Merge commit 'v3.1-rc9' into perf/core

Merge reason: pick up latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

32 files changed, 208 insertions, 77 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3269576dbfa8..3146ed3f6eca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1283,6 +1283,20 @@ config ARM_ERRATA_364296
 	  processor into full low interrupt latency mode. ARM11MPCore
 	  is not affected.
 
+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
 
 source "arch/arm/common/Kconfig"
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/unistd.h b/arch/arm/include/asm/unistd.h
index 2c04ed5efeb5..c60a2944f95b 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -478,8 +478,8 @@
 /*
  * Unimplemented (or alternatively implemented) syscalls
  */
-#define __IGNORE_fadvise64_64		1
-#define __IGNORE_migrate_pages		1
+#define __IGNORE_fadvise64_64
+#define __IGNORE_migrate_pages
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 79ed5e7f204a..7fcddb75c877 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
@@ -37,6 +38,15 @@ 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/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index bf977f8514f6..4e66f62b8d41 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -23,8 +23,10 @@
 
 #if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
 #define ARM_EXIT_KEEP(x)	x
+#define ARM_EXIT_DISCARD(x)
 #else
 #define ARM_EXIT_KEEP(x)
+#define ARM_EXIT_DISCARD(x)	x
 #endif
 
 OUTPUT_ARCH(arm)
@@ -39,6 +41,11 @@ jiffies = jiffies_64 + 4;
 SECTIONS
 {
 	/*
+	 * XXX: The linker does not define how output sections are
+	 * assigned to input sections when there are multiple statements
+	 * matching the same input section name.  There is no documented
+	 * order of matching.
+	 *
 	 * unwind exit sections must be discarded before the rest of the
 	 * unwind sections get included.
 	 */
@@ -47,6 +54,9 @@ SECTIONS
 		*(.ARM.extab.exit.text)
 		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))
 		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))
+		ARM_EXIT_DISCARD(EXIT_TEXT)
+		ARM_EXIT_DISCARD(EXIT_DATA)
+		EXIT_CALL
 #ifndef CONFIG_HOTPLUG
 		*(.ARM.exidx.devexit.text)
 		*(.ARM.extab.devexit.text)
@@ -58,6 +68,8 @@ SECTIONS
 #ifndef CONFIG_SMP_ON_UP
 		*(.alt.smp.init)
 #endif
+		*(.discard)
+		*(.discard.*)
 	}
 
 #ifdef CONFIG_XIP_KERNEL
@@ -279,9 +291,6 @@ SECTIONS
 
 	STABS_DEBUG
 	.comment 0 : { *(.comment) }
-
-	/* Default discards */
-	DISCARDS
 }
 
 /*
diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c
index 79d6cd0c8e7b..86964d2e9e1b 100644
--- a/arch/arm/mach-exynos4/clock.c
+++ b/arch/arm/mach-exynos4/clock.c
@@ -899,8 +899,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 28, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "exynos4-fimc.0",
+			.name		= "sclk_cam0",
 			.enable		= exynos4_clksrc_mask_cam_ctrl,
 			.ctrlbit	= (1 << 16),
 		},
@@ -909,8 +908,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 16, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "exynos4-fimc.1",
+			.name		= "sclk_cam1",
 			.enable		= exynos4_clksrc_mask_cam_ctrl,
 			.ctrlbit	= (1 << 20),
 		},
diff --git a/arch/arm/mach-s3c2443/clock.c b/arch/arm/mach-s3c2443/clock.c
index a1a7176675b9..38058af48972 100644
--- a/arch/arm/mach-s3c2443/clock.c
+++ b/arch/arm/mach-s3c2443/clock.c
@@ -128,7 +128,7 @@ static int s3c2443_armclk_setrate(struct clk *clk, unsigned long rate)
 		unsigned long clkcon0;
 
