arch/x86/kvm/svm/sev.c

// 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/processor.h>

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

static int sev_flush_asids(void);
static DECLARE_RWSEM(sev_deactivate_lock);
static DEFINE_MUTEX(sev_bitmap_lock);
unsigned int max_sev_asid;
static unsigned int min_sev_asid;
static unsigned long *sev_asid_bitmap;
static unsigned long *sev_reclaim_asid_bitmap;
#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)

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

static int sev_flush_asids(void)
{
	int ret, error = 0;

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

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

	up_write(&sev_deactivate_lock);

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

	return ret;
}

/* Must be called with the sev_bitmap_lock held */
static bool __sev_recycle_asids(void)
{
	int pos;

	/* Check if there are any ASIDs to reclaim before performing a flush */
	pos = find_next_bit(sev_reclaim_asid_bitmap,
			    max_sev_asid, min_sev_asid - 1);
	if (pos >= max_sev_asid)
		return false;

	if (sev_flush_asids())
		return false;

	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
		   max_sev_asid);
	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);

	return true;
}

static int sev_asid_new(void)
{
	bool retry = true;
	int pos;

	mutex_lock(&sev_bitmap_lock);

	/*
	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
	 */
again:
	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
	if (pos >= max_sev_asid) {
		if (retry && __sev_recycle_asids()) {
			retry = false;
			goto again;
		}
		mutex_unlock(&sev_bitmap_lock);
		return -EBUSY;
	}

	__set_bit(pos, sev_asid_bitmap);

	mutex_unlock(&sev_bitmap_lock);

	return pos + 1;
}

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(int asid)
{
	struct svm_cpu_data *sd;
	int cpu, pos;

	mutex_lock(&sev_bitmap_lock);

	pos = asid - 1;
	__set_bit(pos, sev_reclaim_asid_bitmap);

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

	mutex_unlock(&sev_bitmap_lock);
}

static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
{
	struct sev_data_decommission *decommission;
	struct sev_data_deactivate *data;

	if (!handle)
		return;

	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		return;

	/* deactivate handle */
	data->handle = handle;

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

	kfree(data);

	decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
	if (!decommission)
		return;

	/* decommission handle */
	decommission->handle = handle;
	sev_guest_decommission(decommission, NULL);

	kfree(decommission);
}

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

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

	asid = sev_asid_new();
	if (asid < 0)
		return ret;

	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(asid);
	return ret;
}

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

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

	/* activate ASID on the given handle */
	data->handle = handle;
	data->asid   = asid;
	ret = sev_guest_activate(data, error);
	kfree(data);

	return ret;
}

static int __sev_issue_cmd(int fd, int id, void *data, int *error)
{
	struct fd f;
	int ret;

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

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

	fdput(f);
	return ret;
}

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

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

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

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

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

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

	dh_blob = NULL;
	if (params.dh_uaddr) {
		dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len);
		if (IS_ERR(dh_blob)) {
			ret = PTR_ERR(dh_blob);
			goto e_free;
		}

		start->dh_cert_address = __sme_set(__pa(dh_blob));
		start->dh_cert_len = params.dh_len;
	}

	session_blob = NULL;
	if (params.session_uaddr) {
		session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len);
		if (IS_ERR(session_blob)) {
			ret = PTR_ERR(session_blob);
			goto e_free_dh;
		}

		start->session_address = __sme_set(__pa(session_blob));
		start->session_len = params.session_len;
	}

	start->handle = params.handle;
	start->policy = params.policy;

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

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

	/* return handle to userspace */
	params.handle = start->handle;
	if (copy_to_user((void __user *)(uintptr_t)argp->data, &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);
e_free:
	kfree(start);
	return ret;
}

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

	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;

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

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

	/* Lock the user memory. */
	inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1);
	if (IS_ERR(inpages)) {
		ret = PTR_ERR(inpages);
		goto e_free;
	}

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

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

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

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

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

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

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

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

static int sev_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;

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

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

	p = (void __user *)(uintptr_t)params.uaddr;
	if (p) {
		if (params.len > SEV_FW_BLOB_MAX_SIZE) {
			ret = -EINVAL;
			goto e_free;
		}

		ret = -ENOMEM;
		blob = kmalloc(params.len, GFP_KERNEL);
		if (!blob)
			goto e_free;

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

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

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

	if (ret)
		goto e_free_blob;

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

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

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

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

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

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

	kfree(data);
	return ret;
}

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

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

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

	data->handle = sev->handle;
	ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error);
	if (ret)
		goto e_free;

	params.policy = data->policy;
	params.state = data->state;
	params.handle = data->handle;

	if (copy_to_user((void __user *)(uintptr_t)argp->data, &params, sizeof(params)))
		ret = -EFAULT;
e_free:
	kfree(data);
	return ret;
}

static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src,
			       unsigned long dst, int size,
			       int *error, bool enc)
{
	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
	struct sev_data_dbg *data;
	int ret;

