diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9a9ce86f86f27fcd4c6b2bb2290660b5c2a0b815..9db3b46aa40648af7fd517483a13375d70b0c2f9 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4312,7 +4312,7 @@ operating system that uses the PIT for timing (e.g. Linux 2.4.x). 4.100 KVM_PPC_CONFIGURE_V3_MMU ------------------------------ -:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 +:Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 :Architectures: ppc :Type: vm ioctl :Parameters: struct kvm_ppc_mmuv3_cfg (in) @@ -4346,7 +4346,7 @@ the Power ISA V3.00, Book III section 5.7.6.1. 4.101 KVM_PPC_GET_RMMU_INFO --------------------------- -:Capability: KVM_CAP_PPC_RADIX_MMU +:Capability: KVM_CAP_PPC_MMU_RADIX :Architectures: ppc :Type: vm ioctl :Parameters: struct kvm_ppc_rmmu_info (out) @@ -6317,6 +6317,67 @@ 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 ======================== @@ -8082,7 +8143,7 @@ capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this will disable the use of APIC hardware virtualization even if supported by the CPU, as it's incompatible with SynIC auto-EOI behavior. -8.3 KVM_CAP_PPC_RADIX_MMU +8.3 KVM_CAP_PPC_MMU_RADIX ------------------------- :Architectures: ppc @@ -8092,7 +8153,7 @@ available, means that the kernel can support guests using the radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 processor). -8.4 KVM_CAP_PPC_HASH_MMU_V3 +8.4 KVM_CAP_PPC_MMU_HASH_V3 --------------------------- :Architectures: ppc diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index 3381556d596ddc34dc6aae0c247bd77ae15c8876..1ddb6a86ce7ff57755349ac1e92ea3826a1dba07 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -95,13 +95,19 @@ 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 */ - __u32 pad[9]; + __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). @@ -112,7 +118,8 @@ They behave as if: KVM_SEV_ES_INIT * the ``flags`` and ``vmsa_features`` fields of ``struct kvm_sev_init`` are - set to zero + 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 @@ -459,6 +466,112 @@ 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 ==================== @@ -490,9 +603,11 @@ 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/anolis/configs/L1-RECOMMEND/x86/CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE b/anolis/configs/L1-RECOMMEND/x86/CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE new file mode 100644 index 0000000000000000000000000000000000000000..d5e3841a448c2a6e176416d8cc1906cc3f95bcf7 --- /dev/null +++ b/anolis/configs/L1-RECOMMEND/x86/CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE @@ -0,0 +1 @@ +CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE=y diff --git a/anolis/configs/L1-RECOMMEND/x86/CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE b/anolis/configs/L1-RECOMMEND/x86/CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE new file mode 100644 index 0000000000000000000000000000000000000000..1371f06c5b4cccdcd8a3727e14b3168765bff66b --- /dev/null +++ b/anolis/configs/L1-RECOMMEND/x86/CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE @@ -0,0 +1 @@ +CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE=y diff --git a/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES new file mode 100644 index 0000000000000000000000000000000000000000..bb5b79df4f2575489397a598c535de40e8df328a --- /dev/null +++ b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES @@ -0,0 +1 @@ +CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES=y diff --git a/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY new file mode 100644 index 0000000000000000000000000000000000000000..7eea0654f002b5699cd853d41741f42b0e7397b5 --- /dev/null +++ b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY @@ -0,0 +1 @@ +CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY=y diff --git a/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_PRIVATE_MEM b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_PRIVATE_MEM new file mode 100644 index 0000000000000000000000000000000000000000..544d061dc069e50c711266ed7b2acf3d4d154d90 --- /dev/null +++ b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_GENERIC_PRIVATE_MEM @@ -0,0 +1 @@ +CONFIG_KVM_GENERIC_PRIVATE_MEM=y diff --git a/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_PRIVATE_MEM b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_PRIVATE_MEM new file mode 100644 index 0000000000000000000000000000000000000000..b4b74d6cb2084101a4d59f483b42f0772d6b8a45 --- /dev/null +++ b/anolis/configs/L1-RECOMMEND/x86/CONFIG_KVM_PRIVATE_MEM @@ -0,0 +1 @@ +CONFIG_KVM_PRIVATE_MEM=y diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 6affff6fe8e0ee5282fc9bb330db7e98898b1678..4201ebc3fa8f63faf104a5147629c6f3ee7fca75 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -304,26 +304,6 @@ 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 @@ -383,6 +363,85 @@ 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 * @@ -433,7 +492,7 @@ 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. * @@ -448,7 +507,7 @@ 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. */ @@ -479,7 +538,20 @@ 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)) @@ -505,85 +577,6 @@ 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/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/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 3eca5b380d4d40fd63e25ec45f64eef99db8c6d0..b53440626b30c77a5ec1b23afa90547caab371b5 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -136,6 +136,9 @@ KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); KVM_X86_OP_OPTIONAL(get_untagged_addr) 