Merge commit 'v3.0.8' into android-3.0

89 files changed, 1628 insertions, 607 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 81f0b93a0cbb..ff8424ba5b89 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1298,6 +1298,20 @@ source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
+config ARM_ERRATA_764369
+	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for erratum 764369
+	  affecting Cortex-A9 MPCore with two or more processors (all
+	  current revisions). Under certain timing circumstances, a data
+	  cache line maintenance operation by MVA targeting an Inner
+	  Shareable memory region may fail to proceed up to either the
+	  Point of Coherency or to the Point of Unification of the
+	  system. This workaround adds a DSB instruction before the
+	  relevant cache maintenance functions and sets a specific bit
+	  in the diagnostic control register of the SCU.
+
 endmenu
 
 menu "Kernel Features"
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 8c73900da9ed..253cc86318bf 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -25,17 +25,17 @@
 
 #ifdef CONFIG_SMP
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	smp_mb();						\
 	__asm__ __volatile__(					\
-	"1:	ldrex	%1, [%2]\n"				\
+	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
-	"2:	strex	%1, %0, [%2]\n"				\
-	"	teq	%1, #0\n"				\
+	"2:	strex	%2, %0, [%3]\n"				\
+	"	teq	%2, #0\n"				\
 	"	bne	1b\n"					\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -73,14 +73,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #include <linux/preempt.h>
 #include <asm/domain.h>
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	" T(ldr) "	%1, [%2]\n"			\
+	"1:	" T(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
-	"2:	" T(str) "	%0, [%2]\n"			\
+	"2:	" T(str) "	%0, [%3]\n"			\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -117,7 +117,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
+	int oldval = 0, ret, tmp;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
@@ -129,19 +129,19 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %3", ret, oldval, uaddr, ~oparg);
+		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	default:
 		ret = -ENOSYS;
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index b3dd3bf61781..2a20876ee3dd 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -65,7 +65,7 @@
 #define L2X0_AUX_CTRL_MASK			0xc0000fff
 #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT	16
 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT		17
-#define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x3 << 17)
+#define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x7 << 17)
 #define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT	22
 #define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT		26
 #define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT		27
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4960686afb58..43727630ae0f 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -264,8 +264,8 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]	    =
 					ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
-	[PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_COHERENT_LINE_HIT,
-	[PERF_COUNT_HW_CACHE_MISSES]	    = ARMV7_PERFCTR_COHERENT_LINE_MISS,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = ARMV7_PERFCTR_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index a1e757c3439b..cb7dd40e0d3b 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -13,6 +13,7 @@
 
 #include <asm/smp_scu.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 
 #define SCU_CTRL		0x00
 #define SCU_CONFIG		0x04
@@ -36,6 +37,15 @@ void __init scu_enable(void __iomem *scu_base)
 {
 	u32 scu_ctrl;
 
+#ifdef CONFIG_ARM_ERRATA_764369
+	/* Cortex-A9 only */
+	if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) {
+		scu_ctrl = __raw_readl(scu_base + 0x30);
+		if (!(scu_ctrl & 1))
+			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+	}
+#endif
+
 	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
 	/* already enabled? */
 	if (scu_ctrl & 1)
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index a7b41bf505f1..e83cc860c87a 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -115,6 +115,32 @@ static struct spi_board_info da850evm_spi_info[] = {
 	},
 };
 
+#ifdef CONFIG_MTD
+static void da850_evm_m25p80_notify_add(struct mtd_info *mtd)
+{
+	char *mac_addr = davinci_soc_info.emac_pdata->mac_addr;
+	size_t retlen;
+
+	if (!strcmp(mtd->name, "MAC-Address")) {
+		mtd->read(mtd, 0, ETH_ALEN, &retlen, mac_addr);
+		if (retlen == ETH_ALEN)
+			pr_info("Read MAC addr from SPI Flash: %pM\n",
+				mac_addr);
+	}
+}
+
+static struct mtd_notifier da850evm_spi_notifier = {
+	.add	= da850_evm_m25p80_notify_add,
+};
+
+static void da850_evm_setup_mac_addr(void)
+{
+	register_mtd_user(&da850evm_spi_notifier);
+}
+#else
+static void da850_evm_setup_mac_addr(void) { }
+#endif
+
 static struct mtd_partition da850_evm_norflash_partition[] = {
 	{
 		.name           = "bootloaders + env",
@@ -1237,6 +1263,8 @@ static __init void da850_evm_init(void)
 	if (ret)
 		pr_warning("da850_evm_init: spi 1 registration failed: %d\n",
 				ret);
+
+	da850_evm_setup_mac_addr();
 }
 
 #ifdef CONFIG_SERIAL_8250_CONSOLE
diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S
index fb5e72b532b0..5f1e045a3ad1 100644
--- a/arch/arm/mach-davinci/sleep.S
+++ b/arch/arm/mach-davinci/sleep.S
@@ -217,7 +217,11 @@ ddr2clk_stop_done:
 ENDPROC(davinci_ddr_psc_config)
 
 CACHE_FLUSH:
-	.word	arm926_flush_kern_cache_all
+#ifdef CONFIG_CPU_V6
+	.word	v6_flush_kern_cache_all
+#else
+	.word   arm926_flush_kern_cache_all
+#endif
 
 ENTRY(davinci_cpu_suspend_sz)
 	.word	. - davinci_cpu_suspend
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index 5ed51b84c1b2..cf7e5985eebf 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -160,7 +160,7 @@ void __init dove_spi0_init(void)
 
 void __init dove_spi1_init(void)
 {
-	orion_spi_init(DOVE_SPI1_PHYS_BASE, get_tclk());
+	orion_spi_1_init(DOVE_SPI1_PHYS_BASE, get_tclk());
 }
 
 /*****************************************************************************
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 2fbbdd5eac35..fcf0ae95651f 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -337,15 +337,15 @@ static unsigned long timer_reload;
 static void integrator_clocksource_init(u32 khz)
 {
 	void __iomem *base = (void __iomem *)TIMER2_VA_BASE;
-	u32 ctrl = TIMER_CTRL_ENABLE;
+	u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC;
 
 	if (khz >= 1500) {
 		khz /= 16;
-		ctrl = TIMER_CTRL_DIV16;
+		ctrl |= TIMER_CTRL_DIV16;
 	}
 
-	writel(ctrl, base + TIMER_CTRL);
 	writel(0xffff, base + TIMER_LOAD);
+	writel(ctrl, base + TIMER_CTRL);
 
 	clocksource_mmio_init(base + TIMER_VALUE, "timer2",
 		khz * 1000, 200, 16, clocksource_mmio_readl_down);
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index f8b9392ee347..9a9706cf1496 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -6,6 +6,7 @@ config UX500_SOC_COMMON
 	select ARM_GIC
 	select HAS_MTU
 	select ARM_ERRATA_753970
+	select ARM_ERRATA_754322
 
 menu "Ux500 SoC"
 
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index d32f02b61866..35931191c84e 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -174,6 +174,10 @@ ENTRY(v7_coherent_user_range)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
  USER(	mcr	p15, 0, r12, c7, c11, 1	)	@ clean D line to the point of unification
 	add	r12, r12, r2
@@ -223,6 +227,10 @@ ENTRY(v7_flush_kern_dcache_area)
 	add	r1, r0, r1
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
 	add	r0, r0, r2
@@ -247,6 +255,10 @@ v7_dma_inv_range:
 	sub	r3, r2, #1
 	tst	r0, r3
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 
 	tst	r1, r3
@@ -270,6 +282,10 @@ v7_dma_clean_range:
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D / U line
 	add	r0, r0, r2
@@ -288,6 +304,10 @@ ENTRY(v7_dma_flush_range)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 	add	r0, r0, r2
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 82a093cee09a..f96d2c730020 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -322,6 +322,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
+	else
+		__dma_free_buffer(page, size);
 
 	return addr;
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index c19571c40a21..4a4eba5192f3 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -473,6 +473,13 @@ static void __init free_unused_memmap(struct meminfo *mi)
 		 */
 		bank_start = min(bank_start,
 				 ALIGN(prev_bank_end, PAGES_PER_SECTION));
+#else
+		/*
+		 * Align down here since the VM subsystem insists that the
+		 * memmap entries are valid from the bank start aligned to
+		 * MAX_ORDER_NR_PAGES.
+		 */
+		bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES);
 #endif
 		/*
 		 * If we had a previous bank, and there is a space
diff --git a/arch/arm/plat-mxc/include/mach/iomux-v3.h b/arch/arm/plat-mxc/include/mach/iomux-v3.h
index 82620af1922f..ebbce33097a7 100644
--- a/arch/arm/plat-mxc/include/mach/iomux-v3.h
+++ b/arch/arm/plat-mxc/include/mach/iomux-v3.h
@@ -66,7 +66,6 @@ typedef u64 iomux_v3_cfg_t;
 #define MUX_MODE_MASK		((iomux_v3_cfg_t)0x1f << MUX_MODE_SHIFT)
 #define MUX_PAD_CTRL_SHIFT	41
 #define MUX_PAD_CTRL_MASK	((iomux_v3_cfg_t)0x1ffff << MUX_PAD_CTRL_SHIFT)
-#define NO_PAD_CTRL		((iomux_v3_cfg_t)1 << (MUX_PAD_CTRL_SHIFT + 16))
 #define MUX_SEL_INPUT_SHIFT	58
 #define MUX_SEL_INPUT_MASK	((iomux_v3_cfg_t)0xf << MUX_SEL_INPUT_SHIFT)
 
@@ -85,6 +84,7 @@ typedef u64 iomux_v3_cfg_t;
  * Use to set PAD control
  */
 
+#define NO_PAD_CTRL			(1 << 16)
 #define PAD_CTL_DVS			(1 << 13)
 #define PAD_CTL_HYS			(1 << 8)
 
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index 850265373611..466af40c5822 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -158,7 +158,7 @@ static int sync_serial_open(struct inode *inode, struct file *file);
 static int sync_serial_release(struct inode *inode, struct file *file);
 static unsigned int sync_serial_poll(struct file *filp, poll_table *wait);
 
-static int sync_serial_ioctl(struct file *file,
+static long sync_serial_ioctl(struct file *file,
 	unsigned int cmd, unsigned long arg);
 static ssize_t sync_serial_write(struct file *file, const char *buf,
 	size_t count, loff_t *ppos);
@@ -625,11 +625,11 @@ static int sync_serial_open(struct inode *inode, struct file *file)
 			*R_IRQ_MASK1_SET = 1 << port->data_avail_bit;
 		DEBUG(printk(KERN_DEBUG "sser%d rec started\n", dev));
 	}
-	ret = 0;
+	err = 0;
 	
 out:
 	mutex_unlock(&sync_serial_mutex);
-	return ret;
+	return err;
 }
 
 static int sync_serial_release(struct inode *inode, struct file *file)
diff --git a/arch/cris/arch-v10/kernel/irq.c b/arch/cris/arch-v10/kernel/irq.c
index 907cfb5a873d..ba0e5965d6e3 100644
--- a/arch/cris/arch-v10/kernel/irq.c
+++ b/arch/cris/arch-v10/kernel/irq.c
@@ -20,6 +20,9 @@
 #define crisv10_mask_irq(irq_nr) (*R_VECT_MASK_CLR = 1 << (irq_nr));
 #define crisv10_unmask_irq(irq_nr) (*R_VECT_MASK_SET = 1 << (irq_nr));
 
+extern void kgdb_init(void);
+extern void breakpoint(void);
+
 /* don't use set_int_vector, it bypasses the linux interrupt handlers. it is
  * global just so that the kernel gdb can use it.
  */
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index 29b74a105830..332f19c54557 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -11,8 +11,6 @@
 
 #ifdef __KERNEL__
 
-#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 #include <asm/processor.h>
@@ -67,8 +65,10 @@ struct thread_info {
 
 #define init_thread_info	(init_thread_union.thread_info)
 
+#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
 /* thread information allocation */
-#define alloc_thread_info(tsk, node) ((struct thread_info *) __get_free_pages(GFP_KERNEL,1))
+#define alloc_thread_info_node(tsk, node)	\
+	((struct thread_info *) __get_free_pages(GFP_KERNEL, 1))
 #define free_thread_info(ti) free_pages((unsigned long) (ti), 1)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index 73031f7fc827..4397972949fa 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -18,7 +18,7 @@
 #include <linux/init.h>
 
 #include <linux/spinlock.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
@@ -86,7 +86,6 @@ struct jz_gpio_chip {
 	spinlock_t lock;
 
 	struct gpio_chip gpio_chip;
-	struct sys_device sysdev;
 };
 
 static struct jz_gpio_chip jz4740_gpio_chips[];
@@ -459,49 +458,47 @@ static struct jz_gpio_chip jz4740_gpio_chips[] = {
 	JZ4740_GPIO_CHIP(D),
 };
 
-static inline struct jz_gpio_chip *sysdev_to_chip(struct sys_device *dev)
+static void jz4740_gpio_suspend_chip(struct jz_gpio_chip *chip)
 {
-	return container_of(dev, struct jz_gpio_chip, sysdev);
+	chip->suspend_mask = readl(chip->base + JZ_REG_GPIO_MASK);
+	writel(~(chip->wakeup), chip->base + JZ_REG_GPIO_MASK_SET);
+	writel(chip->wakeup, chip->base + JZ_REG_GPIO_MASK_CLEAR);
 }
 
-static int jz4740_gpio_suspend(struct sys_device *dev, pm_message_t state)
+static int jz4740_gpio_suspend(void)
 {
-	struct jz_gpio_chip *chip = sysdev_to_chip(dev);
+	int i;
 
-	chip->suspend_mask = readl(chip->base + JZ_REG_GPIO_MASK);
-	writel(~(chip->wakeup), chip->base + JZ_REG_GPIO_MASK_SET);
-	writel(chip->wakeup, chip->base + JZ_REG_GPIO_MASK_CLEAR);
+	for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); i++)
+		jz4740_gpio_suspend_chip(&jz4740_gpio_chips[i]);
 
 	return 0;
 }
 
-static int jz4740_gpio_resume(struct sys_device *dev)
+static void jz4740_gpio_resume_chip(struct jz_gpio_chip *chip)
 {
-	struct jz_gpio_chip *chip = sysdev_to_chip(dev);
 	uint32_t mask = chip->suspend_mask;
 
 	writel(~mask, chip->base + JZ_REG_GPIO_MASK_CLEAR);
 	writel(mask, chip->base + JZ_REG_GPIO_MASK_SET);
+}
 
-	return 0;
+static void jz4740_gpio_resume(void)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(jz4740_gpio_chips) - 1; i >= 0 ; i--)
+		jz4740_gpio_resume_chip(&jz4740_gpio_chips[i]);
 }
 
-static struct sysdev_class jz4740_gpio_sysdev_class = {
-	.name = "gpio",
+static struct syscore_ops jz4740_gpio_syscore_ops = {
 	.suspend = jz4740_gpio_suspend,
 	.resume = jz4740_gpio_resume,
 };
 