 		clkcon0 = __raw_readl(S3C2443_CLKDIV0);
-		clkcon0 &= S3C2443_CLKDIV0_ARMDIV_MASK;
+		clkcon0 &= ~S3C2443_CLKDIV0_ARMDIV_MASK;
 		clkcon0 |= val << S3C2443_CLKDIV0_ARMDIV_SHIFT;
 		__raw_writel(clkcon0, S3C2443_CLKDIV0);
 	}
diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c
index 52a8e607bcc2..f5f8fa89679c 100644
--- a/arch/arm/mach-s5pv210/clock.c
+++ b/arch/arm/mach-s5pv210/clock.c
@@ -815,8 +815,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLK_DIV3, .shift = 20, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "s5pv210-fimc.0",
+			.name		= "sclk_cam0",
 			.enable		= s5pv210_clk_mask0_ctrl,
 			.ctrlbit	= (1 << 3),
 		},
@@ -825,8 +824,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 12, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "s5pv210-fimc.1",
+			.name		= "sclk_cam1",
 			.enable		= s5pv210_clk_mask0_ctrl,
 			.ctrlbit	= (1 << 4),
 		},
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b24bfa3b828..07c4bc8ea0a4 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 0a0a1e7c20d2..c3ff82f92d9c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -324,6 +324,8 @@ __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/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c
index f71078ef6bb5..f88216d23991 100644
--- a/arch/arm/plat-s5p/irq-gpioint.c
+++ b/arch/arm/plat-s5p/irq-gpioint.c
@@ -114,17 +114,18 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip)
 {
 	static int used_gpioint_groups = 0;
 	int group = chip->group;
-	struct s5p_gpioint_bank *bank = NULL;
+	struct s5p_gpioint_bank *b, *bank = NULL;
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 
 	if (used_gpioint_groups >= S5P_GPIOINT_GROUP_COUNT)
 		return -ENOMEM;
 
-	list_for_each_entry(bank, &banks, list) {
-		if (group >= bank->start &&
-		    group < bank->start + bank->nr_groups)
+	list_for_each_entry(b, &banks, list) {
+		if (group >= b->start && group < b->start + b->nr_groups) {
+			bank = b;
 			break;
+		}
 	}
 	if (!bank)
 		return -EINVAL;
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 5cc83851ad06..31a7d3a7ce25 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -561,6 +561,20 @@ static struct pci_ops u4_pcie_pci_ops =
 	.write = u4_pcie_write_config,
 };
 
+static void __devinit pmac_pci_fixup_u4_of_node(struct pci_dev *dev)
+{
+	/* Apple's device-tree "hides" the root complex virtual P2P bridge
+	 * on U4. However, Linux sees it, causing the PCI <-> OF matching
+	 * code to fail to properly match devices below it. This works around
+	 * it by setting the node of the bridge to point to the PHB node,
+	 * which is not entirely correct but fixes the matching code and
+	 * doesn't break anything else. It's also the simplest possible fix.
+	 */
+	if (dev->dev.of_node == NULL)
+		dev->dev.of_node = pcibios_get_phb_of_node(dev->bus);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_APPLE, 0x5b, pmac_pci_fixup_u4_of_node);
+
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC32
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 64b61bf72e93..547f1a6a35d4 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -188,7 +188,8 @@ extern char elf_platform[];
 #define SET_PERSONALITY(ex)					\
 do {								\
 	if (personality(current->personality) != PER_LINUX32)	\
-		set_personality(PER_LINUX);			\
+		set_personality(PER_LINUX |			\
+			(current->personality & ~PER_MASK));	\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32)		\
 		set_thread_flag(TIF_31BIT);			\
 	else							\
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 519eb5f187ef..c0cb794bb365 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -658,12 +658,14 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
  * struct gmap_struct - guest address space
  * @mm: pointer to the parent mm_struct
  * @table: pointer to the page directory
+ * @asce: address space control element for gmap page table
  * @crst_list: list of all crst tables used in the guest address space
  */
 struct gmap {
 	struct list_head list;
 	struct mm_struct *mm;
 	unsigned long *table;
+	unsigned long asce;
 	struct list_head crst_list;
 };
 
