#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#include <linux/kernel.h>
#include <linux/highmem.h>
#include <linux/psp.h>
#include <linux/psp-sev.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/misc_cgroup.h>
#include <linux/processor.h>
#include <linux/trace_events.h>
#include <uapi/linux/sev-guest.h>
#include <asm/pkru.h>
#include <asm/trapnr.h>
#include <asm/fpu/xcr.h>
#include <asm/fpu/xstate.h>
#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/sev.h>
#include "mmu.h"
#include "x86.h"
#include "svm.h"
#include "svm_ops.h"
#include "cpuid.h"
#include "trace.h"
#define GHCB_VERSION_MAX 2ULL
#define GHCB_VERSION_MIN 1ULL
#define GHCB_HV_FT_SUPPORTED (GHCB_HV_FT_SNP | GHCB_HV_FT_SNP_AP_CREATION)
static bool sev_enabled = true;
module_param_named(sev, sev_enabled, bool, 0444);
static bool sev_es_enabled = true;
module_param_named(sev_es, sev_es_enabled, bool, 0444);
static bool sev_snp_enabled = true;
module_param_named(sev_snp, sev_snp_enabled, bool, 0444);
static bool sev_es_debug_swap_enabled = true;
module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
static u64 sev_supported_vmsa_features;
static unsigned int nr_ciphertext_hiding_asids;
module_param_named(ciphertext_hiding_asids, nr_ciphertext_hiding_asids, uint, 0444);
#define AP_RESET_HOLD_NONE 0
#define AP_RESET_HOLD_NAE_EVENT 1
#define AP_RESET_HOLD_MSR_PROTO 2
#define SNP_POLICY_MASK_API_MINOR GENMASK_ULL(7, 0)
#define SNP_POLICY_MASK_API_MAJOR GENMASK_ULL(15, 8)
#define SNP_POLICY_MASK_SMT BIT_ULL(16)
#define SNP_POLICY_MASK_RSVD_MBO BIT_ULL(17)
#define SNP_POLICY_MASK_DEBUG BIT_ULL(19)
#define SNP_POLICY_MASK_SINGLE_SOCKET BIT_ULL(20)
#define SNP_POLICY_MASK_VALID (SNP_POLICY_MASK_API_MINOR | \
SNP_POLICY_MASK_API_MAJOR | \
SNP_POLICY_MASK_SMT | \
SNP_POLICY_MASK_RSVD_MBO | \
SNP_POLICY_MASK_DEBUG | \
SNP_POLICY_MASK_SINGLE_SOCKET)
#define INITIAL_VMSA_GPA 0xFFFFFFFFF000
static u8 sev_enc_bit;
static DECLARE_RWSEM(sev_deactivate_lock);
static DEFINE_MUTEX(sev_bitmap_lock);
unsigned int max_sev_asid;
static unsigned int min_sev_asid;
static unsigned int max_sev_es_asid;
static unsigned int min_sev_es_asid;
static unsigned int max_snp_asid;
static unsigned int min_snp_asid;
static unsigned long sev_me_mask;
static unsigned int nr_asids;
static unsigned long *sev_asid_bitmap;
static unsigned long *sev_reclaim_asid_bitmap;
static int snp_decommission_context(struct kvm *kvm);
struct enc_region {
struct list_head list;
unsigned long npages;
struct page **pages;
unsigned long uaddr;
unsigned long size;
};
static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
{
int ret, error = 0;
unsigned int asid;
asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
if (asid > max_asid)
return -EBUSY;
down_write(&sev_deactivate_lock);
wbinvd_on_all_cpus();
if (sev_snp_enabled)
ret = sev_do_cmd(SEV_CMD_SNP_DF_FLUSH, NULL, &error);
else
ret = sev_guest_df_flush(&error);
up_write(&sev_deactivate_lock);
if (ret)
pr_err("SEV%s: DF_FLUSH failed, ret=%d, error=%#x\n",
sev_snp_enabled ? "-SNP" : "", ret, error);
return ret;
}
static inline bool is_mirroring_enc_context(struct kvm *kvm)
{
return !!to_kvm_sev_info(kvm)->enc_context_owner;
}
static bool sev_vcpu_has_debug_swap(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
return sev->vmsa_features & SVM_SEV_FEAT_DEBUG_SWAP;
}
static bool snp_is_secure_tsc_enabled(struct kvm *kvm)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
return (sev->vmsa_features & SVM_SEV_FEAT_SECURE_TSC) &&
!WARN_ON_ONCE(!sev_snp_guest(kvm));
}
static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid)
{
if (sev_flush_asids(min_asid, max_asid))
return false;
bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
nr_asids);
bitmap_zero(sev_reclaim_asid_bitmap, nr_asids);
return true;
}
static int sev_misc_cg_try_charge(struct kvm_sev_info *sev)
{
enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
return misc_cg_try_charge(type, sev->misc_cg, 1);
}
static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
{
enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
misc_cg_uncharge(type, sev->misc_cg, 1);
}
static int sev_asid_new(struct kvm_sev_info *sev, unsigned long vm_type)
{
unsigned int min_asid, max_asid, asid;
bool retry = true;
int ret;
if (vm_type == KVM_X86_SNP_VM) {
min_asid = min_snp_asid;
max_asid = max_snp_asid;
} else if (sev->es_active) {
min_asid = min_sev_es_asid;
max_asid = max_sev_es_asid;
} else {
min_asid = min_sev_asid;
max_asid = max_sev_asid;
}
if (min_asid > max_asid)
return -ENOTTY;
WARN_ON(sev->misc_cg);
sev->misc_cg = get_current_misc_cg();
ret = sev_misc_cg_try_charge(sev);
if (ret) {
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
return ret;
}
mutex_lock(&sev_bitmap_lock);
again:
asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
if (asid > 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(asid, sev_asid_bitmap);
mutex_unlock(&sev_bitmap_lock);
sev->asid = asid;
return 0;
e_uncharge:
sev_misc_cg_uncharge(sev);
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
return ret;
}
static unsigned int sev_get_asid(struct kvm *kvm)
{
return to_kvm_sev_info(kvm)->asid;
}
static void sev_asid_free(struct kvm_sev_info *sev)
{
struct svm_cpu_data *sd;
int cpu;
mutex_lock(&sev_bitmap_lock);
__set_bit(sev->asid, sev_reclaim_asid_bitmap);
for_each_possible_cpu(cpu) {
sd = per_cpu_ptr(&svm_data, cpu);
sd->sev_vmcbs[sev->asid] = NULL;
}
mutex_unlock(&sev_bitmap_lock);
sev_misc_cg_uncharge(sev);
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
}
static void sev_decommission(unsigned int handle)
{
struct sev_data_decommission decommission;
if (!handle)
return;
decommission.handle = handle;
sev_guest_decommission(&decommission, NULL);
}
static int kvm_rmp_make_shared(struct kvm *kvm, u64 pfn, enum pg_level level)
{
if (KVM_BUG_ON(rmp_make_shared(pfn, level), kvm)) {
snp_leak_pages(pfn, page_level_size(level) >> PAGE_SHIFT);
return -EIO;
}
return 0;
}
static int snp_page_reclaim(struct kvm *kvm, u64 pfn)
{
struct sev_data_snp_page_reclaim data = {0};
int fw_err, rc;
data.paddr = __sme_set(pfn << PAGE_SHIFT);
rc = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &fw_err);
if (KVM_BUG(rc, kvm, "Failed to reclaim PFN %llx, rc %d fw_err %d", pfn, rc, fw_err)) {
snp_leak_pages(pfn, 1);
return -EIO;
}
if (kvm_rmp_make_shared(kvm, pfn, PG_LEVEL_4K))
return -EIO;
return rc;
}
static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
{
struct sev_data_deactivate deactivate;
if (!handle)
return;
deactivate.handle = handle;
down_read(&sev_deactivate_lock);
sev_guest_deactivate(&deactivate, NULL);
up_read(&sev_deactivate_lock);
sev_decommission(handle);
}
static int snp_guest_req_init(struct kvm *kvm)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct page *req_page;
req_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!req_page)
return -ENOMEM;
sev->guest_resp_buf = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!sev->guest_resp_buf) {
__free_page(req_page);
return -EIO;
}
sev->guest_req_buf = page_address(req_page);
mutex_init(&sev->guest_req_mutex);
return 0;
}
static void snp_guest_req_cleanup(struct kvm *kvm)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
if (sev->guest_resp_buf)
snp_free_firmware_page(sev->guest_resp_buf);
if (sev->guest_req_buf)
__free_page(virt_to_page(sev->guest_req_buf));
sev->guest_req_buf = NULL;
sev->guest_resp_buf = NULL;
}
static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
struct kvm_sev_init *data,
unsigned long vm_type)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_platform_init_args init_args = {0};
bool es_active = vm_type != KVM_X86_SEV_VM;
bool snp_active = vm_type == KVM_X86_SNP_VM;
u64 valid_vmsa_features = es_active ? sev_supported_vmsa_features : 0;
int ret;
if (kvm->created_vcpus)
return -EINVAL;
if (data->flags)
return -EINVAL;
if (!snp_active)
valid_vmsa_features &= ~SVM_SEV_FEAT_SECURE_TSC;
if (data->vmsa_features & ~valid_vmsa_features)
return -EINVAL;
if (data->ghcb_version > GHCB_VERSION_MAX || (!es_active && data->ghcb_version))
return -EINVAL;
if (es_active && !data->ghcb_version)
data->ghcb_version = 2;
if (snp_active && data->ghcb_version < 2)
return -EINVAL;
if (unlikely(sev->active))
return -EINVAL;
sev->active = true;
sev->es_active = es_active;
sev->vmsa_features = data->vmsa_features;
sev->ghcb_version = data->ghcb_version;
if (snp_active)
sev->vmsa_features |= SVM_SEV_FEAT_SNP_ACTIVE;
ret = sev_asid_new(sev, vm_type);
if (ret)
goto e_no_asid;
init_args.probe = false;
ret = sev_platform_init(&init_args);
if (ret)
goto e_free_asid;
if (!zalloc_cpumask_var(&sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
ret = -ENOMEM;
goto e_free_asid;
}
if (snp_active) {
ret = snp_guest_req_init(kvm);
if (ret)
goto e_free;
}
INIT_LIST_HEAD(&sev->regions_list);
INIT_LIST_HEAD(&sev->mirror_vms);
sev->need_init = false;
kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV);
return 0;
e_free:
free_cpumask_var(sev->have_run_cpus);
e_free_asid:
argp->error = init_args.error;
sev_asid_free(sev);
sev->asid = 0;
e_no_asid:
sev->vmsa_features = 0;
sev->es_active = false;
sev->active = false;
return ret;
}
static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_init data = {
.vmsa_features = 0,
.ghcb_version = 0,
};
unsigned long vm_type;
if (kvm->arch.vm_type != KVM_X86_DEFAULT_VM)
return -EINVAL;
vm_type = (argp->id == KVM_SEV_INIT ? KVM_X86_SEV_VM : KVM_X86_SEV_ES_VM);
if (vm_type == KVM_X86_SEV_ES_VM)
data.ghcb_version = GHCB_VERSION_MIN;
return __sev_guest_init(kvm, argp, &data, vm_type);
}
static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_init data;
if (!to_kvm_sev_info(kvm)->need_init)
return -EINVAL;
if (kvm->arch.vm_type != KVM_X86_SEV_VM &&
kvm->arch.vm_type != KVM_X86_SEV_ES_VM &&
kvm->arch.vm_type != KVM_X86_SNP_VM)
return -EINVAL;
if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data)))
return -EFAULT;
return __sev_guest_init(kvm, argp, &data, kvm->arch.vm_type);
}
static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
{
unsigned int asid = sev_get_asid(kvm);
struct sev_data_activate activate;
int ret;
activate.handle = handle;
activate.asid = asid;
ret = sev_guest_activate(&activate, error);
return ret;
}
static int __sev_issue_cmd(int fd, int id, void *data, int *error)
{
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
return sev_issue_cmd_external_user(fd_file(f), id, data, error);
}
static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
return __sev_issue_cmd(sev->fd, id, data, error);
}
static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
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, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
memset(&start, 0, sizeof(start));
dh_blob = NULL;
if (params.dh_uaddr) {
dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len);
if (IS_ERR(dh_blob))
return PTR_ERR(dh_blob);
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;
ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, &start, error);
if (ret)
goto e_free_session;
ret = sev_bind_asid(kvm, start.handle, error);
if (ret) {
sev_decommission(start.handle);
goto e_free_session;
}
params.handle = start.handle;
if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) {
sev_unbind_asid(kvm, start.handle);
ret = -EFAULT;
goto e_free_session;
}
sev->policy = params.policy;
sev->handle = start.handle;
sev->fd = argp->sev_fd;
e_free_session:
kfree(session_blob);
e_free_dh:
kfree(dh_blob);
return ret;
}
static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
unsigned long ulen, unsigned long *n,
unsigned int flags)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
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);
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);
size = npages * sizeof(struct page *);
if (size > PAGE_SIZE)
pages = __vmalloc(size, GFP_KERNEL_ACCOUNT);
else
pages = kmalloc(size, GFP_KERNEL_ACCOUNT);
if (!pages)
return ERR_PTR(-ENOMEM);
npinned = pin_user_pages_fast(uaddr, npages, flags, 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)
{
unpin_user_pages(pages, npages);
kvfree(pages);
to_kvm_sev_info(kvm)->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_local_page(pages[i]);
clflush_cache_range(page_virtual, PAGE_SIZE);
kunmap_local(page_virtual);
cond_resched();
}
}
static void sev_writeback_caches(struct kvm *kvm)
{
wbnoinvd_on_cpus_mask(to_kvm_sev_info(kvm)->have_run_cpus);
}
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;
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_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, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
vaddr = params.uaddr;
size = params.len;
vaddr_end = vaddr + size;
inpages = sev_pin_memory(kvm, vaddr, size, &npages, FOLL_WRITE);
if (IS_ERR(inpages))
return PTR_ERR(inpages);
sev_clflush_pages(inpages, npages);
data.reserved = 0;
data.handle = to_kvm_sev_info(kvm)->handle;
for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) {
int offset, len;
offset = vaddr & (PAGE_SIZE - 1);
pages = get_num_contig_pages(i, inpages, npages);
len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size);
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:
for (i = 0; i < npages; i++) {
set_page_dirty_lock(inpages[i]);
mark_page_accessed(inpages[i]);
}
sev_unpin_memory(kvm, inpages, npages);
return ret;
}
static int sev_es_sync_vmsa(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
struct sev_es_save_area *save = svm->sev_es.vmsa;
struct xregs_state *xsave;
const u8 *s;
u8 *d;
int i;
if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1))
return -EINVAL;
memcpy(save, &svm->vmcb->save, sizeof(svm->vmcb->save));
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];
save->xcr0 = svm->vcpu.arch.xcr0;
save->pkru = svm->vcpu.arch.pkru;
save->xss = svm->vcpu.arch.ia32_xss;
save->dr6 = svm->vcpu.arch.dr6;
save->sev_features = sev->vmsa_features;
if (vcpu->kvm->arch.vm_type != KVM_X86_DEFAULT_VM) {
xsave = &vcpu->arch.guest_fpu.fpstate->regs.xsave;
save->x87_dp = xsave->i387.rdp;
save->mxcsr = xsave->i387.mxcsr;
save->x87_ftw = xsave->i387.twd;
save->x87_fsw = xsave->i387.swd;
save->x87_fcw = xsave->i387.cwd;
save->x87_fop = xsave->i387.fop;
save->x87_ds = 0;
save->x87_cs = 0;
save->x87_rip = xsave->i387.rip;
for (i = 0; i < 8; i++) {
d = save->fpreg_x87 + i * 8;
s = ((u8 *)xsave->i387.st_space) + i * 16;
memcpy(d, s, 8);
save->fpreg_x87[64 + i * 2] = s[8];
save->fpreg_x87[64 + i * 2 + 1] = s[9];
}
memcpy(save->fpreg_xmm, xsave->i387.xmm_space, 256);
s = get_xsave_addr(xsave, XFEATURE_YMM);
if (s)
memcpy(save->fpreg_ymm, s, 256);
else
memset(save->fpreg_ymm, 0, 256);
}
pr_debug("Virtual Machine Save Area (VMSA):\n");
print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
return 0;
}
static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
int *error)
{
struct sev_data_launch_update_vmsa vmsa;
struct vcpu_svm *svm = to_svm(vcpu);
int ret;
if (vcpu->guest_debug) {
pr_warn_once("KVM_SET_GUEST_DEBUG for SEV-ES guest is not supported");
return -EINVAL;
}
ret = sev_es_sync_vmsa(svm);
if (ret)
return ret;
clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE);
vmsa.reserved = 0;
vmsa.handle = to_kvm_sev_info(kvm)->handle;
vmsa.address = __sme_pa(svm->sev_es.vmsa);
vmsa.len = PAGE_SIZE;
ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
if (ret)
return ret;
fpstate_set_confidential(&vcpu->arch.guest_fpu);
vcpu->arch.guest_state_protected = true;
svm_enable_lbrv(vcpu);
return 0;
}
static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_vcpu *vcpu;
unsigned long i;
int ret;
if (!sev_es_guest(kvm))
return -ENOTTY;
kvm_for_each_vcpu(i, vcpu, kvm) {
ret = mutex_lock_killable(&vcpu->mutex);
if (ret)
return ret;
ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error);
mutex_unlock(&vcpu->mutex);
if (ret)
return ret;
}
return 0;
}
static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
void __user *measure = u64_to_user_ptr(argp->data);
struct sev_data_launch_measure data;
struct kvm_sev_launch_measure params;
void __user *p = NULL;
void *blob = NULL;
int ret;
if (!sev_guest(kvm))
return -ENOTTY;
if (copy_from_user(¶ms, measure, sizeof(params)))
return -EFAULT;
memset(&data, 0, sizeof(data));
if (!params.len)
goto cmd;
p = u64_to_user_ptr(params.uaddr);
if (p) {
if (params.len > SEV_FW_BLOB_MAX_SIZE)
return -EINVAL;
blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT);
if (!blob)
return -ENOMEM;
data.address = __psp_pa(blob);
data.len = params.len;
}
cmd:
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, &data, &argp->error);
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);
return ret;
}
static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_launch_finish data;
if (!sev_guest(kvm))
return -ENOTTY;
data.handle = to_kvm_sev_info(kvm)->handle;
return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, &data, &argp->error);
}
static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_guest_status params;
struct sev_data_guest_status data;
int ret;
if (!sev_guest(kvm))
return -ENOTTY;
memset(&data, 0, sizeof(data));
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, &data, &argp->error);
if (ret)
return ret;
params.policy = data.policy;
params.state = data.state;
params.handle = data.handle;
if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params)))
ret = -EFAULT;
return ret;
}
static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src,
unsigned long dst, int size,
int *error, bool enc)
{
struct sev_data_dbg data;
data.reserved = 0;
data.handle = to_kvm_sev_info(kvm)->handle;
data.dst_addr = dst;
data.src_addr = src;
data.len = size;
return sev_issue_cmd(kvm,
enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT,
&data, error);
}
static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
unsigned long dst_paddr, int sz, int *err)
{
int offset;
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,
void __user *dst_uaddr,
unsigned long dst_paddr,
int size, int *err)
{
struct page *tpage = NULL;
int ret, offset;
if (!IS_ALIGNED(dst_paddr, 16) ||
!IS_ALIGNED(paddr, 16) ||
!IS_ALIGNED(size, 16)) {
tpage = (void *)alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
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(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,
void __user *vaddr,
unsigned long dst_paddr,
void __user *dst_vaddr,
int size, int *error)
{
struct page *src_tpage = NULL;
struct page *dst_tpage = NULL;
int ret, len = size;
if (!IS_ALIGNED((unsigned long)vaddr, 16)) {
src_tpage = alloc_page(GFP_KERNEL_ACCOUNT);
if (!src_tpage)
return -ENOMEM;
if (copy_from_user(page_address(src_tpage), vaddr, size)) {
__free_page(src_tpage);
return -EFAULT;
}
paddr = __sme_page_pa(src_tpage);
}
if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) {
int dst_offset;
dst_tpage = alloc_page(GFP_KERNEL_ACCOUNT);
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;
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,
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, u64_to_user_ptr(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;
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, FOLL_WRITE);
if (IS_ERR(dst_p)) {
sev_unpin_memory(kvm, src_p, n);
return PTR_ERR(dst_p);
}
sev_clflush_pages(src_p, 1);
sev_clflush_pages(dst_p, 1);
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,
(void __user *)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,
(void __user *)vaddr,
__sme_page_pa(dst_p[0]) + d_off,
(void __user *)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 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, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, FOLL_WRITE);
if (IS_ERR(pages))
return PTR_ERR(pages);
sev_clflush_pages(pages, n);
if (get_num_contig_pages(0, pages, n) != n) {
ret = -EINVAL;
goto e_unpin_memory;
}
memset(&data, 0, sizeof(data));
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_unpin_memory;
}
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 = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, &data, &argp->error);
kfree(hdr);
e_free_blob:
kfree(blob);
e_unpin_memory:
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 = u64_to_user_ptr(argp->data);
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, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
memset(&data, 0, sizeof(data));
if (!params.len)
goto cmd;
p = u64_to_user_ptr(params.uaddr);
if (p) {
if (params.len > SEV_FW_BLOB_MAX_SIZE)
return -EINVAL;
blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT);
if (!blob)
return -ENOMEM;
data.address = __psp_pa(blob);
data.len = params.len;
memcpy(data.mnonce, params.mnonce, sizeof(params.mnonce));
}
cmd:
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, &data, &argp->error);
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);
return ret;
}
static int
__sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp,
struct kvm_sev_send_start *params)
{
struct sev_data_send_start data;
int ret;
memset(&data, 0, sizeof(data));
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);
params->session_len = data.session_len;
if (copy_to_user(u64_to_user_ptr(argp->data), params,
sizeof(struct kvm_sev_send_start)))
ret = -EFAULT;
return ret;
}
static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_send_start data;
struct kvm_sev_send_start params;
void *amd_certs, *session_data;
void *pdh_cert, *plat_certs;
int ret;
if (!sev_guest(kvm))
return -ENOTTY;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_send_start)))
return -EFAULT;
if (!params.session_len)
return __sev_send_start_query_session_length(kvm, argp,
¶ms);
if (!params.pdh_cert_uaddr || !params.pdh_cert_len ||
!params.session_uaddr || params.session_len > SEV_FW_BLOB_MAX_SIZE)
return -EINVAL;
session_data = kzalloc(params.session_len, GFP_KERNEL_ACCOUNT);
if (!session_data)
return -ENOMEM;
pdh_cert = psp_copy_user_blob(params.pdh_cert_uaddr,