-static int jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id)
+static void jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id)
 {
-	int ret, irq;
-
-	chip->sysdev.id = id;
-	chip->sysdev.cls = &jz4740_gpio_sysdev_class;
-	ret = sysdev_register(&chip->sysdev);
-
-	if (ret)
-		return ret;
+	int irq;
 
 	spin_lock_init(&chip->lock);
 
@@ -519,22 +516,17 @@ static int jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id)
 		irq_set_chip_and_handler(irq, &jz_gpio_irq_chip,
 					 handle_level_irq);
 	}
-
-	return 0;
 }
 
 static int __init jz4740_gpio_init(void)
 {
 	unsigned int i;
-	int ret;
-
-	ret = sysdev_class_register(&jz4740_gpio_sysdev_class);
-	if (ret)
-		return ret;
 
 	for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); ++i)
 		jz4740_gpio_chip_init(&jz4740_gpio_chips[i], i);
 
+	register_syscore_ops(&jz4740_gpio_syscore_ops);
+
 	printk(KERN_INFO "JZ4740 GPIO initialized\n");
 
 	return 0;
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index f81955934aeb..26fd1146dda6 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -259,10 +259,10 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define ATOMIC64_INIT(i) ((atomic64_t) { (i) })
 
-static __inline__ int
+static __inline__ s64
 __atomic64_add_return(s64 i, atomic64_t *v)
 {
-	int ret;
+	s64 ret;
 	unsigned long flags;
 	_atomic_spin_lock_irqsave(v, flags);
 
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 67a33cc27ef2..2388bdb32832 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -5,11 +5,14 @@
 
 #include <linux/futex.h>
 #include <linux/uaccess.h>
+#include <asm/atomic.h>
 #include <asm/errno.h>
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
+	unsigned long int flags;
+	u32 val;
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
@@ -18,21 +21,58 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)))
 		return -EFAULT;
 
 	pagefault_disable();
 
+	_atomic_spin_lock_irqsave(uaddr, flags);
+
 	switch (op) {
 	case FUTEX_OP_SET:
+		/* *(int *)UADDR2 = OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret)
+			ret = put_user(oparg, uaddr);
+		break;
 	case FUTEX_OP_ADD:
+		/* *(int *)UADDR2 += OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval + oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_OR:
+		/* *(int *)UADDR2 |= OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval | oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_ANDN:
+		/* *(int *)UADDR2 &= ~OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval & ~oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_XOR:
+		/* *(int *)UADDR2 ^= OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval ^ oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	default:
 		ret = -ENOSYS;
 	}
 
+	_atomic_spin_unlock_irqrestore(uaddr, flags);
+
 	pagefault_enable();
 
 	if (!ret) {
@@ -54,7 +94,9 @@ static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	int ret;
 	u32 val;
+	unsigned long flags;
 
 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
@@ -65,12 +107,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	if (get_user(val, uaddr))
-		return -EFAULT;
-	if (val == oldval && put_user(newval, uaddr))
-		return -EFAULT;
+	/* HPPA has no cmpxchg in hardware and therefore the
+	 * best we can do here is use an array of locks. The
+	 * lock selected is based on a hash of the userspace
+	 * address. This should scale to a couple of CPUs.
+	 */
+
+	_atomic_spin_lock_irqsave(uaddr, flags);
+
+	ret = get_user(val, uaddr);
+
+	if (!ret && val == oldval)
+		ret = put_user(newval, uaddr);
+
 	*uval = val;
-	return 0;
+
+	_atomic_spin_unlock_irqrestore(uaddr, flags);
+
+	return ret;
 }
 
 #endif /*__KERNEL__*/
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
index 3392de3e7be0..d61de64f990a 100644
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@@ -821,8 +821,9 @@
 #define __NR_open_by_handle_at	(__NR_Linux + 326)
 #define __NR_syncfs		(__NR_Linux + 327)
 #define __NR_setns		(__NR_Linux + 328)
+#define __NR_sendmmsg		(__NR_Linux + 329)
 
-#define __NR_Linux_syscalls	(__NR_setns + 1)
+#define __NR_Linux_syscalls	(__NR_sendmmsg + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 34a4f5a2fffb..e66366fd2abc 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -427,6 +427,7 @@
 	ENTRY_COMP(open_by_handle_at)
 	ENTRY_SAME(syncfs)
 	ENTRY_SAME(setns)
+	ENTRY_COMP(sendmmsg)
 
 	/* Nothing yet */
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index c016033ba78d..3b22142c40df 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1020,7 +1020,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align)
 	}
 	if (addr == 0)
 		return 0;
-	RELOC(alloc_bottom) = addr;
+	RELOC(alloc_bottom) = addr + size;
 
 	prom_debug(" -> %x\n", addr);
 	prom_debug("  alloc_bottom : %x\n", RELOC(alloc_bottom));
@@ -1834,7 +1834,7 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
 		chunk = alloc_up(room, 0);
 		if (chunk == 0)
 			prom_panic("No memory for flatten_device_tree (claim failed)");
-		*mem_end = RELOC(alloc_top);
+		*mem_end = chunk + room;
 	}
 
 	ret = (void *)*mem_start;
@@ -2053,7 +2053,7 @@ static void __init flatten_device_tree(void)
 	mem_start = (unsigned long)alloc_up(room, PAGE_SIZE);
 	if (mem_start == 0)
 		prom_panic("Can't allocate initial device-tree chunk\n");
-	mem_end = RELOC(alloc_top);
+	mem_end = mem_start + room;
 
 	/* Get root of tree */
 	root = call_prom("peer", 1, 1, (phandle)0);
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index e9190073bb97..0e8656370063 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -181,7 +181,7 @@ static void dtl_stop(struct dtl *dtl)
 
 	lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
 
-	unregister_dtl(hwcpu, __pa(dtl->buf));
+	unregister_dtl(hwcpu);
 }
 
 static u64 dtl_current_index(struct dtl *dtl)
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 54cf3a4aa16b..1118cb79f9e3 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -26,6 +26,17 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 	/* Don't risk a hypervisor call if we're crashing */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
 		unsigned long addr;
+		int ret;
+
+		if (get_lppaca()->dtl_enable_mask) {
+			ret = unregister_dtl(hard_smp_processor_id());
+			if (ret) {
+				pr_err("WARNING: DTL deregistration for cpu "
+				       "%d (hw %d) failed with %d\n",
+				       smp_processor_id(),
+				       hard_smp_processor_id(), ret);
+			}
+		}
 
 		addr = __pa(get_slb_shadow());
 		if (unregister_slb_shadow(hard_smp_processor_id(), addr))
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 39e6e0a7b2fa..ed96b3765377 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -395,7 +395,7 @@ static void pSeries_lpar_hptab_clear(void)
 		unsigned long ptel;
 	} ptes[4];
 	long lpar_rc;
-	int i, j;
+	unsigned long i, j;
 
 	/* Read in batches of 4,
 	 * invalidate only valid entries not in the VRMA
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index 4bf21207d7d3..a6921aec2d6f 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -73,9 +73,9 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
 	return vpa_call(0x3, cpu, vpa);
 }
 
-static inline long unregister_dtl(unsigned long cpu, unsigned long vpa)
+static inline long unregister_dtl(unsigned long cpu)
 {
-	return vpa_call(0x6, cpu, vpa);
+	return vpa_call(0x6, cpu, 0);
 }
 
 static inline long register_dtl(unsigned long cpu, unsigned long vpa)
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index b3fd081d56f5..cdd765bb66ba 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -54,6 +54,7 @@
 #define ODSR_CLEAR		0x1c00
 #define LTLEECSR_ENABLE_ALL	0xFFC000FC
 #define ESCSR_CLEAR		0x07120204
+#define IECSR_CLEAR		0x80000000
 
 #define RIO_PORT1_EDCSR		0x0640
 #define RIO_PORT2_EDCSR		0x0680
@@ -1089,11 +1090,11 @@ static void port_error_handler(struct rio_mport *port, int offset)
 
 	if (offset == 0) {
 		out_be32((u32 *)(rio_regs_win + RIO_PORT1_EDCSR), 0);
-		out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), IECSR_CLEAR);
 		out_be32((u32 *)(rio_regs_win + RIO_ESCSR), ESCSR_CLEAR);
 	} else {
 		out_be32((u32 *)(rio_regs_win + RIO_PORT2_EDCSR), 0);
-		out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), IECSR_CLEAR);
 		out_be32((u32 *)(rio_regs_win + RIO_PORT2_ESCSR), ESCSR_CLEAR);
 	}
 }
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 253986bd6bb6..2e794193cd9b 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -53,6 +53,7 @@ config SPARC64
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select IRQ_PREFLOW_FASTEOI
+	select HAVE_C_RECORDMCOUNT
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index 38e9aa1b2cea..3fc595ad6188 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -26,61 +26,28 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()
 
-#include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #ifdef __KERNEL__
 
+extern int ffs(int x);
+extern unsigned long __ffs(unsigned long);
+
+#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>
 
 /*
  * hweightN: returns the hamming weight (i.e. the number
  * of bits set) of a N-bit word
  */
 
-#ifdef ULTRA_HAS_POPULATION_COUNT
-
-static inline unsigned int __arch_hweight64(unsigned long w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w));
-	return res;
-}
-
-static inline unsigned int __arch_hweight32(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffffffff));
-	return res;
-}
+extern unsigned long __arch_hweight64(__u64 w);
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);
 
-static inline unsigned int __arch_hweight16(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffff));
-	return res;
-}
-
-static inline unsigned int __arch_hweight8(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xff));
-	return res;
-}
-
-#else
-
-#include <asm-generic/bitops/arch_hweight.h>
-
-#endif
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h
index e67880381b84..7df8b7f544d4 100644
--- a/arch/sparc/include/asm/elf_64.h
+++ b/arch/sparc/include/asm/elf_64.h
@@ -59,15 +59,33 @@
 #define R_SPARC_6		45
 
 /* Bits present in AT_HWCAP, primarily for Sparc32.  */
-
-#define HWCAP_SPARC_FLUSH       1    /* CPU supports flush instruction. */
-#define HWCAP_SPARC_STBAR       2
-#define HWCAP_SPARC_SWAP        4
-#define HWCAP_SPARC_MULDIV      8
-#define HWCAP_SPARC_V9		16
-#define HWCAP_SPARC_ULTRA3	32
-#define HWCAP_SPARC_BLKINIT	64
-#define HWCAP_SPARC_N2		128
+#define HWCAP_SPARC_FLUSH       0x00000001
+#define HWCAP_SPARC_STBAR       0x00000002
+#define HWCAP_SPARC_SWAP        0x00000004
+#define HWCAP_SPARC_MULDIV      0x00000008
+#define HWCAP_SPARC_V9		0x00000010
+#define HWCAP_SPARC_ULTRA3	0x00000020
+#define HWCAP_SPARC_BLKINIT	0x00000040
+#define HWCAP_SPARC_N2		0x00000080
+
+/* Solaris compatible AT_HWCAP bits. */
+#define AV_SPARC_MUL32		0x00000100 /* 32x32 multiply is efficient */
+#define AV_SPARC_DIV32		0x00000200 /* 32x32 divide is efficient */
+#define AV_SPARC_FSMULD		0x00000400 /* 'fsmuld' is efficient */
+#define AV_SPARC_V8PLUS		0x00000800 /* v9 insn available to 32bit */
+#define AV_SPARC_POPC		0x00001000 /* 'popc' is efficient */
+#define AV_SPARC_VIS		0x00002000 /* VIS insns available */
+#define AV_SPARC_VIS2		0x00004000 /* VIS2 insns available */
+#define AV_SPARC_ASI_BLK_INIT	0x00008000 /* block init ASIs available */
+#define AV_SPARC_FMAF		0x00010000 /* fused multiply-add */
+#define AV_SPARC_VIS3		0x00020000 /* VIS3 insns available */
+#define AV_SPARC_HPC		0x00040000 /* HPC insns available */
+#define AV_SPARC_RANDOM		0x00080000 /* 'random' insn available */
+#define AV_SPARC_TRANS		0x00100000 /* transaction insns available */
+#define AV_SPARC_FJFMAU		0x00200000 /* unfused multiply-add */
+#define AV_SPARC_IMA		0x00400000 /* integer multiply-add */
+#define AV_SPARC_ASI_CACHE_SPARING \
+				0x00800000 /* cache sparing ASIs available */
 
 #define CORE_DUMP_USE_REGSET
 
@@ -162,31 +180,8 @@ typedef struct {
 #define ELF_ET_DYN_BASE		0x0000010000000000UL
 #define COMPAT_ELF_ET_DYN_BASE	0x0000000070000000UL
 
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this cpu supports.  */
-
-/* On Ultra, we support all of the v8 capabilities. */
-static inline unsigned int sparc64_elf_hwcap(void)
-{
-	unsigned int cap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
-			    HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV |
-			    HWCAP_SPARC_V9);
-
-	if (tlb_type == cheetah || tlb_type == cheetah_plus)
-		cap |= HWCAP_SPARC_ULTRA3;
-	else if (tlb_type == hypervisor) {
-		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2)
-			cap |= HWCAP_SPARC_BLKINIT;
-		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2)
-			cap |= HWCAP_SPARC_N2;
-	}
-
-	return cap;
-}
-
-#define ELF_HWCAP	sparc64_elf_hwcap();
+extern unsigned long sparc64_elf_hwcap;
+#define ELF_HWCAP	sparc64_elf_hwcap
 
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 75686409be24..015a761eaa32 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2927,6 +2927,13 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_FAST_FIRE_GET_PERFREG	0x120
 #define HV_FAST_FIRE_SET_PERFREG	0x121
 
+#define HV_FAST_REBOOT_DATA_SET		0x172
+
+#ifndef __ASSEMBLY__
+extern unsigned long sun4v_reboot_data_set(unsigned long ra,
+					   unsigned long len);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2940,16 +2947,23 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_GRP_CORE			0x0001
 #define HV_GRP_INTR			0x0002
 #define HV_GRP_SOFT_STATE		0x0003
+#define HV_GRP_TM			0x0080
 #define HV_GRP_PCI			0x0100
 #define HV_GRP_LDOM			0x0101
 #define HV_GRP_SVC_CHAN			0x0102
 #define HV_GRP_NCS			0x0103
 #define HV_GRP_RNG			0x0104
+#define HV_GRP_PBOOT			0x0105
+#define HV_GRP_TPM			0x0107
+#define HV_GRP_SDIO			0x0108
+#define HV_GRP_SDIO_ERR			0x0109
+#define HV_GRP_REBOOT_DATA		0x0110
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
 #define HV_GRP_N2_CPU			0x0202
 #define HV_GRP_NIU			0x0204
 #define HV_GRP_VF_CPU			0x0205
+#define HV_GRP_KT_CPU			0x0209
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/sigcontext.h b/arch/sparc/include/asm/sigcontext.h
index a1607d180354..69914d748130 100644
--- a/arch/sparc/include/asm/sigcontext.h
+++ b/arch/sparc/include/asm/sigcontext.h
@@ -45,6 +45,19 @@ typedef struct {
 	int			si_mask;
 } __siginfo32_t;
 
