diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 71124cf..98a4852 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,5 +1,7 @@
+CONFIG_WERROR=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_USELIB=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -11,23 +13,30 @@
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
+CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
 CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
 CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_MISC=y
+CONFIG_CGROUP_DEBUG=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
-# CONFIG_64BIT is not set
 CONFIG_SMP=y
-CONFIG_X86_GENERIC=y
-CONFIG_HPET_TIMER=y
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PARAVIRT=y
+CONFIG_NR_CPUS=8
 CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
-CONFIG_X86_REBOOTFIXUPS=y
 CONFIG_MICROCODE_AMD=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
-CONFIG_HIGHPTE=y
 CONFIG_X86_CHECK_BIOS_CORRUPTION=y
 # CONFIG_MTRR_SANITIZER is not set
 CONFIG_EFI=y
@@ -43,12 +52,15 @@
 CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_X86_ACPI_CPUFREQ=y
-CONFIG_EFI_VARS=y
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
+CONFIG_COMPAT_32BIT_TIME=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
 CONFIG_BINFMT_MISC=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -103,12 +115,16 @@
 CONFIG_IP6_NF_TARGET_REJECT=y
 CONFIG_IP6_NF_MANGLE=y
 CONFIG_NET_SCHED=y
+CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
+CONFIG_CGROUP_NET_PRIO=y
 CONFIG_CFG80211=y
 CONFIG_MAC80211=y
 CONFIG_MAC80211_LEDS=y
 CONFIG_RFKILL=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MSI=y
@@ -119,13 +135,16 @@
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DEBUG_DEVRES=y
 CONFIG_CONNECTOR=y
+CONFIG_EFI_VARS=y
+CONFIG_EFI_CAPSULE_LOADER=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_SPI_ATTRS=y
-# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_SCSI_VIRTIO=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_ATA_PIIX=y
@@ -143,6 +162,7 @@
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
 CONFIG_NETCONSOLE=y
+CONFIG_VIRTIO_NET=y
 CONFIG_BNX2=y
 CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
@@ -170,6 +190,7 @@
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_NONSTANDARD=y
+CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_HPET=y
@@ -181,12 +202,7 @@
 CONFIG_AGP_INTEL=y
 CONFIG_DRM=y
 CONFIG_DRM_I915=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-CONFIG_FB_EFI=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_DRM_VIRTIO_GPU=y
 CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_HRTIMER=y
@@ -219,6 +235,8 @@
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_DMADEVICES=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_INPUT=y
 CONFIG_EEEPC_LAPTOP=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
@@ -240,6 +258,7 @@
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
+CONFIG_9P_FS=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -251,14 +270,15 @@
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
 CONFIG_PRINTK_TIME=y
+CONFIG_FRAME_WARN=1024
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_DEBUG_STACKOVERFLOW=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_BOOT_PARAMS=y
-CONFIG_KALLSYMS_ALL=y
+CONFIG_UNWINDER_FRAME_POINTER=y
+# CONFIG_64BIT is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 92b1169e..6978450 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,3 +1,4 @@
+CONFIG_WERROR=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
@@ -11,14 +12,25 @@
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
+CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
 CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
 CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_MISC=y
+CONFIG_CGROUP_DEBUG=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_SMP=y
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PARAVIRT=y
 CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
 CONFIG_MICROCODE_AMD=y
 CONFIG_X86_MSR=y
@@ -41,12 +53,14 @@
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_X86_ACPI_CPUFREQ=y
 CONFIG_IA32_EMULATION=y
-CONFIG_EFI_VARS=y
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
 CONFIG_BINFMT_MISC=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -101,12 +115,16 @@
 CONFIG_IP6_NF_TARGET_REJECT=y
 CONFIG_IP6_NF_MANGLE=y
 CONFIG_NET_SCHED=y
+CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
+CONFIG_CGROUP_NET_PRIO=y
 CONFIG_CFG80211=y
 CONFIG_MAC80211=y
 CONFIG_MAC80211_LEDS=y
 CONFIG_RFKILL=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_HOTPLUG_PCI=y
@@ -116,13 +134,15 @@
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DEBUG_DEVRES=y
 CONFIG_CONNECTOR=y
+CONFIG_EFI_VARS=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_SPI_ATTRS=y
-# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_SCSI_VIRTIO=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_ATA_PIIX=y
@@ -138,6 +158,7 @@
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
 CONFIG_NETCONSOLE=y
+CONFIG_VIRTIO_NET=y
 CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
 CONFIG_E100=y
@@ -162,6 +183,7 @@
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_NONSTANDARD=y
+CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 # CONFIG_HW_RANDOM_INTEL is not set
 # CONFIG_HW_RANDOM_AMD is not set
@@ -175,12 +197,7 @@
 CONFIG_AGP_INTEL=y
 CONFIG_DRM=y
 CONFIG_DRM_I915=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-CONFIG_FB_EFI=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_DRM_VIRTIO_GPU=y
 CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_HRTIMER=y
@@ -213,6 +230,8 @@
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_DMADEVICES=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_INPUT=y
 CONFIG_EEEPC_LAPTOP=y
 CONFIG_AMD_IOMMU=y
 CONFIG_INTEL_IOMMU=y
@@ -237,6 +256,7 @@
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
+CONFIG_9P_FS=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -257,4 +277,3 @@
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_BOOT_PARAMS=y
-CONFIG_KALLSYMS_ALL=y
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 19821f0..c049561 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -415,9 +415,6 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
 		xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU);
 		*vpkru = xpkru->pkru;
 	}
-
-	/* Ensure that XCOMP_BV is set up for XSAVES */
-	xstate_init_xcomp_bv(&kstate->regs.xsave, kstate->xfeatures);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 7c7824a..39e1c86 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -81,10 +81,10 @@ static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
 	{ [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
 	{ [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_comp_offsets[XFEATURE_MAX] __ro_after_init =
-	{ [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init =
-	{ [ 0 ... XFEATURE_MAX - 1] = -1};
+static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
+
+#define XSTATE_FLAG_SUPERVISOR	BIT(0)
+#define XSTATE_FLAG_ALIGNED64	BIT(1)
 
