Merge branch 'linus' into x86/urgent, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

201 files changed, 6867 insertions, 3735 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2dc18605831f..7bb15747fea2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -164,10 +164,6 @@ config INSTRUCTION_DECODER
 	def_bool y
 	depends on KPROBES || PERF_EVENTS || UPROBES
 
-config PERF_EVENTS_INTEL_UNCORE
-	def_bool y
-	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
-
 config OUTPUT_FORMAT
 	string
 	default "elf32-i386" if X86_32
@@ -1046,6 +1042,8 @@ config X86_THERMAL_VECTOR
 	def_bool y
 	depends on X86_MCE_INTEL
 
+source "arch/x86/events/Kconfig"
+
 config X86_LEGACY_VM86
 	bool "Legacy VM86 support"
 	default n
@@ -1210,15 +1208,6 @@ config MICROCODE_OLD_INTERFACE
 	def_bool y
 	depends on MICROCODE
 
-config PERF_EVENTS_AMD_POWER
-	depends on PERF_EVENTS && CPU_SUP_AMD
-	tristate "AMD Processor Power Reporting Mechanism"
-	---help---
-	  Provide power reporting mechanism support for AMD processors.
-	  Currently, it leverages X86_FEATURE_ACC_POWER
-	  (CPUID Fn8000_0007_EDX[12]) interface to calculate the
-	  average power consumption on Family 15h processors.
-
 config X86_MSR
 	tristate "/dev/cpu/*/msr - Model-specific register support"
 	---help---
@@ -1932,54 +1921,38 @@ config RELOCATABLE
 	  (CONFIG_PHYSICAL_START) is used as the minimum location.
 
 config RANDOMIZE_BASE
-	bool "Randomize the address of the kernel image"
+	bool "Randomize the address of the kernel image (KASLR)"
 	depends on RELOCATABLE
 	default n
 	---help---
-	   Randomizes the physical and virtual address at which the
-	   kernel image is decompressed, as a security feature that
-	   deters exploit attempts relying on knowledge of the location
-	   of kernel internals.
+	  In support of Kernel Address Space Layout Randomization (KASLR),
+	  this randomizes the physical address at which the kernel image
+	  is decompressed and the virtual address where the kernel
+	  image is mapped, as a security feature that deters exploit
+	  attempts relying on knowledge of the location of kernel
+	  code internals.
+
+	  The kernel physical and virtual address can be randomized
+	  from 16MB up to 1GB on 64-bit and 512MB on 32-bit. (Note that
+	  using RANDOMIZE_BASE reduces the memory space available to
+	  kernel modules from 1.5GB to 1GB.)
+
+	  Entropy is generated using the RDRAND instruction if it is
+	  supported. If RDTSC is supported, its value is mixed into
+	  the entropy pool as well. If neither RDRAND nor RDTSC are
+	  supported, then entropy is read from the i8254 timer.
+
+	  Since the kernel is built using 2GB addressing, and
+	  PHYSICAL_ALIGN must be at a minimum of 2MB, only 10 bits of
+	  entropy is theoretically possible. Currently, with the
+	  default value for PHYSICAL_ALIGN and due to page table
+	  layouts, 64-bit uses 9 bits of entropy and 32-bit uses 8 bits.
+
+	  If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot
+	  time. To enable it, boot with "kaslr" on the kernel command
+	  line (which will also disable hibernation).
 
-	   Entropy is generated using the RDRAND instruction if it is
-	   supported. If RDTSC is supported, it is used as well. If
-	   neither RDRAND nor RDTSC are supported, then randomness is
-	   read from the i8254 timer.
-
-	   The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
-	   and aligned according to PHYSICAL_ALIGN. Since the kernel is
-	   built using 2GiB addressing, and PHYSICAL_ALGIN must be at a
-	   minimum of 2MiB, only 10 bits of entropy is theoretically
-	   possible. At best, due to page table layouts, 64-bit can use
-	   9 bits of entropy and 32-bit uses 8 bits.
-
-	   If unsure, say N.
-
-config RANDOMIZE_BASE_MAX_OFFSET
-	hex "Maximum kASLR offset allowed" if EXPERT
-	depends on RANDOMIZE_BASE
-	range 0x0 0x20000000 if X86_32
-	default "0x20000000" if X86_32
-	range 0x0 0x40000000 if X86_64
-	default "0x40000000" if X86_64
-	---help---
-	  The lesser of RANDOMIZE_BASE_MAX_OFFSET and available physical
-	  memory is used to determine the maximal offset in bytes that will
-	  be applied to the kernel when kernel Address Space Layout
-	  Randomization (kASLR) is active. This must be a multiple of
-	  PHYSICAL_ALIGN.
-
-	  On 32-bit this is limited to 512MiB by page table layouts. The
-	  default is 512MiB.
-
-	  On 64-bit this is limited by how the kernel fixmap page table is
-	  positioned, so this cannot be larger than 1GiB currently. Without
-	  RANDOMIZE_BASE, there is a 512MiB to 1.5GiB split between kernel
-	  and modules. When RANDOMIZE_BASE_MAX_OFFSET is above 512MiB, the
-	  modules area will shrink to compensate, up to the current maximum
-	  1GiB to 1GiB split. The default is 1GiB.
-
-	  If unsure, leave at the default value.
+	  If unsure, say N.
 
 # Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 4086abca0b32..6fce7f096b88 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -208,7 +208,8 @@ endif
 
 head-y := arch/x86/kernel/head_$(BITS).o
 head-y += arch/x86/kernel/head$(BITS).o
-head-y += arch/x86/kernel/head.o
+head-y += arch/x86/kernel/ebda.o
+head-y += arch/x86/kernel/platform-quirks.o
 
 libs-y  += arch/x86/lib/
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index b1ef9e489084..700a9c6e6159 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -86,16 +86,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
-
-quiet_cmd_voffset = VOFFSET $@
-      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
-
-targets += voffset.h
-$(obj)/voffset.h: vmlinux FORCE
-	$(call if_changed,voffset)
-
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
@@ -106,7 +97,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
 
 
 AFLAGS_header.o += -I$(obj)
-$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h
+$(obj)/header.o: $(obj)/zoffset.h
 
 LDFLAGS_setup.elf	:= -T
 $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 8774cb23064f..cfdd8c3f8af2 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -57,12 +57,27 @@ LDFLAGS_vmlinux := -T
 hostprogs-y	:= mkpiggy
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+
+quiet_cmd_voffset = VOFFSET $@
+      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
+
+targets += ../voffset.h
+
+$(obj)/../voffset.h: vmlinux FORCE
+	$(call if_changed,voffset)
+
+$(obj)/misc.o: $(obj)/../voffset.h
+
 vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
-	$(obj)/string.o $(obj)/cmdline.o \
+	$(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \
 	$(obj)/piggy.o $(obj)/cpuflags.o
 
 vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
-vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o
+vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
+ifdef CONFIG_X86_64
+	vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o
+endif
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
@@ -109,10 +124,8 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
-RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
-	     $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
 quiet_cmd_mkpiggy = MKPIGGY $@
-      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
+      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
 
 targets += piggy.S
 $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
deleted file mode 100644
index 6a9b96b4624d..000000000000
--- a/arch/x86/boot/compressed/aslr.c
+++ /dev/null
@@ -1,339 +0,0 @@
-#include "misc.h"
-
-#include <asm/msr.h>
-#include <asm/archrandom.h>
-#include <asm/e820.h>
-
-#include <generated/compile.h>
-#include <linux/module.h>
-#include <linux/uts.h>
-#include <linux/utsname.h>
-#include <generated/utsrelease.h>
-
-/* Simplified build-specific string for starting entropy. */
-static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
-		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
-
-#define I8254_PORT_CONTROL	0x43
-#define I8254_PORT_COUNTER0	0x40
-#define I8254_CMD_READBACK	0xC0
-#define I8254_SELECT_COUNTER0	0x02
-#define I8254_STATUS_NOTREADY	0x40
-static inline u16 i8254(void)
-{
-	u16 status, timer;
-
-	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
-		status = inb(I8254_PORT_COUNTER0);
-		timer  = inb(I8254_PORT_COUNTER0);
-		timer |= inb(I8254_PORT_COUNTER0) << 8;
-	} while (status & I8254_STATUS_NOTREADY);
-
-	return timer;
-}
-
-static unsigned long rotate_xor(unsigned long hash, const void *area,
-				size_t size)
-{
-	size_t i;
-	unsigned long *ptr = (unsigned long *)area;
-
-	for (i = 0; i < size / sizeof(hash); i++) {
-		/* Rotate by odd number of bits and XOR. */
-		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
-		hash ^= ptr[i];
-	}
-
-	return hash;
-}
-
-/* Attempt to create a simple but unpredictable starting entropy. */
-static unsigned long get_random_boot(void)
-{
-	unsigned long hash = 0;
-
-	hash = rotate_xor(hash, build_str, sizeof(build_str));
-	hash = rotate_xor(hash, real_mode, sizeof(*real_mode));
-
-	return hash;
-}
-
-static unsigned long get_random_long(void)
-{
-#ifdef CONFIG_X86_64
-	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
-#else
-	const unsigned long mix_const = 0x3f39e593UL;
-#endif
-	unsigned long raw, random = get_random_boot();
-	bool use_i8254 = true;
-
-	debug_putstr("KASLR using");
-
-	if (has_cpuflag(X86_FEATURE_RDRAND)) {
-		debug_putstr(" RDRAND");
-		if (rdrand_long(&raw)) {
-			random ^= raw;
-			use_i8254 = false;
-		}
-	}
-
-	if (has_cpuflag(X86_FEATURE_TSC)) {
-		debug_putstr(" RDTSC");
-		raw = rdtsc();
-
-		random ^= raw;
-		use_i8254 = false;
-	}
-
-	if (use_i8254) {
-		debug_putstr(" i8254");
-		random ^= i8254();
-	}
-
-	/* Circular multiply for better bit diffusion */
-	asm("mul %3"
-	    : "=a" (random), "=d" (raw)
-	    : "a" (random), "rm" (mix_const));
-	random += raw;
-
-	debug_putstr("...\n");
-
-	return random;
-}
-
-struct mem_vector {
-	unsigned long start;
-	unsigned long size;
-};
-
-#define MEM_AVOID_MAX 5
-static struct mem_vector mem_avoid[MEM_AVOID_MAX];
-
-static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
-{
-	/* Item at least partially before region. */
-	if (item->start < region->start)
-		return false;
-	/* Item at least partially after region. */
-	if (item->start + item->size > region->start + region->size)
-		return false;
-	return true;
-}
-
-static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
-{
-	/* Item one is entirely before item two. */
-	if (one->start + one->size <= two->start)
-		return false;
-	/* Item one is entirely after item two. */
-	if (one->start >= two->start + two->size)
-		return false;
-	return true;
-}
-
-static void mem_avoid_init(unsigned long input, unsigned long input_size,
-			   unsigned long output, unsigned long output_size)
-{
-	u64 initrd_start, initrd_size;
-	u64 cmd_line, cmd_line_size;
-	unsigned long unsafe, unsafe_len;
-	char *ptr;
-
-	/*
-	 * Avoid the region that is unsafe to overlap during
-	 * decompression (see calculations at top of misc.c).
-	 */
-	unsafe_len = (output_size >> 12) + 32768 + 18;
-	unsafe = (unsigned long)input + input_size - unsafe_len;
-	mem_avoid[0].start = unsafe;
-	mem_avoid[0].size = unsafe_len;
-
-	/* Avoid initrd. */
-	initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;
-	initrd_start |= real_mode->hdr.ramdisk_image;
-	initrd_size  = (u64)real_mode->ext_ramdisk_size << 32;
-	initrd_size |= real_mode->hdr.ramdisk_size;
-	mem_avoid[1].start = initrd_start;
-	mem_avoid[1].size = initrd_size;
-
-	/* Avoid kernel command line. */
-	cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;
-	cmd_line |= real_mode->hdr.cmd_line_ptr;
-	/* Calculate size of cmd_line. */
-	ptr = (char *)(unsigned long)cmd_line;
-	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
-		;
-	mem_avoid[2].start = cmd_line;
-	mem_avoid[2].size = cmd_line_size;
-
-	/* Avoid heap memory. */
-	mem_avoid[3].start = (unsigned long)free_mem_ptr;
-	mem_avoid[3].size = BOOT_HEAP_SIZE;
-
-	/* Avoid stack memory. */
-	mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
-	mem_avoid[4].size = BOOT_STACK_SIZE;
-}
-
-/* Does this memory vector overlap a known avoided area? */
-static bool mem_avoid_overlap(struct mem_vector *img)
-{
-	int i;
-	struct setup_data *ptr;
-
-	for (i = 0; i < MEM_AVOID_MAX; i++) {
-		if (mem_overlaps(img, &mem_avoid[i]))
-			return true;
-	}
-
-	/* Avoid all entries in the setup_data linked list. */
-	ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data;
-	while (ptr) {
-		struct mem_vector avoid;
-
-		avoid.start = (unsigned long)ptr;
-		avoid.size = sizeof(*ptr) + ptr->len;
-
-		if (mem_overlaps(img, &avoid))
-			return true;
-
-		ptr = (struct setup_data *)(unsigned long)ptr->next;
-	}
-
-	return false;
-}
-
-static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
-			   CONFIG_PHYSICAL_ALIGN];
-static unsigned long slot_max;
-
-static void slots_append(unsigned long addr)
-{
-	/* Overflowing the slots list should be impossible. */
-	if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
-			CONFIG_PHYSICAL_ALIGN)
-		return;
-
-	slots[slot_max++] = addr;
-}
-
-static unsigned long slots_fetch_random(void)
-{
-	/* Handle case of no slots stored. */
-	if (slot_max == 0)
-		return 0;
-
-	return slots[get_random_long() % slot_max];
-}
-
-static void process_e820_entry(struct e820entry *entry,
-			       unsigned long minimum,
-			       unsigned long image_size)
-{
-	struct mem_vector region, img;
-
-	/* Skip non-RAM entries. */
-	if (entry->type != E820_RAM)
-		return;
-
-	/* Ignore entries entirely above our maximum. */
-	if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
-		return;
-
-	/* Ignore entries entirely below our minimum. */
-	if (entry->addr + entry->size < minimum)
-		return;
-
-	region.start = entry->addr;
-	region.size = entry->size;
-
-	/* Potentially raise address to minimum location. */
-	if (region.start < minimum)
-		region.start = minimum;
-
-	/* Potentially raise address to meet alignment requirements. */
-	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
-
-	/* Did we raise the address above the bounds of this e820 region? */
-	if (region.start > entry->addr + entry->size)
-		return;
-
-	/* Reduce size by any delta from the original address. */
-	region.size -= region.start - entry->addr;
-
-	/* Reduce maximum size to fit end of image within maximum limit. */
-	if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
-		region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start;
-
-	/* Walk each aligned slot and check for avoided areas. */
-	for (img.start = region.start, img.size = image_size ;
-	     mem_contains(&region, &img) ;
-	     img.start += CONFIG_PHYSICAL_ALIGN) {
-		if (mem_avoid_overlap(&img))
-			continue;
-		slots_append(img.start);
-	}
-}
-
-static unsigned long find_random_addr(unsigned long minimum,
-				      unsigned long size)
-{
-	int i;
-	unsigned long addr;
-
-	/* Make sure minimum is aligned. */
-	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
-
-	/* Verify potential e820 positions, appending to slots list. */
-	for (i = 0; i < real_mode->e820_entries; i++) {
-		process_e820_entry(&real_mode->e820_map[i], minimum, size);
-	}
-
-	return slots_fetch_random();
-}
-
-unsigned char *choose_kernel_location(struct boot_params *boot_params,
-				      unsigned char *input,
-				      unsigned long input_size,
-				      unsigned char *output,
-				      unsigned long output_size)
-{
-	unsigned long choice = (unsigned long)output;
-	unsigned long random;
-
-#ifdef CONFIG_HIBERNATION
-	if (!cmdline_find_option_bool("kaslr")) {
-		debug_putstr("KASLR disabled by default...\n");
-		goto out;
-	}
-#else
-	if (cmdline_find_option_bool("nokaslr")) {
-		debug_putstr("KASLR disabled by cmdline...\n");
-		goto out;
-	}
-#endif
-
-	boot_params->hdr.loadflags |= KASLR_FLAG;
-
-	/* Record the various known unsafe memory ranges. */
-	mem_avoid_init((unsigned long)input, input_size,
-		       (unsigned long)output, output_size);
-
-	/* Walk e820 and find a random address. */
-	random = find_random_addr(choice, output_size);
-	if (!random) {
-		debug_putstr("KASLR could not find suitable E820 region...\n");
-		goto out;
-	}
-
-	/* Always enforce the minimum. */
-	if (random < choice)
-		goto out;
-
-	choice = random;
-out:
-	return (unsigned char *)choice;
-}
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index b68e3033e6b9..73ccf63b0f48 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -15,9 +15,9 @@ static inline char rdfs8(addr_t addr)
 #include "../cmdline.c"
 static unsigned long get_cmd_line_ptr(void)
 {
-	unsigned long cmd_line_ptr = real_mode->hdr.cmd_line_ptr;
+	unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr;
 
-	cmd_line_ptr |= (u64)real_mode->ext_cmd_line_ptr << 32;
+	cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32;
 
 	return cmd_line_ptr;
 }
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 583d539a4197..52fef606bc54 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -571,312 +571,6 @@ free_handle:
 	efi_call_early(free_pool, pci_handle);
 }
 
-static void
-setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line,
-		 struct efi_pixel_bitmask pixel_info, int pixel_format)
-{
-	if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
-		si->lfb_depth = 32;
-		si->lfb_linelength = pixels_per_scan_line * 4;
-		si->red_size = 8;
-		si->red_pos = 0;
-		si->green_size = 8;
-		si->green_pos = 8;
-		si->blue_size = 8;
-		si->blue_pos = 16;
-		si->rsvd_size = 8;
-		si->rsvd_pos = 24;
-	} else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) {
-		si->lfb_depth = 32;
-		si->lfb_linelength = pixels_per_scan_line * 4;
-		si->red_size = 8;
-		si->red_pos = 16;
-		si->green_size = 8;
-		si->green_pos = 8;
-		si->blue_size = 8;
-		si->blue_pos = 0;
-		si->rsvd_size = 8;
-		si->rsvd_pos = 24;
-	} else if (pixel_format == PIXEL_BIT_MASK) {
-		find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size);
-		find_bits(pixel_info.green_mask, &si->green_pos,
-			  &si->green_size);
-		find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size);
-		find_bits(pixel_info.reserved_mask, &si->rsvd_pos,
-			  &si->rsvd_size);
-		si->lfb_depth = si->red_size + si->green_size +
-			si->blue_size + si->rsvd_size;
-		si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8;
-	} else {
-		si->lfb_depth = 4;
-		si->lfb_linelength = si->lfb_width / 2;
-		si->red_size = 0;
-		si->red_pos = 0;
-		si->green_size = 0;
-		si->green_pos = 0;
-		si->blue_size = 0;
-		si->blue_pos = 0;
-		si->rsvd_size = 0;
-		si->rsvd_pos = 0;
-	}
-}
-
-static efi_status_t
-__gop_query32(struct efi_graphics_output_protocol_32 *gop32,
-	      struct efi_graphics_output_mode_info **info,
-	      unsigned long *size, u64 *fb_base)
-{
-	struct efi_graphics_output_protocol_mode_32 *mode;
-	efi_status_t status;
-	unsigned long m;
-
-	m = gop32->mode;
-	mode = (struct efi_graphics_output_protocol_mode_32 *)m;
-
-	status = efi_early->call(gop32->query_mode, gop32,
-				 mode->mode, size, info);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	*fb_base = mode->frame_buffer_base;
-	return status;
-}
-
-static efi_status_t
-setup_gop32(struct screen_info *si, efi_guid_t *proto,
-	    unsigned long size, void **gop_handle)
-{
-	struct efi_graphics_output_protocol_32 *gop32, *first_gop;
-	unsigned long nr_gops;
-	u16 width, height;
-	u32 pixels_per_scan_line;
-	u32 ext_lfb_base;
-	u64 fb_base;
-	struct efi_pixel_bitmask pixel_info;
-	int pixel_format;
-	efi_status_t status;
-	u32 *handles = (u32 *)(unsigned long)gop_handle;
-	int i;
-
-	first_gop = NULL;
-	gop32 = NULL;
-
-	nr_gops = size / sizeof(u32);
-	for (i = 0; i < nr_gops; i++) {
-		struct efi_graphics_output_mode_info *info = NULL;
-		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
-		bool conout_found = false;
-		void *dummy = NULL;
-		u32 h = handles[i];
-		u64 current_fb_base;
-
-		status = efi_call_early(handle_protocol, h,
-					proto, (void **)&gop32);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		status = efi_call_early(handle_protocol, h,
-					&conout_proto, &dummy);
-		if (status == EFI_SUCCESS)
-			conout_found = true;
-
-		status = __gop_query32(gop32, &info, &size, &current_fb_base);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
-			/*
-			 * Systems that use the UEFI Console Splitter may
-			 * provide multiple GOP devices, not all of which are
-			 * backed by real hardware. The workaround is to search
-			 * for a GOP implementing the ConOut protocol, and if
-			 * one isn't found, to just fall back to the first GOP.
-			 */
-			width = info->horizontal_resolution;
-			height = info->vertical_resolution;
-			pixel_format = info->pixel_format;
-			pixel_info = info->pixel_information;
-			pixels_per_scan_line = info->pixels_per_scan_line;
-			fb_base = current_fb_base;
-
-			/*
-			 * Once we've found a GOP supporting ConOut,
-			 * don't bother looking any further.
-			 */
-			first_gop = gop32;
-			if (conout_found)
-				break;
-		}
-	}
-
-	/* Did we find any GOPs? */
-	if (!first_gop)
-		goto out;
-
-	/* EFI framebuffer */
-	si->orig_video_isVGA = VIDEO_TYPE_EFI;
-
-	si->lfb_width = width;
-	si->lfb_height = height;
-	si->lfb_base = fb_base;
-
-	ext_lfb_base = (u64)(unsigned long)fb_base >> 32;
-	if (ext_lfb_base) {
-		si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE;
-		si->ext_lfb_base = ext_lfb_base;
-	}
-
-	si->pages = 1;
-
-	setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
-
-	si->lfb_size = si->lfb_linelength * si->lfb_height;
-
-	si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
-out:
-	return status;
-}
-
-static efi_status_t
-__gop_query64(struct efi_graphics_output_protocol_64 *gop64,
-	      struct efi_graphics_output_mode_info **info,
-	      unsigned long *size, u64 *fb_base)
-{
-	struct efi_graphics_output_protocol_mode_64 *mode;
-	efi_status_t status;
-	unsigned long m;
-
-	m = gop64->mode;
-	mode = (struct efi_graphics_output_protocol_mode_64 *)m;
-
-	status = efi_early->call(gop64->query_mode, gop64,
-				 mode->mode, size, info);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	*fb_base = mode->frame_buffer_base;
-	return status;
-}
-
-static efi_status_t
-setup_gop64(struct screen_info *si, efi_guid_t *proto,
-	    unsigned long size, void **gop_handle)
-{
-	struct efi_graphics_output_protocol_64 *gop64, *first_gop;
-	unsigned long nr_gops;
-	u16 width, height;
-	u32 pixels_per_scan_line;
-	u32 ext_lfb_base;
-	u64 fb_base;
-	struct efi_pixel_bitmask pixel_info;
-	int pixel_format;
-	efi_status_t status;
-	u64 *handles = (u64 *)(unsigned long)gop_handle;
-	int i;
-
-	first_gop = NULL;
-	gop64 = NULL;
-
-	nr_gops = size / sizeof(u64);
-	for (i = 0; i < nr_gops; i++) {
-		struct efi_graphics_output_mode_info *info = NULL;
-		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
-		bool conout_found = false;
-		void *dummy = NULL;
-		u64 h = handles[i];
-		u64 current_fb_base;
-
-		status = efi_call_early(handle_protocol, h,
-					proto, (void **)&gop64);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		status = efi_call_early(handle_protocol, h,
-					&conout_proto, &dummy);
-		if (status == EFI_SUCCESS)
-			conout_found = true;
-
-		status = __gop_query64(gop64, &info, &size, &current_fb_base);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
-			/*
-			 * Systems that use the UEFI Console Splitter may
-			 * provide multiple GOP devices, not all of which are
-			 * backed by real hardware. The workaround is to search
-			 * for a GOP implementing the ConOut protocol, and if
-			 * one isn't found, to just fall back to the first GOP.
-			 */
-			width = info->horizontal_resolution;
-			height = info->vertical_resolution;
-			pixel_format = info->pixel_format;
-			pixel_info = info->pixel_information;
-			pixels_per_scan_line = info->pixels_per_scan_line;
-			fb_base = current_fb_base;
-
-			/*
-			 * Once we've found a GOP supporting ConOut,
-			 * don't bother looking any further.
-			 */
-			first_gop = gop64;
-			if (conout_found)
-				break;
-		}
-	}
-
-	/* Did we find any GOPs? */
-	if (!first_gop)
-		goto out;
-
-	/* EFI framebuffer */
-	si->orig_video_isVGA = VIDEO_TYPE_EFI;
-
-	si->lfb_width = width;
-	si->lfb_height = height;
-	si->lfb_base = fb_base;
-
-	ext_lfb_base = (u64)(unsigned long)fb_base >> 32;
-	if (ext_lfb_base) {
-		si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE;
-		si->ext_lfb_base = ext_lfb_base;
-	}
-
-	si->pages = 1;
-
-	setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
-
-	si->lfb_size = si->lfb_linelength * si->lfb_height;
-
-	si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
-out:
-	return status;
-}
-
-/*
- * See if we have Graphics Output Protocol
- */
-static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
-			      unsigned long size)
-{
-	efi_status_t status;
-	void **gop_handle = NULL;
-
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				size, (void **)&gop_handle);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	status = efi_call_early(locate_handle,
-				EFI_LOCATE_BY_PROTOCOL,
-				proto, NULL, &size, gop_handle);
-	if (status != EFI_SUCCESS)
-		goto free_handle;
-
-	if (efi_early->is64)
-		status = setup_gop64(si, proto, size, gop_handle);
-	else
-		status = setup_gop32(si, proto, size, gop_handle);
-
-free_handle:
-	efi_call_early(free_pool, gop_handle);
-	return status;
-}
-
 static efi_status_t
 setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 {
@@ -1038,7 +732,7 @@ void setup_graphics(struct boot_params *boot_params)
 				EFI_LOCATE_BY_PROTOCOL,
 				&graphics_proto, NULL, &size, gop_handle);
 	if (status == EFI_BUFFER_TOO_SMALL)
-		status = setup_gop(si, &graphics_proto, size);
+		status = efi_setup_gop(NULL, si, &graphics_proto, size);
 
 	if (status != EFI_SUCCESS) {
 		size = 0;
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index d487e727f1ec..c0223f1a89d7 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -11,80 +11,6 @@
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
 
-#define EFI_CONSOLE_OUT_DEVICE_GUID    \
-	EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \
-		  0x3f, 0xc1, 0x4d)
-
-#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR		0
-#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR		1
-#define PIXEL_BIT_MASK					2
-#define PIXEL_BLT_ONLY					3
-#define PIXEL_FORMAT_MAX				4
-
-struct efi_pixel_bitmask {
-	u32 red_mask;
-	u32 green_mask;
-	u32 blue_mask;
-	u32 reserved_mask;
-};
-
-struct efi_graphics_output_mode_info {
-	u32 version;
-	u32 horizontal_resolution;
-	u32 vertical_resolution;
-	int pixel_format;
-	struct efi_pixel_bitmask pixel_information;
-	u32 pixels_per_scan_line;
-} __packed;
-
-struct efi_graphics_output_protocol_mode_32 {
-	u32 max_mode;
-	u32 mode;
-	u32 info;
-	u32 size_of_info;
-	u64 frame_buffer_base;
-	u32 frame_buffer_size;
-} __packed;
-
-struct efi_graphics_output_protocol_mode_64 {
-	u32 max_mode;
-	u32 mode;
-	u64 info;
-	u64 size_of_info;
-	u64 frame_buffer_base;
-	u64 frame_buffer_size;
-} __packed;
-
-struct efi_graphics_output_protocol_mode {
-	u32 max_mode;
-	u32 mode;
-	unsigned long info;
-	unsigned long size_of_info;
-	u64 frame_buffer_base;
-	unsigned long frame_buffer_size;
-} __packed;
-
-struct efi_graphics_output_protocol_32 {
-	u32 query_mode;
-	u32 set_mode;
-	u32 blt;
-	u32 mode;
-};
-
-struct efi_graphics_output_protocol_64 {
-	u64 query_mode;
-	u64 set_mode;
-	u64 blt;
-	u64 mode;
-};
-
-struct efi_graphics_output_protocol {
-	void *query_mode;
-	unsigned long set_mode;
-	unsigned long blt;
-	struct efi_graphics_output_protocol_mode *mode;
-};
-
 struct efi_uga_draw_protocol_32 {
 	u32 get_mode;
 	u32 set_mode;
diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c
new file mode 100644
index 000000000000..6248740b68b5
--- /dev/null
+++ b/arch/x86/boot/compressed/error.c
@@ -0,0 +1,22 @@
+/*
+ * Callers outside of misc.c need access to the error reporting routines,
+ * but the *_putstr() functions need to stay in misc.c because of how
+ * memcpy() and memmove() are defined for the compressed boot environment.
+ */
+#include "misc.h"
+
+void warn(char *m)
+{
+	error_putstr("\n\n");
+	error_putstr(m);
+	error_putstr("\n\n");
+}
+
+void error(char *m)
+{
+	warn(m);
+	error_putstr(" -- System halted");
+
+	while (1)
+		asm("hlt");
+}
diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h
new file mode 100644
index 000000000000..2e59dac07f9e
--- /dev/null
+++ b/arch/x86/boot/compressed/error.h
@@ -0,0 +1,7 @@
+#ifndef BOOT_COMPRESSED_ERROR_H
+#define BOOT_COMPRESSED_ERROR_H
+
+void warn(char *m);
+void error(char *m);
+
+#endif /* BOOT_COMPRESSED_ERROR_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 0256064da8da..1038524270e7 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -176,7 +176,9 @@ preferred_addr:
 1:
 
 	/* Target address to relocate to for decompression */
-	addl	$z_extract_offset, %ebx
+	movl    BP_init_size(%esi), %eax
+	subl    $_end, %eax
+	addl    %eax, %ebx
 
 	/* Set up the stack */
 	leal	boot_stack_end(%ebx), %esp
@@ -233,24 +235,28 @@ relocated:
 2:
 
 /*
- * Do the decompression, and jump to the new kernel..
+ * Do the extraction, and jump to the new kernel..
  */
-				/* push arguments for decompress_kernel: */
-	pushl	$z_run_size	/* size of kernel with .bss and .brk */
+				/* push arguments for extract_kernel: */
 	pushl	$z_output_len	/* decompressed length, end of relocs */
-	leal	z_extract_offset_negative(%ebx), %ebp
+
+	movl    BP_init_size(%esi), %eax
+	subl    $_end, %eax
+	movl    %ebx, %ebp
+	subl    %eax, %ebp
 	pushl	%ebp		/* output address */
+
 	pushl	$z_input_len	/* input_len */
 	leal	input_data(%ebx), %eax
 	pushl	%eax		/* input_data */
 	leal	boot_heap(%ebx), %eax
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
-	call	decompress_kernel /* returns kernel location in %eax */
-	addl	$28, %esp
+	call	extract_kernel	/* returns kernel location in %eax */
+	addl	$24, %esp
 
 /*
- * Jump to the decompressed kernel.
+ * Jump to the extracted kernel.
  */
 	xorl	%ebx, %ebx
 	jmp	*%eax
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 86558a199139..0d80a7ad65cd 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -110,7 +110,9 @@ ENTRY(startup_32)
 1:
 
 	/* Target address to relocate to for decompression */
-	addl	$z_extract_offset, %ebx
+	movl	BP_init_size(%esi), %eax
+	subl	$_end, %eax
+	addl	%eax, %ebx
 
 /*
  * Prepare for entering 64 bit mode
@@ -132,7 +134,7 @@ ENTRY(startup_32)
 	/* Initialize Page tables to 0 */
 	leal	pgtable(%ebx), %edi
 	xorl	%eax, %eax
-	movl	$((4096*6)/4), %ecx
+	movl	$(BOOT_INIT_PGT_SIZE/4), %ecx
 	rep	stosl
 
 	/* Build Level 4 */
@@ -338,7 +340,9 @@ preferred_addr:
 1:
 
 	/* Target address to relocate to for decompression */
-	leaq	z_extract_offset(%rbp), %rbx
+	movl	BP_init_size(%rsi), %ebx
+	subl	$_end, %ebx
+	addq	%rbp, %rbx
 
 	/* Set up the stack */
 	leaq	boot_stack_end(%rbx), %rsp
@@ -408,19 +412,16 @@ relocated:
 2:
 	
 /*
- * Do the decompression, and jump to the new kernel..
+ * Do the extraction, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
-	movq	$z_run_size, %r9	/* size of kernel with .bss and .brk */
-	pushq	%r9
 	movq	%rsi, %rdi		/* real mode address */
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
 	movq	$z_output_len, %r9	/* decompressed length, end of relocs */
-	call	decompress_kernel	/* returns kernel location in %rax */
-	popq	%r9
+	call	extract_kernel		/* returns kernel location in %rax */
 	popq	%rsi
 
 /*
@@ -485,4 +486,4 @@ boot_stack_end:
 	.section ".pgtable","a",@nobits
 	.balign 4096
 pgtable:
-	.fill 6*4096, 1, 0
+	.fill BOOT_PGT_SIZE, 1, 0
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
new file mode 100644
index 000000000000..cfeb0259ed81
--- /dev/null
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -0,0 +1,510 @@
+/*
+ * kaslr.c
+ *
+ * This contains the routines needed to generate a reasonable level of
+ * entropy to choose a randomized kernel base address offset in support
+ * of Kernel Address Space Layout Randomization (KASLR). Additionally
+ * handles walking the physical memory maps (and tracking memory regions
+ * to avoid) in order to select a physical memory location that can
+ * contain the entire properly aligned running kernel image.
+ *
+ */
+#include "misc.h"
+#include "error.h"
+
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+#include <asm/e820.h>
+
+#include <generated/compile.h>
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <generated/utsrelease.h>
+
+/* Simplified build-specific string for starting entropy. */
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
+#define I8254_PORT_CONTROL	0x43
+#define I8254_PORT_COUNTER0	0x40
+#define I8254_CMD_READBACK	0xC0
+#define I8254_SELECT_COUNTER0	0x02
+#define I8254_STATUS_NOTREADY	0x40
+static inline u16 i8254(void)
+{
+	u16 status, timer;
+
+	do {
+		outb(I8254_PORT_CONTROL,
+		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		status = inb(I8254_PORT_COUNTER0);
+		timer  = inb(I8254_PORT_COUNTER0);
+		timer |= inb(I8254_PORT_COUNTER0) << 8;
+	} while (status & I8254_STATUS_NOTREADY);
+
+	return timer;
+}
+
+static unsigned long rotate_xor(unsigned long hash, const void *area,
+				size_t size)
+{
+	size_t i;
+	unsigned long *ptr = (unsigned long *)area;
+
+	for (i = 0; i < size / sizeof(hash); i++) {
+		/* Rotate by odd number of bits and XOR. */
+		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+		hash ^= ptr[i];
+	}
+
+	return hash;
+}
+
+/* Attempt to create a simple but unpredictable starting entropy. */
+static unsigned long get_random_boot(void)
+{
+	unsigned long hash = 0;
+
+	hash = rotate_xor(hash, build_str, sizeof(build_str));
+	hash = rotate_xor(hash, boot_params, sizeof(*boot_params));
+
+	return hash;
+}
+
+static unsigned long get_random_long(const char *purpose)
+{
+#ifdef CONFIG_X86_64
+	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+	const unsigned long mix_const = 0x3f39e593UL;
+#endif
+	unsigned long raw, random = get_random_boot();
+	bool use_i8254 = true;
+
+	debug_putstr(purpose);
+	debug_putstr(" KASLR using");
+
+	if (has_cpuflag(X86_FEATURE_RDRAND)) {
+		debug_putstr(" RDRAND");
+		if (rdrand_long(&raw)) {
+			random ^= raw;
+			use_i8254 = false;
+		}
+	}
+
+	if (has_cpuflag(X86_FEATURE_TSC)) {
+		debug_putstr(" RDTSC");
+		raw = rdtsc();
+
+		random ^= raw;
+		use_i8254 = false;
+	}
+
+	if (use_i8254) {
+		debug_putstr(" i8254");
+		random ^= i8254();
+	}
+
+	/* Circular multiply for better bit diffusion */
+	asm("mul %3"
+	    : "=a" (random), "=d" (raw)
+	    : "a" (random), "rm" (mix_const));
+	random += raw;
+
+	debug_putstr("...\n");
+
+	return random;
+}
+
+struct mem_vector {
+	unsigned long start;
+	unsigned long size;
+};
+
+enum mem_avoid_index {
+	MEM_AVOID_ZO_RANGE = 0,
+	MEM_AVOID_INITRD,
+	MEM_AVOID_CMDLINE,
+	MEM_AVOID_BOOTPARAMS,
+	MEM_AVOID_MAX,
+};
+
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
+
+static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
+{
+	/* Item at least partially before region. */
+	if (item->start < region->start)
+		return false;
+	/* Item at least partially after region. */
+	if (item->start + item->size > region->start + region->size)
+		return false;
+	return true;
+}
+
+static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
+{
+	/* Item one is entirely before item two. */
+	if (one->start + one->size <= two->start)
+		return false;
+	/* Item one is entirely after item two. */
+	if (one->start >= two->start + two->size)
+		return false;
+	return true;
+}
+
+/*
+ * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
+ * The mem_avoid array is used to store the ranges that need to be avoided
+ * when KASLR searches for an appropriate random address. We must avoid any
+ * regions that are unsafe to overlap with during decompression, and other
+ * things like the initrd, cmdline and boot_params. This comment seeks to
+ * explain mem_avoid as clearly as possible since incorrect mem_avoid
+ * memory ranges lead to really hard to debug boot failures.
+ *
+ * The initrd, cmdline, and boot_params are trivial to identify for
+ * avoiding. They are MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, and
+ * MEM_AVOID_BOOTPARAMS respectively below.
+ *
+ * What is not obvious how to avoid is the range of memory that is used
+ * during decompression (MEM_AVOID_ZO_RANGE below). This range must cover
+ * the compressed kernel (ZO) and its run space, which is used to extract
+ * the uncompressed kernel (VO) and relocs.
+ *
+ * ZO's full run size sits against the end of the decompression buffer, so
+ * we can calculate where text, data, bss, etc of ZO are positioned more
+ * easily.
+ *
+ * For additional background, the decompression calculations can be found
+ * in header.S, and the memory diagram is based on the one found in misc.c.
+ *
+ * The following conditions are already enforced by the image layouts and
+ * associated code:
+ *  - input + input_size >= output + output_size
+ *  - kernel_total_size <= init_size
+ *  - kernel_total_size <= output_size (see Note below)
+ *  - output + init_size >= output + output_size
+ *
+ * (Note that kernel_total_size and output_size have no fundamental
+ * relationship, but output_size is passed to choose_random_location
+ * as a maximum of the two. The diagram is showing a case where
+ * kernel_total_size is larger than output_size, but this case is
+ * handled by bumping output_size.)
+ *
+ * The above conditions can be illustrated by a diagram:
+ *
+ * 0   output            input            input+input_size    output+init_size
+ * |     |                 |                             |             |
+ * |     |                 |                             |             |
+ * |-----|--------|--------|--------------|-----------|--|-------------|
+ *                |                       |           |
+ *                |                       |           |
+ * output+init_size-ZO_INIT_SIZE  output+output_size  output+kernel_total_size
+ *
+ * [output, output+init_size) is the entire memory range used for
+ * extracting the compressed image.
+ *
+ * [output, output+kernel_total_size) is the range needed for the
+ * uncompressed kernel (VO) and its run size (bss, brk, etc).
+ *
+ * [output, output+output_size) is VO plus relocs (i.e. the entire
+ * uncompressed payload contained by ZO). This is the area of the buffer
+ * written to during decompression.
+ *
+ * [output+init_size-ZO_INIT_SIZE, output+init_size) is the worst-case
+ * range of the copied ZO and decompression code. (i.e. the range
+ * covered backwards of size ZO_INIT_SIZE, starting from output+init_size.)
+ *
+ * [input, input+input_size) is the original copied compressed image (ZO)
+ * (i.e. it does not include its run size). This range must be avoided
+ * because it contains the data used for decompression.
+ *
+ * [input+input_size, output+init_size) is [_text, _end) for ZO. This
+ * range includes ZO's heap and stack, and must be avoided since it
+ * performs the decompression.
+ *
+ * Since the above two ranges need to be avoided and they are adjacent,
+ * they can be merged, resulting in: [input, output+init_size) which
+ * becomes the MEM_AVOID_ZO_RANGE below.
+ */
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+			   unsigned long output)
+{
+	unsigned long init_size = boot_params->hdr.init_size;
+	u64 initrd_start, initrd_size;
+	u64 cmd_line, cmd_line_size;
+	char *ptr;
+
+	/*
+	 * Avoid the region that is unsafe to overlap during
+	 * decompression.
+	 */
+	mem_avoid[MEM_AVOID_ZO_RANGE].start = input;
+	mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
+	add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start,
+			 mem_avoid[MEM_AVOID_ZO_RANGE].size);
+
+	/* Avoid initrd. */
+	initrd_start  = (u64)boot_params->ext_ramdisk_image << 32;
+	initrd_start |= boot_params->hdr.ramdisk_image;
+	initrd_size  = (u64)boot_params->ext_ramdisk_size << 32;
+	initrd_size |= boot_params->hdr.ramdisk_size;
+	mem_avoid[MEM_AVOID_INITRD].start = initrd_start;
+	mem_avoid[MEM_AVOID_INITRD].size = initrd_size;
+	/* No need to set mapping for initrd, it will be handled in VO. */
+
+	/* Avoid kernel command line. */
+	cmd_line  = (u64)boot_params->ext_cmd_line_ptr << 32;
+	cmd_line |= boot_params->hdr.cmd_line_ptr;
+	/* Calculate size of cmd_line. */
+	ptr = (char *)(unsigned long)cmd_line;
+	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+		;
+	mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
+	mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
+	add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
+			 mem_avoid[MEM_AVOID_CMDLINE].size);
+
+	/* Avoid boot parameters. */
+	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
+	mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
+	add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start,
+			 mem_avoid[MEM_AVOID_BOOTPARAMS].size);
+
+	/* We don't need to set a mapping for setup_data. */
+
+#ifdef CONFIG_X86_VERBOSE_BOOTUP
+	/* Make sure video RAM can be used. */
+	add_identity_map(0, PMD_SIZE);
+#endif
+}
+
+/*
+ * Does this memory vector overlap a known avoided area? If so, record the
+ * overlap region with the lowest address.
+ */
+static bool mem_avoid_overlap(struct mem_vector *img,
+			      struct mem_vector *overlap)
+{
+	int i;
+	struct setup_data *ptr;
+	unsigned long earliest = img->start + img->size;
+	bool is_overlapping = false;
+
+	for (i = 0; i < MEM_AVOID_MAX; i++) {
+		if (mem_overlaps(img, &mem_avoid[i]) &&
+		    mem_avoid[i].start < earliest) {
+			*overlap = mem_avoid[i];
+			is_overlapping = true;
+		}
+	}
+
+	/* Avoid all entries in the setup_data linked list. */
+	ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
+	while (ptr) {
+		struct mem_vector avoid;
+
+		avoid.start = (unsigned long)ptr;
+		avoid.size = sizeof(*ptr) + ptr->len;
+
+		if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) {
+			*overlap = avoid;
+			is_overlapping = true;
+		}
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
+	return is_overlapping;
+}
+
+static unsigned long slots[KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN];
+
+struct slot_area {
+	unsigned long addr;
+	int num;
+};
+
+#define MAX_SLOT_AREA 100
+
+static struct slot_area slot_areas[MAX_SLOT_AREA];
+
+static unsigned long slot_max;
+
+static unsigned long slot_area_index;
+
+static void store_slot_info(struct mem_vector *region, unsigned long image_size)
+{
+	struct slot_area slot_area;
+
+	if (slot_area_index == MAX_SLOT_AREA)
+		return;
+
+	slot_area.addr = region->start;
+	slot_area.num = (region->size - image_size) /
+			CONFIG_PHYSICAL_ALIGN + 1;
+
+	if (slot_area.num > 0) {
+		slot_areas[slot_area_index++] = slot_area;
+		slot_max += slot_area.num;
+	}
+}
+
+static void slots_append(unsigned long addr)
+{
+	/* Overflowing the slots list should be impossible. */
+	if (slot_max >= KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN)
+		return;
+
+	slots[slot_max++] = addr;
+}
+
+static unsigned long slots_fetch_random(void)
+{
+	/* Handle case of no slots stored. */
+	if (slot_max == 0)
+		return 0;
+
+	return slots[get_random_long("Physical") % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	struct mem_vector region, img, overlap;
+
+	/* Skip non-RAM entries. */
+	if (entry->type != E820_RAM)
+		return;
+
+	/* Ignore entries entirely above our maximum. */
+	if (entry->addr >= KERNEL_IMAGE_SIZE)
+		return;
+
+	/* Ignore entries entirely below our minimum. */
+	if (entry->addr + entry->size < minimum)
+		return;
+
+	region.start = entry->addr;
+	region.size = entry->size;
+
+	/* Potentially raise address to minimum location. */
+	if (region.start < minimum)
+		region.start = minimum;
+
+	/* Potentially raise address to meet alignment requirements. */
+	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+
+	/* Did we raise the address above the bounds of this e820 region? */
+	if (region.start > entry->addr + entry->size)
+		return;
+
+	/* Reduce size by any delta from the original address. */
+	region.size -= region.start - entry->addr;
+
+	/* Reduce maximum size to fit end of image within maximum limit. */
+	if (region.start + region.size > KERNEL_IMAGE_SIZE)
+		region.size = KERNEL_IMAGE_SIZE - region.start;
+
+	/* Walk each aligned slot and check for avoided areas. */
+	for (img.start = region.start, img.size = image_size ;
+	     mem_contains(&region, &img) ;
+	     img.start += CONFIG_PHYSICAL_ALIGN) {
+		if (mem_avoid_overlap(&img, &overlap))
+			continue;
+		slots_append(img.start);
+	}
+}
+
+static unsigned long find_random_phys_addr(unsigned long minimum,
+					   unsigned long image_size)
+{
+	int i;
+	unsigned long addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < boot_params->e820_entries; i++) {
+		process_e820_entry(&boot_params->e820_map[i], minimum,
+				   image_size);
+	}
+
+	return slots_fetch_random();
+}
+
+static unsigned long find_random_virt_addr(unsigned long minimum,
+					   unsigned long image_size)
+{
+	unsigned long slots, random_addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+	/* Align image_size for easy slot calculations. */
+	image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN);
+
+	/*
+	 * There are how many CONFIG_PHYSICAL_ALIGN-sized slots
+	 * that can hold image_size within the range of minimum to
+	 * KERNEL_IMAGE_SIZE?
+	 */
+	slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
+		 CONFIG_PHYSICAL_ALIGN + 1;
+
+	random_addr = get_random_long("Virtual") % slots;
+
+	return random_addr * CONFIG_PHYSICAL_ALIGN + minimum;
+}
+
+/*
+ * Since this function examines addresses much more numerically,
+ * it takes the input and output pointers as 'unsigned long'.
+ */
+unsigned char *choose_random_location(unsigned long input,
+				      unsigned long input_size,
+				      unsigned long output,
+				      unsigned long output_size)
+{
+	unsigned long choice = output;
+	unsigned long random_addr;
+
+#ifdef CONFIG_HIBERNATION
+	if (!cmdline_find_option_bool("kaslr")) {
+		warn("KASLR disabled: 'kaslr' not on cmdline (hibernation selected).");
+		goto out;
+	}
+#else
+	if (cmdline_find_option_bool("nokaslr")) {
+		warn("KASLR disabled: 'nokaslr' on cmdline.");
+		goto out;
+	}
+#endif
+
+	boot_params->hdr.loadflags |= KASLR_FLAG;
+
+	/* Record the various known unsafe memory ranges. */
+	mem_avoid_init(input, input_size, output);
+
+	/* Walk e820 and find a random address. */
+	random_addr = find_random_phys_addr(output, output_size);
+	if (!random_addr) {
+		warn("KASLR disabled: could not find suitable E820 region!");
+		goto out;
+	}
+
+	/* Always enforce the minimum. */
+	if (random_addr < choice)
+		goto out;
+
+	choice = random_addr;
+
+	add_identity_map(choice, output_size);
+
+	/* This actually loads the identity pagetable on x86_64. */
+	finalize_identity_maps();
+out:
+	return (unsigned char *)choice;
+}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 79dac1758e7c..f14db4e21654 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -1,8 +1,10 @@
 /*
  * misc.c
  *
- * This is a collection of several routines from gzip-1.0.3
- * adapted for Linux.
+ * This is a collection of several routines used to extract the kernel
+ * which includes KASLR relocation, decompression, ELF parsing, and
+ * relocation processing. Additionally included are the screen and serial
+ * output functions and related debugging support functions.
  *
  * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
  * puts by Nick Holloway 1993, better puts by Martin Mares 1995
@@ -10,111 +12,37 @@
  */
 
 #include "misc.h"
+#include "error.h"
 #include "../string.h"
-
-/* WARNING!!
- * This code is compiled with -fPIC and it is relocated dynamically
- * at run time, but no relocation processing is performed.
- * This means that it is not safe to place pointers in static structures.
- */
+#include "../voffset.h"
 
 /*
- * Getting to provable safe in place decompression is hard.
- * Worst case behaviours need to be analyzed.
- * Background information:
- *
- * The file layout is:
- *    magic[2]
- *    method[1]
- *    flags[1]
- *    timestamp[4]
- *    extraflags[1]
- *    os[1]
- *    compressed data blocks[N]
- *    crc[4] orig_len[4]
- *
- * resulting in 18 bytes of non compressed data overhead.
- *
- * Files divided into blocks
- * 1 bit (last block flag)
- * 2 bits (block type)
- *
- * 1 block occurs every 32K -1 bytes or when there 50% compression
- * has been achieved. The smallest block type encoding is always used.
- *
- * stored:
- *    32 bits length in bytes.
- *
- * fixed:
- *    magic fixed tree.
- *    symbols.
- *
- * dynamic:
- *    dynamic tree encoding.
- *    symbols.
- *
- *
- * The buffer for decompression in place is the length of the
- * uncompressed data, plus a small amount extra to keep the algorithm safe.
- * The compressed data is placed at the end of the buffer.  The output
- * pointer is placed at the start of the buffer and the input pointer
- * is placed where the compressed data starts.  Problems will occur
- * when the output pointer overruns the input pointer.
- *
- * The output pointer can only overrun the input pointer if the input
- * pointer is moving faster than the output pointer.  A condition only
- * triggered by data whose compressed form is larger than the uncompressed
- * form.
- *
- * The worst case at the block level is a growth of the compressed data
- * of 5 bytes per 32767 bytes.
- *
- * The worst case internal to a compressed block is very hard to figure.
- * The worst case can at least be boundined by having one bit that represents
- * 32764 bytes and then all of the rest of the bytes representing the very
- * very last byte.
- *
- * All of which is enough to compute an amount of extra data that is required
- * to be safe.  To avoid problems at the block level allocating 5 extra bytes
- * per 32767 bytes of data is sufficient.  To avoind problems internal to a
- * block adding an extra 32767 bytes (the worst case uncompressed block size)
- * is sufficient, to ensure that in the worst case the decompressed data for
- * block will stop the byte before the compressed data for a block begins.
- * To avoid problems with the compressed data's meta information an extra 18
- * bytes are needed.  Leading to the formula:
- *
- * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
- *
- * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
- * Adding 32768 instead of 32767 just makes for round numbers.
- * Adding the decompressor_size is necessary as it musht live after all
- * of the data as well.  Last I measured the decompressor is about 14K.
- * 10K of actual data and 4K of bss.
- *
+ * WARNING!!
+ * This code is compiled with -fPIC and it is relocated dynamically at
+ * run time, but no relocation processing is performed. This means that
+ * it is not safe to place pointers in static structures.
  */
 
-/*
- * gzip declarations
- */
+/* Macros used by the included decompressor code below. */
 #define STATIC		static
 
-#undef memcpy
-
 /*
- * Use a normal definition of memset() from string.c. There are already
+ * Use normal definitions of mem*() from string.c. There are already
  * included header files which expect a definition of memset() and by
  * the time we define memset macro, it is too late.
  */
+#undef memcpy
 #undef memset
 #define memzero(s, n)	memset((s), 0, (n))
+#define memmove		memmove
 
-
-static void error(char *m);
+/* Functions used by the included decompressor code below. */
+void *memmove(void *dest, const void *src, size_t n);
 
 /*
  * This is set up by the setup-routine at boot-time
  */
-struct boot_params *real_mode;		/* Pointer to real-mode data */
+struct boot_params *boot_params;
 
 memptr free_mem_ptr;
 memptr free_mem_end_ptr;
@@ -146,12 +74,16 @@ static int lines, cols;
 #ifdef CONFIG_KERNEL_LZ4
 #include "../../../../lib/decompress_unlz4.c"
 #endif
+/*
+ * NOTE: When adding a new decompressor, please update the analysis in
+ * ../header.S.
+ */
 
 static void scroll(void)
 {
 	int i;
 
-	memcpy(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2);
+	memmove(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2);
 	for (i = (lines - 1) * cols * 2; i < lines * cols * 2; i += 2)
 		vidmem[i] = ' ';
 }
@@ -184,12 +116,12 @@ void __putstr(const char *s)
 		}
 	}
 
-	if (real_mode->screen_info.orig_video_mode == 0 &&
+	if (boot_params->screen_info.orig_video_mode == 0 &&
 	    lines == 0 && cols == 0)
 		return;
 
-	x = real_mode->screen_info.orig_x;
-	y = real_mode->screen_info.orig_y;
+	x = boot_params->screen_info.orig_x;
+	y = boot_params->screen_info.orig_y;
 
 	while ((c = *s++) != '\0') {
 		if (c == '\n') {
@@ -210,8 +142,8 @@ void __putstr(const char *s)
 		}
 	}
 
-	real_mode->screen_info.orig_x = x;
-	real_mode->screen_info.orig_y = y;
+	boot_params->screen_info.orig_x = x;
+	boot_params->screen_info.orig_y = y;
 
 	pos = (x + cols * y) * 2;	/* Update cursor position */
 	outb(14, vidport);
@@ -237,23 +169,13 @@ void __puthex(unsigned long value)
 	}
 }
 
-static void error(char *x)
-{
-	error_putstr("\n\n");
-	error_putstr(x);
-	error_putstr("\n\n -- System halted");
-
-	while (1)
-		asm("hlt");
-}
-
 #if CONFIG_X86_NEED_RELOCS
 static void handle_relocations(void *output, unsigned long output_len)
 {
 	int *reloc;
 	unsigned long delta, map, ptr;
 	unsigned long min_addr = (unsigned long)output;
-	unsigned long max_addr = min_addr + output_len;
+	unsigned long max_addr = min_addr + (VO___bss_start - VO__text);
 
 	/*
 	 * Calculate the delta between where vmlinux was linked to load
@@ -295,7 +217,7 @@ static void handle_relocations(void *output, unsigned long output_len)
 	 * So we work backwards from the end of the decompressed image.
 	 */
 	for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
-		int extended = *reloc;
+		long extended = *reloc;
 		extended += map;
 
 		ptr = (unsigned long)extended;
@@ -372,9 +294,7 @@ static void parse_elf(void *output)
 #else
 			dest = (void *)(phdr->p_paddr);
 #endif
-			memcpy(dest,
-			       output + phdr->p_offset,
-			       phdr->p_filesz);
+			memmove(dest, output + phdr->p_offset, phdr->p_filesz);
 			break;
 		default: /* Ignore other PT_* */ break;
 		}
@@ -383,23 +303,41 @@ static void parse_elf(void *output)
 	free(phdrs);
 }
 
-asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
+/*
+ * The compressed kernel image (ZO), has been moved so that its position
+ * is against the end of the buffer used to hold the uncompressed kernel
+ * image (VO) and the execution environment (.bss, .brk), which makes sure
+ * there is room to do the in-place decompression. (See header.S for the
+ * calculations.)
+ *
+ *                             |-----compressed kernel image------|
+ *                             V                                  V
+ * 0                       extract_offset                      +INIT_SIZE
+ * |-----------|---------------|-------------------------|--------|
+ *             |               |                         |        |
+ *           VO__text      startup_32 of ZO          VO__end    ZO__end
+ *             ^                                         ^
+ *             |-------uncompressed kernel image---------|
+ *
+ */
+asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
-				  unsigned long output_len,
-				  unsigned long run_size)
+				  unsigned long output_len)
 {
+	const unsigned long kernel_total_size = VO__end - VO__text;
 	unsigned char *output_orig = output;
 
-	real_mode = rmode;
+	/* Retain x86 boot parameters pointer passed from startup_32/64. */
+	boot_params = rmode;
 
-	/* Clear it for solely in-kernel use */
-	real_mode->hdr.loadflags &= ~KASLR_FLAG;
+	/* Clear flags intended for solely in-kernel use. */
+	boot_params->hdr.loadflags &= ~KASLR_FLAG;
 
-	sanitize_boot_params(real_mode);
+	sanitize_boot_params(boot_params);
 
-	if (real_mode->screen_info.orig_video_mode == 7) {
+	if (boot_params->screen_info.orig_video_mode == 7) {
 		vidmem = (char *) 0xb0000;
 		vidport = 0x3b4;
 	} else {
@@ -407,11 +345,11 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 		vidport = 0x3d4;
 	}
 
-	lines = real_mode->screen_info.orig_video_lines;
-	cols = real_mode->screen_info.orig_video_cols;
+	lines = boot_params->screen_info.orig_video_lines;
+	cols = boot_params->screen_info.orig_video_cols;
 
 	console_init();
-	debug_putstr("early console in decompress_kernel\n");
+	debug_putstr("early console in extract_kernel\n");
 
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
@@ -421,16 +359,16 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	debug_putaddr(input_len);
 	debug_putaddr(output);
 	debug_putaddr(output_len);
-	debug_putaddr(run_size);
+	debug_putaddr(kernel_total_size);
 
 	/*
 	 * The memory hole needed for the kernel is the larger of either
 	 * the entire decompressed kernel plus relocation table, or the
 	 * entire decompressed kernel plus .bss and .brk sections.
 	 */
-	output = choose_kernel_location(real_mode, input_data, input_len, output,
-					output_len > run_size ? output_len
-							      : run_size);
+	output = choose_random_location((unsigned long)input_data, input_len,
+					(unsigned long)output,
+					max(output_len, kernel_total_size));
 
 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 3783dc3e10b3..b6fec1ff10e4 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -32,7 +32,7 @@
 /* misc.c */
 extern memptr free_mem_ptr;
 extern memptr free_mem_end_ptr;
-extern struct boot_params *real_mode;		/* Pointer to real-mode data */
+extern struct boot_params *boot_params;
 void __putstr(const char *s);
 void __puthex(unsigned long value);
 #define error_putstr(__x)  __putstr(__x)
@@ -66,26 +66,35 @@ int cmdline_find_option_bool(const char *option);
 
 
 #if CONFIG_RANDOMIZE_BASE
-/* aslr.c */
-unsigned char *choose_kernel_location(struct boot_params *boot_params,
-				      unsigned char *input,
+/* kaslr.c */
+unsigned char *choose_random_location(unsigned long input_ptr,
 				      unsigned long input_size,
-				      unsigned char *output,
+				      unsigned long output_ptr,
 				      unsigned long output_size);
 /* cpuflags.c */
 bool has_cpuflag(int flag);
 #else
 static inline
-unsigned char *choose_kernel_location(struct boot_params *boot_params,
-				      unsigned char *input,
+unsigned char *choose_random_location(unsigned long input_ptr,
 				      unsigned long input_size,
-				      unsigned char *output,
+				      unsigned long output_ptr,
 				      unsigned long output_size)
 {
-	return output;
+	return (unsigned char *)output_ptr;
 }
 #endif
 
+#ifdef CONFIG_X86_64
+void add_identity_map(unsigned long start, unsigned long size);
+void finalize_identity_maps(void);
+extern unsigned char _pgtable[];
+#else
+static inline void add_identity_map(unsigned long start, unsigned long size)
+{ }
+static inline void finalize_identity_maps(void)
+{ }
+#endif
+
 #ifdef CONFIG_EARLY_PRINTK
 /* early_serial_console.c */
 extern int early_serial_base;
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index d8222f213182..72bad2c8debe 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -18,11 +18,10 @@
  *
  *  H. Peter Anvin <hpa@linux.intel.com>
  *
- * ----------------------------------------------------------------------- */
-
-/*
- * Compute the desired load offset from a compressed program; outputs
- * a small assembly wrapper with the appropriate symbols defined.
+ * -----------------------------------------------------------------------
+ *
+ * Outputs a small assembly wrapper with the appropriate symbols defined.
+ *
  */
 
 #include <stdlib.h>
@@ -35,14 +34,11 @@ int main(int argc, char *argv[])
 {
 	uint32_t olen;
 	long ilen;
-	unsigned long offs;
-	unsigned long run_size;
 	FILE *f = NULL;
 	int retval = 1;
 
-	if (argc < 3) {
-		fprintf(stderr, "Usage: %s compressed_file run_size\n",
-				argv[0]);
+	if (argc < 2) {
+		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
 		goto bail;
 	}
 
@@ -67,29 +63,11 @@ int main(int argc, char *argv[])
 	ilen = ftell(f);
 	olen = get_unaligned_le32(&olen);
 
-	/*
-	 * Now we have the input (compressed) and output (uncompressed)
-	 * sizes, compute the necessary decompression offset...
-	 */
-
-	offs = (olen > ilen) ? olen - ilen : 0;
-	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
-	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
-	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
-	run_size = atoi(argv[2]);
-
 	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");
 	printf("z_input_len = %lu\n", ilen);
 	printf(".globl z_output_len\n");
 	printf("z_output_len = %lu\n", (unsigned long)olen);
-	printf(".globl z_extract_offset\n");
-	printf("z_extract_offset = 0x%lx\n", offs);
-	/* z_extract_offset_negative allows simplification of head_32.S */
-	printf(".globl z_extract_offset_negative\n");
-	printf("z_extract_offset_negative = -0x%lx\n", offs);
-	printf(".globl z_run_size\n");
-	printf("z_run_size = %lu\n", run_size);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
new file mode 100644
index 000000000000..34b95df14e69
--- /dev/null
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -0,0 +1,129 @@
+/*
+ * This code is used on x86_64 to create page table identity mappings on
+ * demand by building up a new set of page tables (or appending to the
+ * existing ones), and then switching over to them when ready.
+ */
+
+/*
+ * Since we're dealing with identity mappings, physical and virtual
+ * addresses are the same, so override these defines which are ultimately
+ * used by the headers in misc.h.
+ */
+#define __pa(x)  ((unsigned long)(x))
+#define __va(x)  ((void *)((unsigned long)(x)))
+
+#include "misc.h"
+
+/* These actually do the work of building the kernel identity maps. */
+#include <asm/init.h>
+#include <asm/pgtable.h>
+#include "../../mm/ident_map.c"
+
+/* Used by pgtable.h asm code to force instruction serialization. */
+unsigned long __force_order;
+
+/* Used to track our page table allocation area. */
+struct alloc_pgt_data {
+	unsigned char *pgt_buf;
+	unsigned long pgt_buf_size;
+	unsigned long pgt_buf_offset;
+};
+
+/*
+ * Allocates space for a page table entry, using struct alloc_pgt_data
+ * above. Besides the local callers, this is used as the allocation
+ * callback in mapping_info below.
+ */
+static void *alloc_pgt_page(void *context)
+{
+	struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
+	unsigned char *entry;
+
+	/* Validate there is space available for a new page. */
+	if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
+		debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+		return NULL;
+	}
+
+	entry = pages->pgt_buf + pages->pgt_buf_offset;
+	pages->pgt_buf_offset += PAGE_SIZE;
+
+	return entry;
+}
+
+/* Used to track our allocated page tables. */
+static struct alloc_pgt_data pgt_data;
+
+/* The top level page table entry pointer. */
+static unsigned long level4p;
+
+/* Locates and clears a region for a new top level page table. */
+static void prepare_level4(void)
+{
+	/*
+	 * It should be impossible for this not to already be true,
+	 * but since calling this a second time would rewind the other
+	 * counters, let's just make sure this is reset too.
+	 */
+	pgt_data.pgt_buf_offset = 0;
+
+	/*
+	 * If we came here via startup_32(), cr3 will be _pgtable already
+	 * and we must append to the existing area instead of entirely
+	 * overwriting it.
+	 */
+	level4p = read_cr3();
+	if (level4p == (unsigned long)_pgtable) {
+		debug_putstr("booted via startup_32()\n");
+		pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
+		pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
+		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+	} else {
+		debug_putstr("booted via startup_64()\n");
+		pgt_data.pgt_buf = _pgtable;
+		pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
+		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+		level4p = (unsigned long)alloc_pgt_page(&pgt_data);
+	}
+}
+
+/*
+ * Adds the specified range to what will become the new identity mappings.
+ * Once all ranges have been added, the new mapping is activated by calling
+ * finalize_identity_maps() below.
+ */
+void add_identity_map(unsigned long start, unsigned long size)
+{
+	struct x86_mapping_info mapping_info = {
+		.alloc_pgt_page	= alloc_pgt_page,
+		.context	= &pgt_data,
+		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+	};
+	unsigned long end = start + size;
+
+	/* Make sure we have a top level page table ready to use. */
+	if (!level4p)
+		prepare_level4();
+
+	/* Align boundary to 2M. */
+	start = round_down(start, PMD_SIZE);
+	end = round_up(end, PMD_SIZE);
+	if (start >= end)
+		return;
+
+	/* Build the mapping. */
+	kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p,
+				  start, end);
+}
+
+/*
+ * This switches the page tables to the new level4 that has been built
+ * via calls to add_identity_map() above. If booted via startup_32(),
+ * this is effectively a no-op.
+ */
+void finalize_identity_maps(void)
+{
+	write_cr3(level4p);
+}
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index 00e788be1db9..cea140ce6b42 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -1,7 +1,16 @@
+/*
+ * This provides an optimized implementation of memcpy, and a simplified
+ * implementation of memset and memmove. These are used here because the
+ * standard kernel runtime versions are not yet available and we don't
+ * trust the gcc built-in implementations as they may do unexpected things
+ * (e.g. FPU ops) in the minimal decompression stub execution environment.
+ */
+#include "error.h"
+
 #include "../string.c"
 
 #ifdef CONFIG_X86_32
-void *memcpy(void *dest, const void *src, size_t n)
+static void *__memcpy(void *dest, const void *src, size_t n)
 {
 	int d0, d1, d2;
 	asm volatile(
@@ -15,7 +24,7 @@ void *memcpy(void *dest, const void *src, size_t n)
 	return dest;
 }
 #else
-void *memcpy(void *dest, const void *src, size_t n)
+static void *__memcpy(void *dest, const void *src, size_t n)
 {
 	long d0, d1, d2;
 	asm volatile(
@@ -39,3 +48,27 @@ void *memset(void *s, int c, size_t n)
 		ss[i] = c;
 	return s;
 }
+
+void *memmove(void *dest, const void *src, size_t n)
+{
+	unsigned char *d = dest;
+	const unsigned char *s = src;
+
+	if (d <= s || d - s >= n)
+		return __memcpy(dest, src, n);
+
+	while (n-- > 0)
+		d[n] = s[n];
+
+	return dest;
+}
+
+/* Detect and warn about potential overlaps, but handle them with memmove. */
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	if (dest > src && dest - src < n) {
+		warn("Avoiding potentially unsafe overlapping memcpy()!");
+		return memmove(dest, src, n);
+	}
+	return __memcpy(dest, src, n);
+}
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 34d047c98284..e24e0a0c90c9 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -70,5 +70,6 @@ SECTIONS
 		_epgtable = . ;
 	}
 #endif
+	. = ALIGN(PAGE_SIZE);	/* keep ZO size page aligned */
 	_end = .;
 }
diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c
index 45a07684bbab..f0b8d6d93164 100644
--- a/arch/x86/boot/early_serial_console.c
+++ b/arch/x86/boot/early_serial_console.c
@@ -1,3 +1,7 @@
+/*
+ * Serial port routines for use during early boot reporting. This code is
+ * included from both the compressed kernel and the regular kernel.
+ */
 #include "boot.h"
 
