// SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * AMD SVM-SEV support * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ #include #include #include #include #include #include #include #include #include #include #include #include #include "x86.h" #include "svm.h" #include "svm_ops.h" #include "cpuid.h" #include "trace.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) #ifndef CONFIG_KVM_AMD_SEV /* * When this config is not defined, SEV feature is not supported and APIs in * this file are not used but this file still gets compiled into the KVM AMD * module. * * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum * misc_res_type {} defined in linux/misc_cgroup.h. * * Below macros allow compilation to succeed. */ #define MISC_CG_RES_SEV MISC_CG_RES_TYPES #define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES #endif static u8 sev_enc_bit; static int sev_flush_asids(void); static DECLARE_RWSEM(sev_deactivate_lock); static DEFINE_MUTEX(sev_bitmap_lock); unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long *sev_asid_bitmap; static unsigned long *sev_reclaim_asid_bitmap; struct enc_region { struct list_head list; unsigned long npages; struct page **pages; unsigned long uaddr; unsigned long size; }; static int sev_flush_asids(void) { int ret, error = 0; /* * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, * so it must be guarded. */ down_write(&sev_deactivate_lock); wbinvd_on_all_cpus(); 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); return ret; } /* Must be called with the sev_bitmap_lock held */ static bool __sev_recycle_asids(int min_asid, int max_asid) { int pos; /* Check if there are any ASIDs to reclaim before performing a flush */ pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid); if (pos >= max_asid) return false; if (sev_flush_asids()) return false; /* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */ bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, max_sev_asid); bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); return true; } static int sev_asid_new(struct kvm_sev_info *sev) { int pos, min_asid, max_asid, ret; bool retry = true; enum misc_res_type type; type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); ret = misc_cg_try_charge(type, sev->misc_cg, 1); if (ret) { put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; return ret; } mutex_lock(&sev_bitmap_lock); /* * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. */ min_asid = sev->es_active ? 0 : min_sev_asid - 1; max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid); if (pos >= max_asid) { if (retry && __sev_recycle_asids(min_asid, max_asid)) { retry = false; goto again; } mutex_unlock(&sev_bitmap_lock); ret = -EBUSY; goto e_uncharge; } __set_bit(pos, sev_asid_bitmap); mutex_unlock(&sev_bitmap_lock); return pos + 1; e_uncharge: misc_cg_uncharge(type, sev->misc_cg, 1); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; return ret; } static int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->asid; } static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; int cpu, pos; enum misc_res_type type; mutex_lock(&sev_bitmap_lock); pos = sev->asid - 1; __set_bit(pos, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); sd->sev_vmcbs[pos] = NULL; } mutex_unlock(&sev_bitmap_lock); type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; misc_cg_uncharge(type, sev->misc_cg, 1); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; } static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) { struct sev_data_decommission *decommission; struct sev_data_deactivate *data; if (!handle) return; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return; /* deactivate handle */ data->handle = handle; /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ down_read(&sev_deactivate_lock); sev_guest_deactivate(data, NULL); up_read(&sev_deactivate_lock); kfree(data); decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); if (!decommission) return; /* decommission handle */ decommission->handle = handle; sev_guest_decommission(decommission, NULL); kfree(decommission); } static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; int asid, ret; ret = -EBUSY; if (unlikely(sev->active)) return ret; asid = sev_asid_new(sev); if (asid < 0) return ret; sev->asid = asid; ret = sev_platform_init(&argp->error); if (ret) goto e_free; sev->active = true; INIT_LIST_HEAD(&sev->regions_list); return 0; e_free: sev_asid_free(sev); sev->asid = 0; return ret; } static int sev_es_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { if (!sev_es) return -ENOTTY; to_kvm_svm(kvm)->sev_info.es_active = true; return sev_guest_init(kvm, argp); } static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { struct sev_data_activate *data; int asid = sev_get_asid(kvm); int ret; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; /* activate ASID on the given handle */ data->handle = handle; data->asid = asid; ret = sev_guest_activate(data, error); kfree(data); return ret; } static int __sev_issue_cmd(int fd, int id, void *data, int *error) { struct fd f; int ret; f = fdget(fd); if (!f.file) return -EBADF; ret = sev_issue_cmd_external_user(f.file, id, data, error); fdput(f); return ret; } static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return __sev_issue_cmd(sev->fd, id, data, error); } static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_start *start; struct kvm_sev_launch_start params; void *dh_blob, *session_blob; int *error = &argp->error; int ret; if (!sev_guest(kvm)) return -ENOTTY; if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT); if (!start) return -ENOMEM; dh_blob = NULL; if (params.dh_uaddr) { dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len); if (IS_ERR(dh_blob)) { ret = PTR_ERR(dh_blob); goto e_free; } start->dh_cert_address = __sme_set(__pa(dh_blob)); start->dh_cert_len = params.dh_len; } session_blob = NULL; if (params.session_uaddr) { session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len); if (IS_ERR(session_blob)) { ret = PTR_ERR(session_blob); goto e_free_dh; } start->session_address = __sme_set(__pa(session_blob)); start->session_len = params.session_len; } start->handle = params.handle; start->policy = params.policy; /* create memory encryption context */ ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, start, error); if (ret) goto e_free_session; /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start->handle, error); if (ret) goto e_free_session; /* return handle to userspace */ params.handle = start->handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { sev_unbind_asid(kvm, start->handle); ret = -EFAULT; goto e_free_session; } sev->handle = start->handle; sev->fd = argp->sev_fd; e_free_session: kfree(session_blob); e_free_dh: kfree(dh_blob); e_free: kfree(start); return ret; } static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, unsigned long ulen, unsigned long *n, int write) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; unsigned long npages, size; int npinned; unsigned long locked, lock_limit; struct page **pages; unsigned long first, last; int ret; lockdep_assert_held(&kvm->lock); if (ulen == 0 || uaddr + ulen < uaddr) return ERR_PTR(-EINVAL); /* Calculate number of pages. */ first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT; npages = (last - first + 1); locked = sev->pages_locked + npages; lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit); return ERR_PTR(-ENOMEM); } if (WARN_ON_ONCE(npages > INT_MAX)) return ERR_PTR(-EINVAL); /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); if (!pages) return ERR_PTR(-ENOMEM); /* Pin the user virtual address. */ npinned = pin_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); ret = -ENOMEM; goto err; } *n = npages; sev->pages_locked = locked; return pages; err: if (npinned > 0) unpin_user_pages(pages, npinned); kvfree(pages); return ERR_PTR(ret); } static void sev_unpin_memory(struct kvm *kvm, struct page **pages, unsigned long npages) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; unpin_user_pages(pages, npages); kvfree(pages); sev->pages_locked -= npages; } static void sev_clflush_pages(struct page *pages[], unsigned long npages) { uint8_t *page_virtual; unsigned long i; if (this_cpu_has(X86_FEATURE_SME_COHERENT) || npages == 0 || pages == NULL) return; for (i = 0; i < npages; i++) { page_virtual = kmap_atomic(pages[i]); clflush_cache_range(page_virtual, PAGE_SIZE); kunmap_atomic(page_virtual); } } static unsigned long get_num_contig_pages(unsigned long idx, struct page **inpages, unsigned long npages) { unsigned long paddr, next_paddr; unsigned long i = idx + 1, pages = 1; /* find the number of contiguous pages starting from idx */ paddr = __sme_page_pa(inpages[idx]); while (i < npages) { next_paddr = __sme_page_pa(inpages[i++]); if ((paddr + PAGE_SIZE) == next_paddr) { pages++; paddr = next_paddr; continue; } break; } return pages; } static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_launch_update_data params; struct sev_data_launch_update_data *data; struct page **inpages; int ret; if (!sev_guest(kvm)) return -ENOTTY; if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; vaddr = params.uaddr; size = params.len; vaddr_end = vaddr + size; /* Lock the user memory. */ inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1); if (IS_ERR(inpages)) { ret = PTR_ERR(inpages); goto e_free; } /* * Flush (on non-coherent CPUs) before LAUNCH_UPDATE encrypts pages in * place; the cache may contain the data that was written unencrypted. */ sev_clflush_pages(inpages, npages); for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { int offset, len; /* * If the user buffer is not page-aligned, calculate the offset * within the page. */ offset = vaddr & (PAGE_SIZE - 1); /* Calculate the number of pages that can be encrypted in one go. */ pages = get_num_contig_pages(i, inpages, npages); len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); data->handle = sev->handle; data->len = len; data->address = __sme_page_pa(inpages[i]) + offset; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error); if (ret) goto e_unpin; size -= len; next_vaddr = vaddr + len; } e_unpin: /* content of memory is updated, mark pages dirty */ for (i = 0; i < npages; i++) { set_page_dirty_lock(inpages[i]); mark_page_accessed(inpages[i]); } /* unlock the user pages */ sev_unpin_memory(kvm, inpages, npages); e_free: kfree(data); return ret; } static int sev_es_sync_vmsa(struct vcpu_svm *svm) { struct vmcb_save_area *save = &svm->vmcb->save; /* Check some debug related fields before encrypting the VMSA */ if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1)) return -EINVAL; /* Sync registgers */ save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX]; save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX]; save->rcx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; save->rdx = svm->vcpu.arch.regs[VCPU_REGS_RDX]; save->rsp = svm->vcpu.arch.regs[VCPU_REGS_RSP]; save->rbp = svm->vcpu.arch.regs[VCPU_REGS_RBP]; save->rsi = svm->vcpu.arch.regs[VCPU_REGS_RSI]; save->rdi = svm->vcpu.arch.regs[VCPU_REGS_RDI]; #ifdef CONFIG_X86_64 save->r8 = svm->vcpu.arch.regs[VCPU_REGS_R8]; save->r9 = svm->vcpu.arch.regs[VCPU_REGS_R9]; save->r10 = svm->vcpu.arch.regs[VCPU_REGS_R10]; save->r11 = svm->vcpu.arch.regs[VCPU_REGS_R11]; save->r12 = svm->vcpu.arch.regs[VCPU_REGS_R12]; save->r13 = svm->vcpu.arch.regs[VCPU_REGS_R13]; save->r14 = svm->vcpu.arch.regs[VCPU_REGS_R14]; save->r15 = svm->vcpu.arch.regs[VCPU_REGS_R15]; #endif save->rip = svm->vcpu.arch.regs[VCPU_REGS_RIP]; /* Sync some non-GPR registers before encrypting */ save->xcr0 = svm->vcpu.arch.xcr0; save->pkru = svm->vcpu.arch.pkru; save->xss = svm->vcpu.arch.ia32_xss; /* * SEV-ES will use a VMSA that is pointed to by the VMCB, not * the traditional VMSA that is part of the VMCB. Copy the * traditional VMSA as it has been built so far (in prep * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. */ memcpy(svm->vmsa, save, sizeof(*save)); return 0; } static int sev_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_launch_update_vmsa *vmsa; int i, ret; if (!sev_es_guest(kvm)) return -ENOTTY; vmsa = kzalloc(sizeof(*vmsa), GFP_KERNEL); if (!vmsa) return -ENOMEM; for (i = 0; i < kvm->created_vcpus; i++) { struct vcpu_svm *svm = to_svm(kvm->vcpus[i]); /* Perform some pre-encryption checks against the VMSA */ ret = sev_es_sync_vmsa(svm); if (ret) goto e_free; /* * The LAUNCH_UPDATE_VMSA command will perform in-place * encryption of the VMSA memory content (i.e it will write * the same memory region with the guest's key), so invalidate * it first. */ clflush_cache_range(svm->vmsa, PAGE_SIZE); vmsa->handle = sev->handle; vmsa->address = __sme_pa(svm->vmsa); vmsa->len = PAGE_SIZE; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, vmsa, &argp->error); if (ret) goto e_free; svm->vcpu.arch.guest_state_protected = true; } e_free: kfree(vmsa); return ret; } static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { void __user *measure = (void __user *)(uintptr_t)argp->data; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_measure *data; struct kvm_sev_launch_measure params; void __user *p = NULL; void *blob = NULL; int ret; if (!sev_guest(kvm)) return -ENOTTY; if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; /* User wants to query the blob length */ if (!params.len) goto cmd; p = (void __user *)(uintptr_t)params.uaddr; if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) { ret = -EINVAL; goto e_free; } ret = -ENOMEM; blob = kmalloc(params.len, GFP_KERNEL); if (!blob) goto e_free; data->address = __psp_pa(blob); data->len = params.len; } cmd: data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, data, &argp->error); /* * If we query the session length, FW responded with expected data. */ if (!params.len) goto done; if (ret) goto e_free_blob; if (blob) { if (copy_to_user(p, blob, params.len)) ret = -EFAULT; } done: params.len = data->len; if (copy_to_user(measure, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); e_free: kfree(data); return ret; } static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_finish *data; int ret; if (!sev_guest(kvm)) return -ENOTTY; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error); kfree(data); return ret; } static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_guest_status params; struct sev_data_guest_status *data; int ret; if (!sev_guest(kvm)) return -ENOTTY; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error); if (ret) goto e_free; params.policy = data->policy; params.state = data->state; params.handle = data->handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) ret = -EFAULT; e_free: kfree(data); return ret; } static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, unsigned long dst, int size, int *error, bool enc) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_dbg *data; int ret; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; data->handle = sev->handle; data->dst_addr = dst; data->src_addr = src; data->len = size; ret = sev_issue_cmd(kvm, enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, data, error); kfree(data); return ret; } static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, unsigned long dst_paddr, int sz, int *err) { int offset; /* * Its safe to read more than we are asked, caller should ensure that * destination has enough space. */ offset = src_paddr & 15; src_paddr = round_down(src_paddr, 16); sz = round_up(sz + offset, 16); return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); } static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, unsigned long __user dst_uaddr, unsigned long dst_paddr, int size, int *err) { struct page *tpage = NULL; int ret, offset; /* if inputs are not 16-byte then use intermediate buffer */ if (!IS_ALIGNED(dst_paddr, 16) || !IS_ALIGNED(paddr, 16) || !IS_ALIGNED(size, 16)) { tpage = (void *)alloc_page(GFP_KERNEL); if (!tpage) return -ENOMEM; dst_paddr = __sme_page_pa(tpage); } ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err); if (ret) goto e_free; if (tpage) { offset = paddr & 15; if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, page_address(tpage) + offset, size)) ret = -EFAULT; } e_free: if (tpage) __free_page(tpage); return ret; } static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, unsigned long __user vaddr, unsigned long dst_paddr, unsigned long __user dst_vaddr, int size, int *error) { struct page *src_tpage = NULL; struct page *dst_tpage = NULL; int ret, len = size; /* If source