 /*
  * Return whether the system supports a given xfeature.
@@ -124,17 +124,41 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
 }
 EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
 
+static bool xfeature_is_aligned64(int xfeature_nr)
+{
+	return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64;
+}
+
 static bool xfeature_is_supervisor(int xfeature_nr)
 {
-	/*
-	 * Extended State Enumeration Sub-leaves (EAX = 0DH, ECX = n, n > 1)
-	 * returns ECX[0] set to (1) for a supervisor state, and cleared (0)
-	 * for a user state.
-	 */
-	u32 eax, ebx, ecx, edx;
+	return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR;
+}
 
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	return ecx & 1;
+static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature)
+{
+	unsigned int offs, i;
+
+	/*
+	 * Non-compacted format and legacy features use the cached fixed
+	 * offsets.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_XSAVES) || xfeature <= XFEATURE_SSE)
+		return xstate_offsets[xfeature];
+
+	/*
+	 * Compacted format offsets depend on the actual content of the
+	 * compacted xsave area which is determined by the xcomp_bv header
+	 * field.
+	 */
+	offs = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	for_each_extended_xfeature(i, xcomp_bv) {
+		if (xfeature_is_aligned64(i))
+			offs = ALIGN(offs, 64);
+		if (i == xfeature)
+			break;
+		offs += xstate_sizes[i];
+	}
+	return offs;
 }
 
 /*
@@ -182,7 +206,7 @@ static bool xfeature_enabled(enum xfeature xfeature)
  * Record the offsets and sizes of various xstates contained
  * in the XSAVE state memory layout.
  */
-static void __init setup_xstate_features(void)
+static void __init setup_xstate_cache(void)
 {
 	u32 eax, ebx, ecx, edx, i;
 	/* start at the beginning of the "extended state" */
@@ -205,6 +229,7 @@ static void __init setup_xstate_features(void)
 		cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
 
 		xstate_sizes[i] = eax;
+		xstate_flags[i] = ecx;
 
 		/*
 		 * If an xfeature is supervisor state, the offset in EBX is
@@ -264,94 +289,6 @@ static void __init print_xstate_features(void)
 } while (0)
 
 /*
- * We could cache this like xstate_size[], but we only use
- * it here, so it would be a waste of space.
- */
-static int xfeature_is_aligned(int xfeature_nr)
-{
-	u32 eax, ebx, ecx, edx;
-
-	CHECK_XFEATURE(xfeature_nr);
-
-	if (!xfeature_enabled(xfeature_nr)) {
-		WARN_ONCE(1, "Checking alignment of disabled xfeature %d\n",
-			  xfeature_nr);
-		return 0;
-	}
-
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	/*
-	 * The value returned by ECX[1] indicates the alignment
-	 * of state component 'i' when the compacted format
-	 * of the extended region of an XSAVE area is used:
-	 */
-	return !!(ecx & 2);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave area.
- */
-static void __init setup_xstate_comp_offsets(void)
-{
-	unsigned int next_offset;
-	int i;
-
-	/*
-	 * The FP xstates and SSE xstates are legacy states. They are always
-	 * in the fixed offsets in the xsave area in either compacted form
-	 * or standard form.
-	 */
-	xstate_comp_offsets[XFEATURE_FP] = 0;
-	xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state,
-						     xmm_space);
-
-	if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) {
-		for_each_extended_xfeature(i, fpu_kernel_cfg.max_features)
-			xstate_comp_offsets[i] = xstate_offsets[i];
-		return;
-	}
-
-	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		if (xfeature_is_aligned(i))
-			next_offset = ALIGN(next_offset, 64);
-
-		xstate_comp_offsets[i] = next_offset;
-		next_offset += xstate_sizes[i];
-	}
-}
-
-/*
- * Setup offsets of a supervisor-state-only XSAVES buffer:
- *
- * The offsets stored in xstate_comp_offsets[] only work for one specific
- * value of the Requested Feature BitMap (RFBM).  In cases where a different
- * RFBM value is used, a different set of offsets is required.  This set of
- * offsets is for when RFBM=xfeatures_mask_supervisor().
- */
-static void __init setup_supervisor_only_offsets(void)
-{
-	unsigned int next_offset;
-	int i;
-
-	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		if (!xfeature_is_supervisor(i))
-			continue;
-
-		if (xfeature_is_aligned(i))
-			next_offset = ALIGN(next_offset, 64);
-
-		xstate_supervisor_only_offsets[i] = next_offset;
-		next_offset += xstate_sizes[i];
-	}
-}
-
-/*
  * Print out xstate component offsets and sizes
  */
 static void __init print_xstate_offset_size(void)
@@ -360,7 +297,8 @@ static void __init print_xstate_offset_size(void)
 