 #define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 6236b9ec4b76..3dd5be33aaa7 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -440,13 +440,116 @@ setup_data:		.quad 0			# 64-bit physical pointer to
 
 pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 
-#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_extract_offset)
+#
+# Getting to provably safe in-place decompression is hard. Worst case
+# behaviours need to be analyzed. Here let's take the decompression of
+# a gzip-compressed kernel as example, to illustrate it:
+#
+# The file layout of gzip compressed kernel is:
+#
+#    magic[2]
+#    method[1]
+#    flags[1]
+#    timestamp[4]
+#    extraflags[1]
+#    os[1]
+#    compressed data blocks[N]
+#    crc[4] orig_len[4]
+#
+# ... resulting in +18 bytes overhead of uncompressed data.
+#
+# (For more information, please refer to RFC 1951 and RFC 1952.)
+#
+# Files divided into blocks
+# 1 bit (last block flag)
+# 2 bits (block type)
+#
+# 1 block occurs every 32K -1 bytes or when there 50% compression
+# has been achieved. The smallest block type encoding is always used.
+#
+# stored:
+#    32 bits length in bytes.
+#
+# fixed:
+#    magic fixed tree.
+#    symbols.
+#
+# dynamic:
+#    dynamic tree encoding.
+#    symbols.
+#
+#
+# The buffer for decompression in place is the length of the uncompressed
+# data, plus a small amount extra to keep the algorithm safe. The
+# compressed data is placed at the end of the buffer.  The output pointer
+# is placed at the start of the buffer and the input pointer is placed
+# where the compressed data starts. Problems will occur when the output
+# pointer overruns the input pointer.
+#
+# The output pointer can only overrun the input pointer if the input
+# pointer is moving faster than the output pointer.  A condition only
+# triggered by data whose compressed form is larger than the uncompressed
+# form.
+#
+# The worst case at the block level is a growth of the compressed data
+# of 5 bytes per 32767 bytes.
+#
+# The worst case internal to a compressed block is very hard to figure.
+# The worst case can at least be bounded by having one bit that represents
+# 32764 bytes and then all of the rest of the bytes representing the very
+# very last byte.
+#
+# All of which is enough to compute an amount of extra data that is required
+# to be safe.  To avoid problems at the block level allocating 5 extra bytes
+# per 32767 bytes of data is sufficient.  To avoid problems internal to a
+# block adding an extra 32767 bytes (the worst case uncompressed block size)
+# is sufficient, to ensure that in the worst case the decompressed data for
+# block will stop the byte before the compressed data for a block begins.
+# To avoid problems with the compressed data's meta information an extra 18
+# bytes are needed.  Leading to the formula:
+#
+# extra_bytes = (uncompressed_size >> 12) + 32768 + 18
+#
+# Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+# Adding 32768 instead of 32767 just makes for round numbers.
+#
+# Above analysis is for decompressing gzip compressed kernel only. Up to
+# now 6 different decompressor are supported all together. And among them
+# xz stores data in chunks and has maximum chunk of 64K. Hence safety
+# margin should be updated to cover all decompressors so that we don't
+# need to deal with each of them separately. Please check
+# the description in lib/decompressor_xxx.c for specific information.
+#
+# extra_bytes = (uncompressed_size >> 12) + 65536 + 128
+
+#define ZO_z_extra_bytes	((ZO_z_output_len >> 12) + 65536 + 128)
+#if ZO_z_output_len > ZO_z_input_len
+# define ZO_z_extract_offset	(ZO_z_output_len + ZO_z_extra_bytes - \
+				 ZO_z_input_len)
+#else
+# define ZO_z_extract_offset	ZO_z_extra_bytes
+#endif
+
+/*
+ * The extract_offset has to be bigger than ZO head section. Otherwise when
+ * the head code is running to move ZO to the end of the buffer, it will
+ * overwrite the head code itself.
+ */
+#if (ZO__ehead - ZO_startup_32) > ZO_z_extract_offset
+# define ZO_z_min_extract_offset ((ZO__ehead - ZO_startup_32 + 4095) & ~4095)
+#else
+# define ZO_z_min_extract_offset ((ZO_z_extract_offset + 4095) & ~4095)
+#endif
+
+#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_min_extract_offset)
+
 #define VO_INIT_SIZE	(VO__end - VO__text)
 #if ZO_INIT_SIZE > VO_INIT_SIZE
-#define INIT_SIZE ZO_INIT_SIZE
+# define INIT_SIZE ZO_INIT_SIZE
 #else
-#define INIT_SIZE VO_INIT_SIZE
+# define INIT_SIZE VO_INIT_SIZE
 #endif
+
 init_size:		.long INIT_SIZE		# kernel initialization size
 handover_offset:	.long 0			# Filled in by build.c
 
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 4f404a64681b..0c8d7963483c 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -173,6 +173,7 @@ CONFIG_TIGON3=y
 CONFIG_NET_TULIP=y
 CONFIG_E100=y
 CONFIG_E1000=y
+CONFIG_E1000E=y
 CONFIG_SKY2=y
 CONFIG_FORCEDETH=y
 CONFIG_8139TOO=y
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 064c7e2bd7c8..5b7fa1471007 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1477,7 +1477,7 @@ static int __init aesni_init(void)
 	}
 	aesni_ctr_enc_tfm = aesni_ctr_enc;
 #ifdef CONFIG_AS_AVX
-	if (cpu_has_avx) {
+	if (boot_cpu_has(X86_FEATURE_AVX)) {
 		/* optimize performance of ctr mode encryption transform */
 		aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm;
 		pr_info("AES CTR mode by8 optimization enabled\n");
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index d84456924563..60907c139c4e 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -562,7 +562,10 @@ static int __init camellia_aesni_init(void)
 {
 	const char *feature_name;
 
-	if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+	if (!boot_cpu_has(X86_FEATURE_AVX) ||
+	    !boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 		pr_info("AVX2 or AES-NI instructions are not detected.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 93d8f295784e..d96429da88eb 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -554,7 +554,9 @@ static int __init camellia_aesni_init(void)
 {
 	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+	if (!boot_cpu_has(X86_FEATURE_AVX) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 		pr_info("AVX or AES-NI instructions are not detected.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 8baaff5af0b5..2d5c2e0bd939 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -129,7 +129,8 @@ static int __init chacha20_simd_mod_init(void)
 		return -ENODEV;
 
 #ifdef CONFIG_AS_AVX2
-	chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+	chacha20_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
+			    boot_cpu_has(X86_FEATURE_AVX2) &&
 			    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
 #endif
 	return crypto_register_alg(&alg);
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 4264a3d59589..e32142bc071d 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -179,11 +179,12 @@ static struct shash_alg alg = {
 
 static int __init poly1305_simd_mod_init(void)
 {
-	if (!cpu_has_xmm2)
+	if (!boot_cpu_has(X86_FEATURE_XMM2))
 		return -ENODEV;
 
 #ifdef CONFIG_AS_AVX2
-	poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+	poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
+			    boot_cpu_has(X86_FEATURE_AVX2) &&
 			    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
 	alg.descsize = sizeof(struct poly1305_simd_desc_ctx);
 	if (poly1305_use_avx2)
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 6d198342e2de..870f6d812a2d 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -538,7 +538,7 @@ static int __init init(void)
 {
 	const char *feature_name;
 
-	if (!cpu_has_avx2 || !cpu_has_osxsave) {
+	if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 		pr_info("AVX2 instructions are not detected.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 8943407e8917..644f97ab8cac 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -600,7 +600,7 @@ static struct crypto_alg serpent_algs[10] = { {
 
 static int __init serpent_sse2_init(void)
 {
-	if (!cpu_has_xmm2) {
+	if (!boot_cpu_has(X86_FEATURE_XMM2)) {
 		printk(KERN_INFO "SSE2 instructions are not detected.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index 081255cea1ee..9c5af331a956 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -102,14 +102,14 @@ static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)(struct sha1_mb_mgr *st
 static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)(struct sha1_mb_mgr *state);
 static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)(struct sha1_mb_mgr *state);
 
-inline void sha1_init_digest(uint32_t *digest)
+static inline void sha1_init_digest(uint32_t *digest)
 {
 	static const uint32_t initial_digest[SHA1_DIGEST_LENGTH] = {SHA1_H0,
 					SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 };
 	memcpy(digest, initial_digest, sizeof(initial_digest));
 }
 
-inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2],
+static inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2],
 			 uint32_t total_len)
 {
 	uint32_t i = total_len & (SHA1_BLOCK_SIZE - 1);
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index dd14616b7739..1024e378a358 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -166,7 +166,7 @@ static struct shash_alg sha1_avx_alg = {
 static bool avx_usable(void)
 {
 	if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
-		if (cpu_has_avx)
+		if (boot_cpu_has(X86_FEATURE_AVX))
 			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 5f4d6086dc59..3ae0f43ebd37 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -201,7 +201,7 @@ static struct shash_alg sha256_avx_algs[] = { {
 static bool avx_usable(void)
 {
 	if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
-		if (cpu_has_avx)
+		if (boot_cpu_has(X86_FEATURE_AVX))
 			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 34e5083d6f36..0b17c83d027d 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -151,7 +151,7 @@ asmlinkage void sha512_transform_avx(u64 *digest, const char *data,
 static bool avx_usable(void)
 {
 	if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
-		if (cpu_has_avx)
+		if (boot_cpu_has(X86_FEATURE_AVX))
 			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index e79d93d44ecd..ec138e538c44 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -191,7 +191,7 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
 
 long syscall_trace_enter(struct pt_regs *regs)
 {
-	u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+	u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 	unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch);
 
 	if (phase1_result == 0)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 10868aa734dc..983e5d3a0d27 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -207,10 +207,7 @@
 ENTRY(ret_from_fork)
 	pushl	%eax
 	call	schedule_tail
-	GET_THREAD_INFO(%ebp)
 	popl	%eax
-	pushl	$0x0202				# Reset kernel eflags
-	popfl
 
 	/* When we fork, we trace the syscall return in the child, too. */
 	movl    %esp, %eax
@@ -221,10 +218,7 @@ END(ret_from_fork)
 ENTRY(ret_from_kernel_thread)
 	pushl	%eax
 	call	schedule_tail
-	GET_THREAD_INFO(%ebp)
 	popl	%eax
-	pushl	$0x0202				# Reset kernel eflags
-	popfl
 	movl	PT_EBP(%esp), %eax
 	call	*PT_EBX(%esp)
 	movl	$0, PT_EAX(%esp)
@@ -251,7 +245,6 @@ ENDPROC(ret_from_kernel_thread)
 ret_from_exception:
 	preempt_stop(CLBR_ANY)
 ret_from_intr:
-	GET_THREAD_INFO(%ebp)
 #ifdef CONFIG_VM86
 	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS and CS
 	movb	PT_CS(%esp), %al
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 858b555e274b..9ee0da1807ed 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -372,9 +372,6 @@ END(ptregs_\func)
 ENTRY(ret_from_fork)
 	LOCK ; btr $TIF_FORK, TI_flags(%r8)
 
-	pushq	$0x0002
-	popfq					/* reset kernel eflags */
-
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
 	testb	$3, CS(%rsp)			/* from kernel_thread? */
@@ -781,19 +778,25 @@ ENTRY(native_load_gs_index)
 	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	SWAPGS
-gs_change:
+.Lgs_change:
 	movl	%edi, %gs
-2:	mfence					/* workaround */
+2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	SWAPGS
 	popfq
 	ret
 END(native_load_gs_index)
 
-	_ASM_EXTABLE(gs_change, bad_gs)
+	_ASM_EXTABLE(.Lgs_change, bad_gs)
 	.section .fixup, "ax"
 	/* running with kernelgs */
 bad_gs:
 	SWAPGS					/* switch back to user gs */
+.macro ZAP_GS
+	/* This can't be a string because the preprocessor needs to see it. */
+	movl $__USER_DS, %eax
+	movl %eax, %gs
+.endm
+	ALTERNATIVE "", "ZAP_GS", X86_BUG_NULL_SEG
 	xorl	%eax, %eax
 	movl	%eax, %gs
 	jmp	2b
@@ -1019,13 +1022,13 @@ ENTRY(error_entry)
 	movl	%ecx, %eax			/* zero extend */
 	cmpq	%rax, RIP+8(%rsp)
 	je	.Lbstep_iret
-	cmpq	$gs_change, RIP+8(%rsp)
+	cmpq	$.Lgs_change, RIP+8(%rsp)
 	jne	.Lerror_entry_done
 
 	/*
-	 * hack: gs_change can fail with user gsbase.  If this happens, fix up
+	 * hack: .Lgs_change can fail with user gsbase.  If this happens, fix up
 	 * gsbase and proceed.  We'll fix up the exception and land in
-	 * gs_change's error handler with kernel gsbase.
+	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	jmp	.Lerror_entry_from_usermode_swapgs
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 847f2f0c31e5..e1721dafbcb1 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -72,24 +72,23 @@ ENTRY(entry_SYSENTER_compat)
 	pushfq				/* pt_regs->flags (except IF = 0) */
 	orl	$X86_EFLAGS_IF, (%rsp)	/* Fix saved flags */
 	pushq	$__USER32_CS		/* pt_regs->cs */
-	xorq    %r8,%r8
-	pushq	%r8			/* pt_regs->ip = 0 (placeholder) */
+	pushq	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
-	pushq   %r8                     /* pt_regs->r12 = 0 */
-	pushq   %r8                     /* pt_regs->r13 = 0 */
-	pushq   %r8                     /* pt_regs->r14 = 0 */
-	pushq   %r8                     /* pt_regs->r15 = 0 */
+	pushq   $0			/* pt_regs->r12 = 0 */
+	pushq   $0			/* pt_regs->r13 = 0 */
+	pushq   $0			/* pt_regs->r14 = 0 */
+	pushq   $0			/* pt_regs->r15 = 0 */
 	cld
 
 	/*
@@ -205,17 +204,16 @@ ENTRY(entry_SYSCALL_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	xorq    %r8,%r8
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
-	pushq   %r8                     /* pt_regs->r12 = 0 */
-	pushq   %r8                     /* pt_regs->r13 = 0 */
-	pushq   %r8                     /* pt_regs->r14 = 0 */
-	pushq   %r8                     /* pt_regs->r15 = 0 */
+	pushq   $0			/* pt_regs->r12 = 0 */
+	pushq   $0			/* pt_regs->r13 = 0 */
+	pushq   $0			/* pt_regs->r14 = 0 */
+	pushq   $0			/* pt_regs->r15 = 0 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -316,11 +314,10 @@ ENTRY(entry_INT80_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	xorq    %r8,%r8
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
 	pushq   %r12                    /* pt_regs->r12 */
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index cac6d17ce5db..555263e385c9 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -374,3 +374,5 @@
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
 545	x32	execveat		compat_sys_execveat/ptregs
+534	x32	preadv2			compat_sys_preadv2
+535	x32	pwritev2		compat_sys_pwritev2
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 03c3eb77bfce..2f02d23a05ef 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -13,7 +13,6 @@
 
 #include <uapi/linux/time.h>
 #include <asm/vgtod.h>
-#include <asm/hpet.h>
 #include <asm/vvar.h>
 #include <asm/unistd.h>
 #include <asm/msr.h>
@@ -28,16 +27,6 @@ extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
 extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
 extern time_t __vdso_time(time_t *t);
 
-#ifdef CONFIG_HPET_TIMER
-extern u8 hpet_page
-	__attribute__((visibility("hidden")));
-
-static notrace cycle_t vread_hpet(void)
-{
-	return *(const volatile u32 *)(&hpet_page + HPET_COUNTER);
-}
-#endif
-
 #ifdef CONFIG_PARAVIRT_CLOCK
 extern u8 pvclock_page
 	__attribute__((visibility("hidden")));
@@ -195,10 +184,6 @@ notrace static inline u64 vgetsns(int *mode)
 
 	if (gtod->vclock_mode == VCLOCK_TSC)
 		cycles = vread_tsc();
-#ifdef CONFIG_HPET_TIMER
-	else if (gtod->vclock_mode == VCLOCK_HPET)
-		cycles = vread_hpet();
-#endif
 #ifdef CONFIG_PARAVIRT_CLOCK
 	else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
 		cycles = vread_pvclock(mode);
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 4158acc17df0..a708aa90b507 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - 3 * PAGE_SIZE;
+	vvar_start = . - 2 * PAGE_SIZE;
 	vvar_page = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
@@ -35,8 +35,7 @@ SECTIONS
 #undef __VVAR_KERNEL_LDS
 #undef EMIT_VVAR
 
-	hpet_page = vvar_start + PAGE_SIZE;
-	pvclock_page = vvar_start + 2 * PAGE_SIZE;
+	pvclock_page = vvar_start + PAGE_SIZE;
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 10f704584922..b3cf81333a54 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -18,7 +18,6 @@
 #include <asm/vdso.h>
 #include <asm/vvar.h>
 #include <asm/page.h>
-#include <asm/hpet.h>
 #include <asm/desc.h>
 #include <asm/cpufeature.h>
 
@@ -129,16 +128,6 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 	if (sym_offset == image->sym_vvar_page) {
 		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
 				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
-	} else if (sym_offset == image->sym_hpet_page) {
-#ifdef CONFIG_HPET_TIMER
-		if (hpet_address && vclock_was_used(VCLOCK_HPET)) {
-			ret = vm_insert_pfn_prot(
-				vma,
-				(unsigned long)vmf->virtual_address,
-				hpet_address >> PAGE_SHIFT,
-				pgprot_noncached(PAGE_READONLY));
-		}
-#endif
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
 			pvclock_pvti_cpu0_va();
diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
new file mode 100644
index 000000000000..98397db5ceae
--- /dev/null
+++ b/arch/x86/events/Kconfig
@@ -0,0 +1,36 @@
+menu "Performance monitoring"
+
+config PERF_EVENTS_INTEL_UNCORE
+	tristate "Intel uncore performance events"
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	default y
+	---help---
+	Include support for Intel uncore performance events. These are
+	available on NehalemEX and more modern processors.
+
+config PERF_EVENTS_INTEL_RAPL
+	tristate "Intel rapl performance events"
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	default y
+	---help---
+	Include support for Intel rapl performance events for power
+	monitoring on modern processors.
+
+config PERF_EVENTS_INTEL_CSTATE
+	tristate "Intel cstate performance events"
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	default y
+	---help---
+	Include support for Intel cstate performance events for power
+	monitoring on modern processors.
+
+config PERF_EVENTS_AMD_POWER
+	depends on PERF_EVENTS && CPU_SUP_AMD
+	tristate "AMD Processor Power Reporting Mechanism"
+	---help---
+	  Provide power reporting mechanism support for AMD processors.
+	  Currently, it leverages X86_FEATURE_ACC_POWER
+	  (CPUID Fn8000_0007_EDX[12]) interface to calculate the
+	  average power consumption on Family 15h processors.
+
+endmenu
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index f59618a39990..1d392c39fe56 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -6,9 +6,6 @@ obj-$(CONFIG_X86_LOCAL_APIC)            += amd/ibs.o msr.o
 ifdef CONFIG_AMD_IOMMU
 obj-$(CONFIG_CPU_SUP_AMD)               += amd/iommu.o
 endif
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/core.o intel/bts.o intel/cqm.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/cstate.o intel/ds.o intel/knc.o 
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/lbr.o intel/p4.o intel/p6.o intel/pt.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/rapl.o msr.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel/uncore.o intel/uncore_nhmex.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel/uncore_snb.o intel/uncore_snbep.o
+
+obj-$(CONFIG_CPU_SUP_INTEL)		+= msr.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 3db9569e658c..98ac57381bf9 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -263,6 +263,7 @@ static const struct attribute_group *amd_uncore_attr_groups[] = {
 };
 
 static struct pmu amd_nb_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
 	.attr_groups	= amd_uncore_attr_groups,
 	.name		= "amd_nb",
 	.event_init	= amd_uncore_event_init,
@@ -274,6 +275,7 @@ static struct pmu amd_nb_pmu = {
 };
 
 static struct pmu amd_l2_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
 	.attr_groups	= amd_uncore_attr_groups,
 	.name		= "amd_l2",
 	.event_init	= amd_uncore_event_init,
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 041e442a3e28..73a75aa5a66d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -360,6 +360,9 @@ int x86_add_exclusive(unsigned int what)
 {
 	int i;
 
+	if (x86_pmu.lbr_pt_coexist)
+		return 0;
+
 	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
 		mutex_lock(&pmc_reserve_mutex);
 		for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
@@ -380,6 +383,9 @@ fail_unlock:
 
 void x86_del_exclusive(unsigned int what)
 {
+	if (x86_pmu.lbr_pt_coexist)
+		return;
+
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
 	atomic_dec(&active_events);
 }
@@ -1518,7 +1524,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 
 static void __init pmu_check_apic(void)
 {
-	if (cpu_has_apic)
+	if (boot_cpu_has(X86_FEATURE_APIC))
 		return;
 
 	x86_pmu.apic = 0;
@@ -2177,7 +2183,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 * cap_user_time_zero doesn't make sense when we're using a different
 	 * time base for the records.
 	 */
-	if (event->clock == &local_clock) {
+	if (!event->attr.use_clockid) {
 		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = data->cyc2ns_offset;
 	}
@@ -2277,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
 		frame.return_address = 0;
@@ -2337,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 
 	pagefault_disable();
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
new file mode 100644
index 000000000000..3660b2cf245a
--- /dev/null
+++ b/arch/x86/events/intel/Makefile
@@ -0,0 +1,9 @@
+obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
+intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
+intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
+intel-cstate-objs			:= cstate.o
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index b99dc9258c0f..0a6e393a2e62 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -171,18 +171,6 @@ static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head)
 	memset(page_address(phys->page) + index, 0, phys->size - index);
 }
 
-static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts)
-{
-	if (buf->snapshot)
-		return false;
-
-	if (local_read(&buf->data_size) >= bts->handle.size ||
-	    bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE)
-		return true;
-
-	return false;
-}
-
 static void bts_update(struct bts_ctx *bts)
 {
 	int cpu = raw_smp_processor_id();
@@ -213,18 +201,15 @@ static void bts_update(struct bts_ctx *bts)
 	}
 }
 
+static int
+bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+
 static void __bts_event_start(struct perf_event *event)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct bts_buffer *buf = perf_get_aux(&bts->handle);
 	u64 config = 0;
 
-	if (!buf || bts_buffer_is_full(buf, bts))
-		return;
-
-	event->hw.itrace_started = 1;
-	event->hw.state = 0;
-
 	if (!buf->snapshot)
 		config |= ARCH_PERFMON_EVENTSEL_INT;
 	if (!event->attr.exclude_kernel)
@@ -241,16 +226,41 @@ static void __bts_event_start(struct perf_event *event)
 	wmb();
 
 	intel_pmu_enable_bts(config);
+
 }
 
 static void bts_event_start(struct perf_event *event, int flags)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_buffer *buf;
+
+	buf = perf_aux_output_begin(&bts->handle, event);
+	if (!buf)
+		goto fail_stop;
+
+	if (bts_buffer_reset(buf, &bts->handle))
+		goto fail_end_stop;
+
+	bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
+	bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
+	bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold;
+
+	event->hw.itrace_started = 1;
+	event->hw.state = 0;
 
 	__bts_event_start(event);
 
 	/* PMI handler: this counter is running and likely generating PMIs */
 	ACCESS_ONCE(bts->started) = 1;
+
+	return;
+
+fail_end_stop:
+	perf_aux_output_end(&bts->handle, 0, false);
+
+fail_stop:
+	event->hw.state = PERF_HES_STOPPED;
 }
 
 static void __bts_event_stop(struct perf_event *event)
@@ -269,15 +279,32 @@ static void __bts_event_stop(struct perf_event *event)
 
 static void bts_event_stop(struct perf_event *event, int flags)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_buffer *buf = perf_get_aux(&bts->handle);
 
 	/* PMI handler: don't restart this counter */
 	ACCESS_ONCE(bts->started) = 0;
 
 	__bts_event_stop(event);
 
-	if (flags & PERF_EF_UPDATE)
+	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
+
+		if (buf) {
+			if (buf->snapshot)
+				bts->handle.head =
+					local_xchg(&buf->data_size,
+						   buf->nr_pages << PAGE_SHIFT);
+			perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
+					    !!local_xchg(&buf->lost, 0));
+		}
+
+		cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
+		cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base;
+		cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum;
+		cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold;
+	}
 }
 
 void intel_bts_enable_local(void)
@@ -417,34 +444,14 @@ int intel_bts_interrupt(void)
 
 static void bts_event_del(struct perf_event *event, int mode)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
-
 	bts_event_stop(event, PERF_EF_UPDATE);
-
-	if (buf) {
-		if (buf->snapshot)
-			bts->handle.head =
-				local_xchg(&buf->data_size,
-					   buf->nr_pages << PAGE_SHIFT);
-		perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
-				    !!local_xchg(&buf->lost, 0));
-	}
-
-	cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
-	cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base;
-	cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum;
-	cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold;
 }
 
 static int bts_event_add(struct perf_event *event, int mode)
 {
-	struct bts_buffer *buf;
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int ret = -EBUSY;
 
 	event->hw.state = PERF_HES_STOPPED;
 
@@ -454,26 +461,10 @@ static int bts_event_add(struct perf_event *event, int mode)
 	if (bts->handle.event)
 		return -EBUSY;
 
-	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
-		return -EINVAL;
-
-	ret = bts_buffer_reset(buf, &bts->handle);
-	if (ret) {
-		perf_aux_output_end(&bts->handle, 0, false);
-		return ret;
-	}
-
-	bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
-	bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
-	bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold;
-
 	if (mode & PERF_EF_START) {
 		bts_event_start(event, 0);
-		if (hwc->state & PERF_HES_STOPPED) {
-			bts_event_del(event, 0);
-			return -EBUSY;
-		}
+		if (hwc->state & PERF_HES_STOPPED)
+			return -EINVAL;
 	}
 
 	return 0;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6fd4dbcf820..7c666958a625 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1465,6 +1465,140 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
+static struct extra_reg intel_glm_extra_regs[] __read_mostly = {
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x360005ffbfull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+#define GLM_DEMAND_DATA_RD		BIT_ULL(0)
+#define GLM_DEMAND_RFO			BIT_ULL(1)
+#define GLM_ANY_RESPONSE		BIT_ULL(16)
+#define GLM_SNP_NONE_OR_MISS		BIT_ULL(33)
+#define GLM_DEMAND_READ			GLM_DEMAND_DATA_RD
+#define GLM_DEMAND_WRITE		GLM_DEMAND_RFO
+#define GLM_DEMAND_PREFETCH		(SNB_PF_DATA_RD|SNB_PF_RFO)
+#define GLM_LLC_ACCESS			GLM_ANY_RESPONSE
+#define GLM_SNP_ANY			(GLM_SNP_NONE_OR_MISS|SNB_NO_FWD|SNB_HITM)
+#define GLM_LLC_MISS			(GLM_SNP_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 glm_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x0380,	/* ICACHE.ACCESSES */
+			[C(RESULT_MISS)]	= 0x0280,	/* ICACHE.MISSES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c0,	/* INST_RETIRED.ANY_P */
+			[C(RESULT_MISS)]	= 0x0481,	/* ITLB.MISS */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c4,	/* BR_INST_RETIRED.ALL_BRANCHES */
+			[C(RESULT_MISS)]	= 0x00c5,	/* BR_MISP_RETIRED.ALL_BRANCHES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+};
+
+static __initconst const u64 glm_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_PREFETCH|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_PREFETCH|
+						  GLM_LLC_MISS,
+		},
+	},
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -3447,7 +3581,7 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
-		intel_pmu_lbr_init_atom();
+		intel_pmu_lbr_init_slm();
 
 		x86_pmu.event_constraints = intel_slm_event_constraints;
 		x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
@@ -3456,6 +3590,30 @@ __init int intel_pmu_init(void)
 		pr_cont("Silvermont events, ");
 		break;
 
+	case 92: /* 14nm Atom "Goldmont" */
+	case 95: /* 14nm Atom "Goldmont Denverton" */
+		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_glm_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_glm_extra_regs;
+		/*
+		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+		 * for precise cycles.
+		 * :pp is identical to :ppp
+		 */
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		pr_cont("Goldmont events, ");
+		break;
+
 	case 37: /* 32nm Westmere    */
 	case 44: /* 32nm Westmere-EP */
 	case 47: /* 32nm Westmere-EX */
@@ -3708,7 +3866,7 @@ __init int intel_pmu_init(void)
 				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
 			c->idxmsk64 &=
-				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
 			c->weight = hweight64(c->idxmsk64);
 		}
 	}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 7946c4231169..9ba4e4136a15 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -91,6 +91,8 @@
 #include <asm/cpu_device_id.h>
 #include "../perf_event.h"
 
+MODULE_LICENSE("GPL");
+
 #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format)		\
 static ssize_t __cstate_##_var##_show(struct kobject *kobj,	\
 				struct kobj_attribute *attr,	\
@@ -106,22 +108,27 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev,
 				       struct device_attribute *attr,
 				       char *buf);
 
+/* Model -> events mapping */
+struct cstate_model {
+	unsigned long		core_events;
+	unsigned long		pkg_events;
+	unsigned long		quirks;
+};
+
+/* Quirk flags */
+#define SLM_PKG_C6_USE_C7_MSR	(1UL << 0)
+
 struct perf_cstate_msr {
 	u64	msr;
 	struct	perf_pmu_events_attr *attr;
-	bool	(*test)(int idx);
 };
 
 
 /* cstate_core PMU */
-
 static struct pmu cstate_core_pmu;
 static bool has_cstate_core;
 
-enum perf_cstate_core_id {
-	/*
-	 * cstate_core events
-	 */
+enum perf_cstate_core_events {
 	PERF_CSTATE_CORE_C1_RES = 0,
 	PERF_CSTATE_CORE_C3_RES,
 	PERF_CSTATE_CORE_C6_RES,
@@ -130,69 +137,16 @@ enum perf_cstate_core_id {
 	PERF_CSTATE_CORE_EVENT_MAX,
 };
 
-bool test_core(int idx)
-{
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
-	    boot_cpu_data.x86 != 6)
-		return false;
-
-	switch (boot_cpu_data.x86_model) {
-	case 30: /* 45nm Nehalem    */
-	case 26: /* 45nm Nehalem-EP */
-	case 46: /* 45nm Nehalem-EX */
-
-	case 37: /* 32nm Westmere    */
-	case 44: /* 32nm Westmere-EP */
-	case 47: /* 32nm Westmere-EX */
-		if (idx == PERF_CSTATE_CORE_C3_RES ||
-		    idx == PERF_CSTATE_CORE_C6_RES)
-			return true;
-		break;
-	case 42: /* 32nm SandyBridge         */
-	case 45: /* 32nm SandyBridge-E/EN/EP */
-
-	case 58: /* 22nm IvyBridge       */
-	case 62: /* 22nm IvyBridge-EP/EX */
-
-	case 60: /* 22nm Haswell Core */
-	case 63: /* 22nm Haswell Server */
-	case 69: /* 22nm Haswell ULT */
-	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
-
-	case 61: /* 14nm Broadwell Core-M */
-	case 86: /* 14nm Broadwell Xeon D */
-	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
-	case 79: /* 14nm Broadwell Server */
-
-	case 78: /* 14nm Skylake Mobile */
-	case 94: /* 14nm Skylake Desktop */
-		if (idx == PERF_CSTATE_CORE_C3_RES ||
-		    idx == PERF_CSTATE_CORE_C6_RES ||
-		    idx == PERF_CSTATE_CORE_C7_RES)
-			return true;
-		break;
-	case 55: /* 22nm Atom "Silvermont"                */
-	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
-	case 76: /* 14nm Atom "Airmont"                   */
-		if (idx == PERF_CSTATE_CORE_C1_RES ||
-		    idx == PERF_CSTATE_CORE_C6_RES)
-			return true;
-		break;
-	}
-
-	return false;
-}
-
 PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
 PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
 PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
 PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");
 
 static struct perf_cstate_msr core_msr[] = {
-	[PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES,		&evattr_cstate_core_c1,	test_core, },
-	[PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY,	&evattr_cstate_core_c3, test_core, },
-	[PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY,	&evattr_cstate_core_c6, test_core, },
-	[PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY,	&evattr_cstate_core_c7,	test_core, },
+	[PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES,		&evattr_cstate_core_c1 },
+	[PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY,	&evattr_cstate_core_c3 },
+	[PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY,	&evattr_cstate_core_c6 },
+	[PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY,	&evattr_cstate_core_c7 },
 };
 
 static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
@@ -234,18 +188,11 @@ static const struct attribute_group *core_attr_groups[] = {
 	NULL,
 };
 
-/* cstate_core PMU end */
-
-
 /* cstate_pkg PMU */
-
 static struct pmu cstate_pkg_pmu;
 static bool has_cstate_pkg;
 
-enum perf_cstate_pkg_id {
-	/*
-	 * cstate_pkg events
-	 */
+enum perf_cstate_pkg_events {
 	PERF_CSTATE_PKG_C2_RES = 0,
 	PERF_CSTATE_PKG_C3_RES,
 	PERF_CSTATE_PKG_C6_RES,
@@ -257,69 +204,6 @@ enum perf_cstate_pkg_id {
 	PERF_CSTATE_PKG_EVENT_MAX,
 };
 
-bool test_pkg(int idx)
-{
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
-	    boot_cpu_data.x86 != 6)
-		return false;
-
-	switch (boot_cpu_data.x86_model) {
-	case 30: /* 45nm Nehalem    */
-	case 26: /* 45nm Nehalem-EP */
-	case 46: /* 45nm Nehalem-EX */
-
-	case 37: /* 32nm Westmere    */
-	case 44: /* 32nm Westmere-EP */
-	case 47: /* 32nm Westmere-EX */
-		if (idx == PERF_CSTATE_CORE_C3_RES ||
-		    idx == PERF_CSTATE_CORE_C6_RES ||
-		    idx == PERF_CSTATE_CORE_C7_RES)
-			return true;
-		break;
-	case 42: /* 32nm SandyBridge         */
-	case 45: /* 32nm SandyBridge-E/EN/EP */
-
-	case 58: /* 22nm IvyBridge       */
-	case 62: /* 22nm IvyBridge-EP/EX */
-
-	case 60: /* 22nm Haswell Core */
-	case 63: /* 22nm Haswell Server */
-	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
-
-	case 61: /* 14nm Broadwell Core-M */
-	case 86: /* 14nm Broadwell Xeon D */
-	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
-	case 79: /* 14nm Broadwell Server */
-
-	case 78: /* 14nm Skylake Mobile */
-	case 94: /* 14nm Skylake Desktop */
-		if (idx == PERF_CSTATE_PKG_C2_RES ||
-		    idx == PERF_CSTATE_PKG_C3_RES ||
-		    idx == PERF_CSTATE_PKG_C6_RES ||
-		    idx == PERF_CSTATE_PKG_C7_RES)
-			return true;
-		break;
-	case 55: /* 22nm Atom "Silvermont"                */
-	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
-	case 76: /* 14nm Atom "Airmont"                   */
-		if (idx == PERF_CSTATE_CORE_C6_RES)
-			return true;
-		break;
-	case 69: /* 22nm Haswell ULT */
-		if (idx == PERF_CSTATE_PKG_C2_RES ||
-		    idx == PERF_CSTATE_PKG_C3_RES ||
-		    idx == PERF_CSTATE_PKG_C6_RES ||
-		    idx == PERF_CSTATE_PKG_C7_RES ||
-		    idx == PERF_CSTATE_PKG_C8_RES ||
-		    idx == PERF_CSTATE_PKG_C9_RES ||
-		    idx == PERF_CSTATE_PKG_C10_RES)
-			return true;
-		break;
-	}
-
-	return false;
-}
-
 PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
 PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
 PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
@@ -329,13 +213,13 @@ PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
 PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");
 
 static struct perf_cstate_msr pkg_msr[] = {
-	[PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY,	&evattr_cstate_pkg_c2,	test_pkg, },
-	[PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY,	&evattr_cstate_pkg_c3,	test_pkg, },
-	[PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY,	&evattr_cstate_pkg_c6,	test_pkg, },
-	[PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY,	&evattr_cstate_pkg_c7,	test_pkg, },
-	[PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY,	&evattr_cstate_pkg_c8,	test_pkg, },
-	[PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY,	&evattr_cstate_pkg_c9,	test_pkg, },
-	[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY,	&evattr_cstate_pkg_c10,	test_pkg, },
+	[PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY,	&evattr_cstate_pkg_c2 },
+	[PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY,	&evattr_cstate_pkg_c3 },
+	[PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY,	&evattr_cstate_pkg_c6 },
+	[PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY,	&evattr_cstate_pkg_c7 },
+	[PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY,	&evattr_cstate_pkg_c8 },
+	[PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY,	&evattr_cstate_pkg_c9 },
+	[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY,	&evattr_cstate_pkg_c10 },
 };
 
 static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
@@ -366,8 +250,6 @@ static const struct attribute_group *pkg_attr_groups[] = {
 	NULL,
 };
 
-/* cstate_pkg PMU end*/
-
 static ssize_t cstate_get_attr_cpumask(struct device *dev,
 				       struct device_attribute *attr,
 				       char *buf)
@@ -385,7 +267,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev,
 static int cstate_pmu_event_init(struct perf_event *event)
 {
 	u64 cfg = event->attr.config;
-	int ret = 0;
+	int cpu;
 
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
@@ -400,26 +282,36 @@ static int cstate_pmu_event_init(struct perf_event *event)
 	    event->attr.sample_period) /* no sampling */
 		return -EINVAL;
 
+	if (event->cpu < 0)
+		return -EINVAL;
+
 	if (event->pmu == &cstate_core_pmu) {
 		if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
 			return -EINVAL;
 		if (!core_msr[cfg].attr)
 			return -EINVAL;
 		event->hw.event_base = core_msr[cfg].msr;
+		cpu = cpumask_any_and(&cstate_core_cpu_mask,
+				      topology_sibling_cpumask(event->cpu));
 	} else if (event->pmu == &cstate_pkg_pmu) {
 		if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
 			return -EINVAL;
 		if (!pkg_msr[cfg].attr)
 			return -EINVAL;
 		event->hw.event_base = pkg_msr[cfg].msr;
-	} else
+		cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
+				      topology_core_cpumask(event->cpu));
+	} else {
 		return -ENOENT;
+	}
+
+	if (cpu >= nr_cpu_ids)
+		return -ENODEV;
 
-	/* must be done before validate_group */
+	event->cpu = cpu;
 	event->hw.config = cfg;
 	event->hw.idx = -1;
-
-	return ret;
+	return 0;
 }
 
 static inline u64 cstate_pmu_read_counter(struct perf_event *event)
@@ -469,172 +361,91 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode)
 	return 0;
 }
 
+/*
+ * Check if exiting cpu is the designated reader. If so migrate the
+ * events when there is a valid target available
+ */
 static void cstate_cpu_exit(int cpu)
 {
-	int i, id, target;
+	unsigned int target;
 
-	/* cpu exit for cstate core */
-	if (has_cstate_core) {
-		id = topology_core_id(cpu);
-		target = -1;
-
-		for_each_online_cpu(i) {
-			if (i == cpu)
-				continue;
-			if (id == topology_core_id(i)) {
-				target = i;
-				break;
-			}
-		}
-		if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0)
+	if (has_cstate_core &&
+	    cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) {
+
+		target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
+		/* Migrate events if there is a valid target */
+		if (target < nr_cpu_ids) {
 			cpumask_set_cpu(target, &cstate_core_cpu_mask);
-		WARN_ON(cpumask_empty(&cstate_core_cpu_mask));
-		if (target >= 0)
 			perf_pmu_migrate_context(&cstate_core_pmu, cpu, target);
+		}
 	}
 
-	/* cpu exit for cstate pkg */
-	if (has_cstate_pkg) {
-		id = topology_physical_package_id(cpu);
-		target = -1;
-
-		for_each_online_cpu(i) {
-			if (i == cpu)
-				continue;
-			if (id == topology_physical_package_id(i)) {
-				target = i;
-				break;
-			}
-		}
-		if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0)
+	if (has_cstate_pkg &&
+	    cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
+
+		target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+		/* Migrate events if there is a valid target */
+		if (target < nr_cpu_ids) {
 			cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
-		WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask));
-		if (target >= 0)
 			perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
+		}
 	}
 }
 
 static void cstate_cpu_init(int cpu)
 {
-	int i, id;
+	unsigned int target;
 
-	/* cpu init for cstate core */
-	if (has_cstate_core) {
-		id = topology_core_id(cpu);
-		for_each_cpu(i, &cstate_core_cpu_mask) {
-			if (id == topology_core_id(i))
-				break;
-		}
-		if (i >= nr_cpu_ids)
-			cpumask_set_cpu(cpu, &cstate_core_cpu_mask);
-	}
+	/*
+	 * If this is the first online thread of that core, set it in
+	 * the core cpu mask as the designated reader.
+	 */
+	target = cpumask_any_and(&cstate_core_cpu_mask,
+				 topology_sibling_cpumask(cpu));
 
-	/* cpu init for cstate pkg */
-	if (has_cstate_pkg) {
-		id = topology_physical_package_id(cpu);
-		for_each_cpu(i, &cstate_pkg_cpu_mask) {
-			if (id == topology_physical_package_id(i))
-				break;
-		}
-		if (i >= nr_cpu_ids)
-			cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
-	}
+	if (has_cstate_core && target >= nr_cpu_ids)
+		cpumask_set_cpu(cpu, &cstate_core_cpu_mask);
+
+	/*
+	 * If this is the first online thread of that package, set it
+	 * in the package cpu mask as the designated reader.
+	 */
+	target = cpumask_any_and(&cstate_pkg_cpu_mask,
+				 topology_core_cpumask(cpu));
+	if (has_cstate_pkg && target >= nr_cpu_ids)
+		cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
 }
 
 static int cstate_cpu_notifier(struct notifier_block *self,
-				  unsigned long action, void *hcpu)
+			       unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		break;
 	case CPU_STARTING:
 		cstate_cpu_init(cpu);
 		break;
-	case CPU_UP_CANCELED:
-	case CPU_DYING:
-		break;
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		break;
 	case CPU_DOWN_PREPARE:
 		cstate_cpu_exit(cpu);
 		break;
 	default:
 		break;
 	}
-
 	return NOTIFY_OK;
 }
 
-/*
- * Probe the cstate events and insert the available one into sysfs attrs
- * Return false if there is no available events.
- */
-static bool cstate_probe_msr(struct perf_cstate_msr *msr,
-			     struct attribute	**events_attrs,
-			     int max_event_nr)
-{
-	int i, j = 0;
-	u64 val;
-
-	/* Probe the cstate events. */
-	for (i = 0; i < max_event_nr; i++) {
-		if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
-			msr[i].attr = NULL;
-	}
-
-	/* List remaining events in the sysfs attrs. */
-	for (i = 0; i < max_event_nr; i++) {
-		if (msr[i].attr)
-			events_attrs[j++] = &msr[i].attr->attr.attr;
-	}
-	events_attrs[j] = NULL;
-
-	return (j > 0) ? true : false;
-}
-
-static int __init cstate_init(void)
-{
-	/* SLM has different MSR for PKG C6 */
-	switch (boot_cpu_data.x86_model) {
-	case 55:
-	case 76:
-	case 77:
-		pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
-	}
-
-	if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX))
-		has_cstate_core = true;
-
-	if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX))
-		has_cstate_pkg = true;
-
-	return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
-}
-
-static void __init cstate_cpumask_init(void)
-{
-	int cpu;
-
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(cpu)
-		cstate_cpu_init(cpu);
-
-	__perf_cpu_notifier(cstate_cpu_notifier);
-
-	cpu_notifier_register_done();
-}
+static struct notifier_block cstate_cpu_nb = {
+	.notifier_call	= cstate_cpu_notifier,
+	.priority       = CPU_PRI_PERF + 1,
+};
 
 static struct pmu cstate_core_pmu = {
 	.attr_groups	= core_attr_groups,
 	.name		= "cstate_core",
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= cstate_pmu_event_init,
-	.add		= cstate_pmu_event_add, /* must have */
-	.del		= cstate_pmu_event_del, /* must have */
+	.add		= cstate_pmu_event_add,
+	.del		= cstate_pmu_event_del,
 	.start		= cstate_pmu_event_start,
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
@@ -646,49 +457,203 @@ static struct pmu cstate_pkg_pmu = {
 	.name		= "cstate_pkg",
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= cstate_pmu_event_init,
-	.add		= cstate_pmu_event_add, /* must have */
-	.del		= cstate_pmu_event_del, /* must have */
+	.add		= cstate_pmu_event_add,
+	.del		= cstate_pmu_event_del,
 	.start		= cstate_pmu_event_start,
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
 };
 
-static void __init cstate_pmus_register(void)
+static const struct cstate_model nhm_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C7_RES),
+};
+
+static const struct cstate_model snb_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C7_RES),
+};
+
+static const struct cstate_model hswult_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C7_RES) |
+				  BIT(PERF_CSTATE_PKG_C8_RES) |
+				  BIT(PERF_CSTATE_PKG_C9_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
+static const struct cstate_model slm_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C6_RES),
+	.quirks			= SLM_PKG_C6_USE_C7_MSR,
+};
+
+#define X86_CSTATES_MODEL(model, states)				\
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
+
+static const struct x86_cpu_id intel_cstates_match[] __initconst = {
+	X86_CSTATES_MODEL(30, nhm_cstates),    /* 45nm Nehalem              */
+	X86_CSTATES_MODEL(26, nhm_cstates),    /* 45nm Nehalem-EP           */
+	X86_CSTATES_MODEL(46, nhm_cstates),    /* 45nm Nehalem-EX           */
+
+	X86_CSTATES_MODEL(37, nhm_cstates),    /* 32nm Westmere             */
+	X86_CSTATES_MODEL(44, nhm_cstates),    /* 32nm Westmere-EP          */
+	X86_CSTATES_MODEL(47, nhm_cstates),    /* 32nm Westmere-EX          */
+
+	X86_CSTATES_MODEL(42, snb_cstates),    /* 32nm SandyBridge          */
+	X86_CSTATES_MODEL(45, snb_cstates),    /* 32nm SandyBridge-E/EN/EP  */
+
+	X86_CSTATES_MODEL(58, snb_cstates),    /* 22nm IvyBridge            */
+	X86_CSTATES_MODEL(62, snb_cstates),    /* 22nm IvyBridge-EP/EX      */
+
+	X86_CSTATES_MODEL(60, snb_cstates),    /* 22nm Haswell Core         */
+	X86_CSTATES_MODEL(63, snb_cstates),    /* 22nm Haswell Server       */
+	X86_CSTATES_MODEL(70, snb_cstates),    /* 22nm Haswell + GT3e       */
+
+	X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT          */
+
+	X86_CSTATES_MODEL(55, slm_cstates),    /* 22nm Atom Silvermont      */
+	X86_CSTATES_MODEL(77, slm_cstates),    /* 22nm Atom Avoton/Rangely  */
+	X86_CSTATES_MODEL(76, slm_cstates),    /* 22nm Atom Airmont         */
+
+	X86_CSTATES_MODEL(61, snb_cstates),    /* 14nm Broadwell Core-M     */
+	X86_CSTATES_MODEL(86, snb_cstates),    /* 14nm Broadwell Xeon D     */
+	X86_CSTATES_MODEL(71, snb_cstates),    /* 14nm Broadwell + GT3e     */
+	X86_CSTATES_MODEL(79, snb_cstates),    /* 14nm Broadwell Server     */
+
+	X86_CSTATES_MODEL(78, snb_cstates),    /* 14nm Skylake Mobile       */
+	X86_CSTATES_MODEL(94, snb_cstates),    /* 14nm Skylake Desktop      */
+	{ },
+};
+MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
+
+/*
+ * Probe the cstate events and insert the available one into sysfs attrs
+ * Return false if there are no available events.
+ */
+static bool __init cstate_probe_msr(const unsigned long evmsk, int max,
+                                   struct perf_cstate_msr *msr,
+                                   struct attribute **attrs)
 {
-	int err;
+	bool found = false;
+	unsigned int bit;
+	u64 val;
+
+	for (bit = 0; bit < max; bit++) {
+		if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) {
+			*attrs++ = &msr[bit].attr->attr.attr;
+			found = true;
+		} else {
+			msr[bit].attr = NULL;
+		}
+	}
+	*attrs = NULL;
+
+	return found;
+}
+
+static int __init cstate_probe(const struct cstate_model *cm)
+{
+	/* SLM has different MSR for PKG C6 */
+	if (cm->quirks & SLM_PKG_C6_USE_C7_MSR)
+		pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
+
+	has_cstate_core = cstate_probe_msr(cm->core_events,
+					   PERF_CSTATE_CORE_EVENT_MAX,
+					   core_msr, core_events_attrs);
+
+	has_cstate_pkg = cstate_probe_msr(cm->pkg_events,
+					  PERF_CSTATE_PKG_EVENT_MAX,
+					  pkg_msr, pkg_events_attrs);
+
+	return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
+}
+
+static inline void cstate_cleanup(void)
+{
+	if (has_cstate_core)
+		perf_pmu_unregister(&cstate_core_pmu);
+
+	if (has_cstate_pkg)
+		perf_pmu_unregister(&cstate_pkg_pmu);
+}
+
+static int __init cstate_init(void)
+{
+	int cpu, err;
+
+	cpu_notifier_register_begin();
+	for_each_online_cpu(cpu)
+		cstate_cpu_init(cpu);
 
 	if (has_cstate_core) {
 		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
-		if (WARN_ON(err))
-			pr_info("Failed to register PMU %s error %d\n",
-				cstate_core_pmu.name, err);
+		if (err) {
+			has_cstate_core = false;
+			pr_info("Failed to register cstate core pmu\n");
+			goto out;
+		}
 	}
 
 	if (has_cstate_pkg) {
 		err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
-		if (WARN_ON(err))
-			pr_info("Failed to register PMU %s error %d\n",
-				cstate_pkg_pmu.name, err);
+		if (err) {
+			has_cstate_pkg = false;
+			pr_info("Failed to register cstate pkg pmu\n");
+			cstate_cleanup();
+			goto out;
+		}
 	}
+	__register_cpu_notifier(&cstate_cpu_nb);
+out:
+	cpu_notifier_register_done();
+	return err;
 }
 
 static int __init cstate_pmu_init(void)
 {
+	const struct x86_cpu_id *id;
 	int err;
 
-	if (cpu_has_hypervisor)
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return -ENODEV;
+
+	id = x86_match_cpu(intel_cstates_match);
+	if (!id)
 		return -ENODEV;
 
-	err = cstate_init();
+	err = cstate_probe((const struct cstate_model *) id->driver_data);
 	if (err)
 		return err;
 
-	cstate_cpumask_init();
-
-	cstate_pmus_register();
-
-	return 0;
+	return cstate_init();
 }
+module_init(cstate_pmu_init);
 
-device_initcall(cstate_pmu_init);
+static void __exit cstate_pmu_exit(void)
+{
+	cpu_notifier_register_begin();
+	__unregister_cpu_notifier(&cstate_cpu_nb);
+	cstate_cleanup();
+	cpu_notifier_register_done();
+}
+module_exit(cstate_pmu_exit);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8584b90d8e0b..7ce9f3f669e6 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -645,6 +645,12 @@ struct event_constraint intel_slm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_glm_pebs_event_constraints[] = {
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 1ca5d1e7d4f2..9e2b40cdb05f 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -14,7 +14,8 @@ enum {
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
 	LBR_FORMAT_EIP_FLAGS2	= 0x04,
 	LBR_FORMAT_INFO		= 0x05,
-	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_INFO,
+	LBR_FORMAT_TIME		= 0x06,
+	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_TIME,
 };
 
 static enum {
@@ -464,6 +465,16 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 			abort = !!(info & LBR_INFO_ABORT);
 			cycles = (info & LBR_INFO_CYCLES);
 		}
+
+		if (lbr_format == LBR_FORMAT_TIME) {
+			mis = !!(from & LBR_FROM_FLAG_MISPRED);
+			pred = !mis;
+			skip = 1;
+			cycles = ((to >> 48) & LBR_INFO_CYCLES);
+
+			to = (u64)((((s64)to) << 16) >> 16);
+		}
+
 		if (lbr_flags & LBR_EIP_FLAGS) {
 			mis = !!(from & LBR_FROM_FLAG_MISPRED);
 			pred = !mis;
@@ -1049,6 +1060,24 @@ void __init intel_pmu_lbr_init_atom(void)
 	pr_cont("8-deep LBR, ");
 }
 
+/* slm */
+void __init intel_pmu_lbr_init_slm(void)
+{
+	x86_pmu.lbr_nr	   = 8;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("8-deep LBR, ");
+}
+
 /* Knights Landing */
 void intel_pmu_lbr_init_knl(void)
 {
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 09a77dbc73c9..04bb5fb5a8d7 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -67,11 +67,13 @@ static struct pt_cap_desc {
 	PT_CAP(max_subleaf,		0, CR_EAX, 0xffffffff),
 	PT_CAP(cr3_filtering,		0, CR_EBX, BIT(0)),
 	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
+	PT_CAP(ip_filtering,		0, CR_EBX, BIT(2)),
 	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
 	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
 	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
 	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
 	PT_CAP(payloads_lip,		0, CR_ECX, BIT(31)),
+	PT_CAP(num_address_ranges,	1, CR_EAX, 0x3),
 	PT_CAP(mtc_periods,		1, CR_EAX, 0xffff0000),
 	PT_CAP(cycle_thresholds,	1, CR_EBX, 0xffff),
 	PT_CAP(psb_periods,		1, CR_EBX, 0xffff0000),
@@ -125,9 +127,46 @@ static struct attribute_group pt_format_group = {
 	.attrs	= pt_formats_attr,
 };
 
+static ssize_t
+pt_timing_attr_show(struct device *dev, struct device_attribute *attr,
+		    char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_attr, attr);
+
+	switch (pmu_attr->id) {
+	case 0:
+		return sprintf(page, "%lu\n", pt_pmu.max_nonturbo_ratio);
+	case 1:
+		return sprintf(page, "%u:%u\n",
+			       pt_pmu.tsc_art_num,
+			       pt_pmu.tsc_art_den);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+PMU_EVENT_ATTR(max_nonturbo_ratio, timing_attr_max_nonturbo_ratio, 0,
+	       pt_timing_attr_show);
+PMU_EVENT_ATTR(tsc_art_ratio, timing_attr_tsc_art_ratio, 1,
+	       pt_timing_attr_show);
+
+static struct attribute *pt_timing_attr[] = {
+	&timing_attr_max_nonturbo_ratio.attr.attr,
+	&timing_attr_tsc_art_ratio.attr.attr,
+	NULL,
+};
+
+static struct attribute_group pt_timing_group = {
+	.attrs	= pt_timing_attr,
+};
+
 static const struct attribute_group *pt_attr_groups[] = {
 	&pt_cap_group,
 	&pt_format_group,
+	&pt_timing_group,
 	NULL,
 };
 
@@ -140,6 +179,23 @@ static int __init pt_pmu_hw_init(void)
 	int ret;
 	long i;
 
+	rdmsrl(MSR_PLATFORM_INFO, reg);
+	pt_pmu.max_nonturbo_ratio = (reg & 0xff00) >> 8;
+
+	/*
+	 * if available, read in TSC to core crystal clock ratio,
+	 * otherwise, zero for numerator stands for "not enumerated"
+	 * as per SDM
+	 */
+	if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx);
+
+		pt_pmu.tsc_art_num = ebx;
+		pt_pmu.tsc_art_den = eax;
+	}
+
 	if (boot_cpu_has(X86_FEATURE_VMX)) {
 		/*
 		 * Intel SDM, 36.5 "Tracing post-VMXON" says that
@@ -263,6 +319,75 @@ static bool pt_event_valid(struct perf_event *event)
  * These all are cpu affine and operate on a local PT
  */
 
+/* Address ranges and their corresponding msr configuration registers */
+static const struct pt_address_range {
+	unsigned long	msr_a;
+	unsigned long	msr_b;
+	unsigned int	reg_off;
+} pt_address_ranges[] = {
+	{
+		.msr_a	 = MSR_IA32_RTIT_ADDR0_A,
+		.msr_b	 = MSR_IA32_RTIT_ADDR0_B,
+		.reg_off = RTIT_CTL_ADDR0_OFFSET,
+	},
+	{
+		.msr_a	 = MSR_IA32_RTIT_ADDR1_A,
+		.msr_b	 = MSR_IA32_RTIT_ADDR1_B,
+		.reg_off = RTIT_CTL_ADDR1_OFFSET,
+	},
+	{
+		.msr_a	 = MSR_IA32_RTIT_ADDR2_A,
+		.msr_b	 = MSR_IA32_RTIT_ADDR2_B,
+		.reg_off = RTIT_CTL_ADDR2_OFFSET,
+	},
+	{
+		.msr_a	 = MSR_IA32_RTIT_ADDR3_A,
+		.msr_b	 = MSR_IA32_RTIT_ADDR3_B,
+		.reg_off = RTIT_CTL_ADDR3_OFFSET,
+	}
+};
+
+static u64 pt_config_filters(struct perf_event *event)
+{
+	struct pt_filters *filters = event->hw.addr_filters;
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	unsigned int range = 0;
+	u64 rtit_ctl = 0;
+
+	if (!filters)
+		return 0;
+
+	perf_event_addr_filters_sync(event);
+
+	for (range = 0; range < filters->nr_filters; range++) {
+		struct pt_filter *filter = &filters->filter[range];
+
+		/*
+		 * Note, if the range has zero start/end addresses due
+		 * to its dynamic object not being loaded yet, we just
+		 * go ahead and program zeroed range, which will simply
+		 * produce no data. Note^2: if executable code at 0x0
+		 * is a concern, we can set up an "invalid" configuration
+		 * such as msr_b < msr_a.
+		 */
+
+		/* avoid redundant msr writes */
+		if (pt->filters.filter[range].msr_a != filter->msr_a) {
+			wrmsrl(pt_address_ranges[range].msr_a, filter->msr_a);
+			pt->filters.filter[range].msr_a = filter->msr_a;
+		}
+
+		if (pt->filters.filter[range].msr_b != filter->msr_b) {
+			wrmsrl(pt_address_ranges[range].msr_b, filter->msr_b);
+			pt->filters.filter[range].msr_b = filter->msr_b;
+		}
+
+		rtit_ctl |= filter->config << pt_address_ranges[range].reg_off;
+	}
+
+	return rtit_ctl;
+}
+
 static void pt_config(struct perf_event *event)
 {
 	u64 reg;
@@ -272,7 +397,8 @@ static void pt_config(struct perf_event *event)
 		wrmsrl(MSR_IA32_RTIT_STATUS, 0);
 	}
 
-	reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
+	reg = pt_config_filters(event);
+	reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
 
 	if (!event->attr.exclude_kernel)
 		reg |= RTIT_CTL_OS;
@@ -709,6 +835,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 
 	/* clear STOP and INT from current entry */
 	buf->topa_index[buf->stop_pos]->stop = 0;
+	buf->topa_index[buf->stop_pos]->intr = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
 	/* how many pages till the STOP marker */
@@ -733,6 +860,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
+	buf->topa_index[buf->stop_pos]->intr = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
 
 	return 0;
@@ -919,24 +1047,80 @@ static void pt_buffer_free_aux(void *data)
 	kfree(buf);
 }
 
-/**
- * pt_buffer_is_full() - check if the buffer is full
- * @buf:	PT buffer.
- * @pt:		Per-cpu pt handle.
- *
- * If the user hasn't read data from the output region that aux_head
- * points to, the buffer is considered full: the user needs to read at
- * least this region and update aux_tail to point past it.
- */
-static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt)
+static int pt_addr_filters_init(struct perf_event *event)
 {
-	if (buf->snapshot)
-		return false;
+	struct pt_filters *filters;
+	int node = event->cpu == -1 ? -1 : cpu_to_node(event->cpu);
+
+	if (!pt_cap_get(PT_CAP_num_address_ranges))
+		return 0;
+
+	filters = kzalloc_node(sizeof(struct pt_filters), GFP_KERNEL, node);
+	if (!filters)
+		return -ENOMEM;
+
+	if (event->parent)
+		memcpy(filters, event->parent->hw.addr_filters,
+		       sizeof(*filters));
+
+	event->hw.addr_filters = filters;
+
+	return 0;
+}
+
+static void pt_addr_filters_fini(struct perf_event *event)
+{
+	kfree(event->hw.addr_filters);
+	event->hw.addr_filters = NULL;
+}
+
+static int pt_event_addr_filters_validate(struct list_head *filters)
+{
+	struct perf_addr_filter *filter;
+	int range = 0;
+
+	list_for_each_entry(filter, filters, entry) {
+		/* PT doesn't support single address triggers */
+		if (!filter->range)
+			return -EOPNOTSUPP;
+
+		if (!filter->inode && !kernel_ip(filter->offset))
+			return -EINVAL;
+
+		if (++range > pt_cap_get(PT_CAP_num_address_ranges))
+			return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void pt_event_addr_filters_sync(struct perf_event *event)
+{
+	struct perf_addr_filters_head *head = perf_event_addr_filters(event);
+	unsigned long msr_a, msr_b, *offs = event->addr_filters_offs;
+	struct pt_filters *filters = event->hw.addr_filters;
+	struct perf_addr_filter *filter;
+	int range = 0;
+
+	if (!filters)
+		return;
 
-	if (local_read(&buf->data_size) >= pt->handle.size)
-		return true;
+	list_for_each_entry(filter, &head->list, entry) {
+		if (filter->inode && !offs[range]) {
+			msr_a = msr_b = 0;
+		} else {
+			/* apply the offset */
+			msr_a = filter->offset + offs[range];
+			msr_b = filter->size + msr_a;
+		}
+
+		filters->filter[range].msr_a  = msr_a;
+		filters->filter[range].msr_b  = msr_b;
+		filters->filter[range].config = filter->filter ? 1 : 2;
+		range++;
+	}
 
-	return false;
+	filters->nr_filters = range;
 }
 
 /**
@@ -953,7 +1137,7 @@ void intel_pt_interrupt(void)
 	 * after PT has been disabled by pt_event_stop(). Make sure we don't
 	 * do anything (particularly, re-enable) for this event here.
 	 */
-	if (!ACCESS_ONCE(pt->handle_nmi))
+	if (!READ_ONCE(pt->handle_nmi))
 		return;
 
 	/*
@@ -1038,23 +1222,36 @@ EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);
 
 static void pt_event_start(struct perf_event *event, int mode)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
-	struct pt_buffer *buf = perf_get_aux(&pt->handle);
+	struct pt_buffer *buf;
 
 	if (READ_ONCE(pt->vmx_on))
 		return;
 
-	if (!buf || pt_buffer_is_full(buf, pt)) {
-		event->hw.state = PERF_HES_STOPPED;
-		return;
+	buf = perf_aux_output_begin(&pt->handle, event);
+	if (!buf)
+		goto fail_stop;
+
+	pt_buffer_reset_offsets(buf, pt->handle.head);
+	if (!buf->snapshot) {
+		if (pt_buffer_reset_markers(buf, &pt->handle))
+			goto fail_end_stop;
 	}
 
-	ACCESS_ONCE(pt->handle_nmi) = 1;
-	event->hw.state = 0;
+	WRITE_ONCE(pt->handle_nmi, 1);
+	hwc->state = 0;
 
 	pt_config_buffer(buf->cur->table, buf->cur_idx,
 			 buf->output_off);
 	pt_config(event);
+
+	return;
+
+fail_end_stop:
+	perf_aux_output_end(&pt->handle, 0, true);
+fail_stop:
+	hwc->state = PERF_HES_STOPPED;
 }
 
 static void pt_event_stop(struct perf_event *event, int mode)
@@ -1065,7 +1262,7 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	 * Protect against the PMI racing with disabling wrmsr,
 	 * see comment in intel_pt_interrupt().
 	 */
-	ACCESS_ONCE(pt->handle_nmi) = 0;
+	WRITE_ONCE(pt->handle_nmi, 0);
 
 	pt_config_stop(event);
 
@@ -1088,19 +1285,7 @@ static void pt_event_stop(struct perf_event *event, int mode)
 		pt_handle_status(pt);
 
 		pt_update_head(pt);
-	}
-}
-
-static void pt_event_del(struct perf_event *event, int mode)
-{
-	struct pt *pt = this_cpu_ptr(&pt_ctx);
-	struct pt_buffer *buf;
 
-	pt_event_stop(event, PERF_EF_UPDATE);
-
-	buf = perf_get_aux(&pt->handle);
-
-	if (buf) {
 		if (buf->snapshot)
 			pt->handle.head =
 				local_xchg(&buf->data_size,
@@ -1110,9 +1295,13 @@ static void pt_event_del(struct perf_event *event, int mode)
 	}
 }
 
+static void pt_event_del(struct perf_event *event, int mode)
+{
+	pt_event_stop(event, PERF_EF_UPDATE);
+}
+
 static int pt_event_add(struct perf_event *event, int mode)
 {
-	struct pt_buffer *buf;
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct hw_perf_event *hwc = &event->hw;
 	int ret = -EBUSY;
@@ -1120,34 +1309,18 @@ static int pt_event_add(struct perf_event *event, int mode)
 	if (pt->handle.event)
 		goto fail;
 
-	buf = perf_aux_output_begin(&pt->handle, event);
-	ret = -EINVAL;
-	if (!buf)
-		goto fail_stop;
-
-	pt_buffer_reset_offsets(buf, pt->handle.head);
-	if (!buf->snapshot) {
-		ret = pt_buffer_reset_markers(buf, &pt->handle);
-		if (ret)
-			goto fail_end_stop;
-	}
-
 	if (mode & PERF_EF_START) {
 		pt_event_start(event, 0);
-		ret = -EBUSY;
+		ret = -EINVAL;
 		if (hwc->state == PERF_HES_STOPPED)
-			goto fail_end_stop;
+			goto fail;
 	} else {
 		hwc->state = PERF_HES_STOPPED;
 	}
 
-	return 0;
-
-fail_end_stop:
-	perf_aux_output_end(&pt->handle, 0, true);
-fail_stop:
-	hwc->state = PERF_HES_STOPPED;
+	ret = 0;
 fail:
+
 	return ret;
 }
 
@@ -1157,6 +1330,7 @@ static void pt_event_read(struct perf_event *event)
 
 static void pt_event_destroy(struct perf_event *event)
 {
+	pt_addr_filters_fini(event);
 	x86_del_exclusive(x86_lbr_exclusive_pt);
 }
 
@@ -1171,6 +1345,11 @@ static int pt_event_init(struct perf_event *event)
 	if (x86_add_exclusive(x86_lbr_exclusive_pt))
 		return -EBUSY;
 
+	if (pt_addr_filters_init(event)) {
+		x86_del_exclusive(x86_lbr_exclusive_pt);
+		return -ENOMEM;
+	}
+
 	event->destroy = pt_event_destroy;
 
 	return 0;
@@ -1190,7 +1369,7 @@ static __init int pt_init(void)
 
 	BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE);
 
-	if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT))
+	if (!boot_cpu_has(X86_FEATURE_INTEL_PT))
 		return -ENODEV;
 
 	get_online_cpus();
@@ -1224,16 +1403,21 @@ static __init int pt_init(void)
 			PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
 
 	pt_pmu.pmu.capabilities	|= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
-	pt_pmu.pmu.attr_groups	= pt_attr_groups;
-	pt_pmu.pmu.task_ctx_nr	= perf_sw_context;
-	pt_pmu.pmu.event_init	= pt_event_init;
-	pt_pmu.pmu.add		= pt_event_add;
-	pt_pmu.pmu.del		= pt_event_del;
-	pt_pmu.pmu.start	= pt_event_start;
-	pt_pmu.pmu.stop		= pt_event_stop;
-	pt_pmu.pmu.read		= pt_event_read;
-	pt_pmu.pmu.setup_aux	= pt_buffer_setup_aux;
-	pt_pmu.pmu.free_aux	= pt_buffer_free_aux;
+	pt_pmu.pmu.attr_groups		 = pt_attr_groups;
+	pt_pmu.pmu.task_ctx_nr		 = perf_sw_context;
+	pt_pmu.pmu.event_init		 = pt_event_init;
+	pt_pmu.pmu.add			 = pt_event_add;
+	pt_pmu.pmu.del			 = pt_event_del;
+	pt_pmu.pmu.start		 = pt_event_start;
+	pt_pmu.pmu.stop			 = pt_event_stop;
+	pt_pmu.pmu.read			 = pt_event_read;
+	pt_pmu.pmu.setup_aux		 = pt_buffer_setup_aux;
+	pt_pmu.pmu.free_aux		 = pt_buffer_free_aux;
+	pt_pmu.pmu.addr_filters_sync     = pt_event_addr_filters_sync;
+	pt_pmu.pmu.addr_filters_validate = pt_event_addr_filters_validate;
+	pt_pmu.pmu.nr_addr_filters       =
+		pt_cap_get(PT_CAP_num_address_ranges);
+
 	ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1);
 
 	return ret;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 3abb5f5cccc8..efffa4a09f68 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -20,6 +20,40 @@
 #define __INTEL_PT_H__
 
 /*
+ * PT MSR bit definitions
+ */
+#define RTIT_CTL_TRACEEN		BIT(0)
+#define RTIT_CTL_CYCLEACC		BIT(1)
+#define RTIT_CTL_OS			BIT(2)
+#define RTIT_CTL_USR			BIT(3)
+#define RTIT_CTL_CR3EN			BIT(7)
+#define RTIT_CTL_TOPA			BIT(8)
+#define RTIT_CTL_MTC_EN			BIT(9)
+#define RTIT_CTL_TSC_EN			BIT(10)
+#define RTIT_CTL_DISRETC		BIT(11)
+#define RTIT_CTL_BRANCH_EN		BIT(13)
+#define RTIT_CTL_MTC_RANGE_OFFSET	14
+#define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
+#define RTIT_CTL_CYC_THRESH_OFFSET	19
+#define RTIT_CTL_CYC_THRESH		(0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
+#define RTIT_CTL_PSB_FREQ_OFFSET	24
+#define RTIT_CTL_PSB_FREQ      		(0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
+#define RTIT_CTL_ADDR0_OFFSET		32
+#define RTIT_CTL_ADDR0      		(0x0full << RTIT_CTL_ADDR0_OFFSET)
+#define RTIT_CTL_ADDR1_OFFSET		36
+#define RTIT_CTL_ADDR1      		(0x0full << RTIT_CTL_ADDR1_OFFSET)
+#define RTIT_CTL_ADDR2_OFFSET		40
+#define RTIT_CTL_ADDR2      		(0x0full << RTIT_CTL_ADDR2_OFFSET)
+#define RTIT_CTL_ADDR3_OFFSET		44
+#define RTIT_CTL_ADDR3      		(0x0full << RTIT_CTL_ADDR3_OFFSET)
+#define RTIT_STATUS_FILTEREN		BIT(0)
+#define RTIT_STATUS_CONTEXTEN		BIT(1)
+#define RTIT_STATUS_TRIGGEREN		BIT(2)
+#define RTIT_STATUS_BUFFOVF		BIT(3)
+#define RTIT_STATUS_ERROR		BIT(4)
+#define RTIT_STATUS_STOPPED		BIT(5)
+
+/*
  * Single-entry ToPA: when this close to region boundary, switch
  * buffers to avoid losing data.
  */
@@ -48,15 +82,20 @@ struct topa_entry {
 #define PT_CPUID_LEAVES		2
 #define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
 
+/* TSC to Core Crystal Clock Ratio */
+#define CPUID_TSC_LEAF		0x15
+
 enum pt_capabilities {
 	PT_CAP_max_subleaf = 0,
 	PT_CAP_cr3_filtering,
 	PT_CAP_psb_cyc,
+	PT_CAP_ip_filtering,
 	PT_CAP_mtc,
 	PT_CAP_topa_output,
 	PT_CAP_topa_multiple_entries,
 	PT_CAP_single_range_output,
 	PT_CAP_payloads_lip,
+	PT_CAP_num_address_ranges,
 	PT_CAP_mtc_periods,
 	PT_CAP_cycle_thresholds,
 	PT_CAP_psb_periods,
@@ -66,6 +105,9 @@ struct pt_pmu {
 	struct pmu		pmu;
 	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
 	bool			vmx;
+	unsigned long		max_nonturbo_ratio;
+	unsigned int		tsc_art_num;
+	unsigned int		tsc_art_den;
 };
 
