KVM: SVM: Move SEV code to separate file

Move the SEV specific parts of svm.c into the new sev.c file.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Message-Id: <20200324094154.32352-5-joro@8bytes.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/Makefile

@@ -14,7 +14,7 @@ kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
-kvm-amd-y		+= svm/svm.o svm/pmu.o svm/nested.o svm/avic.o
+kvm-amd-y		+= svm/svm.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
 obj-$(CONFIG_KVM_INTEL)	+= kvm-intel.o

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/swap.h>
+
+#include "x86.h"
+#include "svm.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, npinned, size;
+	unsigned long locked, lock_limit;
+	struct page **pages;
+	unsigned long first, last;
+
+	if (ulen == 0 || uaddr + ulen < uaddr)
+		return NULL;
+
+	/* 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 NULL;
+	}
+
+	/* Avoid using vmalloc for smaller buffers. */
+	size = npages * sizeof(struct page *);
+	if (size > PAGE_SIZE)
+		pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+				  PAGE_KERNEL);
+	else
+		pages = kmalloc(size, GFP_KERNEL_ACCOUNT);
+
+	if (!pages)
+		return NULL;
+
+	/* Pin the user virtual address. */
+	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
+	if (npinned != npages) {
+		pr_err("SEV: Failure locking %lu pages.\n", npages);
+		goto err;
+	}
+
+	*n = npages;
+	sev->pages_locked = locked;
+
+	return pages;
+
+err:
+	if (npinned > 0)
+		release_pages(pages, npinned);
+
+	kvfree(pages);
+	return NULL;
+}
+
+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;
+
+	release_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 (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 (!inpages) {
+		ret = -ENOMEM;
+		goto e_free;
+	}
+
+	/*
+	 * The LAUNCH_UPDATE command will perform in-place encryption of the
+	 * memory content (i.e it will write the same memory region with C=1).
+	 * It's possible that the cache may contain the data with C=0, i.e.,
+	 * unencrypted so invalidate it first.
+	 */
+	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 (!src_p)
+			return -EFAULT;
+
+		dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1);
+		if (!dst_p) {
+			sev_unpin_memory(kvm, src_p, n);
+			return -EFAULT;
+		}
+
+		/*
+		 * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the
+		 * memory content (i.e it will write the same memory region with C=1).
+		 * It's possible that the cache may contain the data with C=0, i.e.,
+		 * unencrypted so invalidate it first.
+		 */
+		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;
+	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 (!pages)
+		return -ENOMEM;
+
+	/*
+	 * 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:
+	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())
+		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 (!region->pages) {
+		ret = -ENOMEM;
+		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));
+		}
+	}
+
+	mutex_unlock(&kvm->lock);
+
+	sev_unbind_asid(kvm, sev->handle);
+	sev_asid_free(sev->asid);
+}
+
+int __init sev_hardware_setup(void)
+{
+	struct sev_user_data_status *status;
+	int rc;
+
+	/* Maximum number of encrypted guests supported simultaneously */
+	max_sev_asid = cpuid_ecx(0x8000001F);
+
+	if (!max_sev_asid)
+		return 1;
+
+	/* Minimum ASID value that should be used for SEV guest */
+	min_sev_asid = cpuid_edx(0x8000001F);
+
+	/* Initialize SEV ASID bitmaps */
+	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	if (!sev_asid_bitmap)
+		return 1;
+
+	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	if (!sev_reclaim_asid_bitmap)
+		return 1;
+
+	status = kmalloc(sizeof(*status), GFP_KERNEL);
+	if (!status)
+		return 1;
+
+	/*
+	 * Check SEV platform status.
+	 *
+	 * PLATFORM_STATUS can be called in any state, if we failed to query
+	 * the PLATFORM status then either PSP firmware does not support SEV
+	 * feature or SEV firmware is dead.
+	 */
+	rc = sev_platform_status(status, NULL);
+	if (rc)
+		goto err;
+
+	pr_info("SEV supported\n");
+
+err:
+	kfree(status);
+	return rc;
+}
+
+void sev_hardware_teardown(void)
+{
+	bitmap_free(sev_asid_bitmap);
+	bitmap_free(sev_reclaim_asid_bitmap);
+
+	sev_flush_asids();
+}
+
+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);
+
+	/* Assign the asid allocated with this SEV guest */
+	svm->vmcb->control.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->last_cpu == cpu)
+		return;
+
+	svm->last_cpu = cpu;
+	sd->sev_vmcbs[asid] = svm->vmcb;
+	svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
+	mark_dirty(svm->vmcb, VMCB_ASID);
+}

