[Part2 PATCH v4 24/29] KVM: SVM: Pin guest memory when SEV is active

[Brijesh Singh]

The SEV memory encryption engine uses a tweak such that two identical
plaintext pages at different location will have different ciphertexts.
So swapping or moving ciphertexts of two pages will not result in
plaintexts being swapped. Relocating (or migrating) physical backing
pages for a SEV guest will require some additional steps. The current SEV
key management spec does not provide commands to swap or migrate (move)
ciphertexts. For now, we pin the guest memory registered through
KVM_REGISTER_ENCRYPT_REGION ioctl.

Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: "Radim KrÄmÃÅ" <rkrcmar@xxxxxxxxxx>
Cc: Joerg Roedel <joro@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: kvm@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |   1 +
 arch/x86/kvm/svm.c              | 109 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 110 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 86006dcfe574..3195a8cc517d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -753,6 +753,7 @@ struct kvm_sev_info {
 	unsigned int handle;	/* SEV firmware handle */
 	int fd;			/* SEV device fd */
 	unsigned long locked;	/* Number of pages locked */
+	struct list_head regions_list;  /* list of registered regions */
 };
 
 struct kvm_arch {
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index dadfb8e15db9..0bb62a114a20 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -330,6 +330,14 @@ static unsigned int max_sev_asid;
 static unsigned long *sev_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 max_sev_asid;
@@ -1656,9 +1664,38 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 	}
 }
 
+static void __unregister_enc_region(struct kvm *kvm,
+				    struct enc_region *region)
+{
+	/*
+	 * 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);
+
+	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 = &kvm->arch.sev_info;
+	struct list_head *head = &sev->regions_list;
+	struct list_head *pos, *q;
+
+	/*
+	 * 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(kvm,
+				list_entry(pos, struct enc_region, list));
+		}
+	}
 
 	sev_deactivate_handle(kvm);
 	sev_decommission_handle(kvm);
@@ -5741,6 +5778,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	sev->active = true;
 	sev->asid = asid;
+	INIT_LIST_HEAD(&sev->regions_list);
 	return 0;
 e_shutdown:
 	sev_firmware_exit();
@@ -6524,6 +6562,75 @@ static int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	return r;
 }
 
+static int svm_register_enc_region(struct kvm *kvm,
+				   struct kvm_enc_region *range)
+{
+	struct kvm_sev_info *sev = &kvm->arch.sev_info;
+	struct enc_region *region;
+
+	if (!sev_guest(kvm))
+		return -ENOTTY;
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
+
+	region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages, 1);
+	if (!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;
+	list_add_tail(&region->list, &sev->regions_list);
+	return 0;
+
+e_free:
+	kfree(region);
+	return 1;
+}
+
+static struct enc_region *
+find_enc_region(struct kvm *kvm, struct kvm_enc_region *range)
+{
+	struct kvm_sev_info *sev = &kvm->arch.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;
+
+	if (!sev_guest(kvm))
+		return -ENOTTY;
+
+	region = find_enc_region(kvm, range);
+	if (!region)
+		return -EINVAL;
+
+	__unregister_enc_region(kvm, region);
+
+	return 0;
+}
+
 static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -6636,6 +6743,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.setup_mce = svm_setup_mce,
 
 	.mem_enc_op = svm_mem_enc_op,
+	.mem_enc_register_region = svm_register_enc_region,
+	.mem_enc_unregister_region = svm_unregister_enc_region,
 };
 
 static int __init svm_init(void)
-- 
2.9.5