 /**
@@ -104,14 +146,40 @@ struct pt_buffer {
 	struct topa_entry	*topa_index[0];
 };
 
+#define PT_FILTERS_NUM	4
+
+/**
+ * struct pt_filter - IP range filter configuration
+ * @msr_a:	range start, goes to RTIT_ADDRn_A
+ * @msr_b:	range end, goes to RTIT_ADDRn_B
+ * @config:	4-bit field in RTIT_CTL
+ */
+struct pt_filter {
+	unsigned long	msr_a;
+	unsigned long	msr_b;
+	unsigned long	config;
+};
+
+/**
+ * struct pt_filters - IP range filtering context
+ * @filter:	filters defined for this context
+ * @nr_filters:	number of defined filters in the @filter array
+ */
+struct pt_filters {
+	struct pt_filter	filter[PT_FILTERS_NUM];
+	unsigned int		nr_filters;
+};
+
 /**
  * struct pt - per-cpu pt context
  * @handle:	perf output handle
+ * @filters:		last configured filters
  * @handle_nmi:	do handle PT PMI on this cpu, there's an active event
  * @vmx_on:	1 if VMX is ON on this cpu
  */
 struct pt {
 	struct perf_output_handle handle;
+	struct pt_filters	filters;
 	int			handle_nmi;
 	int			vmx_on;
 };
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 1705c9d75e44..99c4bab123cd 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -27,10 +27,14 @@
  *	  event: rapl_energy_dram
  *    perf code: 0x3
  *
- * dram counter: consumption of the builtin-gpu domain (client only)
+ * gpu counter: consumption of the builtin-gpu domain (client only)
  *	  event: rapl_energy_gpu
  *    perf code: 0x4
  *
+ *  psys counter: consumption of the builtin-psys domain (client only)
+ *	  event: rapl_energy_psys
+ *    perf code: 0x5
+ *
  * We manage those counters as free running (read-only). They may be
  * use simultaneously by other tools, such as turbostat.
  *
@@ -53,6 +57,8 @@
 #include <asm/cpu_device_id.h>
 #include "../perf_event.h"
 
+MODULE_LICENSE("GPL");
+
 /*
  * RAPL energy status counters
  */
@@ -64,13 +70,16 @@
 #define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
 #define RAPL_IDX_PP1_NRG_STAT	3	/* gpu */
 #define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
+#define RAPL_IDX_PSYS_NRG_STAT	4	/* psys */
+#define INTEL_RAPL_PSYS		0x5	/* pseudo-encoding */
 
-#define NR_RAPL_DOMAINS         0x4
+#define NR_RAPL_DOMAINS         0x5
 static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
 	"pp0-core",
 	"package",
 	"dram",
 	"pp1-gpu",
+	"psys",
 };
 
 /* Clients have PP0, PKG */
@@ -89,6 +98,13 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
 			 1<<RAPL_IDX_RAM_NRG_STAT|\
 			 1<<RAPL_IDX_PP1_NRG_STAT)
 
+/* SKL clients have PP0, PKG, RAM, PP1, PSYS */
+#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
+			  1<<RAPL_IDX_PKG_NRG_STAT|\
+			  1<<RAPL_IDX_RAM_NRG_STAT|\
+			  1<<RAPL_IDX_PP1_NRG_STAT|\
+			  1<<RAPL_IDX_PSYS_NRG_STAT)
+
 /* Knights Landing has PKG, RAM */
 #define RAPL_IDX_KNL	(1<<RAPL_IDX_PKG_NRG_STAT|\
 			 1<<RAPL_IDX_RAM_NRG_STAT)
@@ -360,6 +376,10 @@ static int rapl_pmu_event_init(struct perf_event *event)
 		bit = RAPL_IDX_PP1_NRG_STAT;
 		msr = MSR_PP1_ENERGY_STATUS;
 		break;
+	case INTEL_RAPL_PSYS:
+		bit = RAPL_IDX_PSYS_NRG_STAT;
+		msr = MSR_PLATFORM_ENERGY_STATUS;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -414,11 +434,13 @@ RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
 RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
 RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
 RAPL_EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
+RAPL_EVENT_ATTR_STR(energy-psys,   rapl_psys, "event=0x05");
 
 RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-psys.unit,   rapl_psys_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
@@ -427,6 +449,7 @@ RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890
 RAPL_EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
 RAPL_EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
 RAPL_EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-psys.scale,   rapl_psys_scale, "2.3283064365386962890625e-10");
 
 static struct attribute *rapl_events_srv_attr[] = {
 	EVENT_PTR(rapl_cores),
@@ -476,6 +499,27 @@ static struct attribute *rapl_events_hsw_attr[] = {
 	NULL,
 };
 
+static struct attribute *rapl_events_skl_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_gpu),
+	EVENT_PTR(rapl_ram),
+	EVENT_PTR(rapl_psys),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_gpu_unit),
+	EVENT_PTR(rapl_ram_unit),
+	EVENT_PTR(rapl_psys_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_gpu_scale),
+	EVENT_PTR(rapl_ram_scale),
+	EVENT_PTR(rapl_psys_scale),
+	NULL,
+};
+
 static struct attribute *rapl_events_knl_attr[] = {
 	EVENT_PTR(rapl_pkg),
 	EVENT_PTR(rapl_ram),
@@ -592,6 +636,11 @@ static int rapl_cpu_notifier(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+static struct notifier_block rapl_cpu_nb = {
+	.notifier_call	= rapl_cpu_notifier,
+	.priority       = CPU_PRI_PERF + 1,
+};
+
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -660,7 +709,7 @@ static int __init rapl_prepare_cpus(void)
 	return 0;
 }
 
-static void __init cleanup_rapl_pmus(void)
+static void cleanup_rapl_pmus(void)
 {
 	int i;
 
@@ -691,52 +740,92 @@ static int __init init_rapl_pmus(void)
 	return 0;
 }
 
+#define X86_RAPL_MODEL_MATCH(model, init)	\
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
+
+struct intel_rapl_init_fun {
+	bool apply_quirk;
+	int cntr_mask;
+	struct attribute **attrs;
+};
+
+static const struct intel_rapl_init_fun snb_rapl_init __initconst = {
+	.apply_quirk = false,
+	.cntr_mask = RAPL_IDX_CLN,
+	.attrs = rapl_events_cln_attr,
+};
+
+static const struct intel_rapl_init_fun hsx_rapl_init __initconst = {
+	.apply_quirk = true,
+	.cntr_mask = RAPL_IDX_SRV,
+	.attrs = rapl_events_srv_attr,
+};
+
+static const struct intel_rapl_init_fun hsw_rapl_init __initconst = {
+	.apply_quirk = false,
+	.cntr_mask = RAPL_IDX_HSW,
+	.attrs = rapl_events_hsw_attr,
+};
+
+static const struct intel_rapl_init_fun snbep_rapl_init __initconst = {
+	.apply_quirk = false,
+	.cntr_mask = RAPL_IDX_SRV,
+	.attrs = rapl_events_srv_attr,
+};
+
+static const struct intel_rapl_init_fun knl_rapl_init __initconst = {
+	.apply_quirk = true,
+	.cntr_mask = RAPL_IDX_KNL,
+	.attrs = rapl_events_knl_attr,
+};
+
+static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
+	.apply_quirk = false,
+	.cntr_mask = RAPL_IDX_SKL_CLN,
+	.attrs = rapl_events_skl_attr,
+};
+
 static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
-	[0] = { .vendor = X86_VENDOR_INTEL, .family = 6 },
-	[1] = {},
+	X86_RAPL_MODEL_MATCH(42, snb_rapl_init),	/* Sandy Bridge */
+	X86_RAPL_MODEL_MATCH(45, snbep_rapl_init),	/* Sandy Bridge-EP */
+
+	X86_RAPL_MODEL_MATCH(58, snb_rapl_init),	/* Ivy Bridge */
+	X86_RAPL_MODEL_MATCH(62, snbep_rapl_init),	/* IvyTown */
+
+	X86_RAPL_MODEL_MATCH(60, hsw_rapl_init),	/* Haswell */
+	X86_RAPL_MODEL_MATCH(63, hsx_rapl_init),	/* Haswell-Server */
+	X86_RAPL_MODEL_MATCH(69, hsw_rapl_init),	/* Haswell-Celeron */
+	X86_RAPL_MODEL_MATCH(70, hsw_rapl_init),	/* Haswell GT3e */
+
+	X86_RAPL_MODEL_MATCH(61, hsw_rapl_init),	/* Broadwell */
+	X86_RAPL_MODEL_MATCH(71, hsw_rapl_init),	/* Broadwell-H */
+	X86_RAPL_MODEL_MATCH(79, hsx_rapl_init),	/* Broadwell-Server */
+	X86_RAPL_MODEL_MATCH(86, hsx_rapl_init),	/* Broadwell Xeon D */
+
+	X86_RAPL_MODEL_MATCH(87, knl_rapl_init),	/* Knights Landing */
+
+	X86_RAPL_MODEL_MATCH(78, skl_rapl_init),	/* Skylake */
+	X86_RAPL_MODEL_MATCH(94, skl_rapl_init),	/* Skylake H/S */
+	{},
 };
 
+MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match);
+
 static int __init rapl_pmu_init(void)
 {
-	bool apply_quirk = false;
+	const struct x86_cpu_id *id;
+	struct intel_rapl_init_fun *rapl_init;
+	bool apply_quirk;
 	int ret;
 
-	if (!x86_match_cpu(rapl_cpu_match))
+	id = x86_match_cpu(rapl_cpu_match);
+	if (!id)
 		return -ENODEV;
 
-	switch (boot_cpu_data.x86_model) {
-	case 42: /* Sandy Bridge */
-	case 58: /* Ivy Bridge */
-		rapl_cntr_mask = RAPL_IDX_CLN;
-		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
-		break;
-	case 63: /* Haswell-Server */
-	case 79: /* Broadwell-Server */
-		apply_quirk = true;
-		rapl_cntr_mask = RAPL_IDX_SRV;
-		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
-		break;
-	case 60: /* Haswell */
-	case 69: /* Haswell-Celeron */
-	case 70: /* Haswell GT3e */
-	case 61: /* Broadwell */
-	case 71: /* Broadwell-H */
-		rapl_cntr_mask = RAPL_IDX_HSW;
-		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
-		break;
-	case 45: /* Sandy Bridge-EP */
-	case 62: /* IvyTown */
-		rapl_cntr_mask = RAPL_IDX_SRV;
-		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
-		break;
-	case 87: /* Knights Landing */
-		apply_quirk = true;
-		rapl_cntr_mask = RAPL_IDX_KNL;
-		rapl_pmu_events_group.attrs = rapl_events_knl_attr;
-		break;
-	default:
-		return -ENODEV;
-	}
+	rapl_init = (struct intel_rapl_init_fun *)id->driver_data;
+	apply_quirk = rapl_init->apply_quirk;
+	rapl_cntr_mask = rapl_init->cntr_mask;
+	rapl_pmu_events_group.attrs = rapl_init->attrs;
 
 	ret = rapl_check_hw_unit(apply_quirk);
 	if (ret)
@@ -756,7 +845,7 @@ static int __init rapl_pmu_init(void)
 	if (ret)
 		goto out;
 
-	__perf_cpu_notifier(rapl_cpu_notifier);
+	__register_cpu_notifier(&rapl_cpu_nb);
 	cpu_notifier_register_done();
 	rapl_advertise();
 	return 0;
@@ -767,4 +856,14 @@ out:
 	cpu_notifier_register_done();
 	return ret;
 }
-device_initcall(rapl_pmu_init);
+module_init(rapl_pmu_init);
+
+static void __exit intel_rapl_exit(void)
+{
+	cpu_notifier_register_begin();
+	__unregister_cpu_notifier(&rapl_cpu_nb);
+	perf_pmu_unregister(&rapl_pmus->pmu);
+	cleanup_rapl_pmus();
+	cpu_notifier_register_done();
+}
+module_exit(intel_rapl_exit);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 7012d18bb293..16c178916412 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,3 +1,4 @@
+#include <asm/cpu_device_id.h>
 #include "uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
@@ -21,6 +22,8 @@ static struct event_constraint uncore_constraint_fixed =
 struct event_constraint uncore_constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
+MODULE_LICENSE("GPL");
+
 static int uncore_pcibus_to_physid(struct pci_bus *bus)
 {
 	struct pci2phy_map *map;
@@ -754,7 +757,7 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
 	pmu->registered = false;
 }
 
-static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
+static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
 {
 	struct intel_uncore_pmu *pmu = type->pmus;
 	struct intel_uncore_box *box;
@@ -770,7 +773,7 @@ static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
 	}
 }
 
-static void __init uncore_exit_boxes(void *dummy)
+static void uncore_exit_boxes(void *dummy)
 {
 	struct intel_uncore_type **types;
 
@@ -787,7 +790,7 @@ static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 	kfree(pmu->boxes);
 }
 
-static void __init uncore_type_exit(struct intel_uncore_type *type)
+static void uncore_type_exit(struct intel_uncore_type *type)
 {
 	struct intel_uncore_pmu *pmu = type->pmus;
 	int i;
@@ -804,7 +807,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type)
 	type->events_group = NULL;
 }
 
-static void __init uncore_types_exit(struct intel_uncore_type **types)
+static void uncore_types_exit(struct intel_uncore_type **types)
 {
 	for (; *types; types++)
 		uncore_type_exit(*types);
@@ -989,46 +992,6 @@ static int __init uncore_pci_init(void)
 	size_t size;
 	int ret;
 
-	switch (boot_cpu_data.x86_model) {
-	case 45: /* Sandy Bridge-EP */
-		ret = snbep_uncore_pci_init();
-		break;
-	case 62: /* Ivy Bridge-EP */
-		ret = ivbep_uncore_pci_init();
-		break;
-	case 63: /* Haswell-EP */
-		ret = hswep_uncore_pci_init();
-		break;
-	case 79: /* BDX-EP */
-	case 86: /* BDX-DE */
-		ret = bdx_uncore_pci_init();
-		break;
-	case 42: /* Sandy Bridge */
-		ret = snb_uncore_pci_init();
-		break;
-	case 58: /* Ivy Bridge */
-		ret = ivb_uncore_pci_init();
-		break;
-	case 60: /* Haswell */
-	case 69: /* Haswell Celeron */
-		ret = hsw_uncore_pci_init();
-		break;
-	case 61: /* Broadwell */
-		ret = bdw_uncore_pci_init();
-		break;
-	case 87: /* Knights Landing */
-		ret = knl_uncore_pci_init();
-		break;
-	case 94: /* SkyLake */
-		ret = skl_uncore_pci_init();
-		break;
-	default:
-		return -ENODEV;
-	}
-
-	if (ret)
-		return ret;
-
 	size = max_packages * sizeof(struct pci_extra_dev);
 	uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
 	if (!uncore_extra_pci_dev) {
@@ -1060,7 +1023,7 @@ err:
 	return ret;
 }
 
-static void __init uncore_pci_exit(void)
+static void uncore_pci_exit(void)
 {
 	if (pcidrv_registered) {
 		pcidrv_registered = false;
@@ -1287,46 +1250,6 @@ static int __init uncore_cpu_init(void)
 {
 	int ret;
 
-	switch (boot_cpu_data.x86_model) {
-	case 26: /* Nehalem */
-	case 30:
-	case 37: /* Westmere */
-	case 44:
-		nhm_uncore_cpu_init();
-		break;
-	case 42: /* Sandy Bridge */
-	case 58: /* Ivy Bridge */
-	case 60: /* Haswell */
-	case 69: /* Haswell */
-	case 70: /* Haswell */
-	case 61: /* Broadwell */
-	case 71: /* Broadwell */
-		snb_uncore_cpu_init();
-		break;
-	case 45: /* Sandy Bridge-EP */
-		snbep_uncore_cpu_init();
-		break;
-	case 46: /* Nehalem-EX */
-	case 47: /* Westmere-EX aka. Xeon E7 */
-		nhmex_uncore_cpu_init();
-		break;
-	case 62: /* Ivy Bridge-EP */
-		ivbep_uncore_cpu_init();
-		break;
-	case 63: /* Haswell-EP */
-		hswep_uncore_cpu_init();
-		break;
-	case 79: /* BDX-EP */
-	case 86: /* BDX-DE */
-		bdx_uncore_cpu_init();
-		break;
-	case 87: /* Knights Landing */
-		knl_uncore_cpu_init();
-		break;
-	default:
-		return -ENODEV;
-	}
-
 	ret = uncore_types_init(uncore_msr_uncores, true);
 	if (ret)
 		goto err;
@@ -1376,20 +1299,123 @@ static int __init uncore_cpumask_init(bool msr)
 	return 0;
 }
 
+#define X86_UNCORE_MODEL_MATCH(model, init)	\
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
+
+struct intel_uncore_init_fun {
+	void	(*cpu_init)(void);
+	int	(*pci_init)(void);
+};
+
+static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
+	.cpu_init = nhm_uncore_cpu_init,
+};
+
+static const struct intel_uncore_init_fun snb_uncore_init __initconst = {
+	.cpu_init = snb_uncore_cpu_init,
+	.pci_init = snb_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun ivb_uncore_init __initconst = {
+	.cpu_init = snb_uncore_cpu_init,
+	.pci_init = ivb_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun hsw_uncore_init __initconst = {
+	.cpu_init = snb_uncore_cpu_init,
+	.pci_init = hsw_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun bdw_uncore_init __initconst = {
+	.cpu_init = snb_uncore_cpu_init,
+	.pci_init = bdw_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun snbep_uncore_init __initconst = {
+	.cpu_init = snbep_uncore_cpu_init,
+	.pci_init = snbep_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun nhmex_uncore_init __initconst = {
+	.cpu_init = nhmex_uncore_cpu_init,
+};
+
+static const struct intel_uncore_init_fun ivbep_uncore_init __initconst = {
+	.cpu_init = ivbep_uncore_cpu_init,
+	.pci_init = ivbep_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun hswep_uncore_init __initconst = {
+	.cpu_init = hswep_uncore_cpu_init,
+	.pci_init = hswep_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun bdx_uncore_init __initconst = {
+	.cpu_init = bdx_uncore_cpu_init,
+	.pci_init = bdx_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun knl_uncore_init __initconst = {
+	.cpu_init = knl_uncore_cpu_init,
+	.pci_init = knl_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
+	.pci_init = skl_uncore_pci_init,
+};
+
+static const struct x86_cpu_id intel_uncore_match[] __initconst = {
+	X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init),	/* Nehalem */
+	X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init),	/* Westmere */
+	X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(42, snb_uncore_init),	/* Sandy Bridge */
+	X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init),	/* Ivy Bridge */
+	X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init),	/* Haswell */
+	X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init),	/* Haswell Celeron */
+	X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init),	/* Haswell */
+	X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init),	/* Broadwell */
+	X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init),	/* Broadwell */
+	X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init),	/* Sandy Bridge-EP */
+	X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init),	/* Nehalem-EX */
+	X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init),	/* Westmere-EX aka. Xeon E7 */
+	X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init),	/* Ivy Bridge-EP */
+	X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init),	/* Haswell-EP */
+	X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init),	/* BDX-EP */
+	X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init),	/* BDX-DE */
+	X86_UNCORE_MODEL_MATCH(87, knl_uncore_init),	/* Knights Landing */
+	X86_UNCORE_MODEL_MATCH(94, skl_uncore_init),	/* SkyLake */
+	{},
+};
+
+MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
+
 static int __init intel_uncore_init(void)
 {
-	int pret, cret, ret;
+	const struct x86_cpu_id *id;
+	struct intel_uncore_init_fun *uncore_init;
+	int pret = 0, cret = 0, ret;
 
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	id = x86_match_cpu(intel_uncore_match);
+	if (!id)
 		return -ENODEV;
 
-	if (cpu_has_hypervisor)
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return -ENODEV;
 
 	max_packages = topology_max_packages();
 
-	pret = uncore_pci_init();
-	cret = uncore_cpu_init();
+	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
+	if (uncore_init->pci_init) {
+		pret = uncore_init->pci_init();
+		if (!pret)
+			pret = uncore_pci_init();
+	}
+
+	if (uncore_init->cpu_init) {
+		uncore_init->cpu_init();
+		cret = uncore_cpu_init();
+	}
 
 	if (cret && pret)
 		return -ENODEV;
@@ -1409,4 +1435,14 @@ err:
 	cpu_notifier_register_done();
 	return ret;
 }
-device_initcall(intel_uncore_init);
+module_init(intel_uncore_init);
+
+static void __exit intel_uncore_exit(void)
+{
+	cpu_notifier_register_begin();
+	__unregister_cpu_notifier(&uncore_cpu_nb);
+	uncore_types_exit(uncore_msr_uncores);
+	uncore_pci_exit();
+	cpu_notifier_register_done();
+}
+module_exit(intel_uncore_exit);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index ab2bcaaebe38..b2625867ebd1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -219,6 +219,9 @@
 #define KNL_CHA_MSR_PMON_BOX_FILTER_TID		0x1ff
 #define KNL_CHA_MSR_PMON_BOX_FILTER_STATE	(7 << 18)
 #define KNL_CHA_MSR_PMON_BOX_FILTER_OP		(0xfffffe2aULL << 32)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE	(0x1ULL << 32)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE	(0x1ULL << 33)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_NNC		(0x1ULL << 37)
 
 /* KNL EDC/MC UCLK */
 #define KNL_UCLK_MSR_PMON_CTR0_LOW		0x400
@@ -1902,6 +1905,10 @@ static int knl_cha_hw_config(struct intel_uncore_box *box,
 		reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
 			    KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx;
 		reg1->config = event->attr.config1 & knl_cha_filter_mask(idx);
+
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE;
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE;
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_NNC;
 		reg1->idx = idx;
 	}
 	return 0;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index ec863b9a9f78..85ef3c2e80e0 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -6,6 +6,8 @@ enum perf_msr_id {
 	PERF_MSR_MPERF			= 2,
 	PERF_MSR_PPERF			= 3,
 	PERF_MSR_SMI			= 4,
+	PERF_MSR_PTSC			= 5,
+	PERF_MSR_IRPERF			= 6,
 
 	PERF_MSR_EVENT_MAX,
 };
@@ -15,6 +17,16 @@ static bool test_aperfmperf(int idx)
 	return boot_cpu_has(X86_FEATURE_APERFMPERF);
 }
 
+static bool test_ptsc(int idx)
+{
+	return boot_cpu_has(X86_FEATURE_PTSC);
+}
+
+static bool test_irperf(int idx)
+{
+	return boot_cpu_has(X86_FEATURE_IRPERF);
+}
+
 static bool test_intel(int idx)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
@@ -69,18 +81,22 @@ struct perf_msr {
 	bool	(*test)(int idx);
 };
 
-PMU_EVENT_ATTR_STRING(tsc,   evattr_tsc,   "event=0x00");
-PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01");
-PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02");
-PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03");
-PMU_EVENT_ATTR_STRING(smi,   evattr_smi,   "event=0x04");
+PMU_EVENT_ATTR_STRING(tsc,    evattr_tsc,    "event=0x00");
+PMU_EVENT_ATTR_STRING(aperf,  evattr_aperf,  "event=0x01");
+PMU_EVENT_ATTR_STRING(mperf,  evattr_mperf,  "event=0x02");
+PMU_EVENT_ATTR_STRING(pperf,  evattr_pperf,  "event=0x03");
+PMU_EVENT_ATTR_STRING(smi,    evattr_smi,    "event=0x04");
+PMU_EVENT_ATTR_STRING(ptsc,   evattr_ptsc,   "event=0x05");
+PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06");
 
 static struct perf_msr msr[] = {
-	[PERF_MSR_TSC]   = { 0,			&evattr_tsc,	NULL,		 },
-	[PERF_MSR_APERF] = { MSR_IA32_APERF,	&evattr_aperf,	test_aperfmperf, },
-	[PERF_MSR_MPERF] = { MSR_IA32_MPERF,	&evattr_mperf,	test_aperfmperf, },
-	[PERF_MSR_PPERF] = { MSR_PPERF,		&evattr_pperf,	test_intel,	 },
-	[PERF_MSR_SMI]   = { MSR_SMI_COUNT,	&evattr_smi,	test_intel,	 },
+	[PERF_MSR_TSC]    = { 0,		&evattr_tsc,	NULL,		 },
+	[PERF_MSR_APERF]  = { MSR_IA32_APERF,	&evattr_aperf,	test_aperfmperf, },
+	[PERF_MSR_MPERF]  = { MSR_IA32_MPERF,	&evattr_mperf,	test_aperfmperf, },
+	[PERF_MSR_PPERF]  = { MSR_PPERF,	&evattr_pperf,	test_intel,	 },
+	[PERF_MSR_SMI]    = { MSR_SMI_COUNT,	&evattr_smi,	test_intel,	 },
+	[PERF_MSR_PTSC]   = { MSR_F15H_PTSC,	&evattr_ptsc,	test_ptsc,	 },
+	[PERF_MSR_IRPERF] = { MSR_F17H_IRPERF,	&evattr_irperf,	test_irperf,	 },
 };
 
 static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
@@ -166,7 +182,7 @@ again:
 	if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
 		delta = sign_extend64(delta, 31);
 
-	local64_add(now - prev, &event->count);
+	local64_add(delta, &event->count);
 }
 
 static void msr_event_start(struct perf_event *event, int flags)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ad4dc7ffffb5..8bd764df815d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -601,6 +601,7 @@ struct x86_pmu {
 	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
 	const int	*lbr_sel_map;		   /* lbr_select mappings */
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
+	bool		lbr_pt_coexist;		   /* LBR may coexist with PT */
 
 	/*
 	 * Intel PT/LBR/BTS are exclusive
@@ -859,6 +860,8 @@ extern struct event_constraint intel_atom_pebs_event_constraints[];
 
 extern struct event_constraint intel_slm_pebs_event_constraints[];
 
+extern struct event_constraint intel_glm_pebs_event_constraints[];
+
 extern struct event_constraint intel_nehalem_pebs_event_constraints[];
 
 extern struct event_constraint intel_westmere_pebs_event_constraints[];
@@ -907,6 +910,8 @@ void intel_pmu_lbr_init_nhm(void);
 
 void intel_pmu_lbr_init_atom(void);
 
+void intel_pmu_lbr_init_slm(void);
+
 void intel_pmu_lbr_init_snb(void);
 
 void intel_pmu_lbr_init_hsw(void);
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 0552884da18d..2f29f4e407c3 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -357,7 +357,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 		put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
 
 		/* Create the ucontext.  */
-		if (cpu_has_xsave)
+		if (boot_cpu_has(X86_FEATURE_XSAVE))
 			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 99afb665a004..e77a6443104f 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -1,11 +1,12 @@
 #ifndef _ASM_X86_ALTERNATIVE_H
 #define _ASM_X86_ALTERNATIVE_H
 
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
-#include <asm/ptrace.h>
 
 /*
  * Alternative inline assembly for SMP.
@@ -233,36 +234,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
-struct paravirt_patch_site;
-#ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch_site *start,
-		    struct paravirt_patch_site *end);
-#else
-static inline void apply_paravirt(struct paravirt_patch_site *start,
-				  struct paravirt_patch_site *end)
-{}
-#define __parainstructions	NULL
-#define __parainstructions_end	NULL
-#endif
-
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
-
-/*
- * Clear and restore the kernel write-protection flag on the local CPU.
- * Allows the kernel to edit read-only pages.
- * Side-effect: any interrupt handler running between save and restore will have
- * the ability to write to read-only pages.
- *
- * Warning:
- * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
- * no thread can be preempted in the instructions being modified (no iret to an
- * invalid instruction possible) or if the instructions are changed from a
- * consistent state to another consistent state atomically.
- * On the local CPU you need to be protected again NMI or MCE handlers seeing an
- * inconsistent instruction while you patch.
- */
-extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 98f25bbafac4..bc27611fa58f 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -239,10 +239,10 @@ extern void __init check_x2apic(void);
 extern void x2apic_setup(void);
 static inline int x2apic_enabled(void)
 {
-	return cpu_has_x2apic && apic_is_x2apic_enabled();
+	return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled();
 }
 
-#define x2apic_supported()	(cpu_has_x2apic)
+#define x2apic_supported()	(boot_cpu_has(X86_FEATURE_X2APIC))
 #else /* !CONFIG_X86_X2APIC */
 static inline void check_x2apic(void) { }
 static inline void x2apic_setup(void) { }
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
index aa6a3170ab5a..2b00c776f223 100644
--- a/arch/x86/include/asm/bios_ebda.h
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -17,27 +17,6 @@ static inline unsigned int get_bios_ebda(void)
 	return address;	/* 0 means none */
 }
 
-/*
- * Return the sanitized length of the EBDA in bytes, if it exists.
- */
-static inline unsigned int get_bios_ebda_length(void)
-{
-	unsigned int address;
-	unsigned int length;
-
-	address = get_bios_ebda();
-	if (!address)
-		return 0;
-
-	/* EBDA length is byte 0 of the EBDA (stored in KiB) */
-	length = *(unsigned char *)phys_to_virt(address);
-	length <<= 10;
-
-	/* Trim the length if it extends beyond 640KiB */
-	length = min_t(unsigned int, (640 * 1024) - address, length);
-	return length;
-}
-
 void reserve_ebda_region(void);
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 6b8d6e8cd449..abd06b19ddd2 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -12,29 +12,46 @@
 
 /* Minimum kernel alignment, as a power of two */
 #ifdef CONFIG_X86_64
-#define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
+# define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_SIZE_ORDER)
+# define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_SIZE_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
 #if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
 	(CONFIG_PHYSICAL_ALIGN < MIN_KERNEL_ALIGN)
-#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
+# error "Invalid value for CONFIG_PHYSICAL_ALIGN"
 #endif
 
 #ifdef CONFIG_KERNEL_BZIP2
-#define BOOT_HEAP_SIZE             0x400000
+# define BOOT_HEAP_SIZE		0x400000
 #else /* !CONFIG_KERNEL_BZIP2 */
-
-#define BOOT_HEAP_SIZE	0x10000
-
-#endif /* !CONFIG_KERNEL_BZIP2 */
+# define BOOT_HEAP_SIZE		 0x10000
+#endif
 
 #ifdef CONFIG_X86_64
-#define BOOT_STACK_SIZE	0x4000
-#else
-#define BOOT_STACK_SIZE	0x1000
+# define BOOT_STACK_SIZE	0x4000
+
+# define BOOT_INIT_PGT_SIZE	(6*4096)
+# ifdef CONFIG_RANDOMIZE_BASE
+/*
+ * Assuming all cross the 512GB boundary:
+ * 1 page for level4
+ * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
+ * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
+ * Total is 19 pages.
+ */
+#  ifdef CONFIG_X86_VERBOSE_BOOTUP
+#   define BOOT_PGT_SIZE	(19*4096)
+#  else /* !CONFIG_X86_VERBOSE_BOOTUP */
+#   define BOOT_PGT_SIZE	(17*4096)
+#  endif
+# else /* !CONFIG_RANDOMIZE_BASE */
+#  define BOOT_PGT_SIZE		BOOT_INIT_PGT_SIZE
+# endif
+
+#else /* !CONFIG_X86_64 */
+# define BOOT_STACK_SIZE	0x1000
 #endif
 
 #endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index d194266acb28..eae33c7170c8 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -3,11 +3,10 @@
 #ifndef _ASM_X86_CLOCKSOURCE_H
 #define _ASM_X86_CLOCKSOURCE_H
 
-#define VCLOCK_NONE	0  /* No vDSO clock available.	*/
-#define VCLOCK_TSC	1  /* vDSO should use vread_tsc.	*/
-#define VCLOCK_HPET	2  /* vDSO should use vread_hpet.	*/
-#define VCLOCK_PVCLOCK	3 /* vDSO should use vread_pvclock. */
-#define VCLOCK_MAX	3
+#define VCLOCK_NONE	0	/* No vDSO clock available.		*/
+#define VCLOCK_TSC	1	/* vDSO should use vread_tsc.		*/
+#define VCLOCK_PVCLOCK	2	/* vDSO should use vread_pvclock.	*/
+#define VCLOCK_MAX	2
 
 struct arch_clocksource_data {
 	int vclock_mode;
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index ebb102e1bbc7..5a3b2c119ed0 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -307,7 +307,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 	return (void __user *)round_down(sp - len, 16);
 }
 
-static inline bool is_x32_task(void)
+static inline bool in_x32_syscall(void)
 {
 #ifdef CONFIG_X86_X32_ABI
 	if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
@@ -318,7 +318,7 @@ static inline bool is_x32_task(void)
 
 static inline bool in_compat_syscall(void)
 {
-	return is_ia32_task() || is_x32_task();
+	return in_ia32_syscall() || in_x32_syscall();
 }
 #define in_compat_syscall in_compat_syscall	/* override the generic impl */
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aeab47932933..483fb547e3c0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -27,6 +27,7 @@ enum cpuid_leafs
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
+	CPUID_8000_0007_EBX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -118,31 +119,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
-#define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_pse		boot_cpu_has(X86_FEATURE_PSE)
-#define cpu_has_tsc		boot_cpu_has(X86_FEATURE_TSC)
-#define cpu_has_pge		boot_cpu_has(X86_FEATURE_PGE)
-#define cpu_has_apic		boot_cpu_has(X86_FEATURE_APIC)
-#define cpu_has_fxsr		boot_cpu_has(X86_FEATURE_FXSR)
-#define cpu_has_xmm		boot_cpu_has(X86_FEATURE_XMM)
-#define cpu_has_xmm2		boot_cpu_has(X86_FEATURE_XMM2)
-#define cpu_has_aes		boot_cpu_has(X86_FEATURE_AES)
-#define cpu_has_avx		boot_cpu_has(X86_FEATURE_AVX)
-#define cpu_has_avx2		boot_cpu_has(X86_FEATURE_AVX2)
-#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLUSH)
-#define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
-#define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
-#define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
-#define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
-#define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
-#define cpu_has_xsaves		boot_cpu_has(X86_FEATURE_XSAVES)
-#define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
-#define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
-/*
- * Do not add any more of those clumsy macros - use static_cpu_has() for
- * fast paths and boot_cpu_has() otherwise!
- */
-
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 8f9afefd2dc5..4a413485f9eb 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -12,7 +12,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	17	/* N 32-bit words worth of info */
+#define NCAPINTS	18	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -177,6 +177,7 @@
 #define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
 #define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
 #define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
+#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
 #define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
 #define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
 
@@ -250,6 +251,7 @@
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
 #define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
@@ -280,6 +282,11 @@
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
 
+/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+
 /*
  * BUG word(s)
  */
@@ -294,6 +301,9 @@
 #define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
+
 
 #ifdef CONFIG_X86_32
 /*
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 53748c45e488..78d1e7467eae 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,7 @@
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/processor-flags.h>
 #include <asm/tlb.h>
 
 /*
@@ -28,33 +29,22 @@
 
 #define MAX_CMDLINE_ADDRESS	UINT_MAX
 
-#ifdef CONFIG_X86_32
+#define ARCH_EFI_IRQ_FLAGS_MASK	X86_EFLAGS_IF
 
+#ifdef CONFIG_X86_32
 
 extern unsigned long asmlinkage efi_call_phys(void *, ...);
 
+#define arch_efi_call_virt_setup()	kernel_fpu_begin()
+#define arch_efi_call_virt_teardown()	kernel_fpu_end()
+
 /*
  * Wrap all the virtual calls in a way that forces the parameters on the stack.
  */
-
-/* Use this macro if your virtual returns a non-void value */
-#define efi_call_virt(f, args...) \
+#define arch_efi_call_virt(f, args...)					\
 ({									\
-	efi_status_t __s;						\
-	kernel_fpu_begin();						\
-	__s = ((efi_##f##_t __attribute__((regparm(0)))*)		\
-		efi.systab->runtime->f)(args);				\
-	kernel_fpu_end();						\
-	__s;								\
-})
-
-/* Use this macro if your virtual call does not return any value */
-#define __efi_call_virt(f, args...) \
-({									\
-	kernel_fpu_begin();						\
 	((efi_##f##_t __attribute__((regparm(0)))*)			\
 		efi.systab->runtime->f)(args);				\
-	kernel_fpu_end();						\
 })
 
 #define efi_ioremap(addr, size, type, attr)	ioremap_cache(addr, size)
@@ -78,10 +68,8 @@ struct efi_scratch {
 	u64	phys_stack;
 } __packed;
 
-#define efi_call_virt(f, ...)						\
+#define arch_efi_call_virt_setup()					\
 ({									\
-	efi_status_t __s;						\
-									\
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
@@ -91,9 +79,13 @@ struct efi_scratch {
 		write_cr3((unsigned long)efi_scratch.efi_pgt);		\
 		__flush_tlb_all();					\
 	}								\
-									\
-	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
-									\
+})
+
+#define arch_efi_call_virt(f, args...)					\
+	efi_call((void *)efi.systab->runtime->f, args)			\
+
+#define arch_efi_call_virt_teardown()					\
+({									\
 	if (efi_scratch.use_pgd) {					\
 		write_cr3(efi_scratch.prev_cr3);			\
 		__flush_tlb_all();					\
@@ -101,15 +93,8 @@ struct efi_scratch {
 									\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
-	__s;								\
 })
 
-/*
- * All X86_64 virt calls return non-void values. Thus, use non-void call for
- * virt calls that would be void on X86_32.
- */
-#define __efi_call_virt(f, args...) efi_call_virt(f, args)
-
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 					u32 type, u64 attribute);
 
@@ -180,6 +165,8 @@ static inline bool efi_runtime_supported(void)
 extern struct console early_efi_console;
 extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 
+extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
+
 #ifdef CONFIG_EFI_MIXED
 extern void efi_thunk_runtime_setup(void);
 extern efi_status_t efi_thunk_set_virtual_address_map(
@@ -225,6 +212,11 @@ __pure const struct efi_config *__efi_early(void);
 #define efi_call_early(f, ...)						\
 	__efi_early()->call(__efi_early()->f, __VA_ARGS__);
 
+#define __efi_call_early(f, ...)					\
+	__efi_early()->call((unsigned long)f, __VA_ARGS__);
+
+#define efi_is_64bit()		__efi_early()->is64
+
 extern bool efi_reboot_required(void);
 
 #else
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 15340e36ddcb..fea7724141a0 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -176,7 +176,7 @@ static inline void elf_common_init(struct thread_struct *t,
 	regs->si = regs->di = regs->bp = 0;
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0;
 	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
-	t->fs = t->gs = 0;
+	t->fsbase = t->gsbase = 0;
 	t->fsindex = t->gsindex = 0;
 	t->ds = t->es = ds;
 }
@@ -226,8 +226,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fs;			\
-	(pr_reg)[22] = current->thread.gs;			\
+	(pr_reg)[21] = current->thread.fsbase;			\
+	(pr_reg)[22] = current->thread.gsbase;			\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index e6a8613fbfb0..3a106165e03a 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,7 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
-#define hugepages_supported() cpu_has_pse
+#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index d0afb05c84fc..f70604125286 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -5,7 +5,7 @@
 
 static inline bool arch_irq_work_has_interrupt(void)
 {
-	return cpu_has_apic;
+	return boot_cpu_has(X86_FEATURE_APIC);
 }
 
 #endif /* _ASM_IRQ_WORK_H */
diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h
index 332f98c9111f..22a8537eb780 100644
--- a/arch/x86/include/asm/kgdb.h
+++ b/arch/x86/include/asm/kgdb.h
@@ -6,6 +6,8 @@
  * Copyright (C) 2008 Wind River Systems, Inc.
  */
 
+#include <asm/ptrace.h>
+
 /*
  * BUFMAX defines the maximum number of characters in inbound/outbound
  * buffers at least NUMREGBYTES*2 are needed for register packets
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 79327e9483a3..0ccb26dda126 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,40 +8,6 @@
 
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
-
-/*
- * Make sure the compiler doesn't do anything stupid with the
- * arguments on the stack - they are owned by the *caller*, not
- * the callee. This just fools gcc into not spilling into them,
- * and keeps it from doing tailcall recursion and/or using the
- * stack slots for temporaries, since they are live and "used"
- * all the way to the end of the function.
- *
- * NOTE! On x86-64, all the arguments are in registers, so this
- * only matters on a 32-bit kernel.
- */
-#define asmlinkage_protect(n, ret, args...) \
-	__asmlinkage_protect##n(ret, ##args)
-#define __asmlinkage_protect_n(ret, args...) \
-	__asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args)
-#define __asmlinkage_protect0(ret) \
-	__asmlinkage_protect_n(ret)
-#define __asmlinkage_protect1(ret, arg1) \
-	__asmlinkage_protect_n(ret, "m" (arg1))
-#define __asmlinkage_protect2(ret, arg1, arg2) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2))
-#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3))
-#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
-			      "m" (arg4))
-#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
-			      "m" (arg4), "m" (arg5))
-#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
-	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
-			      "m" (arg4), "m" (arg5), "m" (arg6))
-
 #endif /* CONFIG_X86_32 */
 
 #ifdef __ASSEMBLY__
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 92b6f651fa4f..8bf766ef0e18 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -104,13 +104,23 @@
 #define MCE_LOG_SIGNATURE	"MACHINECHECK"
 
 /* AMD Scalable MCA */
+#define MSR_AMD64_SMCA_MC0_CTL		0xc0002000
+#define MSR_AMD64_SMCA_MC0_STATUS	0xc0002001
+#define MSR_AMD64_SMCA_MC0_ADDR		0xc0002002
 #define MSR_AMD64_SMCA_MC0_MISC0	0xc0002003
 #define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
 #define MSR_AMD64_SMCA_MC0_IPID		0xc0002005
+#define MSR_AMD64_SMCA_MC0_DESTAT	0xc0002008
+#define MSR_AMD64_SMCA_MC0_DEADDR	0xc0002009
 #define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
+#define MSR_AMD64_SMCA_MCx_CTL(x)	(MSR_AMD64_SMCA_MC0_CTL + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_STATUS(x)	(MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_ADDR(x)	(MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_MISC(x)	(MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_IPID(x)	(MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_DESTAT(x)	(MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_DEADDR(x)	(MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_MISCy(x, y)	((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
 
 /*
@@ -168,9 +178,18 @@ struct mce_vendor_flags {
 
 	      __reserved_0	: 61;
 };
+
+struct mca_msr_regs {
+	u32 (*ctl)	(int bank);
+	u32 (*status)	(int bank);
+	u32 (*addr)	(int bank);
+	u32 (*misc)	(int bank);
+};
+
 extern struct mce_vendor_flags mce_flags;
 
 extern struct mca_config mca_cfg;
+extern struct mca_msr_regs msr_ops;
 extern void mce_register_decode_chain(struct notifier_block *nb);
 extern void mce_unregister_decode_chain(struct notifier_block *nb);
 
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 84280029cafd..396348196aa7 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -115,103 +115,12 @@ static inline void destroy_context(struct mm_struct *mm)
 	destroy_context_ldt(mm);
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
+extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+		      struct task_struct *tsk);
 
-	if (likely(prev != next)) {
-#ifdef CONFIG_SMP
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-
-		/*
-		 * Re-load page tables.
-		 *
-		 * This logic has an ordering constraint:
-		 *
-		 *  CPU 0: Write to a PTE for 'next'
-		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
-		 *  CPU 1: set bit 1 in next's mm_cpumask
-		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
-		 *
-		 * We need to prevent an outcome in which CPU 1 observes
-		 * the new PTE value and CPU 0 observes bit 1 clear in
-		 * mm_cpumask.  (If that occurs, then the IPI will never
-		 * be sent, and CPU 0's TLB will contain a stale entry.)
-		 *
-		 * The bad outcome can occur if either CPU's load is
-		 * reordered before that CPU's store, so both CPUs must
-		 * execute full barriers to prevent this from happening.
-		 *
-		 * Thus, switch_mm needs a full barrier between the
-		 * store to mm_cpumask and any operation that could load
-		 * from next->pgd.  TLB fills are special and can happen
-		 * due to instruction fetches or for no reason at all,
-		 * and neither LOCK nor MFENCE orders them.
-		 * Fortunately, load_cr3() is serializing and gives the
-		 * ordering guarantee we need.
-		 *
-		 */
-		load_cr3(next->pgd);
-
-		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-
-		/* Stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
-
-		/* Load per-mm CR4 state */
-		load_mm_cr4(next);
-
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-		/*
-		 * Load the LDT, if the LDT is different.
-		 *
-		 * It's possible that prev->context.ldt doesn't match
-		 * the LDT register.  This can happen if leave_mm(prev)
-		 * was called and then modify_ldt changed
-		 * prev->context.ldt but suppressed an IPI to this CPU.
-		 * In this case, prev->context.ldt != NULL, because we
-		 * never set context.ldt to NULL while the mm still
-		 * exists.  That means that next->context.ldt !=
-		 * prev->context.ldt, because mms never share an LDT.
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_mm_ldt(next);
-#endif
-	}
-#ifdef CONFIG_SMP
-	  else {
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
-
-		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * On established mms, the mm_cpumask is only changed
-			 * from irq context, from ptep_clear_flush() while in
-			 * lazy tlb mode, and here. Irqs are blocked during
-			 * schedule, protecting us from simultaneous changes.
-			 */
-			cpumask_set_cpu(cpu, mm_cpumask(next));
-
-			/*
-			 * We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 *
-			 * As above, load_cr3() is serializing and orders TLB
-			 * fills with respect to the mm_cpumask write.
-			 */
-			load_cr3(next->pgd);
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-			load_mm_cr4(next);
-			load_mm_ldt(next);
-		}
-	}
-#endif
-}
+extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			       struct task_struct *tsk);
+#define switch_mm_irqs_off switch_mm_irqs_off
 
 #define activate_mm(prev, next)			\
 do {						\
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 5b3c9a55f51c..5a73a9c62c39 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -89,27 +89,16 @@
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
 
 #define MSR_IA32_RTIT_CTL		0x00000570
-#define RTIT_CTL_TRACEEN		BIT(0)
-#define RTIT_CTL_CYCLEACC		BIT(1)
-#define RTIT_CTL_OS			BIT(2)
-#define RTIT_CTL_USR			BIT(3)
-#define RTIT_CTL_CR3EN			BIT(7)
-#define RTIT_CTL_TOPA			BIT(8)
-#define RTIT_CTL_MTC_EN			BIT(9)
-#define RTIT_CTL_TSC_EN			BIT(10)
-#define RTIT_CTL_DISRETC		BIT(11)
-#define RTIT_CTL_BRANCH_EN		BIT(13)
-#define RTIT_CTL_MTC_RANGE_OFFSET	14
-#define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
-#define RTIT_CTL_CYC_THRESH_OFFSET	19
-#define RTIT_CTL_CYC_THRESH		(0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
-#define RTIT_CTL_PSB_FREQ_OFFSET	24
-#define RTIT_CTL_PSB_FREQ      		(0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
 #define MSR_IA32_RTIT_STATUS		0x00000571
-#define RTIT_STATUS_CONTEXTEN		BIT(1)
-#define RTIT_STATUS_TRIGGEREN		BIT(2)
-#define RTIT_STATUS_ERROR		BIT(4)
-#define RTIT_STATUS_STOPPED		BIT(5)
+#define MSR_IA32_RTIT_STATUS		0x00000571
+#define MSR_IA32_RTIT_ADDR0_A		0x00000580
+#define MSR_IA32_RTIT_ADDR0_B		0x00000581
+#define MSR_IA32_RTIT_ADDR1_A		0x00000582
+#define MSR_IA32_RTIT_ADDR1_B		0x00000583
+#define MSR_IA32_RTIT_ADDR2_A		0x00000584
+#define MSR_IA32_RTIT_ADDR2_B		0x00000585
+#define MSR_IA32_RTIT_ADDR3_A		0x00000586
+#define MSR_IA32_RTIT_ADDR3_B		0x00000587
 #define MSR_IA32_RTIT_CR3_MATCH		0x00000572
 #define MSR_IA32_RTIT_OUTPUT_BASE	0x00000560
 #define MSR_IA32_RTIT_OUTPUT_MASK	0x00000561
@@ -205,6 +194,8 @@
 #define MSR_CONFIG_TDP_CONTROL		0x0000064B
 #define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
 
+#define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
+
 #define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
 #define MSR_PKG_ANY_CORE_C0_RES		0x00000659
 #define MSR_PKG_ANY_GFXE_C0_RES		0x0000065A
@@ -315,6 +306,9 @@
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 
+/* Fam 17h MSRs */
+#define MSR_F17H_IRPERF			0xc00000e9
+
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
@@ -328,6 +322,7 @@
 #define MSR_F15H_PERF_CTR		0xc0010201
 #define MSR_F15H_NB_PERF_CTL		0xc0010240
 #define MSR_F15H_NB_PERF_CTR		0xc0010241
+#define MSR_F15H_PTSC			0xc0010280
 #define MSR_F15H_IC_CFG			0xc0011021
 
 /* Fam 10h MSRs */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 7a79ee2778b3..7dc1d8fef7fd 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -84,7 +84,10 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+	asm volatile("1: rdmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
+		     : EAX_EDX_RET(val, low, high) : "c" (msr));
 	if (msr_tracepoint_active(__tracepoint_read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
@@ -98,7 +101,10 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
 		     "1:\n\t"
 		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
+		     "3: mov %[fault],%[err]\n\t"
+		     "xorl %%eax, %%eax\n\t"
+		     "xorl %%edx, %%edx\n\t"
+		     "jmp 1b\n\t"
 		     ".previous\n\t"
 		     _ASM_EXTABLE(2b, 3b)
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
@@ -108,10 +114,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static inline void native_write_msr(unsigned int msr,
-				    unsigned low, unsigned high)
+/* Can be uninlined because referenced by paravirt */
+notrace static inline void native_write_msr(unsigned int msr,
+					    unsigned low, unsigned high)
 {
-	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+	asm volatile("1: wrmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+		     : : "c" (msr), "a"(low), "d" (high) : "memory");
 	if (msr_tracepoint_active(__tracepoint_read_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f64e23d..dbff1456d215 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
 #define _ASM_X86_MTRR_H
 
 #include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
 
 
 /*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 {
 }
+static inline void mtrr_bp_init(void)
+{
+	pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
 
 #define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
 #define set_mtrr_aps_delayed_init() do {} while (0)
 #define mtrr_aps_init() do {} while (0)
 #define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 802dde30c928..cf8f619b305f 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -37,7 +37,10 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
+#ifndef __pa
 #define __pa(x)		__phys_addr((unsigned long)(x))
+#endif
+
 #define __pa_nodebug(x)	__phys_addr_nodebug((unsigned long)(x))
 /* __pa_symbol should be used for C visible symbols.
    This seems to be the official gcc blessed way to do such arithmetic. */
@@ -51,7 +54,9 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 #define __pa_symbol(x) \
 	__phys_addr_symbol(__phys_reloc_hide((unsigned long)(x)))
 
+#ifndef __va
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
+#endif
 
 #define __boot_va(x)		__va(x)
 #define __boot_pa(x)		__pa(x)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 4928cf0d5af0..d5c2f8b40faa 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -47,12 +47,10 @@
  * are fully set up. If kernel ASLR is configured, it can extend the
  * kernel page table mapping, reducing the size of the modules area.
  */
-#define KERNEL_IMAGE_SIZE_DEFAULT      (512 * 1024 * 1024)
-#if defined(CONFIG_RANDOMIZE_BASE) && \
-	CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE_DEFAULT
-#define KERNEL_IMAGE_SIZE   CONFIG_RANDOMIZE_BASE_MAX_OFFSET
+#if defined(CONFIG_RANDOMIZE_BASE)
+#define KERNEL_IMAGE_SIZE	(1024 * 1024 * 1024)
 #else
-#define KERNEL_IMAGE_SIZE      KERNEL_IMAGE_SIZE_DEFAULT
+#define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
 #endif
 
 #endif /* _ASM_X86_PAGE_64_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 601f1b8f9961..2970d22d7766 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -15,17 +15,6 @@
 #include <linux/cpumask.h>
 #include <asm/frame.h>
 
-static inline int paravirt_enabled(void)
-{
-	return pv_info.paravirt_enabled;
-}
-
-static inline int paravirt_has_feature(unsigned int feature)
-{
-	WARN_ON_ONCE(!pv_info.paravirt_enabled);
-	return (pv_info.features & feature);
-}
-
 static inline void load_sp0(struct tss_struct *tss,
 			     struct thread_struct *thread)
 {
@@ -130,21 +119,31 @@ static inline void wbinvd(void)
 
 #define get_kernel_rpl()  (pv_info.kernel_rpl)
 
-static inline u64 paravirt_read_msr(unsigned msr, int *err)
+static inline u64 paravirt_read_msr(unsigned msr)
+{
+	return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr);
+}
+
+static inline void paravirt_write_msr(unsigned msr,
+				      unsigned low, unsigned high)
+{
+	return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high);
+}
+
+static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
 {
-	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
+	return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err);
 }
 
-static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
+static inline int paravirt_write_msr_safe(unsigned msr,
+					  unsigned low, unsigned high)
 {
-	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
+	return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high);
 }
 
-/* These should all do BUG_ON(_err), but our headers are too tangled. */
 #define rdmsr(msr, val1, val2)			\
 do {						\
-	int _err;				\
-	u64 _l = paravirt_read_msr(msr, &_err);	\
+	u64 _l = paravirt_read_msr(msr);	\
 	val1 = (u32)_l;				\
 	val2 = _l >> 32;			\
 } while (0)
@@ -156,8 +155,7 @@ do {						\
 
 #define rdmsrl(msr, val)			\
 do {						\
-	int _err;				\
-	val = paravirt_read_msr(msr, &_err);	\
+	val = paravirt_read_msr(msr);		\
 } while (0)
 
 static inline void wrmsrl(unsigned msr, u64 val)
@@ -165,23 +163,23 @@ static inline void wrmsrl(unsigned msr, u64 val)
 	wrmsr(msr, (u32)val, (u32)(val>>32));
 }
 
-#define wrmsr_safe(msr, a, b)	paravirt_write_msr(msr, a, b)
+#define wrmsr_safe(msr, a, b)	paravirt_write_msr_safe(msr, a, b)
 
 /* rdmsr with exception handling */
-#define rdmsr_safe(msr, a, b)			\
-({						\
-	int _err;				\
-	u64 _l = paravirt_read_msr(msr, &_err);	\
-	(*a) = (u32)_l;				\
-	(*b) = _l >> 32;			\
-	_err;					\
+#define rdmsr_safe(msr, a, b)				\
+({							\
+	int _err;					\
+	u64 _l = paravirt_read_msr_safe(msr, &_err);	\
+	(*a) = (u32)_l;					\
+	(*b) = _l >> 32;				\
+	_err;						\
 })
 
 static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 {
 	int err;
 
-	*p = paravirt_read_msr(msr, &err);
+	*p = paravirt_read_msr_safe(msr, &err);
 	return err;
 }
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index e8c2326478c8..7fa9e7740ba3 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -69,15 +69,9 @@ struct pv_info {
 	u16 extra_user_64bit_cs;  /* __USER_CS if none */
 #endif
 
-	int paravirt_enabled;
-	unsigned int features;	  /* valid only if paravirt_enabled is set */
 	const char *name;
 };
 
-#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x)
-/* Supported features */
-#define PV_SUPPORTED_RTC        (1<<0)
-
 struct pv_init_ops {
 	/*
 	 * Patch may replace one of the defined code sequences with
@@ -155,10 +149,16 @@ struct pv_cpu_ops {
 	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
 		      unsigned int *ecx, unsigned int *edx);
 
-	/* MSR, PMC and TSR operations.
-	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
-	u64 (*read_msr)(unsigned int msr, int *err);
-	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+	/* Unsafe MSR operations.  These will warn or panic on failure. */
+	u64 (*read_msr)(unsigned int msr);
+	void (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+
+	/*
+	 * Safe MSR operations.
+	 * read sets err to 0 or -EIO.  write returns 0 or -EIO.
+	 */
+	u64 (*read_msr_safe)(unsigned int msr, int *err);
+	int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high);
 
 	u64 (*read_pmc)(int counter);
 
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..0b1ff4c1c14e 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,8 @@
 #include <asm/pgtable_types.h>
 
 bool pat_enabled(void);
+void pat_disable(const char *reason);
 extern void pat_init(void);
-void pat_init_cache_modes(u64);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 97f3242e133c..f86491a7bc9d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -183,7 +183,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 
 static inline int has_transparent_hugepage(void)
 {
-	return cpu_has_pse;
+	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
 #ifdef __HAVE_ARCH_PTE_DEVMAP
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 9264476f3d57..62c6cc3cc5d3 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -388,9 +388,16 @@ struct thread_struct {
 	unsigned long		ip;
 #endif
 #ifdef CONFIG_X86_64
-	unsigned long		fs;
+	unsigned long		fsbase;
+	unsigned long		gsbase;
+#else
+	/*
+	 * XXX: this could presumably be unsigned short.  Alternatively,
+	 * 32-bit kernels could be taught to use fsindex instead.
+	 */
+	unsigned long fs;
+	unsigned long gs;
 #endif
-	unsigned long		gs;
 
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
@@ -473,8 +480,6 @@ static inline unsigned long current_top_of_stack(void)
 #include <asm/paravirt.h>
 #else
 #define __cpuid			native_cpuid
-#define paravirt_enabled()	0
-#define paravirt_has(x) 	0
 
 static inline void load_sp0(struct tss_struct *tss,
 			    struct thread_struct *thread)
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index ceec86eb68e9..453744c1d347 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -99,26 +99,36 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+#define ____down_write(sem, slow_path)			\
+({							\
+	long tmp;					\
+	struct rw_semaphore* ret;			\
+	asm volatile("# beginning down_write\n\t"	\
+		     LOCK_PREFIX "  xadd      %1,(%3)\n\t"	\
+		     /* adds 0xffff0001, returns the old value */ \
+		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
+		     /* was the active mask 0 before? */\
+		     "  jz        1f\n"			\
+		     "  call " slow_path "\n"		\
+		     "1:\n"				\
+		     "# ending down_write"		\
+		     : "+m" (sem->count), "=d" (tmp), "=a" (ret)	\
+		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
+		     : "memory", "cc");			\
+	ret;						\
+})
+
+static inline void __down_write(struct rw_semaphore *sem)
 {
-	long tmp;
-	asm volatile("# beginning down_write\n\t"
-		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
-		     /* adds 0xffff0001, returns the old value */
-		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
-		     /* was the active mask 0 before? */
-		     "  jz        1f\n"
-		     "  call call_rwsem_down_write_failed\n"
-		     "1:\n"
-		     "# ending down_write"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory", "cc");
+	____down_write(sem, "call_rwsem_down_write_failed");
 }
 
-static inline void __down_write(struct rw_semaphore *sem)
+static inline int __down_write_killable(struct rw_semaphore *sem)
 {
-	__down_write_nested(sem, 0);
+	if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable")))
+		return -EINTR;
+
+	return 0;
 }
 
 /*
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 7d5a1929d76b..1549caa098f0 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_SEGMENT_H
 
 #include <linux/const.h>
+#include <asm/alternative.h>
 
 /*
  * Constructor for a conventional segment GDT (or LDT) entry.
@@ -207,13 +208,6 @@
 #define __USER_CS			(GDT_ENTRY_DEFAULT_USER_CS*8 + 3)
 #define __PER_CPU_SEG			(GDT_ENTRY_PER_CPU*8 + 3)
 
-/* TLS indexes for 64-bit - hardcoded in arch_prctl(): */
-#define FS_TLS				0
-#define GS_TLS				1
-
-#define GS_TLS_SEL			((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3)
-#define FS_TLS_SEL			((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3)
-
 #endif
 
 #ifndef CONFIG_PARAVIRT
@@ -249,10 +243,13 @@ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDL
 #endif
 
 /*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
+ * Load a segment. Fall back on loading the zero segment if something goes
+ * wrong.  This variant assumes that loading zero fully clears the segment.
+ * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any
+ * failure to fully clear the cached descriptor is only observable for
+ * FS and GS.
  */
-#define loadsegment(seg, value)						\
+#define __loadsegment_simple(seg, value)				\
 do {									\
 	unsigned short __val = (value);					\
 									\
@@ -269,6 +266,38 @@ do {									\
 		     : "+r" (__val) : : "memory");			\
 } while (0)
 
+#define __loadsegment_ss(value) __loadsegment_simple(ss, (value))
+#define __loadsegment_ds(value) __loadsegment_simple(ds, (value))
+#define __loadsegment_es(value) __loadsegment_simple(es, (value))
+
+#ifdef CONFIG_X86_32
+
+/*
+ * On 32-bit systems, the hidden parts of FS and GS are unobservable if
+ * the selector is NULL, so there's no funny business here.
+ */
+#define __loadsegment_fs(value) __loadsegment_simple(fs, (value))
+#define __loadsegment_gs(value) __loadsegment_simple(gs, (value))
+
+#else
+
+static inline void __loadsegment_fs(unsigned short value)
+{
+	asm volatile("						\n"
+		     "1:	movw %0, %%fs			\n"
+		     "2:					\n"
+
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs)
+
+		     : : "rm" (value) : "memory");
+}
+
+/* __loadsegment_gs is intentionally undefined.  Use load_gs_index instead. */
+
+#endif
+
+#define loadsegment(seg, value) __loadsegment_ ## seg (value)
+
 /*
  * Save a segment register away:
  */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 11af24e09c8a..ac1d5da14734 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -6,6 +6,7 @@
 #define COMMAND_LINE_SIZE 2048
 
 #include <linux/linkage.h>
+#include <asm/page_types.h>
 
 #ifdef __i386__
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b7bf11..8f321a1b03a1 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -39,8 +39,7 @@ do {									\
 	 */								\
 	unsigned long ebx, ecx, edx, esi, edi;				\
 									\
-	asm volatile("pushfl\n\t"		/* save    flags */	\
-		     "pushl %%ebp\n\t"		/* save    EBP   */	\
+	asm volatile("pushl %%ebp\n\t"		/* save    EBP   */	\
 		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
 		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
 		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
@@ -49,7 +48,6 @@ do {									\
 		     "jmp __switch_to\n"	/* regparm call  */	\
 		     "1:\t"						\
 		     "popl %%ebp\n\t"		/* restore EBP   */	\
-		     "popfl\n"			/* restore flags */	\
 									\
 		     /* output parameters */				\
 		     : [prev_sp] "=m" (prev->thread.sp),		\
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
new file mode 100644
index 000000000000..90395063383c
--- /dev/null
+++ b/arch/x86/include/asm/text-patching.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_X86_TEXT_PATCHING_H
+#define _ASM_X86_TEXT_PATCHING_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <asm/ptrace.h>
+
+struct paravirt_patch_site;
+#ifdef CONFIG_PARAVIRT
+void apply_paravirt(struct paravirt_patch_site *start,
+		    struct paravirt_patch_site *end);
+#else
+static inline void apply_paravirt(struct paravirt_patch_site *start,
+				  struct paravirt_patch_site *end)
+{}
+#define __parainstructions	NULL
+#define __parainstructions_end	NULL
+#endif
+
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
+/*
+ * Clear and restore the kernel write-protection flag on the local CPU.
+ * Allows the kernel to edit read-only pages.
+ * Side-effect: any interrupt handler running between save and restore will have
+ * the ability to write to read-only pages.
+ *
+ * Warning:
+ * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
+ * no thread can be preempted in the instructions being modified (no iret to an
+ * invalid instruction possible) or if the instructions are changed from a
+ * consistent state to another consistent state atomically.
+ * On the local CPU you need to be protected again NMI or MCE handlers seeing an
+ * inconsistent instruction while you patch.
+ */
+extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern int poke_int3_handler(struct pt_regs *regs);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+
+#endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index ffae84df8a93..30c133ac05cd 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -255,7 +255,7 @@ static inline bool test_and_clear_restore_sigmask(void)
 	return true;
 }
 
-static inline bool is_ia32_task(void)
+static inline bool in_ia32_syscall(void)
 {
 #ifdef CONFIG_X86_32
 	return true;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 1fde8d580a5b..4e5be94e079a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -181,7 +181,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
 
 static inline void __flush_tlb_all(void)
 {
-	if (cpu_has_pge)
+	if (static_cpu_has(X86_FEATURE_PGE))
 		__flush_tlb_global();
 	else
 		__flush_tlb();
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 174c4212780a..7428697c5b8d 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -22,7 +22,7 @@ extern void disable_TSC(void);
 static inline cycles_t get_cycles(void)
 {
 #ifndef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
+	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return 0;
 #endif
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 2e7513d1f1f4..12f9653bde8d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -118,7 +118,7 @@ struct exception_table_entry {
 
 extern int fixup_exception(struct pt_regs *regs, int trapnr);
 extern bool ex_has_fault_handler(unsigned long ip);
-extern int early_fixup_exception(unsigned long *ip);
+extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
 
 /*
  * These are the main single-value transfer routines.  They automatically
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 71605c7d5c5c..c852590254d5 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -51,15 +51,66 @@ enum {
 	BIOS_STATUS_UNAVAIL		= -EBUSY
 };
 
+/* Address map parameters */
+struct uv_gam_parameters {
+	u64	mmr_base;
+	u64	gru_base;
+	u8	mmr_shift;	/* Convert PNode to MMR space offset */
+	u8	gru_shift;	/* Convert PNode to GRU space offset */
+	u8	gpa_shift;	/* Size of offset field in GRU phys addr */
+	u8	unused1;
+};
+
+/* UV_TABLE_GAM_RANGE_ENTRY values */
+#define UV_GAM_RANGE_TYPE_UNUSED	0 /* End of table */
+#define UV_GAM_RANGE_TYPE_RAM		1 /* Normal RAM */
+#define UV_GAM_RANGE_TYPE_NVRAM		2 /* Non-volatile memory */
+#define UV_GAM_RANGE_TYPE_NV_WINDOW	3 /* NVMDIMM block window */
+#define UV_GAM_RANGE_TYPE_NV_MAILBOX	4 /* NVMDIMM mailbox */
+#define UV_GAM_RANGE_TYPE_HOLE		5 /* Unused address range */
+#define UV_GAM_RANGE_TYPE_MAX		6
+
+/* The structure stores PA bits 56:26, for 64MB granularity */
+#define UV_GAM_RANGE_SHFT		26		/* 64MB */
+
+struct uv_gam_range_entry {
+	char	type;		/* Entry type: GAM_RANGE_TYPE_UNUSED, etc. */
+	char	unused1;
+	u16	nasid;		/* HNasid */
+	u16	sockid;		/* Socket ID, high bits of APIC ID */
+	u16	pnode;		/* Index to MMR and GRU spaces */
+	u32	pxm;		/* ACPI proximity domain number */
+	u32	limit;		/* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
+};
+
+#define	UV_SYSTAB_SIG			"UVST"
+#define	UV_SYSTAB_VERSION_1		1	/* UV1/2/3 BIOS version */
+#define	UV_SYSTAB_VERSION_UV4		0x400	/* UV4 BIOS base version */
+#define	UV_SYSTAB_VERSION_UV4_1		0x401	/* + gpa_shift */
+#define	UV_SYSTAB_VERSION_UV4_2		0x402	/* + TYPE_NVRAM/WINDOW/MBOX */
+#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_2
+
+#define	UV_SYSTAB_TYPE_UNUSED		0	/* End of table (offset == 0) */
+#define	UV_SYSTAB_TYPE_GAM_PARAMS	1	/* GAM PARAM conversions */
+#define	UV_SYSTAB_TYPE_GAM_RNG_TBL	2	/* GAM entry table */
+#define	UV_SYSTAB_TYPE_MAX		3
+
 /*
  * The UV system table describes specific firmware
  * capabilities available to the Linux kernel at runtime.
  */
 struct uv_systab {
-	char signature[4];	/* must be "UVST" */
+	char signature[4];	/* must be UV_SYSTAB_SIG */
 	u32 revision;		/* distinguish different firmware revs */
 	u64 function;		/* BIOS runtime callback function ptr */
+	u32 size;		/* systab size (starting with _VERSION_UV4) */
+	struct {
+		u32 type:8;	/* type of entry */
+		u32 offset:24;	/* byte offset from struct start to entry */
+	} entry[1];		/* additional entries follow */
 };
+extern struct uv_systab *uv_systab;
+/* (... end of definitions from UV BIOS ...) */
 
 enum {
 	BIOS_FREQ_BASE_PLATFORM = 0,
@@ -99,7 +150,11 @@ extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
 extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus);
 
+#ifdef CONFIG_EFI
 extern void uv_bios_init(void);
+#else
+void uv_bios_init(void) { }
+#endif
 
 extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
@@ -107,7 +162,7 @@ extern long sn_partition_id;
 extern long sn_coherency_id;
 extern long sn_region_size;
 extern long system_serial_number;
-#define partition_coherence_id()	(sn_coherency_id)
+#define uv_partition_coherence_id()	(sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index fc808b83fccb..cc44d926c17e 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -598,7 +598,7 @@ struct bau_control {
 	int			timeout_tries;
 	int			ipi_attempts;
 	int			conseccompletes;
-	short			nobau;
+	bool			nobau;
 	short			baudisabled;
 	short			cpu;
 	short			osnode;
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index ea7074784cc4..097b80c989c4 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -16,9 +16,11 @@
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/io.h>
+#include <linux/topology.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
 #include <asm/uv/uv_mmrs.h>
+#include <asm/uv/bios.h>
 #include <asm/irq_vectors.h>
 #include <asm/io_apic.h>
 
@@ -103,7 +105,6 @@
  *	      processor APICID register.
  */
 
-
 /*
  * Maximum number of bricks in all partitions and in all coherency domains.
  * This is the total number of bricks accessible in the numalink fabric. It
@@ -127,6 +128,7 @@
  */
 #define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_BLADES * 2)
 
+/* System Controller Interface Reg info */
 struct uv_scir_s {
 	struct timer_list timer;
 	unsigned long	offset;
@@ -137,71 +139,173 @@ struct uv_scir_s {
 	unsigned char	enabled;
 };
 