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

	data->handle = sev->handle;
	data->dst_addr = dst;
	data->src_addr = src;
	data->len = size;

	ret = sev_issue_cmd(kvm,
			    enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT,
			    data, error);
	kfree(data);
	return ret;
}

static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
			     unsigned long dst_paddr, int sz, int *err)
{
	int offset;

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

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

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

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

		dst_paddr = __sme_page_pa(tpage);
	}

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

	if (tpage) {
		offset = paddr & 15;
		if (copy_to_user((void __user *)(uintptr_t)dst_uaddr,
				 page_address(tpage) + offset, size))
			ret = -EFAULT;
	}

e_free:
	if (tpage)
		__free_page(tpage);

	return ret;
}

static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr,
				  unsigned long __user vaddr,
				  unsigned long dst_paddr,
				  unsigned long __user dst_vaddr,
				  int size, int *error)
{
	struct page *src_tpage = NULL;
	struct page *dst_tpage = NULL;
	int ret, len = size;

	/* If source buffer is not aligned then use an intermediate buffer */
	if (!IS_ALIGNED(vaddr, 16)) {
		src_tpage = alloc_page(GFP_KERNEL);
		if (!src_tpage)
			return -ENOMEM;

		if (copy_from_user(page_address(src_tpage),
				(void __user *)(uintptr_t)vaddr, size)) {
			__free_page(src_tpage);
			return -EFAULT;
		}

		paddr = __sme_page_pa(src_tpage);
	}

	/*
	 *  If destination buffer or length is not aligned then do read-modify-write:
	 *   - decrypt destination in an intermediate buffer
	 *   - copy the source buffer in an intermediate buffer
	 *   - use the intermediate buffer as source buffer
	 */
	if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) {
		int dst_offset;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

		if (dec)
			ret = __sev_dbg_decrypt_user(kvm,
						     __sme_page_pa(src_p[0]) + s_off,
						     dst_vaddr,
						     __sme_page_pa(dst_p[0]) + d_off,
						     len, &argp->error);
		else
			ret = __sev_dbg_encrypt_user(kvm,
						     __sme_page_pa(src_p[0]) + s_off,
						     vaddr,
						     __sme_page_pa(dst_p[0]) + d_off,
						     dst_vaddr,
						     len, &argp->error);

		sev_unpin_memory(kvm, src_p, n);
		sev_unpin_memory(kvm, dst_p, n);

		if (ret)
			goto err;

		next_vaddr = vaddr + len;
		dst_vaddr = dst_vaddr + len;
		size -= len;
	}
err:
	return ret;
}

static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
	struct sev_data_launch_secret *data;
	struct kvm_sev_launch_secret params;
	struct page **pages;
	void *blob, *hdr;
	unsigned long n, i;
	int ret, offset;

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

	if (copy_from_user(&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;
	}

	ret = -ENOMEM;
	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
	if (!data)
		goto e_unpin_memory;

	offset = params.guest_uaddr & (PAGE_SIZE - 1);
	data->guest_address = __sme_page_pa(pages[0]) + offset;
	data->guest_len = params.guest_len;

	blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len);
	if (IS_ERR(blob)) {
		ret = PTR_ERR(blob);
		goto e_free;
	}

	data->trans_address = __psp_pa(blob);
	data->trans_len = params.trans_len;

	hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len);
	if (IS_ERR(hdr)) {
		ret = PTR_ERR(hdr);
		goto e_free_blob;
	}
	data->hdr_address = __psp_pa(hdr);
	data->hdr_len = params.hdr_len;

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

	kfree(hdr);

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

int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
{
	struct kvm_sev_cmd sev_cmd;
	int r;

	if (!svm_sev_enabled() || !sev)
		return -ENOTTY;

	if (!argp)
		return 0;

	if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd)))
		return -EFAULT;

	mutex_lock(&kvm->lock);

	switch (sev_cmd.id) {
	case KVM_SEV_INIT:
		r = sev_guest_init(kvm, &sev_cmd);
		break;
	case KVM_SEV_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_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;
	default:
		r = -EINVAL;
		goto out;
	}

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

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

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

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

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

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

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

	/*
	 * 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);

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

	mutex_lock(&kvm->lock);
	list_add_tail(&region->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_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;

	mutex_lock(&kvm->lock);

	if (!sev_guest(kvm)) {
		ret = -ENOTTY;
		goto failed;
	}

	region = find_enc_region(kvm, range);
	if (!region) {
		ret = -EINVAL;
		goto failed;
	}

