// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * AMD SVM-SEV support
 *
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 */

#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#include <linux/kernel.h>
#include <linux/highmem.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 <asm/fpu/internal.h>

#include <asm/pkru.h>
#include <asm/trapnr.h>

#include "x86.h"
#include "svm.h"
#include "svm_ops.h"
#include "cpuid.h"
#include "trace.h"

#define __ex(x) __kvm_handle_fault_on_reboot(x)

#ifndef CONFIG_KVM_AMD_SEV
/*
 * When this config is not defined, SEV feature is not supported and APIs in
 * this file are not used but this file still gets compiled into the KVM AMD
 * module.
 *
 * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum
 * misc_res_type {} defined in linux/misc_cgroup.h.
 *
 * Below macros allow compilation to succeed.
 */
#define MISC_CG_RES_SEV MISC_CG_RES_TYPES
#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES
#endif

#ifdef CONFIG_KVM_AMD_SEV
/* enable/disable SEV support */
static bool sev_enabled = true;
module_param_named(sev, sev_enabled, bool, 0444);

/* enable/disable SEV-ES support */
static bool sev_es_enabled = true;
module_param_named(sev_es, sev_es_enabled, bool, 0444);
#else
#define sev_enabled false
#define sev_es_enabled false
#endif /* CONFIG_KVM_AMD_SEV */

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 long sev_me_mask;
static unsigned int nr_asids;
static unsigned long *sev_asid_bitmap;
static unsigned long *sev_reclaim_asid_bitmap;

struct enc_region {
        struct list_head list;
        unsigned long npages;
        struct page **pages;
        unsigned long uaddr;
        unsigned long size;
};

/* Called with the sev_bitmap_lock held, or on shutdown  */
static int sev_flush_asids(int min_asid, int max_asid)
{
        int ret, asid, error = 0;

        /* Check if there are any ASIDs to reclaim before performing a flush */
        asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
        if (asid > max_asid)
                return -EBUSY;

        /*
         * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail,
         * so it must be guarded.
         */
        down_write(&sev_deactivate_lock);

        wbinvd_on_all_cpus();
        ret = sev_guest_df_flush(&error);

        up_write(&sev_deactivate_lock);

        if (ret)
                pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);

        return ret;
}

static inline bool is_mirroring_enc_context(struct kvm *kvm)
{
        return !!to_kvm_svm(kvm)->sev_info.enc_context_owner;
}

/* Must be called with the sev_bitmap_lock held */
static bool __sev_recycle_asids(int min_asid, int max_asid)
{
        if (sev_flush_asids(min_asid, max_asid))
                return false;

        /* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
        bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
                   nr_asids);
        bitmap_zero(sev_reclaim_asid_bitmap, nr_asids);

        return true;
}

static int sev_asid_new(struct kvm_sev_info *sev)
{
        int asid, min_asid, max_asid, ret;
        bool retry = true;
        enum misc_res_type type;

        type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
        WARN_ON(sev->misc_cg);
        sev->misc_cg = get_current_misc_cg();
        ret = misc_cg_try_charge(type, sev->misc_cg, 1);
        if (ret) {
                put_misc_cg(sev->misc_cg);
                sev->misc_cg = NULL;
                return ret;
        }

        mutex_lock(&sev_bitmap_lock);

        /*
         * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
         * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
         */
        min_asid = sev->es_active ? 1 : min_sev_asid;
        max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
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);

        return asid;
e_uncharge:
        misc_cg_uncharge(type, sev->misc_cg, 1);
        put_misc_cg(sev->misc_cg);
        sev->misc_cg = NULL;
        return ret;
}

static int sev_get_asid(struct kvm *kvm)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;

        return sev->asid;
}

static void sev_asid_free(struct kvm_sev_info *sev)
{
        struct svm_cpu_data *sd;
        int cpu;
        enum misc_res_type type;

        mutex_lock(&sev_bitmap_lock);

        __set_bit(sev->asid, sev_reclaim_asid_bitmap);

        for_each_possible_cpu(cpu) {
                sd = per_cpu(svm_data, cpu);
                sd->sev_vmcbs[sev->asid] = NULL;
        }

        mutex_unlock(&sev_bitmap_lock);

        type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
        misc_cg_uncharge(type, sev->misc_cg, 1);
        put_misc_cg(sev->misc_cg);
        sev->misc_cg = NULL;
}

static void sev_decommission(unsigned int handle)
{
        struct sev_data_decommission decommission;

        if (!handle)
                return;

        decommission.handle = handle;
        sev_guest_decommission(&decommission, NULL);
}

static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
{
        struct sev_data_deactivate deactivate;

        if (!handle)
                return;

        deactivate.handle = handle;