params.pdh_cert_len);
if (IS_ERR(pdh_cert)) {
ret = PTR_ERR(pdh_cert);
goto e_free_session;
}
plat_certs = psp_copy_user_blob(params.plat_certs_uaddr,
params.plat_certs_len);
if (IS_ERR(plat_certs)) {
ret = PTR_ERR(plat_certs);
goto e_free_pdh;
}
amd_certs = psp_copy_user_blob(params.amd_certs_uaddr,
params.amd_certs_len);
if (IS_ERR(amd_certs)) {
ret = PTR_ERR(amd_certs);
goto e_free_plat_cert;
}
memset(&data, 0, sizeof(data));
data.pdh_cert_address = __psp_pa(pdh_cert);
data.pdh_cert_len = params.pdh_cert_len;
data.plat_certs_address = __psp_pa(plat_certs);
data.plat_certs_len = params.plat_certs_len;
data.amd_certs_address = __psp_pa(amd_certs);
data.amd_certs_len = params.amd_certs_len;
data.session_address = __psp_pa(session_data);
data.session_len = params.session_len;
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);
if (!ret && copy_to_user(u64_to_user_ptr(params.session_uaddr),
session_data, params.session_len)) {
ret = -EFAULT;
goto e_free_amd_cert;
}
params.policy = data.policy;
params.session_len = data.session_len;
if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms,
sizeof(struct kvm_sev_send_start)))
ret = -EFAULT;
e_free_amd_cert:
kfree(amd_certs);
e_free_plat_cert:
kfree(plat_certs);
e_free_pdh:
kfree(pdh_cert);
e_free_session:
kfree(session_data);
return ret;
}
static int
__sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp,
struct kvm_sev_send_update_data *params)
{
struct sev_data_send_update_data data;
int ret;
memset(&data, 0, sizeof(data));
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error);
params->hdr_len = data.hdr_len;
params->trans_len = data.trans_len;
if (copy_to_user(u64_to_user_ptr(argp->data), params,
sizeof(struct kvm_sev_send_update_data)))
ret = -EFAULT;
return ret;
}
static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_send_update_data data;
struct kvm_sev_send_update_data params;
void *hdr, *trans_data;
struct page **guest_page;
unsigned long n;
int ret, offset;
if (!sev_guest(kvm))
return -ENOTTY;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_send_update_data)))
return -EFAULT;
if (!params.trans_len || !params.hdr_len)
return __sev_send_update_data_query_lengths(kvm, argp, ¶ms);
if (!params.trans_uaddr || !params.guest_uaddr ||
!params.guest_len || !params.hdr_uaddr)
return -EINVAL;
offset = params.guest_uaddr & (PAGE_SIZE - 1);
if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE)
return -EINVAL;
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
if (IS_ERR(guest_page))
return PTR_ERR(guest_page);
ret = -ENOMEM;
hdr = kzalloc(params.hdr_len, GFP_KERNEL);
if (!hdr)
goto e_unpin;
trans_data = kzalloc(params.trans_len, GFP_KERNEL);
if (!trans_data)
goto e_free_hdr;
memset(&data, 0, sizeof(data));
data.hdr_address = __psp_pa(hdr);
data.hdr_len = params.hdr_len;
data.trans_address = __psp_pa(trans_data);
data.trans_len = params.trans_len;
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
data.guest_address |= sev_me_mask;
data.guest_len = params.guest_len;
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error);
if (ret)
goto e_free_trans_data;
if (copy_to_user(u64_to_user_ptr(params.trans_uaddr),
trans_data, params.trans_len)) {
ret = -EFAULT;
goto e_free_trans_data;
}
if (copy_to_user(u64_to_user_ptr(params.hdr_uaddr), hdr,
params.hdr_len))
ret = -EFAULT;
e_free_trans_data:
kfree(trans_data);
e_free_hdr:
kfree(hdr);
e_unpin:
sev_unpin_memory(kvm, guest_page, n);
return ret;
}
static int sev_send_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_send_finish data;
if (!sev_guest(kvm))
return -ENOTTY;
data.handle = to_kvm_sev_info(kvm)->handle;
return sev_issue_cmd(kvm, SEV_CMD_SEND_FINISH, &data, &argp->error);
}
static int sev_send_cancel(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_send_cancel data;
if (!sev_guest(kvm))
return -ENOTTY;
data.handle = to_kvm_sev_info(kvm)->handle;
return sev_issue_cmd(kvm, SEV_CMD_SEND_CANCEL, &data, &argp->error);
}
static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_data_receive_start start;
struct kvm_sev_receive_start params;
int *error = &argp->error;
void *session_data;
void *pdh_data;
int ret;
if (!sev_guest(kvm))
return -ENOTTY;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_receive_start)))
return -EFAULT;
if (!params.pdh_uaddr || !params.pdh_len ||
!params.session_uaddr || !params.session_len)
return -EINVAL;
pdh_data = psp_copy_user_blob(params.pdh_uaddr, params.pdh_len);
if (IS_ERR(pdh_data))
return PTR_ERR(pdh_data);
session_data = psp_copy_user_blob(params.session_uaddr,
params.session_len);
if (IS_ERR(session_data)) {
ret = PTR_ERR(session_data);
goto e_free_pdh;
}
memset(&start, 0, sizeof(start));
start.handle = params.handle;
start.policy = params.policy;
start.pdh_cert_address = __psp_pa(pdh_data);
start.pdh_cert_len = params.pdh_len;
start.session_address = __psp_pa(session_data);
start.session_len = params.session_len;
ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_RECEIVE_START, &start,
error);
if (ret)
goto e_free_session;
ret = sev_bind_asid(kvm, start.handle, error);
if (ret) {
sev_decommission(start.handle);
goto e_free_session;
}
params.handle = start.handle;
if (copy_to_user(u64_to_user_ptr(argp->data),
¶ms, sizeof(struct kvm_sev_receive_start))) {
ret = -EFAULT;
sev_unbind_asid(kvm, start.handle);
goto e_free_session;
}
sev->handle = start.handle;
sev->fd = argp->sev_fd;
e_free_session:
kfree(session_data);
e_free_pdh:
kfree(pdh_data);
return ret;
}
static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_receive_update_data params;
struct sev_data_receive_update_data data;
void *hdr = NULL, *trans = NULL;
struct page **guest_page;
unsigned long n;
int ret, offset;
if (!sev_guest(kvm))
return -EINVAL;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_receive_update_data)))
return -EFAULT;
if (!params.hdr_uaddr || !params.hdr_len ||
!params.guest_uaddr || !params.guest_len ||
!params.trans_uaddr || !params.trans_len)
return -EINVAL;
offset = params.guest_uaddr & (PAGE_SIZE - 1);
if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE)
return -EINVAL;
hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len);
if (IS_ERR(hdr))
return PTR_ERR(hdr);
trans = psp_copy_user_blob(params.trans_uaddr, params.trans_len);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto e_free_hdr;
}
memset(&data, 0, sizeof(data));
data.hdr_address = __psp_pa(hdr);
data.hdr_len = params.hdr_len;
data.trans_address = __psp_pa(trans);
data.trans_len = params.trans_len;
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, FOLL_WRITE);
if (IS_ERR(guest_page)) {
ret = PTR_ERR(guest_page);
goto e_free_trans;
}
sev_clflush_pages(guest_page, n);
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
data.guest_address |= sev_me_mask;
data.guest_len = params.guest_len;
data.handle = to_kvm_sev_info(kvm)->handle;
ret = sev_issue_cmd(kvm, SEV_CMD_RECEIVE_UPDATE_DATA, &data,
&argp->error);
sev_unpin_memory(kvm, guest_page, n);
e_free_trans:
kfree(trans);
e_free_hdr:
kfree(hdr);
return ret;
}
static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_receive_finish data;
if (!sev_guest(kvm))
return -ENOTTY;
data.handle = to_kvm_sev_info(kvm)->handle;
return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
}
static bool is_cmd_allowed_from_mirror(u32 cmd_id)
{
if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA ||
cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT ||
cmd_id == KVM_SEV_DBG_ENCRYPT)
return true;
return false;
}
static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
{
struct kvm_sev_info *dst_sev = to_kvm_sev_info(dst_kvm);
struct kvm_sev_info *src_sev = to_kvm_sev_info(src_kvm);
int r = -EBUSY;
if (dst_kvm == src_kvm)
return -EINVAL;
if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1))
return -EBUSY;
if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1))
goto release_dst;
r = -EINTR;
if (mutex_lock_killable(&dst_kvm->lock))
goto release_src;
if (mutex_lock_killable_nested(&src_kvm->lock, SINGLE_DEPTH_NESTING))
goto unlock_dst;
return 0;
unlock_dst:
mutex_unlock(&dst_kvm->lock);
release_src:
atomic_set_release(&src_sev->migration_in_progress, 0);
release_dst:
atomic_set_release(&dst_sev->migration_in_progress, 0);
return r;
}
static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
{
struct kvm_sev_info *dst_sev = to_kvm_sev_info(dst_kvm);
struct kvm_sev_info *src_sev = to_kvm_sev_info(src_kvm);
mutex_unlock(&dst_kvm->lock);
mutex_unlock(&src_kvm->lock);
atomic_set_release(&dst_sev->migration_in_progress, 0);
atomic_set_release(&src_sev->migration_in_progress, 0);
}
static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
{
struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm);
struct kvm_sev_info *src = to_kvm_sev_info(src_kvm);
struct kvm_vcpu *dst_vcpu, *src_vcpu;
struct vcpu_svm *dst_svm, *src_svm;
struct kvm_sev_info *mirror;
unsigned long i;
dst->active = true;
dst->asid = src->asid;
dst->handle = src->handle;
dst->pages_locked = src->pages_locked;
dst->enc_context_owner = src->enc_context_owner;
dst->es_active = src->es_active;
dst->vmsa_features = src->vmsa_features;
src->asid = 0;
src->active = false;
src->handle = 0;
src->pages_locked = 0;
src->enc_context_owner = NULL;
src->es_active = false;
list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list);
list_cut_before(&dst->mirror_vms, &src->mirror_vms, &src->mirror_vms);
list_for_each_entry(mirror, &dst->mirror_vms, mirror_entry) {
kvm_get_kvm(dst_kvm);
kvm_put_kvm(src_kvm);
mirror->enc_context_owner = dst_kvm;
}
if (is_mirroring_enc_context(dst_kvm)) {
struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(dst->enc_context_owner);
list_del(&src->mirror_entry);
list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms);
}
kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) {
dst_svm = to_svm(dst_vcpu);
sev_init_vmcb(dst_svm, false);
if (!dst->es_active)
continue;
src_vcpu = kvm_get_vcpu(src_kvm, i);
src_svm = to_svm(src_vcpu);
memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es));
dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa;
dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa;
dst_vcpu->arch.guest_state_protected = true;
memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es));
src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE;
src_svm->vmcb->control.vmsa_pa = INVALID_PAGE;
src_vcpu->arch.guest_state_protected = false;
}
}
static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
{
struct kvm_vcpu *src_vcpu;
unsigned long i;
if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
dst->created_vcpus != atomic_read(&dst->online_vcpus))
return -EBUSY;
if (!sev_es_guest(src))
return 0;
if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus))
return -EINVAL;
kvm_for_each_vcpu(i, src_vcpu, src) {
if (!src_vcpu->arch.guest_state_protected)
return -EINVAL;
}
return 0;
}
int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
{
struct kvm_sev_info *dst_sev = to_kvm_sev_info(kvm);