+/* GAM (globally addressed memory) range table */
+struct uv_gam_range_s {
+	u32	limit;		/* PA bits 56:26 (GAM_RANGE_SHFT) */
+	u16	nasid;		/* node's global physical address */
+	s8	base;		/* entry index of node's base addr */
+	u8	reserved;
+};
+
 /*
  * The following defines attributes of the HUB chip. These attributes are
- * frequently referenced and are kept in the per-cpu data areas of each cpu.
- * They are kept together in a struct to minimize cache misses.
+ * frequently referenced and are kept in a common per hub struct.
+ * After setup, the struct is read only, so it should be readily
+ * available in the L3 cache on the cpu socket for the node.
  */
 struct uv_hub_info_s {
 	unsigned long		global_mmr_base;
+	unsigned long		global_mmr_shift;
 	unsigned long		gpa_mask;
-	unsigned int		gnode_extra;
+	unsigned short		*socket_to_node;
+	unsigned short		*socket_to_pnode;
+	unsigned short		*pnode_to_socket;
+	struct uv_gam_range_s	*gr_table;
+	unsigned short		min_socket;
+	unsigned short		min_pnode;
+	unsigned char		m_val;
+	unsigned char		n_val;
+	unsigned char		gr_table_len;
 	unsigned char		hub_revision;
 	unsigned char		apic_pnode_shift;
+	unsigned char		gpa_shift;
 	unsigned char		m_shift;
 	unsigned char		n_lshift;
+	unsigned int		gnode_extra;
 	unsigned long		gnode_upper;
 	unsigned long		lowmem_remap_top;
 	unsigned long		lowmem_remap_base;
+	unsigned long		global_gru_base;
+	unsigned long		global_gru_shift;
 	unsigned short		pnode;
 	unsigned short		pnode_mask;
 	unsigned short		coherency_domain_number;
 	unsigned short		numa_blade_id;
-	unsigned char		blade_processor_id;
-	unsigned char		m_val;
-	unsigned char		n_val;
+	unsigned short		nr_possible_cpus;
+	unsigned short		nr_online_cpus;
+	short			memory_nid;
+};
+
+/* CPU specific info with a pointer to the hub common info struct */
+struct uv_cpu_info_s {
+	void			*p_uv_hub_info;
+	unsigned char		blade_cpu_id;
 	struct uv_scir_s	scir;
 };
+DECLARE_PER_CPU(struct uv_cpu_info_s, __uv_cpu_info);
+
+#define uv_cpu_info		this_cpu_ptr(&__uv_cpu_info)
+#define uv_cpu_info_per(cpu)	(&per_cpu(__uv_cpu_info, cpu))
+
+#define	uv_scir_info		(&uv_cpu_info->scir)
+#define	uv_cpu_scir_info(cpu)	(&uv_cpu_info_per(cpu)->scir)
+
+/* Node specific hub common info struct */
+extern void **__uv_hub_info_list;
+static inline struct uv_hub_info_s *uv_hub_info_list(int node)
+{
+	return (struct uv_hub_info_s *)__uv_hub_info_list[node];
+}
+
+static inline struct uv_hub_info_s *_uv_hub_info(void)
+{
+	return (struct uv_hub_info_s *)uv_cpu_info->p_uv_hub_info;
+}
+#define	uv_hub_info	_uv_hub_info()
 
-DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info		this_cpu_ptr(&__uv_hub_info)
-#define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
+static inline struct uv_hub_info_s *uv_cpu_hub_info(int cpu)
+{
+	return (struct uv_hub_info_s *)uv_cpu_info_per(cpu)->p_uv_hub_info;
+}
+
+#define	UV_HUB_INFO_VERSION	0x7150
+extern int uv_hub_info_version(void);
+static inline int uv_hub_info_check(int version)
+{
+	if (uv_hub_info_version() == version)
+		return 0;
+
+	pr_crit("UV: uv_hub_info version(%x) mismatch, expecting(%x)\n",
+		uv_hub_info_version(), version);
+
+	BUG();	/* Catastrophic - cannot continue on unknown UV system */
+}
+#define	_uv_hub_info_check()	uv_hub_info_check(UV_HUB_INFO_VERSION)
 
 /*
- * Hub revisions less than UV2_HUB_REVISION_BASE are UV1 hubs. All UV2
- * hubs have revision numbers greater than or equal to UV2_HUB_REVISION_BASE.
+ * HUB revision ranges for each UV HUB architecture.
  * This is a software convention - NOT the hardware revision numbers in
  * the hub chip.
  */
 #define UV1_HUB_REVISION_BASE		1
 #define UV2_HUB_REVISION_BASE		3
 #define UV3_HUB_REVISION_BASE		5
+#define UV4_HUB_REVISION_BASE		7
 
+#ifdef	UV1_HUB_IS_SUPPORTED
 static inline int is_uv1_hub(void)
 {
 	return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE;
 }
+#else
+static inline int is_uv1_hub(void)
+{
+	return 0;
+}
+#endif
 
+#ifdef	UV2_HUB_IS_SUPPORTED
 static inline int is_uv2_hub(void)
 {
 	return ((uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE) &&
 		(uv_hub_info->hub_revision < UV3_HUB_REVISION_BASE));
 }
+#else
+static inline int is_uv2_hub(void)
+{
+	return 0;
+}
+#endif
 
+#ifdef	UV3_HUB_IS_SUPPORTED
+static inline int is_uv3_hub(void)
+{
+	return ((uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE) &&
+		(uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE));
+}
+#else
 static inline int is_uv3_hub(void)
 {
-	return uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE;
+	return 0;
 }
+#endif
 
-static inline int is_uv_hub(void)
+#ifdef	UV4_HUB_IS_SUPPORTED
+static inline int is_uv4_hub(void)
 {
-	return uv_hub_info->hub_revision;
+	return uv_hub_info->hub_revision >= UV4_HUB_REVISION_BASE;
 }
+#else
+static inline int is_uv4_hub(void)
+{
+	return 0;
+}
+#endif
 
-/* code common to uv2 and uv3 only */
 static inline int is_uvx_hub(void)
 {
-	return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE;
+	if (uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE)
+		return uv_hub_info->hub_revision;
+
+	return 0;
+}
+
+static inline int is_uv_hub(void)
+{
+#ifdef	UV1_HUB_IS_SUPPORTED
+	return uv_hub_info->hub_revision;
+#endif
+	return is_uvx_hub();
 }
 
 union uvh_apicid {
@@ -243,24 +347,42 @@ union uvh_apicid {
 #define UV3_LOCAL_MMR_SIZE		(32UL * 1024 * 1024)
 #define UV3_GLOBAL_MMR32_SIZE		(32UL * 1024 * 1024)
 
-#define UV_LOCAL_MMR_BASE		(is_uv1_hub() ? UV1_LOCAL_MMR_BASE : \
-					(is_uv2_hub() ? UV2_LOCAL_MMR_BASE : \
-							UV3_LOCAL_MMR_BASE))
-#define UV_GLOBAL_MMR32_BASE		(is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE :\
-					(is_uv2_hub() ? UV2_GLOBAL_MMR32_BASE :\
-							UV3_GLOBAL_MMR32_BASE))
-#define UV_LOCAL_MMR_SIZE		(is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \
-					(is_uv2_hub() ? UV2_LOCAL_MMR_SIZE : \
-							UV3_LOCAL_MMR_SIZE))
-#define UV_GLOBAL_MMR32_SIZE		(is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\
-					(is_uv2_hub() ? UV2_GLOBAL_MMR32_SIZE :\
-							UV3_GLOBAL_MMR32_SIZE))
+#define UV4_LOCAL_MMR_BASE		0xfa000000UL
+#define UV4_GLOBAL_MMR32_BASE		0xfc000000UL
+#define UV4_LOCAL_MMR_SIZE		(32UL * 1024 * 1024)
+#define UV4_GLOBAL_MMR32_SIZE		(16UL * 1024 * 1024)
+
+#define UV_LOCAL_MMR_BASE		(				\
+					is_uv1_hub() ? UV1_LOCAL_MMR_BASE : \
+					is_uv2_hub() ? UV2_LOCAL_MMR_BASE : \
+					is_uv3_hub() ? UV3_LOCAL_MMR_BASE : \
+					/*is_uv4_hub*/ UV4_LOCAL_MMR_BASE)
+
+#define UV_GLOBAL_MMR32_BASE		(				\
+					is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE : \
+					is_uv2_hub() ? UV2_GLOBAL_MMR32_BASE : \
+					is_uv3_hub() ? UV3_GLOBAL_MMR32_BASE : \
+					/*is_uv4_hub*/ UV4_GLOBAL_MMR32_BASE)
+
+#define UV_LOCAL_MMR_SIZE		(				\
+					is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \
+					is_uv2_hub() ? UV2_LOCAL_MMR_SIZE : \
+					is_uv3_hub() ? UV3_LOCAL_MMR_SIZE : \
+					/*is_uv4_hub*/ UV4_LOCAL_MMR_SIZE)
+
+#define UV_GLOBAL_MMR32_SIZE		(				\
+					is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE : \
+					is_uv2_hub() ? UV2_GLOBAL_MMR32_SIZE : \
+					is_uv3_hub() ? UV3_GLOBAL_MMR32_SIZE : \
+					/*is_uv4_hub*/ UV4_GLOBAL_MMR32_SIZE)
+
 #define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
 
 #define UV_GLOBAL_GRU_MMR_BASE		0x4000000
 
 #define UV_GLOBAL_MMR32_PNODE_SHIFT	15
-#define UV_GLOBAL_MMR64_PNODE_SHIFT	26
+#define _UV_GLOBAL_MMR64_PNODE_SHIFT	26
+#define UV_GLOBAL_MMR64_PNODE_SHIFT	(uv_hub_info->global_mmr_shift)
 
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
@@ -307,18 +429,74 @@ union uvh_apicid {
  *	      between socket virtual and socket physical addresses.
  */
 
+/* global bits offset - number of local address bits in gpa for this UV arch */
+static inline unsigned int uv_gpa_shift(void)
+{
+	return uv_hub_info->gpa_shift;
+}
+#define	_uv_gpa_shift
+
+/* Find node that has the address range that contains global address  */
+static inline struct uv_gam_range_s *uv_gam_range(unsigned long pa)
+{
+	struct uv_gam_range_s *gr = uv_hub_info->gr_table;
+	unsigned long pal = (pa & uv_hub_info->gpa_mask) >> UV_GAM_RANGE_SHFT;
+	int i, num = uv_hub_info->gr_table_len;
+
+	if (gr) {
+		for (i = 0; i < num; i++, gr++) {
+			if (pal < gr->limit)
+				return gr;
+		}
+	}
+	pr_crit("UV: GAM Range for 0x%lx not found at %p!\n", pa, gr);
+	BUG();
+}
+
+/* Return base address of node that contains global address  */
+static inline unsigned long uv_gam_range_base(unsigned long pa)
+{
+	struct uv_gam_range_s *gr = uv_gam_range(pa);
+	int base = gr->base;
+
+	if (base < 0)
+		return 0UL;
+
+	return uv_hub_info->gr_table[base].limit;
+}
+
+/* socket phys RAM --> UV global NASID (UV4+) */
+static inline unsigned long uv_soc_phys_ram_to_nasid(unsigned long paddr)
+{
+	return uv_gam_range(paddr)->nasid;
+}
+#define	_uv_soc_phys_ram_to_nasid
+
+/* socket virtual --> UV global NASID (UV4+) */
+static inline unsigned long uv_gpa_nasid(void *v)
+{
+	return uv_soc_phys_ram_to_nasid(__pa(v));
+}
+
 /* socket phys RAM --> UV global physical address */
 static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 {
+	unsigned int m_val = uv_hub_info->m_val;
+
 	if (paddr < uv_hub_info->lowmem_remap_top)
 		paddr |= uv_hub_info->lowmem_remap_base;
 	paddr |= uv_hub_info->gnode_upper;
-	paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
-		((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift);
+	if (m_val)
+		paddr = ((paddr << uv_hub_info->m_shift)
+						>> uv_hub_info->m_shift) |
+			((paddr >> uv_hub_info->m_val)
+						<< uv_hub_info->n_lshift);
+	else
+		paddr |= uv_soc_phys_ram_to_nasid(paddr)
+						<< uv_hub_info->gpa_shift;
 	return paddr;
 }
 
-
 /* socket virtual --> UV global physical address */
 static inline unsigned long uv_gpa(void *v)
 {
@@ -338,54 +516,89 @@ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 	unsigned long paddr;
 	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
 	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
+	unsigned int m_val = uv_hub_info->m_val;
+
+	if (m_val)
+		gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
+			((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
 
-	gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
-		((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
 	paddr = gpa & uv_hub_info->gpa_mask;
 	if (paddr >= remap_base && paddr < remap_base + remap_top)
 		paddr -= remap_base;
 	return paddr;
 }
 
-
-/* gpa -> pnode */
+/* gpa -> gnode */
 static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
 {
-	return gpa >> uv_hub_info->n_lshift;
+	unsigned int n_lshift = uv_hub_info->n_lshift;
+
+	if (n_lshift)
+		return gpa >> n_lshift;
+
+	return uv_gam_range(gpa)->nasid >> 1;
 }
 
 /* gpa -> pnode */
 static inline int uv_gpa_to_pnode(unsigned long gpa)
 {
-	unsigned long n_mask = (1UL << uv_hub_info->n_val) - 1;
-
-	return uv_gpa_to_gnode(gpa) & n_mask;
+	return uv_gpa_to_gnode(gpa) & uv_hub_info->pnode_mask;
 }
 
-/* gpa -> node offset*/
+/* gpa -> node offset */
 static inline unsigned long uv_gpa_to_offset(unsigned long gpa)
 {
-	return (gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift;
+	unsigned int m_shift = uv_hub_info->m_shift;
+
+	if (m_shift)
+		return (gpa << m_shift) >> m_shift;
+
+	return (gpa & uv_hub_info->gpa_mask) - uv_gam_range_base(gpa);
+}
+
+/* Convert socket to node */
+static inline int _uv_socket_to_node(int socket, unsigned short *s2nid)
+{
+	return s2nid ? s2nid[socket - uv_hub_info->min_socket] : socket;
+}
+
+static inline int uv_socket_to_node(int socket)
+{
+	return _uv_socket_to_node(socket, uv_hub_info->socket_to_node);
 }
 
 /* pnode, offset --> socket virtual */
 static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
 {
-	return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
-}
+	unsigned int m_val = uv_hub_info->m_val;
+	unsigned long base;
+	unsigned short sockid, node, *p2s;
 
+	if (m_val)
+		return __va(((unsigned long)pnode << m_val) | offset);
 
-/*
- * Extract a PNODE from an APICID (full apicid, not processor subset)
- */
+	p2s = uv_hub_info->pnode_to_socket;
+	sockid = p2s ? p2s[pnode - uv_hub_info->min_pnode] : pnode;
+	node = uv_socket_to_node(sockid);
+
+	/* limit address of previous socket is our base, except node 0 is 0 */
+	if (!node)
+		return __va((unsigned long)offset);
+
+	base = (unsigned long)(uv_hub_info->gr_table[node - 1].limit);
+	return __va(base << UV_GAM_RANGE_SHFT | offset);
+}
+
+/* Extract/Convert a PNODE from an APICID (full apicid, not processor subset) */
 static inline int uv_apicid_to_pnode(int apicid)
 {
-	return (apicid >> uv_hub_info->apic_pnode_shift);
+	int pnode = apicid >> uv_hub_info->apic_pnode_shift;
+	unsigned short *s2pn = uv_hub_info->socket_to_pnode;
+
+	return s2pn ? s2pn[pnode - uv_hub_info->min_socket] : pnode;
 }
 
-/*
- * Convert an apicid to the socket number on the blade
- */
+/* Convert an apicid to the socket number on the blade */
 static inline int uv_apicid_to_socket(int apicid)
 {
 	if (is_uv1_hub())
@@ -434,16 +647,6 @@ static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset
 	return readq(uv_global_mmr64_address(pnode, offset));
 }
 
-/*
- * Global MMR space addresses when referenced by the GRU. (GRU does
- * NOT use socket addressing).
- */
-static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long offset)
-{
-	return UV_GLOBAL_GRU_MMR_BASE | offset |
-		((unsigned long)pnode << uv_hub_info->m_val);
-}
-
 static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val)
 {
 	writeb(val, uv_global_mmr64_address(pnode, offset));
@@ -483,27 +686,23 @@ static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
 	writeb(val, uv_local_mmr_address(offset));
 }
 
-/*
- * Structures and definitions for converting between cpu, node, pnode, and blade
- * numbers.
- */
-struct uv_blade_info {
-	unsigned short	nr_possible_cpus;
-	unsigned short	nr_online_cpus;
-	unsigned short	pnode;
-	short		memory_nid;
-	spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
-	unsigned long	nmi_count;	/* obsolete, see uv_hub_nmi */
-};
-extern struct uv_blade_info *uv_blade_info;
-extern short *uv_node_to_blade;
-extern short *uv_cpu_to_blade;
-extern short uv_possible_blades;
-
 /* Blade-local cpu number of current cpu. Numbered 0 .. <# cpus on the blade> */
 static inline int uv_blade_processor_id(void)
 {
-	return uv_hub_info->blade_processor_id;
+	return uv_cpu_info->blade_cpu_id;
+}
+
+/* Blade-local cpu number of cpu N. Numbered 0 .. <# cpus on the blade> */
+static inline int uv_cpu_blade_processor_id(int cpu)
+{
+	return uv_cpu_info_per(cpu)->blade_cpu_id;
+}
+#define _uv_cpu_blade_processor_id 1	/* indicate function available */
+
+/* Blade number to Node number (UV1..UV4 is 1:1) */
+static inline int uv_blade_to_node(int blade)
+{
+	return blade;
 }
 
 /* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
@@ -512,55 +711,60 @@ static inline int uv_numa_blade_id(void)
 	return uv_hub_info->numa_blade_id;
 }
 
-/* Convert a cpu number to the the UV blade number */
-static inline int uv_cpu_to_blade_id(int cpu)
+/*
+ * Convert linux node number to the UV blade number.
+ * .. Currently for UV1 thru UV4 the node and the blade are identical.
+ * .. If this changes then you MUST check references to this function!
+ */
+static inline int uv_node_to_blade_id(int nid)
 {
-	return uv_cpu_to_blade[cpu];
+	return nid;
 }
 
-/* Convert linux node number to the UV blade number */
-static inline int uv_node_to_blade_id(int nid)
+/* Convert a cpu number to the the UV blade number */
+static inline int uv_cpu_to_blade_id(int cpu)
 {
-	return uv_node_to_blade[nid];
+	return uv_node_to_blade_id(cpu_to_node(cpu));
 }
 
 /* Convert a blade id to the PNODE of the blade */
 static inline int uv_blade_to_pnode(int bid)
 {
-	return uv_blade_info[bid].pnode;
+	return uv_hub_info_list(uv_blade_to_node(bid))->pnode;
 }
 
 /* Nid of memory node on blade. -1 if no blade-local memory */
 static inline int uv_blade_to_memory_nid(int bid)
 {
-	return uv_blade_info[bid].memory_nid;
+	return uv_hub_info_list(uv_blade_to_node(bid))->memory_nid;
 }
 
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {
-	return uv_blade_info[bid].nr_possible_cpus;
+	return uv_hub_info_list(uv_blade_to_node(bid))->nr_possible_cpus;
 }
 
 /* Determine the number of online cpus on a blade */
 static inline int uv_blade_nr_online_cpus(int bid)
 {
-	return uv_blade_info[bid].nr_online_cpus;
+	return uv_hub_info_list(uv_blade_to_node(bid))->nr_online_cpus;
 }
 
 /* Convert a cpu id to the PNODE of the blade containing the cpu */
 static inline int uv_cpu_to_pnode(int cpu)
 {
-	return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
+	return uv_cpu_hub_info(cpu)->pnode;
 }
 
 /* Convert a linux node number to the PNODE of the blade */
 static inline int uv_node_to_pnode(int nid)
 {
-	return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
+	return uv_hub_info_list(nid)->pnode;
 }
 
 /* Maximum possible number of blades */
+extern short uv_possible_blades;
 static inline int uv_num_possible_blades(void)
 {
 	return uv_possible_blades;
@@ -578,9 +782,7 @@ extern void uv_nmi_setup(void);
 /* Newer SMM NMI handler, not present in all systems */
 #define UVH_NMI_MMRX		UVH_EVENT_OCCURRED0
 #define UVH_NMI_MMRX_CLEAR	UVH_EVENT_OCCURRED0_ALIAS
-#define UVH_NMI_MMRX_SHIFT	(is_uv1_hub() ? \
-					UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :\
-					UVXH_EVENT_OCCURRED0_EXTIO_INT0_SHFT)
+#define UVH_NMI_MMRX_SHIFT	UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT
 #define	UVH_NMI_MMRX_TYPE	"EXTIO_INT0"
 
 /* Non-zero indicates newer SMM NMI handler present */
@@ -622,9 +824,9 @@ DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
 /* Update SCIR state */
 static inline void uv_set_scir_bits(unsigned char value)
 {
-	if (uv_hub_info->scir.state != value) {
-		uv_hub_info->scir.state = value;
-		uv_write_local_mmr8(uv_hub_info->scir.offset, value);
+	if (uv_scir_info->state != value) {
+		uv_scir_info->state = value;
+		uv_write_local_mmr8(uv_scir_info->offset, value);
 	}
 }
 
@@ -635,10 +837,10 @@ static inline unsigned long uv_scir_offset(int apicid)
 
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
-	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+	if (uv_cpu_scir_info(cpu)->state != value) {
 		uv_write_global_mmr8(uv_cpu_to_pnode(cpu),
-				uv_cpu_hub_info(cpu)->scir.offset, value);
-		uv_cpu_hub_info(cpu)->scir.state = value;
+				uv_cpu_scir_info(cpu)->offset, value);
+		uv_cpu_scir_info(cpu)->state = value;
 	}
 }
 
@@ -666,10 +868,7 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 
 /*
  * Get the minimum revision number of the hub chips within the partition.
- *     1 - UV1 rev 1.0 initial silicon
- *     2 - UV1 rev 2.0 production silicon
- *     3 - UV2 rev 1.0 initial silicon
- *     5 - UV3 rev 1.0 initial silicon
+ * (See UVx_HUB_REVISION_BASE above for specific values.)
  */
 static inline int uv_get_min_hub_revision_id(void)
 {
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index ddd8db6b6e70..548d684a7960 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -5,7 +5,7 @@
  *
  * SGI UV MMR definitions
  *
- * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2016 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_MMRS_H
@@ -18,10 +18,11 @@
  * grouped by architecture types.
  *
  * UVH  - definitions common to all UV hub types.
- * UVXH - definitions common to all UV eXtended hub types (currently 2 & 3).
+ * UVXH - definitions common to all UV eXtended hub types (currently 2, 3, 4).
  * UV1H - definitions specific to UV type 1 hub.
  * UV2H - definitions specific to UV type 2 hub.
  * UV3H - definitions specific to UV type 3 hub.
+ * UV4H - definitions specific to UV type 4 hub.
  *
  * So in general, MMR addresses and structures are identical on all hubs types.
  * These MMRs are identified as:
@@ -32,19 +33,25 @@
  *		} s;
  *	};
  *
- * If the MMR exists on all hub types but have different addresses:
+ * If the MMR exists on all hub types but have different addresses,
+ * use a conditional operator to define the value at runtime.
  *	#define UV1Hxxx	a
  *	#define UV2Hxxx	b
  *	#define UV3Hxxx	c
+ *	#define UV4Hxxx	d
  *	#define UVHxxx	(is_uv1_hub() ? UV1Hxxx :
  *			(is_uv2_hub() ? UV2Hxxx :
- *					UV3Hxxx))
+ *			(is_uv3_hub() ? UV3Hxxx :
+ *					UV4Hxxx))
  *
- * If the MMR exists on all hub types > 1 but have different addresses:
+ * If the MMR exists on all hub types > 1 but have different addresses, the
+ * variation using "UVX" as the prefix exists.
  *	#define UV2Hxxx	b
  *	#define UV3Hxxx	c
- *	#define UVXHxxx (is_uv2_hub() ? UV2Hxxx :
- *					UV3Hxxx))
+ *	#define UV4Hxxx	d
+ *	#define UVHxxx	(is_uv2_hub() ? UV2Hxxx :
+ *			(is_uv3_hub() ? UV3Hxxx :
+ *					UV4Hxxx))
  *
  *	union uvh_xxx {
  *		unsigned long       v;
@@ -56,6 +63,8 @@
  *		} s2;
  *		struct uv3h_xxx_s {	 # Full UV3 definition (*)
  *		} s3;
+ *		struct uv4h_xxx_s {	 # Full UV4 definition (*)
+ *		} s4;
  *	};
  *		(* - if present and different than the common struct)
  *
@@ -73,7 +82,7 @@
  *		} sn;
  *	};
  *
- * (GEN Flags: mflags_opt= undefs=0 UV23=UVXH)
+ * (GEN Flags: mflags_opt= undefs=function UV234=UVXH)
  */
 
 #define UV_MMR_ENABLE		(1UL << 63)
@@ -83,20 +92,36 @@
 #define UV2_HUB_PART_NUMBER_X	0x1111
 #define UV3_HUB_PART_NUMBER	0x9578
 #define UV3_HUB_PART_NUMBER_X	0x4321
+#define UV4_HUB_PART_NUMBER	0x99a1
 
 /* Compat: Indicate which UV Hubs are supported. */
+#define UV1_HUB_IS_SUPPORTED	1
 #define UV2_HUB_IS_SUPPORTED	1
 #define UV3_HUB_IS_SUPPORTED	1
+#define UV4_HUB_IS_SUPPORTED	1
+
+/* Error function to catch undefined references */
+extern unsigned long uv_undefined(char *str);
 
 /* ========================================================================= */
 /*                          UVH_BAU_DATA_BROADCAST                           */
 /* ========================================================================= */
 #define UVH_BAU_DATA_BROADCAST 0x61688UL
-#define UVH_BAU_DATA_BROADCAST_32 0x440
+
+#define UV1H_BAU_DATA_BROADCAST_32 0x440
+#define UV2H_BAU_DATA_BROADCAST_32 0x440
+#define UV3H_BAU_DATA_BROADCAST_32 0x440
+#define UV4H_BAU_DATA_BROADCAST_32 0x360
+#define UVH_BAU_DATA_BROADCAST_32 (					\
+	is_uv1_hub() ? UV1H_BAU_DATA_BROADCAST_32 :			\
+	is_uv2_hub() ? UV2H_BAU_DATA_BROADCAST_32 :			\
+	is_uv3_hub() ? UV3H_BAU_DATA_BROADCAST_32 :			\
+	/*is_uv4_hub*/ UV4H_BAU_DATA_BROADCAST_32)
 
 #define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT		0
 #define UVH_BAU_DATA_BROADCAST_ENABLE_MASK		0x0000000000000001UL
 
+
 union uvh_bau_data_broadcast_u {
 	unsigned long	v;
 	struct uvh_bau_data_broadcast_s {
@@ -109,7 +134,16 @@ union uvh_bau_data_broadcast_u {
 /*                           UVH_BAU_DATA_CONFIG                             */
 /* ========================================================================= */
 #define UVH_BAU_DATA_CONFIG 0x61680UL
-#define UVH_BAU_DATA_CONFIG_32 0x438
+
+#define UV1H_BAU_DATA_CONFIG_32 0x438
+#define UV2H_BAU_DATA_CONFIG_32 0x438
+#define UV3H_BAU_DATA_CONFIG_32 0x438
+#define UV4H_BAU_DATA_CONFIG_32 0x358
+#define UVH_BAU_DATA_CONFIG_32 (					\
+	is_uv1_hub() ? UV1H_BAU_DATA_CONFIG_32 :			\
+	is_uv2_hub() ? UV2H_BAU_DATA_CONFIG_32 :			\
+	is_uv3_hub() ? UV3H_BAU_DATA_CONFIG_32 :			\
+	/*is_uv4_hub*/ UV4H_BAU_DATA_CONFIG_32)
 
 #define UVH_BAU_DATA_CONFIG_VECTOR_SHFT			0
 #define UVH_BAU_DATA_CONFIG_DM_SHFT			8
@@ -128,6 +162,7 @@ union uvh_bau_data_broadcast_u {
 #define UVH_BAU_DATA_CONFIG_M_MASK			0x0000000000010000UL
 #define UVH_BAU_DATA_CONFIG_APIC_ID_MASK		0xffffffff00000000UL
 
+
 union uvh_bau_data_config_u {
 	unsigned long	v;
 	struct uvh_bau_data_config_s {
@@ -266,7 +301,6 @@ union uvh_bau_data_config_u {
 #define UV1H_EVENT_OCCURRED0_BAU_DATA_MASK		0x0080000000000000UL
 #define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK	0x0100000000000000UL
 
-#define UVXH_EVENT_OCCURRED0_QP_HCERR_SHFT		1
 #define UVXH_EVENT_OCCURRED0_RH_HCERR_SHFT		2
 #define UVXH_EVENT_OCCURRED0_LH0_HCERR_SHFT		3
 #define UVXH_EVENT_OCCURRED0_LH1_HCERR_SHFT		4
@@ -275,55 +309,11 @@ union uvh_bau_data_config_u {
 #define UVXH_EVENT_OCCURRED0_NI0_HCERR_SHFT		7
 #define UVXH_EVENT_OCCURRED0_NI1_HCERR_SHFT		8
 #define UVXH_EVENT_OCCURRED0_LB_AOERR0_SHFT		9
-#define UVXH_EVENT_OCCURRED0_QP_AOERR0_SHFT		10
 #define UVXH_EVENT_OCCURRED0_LH0_AOERR0_SHFT		12
 #define UVXH_EVENT_OCCURRED0_LH1_AOERR0_SHFT		13
 #define UVXH_EVENT_OCCURRED0_GR0_AOERR0_SHFT		14
 #define UVXH_EVENT_OCCURRED0_GR1_AOERR0_SHFT		15
 #define UVXH_EVENT_OCCURRED0_XB_AOERR0_SHFT		16
-#define UVXH_EVENT_OCCURRED0_RT_AOERR0_SHFT		17
-#define UVXH_EVENT_OCCURRED0_NI0_AOERR0_SHFT		18
-#define UVXH_EVENT_OCCURRED0_NI1_AOERR0_SHFT		19
-#define UVXH_EVENT_OCCURRED0_LB_AOERR1_SHFT		20
-#define UVXH_EVENT_OCCURRED0_QP_AOERR1_SHFT		21
-#define UVXH_EVENT_OCCURRED0_RH_AOERR1_SHFT		22
-#define UVXH_EVENT_OCCURRED0_LH0_AOERR1_SHFT		23
-#define UVXH_EVENT_OCCURRED0_LH1_AOERR1_SHFT		24
-#define UVXH_EVENT_OCCURRED0_GR0_AOERR1_SHFT		25
-#define UVXH_EVENT_OCCURRED0_GR1_AOERR1_SHFT		26
-#define UVXH_EVENT_OCCURRED0_XB_AOERR1_SHFT		27
-#define UVXH_EVENT_OCCURRED0_RT_AOERR1_SHFT		28
-#define UVXH_EVENT_OCCURRED0_NI0_AOERR1_SHFT		29
-#define UVXH_EVENT_OCCURRED0_NI1_AOERR1_SHFT		30
-#define UVXH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT	31
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT		32
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT		33
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT		34
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT		35
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT		36
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT		37
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT		38
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT		39
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT		40
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT		41
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT		42
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT		43
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT		44
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT		45
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT		46
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT		47
-#define UVXH_EVENT_OCCURRED0_L1_NMI_INT_SHFT		48
-#define UVXH_EVENT_OCCURRED0_STOP_CLOCK_SHFT		49
-#define UVXH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT		50
-#define UVXH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT		51
-#define UVXH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT	52
-#define UVXH_EVENT_OCCURRED0_IPI_INT_SHFT		53
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT0_SHFT		54
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT1_SHFT		55
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT2_SHFT		56
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT3_SHFT		57
-#define UVXH_EVENT_OCCURRED0_PROFILE_INT_SHFT		58
-#define UVXH_EVENT_OCCURRED0_QP_HCERR_MASK		0x0000000000000002UL
 #define UVXH_EVENT_OCCURRED0_RH_HCERR_MASK		0x0000000000000004UL
 #define UVXH_EVENT_OCCURRED0_LH0_HCERR_MASK		0x0000000000000008UL
 #define UVXH_EVENT_OCCURRED0_LH1_HCERR_MASK		0x0000000000000010UL
@@ -332,54 +322,294 @@ union uvh_bau_data_config_u {
 #define UVXH_EVENT_OCCURRED0_NI0_HCERR_MASK		0x0000000000000080UL
 #define UVXH_EVENT_OCCURRED0_NI1_HCERR_MASK		0x0000000000000100UL
 #define UVXH_EVENT_OCCURRED0_LB_AOERR0_MASK		0x0000000000000200UL
-#define UVXH_EVENT_OCCURRED0_QP_AOERR0_MASK		0x0000000000000400UL
 #define UVXH_EVENT_OCCURRED0_LH0_AOERR0_MASK		0x0000000000001000UL
 #define UVXH_EVENT_OCCURRED0_LH1_AOERR0_MASK		0x0000000000002000UL
 #define UVXH_EVENT_OCCURRED0_GR0_AOERR0_MASK		0x0000000000004000UL
 #define UVXH_EVENT_OCCURRED0_GR1_AOERR0_MASK		0x0000000000008000UL
 #define UVXH_EVENT_OCCURRED0_XB_AOERR0_MASK		0x0000000000010000UL
-#define UVXH_EVENT_OCCURRED0_RT_AOERR0_MASK		0x0000000000020000UL
-#define UVXH_EVENT_OCCURRED0_NI0_AOERR0_MASK		0x0000000000040000UL
-#define UVXH_EVENT_OCCURRED0_NI1_AOERR0_MASK		0x0000000000080000UL
-#define UVXH_EVENT_OCCURRED0_LB_AOERR1_MASK		0x0000000000100000UL
-#define UVXH_EVENT_OCCURRED0_QP_AOERR1_MASK		0x0000000000200000UL
-#define UVXH_EVENT_OCCURRED0_RH_AOERR1_MASK		0x0000000000400000UL
-#define UVXH_EVENT_OCCURRED0_LH0_AOERR1_MASK		0x0000000000800000UL
-#define UVXH_EVENT_OCCURRED0_LH1_AOERR1_MASK		0x0000000001000000UL
-#define UVXH_EVENT_OCCURRED0_GR0_AOERR1_MASK		0x0000000002000000UL
-#define UVXH_EVENT_OCCURRED0_GR1_AOERR1_MASK		0x0000000004000000UL
-#define UVXH_EVENT_OCCURRED0_XB_AOERR1_MASK		0x0000000008000000UL
-#define UVXH_EVENT_OCCURRED0_RT_AOERR1_MASK		0x0000000010000000UL
-#define UVXH_EVENT_OCCURRED0_NI0_AOERR1_MASK		0x0000000020000000UL
-#define UVXH_EVENT_OCCURRED0_NI1_AOERR1_MASK		0x0000000040000000UL
-#define UVXH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK	0x0000000080000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK		0x0000000100000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK		0x0000000200000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK		0x0000000400000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK		0x0000000800000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK		0x0000001000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK		0x0000002000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK		0x0000004000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK		0x0000008000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK		0x0000010000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK		0x0000020000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK		0x0000040000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK		0x0000080000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK		0x0000100000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK		0x0000200000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK		0x0000400000000000UL
-#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK		0x0000800000000000UL
-#define UVXH_EVENT_OCCURRED0_L1_NMI_INT_MASK		0x0001000000000000UL
-#define UVXH_EVENT_OCCURRED0_STOP_CLOCK_MASK		0x0002000000000000UL
-#define UVXH_EVENT_OCCURRED0_ASIC_TO_L1_MASK		0x0004000000000000UL
-#define UVXH_EVENT_OCCURRED0_L1_TO_ASIC_MASK		0x0008000000000000UL
-#define UVXH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK	0x0010000000000000UL
-#define UVXH_EVENT_OCCURRED0_IPI_INT_MASK		0x0020000000000000UL
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT0_MASK		0x0040000000000000UL
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT1_MASK		0x0080000000000000UL
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT2_MASK		0x0100000000000000UL
-#define UVXH_EVENT_OCCURRED0_EXTIO_INT3_MASK		0x0200000000000000UL
-#define UVXH_EVENT_OCCURRED0_PROFILE_INT_MASK		0x0400000000000000UL
+
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT		1
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT		10
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT		17
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT		18
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT		19
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT		20
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT		21
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT		22
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT		23
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT		24
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT		25
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT		26
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT		27
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT		28
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT		29
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT		30
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT	31
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT		32
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT		33
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT		34
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT		35
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT		36
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT		37
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT		38
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT		39
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT		40
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT		41
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT		42
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT		43
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT		44
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT		45
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT		46
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT		47
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT		48
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT		49
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT		50
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT		51
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT	52
+#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT		53
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT		54
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT		55
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT		56
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT		57
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT		58
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK		0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK		0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK		0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK		0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK		0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK		0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK		0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK		0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK		0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK		0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK		0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK		0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK		0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK		0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK		0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK		0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK	0x0000000080000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK		0x0000000100000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK		0x0000000200000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK		0x0000000400000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK		0x0000000800000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK		0x0000001000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK		0x0000002000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK		0x0000004000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK		0x0000008000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK		0x0000010000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK		0x0000020000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK		0x0000040000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK		0x0000080000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK		0x0000100000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK		0x0000200000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK		0x0000400000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK		0x0000800000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK		0x0001000000000000UL
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK		0x0002000000000000UL
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK		0x0004000000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK		0x0008000000000000UL
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK	0x0010000000000000UL
+#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK		0x0020000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK		0x0040000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK		0x0080000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK		0x0100000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK		0x0200000000000000UL
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK		0x0400000000000000UL
+
+#define UV3H_EVENT_OCCURRED0_QP_HCERR_SHFT		1
+#define UV3H_EVENT_OCCURRED0_QP_AOERR0_SHFT		10
+#define UV3H_EVENT_OCCURRED0_RT_AOERR0_SHFT		17
+#define UV3H_EVENT_OCCURRED0_NI0_AOERR0_SHFT		18
+#define UV3H_EVENT_OCCURRED0_NI1_AOERR0_SHFT		19
+#define UV3H_EVENT_OCCURRED0_LB_AOERR1_SHFT		20
+#define UV3H_EVENT_OCCURRED0_QP_AOERR1_SHFT		21
+#define UV3H_EVENT_OCCURRED0_RH_AOERR1_SHFT		22
+#define UV3H_EVENT_OCCURRED0_LH0_AOERR1_SHFT		23
+#define UV3H_EVENT_OCCURRED0_LH1_AOERR1_SHFT		24
+#define UV3H_EVENT_OCCURRED0_GR0_AOERR1_SHFT		25
+#define UV3H_EVENT_OCCURRED0_GR1_AOERR1_SHFT		26
+#define UV3H_EVENT_OCCURRED0_XB_AOERR1_SHFT		27
+#define UV3H_EVENT_OCCURRED0_RT_AOERR1_SHFT		28
+#define UV3H_EVENT_OCCURRED0_NI0_AOERR1_SHFT		29
+#define UV3H_EVENT_OCCURRED0_NI1_AOERR1_SHFT		30
+#define UV3H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT	31
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT		32
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT		33
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT		34
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT		35
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT		36
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT		37
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT		38
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT		39
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT		40
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT		41
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT		42
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT		43
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT		44
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT		45
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT		46
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT		47
+#define UV3H_EVENT_OCCURRED0_L1_NMI_INT_SHFT		48
+#define UV3H_EVENT_OCCURRED0_STOP_CLOCK_SHFT		49
+#define UV3H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT		50
+#define UV3H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT		51
+#define UV3H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT	52
+#define UV3H_EVENT_OCCURRED0_IPI_INT_SHFT		53
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT0_SHFT		54
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT1_SHFT		55
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT2_SHFT		56
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT3_SHFT		57
+#define UV3H_EVENT_OCCURRED0_PROFILE_INT_SHFT		58
+#define UV3H_EVENT_OCCURRED0_QP_HCERR_MASK		0x0000000000000002UL
+#define UV3H_EVENT_OCCURRED0_QP_AOERR0_MASK		0x0000000000000400UL
+#define UV3H_EVENT_OCCURRED0_RT_AOERR0_MASK		0x0000000000020000UL
+#define UV3H_EVENT_OCCURRED0_NI0_AOERR0_MASK		0x0000000000040000UL
+#define UV3H_EVENT_OCCURRED0_NI1_AOERR0_MASK		0x0000000000080000UL
+#define UV3H_EVENT_OCCURRED0_LB_AOERR1_MASK		0x0000000000100000UL
+#define UV3H_EVENT_OCCURRED0_QP_AOERR1_MASK		0x0000000000200000UL
+#define UV3H_EVENT_OCCURRED0_RH_AOERR1_MASK		0x0000000000400000UL
+#define UV3H_EVENT_OCCURRED0_LH0_AOERR1_MASK		0x0000000000800000UL
+#define UV3H_EVENT_OCCURRED0_LH1_AOERR1_MASK		0x0000000001000000UL
+#define UV3H_EVENT_OCCURRED0_GR0_AOERR1_MASK		0x0000000002000000UL
+#define UV3H_EVENT_OCCURRED0_GR1_AOERR1_MASK		0x0000000004000000UL
+#define UV3H_EVENT_OCCURRED0_XB_AOERR1_MASK		0x0000000008000000UL
+#define UV3H_EVENT_OCCURRED0_RT_AOERR1_MASK		0x0000000010000000UL
+#define UV3H_EVENT_OCCURRED0_NI0_AOERR1_MASK		0x0000000020000000UL
+#define UV3H_EVENT_OCCURRED0_NI1_AOERR1_MASK		0x0000000040000000UL
+#define UV3H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK	0x0000000080000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK		0x0000000100000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK		0x0000000200000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK		0x0000000400000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK		0x0000000800000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK		0x0000001000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK		0x0000002000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK		0x0000004000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK		0x0000008000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK		0x0000010000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK		0x0000020000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK		0x0000040000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK		0x0000080000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK		0x0000100000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK		0x0000200000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK		0x0000400000000000UL
+#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK		0x0000800000000000UL
+#define UV3H_EVENT_OCCURRED0_L1_NMI_INT_MASK		0x0001000000000000UL
+#define UV3H_EVENT_OCCURRED0_STOP_CLOCK_MASK		0x0002000000000000UL
+#define UV3H_EVENT_OCCURRED0_ASIC_TO_L1_MASK		0x0004000000000000UL
+#define UV3H_EVENT_OCCURRED0_L1_TO_ASIC_MASK		0x0008000000000000UL
+#define UV3H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK	0x0010000000000000UL
+#define UV3H_EVENT_OCCURRED0_IPI_INT_MASK		0x0020000000000000UL
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT0_MASK		0x0040000000000000UL
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT1_MASK		0x0080000000000000UL
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT2_MASK		0x0100000000000000UL
+#define UV3H_EVENT_OCCURRED0_EXTIO_INT3_MASK		0x0200000000000000UL
+#define UV3H_EVENT_OCCURRED0_PROFILE_INT_MASK		0x0400000000000000UL
+
+#define UV4H_EVENT_OCCURRED0_KT_HCERR_SHFT		1
+#define UV4H_EVENT_OCCURRED0_KT_AOERR0_SHFT		10
+#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR0_SHFT		17
+#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR0_SHFT		18
+#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR0_SHFT		19
+#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR0_SHFT		20
+#define UV4H_EVENT_OCCURRED0_NI0_AOERR0_SHFT		21
+#define UV4H_EVENT_OCCURRED0_NI1_AOERR0_SHFT		22
+#define UV4H_EVENT_OCCURRED0_LB_AOERR1_SHFT		23
+#define UV4H_EVENT_OCCURRED0_KT_AOERR1_SHFT		24
+#define UV4H_EVENT_OCCURRED0_RH_AOERR1_SHFT		25
+#define UV4H_EVENT_OCCURRED0_LH0_AOERR1_SHFT		26
+#define UV4H_EVENT_OCCURRED0_LH1_AOERR1_SHFT		27
+#define UV4H_EVENT_OCCURRED0_GR0_AOERR1_SHFT		28
+#define UV4H_EVENT_OCCURRED0_GR1_AOERR1_SHFT		29
+#define UV4H_EVENT_OCCURRED0_XB_AOERR1_SHFT		30
+#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR1_SHFT		31
+#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR1_SHFT		32
+#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR1_SHFT		33
+#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR1_SHFT		34
+#define UV4H_EVENT_OCCURRED0_NI0_AOERR1_SHFT		35
+#define UV4H_EVENT_OCCURRED0_NI1_AOERR1_SHFT		36
+#define UV4H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT	37
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT		38
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT		39
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT		40
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT		41
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT		42
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT		43
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT		44
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT		45
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT		46
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT		47
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT		48
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT		49
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT		50
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT		51
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT		52
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT		53
+#define UV4H_EVENT_OCCURRED0_L1_NMI_INT_SHFT		54
+#define UV4H_EVENT_OCCURRED0_STOP_CLOCK_SHFT		55
+#define UV4H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT		56
+#define UV4H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT		57
+#define UV4H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT	58
+#define UV4H_EVENT_OCCURRED0_IPI_INT_SHFT		59
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT0_SHFT		60
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT1_SHFT		61
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT2_SHFT		62
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT3_SHFT		63
+#define UV4H_EVENT_OCCURRED0_KT_HCERR_MASK		0x0000000000000002UL
+#define UV4H_EVENT_OCCURRED0_KT_AOERR0_MASK		0x0000000000000400UL
+#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR0_MASK		0x0000000000020000UL
+#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR0_MASK		0x0000000000040000UL
+#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR0_MASK		0x0000000000080000UL
+#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR0_MASK		0x0000000000100000UL
+#define UV4H_EVENT_OCCURRED0_NI0_AOERR0_MASK		0x0000000000200000UL
+#define UV4H_EVENT_OCCURRED0_NI1_AOERR0_MASK		0x0000000000400000UL
+#define UV4H_EVENT_OCCURRED0_LB_AOERR1_MASK		0x0000000000800000UL
+#define UV4H_EVENT_OCCURRED0_KT_AOERR1_MASK		0x0000000001000000UL
+#define UV4H_EVENT_OCCURRED0_RH_AOERR1_MASK		0x0000000002000000UL
+#define UV4H_EVENT_OCCURRED0_LH0_AOERR1_MASK		0x0000000004000000UL
+#define UV4H_EVENT_OCCURRED0_LH1_AOERR1_MASK		0x0000000008000000UL
+#define UV4H_EVENT_OCCURRED0_GR0_AOERR1_MASK		0x0000000010000000UL
+#define UV4H_EVENT_OCCURRED0_GR1_AOERR1_MASK		0x0000000020000000UL
+#define UV4H_EVENT_OCCURRED0_XB_AOERR1_MASK		0x0000000040000000UL
+#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR1_MASK		0x0000000080000000UL
+#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR1_MASK		0x0000000100000000UL
+#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR1_MASK		0x0000000200000000UL
+#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR1_MASK		0x0000000400000000UL
+#define UV4H_EVENT_OCCURRED0_NI0_AOERR1_MASK		0x0000000800000000UL
+#define UV4H_EVENT_OCCURRED0_NI1_AOERR1_MASK		0x0000001000000000UL
+#define UV4H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK	0x0000002000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK		0x0000004000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK		0x0000008000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK		0x0000010000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK		0x0000020000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK		0x0000040000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK		0x0000080000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK		0x0000100000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK		0x0000200000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK		0x0000400000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK		0x0000800000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK		0x0001000000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK		0x0002000000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK		0x0004000000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK		0x0008000000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK		0x0010000000000000UL
+#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK		0x0020000000000000UL
+#define UV4H_EVENT_OCCURRED0_L1_NMI_INT_MASK		0x0040000000000000UL
+#define UV4H_EVENT_OCCURRED0_STOP_CLOCK_MASK		0x0080000000000000UL
+#define UV4H_EVENT_OCCURRED0_ASIC_TO_L1_MASK		0x0100000000000000UL
+#define UV4H_EVENT_OCCURRED0_L1_TO_ASIC_MASK		0x0200000000000000UL
+#define UV4H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK	0x0400000000000000UL
+#define UV4H_EVENT_OCCURRED0_IPI_INT_MASK		0x0800000000000000UL
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT0_MASK		0x1000000000000000UL
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT1_MASK		0x2000000000000000UL
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT2_MASK		0x4000000000000000UL
+#define UV4H_EVENT_OCCURRED0_EXTIO_INT3_MASK		0x8000000000000000UL
+
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT (				\
+	is_uv1_hub() ? UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :		\
+	is_uv2_hub() ? UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :		\
+	is_uv3_hub() ? UV3H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :		\
+	/*is_uv4_hub*/ UV4H_EVENT_OCCURRED0_EXTIO_INT0_SHFT)
 
 union uvh_event_occurred0_u {
 	unsigned long	v;
@@ -391,7 +621,7 @@ union uvh_event_occurred0_u {
 	} s;
 	struct uvxh_event_occurred0_s {
 		unsigned long	lb_hcerr:1;			/* RW */
-		unsigned long	qp_hcerr:1;			/* RW */
+		unsigned long	rsvd_1:1;
 		unsigned long	rh_hcerr:1;			/* RW */
 		unsigned long	lh0_hcerr:1;			/* RW */
 		unsigned long	lh1_hcerr:1;			/* RW */
@@ -400,25 +630,51 @@ union uvh_event_occurred0_u {
 		unsigned long	ni0_hcerr:1;			/* RW */
 		unsigned long	ni1_hcerr:1;			/* RW */
 		unsigned long	lb_aoerr0:1;			/* RW */
-		unsigned long	qp_aoerr0:1;			/* RW */
+		unsigned long	rsvd_10:1;
 		unsigned long	rh_aoerr0:1;			/* RW */
 		unsigned long	lh0_aoerr0:1;			/* RW */
 		unsigned long	lh1_aoerr0:1;			/* RW */
 		unsigned long	gr0_aoerr0:1;			/* RW */
 		unsigned long	gr1_aoerr0:1;			/* RW */
 		unsigned long	xb_aoerr0:1;			/* RW */
-		unsigned long	rt_aoerr0:1;			/* RW */
+		unsigned long	rsvd_17_63:47;
+	} sx;
+	struct uv4h_event_occurred0_s {
+		unsigned long	lb_hcerr:1;			/* RW */
+		unsigned long	kt_hcerr:1;			/* RW */
+		unsigned long	rh_hcerr:1;			/* RW */
+		unsigned long	lh0_hcerr:1;			/* RW */
+		unsigned long	lh1_hcerr:1;			/* RW */
+		unsigned long	gr0_hcerr:1;			/* RW */
+		unsigned long	gr1_hcerr:1;			/* RW */
+		unsigned long	ni0_hcerr:1;			/* RW */
+		unsigned long	ni1_hcerr:1;			/* RW */
+		unsigned long	lb_aoerr0:1;			/* RW */
+		unsigned long	kt_aoerr0:1;			/* RW */
+		unsigned long	rh_aoerr0:1;			/* RW */
+		unsigned long	lh0_aoerr0:1;			/* RW */
+		unsigned long	lh1_aoerr0:1;			/* RW */
+		unsigned long	gr0_aoerr0:1;			/* RW */
+		unsigned long	gr1_aoerr0:1;			/* RW */
+		unsigned long	xb_aoerr0:1;			/* RW */
+		unsigned long	rtq0_aoerr0:1;			/* RW */
+		unsigned long	rtq1_aoerr0:1;			/* RW */
+		unsigned long	rtq2_aoerr0:1;			/* RW */
+		unsigned long	rtq3_aoerr0:1;			/* RW */
 		unsigned long	ni0_aoerr0:1;			/* RW */
 		unsigned long	ni1_aoerr0:1;			/* RW */
 		unsigned long	lb_aoerr1:1;			/* RW */
-		unsigned long	qp_aoerr1:1;			/* RW */
+		unsigned long	kt_aoerr1:1;			/* RW */
 		unsigned long	rh_aoerr1:1;			/* RW */
 		unsigned long	lh0_aoerr1:1;			/* RW */
 		unsigned long	lh1_aoerr1:1;			/* RW */
 		unsigned long	gr0_aoerr1:1;			/* RW */
 		unsigned long	gr1_aoerr1:1;			/* RW */
 		unsigned long	xb_aoerr1:1;			/* RW */
-		unsigned long	rt_aoerr1:1;			/* RW */
+		unsigned long	rtq0_aoerr1:1;			/* RW */
+		unsigned long	rtq1_aoerr1:1;			/* RW */
+		unsigned long	rtq2_aoerr1:1;			/* RW */
+		unsigned long	rtq3_aoerr1:1;			/* RW */
 		unsigned long	ni0_aoerr1:1;			/* RW */
 		unsigned long	ni1_aoerr1:1;			/* RW */
 		unsigned long	system_shutdown_int:1;		/* RW */
@@ -448,9 +704,7 @@ union uvh_event_occurred0_u {
 		unsigned long	extio_int1:1;			/* RW */
 		unsigned long	extio_int2:1;			/* RW */
 		unsigned long	extio_int3:1;			/* RW */
-		unsigned long	profile_int:1;			/* RW */
-		unsigned long	rsvd_59_63:5;
-	} sx;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -464,11 +718,21 @@ union uvh_event_occurred0_u {
 /*                         UVH_EXTIO_INT0_BROADCAST                          */
 /* ========================================================================= */
 #define UVH_EXTIO_INT0_BROADCAST 0x61448UL
-#define UVH_EXTIO_INT0_BROADCAST_32 0x3f0
+
+#define UV1H_EXTIO_INT0_BROADCAST_32 0x3f0
+#define UV2H_EXTIO_INT0_BROADCAST_32 0x3f0
+#define UV3H_EXTIO_INT0_BROADCAST_32 0x3f0
+#define UV4H_EXTIO_INT0_BROADCAST_32 0x310
+#define UVH_EXTIO_INT0_BROADCAST_32 (					\
+	is_uv1_hub() ? UV1H_EXTIO_INT0_BROADCAST_32 :			\
+	is_uv2_hub() ? UV2H_EXTIO_INT0_BROADCAST_32 :			\
+	is_uv3_hub() ? UV3H_EXTIO_INT0_BROADCAST_32 :			\
+	/*is_uv4_hub*/ UV4H_EXTIO_INT0_BROADCAST_32)
 
 #define UVH_EXTIO_INT0_BROADCAST_ENABLE_SHFT		0
 #define UVH_EXTIO_INT0_BROADCAST_ENABLE_MASK		0x0000000000000001UL
 
+
 union uvh_extio_int0_broadcast_u {
 	unsigned long	v;
 	struct uvh_extio_int0_broadcast_s {
@@ -499,6 +763,7 @@ union uvh_extio_int0_broadcast_u {
 #define UVH_GR0_TLB_INT0_CONFIG_M_MASK			0x0000000000010000UL
 #define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK		0xffffffff00000000UL
 
+
 union uvh_gr0_tlb_int0_config_u {
 	unsigned long	v;
 	struct uvh_gr0_tlb_int0_config_s {
@@ -537,6 +802,7 @@ union uvh_gr0_tlb_int0_config_u {
 #define UVH_GR0_TLB_INT1_CONFIG_M_MASK			0x0000000000010000UL
 #define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK		0xffffffff00000000UL
 
+
 union uvh_gr0_tlb_int1_config_u {
 	unsigned long	v;
 	struct uvh_gr0_tlb_int1_config_s {
@@ -559,19 +825,18 @@ union uvh_gr0_tlb_int1_config_u {
 #define UV1H_GR0_TLB_MMR_CONTROL 0x401080UL
 #define UV2H_GR0_TLB_MMR_CONTROL 0xc01080UL
 #define UV3H_GR0_TLB_MMR_CONTROL 0xc01080UL
-#define UVH_GR0_TLB_MMR_CONTROL						\
-		(is_uv1_hub() ? UV1H_GR0_TLB_MMR_CONTROL :		\
-		(is_uv2_hub() ? UV2H_GR0_TLB_MMR_CONTROL :		\
-				UV3H_GR0_TLB_MMR_CONTROL))
+#define UV4H_GR0_TLB_MMR_CONTROL 0x601080UL
+#define UVH_GR0_TLB_MMR_CONTROL (					\
+	is_uv1_hub() ? UV1H_GR0_TLB_MMR_CONTROL :			\
+	is_uv2_hub() ? UV2H_GR0_TLB_MMR_CONTROL :			\
+	is_uv3_hub() ? UV3H_GR0_TLB_MMR_CONTROL :			\
+	/*is_uv4_hub*/ UV4H_GR0_TLB_MMR_CONTROL)
 
 #define UVH_GR0_TLB_MMR_CONTROL_INDEX_SHFT		0
-#define UVH_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT		12
 #define UVH_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT	16
 #define UVH_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT	20
 #define UVH_GR0_TLB_MMR_CONTROL_MMR_WRITE_SHFT		30
 #define UVH_GR0_TLB_MMR_CONTROL_MMR_READ_SHFT		31
-#define UVH_GR0_TLB_MMR_CONTROL_INDEX_MASK		0x0000000000000fffUL
-#define UVH_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK		0x0000000000003000UL
 #define UVH_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK	0x0000000000010000UL
 #define UVH_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK	0x0000000000100000UL
 #define UVH_GR0_TLB_MMR_CONTROL_MMR_WRITE_MASK		0x0000000040000000UL
@@ -601,14 +866,11 @@ union uvh_gr0_tlb_int1_config_u {
 #define UV1H_GR0_TLB_MMR_CONTROL_MMR_INJ_TLBLRUV_MASK	0x1000000000000000UL
 
 #define UVXH_GR0_TLB_MMR_CONTROL_INDEX_SHFT		0
-#define UVXH_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT		12
 #define UVXH_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT	16
 #define UVXH_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT	20
 #define UVXH_GR0_TLB_MMR_CONTROL_MMR_WRITE_SHFT		30
 #define UVXH_GR0_TLB_MMR_CONTROL_MMR_READ_SHFT		31
 #define UVXH_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT	32
-#define UVXH_GR0_TLB_MMR_CONTROL_INDEX_MASK		0x0000000000000fffUL
-#define UVXH_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK		0x0000000000003000UL
 #define UVXH_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK	0x0000000000010000UL
 #define UVXH_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK	0x0000000000100000UL
 #define UVXH_GR0_TLB_MMR_CONTROL_MMR_WRITE_MASK		0x0000000040000000UL
@@ -651,12 +913,45 @@ union uvh_gr0_tlb_int1_config_u {
 #define UV3H_GR0_TLB_MMR_CONTROL_MMR_READ_MASK		0x0000000080000000UL
 #define UV3H_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_MASK	0x0000000100000000UL
 
+#define UV4H_GR0_TLB_MMR_CONTROL_INDEX_SHFT		0
+#define UV4H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT		13
+#define UV4H_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT	16
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT	20
+#define UV4H_GR0_TLB_MMR_CONTROL_ECC_SEL_SHFT		21
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_WRITE_SHFT		30
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_READ_SHFT		31
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT	32
+#define UV4H_GR0_TLB_MMR_CONTROL_PAGE_SIZE_SHFT		59
+#define UV4H_GR0_TLB_MMR_CONTROL_INDEX_MASK		0x0000000000001fffUL
+#define UV4H_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK		0x0000000000006000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK	0x0000000000010000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK	0x0000000000100000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_ECC_SEL_MASK		0x0000000000200000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_WRITE_MASK		0x0000000040000000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_READ_MASK		0x0000000080000000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_MASK	0x0000000100000000UL
+#define UV4H_GR0_TLB_MMR_CONTROL_PAGE_SIZE_MASK		0xf800000000000000UL
+
+#define UVH_GR0_TLB_MMR_CONTROL_INDEX_MASK (				\
+	is_uv1_hub() ? UV1H_GR0_TLB_MMR_CONTROL_INDEX_MASK :		\
+	is_uv2_hub() ? UV2H_GR0_TLB_MMR_CONTROL_INDEX_MASK :		\
+	is_uv3_hub() ? UV3H_GR0_TLB_MMR_CONTROL_INDEX_MASK :		\
+	/*is_uv4_hub*/ UV4H_GR0_TLB_MMR_CONTROL_INDEX_MASK)
+#define UVH_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK (				\
+	is_uv1_hub() ? UV1H_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK :		\
+	is_uv2_hub() ? UV2H_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK :		\
+	is_uv3_hub() ? UV3H_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK :		\
+	/*is_uv4_hub*/ UV4H_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK)
+#define UVH_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT (				\
+	is_uv1_hub() ? UV1H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT :		\
+	is_uv2_hub() ? UV2H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT :		\
+	is_uv3_hub() ? UV3H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT :		\
+	/*is_uv4_hub*/ UV4H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT)
+
 union uvh_gr0_tlb_mmr_control_u {
 	unsigned long	v;
 	struct uvh_gr0_tlb_mmr_control_s {
-		unsigned long	index:12;			/* RW */
-		unsigned long	mem_sel:2;			/* RW */
-		unsigned long	rsvd_14_15:2;
+		unsigned long	rsvd_0_15:16;
 		unsigned long	auto_valid_en:1;		/* RW */
 		unsigned long	rsvd_17_19:3;
 		unsigned long	mmr_hash_index_en:1;		/* RW */
@@ -690,9 +985,7 @@ union uvh_gr0_tlb_mmr_control_u {
 		unsigned long	rsvd_61_63:3;
 	} s1;
 	struct uvxh_gr0_tlb_mmr_control_s {
-		unsigned long	index:12;			/* RW */
-		unsigned long	mem_sel:2;			/* RW */
-		unsigned long	rsvd_14_15:2;
+		unsigned long	rsvd_0_15:16;
 		unsigned long	auto_valid_en:1;		/* RW */
 		unsigned long	rsvd_17_19:3;
 		unsigned long	mmr_hash_index_en:1;		/* RW */
@@ -703,8 +996,7 @@ union uvh_gr0_tlb_mmr_control_u {
 		unsigned long	rsvd_33_47:15;
 		unsigned long	rsvd_48:1;
 		unsigned long	rsvd_49_51:3;
-		unsigned long	rsvd_52:1;
-		unsigned long	rsvd_53_63:11;
+		unsigned long	rsvd_52_63:12;
 	} sx;
 	struct uv2h_gr0_tlb_mmr_control_s {
 		unsigned long	index:12;			/* RW */
@@ -741,6 +1033,24 @@ union uvh_gr0_tlb_mmr_control_u {
 		unsigned long	undef_52:1;			/* Undefined */
 		unsigned long	rsvd_53_63:11;
 	} s3;
+	struct uv4h_gr0_tlb_mmr_control_s {
+		unsigned long	index:13;			/* RW */
+		unsigned long	mem_sel:2;			/* RW */
+		unsigned long	rsvd_15:1;
+		unsigned long	auto_valid_en:1;		/* RW */
+		unsigned long	rsvd_17_19:3;
+		unsigned long	mmr_hash_index_en:1;		/* RW */
+		unsigned long	ecc_sel:1;			/* RW */
+		unsigned long	rsvd_22_29:8;
+		unsigned long	mmr_write:1;			/* WP */
+		unsigned long	mmr_read:1;			/* WP */
+		unsigned long	mmr_op_done:1;			/* RW */
+		unsigned long	rsvd_33_47:15;
+		unsigned long	undef_48:1;			/* Undefined */
+		unsigned long	rsvd_49_51:3;
+		unsigned long	rsvd_52_58:7;
+		unsigned long	page_size:5;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -749,19 +1059,14 @@ union uvh_gr0_tlb_mmr_control_u {
 #define UV1H_GR0_TLB_MMR_READ_DATA_HI 0x4010a0UL
 #define UV2H_GR0_TLB_MMR_READ_DATA_HI 0xc010a0UL
 #define UV3H_GR0_TLB_MMR_READ_DATA_HI 0xc010a0UL
-#define UVH_GR0_TLB_MMR_READ_DATA_HI					\
-		(is_uv1_hub() ? UV1H_GR0_TLB_MMR_READ_DATA_HI :		\
-		(is_uv2_hub() ? UV2H_GR0_TLB_MMR_READ_DATA_HI :		\
-				UV3H_GR0_TLB_MMR_READ_DATA_HI))
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI 0x6010a0UL
+#define UVH_GR0_TLB_MMR_READ_DATA_HI (					\
+	is_uv1_hub() ? UV1H_GR0_TLB_MMR_READ_DATA_HI :			\
+	is_uv2_hub() ? UV2H_GR0_TLB_MMR_READ_DATA_HI :			\
+	is_uv3_hub() ? UV3H_GR0_TLB_MMR_READ_DATA_HI :			\
+	/*is_uv4_hub*/ UV4H_GR0_TLB_MMR_READ_DATA_HI)
 
 #define UVH_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT		43
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT	44
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK		0x000001ffffffffffUL
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK		0x0000060000000000UL
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK		0x0000080000000000UL
-#define UVH_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0000100000000000UL
 
 #define UV1H_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
 #define UV1H_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
@@ -773,13 +1078,6 @@ union uvh_gr0_tlb_mmr_control_u {
 #define UV1H_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0000100000000000UL
 
 #define UVXH_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT	43
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT	44
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK		0x000001ffffffffffUL
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK		0x0000060000000000UL
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK	0x0000080000000000UL
-#define UVXH_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0000100000000000UL
 
 #define UV2H_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
 #define UV2H_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
@@ -803,15 +1101,24 @@ union uvh_gr0_tlb_mmr_control_u {
 #define UV3H_GR0_TLB_MMR_READ_DATA_HI_AA_EXT_MASK	0x0000200000000000UL
 #define UV3H_GR0_TLB_MMR_READ_DATA_HI_WAY_ECC_MASK	0xff80000000000000UL
 
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_PNID_SHFT		34
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT		49
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT	51
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT	52
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_AA_EXT_SHFT	53
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_WAY_ECC_SHFT	55
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK		0x00000003ffffffffUL
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_PNID_MASK		0x0001fffc00000000UL
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK		0x0006000000000000UL
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK	0x0008000000000000UL
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0010000000000000UL
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_AA_EXT_MASK	0x0020000000000000UL
+#define UV4H_GR0_TLB_MMR_READ_DATA_HI_WAY_ECC_MASK	0xff80000000000000UL
+
+
 union uvh_gr0_tlb_mmr_read_data_hi_u {
 	unsigned long	v;
-	struct uvh_gr0_tlb_mmr_read_data_hi_s {
-		unsigned long	pfn:41;				/* RO */
-		unsigned long	gaa:2;				/* RO */
-		unsigned long	dirty:1;			/* RO */
-		unsigned long	larger:1;			/* RO */
-		unsigned long	rsvd_45_63:19;
-	} s;
 	struct uv1h_gr0_tlb_mmr_read_data_hi_s {
 		unsigned long	pfn:41;				/* RO */
 		unsigned long	gaa:2;				/* RO */
@@ -819,13 +1126,6 @@ union uvh_gr0_tlb_mmr_read_data_hi_u {
 		unsigned long	larger:1;			/* RO */
 		unsigned long	rsvd_45_63:19;
 	} s1;
-	struct uvxh_gr0_tlb_mmr_read_data_hi_s {
-		unsigned long	pfn:41;				/* RO */
-		unsigned long	gaa:2;				/* RO */
-		unsigned long	dirty:1;			/* RO */
-		unsigned long	larger:1;			/* RO */
-		unsigned long	rsvd_45_63:19;
-	} sx;
 	struct uv2h_gr0_tlb_mmr_read_data_hi_s {
 		unsigned long	pfn:41;				/* RO */
 		unsigned long	gaa:2;				/* RO */
@@ -842,6 +1142,16 @@ union uvh_gr0_tlb_mmr_read_data_hi_u {
 		unsigned long	undef_46_54:9;			/* Undefined */
 		unsigned long	way_ecc:9;			/* RO */
 	} s3;
+	struct uv4h_gr0_tlb_mmr_read_data_hi_s {
+		unsigned long	pfn:34;				/* RO */
+		unsigned long	pnid:15;			/* RO */
+		unsigned long	gaa:2;				/* RO */
+		unsigned long	dirty:1;			/* RO */
+		unsigned long	larger:1;			/* RO */
+		unsigned long	aa_ext:1;			/* RO */
+		unsigned long	undef_54:1;			/* Undefined */
+		unsigned long	way_ecc:9;			/* RO */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -850,10 +1160,12 @@ union uvh_gr0_tlb_mmr_read_data_hi_u {
 #define UV1H_GR0_TLB_MMR_READ_DATA_LO 0x4010a8UL
 #define UV2H_GR0_TLB_MMR_READ_DATA_LO 0xc010a8UL
 #define UV3H_GR0_TLB_MMR_READ_DATA_LO 0xc010a8UL
-#define UVH_GR0_TLB_MMR_READ_DATA_LO					\
-		(is_uv1_hub() ? UV1H_GR0_TLB_MMR_READ_DATA_LO :		\
-		(is_uv2_hub() ? UV2H_GR0_TLB_MMR_READ_DATA_LO :		\
-				UV3H_GR0_TLB_MMR_READ_DATA_LO))
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO 0x6010a8UL
+#define UVH_GR0_TLB_MMR_READ_DATA_LO (					\
+	is_uv1_hub() ? UV1H_GR0_TLB_MMR_READ_DATA_LO :			\
+	is_uv2_hub() ? UV2H_GR0_TLB_MMR_READ_DATA_LO :			\
+	is_uv3_hub() ? UV3H_GR0_TLB_MMR_READ_DATA_LO :			\
+	/*is_uv4_hub*/ UV4H_GR0_TLB_MMR_READ_DATA_LO)
 
 #define UVH_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT		0
 #define UVH_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT		39
@@ -890,6 +1202,14 @@ union uvh_gr0_tlb_mmr_read_data_hi_u {
 #define UV3H_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK		0x7fffff8000000000UL
 #define UV3H_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK	0x8000000000000000UL
 
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT		0
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT		39
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO_VALID_SHFT	63
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO_VPN_MASK		0x0000007fffffffffUL
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK		0x7fffff8000000000UL
+#define UV4H_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK	0x8000000000000000UL
+
+
 union uvh_gr0_tlb_mmr_read_data_lo_u {
 	unsigned long	v;
 	struct uvh_gr0_tlb_mmr_read_data_lo_s {
@@ -917,12 +1237,25 @@ union uvh_gr0_tlb_mmr_read_data_lo_u {
 		unsigned long	asid:24;			/* RO */
 		unsigned long	valid:1;			/* RO */
 	} s3;
+	struct uv4h_gr0_tlb_mmr_read_data_lo_s {
+		unsigned long	vpn:39;				/* RO */
+		unsigned long	asid:24;			/* RO */
+		unsigned long	valid:1;			/* RO */
+	} s4;
 };
 