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) KVM_X86_OP_OPTIONAL(vm_attestation) KVM_X86_OP_OPTIONAL(arch_hypercall) KVM_X86_OP_OPTIONAL(control_pre_system_reset) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8fb2e23ff1a080722abd5a89e6ffa7514d66620a..225bee2d3c5073a2ba3db9c07dbd8dc64a29848c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -113,6 +113,7 @@ 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(34) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -246,28 +247,31 @@ 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 | \ @@ -1284,6 +1288,7 @@ struct kvm_arch { 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; @@ -1812,6 +1817,9 @@ struct kvm_x86_ops { gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); 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); /* * Interfaces for HYGON CSV guest @@ -1860,6 +1868,7 @@ 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; @@ -1931,6 +1940,7 @@ 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); 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 e7d4ec325bc907271d4dfea55140c8a4192a19e1..b7a2480d296399ae4ac37b7a1293722cc9b8d205 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -718,7 +718,9 @@ #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_IBPB_ON_ENTRY_BIT 23 +#define MSR_AMD64_SNP_IBPB_ON_ENTRY BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT) +#define MSR_AMD64_SNP_RESV_BIT 24 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f 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 4bec4cfb775a4df5a1c16aa6051da8f8b9918626..1698bd650ece5e01178247b50dc6db2e52880a5d 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -90,6 +90,9 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs); /* 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 @@ -115,6 +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; }; @@ -139,7 +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; @@ -268,6 +319,7 @@ int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immut 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_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } @@ -281,6 +333,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as 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 87a7b917d30ea9fe0998df0d11f84e9bdcc00702..604cb618167ae44486f382771eea3b6570c8268c 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -285,7 +285,14 @@ 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) + +#define SVM_SEV_FEAT_INT_INJ_MODES \ + (SVM_SEV_FEAT_RESTRICTED_INJECTION | \ + SVM_SEV_FEAT_ALTERNATE_INJECTION) struct vmcb_seg { u16 selector; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index e85d59dd6e1e8cf57b6adcc970365156ef4f2dec..ddc9691054e5788e3a17f225283801baeb8da0d2 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -690,6 +690,11 @@ enum sev_cmd_id { /* 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, }; @@ -704,7 +709,9 @@ struct kvm_sev_cmd { struct kvm_sev_init { __u64 vmsa_features; __u32 flags; - __u32 pad[9]; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; }; struct kvm_sev_launch_start { @@ -815,6 +822,48 @@ struct kvm_sev_receive_update_data { __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) @@ -865,5 +914,6 @@ struct kvm_hyperv_eventfd { #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/e820.c b/arch/x86/kernel/e820.c index 77188777797c292755ac1d94b72b6284da505d97..658c8dc8aa71cca50441fd22d563aad156c91aef 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -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: */ @@ -805,7 +806,7 @@ 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(); } @@ -1015,17 +1016,6 @@ 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)); @@ -1037,12 +1027,9 @@ 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; @@ -1050,7 +1037,6 @@ 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"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e9d4292ac387c41ef549c44d724bf74fdecdef61..c9ae24996dc064f1cf2ec094f363dde4b2721f1d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1171,7 +1171,7 @@ void __init setup_arch(char **cmdline_p) * Needs to run after memblock setup because it needs the physical * memory size. */ - sev_setup_arch(); + mem_encrypt_setup_arch(); cc_random_init(); efi_fake_memmap(); diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index b469b6b0706b8257ac63dc45eb656e980886c886..8ae582b984f2d8ce3fabba5a504a4263e6f5672f 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -79,6 +79,7 @@ static const char * const sev_status_feat_names[] = { [MSR_AMD64_SNP_IBS_VIRT_BIT] = "IBSVirt", [MSR_AMD64_SNP_VMSA_REG_PROT_BIT] = "VMSARegProt", [MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt", + [MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT] = "IBPBOnEntry", }; /* For early boot hypervisor communication in SEV-ES enabled guests */ @@ -649,7 +650,7 @@ 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; @@ -663,9 +664,9 @@ 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; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a5a5140989de550a458822267f985256a65b727a..896f2eb0a16bd1973801aff2a66f28082584d20a 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -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 @@ -128,6 +129,9 @@ config KVM_AMD_SEV 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. diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index ade33a54306d2bbb431c84d913519c57b624e660..0169c8d25adeb7e281e180c036ef7d748ebc5049 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -215,7 +215,7 @@ 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 +236,7 @@ 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 +246,6 @@ 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 de555993713f2b3bd5ffb4adff135535d7966243..4b3443b98c651d62bd85f5ad291806c6d0825724 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3345,7 +3345,7 @@ 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 @@ -3356,6 +3356,26 @@ 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: * @@ -3456,7 +3476,7 @@ 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); @@ -4245,24 +4265,28 @@ 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; @@ -4275,7 +4299,16 @@ 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) @@ -4303,6 +4336,25 @@ static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, 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 req_max_level; +} + static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { @@ -4320,9 +4372,9 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, return r; } - fault->max_level = min(kvm_max_level_for_order(max_order), - fault->max_level); 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; } @@ -4380,7 +4432,7 @@ 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; } } @@ -4509,6 +4561,9 @@ 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); @@ -4602,6 +4657,82 @@ 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. + */ + kvm_mmu_reload(vcpu); + + 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; @@ -5794,20 +5925,23 @@ 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); @@ -5816,15 +5950,22 @@ 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; @@ -6698,6 +6839,7 @@ 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) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 0669a8a668cacd4d0be68affbecbb686524c5213..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. */ @@ -280,7 +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, @@ -298,7 +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 = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), + .is_private = err & PFERR_PRIVATE_ACCESS, }; int r; @@ -322,20 +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/sev.c b/arch/x86/kvm/svm/sev.c index 7f21792f958e7d53afaf320cba14788e78d18ed0..04ca5ede700af5ea84cc48bae4cc5962bcdf75fe 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -26,6 +27,7 @@ #include #include #include +#include #include "mmu.h" #include "x86.h" @@ -36,9 +38,12 @@ #include "csv.h" -#define GHCB_VERSION_MAX 1ULL +#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) + /* enable/disable SEV support */ static bool sev_enabled = true; module_param_named(sev, sev_enabled, bool, 0444); @@ -47,11 +52,36 @@ 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 = true; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); 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); static DEFINE_MUTEX(sev_bitmap_lock); @@ -62,6 +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; @@ -88,12 +120,17 @@ 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; } @@ -295,6 +332,53 @@ 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; @@ -312,6 +396,78 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_decommission(handle); } +/* + * 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) @@ -332,12 +488,27 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, 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 = 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 @@ -388,6 +559,10 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, if (ret) goto e_free; + /* This needs to happen after SEV/SNP firmware initialization. */ + if (vm_type == KVM_X86_SNP_VM && snp_guest_req_init(kvm)) + goto e_free; + INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); sev->need_init = false; @@ -411,6 +586,7 @@ 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; @@ -418,6 +594,14 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) 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); } @@ -430,7 +614,8 @@ static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp) 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_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))) @@ -2100,6 +2285,418 @@ int sev_dev_get_attr(u32 group, u64 attr, u64 *val) } } +/* + * 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; + } + + return context; +} + +static int snp_bind_asid(struct kvm *kvm, int *error) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + 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); +} + +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 sev_data_snp_launch_start start = {0}; + struct kvm_sev_snp_launch_start params; + int rc; + + if (!sev_snp_guest(kvm)) + return -ENOTTY; + + 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; + + sev->snp_context = snp_context_create(kvm, argp); + if (!sev->snp_context) + return -ENOTTY; + + if (params.flags) + return -EINVAL; + + if (params.policy & ~SNP_POLICY_MASK_VALID) + return -EINVAL; + + /* 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; + + 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; + } + + 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; + } + + return 0; + +e_free_context: + snp_decommission_context(kvm); + + return rc; +} + +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_svm(kvm)->sev_info; + 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; + int level; + + if (!kvm_mem_is_private(kvm, gfn)) { + pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n", + __func__, gfn); + ret = -EINVAL; + goto