+#define __SIGC_MAXWIN	7
+
+typedef struct {
+	unsigned long locals[8];
+	unsigned long ins[8];
+} __siginfo_reg_window;
+
+typedef struct {
+	int			wsaved;
+	__siginfo_reg_window	reg_window[__SIGC_MAXWIN];
+	unsigned long		rwbuf_stkptrs[__SIGC_MAXWIN];
+} __siginfo_rwin_t;
+
 #ifdef CONFIG_SPARC64
 typedef struct {
 	unsigned   int si_float_regs [64];
@@ -73,6 +86,7 @@ struct sigcontext {
 		unsigned long	ss_size;
 	}			sigc_stack;
 	unsigned long		sigc_mask;
+	__siginfo_rwin_t *	sigc_rwin_save;
 };
 
 #else
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index 5f5b8bf3f50d..bcc98fc35281 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -131,6 +131,15 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	*(volatile __u32 *)&lp->lock = ~0U;
 }
 
+static void inline arch_write_unlock(arch_rwlock_t *lock)
+{
+	__asm__ __volatile__(
+"	st		%%g0, [%0]"
+	: /* no outputs */
+	: "r" (lock)
+	: "memory");
+}
+
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned int val;
@@ -175,8 +184,6 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw)
 	res; \
 })
 
-#define arch_write_unlock(rw)	do { (rw)->lock = 0; } while(0)
-
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_read_lock_flags(rw, flags)   arch_read_lock(rw)
 #define arch_write_lock_flags(rw, flags)  arch_write_lock(rw)
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 073936a8b275..968917694978 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -210,14 +210,8 @@ static int inline arch_write_trylock(arch_rwlock_t *lock)
 	return result;
 }
 
-#define arch_read_lock(p)	arch_read_lock(p)
 #define arch_read_lock_flags(p, f) arch_read_lock(p)
-#define arch_read_trylock(p)	arch_read_trylock(p)
-#define arch_read_unlock(p)	arch_read_unlock(p)
-#define arch_write_lock(p)	arch_write_lock(p)
 #define arch_write_lock_flags(p, f) arch_write_lock(p)
-#define arch_write_unlock(p)	arch_write_unlock(p)
-#define arch_write_trylock(p)	arch_write_trylock(p)
 
 #define arch_read_can_lock(rw)		(!((rw)->lock & 0x80000000UL))
 #define arch_write_can_lock(rw)	(!(rw)->lock)
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index f0d0c40c44da..55a17c6efeb8 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -42,6 +42,7 @@
 #define SUN4V_CHIP_INVALID	0x00
 #define SUN4V_CHIP_NIAGARA1	0x01
 #define SUN4V_CHIP_NIAGARA2	0x02
+#define SUN4V_CHIP_NIAGARA3	0x03
 #define SUN4V_CHIP_UNKNOWN	0xff
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 83c571d8c8a7..1a8afd1ad04f 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -133,29 +133,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sub	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TAG);
 
-#define KTSB_LOAD_QUAD(TSB, REG) \
-	ldda		[TSB] ASI_NUCLEUS_QUAD_LDD, REG;
-
-#define KTSB_STORE(ADDR, VAL) \
-	stxa		VAL, [ADDR] ASI_N;
-
-#define KTSB_LOCK_TAG(TSB, REG1, REG2)	\
-99:	lduwa	[TSB] ASI_N, REG1;	\
-	sethi	%hi(TSB_TAG_LOCK_HIGH), REG2;\
-	andcc	REG1, REG2, %g0;	\
-	bne,pn	%icc, 99b;		\
-	 nop;				\
-	casa	[TSB] ASI_N, REG1, REG2;\
-	cmp	REG1, REG2;		\
-	bne,pn	%icc, 99b;		\
-	 nop;				\
-
-#define KTSB_WRITE(TSB, TTE, TAG) \
-	add	TSB, 0x8, TSB;   \
-	stxa	TTE, [TSB] ASI_N;     \
-	sub	TSB, 0x8, TSB;   \
-	stxa	TAG, [TSB] ASI_N;
-
 	/* Do a kernel page table walk.  Leaves physical PTE pointer in
 	 * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
 	 * VADDR will not be clobbered, but REG2 will.
@@ -239,6 +216,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	(KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES	4096
 
+#define KTSB_PHYS_SHIFT		15
+
 	/* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
 	 * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
 	 * and the found TTE will be left in REG1.  REG3 and REG4 must
@@ -247,13 +226,22 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * VADDR and TAG will be preserved and not clobbered by this macro.
 	 */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-	sethi		%hi(swapper_tsb), REG1; \
+661:	sethi		%hi(swapper_tsb), REG1;			\
 	or		REG1, %lo(swapper_tsb), REG1; \
+	.section	.swapper_tsb_phys_patch, "ax"; \
+	.word		661b; \
+	.previous; \
+661:	nop; \
+	.section	.tsb_ldquad_phys_patch, "ax"; \
+	.word		661b; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	.previous; \
 	srlx		VADDR, PAGE_SHIFT, REG2; \
 	and		REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
-	KTSB_LOAD_QUAD(REG2, REG3); \
+	TSB_LOAD_QUAD(REG2, REG3); \
 	cmp		REG3, TAG; \
 	be,a,pt		%xcc, OK_LABEL; \
 	 mov		REG4, REG1;
@@ -263,12 +251,21 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * we can make use of that for the index computation.
 	 */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-	sethi		%hi(swapper_4m_tsb), REG1; \
+661:	sethi		%hi(swapper_4m_tsb), REG1;	     \
 	or		REG1, %lo(swapper_4m_tsb), REG1; \
+	.section	.swapper_4m_tsb_phys_patch, "ax"; \
+	.word		661b; \
+	.previous; \
+661:	nop; \
+	.section	.tsb_ldquad_phys_patch, "ax"; \
+	.word		661b; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	.previous; \
 	and		TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
-	KTSB_LOAD_QUAD(REG2, REG3); \
+	TSB_LOAD_QUAD(REG2, REG3); \
 	cmp		REG3, TAG; \
 	be,a,pt		%xcc, OK_LABEL; \
 	 mov		REG4, REG1;
diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h
index bee4bf4be3af..9ed6ff679ab7 100644
--- a/arch/sparc/include/asm/xor_64.h
+++ b/arch/sparc/include/asm/xor_64.h
@@ -65,6 +65,7 @@ static struct xor_block_template xor_block_niagara = {
 #define XOR_SELECT_TEMPLATE(FASTEST) \
 	((tlb_type == hypervisor && \
 	  (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \
-	   sun4v_chip_type == SUN4V_CHIP_NIAGARA2)) ? \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA3)) ? \
 	 &xor_block_niagara : \
 	 &xor_block_VIS)
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index b90b4a1d070a..cb85458f89d2 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_SPARC32)   += sun4m_irq.o sun4c_irq.o sun4d_irq.o
 
 obj-y                   += process_$(BITS).o
 obj-y                   += signal_$(BITS).o
+obj-y                   += sigutil_$(BITS).o
 obj-$(CONFIG_SPARC32)   += ioport.o
 obj-y                   += setup_$(BITS).o
 obj-y                   += idprom.o
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 138dbbc8dc84..9810fd881058 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -396,6 +396,7 @@ static int show_cpuinfo(struct seq_file *m, void *__unused)
 		   , cpu_data(0).clock_tick
 #endif
 		);
+	cpucap_info(m);
 #ifdef CONFIG_SMP
 	smp_bogo(m);
 #endif
@@ -474,11 +475,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara2";
 		break;
 
+	case SUN4V_CHIP_NIAGARA3:
+		sparc_cpu_type = "UltraSparc T3 (Niagara3)";
+		sparc_fpu_type = "UltraSparc T3 integrated FPU";
+		sparc_pmu_type = "niagara3";
+		break;
+
 	default:
 		printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
 		       prom_cpu_compatible);
 		sparc_cpu_type = "Unknown SUN4V CPU";
 		sparc_fpu_type = "Unknown SUN4V FPU";
+		sparc_pmu_type = "Unknown SUN4V PMU";
 		break;
 	}
 }
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index d91fd782743a..4197e8d62d4c 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -324,6 +324,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	switch (sun4v_chip_type) {
 	case SUN4V_CHIP_NIAGARA1:
 	case SUN4V_CHIP_NIAGARA2:
+	case SUN4V_CHIP_NIAGARA3:
 		rover_inc_table = niagara_iterate_method;
 		break;
 	default:
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index dd1342c0a3be..7429b47c3aca 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -15,12 +15,15 @@
 #include <linux/reboot.h>
 #include <linux/cpu.h>
 
+#include <asm/hypervisor.h>
 #include <asm/ldc.h>
 #include <asm/vio.h>
 #include <asm/mdesc.h>
 #include <asm/head.h>
 #include <asm/irq.h>
 
+#include "kernel.h"
+
 #define DRV_MODULE_NAME		"ds"
 #define PFX DRV_MODULE_NAME	": "
 #define DRV_MODULE_VERSION	"1.0"
@@ -828,18 +831,32 @@ void ldom_set_var(const char *var, const char *value)
 	}
 }
 
+static char full_boot_str[256] __attribute__((aligned(32)));
+static int reboot_data_supported;
+
 void ldom_reboot(const char *boot_command)
 {
 	/* Don't bother with any of this if the boot_command
 	 * is empty.
 	 */
 	if (boot_command && strlen(boot_command)) {
-		char full_boot_str[256];
+		unsigned long len;
 
 		strcpy(full_boot_str, "boot ");
 		strcpy(full_boot_str + strlen("boot "), boot_command);
+		len = strlen(full_boot_str);
 
-		ldom_set_var("reboot-command", full_boot_str);
+		if (reboot_data_supported) {
+			unsigned long ra = kimage_addr_to_ra(full_boot_str);
+			unsigned long hv_ret;
+
+			hv_ret = sun4v_reboot_data_set(ra, len);
+			if (hv_ret != HV_EOK)
+				pr_err("SUN4V: Unable to set reboot data "
+				       "hv_ret=%lu\n", hv_ret);
+		} else {
+			ldom_set_var("reboot-command", full_boot_str);
+		}
 	}
 	sun4v_mach_sir();
 }
@@ -1237,6 +1254,16 @@ static struct vio_driver ds_driver = {
 
 static int __init ds_init(void)
 {
+	unsigned long hv_ret, major, minor;
+
+	if (tlb_type == hypervisor) {
+		hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor);
+		if (hv_ret == HV_EOK) {
+			pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n",
+				major, minor);
+			reboot_data_supported = 1;
+		}
+	}
 	kthread_run(ds_thread, NULL, "kldomd");
 
 	return vio_register_driver(&ds_driver);
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index d1f1361c4167..e27f8ea8656e 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -42,6 +42,20 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
+struct popc_3insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[3];
+};
+extern struct popc_3insn_patch_entry __popc_3insn_patch,
+	__popc_3insn_patch_end;
+
+struct popc_6insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[6];
+};
+extern struct popc_6insn_patch_entry __popc_6insn_patch,
+	__popc_6insn_patch_end;
+
 extern void __init per_cpu_patch(void);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index aa594c792d19..0cbab31d3ec9 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -132,6 +132,8 @@ prom_sun4v_name:
 	.asciz	"sun4v"
 prom_niagara_prefix:
 	.asciz	"SUNW,UltraSPARC-T"
+prom_sparc_prefix:
+	.asciz	"SPARC-T"
 	.align	4
 prom_root_compatible:
 	.skip	64
@@ -382,6 +384,22 @@ sun4v_chip_type:
 90:	ldub	[%g7], %g2
 	ldub	[%g1], %g4
 	cmp	%g2, %g4
+	bne,pn	%icc, 89f
+	 add	%g7, 1, %g7
+	subcc	%g3, 1, %g3
+	bne,pt	%xcc, 90b
+	 add	%g1, 1, %g1
+	ba,pt	%xcc, 91f
+	 nop
+
+89:	sethi	%hi(prom_cpu_compatible), %g1
+	or	%g1, %lo(prom_cpu_compatible), %g1
+	sethi	%hi(prom_sparc_prefix), %g7
+	or	%g7, %lo(prom_sparc_prefix), %g7
+	mov	7, %g3
+90:	ldub	[%g7], %g2
+	ldub	[%g1], %g4
+	cmp	%g2, %g4
 	bne,pn	%icc, 4f
 	 add	%g7, 1, %g7
 	subcc	%g3, 1, %g3
@@ -390,6 +408,15 @@ sun4v_chip_type:
 
 	sethi	%hi(prom_cpu_compatible), %g1
 	or	%g1, %lo(prom_cpu_compatible), %g1
+	ldub	[%g1 + 7], %g2
+	cmp	%g2, '3'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_NIAGARA3, %g4
+	ba,pt	%xcc, 4f
+	 nop
+
+91:	sethi	%hi(prom_cpu_compatible), %g1
+	or	%g1, %lo(prom_cpu_compatible), %g1
 	ldub	[%g1 + 17], %g2
 	cmp	%g2, '1'
 	be,pt	%xcc, 5f
@@ -397,6 +424,7 @@ sun4v_chip_type:
 	cmp	%g2, '2'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA2, %g4
+
 4:
 	mov	SUN4V_CHIP_UNKNOWN, %g4
 5:	sethi	%hi(sun4v_chip_type), %g2
@@ -514,6 +542,9 @@ niagara_tlb_fixup:
 	 cmp	%g1, SUN4V_CHIP_NIAGARA2
 	be,pt	%xcc, niagara2_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_NIAGARA3
+	be,pt	%xcc, niagara2_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
@@ -528,7 +559,7 @@ niagara2_patch:
 	 nop
 	call	niagara_patch_bzero
 	 nop
-	call	niagara2_patch_pageops
+	call	niagara_patch_pageops
 	 nop
 
 	ba,a,pt	%xcc, 80f
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 7c60afb835b0..c2d055d8ba9e 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -28,16 +28,23 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_CORE,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_INTR,					},
 	{ .group = HV_GRP_SOFT_STATE,				},
+	{ .group = HV_GRP_TM,					},
 	{ .group = HV_GRP_PCI,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_LDOM,					},
 	{ .group = HV_GRP_SVC_CHAN,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_NCS,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_RNG,					},
+	{ .group = HV_GRP_PBOOT,				},
+	{ .group = HV_GRP_TPM,					},
+	{ .group = HV_GRP_SDIO,					},
+	{ .group = HV_GRP_SDIO_ERR,				},
+	{ .group = HV_GRP_REBOOT_DATA,				},
 	{ .group = HV_GRP_NIAG_PERF,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_FIRE_PERF,				},
 	{ .group = HV_GRP_N2_CPU,				},
 	{ .group = HV_GRP_NIU,					},
 	{ .group = HV_GRP_VF_CPU,				},
+	{ .group = HV_GRP_KT_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
 };
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index 8a5f35ffb15e..58d60de4d65b 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -798,3 +798,10 @@ ENTRY(sun4v_niagara2_setperf)
 	retl
 	 nop
 ENDPROC(sun4v_niagara2_setperf)
+
+ENTRY(sun4v_reboot_data_set)
+	mov	HV_FAST_REBOOT_DATA_SET, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_reboot_data_set)
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
index 100b9c204e78..42851122bbd9 100644
--- a/arch/sparc/kernel/irq.h
+++ b/arch/sparc/kernel/irq.h
@@ -88,7 +88,7 @@ BTFIXUPDEF_CALL(void, set_irq_udt, int)
 #define set_irq_udt(cpu) BTFIXUP_CALL(set_irq_udt)(cpu)
 