arch/x86/kvm/svm/svm.c

@@ -196,47 +196,6 @@ static u8 rsm_ins_bytes[] = "\x0f\xaa";
 
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
-static int sev_flush_asids(void);
-static DECLARE_RWSEM(sev_deactivate_lock);
-static DEFINE_MUTEX(sev_bitmap_lock);
-static 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 inline bool svm_sev_enabled(void)
-{
-	return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0;
-}
-
-static inline bool sev_guest(struct kvm *kvm)
-{
-#ifdef CONFIG_KVM_AMD_SEV
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	return sev->active;
-#else
-	return false;
-#endif
-}
-
-static inline int sev_get_asid(struct kvm *kvm)
-{
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	return sev->asid;
-}
-
 static unsigned long iopm_base;
 
 struct kvm_ldttss_desc {
@@ -248,23 +207,7 @@ struct kvm_ldttss_desc {
 	u32 zero1;
 } __attribute__((packed));
 
-struct svm_cpu_data {
-	int cpu;
-
-	u64 asid_generation;
-	u32 max_asid;
-	u32 next_asid;
-	u32 min_asid;
-	struct kvm_ldttss_desc *tss_desc;
-
-	struct page *save_area;
-	struct vmcb *current_vmcb;
-
-	/* index = sev_asid, value = vmcb pointer */
-	struct vmcb **sev_vmcbs;
-};
-
-static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
+DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
 
 static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
 
@@ -763,51 +706,6 @@ void disable_nmi_singlestep(struct vcpu_svm *svm)
 	}
 }
 
-static __init int sev_hardware_setup(void)
-{
-	struct sev_user_data_status *status;
-	int rc;
-
-	/* Maximum number of encrypted guests supported simultaneously */
-	max_sev_asid = cpuid_ecx(0x8000001F);
-
-	if (!max_sev_asid)
-		return 1;
-
-	/* Minimum ASID value that should be used for SEV guest */
-	min_sev_asid = cpuid_edx(0x8000001F);
-
-	/* Initialize SEV ASID bitmaps */
-	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
-	if (!sev_asid_bitmap)
-		return 1;
-
-	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
-	if (!sev_reclaim_asid_bitmap)
-		return 1;
-
-	status = kmalloc(sizeof(*status), GFP_KERNEL);
-	if (!status)
-		return 1;
-
-	/*
-	 * Check SEV platform status.
-	 *
-	 * PLATFORM_STATUS can be called in any state, if we failed to query
-	 * the PLATFORM status then either PSP firmware does not support SEV
-	 * feature or SEV firmware is dead.
-	 */
-	rc = sev_platform_status(status, NULL);
-	if (rc)
-		goto err;
-
-	pr_info("SEV supported\n");
-
-err:
-	kfree(status);
-	return rc;
-}
-
 static void grow_ple_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -889,12 +787,8 @@ static void svm_hardware_teardown(void)
 {
 	int cpu;
 
-	if (svm_sev_enabled()) {
-		bitmap_free(sev_asid_bitmap);
-		bitmap_free(sev_reclaim_asid_bitmap);
-
-		sev_flush_asids();
-	}
+	if (svm_sev_enabled())
+		sev_hardware_teardown();
 
 	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
@@ -1250,199 +1144,6 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 }
 
