diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 08b5657e57ed..c259814200bd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3132,15 +3132,89 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+#define XSTATE_COMPACTION_ENABLED (1ULL << 63)
+
+static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
+{
+	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+	u64 valid;
+
+	/*
+	 * Copy legacy XSAVE area, to avoid complications with CPUID
+	 * leaves 0 and 1 in the loop below.
+	 */
+	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
+
+	/* Set XSTATE_BV */
+	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
+
+	/*
+	 * Copy each region from the possibly compacted offset to the
+	 * non-compacted offset.
+	 */
+	valid = xstate_bv & ~XSTATE_FPSSE;
+	while (valid) {
+		u64 feature = valid & -valid;
+		int index = fls64(feature) - 1;
+		void *src = get_xsave_addr(xsave, feature);
+
+		if (src) {
+			u32 size, offset, ecx, edx;
+			cpuid_count(XSTATE_CPUID, index,
+				    &size, &offset, &ecx, &edx);
+			memcpy(dest + offset, src, size);
+		}
+
+		valid -= feature;
+	}
+}
+
+static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
+{
+	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
+	u64 valid;
+
+	/*
+	 * Copy legacy XSAVE area, to avoid complications with CPUID
+	 * leaves 0 and 1 in the loop below.
+	 */
+	memcpy(xsave, src, XSAVE_HDR_OFFSET);
+
+	/* Set XSTATE_BV and possibly XCOMP_BV.  */
+	xsave->xsave_hdr.xstate_bv = xstate_bv;
+	if (cpu_has_xsaves)
+		xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+
+	/*
+	 * Copy each region from the non-compacted offset to the
+	 * possibly compacted offset.
+	 */
+	valid = xstate_bv & ~XSTATE_FPSSE;
+	while (valid) {
+		u64 feature = valid & -valid;
+		int index = fls64(feature) - 1;
+		void *dest = get_xsave_addr(xsave, feature);
+
+		if (dest) {
+			u32 size, offset, ecx, edx;
+			cpuid_count(XSTATE_CPUID, index,
+				    &size, &offset, &ecx, &edx);
+			memcpy(dest, src + offset, size);
+		} else
+			WARN_ON_ONCE(1);
+
+		valid -= feature;
+	}
+}
+
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
 	if (cpu_has_xsave) {
-		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state->xsave,
-			vcpu->arch.guest_xstate_size);
-		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &=
-			vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE;
+		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
+		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->fxsave,
@@ -3164,8 +3238,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 */
 		if (xstate_bv & ~kvm_supported_xcr0())
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state->xsave,
-			guest_xsave->region, vcpu->arch.guest_xstate_size);
+		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
@@ -6882,6 +6955,9 @@ int fx_init(struct kvm_vcpu *vcpu)
 		return err;
 
 	fpu_finit(&vcpu->arch.guest_fpu);
+	if (cpu_has_xsaves)
+		vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
 	 * Ensure guest xcr0 is valid for loading