 /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */
-#define SUN4D_IPI_IRQ 14
+#define SUN4D_IPI_IRQ 13
 
 extern void sun4d_ipi_interrupt(void);
 
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index 6f6544cfa0ef..fd6c36b1df74 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -4,12 +4,27 @@
 #include <linux/interrupt.h>
 
 #include <asm/traps.h>
+#include <asm/head.h>
+#include <asm/io.h>
 
 /* cpu.c */
 extern const char *sparc_pmu_type;
 extern unsigned int fsr_storage;
 extern int ncpus_probed;
 
+#ifdef CONFIG_SPARC64
+/* setup_64.c */
+struct seq_file;
+extern void cpucap_info(struct seq_file *);
+
+static inline unsigned long kimage_addr_to_ra(const char *p)
+{
+	unsigned long val = (unsigned long) p;
+
+	return kern_base + (val - KERNBASE);
+}
+#endif
+
 #ifdef CONFIG_SPARC32
 /* cpu.c */
 extern void cpu_probe(void);
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 1d361477d7d6..79f310364849 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -47,16 +47,16 @@ kvmap_itlb_tsb_miss:
 kvmap_itlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
 	/* Load and check PTE.  */
 	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
 	mov		1, %g7
 	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
 	brgez,a,pn	%g5, kvmap_itlb_longpath
-	 KTSB_STORE(%g1, %g7)
+	 TSB_STORE(%g1, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
 
@@ -102,9 +102,9 @@ kvmap_itlb_longpath:
 kvmap_itlb_obp:
 	OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	ba,pt		%xcc, kvmap_itlb_load
 	 nop
@@ -112,17 +112,17 @@ kvmap_itlb_obp:
 kvmap_dtlb_obp:
 	OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
 	.align		32
 kvmap_dtlb_tsb4m_load:
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_WRITE(%g1, %g5, %g6)
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
@@ -222,16 +222,16 @@ kvmap_linear_patch:
 kvmap_dtlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
 
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
 
 	/* Load and check PTE.  */
 	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
 	mov		1, %g7
 	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
 	brgez,a,pn	%g5, kvmap_dtlb_longpath
-	 KTSB_STORE(%g1, %g7)
+	 TSB_STORE(%g1, %g7)
 
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
 
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 42f28c7420e1..acaebb63c4fd 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -508,6 +508,8 @@ const char *mdesc_node_name(struct mdesc_handle *hp, u64 node)
 }
 EXPORT_SYMBOL(mdesc_node_name);
 
+static u64 max_cpus = 64;
+
 static void __init report_platform_properties(void)
 {
 	struct mdesc_handle *hp = mdesc_grab();
@@ -543,8 +545,10 @@ static void __init report_platform_properties(void)
 	if (v)
 		printk("PLATFORM: watchdog-max-timeout [%llu ms]\n", *v);
 	v = mdesc_get_property(hp, pn, "max-cpus", NULL);
-	if (v)
-		printk("PLATFORM: max-cpus [%llu]\n", *v);
+	if (v) {
+		max_cpus = *v;
+		printk("PLATFORM: max-cpus [%llu]\n", max_cpus);
+	}
 
 #ifdef CONFIG_SMP
 	{
@@ -715,7 +719,7 @@ static void __cpuinit set_proc_ids(struct mdesc_handle *hp)
 }
 
 static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
-					 unsigned char def)
+					 unsigned long def, unsigned long max)
 {
 	u64 val;
 
@@ -726,6 +730,9 @@ static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
 	if (!val || val >= 64)
 		goto use_default;
 
+	if (val > max)
+		val = max;
+
 	*mask = ((1U << val) * 64U) - 1U;
 	return;
 
@@ -736,19 +743,28 @@ use_default:
 static void __cpuinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
 				     struct trap_per_cpu *tb)
 {
+	static int printed;
 	const u64 *val;
 
 	val = mdesc_get_property(hp, mp, "q-cpu-mondo-#bits", NULL);
-	get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7);
+	get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7, ilog2(max_cpus * 2));
 
 	val = mdesc_get_property(hp, mp, "q-dev-mondo-#bits", NULL);
-	get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7);
+	get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7, 8);
 
 	val = mdesc_get_property(hp, mp, "q-resumable-#bits", NULL);
-	get_one_mondo_bits(val, &tb->resum_qmask, 6);
+	get_one_mondo_bits(val, &tb->resum_qmask, 6, 7);
 
 	val = mdesc_get_property(hp, mp, "q-nonresumable-#bits", NULL);
-	get_one_mondo_bits(val, &tb->nonresum_qmask, 2);
+	get_one_mondo_bits(val, &tb->nonresum_qmask, 2, 2);
+	if (!printed++) {
+		pr_info("SUN4V: Mondo queue sizes "
+			"[cpu(%u) dev(%u) r(%u) nr(%u)]\n",
+			tb->cpu_mondo_qmask + 1,
+			tb->dev_mondo_qmask + 1,
+			tb->resum_qmask + 1,
+			tb->nonresum_qmask + 1);
+	}
 }
 
 static void * __cpuinit mdesc_iterate_over_cpus(void *(*func)(struct mdesc_handle *, u64, int, void *), void *arg, cpumask_t *mask)
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 948601a066ff..6418ba6e7dd4 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -352,8 +352,8 @@ int __init pcic_probe(void)
 	strcpy(pbm->prom_name, namebuf);
 
 	{
-		extern volatile int t_nmi[1];
-		extern int pcic_nmi_trap_patch[1];
+		extern volatile int t_nmi[4];
+		extern int pcic_nmi_trap_patch[4];
 
 		t_nmi[0] = pcic_nmi_trap_patch[0];
 		t_nmi[1] = pcic_nmi_trap_patch[1];
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 8ac23e660080..343b0f9e2e7b 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -80,8 +80,11 @@ static void n2_pcr_write(u64 val)
 {
 	unsigned long ret;
 
-	ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
-	if (ret != HV_EOK)
+	if (val & PCR_N2_HTRACE) {
+		ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
+		if (ret != HV_EOK)
+			write_pcr(val);
+	} else
 		write_pcr(val);
 }
 
@@ -106,6 +109,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_N2_CPU;
 			break;
 
+		case SUN4V_CHIP_NIAGARA3:
+			perf_hsvc_group = HV_GRP_KT_CPU;
+			break;
+
 		default:
 			return -ENODEV;
 		}
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 2cb0e1c001e2..6860d40253c3 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1301,7 +1301,8 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara1_pmu;
 		return true;
 	}
-	if (!strcmp(sparc_pmu_type, "niagara2")) {
+	if (!strcmp(sparc_pmu_type, "niagara2") ||
+	    !strcmp(sparc_pmu_type, "niagara3")) {
 		sparc_pmu = &niagara2_pmu;
 		return true;
 	}
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c4dd0999da86..3c5bb784214f 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -29,6 +29,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/initrd.h>
+#include <linux/module.h>
 
 #include <asm/system.h>
 #include <asm/io.h>
@@ -46,6 +47,8 @@
 #include <asm/mmu.h>
 #include <asm/ns87303.h>
 #include <asm/btext.h>
+#include <asm/elf.h>
+#include <asm/mdesc.h>
 
 #ifdef CONFIG_IP_PNP
 #include <net/ipconfig.h>
@@ -269,6 +272,40 @@ void __init sun4v_patch(void)
 	sun4v_hvapi_init();
 }
 
+static void __init popc_patch(void)
+{
+	struct popc_3insn_patch_entry *p3;
+	struct popc_6insn_patch_entry *p6;
+
+	p3 = &__popc_3insn_patch;
+	while (p3 < &__popc_3insn_patch_end) {
+		unsigned long i, addr = p3->addr;
+
+		for (i = 0; i < 3; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p3->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p3++;
+	}
+
+	p6 = &__popc_6insn_patch;
+	while (p6 < &__popc_6insn_patch_end) {
+		unsigned long i, addr = p6->addr;
+
+		for (i = 0; i < 6; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p6->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p6++;
+	}
+}
+
 #ifdef CONFIG_SMP
 void __init boot_cpu_id_too_large(int cpu)
 {
@@ -278,6 +315,160 @@ void __init boot_cpu_id_too_large(int cpu)
 }
 #endif
 
+/* On Ultra, we support all of the v8 capabilities. */
+unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
+				   HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV |
+				   HWCAP_SPARC_V9);
+EXPORT_SYMBOL(sparc64_elf_hwcap);
+
+static const char *hwcaps[] = {
+	"flush", "stbar", "swap", "muldiv", "v9",
+	"ultra3", "blkinit", "n2",
+
+	/* These strings are as they appear in the machine description
+	 * 'hwcap-list' property for cpu nodes.
+	 */
+	"mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2",
+	"ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau",
+	"ima", "cspare",
+};
+
+void cpucap_info(struct seq_file *m)
+{
+	unsigned long caps = sparc64_elf_hwcap;
+	int i, printed = 0;
+
+	seq_puts(m, "cpucaps\t\t: ");
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		unsigned long bit = 1UL << i;
+		if (caps & bit) {
+			seq_printf(m, "%s%s",
+				   printed ? "," : "", hwcaps[i]);
+			printed++;
+		}
+	}
+	seq_putc(m, '\n');
+}
+
+static void __init report_hwcaps(unsigned long caps)
+{
+	int i, printed = 0;
+
+	printk(KERN_INFO "CPU CAPS: [");
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		unsigned long bit = 1UL << i;
+		if (caps & bit) {
+			printk(KERN_CONT "%s%s",
+			       printed ? "," : "", hwcaps[i]);
+			if (++printed == 8) {
+				printk(KERN_CONT "]\n");
+				printk(KERN_INFO "CPU CAPS: [");
+				printed = 0;
+			}
+		}
+	}
+	printk(KERN_CONT "]\n");
+}
+
+static unsigned long __init mdesc_cpu_hwcap_list(void)
+{
+	struct mdesc_handle *hp;
+	unsigned long caps = 0;
+	const char *prop;
+	int len;
+	u64 pn;
+
+	hp = mdesc_grab();
+	if (!hp)
+		return 0;
+
+	pn = mdesc_node_by_name(hp, MDESC_NODE_NULL, "cpu");
+	if (pn == MDESC_NODE_NULL)
+		goto out;
+
+	prop = mdesc_get_property(hp, pn, "hwcap-list", &len);
+	if (!prop)
+		goto out;
+
+	while (len) {
+		int i, plen;
+
+		for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+			unsigned long bit = 1UL << i;
+
+			if (!strcmp(prop, hwcaps[i])) {
+				caps |= bit;
+				break;
+			}
+		}
+
+		plen = strlen(prop) + 1;
+		prop += plen;
+		len -= plen;
+	}
+
+out:
+	mdesc_release(hp);
+	return caps;
+}
+
+/* This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+static void __init init_sparc64_elf_hwcap(void)
+{
+	unsigned long cap = sparc64_elf_hwcap;
+	unsigned long mdesc_caps;
+
+	if (tlb_type == cheetah || tlb_type == cheetah_plus)
+		cap |= HWCAP_SPARC_ULTRA3;
+	else if (tlb_type == hypervisor) {
+		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			cap |= HWCAP_SPARC_BLKINIT;
+		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			cap |= HWCAP_SPARC_N2;
+	}
+
+	cap |= (AV_SPARC_MUL32 | AV_SPARC_DIV32 | AV_SPARC_V8PLUS);
+
+	mdesc_caps = mdesc_cpu_hwcap_list();
+	if (!mdesc_caps) {
+		if (tlb_type == spitfire)
+			cap |= AV_SPARC_VIS;
+		if (tlb_type == cheetah || tlb_type == cheetah_plus)
+			cap |= AV_SPARC_VIS | AV_SPARC_VIS2;
+		if (tlb_type == cheetah_plus) {
+			unsigned long impl, ver;
+
+			__asm__ __volatile__("rdpr %%ver, %0" : "=r" (ver));
+			impl = ((ver >> 32) & 0xffff);
+			if (impl == PANTHER_IMPL)
+				cap |= AV_SPARC_POPC;
+		}
+		if (tlb_type == hypervisor) {
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1)
+				cap |= AV_SPARC_ASI_BLK_INIT;
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
+					AV_SPARC_ASI_BLK_INIT |
+					AV_SPARC_POPC);
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
+					AV_SPARC_FMAF);
+		}
+	}
+	sparc64_elf_hwcap = cap | mdesc_caps;
+
+	report_hwcaps(sparc64_elf_hwcap);
+
+	if (sparc64_elf_hwcap & AV_SPARC_POPC)
+		popc_patch();
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	/* Initialize PROM console and command line. */
@@ -337,6 +528,7 @@ void __init setup_arch(char **cmdline_p)
 	init_cur_cpu_trap(current_thread_info());
 
 	paging_init();
+	init_sparc64_elf_hwcap();
 }
 
 extern int stop_a_enabled;
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 75fad425e249..5d92488fc167 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -29,6 +29,8 @@
 #include <asm/visasm.h>
 #include <asm/compat_signal.h>
 
+#include "sigutil.h"
+
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 /* This magic should be in g_upper[0] for all upper parts
@@ -44,14 +46,14 @@ typedef struct {
 struct signal_frame32 {
 	struct sparc_stackf32	ss;
 	__siginfo32_t		info;
-	/* __siginfo_fpu32_t * */ u32 fpu_save;
+	/* __siginfo_fpu_t * */ u32 fpu_save;
 	unsigned int		insns[2];
 	unsigned int		extramask[_COMPAT_NSIG_WORDS - 1];
 	unsigned int		extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */
 	/* Only valid if (info.si_regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */
 	siginfo_extra_v8plus_t	v8plus;
-	__siginfo_fpu_t		fpu_state;
-};
+	/* __siginfo_rwin_t * */u32 rwin_save;
+} __attribute__((aligned(8)));
 
 typedef struct compat_siginfo{
 	int si_signo;
@@ -110,18 +112,14 @@ struct rt_signal_frame32 {
 	compat_siginfo_t	info;
 	struct pt_regs32	regs;
 	compat_sigset_t		mask;
-	/* __siginfo_fpu32_t * */ u32 fpu_save;
+	/* __siginfo_fpu_t * */ u32 fpu_save;
 	unsigned int		insns[2];
 	stack_t32		stack;
 	unsigned int		extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */
 	/* Only valid if (regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */
 	siginfo_extra_v8plus_t	v8plus;
-	__siginfo_fpu_t		fpu_state;
-};
-
-/* Align macros */
-#define SF_ALIGNEDSZ  (((sizeof(struct signal_frame32) + 15) & (~15)))
-#define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame32) + 15) & (~15)))
+	/* __siginfo_rwin_t * */u32 rwin_save;
+} __attribute__((aligned(8)));
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 {
@@ -192,30 +190,13 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return 0;
 }
 