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 532fd4322156..2b45591e1582 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <asm/vdso.h>
 #include <asm/sigp.h>
+#include <asm/pgtable.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
@@ -126,6 +127,7 @@ int main(void)
 	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
 	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
 	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
+	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
 	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
@@ -151,6 +153,7 @@ int main(void)
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
+	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 #endif /* CONFIG_32BIT */
 	return 0;
 }
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 5f729d627cef..713da0760538 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -1076,6 +1076,11 @@ sie_loop:
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
 	jnz	sie_exit
+	lg	%r14,__LC_GMAP			# get gmap pointer
+	ltgr	%r14,%r14
+	jz	sie_gmap
+	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
+sie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
 	SPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
@@ -1083,6 +1088,7 @@ sie_done:
 	SPP	__LC_CMF_HPP			# set host id
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 sie_exit:
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f17296e4fc89..dc2b580e27bc 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -123,6 +123,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 	switch (ext) {
 	case KVM_CAP_S390_PSW:
+	case KVM_CAP_S390_GMAP:
 		r = 1;
 		break;
 	default:
@@ -263,10 +264,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	restore_access_regs(vcpu->arch.guest_acrs);
+	gmap_enable(vcpu->arch.gmap);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->arch.guest_acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
@@ -461,7 +464,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
-	gmap_enable(vcpu->arch.gmap);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
@@ -470,7 +472,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
-	gmap_disable(vcpu->arch.gmap);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4d1f2bce87b3..5d56c2b95b14 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -160,6 +160,8 @@ struct gmap *gmap_alloc(struct mm_struct *mm)
 	table = (unsigned long *) page_to_phys(page);
 	crst_table_init(table, _REGION1_ENTRY_EMPTY);
 	gmap->table = table;
+	gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
+		     _ASCE_USER_BITS | __pa(table);
 	list_add(&gmap->list, &mm->context.gmap_list);
 	return gmap;
 
@@ -240,10 +242,6 @@ EXPORT_SYMBOL_GPL(gmap_free);
  */
 void gmap_enable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
-				 _ASCE_USER_BITS | __pa(gmap->table);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = (unsigned long) gmap;
 }
 EXPORT_SYMBOL_GPL(gmap_enable);
@@ -254,10 +252,6 @@ EXPORT_SYMBOL_GPL(gmap_enable);
  */
 void gmap_disable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce =
-		gmap->mm->context.asce_bits | __pa(gmap->mm->pgd);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = 0UL;
 }
 EXPORT_SYMBOL_GPL(gmap_disable);
@@ -309,15 +303,15 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 		/* Walk the guest addr space page table */
 		table = gmap->table + (((to + off) >> 53) & 0x7ff);
 		if (*table & _REGION_ENTRY_INV)
-			return 0;
+			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 42) & 0x7ff);
 		if (*table & _REGION_ENTRY_INV)
-			return 0;
+			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 31) & 0x7ff);
 		if (*table & _REGION_ENTRY_INV)
-			return 0;
+			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 20) & 0x7ff);
 
@@ -325,6 +319,7 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 		flush |= gmap_unlink_segment(gmap, table);
 		*table = _SEGMENT_ENTRY_INV;
 	}
+out:
 	up_read(&gmap->mm->mmap_sem);
 	if (flush)
 		gmap_flush_tlb(gmap);
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 55a17c6efeb8..d06a26601753 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -43,6 +43,8 @@
 #define SUN4V_CHIP_NIAGARA1	0x01
 #define SUN4V_CHIP_NIAGARA2	0x02
 #define SUN4V_CHIP_NIAGARA3	0x03
+#define SUN4V_CHIP_NIAGARA4	0x04
+#define SUN4V_CHIP_NIAGARA5	0x05
 #define SUN4V_CHIP_UNKNOWN	0xff
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h
index 9ed6ff679ab7..ee8edc68423e 100644
--- a/arch/sparc/include/asm/xor_64.h
+++ b/arch/sparc/include/asm/xor_64.h
@@ -66,6 +66,8 @@ static struct xor_block_template xor_block_niagara = {
 	((tlb_type == hypervisor && \
 	  (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \
 	   sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \
-	   sun4v_chip_type == SUN4V_CHIP_NIAGARA3)) ? \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA5)) ? \
 	 &xor_block_niagara : \
 	 &xor_block_VIS)
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 9810fd881058..ba9b1cec4e6b 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -481,6 +481,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara3";
 		break;
 