err; + } + + 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 = -EINVAL; + goto err; + } + + if (src) { + void *vaddr = kmap_local_pfn(pfn + i); + + ret = copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE); + if (ret) + 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_svm(kvm)->sev_info; + 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_svm(kvm)->sev_info; + 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_svm(kvm)->sev_info; + 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; @@ -2123,6 +2720,15 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) 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) { @@ -2187,6 +2793,15 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) 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; @@ -2383,11 +2998,36 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) return ret; } -void sev_vm_destroy(struct kvm *kvm) +static int snp_decommission_context(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct list_head *head = &sev->regions_list; - struct list_head *pos, *q; + 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 list_head *head = &sev->regions_list; + struct list_head *pos, *q; if (!sev_guest(kvm)) return; @@ -2424,7 +3064,19 @@ 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); } @@ -2438,6 +3090,10 @@ void __init sev_set_cpu_caps(void) 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 @@ -2459,6 +3115,7 @@ static void sev_install_hooks(void) void __init sev_hardware_setup(void) { 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; @@ -2553,6 +3210,7 @@ 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)) @@ -2570,9 +3228,15 @@ 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; @@ -2669,7 +3333,13 @@ 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(); @@ -2684,6 +3354,18 @@ 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); @@ -2692,6 +3374,7 @@ 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); @@ -2890,10 +3573,31 @@ 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; @@ -2924,6 +3628,9 @@ 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; @@ -3086,10 +3793,539 @@ 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_svm(svm->vcpu.kvm)->sev_info; + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_vcpu *target_vcpu; + struct vcpu_svm *target_svm; + unsigned int request; + unsigned int apic_id; + bool kick; + 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); + + /* + * The target vCPU is valid, so the vCPU will be kicked unless the + * request is for CREATE_ON_INIT. For any errors at this stage, the + * kick will place the vCPU in an non-runnable state. + */ + kick = true; + + mutex_lock(&target_svm->sev_es.snp_vmsa_mutex); + + target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE; + target_svm->sev_es.snp_ap_waiting_for_reset = true; + + /* Interrupt injection mode shouldn't change for AP creation */ + if (request < SVM_VMGEXIT_AP_DESTROY) { + u64 sev_features; + + sev_features = vcpu->arch.regs[VCPU_REGS_RAX]; + sev_features ^= sev->vmsa_features; + + if (sev_features & SVM_SEV_FEAT_INT_INJ_MODES) { + vcpu_unimpl(vcpu, "vmgexit: invalid AP injection mode [%#lx] from guest\n", + vcpu->arch.regs[VCPU_REGS_RAX]); + ret = -EINVAL; + goto out; + } + } + + switch (request) { + case SVM_VMGEXIT_AP_CREATE_ON_INIT: + kick = false; + fallthrough; + case SVM_VMGEXIT_AP_CREATE: + 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. + */ + 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: + break; + default: + vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n", + request); + ret = -EINVAL; + break; + } + +out: + if (kick) { + kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu); + kvm_vcpu_kick(target_vcpu); + } + + mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex); + + return ret; +} + +static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa) +{ + 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; + + 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 int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa) +{ + 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_svm(vcpu->kvm)->sev_info; u64 ghcb_info; int ret = 1; @@ -3100,7 +4336,7 @@ 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; @@ -3142,6 +4378,60 @@ 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; @@ -3154,12 +4444,7 @@ 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 */ @@ -3170,6 +4455,14 @@ 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) @@ -3205,6 +4498,13 @@ 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; @@ -3241,6 +4541,7 @@ 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: { @@ -3265,6 +4566,41 @@ 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", @@ -3358,7 +4694,7 @@ 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 */ @@ -3420,13 +4756,18 @@ 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_svm(vcpu->kvm)->sev_info; + /* * 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 vcpu_svm *svm, struct sev_es_save_area *hostsa) @@ -3479,15 +4820,31 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) return; } - /* - * 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. - */ - if (!svm->sev_es.ghcb) - 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); - ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); + 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) @@ -3521,3 +4878,271 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) 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_svm(kvm)->sev_info; + 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; + + 