struct kvm_sev_info *src_sev, *cg_cleanup_sev;
CLASS(fd, f)(source_fd);
struct kvm *source_kvm;
bool charged = false;
int ret;
if (fd_empty(f))
return -EBADF;
if (!file_is_kvm(fd_file(f)))
return -EBADF;
source_kvm = fd_file(f)->private_data;
ret = sev_lock_two_vms(kvm, source_kvm);
if (ret)
return ret;
if (kvm->arch.vm_type != source_kvm->arch.vm_type ||
sev_guest(kvm) || !sev_guest(source_kvm)) {
ret = -EINVAL;
goto out_unlock;
}
src_sev = to_kvm_sev_info(source_kvm);
dst_sev->misc_cg = get_current_misc_cg();
cg_cleanup_sev = dst_sev;
if (dst_sev->misc_cg != src_sev->misc_cg) {
ret = sev_misc_cg_try_charge(dst_sev);
if (ret)
goto out_dst_cgroup;
charged = true;
}
ret = kvm_lock_all_vcpus(kvm);
if (ret)
goto out_dst_cgroup;
ret = kvm_lock_all_vcpus(source_kvm);
if (ret)
goto out_dst_vcpu;
ret = sev_check_source_vcpus(kvm, source_kvm);
if (ret)
goto out_source_vcpu;
if (!zalloc_cpumask_var(&dst_sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
ret = -ENOMEM;
goto out_source_vcpu;
}
sev_migrate_from(kvm, source_kvm);
kvm_vm_dead(source_kvm);
cg_cleanup_sev = src_sev;
ret = 0;
out_source_vcpu:
kvm_unlock_all_vcpus(source_kvm);
out_dst_vcpu:
kvm_unlock_all_vcpus(kvm);
out_dst_cgroup:
if (charged)
sev_misc_cg_uncharge(cg_cleanup_sev);
put_misc_cg(cg_cleanup_sev->misc_cg);
cg_cleanup_sev->misc_cg = NULL;
out_unlock:
sev_unlock_two_vms(kvm, source_kvm);
return ret;
}
int sev_dev_get_attr(u32 group, u64 attr, u64 *val)
{
if (group != KVM_X86_GRP_SEV)
return -ENXIO;
switch (attr) {
case KVM_X86_SEV_VMSA_FEATURES:
*val = sev_supported_vmsa_features;
return 0;
default:
return -ENXIO;
}
}
static void *snp_context_create(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct sev_data_snp_addr data = {};
void *context;
int rc;
context = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT);
if (!context)
return NULL;
data.address = __psp_pa(context);
rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_GCTX_CREATE, &data, &argp->error);
if (rc) {
pr_warn("Failed to create SEV-SNP context, rc %d fw_error %d",
rc, argp->error);
snp_free_firmware_page(context);
return NULL;
}
return context;
}
static int snp_bind_asid(struct kvm *kvm, int *error)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_data_snp_activate data = {0};
data.gctx_paddr = __psp_pa(sev->snp_context);
data.asid = sev_get_asid(kvm);
return sev_issue_cmd(kvm, SEV_CMD_SNP_ACTIVATE, &data, error);
}
static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_data_snp_launch_start start = {0};
struct kvm_sev_snp_launch_start params;
int rc;
if (!sev_snp_guest(kvm))
return -ENOTTY;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
if (sev->snp_context)
return -EINVAL;
if (params.flags)
return -EINVAL;
if (params.policy & ~SNP_POLICY_MASK_VALID)
return -EINVAL;
if (!(params.policy & SNP_POLICY_MASK_RSVD_MBO))
return -EINVAL;
if (snp_is_secure_tsc_enabled(kvm)) {
if (WARN_ON_ONCE(!kvm->arch.default_tsc_khz))
return -EINVAL;
start.desired_tsc_khz = kvm->arch.default_tsc_khz;
}
sev->snp_context = snp_context_create(kvm, argp);
if (!sev->snp_context)
return -ENOTTY;
start.gctx_paddr = __psp_pa(sev->snp_context);
start.policy = params.policy;
memcpy(start.gosvw, params.gosvw, sizeof(params.gosvw));
rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_START, &start, &argp->error);
if (rc) {
pr_debug("%s: SEV_CMD_SNP_LAUNCH_START firmware command failed, rc %d\n",
__func__, rc);
goto e_free_context;
}
sev->policy = params.policy;
sev->fd = argp->sev_fd;
rc = snp_bind_asid(kvm, &argp->error);
if (rc) {
pr_debug("%s: Failed to bind ASID to SEV-SNP context, rc %d\n",
__func__, rc);
goto e_free_context;
}
return 0;
e_free_context:
snp_decommission_context(kvm);
return rc;
}
struct sev_gmem_populate_args {
__u8 type;
int sev_fd;
int fw_error;
};
static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pfn,
void __user *src, int order, void *opaque)
{
struct sev_gmem_populate_args *sev_populate_args = opaque;
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
int n_private = 0, ret, i;
int npages = (1 << order);
gfn_t gfn;
if (WARN_ON_ONCE(sev_populate_args->type != KVM_SEV_SNP_PAGE_TYPE_ZERO && !src))
return -EINVAL;
for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) {
struct sev_data_snp_launch_update fw_args = {0};
bool assigned = false;
int level;
ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level);
if (ret || assigned) {
pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n",
__func__, gfn, ret, assigned);
ret = ret ? -EINVAL : -EEXIST;
goto err;
}
if (src) {
void *vaddr = kmap_local_pfn(pfn + i);
if (copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE)) {
ret = -EFAULT;
goto err;
}
kunmap_local(vaddr);
}
ret = rmp_make_private(pfn + i, gfn << PAGE_SHIFT, PG_LEVEL_4K,
sev_get_asid(kvm), true);
if (ret)
goto err;
n_private++;
fw_args.gctx_paddr = __psp_pa(sev->snp_context);
fw_args.address = __sme_set(pfn_to_hpa(pfn + i));
fw_args.page_size = PG_LEVEL_TO_RMP(PG_LEVEL_4K);
fw_args.page_type = sev_populate_args->type;
ret = __sev_issue_cmd(sev_populate_args->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
&fw_args, &sev_populate_args->fw_error);
if (ret)
goto fw_err;
}
return 0;
fw_err:
if (!snp_page_reclaim(kvm, pfn + i) &&
sev_populate_args->type == KVM_SEV_SNP_PAGE_TYPE_CPUID &&
sev_populate_args->fw_error == SEV_RET_INVALID_PARAM) {
void *vaddr = kmap_local_pfn(pfn + i);
if (copy_to_user(src + i * PAGE_SIZE, vaddr, PAGE_SIZE))
pr_debug("Failed to write CPUID page back to userspace\n");
kunmap_local(vaddr);
}
n_private--;
err:
pr_debug("%s: exiting with error ret %d (fw_error %d), restoring %d gmem PFNs to shared.\n",
__func__, ret, sev_populate_args->fw_error, n_private);
for (i = 0; i < n_private; i++)
kvm_rmp_make_shared(kvm, pfn + i, PG_LEVEL_4K);
return ret;
}
static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_gmem_populate_args sev_populate_args = {0};
struct kvm_sev_snp_launch_update params;
struct kvm_memory_slot *memslot;
long npages, count;
void __user *src;
int ret = 0;
if (!sev_snp_guest(kvm) || !sev->snp_context)
return -EINVAL;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
pr_debug("%s: GFN start 0x%llx length 0x%llx type %d flags %d\n", __func__,
params.gfn_start, params.len, params.type, params.flags);
if (!params.len || !PAGE_ALIGNED(params.len) || params.flags ||
(params.type != KVM_SEV_SNP_PAGE_TYPE_NORMAL &&
params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO &&
params.type != KVM_SEV_SNP_PAGE_TYPE_UNMEASURED &&
params.type != KVM_SEV_SNP_PAGE_TYPE_SECRETS &&
params.type != KVM_SEV_SNP_PAGE_TYPE_CPUID))
return -EINVAL;
npages = params.len / PAGE_SIZE;
mutex_lock(&kvm->slots_lock);
memslot = gfn_to_memslot(kvm, params.gfn_start);
if (!kvm_slot_has_gmem(memslot)) {
ret = -EINVAL;
goto out;
}
sev_populate_args.sev_fd = argp->sev_fd;
sev_populate_args.type = params.type;
src = params.type == KVM_SEV_SNP_PAGE_TYPE_ZERO ? NULL : u64_to_user_ptr(params.uaddr);
count = kvm_gmem_populate(kvm, params.gfn_start, src, npages,
sev_gmem_post_populate, &sev_populate_args);
if (count < 0) {
argp->error = sev_populate_args.fw_error;
pr_debug("%s: kvm_gmem_populate failed, ret %ld (fw_error %d)\n",
__func__, count, argp->error);
ret = -EIO;
} else {
params.gfn_start += count;
params.len -= count * PAGE_SIZE;
if (params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO)
params.uaddr += count * PAGE_SIZE;
ret = 0;
if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params)))
ret = -EFAULT;
}
out:
mutex_unlock(&kvm->slots_lock);
return ret;
}
static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_data_snp_launch_update data = {};
struct kvm_vcpu *vcpu;
unsigned long i;
int ret;
data.gctx_paddr = __psp_pa(sev->snp_context);
data.page_type = SNP_PAGE_TYPE_VMSA;
kvm_for_each_vcpu(i, vcpu, kvm) {
struct vcpu_svm *svm = to_svm(vcpu);
u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
ret = sev_es_sync_vmsa(svm);
if (ret)
return ret;
ret = rmp_make_private(pfn, INITIAL_VMSA_GPA, PG_LEVEL_4K, sev->asid, true);
if (ret)
return ret;
data.address = __sme_pa(svm->sev_es.vmsa);
ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
&data, &argp->error);
if (ret) {
snp_page_reclaim(kvm, pfn);
return ret;
}
svm->vcpu.arch.guest_state_protected = true;
svm_enable_lbrv(vcpu);
}
return 0;
}
static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct kvm_sev_snp_launch_finish params;
struct sev_data_snp_launch_finish *data;
void *id_block = NULL, *id_auth = NULL;
int ret;
if (!sev_snp_guest(kvm))
return -ENOTTY;
if (!sev->snp_context)
return -EINVAL;
if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
if (params.flags)
return -EINVAL;
ret = snp_launch_update_vmsa(kvm, argp);
if (ret)
return ret;
data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
if (!data)
return -ENOMEM;
if (params.id_block_en) {
id_block = psp_copy_user_blob(params.id_block_uaddr, KVM_SEV_SNP_ID_BLOCK_SIZE);
if (IS_ERR(id_block)) {
ret = PTR_ERR(id_block);
goto e_free;
}
data->id_block_en = 1;
data->id_block_paddr = __sme_pa(id_block);
id_auth = psp_copy_user_blob(params.id_auth_uaddr, KVM_SEV_SNP_ID_AUTH_SIZE);
if (IS_ERR(id_auth)) {
ret = PTR_ERR(id_auth);
goto e_free_id_block;
}
data->id_auth_paddr = __sme_pa(id_auth);
if (params.auth_key_en)
data->auth_key_en = 1;
}
data->vcek_disabled = params.vcek_disabled;
memcpy(data->host_data, params.host_data, KVM_SEV_SNP_FINISH_DATA_SIZE);
data->gctx_paddr = __psp_pa(sev->snp_context);
ret = sev_issue_cmd(kvm, SEV_CMD_SNP_LAUNCH_FINISH, data, &argp->error);
if (!ret)
kvm->arch.pre_fault_allowed = true;
kfree(id_auth);
e_free_id_block:
kfree(id_block);
e_free:
kfree(data);
return ret;
}
int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
{
struct kvm_sev_cmd sev_cmd;
int r;
if (!sev_enabled)
return -ENOTTY;
if (!argp)
return 0;
if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd)))
return -EFAULT;
mutex_lock(&kvm->lock);
if (is_mirroring_enc_context(kvm) &&
!is_cmd_allowed_from_mirror(sev_cmd.id)) {
r = -EINVAL;
goto out;
}
if (sev_snp_guest(kvm) && sev_cmd.id < KVM_SEV_SNP_LAUNCH_START) {
r = -EPERM;
goto out;
}
switch (sev_cmd.id) {
case KVM_SEV_ES_INIT:
if (!sev_es_enabled) {
r = -ENOTTY;
goto out;
}
fallthrough;
case KVM_SEV_INIT:
r = sev_guest_init(kvm, &sev_cmd);
break;
case KVM_SEV_INIT2:
r = sev_guest_init2(kvm, &sev_cmd);
break;
case KVM_SEV_LAUNCH_START:
r = sev_launch_start(kvm, &sev_cmd);
break;
case KVM_SEV_LAUNCH_UPDATE_DATA:
r = sev_launch_update_data(kvm, &sev_cmd);
break;
case KVM_SEV_LAUNCH_UPDATE_VMSA:
r = sev_launch_update_vmsa(kvm, &sev_cmd);
break;
case KVM_SEV_LAUNCH_MEASURE:
r = sev_launch_measure(kvm, &sev_cmd);
break;
case KVM_SEV_LAUNCH_FINISH:
r = sev_launch_finish(kvm, &sev_cmd);
break;
case KVM_SEV_GUEST_STATUS:
r = sev_guest_status(kvm, &sev_cmd);
break;
case KVM_SEV_DBG_DECRYPT:
r = sev_dbg_crypt(kvm, &sev_cmd, true);
break;
case KVM_SEV_DBG_ENCRYPT:
r = sev_dbg_crypt(kvm, &sev_cmd, false);
break;
case KVM_SEV_LAUNCH_SECRET:
r = sev_launch_secret(kvm, &sev_cmd);
break;
case KVM_SEV_GET_ATTESTATION_REPORT:
r = sev_get_attestation_report(kvm, &sev_cmd);
break;
case KVM_SEV_SEND_START:
r = sev_send_start(kvm, &sev_cmd);
break;
case KVM_SEV_SEND_UPDATE_DATA:
r = sev_send_update_data(kvm, &sev_cmd);
break;
case KVM_SEV_SEND_FINISH:
r = sev_send_finish(kvm, &sev_cmd);
break;
case KVM_SEV_SEND_CANCEL:
r = sev_send_cancel(kvm, &sev_cmd);
break;
case KVM_SEV_RECEIVE_START:
r = sev_receive_start(kvm, &sev_cmd);
break;
case KVM_SEV_RECEIVE_UPDATE_DATA:
r = sev_receive_update_data(kvm, &sev_cmd);
break;
case KVM_SEV_RECEIVE_FINISH:
r = sev_receive_finish(kvm, &sev_cmd);
break;
case KVM_SEV_SNP_LAUNCH_START:
r = snp_launch_start(kvm, &sev_cmd);
break;
case KVM_SEV_SNP_LAUNCH_UPDATE:
r = snp_launch_update(kvm, &sev_cmd);
break;
case KVM_SEV_SNP_LAUNCH_FINISH:
r = snp_launch_finish(kvm, &sev_cmd);
break;
default:
r = -EINVAL;
goto out;
}
if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd)))
r = -EFAULT;
out:
mutex_unlock(&kvm->lock);
return r;
}
int sev_mem_enc_register_region(struct kvm *kvm,
struct kvm_enc_region *range)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct enc_region *region;
int ret = 0;
if (!sev_guest(kvm))
return -ENOTTY;
if (is_mirroring_enc_context(kvm))
return -EINVAL;
if (range->addr > ULONG_MAX || range->size > ULONG_MAX)
return -EINVAL;
region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT);
if (!region)
return -ENOMEM;
mutex_lock(&kvm->lock);
region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages,
FOLL_WRITE | FOLL_LONGTERM);
if (IS_ERR(region->pages)) {
ret = PTR_ERR(region->pages);
mutex_unlock(&kvm->lock);
goto e_free;
}
sev_clflush_pages(region->pages, region->npages);
region->uaddr = range->addr;
region->size = range->size;
list_add_tail(®ion->list, &sev->regions_list);
mutex_unlock(&kvm->lock);
return ret;
e_free:
kfree(region);
return ret;
}
static struct enc_region *
find_enc_region(struct kvm *kvm, struct kvm_enc_region *range)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
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 sev_mem_enc_unregister_region(struct kvm *kvm,
struct kvm_enc_region *range)
{
struct enc_region *region;
int ret;
if (is_mirroring_enc_context(kvm))
return -EINVAL;
mutex_lock(&kvm->lock);
if (!sev_guest(kvm)) {
ret = -ENOTTY;
goto failed;
}
region = find_enc_region(kvm, range);
if (!region) {
ret = -EINVAL;
goto failed;
}
sev_writeback_caches(kvm);
__unregister_enc_region_locked(kvm, region);
mutex_unlock(&kvm->lock);
return 0;
failed:
mutex_unlock(&kvm->lock);
return ret;
}
int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
{
CLASS(fd, f)(source_fd);
struct kvm *source_kvm;
struct kvm_sev_info *source_sev, *mirror_sev;
int ret;
if (fd_empty(f))
return -EBADF;
if (!file_is_kvm(fd_file(f)))
return -EBADF;
source_kvm = fd_file(f)->private_data;
ret = sev_lock_two_vms(kvm, source_kvm);
if (ret)
return ret;
if (sev_guest(kvm) || !sev_guest(source_kvm) ||
is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) {
ret = -EINVAL;
goto e_unlock;
}
mirror_sev = to_kvm_sev_info(kvm);
if (!zalloc_cpumask_var(&mirror_sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
ret = -ENOMEM;
goto e_unlock;
}
source_sev = to_kvm_sev_info(source_kvm);
kvm_get_kvm(source_kvm);
list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms);
mirror_sev->enc_context_owner = source_kvm;
mirror_sev->active = true;
mirror_sev->asid = source_sev->asid;
mirror_sev->fd = source_sev->fd;
mirror_sev->es_active = source_sev->es_active;
mirror_sev->need_init = false;
mirror_sev->handle = source_sev->handle;
INIT_LIST_HEAD(&mirror_sev->regions_list);
INIT_LIST_HEAD(&mirror_sev->mirror_vms);
ret = 0;
e_unlock:
sev_unlock_two_vms(kvm, source_kvm);
return ret;
}
static int snp_decommission_context(struct kvm *kvm)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct sev_data_snp_addr data = {};
int ret;
if (!sev->snp_context)
return 0;
data.address = __sme_pa(sev->snp_context);
down_write(&sev_deactivate_lock);
ret = sev_do_cmd(SEV_CMD_SNP_DECOMMISSION, &data, NULL);
up_write(&sev_deactivate_lock);
if (WARN_ONCE(ret, "Failed to release guest context, ret %d", ret))
return ret;
snp_free_firmware_page(sev->snp_context);
sev->snp_context = NULL;
return 0;
}
void sev_vm_destroy(struct kvm *kvm)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
struct list_head *head = &sev->regions_list;
struct list_head *pos, *q;
if (!sev_guest(kvm))
return;
WARN_ON(!list_empty(&sev->mirror_vms));
free_cpumask_var(sev->have_run_cpus);
if (is_mirroring_enc_context(kvm)) {
struct kvm *owner_kvm = sev->enc_context_owner;
mutex_lock(&owner_kvm->lock);
list_del(&sev->mirror_entry);
mutex_unlock(&owner_kvm->lock);
kvm_put_kvm(owner_kvm);
return;
}
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();
}
}
if (sev_snp_guest(kvm)) {
snp_guest_req_cleanup(kvm);
if (snp_decommission_context(kvm))
return;
} else {
sev_unbind_asid(kvm, sev->handle);
}
sev_asid_free(sev);
}
void __init sev_set_cpu_caps(void)
{
if (sev_enabled) {
kvm_cpu_cap_set(X86_FEATURE_SEV);
kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_VM);
}
if (sev_es_enabled) {
kvm_cpu_cap_set(X86_FEATURE_SEV_ES);
kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM);
}
if (sev_snp_enabled) {
kvm_cpu_cap_set(X86_FEATURE_SEV_SNP);
kvm_caps.supported_vm_types |= BIT(KVM_X86_SNP_VM);
}
}
static bool is_sev_snp_initialized(void)
{
struct sev_user_data_snp_status *status;
struct sev_data_snp_addr buf;
bool initialized = false;
int ret, error = 0;
status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO);
if (!status)
return false;
buf.address = __psp_pa(status);
ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error);
if (ret) {
pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n",
ret, error, error);
goto out;
}
initialized = !!status->state;
out:
snp_free_firmware_page(status);
return initialized;
}
void __init sev_hardware_setup(void)
{
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
struct sev_platform_init_args init_args = {0};
bool sev_snp_supported = false;
bool sev_es_supported = false;
bool sev_supported = false;
if (!sev_enabled || !npt_enabled || !nrips)
goto out;
if (!boot_cpu_has(X86_FEATURE_SEV) ||
WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) ||
WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID)))
goto out;
if (IS_BUILTIN(CONFIG_KVM_AMD) && sev_module_init())
goto out;
cpuid(0x8000001f, &eax, &ebx, &ecx, &edx);
sev_enc_bit = ebx & 0x3f;
max_sev_asid = ecx;
if (!max_sev_asid)
goto out;
min_sev_asid = edx;
sev_me_mask = 1UL << (ebx & 0x3f);
nr_asids = max_sev_asid + 1;
sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
if (!sev_asid_bitmap)
goto out;
sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
if (!sev_reclaim_asid_bitmap) {
bitmap_free(sev_asid_bitmap);
sev_asid_bitmap = NULL;
goto out;
}
if (min_sev_asid <= max_sev_asid) {
sev_asid_count = max_sev_asid - min_sev_asid + 1;
WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
}
sev_supported = true;
if (!sev_es_enabled)
goto out;
if (!enable_mmio_caching)
goto out;
if (!boot_cpu_has(X86_FEATURE_SEV_ES))
goto out;
if (!lbrv) {
WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV),
"LBRV must be present for SEV-ES support");
goto out;
}
if (min_sev_asid == 1)
goto out;
min_sev_es_asid = min_snp_asid = 1;
max_sev_es_asid = max_snp_asid = min_sev_asid - 1;
sev_es_asid_count = min_sev_asid - 1;
WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count));
sev_es_supported = true;
sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
out:
if (sev_enabled) {
init_args.probe = true;
if (sev_is_snp_ciphertext_hiding_supported())
init_args.max_snp_asid = min(nr_ciphertext_hiding_asids,
min_sev_asid - 1);
if (sev_platform_init(&init_args))
sev_supported = sev_es_supported = sev_snp_supported = false;
else if (sev_snp_supported)
sev_snp_supported = is_sev_snp_initialized();
if (sev_snp_supported)
nr_ciphertext_hiding_asids = init_args.max_snp_asid;
if (nr_ciphertext_hiding_asids) {
max_snp_asid = nr_ciphertext_hiding_asids;
min_sev_es_asid = max_snp_asid + 1;
pr_info("SEV-SNP ciphertext hiding enabled\n");
}
}
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
"unusable" :
"disabled",
min_sev_asid, max_sev_asid);
if (boot_cpu_has(X86_FEATURE_SEV_ES))
pr_info("SEV-ES %s (ASIDs %u - %u)\n",
sev_es_supported ? min_sev_es_asid <= max_sev_es_asid ? "enabled" :
"unusable" :
"disabled",
min_sev_es_asid, max_sev_es_asid);
if (boot_cpu_has(X86_FEATURE_SEV_SNP))
pr_info("SEV-SNP %s (ASIDs %u - %u)\n",
str_enabled_disabled(sev_snp_supported),
min_snp_asid, max_snp_asid);
sev_enabled = sev_supported;
sev_es_enabled = sev_es_supported;
sev_snp_enabled = sev_snp_supported;
if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
!cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
sev_es_debug_swap_enabled = false;
sev_supported_vmsa_features = 0;
if (sev_es_debug_swap_enabled)
sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
if (sev_snp_enabled && tsc_khz && cpu_feature_enabled(X86_FEATURE_SNP_SECURE_TSC))
sev_supported_vmsa_features |= SVM_SEV_FEAT_SECURE_TSC;
}
void sev_hardware_unsetup(void)
{
if (!sev_enabled)
return;
sev_flush_asids(1, max_sev_asid);
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_platform_shutdown();
}
int sev_cpu_init(struct svm_cpu_data *sd)
{
if (!sev_enabled)
return 0;
sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL);
if (!sd->sev_vmcbs)
return -ENOMEM;
return 0;
}
static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
{
unsigned int asid = sev_get_asid(vcpu->kvm);
unsigned long addr = (unsigned long)va;
if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) {
clflush_cache_range(va, PAGE_SIZE);
return;
}
if (WARN_ON_ONCE(wrmsrq_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
goto do_sev_writeback_caches;
return;
do_sev_writeback_caches:
sev_writeback_caches(vcpu->kvm);
}
void sev_guest_memory_reclaimed(struct kvm *kvm)
{
if (!sev_guest(kvm) || sev_snp_guest(kvm))
return;
sev_writeback_caches(kvm);
}
void sev_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm;
if (!sev_es_guest(vcpu->kvm))
return;
svm = to_svm(vcpu);
if (sev_snp_guest(vcpu->kvm)) {
u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
if (kvm_rmp_make_shared(vcpu->kvm, pfn, PG_LEVEL_4K))
goto skip_vmsa_free;
}
if (vcpu->arch.guest_state_protected)
sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa);
__free_page(virt_to_page(svm->sev_es.vmsa));
skip_vmsa_free:
if (svm->sev_es.ghcb_sa_free)
kvfree(svm->sev_es.ghcb_sa);
}
static u64 kvm_get_cached_sw_exit_code(struct vmcb_control_area *control)
{
return (((u64)control->exit_code_hi) << 32) | control->exit_code;
}
static void dump_ghcb(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
unsigned int nbits;
if (!dump_invalid_vmcb) {
pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