+	case SUN4V_CHIP_NIAGARA4:
+		sparc_cpu_type = "UltraSparc T4 (Niagara4)";
+		sparc_fpu_type = "UltraSparc T4 integrated FPU";
+		sparc_pmu_type = "niagara4";
+		break;
+
+	case SUN4V_CHIP_NIAGARA5:
+		sparc_cpu_type = "UltraSparc T5 (Niagara5)";
+		sparc_fpu_type = "UltraSparc T5 integrated FPU";
+		sparc_pmu_type = "niagara5";
+		break;
+
 	default:
 		printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
 		       prom_cpu_compatible);
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index 4197e8d62d4c..9323eafccb93 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -325,6 +325,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA1:
 	case SUN4V_CHIP_NIAGARA2:
 	case SUN4V_CHIP_NIAGARA3:
+	case SUN4V_CHIP_NIAGARA4:
+	case SUN4V_CHIP_NIAGARA5:
 		rover_inc_table = niagara_iterate_method;
 		break;
 	default:
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 0eac1b2fc53d..0d810c2f1d00 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -133,7 +133,7 @@ prom_sun4v_name:
 prom_niagara_prefix:
 	.asciz	"SUNW,UltraSPARC-T"
 prom_sparc_prefix:
-	.asciz	"SPARC-T"
+	.asciz	"SPARC-"
 	.align	4
 prom_root_compatible:
 	.skip	64
@@ -396,7 +396,7 @@ sun4v_chip_type:
 	or	%g1, %lo(prom_cpu_compatible), %g1
 	sethi	%hi(prom_sparc_prefix), %g7
 	or	%g7, %lo(prom_sparc_prefix), %g7
-	mov	7, %g3
+	mov	6, %g3
 90:	ldub	[%g7], %g2
 	ldub	[%g1], %g4
 	cmp	%g2, %g4
@@ -408,10 +408,23 @@ sun4v_chip_type:
 
 	sethi	%hi(prom_cpu_compatible), %g1
 	or	%g1, %lo(prom_cpu_compatible), %g1
-	ldub	[%g1 + 7], %g2
+	ldub	[%g1 + 6], %g2
+	cmp	%g2, 'T'
+	be,pt	%xcc, 70f
+	 cmp	%g2, 'M'
+	bne,pn	%xcc, 4f
+	 nop
+
+70:	ldub	[%g1 + 7], %g2
 	cmp	%g2, '3'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA3, %g4
+	cmp	%g2, '4'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_NIAGARA4, %g4
+	cmp	%g2, '5'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_NIAGARA5, %g4
 	ba,pt	%xcc, 4f
 	 nop
 
@@ -545,6 +558,12 @@ niagara_tlb_fixup:
 	cmp	%g1, SUN4V_CHIP_NIAGARA3
 	be,pt	%xcc, niagara2_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_NIAGARA4
+	be,pt	%xcc, niagara2_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_NIAGARA5
+	be,pt	%xcc, niagara2_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index c8cc461ff75f..f793742eec2b 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -380,8 +380,7 @@ void flush_thread(void)
 #endif
 	}
 
-	/* Now, this task is no longer a kernel thread. */
-	current->thread.current_ds = USER_DS;
+	/* This task is no longer a kernel thread. */
 	if (current->thread.flags & SPARC_FLAG_KTHREAD) {
 		current->thread.flags &= ~SPARC_FLAG_KTHREAD;
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index c158a95ec664..d959cd0a4aa4 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -368,9 +368,6 @@ void flush_thread(void)
 
 	/* Clear FPU register state. */
 	t->fpsaved[0] = 0;
-	
-	if (get_thread_current_ds() != ASI_AIUS)
-		set_fs(USER_DS);
 }
 