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 1f217791a0d5aa6a93a256d2ebc4a66fb6b877d2..e1a4dff6478c40f0897bf290cfea7aaeea804eda 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1442,6 +1442,9 @@ 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) @@ -2096,15 +2099,33 @@ 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) @@ -2876,10 +2897,24 @@ 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 && @@ -3042,6 +3077,10 @@ 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: @@ -5067,8 +5106,12 @@ static int svm_vm_init(struct kvm *kvm) if (type != KVM_X86_DEFAULT_VM && type != KVM_X86_SW_PROTECTED_VM) { - kvm->arch.has_protected_state = (type == KVM_X86_SEV_ES_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) @@ -5259,6 +5302,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .alloc_apic_backing_page = svm_alloc_apic_backing_page, .arch_hypercall = kvm_hygon_arch_hypercall, + + .gmem_prepare = sev_gmem_prepare, + .gmem_invalidate = sev_gmem_invalidate, + .private_max_mapping_level = sev_private_max_mapping_level, }; /* diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index fb54999d2cecb1d88c2c8c0f81a0b4f36f4a52ce..2d5b16517b671f30e56d8c4a8c5957165e60c899 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -90,11 +90,16 @@ struct kvm_sev_info { 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 { @@ -200,6 +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; @@ -208,12 +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 { @@ -356,6 +374,23 @@ static __always_inline bool sev_es_guest(struct kvm *kvm) #endif } +static __always_inline bool sev_snp_guest(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_AMD_SEV + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) && + !WARN_ON_ONCE(!sev_es_guest(kvm)); +#else + return 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) { vmcb->control.clean = 0; @@ -712,6 +747,11 @@ void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); 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); @@ -725,6 +765,18 @@ 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 15144cd5545c64ade46cad2da86a50ca1ce41efe..11b201ed54d08c93421dce1352857fc6f7f4c9c5 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1934,6 +1934,37 @@ TRACE_EVENT(kvm_csv3_sp_remove, __entry->track_pfn, __entry->track_hva, __entry->order) ); +/* + * 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/x86.c b/arch/x86/kvm/x86.c index dc8ed6d22374969655c64409f9561413f1736038..8df9e19d39ed78568ef1e3eb4a03707f5a3d952e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -96,7 +96,6 @@ struct kvm_caps kvm_caps __read_mostly = { .supported_mce_cap = MCG_CTL_P | MCG_SER_P, - .supported_vm_types = BIT(KVM_X86_DEFAULT_VM), }; EXPORT_SYMBOL_GPL(kvm_caps); @@ -4569,6 +4568,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 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; @@ -9710,6 +9712,8 @@ 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; @@ -10882,6 +10886,14 @@ 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 || @@ -12607,6 +12619,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) 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) @@ -13148,6 +13163,9 @@ 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)) return true; @@ -13595,6 +13613,24 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +bool kvm_arch_gmem_prepare_needed(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_SNP_VM; +} + +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) { @@ -13980,6 +14016,7 @@ 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); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_csv3_sp_insert_dup); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_csv3_sp_insert); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_csv3_sp_hit); diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 183c324cfbd056b44f3ba49627a80833851b1bf6..064cd8bbdbdd0df01e1ff1f84a3f5e95aa28779d 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -12,6 +12,7 @@ #include #include #include +#include #include @@ -102,3 +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 394d799981019338f49d655aacf4962ff2fa467a..22f535bd2554daaee5985f8890327e8fc6e7fb61 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/sev.c b/arch/x86/virt/svm/sev.c index ab0e8448bb6eb2bfbc4fab29321cd0ddbe876f7e..0ce17766c0e5230821cd77cf430a838772cfe1f6 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -120,7 +120,7 @@ static __init void snp_enable(void *arg) bool snp_probe_rmptable_info(void) { - u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end; + u64 rmp_sz, rmp_base, rmp_end; rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); rdmsrl(MSR_AMD64_RMP_END, rmp_end); @@ -137,32 +137,51 @@ bool snp_probe_rmptable_info(void) rmp_sz = rmp_end - rmp_base + 1; - /* - * Calculate the amount the 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 (PHYS_PFN(rmp_end) > max_pfn) - max_rmp_pfn = PHYS_PFN(rmp_end); - - calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ; - - if (calc_rmp_sz > rmp_sz) { - pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", - calc_rmp_sz, rmp_sz); - return false; - } - probed_rmp_base = rmp_base; probed_rmp_size = rmp_sz; pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", - probed_rmp_base, probed_rmp_base + probed_rmp_size - 1); + rmp_base, rmp_end); return true; } +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); + e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + } +} + +void __init snp_fixup_e820_tables(void) +{ + __snp_fixup_e820_tables(probed_rmp_base); + __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size); +} + /* * Do the necessary preparations which are verified by the firmware as * described in the SNP_INIT_EX firmware command description in the SNP @@ -170,9 +189,8 @@ bool snp_probe_rmptable_info(void) */ static int __init snp_rmptable_init(void) { + u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val; void *rmptable_start; - u64 rmptable_size; - u64 val; if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; @@ -183,10 +201,28 @@ static int __init snp_rmptable_init(void) if (!probed_rmp_size) goto nosnp; + rmp_end = probed_rmp_base + probed_rmp_size - 1; + + /* + * Calculate the amount the 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); + goto nosnp; + } + rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB); if (!rmptable_start) { pr_err("Failed to map RMP table\n"); - return 1; + goto nosnp; } /* diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index d0606b77184e6f0f5edf3ed797eaf1da4b51feba..3246bed169184fb1d882a57fa04c6b67a2f29553 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -1707,10 +1707,16 @@ static int sev_update_firmware(struct device *dev) static int __sev_snp_shutdown_locked(int *error, bool panic) { - struct sev_device *sev = psp_master->sev_data; + 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; @@ -2397,9 +2403,22 @@ static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) static void sev_firmware_shutdown(struct sev_device *sev) { - mutex_lock(&sev_cmd_mutex); + 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; /* void return - bail out; cannot propagate -EBUSY */ + } else { + mutex_lock(&sev_cmd_mutex); + } + __sev_firmware_shutdown(sev, false); - mutex_unlock(&sev_cmd_mutex); + + 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); } void sev_dev_destroy(struct psp_device *psp) @@ -2421,18 +2440,30 @@ static int snp_shutdown_on_panic(struct notifier_block *nb, unsigned long reason, void *arg) { struct sev_device *sev = psp_master->sev_data; + int mutex_enabled = READ_ONCE(hygon_psp_hooks.psp_mutex_enabled); /* - * 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 a PSP command is already in flight, then issuing a shutdown + * would fail in unexpected ways. Rather than create even more + * confusion during a panic, just bail out here. + * + * On Hygon with the PSP mailbox mutex enabled, in-flight commands + * serialize on that mutex rather than sev_cmd_mutex, so check it + * here to match sev_do_cmd()/sev_firmware_shutdown() and avoid + * racing with an in-flight command. */ - if (mutex_is_locked(&sev_cmd_mutex)) + if (is_vendor_hygon() && mutex_enabled) { + if (psp_mutex_trylock(&hygon_psp_hooks.psp_misc->data_pg_aligned->mb_mutex) != 1) + return NOTIFY_DONE; + } else if (mutex_is_locked(&sev_cmd_mutex)) { return NOTIFY_DONE; + } __sev_firmware_shutdown(sev, true); + if (is_vendor_hygon() && mutex_enabled) + psp_mutex_unlock(&hygon_psp_hooks.psp_misc->data_pg_aligned->mb_mutex); + return NOTIFY_DONE; } diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index bc564adcf499526aacdbc4fbc35e276f4cbdfee4..198f5827fad349b9f7ea691ef3e6ecc48512de8d 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -29,8 +29,6 @@ #include #include -#include "sev-guest.h" - #define DEVICE_NAME "sev-guest" #define AAD_LEN 48 #define MSG_HDR_VER 1 @@ -59,7 +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; @@ -743,26 +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; @@ -897,8 +895,8 @@ static void unregister_sev_tsm(void *data) 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; @@ -916,7 +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); @@ -924,7 +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; @@ -938,7 +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)); 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/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6f624641e46a79b7749b15e28e63904d0c4a5e55..da533ab27cd66604ec636260756596a173b73402 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2482,4 +2482,45 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, } #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); +bool kvm_arch_gmem_prepare_needed(struct kvm *kvm); +#endif + +/** + * 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); + +#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/pagemap.h b/include/linux/pagemap.h index 322defe67e05b1fc8446dc82a9e2549bf523e61e..66d9b2be14e4d04aaa171fd798bd23ccd730d0ee 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -214,7 +214,8 @@ enum mapping_flags { AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ - AS_UNMOVABLE = 8, /* The mapping cannot be moved, ever */ + AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping, + including to move the mapping */ AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ @@ -329,20 +330,20 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping) clear_bit(AS_STABLE_WRITES, &mapping->flags); } -static inline void mapping_set_unmovable(struct address_space *mapping) +static inline void mapping_set_inaccessible(struct address_space *mapping) { /* - * It's expected unmovable mappings are also unevictable. Compaction + * 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_UNMOVABLE, &mapping->flags); + set_bit(AS_INACCESSIBLE, &mapping->flags); } -static inline bool mapping_unmovable(struct address_space *mapping) +static inline bool mapping_inaccessible(struct address_space *mapping) { - return test_bit(AS_UNMOVABLE, &mapping->flags); + return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline void mapping_set_writeback_may_deadlock_on_reclaim(struct address_space *mapping) diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 2ced37236ed36a66b974e67e839f6ef82339ff80..69442badf3432a3c226069c94a4a1202b9c700ba 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -659,6 +659,7 @@ struct sev_data_snp_launch_update { * @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 */ @@ -668,7 +669,8 @@ struct sev_data_snp_launch_finish { u64 id_auth_paddr; u8 id_block_en:1; u8 auth_key_en:1; - u64 rsvd:62; + u8 vcek_disabled:1; + u64 rsvd:61; u8 host_data[32]; } __packed; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index bb53a4d17e2a1989645414387c2d00849ffae527..affdd59749dc7d7dceb18262c46a425b9c638093 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1233,6 +1233,7 @@ struct kvm_ppc_resize_hpt { #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_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 #define KVM_CAP_RISCV_MP_STATE_RESET 242 @@ -1592,9 +1593,9 @@ 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) @@ -2225,4 +2226,13 @@ struct kvm_create_guest_memfd { __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/sev-guest.h b/include/uapi/linux/sev-guest.h index 154a87a1eca978baf5fccf2280936d103a82ebbb..fcdfea767fca88d7db4672e5566ce05826e9237c 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -89,6 +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/mm/compaction.c b/mm/compaction.c index d452a383307c015336b97defd39db745d568c14b..860f7bb099225dfa5814cf435e021aabb761fe92 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1174,22 +1174,22 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) || (mapping && is_unevictable)) { bool migrate_dirty = true; - bool is_unmovable; + bool is_inaccessible; /* * Only folios without mappings or that have * a ->migrate_folio callback are possible to migrate * without blocking. * - * Folios from unmovable mappings are not migratable. + * 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 unmovable, - * assume every unmovable folio is also unevictable, + * 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. @@ -1202,9 +1202,9 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, migrate_dirty = !mapping || mapping->a_ops->migrate_folio; } - is_unmovable = mapping && mapping_unmovable(mapping); + is_inaccessible = mapping && mapping_inaccessible(mapping); folio_unlock(folio); - if (!migrate_dirty || is_unmovable) + if (!migrate_dirty || is_inaccessible) goto isolate_fail_put; } diff --git a/mm/migrate.c b/mm/migrate.c index bc24b8a7cc4ae30ad12ab207233821cf6b69c0e8..e91e7fea1a961a2ee0b4265903dd76e0cd16389e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1008,7 +1008,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, if (!mapping) rc = migrate_folio(mapping, dst, src, mode); - else if (mapping_unmovable(mapping)) + else if (mapping_inaccessible(mapping)) rc = -EOPNOTSUPP; else if (mapping->a_ops->migrate_folio) /* diff --git a/mm/truncate.c b/mm/truncate.c index cfa88a3c10423f54544c2ef62c46da2e97f93652..d3ea61ac81b5e3c598400fdaec9a705c86dc8665 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -259,7 +259,8 @@ 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/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index ef11aa4cab42536cf1773bf5b787bcf715bd76e9..9fae1b73b529caf53c5c7dd1823fd7a3f320637c 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/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]; @@ -689,6 +694,9 @@ enum sev_cmd_id { /* 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, }; @@ -700,6 +708,14 @@ struct kvm_sev_cmd { __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; @@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd { #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 29462d23938fa8de56c1a71e7b1a04e3c6d9e96a..3c8e90b0ababca587968f8a309d9d5030fe3302c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1204,9 +1204,9 @@ struct kvm_vfio_spapr_tce { /* 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) diff --git a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c b/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c index 7a4a61be119b15b354ec98f6914b94fe04efa388..3fb967f40c6a1626d1d2cff1032c0e2562c8a205 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c @@ -105,11 +105,11 @@ void test_features(uint32_t vm_type, uint64_t supported_features) int i; for (i = 0; i < 64; i++) { - if (!(supported_features & (1u << 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 & (1u << i)) + else if (KNOWN_FEATURES & BIT_ULL(i)) test_init2(vm_type, &(struct kvm_sev_init){ .vmsa_features = BIT_ULL(i) }); } diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 30ee7340409f77985e3de26139792830612053eb..d9466a3a21e40c8a5afde687450e629528b4ba6c 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) @@ -109,3 +112,11 @@ 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/guest_memfd.c b/virt/kvm/guest_memfd.c index fda1c9482b99eccbba4a420a261d3fabb8a79301..b03f2d63549f1786c4ff9f2880529efb66c57203 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -13,39 +13,109 @@ struct kvm_gmem { struct list_head entry; }; -static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) +/** + * 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) { - struct folio *folio; + return folio_pfn(folio) + (index & (folio_nr_pages(folio) - 1)); +} - /* TODO: Support huge pages. */ - folio = filemap_grab_folio(inode->i_mapping, index); - if (IS_ERR_OR_NULL(folio)) - return NULL; +static int __kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio) +{ +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE + struct list_head *gmem_list = &inode->i_mapping->i_private_list; + struct kvm_gmem *gmem; + + list_for_each_entry(gmem, gmem_list, entry) { + struct kvm_memory_slot *slot; + struct kvm *kvm = gmem->kvm; + kvm_pfn_t pfn; + gfn_t gfn; + int rc; + + if (!kvm_arch_gmem_prepare_needed(kvm)) + continue; + + slot = xa_load(&gmem->bindings, index); + if (!slot) + continue; + + pfn = folio_file_pfn(folio, index); + gfn = slot->base_gfn + index - slot->gmem.pgoff; + rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); + if (rc) { + pr_warn_ratelimited("gmem: Failed to prepare folio for GFN %llx PFN %llx error %d.