return;
}
nbits = sizeof(svm->sev_es.valid_bitmap) * 8;
pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
kvm_get_cached_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm));
pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap);
}
static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
struct ghcb *ghcb = svm->sev_es.ghcb;
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->sev_es.ghcb;
u64 exit_code;
memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap));
memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap));
vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm);
vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm);
vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm);
vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm);
vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm);
svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm);
if (kvm_ghcb_xcr0_is_valid(svm))
__kvm_set_xcr(vcpu, 0, kvm_ghcb_get_xcr0(svm));
if (kvm_ghcb_xss_is_valid(svm))
__kvm_emulate_msr_write(vcpu, MSR_IA32_XSS, kvm_ghcb_get_xss(svm));
exit_code = kvm_ghcb_get_sw_exit_code(svm);
control->exit_code = lower_32_bits(exit_code);
control->exit_code_hi = upper_32_bits(exit_code);
control->exit_info_1 = kvm_ghcb_get_sw_exit_info_1(svm);
control->exit_info_2 = kvm_ghcb_get_sw_exit_info_2(svm);
svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm);
memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
}
static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct kvm_vcpu *vcpu = &svm->vcpu;
u64 exit_code;
u64 reason;
exit_code = kvm_get_cached_sw_exit_code(control);
if (svm->sev_es.ghcb->ghcb_usage) {
reason = GHCB_ERR_INVALID_USAGE;
goto vmgexit_err;
}
reason = GHCB_ERR_MISSING_INPUT;
if (!kvm_ghcb_sw_exit_code_is_valid(svm) ||
!kvm_ghcb_sw_exit_info_1_is_valid(svm) ||
!kvm_ghcb_sw_exit_info_2_is_valid(svm))
goto vmgexit_err;
switch (exit_code) {
case SVM_EXIT_READ_DR7:
break;
case SVM_EXIT_WRITE_DR7:
if (!kvm_ghcb_rax_is_valid(svm))
goto vmgexit_err;
break;
case SVM_EXIT_RDTSC:
break;
case SVM_EXIT_RDPMC:
if (!kvm_ghcb_rcx_is_valid(svm))
goto vmgexit_err;
break;
case SVM_EXIT_CPUID:
if (!kvm_ghcb_rax_is_valid(svm) ||
!kvm_ghcb_rcx_is_valid(svm))
goto vmgexit_err;
if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd)
if (!kvm_ghcb_xcr0_is_valid(svm))
goto vmgexit_err;
break;
case SVM_EXIT_INVD:
break;
case SVM_EXIT_IOIO:
if (control->exit_info_1 & SVM_IOIO_STR_MASK) {
if (!kvm_ghcb_sw_scratch_is_valid(svm))
goto vmgexit_err;
} else {
if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK))
if (!kvm_ghcb_rax_is_valid(svm))
goto vmgexit_err;
}
break;
case SVM_EXIT_MSR:
if (!kvm_ghcb_rcx_is_valid(svm))
goto vmgexit_err;
if (control->exit_info_1) {
if (!kvm_ghcb_rax_is_valid(svm) ||
!kvm_ghcb_rdx_is_valid(svm))
goto vmgexit_err;
}
break;
case SVM_EXIT_VMMCALL:
if (!kvm_ghcb_rax_is_valid(svm) ||
!kvm_ghcb_cpl_is_valid(svm))
goto vmgexit_err;
break;
case SVM_EXIT_RDTSCP:
break;
case SVM_EXIT_WBINVD:
break;
case SVM_EXIT_MONITOR:
if (!kvm_ghcb_rax_is_valid(svm) ||
!kvm_ghcb_rcx_is_valid(svm) ||
!kvm_ghcb_rdx_is_valid(svm))
goto vmgexit_err;
break;
case SVM_EXIT_MWAIT:
if (!kvm_ghcb_rax_is_valid(svm) ||
!kvm_ghcb_rcx_is_valid(svm))
goto vmgexit_err;
break;
case SVM_VMGEXIT_MMIO_READ:
case SVM_VMGEXIT_MMIO_WRITE:
if (!kvm_ghcb_sw_scratch_is_valid(svm))
goto vmgexit_err;
break;
case SVM_VMGEXIT_AP_CREATION:
if (!sev_snp_guest(vcpu->kvm))
goto vmgexit_err;
if (lower_32_bits(control->exit_info_1) != SVM_VMGEXIT_AP_DESTROY)
if (!kvm_ghcb_rax_is_valid(svm))
goto vmgexit_err;
break;
case SVM_VMGEXIT_NMI_COMPLETE:
case SVM_VMGEXIT_AP_HLT_LOOP:
case SVM_VMGEXIT_AP_JUMP_TABLE:
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
case SVM_VMGEXIT_HV_FEATURES:
case SVM_VMGEXIT_TERM_REQUEST:
break;
case SVM_VMGEXIT_PSC:
if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm))
goto vmgexit_err;
break;
case SVM_VMGEXIT_GUEST_REQUEST:
case SVM_VMGEXIT_EXT_GUEST_REQUEST:
if (!sev_snp_guest(vcpu->kvm) ||
!PAGE_ALIGNED(control->exit_info_1) ||
!PAGE_ALIGNED(control->exit_info_2) ||
control->exit_info_1 == control->exit_info_2)
goto vmgexit_err;
break;
default:
reason = GHCB_ERR_INVALID_EVENT;
goto vmgexit_err;
}
return 0;
vmgexit_err:
if (reason == GHCB_ERR_INVALID_USAGE) {
vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
svm->sev_es.ghcb->ghcb_usage);
} else if (reason == GHCB_ERR_INVALID_EVENT) {
vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
exit_code);
} else {
vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n",
exit_code);
dump_ghcb(svm);
}
svm_vmgexit_bad_input(svm, reason);
return 1;
}
void sev_es_unmap_ghcb(struct vcpu_svm *svm)
{
svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NONE;
if (!svm->sev_es.ghcb)
return;
if (svm->sev_es.ghcb_sa_free) {
if (svm->sev_es.ghcb_sa_sync) {
kvm_write_guest(svm->vcpu.kvm,
svm->sev_es.sw_scratch,
svm->sev_es.ghcb_sa,
svm->sev_es.ghcb_sa_len);
svm->sev_es.ghcb_sa_sync = false;
}
kvfree(svm->sev_es.ghcb_sa);
svm->sev_es.ghcb_sa = NULL;
svm->sev_es.ghcb_sa_free = false;
}
trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb);
sev_es_sync_to_ghcb(svm);
kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map);
svm->sev_es.ghcb = NULL;
}
int pre_sev_run(struct vcpu_svm *svm, int cpu)
{
struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
struct kvm *kvm = svm->vcpu.kvm;
unsigned int asid = sev_get_asid(kvm);
if (sev_es_guest(kvm) && !VALID_PAGE(svm->vmcb->control.vmsa_pa))
return -EINVAL;
if (!cpumask_test_cpu(cpu, to_kvm_sev_info(kvm)->have_run_cpus))
cpumask_set_cpu(cpu, to_kvm_sev_info(kvm)->have_run_cpus);
svm->asid = asid;
if (sd->sev_vmcbs[asid] == svm->vmcb &&
svm->vcpu.arch.last_vmentry_cpu == cpu)
return 0;
sd->sev_vmcbs[asid] = svm->vmcb;
svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
return 0;
}
#define GHCB_SCRATCH_AREA_LIMIT (16ULL * PAGE_SIZE)
static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
{
struct vmcb_control_area *control = &svm->vmcb->control;
u64 ghcb_scratch_beg, ghcb_scratch_end;
u64 scratch_gpa_beg, scratch_gpa_end;
void *scratch_va;
scratch_gpa_beg = svm->sev_es.sw_scratch;
if (!scratch_gpa_beg) {
pr_err("vmgexit: scratch gpa not provided\n");
goto e_scratch;
}
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);
goto e_scratch;
}
if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
ghcb_scratch_beg = control->ghcb_gpa +
offsetof(struct ghcb, shared_buffer);
ghcb_scratch_end = control->ghcb_gpa +
offsetof(struct ghcb, reserved_0xff0);
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);
goto e_scratch;
}
scratch_va = (void *)svm->sev_es.ghcb;
scratch_va += (scratch_gpa_beg - control->ghcb_gpa);
} else {
if (len > GHCB_SCRATCH_AREA_LIMIT) {
pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
len, GHCB_SCRATCH_AREA_LIMIT);
goto e_scratch;
}
scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT);
if (!scratch_va)
return -ENOMEM;
if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
kvfree(scratch_va);
return -EFAULT;
}
svm->sev_es.ghcb_sa_sync = sync;
svm->sev_es.ghcb_sa_free = true;
}
svm->sev_es.ghcb_sa = scratch_va;
svm->sev_es.ghcb_sa_len = len;
return 0;
e_scratch:
svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_SCRATCH_AREA);
return 1;
}
static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
unsigned int pos)
{
svm->vmcb->control.ghcb_gpa &= ~(mask << pos);
svm->vmcb->control.ghcb_gpa |= (value & mask) << pos;
}
static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos)
{
return (svm->vmcb->control.ghcb_gpa >> pos) & mask;
}
static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
{
svm->vmcb->control.ghcb_gpa = value;
}
static int snp_rmptable_psmash(kvm_pfn_t pfn)
{
int ret;
pfn = pfn & ~(KVM_PAGES_PER_HPAGE(PG_LEVEL_2M) - 1);
do {
ret = psmash(pfn);
} while (ret == PSMASH_FAIL_INUSE);
return ret;
}
static int snp_complete_psc_msr(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (vcpu->run->hypercall.ret)
set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
else
set_ghcb_msr(svm, GHCB_MSR_PSC_RESP);
return 1;
}
static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr)
{
u64 gpa = gfn_to_gpa(GHCB_MSR_PSC_REQ_TO_GFN(ghcb_msr));
u8 op = GHCB_MSR_PSC_REQ_TO_OP(ghcb_msr);
struct kvm_vcpu *vcpu = &svm->vcpu;
if (op != SNP_PAGE_STATE_PRIVATE && op != SNP_PAGE_STATE_SHARED) {
set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
return 1;
}
if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
return 1;
}
vcpu->run->exit_reason = KVM_EXIT_HYPERCALL;
vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
vcpu->run->hypercall.ret = 0;
vcpu->run->hypercall.args[0] = gpa;
vcpu->run->hypercall.args[1] = 1;
vcpu->run->hypercall.args[2] = (op == SNP_PAGE_STATE_PRIVATE)
? KVM_MAP_GPA_RANGE_ENCRYPTED
: KVM_MAP_GPA_RANGE_DECRYPTED;
vcpu->run->hypercall.args[2] |= KVM_MAP_GPA_RANGE_PAGE_SZ_4K;
vcpu->arch.complete_userspace_io = snp_complete_psc_msr;
return 0;
}
struct psc_buffer {
struct psc_hdr hdr;
struct psc_entry entries[];
} __packed;
static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc);
static void snp_complete_psc(struct vcpu_svm *svm, u64 psc_ret)
{
svm->sev_es.psc_inflight = 0;
svm->sev_es.psc_idx = 0;
svm->sev_es.psc_2m = false;
svm_vmgexit_no_action(svm, psc_ret);
}
static void __snp_complete_one_psc(struct vcpu_svm *svm)
{
struct psc_buffer *psc = svm->sev_es.ghcb_sa;
struct psc_entry *entries = psc->entries;
struct psc_hdr *hdr = &psc->hdr;
__u16 idx;
for (idx = svm->sev_es.psc_idx; svm->sev_es.psc_inflight;
svm->sev_es.psc_inflight--, idx++) {
struct psc_entry *entry = &entries[idx];
entry->cur_page = entry->pagesize ? 512 : 1;
}
hdr->cur_entry = idx;
}
static int snp_complete_one_psc(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct psc_buffer *psc = svm->sev_es.ghcb_sa;
if (vcpu->run->hypercall.ret) {
snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
return 1;
}
__snp_complete_one_psc(svm);
return snp_begin_psc(svm, psc);
}
static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc)
{
struct psc_entry *entries = psc->entries;
struct kvm_vcpu *vcpu = &svm->vcpu;
struct psc_hdr *hdr = &psc->hdr;
struct psc_entry entry_start;
u16 idx, idx_start, idx_end;
int npages;
bool huge;
u64 gfn;
if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
return 1;
}
next_range:
if (WARN_ON_ONCE(svm->sev_es.psc_inflight)) {
snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
return 1;
}
idx_start = hdr->cur_entry;
idx_end = hdr->end_entry;
if (idx_end >= VMGEXIT_PSC_MAX_COUNT) {
snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_HDR);
return 1;
}
for (idx = idx_start; idx <= idx_end; idx++, hdr->cur_entry++) {
entry_start = entries[idx];
gfn = entry_start.gfn;
huge = entry_start.pagesize;
npages = huge ? 512 : 1;
if (entry_start.cur_page > npages || !IS_ALIGNED(gfn, npages)) {
snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_ENTRY);
return 1;