buffer is not aligned then use an intermediate buffer */ if (!IS_ALIGNED(vaddr, 16)) { src_tpage = alloc_page(GFP_KERNEL); if (!src_tpage) return -ENOMEM; if (copy_from_user(page_address(src_tpage), (void __user *)(uintptr_t)vaddr, size)) { __free_page(src_tpage); return -EFAULT; } paddr = __sme_page_pa(src_tpage); } /* * If destination buffer or length is not aligned then do read-modify-write: * - decrypt destination in an intermediate buffer * - copy the source buffer in an intermediate buffer * - use the intermediate buffer as source buffer */ if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; dst_tpage = alloc_page(GFP_KERNEL); if (!dst_tpage) { ret = -ENOMEM; goto e_free; } ret = __sev_dbg_decrypt(kvm, dst_paddr, __sme_page_pa(dst_tpage), size, error); if (ret) goto e_free; /* * If source is kernel buffer then use memcpy() otherwise * copy_from_user(). */ dst_offset = dst_paddr & 15; if (src_tpage) memcpy(page_address(dst_tpage) + dst_offset, page_address(src_tpage), size); else { if (copy_from_user(page_address(dst_tpage) + dst_offset, (void __user *)(uintptr_t)vaddr, size)) { ret = -EFAULT; goto e_free; } } paddr = __sme_page_pa(dst_tpage); dst_paddr = round_down(dst_paddr, 16); len = round_up(size, 16); } ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true); e_free: if (src_tpage) __free_page(src_tpage); if (dst_tpage) __free_page(dst_tpage); return ret; } static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) { unsigned long vaddr, vaddr_end, next_vaddr; unsigned long dst_vaddr; struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; unsigned int size; int ret; if (!sev_guest(kvm)) return -ENOTTY; if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) return -EFAULT; if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) return -EINVAL; if (!debug.dst_uaddr) return -EINVAL; vaddr = debug.src_uaddr; size = debug.len; vaddr_end = vaddr + size; dst_vaddr = debug.dst_uaddr; for (; vaddr < vaddr_end; vaddr = next_vaddr) { int len, s_off, d_off; /* lock userspace source and destination page */ src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0); if (IS_ERR(src_p)) return PTR_ERR(src_p); dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1); if (IS_ERR(dst_p)) { sev_unpin_memory(kvm, src_p, n); return PTR_ERR(dst_p); } /* * Flush (on non-coherent CPUs) before DBG_{DE,EN}CRYPT read or modify * the pages; flush the destination too so that future accesses do not * see stale data. */ sev_clflush_pages(src_p, 1); sev_clflush_pages(dst_p, 1); /* * Since user buffer may not be page aligned, calculate the * offset within the page. */ s_off = vaddr & ~PAGE_MASK; d_off = dst_vaddr & ~PAGE_MASK; len = min_t(size_t, (PAGE_SIZE - s_off), size); if (dec) ret = __sev_dbg_decrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, dst_vaddr, __sme_page_pa(dst_p[0]) + d_off, len, &argp->error); else ret = __sev_dbg_encrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, vaddr, __sme_page_pa(dst_p[0]) + d_off, dst_vaddr, len, &argp->error); sev_unpin_memory(kvm, src_p, n); sev_unpin_memory(kvm, dst_p, n); if (ret) goto err; next_vaddr = vaddr + len; dst_vaddr = dst_vaddr + len; size -= len; } err: return ret; } static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_secret *data; struct kvm_sev_launch_secret params; struct page **pages; void *blob, *hdr; unsigned long n, i; int ret, offset; if (!sev_guest(kvm)) return -ENOTTY; if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); if (IS_ERR(pages)) return PTR_ERR(pages); /* * Flush (on non-coherent CPUs) before LAUNCH_SECRET encrypts pages in * place; the cache may contain the data that was written unencrypted. */ sev_clflush_pages(pages, n); /* * The secret must be copied into contiguous memory region, lets verify * that userspace memory pages are contiguous before we issue command. */ if (get_num_contig_pages(0, pages, n) != n) { ret = -EINVAL; goto e_unpin_memory; } ret = -ENOMEM; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) goto e_unpin_memory; offset = params.guest_uaddr & (PAGE_SIZE - 1); data->guest_address = __sme_page_pa(pages[0]) + offset; data->guest_len = params.guest_len; blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); if (IS_ERR(blob)) { ret = PTR_ERR(blob); goto e_free; } data->trans_address = __psp_pa(blob); data->trans_len = params.trans_len; hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); if (IS_ERR(hdr)) { ret = PTR_ERR(hdr); goto e_free_blob; } data->hdr_address = __psp_pa(hdr); data->hdr_len = params.hdr_len; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); kfree(hdr); e_free_blob: kfree(blob); e_free: kfree(data); e_unpin_memory: /* content of memory is updated, mark pages dirty */ for (i = 0; i < n; i++) { set_page_dirty_lock(pages[i]); mark_page_accessed(pages[i]); } sev_unpin_memory(kvm, pages, n); return ret; } static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) { void __user *report = (void __user *)(uintptr_t)argp->data; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_attestation_report *data; struct kvm_sev_attestation_report params; void __user *p; void *blob = NULL; int ret; if (!sev_guest(kvm)) return -ENOTTY; if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; /* User wants to query the blob length */ if (!params.len) goto cmd; p = (void __user *)(uintptr_t)params.uaddr; if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) { ret = -EINVAL; goto e_free; } ret = -ENOMEM; blob = kmalloc(params.len, GFP_KERNEL); if (!blob) goto