        /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */
        down_read(&sev_deactivate_lock);
        sev_guest_deactivate(&deactivate, NULL);
        up_read(&sev_deactivate_lock);

        sev_decommission(handle);
}

static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        bool es_active = argp->id == KVM_SEV_ES_INIT;
        int asid, ret;

        if (kvm->created_vcpus)
                return -EINVAL;

        ret = -EBUSY;
        if (unlikely(sev->active))
                return ret;

        sev->es_active = es_active;
        asid = sev_asid_new(sev);
        if (asid < 0)
                goto e_no_asid;
        sev->asid = asid;

        ret = sev_platform_init(&argp->error);
        if (ret)
                goto e_free;

        sev->active = true;
        sev->asid = asid;
        INIT_LIST_HEAD(&sev->regions_list);

        return 0;

e_free:
        sev_asid_free(sev);
        sev->asid = 0;
e_no_asid:
        sev->es_active = false;
        return ret;
}

static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
{
        struct sev_data_activate activate;
        int asid = sev_get_asid(kvm);
        int ret;

        /* activate ASID on the given handle */
        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)
{
        struct fd f;
        int ret;

        f = fdget(fd);
        if (!f.file)
                return -EBADF;

        ret = sev_issue_cmd_external_user(f.file, id, data, error);

        fdput(f);
        return ret;
}

static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;

        return __sev_issue_cmd(sev->fd, id, data, error);
}

static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_launch_start start;
        struct kvm_sev_launch_start params;
        void *dh_blob, *session_blob;
        int *error = &argp->error;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, (void __user *)(uintptr_t)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;

        /* create memory encryption context */
        ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, &start, error);
        if (ret)
                goto e_free_session;

        /* Bind ASID to this guest */
        ret = sev_bind_asid(kvm, start.handle, error);
        if (ret) {
                sev_decommission(start.handle);
                goto e_free_session;
        }

        /* return handle to userspace */
        params.handle = start.handle;
        if (copy_to_user((void __user *)(uintptr_t)argp->data, &params, sizeof(params))) {
                sev_unbind_asid(kvm, start.handle);
                ret = -EFAULT;
                goto e_free_session;
        }

        sev->handle = start.handle;
        sev->fd = argp->sev_fd;

e_free_session:
        kfree(session_blob);
e_free_dh:
        kfree(dh_blob);
        return ret;
}

static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
                                    unsigned long ulen, unsigned long *n,
                                    int write)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        unsigned long npages, size;
        int npinned;
        unsigned long locked, lock_limit;
        struct page **pages;
        unsigned long first, last;
        int ret;

        lockdep_assert_held(&kvm->lock);

        if (ulen == 0 || uaddr + ulen < uaddr)
                return ERR_PTR(-EINVAL);

        /* Calculate number of pages. */
        first = (uaddr & PAGE_MASK) >> PAGE_SHIFT;
        last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT;
        npages = (last - first + 1);

        locked = sev->pages_locked + npages;
        lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
        if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
                pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit);
                return ERR_PTR(-ENOMEM);
        }

        if (WARN_ON_ONCE(npages > INT_MAX))
                return ERR_PTR(-EINVAL);

        /* Avoid using vmalloc for smaller buffers. */
        size = npages * sizeof(struct page *);
        if (size > PAGE_SIZE)
                pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
        else
                pages = kmalloc(size, GFP_KERNEL_ACCOUNT);

        if (!pages)
                return ERR_PTR(-ENOMEM);

        /* Pin the user virtual address. */
        npinned = pin_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
        if (npinned != npages) {
                pr_err("SEV: Failure locking %lu pages.\n", npages);
                ret = -ENOMEM;
                goto err;
        }

        *n = npages;
        sev->pages_locked = locked;

        return pages;

err:
        if (npinned > 0)
                unpin_user_pages(pages, npinned);

        kvfree(pages);
        return ERR_PTR(ret);
}

static void sev_unpin_memory(struct kvm *kvm, struct page **pages,
                             unsigned long npages)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;

        unpin_user_pages(pages, npages);
        kvfree(pages);
        sev->pages_locked -= npages;
}

static void sev_clflush_pages(struct page *pages[], unsigned long npages)
{
        uint8_t *page_virtual;
        unsigned long i;

        if (this_cpu_has(X86_FEATURE_SME_COHERENT) || npages == 0 ||
            pages == NULL)
                return;

        for (i = 0; i < npages; i++) {
                page_virtual = kmap_atomic(pages[i]);
                clflush_cache_range(page_virtual, PAGE_SIZE);
                kunmap_atomic(page_virtual);
        }
}

static unsigned long get_num_contig_pages(unsigned long idx,
                                struct page **inpages, unsigned long npages)
{
        unsigned long paddr, next_paddr;
        unsigned long i = idx + 1, pages = 1;

        /* find the number of contiguous pages starting from idx */
        paddr = __sme_page_pa(inpages[idx]);
        while (i < npages) {
                next_paddr = __sme_page_pa(inpages[i++]);
                if ((paddr + PAGE_SIZE) == next_paddr) {
                        pages++;
                        paddr = next_paddr;
                        continue;
                }
                break;
        }

        return pages;
}

static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i;
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct kvm_sev_launch_update_data params;
        struct sev_data_launch_update_data data;
        struct page **inpages;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
                return -EFAULT;

        vaddr = params.uaddr;
        size = params.len;
        vaddr_end = vaddr + size;