}
if (entry_start.cur_page) {
npages -= entry_start.cur_page;
gfn += entry_start.cur_page;
huge = false;
}
if (npages)
break;
}
if (idx > idx_end) {
snp_complete_psc(svm, 0);
return 1;
}
svm->sev_es.psc_2m = huge;
svm->sev_es.psc_idx = idx;
svm->sev_es.psc_inflight = 1;
while (++idx <= idx_end) {
struct psc_entry entry = entries[idx];
if (entry.operation != entry_start.operation ||
entry.gfn != entry_start.gfn + npages ||
entry.cur_page || !!entry.pagesize != huge)
break;
svm->sev_es.psc_inflight++;
npages += huge ? 512 : 1;
}
switch (entry_start.operation) {
case VMGEXIT_PSC_OP_PRIVATE:
case VMGEXIT_PSC_OP_SHARED:
vcpu->run->exit_reason = KVM_EXIT_HYPERCALL;
vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
vcpu->run->hypercall.ret = 0;
vcpu->run->hypercall.args[0] = gfn_to_gpa(gfn);
vcpu->run->hypercall.args[1] = npages;
vcpu->run->hypercall.args[2] = entry_start.operation == VMGEXIT_PSC_OP_PRIVATE
? KVM_MAP_GPA_RANGE_ENCRYPTED
: KVM_MAP_GPA_RANGE_DECRYPTED;
vcpu->run->hypercall.args[2] |= entry_start.pagesize
? KVM_MAP_GPA_RANGE_PAGE_SZ_2M
: KVM_MAP_GPA_RANGE_PAGE_SZ_4K;
vcpu->arch.complete_userspace_io = snp_complete_one_psc;
return 0;
default:
__snp_complete_one_psc(svm);
goto next_range;
}
BUG();
}
static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_memory_slot *slot;
struct page *page;
kvm_pfn_t pfn;
gfn_t gfn;
guard(mutex)(&svm->sev_es.snp_vmsa_mutex);
if (!svm->sev_es.snp_ap_waiting_for_reset)
return;
svm->sev_es.snp_ap_waiting_for_reset = false;
vcpu->arch.pv.pv_unhalted = false;
kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED);
svm->vmcb->control.vmsa_pa = INVALID_PAGE;
vmcb_mark_all_dirty(svm->vmcb);
if (!VALID_PAGE(svm->sev_es.snp_vmsa_gpa))
return;
gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
slot = gfn_to_memslot(vcpu->kvm, gfn);
if (!slot)
return;
if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, &page, NULL))
return;
svm->sev_es.snp_has_guest_vmsa = true;
svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
kvm_release_page_clean(page);
}
static int sev_snp_ap_creation(struct vcpu_svm *svm)
{
struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
struct kvm_vcpu *vcpu = &svm->vcpu;
struct kvm_vcpu *target_vcpu;
struct vcpu_svm *target_svm;
unsigned int request;
unsigned int apic_id;
request = lower_32_bits(svm->vmcb->control.exit_info_1);
apic_id = upper_32_bits(svm->vmcb->control.exit_info_1);
target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, apic_id);
if (!target_vcpu) {
vcpu_unimpl(vcpu, "vmgexit: invalid AP APIC ID [%#x] from guest\n",
apic_id);
return -EINVAL;
}
target_svm = to_svm(target_vcpu);
guard(mutex)(&target_svm->sev_es.snp_vmsa_mutex);
switch (request) {
case SVM_VMGEXIT_AP_CREATE_ON_INIT:
case SVM_VMGEXIT_AP_CREATE:
if (vcpu->arch.regs[VCPU_REGS_RAX] != sev->vmsa_features) {
vcpu_unimpl(vcpu, "vmgexit: mismatched AP sev_features [%#lx] != [%#llx] from guest\n",
vcpu->arch.regs[VCPU_REGS_RAX], sev->vmsa_features);
return -EINVAL;
}
if (!page_address_valid(vcpu, svm->vmcb->control.exit_info_2)) {
vcpu_unimpl(vcpu, "vmgexit: invalid AP VMSA address [%#llx] from guest\n",
svm->vmcb->control.exit_info_2);
return -EINVAL;
}
if (IS_ALIGNED(svm->vmcb->control.exit_info_2, PMD_SIZE)) {
vcpu_unimpl(vcpu,
"vmgexit: AP VMSA address [%llx] from guest is unsafe as it is 2M aligned\n",
svm->vmcb->control.exit_info_2);
return -EINVAL;
}
target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
break;
case SVM_VMGEXIT_AP_DESTROY:
target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
break;
default:
vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
request);
return -EINVAL;
}
target_svm->sev_es.snp_ap_waiting_for_reset = true;
if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT)
kvm_make_request_and_kick(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
return 0;
}
static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
{
struct sev_data_snp_guest_request data = {0};
struct kvm *kvm = svm->vcpu.kvm;
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
sev_ret_code fw_err = 0;
int ret;
if (!sev_snp_guest(kvm))
return -EINVAL;
mutex_lock(&sev->guest_req_mutex);
if (kvm_read_guest(kvm, req_gpa, sev->guest_req_buf, PAGE_SIZE)) {
ret = -EIO;
goto out_unlock;
}
data.gctx_paddr = __psp_pa(sev->snp_context);
data.req_paddr = __psp_pa(sev->guest_req_buf);
data.res_paddr = __psp_pa(sev->guest_resp_buf);
ret = sev_issue_cmd(kvm, SEV_CMD_SNP_GUEST_REQUEST, &data, &fw_err);
if (ret && !fw_err)
goto out_unlock;
if (kvm_write_guest(kvm, resp_gpa, sev->guest_resp_buf, PAGE_SIZE)) {
ret = -EIO;
goto out_unlock;
}
svm_vmgexit_no_action(svm, SNP_GUEST_ERR(0, fw_err));
ret = 1;
out_unlock:
mutex_unlock(&sev->guest_req_mutex);
return ret;
}
static int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
{
struct kvm *kvm = svm->vcpu.kvm;
u8 msg_type;
if (!sev_snp_guest(kvm))
return -EINVAL;
if (kvm_read_guest(kvm, req_gpa + offsetof(struct snp_guest_msg_hdr, msg_type),
&msg_type, 1))
return -EIO;
if (msg_type == SNP_MSG_REPORT_REQ) {
struct kvm_vcpu *vcpu = &svm->vcpu;
u64 data_npages;
gpa_t data_gpa;
if (!kvm_ghcb_rax_is_valid(svm) || !kvm_ghcb_rbx_is_valid(svm))
goto request_invalid;
data_gpa = vcpu->arch.regs[VCPU_REGS_RAX];
data_npages = vcpu->arch.regs[VCPU_REGS_RBX];
if (!PAGE_ALIGNED(data_gpa))
goto request_invalid;
if (data_npages && kvm_clear_guest(kvm, data_gpa, 24))
return -EIO;
}
return snp_handle_guest_req(svm, req_gpa, resp_gpa);
request_invalid:
svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_INPUT);
return 1;
}
static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct kvm_vcpu *vcpu = &svm->vcpu;
struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
u64 ghcb_info;
int ret = 1;
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((__u64)sev->ghcb_version,
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);
vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn;
vcpu->arch.regs[VCPU_REGS_RCX] = 0;
ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID);
if (!ret) {
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_AP_RESET_HOLD_REQ:
svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_MSR_PROTO;
ret = kvm_emulate_ap_reset_hold(&svm->vcpu);
set_ghcb_msr_bits(svm, 0,
GHCB_MSR_AP_RESET_HOLD_RESULT_MASK,
GHCB_MSR_AP_RESET_HOLD_RESULT_POS);
set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP,
GHCB_MSR_INFO_MASK,
GHCB_MSR_INFO_POS);
break;
case GHCB_MSR_HV_FT_REQ:
set_ghcb_msr_bits(svm, GHCB_HV_FT_SUPPORTED,
GHCB_MSR_HV_FT_MASK, GHCB_MSR_HV_FT_POS);
set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP,
GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS);
break;
case GHCB_MSR_PREF_GPA_REQ:
if (!sev_snp_guest(vcpu->kvm))
goto out_terminate;
set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_NONE, GHCB_MSR_GPA_VALUE_MASK,
GHCB_MSR_GPA_VALUE_POS);
set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_RESP, GHCB_MSR_INFO_MASK,
GHCB_MSR_INFO_POS);
break;
case GHCB_MSR_REG_GPA_REQ: {
u64 gfn;
if (!sev_snp_guest(vcpu->kvm))
goto out_terminate;
gfn = get_ghcb_msr_bits(svm, GHCB_MSR_GPA_VALUE_MASK,
GHCB_MSR_GPA_VALUE_POS);
svm->sev_es.ghcb_registered_gpa = gfn_to_gpa(gfn);
set_ghcb_msr_bits(svm, gfn, GHCB_MSR_GPA_VALUE_MASK,
GHCB_MSR_GPA_VALUE_POS);
set_ghcb_msr_bits(svm, GHCB_MSR_REG_GPA_RESP, GHCB_MSR_INFO_MASK,
GHCB_MSR_INFO_POS);
break;
}
case GHCB_MSR_PSC_REQ:
if (!sev_snp_guest(vcpu->kvm))
goto out_terminate;
ret = snp_begin_psc_msr(svm, control->ghcb_gpa);
break;
case GHCB_MSR_TERM_REQ: {
u64 reason_set, reason_code;
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);
goto out_terminate;
}
default:
break;
}
trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
control->ghcb_gpa, ret);
return ret;
out_terminate:
vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
vcpu->run->system_event.ndata = 1;
vcpu->run->system_event.data[0] = control->ghcb_gpa;
return 0;
}
int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_control_area *control = &svm->vmcb->control;
u64 ghcb_gpa, exit_code;
int ret;
ghcb_gpa = control->ghcb_gpa;
if (ghcb_gpa & GHCB_MSR_INFO_MASK)
return sev_handle_vmgexit_msr_protocol(svm);
if (!ghcb_gpa) {
vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n");
return 1;
}
if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) {
vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
ghcb_gpa);
return 1;
}
svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb);
sev_es_sync_from_ghcb(svm);
if (sev_snp_guest(svm->vcpu.kvm) && !ghcb_gpa_is_registered(svm, ghcb_gpa)) {
vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB GPA [%#llx] is not registered.\n", ghcb_gpa);
return -EINVAL;
}
ret = sev_es_validate_vmgexit(svm);
if (ret)
return ret;
svm_vmgexit_success(svm, 0);
exit_code = kvm_get_cached_sw_exit_code(control);
switch (exit_code) {
case SVM_VMGEXIT_MMIO_READ:
ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
if (ret)
break;
ret = kvm_sev_es_mmio_read(vcpu,
control->exit_info_1,
control->exit_info_2,
svm->sev_es.ghcb_sa);
break;
case SVM_VMGEXIT_MMIO_WRITE:
ret = setup_vmgexit_scratch(svm, false, control->exit_info_2);
if (ret)
break;
ret = kvm_sev_es_mmio_write(vcpu,
control->exit_info_1,
control->exit_info_2,
svm->sev_es.ghcb_sa);
break;
case SVM_VMGEXIT_NMI_COMPLETE:
++vcpu->stat.nmi_window_exits;
svm->nmi_masked = false;
kvm_make_request(KVM_REQ_EVENT, vcpu);
ret = 1;
break;
case SVM_VMGEXIT_AP_HLT_LOOP:
svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NAE_EVENT;
ret = kvm_emulate_ap_reset_hold(vcpu);
break;
case SVM_VMGEXIT_AP_JUMP_TABLE: {
struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
switch (control->exit_info_1) {
case 0:
sev->ap_jump_table = control->exit_info_2;
break;
case 1:
svm_vmgexit_success(svm, sev->ap_jump_table);
break;
default:
pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
control->exit_info_1);
svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_INPUT);
}
ret = 1;
break;
}
case SVM_VMGEXIT_HV_FEATURES:
svm_vmgexit_success(svm, GHCB_HV_FT_SUPPORTED);
ret = 1;
break;
case SVM_VMGEXIT_TERM_REQUEST:
pr_info("SEV-ES guest requested termination: reason %#llx info %#llx\n",
control->exit_info_1, control->exit_info_2);
vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
vcpu->run->system_event.ndata = 1;
vcpu->run->system_event.data[0] = control->ghcb_gpa;
break;
case SVM_VMGEXIT_PSC:
ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
if (ret)
break;
ret = snp_begin_psc(svm, svm->sev_es.ghcb_sa);
break;
case SVM_VMGEXIT_AP_CREATION:
ret = sev_snp_ap_creation(svm);
if (ret) {
svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_INPUT);
}
ret = 1;
break;
case SVM_VMGEXIT_GUEST_REQUEST:
ret = snp_handle_guest_req(svm, control->exit_info_1, control->exit_info_2);
break;
case SVM_VMGEXIT_EXT_GUEST_REQUEST:
ret = snp_handle_ext_guest_req(svm, control->exit_info_1, control->exit_info_2);
break;
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