-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 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, npinned, size;
-	unsigned long locked, lock_limit;
-	struct page **pages;
-	unsigned long first, last;
-
-	if (ulen == 0 || uaddr + ulen < uaddr)
-		return NULL;
-
-	/* 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 NULL;
-	}
-
-	/* Avoid using vmalloc for smaller buffers. */
-	size = npages * sizeof(struct page *);
-	if (size > PAGE_SIZE)
-		pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO,
-				  PAGE_KERNEL);
-	else
-		pages = kmalloc(size, GFP_KERNEL_ACCOUNT);
-
-	if (!pages)
-		return NULL;
-
-	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
-	if (npinned != npages) {
-		pr_err("SEV: Failure locking %lu pages.\n", npages);
-		goto err;
-	}
-
-	*n = npages;
-	sev->pages_locked = locked;
-
-	return pages;
-
-err:
-	if (npinned > 0)
-		release_pages(pages, npinned);
-
-	kvfree(pages);
-	return NULL;
-}
-
-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;
-
-	release_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 (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 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);
-}
-
-static 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));
-		}
-	}
-
-	mutex_unlock(&kvm->lock);
-
-	sev_unbind_asid(kvm, sev->handle);
-	sev_asid_free(sev->asid);
-}
-
-static void svm_vm_destroy(struct kvm *kvm)
-{
-	avic_vm_destroy(kvm);
-	sev_vm_destroy(kvm);
-}
-
-static int svm_vm_init(struct kvm *kvm)
-{
-	if (avic) {
-		int ret = avic_vm_init(kvm);
-		if (ret)
-			return ret;
-	}
-
-	kvm_apicv_init(kvm, avic);
-	return 0;
-}
-
 static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3292,30 +2993,6 @@ static void reload_tss(struct kvm_vcpu *vcpu)
 	load_TR_desc();
 }
 
-static 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);
-
-	/* Assign the asid allocated with this SEV guest */
-	svm->vmcb->control.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->last_cpu == cpu)
-		return;
-
-	svm->last_cpu = cpu;
-	sd->sev_vmcbs[asid] = svm->vmcb;
-	svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
-	mark_dirty(svm->vmcb, VMCB_ASID);
-}
-
 static void pre_svm_run(struct vcpu_svm *svm)
 {
 	int cpu = raw_smp_processor_id();
@@ -4216,971 +3893,95 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int sev_flush_asids(void)
+static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
 {
-	int ret, error;
+	unsigned long cr4 = kvm_read_cr4(vcpu);
+	bool smep = cr4 & X86_CR4_SMEP;
+	bool smap = cr4 & X86_CR4_SMAP;
+	bool is_user = svm_get_cpl(vcpu) == 3;
 
 	/*
-	 * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail,
-	 * so it must be guarded.
+	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
+	 *
+	 * Errata:
+	 * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is
+	 * possible that CPU microcode implementing DecodeAssist will fail
+	 * to read bytes of instruction which caused #NPF. In this case,
+	 * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly
+	 * return 0 instead of the correct guest instruction bytes.
+	 *
+	 * This happens because CPU microcode reading instruction bytes
+	 * uses a special opcode which attempts to read data using CPL=0
+	 * priviledges. The microcode reads CS:RIP and if it hits a SMAP
+	 * fault, it gives up and returns no instruction bytes.
+	 *
+	 * Detection:
+	 * We reach here in case CPU supports DecodeAssist, raised #NPF and
+	 * returned 0 in GuestIntrBytes field of the VMCB.
+	 * First, errata can only be triggered in case vCPU CR4.SMAP=1.
+	 * Second, if vCPU CR4.SMEP=1, errata could only be triggered
+	 * in case vCPU CPL==3 (Because otherwise guest would have triggered
+	 * a SMEP fault instead of #NPF).
+	 * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL.
+	 * As most guests enable SMAP if they have also enabled SMEP, use above
+	 * logic in order to attempt minimize false-positive of detecting errata
+	 * while still preserving all cases semantic correctness.
+	 *
+	 * Workaround:
+	 * To determine what instruction the guest was executing, the hypervisor
+	 * will have to decode the instruction at the instruction pointer.
+	 *
+	 * In non SEV guest, hypervisor will be able to read the guest
+	 * memory to decode the instruction pointer when insn_len is zero
+	 * so we return true to indicate that decoding is possible.
+	 *
+	 * But in the SEV guest, the guest memory is encrypted with the
+	 * guest specific key and hypervisor will not be able to decode the
+	 * instruction pointer so we will not able to workaround it. Lets
+	 * print the error and request to kill the guest.
 	 */
-	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;
+	if (smap && (!smep || is_user)) {
+		if (!sev_guest(vcpu->kvm))
+			return true;
 