        /* Lock the user memory. */
        inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1);
        if (IS_ERR(inpages))
                return PTR_ERR(inpages);

        /*
         * Flush (on non-coherent CPUs) before LAUNCH_UPDATE encrypts pages in
         * place; the cache may contain the data that was written unencrypted.
         */
        sev_clflush_pages(inpages, npages);

        data.reserved = 0;
        data.handle = sev->handle;

        for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) {
                int offset, len;

                /*
                 * If the user buffer is not page-aligned, calculate the offset
                 * within the page.
                 */
                offset = vaddr & (PAGE_SIZE - 1);

                /* Calculate the number of pages that can be encrypted in one go. */
                pages = get_num_contig_pages(i, inpages, npages);

                len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size);

                data.len = len;
                data.address = __sme_page_pa(inpages[i]) + offset;
                ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, &data, &argp->error);
                if (ret)
                        goto e_unpin;

                size -= len;
                next_vaddr = vaddr + len;
        }

e_unpin:
        /* content of memory is updated, mark pages dirty */
        for (i = 0; i < npages; i++) {
                set_page_dirty_lock(inpages[i]);
                mark_page_accessed(inpages[i]);
        }
        /* unlock the user pages */
        sev_unpin_memory(kvm, inpages, npages);
        return ret;
}

static int sev_es_sync_vmsa(struct vcpu_svm *svm)
{
        struct vmcb_save_area *save = &svm->vmcb->save;

        /* Check some debug related fields before encrypting the VMSA */
        if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1))
                return -EINVAL;

        /* Sync registgers */
        save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX];
        save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX];
        save->rcx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
        save->rdx = svm->vcpu.arch.regs[VCPU_REGS_RDX];
        save->rsp = svm->vcpu.arch.regs[VCPU_REGS_RSP];
        save->rbp = svm->vcpu.arch.regs[VCPU_REGS_RBP];
        save->rsi = svm->vcpu.arch.regs[VCPU_REGS_RSI];
        save->rdi = svm->vcpu.arch.regs[VCPU_REGS_RDI];
#ifdef CONFIG_X86_64
        save->r8  = svm->vcpu.arch.regs[VCPU_REGS_R8];
        save->r9  = svm->vcpu.arch.regs[VCPU_REGS_R9];
        save->r10 = svm->vcpu.arch.regs[VCPU_REGS_R10];
        save->r11 = svm->vcpu.arch.regs[VCPU_REGS_R11];
        save->r12 = svm->vcpu.arch.regs[VCPU_REGS_R12];
        save->r13 = svm->vcpu.arch.regs[VCPU_REGS_R13];
        save->r14 = svm->vcpu.arch.regs[VCPU_REGS_R14];
        save->r15 = svm->vcpu.arch.regs[VCPU_REGS_R15];
#endif
        save->rip = svm->vcpu.arch.regs[VCPU_REGS_RIP];

        /* Sync some non-GPR registers before encrypting */
        save->xcr0 = svm->vcpu.arch.xcr0;
        save->pkru = svm->vcpu.arch.pkru;
        save->xss  = svm->vcpu.arch.ia32_xss;

        /*
         * SEV-ES will use a VMSA that is pointed to by the VMCB, not
         * the traditional VMSA that is part of the VMCB. Copy the
         * traditional VMSA as it has been built so far (in prep
         * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
         */
        memcpy(svm->vmsa, save, sizeof(*save));

        return 0;
}

static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_launch_update_vmsa vmsa;
        struct kvm_vcpu *vcpu;
        int i, ret;

        if (!sev_es_guest(kvm))
                return -ENOTTY;

        vmsa.reserved = 0;

        kvm_for_each_vcpu(i, vcpu, kvm) {
                struct vcpu_svm *svm = to_svm(vcpu);

                /* Perform some pre-encryption checks against the VMSA */
                ret = sev_es_sync_vmsa(svm);
                if (ret)
                        return ret;

                /*
                 * The LAUNCH_UPDATE_VMSA command will perform in-place
                 * encryption of the VMSA memory content (i.e it will write
                 * the same memory region with the guest's key), so invalidate
                 * it first.
                 */
                clflush_cache_range(svm->vmsa, PAGE_SIZE);

                vmsa.handle = sev->handle;
                vmsa.address = __sme_pa(svm->vmsa);
                vmsa.len = PAGE_SIZE;
                ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa,
                                    &argp->error);
                if (ret)
                        return ret;

                svm->vcpu.arch.guest_state_protected = true;
        }

        return 0;
}

static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        void __user *measure = (void __user *)(uintptr_t)argp->data;
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_launch_measure data;
        struct kvm_sev_launch_measure params;
        void __user *p = NULL;
        void *blob = NULL;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, measure, sizeof(params)))
                return -EFAULT;

        memset(&data, 0, sizeof(data));

        /* User wants to query the blob length */
        if (!params.len)
                goto cmd;

        p = (void __user *)(uintptr_t)params.uaddr;
        if (p) {
                if (params.len > SEV_FW_BLOB_MAX_SIZE)
                        return -EINVAL;

                blob = kmalloc(params.len, GFP_KERNEL_ACCOUNT);
                if (!blob)
                        return -ENOMEM;

                data.address = __psp_pa(blob);
                data.len = params.len;
        }

cmd:
        data.handle = sev->handle;
        ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, &data, &argp->error);