 	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
 		pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n",
-			 i, xstate_comp_offsets[i], i, xstate_sizes[i]);
+			i, xfeature_get_offset(fpu_kernel_cfg.max_features, i),
+			i, xstate_sizes[i]);
 	}
 }
 
@@ -419,7 +357,6 @@ static void __init setup_init_fpu_buf(void)
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return;
 
-	setup_xstate_features();
 	print_xstate_features();
 
 	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
@@ -448,25 +385,6 @@ static void __init setup_init_fpu_buf(void)
 	fxsave(&init_fpstate.regs.fxsave);
 }
 
-static int xfeature_uncompacted_offset(int xfeature_nr)
-{
-	u32 eax, ebx, ecx, edx;
-
-	/*
-	 * Only XSAVES supports supervisor states and it uses compacted
-	 * format. Checking a supervisor state's uncompacted offset is
-	 * an error.
-	 */
-	if (XFEATURE_MASK_SUPERVISOR_ALL & BIT_ULL(xfeature_nr)) {
-		WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
-		return -1;
-	}
-
-	CHECK_XFEATURE(xfeature_nr);
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	return ebx;
-}
-
 int xfeature_size(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;
@@ -644,29 +562,15 @@ static bool __init check_xstate_against_struct(int nr)
 
 static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
 {
-	unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-	int i;
+	unsigned int topmost = fls64(xfeatures) -  1;
+	unsigned int offset = xstate_offsets[topmost];
 
-	for_each_extended_xfeature(i, xfeatures) {
-		/* Align from the end of the previous feature */
-		if (xfeature_is_aligned(i))
-			size = ALIGN(size, 64);
-		/*
-		 * In compacted format the enabled features are packed,
-		 * i.e. disabled features do not occupy space.
-		 *
-		 * In non-compacted format the offsets are fixed and
-		 * disabled states still occupy space in the memory buffer.
-		 */
-		if (!compacted)
-			size = xfeature_uncompacted_offset(i);
-		/*
-		 * Add the feature size even for non-compacted format
-		 * to make the end result correct
-		 */
-		size += xfeature_size(i);
-	}
-	return size;
+	if (topmost <= XFEATURE_SSE)
+		return sizeof(struct xregs_state);
+
+	if (compacted)
+		offset = xfeature_get_offset(xfeatures, topmost);
+	return offset + xstate_sizes[topmost];
 }
 
 /*
@@ -935,6 +839,10 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
+
+	/* Cache size, offset and flags for initialization */
+	setup_xstate_cache();
+
 	err = init_xstate_size();
 	if (err)
 		goto out_disable;
@@ -950,8 +858,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 				  fpu_user_cfg.max_features);
 
 	setup_init_fpu_buf();
-	setup_xstate_comp_offsets();
-	setup_supervisor_only_offsets();
 
 	/*
 	 * Paranoia check whether something in the setup modified the
@@ -1006,13 +912,19 @@ void fpu__resume_cpu(void)
  */
 static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 {
-	if (!xfeature_enabled(xfeature_nr)) {
-		WARN_ON_FPU(1);
+	u64 xcomp_bv = xsave->header.xcomp_bv;
+
+	if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
 		return NULL;
+
+	if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
+		if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr))))
+			return NULL;
 	}
 