vcpu_unimpl(vcpu,
"vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
control->exit_info_1, control->exit_info_2);
ret = -EINVAL;
break;
default:
ret = svm_invoke_exit_handler(vcpu, exit_code);
}
return ret;
}
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
{
int count;
int bytes;
int r;
if (svm->vmcb->control.exit_info_2 > INT_MAX)
return -EINVAL;
count = svm->vmcb->control.exit_info_2;
if (unlikely(check_mul_overflow(count, size, &bytes)))
return -EINVAL;
r = setup_vmgexit_scratch(svm, in, bytes);
if (r)
return r;
return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa,
count, in);
}
void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
{
svm_disable_intercept_for_msr(vcpu, MSR_AMD64_SEV_ES_GHCB, MSR_TYPE_RW);
svm_disable_intercept_for_msr(vcpu, MSR_EFER, MSR_TYPE_RW);
svm_disable_intercept_for_msr(vcpu, MSR_IA32_CR_PAT, MSR_TYPE_RW);
if (boot_cpu_has(X86_FEATURE_V_TSC_AUX))
svm_set_intercept_for_msr(vcpu, MSR_TSC_AUX, MSR_TYPE_RW,
!guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) &&
!guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID));
svm_set_intercept_for_msr(vcpu, MSR_AMD64_GUEST_TSC_FREQ, MSR_TYPE_R,
!snp_is_secure_tsc_enabled(vcpu->kvm));
svm_set_intercept_for_msr(vcpu, MSR_IA32_XSS, MSR_TYPE_RW,
!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) ||
!guest_cpuid_has(vcpu, X86_FEATURE_XSAVES));
}
void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
struct kvm_cpuid_entry2 *best;
best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
if (best)
vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
}
static void sev_es_init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
struct vmcb *vmcb = svm->vmcb01.ptr;
svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
if (!svm->sev_es.snp_has_guest_vmsa) {
if (svm->sev_es.vmsa)
svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
else
svm->vmcb->control.vmsa_pa = INVALID_PAGE;
}
if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
VMCB_ALLOWED_SEV_FEATURES_VALID;
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);
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);
vmcb->control.intercepts[INTERCEPT_DR] = 0;
if (!sev_vcpu_has_debug_swap(svm)) {
vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
recalc_intercepts(svm);
} else {
clr_exception_intercept(svm, DB_VECTOR);
}
svm_clr_intercept(svm, INTERCEPT_XSETBV);
if (!init_event)
set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
GHCB_VERSION_MIN,
sev_enc_bit));
}
void sev_init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
clr_exception_intercept(svm, UD_VECTOR);
clr_exception_intercept(svm, GP_VECTOR);
if (init_event && sev_snp_guest(vcpu->kvm))
sev_snp_init_protected_guest_state(vcpu);
if (sev_es_guest(vcpu->kvm))
sev_es_init_vmcb(svm, init_event);
}
int sev_vcpu_create(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct page *vmsa_page;
mutex_init(&svm->sev_es.snp_vmsa_mutex);
if (!sev_es_guest(vcpu->kvm))
return 0;
vmsa_page = snp_safe_alloc_page();
if (!vmsa_page)
return -ENOMEM;
svm->sev_es.vmsa = page_address(vmsa_page);
vcpu->arch.guest_tsc_protected = snp_is_secure_tsc_enabled(vcpu->kvm);
return 0;
}
void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
{
struct kvm *kvm = svm->vcpu.kvm;
hostsa->xcr0 = kvm_host.xcr0;
hostsa->pkru = read_pkru();
hostsa->xss = kvm_host.xss;
if (sev_vcpu_has_debug_swap(svm) ||
(sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3);
}
if (cpu_feature_enabled(X86_FEATURE_V_TSC_AUX) &&
!WARN_ON_ONCE(tsc_aux_uret_slot < 0))
hostsa->tsc_aux = kvm_get_user_return_msr(tsc_aux_uret_slot);
}
void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (!svm->sev_es.received_first_sipi) {
svm->sev_es.received_first_sipi = true;
return;
}
switch (svm->sev_es.ap_reset_hold_type) {
case AP_RESET_HOLD_NAE_EVENT:
svm_vmgexit_success(svm, 1);
break;
case AP_RESET_HOLD_MSR_PROTO:
set_ghcb_msr_bits(svm, 1,
GHCB_MSR_AP_RESET_HOLD_RESULT_MASK,
GHCB_MSR_AP_RESET_HOLD_RESULT_POS);
set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP,
GHCB_MSR_INFO_MASK,
GHCB_MSR_INFO_POS);
break;
default:
break;
}
}
struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
{
unsigned long pfn;
struct page *p;
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return alloc_pages_node(node, gfp | __GFP_ZERO, 0);
p = alloc_pages_node(node, gfp | __GFP_ZERO, 1);
if (!p)
return NULL;
split_page(p, 1);
pfn = page_to_pfn(p);
if (IS_ALIGNED(pfn, PTRS_PER_PMD))
__free_page(p++);
else
__free_page(p + 1);
return p;
}
void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
{
struct kvm_memory_slot *slot;
struct kvm *kvm = vcpu->kvm;
int order, rmp_level, ret;
struct page *page;
bool assigned;
kvm_pfn_t pfn;
gfn_t gfn;
gfn = gpa >> PAGE_SHIFT;
if (!kvm_mem_is_private(kvm, gfn)) {
pr_warn_ratelimited("SEV: Unexpected RMP fault for non-private GPA 0x%llx\n",
gpa);
return;
}
slot = gfn_to_memslot(kvm, gfn);
if (!kvm_slot_has_gmem(slot)) {
pr_warn_ratelimited("SEV: Unexpected RMP fault, non-private slot for GPA 0x%llx\n",
gpa);
return;
}
ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &page, &order);
if (ret) {
pr_warn_ratelimited("SEV: Unexpected RMP fault, no backing page for private GPA 0x%llx\n",
gpa);
return;
}
ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
if (ret || !assigned) {
pr_warn_ratelimited("SEV: Unexpected RMP fault, no assigned RMP entry found for GPA 0x%llx PFN 0x%llx error %d\n",
gpa, pfn, ret);
goto out_no_trace;
}
if (rmp_level == PG_LEVEL_4K)
goto out;
ret = snp_rmptable_psmash(pfn);
if (ret) {
if (!snp_lookup_rmpentry(pfn, &assigned, &rmp_level) &&
assigned && rmp_level == PG_LEVEL_4K)
goto out;
pr_warn_ratelimited("SEV: Unable to split RMP entry for GPA 0x%llx PFN 0x%llx ret %d\n",
gpa, pfn, ret);
}
kvm_zap_gfn_range(kvm, gfn, gfn + PTRS_PER_PMD);
out:
trace_kvm_rmp_fault(vcpu, gpa, pfn, error_code, rmp_level, ret);
out_no_trace:
kvm_release_page_unused(page);
}
static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end)
{
kvm_pfn_t pfn = start;
while (pfn < end) {
int ret, rmp_level;
bool assigned;
ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
if (ret) {
pr_warn_ratelimited("SEV: Failed to retrieve RMP entry: PFN 0x%llx GFN start 0x%llx GFN end 0x%llx RMP level %d error %d\n",
pfn, start, end, rmp_level, ret);
return false;
}
if (assigned) {
pr_debug("%s: overlap detected, PFN 0x%llx start 0x%llx end 0x%llx RMP level %d\n",
__func__, pfn, start, end, rmp_level);
return false;
}
pfn++;
}
return true;
}
static u8 max_level_for_order(int order)
{
if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
return PG_LEVEL_2M;
return PG_LEVEL_4K;
}
static bool is_large_rmp_possible(struct kvm *kvm, kvm_pfn_t pfn, int order)
{
kvm_pfn_t pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
if (max_level_for_order(order) > PG_LEVEL_4K &&
is_pfn_range_shared(pfn_aligned, pfn_aligned + PTRS_PER_PMD))
return true;
return false;
}
int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
{
struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
kvm_pfn_t pfn_aligned;
gfn_t gfn_aligned;
int level, rc;
bool assigned;
if (!sev_snp_guest(kvm))
return 0;
rc = snp_lookup_rmpentry(pfn, &assigned, &level);
if (rc) {
pr_err_ratelimited("SEV: Failed to look up RMP entry: GFN %llx PFN %llx error %d\n",
gfn, pfn, rc);
return -ENOENT;
}
if (assigned) {
pr_debug("%s: already assigned: gfn %llx pfn %llx max_order %d level %d\n",
__func__, gfn, pfn, max_order, level);
return 0;
}
if (is_large_rmp_possible(kvm, pfn, max_order)) {
level = PG_LEVEL_2M;
pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
gfn_aligned = ALIGN_DOWN(gfn, PTRS_PER_PMD);
} else {
level = PG_LEVEL_4K;
pfn_aligned = pfn;
gfn_aligned = gfn;
}
rc = rmp_make_private(pfn_aligned, gfn_to_gpa(gfn_aligned), level, sev->asid, false);
if (rc) {
pr_err_ratelimited("SEV: Failed to update RMP entry: GFN %llx PFN %llx level %d error %d\n",
gfn, pfn, level, rc);
return -EINVAL;
}
pr_debug("%s: updated: gfn %llx pfn %llx pfn_aligned %llx max_order %d level %d\n",
__func__, gfn, pfn, pfn_aligned, max_order, level);
return 0;
}
void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
{
kvm_pfn_t pfn;
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return;
pr_debug("%s: PFN start 0x%llx PFN end 0x%llx\n", __func__, start, end);
for (pfn = start; pfn < end;) {
bool use_2m_update = false;
int rc, rmp_level;
bool assigned;
rc = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
if (rc || !assigned)
goto next_pfn;
use_2m_update = IS_ALIGNED(pfn, PTRS_PER_PMD) &&
end >= (pfn + PTRS_PER_PMD) &&
rmp_level > PG_LEVEL_4K;
if (!use_2m_update && rmp_level > PG_LEVEL_4K) {
rc = snp_rmptable_psmash(pfn);
WARN_ONCE(rc, "SEV: Failed to PSMASH RMP entry for PFN 0x%llx error %d\n",
pfn, rc);
}
rc = rmp_make_shared(pfn, use_2m_update ? PG_LEVEL_2M : PG_LEVEL_4K);
if (WARN_ONCE(rc, "SEV: Failed to update RMP entry for PFN 0x%llx error %d\n",
pfn, rc))
goto next_pfn;
clflush_cache_range(__va(pfn_to_hpa(pfn)),
use_2m_update ? PMD_SIZE : PAGE_SIZE);
next_pfn:
pfn += use_2m_update ? PTRS_PER_PMD : 1;
cond_resched();
}
}
int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private)
{
int level, rc;
bool assigned;
if (!sev_snp_guest(kvm))
return 0;
rc = snp_lookup_rmpentry(pfn, &assigned, &level);
if (rc || !assigned)
return PG_LEVEL_4K;
return level;
}
struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb_save_area *vmsa;
struct kvm_sev_info *sev;
int error = 0;
int ret;
if (!sev_es_guest(vcpu->kvm))
return NULL;
if (!vcpu->arch.guest_state_protected)
return (struct vmcb_save_area *)svm->sev_es.vmsa;
sev = to_kvm_sev_info(vcpu->kvm);
if (sev_snp_guest(vcpu->kvm)) {
if (!(sev->policy & SNP_POLICY_DEBUG))
return NULL;
} else {
if (sev->policy & SEV_POLICY_NODBG)
return NULL;
}
if (sev_snp_guest(vcpu->kvm)) {
struct sev_data_snp_dbg dbg = {0};
vmsa = snp_alloc_firmware_page(__GFP_ZERO);
if (!vmsa)
return NULL;
dbg.gctx_paddr = __psp_pa(sev->snp_context);
dbg.src_addr = svm->vmcb->control.vmsa_pa;
dbg.dst_addr = __psp_pa(vmsa);
ret = sev_do_cmd(SEV_CMD_SNP_DBG_DECRYPT, &dbg, &error);
if (snp_page_reclaim(vcpu->kvm, PHYS_PFN(__pa(vmsa))))
return NULL;
if (ret) {
pr_err("SEV: SNP_DBG_DECRYPT failed ret=%d, fw_error=%d (%#x)\n",
ret, error, error);
free_page((unsigned long)vmsa);
return NULL;
}
} else {
struct sev_data_dbg dbg = {0};
struct page *vmsa_page;
vmsa_page = alloc_page(GFP_KERNEL);
if (!vmsa_page)
return NULL;
vmsa = page_address(vmsa_page);
dbg.handle = sev->handle;
dbg.src_addr = svm->vmcb->control.vmsa_pa;
dbg.dst_addr = __psp_pa(vmsa);
dbg.len = PAGE_SIZE;
ret = sev_do_cmd(SEV_CMD_DBG_DECRYPT, &dbg, &error);
if (ret) {
pr_err("SEV: SEV_CMD_DBG_DECRYPT failed ret=%d, fw_error=%d (0x%x)\n",
ret, error, error);
__free_page(vmsa_page);
return NULL;
}
}
return vmsa;
}
void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa)
{
if (!vcpu->arch.guest_state_protected || !vmsa)
return;
free_page((unsigned long)vmsa);
}