        /*
         * If we query the session length, FW responded with expected data.
         */
        if (!params.len)
                goto done;

        if (ret)
                goto e_free_blob;

        if (blob) {
                if (copy_to_user(p, blob, params.len))
                        ret = -EFAULT;
        }

done:
        params.len = data.len;
        if (copy_to_user(measure, &params, 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 kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_launch_finish data;

        if (!sev_guest(kvm))
                return -ENOTTY;

        data.handle = sev->handle;
        return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, &data, &argp->error);
}

static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct kvm_sev_guest_status params;
        struct sev_data_guest_status data;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        memset(&data, 0, sizeof(data));

        data.handle = sev->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((void __user *)(uintptr_t)argp->data, &params, 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 kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_dbg data;

        data.reserved = 0;
        data.handle = sev->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;

        /*
         * Its safe to read more than we are asked, caller should ensure that
         * destination has enough space.
         */
        offset = src_paddr & 15;
        src_paddr = round_down(src_paddr, 16);
        sz = round_up(sz + offset, 16);

        return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
}

static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr,
                                  void __user *dst_uaddr,
                                  unsigned long dst_paddr,
                                  int size, int *err)
{
        struct page *tpage = NULL;
        int ret, offset;

        /* if inputs are not 16-byte then use intermediate buffer */
        if (!IS_ALIGNED(dst_paddr, 16) ||
            !IS_ALIGNED(paddr,     16) ||
            !IS_ALIGNED(size,      16)) {
                tpage = (void *)alloc_page(GFP_KERNEL);
                if (!tpage)
                        return -ENOMEM;

                dst_paddr = __sme_page_pa(tpage);
        }

        ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err);
        if (ret)
                goto e_free;

        if (tpage) {
                offset = paddr & 15;
                if (copy_to_user(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 source buffer is not aligned then use an intermediate buffer */
        if (!IS_ALIGNED((unsigned long)vaddr, 16)) {
                src_tpage = alloc_page(GFP_KERNEL);
                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 destination buffer or length is not aligned then do read-modify-write:
         *   - decrypt destination in an intermediate buffer
         *   - copy the source buffer in an intermediate buffer
         *   - use the intermediate buffer as source buffer
         */
        if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) {
                int dst_offset;

                dst_tpage = alloc_page(GFP_KERNEL);
                if (!dst_tpage) {
                        ret = -ENOMEM;
                        goto e_free;
                }

                ret = __sev_dbg_decrypt(kvm, dst_paddr,
                                        __sme_page_pa(dst_tpage), size, error);
                if (ret)
                        goto e_free;

                /*
                 *  If source is kernel buffer then use memcpy() otherwise
                 *  copy_from_user().
                 */
                dst_offset = dst_paddr & 15;

                if (src_tpage)
                        memcpy(page_address(dst_tpage) + dst_offset,
                               page_address(src_tpage), size);
                else {
                        if (copy_from_user(page_address(dst_tpage) + dst_offset,
                                           vaddr, size)) {
                                ret = -EFAULT;
                                goto e_free;
                        }
                }

                paddr = __sme_page_pa(dst_tpage);
                dst_paddr = round_down(dst_paddr, 16);
                len = round_up(size, 16);
        }

        ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true);

e_free:
        if (src_tpage)
                __free_page(src_tpage);
        if (dst_tpage)
                __free_page(dst_tpage);
        return ret;
}

static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
{
        unsigned long vaddr, vaddr_end, next_vaddr;
        unsigned long dst_vaddr;
        struct page **src_p, **dst_p;
        struct kvm_sev_dbg debug;
        unsigned long n;
        unsigned int size;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
                return -EFAULT;

        if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr)
                return -EINVAL;
        if (!debug.dst_uaddr)
                return -EINVAL;

        vaddr = debug.src_uaddr;
        size = debug.len;
        vaddr_end = vaddr + size;
        dst_vaddr = debug.dst_uaddr;

        for (; vaddr < vaddr_end; vaddr = next_vaddr) {
                int len, s_off, d_off;

                /* lock userspace source and destination page */
                src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0);
                if (IS_ERR(src_p))
                        return PTR_ERR(src_p);

                dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1);
                if (IS_ERR(dst_p)) {
                        sev_unpin_memory(kvm, src_p, n);
                        return PTR_ERR(dst_p);
                }

                /*
                 * Flush (on non-coherent CPUs) before DBG_{DE,EN}CRYPT read or modify
                 * the pages; flush the destination too so that future accesses do not
                 * see stale data.
                 */
                sev_clflush_pages(src_p, 1);
                sev_clflush_pages(dst_p, 1);