-static int restore_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err;
-	
-	err = __get_user(fprs, &fpu->si_fprs);
-	fprs_write(0);
-	regs->tstate &= ~TSTATE_PEF;
-	if (fprs & FPRS_DL)
-		err |= copy_from_user(fpregs, &fpu->si_float_regs[0], (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], (sizeof(unsigned int) * 32));
-	err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	current_thread_info()->fpsaved[0] |= fprs;
-	return err;
-}
-
 void do_sigreturn32(struct pt_regs *regs)
 {
 	struct signal_frame32 __user *sf;
+	compat_uptr_t fpu_save;
+	compat_uptr_t rwin_save;
 	unsigned int psr;
-	unsigned pc, npc, fpu_save;
+	unsigned pc, npc;
 	sigset_t set;
 	unsigned seta[_COMPAT_NSIG_WORDS];
 	int err, i;
@@ -273,8 +254,13 @@ void do_sigreturn32(struct pt_regs *regs)
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-	if (fpu_save)
-		err |= restore_fpu_state32(regs, &sf->fpu_state);
+	if (!err && fpu_save)
+		err |= restore_fpu_state(regs, compat_ptr(fpu_save));
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(compat_ptr(rwin_save)))
+			goto segv;
+	}
 	err |= __get_user(seta[0], &sf->info.si_mask);
 	err |= copy_from_user(seta+1, &sf->extramask,
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
@@ -300,7 +286,9 @@ segv:
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
-	unsigned int psr, pc, npc, fpu_save, u_ss_sp;
+	unsigned int psr, pc, npc, u_ss_sp;
+	compat_uptr_t fpu_save;
+	compat_uptr_t rwin_save;
 	mm_segment_t old_fs;
 	sigset_t set;
 	compat_sigset_t seta;
@@ -359,8 +347,8 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-	if (fpu_save)
-		err |= restore_fpu_state32(regs, &sf->fpu_state);
+	if (!err && fpu_save)
+		err |= restore_fpu_state(regs, compat_ptr(fpu_save));
 	err |= copy_from_user(&seta, &sf->mask, sizeof(compat_sigset_t));
 	err |= __get_user(u_ss_sp, &sf->stack.ss_sp);
 	st.ss_sp = compat_ptr(u_ss_sp);
@@ -376,6 +364,12 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	do_sigaltstack((stack_t __user *) &st, NULL, (unsigned long)sf);
 	set_fs(old_fs);
 	
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(compat_ptr(rwin_save)))
+			goto segv;
+	}
+
 	switch (_NSIG_WORDS) {
 		case 4: set.sig[3] = seta.sig[6] + (((long)seta.sig[7]) << 32);
 		case 3: set.sig[2] = seta.sig[4] + (((long)seta.sig[5]) << 32);
@@ -433,26 +427,6 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns
 	return (void __user *) sp;
 }
 
-static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err = 0;
-	
-	fprs = current_thread_info()->fpsaved[0];
-	if (fprs & FPRS_DL)
-		err |= copy_to_user(&fpu->si_float_regs[0], fpregs,
-				    (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16,
-				    (sizeof(unsigned int) * 32));
-	err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	err |= __put_user(fprs, &fpu->si_fprs);
-
-	return err;
-}
-
 /* The I-cache flush instruction only works in the primary ASI, which
  * right now is the nucleus, aka. kernel space.
  *
@@ -515,18 +489,23 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			 int signo, sigset_t *oldset)
 {
 	struct signal_frame32 __user *sf;
+	int i, err, wsaved;
+	void __user *tail;
 	int sigframe_size;
 	u32 psr;
-	int i, err;
 	unsigned int seta[_COMPAT_NSIG_WORDS];
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = SF_ALIGNEDSZ;
-	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = get_thread_wsaved();
+
+	sigframe_size = sizeof(*sf);
+	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 
 	sf = (struct signal_frame32 __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
@@ -534,8 +513,7 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill;
 
-	if (get_thread_wsaved() != 0)
-		goto sigill;
+	tail = (sf + 1);
 
 	/* 2. Save the current process state */
 	if (test_thread_flag(TIF_32BIT)) {
@@ -560,11 +538,22 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			  &sf->v8plus.asi);
 
 	if (psr & PSR_EF) {
-		err |= save_fpu_state32(regs, &sf->fpu_state);
-		err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user((u64)fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user((u64)rwp, &sf->rwin_save);
+		set_thread_wsaved(0);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 
 	switch (_NSIG_WORDS) {
 	case 4: seta[7] = (oldset->sig[3] >> 32);
@@ -580,10 +569,21 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	err |= __copy_to_user(sf->extramask, seta + 1,
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
 
-	err |= copy_in_user((u32 __user *)sf,
-			    (u32 __user *)(regs->u_regs[UREG_FP]),
-			    sizeof(struct reg_window32));
-	
+	if (!wsaved) {
+		err |= copy_in_user((u32 __user *)sf,
+				    (u32 __user *)(regs->u_regs[UREG_FP]),
+				    sizeof(struct reg_window32));
+	} else {
+		struct reg_window *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		for (i = 0; i < 8; i++)
+			err |= __put_user(rp->locals[i], &sf->ss.locals[i]);
+		for (i = 0; i < 6; i++)
+			err |= __put_user(rp->ins[i], &sf->ss.ins[i]);
+		err |= __put_user(rp->ins[6], &sf->ss.fp);
+		err |= __put_user(rp->ins[7], &sf->ss.callers_pc);
+	}
 	if (err)
 		goto sigsegv;
 
@@ -613,7 +613,6 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 		err |= __put_user(0x91d02010, &sf->insns[1]); /*t 0x10*/
 		if (err)
 			goto sigsegv;
-
 		flush_signal_insns(address);
 	}
 	return 0;
@@ -632,18 +631,23 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			    siginfo_t *info)
 {
 	struct rt_signal_frame32 __user *sf;
+	int i, err, wsaved;
+	void __user *tail;
 	int sigframe_size;
 	u32 psr;
-	int i, err;
 	compat_sigset_t seta;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = RT_ALIGNEDSZ;
-	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = get_thread_wsaved();
+
+	sigframe_size = sizeof(*sf);
+	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 
 	sf = (struct rt_signal_frame32 __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
@@ -651,8 +655,7 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill;
 
-	if (get_thread_wsaved() != 0)
-		goto sigill;
+	tail = (sf + 1);
 
 	/* 2. Save the current process state */
 	if (test_thread_flag(TIF_32BIT)) {
@@ -677,11 +680,22 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			  &sf->v8plus.asi);
 
 	if (psr & PSR_EF) {
-		err |= save_fpu_state32(regs, &sf->fpu_state);
-		err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user((u64)fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user((u64)rwp, &sf->rwin_save);
+		set_thread_wsaved(0);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 
 	/* Update the siginfo structure.  */
 	err |= copy_siginfo_to_user32(&sf->info, info);
@@ -703,9 +717,21 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	}
 	err |= __copy_to_user(&sf->mask, &seta, sizeof(compat_sigset_t));
 
-	err |= copy_in_user((u32 __user *)sf,
-			    (u32 __user *)(regs->u_regs[UREG_FP]),
-			    sizeof(struct reg_window32));
+	if (!wsaved) {
+		err |= copy_in_user((u32 __user *)sf,
+				    (u32 __user *)(regs->u_regs[UREG_FP]),
+				    sizeof(struct reg_window32));
+	} else {
+		struct reg_window *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		for (i = 0; i < 8; i++)
+			err |= __put_user(rp->locals[i], &sf->ss.locals[i]);
+		for (i = 0; i < 6; i++)
+			err |= __put_user(rp->ins[i], &sf->ss.ins[i]);
+		err |= __put_user(rp->ins[6], &sf->ss.fp);
+		err |= __put_user(rp->ins[7], &sf->ss.callers_pc);
+	}
 	if (err)
 		goto sigsegv;
 	
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 5e5c5fd03783..04ede8f04add 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -26,6 +26,8 @@
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>	/* flush_sig_insns */
 
+#include "sigutil.h"
+
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
@@ -39,8 +41,8 @@ struct signal_frame {
 	unsigned long		insns[2] __attribute__ ((aligned (8)));
 	unsigned int		extramask[_NSIG_WORDS - 1];
 	unsigned int		extra_size; /* Should be 0 */
-	__siginfo_fpu_t		fpu_state;
-};
+	__siginfo_rwin_t __user	*rwin_save;
+} __attribute__((aligned(8)));
 
 struct rt_signal_frame {
 	struct sparc_stackf	ss;
@@ -51,8 +53,8 @@ struct rt_signal_frame {
 	unsigned int		insns[2];
 	stack_t			stack;
 	unsigned int		extra_size; /* Should be 0 */
-	__siginfo_fpu_t		fpu_state;
-};
+	__siginfo_rwin_t __user	*rwin_save;
+} __attribute__((aligned(8)));
 
 /* Align macros */
 #define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
@@ -79,43 +81,13 @@ asmlinkage int sys_sigsuspend(old_sigset_t set)
 	return _sigpause_common(set);
 }
 
-static inline int
-restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	int err;
-#ifdef CONFIG_SMP
-	if (test_tsk_thread_flag(current, TIF_USEDFPU))
-		regs->psr &= ~PSR_EF;
-#else
-	if (current == last_task_used_math) {
-		last_task_used_math = NULL;
-		regs->psr &= ~PSR_EF;
-	}
-#endif
-	set_used_math();
-	clear_tsk_thread_flag(current, TIF_USEDFPU);
-
-	if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu)))
-		return -EFAULT;
-
-	err = __copy_from_user(&current->thread.float_regs[0], &fpu->si_float_regs[0],
-			       (sizeof(unsigned long) * 32));
-	err |= __get_user(current->thread.fsr, &fpu->si_fsr);
-	err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
-	if (current->thread.fpqdepth != 0)
-		err |= __copy_from_user(&current->thread.fpqueue[0],
-					&fpu->si_fpqueue[0],
-					((sizeof(unsigned long) +
-					(sizeof(unsigned long *)))*16));
-	return err;
-}
-
 asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
 	struct signal_frame __user *sf;
 	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
+	__siginfo_rwin_t __user *rwin_save;
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -150,9 +122,11 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-
 	if (fpu_save)
 		err |= restore_fpu_state(regs, fpu_save);
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (rwin_save)
+		err |= restore_rwin_state(rwin_save);
 
 	/* This is pretty much atomic, no amount locking would prevent
 	 * the races which exist anyways.
@@ -180,6 +154,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	struct rt_signal_frame __user *sf;
 	unsigned int psr, pc, npc;
 	__siginfo_fpu_t __user *fpu_save;
+	__siginfo_rwin_t __user *rwin_save;
 	mm_segment_t old_fs;
 	sigset_t set;
 	stack_t st;
@@ -207,8 +182,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-
-	if (fpu_save)
+	if (!err && fpu_save)
 		err |= restore_fpu_state(regs, fpu_save);
 	err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t));
 	
@@ -228,6 +202,12 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	do_sigaltstack((const stack_t __user *) &st, NULL, (unsigned long)sf);
 	set_fs(old_fs);
 
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(rwin_save))
+			goto segv;
+	}
+
 	sigdelsetmask(&set, ~_BLOCKABLE);
 	spin_lock_irq(&current->sighand->siglock);
 	current->blocked = set;
@@ -280,53 +260,23 @@ static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *re
 	return (void __user *) sp;
 }
 
-static inline int
-save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	int err = 0;
-#ifdef CONFIG_SMP
-	if (test_tsk_thread_flag(current, TIF_USEDFPU)) {
-		put_psr(get_psr() | PSR_EF);
-		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
-		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
-		regs->psr &= ~(PSR_EF);
-		clear_tsk_thread_flag(current, TIF_USEDFPU);
-	}
-#else
-	if (current == last_task_used_math) {
-		put_psr(get_psr() | PSR_EF);
-		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
-		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
-		last_task_used_math = NULL;
-		regs->psr &= ~(PSR_EF);
-	}
-#endif
-	err |= __copy_to_user(&fpu->si_float_regs[0],
-			      &current->thread.float_regs[0],
-			      (sizeof(unsigned long) * 32));
-	err |= __put_user(current->thread.fsr, &fpu->si_fsr);
-	err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
-	if (current->thread.fpqdepth != 0)
-		err |= __copy_to_user(&fpu->si_fpqueue[0],
-				      &current->thread.fpqueue[0],
-				      ((sizeof(unsigned long) +
-				      (sizeof(unsigned long *)))*16));
-	clear_used_math();
-	return err;
-}
-
 static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 		       int signo, sigset_t *oldset)
 {
 	struct signal_frame __user *sf;
-	int sigframe_size, err;
+	int sigframe_size, err, wsaved;
+	void __user *tail;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 
-	sigframe_size = SF_ALIGNEDSZ;
-	if (!used_math())
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = current_thread_info()->w_saved;
+
+	sigframe_size = sizeof(*sf);
+	if (used_math())
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 
 	sf = (struct signal_frame __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
@@ -334,8 +284,7 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill_and_return;
 
-	if (current_thread_info()->w_saved != 0)
-		goto sigill_and_return;
+	tail = sf + 1;
 
 	/* 2. Save the current process state */
 	err = __copy_to_user(&sf->info.si_regs, regs, sizeof(struct pt_regs));
@@ -343,17 +292,34 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	err |= __put_user(0, &sf->extra_size);
 
 	if (used_math()) {
-		err |= save_fpu_state(regs, &sf->fpu_state);
-		err |= __put_user(&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user(fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user(rwp, &sf->rwin_save);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 
 	err |= __put_user(oldset->sig[0], &sf->info.si_mask);
 	err |= __copy_to_user(sf->extramask, &oldset->sig[1],
 			      (_NSIG_WORDS - 1) * sizeof(unsigned int));
-	err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
-			      sizeof(struct reg_window32));
+	if (!wsaved) {
+		err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
+				      sizeof(struct reg_window32));
+	} else {
+		struct reg_window32 *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		err |= __copy_to_user(sf, rp, sizeof(struct reg_window32));
+	}
 	if (err)
 		goto sigsegv;
 	
@@ -399,21 +365,24 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 			  int signo, sigset_t *oldset, siginfo_t *info)
 {
 	struct rt_signal_frame __user *sf;
-	int sigframe_size;
+	int sigframe_size, wsaved;
+	void __user *tail;
 	unsigned int psr;
 	int err;
 
 	synchronize_user_stack();
-	sigframe_size = RT_ALIGNEDSZ;
-	if (!used_math())
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = current_thread_info()->w_saved;
+	sigframe_size = sizeof(*sf);
+	if (used_math())
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 	sf = (struct rt_signal_frame __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill;
-	if (current_thread_info()->w_saved != 0)
-		goto sigill;
 