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

	__unregister_enc_region_locked(kvm, region);

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

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

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

	if (!sev_guest(kvm))
		return;

	mutex_lock(&kvm->lock);

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

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

	mutex_unlock(&kvm->lock);

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

void __init sev_hardware_setup(void)
{
	unsigned int eax, ebx, ecx, edx;
	bool sev_es_supported = false;
	bool sev_supported = false;

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

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

	/* Maximum number of encrypted guests supported simultaneously */
	max_sev_asid = ecx;

	if (!svm_sev_enabled())
		goto out;

	/* Minimum ASID value that should be used for SEV guest */
	min_sev_asid = edx;

	/* Initialize SEV ASID bitmaps */
	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
	if (!sev_asid_bitmap)
		goto out;

	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
	if (!sev_reclaim_asid_bitmap)
		goto out;

	pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1);
	sev_supported = true;

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

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

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

	pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1);
	sev_es_supported = true;

out:
	sev = sev_supported;
	sev_es = sev_es_supported;
}

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

	bitmap_free(sev_asid_bitmap);
	bitmap_free(sev_reclaim_asid_bitmap);

	sev_flush_asids();
}

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

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

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

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

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

				start += PAGE_SIZE;
			}

			return;
		}

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

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

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

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

	svm = to_svm(vcpu);

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

static void dump_ghcb(struct vcpu_svm *svm)
{
	struct ghcb *ghcb = svm->ghcb;
	unsigned int nbits;

	/* Re-use the dump_invalid_vmcb module parameter */
	if (!dump_invalid_vmcb) {
		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
		return;
	}

	nbits = sizeof(ghcb->save.valid_bitmap) * 8;

	pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
	       ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
	       ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
	       ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
	pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
	       ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
}

static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
{
	struct kvm_vcpu *vcpu = &svm->vcpu;
	struct ghcb *ghcb = svm->ghcb;

	/*
	 * The GHCB protocol so far allows for the following data
	 * to be returned:
	 *   GPRs RAX, RBX, RCX, RDX
	 *
	 * Copy their values to the GHCB if they are dirty.
	 */
	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX))
		ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]);
	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX))
		ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]);
	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX))
		ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]);
	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX))
		ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]);
}

static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
{
	struct vmcb_control_area *control = &svm->vmcb->control;
	struct kvm_vcpu *vcpu = &svm->vcpu;
	struct ghcb *ghcb = svm->ghcb;
	u64 exit_code;

	/*
	 * The GHCB protocol so far allows for the following data
	 * to be supplied:
	 *   GPRs RAX, RBX, RCX, RDX
	 *   XCR0
	 *   CPL
	 *
	 * VMMCALL allows the guest to provide extra registers. KVM also
	 * expects RSI for hypercalls, so include that, too.
	 *
	 * Copy their values to the appropriate location if supplied.
	 */
	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));

	vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb);
	vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb);
	vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb);
	vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb);
	vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb);

	svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb);

	if (ghcb_xcr0_is_valid(ghcb)) {
		vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb);
		kvm_update_cpuid_runtime(vcpu);
	}

	/* Copy the GHCB exit information into the VMCB fields */
	exit_code = ghcb_get_sw_exit_code(ghcb);
	control->exit_code = lower_32_bits(exit_code);
	control->exit_code_hi = upper_32_bits(exit_code);
	control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb);
	control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb);

	/* Clear the valid entries fields */
	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
}

static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
{
	struct kvm_vcpu *vcpu;
	struct ghcb *ghcb;
	u64 exit_code = 0;

	ghcb = svm->ghcb;

	/* Only GHCB Usage code 0 is supported */
	if (ghcb->ghcb_usage)
		goto vmgexit_err;

	/*
	 * Retrieve the exit code now even though is may not be marked valid
	 * as it could help with debugging.
	 */
	exit_code = ghcb_get_sw_exit_code(ghcb);

