holds the folio lock until after the folio is removed + * from the page so holding it ourselves is sufficient. + * + * To avoid locking the folio just to check inaccessible, + * assume every inaccessible folio is also unevictable, + * which is a cheaper test. If our assumption goes + * wrong, it's not a correctness bug, just potentially + * wasted cycles. */ if (!folio_trylock(folio)) goto isolate_fail_put; mapping = folio_mapping(folio); - migrate_dirty = !mapping || - mapping->a_ops->migrate_folio; + if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) { + migrate_dirty = !mapping || + mapping->a_ops->migrate_folio; + } + is_inaccessible = mapping && mapping_inaccessible(mapping); folio_unlock(folio); - if (!migrate_dirty) + if (!migrate_dirty || is_inaccessible) goto isolate_fail_put; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b94470b4cfc1fbdd3620a3bbae803a8ba2b1378d..8d1dcb06f582ebd78e893e9b59a87d5e4acc0cd4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1152,7 +1152,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode) * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ - return (struct resv_map *)(&inode->i_data)->private_data; + return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) diff --git a/mm/migrate.c b/mm/migrate.c index d2f0b03fe9358c80613913076f3b5fc5b542fe07..8a6482f3f84d9eb333326b0978777094b530dba5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -799,7 +799,7 @@ static int __buffer_migrate_folio(struct address_space *mapping, recheck_buffers: busy = false; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); bh = head; do { if (atomic_read(&bh->b_count)) { @@ -813,7 +813,7 @@ static int __buffer_migrate_folio(struct address_space *mapping, rc = -EAGAIN; goto unlock_buffers; } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; @@ -832,7 +832,7 @@ static int __buffer_migrate_folio(struct address_space *mapping, unlock_buffers: if (check_refs) - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); bh = head; do { unlock_buffer(bh); @@ -987,6 +987,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, if (!mapping) rc = migrate_folio(mapping, dst, src, mode); + else if (mapping_inaccessible(mapping)) + rc = -EOPNOTSUPP; else if (mapping->a_ops->migrate_folio) /* * Most folios have a mapping and most filesystems diff --git a/mm/truncate.c b/mm/truncate.c index 1557a0503f8eabad78f293f5bb369e505e06f613..88e0bffcdc2da0dff5ed2fafd0b6b99a41f5d0e4 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -233,7 +233,8 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) * doing a complex calculation here, and then doing the zeroing * anyway if the page split fails. */ - folio_zero_range(folio, offset, length); + if (!mapping_inaccessible(folio->mapping)) + folio_zero_range(folio, offset, length); if (folio_needs_release(folio)) folio_invalidate(folio, offset, length); diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index bcdf9d6dc37b096227c8e9ffa1b0bf9c3eb36be3..aab074f91ee376e499f7f3887cc6a133c85cd0cc 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -37,9 +37,7 @@ #include #include -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -76,11 +74,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ - KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ - KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 @@ -162,6 +160,11 @@ struct kvm_sync_regs { __u64 device_irq_level; }; +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 9f18fa090f1f1d08179cba6f39f7b832bbd7b95b..1691297a766a9c1a4df9384c4ff02ecd8ce21b92 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -28,7 +28,6 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_GUEST_DEBUG /* Not always available, but if it is, this is the correct offset. */ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -733,4 +732,48 @@ struct kvm_ppc_xive_eq { #define KVM_XIVE_TIMA_PAGE_OFFSET 0 #define KVM_XIVE_ESB_PAGE_OFFSET 4 +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 +#define KVM_PPC_NO_HASH 0x00000004 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index a73cf01a1606671bf77a995c665f90ca7428c9ab..a1a7faea64914d251b2ee6bd67607ce08db9c526 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -12,7 +12,320 @@ #include #define __KVM_S390 -#define __KVM_HAVE_GUEST_DEBUG + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ + }; + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* ignored */ + }; +}; +/* 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 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + +/* 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) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; /* will stay unused for compatibility reasons */ + __u32 len; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ +}; + +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; + +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __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, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, +}; + +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]; +}; + +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) /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 3c3af4eb587731c4396c2c13caa76847f879a34c..80cfe1d088890a8bc6bea9b89a82fb374b43dfa1 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -85,8 +85,8 @@ /* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ /* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +/* Free ( 3*32+ 6) */ +/* Free ( 3*32+ 7) */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ #define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ #define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ @@ -326,6 +326,7 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_INVLPGB (13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */ #define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ #define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ @@ -372,6 +373,7 @@ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ #define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ +#define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ @@ -428,13 +430,17 @@ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ +#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ +#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ @@ -442,6 +448,13 @@ #define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ #define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ +#define X86_FEATURE_SRSO_USER_KERNEL_NO (20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */ +#define X86_FEATURE_SRSO_BP_SPEC_REDUCE (20*32+31) /* + * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs. + * (SRSO_MSR_FIX in the official doc). + */ + +#define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000006, word 20 */ #define X86_FEATURE_ZXPAUSE (30*32 + 0) /* ZHAOXIN ZXPAUSE */ @@ -488,4 +501,5 @@ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 474fd815148e828e2e3b591d34d5b486e7bd942f..f5d57f99111020f1a9333c31efe3a29b57c35f50 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -176,6 +176,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -353,7 +361,8 @@ #define MSR_IA32_PASID_VALID BIT_ULL(31) /* DEBUGCTLMSR bits (others vary by model): */ -#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */ +#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT) #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) @@ -557,6 +566,7 @@ #define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_AMD_PERF_STATUS 0xc0010063 #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 @@ -592,36 +602,51 @@ #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) - -#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_AMD64_RMP_CFG 0xc0010136 +#define MSR_AMD64_SEG_RMP_ENABLED_BIT 0 +#define MSR_AMD64_SEG_RMP_ENABLED BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT) +#define MSR_AMD64_RMP_SEGMENT_SHIFT(x) (((x) & GENMASK_ULL(13, 8)) >> 8) /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 @@ -630,15 +655,17 @@ #define MSR_AMD_CPPC_REQ 0xc00102b3 #define MSR_AMD_CPPC_STATUS 0xc00102b4 -#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff) -#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff) -#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff) -#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff) +/* Masks for use with MSR_AMD_CPPC_CAP1 */ +#define AMD_CPPC_LOWEST_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_LOWNONLIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_NOMINAL_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_HIGHEST_PERF_MASK GENMASK(31, 24) -#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0) -#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8) -#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16) -#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24) +/* Masks for use with MSR_AMD_CPPC_REQ */ +#define AMD_CPPC_MAX_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_MIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_DES_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_EPP_PERF_MASK GENMASK(31, 24) /* AMD Performance Counter Global Status and Control MSRs */ #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300 @@ -648,6 +675,7 @@ /* AMD Last Branch Record MSRs */ #define MSR_AMD64_LBR_SELECT 0xc000010e +#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 @@ -700,8 +728,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 1a6a1f98794967d260e2898b0dbb62f830d45664..9fae1b73b529caf53c5c7dd1823fd7a3f320637c 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -7,6 +7,8 @@ * */ +#include +#include #include #include #include @@ -40,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 @@ -49,7 +50,6 @@ #define __KVM_HAVE_DEBUGREGS #define __KVM_HAVE_XSAVE #define __KVM_HAVE_XCRS -#define __KVM_HAVE_READONLY_MEM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -457,8 +457,13 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 -/* attributes for system fd (group 0) */ -#define KVM_X86_XCOMP_GUEST_SUPP 0 +/* vendor-independent attributes for system fd (group 0) */ +#define KVM_X86_GRP_SYSTEM 0 +# define KVM_X86_XCOMP_GUEST_SUPP 0 + +/* vendor-specific groups and attributes for system fd */ +#define KVM_X86_GRP_SEV 1 +# define KVM_X86_SEV_VMSA_FEATURES 0 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -526,9 +531,312 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 -#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#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) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + union { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + __u64 hva; + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 hva; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + /* Second time is the charm; improved versions of the above ioctls. */ + KVM_SEV_INIT2, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_init { + __u64 vmsa_features; + __u32 flags; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -549,10 +857,10 @@ struct kvm_pmu_event_filter { ((__u64)(!!(exclude)) << 55)) #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ - (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) -#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) + (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55)) #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ @@ -560,6 +868,11 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ /* x86-specific KVM_EXIT_HYPERCALL flags. */ -#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0) + +#define KVM_X86_DEFAULT_VM 0 +#define KVM_X86_SW_PROTECTED_VM 1 +#define KVM_X86_SEV_VM 2 +#define KVM_X86_SEV_ES_VM 3 #endif /* _ASM_X86_KVM_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index bd1a496b5448f192b319221f568895b03d44c5a7..7b6d3492e3af3761075ebba16ecd7714bc45e4ba 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -16,75 +16,10 @@ #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 *** */ - +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { @@ -95,6 +30,19 @@ 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 +50,7 @@ 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 { @@ -141,43 +90,6 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 -struct kvm_s390_skeys { - __u64 start_gfn; - __u64 count; - __u64 skeydata_addr; - __u32 flags; - __u32 reserved[9]; -}; - -#define KVM_S390_CMMA_PEEK (1 << 0) - -/** - * kvm_s390_cmma_log - Used for CMMA migration. - * - * Used both for input and output. - * - * @start_gfn: Guest page number to start from. - * @count: Size of the result buffer. - * @flags: Control operation mode via KVM_S390_CMMA_* flags - * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty - * pages are still remaining. - * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set - * in the PGSTE. - * @values: Pointer to the values buffer. - * - * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. - */ -struct kvm_s390_cmma_log { - __u64 start_gfn; - __u32 count; - __u32 flags; - union { - __u64 remaining; - __u64 mask; - }; - __u64 values; -}; - struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -264,6 +176,7 @@ struct kvm_xen_exit { #define KVM_EXIT_RISCV_SBI 35 #define KVM_EXIT_RISCV_CSR 36 #define KVM_EXIT_NOTIFY 37 +#define KVM_EXIT_MEMORY_FAULT 39 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -362,11 +275,6 @@ struct kvm_run { __u32 ipb; } s390_sieic; /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; /* KVM_EXIT_S390_UCONTROL */ struct { @@ -510,6 +418,13 @@ 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]; }; @@ -576,43 +491,6 @@ struct kvm_translation { __u8 pad[5]; }; -/* for KVM_S390_MEM_OP */ -struct kvm_s390_mem_op { - /* in */ - __u64 gaddr; /* the guest address */ - __u64 flags; /* flags */ - __u32 size; /* amount of bytes */ - __u32 op; /* type of operation */ - __u64 buf; /* buffer in userspace */ - union { - struct { - __u8 ar; /* the access register number */ - __u8 key; /* access key, ignored if flag unset */ - __u8 pad1[6]; /* ignored */ - __u64 old_addr; /* ignored if cmpxchg flag unset */ - }; - __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* ignored */ - }; -}; -/* 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 -#define KVM_S390_MEMOP_ABSOLUTE_READ 4 -#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 -#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 - -/* 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) -#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) - -/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ -#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) -#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) - /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -677,124 +555,6 @@ struct kvm_mp_state { __u32 mp_state; }; -struct kvm_s390_psw { - __u64 mask; - __u64 addr; -}; - -/* valid values for type in kvm_s390_interrupt */ -#define KVM_S390_SIGP_STOP 0xfffe0000u -#define KVM_S390_PROGRAM_INT 0xfffe0001u -#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u -#define KVM_S390_RESTART 0xfffe0003u -#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u -#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u -#define KVM_S390_MCHK 0xfffe1000u -#define KVM_S390_INT_CLOCK_COMP 0xffff1004u -#define KVM_S390_INT_CPU_TIMER 0xffff1005u -#define KVM_S390_INT_VIRTIO 0xffff2603u -#define KVM_S390_INT_SERVICE 0xffff2401u -#define KVM_S390_INT_EMERGENCY 0xffff1201u -#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u -/* Anything below 0xfffe0000u is taken by INT_IO */ -#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ - (((schid)) | \ - ((ssid) << 16) | \ - ((cssid) << 18) | \ - ((ai) << 26)) -#define KVM_S390_INT_IO_MIN 0x00000000u -#define KVM_S390_INT_IO_MAX 0xfffdffffu -#define KVM_S390_INT_IO_AI_MASK 0x04000000u - - -struct kvm_s390_interrupt { - __u32 type; - __u32 parm; - __u64 parm64; -}; - -struct kvm_s390_io_info { - __u16 subchannel_id; - __u16 subchannel_nr; - __u32 io_int_parm; - __u32 io_int_word; -}; - -struct kvm_s390_ext_info { - __u32 ext_params; - __u32 pad; - __u64 ext_params2; -}; - -struct kvm_s390_pgm_info { - __u64 trans_exc_code; - __u64 mon_code; - __u64 per_address; - __u32 data_exc_code; - __u16 code; - __u16 mon_class_nr; - __u8 per_code; - __u8 per_atmid; - __u8 exc_access_id; - __u8 per_access_id; - __u8 op_access_id; -#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 -#define KVM_S390_PGM_FLAGS_ILC_0 0x02 -#define KVM_S390_PGM_FLAGS_ILC_1 0x04 -#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 -#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 - __u8 flags; - __u8 pad[2]; -}; - -struct kvm_s390_prefix_info { - __u32 address; -}; - -struct kvm_s390_extcall_info { - __u16 code; -}; - -struct kvm_s390_emerg_info { - __u16 code; -}; - -#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 -struct kvm_s390_stop_info { - __u32 flags; -}; - -struct kvm_s390_mchk_info { - __u64 cr14; - __u64 mcic; - __u64 failing_storage_address; - __u32 ext_damage_code; - __u32 pad; - __u8 fixed_logout[16]; -}; - -struct kvm_s390_irq { - __u64 type; - union { - struct kvm_s390_io_info io; - struct kvm_s390_ext_info ext; - struct kvm_s390_pgm_info pgm; - struct kvm_s390_emerg_info emerg; - struct kvm_s390_extcall_info extcall; - struct kvm_s390_prefix_info prefix; - struct kvm_s390_stop_info stop; - struct kvm_s390_mchk_info mchk; - char reserved[64]; - } u; -}; - -struct kvm_s390_irq_state { - __u64 buf; - __u32 flags; /* will stay unused for compatibility reasons */ - __u32 len; - __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; - /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -850,50 +610,6 @@ struct kvm_enable_cap { __u8 pad[64]; }; -/* for KVM_PPC_GET_PVINFO */ - -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - -struct kvm_ppc_pvinfo { - /* out */ - __u32 flags; - __u32 hcall[4]; - __u8 pad[108]; -}; - -/* for KVM_PPC_GET_SMMU_INFO */ -#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 - -struct kvm_ppc_one_page_size { - __u32 page_shift; /* Page shift (or 0) */ - __u32 pte_enc; /* Encoding in the HPTE (>>12) */ -}; - -struct kvm_ppc_one_seg_page_size { - __u32 page_shift; /* Base page shift of segment (or 0) */ - __u32 slb_enc; /* SLB encoding for BookS */ - struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 -#define KVM_PPC_1T_SEGMENTS 0x00000002 -#define KVM_PPC_NO_HASH 0x00000004 - -struct kvm_ppc_smmu_info { - __u64 flags; - __u32 slb_size; - __u16 data_keys; /* # storage keys supported for data */ - __u16 instr_keys; /* # storage keys supported for instructions */ - struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ -struct kvm_ppc_resize_hpt { - __u64 flags; - __u32 shift; - __u32 pad; -}; - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ @@ -937,9 +653,6 @@ 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) @@ -966,9 +679,7 @@ struct kvm_ppc_resize_hpt { /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 #define KVM_CAP_USER_NMI 22 -#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 -#endif #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif @@ -1194,8 +905,11 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 #define KVM_CAP_ARM_HW_DIRTY_STATE_TRACK 502 - -#ifdef KVM_CAP_IRQ_ROUTING +#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 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1261,41 +975,6 @@ struct kvm_irq_routing { struct kvm_irq_routing_entry entries[]; }; -#endif - -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#ifdef KVM_CAP_XEN_HVM -#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) -#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) -#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#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) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1474,13 +1153,10 @@ 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 { - __u64 user_addr; - __u64 vcpu_addr; - __u64 length; -}; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) @@ -1498,20 +1174,8 @@ 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) @@ -1528,9 +1192,6 @@ 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 */ @@ -1551,9 +1212,9 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_SPAPR_RESIZE_HPT */ #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) #define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) -/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */ #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) -/* Available with KVM_CAP_PPC_RADIX_MMU */ +/* Available with KVM_CAP_PPC_MMU_RADIX */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* Available with KVM_CAP_PPC_GET_CPU_CHAR */ #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) @@ -1582,8 +1243,6 @@ 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) @@ -1691,89 +1350,6 @@ 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_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, - KVM_PV_SET_SEC_PARMS, - KVM_PV_UNPACK, - KVM_PV_VERIFY, - KVM_PV_PREP_RESET, - KVM_PV_UNSHARE_ALL, - KVM_PV_INFO, - KVM_PV_DUMP, - KVM_PV_ASYNC_CLEANUP_PREPARE, - KVM_PV_ASYNC_CLEANUP_PERFORM, -}; - -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) @@ -1787,58 +1363,6 @@ struct kvm_pv_cmd { #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) -struct kvm_xen_hvm_attr { - __u16 type; - __u16 pad[3]; - union { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } u; -}; - - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 -#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 -#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) @@ -1849,242 +1373,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } u; -}; - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - -/* Available with KVM_CAP_ARM_USER_IRQ */ - -/* Bits for run->s.regs.device_irq_level */ -#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) -#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) -#define KVM_ARM_DEV_PMU (1 << 2) - -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#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) @@ -2231,31 +1519,24 @@ struct kvm_stats_desc { /* 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; +/* 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; }; -/* types for kvm_s390_zpci_op->op */ -#define KVM_S390_ZPCIOP_REG_AEN 0 -#define KVM_S390_ZPCIOP_DEREG_AEN 1 +#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + +#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) -/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ -#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) +struct kvm_create_guest_memfd { + __u64 size; + __u64 flags; + __u64 reserved[6]; +}; #endif /* __LINUX_KVM_H */ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index a3bb36fb3cfc55a423d31c10e86c1fe16b79ca0e..80d3ac325d50f1369904e5b3a3939b0de9a7781a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -37,6 +37,7 @@ LIBKVM_x86_64 += lib/x86_64/handlers.S LIBKVM_x86_64 += lib/x86_64/hyperv.c LIBKVM_x86_64 += lib/x86_64/memstress.c LIBKVM_x86_64 += lib/x86_64/processor.c +LIBKVM_x86_64 += lib/x86_64/sev.c LIBKVM_x86_64 += lib/x86_64/svm.c LIBKVM_x86_64 += lib/x86_64/ucall.c LIBKVM_x86_64 += lib/x86_64/vmx.c @@ -81,6 +82,8 @@ TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test +TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test +TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test @@ -114,7 +117,9 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test +TEST_GEN_PROGS_x86_64 += x86_64/sev_init2_tests TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests +TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test @@ -123,6 +128,7 @@ TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test +TEST_GEN_PROGS_x86_64 += guest_memfd_test TEST_GEN_PROGS_x86_64 += guest_print_test TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 47bb914ab2fa8357c5b813084718ba05afa223d4..b1e2fe5a30eab6d9d26989ae3d65a6243b44d7f3 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -705,7 +705,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) print_test_banner(mode, p); - vm = ____vm_create(mode); + vm = ____vm_create(VM_SHAPE(mode)); setup_memslots(vm, p); kvm_vm_elf_load(vm, program_invocation_name); setup_ucall(vm); diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index e96fababd3f063dce2ffb497bd1b230785762978..4ca747c338465411f93882d38621c472b7d61709 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -686,7 +686,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = __vm_create(mode, 1, extra_mem_pages); + vm = __vm_create(VM_SHAPE(mode), 1, extra_mem_pages); log_mode_create_vm_done(vm); *vcpu = vm_vcpu_add(vm, 0, guest_code); diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c new file mode 100644 index 0000000000000000000000000000000000000000..2f3379b7e67ddf897b67b8fd3a0a40f5cedde9a8 --- /dev/null +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright Intel Corporation, 2023 + * + * Author: Chao Peng + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "test_util.h" +#include "kvm_util_base.h" + +static void test_file_read_write(int fd) +{ + char buf[64]; + + TEST_ASSERT(read(fd, buf, sizeof(buf)) < 0, + "read on a guest_mem fd should fail"); + TEST_ASSERT(write(fd, buf, sizeof(buf)) < 0, + "write on a guest_mem fd should fail"); + TEST_ASSERT(pread(fd, buf, sizeof(buf), 0) < 0, + "pread on a guest_mem fd should fail"); + TEST_ASSERT(pwrite(fd, buf, sizeof(buf), 0) < 0, + "pwrite on a guest_mem fd should fail"); +} + +static void test_mmap(int fd, size_t page_size) +{ + char *mem; + + mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT_EQ(mem, MAP_FAILED); +} + +static void test_file_size(int fd, size_t page_size, size_t total_size) +{ + struct stat sb; + int ret; + + ret = fstat(fd, &sb); + TEST_ASSERT(!ret, "fstat should succeed"); + TEST_ASSERT_EQ(sb.st_size, total_size); + TEST_ASSERT_EQ(sb.st_blksize, page_size); +} + +static void test_fallocate(int fd, size_t page_size, size_t total_size) +{ + int ret; + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, total_size); + TEST_ASSERT(!ret, "fallocate with aligned offset and size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + page_size - 1, page_size); + TEST_ASSERT(ret, "fallocate with unaligned offset should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size, page_size); + TEST_ASSERT(ret, "fallocate beginning at total_size should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size + page_size, page_size); + TEST_ASSERT(ret, "fallocate beginning after total_size should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + total_size, page_size); + TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) at total_size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + total_size + page_size, page_size); + TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) after total_size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + page_size, page_size - 1); + TEST_ASSERT(ret, "fallocate with unaligned size should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + page_size, page_size); + TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) with aligned offset and size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, page_size, page_size); + TEST_ASSERT(!ret, "fallocate to restore punched hole should succeed"); +} + +static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size) +{ + struct { + off_t offset; + off_t len; + } testcases[] = { + {0, 1}, + {0, page_size - 1}, + {0, page_size + 1}, + + {1, 1}, + {1, page_size - 1}, + {1, page_size}, + {1, page_size + 1}, + + {page_size, 1}, + {page_size, page_size - 1}, + {page_size, page_size + 1}, + }; + int ret, i; + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + testcases[i].offset, testcases[i].len); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "PUNCH_HOLE with !PAGE_SIZE offset (%lx) and/or length (%lx) should fail", + testcases[i].offset, testcases[i].len); + } +} + +static void test_create_guest_memfd_invalid(struct kvm_vm *vm) +{ + size_t page_size = getpagesize(); + uint64_t flag; + size_t size; + int fd; + + for (size = 1; size < page_size; size++) { + fd = __vm_create_guest_memfd(vm, size, 0); + TEST_ASSERT(fd == -1 && errno == EINVAL, + "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL", + size); + } + + for (flag = BIT(0); flag; flag <<= 1) { + fd = __vm_create_guest_memfd(vm, page_size, flag); + TEST_ASSERT(fd == -1 && errno == EINVAL, + "guest_memfd() with flag '0x%lx' should fail with EINVAL", + flag); + } +} + +static void test_create_guest_memfd_multiple(struct kvm_vm *vm) +{ + int fd1, fd2, ret; + struct stat st1, st2; + + fd1 = __vm_create_guest_memfd(vm, 4096, 0); + TEST_ASSERT(fd1 != -1, "memfd creation should succeed"); + + ret = fstat(fd1, &st1); + TEST_ASSERT(ret != -1, "memfd fstat should succeed"); + TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size"); + + fd2 = __vm_create_guest_memfd(vm, 8192, 0); + TEST_ASSERT(fd2 != -1, "memfd creation should succeed"); + + ret = fstat(fd2, &st2); + TEST_ASSERT(ret != -1, "memfd fstat should succeed"); + TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size"); + + ret = fstat(fd1, &st1); + TEST_ASSERT(ret != -1, "memfd fstat should succeed"); + TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size"); + TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers"); + + close(fd2); + close(fd1); +} + +int main(int argc, char *argv[]) +{ + size_t page_size; + size_t total_size; + int fd; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + + page_size = getpagesize(); + total_size = page_size * 4; + + vm = vm_create_barebones(); + + test_create_guest_memfd_invalid(vm); + test_create_guest_memfd_multiple(vm); + + fd = vm_create_guest_memfd(vm, total_size, 0); + + test_file_read_write(fd); + test_mmap(fd, page_size); + test_file_size(fd, page_size, total_size); + test_fallocate(fd, page_size, total_size); + test_invalid_punch_hole(fd, page_size, total_size); + + close(fd); +} diff --git a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h new file mode 100644 index 0000000000000000000000000000000000000000..e43a57d99b56cc3f541d7718b868eb92b4a46e10 --- /dev/null +++ b/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index a18db6a7b3cf474fe48cacf16bd962123f977e42..b3ec3c71b4a1a9ee9bfb7eacf650be9094000c80 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -18,9 +18,11 @@ #include #include +#include #include +#include "kvm_util_arch.h" #include "sparsebit.h" /* @@ -44,8 +46,9 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ struct userspace_mem_region { - struct kvm_userspace_memory_region region; + struct kvm_userspace_memory_region2 region; struct sparsebit *unused_phy_pages; + struct sparsebit *protected_phy_pages; int fd; off_t offset; enum vm_mem_backing_src_type backing_src_type; @@ -111,6 +114,9 @@ struct kvm_vm { vm_vaddr_t idt; vm_vaddr_t handlers; uint32_t dirty_ring_size; + uint64_t gpa_tag_mask; + + struct kvm_vm_arch arch; /* Cache of information for binary stats interface */ int stats_fd; @@ -188,6 +194,27 @@ enum vm_guest_mode { NUM_VM_MODES, }; +struct vm_shape { + uint32_t type; + uint8_t mode; + uint8_t pad0; + uint16_t pad1; +}; + +kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); + +#define VM_TYPE_DEFAULT 0 + +#define VM_SHAPE(__mode) \ +({ \ + struct vm_shape shape = { \ + .mode = (__mode), \ + .type = VM_TYPE_DEFAULT \ + }; \ + \ + shape; \ +}) + #if defined(__aarch64__) extern enum vm_guest_mode vm_mode_default; @@ -220,6 +247,8 @@ extern enum vm_guest_mode vm_mode_default; #endif +#define VM_SHAPE_DEFAULT VM_SHAPE(VM_MODE_DEFAULT) + #define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) #define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) @@ -248,6 +277,13 @@ static inline bool kvm_has_cap(long cap) #define __KVM_SYSCALL_ERROR(_name, _ret) \ "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) +/* + * Use the "inner", double-underscore macro when reporting errors from within + * other macros so that the name of ioctl() and not its literal numeric value + * is printed on error. The "outer" macro is strongly preferred when reporting + * errors "directly", i.e. without an additional layer of macros, as it reduces + * the probability of passing in the wrong string. + */ #define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret) #define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret) @@ -260,17 +296,13 @@ static inline bool kvm_has_cap(long cap) #define __kvm_ioctl(kvm_fd, cmd, arg) \ kvm_do_ioctl(kvm_fd, cmd, arg) - -#define _kvm_ioctl(kvm_fd, cmd, name, arg) \ +#define kvm_ioctl(kvm_fd, cmd, arg) \ ({ \ int ret = __kvm_ioctl(kvm_fd, cmd, arg); \ \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \ }) -#define kvm_ioctl(kvm_fd, cmd, arg) \ - _kvm_ioctl(kvm_fd, cmd, #cmd, arg) - static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } #define __vm_ioctl(vm, cmd, arg) \ @@ -279,17 +311,42 @@ static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } kvm_do_ioctl((vm)->fd, cmd, arg); \ }) -#define _vm_ioctl(vm, cmd, name, arg) \ +/* + * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if + * the ioctl() failed because KVM killed/bugged the VM. To detect a dead VM, + * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before + * selftests existed and (b) should never outright fail, i.e. is supposed to + * return 0 or 1. If KVM kills a VM, KVM returns -EIO for all ioctl()s for the + * VM and its vCPUs, including KVM_CHECK_EXTENSION. + */ +#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm) \ +do { \ + int __errno = errno; \ + \ + static_assert_is_vm(vm); \ + \ + if (cond) \ + break; \ + \ + if (errno == EIO && \ + __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) { \ + TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO"); \ + TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues"); \ + } \ + errno = __errno; \ + TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret)); \ +} while (0) + +#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm) \ + __TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm) + +#define vm_ioctl(vm, cmd, arg) \ ({ \ int ret = __vm_ioctl(vm, cmd, arg); \ \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ }) -#define vm_ioctl(vm, cmd, arg) \ - _vm_ioctl(vm, cmd, #cmd, arg) - - static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } #define __vcpu_ioctl(vcpu, cmd, arg) \ @@ -298,16 +355,13 @@ static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } kvm_do_ioctl((vcpu)->fd, cmd, arg); \ }) -#define _vcpu_ioctl(vcpu, cmd, name, arg) \ +#define vcpu_ioctl(vcpu, cmd, arg) \ ({ \ int ret = __vcpu_ioctl(vcpu, cmd, arg); \ \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \ }) -#define vcpu_ioctl(vcpu, cmd, arg) \ - _vcpu_ioctl(vcpu, cmd, #cmd, arg) - /* * Looks up and returns the value corresponding to the capability * (KVM_CAP_*) given by cap. @@ -316,7 +370,7 @@ static inline int vm_check_cap(struct kvm_vm *vm, long cap) { int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap); - TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret)); + TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm); return ret; } @@ -333,6 +387,54 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } +static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, + uint64_t size, uint64_t attributes) +{ + struct kvm_memory_attributes attr = { + .attributes = attributes, + .address = gpa, + .size = size, + .flags = 0, + }; + + /* + * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows + * need significant enhancements to support multiple attributes. + */ + TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, + "Update me to support multiple attributes!"); + + vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); +} + + +static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, 0); +} + +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, + bool punch_hole); + +static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, true); +} + +static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, false); +} + void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); const char *vm_guest_mode_string(uint32_t i); @@ -375,7 +477,7 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm) { int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); - TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd)); + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm); return fd; } @@ -431,14 +533,51 @@ static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) void vm_create_irqchip(struct kvm_vm *vm); +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + struct kvm_create_guest_memfd guest_memfd = { + .size = size, + .flags = flags, + }; + + return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); +} + +static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + int fd = __vm_create_guest_memfd(vm, size, flags); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd)); + return fd; +} + void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, uint64_t gpa, uint64_t size, void *hva); int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, uint64_t gpa, uint64_t size, void *hva); +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); + void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, uint64_t guest_paddr, uint32_t slot, uint64_t npages, uint32_t flags); +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); + +#ifndef vm_arch_has_protected_memory +static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) +{ + return false; +} +#endif void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); @@ -449,6 +588,9 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_mi vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type); vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type); @@ -461,6 +603,12 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); + +static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) +{ + return gpa & ~vm->gpa_tag_mask; +} + void vcpu_run(struct kvm_vcpu *vcpu); int _vcpu_run(struct kvm_vcpu *vcpu); @@ -587,7 +735,7 @@ static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) { int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL); - TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd)); + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm); return fd; } @@ -703,31 +851,54 @@ const char *exit_reason_str(unsigned int exit_reason); vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, uint32_t memslot); -vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot); +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected); vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); +static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot) +{ + /* + * By default, allocate memory as protected for VMs that support + * protected memory, as the majority of memory for such VMs is + * protected, i.e. using shared memory is effectively opt-in. + */ + return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, + vm_arch_has_protected_memory(vm)); +} + /* * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also * loads the test binary into guest memory and creates an IRQ chip (x86 only). * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to * calculate the amount of memory needed for per-vCPU data, e.g. stacks. */ -struct kvm_vm *____vm_create(enum vm_guest_mode mode); -struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, +struct kvm_vm *____vm_create(struct vm_shape shape); +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, uint64_t nr_extra_pages); static inline struct kvm_vm *vm_create_barebones(void) { - return ____vm_create(VM_MODE_DEFAULT); + return ____vm_create(VM_SHAPE_DEFAULT); +} + +static inline struct kvm_vm *vm_create_barebones_type(unsigned long type) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = type, + }; + + return ____vm_create(shape); } static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) { - return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0); + return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); } -struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, uint64_t extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]); @@ -735,17 +906,27 @@ static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, void *guest_code, struct kvm_vcpu *vcpus[]) { - return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0, + return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0, guest_code, vcpus); } + +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code); + /* * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages * additional pages of guest memory. Returns the VM and vCPU (via out param). */ -struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, - void *guest_code); +static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, + extra_mem_pages, guest_code); +} static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, void *guest_code) @@ -753,6 +934,13 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, return __vm_create_with_one_vcpu(vcpu, 0, guest_code); } +static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code); +} + struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); void kvm_pin_this_task_to_pcpu(uint32_t pcpu); @@ -776,10 +964,6 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) return n; } -struct kvm_userspace_memory_region * -kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, - uint64_t end); - #define sync_global_to_guest(vm, g) ({ \ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ memcpy(_p, &(g), sizeof(g)); \ @@ -932,4 +1116,6 @@ void kvm_selftest_arch_init(void); void kvm_arch_vm_post_create(struct kvm_vm *vm); +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); + #endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h new file mode 100644 index 0000000000000000000000000000000000000000..e43a57d99b56cc3f541d7718b868eb92b4a46e10 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h new file mode 100644 index 0000000000000000000000000000000000000000..e43a57d99b56cc3f541d7718b868eb92b4a46e10 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h index 12a9a4b9ceadc20d6421b9eafce2dc02e1bb002a..bc760761e1a320fff163a83e620874ed6be2daed 100644 --- a/tools/testing/selftests/kvm/include/sparsebit.h +++ b/tools/testing/selftests/kvm/include/sparsebit.h @@ -30,26 +30,26 @@ typedef uint64_t sparsebit_num_t; struct sparsebit *sparsebit_alloc(void); void sparsebit_free(struct sparsebit **sbitp); -void sparsebit_copy(struct sparsebit *dstp, struct sparsebit *src); +void sparsebit_copy(struct sparsebit *dstp, const struct sparsebit *src); -bool sparsebit_is_set(struct sparsebit *sbit, sparsebit_idx_t idx); -bool sparsebit_is_set_num(struct sparsebit *sbit, +bool sparsebit_is_set(const struct sparsebit *sbit, sparsebit_idx_t idx); +bool sparsebit_is_set_num(const struct sparsebit *sbit, sparsebit_idx_t idx, sparsebit_num_t num); -bool sparsebit_is_clear(struct sparsebit *sbit, sparsebit_idx_t idx); -bool sparsebit_is_clear_num(struct sparsebit *sbit, +bool sparsebit_is_clear(const struct sparsebit *sbit, sparsebit_idx_t idx); +bool sparsebit_is_clear_num(const struct sparsebit *sbit, sparsebit_idx_t idx, sparsebit_num_t num); -sparsebit_num_t sparsebit_num_set(struct sparsebit *sbit); -bool sparsebit_any_set(struct sparsebit *sbit); -bool sparsebit_any_clear(struct sparsebit *sbit); -bool sparsebit_all_set(struct sparsebit *sbit); -bool sparsebit_all_clear(struct sparsebit *sbit); -sparsebit_idx_t sparsebit_first_set(struct sparsebit *sbit); -sparsebit_idx_t sparsebit_first_clear(struct sparsebit *sbit); -sparsebit_idx_t sparsebit_next_set(struct sparsebit *sbit, sparsebit_idx_t prev); -sparsebit_idx_t sparsebit_next_clear(struct sparsebit *sbit, sparsebit_idx_t prev); -sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *sbit, +sparsebit_num_t sparsebit_num_set(const struct sparsebit *sbit); +bool sparsebit_any_set(const struct sparsebit *sbit); +bool sparsebit_any_clear(const struct sparsebit *sbit); +bool sparsebit_all_set(const struct sparsebit *sbit); +bool sparsebit_all_clear(const struct sparsebit *sbit); +sparsebit_idx_t sparsebit_first_set(const struct sparsebit *sbit); +sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *sbit); +sparsebit_idx_t sparsebit_next_set(const struct sparsebit *sbit, sparsebit_idx_t prev); +sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *sbit, sparsebit_idx_t prev); +sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *sbit, sparsebit_idx_t start, sparsebit_num_t num); -sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *sbit, +sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *sbit, sparsebit_idx_t start, sparsebit_num_t num); void sparsebit_set(struct sparsebit *sbitp, sparsebit_idx_t idx); @@ -62,9 +62,29 @@ void sparsebit_clear_num(struct sparsebit *sbitp, sparsebit_idx_t start, sparsebit_num_t num); void sparsebit_clear_all(struct sparsebit *sbitp); -void sparsebit_dump(FILE *stream, struct sparsebit *sbit, +void sparsebit_dump(FILE *stream, const struct sparsebit *sbit, unsigned int indent); -void sparsebit_validate_internal(struct sparsebit *sbit); +void sparsebit_validate_internal(const struct sparsebit *sbit); + +/* + * Iterate over an inclusive ranges within sparsebit @s. In each iteration, + * @range_begin and @range_end will take the beginning and end of the set + * range, which are of type sparsebit_idx_t. + * + * For example, if the range [3, 7] (inclusive) is set, within the + * iteration,@range_begin will take the value 3 and @range_end will take + * the value 7. + * + * Ensure that there is at least one bit set before using this macro with + * sparsebit_any_set(), because sparsebit_first_set() will abort if none + * are set. + */ +#define sparsebit_for_each_set_range(s, range_begin, range_end) \ + for (range_begin = sparsebit_first_set(s), \ + range_end = sparsebit_next_clear(s, range_begin) - 1; \ + range_begin && range_end; \ + range_begin = sparsebit_next_set(s, range_end), \ + range_end = sparsebit_next_clear(s, range_begin) - 1) #ifdef __cplusplus } diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 7e614adc6cf4778b69a7b8f94f6f08608f44baf5..7257f2243ab9f1533ed02fc10c125cadb0c63de7 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -142,6 +142,11 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; } +static inline bool backing_src_can_be_huge(enum vm_mem_backing_src_type t) +{ + return t != VM_MEM_SRC_ANONYMOUS && t != VM_MEM_SRC_SHMEM; +} + /* Aligns x up to the next multiple of size. Size must be a power of 2. */ static inline uint64_t align_up(uint64_t x, uint64_t size) { diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index ce33d306c2cba7d740697d9625d239be95891ee3..0fb472a5a058547c6ead78684eb1fa29899212cc 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -52,6 +52,17 @@ int ucall_nr_pages_required(uint64_t page_size); #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) #define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) +#define GUEST_SYNC1(arg0) ucall(UCALL_SYNC, 1, arg0) +#define GUEST_SYNC2(arg0, arg1) ucall(UCALL_SYNC, 2, arg0, arg1) +#define GUEST_SYNC3(arg0, arg1, arg2) \ + ucall(UCALL_SYNC, 3, arg0, arg1, arg2) +#define GUEST_SYNC4(arg0, arg1, arg2, arg3) \ + ucall(UCALL_SYNC, 4, arg0, arg1, arg2, arg3) +#define GUEST_SYNC5(arg0, arg1, arg2, arg3, arg4) \ + ucall(UCALL_SYNC, 5, arg0, arg1, arg2, arg3, arg4) +#define GUEST_SYNC6(arg0, arg1, arg2, arg3, arg4, arg5) \ + ucall(UCALL_SYNC, 6, arg0, arg1, arg2, arg3, arg4, arg5) + #define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args) #define GUEST_DONE() ucall(UCALL_DONE, 0) diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h new file mode 100644 index 0000000000000000000000000000000000000000..9f1725192aa224be9a5ae12c5141903fb1a76ac5 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +#include +#include + +struct kvm_vm_arch { + uint64_t c_bit; + uint64_t s_bit; + int sev_fd; + bool is_pt_protected; +}; + +static inline bool __vm_arch_has_protected_memory(struct kvm_vm_arch *arch) +{ + return arch->c_bit || arch->s_bit; +} + +#define vm_arch_has_protected_memory(vm) \ + __vm_arch_has_protected_memory(&(vm)->arch) + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 490a0a7efb3c4b7c7d389708a0d82d2127d44558..3417c6d6fc663293c2628410b52dd247a003aaaa 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -15,6 +15,7 @@ #include #include +#include #include #include "../kvm_util.h" @@ -273,6 +274,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7) #define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15) #define X86_PROPERTY_GUEST_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 16, 23) +#define X86_PROPERTY_SEV_C_BIT KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5) #define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) #define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31) @@ -1059,6 +1061,7 @@ do { \ } while (0) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +void kvm_init_vm_address_properties(struct kvm_vm *vm); bool vm_is_unrestricted_guest(struct kvm_vm *vm); struct ex_regs { @@ -1195,6 +1198,20 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); +static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa, + uint64_t size, uint64_t flags) +{ + return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0); +} + +static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size, + uint64_t flags) +{ + uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); + + GUEST_ASSERT(!ret); +} + void __vm_xsave_require_permission(uint64_t xfeature, const char *name); #define vm_xsave_require_permission(xfeature) \ diff --git a/tools/testing/selftests/kvm/include/x86_64/sev.h b/tools/testing/selftests/kvm/include/x86_64/sev.h new file mode 100644 index 0000000000000000000000000000000000000000..82c11c81a956323d54ea1b27d8b88dbc5eb6db6e --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/sev.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers used for SEV guests + * + */ +#ifndef SELFTEST_KVM_SEV_H +#define SELFTEST_KVM_SEV_H + +#include +#include + +#include "linux/psp-sev.h" + +#include "kvm_util.h" +#include "svm_util.h" +#include "processor.h" + +enum sev_guest_state { + SEV_GUEST_STATE_UNINITIALIZED = 0, + SEV_GUEST_STATE_LAUNCH_UPDATE, + SEV_GUEST_STATE_LAUNCH_SECRET, + SEV_GUEST_STATE_RUNNING, +}; + +#define SEV_POLICY_NO_DBG (1UL << 0) +#define SEV_POLICY_ES (1UL << 2) + +#define GHCB_MSR_TERM_REQ 0x100 + +void sev_vm_launch(struct kvm_vm *vm, uint32_t policy); +void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement); +void sev_vm_launch_finish(struct kvm_vm *vm); + +struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, + struct kvm_vcpu **cpu); +void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement); + +kvm_static_assert(SEV_RET_SUCCESS == 0); + +/* + * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long" + * instead of a proper struct. The size of the parameter is embedded in the + * ioctl number, i.e. is ABI and thus immutable. Hack around the mess by + * creating an overlay to pass in an "unsigned long" without a cast (casting + * will make the compiler unhappy due to dereferencing an aliased pointer). + */ +#define __vm_sev_ioctl(vm, cmd, arg) \ +({ \ + int r; \ + \ + union { \ + struct kvm_sev_cmd c; \ + unsigned long raw; \ + } sev_cmd = { .c = { \ + .id = (cmd), \ + .data = (uint64_t)(arg), \ + .sev_fd = (vm)->arch.sev_fd, \ + } }; \ + \ + r = __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_OP, &sev_cmd.raw); \ + r ?: sev_cmd.c.error; \ +}) + +#define vm_sev_ioctl(vm, cmd, arg) \ +({ \ + int ret = __vm_sev_ioctl(vm, cmd, arg); \ + \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ +}) + +void sev_vm_init(struct kvm_vm *vm); +void sev_es_vm_init(struct kvm_vm *vm); + +static inline void sev_register_encrypted_memory(struct kvm_vm *vm, + struct userspace_mem_region *region) +{ + struct kvm_enc_region range = { + .addr = region->region.userspace_addr, + .size = region->region.memory_size, + }; + + vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); +} + +static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, + uint64_t size) +{ + struct kvm_sev_launch_update_data update_data = { + .uaddr = (unsigned long)addr_gpa2hva(vm, gpa), + .len = size, + }; + + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data); +} + +#endif /* SELFTEST_KVM_SEV_H */ diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 69f26d80c8216ed15c63984794223346f7d307a2..e37dc9c21888f4bc4ed06bf3bacff89e28c68b5d 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -254,7 +254,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = __vm_create_with_vcpus(mode, nr_vcpus, guest_num_pages, + vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus, guest_num_pages, guest_code, test_args.vcpus); /* Align down GPA of the testing memslot */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 7a8af1821f5dae2993995c60e0ef08faa6431919..55b48f53394c2e82ec12a2f8cf55afbd3d634d33 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -209,7 +209,7 @@ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm) (1ULL << (vm->va_bits - 1)) >> vm->page_shift); } -struct kvm_vm *____vm_create(enum vm_guest_mode mode) +struct kvm_vm *____vm_create(struct vm_shape shape) { struct kvm_vm *vm; @@ -221,13 +221,13 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) vm->regions.hva_tree = RB_ROOT; hash_init(vm->regions.slot_hash); - vm->mode = mode; - vm->type = 0; + vm->mode = shape.mode; + vm->type = shape.type; - vm->pa_bits = vm_guest_mode_params[mode].pa_bits; - vm->va_bits = vm_guest_mode_params[mode].va_bits; - vm->page_size = vm_guest_mode_params[mode].page_size; - vm->page_shift = vm_guest_mode_params[mode].page_shift; + vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits; + vm->va_bits = vm_guest_mode_params[vm->mode].va_bits; + vm->page_size = vm_guest_mode_params[vm->mode].page_size; + vm->page_shift = vm_guest_mode_params[vm->mode].page_shift; /* Setup mode specific traits. */ switch (vm->mode) { @@ -262,10 +262,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) case VM_MODE_PXXV48_4K: #ifdef __x86_64__ kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits); + kvm_init_vm_address_properties(vm); /* * Ignore KVM support for 5-level paging (vm->va_bits == 57), * it doesn't take effect unless a CR4.LA57 is set, which it - * isn't for this VM_MODE. + * isn't for this mode (48-bit virtual address space). */ TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57, "Linear address width (%d bits) not supported", @@ -285,10 +286,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) vm->pgtable_levels = 5; break; default: - TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); + TEST_FAIL("Unknown guest mode: 0x%x", vm->mode); } #ifdef __aarch64__ + TEST_ASSERT(!vm->type, "ARM doesn't support test-provided types"); if (vm->pa_bits != 40) vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits); #endif @@ -347,19 +349,19 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, return vm_adjust_num_guest_pages(mode, nr_pages); } -struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, uint64_t nr_extra_pages) { - uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus, + uint64_t nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus, nr_extra_pages); struct userspace_mem_region *slot0; struct kvm_vm *vm; int i; - pr_debug("%s: mode='%s' pages='%ld'\n", __func__, - vm_guest_mode_string(mode), nr_pages); + pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__, + vm_guest_mode_string(shape.mode), shape.type, nr_pages); - vm = ____vm_create(mode); + vm = ____vm_create(shape); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0); for (i = 0; i < NR_MEM_REGIONS; i++) @@ -400,7 +402,7 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, * extra_mem_pages is only used to calculate the maximum page table size, * no real memory allocation for non-slot0 memory in this function. */ -struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, uint64_t extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]) { @@ -409,7 +411,7 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array"); - vm = __vm_create(mode, nr_vcpus, extra_mem_pages); + vm = __vm_create(shape, nr_vcpus, extra_mem_pages); for (i = 0; i < nr_vcpus; ++i) vcpus[i] = vm_vcpu_add(vm, i, guest_code); @@ -417,15 +419,15 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus return vm; } -struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, - void *guest_code) +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) { struct kvm_vcpu *vcpus[1]; struct kvm_vm *vm; - vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages, - guest_code, vcpus); + vm = __vm_create_with_vcpus(shape, 1, extra_mem_pages, guest_code, vcpus); *vcpu = vcpus[0]; return vm; @@ -453,8 +455,9 @@ void kvm_vm_restart(struct kvm_vm *vmp) vm_create_irqchip(vmp); hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { - int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" " guest_phys_addr: 0x%llx size: 0x%llx", @@ -590,35 +593,6 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) return NULL; } -/* - * KVM Userspace Memory Region Find - * - * Input Args: - * vm - Virtual Machine - * start - Starting VM physical address - * end - Ending VM physical address, inclusive. - * - * Output Args: None - * - * Return: - * Pointer to overlapping region, NULL if no such region. - * - * Public interface to userspace_mem_region_find. Allows tests to look up - * the memslot datastructure for a given range of guest physical memory. - */ -struct kvm_userspace_memory_region * -kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, - uint64_t end) -{ - struct userspace_mem_region *region; - - region = userspace_mem_region_find(vm, start, end); - if (!region) - return NULL; - - return ®ion->region; -} - __weak void vcpu_arch_free(struct kvm_vcpu *vcpu) { @@ -686,9 +660,10 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, } region->region.memory_size = 0; - vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); sparsebit_free(®ion->unused_phy_pages); + sparsebit_free(®ion->protected_phy_pages); ret = munmap(region->mmap_start, region->mmap_size); TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); if (region->fd >= 0) { @@ -697,6 +672,8 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); close(region->fd); } + if (region->region.guest_memfd >= 0) + close(region->region.guest_memfd); free(region); } @@ -898,36 +875,44 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, errno, strerror(errno)); } -/* - * VM Userspace Memory Region Add - * - * Input Args: - * vm - Virtual Machine - * src_type - Storage source for this region. - * NULL to use anonymous memory. - * guest_paddr - Starting guest physical address - * slot - KVM region slot - * npages - Number of physical pages - * flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES) - * - * Output Args: None - * - * Return: None - * - * Allocates a memory area of the number of pages specified by npages - * and maps it to the VM specified by vm, at a starting physical address - * given by guest_paddr. The region is created with a KVM region slot - * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM. The - * region is created with the flags given by flags. - */ -void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags) +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset) +{ + struct kvm_userspace_memory_region2 region = { + .slot = slot, + .flags = flags, + .guest_phys_addr = gpa, + .memory_size = size, + .userspace_addr = (uintptr_t)hva, + .guest_memfd = guest_memfd, + .guest_memfd_offset = guest_memfd_offset, + }; + + return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, ®ion); +} + +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset) +{ + int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva, + guest_memfd, guest_memfd_offset); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)", + errno, strerror(errno)); +} + + +/* FIXME: This thing needs to be ripped apart and rewritten. */ +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags, int guest_memfd, uint64_t guest_memfd_offset) { int ret; struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); + size_t mem_size = npages * vm->page_size; size_t alignment; TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages, @@ -980,7 +965,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* Allocate and initialize new mem region structure. */ region = calloc(1, sizeof(*region)); TEST_ASSERT(region != NULL, "Insufficient Memory"); - region->mmap_size = npages * vm->page_size; + region->mmap_size = mem_size; #ifdef __s390x__ /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ @@ -1027,15 +1012,41 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) { - ret = madvise(region->host_mem, npages * vm->page_size, + ret = madvise(region->host_mem, mem_size, src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE); TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s", - region->host_mem, npages * vm->page_size, + region->host_mem, mem_size, vm_mem_backing_src_alias(src_type)->name); } region->backing_src_type = src_type; + + if (flags & KVM_MEM_GUEST_MEMFD) { + if (guest_memfd < 0) { + uint32_t guest_memfd_flags = 0; + TEST_ASSERT(!guest_memfd_offset, + "Offset must be zero when creating new guest_memfd"); + guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); + } else { + /* + * Install a unique fd for each memslot so that the fd + * can be closed when the region is deleted without + * needing to track if the fd is owned by the framework + * or by the caller. + */ + guest_memfd = dup(guest_memfd); + TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("dup()", guest_memfd)); + } + + region->region.guest_memfd = guest_memfd; + region->region.guest_memfd_offset = guest_memfd_offset; + } else { + region->region.guest_memfd = -1; + } + region->unused_phy_pages = sparsebit_alloc(); + if (vm_arch_has_protected_memory(vm)) + region->protected_phy_pages = sparsebit_alloc(); sparsebit_set_num(region->unused_phy_pages, guest_paddr >> vm->page_shift, npages); region->region.slot = slot; @@ -1043,13 +1054,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->region.guest_phys_addr = guest_paddr; region->region.memory_size = npages * vm->page_size; region->region.userspace_addr = (uintptr_t) region->host_mem; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" - " guest_phys_addr: 0x%lx size: 0x%lx", + " guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d\n", ret, errno, slot, flags, - guest_paddr, (uint64_t) region->region.memory_size); + guest_paddr, (uint64_t) region->region.memory_size, + region->region.guest_memfd); /* Add to quick lookup data structures */ vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); @@ -1070,6 +1082,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, } } +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, + uint64_t npages, uint32_t flags) +{ + vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0); +} + /* * Memslot to region * @@ -1126,9 +1146,9 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) region->region.flags = flags; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i slot: %u flags: 0x%x", ret, errno, slot, flags); } @@ -1156,9 +1176,9 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) region->region.guest_phys_addr = new_gpa; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); - TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n" + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed\n" "ret: %i errno: %i slot: %u new_gpa: 0x%lx", ret, errno, slot, new_gpa); } @@ -1181,6 +1201,34 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, + bool punch_hole) +{ + const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0); + struct userspace_mem_region *region; + uint64_t end = base + size; + uint64_t gpa, len; + off_t fd_offset; + int ret; + + for (gpa = base; gpa < end; gpa += len) { + uint64_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD, + "Private memory region not found for GPA 0x%lx", gpa); + + offset = gpa - region->region.guest_phys_addr; + fd_offset = region->region.guest_memfd_offset + offset; + len = min_t(uint64_t, end - gpa, region->region.memory_size - offset); + + ret = fallocate(region->region.guest_memfd, mode, fd_offset, len); + TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx\n", + punch_hole ? "punch hole" : "allocate", gpa, len, + region->region.guest_memfd, mode, fd_offset); + } +} + /* Returns the size of a vCPU's kvm_run structure. */ static int vcpu_mmap_sz(void) { @@ -1227,7 +1275,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) vcpu->vm = vm; vcpu->id = vcpu_id; vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id); - TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd)); + TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm); TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size " "smaller than expected, vcpu_mmap_sz: %i expected_min: %zi", @@ -1329,15 +1377,17 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, return pgidx_start * vm->page_size; } -vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type) +static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type, + bool protected) { uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm); - vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, - KVM_UTIL_MIN_PFN * vm->page_size, - vm->memslots[type]); + vm_paddr_t paddr = __vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + vm->memslots[type], protected); /* * Find an unused range of virtual page addresses of at least @@ -1357,6 +1407,20 @@ vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, return vaddr_start; } +vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type) +{ + return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, + vm_arch_has_protected_memory(vm)); +} + +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type) +{ + return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, false); +} + /* * VM Virtual Address Allocate * @@ -1479,6 +1543,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; + gpa = vm_untag_gpa(vm, gpa); + region = userspace_mem_region_find(vm, gpa, gpa); if (!region) { TEST_FAIL("No vm physical memory at 0x%lx", gpa); @@ -1825,6 +1891,10 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) region->host_mem); fprintf(stream, "%*sunused_phy_pages: ", indent + 2, ""); sparsebit_dump(stream, region->unused_phy_pages, 0); + if (region->protected_phy_pages) { + fprintf(stream, "%*sprotected_phy_pages: ", indent + 2, ""); + sparsebit_dump(stream, region->protected_phy_pages, 0); + } } fprintf(stream, "%*sMapped Virtual Pages:\n", indent, ""); sparsebit_dump(stream, vm->vpages_mapped, indent + 2); @@ -1926,6 +1996,7 @@ const char *exit_reason_str(unsigned int exit_reason) * num - number of pages * paddr_min - Physical address minimum * memslot - Memory region to allocate page from + * protected - True if the pages will be used as protected/private memory * * Output Args: None * @@ -1937,8 +2008,9 @@ const char *exit_reason_str(unsigned int exit_reason) * and their base address is returned. A TEST_ASSERT failure occurs if * not enough pages are available at or above paddr_min. */ -vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot) +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected) { struct userspace_mem_region *region; sparsebit_idx_t pg, base; @@ -1951,8 +2023,10 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, paddr_min, vm->page_size); region = memslot2region(vm, memslot); - base = pg = paddr_min >> vm->page_shift; + TEST_ASSERT(!protected || region->protected_phy_pages, + "Region doesn't support protected memory"); + base = pg = paddr_min >> vm->page_shift; do { for (; pg < base + num; ++pg) { if (!sparsebit_is_set(region->unused_phy_pages, pg)) { @@ -1971,8 +2045,11 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, abort(); } - for (pg = base; pg < base + num; ++pg) + for (pg = base; pg < base + num; ++pg) { sparsebit_clear(region->unused_phy_pages, pg); + if (protected) + sparsebit_set(region->protected_phy_pages, pg); + } return base * vm->page_size; } @@ -2176,3 +2253,18 @@ void __attribute((constructor)) kvm_selftest_init(void) kvm_selftest_arch_init(); } + +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr) +{ + sparsebit_idx_t pg = 0; + struct userspace_mem_region *region; + + if (!vm_arch_has_protected_memory(vm)) + return false; + + region = userspace_mem_region_find(vm, paddr, paddr); + TEST_ASSERT(region, "No vm physical memory at 0x%lx", paddr); + + pg = paddr >> vm->page_shift; + return sparsebit_is_set(region->protected_phy_pages, pg); +} diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index df457452d1464f3fa659d38202e8d8e7dc89de0b..d05487e5a371df1d17c96d4fbec1b1f6b2e60c0f 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -168,7 +168,8 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, * The memory is also added to memslot 0, but that's a benign side * effect as KVM allows aliasing HVAs in meslots. */ - vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages, + vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus, + slot0_pages + guest_num_pages, memstress_guest_code, vcpus); args->vm = vm; diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c index 88cb6b84e6f31009e8fc61e2ae0b69b9728e0ef1..cfed9d26cc71b06a9c4e52c89a52b079944d3a49 100644 --- a/tools/testing/selftests/kvm/lib/sparsebit.c +++ b/tools/testing/selftests/kvm/lib/sparsebit.c @@ -202,7 +202,7 @@ static sparsebit_num_t node_num_set(struct node *nodep) /* Returns a pointer to the node that describes the * lowest bit index. */ -static struct node *node_first(struct sparsebit *s) +static struct node *node_first(const struct sparsebit *s) { struct node *nodep; @@ -216,7 +216,7 @@ static struct node *node_first(struct sparsebit *s) * lowest bit index > the index of the node pointed to by np. * Returns NULL if no node with a higher index exists. */ -static struct node *node_next(struct sparsebit *s, struct node *np) +static struct node *node_next(const struct sparsebit *s, struct node *np) { struct node *nodep = np; @@ -244,7 +244,7 @@ static struct node *node_next(struct sparsebit *s, struct node *np) * highest index < the index of the node pointed to by np. * Returns NULL if no node with a lower index exists. */ -static struct node *node_prev(struct sparsebit *s, struct node *np) +static struct node *node_prev(const struct sparsebit *s, struct node *np) { struct node *nodep = np; @@ -273,7 +273,7 @@ static struct node *node_prev(struct sparsebit *s, struct node *np) * subtree and duplicates the bit settings to the newly allocated nodes. * Returns the newly allocated copy of subtree. */ -static struct node *node_copy_subtree(struct node *subtree) +static struct node *node_copy_subtree(const struct node *subtree) { struct node *root; @@ -307,7 +307,7 @@ static struct node *node_copy_subtree(struct node *subtree) * index is within the bits described by the mask bits or the number of * contiguous bits set after the mask. Returns NULL if there is no such node. */ -static struct node *node_find(struct sparsebit *s, sparsebit_idx_t idx) +static struct node *node_find(const struct sparsebit *s, sparsebit_idx_t idx) { struct node *nodep; @@ -393,7 +393,7 @@ static struct node *node_add(struct sparsebit *s, sparsebit_idx_t idx) } /* Returns whether all the bits in the sparsebit array are set. */ -bool sparsebit_all_set(struct sparsebit *s) +bool sparsebit_all_set(const struct sparsebit *s) { /* * If any nodes there must be at least one bit set. Only case @@ -775,7 +775,7 @@ static void node_reduce(struct sparsebit *s, struct node *nodep) /* Returns whether the bit at the index given by idx, within the * sparsebit array is set or not. */ -bool sparsebit_is_set(struct sparsebit *s, sparsebit_idx_t idx) +bool sparsebit_is_set(const struct sparsebit *s, sparsebit_idx_t idx) { struct node *nodep; @@ -921,7 +921,7 @@ static inline sparsebit_idx_t node_first_clear(struct node *nodep, int start) * used by test cases after they detect an unexpected condition, as a means * to capture diagnostic information. */ -static void sparsebit_dump_internal(FILE *stream, struct sparsebit *s, +static void sparsebit_dump_internal(FILE *stream, const struct sparsebit *s, unsigned int indent) { /* Dump the contents of s */ @@ -969,7 +969,7 @@ void sparsebit_free(struct sparsebit **sbitp) * sparsebit_alloc(). It can though already have bits set, which * if different from src will be cleared. */ -void sparsebit_copy(struct sparsebit *d, struct sparsebit *s) +void sparsebit_copy(struct sparsebit *d, const struct sparsebit *s) { /* First clear any bits already set in the destination */ sparsebit_clear_all(d); @@ -981,7 +981,7 @@ void sparsebit_copy(struct sparsebit *d, struct sparsebit *s) } /* Returns whether num consecutive bits starting at idx are all set. */ -bool sparsebit_is_set_num(struct sparsebit *s, +bool sparsebit_is_set_num(const struct sparsebit *s, sparsebit_idx_t idx, sparsebit_num_t num) { sparsebit_idx_t next_cleared; @@ -1005,14 +1005,14 @@ bool sparsebit_is_set_num(struct sparsebit *s, } /* Returns whether the bit at the index given by idx. */ -bool sparsebit_is_clear(struct sparsebit *s, +bool sparsebit_is_clear(const struct sparsebit *s, sparsebit_idx_t idx) { return !sparsebit_is_set(s, idx); } /* Returns whether num consecutive bits starting at idx are all cleared. */ -bool sparsebit_is_clear_num(struct sparsebit *s, +bool sparsebit_is_clear_num(const struct sparsebit *s, sparsebit_idx_t idx, sparsebit_num_t num) { sparsebit_idx_t next_set; @@ -1041,13 +1041,13 @@ bool sparsebit_is_clear_num(struct sparsebit *s, * value. Use sparsebit_any_set(), instead of sparsebit_num_set() > 0, * to determine if the sparsebit array has any bits set. */ -sparsebit_num_t sparsebit_num_set(struct sparsebit *s) +sparsebit_num_t sparsebit_num_set(const struct sparsebit *s) { return s->num_set; } /* Returns whether any bit is set in the sparsebit array. */ -bool sparsebit_any_set(struct sparsebit *s) +bool sparsebit_any_set(const struct sparsebit *s) { /* * Nodes only describe set bits. If any nodes then there @@ -1070,20 +1070,20 @@ bool sparsebit_any_set(struct sparsebit *s) } /* Returns whether all the bits in the sparsebit array are cleared. */ -bool sparsebit_all_clear(struct sparsebit *s) +bool sparsebit_all_clear(const struct sparsebit *s) { return !sparsebit_any_set(s); } /* Returns whether all the bits in the sparsebit array are set. */ -bool sparsebit_any_clear(struct sparsebit *s) +bool sparsebit_any_clear(const struct sparsebit *s) { return !sparsebit_all_set(s); } /* Returns the index of the first set bit. Abort if no bits are set. */ -sparsebit_idx_t sparsebit_first_set(struct sparsebit *s) +sparsebit_idx_t sparsebit_first_set(const struct sparsebit *s) { struct node *nodep; @@ -1097,7 +1097,7 @@ sparsebit_idx_t sparsebit_first_set(struct sparsebit *s) /* Returns the index of the first cleared bit. Abort if * no bits are cleared. */ -sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s) +sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *s) { struct node *nodep1, *nodep2; @@ -1151,7 +1151,7 @@ sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s) /* Returns index of next bit set within s after the index given by prev. * Returns 0 if there are no bits after prev that are set. */ -sparsebit_idx_t sparsebit_next_set(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_set(const struct sparsebit *s, sparsebit_idx_t prev) { sparsebit_idx_t lowest_possible = prev + 1; @@ -1244,7 +1244,7 @@ sparsebit_idx_t sparsebit_next_set(struct sparsebit *s, /* Returns index of next bit cleared within s after the index given by prev. * Returns 0 if there are no bits after prev that are cleared. */ -sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *s, sparsebit_idx_t prev) { sparsebit_idx_t lowest_possible = prev + 1; @@ -1300,7 +1300,7 @@ sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s, * and returns the index of the first sequence of num consecutively set * bits. Returns a value of 0 of no such sequence exists. */ -sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *s, sparsebit_idx_t start, sparsebit_num_t num) { sparsebit_idx_t idx; @@ -1335,7 +1335,7 @@ sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s, * and returns the index of the first sequence of num consecutively cleared * bits. Returns a value of 0 of no such sequence exists. */ -sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *s, +sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *s, sparsebit_idx_t start, sparsebit_num_t num) { sparsebit_idx_t idx; @@ -1583,7 +1583,7 @@ static size_t display_range(FILE *stream, sparsebit_idx_t low, * contiguous bits. This is done because '-' is used to specify command-line * options, and sometimes ranges are specified as command-line arguments. */ -void sparsebit_dump(FILE *stream, struct sparsebit *s, +void sparsebit_dump(FILE *stream, const struct sparsebit *s, unsigned int indent) { size_t current_line_len = 0; @@ -1681,7 +1681,7 @@ void sparsebit_dump(FILE *stream, struct sparsebit *s, * s. On error, diagnostic information is printed to stderr and * abort is called. */ -void sparsebit_validate_internal(struct sparsebit *s) +void sparsebit_validate_internal(const struct sparsebit *s) { bool error_detected = false; struct node *nodep, *prev = NULL; diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index 816a3fa109bfb6b608eadeda9f0827687ebbe1b5..f5af65a41c296e77f1502f32a8813fcf77dbdf20 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -29,7 +29,8 @@ void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) vm_vaddr_t vaddr; int i; - vaddr = __vm_vaddr_alloc(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, MEM_REGION_DATA); + vaddr = vm_vaddr_alloc_shared(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, + MEM_REGION_DATA); hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr); memset(hdr, 0, sizeof(*hdr)); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 5a035bc2b9c1c0829ee23696b6d22b194565ee2a..b6162b5ca1152ac5cca0a6b53eb7ae18a65394d1 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -9,6 +9,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "sev.h" #ifndef NUM_INTERRUPTS #define NUM_INTERRUPTS 256 @@ -157,6 +158,8 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, { uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level); + paddr = vm_untag_gpa(vm, paddr); + if (!(*pte & PTE_PRESENT_MASK)) { *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; if (current_level == target_level) @@ -200,6 +203,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) "Physical address beyond maximum supported,\n" " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", paddr, vm->max_gfn, vm->page_size); + TEST_ASSERT(vm_untag_gpa(vm, paddr) == paddr, + "Unexpected bits in paddr: %lx", paddr); /* * Allocate upper level page tables, if not already present. Return @@ -222,6 +227,15 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); + + /* + * Neither SEV nor TDX supports shared page tables, so only the final + * leaf PTE needs manually set the C/S-bit. + */ + if (vm_is_gpa_protected(vm, paddr)) + *pte |= vm->arch.c_bit; + else + *pte |= vm->arch.s_bit; } void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) @@ -265,6 +279,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, { uint64_t *pml4e, *pdpe, *pde; + TEST_ASSERT(!vm->arch.is_pt_protected, + "Walking page tables of protected guests is impossible"); + TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM, "Invalid PG_LEVEL_* '%d'", *level); @@ -496,7 +513,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) * No need for a hugepage mask on the PTE, x86-64 requires the "unused" * address bits to be zero. */ - return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level)); + return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level)); } static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) @@ -560,6 +577,12 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm) vm_create_irqchip(vm); sync_global_to_guest(vm, host_cpu_is_intel); sync_global_to_guest(vm, host_cpu_is_amd); + + if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) { + struct kvm_sev_init init = { 0 }; + + vm_sev_ioctl(vm, KVM_SEV_INIT2, &init); + } } struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, @@ -1041,6 +1064,17 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) } } +void kvm_init_vm_address_properties(struct kvm_vm *vm) +{ + if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) { + vm->arch.sev_fd = open_sev_dev_path_or_exit(); + vm->arch.c_bit = BIT_ULL(this_cpu_property(X86_PROPERTY_SEV_C_BIT)); + vm->gpa_tag_mask = vm->arch.c_bit; + } else { + vm->arch.sev_fd = -1; + } +} + static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, int dpl, unsigned short selector) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86_64/sev.c new file mode 100644 index 0000000000000000000000000000000000000000..d482029b60040067cdbe489022f789a560e554dd --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/sev.