 /* ========================================================================= */
 /*                         UVH_GR1_TLB_INT0_CONFIG                           */
 /* ========================================================================= */
-#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL
+#define UV1H_GR1_TLB_INT0_CONFIG 0x61f00UL
+#define UV2H_GR1_TLB_INT0_CONFIG 0x61f00UL
+#define UV3H_GR1_TLB_INT0_CONFIG 0x61f00UL
+#define UV4H_GR1_TLB_INT0_CONFIG 0x62100UL
+#define UVH_GR1_TLB_INT0_CONFIG (					\
+	is_uv1_hub() ? UV1H_GR1_TLB_INT0_CONFIG :			\
+	is_uv2_hub() ? UV2H_GR1_TLB_INT0_CONFIG :			\
+	is_uv3_hub() ? UV3H_GR1_TLB_INT0_CONFIG :			\
+	/*is_uv4_hub*/ UV4H_GR1_TLB_INT0_CONFIG)
 
 #define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT		0
 #define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT			8
@@ -941,6 +1274,7 @@ union uvh_gr0_tlb_mmr_read_data_lo_u {
 #define UVH_GR1_TLB_INT0_CONFIG_M_MASK			0x0000000000010000UL
 #define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK		0xffffffff00000000UL
 
+
 union uvh_gr1_tlb_int0_config_u {
 	unsigned long	v;
 	struct uvh_gr1_tlb_int0_config_s {
@@ -960,7 +1294,15 @@ union uvh_gr1_tlb_int0_config_u {
 /* ========================================================================= */
 /*                         UVH_GR1_TLB_INT1_CONFIG                           */
 /* ========================================================================= */
-#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL
+#define UV1H_GR1_TLB_INT1_CONFIG 0x61f40UL
+#define UV2H_GR1_TLB_INT1_CONFIG 0x61f40UL
+#define UV3H_GR1_TLB_INT1_CONFIG 0x61f40UL
+#define UV4H_GR1_TLB_INT1_CONFIG 0x62140UL
+#define UVH_GR1_TLB_INT1_CONFIG (					\
+	is_uv1_hub() ? UV1H_GR1_TLB_INT1_CONFIG :			\
+	is_uv2_hub() ? UV2H_GR1_TLB_INT1_CONFIG :			\
+	is_uv3_hub() ? UV3H_GR1_TLB_INT1_CONFIG :			\
+	/*is_uv4_hub*/ UV4H_GR1_TLB_INT1_CONFIG)
 
 #define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT		0
 #define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT			8
@@ -979,6 +1321,7 @@ union uvh_gr1_tlb_int0_config_u {
 #define UVH_GR1_TLB_INT1_CONFIG_M_MASK			0x0000000000010000UL
 #define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK		0xffffffff00000000UL
 
+
 union uvh_gr1_tlb_int1_config_u {
 	unsigned long	v;
 	struct uvh_gr1_tlb_int1_config_s {
@@ -1001,19 +1344,18 @@ union uvh_gr1_tlb_int1_config_u {
 #define UV1H_GR1_TLB_MMR_CONTROL 0x801080UL
 #define UV2H_GR1_TLB_MMR_CONTROL 0x1001080UL
 #define UV3H_GR1_TLB_MMR_CONTROL 0x1001080UL
-#define UVH_GR1_TLB_MMR_CONTROL						\
-		(is_uv1_hub() ? UV1H_GR1_TLB_MMR_CONTROL :		\
-		(is_uv2_hub() ? UV2H_GR1_TLB_MMR_CONTROL :		\
-				UV3H_GR1_TLB_MMR_CONTROL))
+#define UV4H_GR1_TLB_MMR_CONTROL 0x701080UL
+#define UVH_GR1_TLB_MMR_CONTROL (					\
+	is_uv1_hub() ? UV1H_GR1_TLB_MMR_CONTROL :			\
+	is_uv2_hub() ? UV2H_GR1_TLB_MMR_CONTROL :			\
+	is_uv3_hub() ? UV3H_GR1_TLB_MMR_CONTROL :			\
+	/*is_uv4_hub*/ UV4H_GR1_TLB_MMR_CONTROL)
 
 #define UVH_GR1_TLB_MMR_CONTROL_INDEX_SHFT		0
-#define UVH_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT		12
 #define UVH_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT	16
 #define UVH_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT	20
 #define UVH_GR1_TLB_MMR_CONTROL_MMR_WRITE_SHFT		30
 #define UVH_GR1_TLB_MMR_CONTROL_MMR_READ_SHFT		31
-#define UVH_GR1_TLB_MMR_CONTROL_INDEX_MASK		0x0000000000000fffUL
-#define UVH_GR1_TLB_MMR_CONTROL_MEM_SEL_MASK		0x0000000000003000UL
 #define UVH_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK	0x0000000000010000UL
 #define UVH_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK	0x0000000000100000UL
 #define UVH_GR1_TLB_MMR_CONTROL_MMR_WRITE_MASK		0x0000000040000000UL
@@ -1043,14 +1385,11 @@ union uvh_gr1_tlb_int1_config_u {
 #define UV1H_GR1_TLB_MMR_CONTROL_MMR_INJ_TLBLRUV_MASK	0x1000000000000000UL
 
 #define UVXH_GR1_TLB_MMR_CONTROL_INDEX_SHFT		0
-#define UVXH_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT		12
 #define UVXH_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT	16
 #define UVXH_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT	20
 #define UVXH_GR1_TLB_MMR_CONTROL_MMR_WRITE_SHFT		30
 #define UVXH_GR1_TLB_MMR_CONTROL_MMR_READ_SHFT		31
 #define UVXH_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT	32
-#define UVXH_GR1_TLB_MMR_CONTROL_INDEX_MASK		0x0000000000000fffUL
-#define UVXH_GR1_TLB_MMR_CONTROL_MEM_SEL_MASK		0x0000000000003000UL
 #define UVXH_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK	0x0000000000010000UL
 #define UVXH_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK	0x0000000000100000UL
 #define UVXH_GR1_TLB_MMR_CONTROL_MMR_WRITE_MASK		0x0000000040000000UL
@@ -1093,12 +1432,30 @@ union uvh_gr1_tlb_int1_config_u {
 #define UV3H_GR1_TLB_MMR_CONTROL_MMR_READ_MASK		0x0000000080000000UL
 #define UV3H_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_MASK	0x0000000100000000UL
 
+#define UV4H_GR1_TLB_MMR_CONTROL_INDEX_SHFT		0
+#define UV4H_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT		13
+#define UV4H_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT	16
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT	20
+#define UV4H_GR1_TLB_MMR_CONTROL_ECC_SEL_SHFT		21
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_WRITE_SHFT		30
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_READ_SHFT		31
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT	32
+#define UV4H_GR1_TLB_MMR_CONTROL_PAGE_SIZE_SHFT		59
+#define UV4H_GR1_TLB_MMR_CONTROL_INDEX_MASK		0x0000000000001fffUL
+#define UV4H_GR1_TLB_MMR_CONTROL_MEM_SEL_MASK		0x0000000000006000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK	0x0000000000010000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK	0x0000000000100000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_ECC_SEL_MASK		0x0000000000200000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_WRITE_MASK		0x0000000040000000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_READ_MASK		0x0000000080000000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_MASK	0x0000000100000000UL
+#define UV4H_GR1_TLB_MMR_CONTROL_PAGE_SIZE_MASK		0xf800000000000000UL
+
+
 union uvh_gr1_tlb_mmr_control_u {
 	unsigned long	v;
 	struct uvh_gr1_tlb_mmr_control_s {
-		unsigned long	index:12;			/* RW */
-		unsigned long	mem_sel:2;			/* RW */
-		unsigned long	rsvd_14_15:2;
+		unsigned long	rsvd_0_15:16;
 		unsigned long	auto_valid_en:1;		/* RW */
 		unsigned long	rsvd_17_19:3;
 		unsigned long	mmr_hash_index_en:1;		/* RW */
@@ -1132,9 +1489,7 @@ union uvh_gr1_tlb_mmr_control_u {
 		unsigned long	rsvd_61_63:3;
 	} s1;
 	struct uvxh_gr1_tlb_mmr_control_s {
-		unsigned long	index:12;			/* RW */
-		unsigned long	mem_sel:2;			/* RW */
-		unsigned long	rsvd_14_15:2;
+		unsigned long	rsvd_0_15:16;
 		unsigned long	auto_valid_en:1;		/* RW */
 		unsigned long	rsvd_17_19:3;
 		unsigned long	mmr_hash_index_en:1;		/* RW */
@@ -1145,8 +1500,7 @@ union uvh_gr1_tlb_mmr_control_u {
 		unsigned long	rsvd_33_47:15;
 		unsigned long	rsvd_48:1;
 		unsigned long	rsvd_49_51:3;
-		unsigned long	rsvd_52:1;
-		unsigned long	rsvd_53_63:11;
+		unsigned long	rsvd_52_63:12;
 	} sx;
 	struct uv2h_gr1_tlb_mmr_control_s {
 		unsigned long	index:12;			/* RW */
@@ -1183,6 +1537,24 @@ union uvh_gr1_tlb_mmr_control_u {
 		unsigned long	undef_52:1;			/* Undefined */
 		unsigned long	rsvd_53_63:11;
 	} s3;
+	struct uv4h_gr1_tlb_mmr_control_s {
+		unsigned long	index:13;			/* RW */
+		unsigned long	mem_sel:2;			/* RW */
+		unsigned long	rsvd_15:1;
+		unsigned long	auto_valid_en:1;		/* RW */
+		unsigned long	rsvd_17_19:3;
+		unsigned long	mmr_hash_index_en:1;		/* RW */
+		unsigned long	ecc_sel:1;			/* RW */
+		unsigned long	rsvd_22_29:8;
+		unsigned long	mmr_write:1;			/* WP */
+		unsigned long	mmr_read:1;			/* WP */
+		unsigned long	mmr_op_done:1;			/* RW */
+		unsigned long	rsvd_33_47:15;
+		unsigned long	undef_48:1;			/* Undefined */
+		unsigned long	rsvd_49_51:3;
+		unsigned long	rsvd_52_58:7;
+		unsigned long	page_size:5;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -1191,19 +1563,14 @@ union uvh_gr1_tlb_mmr_control_u {
 #define UV1H_GR1_TLB_MMR_READ_DATA_HI 0x8010a0UL
 #define UV2H_GR1_TLB_MMR_READ_DATA_HI 0x10010a0UL
 #define UV3H_GR1_TLB_MMR_READ_DATA_HI 0x10010a0UL
-#define UVH_GR1_TLB_MMR_READ_DATA_HI					\
-		(is_uv1_hub() ? UV1H_GR1_TLB_MMR_READ_DATA_HI :		\
-		(is_uv2_hub() ? UV2H_GR1_TLB_MMR_READ_DATA_HI :		\
-				UV3H_GR1_TLB_MMR_READ_DATA_HI))
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI 0x7010a0UL
+#define UVH_GR1_TLB_MMR_READ_DATA_HI (					\
+	is_uv1_hub() ? UV1H_GR1_TLB_MMR_READ_DATA_HI :			\
+	is_uv2_hub() ? UV2H_GR1_TLB_MMR_READ_DATA_HI :			\
+	is_uv3_hub() ? UV3H_GR1_TLB_MMR_READ_DATA_HI :			\
+	/*is_uv4_hub*/ UV4H_GR1_TLB_MMR_READ_DATA_HI)
 
 #define UVH_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT		43
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT	44
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK		0x000001ffffffffffUL
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK		0x0000060000000000UL
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK		0x0000080000000000UL
-#define UVH_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0000100000000000UL
 
 #define UV1H_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
 #define UV1H_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
@@ -1215,13 +1582,6 @@ union uvh_gr1_tlb_mmr_control_u {
 #define UV1H_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0000100000000000UL
 
 #define UVXH_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT	43
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT	44
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK		0x000001ffffffffffUL
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK		0x0000060000000000UL
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK	0x0000080000000000UL
-#define UVXH_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0000100000000000UL
 
 #define UV2H_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
 #define UV2H_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT		41
@@ -1245,15 +1605,24 @@ union uvh_gr1_tlb_mmr_control_u {
 #define UV3H_GR1_TLB_MMR_READ_DATA_HI_AA_EXT_MASK	0x0000200000000000UL
 #define UV3H_GR1_TLB_MMR_READ_DATA_HI_WAY_ECC_MASK	0xff80000000000000UL
 
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT		0
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_PNID_SHFT		34
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT		49
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT	51
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT	52
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_AA_EXT_SHFT	53
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_WAY_ECC_SHFT	55
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK		0x00000003ffffffffUL
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_PNID_MASK		0x0001fffc00000000UL
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK		0x0006000000000000UL
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK	0x0008000000000000UL
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK	0x0010000000000000UL
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_AA_EXT_MASK	0x0020000000000000UL
+#define UV4H_GR1_TLB_MMR_READ_DATA_HI_WAY_ECC_MASK	0xff80000000000000UL
+
+
 union uvh_gr1_tlb_mmr_read_data_hi_u {
 	unsigned long	v;
-	struct uvh_gr1_tlb_mmr_read_data_hi_s {
-		unsigned long	pfn:41;				/* RO */
-		unsigned long	gaa:2;				/* RO */
-		unsigned long	dirty:1;			/* RO */
-		unsigned long	larger:1;			/* RO */
-		unsigned long	rsvd_45_63:19;
-	} s;
 	struct uv1h_gr1_tlb_mmr_read_data_hi_s {
 		unsigned long	pfn:41;				/* RO */
 		unsigned long	gaa:2;				/* RO */
@@ -1261,13 +1630,6 @@ union uvh_gr1_tlb_mmr_read_data_hi_u {
 		unsigned long	larger:1;			/* RO */
 		unsigned long	rsvd_45_63:19;
 	} s1;
-	struct uvxh_gr1_tlb_mmr_read_data_hi_s {
-		unsigned long	pfn:41;				/* RO */
-		unsigned long	gaa:2;				/* RO */
-		unsigned long	dirty:1;			/* RO */
-		unsigned long	larger:1;			/* RO */
-		unsigned long	rsvd_45_63:19;
-	} sx;
 	struct uv2h_gr1_tlb_mmr_read_data_hi_s {
 		unsigned long	pfn:41;				/* RO */
 		unsigned long	gaa:2;				/* RO */
@@ -1284,6 +1646,16 @@ union uvh_gr1_tlb_mmr_read_data_hi_u {
 		unsigned long	undef_46_54:9;			/* Undefined */
 		unsigned long	way_ecc:9;			/* RO */
 	} s3;
+	struct uv4h_gr1_tlb_mmr_read_data_hi_s {
+		unsigned long	pfn:34;				/* RO */
+		unsigned long	pnid:15;			/* RO */
+		unsigned long	gaa:2;				/* RO */
+		unsigned long	dirty:1;			/* RO */
+		unsigned long	larger:1;			/* RO */
+		unsigned long	aa_ext:1;			/* RO */
+		unsigned long	undef_54:1;			/* Undefined */
+		unsigned long	way_ecc:9;			/* RO */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -1292,10 +1664,12 @@ union uvh_gr1_tlb_mmr_read_data_hi_u {
 #define UV1H_GR1_TLB_MMR_READ_DATA_LO 0x8010a8UL
 #define UV2H_GR1_TLB_MMR_READ_DATA_LO 0x10010a8UL
 #define UV3H_GR1_TLB_MMR_READ_DATA_LO 0x10010a8UL
-#define UVH_GR1_TLB_MMR_READ_DATA_LO					\
-		(is_uv1_hub() ? UV1H_GR1_TLB_MMR_READ_DATA_LO :		\
-		(is_uv2_hub() ? UV2H_GR1_TLB_MMR_READ_DATA_LO :		\
-				UV3H_GR1_TLB_MMR_READ_DATA_LO))
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO 0x7010a8UL
+#define UVH_GR1_TLB_MMR_READ_DATA_LO (					\
+	is_uv1_hub() ? UV1H_GR1_TLB_MMR_READ_DATA_LO :			\
+	is_uv2_hub() ? UV2H_GR1_TLB_MMR_READ_DATA_LO :			\
+	is_uv3_hub() ? UV3H_GR1_TLB_MMR_READ_DATA_LO :			\
+	/*is_uv4_hub*/ UV4H_GR1_TLB_MMR_READ_DATA_LO)
 
 #define UVH_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT		0
 #define UVH_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT		39
@@ -1332,6 +1706,14 @@ union uvh_gr1_tlb_mmr_read_data_hi_u {
 #define UV3H_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK		0x7fffff8000000000UL
 #define UV3H_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK	0x8000000000000000UL
 
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT		0
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT		39
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO_VALID_SHFT	63
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO_VPN_MASK		0x0000007fffffffffUL
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK		0x7fffff8000000000UL
+#define UV4H_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK	0x8000000000000000UL
+
+
 union uvh_gr1_tlb_mmr_read_data_lo_u {
 	unsigned long	v;
 	struct uvh_gr1_tlb_mmr_read_data_lo_s {
@@ -1359,6 +1741,11 @@ union uvh_gr1_tlb_mmr_read_data_lo_u {
 		unsigned long	asid:24;			/* RO */
 		unsigned long	valid:1;			/* RO */
 	} s3;
+	struct uv4h_gr1_tlb_mmr_read_data_lo_s {
+		unsigned long	vpn:39;				/* RO */
+		unsigned long	asid:24;			/* RO */
+		unsigned long	valid:1;			/* RO */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -1369,6 +1756,7 @@ union uvh_gr1_tlb_mmr_read_data_lo_u {
 #define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT		0
 #define UVH_INT_CMPB_REAL_TIME_CMPB_MASK		0x00ffffffffffffffUL
 
+
 union uvh_int_cmpb_u {
 	unsigned long	v;
 	struct uvh_int_cmpb_s {
@@ -1382,12 +1770,14 @@ union uvh_int_cmpb_u {
 /* ========================================================================= */
 #define UVH_INT_CMPC 0x22100UL
 
+
 #define UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT		0
 #define UV1H_INT_CMPC_REAL_TIME_CMPC_MASK		0x00ffffffffffffffUL
 
 #define UVXH_INT_CMPC_REAL_TIME_CMP_2_SHFT		0
 #define UVXH_INT_CMPC_REAL_TIME_CMP_2_MASK		0x00ffffffffffffffUL
 
+
 union uvh_int_cmpc_u {
 	unsigned long	v;
 	struct uvh_int_cmpc_s {
@@ -1401,12 +1791,14 @@ union uvh_int_cmpc_u {
 /* ========================================================================= */
 #define UVH_INT_CMPD 0x22180UL
 
+
 #define UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT		0
 #define UV1H_INT_CMPD_REAL_TIME_CMPD_MASK		0x00ffffffffffffffUL
 
 #define UVXH_INT_CMPD_REAL_TIME_CMP_3_SHFT		0
 #define UVXH_INT_CMPD_REAL_TIME_CMP_3_MASK		0x00ffffffffffffffUL
 
+
 union uvh_int_cmpd_u {
 	unsigned long	v;
 	struct uvh_int_cmpd_s {
@@ -1419,7 +1811,16 @@ union uvh_int_cmpd_u {
 /*                               UVH_IPI_INT                                 */
 /* ========================================================================= */
 #define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x348
+
+#define UV1H_IPI_INT_32 0x348
+#define UV2H_IPI_INT_32 0x348
+#define UV3H_IPI_INT_32 0x348
+#define UV4H_IPI_INT_32 0x268
+#define UVH_IPI_INT_32 (						\
+	is_uv1_hub() ? UV1H_IPI_INT_32 :				\
+	is_uv2_hub() ? UV2H_IPI_INT_32 :				\
+	is_uv3_hub() ? UV3H_IPI_INT_32 :				\
+	/*is_uv4_hub*/ UV4H_IPI_INT_32)
 
 #define UVH_IPI_INT_VECTOR_SHFT				0
 #define UVH_IPI_INT_DELIVERY_MODE_SHFT			8
@@ -1432,6 +1833,7 @@ union uvh_int_cmpd_u {
 #define UVH_IPI_INT_APIC_ID_MASK			0x0000ffffffff0000UL
 #define UVH_IPI_INT_SEND_MASK				0x8000000000000000UL
 
+
 union uvh_ipi_int_u {
 	unsigned long	v;
 	struct uvh_ipi_int_s {
@@ -1448,103 +1850,269 @@ union uvh_ipi_int_u {
 /* ========================================================================= */
 /*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
 /* ========================================================================= */
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
+#define UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST uv_undefined("UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST")
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST (				\
+	is_uv1_hub() ? UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST :		\
+	is_uv2_hub() ? UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST :		\
+	is_uv3_hub() ? UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST)
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0
 
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_MASK 0x7ffe000000000000UL
+
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_MASK 0x7ffe000000000000UL
+
+
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_MASK 0x7ffe000000000000UL
+
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_MASK 0x7ffe000000000000UL
+
 
 union uvh_lb_bau_intd_payload_queue_first_u {
 	unsigned long	v;
-	struct uvh_lb_bau_intd_payload_queue_first_s {
+	struct uv1h_lb_bau_intd_payload_queue_first_s {
 		unsigned long	rsvd_0_3:4;
 		unsigned long	address:39;			/* RW */
 		unsigned long	rsvd_43_48:6;
 		unsigned long	node_id:14;			/* RW */
 		unsigned long	rsvd_63:1;
-	} s;
+	} s1;
+	struct uv2h_lb_bau_intd_payload_queue_first_s {
+		unsigned long	rsvd_0_3:4;
+		unsigned long	address:39;			/* RW */
+		unsigned long	rsvd_43_48:6;
+		unsigned long	node_id:14;			/* RW */
+		unsigned long	rsvd_63:1;
+	} s2;
+	struct uv3h_lb_bau_intd_payload_queue_first_s {
+		unsigned long	rsvd_0_3:4;
+		unsigned long	address:39;			/* RW */
+		unsigned long	rsvd_43_48:6;
+		unsigned long	node_id:14;			/* RW */
+		unsigned long	rsvd_63:1;
+	} s3;
 };
 
 /* ========================================================================= */
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
 /* ========================================================================= */
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
+#define UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST uv_undefined("UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST")
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST (				\
+	is_uv1_hub() ? UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST :		\
+	is_uv2_hub() ? UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST :		\
+	is_uv3_hub() ? UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST)
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8
 
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT	4
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK	0x000007fffffffff0UL
+
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
+
+
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
+
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
+
 
 union uvh_lb_bau_intd_payload_queue_last_u {
 	unsigned long	v;
-	struct uvh_lb_bau_intd_payload_queue_last_s {
+	struct uv1h_lb_bau_intd_payload_queue_last_s {
 		unsigned long	rsvd_0_3:4;
 		unsigned long	address:39;			/* RW */
 		unsigned long	rsvd_43_63:21;
-	} s;
+	} s1;
+	struct uv2h_lb_bau_intd_payload_queue_last_s {
+		unsigned long	rsvd_0_3:4;
+		unsigned long	address:39;			/* RW */
+		unsigned long	rsvd_43_63:21;
+	} s2;
+	struct uv3h_lb_bau_intd_payload_queue_last_s {
+		unsigned long	rsvd_0_3:4;
+		unsigned long	address:39;			/* RW */
+		unsigned long	rsvd_43_63:21;
+	} s3;
 };
 
 /* ========================================================================= */
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
 /* ========================================================================= */
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
+#define UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL uv_undefined("UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL")
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL (				\
+	is_uv1_hub() ? UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL :		\
+	is_uv2_hub() ? UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL :		\
+	is_uv3_hub() ? UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL)
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0
 
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT	4
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK	0x000007fffffffff0UL
+
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
+#define UV1H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
+
+
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
+#define UV2H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
+
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
+#define UV3H_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
+
 
 union uvh_lb_bau_intd_payload_queue_tail_u {
 	unsigned long	v;
-	struct uvh_lb_bau_intd_payload_queue_tail_s {
+	struct uv1h_lb_bau_intd_payload_queue_tail_s {
 		unsigned long	rsvd_0_3:4;
 		unsigned long	address:39;			/* RW */
 		unsigned long	rsvd_43_63:21;
-	} s;
+	} s1;
+	struct uv2h_lb_bau_intd_payload_queue_tail_s {
+		unsigned long	rsvd_0_3:4;
+		unsigned long	address:39;			/* RW */
+		unsigned long	rsvd_43_63:21;
+	} s2;
+	struct uv3h_lb_bau_intd_payload_queue_tail_s {
+		unsigned long	rsvd_0_3:4;
+		unsigned long	address:39;			/* RW */
+		unsigned long	rsvd_43_63:21;
+	} s3;
 };
 
 /* ========================================================================= */
 /*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
 /* ========================================================================= */
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UV4H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE uv_undefined("UV4H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE")
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE (				\
+	is_uv1_hub() ? UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE :		\
+	is_uv2_hub() ? UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE :		\
+	is_uv3_hub() ? UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE)
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68
 
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_SHFT 2
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_SHFT 3
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_SHFT 4
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_SHFT 5
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_SHFT 6
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_SHFT 7
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_SHFT 8
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_SHFT 9
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_SHFT 10
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_SHFT 11
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_SHFT 12
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_SHFT 13
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_SHFT 14
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_MASK 0x0000000000000002UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_MASK 0x0000000000000004UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_MASK 0x0000000000000008UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_MASK 0x0000000000000010UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_MASK 0x0000000000000020UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_MASK 0x0000000000000040UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_MASK 0x0000000000000080UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_MASK 0x0000000000000100UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_MASK 0x0000000000000200UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_MASK 0x0000000000000400UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_MASK 0x0000000000000800UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_MASK 0x0000000000001000UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_MASK 0x0000000000002000UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_SHFT 2
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_SHFT 3
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_SHFT 4
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_SHFT 5
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_SHFT 6
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_SHFT 7
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_SHFT 8
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_SHFT 9
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_SHFT 10
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_SHFT 11
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_SHFT 12
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_SHFT 13
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_SHFT 14
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_MASK 0x0000000000000002UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_MASK 0x0000000000000004UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_MASK 0x0000000000000008UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_MASK 0x0000000000000010UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_MASK 0x0000000000000020UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_MASK 0x0000000000000040UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_MASK 0x0000000000000080UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_MASK 0x0000000000000100UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_MASK 0x0000000000000200UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_MASK 0x0000000000000400UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_MASK 0x0000000000000800UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_MASK 0x0000000000001000UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_MASK 0x0000000000002000UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
+
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_SHFT 2
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_SHFT 3
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_SHFT 4
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_SHFT 5
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_SHFT 6
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_SHFT 7
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_SHFT 8
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_SHFT 9
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_SHFT 10
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_SHFT 11
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_SHFT 12
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_SHFT 13
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_SHFT 14
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_MASK 0x0000000000000002UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_MASK 0x0000000000000004UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_MASK 0x0000000000000008UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_MASK 0x0000000000000010UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_MASK 0x0000000000000020UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_MASK 0x0000000000000040UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_MASK 0x0000000000000080UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_MASK 0x0000000000000100UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_MASK 0x0000000000000200UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_MASK 0x0000000000000400UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_MASK 0x0000000000000800UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_MASK 0x0000000000001000UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_MASK 0x0000000000002000UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_SHFT 2
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_SHFT 3
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_SHFT 4
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_SHFT 5
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_SHFT 6
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_SHFT 7
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_SHFT 8
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_SHFT 9
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_SHFT 10
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_SHFT 11
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_SHFT 12
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_SHFT 13
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_SHFT 14
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_MASK 0x0000000000000002UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_MASK 0x0000000000000004UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_MASK 0x0000000000000008UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_MASK 0x0000000000000010UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_MASK 0x0000000000000020UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_MASK 0x0000000000000040UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_MASK 0x0000000000000080UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_MASK 0x0000000000000100UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_MASK 0x0000000000000200UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_MASK 0x0000000000000400UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_MASK 0x0000000000000800UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_MASK 0x0000000000001000UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_MASK 0x0000000000002000UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
 
 union uvh_lb_bau_intd_software_acknowledge_u {
 	unsigned long	v;
-	struct uvh_lb_bau_intd_software_acknowledge_s {
+	struct uv1h_lb_bau_intd_software_acknowledge_s {
 		unsigned long	pending_0:1;			/* RW, W1C */
 		unsigned long	pending_1:1;			/* RW, W1C */
 		unsigned long	pending_2:1;			/* RW, W1C */
@@ -1562,27 +2130,84 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 		unsigned long	timeout_6:1;			/* RW, W1C */
 		unsigned long	timeout_7:1;			/* RW, W1C */
 		unsigned long	rsvd_16_63:48;
-	} s;
+	} s1;
+	struct uv2h_lb_bau_intd_software_acknowledge_s {
+		unsigned long	pending_0:1;			/* RW */
+		unsigned long	pending_1:1;			/* RW */
+		unsigned long	pending_2:1;			/* RW */
+		unsigned long	pending_3:1;			/* RW */
+		unsigned long	pending_4:1;			/* RW */
+		unsigned long	pending_5:1;			/* RW */
+		unsigned long	pending_6:1;			/* RW */
+		unsigned long	pending_7:1;			/* RW */
+		unsigned long	timeout_0:1;			/* RW */
+		unsigned long	timeout_1:1;			/* RW */
+		unsigned long	timeout_2:1;			/* RW */
+		unsigned long	timeout_3:1;			/* RW */
+		unsigned long	timeout_4:1;			/* RW */
+		unsigned long	timeout_5:1;			/* RW */
+		unsigned long	timeout_6:1;			/* RW */
+		unsigned long	timeout_7:1;			/* RW */
+		unsigned long	rsvd_16_63:48;
+	} s2;
+	struct uv3h_lb_bau_intd_software_acknowledge_s {
+		unsigned long	pending_0:1;			/* RW */
+		unsigned long	pending_1:1;			/* RW */
+		unsigned long	pending_2:1;			/* RW */
+		unsigned long	pending_3:1;			/* RW */
+		unsigned long	pending_4:1;			/* RW */
+		unsigned long	pending_5:1;			/* RW */
+		unsigned long	pending_6:1;			/* RW */
+		unsigned long	pending_7:1;			/* RW */
+		unsigned long	timeout_0:1;			/* RW */
+		unsigned long	timeout_1:1;			/* RW */
+		unsigned long	timeout_2:1;			/* RW */
+		unsigned long	timeout_3:1;			/* RW */
+		unsigned long	timeout_4:1;			/* RW */
+		unsigned long	timeout_5:1;			/* RW */
+		unsigned long	timeout_6:1;			/* RW */
+		unsigned long	timeout_7:1;			/* RW */
+		unsigned long	rsvd_16_63:48;
+	} s3;
 };
 
 /* ========================================================================= */
 /*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
 /* ========================================================================= */
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x320088UL
+#define UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x320088UL
+#define UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x320088UL
+#define UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x320088UL
+#define UV4H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS uv_undefined("UV4H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS")
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS (			\
+	is_uv1_hub() ? UV1H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS :	\
+	is_uv2_hub() ? UV2H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS :	\
+	is_uv3_hub() ? UV3H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS)
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70
 
 
 /* ========================================================================= */
 /*                         UVH_LB_BAU_MISC_CONTROL                           */
 /* ========================================================================= */
-#define UVH_LB_BAU_MISC_CONTROL 0x320170UL
 #define UV1H_LB_BAU_MISC_CONTROL 0x320170UL
 #define UV2H_LB_BAU_MISC_CONTROL 0x320170UL
 #define UV3H_LB_BAU_MISC_CONTROL 0x320170UL
-#define UVH_LB_BAU_MISC_CONTROL_32 0xa10
-#define UV1H_LB_BAU_MISC_CONTROL_32 0x320170UL
-#define UV2H_LB_BAU_MISC_CONTROL_32 0x320170UL
-#define UV3H_LB_BAU_MISC_CONTROL_32 0x320170UL
+#define UV4H_LB_BAU_MISC_CONTROL 0xc8170UL
+#define UVH_LB_BAU_MISC_CONTROL (					\
+	is_uv1_hub() ? UV1H_LB_BAU_MISC_CONTROL :			\
+	is_uv2_hub() ? UV2H_LB_BAU_MISC_CONTROL :			\
+	is_uv3_hub() ? UV3H_LB_BAU_MISC_CONTROL :			\
+	/*is_uv4_hub*/ UV4H_LB_BAU_MISC_CONTROL)
+
+#define UV1H_LB_BAU_MISC_CONTROL_32 0xa10
+#define UV2H_LB_BAU_MISC_CONTROL_32 0xa10
+#define UV3H_LB_BAU_MISC_CONTROL_32 0xa10
+#define UV4H_LB_BAU_MISC_CONTROL_32 0xa18
+#define UVH_LB_BAU_MISC_CONTROL_32 (					\
+	is_uv1_hub() ? UV1H_LB_BAU_MISC_CONTROL_32 :			\
+	is_uv2_hub() ? UV2H_LB_BAU_MISC_CONTROL_32 :			\
+	is_uv3_hub() ? UV3H_LB_BAU_MISC_CONTROL_32 :			\
+	/*is_uv4_hub*/ UV4H_LB_BAU_MISC_CONTROL_32)
 
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT	0
 #define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT		8
@@ -1590,8 +2215,6 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT	10
 #define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
-#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
-#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
 #define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
 #define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
@@ -1606,8 +2229,6 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK	0x0000000000000400UL
 #define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
-#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
-#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
 #define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
 #define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
@@ -1656,8 +2277,6 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVXH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT	10
 #define UVXH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
 #define UVXH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
-#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
-#define UVXH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
 #define UVXH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
 #define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
 #define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
@@ -1679,8 +2298,6 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVXH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK	0x0000000000000400UL
 #define UVXH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
 #define UVXH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
-#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
-#define UVXH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
 #define UVXH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
 #define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
 #define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
@@ -1797,6 +2414,88 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UV3H_LB_BAU_MISC_CONTROL_THREAD_KILL_TIMEBASE_MASK 0x00003fc000000000UL
 #define UV3H_LB_BAU_MISC_CONTROL_FUN_MASK		0xffff000000000000UL
 
+#define UV4H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT	0
+#define UV4H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT		8
+#define UV4H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT	9
+#define UV4H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT	10
+#define UV4H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV4H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV4H_LB_BAU_MISC_CONTROL_RESERVED_15_19_SHFT	15
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV4H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV4H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV4H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV4H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29
+#define UV4H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT	30
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34
+#define UV4H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_QUIESCE_MSGS_TO_QPI_SHFT 36
+#define UV4H_LB_BAU_MISC_CONTROL_RESERVED_37_SHFT	37
+#define UV4H_LB_BAU_MISC_CONTROL_THREAD_KILL_TIMEBASE_SHFT 38
+#define UV4H_LB_BAU_MISC_CONTROL_ADDRESS_INTERLEAVE_SELECT_SHFT 46
+#define UV4H_LB_BAU_MISC_CONTROL_FUN_SHFT		48
+#define UV4H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK	0x00000000000000ffUL
+#define UV4H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK		0x0000000000000100UL
+#define UV4H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK	0x0000000000000200UL
+#define UV4H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK	0x0000000000000400UL
+#define UV4H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV4H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV4H_LB_BAU_MISC_CONTROL_RESERVED_15_19_MASK	0x00000000000f8000UL
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV4H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV4H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV4H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK	0x0000000040000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_SUPPRESS_QUIESCE_MSGS_TO_QPI_MASK 0x0000001000000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_RESERVED_37_MASK	0x0000002000000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_THREAD_KILL_TIMEBASE_MASK 0x00003fc000000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_ADDRESS_INTERLEAVE_SELECT_MASK 0x0000400000000000UL
+#define UV4H_LB_BAU_MISC_CONTROL_FUN_MASK		0xffff000000000000UL
+
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK	\
+	uv_undefined("UV4H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK")
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK (	\
+	is_uv1_hub() ? UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK : \
+	is_uv2_hub() ? UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK : \
+	is_uv3_hub() ? UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK : \
+	/*is_uv4_hub*/ UV4H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK)
+#define UV4H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT	\
+	uv_undefined("UV4H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT")
+#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT (	\
+	is_uv1_hub() ? UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT : \
+	is_uv2_hub() ? UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT : \
+	is_uv3_hub() ? UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT : \
+	/*is_uv4_hub*/ UV4H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT)
+#define UV4H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK	\
+	uv_undefined("UV4H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK")
+#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK (	\
+	is_uv1_hub() ? UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK : \
+	is_uv2_hub() ? UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK : \
+	is_uv3_hub() ? UV3H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK : \
+	/*is_uv4_hub*/ UV4H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK)
+#define UV4H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT	\
+	uv_undefined("UV4H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT")
+#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT (	\
+	is_uv1_hub() ? UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT : \
+	is_uv2_hub() ? UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT : \
+	is_uv3_hub() ? UV3H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT : \
+	/*is_uv4_hub*/ UV4H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT)
+
 union uvh_lb_bau_misc_control_u {
 	unsigned long	v;
 	struct uvh_lb_bau_misc_control_s {
@@ -1806,8 +2505,7 @@ union uvh_lb_bau_misc_control_u {
 		unsigned long	force_lock_nop:1;		/* RW */
 		unsigned long	qpi_agent_presence_vector:3;	/* RW */
 		unsigned long	descriptor_fetch_mode:1;	/* RW */
-		unsigned long	enable_intd_soft_ack_mode:1;	/* RW */
-		unsigned long	intd_soft_ack_timeout_period:4;	/* RW */
+		unsigned long	rsvd_15_19:5;
 		unsigned long	enable_dual_mapping_mode:1;	/* RW */
 		unsigned long	vga_io_port_decode_enable:1;	/* RW */
 		unsigned long	vga_io_port_16_bit_decode:1;	/* RW */
@@ -1844,8 +2542,7 @@ union uvh_lb_bau_misc_control_u {
 		unsigned long	force_lock_nop:1;		/* RW */
 		unsigned long	qpi_agent_presence_vector:3;	/* RW */
 		unsigned long	descriptor_fetch_mode:1;	/* RW */
-		unsigned long	enable_intd_soft_ack_mode:1;	/* RW */
-		unsigned long	intd_soft_ack_timeout_period:4;	/* RW */
+		unsigned long	rsvd_15_19:5;
 		unsigned long	enable_dual_mapping_mode:1;	/* RW */
 		unsigned long	vga_io_port_decode_enable:1;	/* RW */
 		unsigned long	vga_io_port_16_bit_decode:1;	/* RW */
@@ -1918,13 +2615,59 @@ union uvh_lb_bau_misc_control_u {
 		unsigned long	rsvd_46_47:2;
 		unsigned long	fun:16;				/* RW */
 	} s3;
+	struct uv4h_lb_bau_misc_control_s {
+		unsigned long	rejection_delay:8;		/* RW */
+		unsigned long	apic_mode:1;			/* RW */
+		unsigned long	force_broadcast:1;		/* RW */
+		unsigned long	force_lock_nop:1;		/* RW */
+		unsigned long	qpi_agent_presence_vector:3;	/* RW */
+		unsigned long	descriptor_fetch_mode:1;	/* RW */
+		unsigned long	rsvd_15_19:5;
+		unsigned long	enable_dual_mapping_mode:1;	/* RW */
+		unsigned long	vga_io_port_decode_enable:1;	/* RW */
+		unsigned long	vga_io_port_16_bit_decode:1;	/* RW */
+		unsigned long	suppress_dest_registration:1;	/* RW */
+		unsigned long	programmed_initial_priority:3;	/* RW */
+		unsigned long	use_incoming_priority:1;	/* RW */
+		unsigned long	enable_programmed_initial_priority:1;/* RW */
+		unsigned long	enable_automatic_apic_mode_selection:1;/* RW */
+		unsigned long	apic_mode_status:1;		/* RO */
+		unsigned long	suppress_interrupts_to_self:1;	/* RW */
+		unsigned long	enable_lock_based_system_flush:1;/* RW */
+		unsigned long	enable_extended_sb_status:1;	/* RW */
+		unsigned long	suppress_int_prio_udt_to_self:1;/* RW */
+		unsigned long	use_legacy_descriptor_formats:1;/* RW */
+		unsigned long	suppress_quiesce_msgs_to_qpi:1;	/* RW */
+		unsigned long	rsvd_37:1;
+		unsigned long	thread_kill_timebase:8;		/* RW */
+		unsigned long	address_interleave_select:1;	/* RW */
+		unsigned long	rsvd_47:1;
+		unsigned long	fun:16;				/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
+#define UV1H_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
+#define UV2H_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
+#define UV3H_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
+#define UV4H_LB_BAU_SB_ACTIVATION_CONTROL 0xc8020UL
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_ACTIVATION_CONTROL :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_CONTROL :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_CONTROL :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_CONTROL)
+
+#define UV1H_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
+#define UV2H_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
+#define UV3H_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
+#define UV4H_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9c8
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_ACTIVATION_CONTROL_32 :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_CONTROL_32 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_CONTROL_32 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_CONTROL_32)
 
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT	0
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT	62
@@ -1933,6 +2676,7 @@ union uvh_lb_bau_misc_control_u {
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_MASK	0x4000000000000000UL
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INIT_MASK	0x8000000000000000UL
 
+
 union uvh_lb_bau_sb_activation_control_u {
 	unsigned long	v;
 	struct uvh_lb_bau_sb_activation_control_s {
@@ -1946,12 +2690,30 @@ union uvh_lb_bau_sb_activation_control_u {
 /* ========================================================================= */
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
 /* ========================================================================= */
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
+#define UV1H_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
+#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_0 0xc8030UL
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_ACTIVATION_STATUS_0 :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_STATUS_0 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_STATUS_0 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_STATUS_0)
+
+#define UV1H_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
+#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9d0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_ACTIVATION_STATUS_0_32 :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_STATUS_0_32 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_STATUS_0_32 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_STATUS_0_32)
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT	0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK	0xffffffffffffffffUL
 
+
 union uvh_lb_bau_sb_activation_status_0_u {
 	unsigned long	v;
 	struct uvh_lb_bau_sb_activation_status_0_s {
@@ -1962,12 +2724,30 @@ union uvh_lb_bau_sb_activation_status_0_u {
 /* ========================================================================= */
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
 /* ========================================================================= */
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
+#define UV1H_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
+#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_1 0xc8040UL
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_ACTIVATION_STATUS_1 :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_STATUS_1 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_STATUS_1 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_STATUS_1)
+
+#define UV1H_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
+#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9d8
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_ACTIVATION_STATUS_1_32 :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_STATUS_1_32 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_STATUS_1_32 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_STATUS_1_32)
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT	0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK	0xffffffffffffffffUL
 
+
 union uvh_lb_bau_sb_activation_status_1_u {
 	unsigned long	v;
 	struct uvh_lb_bau_sb_activation_status_1_s {
@@ -1978,23 +2758,55 @@ union uvh_lb_bau_sb_activation_status_1_u {
 /* ========================================================================= */
 /*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
 /* ========================================================================= */
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE 0xc8010UL
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE (					\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE :			\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE :			\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE :			\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE)
+
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9c0
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 (				\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_32 :		\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_32 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_32 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_32)
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT	12
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK	0x000007fffffff000UL
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+
+
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x00003ffffffff000UL
+
+
 union uvh_lb_bau_sb_descriptor_base_u {
 	unsigned long	v;
 	struct uvh_lb_bau_sb_descriptor_base_s {
 		unsigned long	rsvd_0_11:12;
-		unsigned long	page_address:31;		/* RW */
-		unsigned long	rsvd_43_48:6;
+		unsigned long	rsvd_12_48:37;
 		unsigned long	node_id:14;			/* RW */
 		unsigned long	rsvd_63:1;
 	} s;
+	struct uv4h_lb_bau_sb_descriptor_base_s {
+		unsigned long	rsvd_0_11:12;
+		unsigned long	page_address:34;		/* RW */
+		unsigned long	rsvd_46_48:3;
+		unsigned long	node_id:14;			/* RW */
+		unsigned long	rsvd_63:1;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -2004,6 +2816,7 @@ union uvh_lb_bau_sb_descriptor_base_u {
 #define UV1H_NODE_ID 0x0UL
 #define UV2H_NODE_ID 0x0UL
 #define UV3H_NODE_ID 0x0UL
+#define UV4H_NODE_ID 0x0UL
 
 #define UVH_NODE_ID_FORCE1_SHFT				0
 #define UVH_NODE_ID_MANUFACTURER_SHFT			1
@@ -2080,6 +2893,26 @@ union uvh_lb_bau_sb_descriptor_base_u {
 #define UV3H_NODE_ID_NODES_PER_BIT_MASK			0x01fc000000000000UL
 #define UV3H_NODE_ID_NI_PORT_MASK			0x3e00000000000000UL
 
+#define UV4H_NODE_ID_FORCE1_SHFT			0
+#define UV4H_NODE_ID_MANUFACTURER_SHFT			1
+#define UV4H_NODE_ID_PART_NUMBER_SHFT			12
+#define UV4H_NODE_ID_REVISION_SHFT			28
+#define UV4H_NODE_ID_NODE_ID_SHFT			32
+#define UV4H_NODE_ID_ROUTER_SELECT_SHFT			48
+#define UV4H_NODE_ID_RESERVED_2_SHFT			49
+#define UV4H_NODE_ID_NODES_PER_BIT_SHFT			50
+#define UV4H_NODE_ID_NI_PORT_SHFT			57
+#define UV4H_NODE_ID_FORCE1_MASK			0x0000000000000001UL
+#define UV4H_NODE_ID_MANUFACTURER_MASK			0x0000000000000ffeUL
+#define UV4H_NODE_ID_PART_NUMBER_MASK			0x000000000ffff000UL
+#define UV4H_NODE_ID_REVISION_MASK			0x00000000f0000000UL
+#define UV4H_NODE_ID_NODE_ID_MASK			0x00007fff00000000UL
+#define UV4H_NODE_ID_ROUTER_SELECT_MASK			0x0001000000000000UL
+#define UV4H_NODE_ID_RESERVED_2_MASK			0x0002000000000000UL
+#define UV4H_NODE_ID_NODES_PER_BIT_MASK			0x01fc000000000000UL
+#define UV4H_NODE_ID_NI_PORT_MASK			0x3e00000000000000UL
+
+
 union uvh_node_id_u {
 	unsigned long	v;
 	struct uvh_node_id_s {
@@ -2137,17 +2970,40 @@ union uvh_node_id_u {
 		unsigned long	ni_port:5;			/* RO */
 		unsigned long	rsvd_62_63:2;
 	} s3;
+	struct uv4h_node_id_s {
+		unsigned long	force1:1;			/* RO */
+		unsigned long	manufacturer:11;		/* RO */
+		unsigned long	part_number:16;			/* RO */
+		unsigned long	revision:4;			/* RO */
+		unsigned long	node_id:15;			/* RW */
+		unsigned long	rsvd_47:1;
+		unsigned long	router_select:1;		/* RO */
+		unsigned long	rsvd_49:1;
+		unsigned long	nodes_per_bit:7;		/* RO */
+		unsigned long	ni_port:5;			/* RO */
+		unsigned long	rsvd_62_63:2;
+	} s4;
 };
 
 /* ========================================================================= */
 /*                          UVH_NODE_PRESENT_TABLE                           */
 /* ========================================================================= */
 #define UVH_NODE_PRESENT_TABLE 0x1400UL
-#define UVH_NODE_PRESENT_TABLE_DEPTH 16
+
+#define UV1H_NODE_PRESENT_TABLE_DEPTH 16
+#define UV2H_NODE_PRESENT_TABLE_DEPTH 16
+#define UV3H_NODE_PRESENT_TABLE_DEPTH 16
+#define UV4H_NODE_PRESENT_TABLE_DEPTH 4
+#define UVH_NODE_PRESENT_TABLE_DEPTH (					\
+	is_uv1_hub() ? UV1H_NODE_PRESENT_TABLE_DEPTH :			\
+	is_uv2_hub() ? UV2H_NODE_PRESENT_TABLE_DEPTH :			\
+	is_uv3_hub() ? UV3H_NODE_PRESENT_TABLE_DEPTH :			\
+	/*is_uv4_hub*/ UV4H_NODE_PRESENT_TABLE_DEPTH)
 
 #define UVH_NODE_PRESENT_TABLE_NODES_SHFT		0
 #define UVH_NODE_PRESENT_TABLE_NODES_MASK		0xffffffffffffffffUL
 
+
 union uvh_node_present_table_u {
 	unsigned long	v;
 	struct uvh_node_present_table_s {
@@ -2158,7 +3014,15 @@ union uvh_node_present_table_u {
 /* ========================================================================= */
 /*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR                  */
 /* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x4800c8UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR (			\
+	is_uv1_hub() ? UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR :	\
+	is_uv2_hub() ? UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR :	\
+	is_uv3_hub() ? UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR)
 
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
@@ -2167,6 +3031,7 @@ union uvh_node_present_table_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
 
+
 union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_alias210_overlay_config_0_mmr_s {
@@ -2182,7 +3047,15 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 /* ========================================================================= */
 /*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR                  */
 /* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x4800d8UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR (			\
+	is_uv1_hub() ? UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR :	\
+	is_uv2_hub() ? UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR :	\
+	is_uv3_hub() ? UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR)
 
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
@@ -2191,6 +3064,7 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
 
+
 union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_alias210_overlay_config_1_mmr_s {
@@ -2206,7 +3080,15 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 /* ========================================================================= */
 /*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR                  */
 /* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x4800e8UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR (			\
+	is_uv1_hub() ? UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR :	\
+	is_uv2_hub() ? UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR :	\
+	is_uv3_hub() ? UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR)
 
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
@@ -2215,6 +3097,7 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
 
+
 union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_alias210_overlay_config_2_mmr_s {
@@ -2230,11 +3113,20 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 /* ========================================================================= */
 /*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
 /* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x4800d0UL
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR (			\
+	is_uv1_hub() ? UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR :	\
+	is_uv2_hub() ? UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR :	\
+	is_uv3_hub() ? UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR)
 
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+
 union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_alias210_redirect_config_0_mmr_s {
@@ -2247,11 +3139,20 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 /* ========================================================================= */
 /*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR                  */
 /* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x4800e0UL
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR (			\
+	is_uv1_hub() ? UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR :	\
+	is_uv2_hub() ? UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR :	\
+	is_uv3_hub() ? UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR)
 
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+
 union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_alias210_redirect_config_1_mmr_s {
@@ -2264,11 +3165,20 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 /* ========================================================================= */
 /*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR                  */
 /* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x4800f0UL
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR (			\
+	is_uv1_hub() ? UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR :	\
+	is_uv2_hub() ? UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR :	\
+	is_uv3_hub() ? UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR)
 
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+
 union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_alias210_redirect_config_2_mmr_s {
@@ -2281,14 +3191,17 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 /* ========================================================================= */
 /*                          UVH_RH_GAM_CONFIG_MMR                            */
 /* ========================================================================= */
-#define UVH_RH_GAM_CONFIG_MMR 0x1600000UL
 #define UV1H_RH_GAM_CONFIG_MMR 0x1600000UL
 #define UV2H_RH_GAM_CONFIG_MMR 0x1600000UL
 #define UV3H_RH_GAM_CONFIG_MMR 0x1600000UL
+#define UV4H_RH_GAM_CONFIG_MMR 0x480000UL
+#define UVH_RH_GAM_CONFIG_MMR (						\
+	is_uv1_hub() ? UV1H_RH_GAM_CONFIG_MMR :				\
+	is_uv2_hub() ? UV2H_RH_GAM_CONFIG_MMR :				\
+	is_uv3_hub() ? UV3H_RH_GAM_CONFIG_MMR :				\
+	/*is_uv4_hub*/ UV4H_RH_GAM_CONFIG_MMR)
 
-#define UVH_RH_GAM_CONFIG_MMR_M_SKT_SHFT		0
 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT		6
-#define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK		0x000000000000003fUL
 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK		0x00000000000003c0UL
 
 #define UV1H_RH_GAM_CONFIG_MMR_M_SKT_SHFT		0
@@ -2298,9 +3211,7 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 #define UV1H_RH_GAM_CONFIG_MMR_N_SKT_MASK		0x00000000000003c0UL
 #define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK		0x0000000000001000UL
 
-#define UVXH_RH_GAM_CONFIG_MMR_M_SKT_SHFT		0
 #define UVXH_RH_GAM_CONFIG_MMR_N_SKT_SHFT		6
-#define UVXH_RH_GAM_CONFIG_MMR_M_SKT_MASK		0x000000000000003fUL
 #define UVXH_RH_GAM_CONFIG_MMR_N_SKT_MASK		0x00000000000003c0UL
 
 #define UV2H_RH_GAM_CONFIG_MMR_M_SKT_SHFT		0
@@ -2313,10 +3224,14 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 #define UV3H_RH_GAM_CONFIG_MMR_M_SKT_MASK		0x000000000000003fUL
 #define UV3H_RH_GAM_CONFIG_MMR_N_SKT_MASK		0x00000000000003c0UL
 
+#define UV4H_RH_GAM_CONFIG_MMR_N_SKT_SHFT		6
+#define UV4H_RH_GAM_CONFIG_MMR_N_SKT_MASK		0x00000000000003c0UL
+
+
 union uvh_rh_gam_config_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_config_mmr_s {
-		unsigned long	m_skt:6;			/* RW */
+		unsigned long	rsvd_0_5:6;
 		unsigned long	n_skt:4;			/* RW */
 		unsigned long	rsvd_10_63:54;
 	} s;
@@ -2328,7 +3243,7 @@ union uvh_rh_gam_config_mmr_u {
 		unsigned long	rsvd_13_63:51;
 	} s1;
 	struct uvxh_rh_gam_config_mmr_s {
-		unsigned long	m_skt:6;			/* RW */
+		unsigned long	rsvd_0_5:6;
 		unsigned long	n_skt:4;			/* RW */
 		unsigned long	rsvd_10_63:54;
 	} sx;
@@ -2342,20 +3257,28 @@ union uvh_rh_gam_config_mmr_u {
 		unsigned long	n_skt:4;			/* RW */
 		unsigned long	rsvd_10_63:54;
 	} s3;
+	struct uv4h_rh_gam_config_mmr_s {
+		unsigned long	rsvd_0_5:6;
+		unsigned long	n_skt:4;			/* RW */
+		unsigned long	rsvd_10_63:54;
+	} s4;
 };
 
 /* ========================================================================= */
 /*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
 #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
 #define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
 #define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x480010UL
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR)
 
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT	28
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT	52
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT	63
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK	0x00003ffff0000000UL
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK	0x00f0000000000000UL
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
 
@@ -2368,10 +3291,8 @@ union uvh_rh_gam_config_mmr_u {
 #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK	0x00f0000000000000UL
 #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
 
-#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT	28
 #define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT	52
 #define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT	63
-#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK	0x00003ffff0000000UL
 #define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK	0x00f0000000000000UL
 #define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
 
@@ -2391,12 +3312,28 @@ union uvh_rh_gam_config_mmr_u {
 #define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_MODE_MASK	0x4000000000000000UL
 #define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
 
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT	26
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT	52
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT	63
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK	0x00f0000000000000UL
+#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
+
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK (			\
+	is_uv1_hub() ? UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK :	\
+	is_uv2_hub() ? UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK :	\
+	is_uv3_hub() ? UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK)
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT (			\
+	is_uv1_hub() ? UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT :	\
+	is_uv2_hub() ? UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT :	\
+	is_uv3_hub() ? UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT)
+
 union uvh_rh_gam_gru_overlay_config_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_gru_overlay_config_mmr_s {
-		unsigned long	rsvd_0_27:28;
-		unsigned long	base:18;			/* RW */
-		unsigned long	rsvd_46_51:6;
+		unsigned long	rsvd_0_51:52;
 		unsigned long	n_gru:4;			/* RW */
 		unsigned long	rsvd_56_62:7;
 		unsigned long	enable:1;			/* RW */
@@ -2412,8 +3349,7 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 		unsigned long	enable:1;			/* RW */
 	} s1;
 	struct uvxh_rh_gam_gru_overlay_config_mmr_s {
-		unsigned long	rsvd_0_27:28;
-		unsigned long	base:18;			/* RW */
+		unsigned long	rsvd_0_45:46;
 		unsigned long	rsvd_46_51:6;
 		unsigned long	n_gru:4;			/* RW */
 		unsigned long	rsvd_56_62:7;
@@ -2436,6 +3372,15 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 		unsigned long	mode:1;				/* RW */
 		unsigned long	enable:1;			/* RW */
 	} s3;
+	struct uv4h_rh_gam_gru_overlay_config_mmr_s {
+		unsigned long	rsvd_0_24:25;
+		unsigned long	undef_25:1;			/* Undefined */
+		unsigned long	base:20;			/* RW */
+		unsigned long	rsvd_46_51:6;
+		unsigned long	n_gru:4;			/* RW */
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -2443,6 +3388,14 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 /* ========================================================================= */
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
 #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR uv_undefined("UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR")
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR uv_undefined("UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR")
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR)
+
 
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT	30
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT	46
@@ -2453,6 +3406,7 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK	0x00f0000000000000UL
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
+
 #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT	27
 #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT	46
 #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT	52
@@ -2462,6 +3416,7 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK	0x00f0000000000000UL
 #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
+
 union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 	unsigned long	v;
 	struct uv1h_rh_gam_mmioh_overlay_config_mmr_s {
@@ -2485,10 +3440,15 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 /* ========================================================================= */
 /*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
 #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
 #define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
 #define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
+#define UV4H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x480028UL
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMR_OVERLAY_CONFIG_MMR)
 
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT	26
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT	63
@@ -2517,6 +3477,12 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 #define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK	0x00003ffffc000000UL
 #define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
 
+#define UV4H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT	26
+#define UV4H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT	63
+#define UV4H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK	0x8000000000000000UL
+
+
 union uvh_rh_gam_mmr_overlay_config_mmr_u {
 	unsigned long	v;
 	struct uvh_rh_gam_mmr_overlay_config_mmr_s {
@@ -2550,16 +3516,31 @@ union uvh_rh_gam_mmr_overlay_config_mmr_u {
 		unsigned long	rsvd_46_62:17;
 		unsigned long	enable:1;			/* RW */
 	} s3;
+	struct uv4h_rh_gam_mmr_overlay_config_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	rsvd_46_62:17;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
 /*                                 UVH_RTC                                   */
 /* ========================================================================= */
-#define UVH_RTC 0x340000UL
+#define UV1H_RTC 0x340000UL
+#define UV2H_RTC 0x340000UL
+#define UV3H_RTC 0x340000UL
+#define UV4H_RTC 0xe0000UL
+#define UVH_RTC (							\
+	is_uv1_hub() ? UV1H_RTC :					\
+	is_uv2_hub() ? UV2H_RTC :					\
+	is_uv3_hub() ? UV3H_RTC :					\
+	/*is_uv4_hub*/ UV4H_RTC)
 
 #define UVH_RTC_REAL_TIME_CLOCK_SHFT			0
 #define UVH_RTC_REAL_TIME_CLOCK_MASK			0x00ffffffffffffffUL
 
+
 union uvh_rtc_u {
 	unsigned long	v;
 	struct uvh_rtc_s {
@@ -2590,6 +3571,7 @@ union uvh_rtc_u {
 #define UVH_RTC1_INT_CONFIG_M_MASK			0x0000000000010000UL
 #define UVH_RTC1_INT_CONFIG_APIC_ID_MASK		0xffffffff00000000UL
 
+
 union uvh_rtc1_int_config_u {
 	unsigned long	v;
 	struct uvh_rtc1_int_config_s {
@@ -2609,12 +3591,30 @@ union uvh_rtc1_int_config_u {
 /* ========================================================================= */
 /*                               UVH_SCRATCH5                                */
 /* ========================================================================= */
-#define UVH_SCRATCH5 0x2d0200UL
-#define UVH_SCRATCH5_32 0x778
+#define UV1H_SCRATCH5 0x2d0200UL
+#define UV2H_SCRATCH5 0x2d0200UL
+#define UV3H_SCRATCH5 0x2d0200UL
+#define UV4H_SCRATCH5 0xb0200UL
+#define UVH_SCRATCH5 (							\
+	is_uv1_hub() ? UV1H_SCRATCH5 :					\
+	is_uv2_hub() ? UV2H_SCRATCH5 :					\
+	is_uv3_hub() ? UV3H_SCRATCH5 :					\
+	/*is_uv4_hub*/ UV4H_SCRATCH5)
+
+#define UV1H_SCRATCH5_32 0x778
+#define UV2H_SCRATCH5_32 0x778
+#define UV3H_SCRATCH5_32 0x778
+#define UV4H_SCRATCH5_32 0x798
+#define UVH_SCRATCH5_32 (						\
+	is_uv1_hub() ? UV1H_SCRATCH5_32 :				\
+	is_uv2_hub() ? UV2H_SCRATCH5_32 :				\
+	is_uv3_hub() ? UV3H_SCRATCH5_32 :				\
+	/*is_uv4_hub*/ UV4H_SCRATCH5_32)
 
 #define UVH_SCRATCH5_SCRATCH5_SHFT			0
 #define UVH_SCRATCH5_SCRATCH5_MASK			0xffffffffffffffffUL
 
+
 union uvh_scratch5_u {
 	unsigned long	v;
 	struct uvh_scratch5_s {
@@ -2625,14 +3625,39 @@ union uvh_scratch5_u {
 /* ========================================================================= */
 /*                            UVH_SCRATCH5_ALIAS                             */
 /* ========================================================================= */
-#define UVH_SCRATCH5_ALIAS 0x2d0208UL
-#define UVH_SCRATCH5_ALIAS_32 0x780
+#define UV1H_SCRATCH5_ALIAS 0x2d0208UL
+#define UV2H_SCRATCH5_ALIAS 0x2d0208UL
+#define UV3H_SCRATCH5_ALIAS 0x2d0208UL
+#define UV4H_SCRATCH5_ALIAS 0xb0208UL
+#define UVH_SCRATCH5_ALIAS (						\
+	is_uv1_hub() ? UV1H_SCRATCH5_ALIAS :				\
+	is_uv2_hub() ? UV2H_SCRATCH5_ALIAS :				\
+	is_uv3_hub() ? UV3H_SCRATCH5_ALIAS :				\
+	/*is_uv4_hub*/ UV4H_SCRATCH5_ALIAS)
+
+#define UV1H_SCRATCH5_ALIAS_32 0x780
+#define UV2H_SCRATCH5_ALIAS_32 0x780
+#define UV3H_SCRATCH5_ALIAS_32 0x780
+#define UV4H_SCRATCH5_ALIAS_32 0x7a0
+#define UVH_SCRATCH5_ALIAS_32 (						\
+	is_uv1_hub() ? UV1H_SCRATCH5_ALIAS_32 :				\
+	is_uv2_hub() ? UV2H_SCRATCH5_ALIAS_32 :				\
+	is_uv3_hub() ? UV3H_SCRATCH5_ALIAS_32 :				\
+	/*is_uv4_hub*/ UV4H_SCRATCH5_ALIAS_32)
 
 
 /* ========================================================================= */
 /*                           UVH_SCRATCH5_ALIAS_2                            */
 /* ========================================================================= */
-#define UVH_SCRATCH5_ALIAS_2 0x2d0210UL
+#define UV1H_SCRATCH5_ALIAS_2 0x2d0210UL
+#define UV2H_SCRATCH5_ALIAS_2 0x2d0210UL
+#define UV3H_SCRATCH5_ALIAS_2 0x2d0210UL
+#define UV4H_SCRATCH5_ALIAS_2 0xb0210UL
+#define UVH_SCRATCH5_ALIAS_2 (						\
+	is_uv1_hub() ? UV1H_SCRATCH5_ALIAS_2 :				\
+	is_uv2_hub() ? UV2H_SCRATCH5_ALIAS_2 :				\
+	is_uv3_hub() ? UV3H_SCRATCH5_ALIAS_2 :				\
+	/*is_uv4_hub*/ UV4H_SCRATCH5_ALIAS_2)
 #define UVH_SCRATCH5_ALIAS_2_32 0x788
 