	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
	    !ghcb_sw_exit_info_2_is_valid(ghcb))
		goto vmgexit_err;

	switch (ghcb_get_sw_exit_code(ghcb)) {
	case SVM_EXIT_READ_DR7:
		break;
	case SVM_EXIT_WRITE_DR7:
		if (!ghcb_rax_is_valid(ghcb))
			goto vmgexit_err;
		break;
	case SVM_EXIT_RDTSC:
		break;
	case SVM_EXIT_RDPMC:
		if (!ghcb_rcx_is_valid(ghcb))
			goto vmgexit_err;
		break;
	case SVM_EXIT_CPUID:
		if (!ghcb_rax_is_valid(ghcb) ||
		    !ghcb_rcx_is_valid(ghcb))
			goto vmgexit_err;
		if (ghcb_get_rax(ghcb) == 0xd)
			if (!ghcb_xcr0_is_valid(ghcb))
				goto vmgexit_err;
		break;
	case SVM_EXIT_INVD:
		break;
	case SVM_EXIT_IOIO:
		if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK))
			if (!ghcb_rax_is_valid(ghcb))
				goto vmgexit_err;
		break;
	case SVM_EXIT_MSR:
		if (!ghcb_rcx_is_valid(ghcb))
			goto vmgexit_err;
		if (ghcb_get_sw_exit_info_1(ghcb)) {
			if (!ghcb_rax_is_valid(ghcb) ||
			    !ghcb_rdx_is_valid(ghcb))
				goto vmgexit_err;
		}
		break;
	case SVM_EXIT_VMMCALL:
		if (!ghcb_rax_is_valid(ghcb) ||
		    !ghcb_cpl_is_valid(ghcb))
			goto vmgexit_err;
		break;
	case SVM_EXIT_RDTSCP:
		break;
	case SVM_EXIT_WBINVD:
		break;
	case SVM_EXIT_MONITOR:
		if (!ghcb_rax_is_valid(ghcb) ||
		    !ghcb_rcx_is_valid(ghcb) ||
		    !ghcb_rdx_is_valid(ghcb))
			goto vmgexit_err;
		break;
	case SVM_EXIT_MWAIT:
		if (!ghcb_rax_is_valid(ghcb) ||
		    !ghcb_rcx_is_valid(ghcb))
			goto vmgexit_err;
		break;
	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
		break;
	default:
		goto vmgexit_err;
	}

	return 0;

vmgexit_err:
	vcpu = &svm->vcpu;

	if (ghcb->ghcb_usage) {
		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
			    ghcb->ghcb_usage);
	} else {
		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
			    exit_code);
		dump_ghcb(svm);
	}

	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
	vcpu->run->internal.ndata = 2;
	vcpu->run->internal.data[0] = exit_code;
	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;

	return -EINVAL;
}

static void pre_sev_es_run(struct vcpu_svm *svm)
{
	if (!svm->ghcb)
		return;

	sev_es_sync_to_ghcb(svm);

	kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true);
	svm->ghcb = NULL;
}

void pre_sev_run(struct vcpu_svm *svm, int cpu)
{
	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
	int asid = sev_get_asid(svm->vcpu.kvm);

	/* Perform any SEV-ES pre-run actions */
	pre_sev_es_run(svm);

	/* Assign the asid allocated with this SEV guest */
	svm->asid = asid;

	/*
	 * Flush guest TLB:
	 *
	 * 1) when different VMCB for the same ASID is to be run on the same host CPU.
	 * 2) or this VMCB was executed on different host CPU in previous VMRUNs.
	 */
	if (sd->sev_vmcbs[asid] == svm->vmcb &&
	    svm->vcpu.arch.last_vmentry_cpu == cpu)
		return;

	sd->sev_vmcbs[asid] = svm->vmcb;
	svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
}

static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
	return -EINVAL;
}

int sev_handle_vmgexit(struct vcpu_svm *svm)
{
	struct vmcb_control_area *control = &svm->vmcb->control;
	u64 ghcb_gpa, exit_code;
	struct ghcb *ghcb;
	int ret;

	/* Validate the GHCB */
	ghcb_gpa = control->ghcb_gpa;
	if (ghcb_gpa & GHCB_MSR_INFO_MASK)
		return sev_handle_vmgexit_msr_protocol(svm);

	if (!ghcb_gpa) {
		vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB gpa is not set\n");
		return -EINVAL;
	}

	if (kvm_vcpu_map(&svm->vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) {
		/* Unable to map GHCB from guest */
		vcpu_unimpl(&svm->vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
			    ghcb_gpa);
		return -EINVAL;
	}

	svm->ghcb = svm->ghcb_map.hva;
	ghcb = svm->ghcb_map.hva;

	exit_code = ghcb_get_sw_exit_code(ghcb);

	ret = sev_es_validate_vmgexit(svm);
	if (ret)
		return ret;

	sev_es_sync_from_ghcb(svm);
	ghcb_set_sw_exit_info_1(ghcb, 0);
	ghcb_set_sw_exit_info_2(ghcb, 0);

	ret = -EINVAL;
	switch (exit_code) {
	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
		vcpu_unimpl(&svm->vcpu,
			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
			    control->exit_info_1, control->exit_info_2);
		break;
	default:
		ret = svm_invoke_exit_handler(svm, exit_code);
	}

	return ret;
}