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include +#include + +#include "sev.h" + +/* + * sparsebit_next_clear() can return 0 if [x, 2**64-1] are all set, and the + * -1 would then cause an underflow back to 2**64 - 1. This is expected and + * correct. + * + * If the last range in the sparsebit is [x, y] and we try to iterate, + * sparsebit_next_set() will return 0, and sparsebit_next_clear() will try + * and find the first range, but that's correct because the condition + * expression would cause us to quit the loop. + */ +static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region) +{ + const struct sparsebit *protected_phy_pages = region->protected_phy_pages; + const vm_paddr_t gpa_base = region->region.guest_phys_addr; + const sparsebit_idx_t lowest_page_in_region = gpa_base >> vm->page_shift; + sparsebit_idx_t i, j; + + if (!sparsebit_any_set(protected_phy_pages)) + return; + + sev_register_encrypted_memory(vm, region); + + sparsebit_for_each_set_range(protected_phy_pages, i, j) { + const uint64_t size = (j - i + 1) * vm->page_size; + const uint64_t offset = (i - lowest_page_in_region) * vm->page_size; + + sev_launch_update_data(vm, gpa_base + offset, size); + } +} + +void sev_vm_init(struct kvm_vm *vm) +{ + if (vm->type == KVM_X86_DEFAULT_VM) { + assert(vm->arch.sev_fd == -1); + vm->arch.sev_fd = open_sev_dev_path_or_exit(); + vm_sev_ioctl(vm, KVM_SEV_INIT, NULL); + } else { + struct kvm_sev_init init = { 0 }; + assert(vm->type == KVM_X86_SEV_VM); + vm_sev_ioctl(vm, KVM_SEV_INIT2, &init); + } +} + +void sev_es_vm_init(struct kvm_vm *vm) +{ + if (vm->type == KVM_X86_DEFAULT_VM) { + assert(vm->arch.sev_fd == -1); + vm->arch.sev_fd = open_sev_dev_path_or_exit(); + vm_sev_ioctl(vm, KVM_SEV_ES_INIT, NULL); + } else { + struct kvm_sev_init init = { 0 }; + assert(vm->type == KVM_X86_SEV_ES_VM); + vm_sev_ioctl(vm, KVM_SEV_INIT2, &init); + } +} + +void sev_vm_launch(struct kvm_vm *vm, uint32_t policy) +{ + struct kvm_sev_launch_start launch_start = { + .policy = policy, + }; + struct userspace_mem_region *region; + struct kvm_sev_guest_status status; + int ctr; + + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_START, &launch_start); + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); + + TEST_ASSERT_EQ(status.policy, policy); + TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_LAUNCH_UPDATE); + + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) + encrypt_region(vm, region); + + if (policy & SEV_POLICY_ES) + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + + vm->arch.is_pt_protected = true; +} + +void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement) +{ + struct kvm_sev_launch_measure launch_measure; + struct kvm_sev_guest_status guest_status; + + launch_measure.len = 256; + launch_measure.uaddr = (__u64)measurement; + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_MEASURE, &launch_measure); + + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &guest_status); + TEST_ASSERT_EQ(guest_status.state, SEV_GUEST_STATE_LAUNCH_SECRET); +} + +void sev_vm_launch_finish(struct kvm_vm *vm) +{ + struct kvm_sev_guest_status status; + + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); + TEST_ASSERT(status.state == SEV_GUEST_STATE_LAUNCH_UPDATE || + status.state == SEV_GUEST_STATE_LAUNCH_SECRET, + "Unexpected guest state: %d", status.state); + + vm_sev_ioctl(vm, KVM_SEV_LAUNCH_FINISH, NULL); + + vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status); + TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING); +} + +struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, + struct kvm_vcpu **cpu) +{ + struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = type, + }; + struct kvm_vm *vm; + struct kvm_vcpu *cpus[1]; + + vm = __vm_create_with_vcpus(shape, 1, 0, guest_code, cpus); + *cpu = cpus[0]; + + return vm; +} + +void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement) +{ + sev_vm_launch(vm, policy); + + if (!measurement) + measurement = alloca(256); + + sev_vm_launch_measure(vm, measurement); + + sev_vm_launch_finish(vm); +} diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index b32960189f5f18eb688ae5a9066ed6764efdabd1..4e2b0f27a4cef09427df551c001b69f0ee66d001 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -326,6 +326,57 @@ static void test_zero_memory_regions(void) } #endif /* __x86_64__ */ +static void test_invalid_memory_region_flags(void) +{ + uint32_t supported_flags = KVM_MEM_LOG_DIRTY_PAGES; + const uint32_t v2_only_flags = KVM_MEM_GUEST_MEMFD; + struct kvm_vm *vm; + int r, i; + +#ifdef __x86_64__ + supported_flags |= KVM_MEM_READONLY; + + if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)) + vm = vm_create_barebones_type(KVM_X86_SW_PROTECTED_VM); + else +#endif + vm = vm_create_barebones(); + + if (kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES) & KVM_MEMORY_ATTRIBUTE_PRIVATE) + supported_flags |= KVM_MEM_GUEST_MEMFD; + + for (i = 0; i < 32; i++) { + if ((supported_flags & BIT(i)) && !(v2_only_flags & BIT(i))) + continue; + + r = __vm_set_user_memory_region(vm, 0, BIT(i), + 0, MEM_REGION_SIZE, NULL); + + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION should have failed on v2 only flag 0x%lx", BIT(i)); + + if (supported_flags & BIT(i)) + continue; + + r = __vm_set_user_memory_region2(vm, 0, BIT(i), + 0, MEM_REGION_SIZE, NULL, 0, 0); + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION2 should have failed on unsupported flag 0x%lx", BIT(i)); + } + + if (supported_flags & KVM_MEM_GUEST_MEMFD) { + int guest_memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0); + + r = __vm_set_user_memory_region2(vm, 0, + KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD, + 0, MEM_REGION_SIZE, NULL, guest_memfd, 0); + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported"); + + close(guest_memfd); + } +} + /* * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any * tentative to add further slots should fail. @@ -385,13 +436,105 @@ static void test_add_max_memory_regions(void) kvm_vm_free(vm); } + +#ifdef __x86_64__ +static void test_invalid_guest_memfd(struct kvm_vm *vm, int memfd, + size_t offset, const char *msg) +{ + int r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE, + 0, memfd, offset); + TEST_ASSERT(r == -1 && errno == EINVAL, "%s", msg); +} + +static void test_add_private_memory_region(void) +{ + struct kvm_vm *vm, *vm2; + int memfd, i; + + pr_info("Testing ADD of KVM_MEM_GUEST_MEMFD memory regions\n"); + + vm = vm_create_barebones_type(KVM_X86_SW_PROTECTED_VM); + + test_invalid_guest_memfd(vm, vm->kvm_fd, 0, "KVM fd should fail"); + test_invalid_guest_memfd(vm, vm->fd, 0, "VM's fd should fail"); + + memfd = kvm_memfd_alloc(MEM_REGION_SIZE, false); + test_invalid_guest_memfd(vm, memfd, 0, "Regular memfd() should fail"); + close(memfd); + + vm2 = vm_create_barebones_type(KVM_X86_SW_PROTECTED_VM); + memfd = vm_create_guest_memfd(vm2, MEM_REGION_SIZE, 0); + test_invalid_guest_memfd(vm, memfd, 0, "Other VM's guest_memfd() should fail"); + + vm_set_user_memory_region2(vm2, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0); + close(memfd); + kvm_vm_free(vm2); + + memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0); + for (i = 1; i < PAGE_SIZE; i++) + test_invalid_guest_memfd(vm, memfd, i, "Unaligned offset should fail"); + + vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0); + close(memfd); + + kvm_vm_free(vm); +} + +static void test_add_overlapping_private_memory_regions(void) +{ + struct kvm_vm *vm; + int memfd; + int r; + + pr_info("Testing ADD of overlapping KVM_MEM_GUEST_MEMFD memory regions\n"); + + vm = vm_create_barebones_type(KVM_X86_SW_PROTECTED_VM); + + memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE * 4, 0); + + vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE * 2, 0, memfd, 0); + + vm_set_user_memory_region2(vm, MEM_REGION_SLOT + 1, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA * 2, MEM_REGION_SIZE * 2, + 0, memfd, MEM_REGION_SIZE * 2); + + /* + * Delete the first memslot, and then attempt to recreate it except + * with a "bad" offset that results in overlap in the guest_memfd(). + */ + vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, 0, NULL, -1, 0); + + /* Overlap the front half of the other slot. */ + r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA * 2 - MEM_REGION_SIZE, + MEM_REGION_SIZE * 2, + 0, memfd, 0); + TEST_ASSERT(r == -1 && errno == EEXIST, "%s", + "Overlapping guest_memfd() bindings should fail with EEXIST"); + + /* And now the back half of the other slot. */ + r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA * 2 + MEM_REGION_SIZE, + MEM_REGION_SIZE * 2, + 0, memfd, 0); + TEST_ASSERT(r == -1 && errno == EEXIST, "%s", + "Overlapping guest_memfd() bindings should fail with EEXIST"); + + close(memfd); + kvm_vm_free(vm); +} +#endif + int main(int argc, char *argv[]) { #ifdef __x86_64__ int i, loops; -#endif -#ifdef __x86_64__ /* * FIXME: the zero-memslot test fails on aarch64 and s390x because * KVM_RUN fails with ENOEXEC or EFAULT. @@ -399,9 +542,19 @@ int main(int argc, char *argv[]) test_zero_memory_regions(); #endif + test_invalid_memory_region_flags(); + test_add_max_memory_regions(); #ifdef __x86_64__ + if (kvm_has_cap(KVM_CAP_GUEST_MEMFD) && + (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))) { + test_add_private_memory_region(); + test_add_overlapping_private_memory_regions(); + } else { + pr_info("Skipping tests for KVM_MEM_GUEST_MEMFD memory regions\n"); + } + if (argc > 1) loops = atoi_positive("Number of iterations", argv[1]); else diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c new file mode 100644 index 0000000000000000000000000000000000000000..39c994bff1a78c064311b843e3ffd3089ffee073 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022, Google LLC. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include +#include +#include + +#define BASE_DATA_SLOT 10 +#define BASE_DATA_GPA ((uint64_t)(1ull << 32)) +#define PER_CPU_DATA_SIZE ((uint64_t)(SZ_2M + PAGE_SIZE)) + +/* Horrific macro so that the line info is captured accurately :-( */ +#define memcmp_g(gpa, pattern, size) \ +do { \ + uint8_t *mem = (uint8_t *)gpa; \ + size_t i; \ + \ + for (i = 0; i < size; i++) \ + __GUEST_ASSERT(mem[i] == pattern, \ + "Guest expected 0x%x at offset %lu (gpa 0x%llx), got 0x%x", \ + pattern, i, gpa + i, mem[i]); \ +} while (0) + +static void memcmp_h(uint8_t *mem, uint64_t gpa, uint8_t pattern, size_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + TEST_ASSERT(mem[i] == pattern, + "Host expected 0x%x at gpa 0x%lx, got 0x%x", + pattern, gpa + i, mem[i]); +} + +/* + * Run memory conversion tests with explicit conversion: + * Execute KVM hypercall to map/unmap gpa range which will cause userspace exit + * to back/unback private memory. Subsequent accesses by guest to the gpa range + * will not cause exit to userspace. + * + * Test memory conversion scenarios with following steps: + * 1) Access private memory using private access and verify that memory contents + * are not visible to userspace. + * 2) Convert memory to shared using explicit conversions and ensure that + * userspace is able to access the shared regions. + * 3) Convert memory back to private using explicit conversions and ensure that + * userspace is again not able to access converted private regions. + */ + +#define GUEST_STAGE(o, s) { .offset = o, .size = s } + +enum ucall_syncs { + SYNC_SHARED, + SYNC_PRIVATE, +}; + +static void guest_sync_shared(uint64_t gpa, uint64_t size, + uint8_t current_pattern, uint8_t new_pattern) +{ + GUEST_SYNC5(SYNC_SHARED, gpa, size, current_pattern, new_pattern); +} + +static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern) +{ + GUEST_SYNC4(SYNC_PRIVATE, gpa, size, pattern); +} + +/* Arbitrary values, KVM doesn't care about the attribute flags. */ +#define MAP_GPA_SET_ATTRIBUTES BIT(0) +#define MAP_GPA_SHARED BIT(1) +#define MAP_GPA_DO_FALLOCATE BIT(2) + +static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared, + bool do_fallocate) +{ + uint64_t flags = MAP_GPA_SET_ATTRIBUTES; + + if (map_shared) + flags |= MAP_GPA_SHARED; + if (do_fallocate) + flags |= MAP_GPA_DO_FALLOCATE; + kvm_hypercall_map_gpa_range(gpa, size, flags); +} + +static void guest_map_shared(uint64_t gpa, uint64_t size, bool do_fallocate) +{ + guest_map_mem(gpa, size, true, do_fallocate); +} + +static void guest_map_private(uint64_t gpa, uint64_t size, bool do_fallocate) +{ + guest_map_mem(gpa, size, false, do_fallocate); +} + +struct { + uint64_t offset; + uint64_t size; +} static const test_ranges[] = { + GUEST_STAGE(0, PAGE_SIZE), + GUEST_STAGE(0, SZ_2M), + GUEST_STAGE(PAGE_SIZE, PAGE_SIZE), + GUEST_STAGE(PAGE_SIZE, SZ_2M), + GUEST_STAGE(SZ_2M, PAGE_SIZE), +}; + +static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate) +{ + const uint8_t def_p = 0xaa; + const uint8_t init_p = 0xcc; + uint64_t j; + int i; + + /* Memory should be shared by default. */ + memset((void *)base_gpa, def_p, PER_CPU_DATA_SIZE); + memcmp_g(base_gpa, def_p, PER_CPU_DATA_SIZE); + guest_sync_shared(base_gpa, PER_CPU_DATA_SIZE, def_p, init_p); + + memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE); + + for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { + uint64_t gpa = base_gpa + test_ranges[i].offset; + uint64_t size = test_ranges[i].size; + uint8_t p1 = 0x11; + uint8_t p2 = 0x22; + uint8_t p3 = 0x33; + uint8_t p4 = 0x44; + + /* + * Set the test region to pattern one to differentiate it from + * the data range as a whole (contains the initial pattern). + */ + memset((void *)gpa, p1, size); + + /* + * Convert to private, set and verify the private data, and + * then verify that the rest of the data (map shared) still + * holds the initial pattern, and that the host always sees the + * shared memory (initial pattern). Unlike shared memory, + * punching a hole in private memory is destructive, i.e. + * previous values aren't guaranteed to be preserved. + */ + guest_map_private(gpa, size, do_fallocate); + + if (size > PAGE_SIZE) { + memset((void *)gpa, p2, PAGE_SIZE); + goto skip; + } + + memset((void *)gpa, p2, size); + guest_sync_private(gpa, size, p1); + + /* + * Verify that the private memory was set to pattern two, and + * that shared memory still holds the initial pattern. + */ + memcmp_g(gpa, p2, size); + if (gpa > base_gpa) + memcmp_g(base_gpa, init_p, gpa - base_gpa); + if (gpa + size < base_gpa + PER_CPU_DATA_SIZE) + memcmp_g(gpa + size, init_p, + (base_gpa + PER_CPU_DATA_SIZE) - (gpa + size)); + + /* + * Convert odd-number page frames back to shared to verify KVM + * also correctly handles holes in private ranges. + */ + for (j = 0; j < size; j += PAGE_SIZE) { + if ((j >> PAGE_SHIFT) & 1) { + guest_map_shared(gpa + j, PAGE_SIZE, do_fallocate); + guest_sync_shared(gpa + j, PAGE_SIZE, p1, p3); + + memcmp_g(gpa + j, p3, PAGE_SIZE); + } else { + guest_sync_private(gpa + j, PAGE_SIZE, p1); + } + } + +skip: + /* + * Convert the entire region back to shared, explicitly write + * pattern three to fill in the even-number frames before + * asking the host to verify (and write pattern four). + */ + guest_map_shared(gpa, size, do_fallocate); + memset((void *)gpa, p3, size); + guest_sync_shared(gpa, size, p3, p4); + memcmp_g(gpa, p4, size); + + /* Reset the shared memory back to the initial pattern. */ + memset((void *)gpa, init_p, size); + + /* + * Free (via PUNCH_HOLE) *all* private memory so that the next + * iteration starts from a clean slate, e.g. with respect to + * whether or not there are pages/folios in guest_mem. + */ + guest_map_shared(base_gpa, PER_CPU_DATA_SIZE, true); + } +} + +static void guest_punch_hole(uint64_t gpa, uint64_t size) +{ + /* "Mapping" memory shared via fallocate() is done via PUNCH_HOLE. */ + uint64_t flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE; + + kvm_hypercall_map_gpa_range(gpa, size, flags); +} + +/* + * Test that PUNCH_HOLE actually frees memory by punching holes without doing a + * proper conversion. Freeing (PUNCH_HOLE) should zap SPTEs, and reallocating + * (subsequent fault) should zero memory. + */ +static void guest_test_punch_hole(uint64_t base_gpa, bool precise) +{ + const uint8_t init_p = 0xcc; + int i; + + /* + * Convert the entire range to private, this testcase is all about + * punching holes in guest_memfd, i.e. shared mappings aren't needed. + */ + guest_map_private(base_gpa, PER_CPU_DATA_SIZE, false); + + for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { + uint64_t gpa = base_gpa + test_ranges[i].offset; + uint64_t size = test_ranges[i].size; + + /* + * Free all memory before each iteration, even for the !precise + * case where the memory will be faulted back in. Freeing and + * reallocating should obviously work, and freeing all memory + * minimizes the probability of cross-testcase influence. + */ + guest_punch_hole(base_gpa, PER_CPU_DATA_SIZE); + + /* Fault-in and initialize memory, and verify the pattern. */ + if (precise) { + memset((void *)gpa, init_p, size); + memcmp_g(gpa, init_p, size); + } else { + memset((void *)base_gpa, init_p, PER_CPU_DATA_SIZE); + memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE); + } + + /* + * Punch a hole at the target range and verify that reads from + * the guest succeed and return zeroes. + */ + guest_punch_hole(gpa, size); + memcmp_g(gpa, 0, size); + } +} + +static void guest_code(uint64_t base_gpa) +{ + /* + * Run the conversion test twice, with and without doing fallocate() on + * the guest_memfd backing when converting between shared and private. + */ + guest_test_explicit_conversion(base_gpa, false); + guest_test_explicit_conversion(base_gpa, true); + + /* + * Run the PUNCH_HOLE test twice too, once with the entire guest_memfd + * faulted in, once with only the target range faulted in. + */ + guest_test_punch_hole(base_gpa, false); + guest_test_punch_hole(base_gpa, true); + GUEST_DONE(); +} + +static void handle_exit_hypercall(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint64_t gpa = run->hypercall.args[0]; + uint64_t size = run->hypercall.args[1] * PAGE_SIZE; + bool set_attributes = run->hypercall.args[2] & MAP_GPA_SET_ATTRIBUTES; + bool map_shared = run->hypercall.args[2] & MAP_GPA_SHARED; + bool do_fallocate = run->hypercall.args[2] & MAP_GPA_DO_FALLOCATE; + struct kvm_vm *vm = vcpu->vm; + + TEST_ASSERT(run->hypercall.nr == KVM_HC_MAP_GPA_RANGE, + "Wanted MAP_GPA_RANGE (%u), got '%llu'", + KVM_HC_MAP_GPA_RANGE, run->hypercall.nr); + + if (do_fallocate) + vm_guest_mem_fallocate(vm, gpa, size, map_shared); + + if (set_attributes) + vm_set_memory_attributes(vm, gpa, size, + map_shared ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE); + run->hypercall.ret = 0; +} + +static bool run_vcpus; + +static void *__test_mem_conversions(void *__vcpu) +{ + struct kvm_vcpu *vcpu = __vcpu; + struct kvm_run *run = vcpu->run; + struct kvm_vm *vm = vcpu->vm; + struct ucall uc; + + while (!READ_ONCE(run_vcpus)) + ; + + for ( ;; ) { + vcpu_run(vcpu); + + if (run->exit_reason == KVM_EXIT_HYPERCALL) { + handle_exit_hypercall(vcpu); + continue; + } + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Wanted KVM_EXIT_IO, got exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: { + uint64_t gpa = uc.args[1]; + size_t size = uc.args[2]; + size_t i; + + TEST_ASSERT(uc.args[0] == SYNC_SHARED || + uc.args[0] == SYNC_PRIVATE, + "Unknown sync command '%ld'", uc.args[0]); + + for (i = 0; i < size; i += vm->page_size) { + size_t nr_bytes = min_t(size_t, vm->page_size, size - i); + uint8_t *hva = addr_gpa2hva(vm, gpa + i); + + /* In all cases, the host should observe the shared data. */ + memcmp_h(hva, gpa + i, uc.args[3], nr_bytes); + + /* For shared, write the new pattern to guest memory. */ + if (uc.args[0] == SYNC_SHARED) + memset(hva, uc.args[4], nr_bytes); + } + break; + } + case UCALL_DONE: + return NULL; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } + } +} + +static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t nr_vcpus, + uint32_t nr_memslots) +{ + /* + * Allocate enough memory so that each vCPU's chunk of memory can be + * naturally aligned with respect to the size of the backing store. + */ + const size_t alignment = max_t(size_t, SZ_2M, get_backing_src_pagesz(src_type)); + const size_t per_cpu_size = align_up(PER_CPU_DATA_SIZE, alignment); + const size_t memfd_size = per_cpu_size * nr_vcpus; + const size_t slot_size = memfd_size / nr_memslots; + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + pthread_t threads[KVM_MAX_VCPUS]; + struct kvm_vm *vm; + int memfd, i, r; + + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = KVM_X86_SW_PROTECTED_VM, + }; + + TEST_ASSERT(slot_size * nr_memslots == memfd_size, + "The memfd size (0x%lx) needs to be cleanly divisible by the number of memslots (%u)", + memfd_size, nr_memslots); + vm = __vm_create_with_vcpus(shape, nr_vcpus, 0, guest_code, vcpus); + + vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, (1 << KVM_HC_MAP_GPA_RANGE)); + + memfd = vm_create_guest_memfd(vm, memfd_size, 0); + + for (i = 0; i < nr_memslots; i++) + vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i, + BASE_DATA_SLOT + i, slot_size / vm->page_size, + KVM_MEM_GUEST_MEMFD, memfd, slot_size * i); + + for (i = 0; i < nr_vcpus; i++) { + uint64_t gpa = BASE_DATA_GPA + i * per_cpu_size; + + vcpu_args_set(vcpus[i], 1, gpa); + + /* + * Map only what is needed so that an out-of-bounds access + * results #PF => SHUTDOWN instead of data corruption. + */ + virt_map(vm, gpa, gpa, PER_CPU_DATA_SIZE / vm->page_size); + + pthread_create(&threads[i], NULL, __test_mem_conversions, vcpus[i]); + } + + WRITE_ONCE(run_vcpus, true); + + for (i = 0; i < nr_vcpus; i++) + pthread_join(threads[i], NULL); + + kvm_vm_free(vm); + + /* + * Allocate and free memory from the guest_memfd after closing the VM + * fd. The guest_memfd is gifted a reference to its owning VM, i.e. + * should prevent the VM from being fully destroyed until the last + * reference to the guest_memfd is also put. + */ + r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size); + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); + + r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size); + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); + + close(memfd); +} + +static void usage(const char *cmd) +{ + puts(""); + printf("usage: %s [-h] [-m nr_memslots] [-s mem_type] [-n nr_vcpus]\n", cmd); + puts(""); + backing_src_help("-s"); + puts(""); + puts(" -n: specify the number of vcpus (default: 1)"); + puts(""); + puts(" -m: specify the number of memslots (default: 1)"); + puts(""); +} + +int main(int argc, char *argv[]) +{ + enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC; + uint32_t nr_memslots = 1; + uint32_t nr_vcpus = 1; + int opt; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); + + while ((opt = getopt(argc, argv, "hm:s:n:")) != -1) { + switch (opt) { + case 's': + src_type = parse_backing_src_type(optarg); + break; + case 'n': + nr_vcpus = atoi_positive("nr_vcpus", optarg); + break; + case 'm': + nr_memslots = atoi_positive("nr_memslots", optarg); + break; + case 'h': + default: + usage(argv[0]); + exit(0); + } + } + + test_mem_conversions(src_type, nr_vcpus, nr_memslots); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c new file mode 100644 index 0000000000000000000000000000000000000000..13e72fcec8dd2f1b97cbc9bbae7635de7098b168 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023, Google LLC. + */ +#include +#include +#include + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +/* Arbitrarily selected to avoid overlaps with anything else */ +#define EXITS_TEST_GVA 0xc0000000 +#define EXITS_TEST_GPA EXITS_TEST_GVA +#define EXITS_TEST_NPAGES 1 +#define EXITS_TEST_SIZE (EXITS_TEST_NPAGES * PAGE_SIZE) +#define EXITS_TEST_SLOT 10 + +static uint64_t guest_repeatedly_read(void) +{ + volatile uint64_t value; + + while (true) + value = *((uint64_t *) EXITS_TEST_GVA); + + return value; +} + +static uint32_t run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu) +{ + int r; + + r = _vcpu_run(vcpu); + if (r) { + TEST_ASSERT(errno == EFAULT, KVM_IOCTL_ERROR(KVM_RUN, r)); + TEST_ASSERT_EQ(vcpu->run->exit_reason, KVM_EXIT_MEMORY_FAULT); + } + return vcpu->run->exit_reason; +} + +const struct vm_shape protected_vm_shape = { + .mode = VM_MODE_DEFAULT, + .type = KVM_X86_SW_PROTECTED_VM, +}; + +static void test_private_access_memslot_deleted(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + pthread_t vm_thread; + void *thread_return; + uint32_t exit_reason; + + vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, + guest_repeatedly_read); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + EXITS_TEST_GPA, EXITS_TEST_SLOT, + EXITS_TEST_NPAGES, + KVM_MEM_GUEST_MEMFD); + + virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES); + + /* Request to access page privately */ + vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE); + + pthread_create(&vm_thread, NULL, + (void *(*)(void *))run_vcpu_get_exit_reason, + (void *)vcpu); + + vm_mem_region_delete(vm, EXITS_TEST_SLOT); + + pthread_join(vm_thread, &thread_return); + exit_reason = (uint32_t)(uint64_t)thread_return; + + TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); + TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); + TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA); + TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE); + + kvm_vm_free(vm); +} + +static void test_private_access_memslot_not_private(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + uint32_t exit_reason; + + vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, + guest_repeatedly_read); + + /* Add a non-private memslot (flags = 0) */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + EXITS_TEST_GPA, EXITS_TEST_SLOT, + EXITS_TEST_NPAGES, 0); + + virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES); + + /* Request to access page privately */ + vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE); + + exit_reason = run_vcpu_get_exit_reason(vcpu); + + TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); + TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); + TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA); + TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); + + test_private_access_memslot_deleted(); + test_private_access_memslot_not_private(); +} diff --git a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c b/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c new file mode 100644 index 0000000000000000000000000000000000000000..3fb967f40c6a1626d1d2cff1032c0e2562c8a205 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "kselftest.h" + +#define SVM_SEV_FEAT_DEBUG_SWAP 32u + +/* + * Some features may have hidden dependencies, or may only work + * for certain VM types. Err on the side of safety and don't + * expect that all supported features can be passed one by one + * to KVM_SEV_INIT2. + * + * (Well, right now there's only one...) + */ +#define KNOWN_FEATURES SVM_SEV_FEAT_DEBUG_SWAP + +int kvm_fd; +u64 supported_vmsa_features; +bool have_sev_es; + +static int __sev_ioctl(int vm_fd, int cmd_id, void *data) +{ + struct kvm_sev_cmd cmd = { + .id = cmd_id, + .data = (uint64_t)data, + .sev_fd = open_sev_dev_path_or_exit(), + }; + int ret; + + ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); + TEST_ASSERT(ret < 0 || cmd.error == SEV_RET_SUCCESS, + "%d failed: fw error: %d\n", + cmd_id, cmd.error); + + return ret; +} + +static void test_init2(unsigned long vm_type, struct kvm_sev_init *init) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create_barebones_type(vm_type); + ret = __sev_ioctl(vm->fd, KVM_SEV_INIT2, init); + TEST_ASSERT(ret == 0, + "KVM_SEV_INIT2 return code is %d (expected 0), errno: %d", + ret, errno); + kvm_vm_free(vm); +} + +static void test_init2_invalid(unsigned long vm_type, struct kvm_sev_init *init, const char *msg) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create_barebones_type(vm_type); + ret = __sev_ioctl(vm->fd, KVM_SEV_INIT2, init); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "KVM_SEV_INIT2 should fail, %s.", + msg); + kvm_vm_free(vm); +} + +void test_vm_types(void) +{ + test_init2(KVM_X86_SEV_VM, &(struct kvm_sev_init){}); + + /* + * TODO: check that unsupported types cannot be created. Probably + * a separate selftest. + */ + if (have_sev_es) + test_init2(KVM_X86_SEV_ES_VM, &(struct kvm_sev_init){}); + + test_init2_invalid(0, &(struct kvm_sev_init){}, + "VM type is KVM_X86_DEFAULT_VM"); + if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)) + test_init2_invalid(KVM_X86_SW_PROTECTED_VM, &(struct kvm_sev_init){}, + "VM type is KVM_X86_SW_PROTECTED_VM"); +} + +void test_flags(uint32_t vm_type) +{ + int i; + + for (i = 0; i < 32; i++) + test_init2_invalid(vm_type, + &(struct kvm_sev_init){ .flags = BIT(i) }, + "invalid flag"); +} + +void test_features(uint32_t vm_type, uint64_t supported_features) +{ + int i; + + for (i = 0; i < 64; i++) { + if (!(supported_features & BIT_ULL(i))) + test_init2_invalid(vm_type, + &(struct kvm_sev_init){ .vmsa_features = BIT_ULL(i) }, + "unknown feature"); + else if (KNOWN_FEATURES & BIT_ULL(i)) + test_init2(vm_type, + &(struct kvm_sev_init){ .vmsa_features = BIT_ULL(i) }); + } +} + +int main(int argc, char *argv[]) +{ + int kvm_fd = open_kvm_dev_path_or_exit(); + bool have_sev; + + TEST_REQUIRE(__kvm_has_device_attr(kvm_fd, KVM_X86_GRP_SEV, + KVM_X86_SEV_VMSA_FEATURES) == 0); + kvm_device_attr_get(kvm_fd, KVM_X86_GRP_SEV, + KVM_X86_SEV_VMSA_FEATURES, + &supported_vmsa_features); + + have_sev = kvm_cpu_has(X86_FEATURE_SEV); + TEST_ASSERT(have_sev == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)), + "sev: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)", + kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_VM); + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)); + have_sev_es = kvm_cpu_has(X86_FEATURE_SEV_ES); + + TEST_ASSERT(have_sev_es == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM)), + "sev-es: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)", + kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_ES_VM); + + test_vm_types(); + + test_flags(KVM_X86_SEV_VM); + if (have_sev_es) + test_flags(KVM_X86_SEV_ES_VM); + + test_features(KVM_X86_SEV_VM, 0); + if (have_sev_es) + test_features(KVM_X86_SEV_ES_VM, supported_vmsa_features); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c new file mode 100644 index 0000000000000000000000000000000000000000..e8d76eac7555d8e1ab9720f8e765ef6af6947512 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "linux/psp-sev.h" +#include "sev.h" + + +#define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM) + +static void guest_sev_es_code(void) +{ + /* TODO: Check CPUID after GHCB-based hypercall support is added. */ + GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED); + + /* + * TODO: Add GHCB and ucall support for SEV-ES guests. For now, simply + * force "termination" to signal "done" via the GHCB MSR protocol. + */ + wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); + __asm__ __volatile__("rep; vmmcall"); +} + +static void guest_sev_code(void) +{ + GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV)); + GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + + GUEST_DONE(); +} + +/* Stash state passed via VMSA before any compiled code runs. */ +extern void guest_code_xsave(void); +asm("guest_code_xsave:\n" + "mov $-1, %eax\n" + "mov $-1, %edx\n" + "xsave (%rdi)\n" + "jmp guest_sev_es_code"); + +static void compare_xsave(u8 *from_host, u8 *from_guest) +{ + int i; + bool bad = false; + for (i = 0; i < 4095; i++) { + if (from_host[i] != from_guest[i]) { + printf("mismatch at %u | %02hhx %02hhx\n", + i, from_host[i], from_guest[i]); + bad = true; + } + } + + if (bad) + abort(); +} + +static void test_sync_vmsa(uint32_t policy) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + vm_vaddr_t gva; + void *hva; + + double x87val = M_PI; + struct kvm_xsave __attribute__((aligned(64))) xsave = { 0 }; + struct kvm_sregs sregs; + struct kvm_xcrs xcrs = { + .nr_xcrs = 1, + .xcrs[0].xcr = 0, + .xcrs[0].value = XFEATURE_MASK_X87_AVX, + }; + + vm = vm_sev_create_with_one_vcpu(KVM_X86_SEV_ES_VM, guest_code_xsave, &vcpu); + gva = vm_vaddr_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR, + MEM_REGION_TEST_DATA); + hva = addr_gva2hva(vm, gva); + + vcpu_args_set(vcpu, 1, gva); + + vcpu_sregs_get(vcpu, &sregs); + sregs.cr4 |= X86_CR4_OSFXSR | X86_CR4_OSXSAVE; + vcpu_sregs_set(vcpu, &sregs); + + vcpu_xcrs_set(vcpu, &xcrs); + asm("fninit\n" + "vpcmpeqb %%ymm4, %%ymm4, %%ymm4\n" + "fldl %3\n" + "xsave (%2)\n" + "fstp %%st\n" + : "=m"(xsave) + : "A"(XFEATURE_MASK_X87_AVX), "r"(&xsave), "m" (x87val) + : "ymm4", "st", "st(1)", "st(2)", "st(3)", "st(4)", "st(5)", "st(6)", "st(7)"); + vcpu_xsave_set(vcpu, &xsave); + + vm_sev_launch(vm, SEV_POLICY_ES | policy, NULL); + + /* This page is shared, so make it decrypted. */ + memset(hva, 0, 4096); + + vcpu_run(vcpu); + + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT, + "Wanted SYSTEM_EVENT, got %s", + exit_reason_str(vcpu->run->exit_reason)); + TEST_ASSERT_EQ(vcpu->run->system_event.type, KVM_SYSTEM_EVENT_SEV_TERM); + TEST_ASSERT_EQ(vcpu->run->system_event.ndata, 1); + TEST_ASSERT_EQ(vcpu->run->system_event.data[0], GHCB_MSR_TERM_REQ); + + compare_xsave((u8 *)&xsave, (u8 *)hva); + + kvm_vm_free(vm); +} + +static void test_sev(void *guest_code, uint64_t policy) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + + uint32_t type = policy & SEV_POLICY_ES ? KVM_X86_SEV_ES_VM : KVM_X86_SEV_VM; + + vm = vm_sev_create_with_one_vcpu(type, guest_code, &vcpu); + + /* TODO: Validate the measurement is as expected. */ + vm_sev_launch(vm, policy, NULL); + + for (;;) { + vcpu_run(vcpu); + + if (policy & SEV_POLICY_ES) { + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT, + "Wanted SYSTEM_EVENT, got %s", + exit_reason_str(vcpu->run->exit_reason)); + TEST_ASSERT_EQ(vcpu->run->system_event.type, KVM_SYSTEM_EVENT_SEV_TERM); + TEST_ASSERT_EQ(vcpu->run->system_event.ndata, 1); + TEST_ASSERT_EQ(vcpu->run->system_event.data[0], GHCB_MSR_TERM_REQ); + break; + } + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + continue; + case UCALL_DONE: + return; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected exit: %s", + exit_reason_str(vcpu->run->exit_reason)); + } + } + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); + + test_sev(guest_sev_code, SEV_POLICY_NO_DBG); + test_sev(guest_sev_code, 0); + + if (kvm_cpu_has(X86_FEATURE_SEV_ES)) { + test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); + test_sev(guest_sev_es_code, SEV_POLICY_ES); + + if (kvm_has_cap(KVM_CAP_XCRS) && + (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) { + test_sync_vmsa(0); + test_sync_vmsa(SEV_POLICY_NO_DBG); + } + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c index 85f34ca7e49e531c11e09f700738d0eec2a0e0fa..0ed32ec903d03548ce11fa5bcc42eba329808506 100644 --- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -271,7 +271,7 @@ int main(int argc, char *argv[]) kvm_check_cap(KVM_CAP_MCE); - vm = __vm_create(VM_MODE_DEFAULT, 3, 0); + vm = __vm_create(VM_SHAPE_DEFAULT, 3, 0); kvm_ioctl(vm->kvm_fd, KVM_X86_GET_MCE_CAP_SUPPORTED, &supported_mcg_caps); diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 484d0873061ca5041c546f1c44520a1848ec1d16..c23f3ac0e1506b1fe2b59d290d52bb7dd18e287e 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -68,6 +68,9 @@ config HAVE_KVM_INVALID_WAKEUPS config KVM_GENERIC_DIRTYLOG_READ_PROTECT bool +config KVM_GENERIC_PRE_FAULT_MEMORY + bool + config KVM_COMPAT def_bool y depends on KVM && COMPAT && !(S390 || ARM64 || RISCV) @@ -92,3 +95,28 @@ config HAVE_KVM_PM_NOTIFIER config KVM_GENERIC_HARDWARE_ENABLING bool + +config KVM_GENERIC_MMU_NOTIFIER + select MMU_NOTIFIER + bool + +config KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_GENERIC_MMU_NOTIFIER + bool + +config KVM_PRIVATE_MEM + select XARRAY_MULTI + bool + +config KVM_GENERIC_PRIVATE_MEM + select KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_PRIVATE_MEM + bool + +config HAVE_KVM_ARCH_GMEM_PREPARE + bool + depends on KVM_PRIVATE_MEM + +config HAVE_KVM_ARCH_GMEM_INVALIDATE + bool + depends on KVM_PRIVATE_MEM diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm index 2c27d5d0c367c5873902c512604e1ce418f6a11f..724c89af78af963c1d3b160486cf3dc09e5a4e2b 100644 --- a/virt/kvm/Makefile.kvm +++ b/virt/kvm/Makefile.kvm @@ -12,3 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o +kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 27e50190d419be6c7c657a3dd41914f150891027..7bc74969a819afb5198fc2dfb7c9e83b80f967e0 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -61,7 +61,7 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) as_id = slot >> 16; id = (u16)slot; - if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return; memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c new file mode 100644 index 0000000000000000000000000000000000000000..ebaaa102c17c791b0e731d42f6054b4d3269a99b --- /dev/null +++ b/virt/kvm/guest_memfd.c @@ -0,0 +1,708 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +#include "kvm_mm.h" + +struct kvm_gmem { + struct kvm *kvm; + struct xarray bindings; + struct list_head entry; +}; + +/** + * folio_file_pfn - like folio_file_page, but return a pfn. + * @folio: The folio which contains this index. + * @index: The index we want to look up. + * + * Return: The pfn for this index. + */ +static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index) +{ + return folio_pfn(folio) + (index & (folio_nr_pages(folio) - 1)); +} + +static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, + pgoff_t index, struct folio *folio) +{ +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE + kvm_pfn_t pfn = folio_file_pfn(folio, index); + gfn_t gfn = slot->base_gfn + index - slot->gmem.pgoff; + int rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); + if (rc) { + pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n", + index, gfn, pfn, rc); + return rc; + } +#endif + + return 0; +} + +static inline void kvm_gmem_mark_prepared(struct folio *folio) +{ + folio_mark_uptodate(folio); +} + +/* + * Process @folio, which contains @gfn, so that the guest can use it. + * The folio must be locked and the gfn must be contained in @slot. + * On successful return the guest sees a zero page so as to avoid + * leaking host data and the up-to-date flag is set. + */ +static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, struct folio *folio) +{ + unsigned long nr_pages, i; + pgoff_t index; + int r; + + nr_pages = folio_nr_pages(folio); + for (i = 0; i < nr_pages; i++) + clear_highpage(folio_page(folio, i)); + + /* + * Preparing huge folios should always be safe, since it should + * be possible to split them later if needed. + * + * Right now the folio order is always going to be zero, but the + * code is ready for huge folios. The only assumption is that + * the base pgoff of memslots is naturally aligned with the + * requested page order, ensuring that huge folios can also use + * huge page table entries for GPA->HPA mapping. + * + * The order will be passed when creating the guest_memfd, and + * checked when creating memslots. + */ + WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, 1 << folio_order(folio))); + index = gfn - slot->base_gfn + slot->gmem.pgoff; + index = ALIGN_DOWN(index, 1 << folio_order(folio)); + r = __kvm_gmem_prepare_folio(kvm, slot, index, folio); + if (!r) + kvm_gmem_mark_prepared(folio); + + return r; +} + +/* + * Returns a locked folio on success. The caller is responsible for + * setting the up-to-date flag before the memory is mapped into the guest. + * There is no backing storage for the memory, so the folio will remain + * up-to-date until it's removed. + * + * Ignore accessed, referenced, and dirty flags. The memory is + * unevictable and there is no storage to write back to. + */ +static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) +{ + /* TODO: Support huge pages. */ + return filemap_grab_folio(inode->i_mapping, index); +} + +static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, + pgoff_t end) +{ + bool flush = false, found_memslot = false; + struct kvm_memory_slot *slot; + struct kvm *kvm = gmem->kvm; + unsigned long index; + + xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) { + pgoff_t pgoff = slot->gmem.pgoff; + + struct kvm_gfn_range gfn_range = { + .start = slot->base_gfn + max(pgoff, start) - pgoff, + .