 
@@ -2640,76 +3665,255 @@ union uvh_scratch5_u {
 /*                          UVXH_EVENT_OCCURRED2                             */
 /* ========================================================================= */
 #define UVXH_EVENT_OCCURRED2 0x70100UL
-#define UVXH_EVENT_OCCURRED2_32 0xb68
-
-#define UVXH_EVENT_OCCURRED2_RTC_0_SHFT			0
-#define UVXH_EVENT_OCCURRED2_RTC_1_SHFT			1
-#define UVXH_EVENT_OCCURRED2_RTC_2_SHFT			2
-#define UVXH_EVENT_OCCURRED2_RTC_3_SHFT			3
-#define UVXH_EVENT_OCCURRED2_RTC_4_SHFT			4
-#define UVXH_EVENT_OCCURRED2_RTC_5_SHFT			5
-#define UVXH_EVENT_OCCURRED2_RTC_6_SHFT			6
-#define UVXH_EVENT_OCCURRED2_RTC_7_SHFT			7
-#define UVXH_EVENT_OCCURRED2_RTC_8_SHFT			8
-#define UVXH_EVENT_OCCURRED2_RTC_9_SHFT			9
-#define UVXH_EVENT_OCCURRED2_RTC_10_SHFT		10
-#define UVXH_EVENT_OCCURRED2_RTC_11_SHFT		11
-#define UVXH_EVENT_OCCURRED2_RTC_12_SHFT		12
-#define UVXH_EVENT_OCCURRED2_RTC_13_SHFT		13
-#define UVXH_EVENT_OCCURRED2_RTC_14_SHFT		14
-#define UVXH_EVENT_OCCURRED2_RTC_15_SHFT		15
-#define UVXH_EVENT_OCCURRED2_RTC_16_SHFT		16
-#define UVXH_EVENT_OCCURRED2_RTC_17_SHFT		17
-#define UVXH_EVENT_OCCURRED2_RTC_18_SHFT		18
-#define UVXH_EVENT_OCCURRED2_RTC_19_SHFT		19
-#define UVXH_EVENT_OCCURRED2_RTC_20_SHFT		20
-#define UVXH_EVENT_OCCURRED2_RTC_21_SHFT		21
-#define UVXH_EVENT_OCCURRED2_RTC_22_SHFT		22
-#define UVXH_EVENT_OCCURRED2_RTC_23_SHFT		23
-#define UVXH_EVENT_OCCURRED2_RTC_24_SHFT		24
-#define UVXH_EVENT_OCCURRED2_RTC_25_SHFT		25
-#define UVXH_EVENT_OCCURRED2_RTC_26_SHFT		26
-#define UVXH_EVENT_OCCURRED2_RTC_27_SHFT		27
-#define UVXH_EVENT_OCCURRED2_RTC_28_SHFT		28
-#define UVXH_EVENT_OCCURRED2_RTC_29_SHFT		29
-#define UVXH_EVENT_OCCURRED2_RTC_30_SHFT		30
-#define UVXH_EVENT_OCCURRED2_RTC_31_SHFT		31
-#define UVXH_EVENT_OCCURRED2_RTC_0_MASK			0x0000000000000001UL
-#define UVXH_EVENT_OCCURRED2_RTC_1_MASK			0x0000000000000002UL
-#define UVXH_EVENT_OCCURRED2_RTC_2_MASK			0x0000000000000004UL
-#define UVXH_EVENT_OCCURRED2_RTC_3_MASK			0x0000000000000008UL
-#define UVXH_EVENT_OCCURRED2_RTC_4_MASK			0x0000000000000010UL
-#define UVXH_EVENT_OCCURRED2_RTC_5_MASK			0x0000000000000020UL
-#define UVXH_EVENT_OCCURRED2_RTC_6_MASK			0x0000000000000040UL
-#define UVXH_EVENT_OCCURRED2_RTC_7_MASK			0x0000000000000080UL
-#define UVXH_EVENT_OCCURRED2_RTC_8_MASK			0x0000000000000100UL
-#define UVXH_EVENT_OCCURRED2_RTC_9_MASK			0x0000000000000200UL
-#define UVXH_EVENT_OCCURRED2_RTC_10_MASK		0x0000000000000400UL
-#define UVXH_EVENT_OCCURRED2_RTC_11_MASK		0x0000000000000800UL
-#define UVXH_EVENT_OCCURRED2_RTC_12_MASK		0x0000000000001000UL
-#define UVXH_EVENT_OCCURRED2_RTC_13_MASK		0x0000000000002000UL
-#define UVXH_EVENT_OCCURRED2_RTC_14_MASK		0x0000000000004000UL
-#define UVXH_EVENT_OCCURRED2_RTC_15_MASK		0x0000000000008000UL
-#define UVXH_EVENT_OCCURRED2_RTC_16_MASK		0x0000000000010000UL
-#define UVXH_EVENT_OCCURRED2_RTC_17_MASK		0x0000000000020000UL
-#define UVXH_EVENT_OCCURRED2_RTC_18_MASK		0x0000000000040000UL
-#define UVXH_EVENT_OCCURRED2_RTC_19_MASK		0x0000000000080000UL
-#define UVXH_EVENT_OCCURRED2_RTC_20_MASK		0x0000000000100000UL
-#define UVXH_EVENT_OCCURRED2_RTC_21_MASK		0x0000000000200000UL
-#define UVXH_EVENT_OCCURRED2_RTC_22_MASK		0x0000000000400000UL
-#define UVXH_EVENT_OCCURRED2_RTC_23_MASK		0x0000000000800000UL
-#define UVXH_EVENT_OCCURRED2_RTC_24_MASK		0x0000000001000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_25_MASK		0x0000000002000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_26_MASK		0x0000000004000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_27_MASK		0x0000000008000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_28_MASK		0x0000000010000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_29_MASK		0x0000000020000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_30_MASK		0x0000000040000000UL
-#define UVXH_EVENT_OCCURRED2_RTC_31_MASK		0x0000000080000000UL
-
-union uvxh_event_occurred2_u {
+
+#define UV2H_EVENT_OCCURRED2_32 0xb68
+#define UV3H_EVENT_OCCURRED2_32 0xb68
+#define UV4H_EVENT_OCCURRED2_32 0x608
+#define UVH_EVENT_OCCURRED2_32 (					\
+	is_uv2_hub() ? UV2H_EVENT_OCCURRED2_32 :			\
+	is_uv3_hub() ? UV3H_EVENT_OCCURRED2_32 :			\
+	/*is_uv4_hub*/ UV4H_EVENT_OCCURRED2_32)
+
+
+#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT			0
+#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT			1
+#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT			2
+#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT			3
+#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT			4
+#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT			5
+#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT			6
+#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT			7
+#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT			8
+#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT			9
+#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT		10
+#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT		11
+#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT		12
+#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT		13
+#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT		14
+#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT		15
+#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT		16
+#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT		17
+#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT		18
+#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT		19
+#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT		20
+#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT		21
+#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT		22
+#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT		23
+#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT		24
+#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT		25
+#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT		26
+#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT		27
+#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT		28
+#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT		29
+#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT		30
+#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT		31
+#define UV2H_EVENT_OCCURRED2_RTC_0_MASK			0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED2_RTC_1_MASK			0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED2_RTC_2_MASK			0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED2_RTC_3_MASK			0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED2_RTC_4_MASK			0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED2_RTC_5_MASK			0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED2_RTC_6_MASK			0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED2_RTC_7_MASK			0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED2_RTC_8_MASK			0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED2_RTC_9_MASK			0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED2_RTC_10_MASK		0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED2_RTC_11_MASK		0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED2_RTC_12_MASK		0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED2_RTC_13_MASK		0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED2_RTC_14_MASK		0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED2_RTC_15_MASK		0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED2_RTC_16_MASK		0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED2_RTC_17_MASK		0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED2_RTC_18_MASK		0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED2_RTC_19_MASK		0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED2_RTC_20_MASK		0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED2_RTC_21_MASK		0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED2_RTC_22_MASK		0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED2_RTC_23_MASK		0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED2_RTC_24_MASK		0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_25_MASK		0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_26_MASK		0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_27_MASK		0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_28_MASK		0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_29_MASK		0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_30_MASK		0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_31_MASK		0x0000000080000000UL
+
+#define UV3H_EVENT_OCCURRED2_RTC_0_SHFT			0
+#define UV3H_EVENT_OCCURRED2_RTC_1_SHFT			1
+#define UV3H_EVENT_OCCURRED2_RTC_2_SHFT			2
+#define UV3H_EVENT_OCCURRED2_RTC_3_SHFT			3
+#define UV3H_EVENT_OCCURRED2_RTC_4_SHFT			4
+#define UV3H_EVENT_OCCURRED2_RTC_5_SHFT			5
+#define UV3H_EVENT_OCCURRED2_RTC_6_SHFT			6
+#define UV3H_EVENT_OCCURRED2_RTC_7_SHFT			7
+#define UV3H_EVENT_OCCURRED2_RTC_8_SHFT			8
+#define UV3H_EVENT_OCCURRED2_RTC_9_SHFT			9
+#define UV3H_EVENT_OCCURRED2_RTC_10_SHFT		10
+#define UV3H_EVENT_OCCURRED2_RTC_11_SHFT		11
+#define UV3H_EVENT_OCCURRED2_RTC_12_SHFT		12
+#define UV3H_EVENT_OCCURRED2_RTC_13_SHFT		13
+#define UV3H_EVENT_OCCURRED2_RTC_14_SHFT		14
+#define UV3H_EVENT_OCCURRED2_RTC_15_SHFT		15
+#define UV3H_EVENT_OCCURRED2_RTC_16_SHFT		16
+#define UV3H_EVENT_OCCURRED2_RTC_17_SHFT		17
+#define UV3H_EVENT_OCCURRED2_RTC_18_SHFT		18
+#define UV3H_EVENT_OCCURRED2_RTC_19_SHFT		19
+#define UV3H_EVENT_OCCURRED2_RTC_20_SHFT		20
+#define UV3H_EVENT_OCCURRED2_RTC_21_SHFT		21
+#define UV3H_EVENT_OCCURRED2_RTC_22_SHFT		22
+#define UV3H_EVENT_OCCURRED2_RTC_23_SHFT		23
+#define UV3H_EVENT_OCCURRED2_RTC_24_SHFT		24
+#define UV3H_EVENT_OCCURRED2_RTC_25_SHFT		25
+#define UV3H_EVENT_OCCURRED2_RTC_26_SHFT		26
+#define UV3H_EVENT_OCCURRED2_RTC_27_SHFT		27
+#define UV3H_EVENT_OCCURRED2_RTC_28_SHFT		28
+#define UV3H_EVENT_OCCURRED2_RTC_29_SHFT		29
+#define UV3H_EVENT_OCCURRED2_RTC_30_SHFT		30
+#define UV3H_EVENT_OCCURRED2_RTC_31_SHFT		31
+#define UV3H_EVENT_OCCURRED2_RTC_0_MASK			0x0000000000000001UL
+#define UV3H_EVENT_OCCURRED2_RTC_1_MASK			0x0000000000000002UL
+#define UV3H_EVENT_OCCURRED2_RTC_2_MASK			0x0000000000000004UL
+#define UV3H_EVENT_OCCURRED2_RTC_3_MASK			0x0000000000000008UL
+#define UV3H_EVENT_OCCURRED2_RTC_4_MASK			0x0000000000000010UL
+#define UV3H_EVENT_OCCURRED2_RTC_5_MASK			0x0000000000000020UL
+#define UV3H_EVENT_OCCURRED2_RTC_6_MASK			0x0000000000000040UL
+#define UV3H_EVENT_OCCURRED2_RTC_7_MASK			0x0000000000000080UL
+#define UV3H_EVENT_OCCURRED2_RTC_8_MASK			0x0000000000000100UL
+#define UV3H_EVENT_OCCURRED2_RTC_9_MASK			0x0000000000000200UL
+#define UV3H_EVENT_OCCURRED2_RTC_10_MASK		0x0000000000000400UL
+#define UV3H_EVENT_OCCURRED2_RTC_11_MASK		0x0000000000000800UL
+#define UV3H_EVENT_OCCURRED2_RTC_12_MASK		0x0000000000001000UL
+#define UV3H_EVENT_OCCURRED2_RTC_13_MASK		0x0000000000002000UL
+#define UV3H_EVENT_OCCURRED2_RTC_14_MASK		0x0000000000004000UL
+#define UV3H_EVENT_OCCURRED2_RTC_15_MASK		0x0000000000008000UL
+#define UV3H_EVENT_OCCURRED2_RTC_16_MASK		0x0000000000010000UL
+#define UV3H_EVENT_OCCURRED2_RTC_17_MASK		0x0000000000020000UL
+#define UV3H_EVENT_OCCURRED2_RTC_18_MASK		0x0000000000040000UL
+#define UV3H_EVENT_OCCURRED2_RTC_19_MASK		0x0000000000080000UL
+#define UV3H_EVENT_OCCURRED2_RTC_20_MASK		0x0000000000100000UL
+#define UV3H_EVENT_OCCURRED2_RTC_21_MASK		0x0000000000200000UL
+#define UV3H_EVENT_OCCURRED2_RTC_22_MASK		0x0000000000400000UL
+#define UV3H_EVENT_OCCURRED2_RTC_23_MASK		0x0000000000800000UL
+#define UV3H_EVENT_OCCURRED2_RTC_24_MASK		0x0000000001000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_25_MASK		0x0000000002000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_26_MASK		0x0000000004000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_27_MASK		0x0000000008000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_28_MASK		0x0000000010000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_29_MASK		0x0000000020000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_30_MASK		0x0000000040000000UL
+#define UV3H_EVENT_OCCURRED2_RTC_31_MASK		0x0000000080000000UL
+
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT0_SHFT 0
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT1_SHFT 1
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT2_SHFT 2
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT3_SHFT 3
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT4_SHFT 4
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT5_SHFT 5
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT6_SHFT 6
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT7_SHFT 7
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT8_SHFT 8
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT9_SHFT 9
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT10_SHFT 10
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT11_SHFT 11
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT12_SHFT 12
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT13_SHFT 13
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT14_SHFT 14
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT15_SHFT 15
+#define UV4H_EVENT_OCCURRED2_RTC_INTERVAL_INT_SHFT	16
+#define UV4H_EVENT_OCCURRED2_BAU_DASHBOARD_INT_SHFT	17
+#define UV4H_EVENT_OCCURRED2_RTC_0_SHFT			18
+#define UV4H_EVENT_OCCURRED2_RTC_1_SHFT			19
+#define UV4H_EVENT_OCCURRED2_RTC_2_SHFT			20
+#define UV4H_EVENT_OCCURRED2_RTC_3_SHFT			21
+#define UV4H_EVENT_OCCURRED2_RTC_4_SHFT			22
+#define UV4H_EVENT_OCCURRED2_RTC_5_SHFT			23
+#define UV4H_EVENT_OCCURRED2_RTC_6_SHFT			24
+#define UV4H_EVENT_OCCURRED2_RTC_7_SHFT			25
+#define UV4H_EVENT_OCCURRED2_RTC_8_SHFT			26
+#define UV4H_EVENT_OCCURRED2_RTC_9_SHFT			27
+#define UV4H_EVENT_OCCURRED2_RTC_10_SHFT		28
+#define UV4H_EVENT_OCCURRED2_RTC_11_SHFT		29
+#define UV4H_EVENT_OCCURRED2_RTC_12_SHFT		30
+#define UV4H_EVENT_OCCURRED2_RTC_13_SHFT		31
+#define UV4H_EVENT_OCCURRED2_RTC_14_SHFT		32
+#define UV4H_EVENT_OCCURRED2_RTC_15_SHFT		33
+#define UV4H_EVENT_OCCURRED2_RTC_16_SHFT		34
+#define UV4H_EVENT_OCCURRED2_RTC_17_SHFT		35
+#define UV4H_EVENT_OCCURRED2_RTC_18_SHFT		36
+#define UV4H_EVENT_OCCURRED2_RTC_19_SHFT		37
+#define UV4H_EVENT_OCCURRED2_RTC_20_SHFT		38
+#define UV4H_EVENT_OCCURRED2_RTC_21_SHFT		39
+#define UV4H_EVENT_OCCURRED2_RTC_22_SHFT		40
+#define UV4H_EVENT_OCCURRED2_RTC_23_SHFT		41
+#define UV4H_EVENT_OCCURRED2_RTC_24_SHFT		42
+#define UV4H_EVENT_OCCURRED2_RTC_25_SHFT		43
+#define UV4H_EVENT_OCCURRED2_RTC_26_SHFT		44
+#define UV4H_EVENT_OCCURRED2_RTC_27_SHFT		45
+#define UV4H_EVENT_OCCURRED2_RTC_28_SHFT		46
+#define UV4H_EVENT_OCCURRED2_RTC_29_SHFT		47
+#define UV4H_EVENT_OCCURRED2_RTC_30_SHFT		48
+#define UV4H_EVENT_OCCURRED2_RTC_31_SHFT		49
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT0_MASK 0x0000000000000001UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT1_MASK 0x0000000000000002UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT2_MASK 0x0000000000000004UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT3_MASK 0x0000000000000008UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT4_MASK 0x0000000000000010UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT5_MASK 0x0000000000000020UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT6_MASK 0x0000000000000040UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT7_MASK 0x0000000000000080UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT8_MASK 0x0000000000000100UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT9_MASK 0x0000000000000200UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT10_MASK 0x0000000000000400UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT11_MASK 0x0000000000000800UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT12_MASK 0x0000000000001000UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT13_MASK 0x0000000000002000UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT14_MASK 0x0000000000004000UL
+#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT15_MASK 0x0000000000008000UL
+#define UV4H_EVENT_OCCURRED2_RTC_INTERVAL_INT_MASK	0x0000000000010000UL
+#define UV4H_EVENT_OCCURRED2_BAU_DASHBOARD_INT_MASK	0x0000000000020000UL
+#define UV4H_EVENT_OCCURRED2_RTC_0_MASK			0x0000000000040000UL
+#define UV4H_EVENT_OCCURRED2_RTC_1_MASK			0x0000000000080000UL
+#define UV4H_EVENT_OCCURRED2_RTC_2_MASK			0x0000000000100000UL
+#define UV4H_EVENT_OCCURRED2_RTC_3_MASK			0x0000000000200000UL
+#define UV4H_EVENT_OCCURRED2_RTC_4_MASK			0x0000000000400000UL
+#define UV4H_EVENT_OCCURRED2_RTC_5_MASK			0x0000000000800000UL
+#define UV4H_EVENT_OCCURRED2_RTC_6_MASK			0x0000000001000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_7_MASK			0x0000000002000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_8_MASK			0x0000000004000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_9_MASK			0x0000000008000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_10_MASK		0x0000000010000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_11_MASK		0x0000000020000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_12_MASK		0x0000000040000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_13_MASK		0x0000000080000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_14_MASK		0x0000000100000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_15_MASK		0x0000000200000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_16_MASK		0x0000000400000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_17_MASK		0x0000000800000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_18_MASK		0x0000001000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_19_MASK		0x0000002000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_20_MASK		0x0000004000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_21_MASK		0x0000008000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_22_MASK		0x0000010000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_23_MASK		0x0000020000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_24_MASK		0x0000040000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_25_MASK		0x0000080000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_26_MASK		0x0000100000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_27_MASK		0x0000200000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_28_MASK		0x0000400000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_29_MASK		0x0000800000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_30_MASK		0x0001000000000000UL
+#define UV4H_EVENT_OCCURRED2_RTC_31_MASK		0x0002000000000000UL
+
+#define UVXH_EVENT_OCCURRED2_RTC_1_MASK (				\
+	is_uv2_hub() ? UV2H_EVENT_OCCURRED2_RTC_1_MASK :		\
+	is_uv3_hub() ? UV3H_EVENT_OCCURRED2_RTC_1_MASK :		\
+	/*is_uv4_hub*/ UV4H_EVENT_OCCURRED2_RTC_1_MASK)
+
+union uvh_event_occurred2_u {
 	unsigned long	v;
-	struct uvxh_event_occurred2_s {
+	struct uv2h_event_occurred2_s {
 		unsigned long	rtc_0:1;			/* RW */
 		unsigned long	rtc_1:1;			/* RW */
 		unsigned long	rtc_2:1;			/* RW */
@@ -2743,25 +3947,129 @@ union uvxh_event_occurred2_u {
 		unsigned long	rtc_30:1;			/* RW */
 		unsigned long	rtc_31:1;			/* RW */
 		unsigned long	rsvd_32_63:32;
-	} sx;
+	} s2;
+	struct uv3h_event_occurred2_s {
+		unsigned long	rtc_0:1;			/* RW */
+		unsigned long	rtc_1:1;			/* RW */
+		unsigned long	rtc_2:1;			/* RW */
+		unsigned long	rtc_3:1;			/* RW */
+		unsigned long	rtc_4:1;			/* RW */
+		unsigned long	rtc_5:1;			/* RW */
+		unsigned long	rtc_6:1;			/* RW */
+		unsigned long	rtc_7:1;			/* RW */
+		unsigned long	rtc_8:1;			/* RW */
+		unsigned long	rtc_9:1;			/* RW */
+		unsigned long	rtc_10:1;			/* RW */
+		unsigned long	rtc_11:1;			/* RW */
+		unsigned long	rtc_12:1;			/* RW */
+		unsigned long	rtc_13:1;			/* RW */
+		unsigned long	rtc_14:1;			/* RW */
+		unsigned long	rtc_15:1;			/* RW */
+		unsigned long	rtc_16:1;			/* RW */
+		unsigned long	rtc_17:1;			/* RW */
+		unsigned long	rtc_18:1;			/* RW */
+		unsigned long	rtc_19:1;			/* RW */
+		unsigned long	rtc_20:1;			/* RW */
+		unsigned long	rtc_21:1;			/* RW */
+		unsigned long	rtc_22:1;			/* RW */
+		unsigned long	rtc_23:1;			/* RW */
+		unsigned long	rtc_24:1;			/* RW */
+		unsigned long	rtc_25:1;			/* RW */
+		unsigned long	rtc_26:1;			/* RW */
+		unsigned long	rtc_27:1;			/* RW */
+		unsigned long	rtc_28:1;			/* RW */
+		unsigned long	rtc_29:1;			/* RW */
+		unsigned long	rtc_30:1;			/* RW */
+		unsigned long	rtc_31:1;			/* RW */
+		unsigned long	rsvd_32_63:32;
+	} s3;
+	struct uv4h_event_occurred2_s {
+		unsigned long	message_accelerator_int0:1;	/* RW */
+		unsigned long	message_accelerator_int1:1;	/* RW */
+		unsigned long	message_accelerator_int2:1;	/* RW */
+		unsigned long	message_accelerator_int3:1;	/* RW */
+		unsigned long	message_accelerator_int4:1;	/* RW */
+		unsigned long	message_accelerator_int5:1;	/* RW */
+		unsigned long	message_accelerator_int6:1;	/* RW */
+		unsigned long	message_accelerator_int7:1;	/* RW */
+		unsigned long	message_accelerator_int8:1;	/* RW */
+		unsigned long	message_accelerator_int9:1;	/* RW */
+		unsigned long	message_accelerator_int10:1;	/* RW */
+		unsigned long	message_accelerator_int11:1;	/* RW */
+		unsigned long	message_accelerator_int12:1;	/* RW */
+		unsigned long	message_accelerator_int13:1;	/* RW */
+		unsigned long	message_accelerator_int14:1;	/* RW */
+		unsigned long	message_accelerator_int15:1;	/* RW */
+		unsigned long	rtc_interval_int:1;		/* RW */
+		unsigned long	bau_dashboard_int:1;		/* RW */
+		unsigned long	rtc_0:1;			/* RW */
+		unsigned long	rtc_1:1;			/* RW */
+		unsigned long	rtc_2:1;			/* RW */
+		unsigned long	rtc_3:1;			/* RW */
+		unsigned long	rtc_4:1;			/* RW */
+		unsigned long	rtc_5:1;			/* RW */
+		unsigned long	rtc_6:1;			/* RW */
+		unsigned long	rtc_7:1;			/* RW */
+		unsigned long	rtc_8:1;			/* RW */
+		unsigned long	rtc_9:1;			/* RW */
+		unsigned long	rtc_10:1;			/* RW */
+		unsigned long	rtc_11:1;			/* RW */
+		unsigned long	rtc_12:1;			/* RW */
+		unsigned long	rtc_13:1;			/* RW */
+		unsigned long	rtc_14:1;			/* RW */
+		unsigned long	rtc_15:1;			/* RW */
+		unsigned long	rtc_16:1;			/* RW */
+		unsigned long	rtc_17:1;			/* RW */
+		unsigned long	rtc_18:1;			/* RW */
+		unsigned long	rtc_19:1;			/* RW */
+		unsigned long	rtc_20:1;			/* RW */
+		unsigned long	rtc_21:1;			/* RW */
+		unsigned long	rtc_22:1;			/* RW */
+		unsigned long	rtc_23:1;			/* RW */
+		unsigned long	rtc_24:1;			/* RW */
+		unsigned long	rtc_25:1;			/* RW */
+		unsigned long	rtc_26:1;			/* RW */
+		unsigned long	rtc_27:1;			/* RW */
+		unsigned long	rtc_28:1;			/* RW */
+		unsigned long	rtc_29:1;			/* RW */
+		unsigned long	rtc_30:1;			/* RW */
+		unsigned long	rtc_31:1;			/* RW */
+		unsigned long	rsvd_50_63:14;
+	} s4;
 };
 
 /* ========================================================================= */
 /*                       UVXH_EVENT_OCCURRED2_ALIAS                          */
 /* ========================================================================= */
 #define UVXH_EVENT_OCCURRED2_ALIAS 0x70108UL
-#define UVXH_EVENT_OCCURRED2_ALIAS_32 0xb70
+
+#define UV2H_EVENT_OCCURRED2_ALIAS_32 0xb70
+#define UV3H_EVENT_OCCURRED2_ALIAS_32 0xb70
+#define UV4H_EVENT_OCCURRED2_ALIAS_32 0x610
+#define UVH_EVENT_OCCURRED2_ALIAS_32 (					\
+	is_uv2_hub() ? UV2H_EVENT_OCCURRED2_ALIAS_32 :			\
+	is_uv3_hub() ? UV3H_EVENT_OCCURRED2_ALIAS_32 :			\
+	/*is_uv4_hub*/ UV4H_EVENT_OCCURRED2_ALIAS_32)
 
 
 /* ========================================================================= */
 /*                   UVXH_LB_BAU_SB_ACTIVATION_STATUS_2                      */
 /* ========================================================================= */
-#define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL
 #define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL
 #define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL
-#define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0
-#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x320130UL
-#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x320130UL
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_2 0xc8130UL
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_2 (				\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_STATUS_2 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_STATUS_2)
+
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0
+#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0xa10
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_2_32 (				\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 :		\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_32 :		\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_ACTIVATION_STATUS_2_32)
 
 #define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0
 #define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL
@@ -2772,6 +4080,10 @@ union uvxh_event_occurred2_u {
 #define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0
 #define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL
 
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0
+#define UV4H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL
+
+
 union uvxh_lb_bau_sb_activation_status_2_u {
 	unsigned long	v;
 	struct uvxh_lb_bau_sb_activation_status_2_s {
@@ -2783,6 +4095,9 @@ union uvxh_lb_bau_sb_activation_status_2_u {
 	struct uv3h_lb_bau_sb_activation_status_2_s {
 		unsigned long	aux_error:64;			/* RW */
 	} s3;
+	struct uv4h_lb_bau_sb_activation_status_2_s {
+		unsigned long	aux_error:64;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -2823,26 +4138,6 @@ union uv3h_gr0_gam_gr_config_u {
 };
 
 /* ========================================================================= */
-/*                          UV3H_GR1_GAM_GR_CONFIG                           */
-/* ========================================================================= */
-#define UV3H_GR1_GAM_GR_CONFIG				0x1000028UL
-
-#define UV3H_GR1_GAM_GR_CONFIG_M_SKT_SHFT		0
-#define UV3H_GR1_GAM_GR_CONFIG_SUBSPACE_SHFT		10
-#define UV3H_GR1_GAM_GR_CONFIG_M_SKT_MASK		0x000000000000003fUL
-#define UV3H_GR1_GAM_GR_CONFIG_SUBSPACE_MASK		0x0000000000000400UL
-
-union uv3h_gr1_gam_gr_config_u {
-	unsigned long	v;
-	struct uv3h_gr1_gam_gr_config_s {
-		unsigned long	m_skt:6;			/* RW */
-		unsigned long	undef_6_9:4;			/* Undefined */
-		unsigned long	subspace:1;			/* RW */
-		unsigned long	reserved:53;
-	} s3;
-};
-
-/* ========================================================================= */
 /*                   UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR                   */
 /* ========================================================================= */
 #define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR		0x1603000UL
@@ -2924,5 +4219,67 @@ union uv3h_rh_gam_mmioh_redirect_config1_mmr_u {
 	} s3;
 };
 
+/* ========================================================================= */
+/*                       UV4H_LB_PROC_INTD_QUEUE_FIRST                       */
+/* ========================================================================= */
+#define UV4H_LB_PROC_INTD_QUEUE_FIRST			0xa4100UL
+
+#define UV4H_LB_PROC_INTD_QUEUE_FIRST_FIRST_PAYLOAD_ADDRESS_SHFT 6
+#define UV4H_LB_PROC_INTD_QUEUE_FIRST_FIRST_PAYLOAD_ADDRESS_MASK 0x00003fffffffffc0UL
+
+union uv4h_lb_proc_intd_queue_first_u {
+	unsigned long	v;
+	struct uv4h_lb_proc_intd_queue_first_s {
+		unsigned long	undef_0_5:6;			/* Undefined */
+		unsigned long	first_payload_address:40;	/* RW */
+	} s4;
+};
+
+/* ========================================================================= */
+/*                       UV4H_LB_PROC_INTD_QUEUE_LAST                        */
+/* ========================================================================= */
+#define UV4H_LB_PROC_INTD_QUEUE_LAST			0xa4108UL
+
+#define UV4H_LB_PROC_INTD_QUEUE_LAST_LAST_PAYLOAD_ADDRESS_SHFT 5
+#define UV4H_LB_PROC_INTD_QUEUE_LAST_LAST_PAYLOAD_ADDRESS_MASK 0x00003fffffffffe0UL
+
+union uv4h_lb_proc_intd_queue_last_u {
+	unsigned long	v;
+	struct uv4h_lb_proc_intd_queue_last_s {
+		unsigned long	undef_0_4:5;			/* Undefined */
+		unsigned long	last_payload_address:41;	/* RW */
+	} s4;
+};
+
+/* ========================================================================= */
+/*                     UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR                      */
+/* ========================================================================= */
+#define UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR		0xa4118UL
+
+#define UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR_SOFT_ACK_PENDING_FLAGS_SHFT 0
+#define UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR_SOFT_ACK_PENDING_FLAGS_MASK 0x00000000000000ffUL
+
+union uv4h_lb_proc_intd_soft_ack_clear_u {
+	unsigned long	v;
+	struct uv4h_lb_proc_intd_soft_ack_clear_s {
+		unsigned long	soft_ack_pending_flags:8;	/* WP */
+	} s4;
+};
+
+/* ========================================================================= */
+/*                    UV4H_LB_PROC_INTD_SOFT_ACK_PENDING                     */
+/* ========================================================================= */
+#define UV4H_LB_PROC_INTD_SOFT_ACK_PENDING		0xa4110UL
+
+#define UV4H_LB_PROC_INTD_SOFT_ACK_PENDING_SOFT_ACK_FLAGS_SHFT 0
+#define UV4H_LB_PROC_INTD_SOFT_ACK_PENDING_SOFT_ACK_FLAGS_MASK 0x00000000000000ffUL
+
+union uv4h_lb_proc_intd_soft_ack_pending_u {
+	unsigned long	v;
+	struct uv4h_lb_proc_intd_soft_ack_pending_s {
+		unsigned long	soft_ack_flags:8;		/* RW */
+	} s4;
+};
+
 
 #endif /* _ASM_X86_UV_UV_MMRS_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 1ae89a2721d6..4dcdf74dfed8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -142,6 +142,44 @@ struct x86_cpuinit_ops {
 struct timespec;
 
 /**
+ * struct x86_legacy_devices - legacy x86 devices
+ *
+ * @pnpbios: this platform can have a PNPBIOS. If this is disabled the platform
+ * 	is known to never have a PNPBIOS.
+ *
+ * These are devices known to require LPC or ISA bus. The definition of legacy
+ * devices adheres to the ACPI 5.2.9.3 IA-PC Boot Architecture flag
+ * ACPI_FADT_LEGACY_DEVICES. These devices consist of user visible devices on
+ * the LPC or ISA bus. User visible devices are devices that have end-user
+ * accessible connectors (for example, LPT parallel port). Legacy devices on
+ * the LPC bus consist for example of serial and parallel ports, PS/2 keyboard
+ * / mouse, and the floppy disk controller. A system that lacks all known
+ * legacy devices can assume all devices can be detected exclusively via
+ * standard device enumeration mechanisms including the ACPI namespace.
+ *
+ * A system which has does not have ACPI_FADT_LEGACY_DEVICES enabled must not
+ * have any of the legacy devices enumerated below present.
+ */
+struct x86_legacy_devices {
+	int pnpbios;
+};
+
+/**
+ * struct x86_legacy_features - legacy x86 features
+ *
+ * @rtc: this device has a CMOS real-time clock present
+ * @ebda_search: it's safe to search for the EBDA signature in the hardware's
+ * 	low RAM
+ * @devices: legacy x86 devices, refer to struct x86_legacy_devices
+ * 	documentation for further details.
+ */
+struct x86_legacy_features {
+	int rtc;
+	int ebda_search;
+	struct x86_legacy_devices devices;
+};
+
+/**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:		calibrate TSC
  * @get_wallclock:		get time from HW clock like RTC etc.
@@ -152,6 +190,14 @@ struct timespec;
  * @save_sched_clock_state:	save state for sched_clock() on suspend
  * @restore_sched_clock_state:	restore state for sched_clock() on resume
  * @apic_post_init:		adjust apic if neeeded
+ * @legacy:			legacy features
+ * @set_legacy_features:	override legacy features. Use of this callback
+ * 				is highly discouraged. You should only need
+ * 				this if your hardware platform requires further
+ * 				custom fine tuning far beyong what may be
+ * 				possible in x86_early_init_platform_quirks() by
+ * 				only using the current x86_hardware_subarch
+ * 				semantics.
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
@@ -165,6 +211,8 @@ struct x86_platform_ops {
 	void (*save_sched_clock_state)(void);
 	void (*restore_sched_clock_state)(void);
 	void (*apic_post_init)(void);
+	struct x86_legacy_features legacy;
+	void (*set_legacy_features)(void);
 };
 
 struct pci_dev;
@@ -186,6 +234,8 @@ extern struct x86_cpuinit_ops x86_cpuinit;
 extern struct x86_platform_ops x86_platform;
 extern struct x86_msi_ops x86_msi;
 extern struct x86_io_apic_ops x86_io_apic_ops;
+
+extern void x86_early_init_platform_quirks(void);
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
 
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index c54beb44c4c1..635eac543922 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -550,7 +550,7 @@ static struct xor_block_template xor_block_pIII_sse = {
 #define XOR_TRY_TEMPLATES				\
 do {							\
 	AVX_XOR_SPEED;					\
-	if (cpu_has_xmm) {				\
+	if (boot_cpu_has(X86_FEATURE_XMM)) {				\
 		xor_speed(&xor_block_pIII_sse);		\
 		xor_speed(&xor_block_sse_pf64);		\
 	} else if (boot_cpu_has(X86_FEATURE_MMX)) {	\
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7c0a517ec751..22a7b1870a31 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = {
 
 #define AVX_XOR_SPEED \
 do { \
-	if (cpu_has_avx && cpu_has_osxsave) \
+	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE)) \
 		xor_speed(&xor_block_avx); \
 } while (0)
 
 #define AVX_SELECT(FASTEST) \
-	(cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
+	(boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST)
 
 #else
 
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 329254373479..c18ce67495fa 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -157,7 +157,46 @@ struct boot_params {
 	__u8  _pad9[276];				/* 0xeec */
 } __attribute__((packed));
 
-enum {
+/**
+ * enum x86_hardware_subarch - x86 hardware subarchitecture
+ *
+ * The x86 hardware_subarch and hardware_subarch_data were added as of the x86
+ * boot protocol 2.07 to help distinguish and support custom x86 boot
+ * sequences. This enum represents accepted values for the x86
+ * hardware_subarch.  Custom x86 boot sequences (not X86_SUBARCH_PC) do not
+ * have or simply *cannot* make use of natural stubs like BIOS or EFI, the
+ * hardware_subarch can be used on the Linux entry path to revector to a
+ * subarchitecture stub when needed. This subarchitecture stub can be used to
+ * set up Linux boot parameters or for special care to account for nonstandard
+ * handling of page tables.
+ *
+ * These enums should only ever be used by x86 code, and the code that uses
+ * it should be well contained and compartamentalized.
+ *
+ * KVM and Xen HVM do not have a subarch as these are expected to follow
+ * standard x86 boot entries. If there is a genuine need for "hypervisor" type
+ * that should be considered separately in the future. Future guest types
+ * should seriously consider working with standard x86 boot stubs such as
+ * the BIOS or EFI boot stubs.
+ *
+ * WARNING: this enum is only used for legacy hacks, for platform features that
+ *	    are not easily enumerated or discoverable. You should not ever use
+ *	    this for new features.
+ *
+ * @X86_SUBARCH_PC: Should be used if the hardware is enumerable using standard
+ *	PC mechanisms (PCI, ACPI) and doesn't need a special boot flow.
+ * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest
+ * @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path,
+ * 	which start at asm startup_xen() entry point and later jump to the C
+ * 	xen_start_kernel() entry point. Both domU and dom0 type of guests are
+ * 	currently supportd through this PV boot path.
+ * @X86_SUBARCH_INTEL_MID: Used for Intel MID (Mobile Internet Device) platform
+ *	systems which do not have the PCI legacy interfaces.
+ * @X86_SUBARCH_CE4100: Used for Intel CE media processor (CE4100) SoC for
+ * 	for settop boxes and media devices, the use of a subarch for CE4100
+ * 	is more of a hack...
+ */
+enum x86_hardware_subarch {
 	X86_SUBARCH_PC = 0,
 	X86_SUBARCH_LGUEST,
 	X86_SUBARCH_XEN,
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 616ebd22ef9a..9abf8551c7e4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -2,7 +2,11 @@
 # Makefile for the linux kernel.
 #
 
-extra-y                := head_$(BITS).o head$(BITS).o head.o vmlinux.lds
+extra-y	:= head_$(BITS).o
+extra-y	+= head$(BITS).o
+extra-y	+= ebda.o
+extra-y	+= platform-quirks.o
+extra-y	+= vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8c2f1ef6ca23..f115a58f7c84 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -136,7 +136,7 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
 {
 	struct acpi_table_madt *madt = NULL;
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -EINVAL;
 
 	madt = (struct acpi_table_madt *)table;
@@ -913,6 +913,15 @@ late_initcall(hpet_insert_resource);
 
 static int __init acpi_parse_fadt(struct acpi_table_header *table)
 {
+	if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) {
+		pr_debug("ACPI: no legacy devices present\n");
+		x86_platform.legacy.devices.pnpbios = 0;
+	}
+
+	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
+		pr_debug("ACPI: not registering RTC platform device\n");
+		x86_platform.legacy.rtc = 0;
+	}
 
 #ifdef CONFIG_X86_PM_TIMER
 	/* detect the location of the ACPI PM Timer */
@@ -951,7 +960,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 {
 	int count;
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
 
 	/*
@@ -979,7 +988,7 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	int ret;
 	struct acpi_subtable_proc madt_proc[2];
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
 
 	/*
@@ -1125,7 +1134,7 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 	if (acpi_disabled || acpi_noirq)
 		return -ENODEV;
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
 
 	/*
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 25f909362b7a..5cb272a7a5a3 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,7 @@
 #include <linux/stop_machine.h>
 #include <linux/slab.h>
 #include <linux/kdebug.h>
+#include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d356987a04e9..60078a67d7e3 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -607,7 +607,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
 	long tapic = apic_read(APIC_TMCCT);
 	unsigned long pm = acpi_pm_read_early();
 
-	if (cpu_has_tsc)
+	if (boot_cpu_has(X86_FEATURE_TSC))
 		tsc = rdtsc();
 
 	switch (lapic_cal_loops++) {
@@ -668,7 +668,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 	*delta = (long)res;
 
 	/* Correct the tsc counter value */
-	if (cpu_has_tsc) {
+	if (boot_cpu_has(X86_FEATURE_TSC)) {
 		res = (((u64)(*deltatsc)) * pm_100ms);
 		do_div(res, deltapm);
 		apic_printk(APIC_VERBOSE, "TSC delta adjusted to "
@@ -760,7 +760,7 @@ static int __init calibrate_APIC_clock(void)
 	apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
 		    lapic_timer_frequency);
 
-	if (cpu_has_tsc) {
+	if (boot_cpu_has(X86_FEATURE_TSC)) {
 		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
 			    "%ld.%04ld MHz.\n",
 			    (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ),
@@ -1085,7 +1085,7 @@ void lapic_shutdown(void)
 {
 	unsigned long flags;
 
-	if (!cpu_has_apic && !apic_from_smp_config())
+	if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config())
 		return;
 
 	local_irq_save(flags);
@@ -1134,7 +1134,7 @@ void __init init_bsp_APIC(void)
 	 * Don't do the setup now if we have a SMP BIOS as the
 	 * through-I/O-APIC virtual wire mode might be active.
 	 */
-	if (smp_found_config || !cpu_has_apic)
+	if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC))
 		return;
 
 	/*
@@ -1227,7 +1227,7 @@ void setup_local_APIC(void)
 	unsigned long long tsc = 0, ntsc;
 	long long max_loops = cpu_khz ? cpu_khz : 1000000;
 
-	if (cpu_has_tsc)
+	if (boot_cpu_has(X86_FEATURE_TSC))
 		tsc = rdtsc();
 
 	if (disable_apic) {
@@ -1311,7 +1311,7 @@ void setup_local_APIC(void)
 			break;
 		}
 		if (queued) {
-			if (cpu_has_tsc && cpu_khz) {
+			if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
 				ntsc = rdtsc();
 				max_loops = (cpu_khz << 10) - (ntsc - tsc);
 			} else
@@ -1445,7 +1445,7 @@ static void __x2apic_disable(void)
 {
 	u64 msr;
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return;
 
 	rdmsrl(MSR_IA32_APICBASE, msr);
@@ -1561,7 +1561,7 @@ void __init check_x2apic(void)
 		pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n");
 		x2apic_mode = 1;
 		x2apic_state = X2APIC_ON;
-	} else if (!cpu_has_x2apic) {
+	} else if (!boot_cpu_has(X86_FEATURE_X2APIC)) {
 		x2apic_state = X2APIC_DISABLED;
 	}
 }
@@ -1632,7 +1632,7 @@ void __init enable_IR_x2apic(void)
  */
 static int __init detect_init_APIC(void)
 {
-	if (!cpu_has_apic) {
+	if (!boot_cpu_has(X86_FEATURE_APIC)) {
 		pr_info("No local APIC present\n");
 		return -1;
 	}
@@ -1711,14 +1711,14 @@ static int __init detect_init_APIC(void)
 		goto no_apic;
 	case X86_VENDOR_INTEL:
 		if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
-		    (boot_cpu_data.x86 == 5 && cpu_has_apic))
+		    (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
 			break;
 		goto no_apic;
 	default:
 		goto no_apic;
 	}
 
-	if (!cpu_has_apic) {
+	if (!boot_cpu_has(X86_FEATURE_APIC)) {
 		/*
 		 * Over-ride BIOS and try to enable the local APIC only if
 		 * "lapic" specified.
@@ -2233,19 +2233,19 @@ int __init APIC_init_uniprocessor(void)
 		return -1;
 	}
 #ifdef CONFIG_X86_64
-	if (!cpu_has_apic) {
+	if (!boot_cpu_has(X86_FEATURE_APIC)) {
 		disable_apic = 1;
 		pr_info("Apic disabled by BIOS\n");
 		return -1;
 	}
 #else
-	if (!smp_found_config && !cpu_has_apic)
+	if (!smp_found_config && !boot_cpu_has(X86_FEATURE_APIC))
 		return -1;
 
 	/*
 	 * Complain if the BIOS pretends there is one.
 	 */
-	if (!cpu_has_apic &&
+	if (!boot_cpu_has(X86_FEATURE_APIC) &&
 	    APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
 		pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
 			boot_cpu_physical_apicid);
@@ -2426,7 +2426,7 @@ static void apic_pm_activate(void)
 static int __init init_lapic_sysfs(void)
 {
 	/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
-	if (cpu_has_apic)
+	if (boot_cpu_has(X86_FEATURE_APIC))
 		register_syscore_ops(&lapic_syscore_ops);
 
 	return 0;
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 331a7a07c48f..13d19ed58514 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -100,13 +100,13 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask,
 
 static u32 noop_apic_read(u32 reg)
 {
-	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+	WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic);
 	return 0;
 }
 
 static void noop_apic_write(u32 reg, u32 v)
 {
-	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
+	WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic);
 }
 
 struct apic apic_noop = {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fdb0fbfb1197..84e33ff5a6d5 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1454,7 +1454,7 @@ void native_disable_io_apic(void)
 		ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry);
 	}
 
-	if (cpu_has_apic || apic_from_smp_config())
+	if (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config())
 		disconnect_bsp_APIC(ioapic_i8259.pin != -1);
 }
 
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 28bde88b0085..2a0f225afebd 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -230,7 +230,7 @@ int safe_smp_processor_id(void)
 {
 	int apicid, cpuid;
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return 0;
 
 	apicid = hard_smp_processor_id();
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index ef495511f019..a5e400afc563 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -944,7 +944,7 @@ static int __init print_ICs(void)
 	print_PIC();
 
 	/* don't print out if apic is not there */
-	if (!cpu_has_apic && !apic_from_smp_config())
+	if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config())
 		return 0;
 
 	print_local_APICs(show_lapic);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d7ce96a7daca..29003154fafd 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -48,12 +48,35 @@ static u64 gru_start_paddr, gru_end_paddr;
 static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
 static u64 gru_dist_lmask, gru_dist_umask;
 static union uvh_apicid uvh_apicid;
+
+/* info derived from CPUID */
+static struct {
+	unsigned int apicid_shift;
+	unsigned int apicid_mask;
+	unsigned int socketid_shift;	/* aka pnode_shift for UV1/2/3 */
+	unsigned int pnode_mask;
+	unsigned int gpa_shift;
+} uv_cpuid;
+
 int uv_min_hub_revision_id;
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
 unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 
 static struct apic apic_x2apic_uv_x;
+static struct uv_hub_info_s uv_hub_info_node0;
+
+/* Set this to use hardware error handler instead of kernel panic */
+static int disable_uv_undefined_panic = 1;
+unsigned long uv_undefined(char *str)
+{
+	if (likely(!disable_uv_undefined_panic))
+		panic("UV: error: undefined MMR: %s\n", str);
+	else
+		pr_crit("UV: error: undefined MMR: %s\n", str);
+	return ~0ul;	/* cause a machine fault  */
+}
+EXPORT_SYMBOL(uv_undefined);
 
 static unsigned long __init uv_early_read_mmr(unsigned long addr)
 {
@@ -108,21 +131,71 @@ static int __init early_get_pnodeid(void)
 	case UV3_HUB_PART_NUMBER_X:
 		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
+	case UV4_HUB_PART_NUMBER:
+		uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
+		break;
 	}
 
 	uv_hub_info->hub_revision = uv_min_hub_revision_id;
-	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
+	uv_cpuid.pnode_mask = (1 << m_n_config.s.n_skt) - 1;
+	pnode = (node_id.s.node_id >> 1) & uv_cpuid.pnode_mask;
+	uv_cpuid.gpa_shift = 46;	/* default unless changed */
+
+	pr_info("UV: rev:%d part#:%x nodeid:%04x n_skt:%d pnmsk:%x pn:%x\n",
+		node_id.s.revision, node_id.s.part_number, node_id.s.node_id,
+		m_n_config.s.n_skt, uv_cpuid.pnode_mask, pnode);
 	return pnode;
 }
 
-static void __init early_get_apic_pnode_shift(void)
+/* [copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
+#define SMT_LEVEL	0	/* leaf 0xb SMT level */
+#define INVALID_TYPE	0	/* leaf 0xb sub-leaf types */
+#define SMT_TYPE	1
+#define CORE_TYPE	2
+#define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
+#define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
+
+static void set_x2apic_bits(void)
+{
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int sid_shift;
+
+	cpuid(0, &eax, &ebx, &ecx, &edx);
+	if (eax < 0xb) {
+		pr_info("UV: CPU does not have CPUID.11\n");
+		return;
+	}
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) {
+		pr_info("UV: CPUID.11 not implemented\n");
+		return;
+	}
+	sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
+	sub_index = 1;
+	do {
+		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
+			sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
+			break;
+		}
+		sub_index++;
+	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+	uv_cpuid.apicid_shift = 0;
+	uv_cpuid.apicid_mask = (~(-1 << sid_shift));
+	uv_cpuid.socketid_shift = sid_shift;
+}
+
+static void __init early_get_apic_socketid_shift(void)
 {
-	uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
-	if (!uvh_apicid.v)
-		/*
-		 * Old bios, use default value
-		 */
-		uvh_apicid.s.pnode_shift = UV_APIC_PNODE_SHIFT;
+	if (is_uv2_hub() || is_uv3_hub())
+		uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
+
+	set_x2apic_bits();
+
+	pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n",
+		uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
+	pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n",
+		uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
 }
 
 /*
@@ -150,13 +223,18 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	if (strncmp(oem_id, "SGI", 3) != 0)
 		return 0;
 
+	/* Setup early hub type field in uv_hub_info for Node 0 */
+	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
+
 	/*
 	 * Determine UV arch type.
 	 *   SGI: UV100/1000
 	 *   SGI2: UV2000/3000
 	 *   SGI3: UV300 (truncated to 4 chars because of different varieties)
+	 *   SGI4: UV400 (truncated to 4 chars because of different varieties)
 	 */
 	uv_hub_info->hub_revision =
+		!strncmp(oem_id, "SGI4", 4) ? UV4_HUB_REVISION_BASE :
 		!strncmp(oem_id, "SGI3", 4) ? UV3_HUB_REVISION_BASE :
 		!strcmp(oem_id, "SGI2") ? UV2_HUB_REVISION_BASE :
 		!strcmp(oem_id, "SGI") ? UV1_HUB_REVISION_BASE : 0;
@@ -165,7 +243,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		goto badbios;
 
 	pnodeid = early_get_pnodeid();
-	early_get_apic_pnode_shift();
+	early_get_apic_socketid_shift();
 	x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 	x86_platform.nmi_init = uv_nmi_init;
 
@@ -211,17 +289,11 @@ int is_uv_system(void)
 }
 EXPORT_SYMBOL_GPL(is_uv_system);
 
-DEFINE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info);
-
-struct uv_blade_info *uv_blade_info;
-EXPORT_SYMBOL_GPL(uv_blade_info);
-
-short *uv_node_to_blade;
-EXPORT_SYMBOL_GPL(uv_node_to_blade);
+void **__uv_hub_info_list;
+EXPORT_SYMBOL_GPL(__uv_hub_info_list);
 
-short *uv_cpu_to_blade;
-EXPORT_SYMBOL_GPL(uv_cpu_to_blade);
+DEFINE_PER_CPU(struct uv_cpu_info_s, __uv_cpu_info);
+EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_info);
 
 short uv_possible_blades;
 EXPORT_SYMBOL_GPL(uv_possible_blades);
@@ -229,6 +301,115 @@ EXPORT_SYMBOL_GPL(uv_possible_blades);
 unsigned long sn_rtc_cycles_per_second;
 EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 
+/* the following values are used for the per node hub info struct */
+static __initdata unsigned short *_node_to_pnode;
+static __initdata unsigned short _min_socket, _max_socket;
+static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len;
+static __initdata struct uv_gam_range_entry *uv_gre_table;
+static __initdata struct uv_gam_parameters *uv_gp_table;
+static __initdata unsigned short *_socket_to_node;
+static __initdata unsigned short *_socket_to_pnode;
+static __initdata unsigned short *_pnode_to_socket;
+static __initdata struct uv_gam_range_s *_gr_table;
+#define	SOCK_EMPTY	((unsigned short)~0)
+
+extern int uv_hub_info_version(void)
+{
+	return UV_HUB_INFO_VERSION;
+}
+EXPORT_SYMBOL(uv_hub_info_version);
+
+/* Build GAM range lookup table */
+static __init void build_uv_gr_table(void)
+{
+	struct uv_gam_range_entry *gre = uv_gre_table;
+	struct uv_gam_range_s *grt;
+	unsigned long last_limit = 0, ram_limit = 0;
+	int bytes, i, sid, lsid = -1;
+
+	if (!gre)
+		return;
+
+	bytes = _gr_table_len * sizeof(struct uv_gam_range_s);
+	grt = kzalloc(bytes, GFP_KERNEL);
+	BUG_ON(!grt);
+	_gr_table = grt;
+
+	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		if (gre->type == UV_GAM_RANGE_TYPE_HOLE) {
+			if (!ram_limit) {   /* mark hole between ram/non-ram */
+				ram_limit = last_limit;
+				last_limit = gre->limit;
+				lsid++;
+				continue;
+			}
+			last_limit = gre->limit;
+			pr_info("UV: extra hole in GAM RE table @%d\n",
+				(int)(gre - uv_gre_table));
+			continue;
+		}
+		if (_max_socket < gre->sockid) {
+			pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n",
+				gre->sockid, _max_socket,
+				(int)(gre - uv_gre_table));
+			continue;
+		}
+		sid = gre->sockid - _min_socket;
+		if (lsid < sid) {		/* new range */
+			grt = &_gr_table[sid];
+			grt->base = lsid;
+			grt->nasid = gre->nasid;
+			grt->limit = last_limit = gre->limit;
+			lsid = sid;
+			continue;
+		}
+		if (lsid == sid && !ram_limit) {	/* update range */
+			if (grt->limit == last_limit) {	/* .. if contiguous */
+				grt->limit = last_limit = gre->limit;
+				continue;
+			}
+		}
+		if (!ram_limit) {		/* non-contiguous ram range */
+			grt++;
+			grt->base = sid - 1;
+			grt->nasid = gre->nasid;
+			grt->limit = last_limit = gre->limit;
+			continue;
+		}
+		grt++;				/* non-contiguous/non-ram */
+		grt->base = grt - _gr_table;	/* base is this entry */
+		grt->nasid = gre->nasid;
+		grt->limit = last_limit = gre->limit;
+		lsid++;
+	}
+
+	/* shorten table if possible */
+	grt++;
+	i = grt - _gr_table;
+	if (i < _gr_table_len) {
+		void *ret;
+
+		bytes = i * sizeof(struct uv_gam_range_s);
+		ret = krealloc(_gr_table, bytes, GFP_KERNEL);
+		if (ret) {
+			_gr_table = ret;
+			_gr_table_len = i;
+		}
+	}
+
+	/* display resultant gam range table */
+	for (i = 0, grt = _gr_table; i < _gr_table_len; i++, grt++) {
+		int gb = grt->base;
+		unsigned long start = gb < 0 ?  0 :
+			(unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT;
+		unsigned long end =
+			(unsigned long)grt->limit << UV_GAM_RANGE_SHFT;
+
+		pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n",
+			i, grt->nasid, start, end, gb);
+	}
+}
+
 static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
 	unsigned long val;
@@ -355,7 +536,6 @@ static unsigned long set_apic_id(unsigned int id)
 
 static unsigned int uv_read_apic_id(void)
 {
-
 	return x2apic_get_apic_id(apic_read(APIC_ID));
 }
 
@@ -430,58 +610,38 @@ static void set_x2apic_extra_bits(int pnode)
 	__this_cpu_write(x2apic_extra_bits, pnode << uvh_apicid.s.pnode_shift);
 }
 
-/*
- * Called on boot cpu.
- */
-static __init int boot_pnode_to_blade(int pnode)
-{
-	int blade;
-
-	for (blade = 0; blade < uv_num_possible_blades(); blade++)
-		if (pnode == uv_blade_info[blade].pnode)
-			return blade;
-	BUG();
-}
-
-struct redir_addr {
-	unsigned long redirect;
-	unsigned long alias;
-};
-
+#define	UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_LENGTH	3
 #define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
 
-static __initdata struct redir_addr redir_addrs[] = {
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR},
-};
-
-static unsigned char get_n_lshift(int m_val)
-{
-	union uv3h_gr0_gam_gr_config_u m_gr_config;
-
-	if (is_uv1_hub())
-		return m_val;
-
-	if (is_uv2_hub())
-		return m_val == 40 ? 40 : 39;
-
-	m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
-	return m_gr_config.s3.m_skt;
-}
-
 static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 {
 	union uvh_rh_gam_alias210_overlay_config_2_mmr_u alias;
 	union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
+	unsigned long m_redirect;
+	unsigned long m_overlay;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
-		alias.v = uv_read_local_mmr(redir_addrs[i].alias);
+	for (i = 0; i < UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_LENGTH; i++) {
+		switch (i) {
+		case 0:
+			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR;
+			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR;
+			break;
+		case 1:
+			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR;
+			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR;
+			break;
+		case 2:
+			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR;
+			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR;
+			break;
+		}
+		alias.v = uv_read_local_mmr(m_overlay);
 		if (alias.s.enable && alias.s.base == 0) {
 			*size = (1UL << alias.s.m_alias);
-			redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
-			*base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
+			redirect.v = uv_read_local_mmr(m_redirect);
+			*base = (unsigned long)redirect.s.dest_base
+							<< DEST_SHIFT;
 			return;
 		}
 	}
@@ -544,6 +704,8 @@ static __init void map_gru_high(int max_pnode)
 {
 	union uvh_rh_gam_gru_overlay_config_mmr_u gru;
 	int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
+	unsigned long mask = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK;
+	unsigned long base;
 
 	gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
 	if (!gru.s.enable) {
@@ -555,8 +717,9 @@ static __init void map_gru_high(int max_pnode)
 		map_gru_distributed(gru.v);
 		return;
 	}
-	map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb);
-	gru_start_paddr = ((u64)gru.s.base << shift);
+	base = (gru.v & mask) >> shift;
+	map_high("GRU", base, shift, shift, max_pnode, map_wb);
+	gru_start_paddr = ((u64)base << shift);
 	gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1);
 }
 
@@ -595,6 +758,7 @@ static __initdata struct mmioh_config mmiohs[] = {
 	},
 };
 
+/* UV3 & UV4 have identical MMIOH overlay configs */
 static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 {
 	union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay;
@@ -674,7 +838,7 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
 	unsigned long mmr, base;
 	int shift, enable, m_io, n_io;
 
-	if (is_uv3_hub()) {
+	if (is_uv3_hub() || is_uv4_hub()) {
 		/* Map both MMIOH Regions */
 		map_mmioh_high_uv3(0, min_pnode, max_pnode);
 		map_mmioh_high_uv3(1, min_pnode, max_pnode);
@@ -739,8 +903,8 @@ static __init void uv_rtc_init(void)
  */
 static void uv_heartbeat(unsigned long ignored)
 {
-	struct timer_list *timer = &uv_hub_info->scir.timer;
-	unsigned char bits = uv_hub_info->scir.state;
+	struct timer_list *timer = &uv_scir_info->timer;
+	unsigned char bits = uv_scir_info->state;
 
 	/* flip heartbeat bit */
 	bits ^= SCIR_CPU_HEARTBEAT;
@@ -760,14 +924,14 @@ static void uv_heartbeat(unsigned long ignored)
 
 static void uv_heartbeat_enable(int cpu)
 {
-	while (!uv_cpu_hub_info(cpu)->scir.enabled) {
-		struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
+	while (!uv_cpu_scir_info(cpu)->enabled) {
+		struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer;
 
 		uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
 		setup_timer(timer, uv_heartbeat, cpu);
 		timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
 		add_timer_on(timer, cpu);
-		uv_cpu_hub_info(cpu)->scir.enabled = 1;
+		uv_cpu_scir_info(cpu)->enabled = 1;
 
 		/* also ensure that boot cpu is enabled */
 		cpu = 0;
@@ -777,9 +941,9 @@ static void uv_heartbeat_enable(int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 static void uv_heartbeat_disable(int cpu)
 {
-	if (uv_cpu_hub_info(cpu)->scir.enabled) {
-		uv_cpu_hub_info(cpu)->scir.enabled = 0;
-		del_timer(&uv_cpu_hub_info(cpu)->scir.timer);
+	if (uv_cpu_scir_info(cpu)->enabled) {
+		uv_cpu_scir_info(cpu)->enabled = 0;
+		del_timer(&uv_cpu_scir_info(cpu)->timer);
 	}
 	uv_set_cpu_scir_bits(cpu, 0xff);
 }
@@ -862,155 +1026,475 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode,
 void uv_cpu_init(void)
 {
 	/* CPU 0 initialization will be done via uv_system_init. */
-	if (!uv_blade_info)
+	if (smp_processor_id() == 0)
 		return;
 
-	uv_blade_info[uv_numa_blade_id()].nr_online_cpus++;
+	uv_hub_info->nr_online_cpus++;
 
 	if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
 		set_x2apic_extra_bits(uv_hub_info->pnode);
 }
 
-void __init uv_system_init(void)
+struct mn {
+	unsigned char	m_val;
+	unsigned char	n_val;
+	unsigned char	m_shift;
+	unsigned char	n_lshift;
+};
+
+static void get_mn(struct mn *mnp)
 {
-	union uvh_rh_gam_config_mmr_u  m_n_config;
-	union uvh_node_id_u node_id;
-	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
-	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
-	int gnode_extra, min_pnode = 999999, max_pnode = -1;
-	unsigned long mmr_base, present, paddr;
-	unsigned short pnode_mask;
-	unsigned char n_lshift;
-	char *hub = (is_uv1_hub() ? "UV100/1000" :
-		    (is_uv2_hub() ? "UV2000/3000" :
-		    (is_uv3_hub() ? "UV300" : NULL)));
+	union uvh_rh_gam_config_mmr_u m_n_config;
+	union uv3h_gr0_gam_gr_config_u m_gr_config;
 
-	if (!hub) {
-		pr_err("UV: Unknown/unsupported UV hub\n");
-		return;
+	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR);
+	mnp->n_val = m_n_config.s.n_skt;
+	if (is_uv4_hub()) {
+		mnp->m_val = 0;
+		mnp->n_lshift = 0;
+	} else if (is_uv3_hub()) {
+		mnp->m_val = m_n_config.s3.m_skt;
+		m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
+		mnp->n_lshift = m_gr_config.s3.m_skt;
+	} else if (is_uv2_hub()) {
+		mnp->m_val = m_n_config.s2.m_skt;
+		mnp->n_lshift = mnp->m_val == 40 ? 40 : 39;
+	} else if (is_uv1_hub()) {
+		mnp->m_val = m_n_config.s1.m_skt;
+		mnp->n_lshift = mnp->m_val;
 	}
-	pr_info("UV: Found %s hub\n", hub);
+	mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0;
+}
 
-	map_low_mmrs();
+void __init uv_init_hub_info(struct uv_hub_info_s *hub_info)
+{
+	struct mn mn = {0};	/* avoid unitialized warnings */
+	union uvh_node_id_u node_id;
 
-	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
-	m_val = m_n_config.s.m_skt;
-	n_val = m_n_config.s.n_skt;
-	pnode_mask = (1 << n_val) - 1;
-	n_lshift = get_n_lshift(m_val);
-	mmr_base =
-	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
-	    ~UV_MMR_ENABLE;
+	get_mn(&mn);
+	hub_info->m_val = mn.m_val;
+	hub_info->n_val = mn.n_val;
+	hub_info->m_shift = mn.m_shift;
+	hub_info->n_lshift = mn.n_lshift ? mn.n_lshift : 0;
+
+	hub_info->hub_revision = uv_hub_info->hub_revision;
+	hub_info->pnode_mask = uv_cpuid.pnode_mask;
+	hub_info->min_pnode = _min_pnode;
+	hub_info->min_socket = _min_socket;
+	hub_info->pnode_to_socket = _pnode_to_socket;
+	hub_info->socket_to_node = _socket_to_node;
+	hub_info->socket_to_pnode = _socket_to_pnode;
+	hub_info->gr_table_len = _gr_table_len;
+	hub_info->gr_table = _gr_table;
+	hub_info->gpa_mask = mn.m_val ?
+		(1UL << (mn.m_val + mn.n_val)) - 1 :
+		(1UL << uv_cpuid.gpa_shift) - 1;
 
 	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
-	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
-	gnode_upper = ((unsigned long)gnode_extra  << m_val);
-	pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x n_lshift 0x%x\n",
-			n_val, m_val, pnode_mask, gnode_upper, gnode_extra,
-			n_lshift);
+	hub_info->gnode_extra =
+		(node_id.s.node_id & ~((1 << mn.n_val) - 1)) >> 1;
+
+	hub_info->gnode_upper =
+		((unsigned long)hub_info->gnode_extra << mn.m_val);
+
+	if (uv_gp_table) {
+		hub_info->global_mmr_base = uv_gp_table->mmr_base;
+		hub_info->global_mmr_shift = uv_gp_table->mmr_shift;
+		hub_info->global_gru_base = uv_gp_table->gru_base;
+		hub_info->global_gru_shift = uv_gp_table->gru_shift;
+		hub_info->gpa_shift = uv_gp_table->gpa_shift;
+		hub_info->gpa_mask = (1UL << hub_info->gpa_shift) - 1;
+	} else {
+		hub_info->global_mmr_base =
+			uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
+					~UV_MMR_ENABLE;
+		hub_info->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT;
+	}
 
-	pr_info("UV: global MMR base 0x%lx\n", mmr_base);
+	get_lowmem_redirect(
+		&hub_info->lowmem_remap_base, &hub_info->lowmem_remap_top);
 
-	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
-		uv_possible_blades +=
-		  hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
+	hub_info->apic_pnode_shift = uv_cpuid.socketid_shift;
 
-	/* uv_num_possible_blades() is really the hub count */
-	pr_info("UV: Found %d blades, %d hubs\n",
-			is_uv1_hub() ? uv_num_possible_blades() :
-			(uv_num_possible_blades() + 1) / 2,
-			uv_num_possible_blades());
+	/* show system specific info */
+	pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n",
+		hub_info->n_val, hub_info->m_val,
+		hub_info->m_shift, hub_info->n_lshift);
 
-	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
-	uv_blade_info = kzalloc(bytes, GFP_KERNEL);
-	BUG_ON(!uv_blade_info);
+	pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n",
+		hub_info->gpa_mask, hub_info->gpa_shift,
+		hub_info->pnode_mask, hub_info->apic_pnode_shift);
 
-	for (blade = 0; blade < uv_num_possible_blades(); blade++)
-		uv_blade_info[blade].memory_nid = -1;
+	pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n",
+		hub_info->global_mmr_base, hub_info->global_mmr_shift,
+		hub_info->global_gru_base, hub_info->global_gru_shift);
 
-	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
+	pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n",
+		hub_info->gnode_upper, hub_info->gnode_extra);
+}
+
+static void __init decode_gam_params(unsigned long ptr)
+{
+	uv_gp_table = (struct uv_gam_parameters *)ptr;
+
+	pr_info("UV: GAM Params...\n");
+	pr_info("UV: mmr_base/shift:0x%llx/%d gru_base/shift:0x%llx/%d gpa_shift:%d\n",
+		uv_gp_table->mmr_base, uv_gp_table->mmr_shift,
+		uv_gp_table->gru_base, uv_gp_table->gru_shift,
+		uv_gp_table->gpa_shift);
+}
+
+static void __init decode_gam_rng_tbl(unsigned long ptr)
+{
+	struct uv_gam_range_entry *gre = (struct uv_gam_range_entry *)ptr;
+	unsigned long lgre = 0;
+	int index = 0;
+	int sock_min = 999999, pnode_min = 99999;
+	int sock_max = -1, pnode_max = -1;
+
+	uv_gre_table = gre;
+	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		if (!index) {
+			pr_info("UV: GAM Range Table...\n");
+			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s %3s\n",
+				"Range", "", "Size", "Type", "NASID",
+				"SID", "PN", "PXM");
+		}
+		pr_info(
+		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x %3d\n",
+			index++,
+			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
+			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
+			((unsigned long)(gre->limit - lgre)) >>
+				(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
+			gre->type, gre->nasid, gre->sockid,
+			gre->pnode, gre->pxm);
+
+		lgre = gre->limit;
+		if (sock_min > gre->sockid)
+			sock_min = gre->sockid;
+		if (sock_max < gre->sockid)
+			sock_max = gre->sockid;
+		if (pnode_min > gre->pnode)
+			pnode_min = gre->pnode;
+		if (pnode_max < gre->pnode)
+			pnode_max = gre->pnode;
+	}
+	_min_socket = sock_min;
+	_max_socket = sock_max;
+	_min_pnode = pnode_min;
+	_max_pnode = pnode_max;
+	_gr_table_len = index;
+	pr_info(
+	"UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n",
+		index, _min_socket, _max_socket, _min_pnode, _max_pnode);
+}
+
+static void __init decode_uv_systab(void)
+{
+	struct uv_systab *st;
+	int i;
+
+	st = uv_systab;
+	if ((!st || st->revision < UV_SYSTAB_VERSION_UV4) && !is_uv4_hub())
+		return;
+	if (st->revision != UV_SYSTAB_VERSION_UV4_LATEST) {
+		pr_crit(
+		"UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n",
+			st->revision, UV_SYSTAB_VERSION_UV4_LATEST);
+		BUG();
+	}
+
+	for (i = 0; st->entry[i].type != UV_SYSTAB_TYPE_UNUSED; i++) {
+		unsigned long ptr = st->entry[i].offset;
 
-	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
-	uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
-	BUG_ON(!uv_node_to_blade);
-	memset(uv_node_to_blade, 255, bytes);
+		if (!ptr)
+			continue;
+
+		ptr = ptr + (unsigned long)st;
+
+		switch (st->entry[i].type) {
+		case UV_SYSTAB_TYPE_GAM_PARAMS:
+			decode_gam_params(ptr);
+			break;
+
+		case UV_SYSTAB_TYPE_GAM_RNG_TBL:
+			decode_gam_rng_tbl(ptr);
+			break;
+		}
+	}
+}
 
-	bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
-	uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
-	BUG_ON(!uv_cpu_to_blade);
-	memset(uv_cpu_to_blade, 255, bytes);
+/*
+ * Setup physical blade translations from UVH_NODE_PRESENT_TABLE
+ * .. NB: UVH_NODE_PRESENT_TABLE is going away,
+ * .. being replaced by GAM Range Table
+ */
+static __init void boot_init_possible_blades(struct uv_hub_info_s *hub_info)
+{
+	int i, uv_pb = 0;
 
-	blade = 0;
+	pr_info("UV: NODE_PRESENT_DEPTH = %d\n", UVH_NODE_PRESENT_TABLE_DEPTH);
 	for (i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) {
-		present = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
-		for (j = 0; j < 64; j++) {
-			if (!test_bit(j, &present))
-				continue;
-			pnode = (i * 64 + j) & pnode_mask;
-			uv_blade_info[blade].pnode = pnode;
-			uv_blade_info[blade].nr_possible_cpus = 0;
-			uv_blade_info[blade].nr_online_cpus = 0;
-			spin_lock_init(&uv_blade_info[blade].nmi_lock);
-			min_pnode = min(pnode, min_pnode);
-			max_pnode = max(pnode, max_pnode);
-			blade++;
+		unsigned long np;
+
+		np = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
+		if (np)
+			pr_info("UV: NODE_PRESENT(%d) = 0x%016lx\n", i, np);
+
+		uv_pb += hweight64(np);
+	}
+	if (uv_possible_blades != uv_pb)
+		uv_possible_blades = uv_pb;
+}
+
+static void __init build_socket_tables(void)
+{
+	struct uv_gam_range_entry *gre = uv_gre_table;
+	int num, nump;
+	int cpu, i, lnid;
+	int minsock = _min_socket;
+	int maxsock = _max_socket;
+	int minpnode = _min_pnode;
+	int maxpnode = _max_pnode;
+	size_t bytes;
+
+	if (!gre) {
+		if (is_uv1_hub() || is_uv2_hub() || is_uv3_hub()) {
+			pr_info("UV: No UVsystab socket table, ignoring\n");
+			return;		/* not required */
 		}
+		pr_crit(
+		"UV: Error: UVsystab address translations not available!\n");
+		BUG();
+	}
+
+	/* build socket id -> node id, pnode */
+	num = maxsock - minsock + 1;
+	bytes = num * sizeof(_socket_to_node[0]);
+	_socket_to_node = kmalloc(bytes, GFP_KERNEL);
+	_socket_to_pnode = kmalloc(bytes, GFP_KERNEL);
+
+	nump = maxpnode - minpnode + 1;
+	bytes = nump * sizeof(_pnode_to_socket[0]);
+	_pnode_to_socket = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!_socket_to_node || !_socket_to_pnode || !_pnode_to_socket);
+
+	for (i = 0; i < num; i++)
+		_socket_to_node[i] = _socket_to_pnode[i] = SOCK_EMPTY;
+
+	for (i = 0; i < nump; i++)
+		_pnode_to_socket[i] = SOCK_EMPTY;
+
+	/* fill in pnode/node/addr conversion list values */
+	pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n");
+	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
+			continue;
+		i = gre->sockid - minsock;
+		if (_socket_to_pnode[i] != SOCK_EMPTY)
+			continue;	/* duplicate */
+		_socket_to_pnode[i] = gre->pnode;
+		_socket_to_node[i] = gre->pxm;
+
+		i = gre->pnode - minpnode;
+		_pnode_to_socket[i] = gre->sockid;
+
+		pr_info(
+		"UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n",
+			gre->sockid, gre->type, gre->nasid,
+			_socket_to_pnode[gre->sockid - minsock],
+			_socket_to_node[gre->sockid - minsock],
+			_pnode_to_socket[gre->pnode - minpnode]);
 	}
 
-	uv_bios_init();
+	/* check socket -> node values */
+	lnid = -1;
+	for_each_present_cpu(cpu) {
+		int nid = cpu_to_node(cpu);
+		int apicid, sockid;
+
+		if (lnid == nid)
+			continue;
+		lnid = nid;
+		apicid = per_cpu(x86_cpu_to_apicid, cpu);
+		sockid = apicid >> uv_cpuid.socketid_shift;
+		i = sockid - minsock;
+
+		if (nid != _socket_to_node[i]) {
+			pr_warn(
+			"UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n",
+				i, sockid, gre->type, _socket_to_node[i], nid);
+			_socket_to_node[i] = nid;
+		}
+	}
+
+	/* Setup physical blade to pnode translation from GAM Range Table */
+	bytes = num_possible_nodes() * sizeof(_node_to_pnode[0]);
+	_node_to_pnode = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!_node_to_pnode);
+
+	for (lnid = 0; lnid < num_possible_nodes(); lnid++) {
+		unsigned short sockid;
+
+		for (sockid = minsock; sockid <= maxsock; sockid++) {
+			if (lnid == _socket_to_node[sockid - minsock]) {
+				_node_to_pnode[lnid] =
+					_socket_to_pnode[sockid - minsock];
+				break;
+			}
+		}
+		if (sockid > maxsock) {
+			pr_err("UV: socket for node %d not found!\n", lnid);
+			BUG();
+		}
+	}
+
+	/*
+	 * If socket id == pnode or socket id == node for all nodes,
+	 *   system runs faster by removing corresponding conversion table.
+	 */
+	pr_info("UV: Checking socket->node/pnode for identity maps\n");
+	if (minsock == 0) {
+		for (i = 0; i < num; i++)
+			if (_socket_to_node[i] == SOCK_EMPTY ||
+				i != _socket_to_node[i])
+				break;
+		if (i >= num) {
+			kfree(_socket_to_node);
+			_socket_to_node = NULL;
+			pr_info("UV: 1:1 socket_to_node table removed\n");
+		}
+	}
+	if (minsock == minpnode) {
+		for (i = 0; i < num; i++)
+			if (_socket_to_pnode[i] != SOCK_EMPTY &&
+				_socket_to_pnode[i] != i + minpnode)
+				break;
+		if (i >= num) {
+			kfree(_socket_to_pnode);
+			_socket_to_pnode = NULL;
+			pr_info("UV: 1:1 socket_to_pnode table removed\n");
+		}
+	}
+}
+
+void __init uv_system_init(void)
+{
+	struct uv_hub_info_s hub_info = {0};
+	int bytes, cpu, nodeid;
+	unsigned short min_pnode = 9999, max_pnode = 0;
+	char *hub = is_uv4_hub() ? "UV400" :
+		    is_uv3_hub() ? "UV300" :
+		    is_uv2_hub() ? "UV2000/3000" :
+		    is_uv1_hub() ? "UV100/1000" : NULL;
+
+	if (!hub) {
+		pr_err("UV: Unknown/unsupported UV hub\n");
+		return;
+	}
+	pr_info("UV: Found %s hub\n", hub);
+
+	map_low_mmrs();
+
+	uv_bios_init();			/* get uv_systab for decoding */
+	decode_uv_systab();
+	build_socket_tables();
+	build_uv_gr_table();
+	uv_init_hub_info(&hub_info);
+	uv_possible_blades = num_possible_nodes();
+	if (!_node_to_pnode)
+		boot_init_possible_blades(&hub_info);
+
+	/* uv_num_possible_blades() is really the hub count */
+	pr_info("UV: Found %d hubs, %d nodes, %d cpus\n",
+			uv_num_possible_blades(),
+			num_possible_nodes(),
+			num_possible_cpus());
+
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id,
 			    &sn_region_size, &system_serial_number);
+	hub_info.coherency_domain_number = sn_coherency_id;
 	uv_rtc_init();
 
