diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 007bab9f2a0e39..45060e7cea4859 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1552,6 +1552,7 @@ config AMD_MEM_ENCRYPT select ARCH_HAS_CC_PLATFORM select X86_MEM_ENCRYPT select UNACCEPTED_MEMORY + select CRYPTO_LIB_AESGCM help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index cd44e120fe5377..bb55934c1cee70 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -401,7 +401,8 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) * by the guest kernel. As and when a new feature is implemented in the * guest kernel, a corresponding bit should be added to the mask. */ -#define SNP_FEATURES_PRESENT MSR_AMD64_SNP_DEBUG_SWAP +#define SNP_FEATURES_PRESENT (MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_SECURE_TSC) u64 snp_get_unsupported_features(u64 status) { diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index 0f81f70aca822e..9a0ddda3aa6976 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -65,7 +65,6 @@ static __maybe_unused __always_inline bool amd_cc_platform_vtom(enum cc_attr att * up under SME the trampoline area cannot be encrypted, whereas under SEV * the trampoline area must be encrypted. */ - static bool noinstr amd_cc_platform_has(enum cc_attr attr) { #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -97,6 +96,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_GUEST_SNP_SECURE_TSC: + return sev_status & MSR_AMD64_SNP_SECURE_TSC; + case CC_ATTR_HOST_SEV_SNP: return cc_flags.host_sev_snp; diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index 3069feb91409d6..745a8911210f20 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -93,6 +94,18 @@ static struct ghcb *boot_ghcb __section(".data"); /* Bitmap of SEV features supported by the hypervisor */ static u64 sev_hv_features __ro_after_init; +/* Secrets page physical address from the CC blob */ +static u64 secrets_pa __ro_after_init; + +/* + * For Secure TSC guests, the BSP fetches TSC_INFO using SNP guest messaging and + * initializes snp_tsc_scale and snp_tsc_offset. These values are replicated + * across the APs VMSA fields (TSC_SCALE and TSC_OFFSET). + */ +static u64 snp_tsc_scale __ro_after_init; +static u64 snp_tsc_offset __ro_after_init; +static u64 snp_tsc_freq_khz __ro_after_init; + /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { struct ghcb ghcb_page; @@ -723,45 +736,13 @@ void noinstr __sev_es_nmi_complete(void) __sev_put_ghcb(&state); } -static u64 __init get_secrets_page(void) -{ - u64 pa_data = boot_params.cc_blob_address; - struct cc_blob_sev_info info; - void *map; - - /* - * The CC blob contains the address of the secrets page, check if the - * blob is present. - */ - if (!pa_data) - return 0; - - map = early_memremap(pa_data, sizeof(info)); - if (!map) { - pr_err("Unable to locate SNP secrets page: failed to map the Confidential Computing blob.\n"); - return 0; - } - memcpy(&info, map, sizeof(info)); - early_memunmap(map, sizeof(info)); - - /* smoke-test the secrets page passed */ - if (!info.secrets_phys || info.secrets_len != PAGE_SIZE) - return 0; - - return info.secrets_phys; -} - static u64 __init get_snp_jump_table_addr(void) { struct snp_secrets_page *secrets; void __iomem *mem; - u64 pa, addr; + u64 addr; - pa = get_secrets_page(); - if (!pa) - return 0; - - mem = ioremap_encrypted(pa, PAGE_SIZE); + mem = ioremap_encrypted(secrets_pa, PAGE_SIZE); if (!mem) { pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n"); return 0; @@ -1202,6 +1183,12 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) vmsa->vmpl = snp_vmpl; vmsa->sev_features = sev_status >> 2; + /* Populate AP's TSC scale/offset to get accurate TSC values. */ + if (cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) { + vmsa->tsc_scale = snp_tsc_scale; + vmsa->tsc_offset = snp_tsc_offset; + } + /* Switch the page over to a VMSA page now that it is initialized */ ret = snp_set_vmsa(vmsa, caa, apic_id, true); if (ret) { @@ -1332,35 +1319,84 @@ int __init sev_es_efi_map_ghcbs(pgd_t *pgd) return 0; } -static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +/* Writes to the SVSM CAA MSR are ignored */ +static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write) { - struct pt_regs *regs = ctxt->regs; - enum es_result ret; - u64 exit_info_1; + if (write) + return ES_OK; - /* Is it a WRMSR? */ - exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0; + regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa)); + regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa)); - if (regs->cx == MSR_SVSM_CAA) { - /* Writes to the SVSM CAA msr are ignored */ - if (exit_info_1) - return ES_OK; + return ES_OK; +} + +/* + * TSC related accesses should not exit to the hypervisor when a guest is + * executing with Secure TSC enabled, so special handling is required for + * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ. + */ +static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write) +{ + u64 tsc; - regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa)); - regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa)); + /* + * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled. + * Terminate the SNP guest when the interception is enabled. + */ + if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) + return ES_VMM_ERROR; + /* + * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC + * to return undefined values, so ignore all writes. + * + * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use + * the value returned by rdtsc_ordered(). + */ + if (write) { + WARN_ONCE(1, "TSC MSR writes are verboten!\n"); return ES_OK; } + tsc = rdtsc_ordered(); + regs->ax = lower_32_bits(tsc); + regs->dx = upper_32_bits(tsc); + + return ES_OK; +} + +static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + enum es_result ret; + bool write; + + /* Is it a WRMSR? */ + write = ctxt->insn.opcode.bytes[1] == 0x30; + + switch (regs->cx) { + case MSR_SVSM_CAA: + return __vc_handle_msr_caa(regs, write); + case MSR_IA32_TSC: + case MSR_AMD64_GUEST_TSC_FREQ: + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + return __vc_handle_secure_tsc_msrs(regs, write); + else + break; + default: + break; + } + ghcb_set_rcx(ghcb, regs->cx); - if (exit_info_1) { + if (write) { ghcb_set_rax(ghcb, regs->ax); ghcb_set_rdx(ghcb, regs->dx); } - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0); - if ((ret == ES_OK) && (!exit_info_1)) { + if ((ret == ES_OK) && !write) { regs->ax = ghcb->save.rax; regs->dx = ghcb->save.rdx; } @@ -2301,6 +2337,11 @@ bool __head snp_init(struct boot_params *bp) if (!cc_info) return false; + if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE) + secrets_pa = cc_info->secrets_phys; + else + return false; + setup_cpuid_table(cc_info); svsm_setup(cc_info); @@ -2442,7 +2483,8 @@ int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, } EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req); -int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) +static int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, + struct snp_guest_request_ioctl *rio) { struct ghcb_state state; struct es_em_ctxt ctxt; @@ -2466,12 +2508,12 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn vc_ghcb_invalidate(ghcb); - if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { + if (req->exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { ghcb_set_rax(ghcb, input->data_gpa); ghcb_set_rbx(ghcb, input->data_npages); } - ret = sev_es_ghcb_hv_call(ghcb, &ctxt, exit_code, input->req_gpa, input->resp_gpa); + ret = sev_es_ghcb_hv_call(ghcb, &ctxt, req->exit_code, input->req_gpa, input->resp_gpa); if (ret) goto e_put; @@ -2486,7 +2528,7 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn case SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN): /* Number of expected pages are returned in RBX */ - if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { + if (req->exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { input->data_npages = ghcb_get_rbx(ghcb); ret = -ENOSPC; break; @@ -2504,7 +2546,6 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn return ret; } -EXPORT_SYMBOL_GPL(snp_issue_guest_request); static struct platform_device sev_guest_device = { .name = "sev-guest", @@ -2557,20 +2598,9 @@ static bool is_svsm_vtpm_send_command_supported(void) static int __init snp_init_platform_device(void) { - struct sev_guest_platform_data data; - u64 gpa; - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return -ENODEV; - gpa = get_secrets_page(); - if (!gpa) - return -ENODEV; - - data.secrets_gpa = gpa; - if (platform_device_add_data(&sev_guest_device, &data, sizeof(data))) - return -ENODEV; - if (platform_device_register(&sev_guest_device)) return -ENODEV; @@ -2667,3 +2697,581 @@ static int __init sev_sysfs_init(void) } arch_initcall(sev_sysfs_init); #endif // CONFIG_SYSFS + +static void free_shared_pages(void *buf, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + int ret; + + if (!buf) + return; + + ret = set_memory_encrypted((unsigned long)buf, npages); + if (ret) { + WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); + return; + } + + __free_pages(virt_to_page(buf), get_order(sz)); +} + +static void *alloc_shared_pages(size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + struct page *page; + int ret; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); + if (!page) + return NULL; + + ret = set_memory_decrypted((unsigned long)page_address(page), npages); + if (ret) { + pr_err("failed to mark page shared, ret=%d\n", ret); + __free_pages(page, get_order(sz)); + return NULL; + } + + return page_address(page); +} + +static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) +{ + u8 *key = NULL; + + switch (id) { + case 0: + *seqno = &secrets->os_area.msg_seqno_0; + key = secrets->vmpck0; + break; + case 1: + *seqno = &secrets->os_area.msg_seqno_1; + key = secrets->vmpck1; + break; + case 2: + *seqno = &secrets->os_area.msg_seqno_2; + key = secrets->vmpck2; + break; + case 3: + *seqno = &secrets->os_area.msg_seqno_3; + key = secrets->vmpck3; + break; + default: + break; + } + + return key; +} + +static struct aesgcm_ctx *snp_init_crypto(u8 *key, size_t keylen) +{ + struct aesgcm_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + if (aesgcm_expandkey(ctx, key, keylen, AUTHTAG_LEN)) { + pr_err("Crypto context initialization failed\n"); + kfree(ctx); + return NULL; + } + + return ctx; +} + +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) +{ + /* Adjust the default VMPCK key based on the executing VMPL level */ + if (vmpck_id == -1) + vmpck_id = snp_vmpl; + + mdesc->vmpck = get_vmpck(vmpck_id, mdesc->secrets, &mdesc->os_area_msg_seqno); + if (!mdesc->vmpck) { + pr_err("Invalid VMPCK%d communication key\n", vmpck_id); + return -EINVAL; + } + + /* Verify that VMPCK is not zero. */ + if (!memchr_inv(mdesc->vmpck, 0, VMPCK_KEY_LEN)) { + pr_err("Empty VMPCK%d communication key\n", vmpck_id); + return -EINVAL; + } + + mdesc->vmpck_id = vmpck_id; + + mdesc->ctx = snp_init_crypto(mdesc->vmpck, VMPCK_KEY_LEN); + if (!mdesc->ctx) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(snp_msg_init); + +struct snp_msg_desc *snp_msg_alloc(void) +{ + struct snp_msg_desc *mdesc; + void __iomem *mem; + + BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE); + + mdesc = kzalloc(sizeof(struct snp_msg_desc), GFP_KERNEL); + if (!mdesc) + return ERR_PTR(-ENOMEM); + + mem = ioremap_encrypted(secrets_pa, PAGE_SIZE); + if (!mem) + goto e_free_mdesc; + + mdesc->secrets = (__force struct snp_secrets_page *)mem; + + /* Allocate the shared page used for the request and response message. */ + mdesc->request = alloc_shared_pages(sizeof(struct snp_guest_msg)); + if (!mdesc->request) + goto e_unmap; + + mdesc->response = alloc_shared_pages(sizeof(struct snp_guest_msg)); + if (!mdesc->response) + goto e_free_request; + + mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE); + if (!mdesc->certs_data) + goto e_free_response; + + /* initial the input address for guest request */ + mdesc->input.req_gpa = __pa(mdesc->request); + mdesc->input.resp_gpa = __pa(mdesc->response); + mdesc->input.data_gpa = __pa(mdesc->certs_data); + + return mdesc; + +e_free_response: + free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); +e_free_request: + free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); +e_unmap: + iounmap(mem); +e_free_mdesc: + kfree(mdesc); + + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL_GPL(snp_msg_alloc); + +void snp_msg_free(struct snp_msg_desc *mdesc) +{ + if (!mdesc) + return; + + kfree(mdesc->ctx); + free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); + free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); + free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); + iounmap((__force void __iomem *)mdesc->secrets); + + memset(mdesc, 0, sizeof(*mdesc)); + kfree(mdesc); +} +EXPORT_SYMBOL_GPL(snp_msg_free); + +/* Mutex to serialize the shared buffer access and command handling. */ +static DEFINE_MUTEX(snp_cmd_mutex); + +/* + * If an error is received from the host or AMD Secure Processor (ASP) there + * are two options. Either retry the exact same encrypted request or discontinue + * using the VMPCK. + * + * This is because in the current encryption scheme GHCB v2 uses AES-GCM to + * encrypt the requests. The IV for this scheme is the sequence number. GCM + * cannot tolerate IV reuse. + * + * The ASP FW v1.51 only increments the sequence numbers on a successful + * guest<->ASP back and forth and only accepts messages at its exact sequence + * number. + * + * So if the sequence number were to be reused the encryption scheme is + * vulnerable. If the sequence number were incremented for a fresh IV the ASP + * will reject the request. + */ +static void snp_disable_vmpck(struct snp_msg_desc *mdesc) +{ + pr_alert("Disabling VMPCK%d communication key to prevent IV reuse.\n", + mdesc->vmpck_id); + memzero_explicit(mdesc->vmpck, VMPCK_KEY_LEN); + mdesc->vmpck = NULL; +} + +static inline u64 __snp_get_msg_seqno(struct snp_msg_desc *mdesc) +{ + u64 count; + + lockdep_assert_held(&snp_cmd_mutex); + + /* Read the current message sequence counter from secrets pages */ + count = *mdesc->os_area_msg_seqno; + + return count + 1; +} + +/* Return a non-zero on success */ +static u64 snp_get_msg_seqno(struct snp_msg_desc *mdesc) +{ + u64 count = __snp_get_msg_seqno(mdesc); + + /* + * The message sequence counter for the SNP guest request is a 64-bit + * value but the version 2 of GHCB specification defines a 32-bit storage + * for it. If the counter exceeds the 32-bit value then return zero. + * The caller should check the return value, but if the caller happens to + * not check the value and use it, then the firmware treats zero as an + * invalid number and will fail the message request. + */ + if (count >= UINT_MAX) { + pr_err("request message sequence counter overflow\n"); + return 0; + } + + return count; +} + +static void snp_inc_msg_seqno(struct snp_msg_desc *mdesc) +{ + /* + * The counter is also incremented by the PSP, so increment it by 2 + * and save in secrets page. + */ + *mdesc->os_area_msg_seqno += 2; +} + +static int verify_and_dec_payload(struct snp_msg_desc *mdesc, struct snp_guest_req *req) +{ + struct snp_guest_msg *resp_msg = &mdesc->secret_response; + struct snp_guest_msg *req_msg = &mdesc->secret_request; + struct snp_guest_msg_hdr *req_msg_hdr = &req_msg->hdr; + struct snp_guest_msg_hdr *resp_msg_hdr = &resp_msg->hdr; + struct aesgcm_ctx *ctx = mdesc->ctx; + u8 iv[GCM_AES_IV_SIZE] = {}; + + pr_debug("response [seqno %lld type %d version %d sz %d]\n", + resp_msg_hdr->msg_seqno, resp_msg_hdr->msg_type, resp_msg_hdr->msg_version, + resp_msg_hdr->msg_sz); + + /* Copy response from shared memory to encrypted memory. */ + memcpy(resp_msg, mdesc->response, sizeof(*resp_msg)); + + /* Verify that the sequence counter is incremented by 1 */ + if (unlikely(resp_msg_hdr->msg_seqno != (req_msg_hdr->msg_seqno + 1))) + return -EBADMSG; + + /* Verify response message type and version number. */ + if (resp_msg_hdr->msg_type != (req_msg_hdr->msg_type + 1) || + resp_msg_hdr->msg_version != req_msg_hdr->msg_version) + return -EBADMSG; + + /* + * If the message size is greater than our buffer length then return + * an error. + */ + if (unlikely((resp_msg_hdr->msg_sz + ctx->authsize) > req->resp_sz)) + return -EBADMSG; + + /* Decrypt the payload */ + memcpy(iv, &resp_msg_hdr->msg_seqno, min(sizeof(iv), sizeof(resp_msg_hdr->msg_seqno))); + if (!aesgcm_decrypt(ctx, req->resp_buf, resp_msg->payload, resp_msg_hdr->msg_sz, + &resp_msg_hdr->algo, AAD_LEN, iv, resp_msg_hdr->authtag)) + return -EBADMSG; + + return 0; +} + +static int enc_payload(struct snp_msg_desc *mdesc, u64 seqno, struct snp_guest_req *req) +{ + struct snp_guest_msg *msg = &mdesc->secret_request; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + struct aesgcm_ctx *ctx = mdesc->ctx; + u8 iv[GCM_AES_IV_SIZE] = {}; + + memset(msg, 0, sizeof(*msg)); + + hdr->algo = SNP_AEAD_AES_256_GCM; + hdr->hdr_version = MSG_HDR_VER; + hdr->hdr_sz = sizeof(*hdr); + hdr->msg_type = req->msg_type; + hdr->msg_version = req->msg_version; + hdr->msg_seqno = seqno; + hdr->msg_vmpck = req->vmpck_id; + hdr->msg_sz = req->req_sz; + + /* Verify the sequence number is non-zero */ + if (!hdr->msg_seqno) + return -ENOSR; + + pr_debug("request [seqno %lld type %d version %d sz %d]\n", + hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); + + if (WARN_ON((req->req_sz + ctx->authsize) > sizeof(msg->payload))) + return -EBADMSG; + + memcpy(iv, &hdr->msg_seqno, min(sizeof(iv), sizeof(hdr->msg_seqno))); + aesgcm_encrypt(ctx, msg->payload, req->req_buf, req->req_sz, &hdr->algo, + AAD_LEN, iv, hdr->authtag); + + return 0; +} + +static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) +{ + unsigned long req_start = jiffies; + unsigned int override_npages = 0; + u64 override_err = 0; + int rc; + +retry_request: + /* + * Call firmware to process the request. In this function the encrypted + * message enters shared memory with the host. So after this call the + * sequence number must be incremented or the VMPCK must be deleted to + * prevent reuse of the IV. + */ + rc = snp_issue_guest_request(req, &mdesc->input, rio); + switch (rc) { + case -ENOSPC: + /* + * If the extended guest request fails due to having too + * small of a certificate data buffer, retry the same + * guest request without the extended data request in + * order to increment the sequence number and thus avoid + * IV reuse. + */ + override_npages = mdesc->input.data_npages; + req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + /* + * Override the error to inform callers the given extended + * request buffer size was too small and give the caller the + * required buffer size. + */ + override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN); + + /* + * If this call to the firmware succeeds, the sequence number can + * be incremented allowing for continued use of the VMPCK. If + * there is an error reflected in the return value, this value + * is checked further down and the result will be the deletion + * of the VMPCK and the error code being propagated back to the + * user as an ioctl() return code. + */ + goto retry_request; + + /* + * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been + * throttled. Retry in the driver to avoid returning and reusing the + * message sequence number on a different message. + */ + case -EAGAIN: + if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) { + rc = -ETIMEDOUT; + break; + } + schedule_timeout_killable(SNP_REQ_RETRY_DELAY); + goto retry_request; + } + + /* + * Increment the message sequence number. There is no harm in doing + * this now because decryption uses the value stored in the response + * structure and any failure will wipe the VMPCK, preventing further + * use anyway. + */ + snp_inc_msg_seqno(mdesc); + + if (override_err) { + rio->exitinfo2 = override_err; + + /* + * If an extended guest request was issued and the supplied certificate + * buffer was not large enough, a standard guest request was issued to + * prevent IV reuse. If the standard request was successful, return -EIO + * back to the caller as would have originally been returned. + */ + if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) + rc = -EIO; + } + + if (override_npages) + mdesc->input.data_npages = override_npages; + + return rc; +} + +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) +{ + u64 seqno; + int rc; + + guard(mutex)(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (!mdesc->vmpck || !memchr_inv(mdesc->vmpck, 0, VMPCK_KEY_LEN)) { + pr_err_ratelimited("VMPCK is disabled\n"); + return -ENOTTY; + } + + /* Get message sequence and verify that its a non-zero */ + seqno = snp_get_msg_seqno(mdesc); + if (!seqno) + return -EIO; + + /* Clear shared memory's response for the host to populate. */ + memset(mdesc->response, 0, sizeof(struct snp_guest_msg)); + + /* Encrypt the userspace provided payload in mdesc->secret_request. */ + rc = enc_payload(mdesc, seqno, req); + if (rc) + return rc; + + /* + * Write the fully encrypted request to the shared unencrypted + * request page. + */ + memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request)); + + rc = __handle_guest_request(mdesc, req, rio); + if (rc) { + if (rc == -EIO && + rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) + return rc; + + pr_alert("Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n", + rc, rio->exitinfo2); + + snp_disable_vmpck(mdesc); + return rc; + } + + rc = verify_and_dec_payload(mdesc, req); + if (rc) { + pr_alert("Detected unexpected decode failure from ASP. rc: %d\n", rc); + snp_disable_vmpck(mdesc); + return rc; + } + + return 0; +} +EXPORT_SYMBOL_GPL(snp_send_guest_request); + +static int __init snp_get_tsc_info(void) +{ + struct snp_guest_request_ioctl *rio; + struct snp_tsc_info_resp *tsc_resp; + struct snp_tsc_info_req *tsc_req; + struct snp_msg_desc *mdesc; + struct snp_guest_req *req; + int rc = -ENOMEM; + + tsc_req = kzalloc(sizeof(*tsc_req), GFP_KERNEL); + if (!tsc_req) + return rc; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover + * the authtag. + */ + tsc_resp = kzalloc(sizeof(*tsc_resp) + AUTHTAG_LEN, GFP_KERNEL); + if (!tsc_resp) + goto e_free_tsc_req; + + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + goto e_free_tsc_resp; + + rio = kzalloc(sizeof(*rio), GFP_KERNEL); + if (!rio) + goto e_free_req; + + mdesc = snp_msg_alloc(); + if (IS_ERR_OR_NULL(mdesc)) + goto e_free_rio; + + rc = snp_msg_init(mdesc, snp_vmpl); + if (rc) + goto e_free_mdesc; + + req->msg_version = MSG_HDR_VER; + req->msg_type = SNP_MSG_TSC_INFO_REQ; + req->vmpck_id = snp_vmpl; + req->req_buf = tsc_req; + req->req_sz = sizeof(*tsc_req); + req->resp_buf = (void *)tsc_resp; + req->resp_sz = sizeof(*tsc_resp) + AUTHTAG_LEN; + req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + rc = snp_send_guest_request(mdesc, req, rio); + if (rc) + goto e_request; + + pr_debug("%s: response status 0x%x scale 0x%llx offset 0x%llx factor 0x%x\n", + __func__, tsc_resp->status, tsc_resp->tsc_scale, tsc_resp->tsc_offset, + tsc_resp->tsc_factor); + + if (!tsc_resp->status) { + snp_tsc_scale = tsc_resp->tsc_scale; + snp_tsc_offset = tsc_resp->tsc_offset; + } else { + pr_err("Failed to get TSC info, response status 0x%x\n", tsc_resp->status); + rc = -EIO; + } + +e_request: + /* The response buffer contains sensitive data, explicitly clear it. */ + memzero_explicit(tsc_resp, sizeof(*tsc_resp) + AUTHTAG_LEN); +e_free_mdesc: + snp_msg_free(mdesc); +e_free_rio: + kfree(rio); +e_free_req: + kfree(req); + e_free_tsc_resp: + kfree(tsc_resp); +e_free_tsc_req: + kfree(tsc_req); + + return rc; +} + +void __init snp_secure_tsc_prepare(void) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) + return; + + if (snp_get_tsc_info()) { + pr_alert("Unable to retrieve Secure TSC info from ASP\n"); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC); + } + + pr_debug("SecureTSC enabled"); +} + +static unsigned long securetsc_get_tsc_khz(void) +{ + return snp_tsc_freq_khz; +} + +void __init snp_secure_tsc_init(void) +{ + unsigned long long tsc_freq_mhz; + + if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) + return; + + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + rdmsrl(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz); + snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000); + + x86_platform.calibrate_cpu = securetsc_get_tsc_khz; + x86_platform.calibrate_tsc = securetsc_get_tsc_khz; +} diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/coco/sev/shared.c index 71de5319408910..4386f37bd31d54 100644 --- a/arch/x86/coco/sev/shared.c +++ b/arch/x86/coco/sev/shared.c @@ -1140,6 +1140,16 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); enum es_result ret; + /* + * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure + * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP + * instructions are being intercepted. If this should occur and Secure + * TSC is enabled, guest execution should be terminated as the guest + * cannot rely on the TSC value provided by the hypervisor. + */ + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + return ES_VMM_ERROR; + ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); if (ret != ES_OK) return ret; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index ff846640540933..24ca5819281c8e 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -442,8 +442,9 @@ #define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ #define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SNP_SECURE_TSC (19*32+ 8) /* SEV-SNP Secure TSC */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ #define X86_FEATURE_RESTRICTED_INJECTION (19*32+12) /* AMD SEV Restricted Injection */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f6250299e17a1d..20b9a4cf2b9b18 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1032,6 +1032,7 @@ struct kvm_vcpu_arch { /* Protected Guests */ bool guest_state_protected; + bool guest_tsc_protected; /* * Set when PDPTS were loaded directly by the userspace without diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 82c6a4d350e09e..b15635de129049 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -586,6 +586,7 @@ #define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_AMD_PERF_STATUS 0xc0010063 #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index fbf86829714a7a..9a4026604ba4f9 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -214,6 +214,7 @@ struct snp_psc_desc { #define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */ #define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */ #define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */ +#define GHCB_TERM_SECURE_TSC 10 /* Secure TSC initialization failed */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 79bbe2be900eb7..706635df00a64e 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -14,6 +14,7 @@ #include #include #include +#include #define GHCB_PROTOCOL_MIN 1ULL #define GHCB_PROTOCOL_MAX 2ULL @@ -120,6 +121,12 @@ struct snp_req_data { }; #define MAX_AUTHTAG_LEN 32 +#define AUTHTAG_LEN 16 +#define AAD_LEN 48 +#define MSG_HDR_VER 1 + +#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) +#define SNP_REQ_RETRY_DELAY (2*HZ) /* See SNP spec SNP_GUEST_REQUEST section for the structure */ enum msg_type { @@ -139,6 +146,9 @@ enum msg_type { SNP_MSG_VMRK_REQ, SNP_MSG_VMRK_RSP, + SNP_MSG_TSC_INFO_REQ = 17, + SNP_MSG_TSC_INFO_RSP, + SNP_MSG_TYPE_MAX }; @@ -164,11 +174,35 @@ struct snp_guest_msg_hdr { struct snp_guest_msg { struct snp_guest_msg_hdr hdr; - u8 payload[4000]; + u8 payload[PAGE_SIZE - sizeof(struct snp_guest_msg_hdr)]; +} __packed; + +#define SNP_TSC_INFO_REQ_SZ 128 + +struct snp_tsc_info_req { + u8 rsvd[SNP_TSC_INFO_REQ_SZ]; +} __packed; + +struct snp_tsc_info_resp { + u32 status; + u32 rsvd1; + u64 tsc_scale; + u64 tsc_offset; + u32 tsc_factor; + u8 rsvd2[100]; } __packed; -struct sev_guest_platform_data { - u64 secrets_gpa; +struct snp_guest_req { + void *req_buf; + size_t req_sz; + + void *resp_buf; + size_t resp_sz; + + u64 exit_code; + unsigned int vmpck_id; + u8 msg_version; + u8 msg_type; }; /* @@ -218,6 +252,28 @@ struct snp_secrets_page { u8 rsvd4[3744]; } __packed; +struct snp_msg_desc { + /* request and response are in unencrypted memory */ + struct snp_guest_msg *request, *response; + + /* + * Avoid information leakage by double-buffering shared messages + * in fields that are in regular encrypted memory. + */ + struct snp_guest_msg secret_request, secret_response; + + struct snp_secrets_page *secrets; + struct snp_req_data input; + + void *certs_data; + + struct aesgcm_ctx *ctx; + + u32 *os_area_msg_seqno; + u8 *vmpck; + int vmpck_id; +}; + /* * The SVSM Calling Area (CA) related structures. */ @@ -392,7 +448,6 @@ void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); void __noreturn snp_abort(void); void snp_dmi_setup(void); -int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); @@ -400,6 +455,15 @@ u64 sev_get_status(void); void sev_show_status(void); void snp_update_svsm_ca(void); +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id); +struct snp_msg_desc *snp_msg_alloc(void); +void snp_msg_free(struct snp_msg_desc *mdesc); +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio); + +void __init snp_secure_tsc_prepare(void); +void __init snp_secure_tsc_init(void); + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define snp_vmpl 0 @@ -422,10 +486,6 @@ static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } static inline void snp_dmi_setup(void) { } -static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) -{ - return -ENOTTY; -} static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input) { return -ENOTTY; @@ -435,6 +495,13 @@ static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } static inline void sev_show_status(void) { } static inline void snp_update_svsm_ca(void) { } +static inline int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) { return -1; } +static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; } +static inline void snp_msg_free(struct snp_msg_desc *mdesc) { } +static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) { return -ENODEV; } +static inline void __init snp_secure_tsc_prepare(void) { } +static inline void __init snp_secure_tsc_init(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 7fa276bdd0e4eb..3e3da133545b96 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -289,6 +289,7 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_ #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_SECURE_TSC BIT(9) #define SVM_SEV_FEAT_INT_INJ_MODES \ (SVM_SEV_FEAT_RESTRICTED_INJECTION | \ @@ -426,7 +427,9 @@ struct sev_es_save_area { u8 reserved_0x298[80]; u32 pkru; u32 tsc_aux; - u8 reserved_0x2f0[24]; + u64 tsc_scale; + u64 tsc_offset; + u8 reserved_0x300[8]; u64 rcx; u64 rdx; u64 rbx; @@ -599,7 +602,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); - BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x300); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index a24f3197e240f1..22ccaf55a40d56 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -838,7 +838,8 @@ struct kvm_sev_snp_launch_start { __u64 policy; __u8 gosvw[16]; __u16 flags; - __u8 pad0[6]; + __u8 pad0[2]; + __u32 desired_tsc_khz; __u64 pad1[4]; }; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index d4462fb2629969..ed2ad09c650399 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -29,6 +29,7 @@ #include #include #include +#include unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1516,6 +1517,9 @@ void __init tsc_early_init(void) /* Don't change UV TSC multi-chassis synchronization */ if (is_early_uv_system()) return; + + snp_secure_tsc_init(); + if (!determine_cpu_tsc_frequencies(true)) return; tsc_enable_sched_clock(); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 55384e4e976b73..16e2d5b7f38adb 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2253,6 +2253,14 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) start.gctx_paddr = __psp_pa(sev->snp_context); start.policy = params.policy; + + if (snp_secure_tsc_enabled(kvm)) { + if (!kvm->arch.default_tsc_khz) + return -EINVAL; + + start.desired_tsc_khz = kvm->arch.default_tsc_khz; + } + 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) { @@ -2579,7 +2587,9 @@ static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) return ret; } - svm->vcpu.arch.guest_state_protected = true; + vcpu->arch.guest_state_protected = true; + vcpu->arch.guest_tsc_protected = snp_secure_tsc_enabled(kvm); + /* * SEV-ES (and thus SNP) guest mandates LBR Virtualization to * be _always_ ON. Enable it only after setting @@ -3202,11 +3212,11 @@ void __init sev_hardware_setup(void) if (sev_es_debug_swap_enabled) sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP; - if (!sev_snp_enabled || !cpu_feature_enabled(X86_FEATURE_RESTRICTED_INJECTION)) - sev_snp_restricted_injection_enabled = false; - if (sev_snp_restricted_injection_enabled) sev_supported_vmsa_features |= SVM_SEV_FEAT_RESTRICTED_INJECTION; + + if (sev_snp_enabled && cpu_feature_enabled(X86_FEATURE_SNP_SECURE_TSC)) + sev_supported_vmsa_features |= SVM_SEV_FEAT_SECURE_TSC; } void sev_hardware_unsetup(void) @@ -5023,6 +5033,9 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) if (sev_snp_guest(vcpu->kvm)) sev_snp_init_vmcb(svm); + + if (snp_secure_tsc_enabled(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_AMD64_GUEST_TSC_FREQ, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cb172369c606d1..417d3f0aa58481 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -151,6 +151,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_PL2_SSP, .always = false }, { .index = MSR_IA32_PL3_SSP, .always = false }, { .index = MSR_IA32_INT_SSP_TAB, .always = false }, + { .index = MSR_AMD64_GUEST_TSC_FREQ, .always = false }, { .index = MSR_INVALID, .always = false }, }; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8b40e4bd1c200c..efc3eaf20cdba6 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 55 +#define MAX_DIRECT_ACCESS_MSRS 56 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -383,39 +383,41 @@ static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm) return &to_kvm_svm(kvm)->sev_info; } +#ifdef CONFIG_KVM_AMD_SEV static __always_inline bool sev_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->active; -#else - return false; -#endif } - static __always_inline bool sev_es_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->es_active && !WARN_ON_ONCE(!sev->active); -#else - return false; -#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_VMPL0] & SVM_SEV_FEAT_SNP_ACTIVE) && !WARN_ON_ONCE(!sev_es_guest(kvm)); +} + +static inline bool snp_secure_tsc_enabled(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + + return (sev->vmsa_features[SVM_SEV_VMPL0] & SVM_SEV_FEAT_SECURE_TSC) && + !WARN_ON_ONCE(!sev_snp_guest(kvm)); +} #else - return false; +#define sev_guest(kvm) false +#define sev_es_guest(kvm) false +#define sev_snp_guest(kvm) false +#define snp_secure_tsc_enabled(kvm) false #endif -} static inline bool ghcb_gpa_is_registered(struct vcpu_svm *svm, u64 val) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b78fb6806bd822..bc295f5d994a34 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2587,6 +2587,9 @@ EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) { + if (vcpu->arch.guest_tsc_protected) + return; + trace_kvm_write_tsc_offset(vcpu->vcpu_id, vcpu->arch.l1_tsc_offset, l1_offset); @@ -2644,12 +2647,18 @@ static inline bool kvm_check_tsc_unstable(void) * participates in. */ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, - u64 ns, bool matched) + u64 ns, bool matched, bool user_set_tsc) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.tsc_write_lock); + if (vcpu->arch.guest_tsc_protected) + return; + + if (user_set_tsc) + vcpu->kvm->arch.user_set_tsc = true; + /* * We also track th most recent recorded KHZ, write and time to * allow the matching interval to be extended at each write. @@ -2735,8 +2744,6 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) } } - if (user_value) - kvm->arch.user_set_tsc = true; /* * For a reliable TSC, we can match TSC offsets, and for an unstable @@ -2756,7 +2763,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) matched = true; } - __kvm_synchronize_tsc(vcpu, offset, data, ns, matched); + __kvm_synchronize_tsc(vcpu, offset, data, ns, matched, !!user_value); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); } @@ -3933,7 +3940,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: if (msr_info->host_initiated) { kvm_synchronize_tsc(vcpu, &data); - } else { + } else if (!vcpu->arch.guest_tsc_protected) { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; @@ -5029,7 +5036,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); - vcpu->arch.tsc_catchup = 1; + if (!vcpu->arch.guest_tsc_protected) + vcpu->arch.tsc_catchup = 1; } if (kvm_lapic_hv_timer_in_use(vcpu)) @@ -5762,8 +5770,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); - kvm->arch.user_set_tsc = true; - __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); + __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched, true); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); r = 0; diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 0a120d85d7bba8..95bae74fdab233 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -94,6 +94,8 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); + snp_secure_tsc_prepare(); + print_mem_encrypt_feature_info(); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 86a476a426c26d..24b84ebc5dc427 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -516,6 +516,9 @@ void __init sme_early_init(void) * kernel mapped. */ snp_update_svsm_ca(); + + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index ac33b2263a434d..e6c7686f443a06 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -495,10 +495,10 @@ void __head sme_enable(struct boot_params *bp) unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; unsigned long me_mask; - bool snp; + bool snp_en; u64 msr; - snp = snp_init(bp); + snp_en = snp_init(bp); /* Check for the SME/SEV support leaf */ eax = 0x80000000; @@ -531,8 +531,11 @@ void __head sme_enable(struct boot_params *bp) RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; - /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) + /* + * Any discrepancies between the presence of a CC blob and SNP + * enablement abort the guest. + */ + if (snp_en ^ !!(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig index 1cffc72c41cb14..a6405ab6c2c37c 100644 --- a/drivers/virt/coco/sev-guest/Kconfig +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -2,9 +2,6 @@ config SEV_GUEST tristate "AMD SEV Guest driver" default m depends on AMD_MEM_ENCRYPT - select CRYPTO - select CRYPTO_AEAD2 - select CRYPTO_GCM select TSM_REPORTS help SEV-SNP firmware provides the guest a mechanism to communicate with diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index 6fc7884ea0a11d..82e4242495227c 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -17,8 +17,7 @@ #include #include #include -#include -#include +#include #include #include #include @@ -31,44 +30,20 @@ #include #define DEVICE_NAME "sev-guest" -#define AAD_LEN 48 -#define MSG_HDR_VER 1 - -#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) -#define SNP_REQ_RETRY_DELAY (2*HZ) #define SVSM_MAX_RETRIES 3 -struct snp_guest_crypto { - struct crypto_aead *tfm; - u8 *iv, *authtag; - int iv_len, a_len; -}; - struct snp_guest_dev { struct device *dev; struct miscdevice misc; - void *certs_data; - struct snp_guest_crypto *crypto; - /* request and response are in unencrypted memory */ - struct snp_guest_msg *request, *response; + struct snp_msg_desc *msg_desc; - /* - * Avoid information leakage by double-buffering shared messages - * in fields that are in regular encrypted memory. - */ - struct snp_guest_msg secret_request, secret_response; - - struct snp_secrets_page *secrets; - struct snp_req_data input; union { struct snp_report_req report; struct snp_derived_key_req derived_key; struct snp_ext_report_req ext_report; } req; - u32 *os_area_msg_seqno; - u8 *vmpck; }; /* @@ -82,86 +57,6 @@ static int vmpck_id = -1; module_param(vmpck_id, int, 0444); MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP."); -/* Mutex to serialize the shared buffer access and command handling. */ -static DEFINE_MUTEX(snp_cmd_mutex); - -static bool is_vmpck_empty(struct snp_guest_dev *snp_dev) -{ - char zero_key[VMPCK_KEY_LEN] = {0}; - - if (snp_dev->vmpck) - return !memcmp(snp_dev->vmpck, zero_key, VMPCK_KEY_LEN); - - return true; -} - -/* - * If an error is received from the host or AMD Secure Processor (ASP) there - * are two options. Either retry the exact same encrypted request or discontinue - * using the VMPCK. - * - * This is because in the current encryption scheme GHCB v2 uses AES-GCM to - * encrypt the requests. The IV for this scheme is the sequence number. GCM - * cannot tolerate IV reuse. - * - * The ASP FW v1.51 only increments the sequence numbers on a successful - * guest<->ASP back and forth and only accepts messages at its exact sequence - * number. - * - * So if the sequence number were to be reused the encryption scheme is - * vulnerable. If the sequence number were incremented for a fresh IV the ASP - * will reject the request. - */ -static void snp_disable_vmpck(struct snp_guest_dev *snp_dev) -{ - dev_alert(snp_dev->dev, "Disabling vmpck_id %d to prevent IV reuse.