+	tail = sf + 1;
 	err  = __put_user(regs->pc, &sf->regs.pc);
 	err |= __put_user(regs->npc, &sf->regs.npc);
 	err |= __put_user(regs->y, &sf->regs.y);
@@ -425,11 +394,21 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	err |= __put_user(0, &sf->extra_size);
 
 	if (psr & PSR_EF) {
-		err |= save_fpu_state(regs, &sf->fpu_state);
-		err |= __put_user(&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user(fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user(rwp, &sf->rwin_save);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 	err |= __copy_to_user(&sf->mask, &oldset->sig[0], sizeof(sigset_t));
 	
 	/* Setup sigaltstack */
@@ -437,8 +416,15 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	err |= __put_user(sas_ss_flags(regs->u_regs[UREG_FP]), &sf->stack.ss_flags);
 	err |= __put_user(current->sas_ss_size, &sf->stack.ss_size);
 	
-	err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
-			      sizeof(struct reg_window32));
+	if (!wsaved) {
+		err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
+				      sizeof(struct reg_window32));
+	} else {
+		struct reg_window32 *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		err |= __copy_to_user(sf, rp, sizeof(struct reg_window32));
+	}
 
 	err |= copy_siginfo_to_user(&sf->info, info);
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 006fe4515886..47509df3b893 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -34,6 +34,7 @@
 
 #include "entry.h"
 #include "systbls.h"
+#include "sigutil.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
@@ -236,7 +237,7 @@ struct rt_signal_frame {
 	__siginfo_fpu_t __user	*fpu_save;
 	stack_t			stack;
 	sigset_t		mask;
-	__siginfo_fpu_t		fpu_state;
+	__siginfo_rwin_t	*rwin_save;
 };
 
 static long _sigpause_common(old_sigset_t set)
@@ -266,33 +267,12 @@ asmlinkage long sys_sigsuspend(old_sigset_t set)
 	return _sigpause_common(set);
 }
 
-static inline int
-restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err;
-
-	err = __get_user(fprs, &fpu->si_fprs);
-	fprs_write(0);
-	regs->tstate &= ~TSTATE_PEF;
-	if (fprs & FPRS_DL)
-		err |= copy_from_user(fpregs, &fpu->si_float_regs[0],
-		       	       (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32],
-		       	       (sizeof(unsigned int) * 32));
-	err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	current_thread_info()->fpsaved[0] |= fprs;
-	return err;
-}
-
 void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
 	unsigned long tpc, tnpc, tstate;
 	__siginfo_fpu_t __user *fpu_save;
+	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
 	int err;
 
@@ -325,8 +305,8 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	regs->tstate |= (tstate & (TSTATE_ASI | TSTATE_ICC | TSTATE_XCC));
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-	if (fpu_save)
-		err |= restore_fpu_state(regs, &sf->fpu_state);
+	if (!err && fpu_save)
+		err |= restore_fpu_state(regs, fpu_save);
 
 	err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t));
 	err |= do_sigaltstack(&sf->stack, NULL, (unsigned long)sf);
@@ -334,6 +314,12 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	if (err)
 		goto segv;
 
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(rwin_save))
+			goto segv;
+	}
+
 	regs->tpc = tpc;
 	regs->tnpc = tnpc;
 
@@ -351,34 +337,13 @@ segv:
 }
 
 /* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
+static int invalid_frame_pointer(void __user *fp)
 {
 	if (((unsigned long) fp) & 15)
 		return 1;
 	return 0;
 }
 
-static inline int
-save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err = 0;
-	
-	fprs = current_thread_info()->fpsaved[0];
-	if (fprs & FPRS_DL)
-		err |= copy_to_user(&fpu->si_float_regs[0], fpregs,
-				    (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16,
-				    (sizeof(unsigned int) * 32));
-	err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	err |= __put_user(fprs, &fpu->si_fprs);
-
-	return err;
-}
-
 static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
@@ -414,34 +379,48 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	       int signo, sigset_t *oldset, siginfo_t *info)
 {
 	struct rt_signal_frame __user *sf;
-	int sigframe_size, err;
+	int wsaved, err, sf_size;
+	void __user *tail;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = sizeof(struct rt_signal_frame);
-	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = get_thread_wsaved();
 
+	sf_size = sizeof(struct rt_signal_frame);
+	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
+		sf_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sf_size += sizeof(__siginfo_rwin_t);
 	sf = (struct rt_signal_frame __user *)
-		get_sigframe(ka, regs, sigframe_size);
-	
-	if (invalid_frame_pointer (sf, sigframe_size))
-		goto sigill;
+		get_sigframe(ka, regs, sf_size);
 
-	if (get_thread_wsaved() != 0)
+	if (invalid_frame_pointer (sf))
 		goto sigill;
 
+	tail = (sf + 1);
+
 	/* 2. Save the current process state */
 	err = copy_to_user(&sf->regs, regs, sizeof (*regs));
 
 	if (current_thread_info()->fpsaved[0] & FPRS_FEF) {
-		err |= save_fpu_state(regs, &sf->fpu_state);
-		err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fpu_save = tail;
+		tail += sizeof(__siginfo_fpu_t);
+		err |= save_fpu_state(regs, fpu_save);
+		err |= __put_user((u64)fpu_save, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwin_save = tail;
+		tail += sizeof(__siginfo_rwin_t);
+		err |= save_rwin_state(wsaved, rwin_save);
+		err |= __put_user((u64)rwin_save, &sf->rwin_save);
+		set_thread_wsaved(0);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 	
 	/* Setup sigaltstack */
 	err |= __put_user(current->sas_ss_sp, &sf->stack.ss_sp);
@@ -450,10 +429,17 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 
 	err |= copy_to_user(&sf->mask, oldset, sizeof(sigset_t));
 
-	err |= copy_in_user((u64 __user *)sf,
-			    (u64 __user *)(regs->u_regs[UREG_FP]+STACK_BIAS),
-			    sizeof(struct reg_window));
+	if (!wsaved) {
+		err |= copy_in_user((u64 __user *)sf,
+				    (u64 __user *)(regs->u_regs[UREG_FP] +
+						   STACK_BIAS),
+				    sizeof(struct reg_window));
+	} else {
+		struct reg_window *rp;
 
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		err |= copy_to_user(sf, rp, sizeof(struct reg_window));
+	}
 	if (info)
 		err |= copy_siginfo_to_user(&sf->info, info);
 	else {
diff --git a/arch/sparc/kernel/sigutil.h b/arch/sparc/kernel/sigutil.h
new file mode 100644
index 000000000000..d223aa432bb6
--- /dev/null
+++ b/arch/sparc/kernel/sigutil.h
@@ -0,0 +1,9 @@
+#ifndef _SIGUTIL_H
+#define _SIGUTIL_H
+
+int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu);
+int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu);
+int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin);
+int restore_rwin_state(__siginfo_rwin_t __user *rp);
+
+#endif /* _SIGUTIL_H */
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
new file mode 100644
index 000000000000..35c7897b009a
--- /dev/null
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -0,0 +1,120 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+
+#include <asm/sigcontext.h>
+#include <asm/fpumacro.h>
+#include <asm/ptrace.h>
+
+#include "sigutil.h"
+
+int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	int err = 0;
+#ifdef CONFIG_SMP
+	if (test_tsk_thread_flag(current, TIF_USEDFPU)) {
+		put_psr(get_psr() | PSR_EF);
+		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
+		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
+		regs->psr &= ~(PSR_EF);
+		clear_tsk_thread_flag(current, TIF_USEDFPU);
+	}
+#else
+	if (current == last_task_used_math) {
+		put_psr(get_psr() | PSR_EF);
+		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
+		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
+		last_task_used_math = NULL;
+		regs->psr &= ~(PSR_EF);
+	}
+#endif
+	err |= __copy_to_user(&fpu->si_float_regs[0],
+			      &current->thread.float_regs[0],
+			      (sizeof(unsigned long) * 32));
+	err |= __put_user(current->thread.fsr, &fpu->si_fsr);
+	err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
+	if (current->thread.fpqdepth != 0)
+		err |= __copy_to_user(&fpu->si_fpqueue[0],
+				      &current->thread.fpqueue[0],
+				      ((sizeof(unsigned long) +
+				      (sizeof(unsigned long *)))*16));
+	clear_used_math();
+	return err;
+}
+
+int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	int err;
+#ifdef CONFIG_SMP
+	if (test_tsk_thread_flag(current, TIF_USEDFPU))
+		regs->psr &= ~PSR_EF;
+#else
+	if (current == last_task_used_math) {
+		last_task_used_math = NULL;
+		regs->psr &= ~PSR_EF;
+	}
+#endif
+	set_used_math();
+	clear_tsk_thread_flag(current, TIF_USEDFPU);
+
+	if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu)))
+		return -EFAULT;
+
+	err = __copy_from_user(&current->thread.float_regs[0], &fpu->si_float_regs[0],
+			       (sizeof(unsigned long) * 32));
+	err |= __get_user(current->thread.fsr, &fpu->si_fsr);
+	err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
+	if (current->thread.fpqdepth != 0)
+		err |= __copy_from_user(&current->thread.fpqueue[0],
+					&fpu->si_fpqueue[0],
+					((sizeof(unsigned long) +
+					(sizeof(unsigned long *)))*16));
+	return err;
+}
+
+int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin)
+{
+	int i, err = __put_user(wsaved, &rwin->wsaved);
+
+	for (i = 0; i < wsaved; i++) {
+		struct reg_window32 *rp;
+		unsigned long fp;
+
+		rp = &current_thread_info()->reg_window[i];
+		fp = current_thread_info()->rwbuf_stkptrs[i];
+		err |= copy_to_user(&rwin->reg_window[i], rp,
+				    sizeof(struct reg_window32));
+		err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]);
+	}
+	return err;
+}
+
+int restore_rwin_state(__siginfo_rwin_t __user *rp)
+{
+	struct thread_info *t = current_thread_info();
+	int i, wsaved, err;
+
+	__get_user(wsaved, &rp->wsaved);
+	if (wsaved > NSWINS)
+		return -EFAULT;
+
+	err = 0;
+	for (i = 0; i < wsaved; i++) {
+		err |= copy_from_user(&t->reg_window[i],
+				      &rp->reg_window[i],
+				      sizeof(struct reg_window32));
+		err |= __get_user(t->rwbuf_stkptrs[i],
+				  &rp->rwbuf_stkptrs[i]);
+	}
+	if (err)
+		return err;
+
+	t->w_saved = wsaved;
+	synchronize_user_stack();
+	if (t->w_saved)
+		return -EFAULT;
+	return 0;
+
+}
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
new file mode 100644
index 000000000000..6edc4e5c48d1
--- /dev/null
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -0,0 +1,93 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+#include <linux/uaccess.h>
+
+#include <asm/sigcontext.h>
+#include <asm/fpumacro.h>
+#include <asm/ptrace.h>
+
+#include "sigutil.h"
+
+int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	unsigned long *fpregs = current_thread_info()->fpregs;
+	unsigned long fprs;
+	int err = 0;
+
+	fprs = current_thread_info()->fpsaved[0];
+	if (fprs & FPRS_DL)
+		err |= copy_to_user(&fpu->si_float_regs[0], fpregs,
+				    (sizeof(unsigned int) * 32));
+	if (fprs & FPRS_DU)
+		err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16,
+				    (sizeof(unsigned int) * 32));
+	err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
+	err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr);
+	err |= __put_user(fprs, &fpu->si_fprs);
+
+	return err;
+}
+
+int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	unsigned long *fpregs = current_thread_info()->fpregs;
+	unsigned long fprs;
+	int err;
+
+	err = __get_user(fprs, &fpu->si_fprs);
+	fprs_write(0);
+	regs->tstate &= ~TSTATE_PEF;
+	if (fprs & FPRS_DL)
+		err |= copy_from_user(fpregs, &fpu->si_float_regs[0],
+		       	       (sizeof(unsigned int) * 32));
+	if (fprs & FPRS_DU)
+		err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32],
+		       	       (sizeof(unsigned int) * 32));
+	err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
+	err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr);
+	current_thread_info()->fpsaved[0] |= fprs;
+	return err;
+}
+
+int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin)
+{
+	int i, err = __put_user(wsaved, &rwin->wsaved);
+
+	for (i = 0; i < wsaved; i++) {
+		struct reg_window *rp = &current_thread_info()->reg_window[i];
+		unsigned long fp = current_thread_info()->rwbuf_stkptrs[i];
+
+		err |= copy_to_user(&rwin->reg_window[i], rp,
+				    sizeof(struct reg_window));
+		err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]);
+	}
+	return err;
+}
+
+int restore_rwin_state(__siginfo_rwin_t __user *rp)
+{
+	struct thread_info *t = current_thread_info();
+	int i, wsaved, err;
+
+	__get_user(wsaved, &rp->wsaved);
+	if (wsaved > NSWINS)
+		return -EFAULT;
+
+	err = 0;
+	for (i = 0; i < wsaved; i++) {
+		err |= copy_from_user(&t->reg_window[i],
+				      &rp->reg_window[i],
+				      sizeof(struct reg_window));
+		err |= __get_user(t->rwbuf_stkptrs[i],
+				  &rp->rwbuf_stkptrs[i]);
+	}
+	if (err)
+		return err;
+
+	set_thread_wsaved(wsaved);
+	synchronize_user_stack();
+	if (get_thread_wsaved())
+		return -EFAULT;
+	return 0;
+}
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
index 372ad59c4cba..83b47ab02d96 100644
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/bitops.h>
 
 #include <asm/system.h>
 #include <asm/cpudata.h>
@@ -38,5 +39,15 @@ EXPORT_SYMBOL(sun4v_niagara_setperf);
 EXPORT_SYMBOL(sun4v_niagara2_getperf);
 EXPORT_SYMBOL(sun4v_niagara2_setperf);
 
+/* from hweight.S */
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+
+/* from ffs_ffz.S */
+EXPORT_SYMBOL(ffs);
+EXPORT_SYMBOL(__ffs);
+
 /* Exporting a symbol from /init/main.c */
 EXPORT_SYMBOL(saved_command_line);
diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c
index 8cdbe5946b43..c59af546f522 100644
--- a/arch/sparc/kernel/sstate.c
+++ b/arch/sparc/kernel/sstate.c
@@ -14,14 +14,9 @@
 #include <asm/head.h>
 #include <asm/io.h>
 
-static int hv_supports_soft_state;
-
-static unsigned long kimage_addr_to_ra(const char *p)
-{
-	unsigned long val = (unsigned long) p;
+#include "kernel.h"
 
-	return kern_base + (val - KERNBASE);
-}
+static int hv_supports_soft_state;
 
 static void do_set_sstate(unsigned long state, const char *msg)
 {
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index b2b019ea8caa..9043106a2622 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/perf_event.h>
 #include <linux/ratelimit.h>
+#include <linux/bitops.h>
 #include <asm/fpumacro.h>
 
 enum direction {
@@ -373,16 +374,11 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 	}
 }
 
-static char popc_helper[] = {
-0, 1, 1, 2, 1, 2, 2, 3,
-1, 2, 2, 3, 2, 3, 3, 4, 
-};
-
 int handle_popc(u32 insn, struct pt_regs *regs)
 {
-	u64 value;
-	int ret, i, rd = ((insn >> 25) & 0x1f);
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+	int ret, rd = ((insn >> 25) & 0x1f);
+	u64 value;
 	                        