-	/* 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;
+		pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	}
 
-	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)
+static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 {
-	bool retry = true;
-	int pos;
-
-	mutex_lock(&sev_bitmap_lock);
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	/*
-	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
+	 * TODO: Last condition latch INIT signals on vCPU when
+	 * vCPU is in guest-mode and vmcb12 defines intercept on INIT.
+	 * To properly emulate the INIT intercept, SVM should implement
+	 * kvm_x86_ops.check_nested_events() and call nested_svm_vmexit()
+	 * there if an INIT signal is pending.
 	 */
-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;
+	return !gif_set(svm) ||
+		   (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT));
 }
 
-static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+static void svm_vm_destroy(struct kvm *kvm)
 {
-	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;
+	avic_vm_destroy(kvm);
+	sev_vm_destroy(kvm);
 }
 
-static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
+static int svm_vm_init(struct kvm *kvm)
 {
-	struct sev_data_activate *data;
-	int asid = sev_get_asid(kvm);
-	int ret;
+	if (avic) {
+		int ret = avic_vm_init(kvm);
+		if (ret)
+			return 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 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 (!inpages) {
-		ret = -ENOMEM;
-		goto e_free;
-	}
-
-	/*
-	 * The LAUNCH_UPDATE command will perform in-place encryption of the
-	 * memory content (i.e it will write the same memory region with C=1).
-	 * It's possible that the cache may contain the data with C=0, i.e.,
-	 * unencrypted so invalidate it first.
-	 */
-	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 (!src_p)
-			return -EFAULT;
-
-		dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1);
-		if (!dst_p) {
-			sev_unpin_memory(kvm, src_p, n);
-			return -EFAULT;
-		}
-
-		/*
-		 * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the
-		 * memory content (i.e it will write the same memory region with C=1).
-		 * It's possible that the cache may contain the data with C=0, i.e.,
-		 * unencrypted so invalidate it first.
-		 */
-		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;
-	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 (!pages)
-		return -ENOMEM;
-
-	/*
-	 * 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:
-	sev_unpin_memory(kvm, pages, n);
-	return ret;
-}
-
-static int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
-{
-	struct kvm_sev_cmd sev_cmd;
-	int r;
-
-	if (!svm_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);
-
-	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;
-}
-
-static 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 (!region->pages) {
-		ret = -ENOMEM;
-		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 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);
+	kvm_apicv_init(kvm, avic);
 	return 0;
-
-failed:
-	mutex_unlock(&kvm->lock);
-	return ret;
-}
-
-static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
-{
-	unsigned long cr4 = kvm_read_cr4(vcpu);
-	bool smep = cr4 & X86_CR4_SMEP;
-	bool smap = cr4 & X86_CR4_SMAP;
-	bool is_user = svm_get_cpl(vcpu) == 3;
-
-	/*
-	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
-	 *
-	 * Errata:
-	 * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is
-	 * possible that CPU microcode implementing DecodeAssist will fail
-	 * to read bytes of instruction which caused #NPF. In this case,
-	 * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly
-	 * return 0 instead of the correct guest instruction bytes.
-	 *
-	 * This happens because CPU microcode reading instruction bytes
-	 * uses a special opcode which attempts to read data using CPL=0
-	 * priviledges. The microcode reads CS:RIP and if it hits a SMAP
-	 * fault, it gives up and returns no instruction bytes.
-	 *
-	 * Detection:
-	 * We reach here in case CPU supports DecodeAssist, raised #NPF and
-	 * returned 0 in GuestIntrBytes field of the VMCB.
-	 * First, errata can only be triggered in case vCPU CR4.SMAP=1.
-	 * Second, if vCPU CR4.SMEP=1, errata could only be triggered
-	 * in case vCPU CPL==3 (Because otherwise guest would have triggered
-	 * a SMEP fault instead of #NPF).
-	 * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL.
-	 * As most guests enable SMAP if they have also enabled SMEP, use above
-	 * logic in order to attempt minimize false-positive of detecting errata
-	 * while still preserving all cases semantic correctness.
-	 *
-	 * Workaround:
-	 * To determine what instruction the guest was executing, the hypervisor
-	 * will have to decode the instruction at the instruction pointer.
-	 *
-	 * In non SEV guest, hypervisor will be able to read the guest
-	 * memory to decode the instruction pointer when insn_len is zero
-	 * so we return true to indicate that decoding is possible.
-	 *
-	 * But in the SEV guest, the guest memory is encrypted with the
-	 * guest specific key and hypervisor will not be able to decode the
-	 * instruction pointer so we will not able to workaround it. Lets
-	 * print the error and request to kill the guest.
-	 */
-	if (smap && (!smep || is_user)) {
-		if (!sev_guest(vcpu->kvm))
-			return true;
-
-		pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-	}
-
-	return false;
-}
-
-static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	/*
-	 * TODO: Last condition latch INIT signals on vCPU when
-	 * vCPU is in guest-mode and vmcb12 defines intercept on INIT.
-	 * To properly emulate the INIT intercept, SVM should implement
-	 * kvm_x86_ops.check_nested_events() and call nested_svm_vmexit()
-	 * there if an INIT signal is pending.
-	 */
-	return !gif_set(svm) ||
-		   (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT));
 }
 