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff, + .slot = slot, + .may_block = true, + /* guest memfd is relevant to only private mappings. */ + .attr_filter = KVM_FILTER_PRIVATE, + }; + + if (!found_memslot) { + found_memslot = true; + + KVM_MMU_LOCK(kvm); + kvm_mmu_invalidate_begin(kvm); + } + + flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range); + } + + if (flush) + kvm_flush_remote_tlbs(kvm); + + if (found_memslot) + KVM_MMU_UNLOCK(kvm); +} + +static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start, + pgoff_t end) +{ + struct kvm *kvm = gmem->kvm; + + if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { + KVM_MMU_LOCK(kvm); + kvm_mmu_invalidate_end(kvm); + KVM_MMU_UNLOCK(kvm); + } +} + +static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len) +{ + struct list_head *gmem_list = &inode->i_mapping->i_private_list; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + len) >> PAGE_SHIFT; + struct kvm_gmem *gmem; + + /* + * Bindings must be stable across invalidation to ensure the start+end + * are balanced. + */ + filemap_invalidate_lock(inode->i_mapping); + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_begin(gmem, start, end); + + truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1); + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_end(gmem, start, end); + + filemap_invalidate_unlock(inode->i_mapping); + + return 0; +} + +static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t start, index, end; + int r; + + /* Dedicated guest is immutable by default. */ + if (offset + len > i_size_read(inode)) + return -EINVAL; + + filemap_invalidate_lock_shared(mapping); + + start = offset >> PAGE_SHIFT; + end = (offset + len) >> PAGE_SHIFT; + + r = 0; + for (index = start; index < end; ) { + struct folio *folio; + + if (signal_pending(current)) { + r = -EINTR; + break; + } + + folio = kvm_gmem_get_folio(inode, index); + if (IS_ERR(folio)) { + r = PTR_ERR(folio); + break; + } + + index = folio_next_index(folio); + + folio_unlock(folio); + folio_put(folio); + + /* 64-bit only, wrapping the index should be impossible. */ + if (WARN_ON_ONCE(!index)) + break; + + cond_resched(); + } + + filemap_invalidate_unlock_shared(mapping); + + return r; +} + +static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + int ret; + + if (!(mode & FALLOC_FL_KEEP_SIZE)) + return -EOPNOTSUPP; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len)) + return -EINVAL; + + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = kvm_gmem_punch_hole(file_inode(file), offset, len); + else + ret = kvm_gmem_allocate(file_inode(file), offset, len); + + if (!ret) + file_modified(file); + return ret; +} + +static int kvm_gmem_release(struct inode *inode, struct file *file) +{ + struct kvm_gmem *gmem = file->private_data; + struct kvm_memory_slot *slot; + struct kvm *kvm = gmem->kvm; + unsigned long index; + + /* + * Prevent concurrent attempts to *unbind* a memslot. This is the last + * reference to the file and thus no new bindings can be created, but + * dereferencing the slot for existing bindings needs to be protected + * against memslot updates, specifically so that unbind doesn't race + * and free the memslot (kvm_gmem_get_file() will return NULL). + */ + mutex_lock(&kvm->slots_lock); + + filemap_invalidate_lock(inode->i_mapping); + + xa_for_each(&gmem->bindings, index, slot) + rcu_assign_pointer(slot->gmem.file, NULL); + + synchronize_rcu(); + + /* + * All in-flight operations are gone and new bindings can be created. + * Zap all SPTEs pointed at by this file. Do not free the backing + * memory, as its lifetime is associated with the inode, not the file. + */ + kvm_gmem_invalidate_begin(gmem, 0, -1ul); + kvm_gmem_invalidate_end(gmem, 0, -1ul); + + list_del(&gmem->entry); + + filemap_invalidate_unlock(inode->i_mapping); + + mutex_unlock(&kvm->slots_lock); + + xa_destroy(&gmem->bindings); + kfree(gmem); + + kvm_put_kvm(kvm); + + return 0; +} + +static struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) +{ + struct file *file; + + rcu_read_lock(); + + file = rcu_dereference(slot->gmem.file); + if (file && !get_file_rcu(file)) + file = NULL; + + rcu_read_unlock(); + + return file; +} + +static struct file_operations kvm_gmem_fops = { + .open = generic_file_open, + .release = kvm_gmem_release, + .fallocate = kvm_gmem_fallocate, +}; + +void kvm_gmem_init(struct module *module) +{ + kvm_gmem_fops.owner = module; +} + +static int kvm_gmem_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, + enum migrate_mode mode) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int kvm_gmem_error_page(struct address_space *mapping, struct page *page) +{ + struct list_head *gmem_list = &mapping->i_private_list; + struct kvm_gmem *gmem; + pgoff_t start, end; + + filemap_invalidate_lock_shared(mapping); + + start = page->index; + end = start + thp_nr_pages(page); + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_begin(gmem, start, end); + + /* + * Do not truncate the range, what action is taken in response to the + * error is userspace's decision (assuming the architecture supports + * gracefully handling memory errors). If/when the guest attempts to + * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON, + * at which point KVM can either terminate the VM or propagate the + * error to userspace. + */ + + list_for_each_entry(gmem, gmem_list, entry) + kvm_gmem_invalidate_end(gmem, start, end); + + filemap_invalidate_unlock_shared(mapping); + + return MF_DELAYED; +} + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +static void kvm_gmem_free_folio(struct folio *folio) +{ + struct page *page = folio_page(folio, 0); + kvm_pfn_t pfn = page_to_pfn(page); + int order = folio_order(folio); + + kvm_arch_gmem_invalidate(pfn, pfn + (1ul << order)); +} +#endif + +static const struct address_space_operations kvm_gmem_aops = { + .dirty_folio = noop_dirty_folio, + .migrate_folio = kvm_gmem_migrate_folio, + .error_remove_page = kvm_gmem_error_page, +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE + .free_folio = kvm_gmem_free_folio, +#endif +}; + +static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + struct inode *inode = path->dentry->d_inode; + + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + return -EINVAL; +} +static const struct inode_operations kvm_gmem_iops = { + .getattr = kvm_gmem_getattr, + .setattr = kvm_gmem_setattr, +}; + +static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) +{ + const char *anon_name = "[kvm-gmem]"; + struct kvm_gmem *gmem; + struct inode *inode; + struct file *file; + int fd, err; + + fd = get_unused_fd_flags(0); + if (fd < 0) + return fd; + + gmem = kzalloc(sizeof(*gmem), GFP_KERNEL); + if (!gmem) { + err = -ENOMEM; + goto err_fd; + } + + file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem, + O_RDWR, NULL); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto err_gmem; + } + + file->f_flags |= O_LARGEFILE; + + inode = file->f_inode; + WARN_ON(file->f_mapping != inode->i_mapping); + + inode->i_private = (void *)(unsigned long)flags; + inode->i_op = &kvm_gmem_iops; + inode->i_mapping->a_ops = &kvm_gmem_aops; + inode->i_mode |= S_IFREG; + inode->i_size = size; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); + mapping_set_inaccessible(inode->i_mapping); + /* Unmovable mappings are supposed to be marked unevictable as well. */ + WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); + + kvm_get_kvm(kvm); + gmem->kvm = kvm; + xa_init(&gmem->bindings); + list_add(&gmem->entry, &inode->i_mapping->i_private_list); + + fd_install(fd, file); + return fd; + +err_gmem: + kfree(gmem); +err_fd: + put_unused_fd(fd); + return err; +} + +int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) +{ + loff_t size = args->size; + u64 flags = args->flags; + u64 valid_flags = 0; + + if (flags & ~valid_flags) + return -EINVAL; + + if (size <= 0 || !PAGE_ALIGNED(size)) + return -EINVAL; + + return __kvm_gmem_create(kvm, size, flags); +} + +int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset) +{ + loff_t size = slot->npages << PAGE_SHIFT; + unsigned long start, end; + struct kvm_gmem *gmem; + struct inode *inode; + struct file *file; + int r = -EINVAL; + + BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff)); + + file = fget(fd); + if (!file) + return -EBADF; + + if (file->f_op != &kvm_gmem_fops) + goto err; + + gmem = file->private_data; + if (gmem->kvm != kvm) + goto err; + + inode = file_inode(file); + + if (offset < 0 || !PAGE_ALIGNED(offset) || + offset + size > i_size_read(inode)) + goto err; + + filemap_invalidate_lock(inode->i_mapping); + + start = offset >> PAGE_SHIFT; + end = start + slot->npages; + + if (!xa_empty(&gmem->bindings) && + xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { + filemap_invalidate_unlock(inode->i_mapping); + goto err; + } + + /* + * No synchronize_rcu() needed, any in-flight readers are guaranteed to + * be see either a NULL file or this new file, no need for them to go + * away. + */ + rcu_assign_pointer(slot->gmem.file, file); + slot->gmem.pgoff = start; + + xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); + filemap_invalidate_unlock(inode->i_mapping); + + /* + * Drop the reference to the file, even on success. The file pins KVM, + * not the other way 'round. Active bindings are invalidated if the + * file is closed before memslots are destroyed. + */ + r = 0; +err: + fput(file); + return r; +} + +void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + unsigned long start = slot->gmem.pgoff; + unsigned long end = start + slot->npages; + struct kvm_gmem *gmem; + struct file *file; + + /* + * Nothing to do if the underlying file was already closed (or is being + * closed right now), kvm_gmem_release() invalidates all bindings. + */ + file = kvm_gmem_get_file(slot); + if (!file) + return; + + gmem = file->private_data; + + filemap_invalidate_lock(file->f_mapping); + xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + rcu_assign_pointer(slot->gmem.file, NULL); + synchronize_rcu(); + filemap_invalidate_unlock(file->f_mapping); + + fput(file); +} + +/* Returns a locked folio on success. */ +static struct folio * +__kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, bool *is_prepared, + int *max_order) +{ + pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff; + struct kvm_gmem *gmem = file->private_data; + struct folio *folio; + + if (file != slot->gmem.file) { + WARN_ON_ONCE(slot->gmem.file); + return ERR_PTR(-EFAULT); + } + + gmem = file->private_data; + if (xa_load(&gmem->bindings, index) != slot) { + WARN_ON_ONCE(xa_load(&gmem->bindings, index)); + return ERR_PTR(-EIO); + } + + folio = kvm_gmem_get_folio(file_inode(file), index); + if (IS_ERR(folio)) + return folio; + + if (folio_test_hwpoison(folio)) { + folio_unlock(folio); + folio_put(folio); + return ERR_PTR(-EHWPOISON); + } + + *pfn = folio_file_pfn(folio, index); + if (max_order) + *max_order = 0; + + *is_prepared = folio_test_uptodate(folio); + return folio; +} + +int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, int *max_order) +{ + struct file *file = kvm_gmem_get_file(slot); + struct folio *folio; + bool is_prepared = false; + int r = 0; + + if (!file) + return -EFAULT; + + folio = __kvm_gmem_get_pfn(file, slot, gfn, pfn, &is_prepared, max_order); + if (IS_ERR(folio)) { + r = PTR_ERR(folio); + goto out; + } + + if (!is_prepared) + r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio); + + folio_unlock(folio); + if (r < 0) + folio_put(folio); + +out: + fput(file); + return r; +} +EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn); + +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque) +{ + struct file *file; + struct kvm_memory_slot *slot; + void __user *p; + + int ret = 0, max_order; + long i; + + lockdep_assert_held(&kvm->slots_lock); + if (npages < 0) + return -EINVAL; + + slot = gfn_to_memslot(kvm, start_gfn); + if (!kvm_slot_can_be_private(slot)) + return -EINVAL; + + file = kvm_gmem_get_file(slot); + if (!file) + return -EFAULT; + + filemap_invalidate_lock(file->f_mapping); + + npages = min_t(ulong, slot->npages - (start_gfn - slot->base_gfn), npages); + for (i = 0; i < npages; i += (1 << max_order)) { + struct folio *folio; + gfn_t gfn = start_gfn + i; + bool is_prepared = false; + kvm_pfn_t pfn; + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + folio = __kvm_gmem_get_pfn(file, slot, gfn, &pfn, &is_prepared, &max_order); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); + break; + } + + if (is_prepared) { + folio_unlock(folio); + folio_put(folio); + ret = -EEXIST; + break; + } + + folio_unlock(folio); + WARN_ON(!IS_ALIGNED(gfn, 1 << max_order) || + (npages - i) < (1 << max_order)); + + ret = -EINVAL; + while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order), + KVM_MEMORY_ATTRIBUTE_PRIVATE, + KVM_MEMORY_ATTRIBUTE_PRIVATE)) { + if (!max_order) + goto put_folio_and_exit; + max_order--; + } + + p = src ? src + i * PAGE_SIZE : NULL; + ret = post_populate(kvm, gfn, pfn, p, max_order, opaque); + if (!ret) + kvm_gmem_mark_prepared(folio); + +put_folio_and_exit: + folio_put(folio); + if (ret) + break; + } + + filemap_invalidate_unlock(file->f_mapping); + + fput(file); + return ret && !i ? ret : i; +} +EXPORT_SYMBOL_GPL(kvm_gmem_populate); +#endif diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 79f73ebb728df2df7b855d9c5e8f771ecd04fa8a..0ee2f29483171390c8c88c722d2c23769630e650 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -548,30 +548,43 @@ void kvm_destroy_vcpus(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); } -typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); +typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); -typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start, - unsigned long end); +typedef void (*on_lock_fn_t)(struct kvm *kvm); -typedef void (*on_unlock_fn_t)(struct kvm *kvm); - -struct kvm_hva_range { - unsigned long start; - unsigned long end; +struct kvm_mmu_notifier_range { + /* + * 64-bit addresses, as KVM notifiers can operate on host virtual + * addresses (unsigned long) and guest physical addresses (64-bit). + */ + u64 start; + u64 end; union kvm_mmu_notifier_arg arg; - hva_handler_t handler; + gfn_handler_t handler; on_lock_fn_t on_lock; - on_unlock_fn_t on_unlock; bool flush_on_ret; bool may_block; }; +/* + * The inner-most helper returns a tuple containing the return value from the + * arch- and action-specific handler, plus a flag indicating whether or not at + * least one memslot was found, i.e. if the handler found guest memory. + * + * Note, most notifiers are averse to booleans, so even though KVM tracks the + * return from arch code as a bool, outer helpers will cast it to an int. :-( + */ +typedef struct kvm_mmu_notifier_return { + bool ret; + bool found_memslot; +} kvm_mn_ret_t; + /* * Use a dedicated stub instead of NULL to indicate that there is no callback * function/handler. The compiler technically can't guarantee that a real @@ -593,26 +606,29 @@ static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG; node; \ node = interval_tree_iter_next(node, start, last)) \ -static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, - const struct kvm_hva_range *range) +static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, + const struct kvm_mmu_notifier_range *range) { - bool ret = false, locked = false; + struct kvm_mmu_notifier_return r = { + .ret = false, + .found_memslot = false, + }; struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; int i, idx; if (WARN_ON_ONCE(range->end <= range->start)) - return 0; + return r; /* A null handler is allowed if and only if on_lock() is provided. */ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && IS_KVM_NULL_FN(range->handler))) - return 0; + return r; idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct interval_tree_node *node; slots = __kvm_memslots(kvm, i); @@ -621,9 +637,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, unsigned long hva_start, hva_end; slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); - hva_start = max(range->start, slot->userspace_addr); - hva_end = min(range->end, slot->userspace_addr + - (slot->npages << PAGE_SHIFT)); + hva_start = max_t(unsigned long, range->start, slot->userspace_addr); + hva_end = min_t(unsigned long, range->end, + slot->userspace_addr + (slot->npages << PAGE_SHIFT)); /* * To optimize for the likely case where the address @@ -633,6 +649,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, */ gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; + /* + * HVA-based notifications aren't relevant to private + * mappings as they don't have a userspace mapping. + */ + gfn_range.attr_filter = KVM_FILTER_SHARED; /* * {gfn(page) | page intersects with [hva_start, hva_end)} = @@ -642,71 +663,66 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot); gfn_range.slot = slot; - if (!locked) { - locked = true; + if (!r.found_memslot) { + r.found_memslot = true; KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) - range->on_lock(kvm, range->start, range->end); + range->on_lock(kvm); + if (IS_KVM_NULL_FN(range->handler)) break; } - ret |= range->handler(kvm, &gfn_range); + r.ret |= range->handler(kvm, &gfn_range); } } - if (range->flush_on_ret && ret) + if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); - if (locked) { + if (r.found_memslot) KVM_MMU_UNLOCK(kvm); - if (!IS_KVM_NULL_FN(range->on_unlock)) - range->on_unlock(kvm); - } srcu_read_unlock(&kvm->srcu, idx); - /* The notifiers are averse to booleans. :-( */ - return (int)ret; + return r; } static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, unsigned long start, unsigned long end, union kvm_mmu_notifier_arg arg, - hva_handler_t handler) + gfn_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - const struct kvm_hva_range range = { + const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .arg = arg, .handler = handler, .on_lock = (void *)kvm_null_fn, - .on_unlock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; - return __kvm_handle_hva_range(kvm, &range); + return __kvm_handle_hva_range(kvm, &range).ret; } static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn, unsigned long start, unsigned long end, - hva_handler_t handler) + gfn_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - const struct kvm_hva_range range = { + const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .handler = handler, .on_lock = (void *)kvm_null_fn, - .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; - return __kvm_handle_hva_range(kvm, &range); + return __kvm_handle_hva_range(kvm, &range).ret; } static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -751,16 +767,29 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn); } -void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, - unsigned long end) +void kvm_mmu_invalidate_begin(struct kvm *kvm) { + lockdep_assert_held_write(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ kvm->mmu_invalidate_in_progress++; + if (likely(kvm->mmu_invalidate_in_progress == 1)) { + kvm->mmu_invalidate_range_start = INVALID_GPA; + kvm->mmu_invalidate_range_end = INVALID_GPA; + } +} + +void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end) +{ + lockdep_assert_held_write(&kvm->mmu_lock); + + WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress); + + if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) { kvm->mmu_invalidate_range_start = start; kvm->mmu_invalidate_range_end = end; } else { @@ -780,16 +809,21 @@ void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, } } +bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) +{ + kvm_mmu_invalidate_range_add(kvm, range->start, range->end); + return kvm_unmap_gfn_range(kvm, range); +} + static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - const struct kvm_hva_range hva_range = { + const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, - .handler = kvm_unmap_gfn_range, + .handler = kvm_mmu_unmap_gfn_range, .on_lock = kvm_mmu_invalidate_begin, - .on_unlock = kvm_arch_guest_memory_reclaimed, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; @@ -821,14 +855,21 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end, hva_range.may_block); - __kvm_handle_hva_range(kvm, &hva_range); + /* + * If one or more memslots were found and thus zapped, notify arch code + * that guest memory has been reclaimed. This needs to be done *after* + * dropping mmu_lock, as x86's reclaim path is slooooow. + */ + if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot) + kvm_arch_guest_memory_reclaimed(kvm); return 0; } -void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start, - unsigned long end) +void kvm_mmu_invalidate_end(struct kvm *kvm) { + lockdep_assert_held_write(&kvm->mmu_lock); + /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have @@ -842,18 +883,24 @@ void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start, * in conjunction with the smp_rmb in mmu_invalidate_retry(). */ kvm->mmu_invalidate_in_progress--; + KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm); + + /* + * Assert that at least one range was added between start() and end(). + * Not adding a range isn't fatal, but it is a KVM bug. + */ + WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA); } static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - const struct kvm_hva_range hva_range = { + const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = (void *)kvm_null_fn, .on_lock = kvm_mmu_invalidate_end, - .