-	for_each_present_cpu(cpu) {
-		int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+	bytes = sizeof(void *) * uv_num_possible_blades();
+	__uv_hub_info_list = kzalloc(bytes, GFP_KERNEL);
+	BUG_ON(!__uv_hub_info_list);
 
-		nid = cpu_to_node(cpu);
-		/*
-		 * apic_pnode_shift must be set before calling uv_apicid_to_pnode();
-		 */
-		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
-		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
-		uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision;
+	bytes = sizeof(struct uv_hub_info_s);
+	for_each_node(nodeid) {
+		struct uv_hub_info_s *new_hub;
 
-		uv_cpu_hub_info(cpu)->m_shift = 64 - m_val;
-		uv_cpu_hub_info(cpu)->n_lshift = n_lshift;
+		if (__uv_hub_info_list[nodeid]) {
+			pr_err("UV: Node %d UV HUB already initialized!?\n",
+				nodeid);
+			BUG();
+		}
+
+		/* Allocate new per hub info list */
+		new_hub = (nodeid == 0) ?
+			&uv_hub_info_node0 :
+			kzalloc_node(bytes, GFP_KERNEL, nodeid);
+		BUG_ON(!new_hub);
+		__uv_hub_info_list[nodeid] = new_hub;
+		new_hub = uv_hub_info_list(nodeid);
+		BUG_ON(!new_hub);
+		*new_hub = hub_info;
+
+		/* Use information from GAM table if available */
+		if (_node_to_pnode)
+			new_hub->pnode = _node_to_pnode[nodeid];
+		else	/* Fill in during cpu loop */
+			new_hub->pnode = 0xffff;
+		new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
+		new_hub->memory_nid = -1;
+		new_hub->nr_possible_cpus = 0;
+		new_hub->nr_online_cpus = 0;
+	}
 
+	/* Initialize per cpu info */
+	for_each_possible_cpu(cpu) {
+		int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+		int numa_node_id;
+		unsigned short pnode;
+
+		nodeid = cpu_to_node(cpu);
+		numa_node_id = numa_cpu_node(cpu);
 		pnode = uv_apicid_to_pnode(apicid);
-		blade = boot_pnode_to_blade(pnode);
-		lcpu = uv_blade_info[blade].nr_possible_cpus;
-		uv_blade_info[blade].nr_possible_cpus++;
-
-		/* Any node on the blade, else will contain -1. */
-		uv_blade_info[blade].memory_nid = nid;
-
-		uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
-		uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
-		uv_cpu_hub_info(cpu)->m_val = m_val;
-		uv_cpu_hub_info(cpu)->n_val = n_val;
-		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
-		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
-		uv_cpu_hub_info(cpu)->pnode = pnode;
-		uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
-		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
-		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
-		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
-		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
-		uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid);
-		uv_node_to_blade[nid] = blade;
-		uv_cpu_to_blade[cpu] = blade;
+
+		uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
+		uv_cpu_info_per(cpu)->blade_cpu_id =
+			uv_cpu_hub_info(cpu)->nr_possible_cpus++;
+		if (uv_cpu_hub_info(cpu)->memory_nid == -1)
+			uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
+		if (nodeid != numa_node_id &&	/* init memoryless node */
+		    uv_hub_info_list(numa_node_id)->pnode == 0xffff)
+			uv_hub_info_list(numa_node_id)->pnode = pnode;
+		else if (uv_cpu_hub_info(cpu)->pnode == 0xffff)
+			uv_cpu_hub_info(cpu)->pnode = pnode;
+		uv_cpu_scir_info(cpu)->offset = uv_scir_offset(apicid);
 	}
 
-	/* Add blade/pnode info for nodes without cpus */
-	for_each_online_node(nid) {
-		if (uv_node_to_blade[nid] >= 0)
-			continue;
-		paddr = node_start_pfn(nid) << PAGE_SHIFT;
-		pnode = uv_gpa_to_pnode(uv_soc_phys_ram_to_gpa(paddr));
-		blade = boot_pnode_to_blade(pnode);
-		uv_node_to_blade[nid] = blade;
+	for_each_node(nodeid) {
+		unsigned short pnode = uv_hub_info_list(nodeid)->pnode;
+
+		/* Add pnode info for pre-GAM list nodes without cpus */
+		if (pnode == 0xffff) {
+			unsigned long paddr;
+
+			paddr = node_start_pfn(nodeid) << PAGE_SHIFT;
+			pnode = uv_gpa_to_pnode(uv_soc_phys_ram_to_gpa(paddr));
+			uv_hub_info_list(nodeid)->pnode = pnode;
+		}
+		min_pnode = min(pnode, min_pnode);
+		max_pnode = max(pnode, max_pnode);
+		pr_info("UV: UVHUB node:%2d pn:%02x nrcpus:%d\n",
+			nodeid,
+			uv_hub_info_list(nodeid)->pnode,
+			uv_hub_info_list(nodeid)->nr_possible_cpus);
 	}
 
+	pr_info("UV: min_pnode:%02x max_pnode:%02x\n", min_pnode, max_pnode);
 	map_gru_high(max_pnode);
 	map_mmr_high(max_pnode);
 	map_mmioh_high(min_pnode, max_pnode);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 9307f182fe30..c7364bd633e1 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -2267,7 +2267,7 @@ static int __init apm_init(void)
 
 	dmi_check_system(apm_dmi_table);
 
-	if (apm_info.bios.version == 0 || paravirt_enabled() || machine_is_olpc()) {
+	if (apm_info.bios.version == 0 || machine_is_olpc()) {
 		printk(KERN_INFO "apm: BIOS not found.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 5c042466f274..674134e9f5e5 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -80,6 +80,7 @@ void common(void) {
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
 	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+	OFFSET(BP_init_size, boot_params, hdr.init_size);
 	OFFSET(BP_pref_address, boot_params, hdr.pref_address);
 	OFFSET(BP_code32_start, boot_params, hdr.code32_start);
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7b76eb67a9b3..c343a54bed39 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -565,14 +565,17 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	 * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
 	 * after 16h.
 	 */
-	if (cpu_has_apic && c->x86 > 0x16) {
-		set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
-	} else if (cpu_has_apic && c->x86 >= 0xf) {
-		/* check CPU config space for extended APIC ID */
-		unsigned int val;
-		val = read_pci_config(0, 24, 0, 0x68);
-		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
+	if (boot_cpu_has(X86_FEATURE_APIC)) {
+		if (c->x86 > 0x16)
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+		else if (c->x86 >= 0xf) {
+			/* check CPU config space for extended APIC ID */
+			unsigned int val;
+
+			val = read_pci_config(0, 24, 0, 0x68);
+			if ((val >> 17 & 0x3) == 0x3)
+				set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+		}
 	}
 #endif
 
@@ -628,6 +631,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 */
 	msr_set_bit(MSR_K7_HWCR, 6);
 #endif
+	set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
 }
 
 static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -746,7 +750,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
-	if (cpu_has_xmm2) {
+	if (cpu_has(c, X86_FEATURE_XMM2)) {
 		/* MFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 62ff5255ae16..0fe6953f421c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -437,7 +437,7 @@ void load_percpu_segment(int cpu)
 #ifdef CONFIG_X86_32
 	loadsegment(fs, __KERNEL_PERCPU);
 #else
-	loadsegment(gs, 0);
+	__loadsegment_simple(gs, 0);
 	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
 #endif
 	load_stack_canary_segment();
@@ -724,6 +724,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		}
 	}
 
+	if (c->extended_cpuid_level >= 0x80000007) {
+		cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
+
+		c->x86_capability[CPUID_8000_0007_EBX] = ebx;
+		c->x86_power = edx;
+	}
+
 	if (c->extended_cpuid_level >= 0x80000008) {
 		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
 
@@ -736,9 +743,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_phys_bits = 36;
 #endif
 
-	if (c->extended_cpuid_level >= 0x80000007)
-		c->x86_power = cpuid_edx(0x80000007);
-
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
@@ -869,30 +873,34 @@ static void detect_nopl(struct cpuinfo_x86 *c)
 #else
 	set_cpu_cap(c, X86_FEATURE_NOPL);
 #endif
+}
 
+static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
 	/*
-	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
-	 * systems that run Linux at CPL > 0 may or may not have the
-	 * issue, but, even if they have the issue, there's absolutely
-	 * nothing we can do about it because we can't use the real IRET
-	 * instruction.
+	 * Empirically, writing zero to a segment selector on AMD does
+	 * not clear the base, whereas writing zero to a segment
+	 * selector on Intel does clear the base.  Intel's behavior
+	 * allows slightly faster context switches in the common case
+	 * where GS is unused by the prev and next threads.
 	 *
-	 * NB: For the time being, only 32-bit kernels support
-	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
-	 * whether to apply espfix using paravirt hooks.  If any
-	 * non-paravirt system ever shows up that does *not* have the
-	 * ESPFIX issue, we can change this.
+	 * Since neither vendor documents this anywhere that I can see,
+	 * detect it directly instead of hardcoding the choice by
+	 * vendor.
+	 *
+	 * I've designated AMD's behavior as the "bug" because it's
+	 * counterintuitive and less friendly.
 	 */
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_PARAVIRT
-	do {
-		extern void native_iret(void);
-		if (pv_cpu_ops.iret == native_iret)
-			set_cpu_bug(c, X86_BUG_ESPFIX);
-	} while (0);
-#else
-	set_cpu_bug(c, X86_BUG_ESPFIX);
-#endif
+
+	unsigned long old_base, tmp;
+	rdmsrl(MSR_FS_BASE, old_base);
+	wrmsrl(MSR_FS_BASE, 1);
+	loadsegment(fs, 0);
+	rdmsrl(MSR_FS_BASE, tmp);
+	if (tmp != 0)
+		set_cpu_bug(c, X86_BUG_NULL_SEG);
+	wrmsrl(MSR_FS_BASE, old_base);
 #endif
 }
 
@@ -928,6 +936,33 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	get_model_name(c); /* Default name */
 
 	detect_nopl(c);
+
+	detect_null_seg_behavior(c);
+
+	/*
+	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
+	 * systems that run Linux at CPL > 0 may or may not have the
+	 * issue, but, even if they have the issue, there's absolutely
+	 * nothing we can do about it because we can't use the real IRET
+	 * instruction.
+	 *
+	 * NB: For the time being, only 32-bit kernels support
+	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
+	 * whether to apply espfix using paravirt hooks.  If any
+	 * non-paravirt system ever shows up that does *not* have the
+	 * ESPFIX issue, we can change this.
+	 */
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_PARAVIRT
+	do {
+		extern void native_iret(void);
+		if (pv_cpu_ops.iret == native_iret)
+			set_cpu_bug(c, X86_BUG_ESPFIX);
+	} while (0);
+# else
+	set_cpu_bug(c, X86_BUG_ESPFIX);
+# endif
+#endif
 }
 
 static void x86_init_cache_qos(struct cpuinfo_x86 *c)
@@ -1083,12 +1118,12 @@ void enable_sep_cpu(void)
 	struct tss_struct *tss;
 	int cpu;
 
+	if (!boot_cpu_has(X86_FEATURE_SEP))
+		return;
+
 	cpu = get_cpu();
 	tss = &per_cpu(cpu_tss, cpu);
 
-	if (!boot_cpu_has(X86_FEATURE_SEP))
-		goto out;
-
 	/*
 	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
 	 * see the big comment in struct x86_hw_tss's definition.
@@ -1103,7 +1138,6 @@ void enable_sep_cpu(void)
 
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
-out:
 	put_cpu();
 }
 #endif
@@ -1535,7 +1569,7 @@ void cpu_init(void)
 	pr_info("Initializing CPU#%d\n", cpu);
 
 	if (cpu_feature_enabled(X86_FEATURE_VME) ||
-	    cpu_has_tsc ||
+	    boot_cpu_has(X86_FEATURE_TSC) ||
 	    boot_cpu_has(X86_FEATURE_DE))
 		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 6adef9cac23e..bd9dcd6b712d 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -333,7 +333,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 		switch (dir0_lsn) {
 		case 0xd:  /* either a 486SLC or DLC w/o DEVID */
 			dir0_msn = 0;
-			p = Cx486_name[(cpu_has_fpu ? 1 : 0)];
+			p = Cx486_name[!!boot_cpu_has(X86_FEATURE_FPU)];
 			break;
 
 		case 0xe:  /* a 486S A step */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b47df99dc5d2..6e2ffbebbcdb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -187,9 +187,9 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 *  the TLB when any changes are made to any of the page table entries.
 	 *  The operating system must reload CR3 to cause the TLB to be flushed"
 	 *
-	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
-	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
-	 * to be modified
+	 * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h
+	 * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified.
 	 */
 	if (c->x86 == 5 && c->x86_model == 9) {
 		pr_info("Disabling PGE capability bit\n");
@@ -270,7 +270,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * The Quark is also family 5, but does not have the same bug.
 	 */
 	clear_cpu_bug(c, X86_BUG_F00F);
-	if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) {
+	if (c->x86 == 5 && c->x86_model < 9) {
 		static int f00f_workaround_enabled;
 
 		set_cpu_bug(c, X86_BUG_F00F);
@@ -318,7 +318,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * integrated APIC (see 11AP erratum in "Pentium Processor
 	 * Specification Update").
 	 */
-	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+	if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
 	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
 		set_cpu_bug(c, X86_BUG_11AP);
 
@@ -493,7 +493,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
 	}
 
-	if (cpu_has_xmm2)
+	if (cpu_has(c, X86_FEATURE_XMM2))
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 
 	if (boot_cpu_has(X86_FEATURE_DS)) {
@@ -505,7 +505,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
-	if (c->x86 == 6 && cpu_has_clflush &&
+	if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) &&
 	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 2658e2af74ec..93d824ec3120 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -26,6 +26,52 @@ static struct gen_pool *mce_evt_pool;
 static LLIST_HEAD(mce_event_llist);
 static char gen_pool_buf[MCE_POOLSZ];
 
+/*
+ * Compare the record "t" with each of the records on list "l" to see if
+ * an equivalent one is present in the list.
+ */
+static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l)
+{
+	struct mce_evt_llist *node;
+	struct mce *m1, *m2;
+
+	m1 = &t->mce;
+
+	llist_for_each_entry(node, &l->llnode, llnode) {
+		m2 = &node->mce;
+
+		if (!mce_cmp(m1, m2))
+			return true;
+	}
+	return false;
+}
+
+/*
+ * The system has panicked - we'd like to peruse the list of MCE records
+ * that have been queued, but not seen by anyone yet.  The list is in
+ * reverse time order, so we need to reverse it. While doing that we can
+ * also drop duplicate records (these were logged because some banks are
+ * shared between cores or by all threads on a socket).
+ */
+struct llist_node *mce_gen_pool_prepare_records(void)
+{
+	struct llist_node *head;
+	LLIST_HEAD(new_head);
+	struct mce_evt_llist *node, *t;
+
+	head = llist_del_all(&mce_event_llist);
+	if (!head)
+		return NULL;
+
+	/* squeeze out duplicates while reversing order */
+	llist_for_each_entry_safe(node, t, head, llnode) {
+		if (!is_duplicate_mce_record(node, t))
+			llist_add(&node->llnode, &new_head);
+	}
+
+	return new_head.first;
+}
+
 void mce_gen_pool_process(void)
 {
 	struct llist_node *head;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 547720efd923..cd74a3f00aea 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -35,6 +35,7 @@ void mce_gen_pool_process(void);
 bool mce_gen_pool_empty(void);
 int mce_gen_pool_add(struct mce *mce);
 int mce_gen_pool_init(void);
+struct llist_node *mce_gen_pool_prepare_records(void);
 
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
@@ -81,3 +82,17 @@ static inline int apei_clear_mce(u64 record_id)
 #endif
 
 void mce_inject_log(struct mce *m);
+
+/*
+ * We consider records to be equivalent if bank+status+addr+misc all match.
+ * This is only used when the system is going down because of a fatal error
+ * to avoid cluttering the console log with essentially repeated information.
+ * In normal processing all errors seen are logged.
+ */
+static inline bool mce_cmp(struct mce *m1, struct mce *m2)
+{
+	return m1->bank != m2->bank ||
+		m1->status != m2->status ||
+		m1->addr != m2->addr ||
+		m1->misc != m2->misc;
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 5119766d9889..631356c8cca4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -204,6 +204,33 @@ static int error_context(struct mce *m)
 	return IN_KERNEL;
 }
 
+static int mce_severity_amd_smca(struct mce *m, int err_ctx)
+{
+	u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
+	u32 low, high;
+
+	/*
+	 * We need to look at the following bits:
+	 * - "succor" bit (data poisoning support), and
+	 * - TCC bit (Task Context Corrupt)
+	 * in MCi_STATUS to determine error severity.
+	 */
+	if (!mce_flags.succor)
+		return MCE_PANIC_SEVERITY;
+
+	if (rdmsr_safe(addr, &low, &high))
+		return MCE_PANIC_SEVERITY;
+
+	/* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */
+	if ((low & MCI_CONFIG_MCAX) &&
+	    (m->status & MCI_STATUS_TCC) &&
+	    (err_ctx == IN_KERNEL))
+		return MCE_PANIC_SEVERITY;
+
+	 /* ...otherwise invoke hwpoison handler. */
+	return MCE_AR_SEVERITY;
+}
+
 /*
  * See AMD Error Scope Hierarchy table in a newer BKDG. For example
  * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features"
@@ -225,6 +252,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc
 		 * to at least kill process to prolong system operation.
 		 */
 		if (mce_flags.overflow_recov) {
+			if (mce_flags.smca)
+				return mce_severity_amd_smca(m, ctx);
+
 			/* software can try to contain */
 			if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL))
 				return MCE_PANIC_SEVERITY;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index f0c921b03e42..92e5e37d97bf 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -161,7 +161,6 @@ void mce_log(struct mce *mce)
 	if (!mce_gen_pool_add(mce))
 		irq_work_queue(&mce_irq_work);
 
-	mce->finished = 0;
 	wmb();
 	for (;;) {
 		entry = mce_log_get_idx_check(mcelog.next);
@@ -194,7 +193,6 @@ void mce_log(struct mce *mce)
 	mcelog.entry[entry].finished = 1;
 	wmb();
 
-	mce->finished = 1;
 	set_bit(0, &mce_need_notify);
 }
 
@@ -224,6 +222,53 @@ void mce_unregister_decode_chain(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
 
+static inline u32 ctl_reg(int bank)
+{
+	return MSR_IA32_MCx_CTL(bank);
+}
+
+static inline u32 status_reg(int bank)
+{
+	return MSR_IA32_MCx_STATUS(bank);
+}
+
+static inline u32 addr_reg(int bank)
+{
+	return MSR_IA32_MCx_ADDR(bank);
+}
+
+static inline u32 misc_reg(int bank)
+{
+	return MSR_IA32_MCx_MISC(bank);
+}
+
+static inline u32 smca_ctl_reg(int bank)
+{
+	return MSR_AMD64_SMCA_MCx_CTL(bank);
+}
+
+static inline u32 smca_status_reg(int bank)
+{
+	return MSR_AMD64_SMCA_MCx_STATUS(bank);
+}
+
+static inline u32 smca_addr_reg(int bank)
+{
+	return MSR_AMD64_SMCA_MCx_ADDR(bank);
+}
+
+static inline u32 smca_misc_reg(int bank)
+{
+	return MSR_AMD64_SMCA_MCx_MISC(bank);
+}
+
+struct mca_msr_regs msr_ops = {
+	.ctl	= ctl_reg,
+	.status	= status_reg,
+	.addr	= addr_reg,
+	.misc	= misc_reg
+};
+
 static void print_mce(struct mce *m)
 {
 	int ret = 0;
@@ -290,7 +335,9 @@ static void wait_for_panic(void)
 
 static void mce_panic(const char *msg, struct mce *final, char *exp)
 {
-	int i, apei_err = 0;
+	int apei_err = 0;
+	struct llist_node *pending;
+	struct mce_evt_llist *l;
 
 	if (!fake_panic) {
 		/*
@@ -307,11 +354,10 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 		if (atomic_inc_return(&mce_fake_panicked) > 1)
 			return;
 	}
+	pending = mce_gen_pool_prepare_records();
 	/* First print corrected ones that are still unlogged */
-	for (i = 0; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog.entry[i];
-		if (!(m->status & MCI_STATUS_VAL))
-			continue;
+	llist_for_each_entry(l, pending, llnode) {
+		struct mce *m = &l->mce;
 		if (!(m->status & MCI_STATUS_UC)) {
 			print_mce(m);
 			if (!apei_err)
@@ -319,13 +365,11 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 		}
 	}
 	/* Now print uncorrected but with the final one last */
-	for (i = 0; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog.entry[i];
-		if (!(m->status & MCI_STATUS_VAL))
-			continue;
+	llist_for_each_entry(l, pending, llnode) {
+		struct mce *m = &l->mce;
 		if (!(m->status & MCI_STATUS_UC))
 			continue;
-		if (!final || memcmp(m, final, sizeof(struct mce))) {
+		if (!final || mce_cmp(m, final)) {
 			print_mce(m);
 			if (!apei_err)
 				apei_err = apei_write_mce(m);
@@ -356,11 +400,11 @@ static int msr_to_offset(u32 msr)
 
 	if (msr == mca_cfg.rip_msr)
 		return offsetof(struct mce, ip);
-	if (msr == MSR_IA32_MCx_STATUS(bank))
+	if (msr == msr_ops.status(bank))
 		return offsetof(struct mce, status);
-	if (msr == MSR_IA32_MCx_ADDR(bank))
+	if (msr == msr_ops.addr(bank))
 		return offsetof(struct mce, addr);
-	if (msr == MSR_IA32_MCx_MISC(bank))
+	if (msr == msr_ops.misc(bank))
 		return offsetof(struct mce, misc);
 	if (msr == MSR_IA32_MCG_STATUS)
 		return offsetof(struct mce, mcgstatus);
@@ -523,9 +567,9 @@ static struct notifier_block mce_srao_nb = {
 static void mce_read_aux(struct mce *m, int i)
 {
 	if (m->status & MCI_STATUS_MISCV)
-		m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
+		m->misc = mce_rdmsrl(msr_ops.misc(i));
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+		m->addr = mce_rdmsrl(msr_ops.addr(i));
 
 		/*
 		 * Mask the reported address by the reported granularity.
@@ -607,7 +651,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m.tsc = 0;
 
 		barrier();
-		m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+		m.status = mce_rdmsrl(msr_ops.status(i));
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
@@ -654,7 +698,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		/*
 		 * Clear state for this bank.
 		 */
-		mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+		mce_wrmsrl(msr_ops.status(i), 0);
 	}
 
 	/*
@@ -679,7 +723,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 	char *tmp;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
-		m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+		m->status = mce_rdmsrl(msr_ops.status(i));
 		if (m->status & MCI_STATUS_VAL) {
 			__set_bit(i, validp);
 			if (quirk_no_way_out)
@@ -830,9 +874,9 @@ static int mce_start(int *no_way_out)
 
 	atomic_add(*no_way_out, &global_nwo);
 	/*
-	 * global_nwo should be updated before mce_callin
+	 * Rely on the implied barrier below, such that global_nwo
+	 * is updated before mce_callin.
 	 */
-	smp_wmb();
 	order = atomic_inc_return(&mce_callin);
 
 	/*
@@ -957,7 +1001,7 @@ static void mce_clear_state(unsigned long *toclear)
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		if (test_bit(i, toclear))
-			mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+			mce_wrmsrl(msr_ops.status(i), 0);
 	}
 }
 
@@ -994,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int i;
 	int worst = 0;
 	int severity;
+
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
-	int order;
+	int order = -1;
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
@@ -1012,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
-	int lmce = 0;
+
+	/*
+	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
+	 * on Intel.
+	 */
+	int lmce = 1;
 
 	/* If this CPU is offline, just bail out. */
 	if (cpu_is_offline(smp_processor_id())) {
@@ -1051,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Check if this MCE is signaled to only this logical processor
+	 * Check if this MCE is signaled to only this logical processor,
+	 * on Intel only.
 	 */
-	if (m.mcgstatus & MCG_STATUS_LMCES)
-		lmce = 1;
-	else {
-		/*
-		 * Go through all the banks in exclusion of the other CPUs.
-		 * This way we don't report duplicated events on shared banks
-		 * because the first one to see it will clear it.
-		 * If this is a Local MCE, then no need to perform rendezvous.
-		 */
+	if (m.cpuvendor == X86_VENDOR_INTEL)
+		lmce = m.mcgstatus & MCG_STATUS_LMCES;
+
+	/*
+	 * Go through all banks in exclusion of the other CPUs. This way we
+	 * don't report duplicated events on shared banks because the first one
+	 * to see it will clear it. If this is a Local MCE, then no need to
+	 * perform rendezvous.
+	 */
+	if (!lmce)
 		order = mce_start(&no_way_out);
-	}
 
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);
@@ -1076,7 +1127,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		m.addr = 0;
 		m.bank = i;
 
-		m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+		m.status = mce_rdmsrl(msr_ops.status(i));
 		if ((m.status & MCI_STATUS_VAL) == 0)
 			continue;
 
@@ -1420,7 +1471,6 @@ static void __mcheck_cpu_init_generic(void)
 	enum mcp_flags m_fl = 0;
 	mce_banks_t all_banks;
 	u64 cap;
-	int i;
 
 	if (!mca_cfg.bootlog)
 		m_fl = MCP_DONTLOG;
@@ -1436,14 +1486,19 @@ static void __mcheck_cpu_init_generic(void)
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (cap & MCG_CTL_P)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+}
+
+static void __mcheck_cpu_init_clear_banks(void)
+{
+	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (!b->init)
 			continue;
-		wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
-		wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+		wrmsrl(msr_ops.ctl(i), b->ctl);
+		wrmsrl(msr_ops.status(i), 0);
 	}
 }
 
@@ -1495,7 +1550,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 			 */
 			clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
 		}
-		if (c->x86 <= 17 && cfg->bootlog < 0) {
+		if (c->x86 < 17 && cfg->bootlog < 0) {
 			/*
 			 * Lots of broken BIOS around that don't clear them
 			 * by default and leave crap in there. Don't log:
@@ -1628,11 +1683,19 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		break;
 
 	case X86_VENDOR_AMD: {
-		u32 ebx = cpuid_ebx(0x80000007);
+		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
+		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
+		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);
 
-		mce_flags.overflow_recov = !!(ebx & BIT(0));
-		mce_flags.succor	 = !!(ebx & BIT(1));
-		mce_flags.smca		 = !!(ebx & BIT(3));
+		/*
+		 * Install proper ops for Scalable MCA enabled processors
+		 */
+		if (mce_flags.smca) {
+			msr_ops.ctl	= smca_ctl_reg;
+			msr_ops.status	= smca_status_reg;
+			msr_ops.addr	= smca_addr_reg;
+			msr_ops.misc	= smca_misc_reg;
+		}
 		mce_amd_feature_init(c);
 
 		break;
@@ -1717,6 +1780,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
+	__mcheck_cpu_init_clear_banks();
 	__mcheck_cpu_init_timer();
 }
 
@@ -2082,7 +2146,7 @@ static void mce_disable_error_reporting(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(MSR_IA32_MCx_CTL(i), 0);
+			wrmsrl(msr_ops.ctl(i), 0);
 	}
 	return;
 }
@@ -2121,6 +2185,7 @@ static void mce_syscore_resume(void)
 {
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
+	__mcheck_cpu_init_clear_banks();
 }
 
 static struct syscore_ops mce_syscore_ops = {
@@ -2138,6 +2203,7 @@ static void mce_cpu_restart(void *data)
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
+	__mcheck_cpu_init_clear_banks();
 	__mcheck_cpu_init_timer();
 }
 
@@ -2413,7 +2479,7 @@ static void mce_reenable_cpu(void *h)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
+			wrmsrl(msr_ops.ctl(i), b->ctl);
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 9d656fd436ef..10b0661651e0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -54,14 +54,6 @@
 /* Threshold LVT offset is at MSR0xC0000410[15:12] */
 #define SMCA_THR_LVT_OFF	0xF000
 
-/*
- * OS is required to set the MCAX bit to acknowledge that it is now using the
- * new MSR ranges and new registers under each bank. It also means that the OS
- * will configure deferred errors in the new MCx_CONFIG register. If the bit is
- * not set, uncorrectable errors will cause a system panic.
- */
-#define SMCA_MCAX_EN_OFF	0x1
-
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -333,7 +325,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 	/* Fall back to method we used for older processors: */
 	switch (block) {
 	case 0:
-		addr = MSR_IA32_MCx_MISC(bank);
+		addr = msr_ops.misc(bank);
 		break;
 	case 1:
 		offset = ((low & MASK_BLKPTR_LO) >> 21);
@@ -351,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 			int offset, u32 misc_high)
 {
 	unsigned int cpu = smp_processor_id();
+	u32 smca_low, smca_high, smca_addr;
 	struct threshold_block b;
 	int new;
 
@@ -369,24 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 
 	b.interrupt_enable = 1;
 
-	if (mce_flags.smca) {
-		u32 smca_low, smca_high;
-		u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
+	if (!mce_flags.smca) {
+		new = (misc_high & MASK_LVTOFF_HI) >> 20;
+		goto set_offset;
+	}
 
-		if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
-			smca_high |= SMCA_MCAX_EN_OFF;
-			wrmsr(smca_addr, smca_low, smca_high);
-		}
+	smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
 
-		/* Gather LVT offset for thresholding: */
-		if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
-			goto out;
+	if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
+		/*
+		 * OS is required to set the MCAX bit to acknowledge that it is
+		 * now using the new MSR ranges and new registers under each
+		 * bank. It also means that the OS will configure deferred
+		 * errors in the new MCx_CONFIG register. If the bit is not set,
+		 * uncorrectable errors will cause a system panic.
+		 *
+		 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.)
+		 */
+		smca_high |= BIT(0);
 
-		new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
-	} else {
-		new = (misc_high & MASK_LVTOFF_HI) >> 20;
+		/*
+		 * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR}
+		 * registers with the option of additionally logging to
+		 * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set.
+		 *
+		 * This bit is usually set by BIOS to retain the old behavior
+		 * for OSes that don't use the new registers. Linux supports the
+		 * new registers so let's disable that additional logging here.
+		 *
+		 * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high
+		 * portion of the MSR).
+		 */
+		smca_high &= ~BIT(2);
+
+		wrmsr(smca_addr, smca_low, smca_high);
 	}
 
+	/* Gather LVT offset for thresholding: */
+	if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
+		goto out;
+
+	new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
+
+set_offset:
 	offset = setup_APIC_mce_threshold(offset, new);
 
 	if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt))
@@ -430,12 +448,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		deferred_error_interrupt_enable(c);
 }
 
-static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+static void
+__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
 {
+	u32 msr_status = msr_ops.status(bank);
+	u32 msr_addr = msr_ops.addr(bank);
 	struct mce m;
 	u64 status;
 
-	rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+	WARN_ON_ONCE(deferred_err && threshold_err);
+
+	if (deferred_err && mce_flags.smca) {
+		msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank);
+		msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank);
+	}
+
+	rdmsrl(msr_status, status);
+
 	if (!(status & MCI_STATUS_VAL))
 		return;
 
@@ -448,10 +477,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
 		m.misc = misc;
 
 	if (m.status & MCI_STATUS_ADDRV)
-		rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+		rdmsrl(msr_addr, m.addr);
 
 	mce_log(&m);
-	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+
+	wrmsrl(msr_status, 0);
 }
 
 static inline void __smp_deferred_error_interrupt(void)
@@ -479,17 +509,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
 /* APIC interrupt handler for deferred errors */
 static void amd_deferred_error_interrupt(void)
 {
-	u64 status;
 	unsigned int bank;
+	u32 msr_status;
+	u64 status;
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
-		rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+		msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank)
+					      : msr_ops.status(bank);
+
+		rdmsrl(msr_status, status);
 
 		if (!(status & MCI_STATUS_VAL) ||
 		    !(status & MCI_STATUS_DEFERRED))
 			continue;
 
-		__log_error(bank, false, 0);
+		__log_error(bank, true, false, 0);
 		break;
 	}
 }
@@ -544,7 +578,7 @@ static void amd_threshold_interrupt(void)
 	return;
 
 log:
-	__log_error(bank, true, ((u64)high << 32) | low);
+	__log_error(bank, false, true, ((u64)high << 32) | low);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 1e8bb6c94f14..1defb8ea882c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -84,7 +84,7 @@ static int cmci_supported(int *banks)
 	 */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 0;
-	if (!cpu_has_apic || lapic_get_maxlvt() < 6)
+	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return 0;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	*banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff);
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index ac780cad3b86..6b9dc4d18ccc 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -450,7 +450,7 @@ asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs)
 /* Thermal monitoring depends on APIC, ACPI and clock modulation */
 static int intel_thermal_supported(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return 0;
 	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
 		return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index f8c81ba0b465..b1086f79e57e 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -137,7 +137,7 @@ static void prepare_set(void)
 	u32 cr0;
 
 	/*  Save value of CR4 and clear Page Global Enable (bit 7)  */
-	if (cpu_has_pge) {
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4 = __read_cr4();
 		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
@@ -170,7 +170,7 @@ static void post_set(void)
 	write_cr0(read_cr0() & ~X86_CR0_CD);
 
 	/* Restore value of CR4 */
-	if (cpu_has_pge)
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		__write_cr4(cr4);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 19f57360dfd2..16e37a2581ac 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@ static void __init print_mtrr_state(void)
 		pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
 }
 
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	prepare_set();
+
+	pat_init();
+
+	post_set();
+	local_irq_restore(flags);
+}
+
 /* Grab all of the MTRR state for this CPU into *state */
 bool __init get_mtrr_state(void)
 {
 	struct mtrr_var_range *vrs;
-	unsigned long flags;
 	unsigned lo, dummy;
 	unsigned int i;
 
@@ -481,15 +494,6 @@ bool __init get_mtrr_state(void)
 
 	mtrr_state_set = 1;
 
-	/* PAT setup for BP. We need to go through sync steps here */
-	local_irq_save(flags);
-	prepare_set();
-
-	pat_init();
-
-	post_set();
-	local_irq_restore(flags);
-
 	return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
 }
 
@@ -741,7 +745,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	wbinvd();
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
-	if (cpu_has_pge) {
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4 = __read_cr4();
 		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
@@ -771,7 +775,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 	write_cr0(read_cr0() & ~X86_CR0_CD);
 
 	/* Restore value of CR4 */
-	if (cpu_has_pge)
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		__write_cr4(cr4);
 	raw_spin_unlock(&set_atomicity_lock);
 }
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 10f8d4796240..7d393ecdeee6 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@ void __init mtrr_bp_init(void)
 			/* BIOS may override */
 			__mtrr_enabled = get_mtrr_state();
 
+			if (mtrr_enabled())
+				mtrr_bp_pat_init();
+
 			if (mtrr_cleanup(phys_addr)) {
 				changed_by_mtrr_cleanup = 1;
 				mtrr_if->set_all();
@@ -759,8 +762,16 @@ void __init mtrr_bp_init(void)
 		}
 	}
 
-	if (!mtrr_enabled())
+	if (!mtrr_enabled()) {
 		pr_info("MTRR: Disabled\n");
+
+		/*
+		 * PAT initialization relies on MTRR's rendezvous handler.
+		 * Skip PAT init until the handler can initialize both
+		 * features independently.
+		 */
+		pat_disable("MTRRs disabled, skipping PAT initialization too.");
+	}
 }
 
 void mtrr_ap_init(void)
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884dcc433..6c7ced07d16d 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
 bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
 
 extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 364e58346897..8cac429b6a1d 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -94,7 +94,7 @@ static void __init vmware_platform_setup(void)
  */
 static uint32_t __init vmware_platform(void)
 {
-	if (cpu_has_hypervisor) {
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
 		unsigned int eax;
 		unsigned int hyper_vendor_id[3];
 
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 1f4acd68b98b..3fe45f84ced4 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -151,7 +151,7 @@ static void __init dtb_lapic_setup(void)
 		return;
 
 	/* Did the boot loader setup the local APIC ? */
-	if (!cpu_has_apic) {
+	if (!boot_cpu_has(X86_FEATURE_APIC)) {
 		if (apic_force_enable(r.start))
 			return;
 	}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 8efa57a5f29e..2bb25c3fe2e8 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -260,19 +260,12 @@ int __die(const char *str, struct pt_regs *regs, long err)
 	unsigned long sp;
 #endif
 	printk(KERN_DEFAULT
-	       "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-	printk("SMP ");
-#endif
-	if (debug_pagealloc_enabled())
-		printk("DEBUG_PAGEALLOC ");
-#ifdef CONFIG_KASAN
-	printk("KASAN");
-#endif
-	printk("\n");
+	       "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT"         : "",
+	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
+	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
+	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "");
+
 	if (notify_die(DIE_OOPS, str, regs, err,
 			current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
 		return 1;
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/ebda.c
index 992f442ca155..afe65dffee80 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/ebda.c
@@ -38,7 +38,7 @@ void __init reserve_ebda_region(void)
 	 * that the paravirt case can handle memory setup
 	 * correctly, without our help.
 	 */
-	if (paravirt_enabled())
+	if (!x86_platform.legacy.ebda_search)
 		return;
 
 	/* end of low (conventional) memory */
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
index dd9ca9b60ff3..aad34aafc0e0 100644
--- a/arch/x86/kernel/fpu/bugs.c
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -21,11 +21,15 @@ static double __initdata y = 3145727.0;
  * We should really only care about bugs here
  * anyway. Not features.
  */
-static void __init check_fpu(void)
+void __init fpu__init_check_bugs(void)
 {
 	u32 cr0_saved;
 	s32 fdiv_bug;
 
+	/* kernel_fpu_begin/end() relies on patched alternative instructions. */
+	if (!boot_cpu_has(X86_FEATURE_FPU))
+		return;
+
 	/* We might have CR0::TS set already, clear it: */
 	cr0_saved = read_cr0();
 	write_cr0(cr0_saved & ~X86_CR0_TS);
@@ -59,13 +63,3 @@ static void __init check_fpu(void)
 		pr_warn("Hmm, FPU with FDIV bug\n");
 	}
 }
-
-void __init fpu__init_check_bugs(void)
-{
-	/*
-	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
-	 * alternative instructions.
-	 */
-	if (cpu_has_fpu)
-		check_fpu();
-}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8e37cc8a539a..97027545a72d 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -217,14 +217,14 @@ static inline void fpstate_init_fstate(struct fregs_state *fp)
 
 void fpstate_init(union fpregs_state *state)
 {
-	if (!cpu_has_fpu) {
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
 		fpstate_init_soft(&state->soft);
 		return;
 	}
 
 	memset(state, 0, xstate_size);
 
-	if (cpu_has_fxsr)
+	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
 	else
 		fpstate_init_fstate(&state->fsave);
@@ -237,7 +237,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->fpstate_active || !cpu_has_fpu)
+	if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -506,33 +506,6 @@ void fpu__clear(struct fpu *fpu)
  * x87 math exception handling:
  */
 
-static inline unsigned short get_fpu_cwd(struct fpu *fpu)
-{
-	if (cpu_has_fxsr) {
-		return fpu->state.fxsave.cwd;
-	} else {
-		return (unsigned short)fpu->state.fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct fpu *fpu)
-{
-	if (cpu_has_fxsr) {
-		return fpu->state.fxsave.swd;
-	} else {
-		return (unsigned short)fpu->state.fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
-{
-	if (cpu_has_xmm) {
-		return fpu->state.fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
 int fpu__exception_code(struct fpu *fpu, int trap_nr)
 {
 	int err;
@@ -547,10 +520,15 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 		 * so if this combination doesn't produce any single exception,
 		 * then we have a bad program that isn't synchronizing its FPU usage
 		 * and it will suffer the consequences since we won't be able to
-		 * fully reproduce the context of the exception
+		 * fully reproduce the context of the exception.
 		 */
-		cwd = get_fpu_cwd(fpu);
-		swd = get_fpu_swd(fpu);
+		if (boot_cpu_has(X86_FEATURE_FXSR)) {
+			cwd = fpu->state.fxsave.cwd;
+			swd = fpu->state.fxsave.swd;
+		} else {
+			cwd = (unsigned short)fpu->state.fsave.cwd;
+			swd = (unsigned short)fpu->state.fsave.swd;
+		}
 
 		err = swd & ~cwd;
 	} else {
@@ -560,7 +538,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 		 * unmasked exception was caught we must mask the exception mask bits
 		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
 		 */
-		unsigned short mxcsr = get_fpu_mxcsr(fpu);
+		unsigned short mxcsr = MXCSR_DEFAULT;
+
+		if (boot_cpu_has(X86_FEATURE_XMM))
+			mxcsr = fpu->state.fxsave.mxcsr;
+
 		err = ~(mxcsr >> 7) & mxcsr;
 	}
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 54c86fffbf9f..aacfd7a82cec 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -29,22 +29,22 @@ static void fpu__init_cpu_generic(void)
 	unsigned long cr0;
 	unsigned long cr4_mask = 0;
 
-	if (cpu_has_fxsr)
+	if (boot_cpu_has(X86_FEATURE_FXSR))
 		cr4_mask |= X86_CR4_OSFXSR;
-	if (cpu_has_xmm)
+	if (boot_cpu_has(X86_FEATURE_XMM))
 		cr4_mask |= X86_CR4_OSXMMEXCPT;
 	if (cr4_mask)
 		cr4_set_bits(cr4_mask);
 
 	cr0 = read_cr0();
 	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
-	if (!cpu_has_fpu)
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		cr0 |= X86_CR0_EM;
 	write_cr0(cr0);
 
 	/* Flush out any pending x87 state: */
 #ifdef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu)
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		fpstate_init_soft(&current->thread.fpu.state.soft);
 	else
 #endif
@@ -89,7 +89,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
 	}
 
 #ifndef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu) {
+	if (!boot_cpu_has(X86_FEATURE_FPU)) {
 		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
 		for (;;)
 			asm volatile("hlt");
@@ -106,7 +106,7 @@ static void __init fpu__init_system_mxcsr(void)
 {
 	unsigned int mask = 0;
 
-	if (cpu_has_fxsr) {
+	if (boot_cpu_has(X86_FEATURE_FXSR)) {
 		/* Static because GCC does not get 16-byte stack alignment right: */
 		static struct fxregs_state fxregs __initdata;
 
@@ -212,7 +212,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	 * fpu__init_system_xstate().
 	 */
 
-	if (!cpu_has_fpu) {
+	if (!boot_cpu_has(X86_FEATURE_FPU)) {
 		/*
 		 * Disable xsave as we do not support it if i387
 		 * emulation is enabled.
@@ -221,7 +221,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 		xstate_size = sizeof(struct swregs_state);
 	} else {
-		if (cpu_has_fxsr)
+		if (boot_cpu_has(X86_FEATURE_FXSR))
 			xstate_size = sizeof(struct fxregs_state);
 		else
 			xstate_size = sizeof(struct fregs_state);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 8bd1c003942a..81422dfb152b 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -21,7 +21,10 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r
 {
 	struct fpu *target_fpu = &target->thread.fpu;
 
-	return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active)
+		return regset->n;
+	else
+		return 0;
 }
 
 int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
@@ -30,7 +33,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 {
 	struct fpu *fpu = &target->thread.fpu;
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
 	fpu__activate_fpstate_read(fpu);
@@ -47,7 +50,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct fpu *fpu = &target->thread.fpu;
 	int ret;
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
 	fpu__activate_fpstate_write(fpu);
@@ -65,7 +68,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	 * update the header bits in the xsave header, indicating the
 	 * presence of FP and SSE state.
 	 */
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
 
 	return ret;
@@ -79,7 +82,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 	struct xregs_state *xsave;
 	int ret;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
 	fpu__activate_fpstate_read(fpu);
@@ -108,7 +111,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct xregs_state *xsave;
 	int ret;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
 	fpu__activate_fpstate_write(fpu);
@@ -275,10 +278,10 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 
 	fpu__activate_fpstate_read(fpu);
 
-	if (!static_cpu_has(X86_FEATURE_FPU))
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 					   &fpu->state.fsave, 0,
 					   -1);
@@ -306,10 +309,10 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	fpu__activate_fpstate_write(fpu);
 	fpstate_sanitize_xstate(fpu);
 
-	if (!static_cpu_has(X86_FEATURE_FPU))
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					  &fpu->state.fsave, 0,
 					  -1);
@@ -325,7 +328,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	 * update the header bit in the xsave header, indicating the
 	 * presence of FP.
 	 */
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP;
 	return ret;
 }
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index b48ef35b28d4..4ea2a59483c7 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -190,7 +190,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
  */
 void fpu__init_cpu_xstate(void)
 {
-	if (!cpu_has_xsave || !xfeatures_mask)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask)
 		return;
 
 	cr4_set_bits(X86_CR4_OSXSAVE);
@@ -280,7 +280,7 @@ static void __init setup_xstate_comp(void)
 	xstate_comp_offsets[0] = 0;
 	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
 
-	if (!cpu_has_xsaves) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
 		for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 			if (xfeature_enabled(i)) {
 				xstate_comp_offsets[i] = xstate_offsets[i];
@@ -316,13 +316,13 @@ static void __init setup_init_fpu_buf(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return;
 
 	setup_xstate_features();
 	print_xstate_features();
 
-	if (cpu_has_xsaves) {
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
 		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
 		init_fpstate.xsave.header.xfeatures = xfeatures_mask;
 	}
@@ -417,7 +417,7 @@ static int xfeature_size(int xfeature_nr)
  */
 static int using_compacted_format(void)
 {
-	return cpu_has_xsaves;
+	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
 static void __xstate_dump_leaves(void)
@@ -549,7 +549,7 @@ static unsigned int __init calculate_xstate_size(void)
 	unsigned int eax, ebx, ecx, edx;
 	unsigned int calculated_xstate_size;
 
-	if (!cpu_has_xsaves) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
 		/*
 		 * - CPUID function 0DH, sub-function 0:
 		 *    EBX enumerates the size (in bytes) required by
@@ -630,7 +630,7 @@ void __init fpu__init_system_xstate(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
-	if (!cpu_has_xsave) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
 		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
 		return;
 	}
@@ -667,7 +667,7 @@ void __init fpu__init_system_xstate(void)
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		xfeatures_mask,
 		xstate_size,
-		cpu_has_xsaves ? "compacted" : "standard");
+		boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
 }
 
 /*
@@ -678,7 +678,7 @@ void fpu__resume_cpu(void)
 	/*
 	 * Restore XCR0 on xsave capable CPUs:
 	 */
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
 }
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 2911ef3a9f1c..d784bb547a9d 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -34,6 +34,8 @@ asmlinkage __visible void __init i386_start_kernel(void)
 	cr4_init_shadow();
 	sanitize_boot_params(&boot_params);
 
+	x86_early_init_platform_quirks();
+
 	/* Call the subarch specific early setup function */
 	switch (boot_params.hdr.hardware_subarch) {
 	case X86_SUBARCH_INTEL_MID:
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 1f4422d5c8d0..b72fb0b71dd1 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -182,6 +182,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 	if (!boot_params.hdr.version)
 		copy_bootdata(__va(real_mode_data));
 
+	x86_early_init_platform_quirks();
 	reserve_ebda_region();
 
 	switch (boot_params.hdr.hardware_subarch) {
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index af1112980dd4..6f8902b0d151 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -555,62 +555,53 @@ early_idt_handler_common:
 	 */
 	cld
 
-	cmpl $2,(%esp)		# X86_TRAP_NMI
-	je .Lis_nmi		# Ignore NMI
-
-	cmpl $2,%ss:early_recursion_flag
-	je hlt_loop
 	incl %ss:early_recursion_flag
 
-	push %eax		# 16(%esp)
-	push %ecx		# 12(%esp)
-	push %edx		#  8(%esp)
-	push %ds		#  4(%esp)
-	push %es		#  0(%esp)
-	movl $(__KERNEL_DS),%eax
-	movl %eax,%ds
-	movl %eax,%es
-
-	cmpl $(__KERNEL_CS),32(%esp)
-	jne 10f
+	/* The vector number is in pt_regs->gs */
 
-	leal 28(%esp),%eax	# Pointer to %eip
-	call early_fixup_exception
-	andl %eax,%eax
-	jnz ex_entry		/* found an exception entry */
-
-10:
-#ifdef CONFIG_PRINTK
-	xorl %eax,%eax
-	movw %ax,2(%esp)	/* clean up the segment values on some cpus */
-	movw %ax,6(%esp)
-	movw %ax,34(%esp)
-	leal  40(%esp),%eax
-	pushl %eax		/* %esp before the exception */
-	pushl %ebx
-	pushl %ebp
-	pushl %esi
-	pushl %edi
-	movl %cr2,%eax
-	pushl %eax
-	pushl (20+6*4)(%esp)	/* trapno */
-	pushl $fault_msg
-	call printk
-#endif
-	call dump_stack
-hlt_loop:
-	hlt
-	jmp hlt_loop
-
-ex_entry:
-	pop %es
-	pop %ds
-	pop %edx
-	pop %ecx
-	pop %eax
-	decl %ss:early_recursion_flag
-.Lis_nmi:
-	addl $8,%esp		/* drop vector number and error code */
+	cld
+	pushl	%fs		/* pt_regs->fs */
+	movw	$0, 2(%esp)	/* clear high bits (some CPUs leave garbage) */
+	pushl	%es		/* pt_regs->es */
+	movw	$0, 2(%esp)	/* clear high bits (some CPUs leave garbage) */
+	pushl	%ds		/* pt_regs->ds */
+	movw	$0, 2(%esp)	/* clear high bits (some CPUs leave garbage) */
+	pushl	%eax		/* pt_regs->ax */
+	pushl	%ebp		/* pt_regs->bp */
+	pushl	%edi		/* pt_regs->di */
+	pushl	%esi		/* pt_regs->si */
+	pushl	%edx		/* pt_regs->dx */
+	pushl	%ecx		/* pt_regs->cx */
+	pushl	%ebx		/* pt_regs->bx */
+
+	/* Fix up DS and ES */
+	movl	$(__KERNEL_DS), %ecx
+	movl	%ecx, %ds
+	movl	%ecx, %es
+
+	/* Load the vector number into EDX */
+	movl	PT_GS(%esp), %edx
+
+	/* Load GS into pt_regs->gs and clear high bits */
+	movw	%gs, PT_GS(%esp)
+	movw	$0, PT_GS+2(%esp)
+
+	movl	%esp, %eax	/* args are pt_regs (EAX), trapnr (EDX) */
+	call	early_fixup_exception
+
+	popl	%ebx		/* pt_regs->bx */
+	popl	%ecx		/* pt_regs->cx */
+	popl	%edx		/* pt_regs->dx */
+	popl	%esi		/* pt_regs->si */
+	popl	%edi		/* pt_regs->di */
+	popl	%ebp		/* pt_regs->bp */
+	popl	%eax		/* pt_regs->ax */
+	popl	%ds		/* pt_regs->ds */
+	popl	%es		/* pt_regs->es */
+	popl	%fs		/* pt_regs->fs */
+	popl	%gs		/* pt_regs->gs */
+	decl	%ss:early_recursion_flag
+	addl	$4, %esp	/* pop pt_regs->orig_ax */
 	iret
 ENDPROC(early_idt_handler_common)
 
@@ -647,10 +638,14 @@ ignore_int:
 	popl %eax
 #endif
 	iret
+
+hlt_loop:
+	hlt
+	jmp hlt_loop
 ENDPROC(ignore_int)
 __INITDATA
 	.align 4
-early_recursion_flag:
+GLOBAL(early_recursion_flag)
 	.long 0
 
 __REFDATA
@@ -715,19 +710,6 @@ __INITRODATA
 int_msg:
 	.asciz "Unknown interrupt or fault at: %p %p %p\n"
 
-fault_msg:
-/* fault info: */
-	.ascii "BUG: Int %d: CR2 %p\n"
-/* regs pushed in early_idt_handler: */
-	.ascii "     EDI %p  ESI %p  EBP %p  EBX %p\n"
-	.ascii "     ESP %p   ES %p   DS %p\n"
-	.ascii "     EDX %p  ECX %p  EAX %p\n"
-/* fault frame: */
-	.ascii "     vec %p  err %p  EIP %p   CS %p  flg %p\n"
-	.ascii "Stack: %p %p %p %p %p %p %p %p\n"
-	.ascii "       %p %p %p %p %p %p %p %p\n"
-	.asciz "       %p %p %p %p %p %p %p %p\n"
-
 #include "../../x86/xen/xen-head.S"
 
 /*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 22fbf9df61bb..5df831ef1442 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -20,6 +20,7 @@
 #include <asm/processor-flags.h>
 #include <asm/percpu.h>
 #include <asm/nops.h>
+#include "../entry/calling.h"
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -64,6 +65,14 @@ startup_64:
 	 * tables and then reload them.
 	 */
 
+	/*
+	 * Setup stack for verify_cpu(). "-8" because stack_start is defined
+	 * this way, see below. Our best guess is a NULL ptr for stack
+	 * termination heuristics and we don't want to break anything which
+	 * might depend on it (kgdb, ...).
+	 */
+	leaq	(__end_init_task - 8)(%rip), %rsp
+
 	/* Sanitize CPU configuration */
 	call verify_cpu
 
@@ -350,90 +359,48 @@ early_idt_handler_common:
 	 */
 	cld
 
-	cmpl $2,(%rsp)		# X86_TRAP_NMI
-	je .Lis_nmi		# Ignore NMI
-
-	cmpl $2,early_recursion_flag(%rip)
-	jz  1f
 	incl early_recursion_flag(%rip)
 
-	pushq %rax		# 64(%rsp)
-	pushq %rcx		# 56(%rsp)
-	pushq %rdx		# 48(%rsp)
-	pushq %rsi		# 40(%rsp)
-	pushq %rdi		# 32(%rsp)
-	pushq %r8		# 24(%rsp)
-	pushq %r9		# 16(%rsp)
-	pushq %r10		#  8(%rsp)
-	pushq %r11		#  0(%rsp)
-
-	cmpl $__KERNEL_CS,96(%rsp)
-	jne 11f
-
-	cmpl $14,72(%rsp)	# Page fault?
+	/* The vector number is currently in the pt_regs->di slot. */
+	pushq %rsi				/* pt_regs->si */
+	movq 8(%rsp), %rsi			/* RSI = vector number */
+	movq %rdi, 8(%rsp)			/* pt_regs->di = RDI */
+	pushq %rdx				/* pt_regs->dx */
+	pushq %rcx				/* pt_regs->cx */
+	pushq %rax				/* pt_regs->ax */
+	pushq %r8				/* pt_regs->r8 */
+	pushq %r9				/* pt_regs->r9 */
+	pushq %r10				/* pt_regs->r10 */
+	pushq %r11				/* pt_regs->r11 */
+	pushq %rbx				/* pt_regs->bx */
+	pushq %rbp				/* pt_regs->bp */
+	pushq %r12				/* pt_regs->r12 */
+	pushq %r13				/* pt_regs->r13 */
+	pushq %r14				/* pt_regs->r14 */
+	pushq %r15				/* pt_regs->r15 */
+
+	cmpq $14,%rsi		/* Page fault? */
 	jnz 10f
-	GET_CR2_INTO(%rdi)	# can clobber any volatile register if pv
+	GET_CR2_INTO(%rdi)	/* Can clobber any volatile register if pv */
 	call early_make_pgtable
 	andl %eax,%eax
-	jz 20f			# All good
+	jz 20f			/* All good */
 
 10:
-	leaq 88(%rsp),%rdi	# Pointer to %rip
+	movq %rsp,%rdi		/* RDI = pt_regs; RSI is already trapnr */
 	call early_fixup_exception
-	andl %eax,%eax
-	jnz 20f			# Found an exception entry
-
-11:
-#ifdef CONFIG_EARLY_PRINTK
-	GET_CR2_INTO(%r9)	# can clobber any volatile register if pv
-	movl 80(%rsp),%r8d	# error code
-	movl 72(%rsp),%esi	# vector number
-	movl 96(%rsp),%edx	# %cs
-	movq 88(%rsp),%rcx	# %rip
-	xorl %eax,%eax
-	leaq early_idt_msg(%rip),%rdi
-	call early_printk
-	cmpl $2,early_recursion_flag(%rip)
-	jz  1f
-	call dump_stack
-#ifdef CONFIG_KALLSYMS	
-	leaq early_idt_ripmsg(%rip),%rdi
-	movq 40(%rsp),%rsi	# %rip again
-	call __print_symbol
-#endif
-#endif /* EARLY_PRINTK */
-1:	hlt
-	jmp 1b
-
-20:	# Exception table entry found or page table generated
-	popq %r11
-	popq %r10
-	popq %r9
-	popq %r8
-	popq %rdi
-	popq %rsi
-	popq %rdx
-	popq %rcx
-	popq %rax
+
+20:
 	decl early_recursion_flag(%rip)
-.Lis_nmi:
-	addq $16,%rsp		# drop vector number and error code
-	INTERRUPT_RETURN
+	jmp restore_regs_and_iret
 ENDPROC(early_idt_handler_common)
 
 	__INITDATA
 
 	.balign 4
-early_recursion_flag:
+GLOBAL(early_recursion_flag)
 	.long 0
 
-#ifdef CONFIG_EARLY_PRINTK
-early_idt_msg:
-	.asciz "PANIC: early exception %02lx rip %lx:%lx error %lx cr2 %lx\n"
-early_idt_ripmsg:
-	.asciz "RIP %s\n"
-#endif /* CONFIG_EARLY_PRINTK */
-
 #define NEXT_PAGE(name) \
 	.balign	PAGE_SIZE; \
 GLOBAL(name)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index a1f0e4a5c47e..f112af7aa62e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -54,7 +54,7 @@ struct hpet_dev {
 	char				name[10];
 };
 
-inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev)
+static inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev)
 {
 	return container_of(evtdev, struct hpet_dev, evt);
 }
@@ -773,7 +773,6 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	.resume		= hpet_resume_counter,
-	.archdata	= { .vclock_mode = VCLOCK_HPET },
 };
 
 static int hpet_clocksource_register(void)
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index e565e0e4d216..fc25f698d792 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -13,6 +13,7 @@
 #include <linux/cpu.h>
 #include <asm/kprobes.h>
 #include <asm/alternative.h>
+#include <asm/text-patching.h>
 
 #ifdef HAVE_JUMP_LABEL
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 2da6ee9ae69b..04cde527d728 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -45,6 +45,7 @@
 #include <linux/uaccess.h>
 #include <linux/memory.h>
 
+#include <asm/text-patching.h>
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
 #include <asm/apic.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index ae703acb85c1..38cf7a741250 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -51,6 +51,7 @@
 #include <linux/ftrace.h>
 #include <linux/frame.h>
 
+#include <asm/text-patching.h>
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7b3b9d15c47a..4425f593f0ec 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -29,6 +29,7 @@
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
 
+#include <asm/text-patching.h>
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 807950860fb7..eea2a6f72b31 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -285,14 +285,6 @@ static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
 
-	/*
-	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
-	 * guest kernel works like a bare metal kernel with additional
-	 * features, and paravirt_enabled is about features that are
-	 * missing.
-	 */
-	pv_info.paravirt_enabled = 0;
-
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
 
@@ -522,7 +514,7 @@ static noinline uint32_t __kvm_cpuid_base(void)
 	if (boot_cpu_data.cpuid_level < 0)
 		return 0;	/* So we don't blow up on old processors */
 
-	if (cpu_has_hypervisor)
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
 
 	return 0;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 005c03e93fc5..477ae806c2fa 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -31,6 +31,7 @@
 #include <linux/jump_label.h>
 #include <linux/random.h>
 
+#include <asm/text-patching.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f08ac28b8136..7b3b3f24c3ea 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -294,7 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 
 struct pv_info pv_info = {
 	.name = "bare hardware",
-	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
 	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
 
@@ -339,8 +338,10 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 	.write_cr8 = native_write_cr8,
 #endif
 	.wbinvd = native_wbinvd,
-	.read_msr = native_read_msr_safe,
-	.write_msr = native_write_msr_safe,
+	.read_msr = native_read_msr,
+	.write_msr = native_write_msr,
+	.read_msr_safe = native_read_msr_safe,
+	.write_msr_safe = native_write_msr_safe,
 	.read_pmc = native_read_pmc,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 35ccf75696eb..f712dfdf1357 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -72,7 +72,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 	}
 }
 #else
-inline void check_iommu_entries(struct iommu_table_entry *start,
+void __init check_iommu_entries(struct iommu_table_entry *start,
 				       struct iommu_table_entry *finish)
 {
 }
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
new file mode 100644
index 000000000000..b2f8a33b36ff
--- /dev/null
+++ b/arch/x86/kernel/platform-quirks.c
@@ -0,0 +1,35 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+
+#include <asm/setup.h>
+#include <asm/bios_ebda.h>
+
+void __init x86_early_init_platform_quirks(void)
+{
+	x86_platform.legacy.rtc = 1;
+	x86_platform.legacy.ebda_search = 0;
+	x86_platform.legacy.devices.pnpbios = 1;
+
+	switch (boot_params.hdr.hardware_subarch) {
+	case X86_SUBARCH_PC:
+		x86_platform.legacy.ebda_search = 1;
+		break;
+	case X86_SUBARCH_XEN:
+	case X86_SUBARCH_LGUEST:
+	case X86_SUBARCH_INTEL_MID:
+	case X86_SUBARCH_CE4100:
+		x86_platform.legacy.devices.pnpbios = 0;
+		x86_platform.legacy.rtc = 0;
+		break;
+	}
+
+	if (x86_platform.set_legacy_features)
+		x86_platform.set_legacy_features();
+}
+
+#if defined(CONFIG_PNPBIOS)
+bool __init arch_pnpbios_disabled(void)
+{
+	return x86_platform.legacy.devices.pnpbios == 0;
+}
+#endif
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6cbab31ac23a..6b16c36f0939 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -136,25 +136,6 @@ void release_thread(struct task_struct *dead_task)
 	}
 }
 
-static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
-{
-	struct user_desc ud = {
-		.base_addr = addr,
-		.limit = 0xfffff,
-		.seg_32bit = 1,
-		.limit_in_pages = 1,
-		.useable = 1,
-	};
-	struct desc_struct *desc = t->thread.tls_array;
-	desc += tls;
-	fill_ldt(desc, &ud);
-}
-
-static inline u32 read_32bit_tls(struct task_struct *t, int tls)
-{
-	return get_desc_base(&t->thread.tls_array[tls]);
-}
-
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
@@ -169,9 +150,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
-	p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs;
+	p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase;
 	savesegment(fs, p->thread.fsindex);
-	p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
+	p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase;
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
 	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
@@ -210,7 +191,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	 */
 	if (clone_flags & CLONE_SETTLS) {
 #ifdef CONFIG_IA32_EMULATION
-		if (is_ia32_task())
+		if (in_ia32_syscall())
 			err = do_set_thread_area(p, -1,
 				(struct user_desc __user *)tls, 0);
 		else
@@ -282,7 +263,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	unsigned fsindex, gsindex;
+	unsigned prev_fsindex, prev_gsindex;
 	fpu_switch_t fpu_switch;
 
 	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
@@ -292,8 +273,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 *
 	 * (e.g. xen_load_tls())
 	 */
-	savesegment(fs, fsindex);
-	savesegment(gs, gsindex);
+	savesegment(fs, prev_fsindex);
+	savesegment(gs, prev_gsindex);
 
 	/*
 	 * Load TLS before restoring any segments so that segment loads
@@ -336,66 +317,104 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Switch FS and GS.
 	 *
 	 * These are even more complicated than DS and ES: they have
-	 * 64-bit bases are that controlled by arch_prctl.  Those bases
-	 * only differ from the values in the GDT or LDT if the selector
-	 * is 0.
-	 *
-	 * Loading the segment register resets the hidden base part of
-	 * the register to 0 or the value from the GDT / LDT.  If the
-	 * next base address zero, writing 0 to the segment register is
-	 * much faster than using wrmsr to explicitly zero the base.
-	 *
-	 * The thread_struct.fs and thread_struct.gs values are 0
-	 * if the fs and gs bases respectively are not overridden
-	 * from the values implied by fsindex and gsindex.  They
-	 * are nonzero, and store the nonzero base addresses, if
-	 * the bases are overridden.
-	 *
-	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
-	 * be impossible.
-	 *
-	 * Therefore we need to reload the segment registers if either
-	 * the old or new selector is nonzero, and we need to override
-	 * the base address if next thread expects it to be overridden.
+	 * 64-bit bases are that controlled by arch_prctl.  The bases
+	 * don't necessarily match the selectors, as user code can do
+	 * any number of things to cause them to be inconsistent.
 	 *
-	 * This code is unnecessarily slow in the case where the old and
-	 * new indexes are zero and the new base is nonzero -- it will
-	 * unnecessarily write 0 to the selector before writing the new
-	 * base address.
+	 * We don't promise to preserve the bases if the selectors are
+	 * nonzero.  We also don't promise to preserve the base if the
+	 * selector is zero and the base doesn't match whatever was
+	 * most recently passed to ARCH_SET_FS/GS.  (If/when the
+	 * FSGSBASE instructions are enabled, we'll need to offer
+	 * stronger guarantees.)
 	 *
-	 * Note: This all depends on arch_prctl being the only way that
-	 * user code can override the segment base.  Once wrfsbase and
-	 * wrgsbase are enabled, most of this code will need to change.
+	 * As an invariant,
+	 * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is
+	 * impossible.
 	 */
-	if (unlikely(fsindex | next->fsindex | prev->fs)) {
+	if (next->fsindex) {
+		/* Loading a nonzero value into FS sets the index and base. */
 		loadsegment(fs, next->fsindex);
-
-		/*
-		 * If user code wrote a nonzero value to FS, then it also
-		 * cleared the overridden base address.
-		 *
-		 * XXX: if user code wrote 0 to FS and cleared the base
-		 * address itself, we won't notice and we'll incorrectly
-		 * restore the prior base address next time we reschdule
-		 * the process.
-		 */
-		if (fsindex)
-			prev->fs = 0;
+	} else {
+		if (next->fsbase) {
+			/* Next index is zero but next base is nonzero. */
+			if (prev_fsindex)
+				loadsegment(fs, 0);
+			wrmsrl(MSR_FS_BASE, next->fsbase);
+		} else {
+			/* Next base and index are both zero. */
+			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+				/*
+				 * We don't know the previous base and can't
+				 * find out without RDMSR.  Forcibly clear it.
+				 */
+				loadsegment(fs, __USER_DS);
+				loadsegment(fs, 0);
+			} else {
+				/*
+				 * If the previous index is zero and ARCH_SET_FS
+				 * didn't change the base, then the base is
+				 * also zero and we don't need to do anything.
+				 */
+				if (prev->fsbase || prev_fsindex)
+					loadsegment(fs, 0);
+			}
+		}
 	}
-	if (next->fs)
-		wrmsrl(MSR_FS_BASE, next->fs);
-	prev->fsindex = fsindex;
+	/*
+	 * Save the old state and preserve the invariant.
+	 * NB: if prev_fsindex == 0, then we can't reliably learn the base
+	 * without RDMSR because Intel user code can zero it without telling
+	 * us and AMD user code can program any 32-bit value without telling
+	 * us.
+	 */
+	if (prev_fsindex)
+		prev->fsbase = 0;
+	prev->fsindex = prev_fsindex;
 
-	if (unlikely(gsindex | next->gsindex | prev->gs)) {
+	if (next->gsindex) {
+		/* Loading a nonzero value into GS sets the index and base. */
 		load_gs_index(next->gsindex);
-
-		/* This works (and fails) the same way as fsindex above. */
-		if (gsindex)
-			prev->gs = 0;
+	} else {
+		if (next->gsbase) {
+			/* Next index is zero but next base is nonzero. */
+			if (prev_gsindex)
+				load_gs_index(0);
+			wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase);
+		} else {
+			/* Next base and index are both zero. */
+			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+				/*
+				 * We don't know the previous base and can't
+				 * find out without RDMSR.  Forcibly clear it.
+				 *
+				 * This contains a pointless SWAPGS pair.
+				 * Fixing it would involve an explicit check
+				 * for Xen or a new pvop.
+				 */
+				load_gs_index(__USER_DS);
+				load_gs_index(0);
+			} else {
+				/*
+				 * If the previous index is zero and ARCH_SET_GS
+				 * didn't change the base, then the base is
+				 * also zero and we don't need to do anything.
+				 */
+				if (prev->gsbase || prev_gsindex)
+					load_gs_index(0);
+			}
+		}
 	}
-	if (next->gs)
-		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
-	prev->gsindex = gsindex;
+	/*
+	 * Save the old state and preserve the invariant.
+	 * NB: if prev_gsindex == 0, then we can't reliably learn the base
+	 * without RDMSR because Intel user code can zero it without telling
+	 * us and AMD user code can program any 32-bit value without telling
+	 * us.
+	 */
+	if (prev_gsindex)
+		prev->gsbase = 0;
+	prev->gsindex = prev_gsindex;
 
 	switch_fpu_finish(next_fpu, fpu_switch);
 