 static struct kvm_x86_ops svm_x86_ops __initdata = {

arch/x86/kvm/svm/svm.h

@@ -171,6 +171,24 @@ struct vcpu_svm {
 	unsigned int last_cpu;
 };
 
+struct svm_cpu_data {
+	int cpu;
+
+	u64 asid_generation;
+	u32 max_asid;
+	u32 next_asid;
+	u32 min_asid;
+	struct kvm_ldttss_desc *tss_desc;
+
+	struct page *save_area;
+	struct vmcb *current_vmcb;
+
+	/* index = sev_asid, value = vmcb pointer */
+	struct vmcb **sev_vmcbs;
+};
+
+DECLARE_PER_CPU(struct svm_cpu_data *, svm_data);
+
 void recalc_intercepts(struct vcpu_svm *svm);
 
 static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
@@ -440,4 +458,34 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu);
 void svm_vcpu_unblocking(struct kvm_vcpu *vcpu);
 
+/* sev.c */
+
+extern unsigned int max_sev_asid;
+
+static inline bool sev_guest(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_AMD_SEV
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+	return sev->active;
+#else
+	return false;
+#endif
+}
+
+static inline bool svm_sev_enabled(void)
+{
+	return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0;
+}
+
+void sev_vm_destroy(struct kvm *kvm);
+int svm_mem_enc_op(struct kvm *kvm, void __user *argp);
+int svm_register_enc_region(struct kvm *kvm,
+			    struct kvm_enc_region *range);
+int svm_unregister_enc_region(struct kvm *kvm,
+			      struct kvm_enc_region *range);
+void pre_sev_run(struct vcpu_svm *svm, int cpu);
+int __init sev_hardware_setup(void);
+void sev_hardware_teardown(void);
+
 #endif