-	return (void *)xsave + xstate_comp_offsets[xfeature_nr];
+	return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr);
 }
+
 /*
  * Given the xsave area and a state inside, this function returns the
  * address of the state.
@@ -1043,8 +955,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 	 * We should not ever be requesting features that we
 	 * have not enabled.
 	 */
-	WARN_ONCE(!(fpu_kernel_cfg.max_features & BIT_ULL(xfeature_nr)),
-		  "get of unsupported state");
+	if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
+		return NULL;
+
 	/*
 	 * This assumes the last 'xsave*' instruction to
 	 * have requested that 'xfeature_nr' be saved.
@@ -1625,6 +1538,9 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 
 	/* Calculate the resulting kernel state size */
 	mask = permitted | requested;
+	/* Take supervisor states into account on the host */
+	if (!guest)
+		mask |= xfeatures_mask_supervisor();
 	ksize = xstate_calculate_size(mask, compacted);
 
 	/* Calculate the resulting user state size */
@@ -1639,7 +1555,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 
 	perm = guest ? &fpu->guest_perm : &fpu->perm;
 	/* Pairs with the READ_ONCE() in xstate_get_group_perm() */
-	WRITE_ONCE(perm->__state_perm, requested);
+	WRITE_ONCE(perm->__state_perm, mask);
 	/* Protected by sighand lock */
 	perm->__state_size = ksize;
 	perm->__user_state_size = usize;
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index df50451..3e2f33f 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -22,7 +22,7 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n)
 		     : "memory");
 }
 
-void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 {
 	if (unlikely(!n))
 		return;
@@ -38,9 +38,8 @@ void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 	}
 	rep_movs(to, (const void *)from, n);
 }
-EXPORT_SYMBOL(memcpy_fromio);
 
-void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 {
 	if (unlikely(!n))
 		return;
@@ -56,14 +55,64 @@ void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 	}
 	rep_movs((void *)to, (const void *) from, n);
 }
+
+static void unrolled_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+	const volatile char __iomem *in = from;
+	char *out = to;
+	int i;
+
+	for (i = 0; i < n; ++i)
+		out[i] = readb(&in[i]);
+}
+
+static void unrolled_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+	volatile char __iomem *out = to;
+	const char *in = from;
+	int i;
+
+	for (i = 0; i < n; ++i)
+		writeb(in[i], &out[i]);
+}
+
+static void unrolled_memset_io(volatile void __iomem *a, int b, size_t c)
+{
+	volatile char __iomem *mem = a;
+	int i;
+
+	for (i = 0; i < c; ++i)
+		writeb(b, &mem[i]);
+}
+
+void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+		unrolled_memcpy_fromio(to, from, n);
+	else
+		string_memcpy_fromio(to, from, n);
+}
+EXPORT_SYMBOL(memcpy_fromio);
+
+void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+		unrolled_memcpy_toio(to, from, n);
+	else
+		string_memcpy_toio(to, from, n);
+}
 EXPORT_SYMBOL(memcpy_toio);
 
 void memset_io(volatile void __iomem *a, int b, size_t c)
 {
-	/*
-	 * TODO: memset can mangle the IO patterns quite a bit.
-	 * perhaps it would be better to use a dumb one:
-	 */
-	memset((void *)a, b, c);
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) {
+		unrolled_memset_io(a, b, c);
+	} else {
+		/*
+		 * TODO: memset can mangle the IO patterns quite a bit.
+		 * perhaps it would be better to use a dumb one:
+		 */
+		memset((void *)a, b, c);
+	}
 }
 EXPORT_SYMBOL(memset_io);
diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
index 3615ef4..2189f03 100644
--- a/tools/testing/selftests/x86/amx.c
+++ b/tools/testing/selftests/x86/amx.c
@@ -368,9 +368,16 @@ static void req_xtiledata_perm(void)
 
 static void validate_req_xcomp_perm(enum expected_result exp)
 {
-	unsigned long bitmask;
+	unsigned long bitmask, expected_bitmask;
 	long rc;
 
+	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask);
+	if (rc) {
+		fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc);
+	} else if (!(bitmask & XFEATURE_MASK_XTILECFG)) {
+		fatal_error("ARCH_GET_XCOMP_PERM returns XFEATURE_XTILECFG off.");
+	}
+
 	rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA);
 	if (exp == FAIL_EXPECTED) {
 		if (rc) {
@@ -383,10 +390,15 @@ static void validate_req_xcomp_perm(enum expected_result exp)
 		fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected failure.\n");
 	}
 
+	expected_bitmask = bitmask | XFEATURE_MASK_XTILEDATA;
+
 	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask);
 	if (rc) {
 		fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc);
-	} else if (bitmask & XFEATURE_MASK_XTILE) {
+	} else if (bitmask != expected_bitmask) {
+		fatal_error("ARCH_REQ_XCOMP_PERM set a wrong bitmask: %lx, expected: %lx.\n",
+			    bitmask, expected_bitmask);
+	} else {
 		printf("\tARCH_REQ_XCOMP_PERM is successful.\n");
 	}
 }