@@ -516,23 +535,11 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 		if (addr >= TASK_SIZE_OF(task))
 			return -EPERM;
 		cpu = get_cpu();
-		/* handle small bases via the GDT because that's faster to
-		   switch. */
-		if (addr <= 0xffffffff) {
-			set_32bit_tls(task, GS_TLS, addr);
-			if (doit) {
-				load_TLS(&task->thread, cpu);
-				load_gs_index(GS_TLS_SEL);
-			}
-			task->thread.gsindex = GS_TLS_SEL;
-			task->thread.gs = 0;
-		} else {
-			task->thread.gsindex = 0;
-			task->thread.gs = addr;
-			if (doit) {
-				load_gs_index(0);
-				ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
-			}
+		task->thread.gsindex = 0;
+		task->thread.gsbase = addr;
+		if (doit) {
+			load_gs_index(0);
+			ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
 		}
 		put_cpu();
 		break;
@@ -542,52 +549,30 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 		if (addr >= TASK_SIZE_OF(task))
 			return -EPERM;
 		cpu = get_cpu();
-		/* handle small bases via the GDT because that's faster to
-		   switch. */
-		if (addr <= 0xffffffff) {
-			set_32bit_tls(task, FS_TLS, addr);
-			if (doit) {
-				load_TLS(&task->thread, cpu);
-				loadsegment(fs, FS_TLS_SEL);
-			}
-			task->thread.fsindex = FS_TLS_SEL;
-			task->thread.fs = 0;
-		} else {
-			task->thread.fsindex = 0;
-			task->thread.fs = addr;
-			if (doit) {
-				/* set the selector to 0 to not confuse
-				   __switch_to */
-				loadsegment(fs, 0);
-				ret = wrmsrl_safe(MSR_FS_BASE, addr);
-			}
+		task->thread.fsindex = 0;
+		task->thread.fsbase = addr;
+		if (doit) {
+			/* set the selector to 0 to not confuse __switch_to */
+			loadsegment(fs, 0);
+			ret = wrmsrl_safe(MSR_FS_BASE, addr);
 		}
 		put_cpu();
 		break;
 	case ARCH_GET_FS: {
 		unsigned long base;
-		if (task->thread.fsindex == FS_TLS_SEL)
-			base = read_32bit_tls(task, FS_TLS);
-		else if (doit)
+		if (doit)
 			rdmsrl(MSR_FS_BASE, base);
 		else
-			base = task->thread.fs;
+			base = task->thread.fsbase;
 		ret = put_user(base, (unsigned long __user *)addr);
 		break;
 	}
 	case ARCH_GET_GS: {
 		unsigned long base;
-		unsigned gsindex;
-		if (task->thread.gsindex == GS_TLS_SEL)
-			base = read_32bit_tls(task, GS_TLS);
-		else if (doit) {
-			savesegment(gs, gsindex);
-			if (gsindex)
-				rdmsrl(MSR_KERNEL_GS_BASE, base);
-			else
-				base = task->thread.gs;
-		} else
-			base = task->thread.gs;
+		if (doit)
+			rdmsrl(MSR_KERNEL_GS_BASE, base);
+		else
+			base = task->thread.gsbase;
 		ret = put_user(base, (unsigned long __user *)addr);
 		break;
 	}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 32e9d9cbb884..e60ef918f53d 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -303,29 +303,11 @@ static int set_segment_reg(struct task_struct *task,
 
 	switch (offset) {
 	case offsetof(struct user_regs_struct,fs):
-		/*
-		 * If this is setting fs as for normal 64-bit use but
-		 * setting fs_base has implicitly changed it, leave it.
-		 */
-		if ((value == FS_TLS_SEL && task->thread.fsindex == 0 &&
-		     task->thread.fs != 0) ||
-		    (value == 0 && task->thread.fsindex == FS_TLS_SEL &&
-		     task->thread.fs == 0))
-			break;
 		task->thread.fsindex = value;
 		if (task == current)
 			loadsegment(fs, task->thread.fsindex);
 		break;
 	case offsetof(struct user_regs_struct,gs):
-		/*
-		 * If this is setting gs as for normal 64-bit use but
-		 * setting gs_base has implicitly changed it, leave it.
-		 */
-		if ((value == GS_TLS_SEL && task->thread.gsindex == 0 &&
-		     task->thread.gs != 0) ||
-		    (value == 0 && task->thread.gsindex == GS_TLS_SEL &&
-		     task->thread.gs == 0))
-			break;
 		task->thread.gsindex = value;
 		if (task == current)
 			load_gs_index(task->thread.gsindex);
@@ -417,7 +399,7 @@ static int putreg(struct task_struct *child,
 		 * to set either thread.fs or thread.fsindex and the
 		 * corresponding GDT slot.
 		 */
-		if (child->thread.fs != value)
+		if (child->thread.fsbase != value)
 			return do_arch_prctl(child, ARCH_SET_FS, value);
 		return 0;
 	case offsetof(struct user_regs_struct,gs_base):
@@ -426,7 +408,7 @@ static int putreg(struct task_struct *child,
 		 */
 		if (value >= TASK_SIZE_OF(child))
 			return -EIO;
-		if (child->thread.gs != value)
+		if (child->thread.gsbase != value)
 			return do_arch_prctl(child, ARCH_SET_GS, value);
 		return 0;
 #endif
@@ -453,31 +435,17 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset)
 #ifdef CONFIG_X86_64
 	case offsetof(struct user_regs_struct, fs_base): {
 		/*
-		 * do_arch_prctl may have used a GDT slot instead of
-		 * the MSR.  To userland, it appears the same either
-		 * way, except the %fs segment selector might not be 0.
+		 * XXX: This will not behave as expected if called on
+		 * current or if fsindex != 0.
 		 */
-		unsigned int seg = task->thread.fsindex;
-		if (task->thread.fs != 0)
-			return task->thread.fs;
-		if (task == current)
-			asm("movl %%fs,%0" : "=r" (seg));
-		if (seg != FS_TLS_SEL)
-			return 0;
-		return get_desc_base(&task->thread.tls_array[FS_TLS]);
+		return task->thread.fsbase;
 	}
 	case offsetof(struct user_regs_struct, gs_base): {
 		/*
-		 * Exactly the same here as the %fs handling above.
+		 * XXX: This will not behave as expected if called on
+		 * current or if fsindex != 0.
 		 */
-		unsigned int seg = task->thread.gsindex;
-		if (task->thread.gs != 0)
-			return task->thread.gs;
-		if (task == current)
-			asm("movl %%gs,%0" : "=r" (seg));
-		if (seg != GS_TLS_SEL)
-			return 0;
-		return get_desc_base(&task->thread.tls_array[GS_TLS]);
+		return task->thread.gsbase;
 	}
 #endif
 	}
@@ -1266,7 +1234,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			compat_ulong_t caddr, compat_ulong_t cdata)
 {
 #ifdef CONFIG_X86_X32_ABI
-	if (!is_ia32_task())
+	if (!in_ia32_syscall())
 		return x32_arch_ptrace(child, request, caddr, cdata);
 #endif
 #ifdef CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index ab0adc0fa5db..a9b31eb815f2 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -535,6 +535,15 @@ static void native_machine_emergency_restart(void)
 	mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0;
 	*((unsigned short *)__va(0x472)) = mode;
 
+	/*
+	 * If an EFI capsule has been registered with the firmware then
+	 * override the reboot= parameter.
+	 */
+	if (efi_capsule_pending(NULL)) {
+		pr_info("EFI capsule is pending, forcing EFI reboot.\n");
+		reboot_type = BOOT_EFI;
+	}
+
 	for (;;) {
 		/* Could also try the reset bit in the Hammer NB */
 		switch (reboot_type) {
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 4af8d063fb36..eceaa082ec3f 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -14,6 +14,7 @@
 #include <asm/time.h>
 #include <asm/intel-mid.h>
 #include <asm/rtc.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_X86_32
 /*
@@ -185,22 +186,7 @@ static __init int add_rtc_cmos(void)
 		}
 	}
 #endif
-	if (of_have_populated_dt())
-		return 0;
-
-	/* Intel MID platforms don't have ioport rtc */
-	if (intel_mid_identify_cpu())
-		return -ENODEV;
-
-#ifdef CONFIG_ACPI
-	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
-		/* This warning can likely go away again in a year or two. */
-		pr_info("ACPI: not registering RTC platform device\n");
-		return -ENODEV;
-	}
-#endif
-
-	if (paravirt_enabled() && !paravirt_has(RTC))
+	if (!x86_platform.legacy.rtc)
 		return -ENODEV;
 
 	platform_device_register(&rtc_device);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 548ddf7d6fd2..22cc2f9f8aec 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -248,18 +248,17 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	if (config_enabled(CONFIG_X86_64))
 		sp -= 128;
 
-	if (!onsigstack) {
-		/* This is the X/Open sanctioned signal stack switching.  */
-		if (ka->sa.sa_flags & SA_ONSTACK) {
-			if (current->sas_ss_size)
-				sp = current->sas_ss_sp + current->sas_ss_size;
-		} else if (config_enabled(CONFIG_X86_32) &&
-			   (regs->ss & 0xffff) != __USER_DS &&
-			   !(ka->sa.sa_flags & SA_RESTORER) &&
-			   ka->sa.sa_restorer) {
-				/* This is the legacy signal stack switching. */
-				sp = (unsigned long) ka->sa.sa_restorer;
-		}
+	/* This is the X/Open sanctioned signal stack switching.  */
+	if (ka->sa.sa_flags & SA_ONSTACK) {
+		if (sas_ss_flags(sp) == 0)
+			sp = current->sas_ss_sp + current->sas_ss_size;
+	} else if (config_enabled(CONFIG_X86_32) &&
+		   !onsigstack &&
+		   (regs->ss & 0xffff) != __USER_DS &&
+		   !(ka->sa.sa_flags & SA_RESTORER) &&
+		   ka->sa.sa_restorer) {
+		/* This is the legacy signal stack switching. */
+		sp = (unsigned long) ka->sa.sa_restorer;
 	}
 
 	if (fpu->fpstate_active) {
@@ -391,7 +390,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		put_user_ex(&frame->uc, &frame->puc);
 
 		/* Create the ucontext.  */
-		if (cpu_has_xsave)
+		if (boot_cpu_has(X86_FEATURE_XSAVE))
 			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
@@ -442,7 +441,7 @@ static unsigned long frame_uc_flags(struct pt_regs *regs)
 {
 	unsigned long flags;
 
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS;
 	else
 		flags = UC_SIGCONTEXT_SS;
@@ -762,7 +761,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_64
-	if (is_ia32_task())
+	if (in_ia32_syscall())
 		return __NR_ia32_restart_syscall;
 #endif
 #ifdef CONFIG_X86_X32_ABI
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0e4329ed91ef..fafe8b923cac 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1236,7 +1236,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	 * If we couldn't find a local APIC, then get out of here now!
 	 */
 	if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
-	    !cpu_has_apic) {
+	    !boot_cpu_has(X86_FEATURE_APIC)) {
 		if (!disable_apic) {
 			pr_err("BIOS bug, local APIC #%d not detected!...\n",
 				boot_cpu_physical_apicid);
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index 5da924bbf0a0..623965e86b65 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -68,6 +68,21 @@ struct efifb_dmi_info efifb_dmi_list[] = {
 	[M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE }
 };
 
+void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
+{
+	int i;
+
+	for (i = 0; i < M_UNKNOWN; i++) {
+		if (efifb_dmi_list[i].base != 0 &&
+		    !strcmp(opt, efifb_dmi_list[i].optname)) {
+			si->lfb_base = efifb_dmi_list[i].base;
+			si->lfb_linelength = efifb_dmi_list[i].stride;
+			si->lfb_width = efifb_dmi_list[i].width;
+			si->lfb_height = efifb_dmi_list[i].height;
+		}
+	}
+}
+
 #define choose_value(dmivalue, fwvalue, field, flags) ({	\
 		typeof(fwvalue) _ret_ = fwvalue;		\
 		if ((flags) & (field))				\
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index e72a07f20b05..9b0185fbe3eb 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -74,12 +74,6 @@ void __init tboot_probe(void)
 		return;
 	}
 
-	/* only a natively booted kernel should be using TXT */
-	if (paravirt_enabled()) {
-		pr_warning("non-0 tboot_addr but pv_ops is enabled\n");
-		return;
-	}
-
 	/* Map and check for tboot UUID. */
 	set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr);
 	tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE);
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
index ab40954e113e..f386bad0984e 100644
--- a/arch/x86/kernel/tce_64.c
+++ b/arch/x86/kernel/tce_64.c
@@ -40,7 +40,7 @@
 static inline void flush_tce(void* tceaddr)
 {
 	/* a single tce can't cross a cache line */
-	if (cpu_has_clflush)
+	if (boot_cpu_has(X86_FEATURE_CLFLUSH))
 		clflush(tceaddr);
 	else
 		wbinvd();
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 7fc5e843f247..9692a5e9fdab 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -114,6 +114,7 @@ int do_set_thread_area(struct task_struct *p, int idx,
 		       int can_allocate)
 {
 	struct user_desc info;
+	unsigned short __maybe_unused sel, modified_sel;
 
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
@@ -141,6 +142,47 @@ int do_set_thread_area(struct task_struct *p, int idx,
 
 	set_tls_desc(p, idx, &info, 1);
 
+	/*
+	 * If DS, ES, FS, or GS points to the modified segment, forcibly
+	 * refresh it.  Only needed on x86_64 because x86_32 reloads them
+	 * on return to user mode.
+	 */
+	modified_sel = (idx << 3) | 3;
+
+	if (p == current) {
+#ifdef CONFIG_X86_64
+		savesegment(ds, sel);
+		if (sel == modified_sel)
+			loadsegment(ds, sel);
+
+		savesegment(es, sel);
+		if (sel == modified_sel)
+			loadsegment(es, sel);
+
+		savesegment(fs, sel);
+		if (sel == modified_sel)
+			loadsegment(fs, sel);
+
+		savesegment(gs, sel);
+		if (sel == modified_sel)
+			load_gs_index(sel);
+#endif
+
+#ifdef CONFIG_X86_32_LAZY_GS
+		savesegment(gs, sel);
+		if (sel == modified_sel)
+			loadsegment(gs, sel);
+#endif
+	} else {
+#ifdef CONFIG_X86_64
+		if (p->thread.fsindex == modified_sel)
+			p->thread.fsbase = info.base_addr;
+
+		if (p->thread.gsindex == modified_sel)
+			p->thread.gsbase = info.base_addr;
+#endif
+	}
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 06cbe25861f1..d1590486204a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <linux/atomic.h>
+#include <asm/text-patching.h>
 #include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c9c4c7ce3eb2..38ba6de56ede 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -36,7 +36,7 @@ static int __read_mostly tsc_unstable;
 
 /* native_sched_clock() is called before tsc_init(), so
    we must start with the TSC soft disabled to prevent
-   erroneous rdtsc usage on !cpu_has_tsc processors */
+   erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */
 static int __read_mostly tsc_disabled = -1;
 
 static DEFINE_STATIC_KEY_FALSE(__use_tsc);
@@ -834,15 +834,15 @@ int recalibrate_cpu_khz(void)
 #ifndef CONFIG_SMP
 	unsigned long cpu_khz_old = cpu_khz;
 
-	if (cpu_has_tsc) {
-		tsc_khz = x86_platform.calibrate_tsc();
-		cpu_khz = tsc_khz;
-		cpu_data(0).loops_per_jiffy =
-			cpufreq_scale(cpu_data(0).loops_per_jiffy,
-					cpu_khz_old, cpu_khz);
-		return 0;
-	} else
+	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return -ENODEV;
+
+	tsc_khz = x86_platform.calibrate_tsc();
+	cpu_khz = tsc_khz;
+	cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy,
+						    cpu_khz_old, cpu_khz);
+
+	return 0;
 #else
 	return -ENODEV;
 #endif
@@ -922,9 +922,6 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 	struct cpufreq_freqs *freq = data;
 	unsigned long *lpj;
 
-	if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC))
-		return 0;
-
 	lpj = &boot_cpu_data.loops_per_jiffy;
 #ifdef CONFIG_SMP
 	if (!(freq->flags & CPUFREQ_CONST_LOOPS))
@@ -954,9 +951,9 @@ static struct notifier_block time_cpufreq_notifier_block = {
 	.notifier_call  = time_cpufreq_notifier
 };
 
-static int __init cpufreq_tsc(void)
+static int __init cpufreq_register_tsc_scaling(void)
 {
-	if (!cpu_has_tsc)
+	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return 0;
 	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		return 0;
@@ -965,7 +962,7 @@ static int __init cpufreq_tsc(void)
 	return 0;
 }
 
-core_initcall(cpufreq_tsc);
+core_initcall(cpufreq_register_tsc_scaling);
 
 #endif /* CONFIG_CPU_FREQ */
 
@@ -1081,7 +1078,7 @@ static void __init check_system_tsc_reliable(void)
  */
 int unsynchronized_tsc(void)
 {
-	if (!cpu_has_tsc || tsc_unstable)
+	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable)
 		return 1;
 
 #ifdef CONFIG_SMP
@@ -1205,7 +1202,7 @@ out:
 
 static int __init init_tsc_clocksource(void)
 {
-	if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz)
+	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
 		return 0;
 
 	if (tsc_clocksource_reliable)
@@ -1242,7 +1239,7 @@ void __init tsc_init(void)
 	u64 lpj;
 	int cpu;
 
-	if (!cpu_has_tsc) {
+	if (!boot_cpu_has(X86_FEATURE_TSC)) {
 		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
 	}
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index bf4db6eaec8f..6c1ff31d99ff 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -516,7 +516,7 @@ struct uprobe_xol_ops {
 
 static inline int sizeof_long(void)
 {
-	return is_ia32_task() ? 4 : 8;
+	return in_ia32_syscall() ? 4 : 8;
 }
 
 static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
@@ -578,7 +578,7 @@ static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	riprel_post_xol(auprobe, regs);
 }
 
-static struct uprobe_xol_ops default_xol_ops = {
+static const struct uprobe_xol_ops default_xol_ops = {
 	.pre_xol  = default_pre_xol_op,
 	.post_xol = default_post_xol_op,
 	.abort	  = default_abort_op,
@@ -695,7 +695,7 @@ static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn)
 		0, insn->immediate.nbytes);
 }
 
-static struct uprobe_xol_ops branch_xol_ops = {
+static const struct uprobe_xol_ops branch_xol_ops = {
 	.emulate  = branch_emulate_op,
 	.post_xol = branch_post_xol_op,
 };
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4c941f88d405..9297a002d8e5 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -334,7 +334,7 @@ SECTIONS
 		__brk_limit = .;
 	}
 
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
 
         STABS_DEBUG
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bbbaa802d13e..769af907f824 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -75,7 +75,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 		return 0;
 
 	/* Update OSXSAVE bit */
-	if (cpu_has_xsave && best->function == 0x1) {
+	if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) {
 		best->ecx &= ~F(OSXSAVE);
 		if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
 			best->ecx |= F(OSXSAVE);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b6f50e8b0a39..38c0c32926c9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3844,7 +3844,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
-					cpu_has_gbpages, true, true);
+					boot_cpu_has(X86_FEATURE_GBPAGES),
+					true, true);
 	else
 		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 31346a3f20a5..fafd720ce10a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1254,7 +1254,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_load_ldt(svm->host.ldt);
 #ifdef CONFIG_X86_64
 	loadsegment(fs, svm->host.fs);
-	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
+	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase);
 	load_gs_index(svm->host.gs);
 #else
 #ifdef CONFIG_X86_32_LAZY_GS
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 2f1ea2f61e1f..b72743c5668d 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -809,8 +809,7 @@ TRACE_EVENT(kvm_write_tsc_offset,
 
 #define host_clocks					\
 	{VCLOCK_NONE, "none"},				\
-	{VCLOCK_TSC,  "tsc"},				\
-	{VCLOCK_HPET, "hpet"}				\
+	{VCLOCK_TSC,  "tsc"}				\
 
 TRACE_EVENT(kvm_update_master_clock,
 	TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched),
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 133679d520af..cb47fe3da292 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3390,7 +3390,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		}
 	}
 
-	if (cpu_has_xsaves)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		rdmsrl(MSR_IA32_XSS, host_xss);
 
 	return 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b7798c7b210..12f33e662382 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2611,7 +2611,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_MAX_MCE_BANKS;
 		break;
 	case KVM_CAP_XCRS:
-		r = cpu_has_xsave;
+		r = boot_cpu_has(X86_FEATURE_XSAVE);
 		break;
 	case KVM_CAP_TSC_CONTROL:
 		r = kvm_has_tsc_control;
@@ -3094,7 +3094,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 
 	/* Set XSTATE_BV and possibly XCOMP_BV.  */
 	xsave->header.xfeatures = xstate_bv;
-	if (cpu_has_xsaves)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
@@ -3121,7 +3121,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	if (cpu_has_xsave) {
+	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
@@ -3139,7 +3139,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
 
-	if (cpu_has_xsave) {
+	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
 		 * Here we allow setting states that are not present in
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
@@ -3160,7 +3160,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
 					struct kvm_xcrs *guest_xcrs)
 {
-	if (!cpu_has_xsave) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
 		guest_xcrs->nr_xcrs = 0;
 		return;
 	}
@@ -3176,7 +3176,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 {
 	int i, r = 0;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -EINVAL;
 
 	if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
@@ -5865,7 +5865,7 @@ int kvm_arch_init(void *opaque)
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);
 
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 
 	kvm_lapic_init();
@@ -7293,7 +7293,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 static void fx_init(struct kvm_vcpu *vcpu)
 {
 	fpstate_init(&vcpu->arch.guest_fpu.state);
-	if (cpu_has_xsaves)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
 			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index fd57d3ae7e16..3847e736702e 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1408,13 +1408,10 @@ __init void lguest_init(void)
 {
 	/* We're under lguest. */
 	pv_info.name = "lguest";
-	/* Paravirt is enabled. */
-	pv_info.paravirt_enabled = 1;
 	/* We're running at privilege level 1, not 0 as normal. */
 	pv_info.kernel_rpl = 1;
 	/* Everyone except Xen runs with this set. */
 	pv_info.shared_kernel_pmd = 1;
-	pv_info.features = 0;
 
 	/*
 	 * We set up all the lguest overrides for sensitive operations.  These
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index be110efa0096..bf2c6074efd2 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -29,8 +29,10 @@
  * there is contention on the semaphore.
  *
  * %eax contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax whish is either a return
- * value or just clobbered..
+ * registers (%eax, %edx and %ecx) except %eax which is either a return
+ * value or just gets clobbered. Same is true for %edx so make sure GCC
+ * reloads it after the slow path, by making it hold a temporary, for
+ * example see ____down_write().
  */
 
 #define save_common_regs \
@@ -106,6 +108,16 @@ ENTRY(call_rwsem_down_write_failed)
 	ret
 ENDPROC(call_rwsem_down_write_failed)
 
+ENTRY(call_rwsem_down_write_failed_killable)
+	FRAME_BEGIN
+	save_common_regs
+	movq %rax,%rdi
+	call rwsem_down_write_failed_killable
+	restore_common_regs
+	FRAME_END
+	ret
+ENDPROC(call_rwsem_down_write_failed_killable)
+
 ENTRY(call_rwsem_wake)
 	FRAME_BEGIN
 	/* do nothing if still outstanding active readers */
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 91d93b95bd86..b559d9238781 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -612,7 +612,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 {
 	stac();
 #ifdef CONFIG_X86_INTEL_USERCOPY
-	if (n > 64 && cpu_has_xmm2)
+	if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
 	else
 		__copy_user_zeroing(to, from, n);
@@ -629,7 +629,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
 {
 	stac();
 #ifdef CONFIG_X86_INTEL_USERCOPY
-	if (n > 64 && cpu_has_xmm2)
+	if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
 		n = __copy_user_intel_nocache(to, from, n);
 	else
 		__copy_user(to, from, n);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index f98913258c63..62c0043a5fd5 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -2,7 +2,7 @@
 KCOV_INSTRUMENT_tlb.o	:= n
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o gup.o setup_nx.o
+	    pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
@@ -12,7 +12,6 @@ CFLAGS_setup_nx.o		:= $(nostackp)
 CFLAGS_fault.o := -I$(src)/../include/asm/trace
 
 obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
-obj-$(CONFIG_SMP)		+= tlb.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 82447b3fba38..4bb53b89f3c5 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,5 +1,6 @@
 #include <linux/module.h>
 #include <asm/uaccess.h>
+#include <asm/traps.h>
 
 typedef bool (*ex_handler_t)(const struct exception_table_entry *,
 			    struct pt_regs *, int);
@@ -42,6 +43,43 @@ bool ex_handler_ext(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL(ex_handler_ext);
 
+bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, int trapnr)
+{
+	WARN_ONCE(1, "unchecked MSR access error: RDMSR from 0x%x\n",
+		  (unsigned int)regs->cx);
+
+	/* Pretend that the read succeeded and returned 0. */
+	regs->ip = ex_fixup_addr(fixup);
+	regs->ax = 0;
+	regs->dx = 0;
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
+
+bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, int trapnr)
+{
+	WARN_ONCE(1, "unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x)\n",
+		  (unsigned int)regs->cx,
+		  (unsigned int)regs->dx, (unsigned int)regs->ax);
+
+	/* Pretend that the write succeeded. */
+	regs->ip = ex_fixup_addr(fixup);
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
+
+bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
+			 struct pt_regs *regs, int trapnr)
+{
+	if (static_cpu_has(X86_BUG_NULL_SEG))
+		asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
+	asm volatile ("mov %0, %%fs" : : "rm" (0));
+	return ex_handler_default(fixup, regs, trapnr);
+}
+EXPORT_SYMBOL(ex_handler_clear_fs);
+
 bool ex_has_fault_handler(unsigned long ip)
 {
 	const struct exception_table_entry *e;
@@ -82,24 +120,46 @@ int fixup_exception(struct pt_regs *regs, int trapnr)
 	return handler(e, regs, trapnr);
 }
 
+extern unsigned int early_recursion_flag;
+
 /* Restricted version used during very early boot */
-int __init early_fixup_exception(unsigned long *ip)
+void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 {
-	const struct exception_table_entry *e;
-	unsigned long new_ip;
-	ex_handler_t handler;
-
-	e = search_exception_tables(*ip);
-	if (!e)
-		return 0;
-
-	new_ip  = ex_fixup_addr(e);
-	handler = ex_fixup_handler(e);
-
-	/* special handling not supported during early boot */
-	if (handler != ex_handler_default)
-		return 0;
-
-	*ip = new_ip;
-	return 1;
+	/* Ignore early NMIs. */
+	if (trapnr == X86_TRAP_NMI)
+		return;
+
+	if (early_recursion_flag > 2)
+		goto halt_loop;
+
+	if (regs->cs != __KERNEL_CS)
+		goto fail;
+
+	/*
+	 * The full exception fixup machinery is available as soon as
+	 * the early IDT is loaded.  This means that it is the
+	 * responsibility of extable users to either function correctly
+	 * when handlers are invoked early or to simply avoid causing
+	 * exceptions before they're ready to handle them.
+	 *
+	 * This is better than filtering which handlers can be used,
+	 * because refusing to call a handler here is guaranteed to
+	 * result in a hard-to-debug panic.
+	 *
+	 * Keep in mind that not all vectors actually get here.  Early
+	 * fage faults, for example, are special.
+	 */
+	if (fixup_exception(regs, trapnr))
+		return;
+
+fail:
+	early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n",
+		     (unsigned)trapnr, (unsigned long)regs->cs, regs->ip,
+		     regs->orig_ax, read_cr2());
+
+	show_regs(regs);
+
+halt_loop:
+	while (true)
+		halt();
 }
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 740d7ac03a55..14a95054d4e0 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -162,7 +162,7 @@ static __init int setup_hugepagesz(char *opt)
 	unsigned long ps = memparse(opt, &opt);
 	if (ps == PMD_SIZE) {
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
-	} else if (ps == PUD_SIZE && cpu_has_gbpages) {
+	} else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	} else {
 		printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
@@ -177,7 +177,7 @@ __setup("hugepagesz=", setup_hugepagesz);
 static __init int gigantic_pages_init(void)
 {
 	/* With compaction or CMA we can allocate gigantic pages at runtime */
-	if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
+	if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT))
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	return 0;
 }
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
new file mode 100644
index 000000000000..ec21796ac5fd
--- /dev/null
+++ b/arch/x86/mm/ident_map.c
@@ -0,0 +1,79 @@
+/*
+ * Helper routines for building identity mapping page tables. This is
+ * included by both the compressed kernel and the regular kernel.
+ */
+
+static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+			   unsigned long addr, unsigned long end)
+{
+	addr &= PMD_MASK;
+	for (; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd = pmd_page + pmd_index(addr);
+
+		if (!pmd_present(*pmd))
+			set_pmd(pmd, __pmd(addr | pmd_flag));
+	}
+}
+
+static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+
+		next = (addr & PUD_MASK) + PUD_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pud_present(*pud)) {
+			pmd = pmd_offset(pud, 0);
+			ident_pmd_init(info->pmd_flag, pmd, addr, next);
+			continue;
+		}
+		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
+		if (!pmd)
+			return -ENOMEM;
+		ident_pmd_init(info->pmd_flag, pmd, addr, next);
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
+int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
+			      unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	int result;
+	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
+
+	for (; addr < end; addr = next) {
+		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+		pud_t *pud;
+
+		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pgd_present(*pgd)) {
+			pud = pud_offset(pgd, 0);
+			result = ident_pud_init(info, pud, addr, next);
+			if (result)
+				return result;
+			continue;
+		}
+
+		pud = (pud_t *)info->alloc_pgt_page(info->context);
+		if (!pud)
+			return -ENOMEM;
+		result = ident_pud_init(info, pud, addr, next);
+		if (result)
+			return result;
+		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 9d56f271d519..372aad2b3291 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -157,23 +157,23 @@ static void __init probe_page_size_mask(void)
 	 * This will simplify cpa(), which otherwise needs to support splitting
 	 * large pages into small in interrupt context, etc.
 	 */
-	if (cpu_has_pse && !debug_pagealloc_enabled())
+	if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled())
 		page_size_mask |= 1 << PG_LEVEL_2M;
 #endif
 
 	/* Enable PSE if available */
-	if (cpu_has_pse)
+	if (boot_cpu_has(X86_FEATURE_PSE))
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	/* Enable PGE if available */
-	if (cpu_has_pge) {
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	} else
 		__supported_pte_mask &= ~_PAGE_GLOBAL;
 
 	/* Enable 1 GB linear kernel mappings if available: */
-	if (direct_gbpages && cpu_has_gbpages) {
+	if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
 		printk(KERN_INFO "Using GB pages for direct mapping\n");
 		page_size_mask |= 1 << PG_LEVEL_1G;
 	} else {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bd7a9b9e2e14..84df150ee77e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -284,7 +284,7 @@ kernel_physical_mapping_init(unsigned long start,
 	 */
 	mapping_iter = 1;
 
-	if (!cpu_has_pse)
+	if (!boot_cpu_has(X86_FEATURE_PSE))
 		use_pse = 0;
 
 repeat:
@@ -804,9 +804,6 @@ void __init mem_init(void)
 	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
 #undef high_memory
 #undef __FIXADDR_TOP
-#ifdef CONFIG_RANDOMIZE_BASE
-	BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE);
-#endif
 
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 214afda97911..bce2e5d9edd4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -58,79 +58,7 @@
 
 #include "mm_internal.h"
 
-static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
-			   unsigned long addr, unsigned long end)
-{
-	addr &= PMD_MASK;
-	for (; addr < end; addr += PMD_SIZE) {
-		pmd_t *pmd = pmd_page + pmd_index(addr);
-
-		if (!pmd_present(*pmd))
-			set_pmd(pmd, __pmd(addr | pmd_flag));
-	}
-}
-static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
-			  unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-
-	for (; addr < end; addr = next) {
-		pud_t *pud = pud_page + pud_index(addr);
-		pmd_t *pmd;
-
-		next = (addr & PUD_MASK) + PUD_SIZE;
-		if (next > end)
-			next = end;
-
-		if (pud_present(*pud)) {
-			pmd = pmd_offset(pud, 0);
-			ident_pmd_init(info->pmd_flag, pmd, addr, next);
-			continue;
-		}
-		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
-		if (!pmd)
-			return -ENOMEM;
-		ident_pmd_init(info->pmd_flag, pmd, addr, next);
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
-	}
-
-	return 0;
-}
-
-int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
-			      unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-	int result;
-	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
-
-	for (; addr < end; addr = next) {
-		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
-		pud_t *pud;
-
-		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-
-		if (pgd_present(*pgd)) {
-			pud = pud_offset(pgd, 0);
-			result = ident_pud_init(info, pud, addr, next);
-			if (result)
-				return result;
-			continue;
-		}
-
-		pud = (pud_t *)info->alloc_pgt_page(info->context);
-		if (!pud)
-			return -ENOMEM;
-		result = ident_pud_init(info, pud, addr, next);
-		if (result)
-			return result;
-		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
-	}
-
-	return 0;
-}
+#include "ident_map.c"
 
 /*
  * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
@@ -1295,7 +1223,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	struct vmem_altmap *altmap = to_vmem_altmap(start);
 	int err;
 
-	if (cpu_has_pse)
+	if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
 	else if (altmap) {
 		pr_err_once("%s: no cpu support for altmap allocations\n",
@@ -1338,7 +1266,7 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-		if (!cpu_has_pse) {
+		if (!boot_cpu_has(X86_FEATURE_PSE)) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
 			pmd = pmd_offset(pud, addr);
 			if (pmd_none(*pmd))
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0d8d53d1f5cc..f0894910bdd7 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -378,7 +378,7 @@ EXPORT_SYMBOL(iounmap);
 int __init arch_ioremap_pud_supported(void)
 {
 #ifdef CONFIG_X86_64
-	return cpu_has_gbpages;
+	return boot_cpu_has(X86_FEATURE_GBPAGES);
 #else
 	return 0;
 #endif
@@ -386,7 +386,7 @@ int __init arch_ioremap_pud_supported(void)
 
 int __init arch_ioremap_pmd_supported(void)
 {
-	return cpu_has_pse;
+	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
 /*
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 01be9ec3bf79..7a1f7bbf4105 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1055,7 +1055,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	/*
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
-	while (cpu_has_gbpages && end - start >= PUD_SIZE) {
+	while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
 		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
 				   massage_pgprot(pud_pgprot)));
 
@@ -1125,8 +1125,14 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 			       int primary)
 {
-	if (cpa->pgd)
+	if (cpa->pgd) {
+		/*
+		 * Right now, we only execute this code path when mapping
+		 * the EFI virtual memory map regions, no other users
+		 * provide a ->pgd value. This may change in the future.
+		 */
 		return populate_pgd(cpa, vaddr);
+	}
 
 	/*
 	 * Ignore all non primary paths.
@@ -1460,7 +1466,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	 * error case we fall back to cpa_flush_all (which uses
 	 * WBINVD):
 	 */
-	if (!ret && cpu_has_clflush) {
+	if (!ret && boot_cpu_has(X86_FEATURE_CLFLUSH)) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index faec01e7a17d..fb0604f11eec 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -40,11 +40,22 @@
 static bool boot_cpu_done;
 
 static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
+static void init_cache_modes(void);
 
-static inline void pat_disable(const char *reason)
+void pat_disable(const char *reason)
 {
+	if (!__pat_enabled)
+		return;
+
+	if (boot_cpu_done) {
+		WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
+		return;
+	}
+
 	__pat_enabled = 0;
 	pr_info("x86/PAT: %s\n", reason);
+
+	init_cache_modes();
 }
 
 static int __init nopat(char *str)
@@ -181,7 +192,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
  * configuration.
  * Using lower indices is preferred, so we start with highest index.
  */
-void pat_init_cache_modes(u64 pat)
+static void __init_cache_modes(u64 pat)
 {
 	enum page_cache_mode cache;
 	char pat_msg[33];
@@ -202,14 +213,11 @@ static void pat_bsp_init(u64 pat)
 {
 	u64 tmp_pat;
 
-	if (!cpu_has_pat) {
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
 		pat_disable("PAT not supported by CPU.");
 		return;
 	}
 
-	if (!pat_enabled())
-		goto done;
-
 	rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
 	if (!tmp_pat) {
 		pat_disable("PAT MSR is 0, disabled.");
@@ -218,16 +226,12 @@ static void pat_bsp_init(u64 pat)
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 
-done:
-	pat_init_cache_modes(pat);
+	__init_cache_modes(pat);
 }
 
 static void pat_ap_init(u64 pat)
 {
-	if (!pat_enabled())
-		return;
-
-	if (!cpu_has_pat) {
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
 		/*
 		 * If this happens we are on a secondary CPU, but switched to
 		 * PAT on the boot CPU. We have no way to undo PAT.
@@ -238,18 +242,32 @@ static void pat_ap_init(u64 pat)
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 }
 
-void pat_init(void)
+static void init_cache_modes(void)
 {
-	u64 pat;
-	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u64 pat = 0;
+	static int init_cm_done;
 
-	if (!pat_enabled()) {
+	if (init_cm_done)
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_PAT)) {
+		/*
+		 * CPU supports PAT. Set PAT table to be consistent with
+		 * PAT MSR. This case supports "nopat" boot option, and
+		 * virtual machine environments which support PAT without
+		 * MTRRs. In specific, Xen has unique setup to PAT MSR.
+		 *
+		 * If PAT MSR returns 0, it is considered invalid and emulates
+		 * as No PAT.
+		 */
+		rdmsrl(MSR_IA32_CR_PAT, pat);
+	}
+
+	if (!pat) {
 		/*
 		 * No PAT. Emulate the PAT table that corresponds to the two
-		 * cache bits, PWT (Write Through) and PCD (Cache Disable). This
-		 * setup is the same as the BIOS default setup when the system
-		 * has PAT but the "nopat" boot option has been specified. This
-		 * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+		 * cache bits, PWT (Write Through) and PCD (Cache Disable).
+		 * This setup is also the same as the BIOS default setup.
 		 *
 		 * PTE encoding:
 		 *
@@ -266,10 +284,36 @@ void pat_init(void)
 		 */
 		pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
 		      PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+	}
+
+	__init_cache_modes(pat);
+
+	init_cm_done = 1;
+}
+
+/**
+ * pat_init - Initialize PAT MSR and PAT table
+ *
+ * This function initializes PAT MSR and PAT table with an OS-defined value
+ * to enable additional cache attributes, WC and WT.
+ *
+ * This function must be called on all CPUs using the specific sequence of
+ * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
+ * procedure for PAT.
+ */
+void pat_init(void)
+{
+	u64 pat;
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (!pat_enabled()) {
+		init_cache_modes();
+		return;
+	}
 
-	} else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
-		   (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
-		    ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+	if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+	    (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+	     ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
 		/*
 		 * PAT support with the lower four entries. Intel Pentium 2,
 		 * 3, M, and 4 are affected by PAT errata, which makes the
@@ -734,25 +778,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	if (file->f_flags & O_DSYNC)
 		pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
-#ifdef CONFIG_X86_32
-	/*
-	 * On the PPro and successors, the MTRRs are used to set
-	 * memory types for physical addresses outside main memory,
-	 * so blindly setting UC or PWT on those pages is wrong.
-	 * For Pentiums and earlier, the surround logic should disable
-	 * caching for the high addresses through the KEN pin, but
-	 * we maintain the tradition of paranoia in this code.
-	 */
-	if (!pat_enabled() &&
-	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
-	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
-	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
-	      boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
-	    (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
-		pcm = _PAGE_CACHE_MODE_UC;
-	}
-#endif
-
 	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
 			     cachemode2protval(pcm));
 	return 1;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index fe9b9f776361..5643fd0b1a7d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,8 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+#ifdef CONFIG_SMP
+
 struct flush_tlb_info {
 	struct mm_struct *flush_mm;
 	unsigned long flush_start;
@@ -57,6 +59,118 @@ void leave_mm(int cpu)
 }
 EXPORT_SYMBOL_GPL(leave_mm);
 
+#endif /* CONFIG_SMP */
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	       struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(prev, next, tsk);
+	local_irq_restore(flags);
+}
+
+void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+#ifdef CONFIG_SMP
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		this_cpu_write(cpu_tlbstate.active_mm, next);
+#endif
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+
+		/*
+		 * Re-load page tables.
+		 *
+		 * This logic has an ordering constraint:
+		 *
+		 *  CPU 0: Write to a PTE for 'next'
+		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
+		 *  CPU 1: set bit 1 in next's mm_cpumask
+		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
+		 *
+		 * We need to prevent an outcome in which CPU 1 observes
+		 * the new PTE value and CPU 0 observes bit 1 clear in
+		 * mm_cpumask.  (If that occurs, then the IPI will never
+		 * be sent, and CPU 0's TLB will contain a stale entry.)
+		 *
+		 * The bad outcome can occur if either CPU's load is
+		 * reordered before that CPU's store, so both CPUs must
+		 * execute full barriers to prevent this from happening.
+		 *
+		 * Thus, switch_mm needs a full barrier between the
+		 * store to mm_cpumask and any operation that could load
+		 * from next->pgd.  TLB fills are special and can happen
+		 * due to instruction fetches or for no reason at all,
+		 * and neither LOCK nor MFENCE orders them.
+		 * Fortunately, load_cr3() is serializing and gives the
+		 * ordering guarantee we need.
+		 *
+		 */
+		load_cr3(next->pgd);
+
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+
+		/* Stop flush ipis for the previous mm */
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+
+		/* Load per-mm CR4 state */
+		load_mm_cr4(next);
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+		/*
+		 * Load the LDT, if the LDT is different.
+		 *
+		 * It's possible that prev->context.ldt doesn't match
+		 * the LDT register.  This can happen if leave_mm(prev)
+		 * was called and then modify_ldt changed
+		 * prev->context.ldt but suppressed an IPI to this CPU.
+		 * In this case, prev->context.ldt != NULL, because we
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
+		 */
+		if (unlikely(prev->context.ldt != next->context.ldt))
+			load_mm_ldt(next);
+#endif
+	}
+#ifdef CONFIG_SMP
+	  else {
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
+
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload CR3
+			 * to make sure to use no freed page tables.
+			 *
+			 * As above, load_cr3() is serializing and orders TLB
+			 * fills with respect to the mm_cpumask write.
+			 */
+			load_cr3(next->pgd);
+			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+			load_mm_cr4(next);
+			load_mm_ldt(next);
+		}
+	}
+#endif
+}
+
+#ifdef CONFIG_SMP
+
 /*
  * The flush IPI assumes that a thread switch happens in this order:
  * [cpu0: the cpu that switches]
@@ -353,3 +467,5 @@ static int __init create_tlb_single_page_flush_ceiling(void)
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
+
+#endif /* CONFIG_SMP */
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 0e07e0968c3a..28c04123b6dd 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -636,7 +636,7 @@ static int __init ppro_init(char **cpu_type)
 	__u8 cpu_model = boot_cpu_data.x86_model;
 	struct op_x86_model_spec *spec = &op_ppro_spec;	/* default */
 
-	if (force_cpu_type == arch_perfmon && cpu_has_arch_perfmon)
+	if (force_cpu_type == arch_perfmon && boot_cpu_has(X86_FEATURE_ARCH_PERFMON))
 		return 0;
 
 	/*
@@ -700,7 +700,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	char *cpu_type = NULL;
 	int ret = 0;
 
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
 
 	if (force_cpu_type == timer)
@@ -761,7 +761,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		if (cpu_type)
 			break;
 
-		if (!cpu_has_arch_perfmon)
+		if (!boot_cpu_has(X86_FEATURE_ARCH_PERFMON))
 			return -ENODEV;
 
 		/* use arch perfmon as fallback */
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index d90528ea5412..350f7096baac 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -75,7 +75,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
 	u64 val;
 	int i;
 
-	if (cpu_has_arch_perfmon) {
+	if (boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) {
 		union cpuid10_eax eax;
 		eax.full = cpuid_eax(0xa);
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index beac4dfdade6..4bd08b0fc8ea 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -445,7 +445,7 @@ void __init xen_msi_init(void)
 		uint32_t eax = cpuid_eax(xen_cpuid_base() + 4);
 
 		if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) ||
-		    ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && cpu_has_apic))
+		    ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC)))
 			return;
 	}
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 994a7df84a7b..f93545e7dc54 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -54,10 +54,6 @@
 #include <asm/rtc.h>
 #include <asm/uv/uv.h>
 
-#define EFI_DEBUG
-
-struct efi_memory_map memmap;
-
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
@@ -119,11 +115,10 @@ void efi_get_time(struct timespec *now)
 
 void __init efi_find_mirror(void)
 {
-	void *p;
+	efi_memory_desc_t *md;
 	u64 mirror_size = 0, total_size = 0;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
+	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
 
@@ -146,10 +141,9 @@ void __init efi_find_mirror(void)
 
 static void __init do_add_efi_memmap(void)
 {
-	void *p;
+	efi_memory_desc_t *md;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
+	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
 		int e820_type;
@@ -209,47 +203,47 @@ int __init efi_memblock_x86_reserve_range(void)
 #else
 	pmap = (e->efi_memmap |	((__u64)e->efi_memmap_hi << 32));
 #endif
-	memmap.phys_map		= pmap;
-	memmap.nr_map		= e->efi_memmap_size /
+	efi.memmap.phys_map	= pmap;
+	efi.memmap.nr_map	= e->efi_memmap_size /
 				  e->efi_memdesc_size;
-	memmap.desc_size	= e->efi_memdesc_size;
-	memmap.desc_version	= e->efi_memdesc_version;
+	efi.memmap.desc_size	= e->efi_memdesc_size;
+	efi.memmap.desc_version	= e->efi_memdesc_version;
 
-	memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
+	WARN(efi.memmap.desc_version != 1,
+	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
+	     efi.memmap.desc_version);
 
-	efi.memmap = &memmap;
+	memblock_reserve(pmap, efi.memmap.nr_map * efi.memmap.desc_size);
 
 	return 0;
 }
 
 void __init efi_print_memmap(void)
 {
-#ifdef EFI_DEBUG
 	efi_memory_desc_t *md;
-	void *p;
-	int i;
+	int i = 0;
 
-	for (p = memmap.map, i = 0;
-	     p < memmap.map_end;
-	     p += memmap.desc_size, i++) {
+	for_each_efi_memory_desc(md) {
 		char buf[64];
 
-		md = p;
 		pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n",
-			i, efi_md_typeattr_format(buf, sizeof(buf), md),
+			i++, efi_md_typeattr_format(buf, sizeof(buf), md),
 			md->phys_addr,
 			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1,
 			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
 	}
-#endif  /*  EFI_DEBUG  */
 }
 
 void __init efi_unmap_memmap(void)
 {
+	unsigned long size;
+
 	clear_bit(EFI_MEMMAP, &efi.flags);
-	if (memmap.map) {
-		early_memunmap(memmap.map, memmap.nr_map * memmap.desc_size);
-		memmap.map = NULL;
+
+	size = efi.memmap.nr_map * efi.memmap.desc_size;
+	if (efi.memmap.map) {
+		early_memunmap(efi.memmap.map, size);
+		efi.memmap.map = NULL;
 	}
 }
 
@@ -352,8 +346,6 @@ static int __init efi_systab_init(void *phys)
 		       efi.systab->hdr.revision >> 16,
 		       efi.systab->hdr.revision & 0xffff);
 
-	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
-
 	return 0;
 }
 
@@ -440,17 +432,22 @@ static int __init efi_runtime_init(void)
 
 static int __init efi_memmap_init(void)
 {
+	unsigned long addr, size;
+
 	if (efi_enabled(EFI_PARAVIRT))
 		return 0;
 
 	/* Map the EFI memory map */
-	memmap.map = early_memremap((unsigned long)memmap.phys_map,
-				   memmap.nr_map * memmap.desc_size);
-	if (memmap.map == NULL) {
+	size = efi.memmap.nr_map * efi.memmap.desc_size;
+	addr = (unsigned long)efi.memmap.phys_map;
+
+	efi.memmap.map = early_memremap(addr, size);
+	if (efi.memmap.map == NULL) {
 		pr_err("Could not map the memory map!\n");
 		return -ENOMEM;
 	}
-	memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
+
+	efi.memmap.map_end = efi.memmap.map + size;
 
 	if (add_efi_memmap)
 		do_add_efi_memmap();
@@ -552,12 +549,9 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
 void __init runtime_code_page_mkexec(void)
 {
 	efi_memory_desc_t *md;
-	void *p;
 
 	/* Make EFI runtime service code area executable */
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		md = p;
-
+	for_each_efi_memory_desc(md) {
 		if (md->type != EFI_RUNTIME_SERVICES_CODE)
 			continue;
 
@@ -604,12 +598,10 @@ void __init old_map_region(efi_memory_desc_t *md)
 /* Merge contiguous regions of the same type and attribute */
 static void __init efi_merge_regions(void)
 {
-	void *p;
 	efi_memory_desc_t *md, *prev_md = NULL;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+	for_each_efi_memory_desc(md) {
 		u64 prev_size;
-		md = p;
 
 		if (!prev_md) {
 			prev_md = md;
@@ -651,30 +643,31 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
 static void __init save_runtime_map(void)
 {
 #ifdef CONFIG_KEXEC_CORE
+	unsigned long desc_size;
 	efi_memory_desc_t *md;
-	void *tmp, *p, *q = NULL;
+	void *tmp, *q = NULL;
 	int count = 0;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		md = p;
+	desc_size = efi.memmap.desc_size;
 
+	for_each_efi_memory_desc(md) {
 		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
 		    (md->type == EFI_BOOT_SERVICES_CODE) ||
 		    (md->type == EFI_BOOT_SERVICES_DATA))
 			continue;
-		tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL);
+		tmp = krealloc(q, (count + 1) * desc_size, GFP_KERNEL);
 		if (!tmp)
 			goto out;
 		q = tmp;
 
-		memcpy(q + count * memmap.desc_size, md, memmap.desc_size);
+		memcpy(q + count * desc_size, md, desc_size);
 		count++;
 	}
 
-	efi_runtime_map_setup(q, count, memmap.desc_size);
+	efi_runtime_map_setup(q, count, desc_size);
 	return;
 
 out:
@@ -714,10 +707,10 @@ static inline void *efi_map_next_entry_reverse(void *entry)
 {
 	/* Initial call */
 	if (!entry)
-		return memmap.map_end - memmap.desc_size;
+		return efi.memmap.map_end - efi.memmap.desc_size;
 
-	entry -= memmap.desc_size;
-	if (entry < memmap.map)
+	entry -= efi.memmap.desc_size;
+	if (entry < efi.memmap.map)
 		return NULL;
 
 	return entry;
@@ -759,10 +752,10 @@ static void *efi_map_next_entry(void *entry)
 
 	/* Initial call */
 	if (!entry)
-		return memmap.map;
+		return efi.memmap.map;
 
-	entry += memmap.desc_size;
-	if (entry >= memmap.map_end)
+	entry += efi.memmap.desc_size;
+	if (entry >= efi.memmap.map_end)
 		return NULL;
 
 	return entry;
@@ -776,8 +769,11 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 {
 	void *p, *new_memmap = NULL;
 	unsigned long left = 0;
+	unsigned long desc_size;
 	efi_memory_desc_t *md;
 
+	desc_size = efi.memmap.desc_size;
+
 	p = NULL;
 	while ((p = efi_map_next_entry(p))) {
 		md = p;
@@ -792,7 +788,7 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 		efi_map_region(md);
 		get_systab_virt_addr(md);
 
-		if (left < memmap.desc_size) {
+		if (left < desc_size) {
 			new_memmap = realloc_pages(new_memmap, *pg_shift);
 			if (!new_memmap)
 				return NULL;
@@ -801,10 +797,9 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 			(*pg_shift)++;
 		}
 
-		memcpy(new_memmap + (*count * memmap.desc_size), md,
-		       memmap.desc_size);
+		memcpy(new_memmap + (*count * desc_size), md, desc_size);
 
-		left -= memmap.desc_size;
+		left -= desc_size;
 		(*count)++;
 	}
 
@@ -816,7 +811,6 @@ static void __init kexec_enter_virtual_mode(void)
 #ifdef CONFIG_KEXEC_CORE
 	efi_memory_desc_t *md;
 	unsigned int num_pages;
-	void *p;
 
 	efi.systab = NULL;
 
@@ -840,8 +834,7 @@ static void __init kexec_enter_virtual_mode(void)
 	* Map efi regions which were passed via setup_data. The virt_addr is a
 	* fixed addr which was used in first kernel of a kexec boot.
 	*/
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		md = p;
+	for_each_efi_memory_desc(md) {
 		efi_map_region_fixed(md); /* FIXME: add error handling */
 		get_systab_virt_addr(md);
 	}
@@ -850,10 +843,10 @@ static void __init kexec_enter_virtual_mode(void)
 
 	BUG_ON(!efi.systab);
 
-	num_pages = ALIGN(memmap.nr_map * memmap.desc_size, PAGE_SIZE);
+	num_pages = ALIGN(efi.memmap.nr_map * efi.memmap.desc_size, PAGE_SIZE);
 	num_pages >>= PAGE_SHIFT;
 
-	if (efi_setup_page_tables(memmap.phys_map, num_pages)) {
+	if (efi_setup_page_tables(efi.memmap.phys_map, num_pages)) {
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;
 	}
@@ -937,16 +930,16 @@ static void __init __efi_enter_virtual_mode(void)
 
 	if (efi_is_native()) {
 		status = phys_efi_set_virtual_address_map(
-				memmap.desc_size * count,
-				memmap.desc_size,
-				memmap.desc_version,
+				efi.memmap.desc_size * count,
+				efi.memmap.desc_size,
+				efi.memmap.desc_version,
 				(efi_memory_desc_t *)__pa(new_memmap));
 	} else {
 		status = efi_thunk_set_virtual_address_map(
 				efi_phys.set_virtual_address_map,
-				memmap.desc_size * count,
-				memmap.desc_size,
-				memmap.desc_version,
+				efi.memmap.desc_size * count,
+				efi.memmap.desc_size,
+				efi.memmap.desc_version,
 				(efi_memory_desc_t *)__pa(new_memmap));
 	}
 
@@ -1011,13 +1004,11 @@ void __init efi_enter_virtual_mode(void)
 u32 efi_mem_type(unsigned long phys_addr)
 {
 	efi_memory_desc_t *md;
-	void *p;
 
 	if (!efi_enabled(EFI_MEMMAP))
 		return 0;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		md = p;
+	for_each_efi_memory_desc(md) {
 		if ((md->phys_addr <= phys_addr) &&
 		    (phys_addr < (md->phys_addr +
 				  (md->num_pages << EFI_PAGE_SHIFT))))
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 49e4dd4a1f58..6e7242be1c87 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -55,14 +55,12 @@ struct efi_scratch efi_scratch;
 static void __init early_code_mapping_set_exec(int executable)
 {
 	efi_memory_desc_t *md;
-	void *p;
 
 	if (!(__supported_pte_mask & _PAGE_NX))
 		return;
 
 	/* Make EFI service code area executable */
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		md = p;
+	for_each_efi_memory_desc(md) {
 		if (md->type == EFI_RUNTIME_SERVICES_CODE ||
 		    md->type == EFI_BOOT_SERVICES_CODE)
 			efi_set_executable(md, executable);
@@ -253,7 +251,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	 * Map all of RAM so that we can access arguments in the 1:1
 	 * mapping when making EFI runtime calls.
 	 */
-	for_each_efi_memory_desc(&memmap, md) {
+	for_each_efi_memory_desc(md) {
 		if (md->type != EFI_CONVENTIONAL_MEMORY &&
 		    md->type != EFI_LOADER_DATA &&
 		    md->type != EFI_LOADER_CODE)
@@ -398,7 +396,6 @@ void __init efi_runtime_update_mappings(void)
 	unsigned long pfn;
 	pgd_t *pgd = efi_pgd;
 	efi_memory_desc_t *md;
-	void *p;
 
 	if (efi_enabled(EFI_OLD_MEMMAP)) {
 		if (__supported_pte_mask & _PAGE_NX)
@@ -409,9 +406,8 @@ void __init efi_runtime_update_mappings(void)
 	if (!efi_enabled(EFI_NX_PE_DATA))
 		return;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+	for_each_efi_memory_desc(md) {
 		unsigned long pf = 0;
-		md = p;
 
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
 			continue;
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index ab50ada1d56e..097cb09d917b 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -195,10 +195,9 @@ static bool can_free_region(u64 start, u64 size)
 */
 void __init efi_reserve_boot_services(void)
 {
-	void *p;
+	efi_memory_desc_t *md;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
+	for_each_efi_memory_desc(md) {
 		u64 start = md->phys_addr;
 		u64 size = md->num_pages << EFI_PAGE_SHIFT;
 		bool already_reserved;
@@ -250,10 +249,9 @@ void __init efi_reserve_boot_services(void)
 
 void __init efi_free_boot_services(void)
 {
-	void *p;
+	efi_memory_desc_t *md;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
+	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
 
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index 1584cbed0dce..815fec6e05e2 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -21,19 +21,20 @@
 
 #include <linux/efi.h>
 #include <linux/export.h>
+#include <linux/slab.h>
 #include <asm/efi.h>
 #include <linux/io.h>
 #include <asm/uv/bios.h>
 #include <asm/uv/uv_hub.h>
 
-static struct uv_systab uv_systab;
+struct uv_systab *uv_systab;
 
 s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 {
-	struct uv_systab *tab = &uv_systab;
+	struct uv_systab *tab = uv_systab;
 	s64 ret;
 
-	if (!tab->function)
+	if (!tab || !tab->function)
 		/*
 		 * BIOS does not support UV systab
 		 */
@@ -183,34 +184,31 @@ int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus)
 }
 EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
 
-
 #ifdef CONFIG_EFI
 void uv_bios_init(void)
 {
-	struct uv_systab *tab;
-
-	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
-	    (efi.uv_systab == (unsigned long)NULL)) {
-		printk(KERN_CRIT "No EFI UV System Table.\n");
-		uv_systab.function = (unsigned long)NULL;
+	uv_systab = NULL;
+	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) {
+		pr_crit("UV: UVsystab: missing\n");
 		return;
 	}
 
-	tab = (struct uv_systab *)ioremap(efi.uv_systab,
-					sizeof(struct uv_systab));
-	if (strncmp(tab->signature, "UVST", 4) != 0)
-		printk(KERN_ERR "bad signature in UV system table!");
-
-	/*
-	 * Copy table to permanent spot for later use.
-	 */
-	memcpy(&uv_systab, tab, sizeof(struct uv_systab));
-	iounmap(tab);
+	uv_systab = ioremap(efi.uv_systab, sizeof(struct uv_systab));
+	if (!uv_systab || strncmp(uv_systab->signature, UV_SYSTAB_SIG, 4)) {
+		pr_err("UV: UVsystab: bad signature!\n");
+		iounmap(uv_systab);
+		return;
+	}
 
-	printk(KERN_INFO "EFI UV System Table Revision %d\n",
-					uv_systab.revision);
+	if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) {
+		iounmap(uv_systab);
+		uv_systab = ioremap(efi.uv_systab, uv_systab->size);
+		if (!uv_systab) {
+			pr_err("UV: UVsystab: ioremap(%d) failed!\n",
+				uv_systab->size);
+			return;
+		}
+	}
+	pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision);
 }
-#else	/* !CONFIG_EFI */
-
-void uv_bios_init(void) { }
 #endif
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3b6ec42718e4..fdb4d42b4ce5 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -37,7 +37,7 @@ static int timeout_base_ns[] = {
 };
 
 static int timeout_us;
-static int nobau;
+static bool nobau = true;
 static int nobau_perm;
 static cycles_t congested_cycles;
 
@@ -106,13 +106,28 @@ static char *stat_description[] = {
 	"enable:   number times use of the BAU was re-enabled"
 };
 
-static int __init
-setup_nobau(char *arg)
+static int __init setup_bau(char *arg)
 {
-	nobau = 1;
+	int result;
+
+	if (!arg)
+		return -EINVAL;
+
+	result = strtobool(arg, &nobau);
+	if (result)
+		return result;
+
+	/* we need to flip the logic here, so that bau=y sets nobau to false */
+	nobau = !nobau;
+
+	if (!nobau)
+		pr_info("UV BAU Enabled\n");
+	else
+		pr_info("UV BAU Disabled\n");
+
 	return 0;
 }
-early_param("nobau", setup_nobau);
+early_param("bau", setup_bau);
 
 /* base pnode in this partition */
 static int uv_base_pnode __read_mostly;
@@ -131,10 +146,10 @@ set_bau_on(void)
 		pr_info("BAU not initialized; cannot be turned on\n");
 		return;
 	}
-	nobau = 0;
+	nobau = false;
 	for_each_present_cpu(cpu) {
 		bcp = &per_cpu(bau_control, cpu);
-		bcp->nobau = 0;
+		bcp->nobau = false;
 	}
 	pr_info("BAU turned on\n");
 	return;
@@ -146,10 +161,10 @@ set_bau_off(void)
 	int cpu;
 	struct bau_control *bcp;
 
-	nobau = 1;
+	nobau = true;
 	for_each_present_cpu(cpu) {
 		bcp = &per_cpu(bau_control, cpu);
-		bcp->nobau = 1;
+		bcp->nobau = true;
 	}
 	pr_info("BAU turned off\n");
 	return;
@@ -1886,7 +1901,7 @@ static void __init init_per_cpu_tunables(void)
 		bcp = &per_cpu(bau_control, cpu);
 		bcp->baudisabled		= 0;
 		if (nobau)
-			bcp->nobau		= 1;
+			bcp->nobau		= true;
 		bcp->statp			= &per_cpu(ptcstats, cpu);
 		/* time interval to catch a hardware stay-busy bug */
 		bcp->timeout_interval		= usec_2_cycles(2*timeout_us);
@@ -2025,7 +2040,8 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 			return 1;
 		}
 		bcp->uvhub_master = *hmasterp;
-		bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu);
+
 		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
 			printk(KERN_EMERG "%d cpus per uvhub invalid\n",
 				bcp->uvhub_cpu);
diff --git a/arch/x86/platform/uv/uv_sysfs.c b/arch/x86/platform/uv/uv_sysfs.c
index 5d4ba301e776..e9da9ebd924a 100644
--- a/arch/x86/platform/uv/uv_sysfs.c
+++ b/arch/x86/platform/uv/uv_sysfs.c
@@ -34,7 +34,7 @@ static ssize_t partition_id_show(struct kobject *kobj,
 static ssize_t coherence_id_show(struct kobject *kobj,
 			struct kobj_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%ld\n", partition_coherence_id());
+	return snprintf(buf, PAGE_SIZE, "%ld\n", uv_partition_coherence_id());
 }
 
 static struct kobj_attribute partition_id_attr =
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 2b158a9fa1d7..b333fc45f9ec 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -165,7 +165,7 @@ static __init int uv_rtc_allocate_timers(void)
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
 		int bid = uv_cpu_to_blade_id(cpu);
-		int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		int bcpu = uv_cpu_blade_processor_id(cpu);
 		struct uv_rtc_timer_head *head = blade_info[bid];
 
 		if (!head) {
@@ -226,7 +226,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 	int pnode = uv_cpu_to_pnode(cpu);
 	int bid = uv_cpu_to_blade_id(cpu);
 	struct uv_rtc_timer_head *head = blade_info[bid];
-	int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+	int bcpu = uv_cpu_blade_processor_id(cpu);
 	u64 *t = &head->cpu[bcpu].expires;
 	unsigned long flags;
 	int next_cpu;
@@ -262,7 +262,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
 	int pnode = uv_cpu_to_pnode(cpu);
 	int bid = uv_cpu_to_blade_id(cpu);
 	struct uv_rtc_timer_head *head = blade_info[bid];
-	int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+	int bcpu = uv_cpu_blade_processor_id(cpu);
 	u64 *t = &head->cpu[bcpu].expires;
 	unsigned long flags;
 	int rc = 0;
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 291226b952a9..9f14bd34581d 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -106,7 +106,7 @@ static int resume_physical_mapping_init(pgd_t *pgd_base)
 			 * normal page tables.
 			 * NOTE: We can mark everything as executable here
 			 */
-			if (cpu_has_pse) {
+			if (boot_cpu_has(X86_FEATURE_PSE)) {
 				set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC));
 				pfn += PTRS_PER_PTE;
 			} else {
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index df280da34825..d957d5f21a86 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -1,4 +1,4 @@
-config AMD_MCE_INJ
+config MCE_AMD_INJ
 	tristate "Simple MCE injection interface for AMD processors"
 	depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB
 	default n
diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile
index dd2c98b84037..5f94546db280 100644
--- a/arch/x86/ras/Makefile
+++ b/arch/x86/ras/Makefile
@@ -1,2 +1,2 @@
-obj-$(CONFIG_AMD_MCE_INJ)		+= mce_amd_inj.o
+obj-$(CONFIG_MCE_AMD_INJ)		+= mce_amd_inj.o
 
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 9e02dcaef683..e69f4701a076 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -290,14 +290,33 @@ static void do_inject(void)
 	wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS,
 		     (u32)mcg_status, (u32)(mcg_status >> 32));
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b),
-		     (u32)i_mce.status, (u32)(i_mce.status >> 32));
+	if (boot_cpu_has(X86_FEATURE_SMCA)) {
+		if (inj_type == DFR_INT_INJ) {
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b),
+				     (u32)i_mce.status, (u32)(i_mce.status >> 32));
+
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b),
+				     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
+		} else {
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b),
+				     (u32)i_mce.status, (u32)(i_mce.status >> 32));
+
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b),
+				     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
+		}
+
+		wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b),
+			     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
+	} else {
+		wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b),
+			     (u32)i_mce.status, (u32)(i_mce.status >> 32));
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b),
-		     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
+		wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b),
+			     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b),
-		     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
+		wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b),
+			     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
+	}
 
 	toggle_hw_mce_inject(cpu, false);
 
diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh
deleted file mode 100644
index 1a4c17bb3910..000000000000
--- a/arch/x86/tools/calc_run_size.sh
+++ /dev/null
@@ -1,42 +0,0 @@
-#!/bin/sh
-#
-# Calculate the amount of space needed to run the kernel, including room for
-# the .bss and .brk sections.
-#
-# Usage:
-# objdump -h a.out | sh calc_run_size.sh
-
-NUM='\([0-9a-fA-F]*[ \t]*\)'
-OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p')
-if [ -z "$OUT" ] ; then
-	echo "Never found .bss or .brk file offset" >&2
-	exit 1
-fi
-
-OUT=$(echo ${OUT# })
-sizeA=$(printf "%d" 0x${OUT%% *})
-OUT=${OUT#* }
-offsetA=$(printf "%d" 0x${OUT%% *})
-OUT=${OUT#* }
-sizeB=$(printf "%d" 0x${OUT%% *})
-OUT=${OUT#* }
-offsetB=$(printf "%d" 0x${OUT%% *})
-
-run_size=$(( $offsetA + $sizeA + $sizeB ))
-
-# BFD linker shows the same file offset in ELF.
-if [ "$offsetA" -ne "$offsetB" ] ; then
-	# Gold linker shows them as consecutive.
-	endB=$(( $offsetB + $sizeB ))
-	if [ "$endB" != "$run_size" ] ; then
-		printf "sizeA: 0x%x\n" $sizeA >&2
-		printf "offsetA: 0x%x\n" $offsetA >&2
-		printf "sizeB: 0x%x\n" $sizeB >&2
-		printf "offsetB: 0x%x\n" $offsetB >&2
-		echo ".bss and .brk are non-contiguous" >&2
-		exit 1
-	fi
-fi
-
-printf "%d\n" $run_size
-exit 0
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 880862c7d9dd..760789ae8562 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -75,7 +75,6 @@
 #include <asm/mach_traps.h>
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
-#include <asm/pat.h>
 #include <asm/cpu.h>
 
 #ifdef CONFIG_ACPI
@@ -1093,6 +1092,26 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 	return ret;
 }
 
+static u64 xen_read_msr(unsigned int msr)
+{
+	/*
+	 * This will silently swallow a #GP from RDMSR.  It may be worth
+	 * changing that.
+	 */
+	int err;
+
+	return xen_read_msr_safe(msr, &err);
+}
+
+static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+{
+	/*
+	 * This will silently swallow a #GP from WRMSR.  It may be worth
+	 * changing that.
+	 */
+	xen_write_msr_safe(msr, low, high);
+}
+
 void xen_setup_shared_info(void)
 {
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
@@ -1187,13 +1206,11 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 }
 
 static const struct pv_info xen_info __initconst = {
-	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
 #ifdef CONFIG_X86_64
 	.extra_user_64bit_cs = FLAT_USER_CS64,
 #endif
-	.features = 0,
 	.name = "Xen",
 };
 
@@ -1223,8 +1240,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
 	.wbinvd = native_wbinvd,
 
-	.read_msr = xen_read_msr_safe,
-	.write_msr = xen_write_msr_safe,
+	.read_msr = xen_read_msr,
+	.write_msr = xen_write_msr,
+
+	.read_msr_safe = xen_read_msr_safe,
+	.write_msr_safe = xen_write_msr_safe,
 
 	.read_pmc = xen_read_pmc,
 
@@ -1469,10 +1489,10 @@ static void xen_pvh_set_cr_flags(int cpu)
 	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
 	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
 	*/
-	if (cpu_has_pse)
+	if (boot_cpu_has(X86_FEATURE_PSE))
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
-	if (cpu_has_pge)
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 }
 
@@ -1506,12 +1526,16 @@ static void __init xen_pvh_early_guest_init(void)
 }
 #endif    /* CONFIG_XEN_PVH */
 
+static void __init xen_dom0_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 1;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	unsigned long initrd_start = 0;
-	u64 pat;
 	int rc;
 
 	if (!xen_start_info)
@@ -1527,8 +1551,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	if (xen_initial_domain())
-		pv_info.features |= PV_SUPPORTED_RTC;
 	pv_init_ops = xen_init_ops;
 	if (!xen_pvh_domain()) {
 		pv_cpu_ops = xen_cpu_ops;
@@ -1618,13 +1640,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 				   xen_start_info->nr_pages);
 	xen_reserve_special_pages();
 
-	/*
-	 * Modify the cache mode translation tables to match Xen's PAT
-	 * configuration.
-	 */
-	rdmsrl(MSR_IA32_CR_PAT, pat);
-	pat_init_cache_modes(pat);
-
 	/* keep using Xen gdt for now; no urgent need to change it */
 
 #ifdef CONFIG_X86_32
@@ -1670,6 +1685,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	boot_params.hdr.ramdisk_image = initrd_start;
 	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
+	boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
 
 	if (!xen_initial_domain()) {
 		add_preferred_console("xenboot", 0, NULL);
@@ -1687,6 +1703,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 			.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
 		};
 
+		x86_platform.set_legacy_features =
+				xen_dom0_set_legacy_features;
 		xen_init_vga(info, xen_start_info->console.dom0.info_size);
 		xen_start_info->console.domU.mfn = 0;
 		xen_start_info->console.domU.evtchn = 0;