\n", - vmpck_id); - memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN); - snp_dev->vmpck = NULL; -} - -static inline u64 __snp_get_msg_seqno(struct snp_guest_dev *snp_dev) -{ - u64 count; - - lockdep_assert_held(&snp_cmd_mutex); - - /* Read the current message sequence counter from secrets pages */ - count = *snp_dev->os_area_msg_seqno; - - return count + 1; -} - -/* Return a non-zero on success */ -static u64 snp_get_msg_seqno(struct snp_guest_dev *snp_dev) -{ - u64 count = __snp_get_msg_seqno(snp_dev); - - /* - * The message sequence counter for the SNP guest request is a 64-bit - * value but the version 2 of GHCB specification defines a 32-bit storage - * for it. If the counter exceeds the 32-bit value then return zero. - * The caller should check the return value, but if the caller happens to - * not check the value and use it, then the firmware treats zero as an - * invalid number and will fail the message request. - */ - if (count >= UINT_MAX) { - dev_err(snp_dev->dev, "request message sequence counter overflow\n"); - return 0; - } - - return count; -} - -static void snp_inc_msg_seqno(struct snp_guest_dev *snp_dev) -{ - /* - * The counter is also incremented by the PSP, so increment it by 2 - * and save in secrets page. - */ - *snp_dev->os_area_msg_seqno += 2; -} - static inline struct snp_guest_dev *to_snp_dev(struct file *file) { struct miscdevice *dev = file->private_data; @@ -169,324 +64,6 @@ static inline struct snp_guest_dev *to_snp_dev(struct file *file) return container_of(dev, struct snp_guest_dev, misc); } -static struct snp_guest_crypto *init_crypto(struct snp_guest_dev *snp_dev, u8 *key, size_t keylen) -{ - struct snp_guest_crypto *crypto; - - crypto = kzalloc(sizeof(*crypto), GFP_KERNEL_ACCOUNT); - if (!crypto) - return NULL; - - crypto->tfm = crypto_alloc_aead("gcm(aes)", 0, 0); - if (IS_ERR(crypto->tfm)) - goto e_free; - - if (crypto_aead_setkey(crypto->tfm, key, keylen)) - goto e_free_crypto; - - crypto->iv_len = crypto_aead_ivsize(crypto->tfm); - crypto->iv = kmalloc(crypto->iv_len, GFP_KERNEL_ACCOUNT); - if (!crypto->iv) - goto e_free_crypto; - - if (crypto_aead_authsize(crypto->tfm) > MAX_AUTHTAG_LEN) { - if (crypto_aead_setauthsize(crypto->tfm, MAX_AUTHTAG_LEN)) { - dev_err(snp_dev->dev, "failed to set authsize to %d\n", MAX_AUTHTAG_LEN); - goto e_free_iv; - } - } - - crypto->a_len = crypto_aead_authsize(crypto->tfm); - crypto->authtag = kmalloc(crypto->a_len, GFP_KERNEL_ACCOUNT); - if (!crypto->authtag) - goto e_free_iv; - - return crypto; - -e_free_iv: - kfree(crypto->iv); -e_free_crypto: - crypto_free_aead(crypto->tfm); -e_free: - kfree(crypto); - - return NULL; -} - -static void deinit_crypto(struct snp_guest_crypto *crypto) -{ - crypto_free_aead(crypto->tfm); - kfree(crypto->iv); - kfree(crypto->authtag); - kfree(crypto); -} - -static int enc_dec_message(struct snp_guest_crypto *crypto, struct snp_guest_msg *msg, - u8 *src_buf, u8 *dst_buf, size_t len, bool enc) -{ - struct snp_guest_msg_hdr *hdr = &msg->hdr; - struct scatterlist src[3], dst[3]; - DECLARE_CRYPTO_WAIT(wait); - struct aead_request *req; - int ret; - - req = aead_request_alloc(crypto->tfm, GFP_KERNEL); - if (!req) - return -ENOMEM; - - /* - * AEAD memory operations: - * +------ AAD -------+------- DATA -----+---- AUTHTAG----+ - * | msg header | plaintext | hdr->authtag | - * | bytes 30h - 5Fh | or | | - * | | cipher | | - * +------------------+------------------+----------------+ - */ - sg_init_table(src, 3); - sg_set_buf(&src[0], &hdr->algo, AAD_LEN); - sg_set_buf(&src[1], src_buf, hdr->msg_sz); - sg_set_buf(&src[2], hdr->authtag, crypto->a_len); - - sg_init_table(dst, 3); - sg_set_buf(&dst[0], &hdr->algo, AAD_LEN); - sg_set_buf(&dst[1], dst_buf, hdr->msg_sz); - sg_set_buf(&dst[2], hdr->authtag, crypto->a_len); - - aead_request_set_ad(req, AAD_LEN); - aead_request_set_tfm(req, crypto->tfm); - aead_request_set_callback(req, 0, crypto_req_done, &wait); - - aead_request_set_crypt(req, src, dst, len, crypto->iv); - ret = crypto_wait_req(enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req), &wait); - - aead_request_free(req); - return ret; -} - -static int __enc_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg, - void *plaintext, size_t len) -{ - struct snp_guest_crypto *crypto = snp_dev->crypto; - struct snp_guest_msg_hdr *hdr = &msg->hdr; - - memset(crypto->iv, 0, crypto->iv_len); - memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno)); - - return enc_dec_message(crypto, msg, plaintext, msg->payload, len, true); -} - -static int dec_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg, - void *plaintext, size_t len) -{ - struct snp_guest_crypto *crypto = snp_dev->crypto; - struct snp_guest_msg_hdr *hdr = &msg->hdr; - - /* Build IV with response buffer sequence number */ - memset(crypto->iv, 0, crypto->iv_len); - memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno)); - - return enc_dec_message(crypto, msg, msg->payload, plaintext, len, false); -} - -static int verify_and_dec_payload(struct snp_guest_dev *snp_dev, void *payload, u32 sz) -{ - struct snp_guest_crypto *crypto = snp_dev->crypto; - struct snp_guest_msg *resp = &snp_dev->secret_response; - struct snp_guest_msg *req = &snp_dev->secret_request; - struct snp_guest_msg_hdr *req_hdr = &req->hdr; - struct snp_guest_msg_hdr *resp_hdr = &resp->hdr; - - dev_dbg(snp_dev->dev, "response [seqno %lld type %d version %d sz %d]\n", - resp_hdr->msg_seqno, resp_hdr->msg_type, resp_hdr->msg_version, resp_hdr->msg_sz); - - /* Copy response from shared memory to encrypted memory. */ - memcpy(resp, snp_dev->response, sizeof(*resp)); - - /* Verify that the sequence counter is incremented by 1 */ - if (unlikely(resp_hdr->msg_seqno != (req_hdr->msg_seqno + 1))) - return -EBADMSG; - - /* Verify response message type and version number. */ - if (resp_hdr->msg_type != (req_hdr->msg_type + 1) || - resp_hdr->msg_version != req_hdr->msg_version) - return -EBADMSG; - - /* - * If the message size is greater than our buffer length then return - * an error. - */ - if (unlikely((resp_hdr->msg_sz + crypto->a_len) > sz)) - return -EBADMSG; - - /* Decrypt the payload */ - return dec_payload(snp_dev, resp, payload, resp_hdr->msg_sz + crypto->a_len); -} - -static int enc_payload(struct snp_guest_dev *snp_dev, u64 seqno, int version, u8 type, - void *payload, size_t sz) -{ - struct snp_guest_msg *req = &snp_dev->secret_request; - struct snp_guest_msg_hdr *hdr = &req->hdr; - - memset(req, 0, sizeof(*req)); - - hdr->algo = SNP_AEAD_AES_256_GCM; - hdr->hdr_version = MSG_HDR_VER; - hdr->hdr_sz = sizeof(*hdr); - hdr->msg_type = type; - hdr->msg_version = version; - hdr->msg_seqno = seqno; - hdr->msg_vmpck = vmpck_id; - hdr->msg_sz = sz; - - /* Verify the sequence number is non-zero */ - if (!hdr->msg_seqno) - return -ENOSR; - - dev_dbg(snp_dev->dev, "request [seqno %lld type %d version %d sz %d]\n", - hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); - - return __enc_payload(snp_dev, req, payload, sz); -} - -static int __handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, - struct snp_guest_request_ioctl *rio) -{ - unsigned long req_start = jiffies; - unsigned int override_npages = 0; - u64 override_err = 0; - int rc; - -retry_request: - /* - * Call firmware to process the request. In this function the encrypted - * message enters shared memory with the host. So after this call the - * sequence number must be incremented or the VMPCK must be deleted to - * prevent reuse of the IV. - */ - rc = snp_issue_guest_request(exit_code, &snp_dev->input, rio); - switch (rc) { - case -ENOSPC: - /* - * If the extended guest request fails due to having too - * small of a certificate data buffer, retry the same - * guest request without the extended data request in - * order to increment the sequence number and thus avoid - * IV reuse. - */ - override_npages = snp_dev->input.data_npages; - exit_code = SVM_VMGEXIT_GUEST_REQUEST; - - /* - * Override the error to inform callers the given extended - * request buffer size was too small and give the caller the - * required buffer size. - */ - override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN); - - /* - * If this call to the firmware succeeds, the sequence number can - * be incremented allowing for continued use of the VMPCK. If - * there is an error reflected in the return value, this value - * is checked further down and the result will be the deletion - * of the VMPCK and the error code being propagated back to the - * user as an ioctl() return code. - */ - goto retry_request; - - /* - * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been - * throttled. Retry in the driver to avoid returning and reusing the - * message sequence number on a different message. - */ - case -EAGAIN: - if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) { - rc = -ETIMEDOUT; - break; - } - schedule_timeout_killable(SNP_REQ_RETRY_DELAY); - goto retry_request; - } - - /* - * Increment the message sequence number. There is no harm in doing - * this now because decryption uses the value stored in the response - * structure and any failure will wipe the VMPCK, preventing further - * use anyway. - */ - snp_inc_msg_seqno(snp_dev); - - if (override_err) { - rio->exitinfo2 = override_err; - - /* - * If an extended guest request was issued and the supplied certificate - * buffer was not large enough, a standard guest request was issued to - * prevent IV reuse. If the standard request was successful, return -EIO - * back to the caller as would have originally been returned. - */ - if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) - rc = -EIO; - } - - if (override_npages) - snp_dev->input.data_npages = override_npages; - - return rc; -} - -static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, - struct snp_guest_request_ioctl *rio, u8 type, - void *req_buf, size_t req_sz, void *resp_buf, - u32 resp_sz) -{ - u64 seqno; - int rc; - - /* Get message sequence and verify that its a non-zero */ - seqno = snp_get_msg_seqno(snp_dev); - if (!seqno) - return -EIO; - - /* Clear shared memory's response for the host to populate. */ - memset(snp_dev->response, 0, sizeof(struct snp_guest_msg)); - - /* Encrypt the userspace provided payload in snp_dev->secret_request. */ - rc = enc_payload(snp_dev, seqno, rio->msg_version, type, req_buf, req_sz); - if (rc) - return rc; - - /* - * Write the fully encrypted request to the shared unencrypted - * request page. - */ - memcpy(snp_dev->request, &snp_dev->secret_request, - sizeof(snp_dev->secret_request)); - - rc = __handle_guest_request(snp_dev, exit_code, rio); - if (rc) { - if (rc == -EIO && - rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) - return rc; - - dev_alert(snp_dev->dev, - "Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n", - rc, rio->exitinfo2); - - snp_disable_vmpck(snp_dev); - return rc; - } - - rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz); - if (rc) { - dev_alert(snp_dev->dev, "Detected unexpected decode failure from ASP. rc: %d\n", rc); - snp_disable_vmpck(snp_dev); - return rc; - } - - return 0; -} - struct snp_req_resp { sockptr_t req_data; sockptr_t resp_data; @@ -494,17 +71,16 @@ struct snp_req_resp { static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) { - struct snp_guest_crypto *crypto = snp_dev->crypto; - struct snp_report_req *req = &snp_dev->req.report; - struct snp_report_resp *resp; + struct snp_report_req *report_req = &snp_dev->req.report; + struct snp_msg_desc *mdesc = snp_dev->msg_desc; + struct snp_report_resp *report_resp; + struct snp_guest_req req = {}; int rc, resp_len; - lockdep_assert_held(&snp_cmd_mutex); - if (!arg->req_data || !arg->resp_data) return -EINVAL; - if (copy_from_user(req, (void __user *)arg->req_data, sizeof(*req))) + if (copy_from_user(report_req, (void __user *)arg->req_data, sizeof(*report_req))) return -EFAULT; /* @@ -512,36 +88,42 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io * response payload. Make sure that it has enough space to cover the * authtag. */ - resp_len = sizeof(resp->data) + crypto->a_len; - resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); - if (!resp) + resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize; + report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!report_resp) return -ENOMEM; - rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg, - SNP_MSG_REPORT_REQ, req, sizeof(*req), resp->data, - resp_len); + req.msg_version = arg->msg_version; + req.msg_type = SNP_MSG_REPORT_REQ; + req.vmpck_id = mdesc->vmpck_id; + req.req_buf = report_req; + req.req_sz = sizeof(*report_req); + req.resp_buf = report_resp->data; + req.resp_sz = resp_len; + req.exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + rc = snp_send_guest_request(mdesc, &req, arg); if (rc) goto e_free; - if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp))) + if (copy_to_user((void __user *)arg->resp_data, report_resp, sizeof(*report_resp))) rc = -EFAULT; e_free: - kfree(resp); + kfree(report_resp); return rc; } static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) { - struct snp_derived_key_req *req = &snp_dev->req.derived_key; - struct snp_guest_crypto *crypto = snp_dev->crypto; - struct snp_derived_key_resp resp = {0}; + struct snp_derived_key_req *derived_key_req = &snp_dev->req.derived_key; + struct snp_derived_key_resp derived_key_resp = {0}; + struct snp_msg_desc *mdesc = snp_dev->msg_desc; + struct snp_guest_req req = {}; int rc, resp_len; /* Response data is 64 bytes and max authsize for GCM is 16 bytes. */ u8 buf[64 + 16]; - lockdep_assert_held(&snp_cmd_mutex); - if (!arg->req_data || !arg->resp_data) return -EINVAL; @@ -550,25 +132,35 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque * response payload. Make sure that it has enough space to cover the * authtag. */ - resp_len = sizeof(resp.data) + crypto->a_len; + resp_len = sizeof(derived_key_resp.data) + mdesc->ctx->authsize; if (sizeof(buf) < resp_len) return -ENOMEM; - if (copy_from_user(req, (void __user *)arg->req_data, sizeof(*req))) + if (copy_from_user(derived_key_req, (void __user *)arg->req_data, + sizeof(*derived_key_req))) return -EFAULT; - rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg, - SNP_MSG_KEY_REQ, req, sizeof(*req), buf, resp_len); + req.msg_version = arg->msg_version; + req.msg_type = SNP_MSG_KEY_REQ; + req.vmpck_id = mdesc->vmpck_id; + req.req_buf = derived_key_req; + req.req_sz = sizeof(*derived_key_req); + req.resp_buf = buf; + req.resp_sz = resp_len; + req.exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + rc = snp_send_guest_request(mdesc, &req, arg); if (rc) return rc; - memcpy(resp.data, buf, sizeof(resp.data)); - if (copy_to_user((void __user *)arg->resp_data, &resp, sizeof(resp))) + memcpy(derived_key_resp.data, buf, sizeof(derived_key_resp.data)); + if (copy_to_user((void __user *)arg->resp_data, &derived_key_resp, + sizeof(derived_key_resp))) rc = -EFAULT; /* The response buffer contains the sensitive data, explicitly clear it. */ memzero_explicit(buf, sizeof(buf)); - memzero_explicit(&resp, sizeof(resp)); + memzero_explicit(&derived_key_resp, sizeof(derived_key_resp)); return rc; } @@ -576,33 +168,32 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques struct snp_req_resp *io) { - struct snp_ext_report_req *req = &snp_dev->req.ext_report; - struct snp_guest_crypto *crypto = snp_dev->crypto; - struct snp_report_resp *resp; + struct snp_ext_report_req *report_req = &snp_dev->req.ext_report; + struct snp_msg_desc *mdesc = snp_dev->msg_desc; + struct snp_report_resp *report_resp; + struct snp_guest_req req = {}; int ret, npages = 0, resp_len; sockptr_t certs_address; - lockdep_assert_held(&snp_cmd_mutex); - if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data)) return -EINVAL; - if (copy_from_sockptr(req, io->req_data, sizeof(*req))) + if (copy_from_sockptr(report_req, io->req_data, sizeof(*report_req))) return -EFAULT; /* caller does not want certificate data */ - if (!req->certs_len || !req->certs_address) + if (!report_req->certs_len || !report_req->certs_address) goto cmd; - if (req->certs_len > SEV_FW_BLOB_MAX_SIZE || - !IS_ALIGNED(req->certs_len, PAGE_SIZE)) + if (report_req->certs_len > SEV_FW_BLOB_MAX_SIZE || + !IS_ALIGNED(report_req->certs_len, PAGE_SIZE)) return -EINVAL; if (sockptr_is_kernel(io->resp_data)) { - certs_address = KERNEL_SOCKPTR((void *)req->certs_address); + certs_address = KERNEL_SOCKPTR((void *)report_req->certs_address); } else { - certs_address = USER_SOCKPTR((void __user *)req->certs_address); - if (!access_ok(certs_address.user, req->certs_len)) + certs_address = USER_SOCKPTR((void __user *)report_req->certs_address); + if (!access_ok(certs_address.user, report_req->certs_len)) return -EFAULT; } @@ -612,45 +203,53 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques * the host. If host does not supply any certs in it, then copy * zeros to indicate that certificate data was not provided. */ - memset(snp_dev->certs_data, 0, req->certs_len); - npages = req->certs_len >> PAGE_SHIFT; + memset(mdesc->certs_data, 0, report_req->certs_len); + npages = report_req->certs_len >> PAGE_SHIFT; cmd: /* * The intermediate response buffer is used while decrypting the * response payload. Make sure that it has enough space to cover the * authtag. */ - resp_len = sizeof(resp->data) + crypto->a_len; - resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); - if (!resp) + resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize; + report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!report_resp) return -ENOMEM; - snp_dev->input.data_npages = npages; - ret = handle_guest_request(snp_dev, SVM_VMGEXIT_EXT_GUEST_REQUEST, arg, - SNP_MSG_REPORT_REQ, &req->data, - sizeof(req->data), resp->data, resp_len); + mdesc->input.data_npages = npages; + + req.msg_version = arg->msg_version; + req.msg_type = SNP_MSG_REPORT_REQ; + req.vmpck_id = mdesc->vmpck_id; + req.req_buf = &report_req->data; + req.req_sz = sizeof(report_req->data); + req.resp_buf = report_resp->data; + req.resp_sz = resp_len; + req.exit_code = SVM_VMGEXIT_EXT_GUEST_REQUEST; + + ret = snp_send_guest_request(mdesc, &req, arg); /* If certs length is invalid then copy the returned length */ if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) { - req->certs_len = snp_dev->input.data_npages << PAGE_SHIFT; + report_req->certs_len = mdesc->input.data_npages << PAGE_SHIFT; - if (copy_to_sockptr(io->req_data, req, sizeof(*req))) + if (copy_to_sockptr(io->req_data, report_req, sizeof(*report_req))) ret = -EFAULT; } if (ret) goto e_free; - if (npages && copy_to_sockptr(certs_address, snp_dev->certs_data, req->certs_len)) { + if (npages && copy_to_sockptr(certs_address, mdesc->certs_data, report_req->certs_len)) { ret = -EFAULT; goto e_free; } - if (copy_to_sockptr(io->resp_data, resp, sizeof(*resp))) + if (copy_to_sockptr(io->resp_data, report_resp, sizeof(*report_resp))) ret = -EFAULT; e_free: - kfree(resp); + kfree(report_resp); return ret; } @@ -671,15 +270,6 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long if (!input.msg_version) return -EINVAL; - mutex_lock(&snp_cmd_mutex); - - /* Check if the VMPCK is not empty */ - if (is_vmpck_empty(snp_dev)) { - dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n"); - mutex_unlock(&snp_cmd_mutex); - return -ENOTTY; - } - switch (ioctl) { case SNP_GET_REPORT: ret = get_report(snp_dev, &input); @@ -701,84 +291,17 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long break; } - mutex_unlock(&snp_cmd_mutex); - if (input.exitinfo2 && copy_to_user(argp, &input, sizeof(input))) return -EFAULT; return ret; } -static void free_shared_pages(void *buf, size_t sz) -{ - unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - int ret; - - if (!buf) - return; - - ret = set_memory_encrypted((unsigned long)buf, npages); - if (ret) { - WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); - return; - } - - __free_pages(virt_to_page(buf), get_order(sz)); -} - -static void *alloc_shared_pages(struct device *dev, size_t sz) -{ - unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - struct page *page; - int ret; - - page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); - if (!page) - return NULL; - - ret = set_memory_decrypted((unsigned long)page_address(page), npages); - if (ret) { - dev_err(dev, "failed to mark page shared, ret=%d\n", ret); - __free_pages(page, get_order(sz)); - return NULL; - } - - return page_address(page); -} - static const struct file_operations snp_guest_fops = { .owner = THIS_MODULE, .unlocked_ioctl = snp_guest_ioctl, }; -static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) -{ - u8 *key = NULL; - - switch (id) { - case 0: - *seqno = &secrets->os_area.msg_seqno_0; - key = secrets->vmpck0; - break; - case 1: - *seqno = &secrets->os_area.msg_seqno_1; - key = secrets->vmpck1; - break; - case 2: - *seqno = &secrets->os_area.msg_seqno_2; - key = secrets->vmpck2; - break; - case 3: - *seqno = &secrets->os_area.msg_seqno_3; - key = secrets->vmpck3; - break; - default: - break; - } - - return key; -} - struct snp_msg_report_resp_hdr { u32 status; u32 report_size; @@ -817,8 +340,6 @@ static int sev_svsm_report_new(struct tsm_report *report, void *data) man_len = SZ_4K; certs_len = SEV_FW_BLOB_MAX_SIZE; - guard(mutex)(&snp_cmd_mutex); - if (guid_is_null(&desc->service_guid)) { call_id = SVSM_ATTEST_CALL(SVSM_ATTEST_SERVICES); } else { @@ -953,14 +474,6 @@ static int sev_report_new(struct tsm_report *report, void *data) if (!buf) return -ENOMEM; - guard(mutex)(&snp_cmd_mutex); - - /* Check if the VMPCK is not empty */ - if (is_vmpck_empty(snp_dev)) { - dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n"); - return -ENOTTY; - } - cert_table = buf + report_size; struct snp_ext_report_req ext_req = { .data = { .vmpl = desc->privlevel }, @@ -1082,107 +595,60 @@ static void unregister_sev_tsm(void *data) static int __init sev_guest_probe(struct platform_device *pdev) { - struct sev_guest_platform_data *data; - struct snp_secrets_page *secrets; struct device *dev = &pdev->dev; struct snp_guest_dev *snp_dev; + struct snp_msg_desc *mdesc; struct miscdevice *misc; - void __iomem *mapping; int ret; - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) - return -ENODEV; + BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE); - if (!dev->platform_data) - return -ENODEV; - - data = (struct sev_guest_platform_data *)dev->platform_data; - mapping = ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); - if (!mapping) + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return -ENODEV; - secrets = (__force void *)mapping; - - ret = -ENOMEM; snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); if (!snp_dev) - goto e_unmap; - - /* Adjust the default VMPCK key based on the executing VMPL level */ - if (vmpck_id == -1) - vmpck_id = snp_vmpl; + return -ENOMEM; - ret = -EINVAL; - 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; - } + mdesc = snp_msg_alloc(); + if (IS_ERR_OR_NULL(mdesc)) + return -ENOMEM; - /* Verify that VMPCK is not zero. */ - if (is_vmpck_empty(snp_dev)) { - dev_err(dev, "vmpck id %d is null\n", vmpck_id); - goto e_unmap; - } + ret = snp_msg_init(mdesc, vmpck_id); + if (ret) + goto e_msg_init; platform_set_drvdata(pdev, snp_dev); snp_dev->dev = dev; - 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)); - if (!snp_dev->request) - goto e_unmap; - - snp_dev->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); - if (!snp_dev->response) - goto e_free_request; - - snp_dev->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE); - if (!snp_dev->certs_data) - goto e_free_response; - - ret = -EIO; - snp_dev->crypto = init_crypto(snp_dev, snp_dev->vmpck, VMPCK_KEY_LEN); - if (!snp_dev->crypto) - goto e_free_cert_data; misc = &snp_dev->misc; misc->minor = MISC_DYNAMIC_MINOR; misc->name = DEVICE_NAME; misc->fops = &snp_guest_fops; - /* initial the input address for guest request */ - snp_dev->input.req_gpa = __pa(snp_dev->request); - snp_dev->input.resp_gpa = __pa(snp_dev->response); - snp_dev->input.data_gpa = __pa(snp_dev->certs_data); - /* Set the privlevel_floor attribute based on the vmpck_id */ - sev_tsm_ops.privlevel_floor = vmpck_id; + sev_tsm_ops.privlevel_floor = mdesc->vmpck_id; ret = tsm_register(&sev_tsm_ops, snp_dev); if (ret) - goto e_free_cert_data; + goto e_msg_init; ret = devm_add_action_or_reset(&pdev->dev, unregister_sev_tsm, NULL); if (ret) - goto e_free_cert_data; + goto e_msg_init; ret = misc_register(misc); if (ret) - goto e_free_cert_data; + goto e_msg_init; - dev_info(dev, "Initialized SEV guest driver (using vmpck_id %d)\n", vmpck_id); + snp_dev->msg_desc = mdesc; + dev_info(dev, "Initialized SEV guest driver (using VMPCK%d communication key)\n", + mdesc->vmpck_id); return 0; -e_free_cert_data: - free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE); -e_free_response: - free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg)); -e_free_request: - free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); -e_unmap: - iounmap(mapping); +e_msg_init: + snp_msg_free(mdesc); + return ret; } @@ -1190,10 +656,7 @@ static void __exit sev_guest_remove(struct platform_device *pdev) { struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev); - free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE); - free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg)); - free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); - deinit_crypto(snp_dev->crypto); + snp_msg_free(snp_dev->msg_desc); misc_deregister(&snp_dev->misc); } diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index caa4b443063469..0bf7d33a1048cf 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -81,6 +81,14 @@ enum cc_attr { */ CC_ATTR_GUEST_SEV_SNP, + /** + * @CC_ATTR_GUEST_SNP_SECURE_TSC: SNP Secure TSC is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP Secure TSC feature. + */ + CC_ATTR_GUEST_SNP_SECURE_TSC, + /** * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. * diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 903ddfea858505..613a8209bed275 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -594,6 +594,7 @@ struct sev_data_snp_addr { * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the * purpose of guest-assisted migration. * @rsvd: reserved + * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest * @gosvw: guest OS-visible workarounds, as defined by hypervisor */ struct sev_data_snp_launch_start { @@ -603,6 +604,7 @@ struct sev_data_snp_launch_start { u32 ma_en:1; /* In */ u32 imi_en:1; /* In */ u32 rsvd:30; + u32 desired_tsc_khz; /* In */ u8 gosvw[16]; /* In */ } __packed;