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
 	if (insn & 0x2000) {
@@ -392,10 +388,7 @@ int handle_popc(u32 insn, struct pt_regs *regs)
 		maybe_flush_windows(0, insn & 0x1f, rd, from_kernel);
 		value = fetch_reg(insn & 0x1f, regs);
 	}
-	for (ret = 0, i = 0; i < 16; i++) {
-		ret += popc_helper[value & 0xf];
-		value >>= 4;
-	}
+	ret = hweight64(value);
 	if (rd < 16) {
 		if (rd)
 			regs->u_regs[rd] = ret;
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index c0220759003e..0e1605697b49 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -107,7 +107,26 @@ SECTIONS
 		*(.sun4v_2insn_patch)
 		__sun4v_2insn_patch_end = .;
 	}
-
+	.swapper_tsb_phys_patch : {
+		__swapper_tsb_phys_patch = .;
+		*(.swapper_tsb_phys_patch)
+		__swapper_tsb_phys_patch_end = .;
+	}
+	.swapper_4m_tsb_phys_patch : {
+		__swapper_4m_tsb_phys_patch = .;
+		*(.swapper_4m_tsb_phys_patch)
+		__swapper_4m_tsb_phys_patch_end = .;
+	}
+	.popc_3insn_patch : {
+		__popc_3insn_patch = .;
+		*(.popc_3insn_patch)
+		__popc_3insn_patch_end = .;
+	}
+	.popc_6insn_patch : {
+		__popc_6insn_patch = .;
+		*(.popc_6insn_patch)
+		__popc_6insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 7f01b8fce8bc..a3fc4375a150 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -31,13 +31,13 @@ lib-$(CONFIG_SPARC64) += NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o
 lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o
 
 lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o
-lib-$(CONFIG_SPARC64) +=  NG2patch.o NG2page.o
+lib-$(CONFIG_SPARC64) +=  NG2patch.o
 
 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
 
 lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
-lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o
+lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
 obj-y                 += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o
diff --git a/arch/sparc/lib/NG2page.S b/arch/sparc/lib/NG2page.S
deleted file mode 100644
index 73b6b7c72cbf..000000000000
--- a/arch/sparc/lib/NG2page.S
+++ /dev/null
@@ -1,61 +0,0 @@
-/* NG2page.S: Niagara-2 optimized clear and copy page.
- *
- * Copyright (C) 2007 (davem@davemloft.net)
- */
-
-#include <asm/asi.h>
-#include <asm/page.h>
-#include <asm/visasm.h>
-
-	.text
-	.align	32
-
-	/* This is heavily simplified from the sun4u variants
-	 * because Niagara-2 does not have any D-cache aliasing issues.
-	 */
-NG2copy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	prefetch	[%o1 + 0x40], #one_read
-	VISEntryHalf
-	set		PAGE_SIZE, %g7
-	sub		%o0, %o1, %g3
-1:	stxa		%g0, [%o1 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
-	ldda		[%o1] ASI_BLK_P, %f0
-	stda		%f0, [%o1 + %g3] ASI_BLK_P
-	add		%o1, 64, %o1
-	bne,pt		%xcc, 1b
-	 prefetch	[%o1 + 0x40], #one_read
-	membar		#Sync
-	VISExitHalf
-	retl
-	 nop
-
-#define BRANCH_ALWAYS	0x10680000
-#define NOP		0x01000000
-#define NG_DO_PATCH(OLD, NEW)	\
-	sethi	%hi(NEW), %g1; \
-	or	%g1, %lo(NEW), %g1; \
-	sethi	%hi(OLD), %g2; \
-	or	%g2, %lo(OLD), %g2; \
-	sub	%g1, %g2, %g1; \
-	sethi	%hi(BRANCH_ALWAYS), %g3; \
-	sll	%g1, 11, %g1; \
-	srl	%g1, 11 + 2, %g1; \
-	or	%g3, %lo(BRANCH_ALWAYS), %g3; \
-	or	%g3, %g1, %g3; \
-	stw	%g3, [%g2]; \
-	sethi	%hi(NOP), %g3; \
-	or	%g3, %lo(NOP), %g3; \
-	stw	%g3, [%g2 + 0x4]; \
-	flush	%g2;
-
-	.globl	niagara2_patch_pageops
-	.type	niagara2_patch_pageops,#function
-niagara2_patch_pageops:
-	NG_DO_PATCH(copy_user_page, NG2copy_user_page)
-	NG_DO_PATCH(_clear_page, NGclear_page)
-	NG_DO_PATCH(clear_user_page, NGclear_user_page)
-	retl
-	 nop
-	.size	niagara2_patch_pageops,.-niagara2_patch_pageops
diff --git a/arch/sparc/lib/NGpage.S b/arch/sparc/lib/NGpage.S
index 428920de05ba..b9e790b9c6b8 100644
--- a/arch/sparc/lib/NGpage.S
+++ b/arch/sparc/lib/NGpage.S
@@ -16,55 +16,91 @@
 	 */
 
 NGcopy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	mov		8, %g1
-	mov		16, %g2
-	mov		24, %g3
+	save		%sp, -192, %sp
+	rd		%asi, %g3
+	wr		%g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
 	set		PAGE_SIZE, %g7
+	prefetch	[%i1 + 0x00], #one_read
+	prefetch	[%i1 + 0x40], #one_read
 
-1:	ldda		[%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
-	ldda		[%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
-	prefetch	[%o1 + 0x40], #one_read
-	add		%o1, 32, %o1
-	stxa		%o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	ldda		[%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
-	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	ldda		[%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
-	add		%o1, 32, %o1
-	add		%o0, 32, %o0
-	stxa		%o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
+1:	prefetch	[%i1 + 0x80], #one_read
+	prefetch	[%i1 + 0xc0], #one_read
+	ldda		[%i1 + 0x00] %asi, %o2
+	ldda		[%i1 + 0x10] %asi, %o4
+	ldda		[%i1 + 0x20] %asi, %l2
+	ldda		[%i1 + 0x30] %asi, %l4
+	stxa		%o2, [%i0 + 0x00] %asi
+	stxa		%o3, [%i0 + 0x08] %asi
+	stxa		%o4, [%i0 + 0x10] %asi
+	stxa		%o5, [%i0 + 0x18] %asi
+	stxa		%l2, [%i0 + 0x20] %asi
+	stxa		%l3, [%i0 + 0x28] %asi
+	stxa		%l4, [%i0 + 0x30] %asi
+	stxa		%l5, [%i0 + 0x38] %asi
+	ldda		[%i1 + 0x40] %asi, %o2
+	ldda		[%i1 + 0x50] %asi, %o4
+	ldda		[%i1 + 0x60] %asi, %l2
+	ldda		[%i1 + 0x70] %asi, %l4
+	stxa		%o2, [%i0 + 0x40] %asi
+	stxa		%o3, [%i0 + 0x48] %asi
+	stxa		%o4, [%i0 + 0x50] %asi
+	stxa		%o5, [%i0 + 0x58] %asi
+	stxa		%l2, [%i0 + 0x60] %asi
+	stxa		%l3, [%i0 + 0x68] %asi
+	stxa		%l4, [%i0 + 0x70] %asi
+	stxa		%l5, [%i0 + 0x78] %asi
+	add		%i1, 128, %i1
+	subcc		%g7, 128, %g7
 	bne,pt		%xcc, 1b
-	 add		%o0, 32, %o0
+	 add		%i0, 128, %i0
+	wr		%g3, 0x0, %asi
 	membar		#Sync
-	retl
-	 nop
+	ret
+	 restore
 
-	.globl		NGclear_page, NGclear_user_page
+	.align		32
 NGclear_page:		/* %o0=dest */
 NGclear_user_page:	/* %o0=dest, %o1=vaddr */
-	mov		8, %g1
-	mov		16, %g2
-	mov		24, %g3
+	rd		%asi, %g3
+	wr		%g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
 	set		PAGE_SIZE, %g7
 
-1:	stxa		%g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	add		%o0, 32, %o0
-	stxa		%g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
+1:	stxa		%g0, [%o0 + 0x00] %asi
+	stxa		%g0, [%o0 + 0x08] %asi
+	stxa		%g0, [%o0 + 0x10] %asi
+	stxa		%g0, [%o0 + 0x18] %asi
+	stxa		%g0, [%o0 + 0x20] %asi
+	stxa		%g0, [%o0 + 0x28] %asi
+	stxa		%g0, [%o0 + 0x30] %asi
+	stxa		%g0, [%o0 + 0x38] %asi
+	stxa		%g0, [%o0 + 0x40] %asi
+	stxa		%g0, [%o0 + 0x48] %asi
+	stxa		%g0, [%o0 + 0x50] %asi
+	stxa		%g0, [%o0 + 0x58] %asi
+	stxa		%g0, [%o0 + 0x60] %asi
+	stxa		%g0, [%o0 + 0x68] %asi
+	stxa		%g0, [%o0 + 0x70] %asi
+	stxa		%g0, [%o0 + 0x78] %asi
+	stxa		%g0, [%o0 + 0x80] %asi
+	stxa		%g0, [%o0 + 0x88] %asi
+	stxa		%g0, [%o0 + 0x90] %asi
+	stxa		%g0, [%o0 + 0x98] %asi
+	stxa		%g0, [%o0 + 0xa0] %asi
+	stxa		%g0, [%o0 + 0xa8] %asi
+	stxa		%g0, [%o0 + 0xb0] %asi
+	stxa		%g0, [%o0 + 0xb8] %asi
+	stxa		%g0, [%o0 + 0xc0] %asi
+	stxa		%g0, [%o0 + 0xc8] %asi
+	stxa		%g0, [%o0 + 0xd0] %asi
+	stxa		%g0, [%o0 + 0xd8] %asi
+	stxa		%g0, [%o0 + 0xe0] %asi
+	stxa		%g0, [%o0 + 0xe8] %asi
+	stxa		%g0, [%o0 + 0xf0] %asi
+	stxa		%g0, [%o0 + 0xf8] %asi
+	subcc		%g7, 256, %g7
 	bne,pt		%xcc, 1b
-	 add		%o0, 32, %o0
+	 add		%o0, 256, %o0
+	wr		%g3, 0x0, %asi
 	membar		#Sync
 	retl
 	 nop
diff --git a/arch/sparc/lib/ffs.S b/arch/sparc/lib/ffs.S
new file mode 100644
index 000000000000..b39389f69899
--- /dev/null
+++ b/arch/sparc/lib/ffs.S
@@ -0,0 +1,84 @@
+#include <linux/linkage.h>
+
+	.register	%g2,#scratch
+
+	.text
+	.align	32
+
+ENTRY(ffs)
+	brnz,pt	%o0, 1f
+	 mov	1, %o1
+	retl
+	 clr	%o0
+	nop
+	nop
+ENTRY(__ffs)
+	sllx	%o0, 32, %g1		/* 1  */
+	srlx	%o0, 32, %g2
+
+	clr	%o1			/* 2  */
+	movrz	%g1, %g2, %o0
+
+	movrz	%g1, 32, %o1		/* 3  */
+1:	clr	%o2
+
+	sllx	%o0, (64 - 16), %g1	/* 4  */
+	srlx	%o0, 16, %g2
+
+	movrz	%g1, %g2, %o0		/* 5  */
+	clr	%o3
+
+	movrz	%g1, 16, %o2		/* 6  */
+	clr	%o4
+
+	and	%o0, 0xff, %g1		/* 7  */
+	srlx	%o0, 8, %g2
+
+	movrz	%g1, %g2, %o0		/* 8  */
+	clr	%o5
+
+	movrz	%g1, 8, %o3		/* 9  */
+	add	%o2, %o1, %o2
+
+	and	%o0, 0xf, %g1		/* 10 */
+	srlx	%o0, 4, %g2
+
+	movrz	%g1, %g2, %o0		/* 11 */
+	add	%o2, %o3, %o2
+
+	movrz	%g1, 4, %o4		/* 12 */
+
+	and	%o0, 0x3, %g1		/* 13 */
+	srlx	%o0, 2, %g2
+
+	movrz	%g1, %g2, %o0		/* 14 */
+	add	%o2, %o4, %o2
+
+	movrz	%g1, 2, %o5		/* 15 */
+
+	and	%o0, 0x1, %g1		/* 16 */
+
+	add	%o2, %o5, %o2		/* 17 */
+	xor	%g1, 0x1, %g1
+
+	retl				/* 18 */
+	 add	%o2, %g1, %o0
+ENDPROC(ffs)
+ENDPROC(__ffs)
+
+	.section	.popc_6insn_patch, "ax"
+	.word		ffs
+	brz,pn	%o0, 98f
+	 neg	%o0, %g1
+	xnor	%o0, %g1, %o1
+	popc	%o1, %o0
+98:	retl
+	 nop
+	.word		__ffs
+	neg	%o0, %g1
+	xnor	%o0, %g1, %o1
+	popc	%o1, %o0
+	retl
+	 sub	%o0, 1, %o0
+	nop
+	.previous
diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
new file mode 100644
index 000000000000..95414e0a6808
--- /dev/null
+++ b/arch/sparc/lib/hweight.S
@@ -0,0 +1,51 @@
+#include <linux/linkage.h>
+
+	.text
+	.align	32
+ENTRY(__arch_hweight8)
+	ba,pt	%xcc, __sw_hweight8
+	 nop
+	nop
+ENDPROC(__arch_hweight8)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight8
+	sllx		%o0, 64-8, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight16)
+	ba,pt	%xcc, __sw_hweight16
+	 nop
+	nop
+ENDPROC(__arch_hweight16)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight16
+	sllx		%o0, 64-16, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight32)
+	ba,pt	%xcc, __sw_hweight32
+	 nop
+	nop
+ENDPROC(__arch_hweight32)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight32
+	sllx		%o0, 64-32, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight64)
+	ba,pt	%xcc, __sw_hweight64
+	 nop
+	nop
+ENDPROC(__arch_hweight64)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight64
+	retl
+	 popc		%o0, %o0
+	nop
+	.previous
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3fd8e18bed80..8e073d802139 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -511,6 +511,11 @@ static void __init read_obp_translations(void)
 		for (i = 0; i < prom_trans_ents; i++)
 			prom_trans[i].data &= ~0x0003fe0000000000UL;
 	}
+
+	/* Force execute bit on.  */
+	for (i = 0; i < prom_trans_ents; i++)
+		prom_trans[i].data |= (tlb_type == hypervisor ?
+				       _PAGE_EXEC_4V : _PAGE_EXEC_4U);
 }
 
 static void __init hypervisor_tlb_lock(unsigned long vaddr,
@@ -1597,6 +1602,44 @@ static void __init tsb_phys_patch(void)
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
+static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
+{
+	pa >>= KTSB_PHYS_SHIFT;
+
+	while (start < end) {
+		unsigned int *ia = (unsigned int *)(unsigned long)*start;
+
+		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		__asm__ __volatile__("flush	%0" : : "r" (ia));
+
+		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
+
+		start++;
+	}
+}
+
+static void ktsb_phys_patch(void)
+{
+	extern unsigned int __swapper_tsb_phys_patch;
+	extern unsigned int __swapper_tsb_phys_patch_end;
+	unsigned long ktsb_pa;
+
+	ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE);
+	patch_one_ktsb_phys(&__swapper_tsb_phys_patch,
+			    &__swapper_tsb_phys_patch_end, ktsb_pa);
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	{
+	extern unsigned int __swapper_4m_tsb_phys_patch;
+	extern unsigned int __swapper_4m_tsb_phys_patch_end;
+	ktsb_pa = (kern_base +
+		   ((unsigned long)&swapper_4m_tsb[0] - KERNBASE));
+	patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch,
+			    &__swapper_4m_tsb_phys_patch_end, ktsb_pa);
+	}
+#endif
+}
+
 static void __init sun4v_ktsb_init(void)
 {
 	unsigned long ktsb_pa;
@@ -1716,8 +1759,10 @@ void __init paging_init(void)
 		sun4u_pgprot_init();
 
 	if (tlb_type == cheetah_plus ||
-	    tlb_type == hypervisor)
+	    tlb_type == hypervisor) {
 		tsb_phys_patch();
+		ktsb_phys_patch();
+	}
 
 	if (tlb_type == hypervisor) {
 		sun4v_patch_tlb_handlers();
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 64a619d47d34..7ff4669580cf 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -39,7 +39,7 @@ typedef struct xpaddr {
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 
 extern unsigned long *machine_to_phys_mapping;
-extern unsigned int   machine_to_phys_order;
+extern unsigned long  machine_to_phys_nr;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
@@ -87,7 +87,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+	if (unlikely(mfn >= machine_to_phys_nr)) {
 		pfn = ~0;
 		goto try_override;
 	}
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 7c3a95e54ec5..d3d9d50d93a5 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -531,7 +531,9 @@ static void build_inv_all(struct iommu_cmd *cmd)
  * Writes the command to the IOMMUs command buffer and informs the
  * hardware about the new command.
  */
-static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+				    struct iommu_cmd *cmd,
+				    bool sync)
 {
 	u32 left, tail, head, next_tail;
 	unsigned long flags;
@@ -565,13 +567,18 @@ again:
 	copy_cmd_to_buffer(iommu, cmd, tail);
 