                /*
                 * Since user buffer may not be page aligned, calculate the
                 * offset within the page.
                 */
                s_off = vaddr & ~PAGE_MASK;
                d_off = dst_vaddr & ~PAGE_MASK;
                len = min_t(size_t, (PAGE_SIZE - s_off), size);

                if (dec)
                        ret = __sev_dbg_decrypt_user(kvm,
                                                     __sme_page_pa(src_p[0]) + s_off,
                                                     (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 kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_launch_secret data;
        struct kvm_sev_launch_secret params;
        struct page **pages;
        void *blob, *hdr;
        unsigned long n, i;
        int ret, offset;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
                return -EFAULT;

        pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1);
        if (IS_ERR(pages))
                return PTR_ERR(pages);

        /*
         * Flush (on non-coherent CPUs) before LAUNCH_SECRET encrypts pages in
         * place; the cache may contain the data that was written unencrypted.
         */
        sev_clflush_pages(pages, n);

        /*
         * The secret must be copied into contiguous memory region, lets verify
         * that userspace memory pages are contiguous before we issue command.

         */
        if (get_num_contig_pages(0, pages, n) != n) {
                ret = -EINVAL;
                goto e_unpin_memory;
        }

        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 = sev->handle;
        ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, &data, &argp->error);

        kfree(hdr);

e_free_blob:
        kfree(blob);
e_unpin_memory:
        /* content of memory is updated, mark pages dirty */
        for (i = 0; i < n; i++) {
                set_page_dirty_lock(pages[i]);
                mark_page_accessed(pages[i]);
        }
        sev_unpin_memory(kvm, pages, n);
        return ret;
}

static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        void __user *report = (void __user *)(uintptr_t)argp->data;
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_attestation_report data;
        struct kvm_sev_attestation_report params;
        void __user *p;
        void *blob = NULL;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
                return -EFAULT;

        memset(&data, 0, sizeof(data));

        /* User wants to query the blob length */
        if (!params.len)
                goto cmd;

        p = (void __user *)(uintptr_t)params.uaddr;
        if (p) {
                if (params.len > SEV_FW_BLOB_MAX_SIZE)
                        return -EINVAL;

                blob = kmalloc(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 = sev->handle;
        ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, &data, &argp->error);
        /*
         * If we query the session length, FW responded with expected data.
         */
        if (!params.len)
                goto done;

        if (ret)
                goto e_free_blob;

        if (blob) {
                if (copy_to_user(p, blob, params.len))
                        ret = -EFAULT;
        }

done:
        params.len = data.len;
        if (copy_to_user(report, &params, sizeof(params)))
                ret = -EFAULT;
e_free_blob:
        kfree(blob);
        return ret;
}

/* Userspace wants to query session length. */
static int
__sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp,
                                      struct kvm_sev_send_start *params)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_send_start data;
        int ret;

        memset(&data, 0, sizeof(data));
        data.handle = sev->handle;
        ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);

        params->session_len = data.session_len;
        if (copy_to_user((void __user *)(uintptr_t)argp->data, params,
                                sizeof(struct kvm_sev_send_start)))
                ret = -EFAULT;

        return ret;
}

static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_send_start data;
        struct kvm_sev_send_start params;
        void *amd_certs, *session_data;
        void *pdh_cert, *plat_certs;
        int ret;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
                                sizeof(struct kvm_sev_send_start)))
                return -EFAULT;

        /* if session_len is zero, userspace wants to query the session length */
        if (!params.session_len)
                return __sev_send_start_query_session_length(kvm, argp,
                                &params);

        /* some sanity checks */
        if (!params.pdh_cert_uaddr || !params.pdh_cert_len ||
            !params.session_uaddr || params.session_len > SEV_FW_BLOB_MAX_SIZE)
                return -EINVAL;

        /* allocate the memory to hold the session data blob */
        session_data = kmalloc(params.session_len, GFP_KERNEL_ACCOUNT);
        if (!session_data)
                return -ENOMEM;

        /* copy the certificate blobs from userspace */
        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;
        }

        /* populate the FW SEND_START field with system physical address */
        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 = sev->handle;

        ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);

        if (!ret && copy_to_user((void __user *)(uintptr_t)params.session_uaddr,
                        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((void __user *)(uintptr_t)argp->data, &params,
                                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;
}

/* Userspace wants to query either header or trans length. */
static int
__sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp,
                                     struct kvm_sev_send_update_data *params)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_send_update_data data;
        int ret;

        memset(&data, 0, sizeof(data));
        data.handle = sev->handle;
        ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error);

        params->hdr_len = data.hdr_len;
        params->trans_len = data.trans_len;

        if (copy_to_user((void __user *)(uintptr_t)argp->data, params,
                         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 kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_send_update_data data;
        struct kvm_sev_send_update_data params;
        void *hdr, *trans_data;
        struct page **guest_page;
        unsigned long n;
        int ret, offset;

        if (!sev_guest(kvm))
                return -ENOTTY;

        if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
                        sizeof(struct kvm_sev_send_update_data)))
                return -EFAULT;

        /* userspace wants to query either header or trans length */
        if (!params.trans_len || !params.hdr_len)
                return __sev_send_update_data_query_lengths(kvm, argp, &params);

        if (!params.trans_uaddr || !params.guest_uaddr ||
            !params.guest_len || !params.hdr_uaddr)
                return -EINVAL;