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; @@ -872,8 +919,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, */ if (wake) rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); - - BUG_ON(kvm->mmu_invalidate_in_progress < 0); } static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, @@ -947,14 +992,14 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } -#else /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */ +#else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */ static int kvm_init_mmu_notifier(struct kvm *kvm) { return 0; } -#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ +#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */ #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_pm_notifier_call(struct notifier_block *bl, @@ -1000,6 +1045,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) /* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { + if (slot->flags & KVM_MEM_GUEST_MEMFD) + kvm_gmem_unbind(slot); + kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); @@ -1184,6 +1232,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + xa_init(&kvm->mem_attr_array); +#endif INIT_LIST_HEAD(&kvm->gpc_list); spin_lock_init(&kvm->gpc_lock); @@ -1208,7 +1259,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) goto out_err_no_irq_srcu; refcount_set(&kvm->users_count, 1); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { for (j = 0; j < 2; j++) { slots = &kvm->__memslots[i][j]; @@ -1274,7 +1325,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) out_err_no_debugfs: kvm_coalesced_mmio_free(kvm); out_no_coalesced_mmio: -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif @@ -1350,7 +1401,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); /* * At this point, pending calls to invalidate_range_start() @@ -1359,20 +1410,30 @@ static void kvm_destroy_vm(struct kvm *kvm) * No threads can be waiting in kvm_swap_active_memslots() as the * last reference on KVM has been dropped, but freeing * memslots would deadlock without this manual intervention. + * + * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU + * notifier between a start() and end(), then there shouldn't be any + * in-progress invalidations. */ WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); - kvm->mn_active_invalidate_count = 0; + if (kvm->mn_active_invalidate_count) + kvm->mn_active_invalidate_count = 0; + else + WARN_ON(kvm->mmu_invalidate_in_progress); #else kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { kvm_free_memslots(kvm, &kvm->__memslots[i][0]); kvm_free_memslots(kvm, &kvm->__memslots[i][1]); } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + xa_destroy(&kvm->mem_attr_array); +#endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); hardware_disable_all(); @@ -1574,13 +1635,34 @@ static void kvm_replace_memslot(struct kvm *kvm, } } -static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) +/* + * Flags that do not access any of the extra space of struct + * kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS + * only allows these. + */ +#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ + (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) + +static int check_memory_region_flags(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; -#ifdef __KVM_HAVE_READONLY_MEM - valid_flags |= KVM_MEM_READONLY; -#endif + if (kvm_arch_has_private_mem(kvm)) + valid_flags |= KVM_MEM_GUEST_MEMFD; + + /* Dirty logging private memory is not currently supported. */ + if (mem->flags & KVM_MEM_GUEST_MEMFD) + valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; + + /* + * GUEST_MEMFD is incompatible with read-only memslots, as writes to + * read-only memslots have emulated MMIO, not page fault, semantics, + * and KVM doesn't allow emulated MMIO for private memory. + */ + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) + valid_flags |= KVM_MEM_READONLY; if (mem->flags & ~valid_flags) return -EINVAL; @@ -1639,7 +1721,7 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) * space 0 will use generations 0, 2, 4, ... while address space 1 will * use generations 1, 3, 5, ... */ - gen += KVM_ADDRESS_SPACE_NUM; + gen += kvm_arch_nr_memslot_as_ids(kvm); kvm_arch_memslots_updated(kvm, gen); @@ -1976,7 +2058,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, * Must be called holding kvm->slots_lock for write. */ int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region2 *mem) { struct kvm_memory_slot *old, *new; struct kvm_memslots *slots; @@ -1986,7 +2068,7 @@ int __kvm_set_memory_region(struct kvm *kvm, int as_id, id; int r; - r = check_memory_region_flags(mem); + r = check_memory_region_flags(kvm, mem); if (r) return r; @@ -2005,7 +2087,11 @@ int __kvm_set_memory_region(struct kvm *kvm, !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; - if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) + if (mem->flags & KVM_MEM_GUEST_MEMFD && + (mem->guest_memfd_offset & (PAGE_SIZE - 1) || + mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset)) + return -EINVAL; + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM) return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; @@ -2043,6 +2129,9 @@ int __kvm_set_memory_region(struct kvm *kvm, if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) return -EINVAL; } else { /* Modify an existing slot. */ + /* Private memslots are immutable, they can only be deleted. */ + if (mem->flags & KVM_MEM_GUEST_MEMFD) + return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) @@ -2071,16 +2160,29 @@ int __kvm_set_memory_region(struct kvm *kvm, new->npages = npages; new->flags = mem->flags; new->userspace_addr = mem->userspace_addr; + if (mem->flags & KVM_MEM_GUEST_MEMFD) { + r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset); + if (r) + goto out; + } r = kvm_set_memslot(kvm, old, new, change); if (r) - kfree(new); + goto out_unbind; + + return 0; + +out_unbind: + if (mem->flags & KVM_MEM_GUEST_MEMFD) + kvm_gmem_unbind(new); +out: + kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region2 *mem) { int r; @@ -2092,7 +2194,7 @@ int kvm_set_memory_region(struct kvm *kvm, EXPORT_SYMBOL_GPL(kvm_set_memory_region); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) + struct kvm_userspace_memory_region2 *mem) { if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; @@ -2125,7 +2227,7 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, as_id = log->slot >> 16; id = (u16)log->slot; - if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); @@ -2187,7 +2289,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) as_id = log->slot >> 16; id = (u16)log->slot; - if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); @@ -2299,7 +2401,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm, as_id = log->slot >> 16; id = (u16)log->slot; - if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; if (log->first_page & 63) @@ -2371,6 +2473,211 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static u64 kvm_supported_mem_attributes(struct kvm *kvm) +{ + if (!kvm || kvm_arch_has_private_mem(kvm)) + return KVM_MEMORY_ATTRIBUTE_PRIVATE; + + return 0; +} + +/* + * Returns true if _all_ gfns in the range [@start, @end) have attributes + * such that the bits in @mask match @attrs. + */ +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long mask, unsigned long attrs) +{ + XA_STATE(xas, &kvm->mem_attr_array, start); + unsigned long index; + void *entry; + + mask &= kvm_supported_mem_attributes(kvm); + if (attrs & ~mask) + return false; + + if (end == start + 1) + return (kvm_get_memory_attributes(kvm, start) & mask) == attrs; + + guard(rcu)(); + if (!attrs) + return !xas_find(&xas, end - 1); + + for (index = start; index < end; index++) { + do { + entry = xas_next(&xas); + } while (xas_retry(&xas, entry)); + + if (xas.xa_index != index || + (xa_to_value(entry) & mask) != attrs) + return false; + } + + return true; +} + +static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, + struct kvm_mmu_notifier_range *range) +{ + struct kvm_gfn_range gfn_range; + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + struct kvm_memslot_iter iter; + bool found_memslot = false; + bool ret = false; + int i; + + gfn_range.arg = range->arg; + gfn_range.may_block = range->may_block; + + /* + * If/when KVM supports more attributes beyond private .vs shared, this + * _could_ set KVM_FILTER_{SHARED,PRIVATE} appropriately if the entire target + * range already has the desired private vs. shared state (it's unclear + * if that is a net win). For now, KVM reaches this point if and only + * if the private flag is being toggled, i.e. all mappings are in play. + */ + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + slots = __kvm_memslots(kvm, i); + + kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) { + slot = iter.slot; + gfn_range.slot = slot; + + gfn_range.start = max(range->start, slot->base_gfn); + gfn_range.end = min(range->end, slot->base_gfn + slot->npages); + if (gfn_range.start >= gfn_range.end) + continue; + + if (!found_memslot) { + found_memslot = true; + KVM_MMU_LOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_lock)) + range->on_lock(kvm); + } + + ret |= range->handler(kvm, &gfn_range); + } + } + + if (range->flush_on_ret && ret) + kvm_flush_remote_tlbs(kvm); + + if (found_memslot) + KVM_MMU_UNLOCK(kvm); +} + +static bool kvm_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Unconditionally add the range to the invalidation set, regardless of + * whether or not the arch callback actually needs to zap SPTEs. E.g. + * if KVM supports RWX attributes in the future and the attributes are + * going from R=>RW, zapping isn't strictly necessary. Unconditionally + * adding the range allows KVM to require that MMU invalidations add at + * least one range between begin() and end(), e.g. allows KVM to detect + * bugs where the add() is missed. Relaxing the rule *might* be safe, + * but it's not obvious that allowing new mappings while the attributes + * are in flux is desirable or worth the complexity. + */ + kvm_mmu_invalidate_range_add(kvm, range->start, range->end); + + return kvm_arch_pre_set_memory_attributes(kvm, range); +} + +/* Set @attributes for the gfn range [@start, @end). */ +static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long attributes) +{ + struct kvm_mmu_notifier_range pre_set_range = { + .start = start, + .end = end, + .arg.attributes = attributes, + .handler = kvm_pre_set_memory_attributes, + .on_lock = kvm_mmu_invalidate_begin, + .flush_on_ret = true, + .may_block = true, + }; + struct kvm_mmu_notifier_range post_set_range = { + .start = start, + .end = end, + .arg.attributes = attributes, + .handler = kvm_arch_post_set_memory_attributes, + .on_lock = kvm_mmu_invalidate_end, + .may_block = true, + }; + unsigned long i; + void *entry; + int r = 0; + + entry = attributes ? xa_mk_value(attributes) : NULL; + + mutex_lock(&kvm->slots_lock); + + /* Nothing to do if the entire range as the desired attributes. */ + if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) + goto out_unlock; + + /* + * Reserve memory ahead of time to avoid having to deal with failures + * partway through setting the new attributes. + */ + for (i = start; i < end; i++) { + r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); + if (r) + goto out_unlock; + + cond_resched(); + } + + kvm_handle_gfn_range(kvm, &pre_set_range); + + for (i = start; i < end; i++) { + r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, + GFP_KERNEL_ACCOUNT)); + KVM_BUG_ON(r, kvm); + cond_resched(); + } + + kvm_handle_gfn_range(kvm, &post_set_range); + +out_unlock: + mutex_unlock(&kvm->slots_lock); + + return r; +} +static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, + struct kvm_memory_attributes *attrs) +{ + gfn_t start, end; + + /* flags is currently not used. */ + if (attrs->flags) + return -EINVAL; + if (attrs->attributes & ~kvm_supported_mem_attributes(kvm)) + return -EINVAL; + if (attrs->size == 0 || attrs->address + attrs->size < attrs->address) + return -EINVAL; + if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size)) + return -EINVAL; + + start = attrs->address >> PAGE_SHIFT; + end = (attrs->address + attrs->size) >> PAGE_SHIFT; + + /* + * xarray tracks data using "unsigned long", and as a result so does + * KVM. For simplicity, supports generic attributes only on 64-bit + * architectures. + */ + BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long)); + + return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); +} +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ + struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); @@ -3683,7 +3990,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); /* * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. */ -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +void __kvm_vcpu_kick(struct kvm_vcpu *vcpu, bool wait) { int me, cpu; @@ -3712,13 +4019,24 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) */ if (kvm_arch_vcpu_should_kick(vcpu)) { cpu = READ_ONCE(vcpu->cpu); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - smp_send_reschedule(cpu); + if (cpu != me && (unsigned int)cpu < nr_cpu_ids && cpu_online(cpu)) { + /* + * Use a reschedule IPI to kick the vCPU if the caller + * doesn't need to wait for a response, as KVM allows + * kicking vCPUs while IRQs are disabled, but using the + * SMP function call framework with IRQs disabled can + * deadlock due to taking cross-CPU locks. + */ + if (wait) + smp_call_function_single(cpu, ack_kick, NULL, wait); + else + smp_send_reschedule(cpu); + } } out: put_cpu(); } -EXPORT_SYMBOL_GPL(kvm_vcpu_kick); +EXPORT_SYMBOL_GPL(__kvm_vcpu_kick); #endif /* !CONFIG_S390 */ int kvm_vcpu_yield_to(struct kvm_vcpu *target) @@ -4153,6 +4471,52 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) return fd; } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + int idx; + long r; + u64 full_size; + + if (range->flags) + return -EINVAL; + + if (!PAGE_ALIGNED(range->gpa) || + !PAGE_ALIGNED(range->size) || + range->gpa + range->size <= range->gpa) + return -EINVAL; + + vcpu_load(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + + full_size = range->size; + do { + if (signal_pending(current)) { + r = -EINTR; + break; + } + + r = kvm_arch_vcpu_pre_fault_memory(vcpu, range); + if (WARN_ON_ONCE(r == 0 || r == -EIO)) + break; + + if (r < 0) + break; + + range->size -= r; + range->gpa += r; + cond_resched(); + } while (range->size); + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + vcpu_put(vcpu); + + /* Return success if at least one page was mapped successfully. */ + return full_size == range->size ? r : 0; +} +#endif + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4360,6 +4724,20 @@ static long kvm_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_get_stats_fd(vcpu); break; } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY + case KVM_PRE_FAULT_MEMORY: { + struct kvm_pre_fault_memory range; + + r = -EFAULT; + if (copy_from_user(&range, argp, sizeof(range))) + break; + r = kvm_vcpu_pre_fault_memory(vcpu, &range); + /* Pass back leftover range. */ + if (copy_to_user(argp, &range, sizeof(range))) + r = -EFAULT; + break; + } +#endif default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } @@ -4580,6 +4958,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: + case KVM_CAP_USER_MEMORY2: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: case KVM_CAP_INTERNAL_ERROR_DATA: @@ -4608,9 +4987,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif -#if KVM_ADDRESS_SPACE_NUM > 1 +#if KVM_MAX_NR_ADDRESS_SPACES > 1 case KVM_CAP_MULTI_ADDRESS_SPACE: - return KVM_ADDRESS_SPACE_NUM; + if (kvm) + return kvm_arch_nr_memslot_as_ids(kvm); + return KVM_MAX_NR_ADDRESS_SPACES; #endif case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; @@ -4632,6 +5013,14 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: return 1; +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + case KVM_CAP_MEMORY_ATTRIBUTES: + return kvm_supported_mem_attributes(kvm); +#endif +#ifdef CONFIG_KVM_PRIVATE_MEM + case KVM_CAP_GUEST_MEMFD: + return !kvm || kvm_arch_has_private_mem(kvm); +#endif default: break; } @@ -4710,7 +5099,7 @@ bool kvm_are_all_memslots_empty(struct kvm *kvm) lockdep_assert_held(&kvm->slots_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) return false; } @@ -4835,6 +5224,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) return fd; } +#define SANITY_CHECK_MEM_REGION_FIELD(field) \ +do { \ + BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \ + offsetof(struct kvm_userspace_memory_region2, field)); \ + BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \ + sizeof_field(struct kvm_userspace_memory_region2, field)); \ +} while (0) + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4857,15 +5254,39 @@ static long kvm_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap); break; } + case KVM_SET_USER_MEMORY_REGION2: case KVM_SET_USER_MEMORY_REGION: { - struct kvm_userspace_memory_region kvm_userspace_mem; + struct kvm_userspace_memory_region2 mem; + unsigned long size; + + if (ioctl == KVM_SET_USER_MEMORY_REGION) { + /* + * Fields beyond struct kvm_userspace_memory_region shouldn't be + * accessed, but avoid leaking kernel memory in case of a bug. + */ + memset(&mem, 0, sizeof(mem)); + size = sizeof(struct kvm_userspace_memory_region); + } else { + size = sizeof(struct kvm_userspace_memory_region2); + } + + /* Ensure the common parts of the two structs are identical. */ + SANITY_CHECK_MEM_REGION_FIELD(slot); + SANITY_CHECK_MEM_REGION_FIELD(flags); + SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr); + SANITY_CHECK_MEM_REGION_FIELD(memory_size); + SANITY_CHECK_MEM_REGION_FIELD(userspace_addr); r = -EFAULT; - if (copy_from_user(&kvm_userspace_mem, argp, - sizeof(kvm_userspace_mem))) + if (copy_from_user(&mem, argp, size)) + goto out; + + r = -EINVAL; + if (ioctl == KVM_SET_USER_MEMORY_REGION && + (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS)) goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem); + r = kvm_vm_ioctl_set_memory_region(kvm, &mem); break; } case KVM_GET_DIRTY_LOG: { @@ -4993,6 +5414,18 @@ static long kvm_vm_ioctl(struct file *filp, break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + case KVM_SET_MEMORY_ATTRIBUTES: { + struct kvm_memory_attributes attrs; + + r = -EFAULT; + if (copy_from_user(&attrs, argp, sizeof(attrs))) + goto out; + + r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); + break; + } +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; @@ -5020,6 +5453,18 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_GET_STATS_FD: r = kvm_vm_ioctl_get_stats_fd(kvm); break; +#ifdef CONFIG_KVM_PRIVATE_MEM + case KVM_CREATE_GUEST_MEMFD: { + struct kvm_create_guest_memfd guest_memfd; + + r = -EFAULT; + if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd))) + goto out; + + r = kvm_gmem_create(kvm, &guest_memfd); + break; + } +#endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } @@ -6419,6 +6864,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (WARN_ON_ONCE(r)) goto err_vfio; + kvm_gmem_init(module); + /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index 180f1a09e6ba7bc8b25275e6f938a1484c6e5f30..ecefc7ec51af8516c14c13bf0ad68ad1bc369e77 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -37,4 +37,30 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, } #endif /* HAVE_KVM_PFNCACHE */ +#ifdef CONFIG_KVM_PRIVATE_MEM +void kvm_gmem_init(struct module *module); +int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args); +int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset); +void kvm_gmem_unbind(struct kvm_memory_slot *slot); +#else +static inline void kvm_gmem_init(struct module *module) +{ + +} + +static inline int kvm_gmem_bind(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset) +{ + WARN_ON_ONCE(1); + return -EIO; +} + +static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + WARN_ON_ONCE(1); +} +#endif /* CONFIG_KVM_PRIVATE_MEM */ + #endif /* __KVM_MM_H__ */