 	/* We need to sync now to make sure all commands are processed */
-	iommu->need_sync = true;
+	iommu->need_sync = sync;
 
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	return 0;
 }
 
+static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
+{
+	return iommu_queue_command_sync(iommu, cmd, true);
+}
+
 /*
  * This function queues a completion wait command into the command
  * buffer of an IOMMU
@@ -587,7 +594,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
 	build_completion_wait(&cmd, (u64)&sem);
 
-	ret = iommu_queue_command(iommu, &cmd);
+	ret = iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		return ret;
 
@@ -773,14 +780,9 @@ static void domain_flush_complete(struct protection_domain *domain)
 static void domain_flush_devices(struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data;
-	unsigned long flags;
-
-	spin_lock_irqsave(&domain->lock, flags);
 
 	list_for_each_entry(dev_data, &domain->dev_list, list)
 		device_flush_dte(dev_data->dev);
-
-	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
 /****************************************************************************
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index adc66c3a1fef..34b18594e724 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -207,7 +207,6 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri
 	    ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_INIT;
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
-	mdelay(10);
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index da0d779ecd9e..ed6086eedf1d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -465,11 +465,11 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 		u64 epb;
 
 		rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-		if ((epb & 0xF) == 0) {
-			printk_once(KERN_WARNING, "x86: updated energy_perf_bias"
-				" to 'normal' from 'performance'\n"
-				"You can view and update epb via utility,"
-				" such as x86_energy_perf_policy(8)\n");
+		if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) {
+			printk_once(KERN_WARNING "ENERGY_PERF_BIAS:"
+				" Set to 'normal', was 'performance'\n"
+				"ENERGY_PERF_BIAS: View and update with"
+				" x86_energy_perf_policy(8)\n");
 			epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
 			wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
 		}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 929739a653d1..3d17bc7f06e6 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -248,6 +248,25 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 	unsigned long flags;
 	int cpu;
 
+#ifdef CONFIG_SMP
+	/*
+	 * If this cpu is not yet active, we are in the cpu online path. There
+	 * can be no stop_machine() in parallel, as stop machine ensures this
+	 * by using get_online_cpus(). We can skip taking the stop_cpus_mutex,
+	 * as we don't need it and also we can't afford to block while waiting
+	 * for the mutex.
+	 *
+	 * If this cpu is active, we need to prevent stop_machine() happening
+	 * in parallel by taking the stop cpus mutex.
+	 *
+	 * Also, this is called in the context of cpu online path or in the
+	 * context where cpu hotplug is prevented. So checking the active status
+	 * of the raw_smp_processor_id() is safe.
+	 */
+	if (cpu_active(raw_smp_processor_id()))
+		mutex_lock(&stop_cpus_mutex);
+#endif
+
 	preempt_disable();
 
 	data.smp_reg = reg;
@@ -330,6 +349,10 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 
 	local_irq_restore(flags);
 	preempt_enable();
+#ifdef CONFIG_SMP
+	if (cpu_active(raw_smp_processor_id()))
+		mutex_unlock(&stop_cpus_mutex);
+#endif
 }
 
 /**
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3a0338b4b179..bf6d692c4d0f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1856,6 +1856,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	perf_callchain_store(entry, regs->ip);
 
+	if (!current->mm)
+		return;
+
 	if (perf_callchain_user32(regs, entry))
 		return;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 41178c826c48..dd208a829b2b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1495,6 +1495,7 @@ static __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
+	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 30326443ab81..87488b93a65c 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -63,9 +63,8 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #ifdef CONFIG_X86_32
 	/* for fixmap */
 	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-
-	good_end = max_pfn_mapped << PAGE_SHIFT;
 #endif
+	good_end = max_pfn_mapped << PAGE_SHIFT;
 
 	base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
 	if (base == MEMBLOCK_ERROR)
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 68c3c1395202..50b3f14c59a1 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -43,6 +43,17 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ALiveSATA2-GLAN"),
                 },
         },
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=30552 */
+	/* 2006 AMD HT/VIA system with two host bridges */
+	{
+		.callback = set_use_crs,
+		.ident = "ASUS M2V-MX SE",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "M2V-MX SE"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
+		},
+	},
 	{}
 };
 
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 0060fd59ea00..02e39345dc6d 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -157,13 +157,13 @@ restart:
 	if (inbuf && inlen) {
 		/* write data to EC */
 		for (i = 0; i < inlen; i++) {
+			pr_devel("olpc-ec:  sending cmd arg 0x%x\n", inbuf[i]);
+			outb(inbuf[i], 0x68);
 			if (wait_on_ibf(0x6c, 0)) {
 				printk(KERN_ERR "olpc-ec:  timeout waiting for"
 						" EC accept data!\n");
 				goto err;
 			}
-			pr_devel("olpc-ec:  sending cmd arg 0x%x\n", inbuf[i]);
-			outb(inbuf[i], 0x68);
 		}
 	}
 	if (outbuf && outlen) {
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/vdso/vdso32/sysenter.S
index e2800affa754..e354bceee0e0 100644
--- a/arch/x86/vdso/vdso32/sysenter.S
+++ b/arch/x86/vdso/vdso32/sysenter.S
@@ -43,7 +43,7 @@ __kernel_vsyscall:
 	.space 7,0x90
 
 	/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
-	jmp .Lenter_kernel
+	int $0x80
 	/* 16: System call normal return point is here! */
 VDSO32_SYSENTER_RETURN:	/* Symbol used by sysenter.c via vdso32-syms.h */
 	pop %ebp
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 17c565de3d64..a6575b949b11 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -18,5 +18,5 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5525163a0398..67d69f1e2b73 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -77,8 +77,8 @@ EXPORT_SYMBOL_GPL(xen_domain_type);
 
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
-unsigned int   machine_to_phys_order;
-EXPORT_SYMBOL(machine_to_phys_order);
+unsigned long  machine_to_phys_nr;
+EXPORT_SYMBOL(machine_to_phys_nr);
 
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -1248,6 +1248,14 @@ asmlinkage void __init xen_start_kernel(void)
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 	} else {
+		const struct dom0_vga_console_info *info =
+			(void *)((char *)xen_start_info +
+				 xen_start_info->console.dom0.info_off);
+
+		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;
+
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0ccccb67a993..5f76c0acb2c7 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1626,15 +1626,19 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 void __init xen_setup_machphys_mapping(void)
 {
 	struct xen_machphys_mapping mapping;
-	unsigned long machine_to_phys_nr_ents;
 
 	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
 		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
-		machine_to_phys_nr_ents = mapping.max_mfn + 1;
+		machine_to_phys_nr = mapping.max_mfn + 1;
 	} else {
-		machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
 	}
-	machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+#ifdef CONFIG_X86_32
+	if ((machine_to_phys_mapping + machine_to_phys_nr)
+	    < machine_to_phys_mapping)
+		machine_to_phys_nr = (unsigned long *)NULL
+				     - machine_to_phys_mapping;
+#endif
 }
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 60aeeb56948f..acea42ee4eed 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -185,6 +185,19 @@ static unsigned long __init xen_set_identity(const struct e820entry *list,
 					PFN_UP(start_pci), PFN_DOWN(last));
 	return identity;
 }
+
+static unsigned long __init xen_get_max_pages(void)
+{
+	unsigned long max_pages = MAX_DOMAIN_PAGES;
+	domid_t domid = DOMID_SELF;
+	int ret;
+
+	ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+	if (ret > 0)
+		max_pages = ret;
+	return min(max_pages, MAX_DOMAIN_PAGES);
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -293,6 +306,14 @@ char * __init xen_memory_setup(void)
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
+	extra_limit = xen_get_max_pages();
+	if (max_pfn + extra_pages > extra_limit) {
+		if (extra_limit > max_pfn)
+			extra_pages = extra_limit - max_pfn;
+		else
+			extra_pages = 0;
+	}
+
 	extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
 
 	/*
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b4533a86d7e4..d4fc6d454f8d 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -32,6 +32,7 @@
 #include <xen/page.h>
 #include <xen/events.h>
 
+#include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "mmu.h"
 
@@ -207,6 +208,15 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	unsigned cpu;
 	unsigned int i;
 
+	if (skip_ioapic_setup) {
+		char *m = (max_cpus == 0) ?
+			"The nosmp parameter is incompatible with Xen; " \
+			"use Xen dom0_max_vcpus=1 parameter" :
+			"The noapic parameter is incompatible with Xen";
+
+		xen_raw_printk(m);
+		panic(m);
+	}
 	xen_init_lock_cpu(0);
 
 	smp_store_cpu_info(0);
@@ -521,8 +531,6 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	native_smp_prepare_cpus(max_cpus);
 	WARN_ON(xen_smp_intr_init(0));
 
-	if (!xen_have_vector_callback)
-		return;
 	xen_init_lock_cpu(0);
 	xen_init_spinlocks();
 }
@@ -546,6 +554,8 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 
 void __init xen_hvm_smp_init(void)
 {
+	if (!xen_have_vector_callback)
+		return;
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
 	smp_ops.cpu_up = xen_hvm_cpu_up;
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
new file mode 100644
index 000000000000..1cd7f4d11e29
--- /dev/null
+++ b/arch/x86/xen/vga.c
@@ -0,0 +1,67 @@
+#include <linux/screen_info.h>
+#include <linux/init.h>
+
+#include <asm/bootparam.h>
+#include <asm/setup.h>
+
+#include <xen/interface/xen.h>
+
+#include "xen-ops.h"
+
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+{
+	struct screen_info *screen_info = &boot_params.screen_info;
+
+	/* This is drawn from a dump from vgacon:startup in
+	 * standard Linux. */
+	screen_info->orig_video_mode = 3;
+	screen_info->orig_video_isVGA = 1;
+	screen_info->orig_video_lines = 25;
+	screen_info->orig_video_cols = 80;
+	screen_info->orig_video_ega_bx = 3;
+	screen_info->orig_video_points = 16;
+	screen_info->orig_y = screen_info->orig_video_lines - 1;
+
+	switch (info->video_type) {
+	case XEN_VGATYPE_TEXT_MODE_3:
+		if (size < offsetof(struct dom0_vga_console_info, u.text_mode_3)
+		    + sizeof(info->u.text_mode_3))
+			break;
+		screen_info->orig_video_lines = info->u.text_mode_3.rows;
+		screen_info->orig_video_cols = info->u.text_mode_3.columns;
+		screen_info->orig_x = info->u.text_mode_3.cursor_x;
+		screen_info->orig_y = info->u.text_mode_3.cursor_y;
+		screen_info->orig_video_points =
+			info->u.text_mode_3.font_height;
+		break;
+
+	case XEN_VGATYPE_VESA_LFB:
+		if (size < offsetof(struct dom0_vga_console_info,
+				    u.vesa_lfb.gbl_caps))
+			break;
+		screen_info->orig_video_isVGA = VIDEO_TYPE_VLFB;
+		screen_info->lfb_width = info->u.vesa_lfb.width;
+		screen_info->lfb_height = info->u.vesa_lfb.height;
+		screen_info->lfb_depth = info->u.vesa_lfb.bits_per_pixel;
+		screen_info->lfb_base = info->u.vesa_lfb.lfb_base;
+		screen_info->lfb_size = info->u.vesa_lfb.lfb_size;
+		screen_info->lfb_linelength = info->u.vesa_lfb.bytes_per_line;
+		screen_info->red_size = info->u.vesa_lfb.red_size;
+		screen_info->red_pos = info->u.vesa_lfb.red_pos;
+		screen_info->green_size = info->u.vesa_lfb.green_size;
+		screen_info->green_pos = info->u.vesa_lfb.green_pos;
+		screen_info->blue_size = info->u.vesa_lfb.blue_size;
+		screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
+		screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
+		screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.gbl_caps)
+		    + sizeof(info->u.vesa_lfb.gbl_caps))
+			screen_info->capabilities = info->u.vesa_lfb.gbl_caps;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.mode_attrs)
+		    + sizeof(info->u.vesa_lfb.mode_attrs))
+			screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs;
+		break;
+	}
+}
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 22a2093b5862..b040b0e518ca 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -113,11 +113,13 @@ xen_iret_start_crit:
 
 	/*
 	 * If there's something pending, mask events again so we can
-	 * jump back into xen_hypervisor_callback
+	 * jump back into xen_hypervisor_callback. Otherwise do not
+	 * touch XEN_vcpu_info_mask.
 	 */
-	sete XEN_vcpu_info_mask(%eax)
+	jne 1f
+	movb $1, XEN_vcpu_info_mask(%eax)
 
-	popl %eax
+1:	popl %eax
 
 	/*
 	 * From this point on the registers are restored and the stack
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 97dfdc8757b3..b095739ccd4c 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -88,6 +88,17 @@ static inline void xen_uninit_lock_cpu(int cpu)
 }
 #endif
 
+struct dom0_vga_console_info;
+
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#else
+static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
+				       size_t size)
+{
+}
+#endif
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\