        /* Check if we are crossing the page boundary */
        offset = params.guest_uaddr & (PAGE_SIZE - 1);
        if ((params.guest_len + offset > PAGE_SIZE))
                return -EINVAL;

        /* Pin guest memory */
        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);

        /* allocate memory for header and transport buffer */
        ret = -ENOMEM;
        hdr = kmalloc(params.hdr_len, GFP_KERNEL_ACCOUNT);
        if (!hdr)
                goto e_unpin;

        trans_data = kmalloc(params.trans_len, GFP_KERNEL_ACCOUNT);
        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;

        /* The SEND_UPDATE_DATA command requires C-bit to be always set. */
        data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
        data.guest_address |= sev_me_mask;
        data.guest_len = params.guest_len;
        data.handle = sev->handle;

        ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error);

        if (ret)
                goto e_free_trans_data;

        /* copy transport buffer to user space */
        if (copy_to_user((void __user *)(uintptr_t)params.trans_uaddr,
                         trans_data, params.trans_len)) {
                ret = -EFAULT;
                goto e_free_trans_data;
        }

        /* Copy packet header to userspace. */
        if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
                         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 kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_send_finish data;

        if (!sev_guest(kvm))
                return -ENOTTY;

        data.handle = sev->handle;
        return sev_issue_cmd(kvm, SEV_CMD_SEND_FINISH, &data, &argp->error);
}

static int sev_send_cancel(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_send_cancel data;

        if (!sev_guest(kvm))
                return -ENOTTY;

        data.handle = sev->handle;
        return sev_issue_cmd(kvm, SEV_CMD_SEND_CANCEL, &data, &argp->error);
}

static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct 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;

        /* Get parameter from the userspace */
        if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
                        sizeof(struct kvm_sev_receive_start)))
                return -EFAULT;

        /* some sanity checks */
        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;

        /* create memory encryption context */
        ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_RECEIVE_START, &start,
                                error);
        if (ret)
                goto e_free_session;

        /* Bind ASID to this guest */
        ret = sev_bind_asid(kvm, start.handle, error);
        if (ret)
                goto e_free_session;

        params.handle = start.handle;
        if (copy_to_user((void __user *)(uintptr_t)argp->data,
                         &params, 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_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct kvm_sev_receive_update_data params;
        struct sev_data_receive_update_data data;
        void *hdr = NULL, *trans = NULL;
        struct page **guest_page;
        unsigned long n;
        int ret, offset;

        if (!sev_guest(kvm))
                return -EINVAL;

        if (copy_from_user(&params, (void __user *)(uintptr_t)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;

        /* Check if we are crossing the page boundary */
        offset = params.guest_uaddr & (PAGE_SIZE - 1);
        if ((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;

        /* Pin guest memory */
        guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
                                    PAGE_SIZE, &n, 0);
        if (IS_ERR(guest_page)) {
                ret = PTR_ERR(guest_page);
                goto e_free_trans;
        }

        /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
        data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
        data.guest_address |= sev_me_mask;
        data.guest_len = params.guest_len;
        data.handle = sev->handle;

        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 kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct sev_data_receive_finish data;

        if (!sev_guest(kvm))
                return -ENOTTY;

        data.handle = sev->handle;
        return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
}

int svm_mem_enc_op(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);

        /* enc_context_owner handles all memory enc operations */
        if (is_mirroring_enc_context(kvm)) {
                r = -EINVAL;
                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_LAUNCH_START:
                r = sev_launch_start(kvm, &sev_cmd);
                break;
        case KVM_SEV_LAUNCH_UPDATE_DATA:
                r = sev_launch_update_data(kvm, &sev_cmd);
                break;
        case KVM_SEV_LAUNCH_UPDATE_VMSA:
                r = sev_launch_update_vmsa(kvm, &sev_cmd);
                break;
        case KVM_SEV_LAUNCH_MEASURE:
                r = sev_launch_measure(kvm, &sev_cmd);
                break;
        case KVM_SEV_LAUNCH_FINISH:
                r = sev_launch_finish(kvm, &sev_cmd);
                break;
        case KVM_SEV_GUEST_STATUS:
                r = sev_guest_status(kvm, &sev_cmd);
                break;
        case KVM_SEV_DBG_DECRYPT:
                r = sev_dbg_crypt(kvm, &sev_cmd, true);
                break;
        case KVM_SEV_DBG_ENCRYPT:
                r = sev_dbg_crypt(kvm, &sev_cmd, false);
                break;
        case KVM_SEV_LAUNCH_SECRET:
                r = sev_launch_secret(kvm, &sev_cmd);
                break;
        case KVM_SEV_GET_ATTESTATION_REPORT:
                r = sev_get_attestation_report(kvm, &sev_cmd);
                break;
        case KVM_SEV_SEND_START:
                r = sev_send_start(kvm, &sev_cmd);
                break;
        case KVM_SEV_SEND_UPDATE_DATA:
                r = sev_send_update_data(kvm, &sev_cmd);
                break;
        case KVM_SEV_SEND_FINISH:
                r = sev_send_finish(kvm, &sev_cmd);
                break;
        case KVM_SEV_SEND_CANCEL:
                r = sev_send_cancel(kvm, &sev_cmd);
                break;
        case KVM_SEV_RECEIVE_START:
                r = sev_receive_start(kvm, &sev_cmd);
                break;
        case KVM_SEV_RECEIVE_UPDATE_DATA:
                r = sev_receive_update_data(kvm, &sev_cmd);
                break;
        case KVM_SEV_RECEIVE_FINISH:
                r = sev_receive_finish(kvm, &sev_cmd);
                break;
        default:
                r = -EINVAL;
                goto out;
        }