\n", + gfn, pfn, rc); + return rc; + } + } + +#endif + return 0; +} + +/* + * 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 file *file, struct kvm_memory_slot *slot, + gfn_t gfn, struct folio *folio) +{ + unsigned long nr_pages, i; + pgoff_t index; + int r; + + if (folio_test_uptodate(folio)) + return 0; + + nr_pages = folio_nr_pages(folio); + for (i = 0; i < nr_pages; i++) + clear_highpage(folio_page(folio, i)); /* - * Use the up-to-date flag to track whether or not the memory has been - * zeroed before being handed off to the guest. There is no backing - * storage for the memory, so the folio will remain up-to-date until - * it's removed. + * 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. * - * TODO: Skip clearing pages when trusted firmware will do it when - * assigning memory to the guest. + * The order will be passed when creating the guest_memfd, and + * checked when creating memslots. */ - if (!folio_test_uptodate(folio)) { - unsigned long nr_pages = folio_nr_pages(folio); - unsigned long i; - - for (i = 0; i < nr_pages; i++) - clear_highpage(folio_page(folio, i)); + 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(file_inode(file), index, folio); + if (!r) folio_mark_uptodate(folio); - } - /* - * Ignore accessed, referenced, and dirty flags. The memory is - * unevictable and there is no storage to write back to. - */ - return 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, @@ -146,8 +216,8 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len) } folio = kvm_gmem_get_folio(inode, index); - if (!folio) { - r = -ENOMEM; + if (IS_ERR(folio)) { + r = PTR_ERR(folio); break; } @@ -302,10 +372,24 @@ static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *fol 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_folio = kvm_gmem_error_folio, +#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, @@ -364,7 +448,7 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) inode->i_mode |= S_IFREG; inode->i_size = size; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); - mapping_set_unmovable(inode->i_mapping); + mapping_set_inaccessible(inode->i_mapping); /* Unmovable mappings are supposed to be marked unevictable as well. */ WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); @@ -486,51 +570,129 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot) fput(file); } -int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, - gfn_t gfn, kvm_pfn_t *pfn, int *max_order) +/* 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, int *max_order) { pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff; - struct kvm_gmem *gmem; + struct kvm_gmem *gmem = file->private_data; struct folio *folio; - struct page *page; - struct file *file; - int r; - file = kvm_gmem_get_file(slot); - if (!file) - return -EFAULT; + if (file != slot->gmem.file) { + WARN_ON_ONCE(slot->gmem.file); + return ERR_PTR(-EFAULT); + } gmem = file->private_data; - - if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) { - r = -EIO; - goto out_fput; + 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 (!folio) { - r = -ENOMEM; - goto out_fput; - } + if (IS_ERR(folio)) + return folio; if (folio_test_hwpoison(folio)) { - r = -EHWPOISON; - goto out_unlock; + folio_unlock(folio); + folio_put(folio); + return ERR_PTR(-EHWPOISON); } - page = folio_file_page(folio, index); - - *pfn = page_to_pfn(page); + *pfn = folio_file_pfn(folio, index); if (max_order) *max_order = 0; - r = 0; + return folio; +} -out_unlock: +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; + int r = 0; + + if (!file) + return -EFAULT; + + folio = __kvm_gmem_get_pfn(file, slot, gfn, pfn, max_order); + if (IS_ERR(folio)) { + r = PTR_ERR(folio); + goto out; + } + + r = kvm_gmem_prepare_folio(file, slot, gfn, folio); folio_unlock(folio); -out_fput: - fput(file); + if (r < 0) + folio_put(folio); +out: + fput(file); return r; } EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn); + +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; + kvm_pfn_t pfn; + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + folio = __kvm_gmem_get_pfn(file, slot, gfn, &pfn, &max_order); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); + break; + } + + folio_unlock(folio); + if (!IS_ALIGNED(gfn, (1 << max_order)) || + (npages - i) < (1 << max_order)) + max_order = 0; + + p = src ? src + i * PAGE_SIZE : NULL; + ret = post_populate(kvm, gfn, pfn, p, max_order, opaque); + if (!ret) + folio_mark_uptodate(folio); + + 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); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index bcd8b7639f21231b23bc9d5f1e1b0ed807fa7e86..0e2f3baa5eb07a0cfa51a4ce69554e4dfce270e5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4407,6 +4407,52 @@ 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) { @@ -4611,6 +4657,20 @@ 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); }