e_free; data->address = __psp_pa(blob); data->len = params.len; memcpy(data->mnonce, params.mnonce, sizeof(params.mnonce)); } cmd: data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, data, &argp->error); /* * If we query the session length, FW responded with expected data. */ if (!params.len) goto done; if (ret) goto e_free_blob; if (blob) { if (copy_to_user(p, blob, params.len)) ret = -EFAULT; } done: params.len = data->len; if (copy_to_user(report, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); e_free: kfree(data); return ret; } int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; int r; if (!svm_sev_enabled() || !sev) return -ENOTTY; if (!argp) return 0; if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) return -EFAULT; mutex_lock(&kvm->lock); switch (sev_cmd.id) { case KVM_SEV_INIT: r = sev_guest_init(kvm, &sev_cmd); break; case KVM_SEV_ES_INIT: r = sev_es_guest_init(kvm, &sev_cmd); break; case KVM_SEV_LAUNCH_START: r = sev_launch_start(kvm, &sev_cmd); break; case KVM_SEV_LAUNCH_UPDATE_DATA: r = sev_launch_update_data(kvm, &sev_cmd); break; case KVM_SEV_LAUNCH_UPDATE_VMSA: r = sev_launch_update_vmsa(kvm, &sev_cmd); break; case KVM_SEV_LAUNCH_MEASURE: r = sev_launch_measure(kvm, &sev_cmd); break; case KVM_SEV_LAUNCH_FINISH: r = sev_launch_finish(kvm, &sev_cmd); break; case KVM_SEV_GUEST_STATUS: r = sev_guest_status(kvm, &sev_cmd); break; case KVM_SEV_DBG_DECRYPT: r = sev_dbg_crypt(kvm, &sev_cmd, true); break; case KVM_SEV_DBG_ENCRYPT: r = sev_dbg_crypt(kvm, &sev_cmd, false); break; case KVM_SEV_LAUNCH_SECRET: r = sev_launch_secret(kvm, &sev_cmd); break; case KVM_SEV_GET_ATTESTATION_REPORT: r = sev_get_attestation_report(kvm, &sev_cmd); break; default: r = -EINVAL; goto out; } if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) r = -EFAULT; out: mutex_unlock(&kvm->lock); return r; } int svm_register_enc_region(struct kvm *kvm, struct kvm_enc_region *range) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct enc_region *region; int ret = 0; if (!sev_guest(kvm)) return -ENOTTY; if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); if (!region) return -ENOMEM; mutex_lock(&kvm->lock); region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); if (IS_ERR(region->pages)) { ret = PTR_ERR(region->pages); mutex_unlock(&kvm->lock); goto e_free; } region->uaddr = range->addr; region->size = range->size; list_add_tail(®ion->list, &sev->regions_list); mutex_unlock(&kvm->lock); /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with * correct C-bit. */ sev_clflush_pages(region->pages, region->npages); return ret; e_free: kfree(region); return ret; } static struct enc_region * find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct list_head *head = &sev->regions_list; struct enc_region *i; list_for_each_entry(i, head, list) { if (i->uaddr == range->addr && i->size == range->size) return i; } return NULL; } static void __unregister_enc_region_locked(struct kvm *kvm, struct enc_region *region) { sev_unpin_memory(kvm, region->pages, region->npages); list_del(®ion->list); kfree(region); } int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range) { struct enc_region *region; int ret; mutex_lock(&kvm->lock); if (!sev_guest(kvm)) { ret = -ENOTTY; goto failed; } region = find_enc_region(kvm, range); if (!region) { ret = -EINVAL; goto failed; } /* * Ensure that all guest tagged cache entries are flushed before * releasing the pages back to the system for use. CLFLUSH will * not do this, so issue a WBINVD. */ wbinvd_on_all_cpus(); __unregister_enc_region_locked(kvm, region); mutex_unlock(&kvm->lock); return 0; failed: mutex_unlock(&kvm->lock); return ret; } 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; mutex_lock(&kvm->lock); /* * Ensure that all guest tagged cache entries are flushed before * releasing the pages back to the system for use. CLFLUSH will * not do this, so issue a WBINVD. */ wbinvd_on_all_cpus(); /* * if userspace was terminated before unregistering the memory regions * then lets unpin all the registered memory. */ if (!list_empty(head)) { list_for_each_safe(pos, q, head) { __unregister_enc_region_locked(kvm, list_entry(pos, struct enc_region, list)); cond_resched(); } } mutex_unlock(&kvm->lock); sev_unbind_asid(kvm, sev->handle); sev_asid_free(sev); } void __init sev_hardware_setup(void) { unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count; bool sev_es_supported = false; bool sev_supported = false; /* Does the CPU support SEV? */ if (!boot_cpu_has(X86_FEATURE_SEV)) goto out; /* Retrieve SEV CPUID information */ cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); /* Set encryption bit location for SEV-ES guests */ sev_enc_bit = ebx & 0x3f; /* Maximum number of encrypted guests supported simultaneously */ max_sev_asid = ecx; if (!svm_sev_enabled()) goto out; /* Minimum ASID value that should be used for SEV guest */ min_sev_asid = edx; /* Initialize SEV ASID bitmaps */ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) goto out; sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_reclaim_asid_bitmap) goto out; sev_asid_count = max_sev_asid - min_sev_asid + 1; if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)) goto out; pr_info("SEV supported: %u ASIDs\n", sev_asid_count); sev_supported = true; /* SEV-ES support requested? */ if (!sev_es) goto out; /* Does the CPU support SEV-ES? */ if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; /* Has the system been allocated ASIDs for SEV-ES? */ if (min_sev_asid == 1) goto out; sev_es_asid_count = min_sev_asid - 1; if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)) goto out; pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count); sev_es_supported = true; out: sev = sev_supported; sev_es = sev_es_supported; } void sev_hardware_teardown(void) { if (!svm_sev_enabled()) return; bitmap_free(sev_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap); misc_cg_set_capacity(MISC_CG_RES_SEV, 0); misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0); sev_flush_asids(); } /* * Pages used by hardware to hold guest encrypted state must be flushed before * returning them to the system. */ static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, unsigned long len) { /* * If hardware enforced cache coherency for encrypted mappings of the * same physical page is supported, nothing to do. */ if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) return; /* * If the VM Page Flush MSR is supported, use it to flush the page * (using the page virtual address and the guest ASID). */ if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) { struct kvm_sev_info *sev; unsigned long va_start; u64 start, stop; /* Align start and stop to page boundaries. */ va_start = (unsigned long)va; start = (u64)va_start & PAGE_MASK; stop = PAGE_ALIGN((u64)va_start + len); if (start < stop) { sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; while (start < stop) { wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, start | sev->asid); start += PAGE_SIZE; } return; } WARN(1, "Address overflow, using WBINVD\n"); } /* * Hardware should always have one of the above features, * but if not, use WBINVD and issue a warning. */ WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); wbinvd_on_all_cpus(); } void sev_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; if (!sev_es_guest(vcpu->kvm)) return; svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE); __free_page(virt_to_page(svm->vmsa)); if (svm->ghcb_sa_free) kfree(svm->ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) { struct ghcb *ghcb = svm->ghcb; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ if (!dump_invalid_vmcb) { pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n"); return; } nbits = sizeof(ghcb->save.valid_bitmap) * 8; pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code", ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1", ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2", ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb)); pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch", ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb)); pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap); } static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; struct ghcb *ghcb = svm->ghcb; /* * The GHCB protocol so far allows for the following data * to be returned: * GPRs RAX, RBX, RCX, RDX * * Copy their values, even if they may not have been written during the * VM-Exit. It's the guest's responsibility to not consume random data. */ ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); } static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; struct ghcb *ghcb = svm->ghcb; u64 exit_code; /* * The GHCB protocol so far allows for the following data * to be supplied: * GPRs RAX, RBX, RCX, RDX * XCR0 * CPL * * VMMCALL allows the guest to provide extra registers. KVM also * expects RSI for hypercalls, so include that, too. * * Copy their values to the appropriate location if supplied. */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb); vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb); vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb); vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb); vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb); svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb); if (ghcb_xcr0_is_valid(ghcb)) { vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); kvm_update_cpuid_runtime(vcpu); } /* Copy the GHCB exit information into the VMCB fields */ exit_code = ghcb_get_sw_exit_code(ghcb); control->exit_code = lower_32_bits(exit_code); control->exit_code_hi = upper_32_bits(exit_code); control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); /* Clear the valid entries fields */ memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu; struct ghcb *ghcb; u64 exit_code = 0; ghcb = svm->ghcb; /* Only GHCB Usage code 0 is supported */ if (ghcb->ghcb_usage) goto vmgexit_err; /* * Retrieve the exit code now even though is may not be marked valid * as it could help with debugging. */ exit_code = ghcb_get_sw_exit_code(ghcb); if (!ghcb_sw_exit_code_is_valid(ghcb) || !ghcb_sw_exit_info_1_is_valid(ghcb) || !ghcb_sw_exit_info_2_is_valid(ghcb)) goto vmgexit_err; switch (ghcb_get_sw_exit_code(ghcb)) { case SVM_EXIT_READ_DR7: break; case SVM_EXIT_WRITE_DR7: if (!ghcb_rax_is_valid(ghcb)) goto vmgexit_err; break; case SVM_EXIT_RDTSC: break; case SVM_EXIT_RDPMC: if (!ghcb_rcx_is_valid(ghcb)) goto vmgexit_err; break; case SVM_EXIT_CPUID: if (!ghcb_rax_is_valid(ghcb) || !ghcb_rcx_is_valid(ghcb)) goto vmgexit_err; if (ghcb_get_rax(ghcb) == 0xd) if (!ghcb_xcr0_is_valid(ghcb)) goto vmgexit_err; break; case SVM_EXIT_INVD: break; case SVM_EXIT_IOIO: if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { if (!ghcb_sw_scratch_is_valid(ghcb)) goto vmgexit_err; } else { if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) if (!ghcb_rax_is_valid(ghcb)) goto vmgexit_err; } break; case SVM_EXIT_MSR: if (!ghcb_rcx_is_valid(ghcb)) goto vmgexit_err; if (ghcb_get_sw_exit_info_1(ghcb)) { if (!ghcb_rax_is_valid(ghcb) || !ghcb_rdx_is_valid(ghcb)) goto vmgexit_err; } break; case SVM_EXIT_VMMCALL: if (!ghcb_rax_is_valid(ghcb) || !ghcb_cpl_is_valid(ghcb)) goto vmgexit_err; break; case SVM_EXIT_RDTSCP: break; case SVM_EXIT_WBINVD: break; case SVM_EXIT_MONITOR: if (!ghcb_rax_is_valid(ghcb) || !ghcb_rcx_is_valid(ghcb) || !ghcb_rdx_is_valid(ghcb)) goto vmgexit_err; break; case SVM_EXIT_MWAIT: if (!ghcb_rax_is_valid(ghcb) || !ghcb_rcx_is_valid(ghcb)) goto vmgexit_err; break; case SVM_VMGEXIT_MMIO_READ: case SVM_VMGEXIT_MMIO_WRITE: if (!ghcb_sw_scratch_is_valid(ghcb)) 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: break; default: goto vmgexit_err; } return 0; vmgexit_err: vcpu = &svm->vcpu; if (ghcb->ghcb_usage) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); } else { vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n", exit_code); dump_ghcb(svm); } vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; vcpu->run->internal.ndata = 2; vcpu->run->internal.data[0] = exit_code; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; return -EINVAL; } static void pre_sev_es_run(struct vcpu_svm *svm) { if (!svm->ghcb) return; if (svm->ghcb_sa_free) { /* * The scratch area lives outside the GHCB, so there is a * buffer that, depending on the operation performed, may * need to be synced, then freed. */ if (svm->ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, ghcb_get_sw_scratch(svm->ghcb), svm->ghcb_sa, svm->ghcb_sa_len); svm->ghcb_sa_sync = false; } kfree(svm->ghcb_sa); svm->ghcb_sa = NULL; svm->ghcb_sa_free = false; } trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb); sev_es_sync_to_ghcb(svm); kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true); svm->ghcb = NULL; } void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); /* Perform any SEV-ES pre-run actions */ pre_sev_es_run(svm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; /* * Flush guest TLB: * * 1) when different VMCB for the same ASID is to be run on the same host CPU. * 2) or this VMCB was executed on different host CPU in previous VMRUNs. */ if (sd->sev_vmcbs[asid] == svm->vmcb && svm->vcpu.arch.last_vmentry_cpu == cpu) return; sd->sev_vmcbs[asid] = svm->vmcb; svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; vmcb_mark_dirty(svm->vmcb, VMCB_ASID); } #define GHCB_SCRATCH_AREA_LIMIT (16ULL * PAGE_SIZE) static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; struct ghcb *ghcb = svm->ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); return false; } scratch_gpa_end = scratch_gpa_beg + len; if (scratch_gpa_end < scratch_gpa_beg) { pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", len, scratch_gpa_beg); return false; } if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { /* Scratch area begins within GHCB */ ghcb_scratch_beg = control->ghcb_gpa + offsetof(struct ghcb, shared_buffer); ghcb_scratch_end = control->ghcb_gpa + offsetof(struct ghcb, reserved_1); /* * If the scratch area begins within the GHCB, it must be * completely contained in the GHCB shared buffer area. */ if (scratch_gpa_beg < ghcb_scratch_beg || scratch_gpa_end > ghcb_scratch_end) { pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", scratch_gpa_beg, scratch_gpa_end); return false; } scratch_va = (void *)svm->ghcb; scratch_va += (scratch_gpa_beg - control->ghcb_gpa); } else { /* * The guest memory must be read into a kernel buffer, so * limit the size */ if (len > GHCB_SCRATCH_AREA_LIMIT) { pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", len, GHCB_SCRATCH_AREA_LIMIT); return false; } scratch_va = kzalloc(len, GFP_KERNEL); if (!scratch_va) return false; if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { /* Unable to copy scratch area from guest */ pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); kfree(scratch_va); return false; } /* * The scratch area is outside the GHCB. The operation will * dictate whether the buffer needs to be synced before running * the vCPU next time (i.e. a read was requested so the data * must be written back to the guest memory). */ svm->ghcb_sa_sync = sync; svm->ghcb_sa_free = true; } svm->ghcb_sa = scratch_va; svm->ghcb_sa_len = len; return true; } static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, unsigned int pos) { svm->vmcb->control.ghcb_gpa &= ~(mask << pos); svm->vmcb->control.ghcb_gpa |= (value & mask) << pos; } static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos) { return (svm->vmcb->control.ghcb_gpa >> pos) & mask; } static void set_ghcb_msr(struct vcpu_svm *svm, u64 value) { svm->vmcb->control.ghcb_gpa = value; } static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; u64 ghcb_info; int ret = 1; ghcb_info = control->ghcb_gpa & GHCB_MSR_INFO_MASK; trace_kvm_vmgexit_msr_protocol_enter(svm->vcpu.vcpu_id, control->ghcb_gpa); switch (ghcb_info) { case GHCB_MSR_SEV_INFO_REQ: set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, GHCB_VERSION_MIN, sev_enc_bit)); break; case GHCB_MSR_CPUID_REQ: { u64 cpuid_fn, cpuid_reg, cpuid_value; cpuid_fn = get_ghcb_msr_bits(svm, GHCB_MSR_CPUID_FUNC_MASK, GHCB_MSR_CPUID_FUNC_POS); /* Initialize the registers needed by the CPUID intercept */ vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn; vcpu->arch.regs[VCPU_REGS_RCX] = 0; ret = svm_invoke_exit_handler(svm, SVM_EXIT_CPUID); if (!ret) { ret = -EINVAL; break; } cpuid_reg = get_ghcb_msr_bits(svm, GHCB_MSR_CPUID_REG_MASK, GHCB_MSR_CPUID_REG_POS); if (cpuid_reg == 0) cpuid_value = vcpu->arch.regs[VCPU_REGS_RAX]; else if (cpuid_reg == 1) cpuid_value = vcpu->arch.regs[VCPU_REGS_RBX]; else if (cpuid_reg == 2) cpuid_value = vcpu->arch.regs[VCPU_REGS_RCX]; else cpuid_value = vcpu->arch.regs[VCPU_REGS_RDX]; set_ghcb_msr_bits(svm, cpuid_value, GHCB_MSR_CPUID_VALUE_MASK, GHCB_MSR_CPUID_VALUE_POS); set_ghcb_msr_bits(svm, GHCB_MSR_CPUID_RESP, GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS); break; } case GHCB_MSR_TERM_REQ: { u64 reason_set, reason_code; reason_set = get_ghcb_msr_bits(svm, GHCB_MSR_TERM_REASON_SET_MASK, GHCB_MSR_TERM_REASON_SET_POS); reason_code = get_ghcb_msr_bits(svm, GHCB_MSR_TERM_REASON_MASK, GHCB_MSR_TERM_REASON_POS); pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); fallthrough; } default: ret = -EINVAL; } trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, control->ghcb_gpa, ret); return ret; } int sev_handle_vmgexit(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; u64 ghcb_gpa, exit_code; struct ghcb *ghcb; int ret; /* Validate the GHCB */ ghcb_gpa = control->ghcb_gpa; if (ghcb_gpa & GHCB_MSR_INFO_MASK) return sev_handle_vmgexit_msr_protocol(svm); if (!ghcb_gpa) { vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB gpa is not set\n"); return -EINVAL; } if (kvm_vcpu_map(&svm->vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(&svm->vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); return -EINVAL; } svm->ghcb = svm->ghcb_map.hva; ghcb = svm->ghcb_map.hva; trace_kvm_vmgexit_enter(svm->vcpu.vcpu_id, ghcb); exit_code = ghcb_get_sw_exit_code(ghcb); ret = sev_es_validate_vmgexit(svm); if (ret) return ret; sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); ret = -EINVAL; switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) break; ret = kvm_sev_es_mmio_read(&svm->vcpu, control->exit_info_1, control->exit_info_2, svm->ghcb_sa); break; case SVM_VMGEXIT_MMIO_WRITE: if (!setup_vmgexit_scratch(svm, false, control->exit_info_2)) break; ret = kvm_sev_es_mmio_write(&svm->vcpu, control->exit_info_1, control->exit_info_2, svm->ghcb_sa); break; case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); break; case SVM_VMGEXIT_AP_HLT_LOOP: ret = kvm_emulate_ap_reset_hold(&svm->vcpu); break; case SVM_VMGEXIT_AP_JUMP_TABLE: { struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; switch (control->exit_info_1) { case 0: /* Set AP jump table address */ sev->ap_jump_table = control->exit_info_2; break; case 1: /* Get AP jump table address */ ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table); break; default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); ghcb_set_sw_exit_info_1(ghcb, 1); ghcb_set_sw_exit_info_2(ghcb, X86_TRAP_UD | SVM_EVTINJ_TYPE_EXEPT | SVM_EVTINJ_VALID); } ret = 1; break; } case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(&svm->vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", control->exit_info_1, control->exit_info_2); break; default: ret = svm_invoke_exit_handler(svm, exit_code); } return ret; } int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) { if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2)) return -EINVAL; return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, svm->ghcb_sa_len, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; /* * An SEV-ES guest requires a VMSA area that is a separate from the * VMCB page. Do not include the encryption mask on the VMSA physical * address since hardware will access it using the guest key. */ svm->vmcb->control.vmsa_pa = __pa(svm->vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); svm_clr_intercept(svm, INTERCEPT_CR4_READ); svm_clr_intercept(svm, INTERCEPT_CR8_READ); svm_clr_intercept(svm, INTERCEPT_CR0_WRITE); svm_clr_intercept(svm, INTERCEPT_CR4_WRITE); svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); svm_clr_intercept(svm, INTERCEPT_SELECTIVE_CR0); /* Track EFER/CR register changes */ svm_set_intercept(svm, TRAP_EFER_WRITE); svm_set_intercept(svm, TRAP_CR0_WRITE); svm_set_intercept(svm, TRAP_CR4_WRITE); svm_set_intercept(svm, TRAP_CR8_WRITE); /* No support for enable_vmware_backdoor */ clr_exception_intercept(svm, GP_VECTOR); /* Can't intercept XSETBV, HV can't modify XCR0 directly */ svm_clr_intercept(svm, INTERCEPT_XSETBV); /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } void sev_es_create_vcpu(struct vcpu_svm *svm) { /* * Set the GHCB MSR value as per the GHCB specification when creating * a vCPU for an SEV-ES guest. */ set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, GHCB_VERSION_MIN, sev_enc_bit)); } void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu) { struct svm_cpu_data *sd = per_cpu(svm_data, cpu); struct vmcb_save_area *hostsa; /* * As an SEV-ES guest, hardware will restore the host state on VMEXIT, * of which one step is to perform a VMLOAD. Since hardware does not * perform a VMSAVE on VMRUN, the host savearea must be updated. */ vmsave(__sme_page_pa(sd->save_area)); /* XCR0 is restored on VMEXIT, save the current host value */ hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); /* PKRU is restored on VMEXIT, save the current host value */ hostsa->pkru = read_pkru(); /* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */ hostsa->xss = host_xss; } void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { struct vcpu_svm *svm = to_svm(vcpu); /* First SIPI: Use the values as initially set by the VMM */ if (!svm->received_first_sipi) { svm->received_first_sipi = true; 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. */ ghcb_set_sw_exit_info_2(svm->ghcb, 1); }