        if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd)))
                r = -EFAULT;

out:
        mutex_unlock(&kvm->lock);
        return r;
}

int svm_register_enc_region(struct kvm *kvm,
                            struct kvm_enc_region *range)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct enc_region *region;
        int ret = 0;

        if (!sev_guest(kvm))
                return -ENOTTY;

        /* If kvm is mirroring encryption context it isn't responsible for it */
        if (is_mirroring_enc_context(kvm))
                return -EINVAL;

        if (range->addr > ULONG_MAX || range->size > ULONG_MAX)
                return -EINVAL;

        region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT);
        if (!region)
                return -ENOMEM;

        mutex_lock(&kvm->lock);
        region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages, 1);
        if (IS_ERR(region->pages)) {
                ret = PTR_ERR(region->pages);
                mutex_unlock(&kvm->lock);
                goto e_free;
        }

        region->uaddr = range->addr;
        region->size = range->size;

        list_add_tail(&region->list, &sev->regions_list);
        mutex_unlock(&kvm->lock);

        /*
         * The guest may change the memory encryption attribute from C=0 -> C=1
         * or vice versa for this memory range. Lets make sure caches are
         * flushed to ensure that guest data gets written into memory with
         * correct C-bit.
         */
        sev_clflush_pages(region->pages, region->npages);

        return ret;

e_free:
        kfree(region);
        return ret;
}

static struct enc_region *
find_enc_region(struct kvm *kvm, struct kvm_enc_region *range)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct list_head *head = &sev->regions_list;
        struct enc_region *i;

        list_for_each_entry(i, head, list) {
                if (i->uaddr == range->addr &&
                    i->size == range->size)
                        return i;
        }

        return NULL;
}

static void __unregister_enc_region_locked(struct kvm *kvm,
                                           struct enc_region *region)
{
        sev_unpin_memory(kvm, region->pages, region->npages);
        list_del(&region->list);
        kfree(region);
}

int svm_unregister_enc_region(struct kvm *kvm,
                              struct kvm_enc_region *range)
{
        struct enc_region *region;
        int ret;

        /* If kvm is mirroring encryption context it isn't responsible for it */
        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;
        }

        /*
         * Ensure that all guest tagged cache entries are flushed before
         * releasing the pages back to the system for use. CLFLUSH will
         * not do this, so issue a WBINVD.
         */
        wbinvd_on_all_cpus();

        __unregister_enc_region_locked(kvm, region);

        mutex_unlock(&kvm->lock);
        return 0;

failed:
        mutex_unlock(&kvm->lock);
        return ret;
}

int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
{
        struct file *source_kvm_file;
        struct kvm *source_kvm;
        struct kvm_sev_info *mirror_sev;
        unsigned int asid;
        int ret;

        source_kvm_file = fget(source_fd);
        if (!file_is_kvm(source_kvm_file)) {
                ret = -EBADF;
                goto e_source_put;
        }

        source_kvm = source_kvm_file->private_data;
        mutex_lock(&source_kvm->lock);

        if (!sev_guest(source_kvm)) {
                ret = -EINVAL;
                goto e_source_unlock;
        }

        /* Mirrors of mirrors should work, but let's not get silly */
        if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) {
                ret = -EINVAL;
                goto e_source_unlock;
        }

        asid = to_kvm_svm(source_kvm)->sev_info.asid;

        /*
         * The mirror kvm holds an enc_context_owner ref so its asid can't
         * disappear until we're done with it
         */
        kvm_get_kvm(source_kvm);

        fput(source_kvm_file);
        mutex_unlock(&source_kvm->lock);
        mutex_lock(&kvm->lock);

        if (sev_guest(kvm)) {
                ret = -EINVAL;
                goto e_mirror_unlock;
        }

        /* Set enc_context_owner and copy its encryption context over */
        mirror_sev = &to_kvm_svm(kvm)->sev_info;
        mirror_sev->enc_context_owner = source_kvm;
        mirror_sev->asid = asid;
        mirror_sev->active = true;

        mutex_unlock(&kvm->lock);
        return 0;

e_mirror_unlock:
        mutex_unlock(&kvm->lock);
        kvm_put_kvm(source_kvm);
        return ret;
e_source_unlock:
        mutex_unlock(&source_kvm->lock);
e_source_put:
        if (source_kvm_file)
                fput(source_kvm_file);
        return ret;
}

void sev_vm_destroy(struct kvm *kvm)
{
        struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
        struct list_head *head = &sev->regions_list;
        struct list_head *pos, *q;

        if (!sev_guest(kvm))
                return;

        /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
        if (is_mirroring_enc_context(kvm)) {
                kvm_put_kvm(sev->enc_context_owner);
                return;
        }

        mutex_lock(&kvm->lock);

        /*
         * Ensure that all guest tagged cache entries are flushed before
         * releasing the pages back to the system for use. CLFLUSH will
         * not do this, so issue a WBINVD.
         */
        wbinvd_on_all_cpus();

        /*
         * if userspace was terminated before unregistering the memory regions
         * then lets unpin all the registered memory.
         */
        if (!list_empty(head)) {
                list_for_each_safe(pos, q, head) {
                        __unregister_enc_region_locked(kvm,
                                list_entry(pos, struct enc_region, list));
                        cond_resched();
                }
        }

        mutex_unlock(&kvm->lock);

        sev_unbind_asid(kvm, sev->handle);
        sev_asid_free(sev);
}

void __init sev_set_cpu_caps(void)
{
        if (!sev_enabled)
                kvm_cpu_cap_clear(X86_FEATURE_SEV);
        if (!sev_es_enabled)
                kvm_cpu_cap_clear(X86_FEATURE_SEV_ES);
}

void __init sev_hardware_setup(void)
{
#ifdef CONFIG_KVM_AMD_SEV
        unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
        bool sev_es_supported = false;
        bool sev_supported = false;

        if (!sev_enabled || !npt_enabled)
                goto out;

        /* Does the CPU support SEV? */
        if (!boot_cpu_has(X86_FEATURE_SEV))
                goto out;

        /* Retrieve SEV CPUID information */
        cpuid(0x8000001f, &eax, &ebx, &ecx, &edx);

        /* Set encryption bit location for SEV-ES guests */
        sev_enc_bit = ebx & 0x3f;

        /* Maximum number of encrypted guests supported simultaneously */
        max_sev_asid = ecx;
        if (!max_sev_asid)
                goto out;

        /* Minimum ASID value that should be used for SEV guest */
        min_sev_asid = edx;
        sev_me_mask = 1UL << (ebx & 0x3f);

        /*
         * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap,
         * even though it's never used, so that the bitmap is indexed by the
         * actual ASID.
         */
        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;
        }

        sev_asid_count = max_sev_asid - min_sev_asid + 1;
        if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count))
                goto out;

        pr_info("SEV supported: %u ASIDs\n", sev_asid_count);
        sev_supported = true;

        /* SEV-ES support requested? */
        if (!sev_es_enabled)
                goto out;

        /* Does the CPU support SEV-ES? */
        if (!boot_cpu_has(X86_FEATURE_SEV_ES))
                goto out;

        /* Has the system been allocated ASIDs for SEV-ES? */
        if (min_sev_asid == 1)
                goto out;

        sev_es_asid_count = min_sev_asid - 1;
        if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count))
                goto out;

        pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count);
        sev_es_supported = true;

out:
        sev_enabled = sev_supported;
        sev_es_enabled = sev_es_supported;
#endif
}

void sev_hardware_teardown(void)
{
        if (!sev_enabled)
                return;

        /* No need to take sev_bitmap_lock, all VMs have been destroyed. */
        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);
}

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;
}

/*
 * Pages used by hardware to hold guest encrypted state must be flushed before
 * returning them to the system.
 */
static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va,
                                   unsigned long len)
{
        /*
         * If hardware enforced cache coherency for encrypted mappings of the
         * same physical page is supported, nothing to do.
         */
        if (boot_cpu_has(X86_FEATURE_SME_COHERENT))
                return;

        /*
         * If the VM Page Flush MSR is supported, use it to flush the page
         * (using the page virtual address and the guest ASID).
         */
        if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) {
                struct kvm_sev_info *sev;
                unsigned long va_start;
                u64 start, stop;

                /* Align start and stop to page boundaries. */
                va_start = (unsigned long)va;
                start = (u64)va_start & PAGE_MASK;
                stop = PAGE_ALIGN((u64)va_start + len);

                if (start < stop) {
                        sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;

                        while (start < stop) {
                                wrmsrl(MSR_AMD64_VM_PAGE_FLUSH,
                                       start | sev->asid);

                                start += PAGE_SIZE;
                        }

                        return;
                }

                WARN(1, "Address overflow, using WBINVD\n");
        }

        /*
         * Hardware should always have one of the above features,
         * but if not, use WBINVD and issue a warning.
         */
        WARN_ONCE(1, "Using WBINVD to flush guest memory\n");
        wbinvd_on_all_cpus();
}

void sev_free_vcpu(struct kvm_vcpu *vcpu)
{
        struct vcpu_svm *svm;

        if (!sev_es_guest(vcpu->kvm))
                return;

        svm = to_svm(vcpu);

        if (vcpu->arch.guest_state_protected)
                sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE);
        __free_page(virt_to_page(svm->vmsa));