 /* It's a bit more tricky when 64-bit tasks are involved... */
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index d26e1f6c717a..3e3e2914c70b 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -137,7 +137,7 @@ static void __init process_switch(char c)
 		prom_halt();
 		break;
 	case 'p':
-		/* Just ignore, this behavior is now the default.  */
+		prom_early_console.flags &= ~CON_BOOT;
 		break;
 	default:
 		printk("Unknown boot switch (-%c)\n", c);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3c5bb784214f..c965595aa7e9 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -106,7 +106,7 @@ static void __init process_switch(char c)
 		prom_halt();
 		break;
 	case 'p':
-		/* Just ignore, this behavior is now the default.  */
+		prom_early_console.flags &= ~CON_BOOT;
 		break;
 	case 'P':
 		/* Force UltraSPARC-III P-Cache on. */
@@ -425,10 +425,14 @@ static void __init init_sparc64_elf_hwcap(void)
 	else if (tlb_type == hypervisor) {
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 			cap |= HWCAP_SPARC_N2;
 	}
 
@@ -452,11 +456,15 @@ static void __init init_sparc64_elf_hwcap(void)
 			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)
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
 					AV_SPARC_POPC);
-			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
 		}
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 581531dbc8b5..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,
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 3f2ad2640d85..ccdbc16b8941 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -42,8 +42,11 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes, cmos_minutes;
 	unsigned char save_control, save_freq_select;
+	unsigned long flags;
 	int retval = 0;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	 /* tell the clock it's being set */
 	save_control = CMOS_READ(RTC_CONTROL);
 	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
@@ -93,12 +96,17 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 	CMOS_WRITE(save_control, RTC_CONTROL);
 	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return retval;
 }
 
 unsigned long mach_get_cmos_time(void)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc_lock, flags);
 
 	/*
 	 * If UIP is clear, then we have >= 244 microseconds before
@@ -125,6 +133,8 @@ unsigned long mach_get_cmos_time(void)
 	status = CMOS_READ(RTC_CONTROL);
 	WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
 		sec = bcd2bin(sec);
 		min = bcd2bin(min);
@@ -169,24 +179,15 @@ EXPORT_SYMBOL(rtc_cmos_write);
 
 int update_persistent_clock(struct timespec now)
 {
-	unsigned long flags;
-	int retval;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	retval = x86_platform.set_wallclock(now.tv_sec);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return retval;
+	return x86_platform.set_wallclock(now.tv_sec);
 }
 
 /* not static: needed by APM */
 void read_persistent_clock(struct timespec *ts)
 {
-	unsigned long retval, flags;
+	unsigned long retval;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	retval = x86_platform.get_wallclock();
-	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	ts->tv_sec = retval;
 	ts->tv_nsec = 0;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6f08bc940fa8..8b4cc5f067de 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3603,7 +3603,7 @@ done_prefixes:
 		break;
 	case Src2CL:
 		ctxt->src2.bytes = 1;
-		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0x8;
+		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff;
 		break;
 	case Src2ImmByte:
 		rc = decode_imm(ctxt, &ctxt->src2, 1, true);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1c5b69373a00..8e8da7960dbe 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -400,7 +400,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 
 	/* xchg acts as a barrier before the setting of the high bits */
 	orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
-	orig.spte_high = ssptep->spte_high = sspte.spte_high;
+	orig.spte_high = ssptep->spte_high;
+	ssptep->spte_high = sspte.spte_high;
 	count_spte_clear(sptep, spte);
 
 	return orig.spte;
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 73d70d65e76e..6d5dbcdd444a 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -58,8 +58,11 @@ EXPORT_SYMBOL_GPL(vrtc_cmos_write);
 unsigned long vrtc_get_time(void)
 {
 	u8 sec, min, hour, mday, mon;
+	unsigned long flags;
 	u32 year;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP))
 		cpu_relax();
 
@@ -70,6 +73,8 @@ unsigned long vrtc_get_time(void)
 	mon = vrtc_cmos_read(RTC_MONTH);
 	year = vrtc_cmos_read(RTC_YEAR);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	/* vRTC YEAR reg contains the offset to 1960 */
 	year += 1960;
 
@@ -83,8 +88,10 @@ unsigned long vrtc_get_time(void)
 int vrtc_set_mmss(unsigned long nowtime)
 {
 	int real_sec, real_min;
+	unsigned long flags;
 	int vrtc_min;
 
+	spin_lock_irqsave(&rtc_lock, flags);
 	vrtc_min = vrtc_cmos_read(RTC_MINUTES);
 
 	real_sec = nowtime % 60;
@@ -95,6 +102,8 @@ int vrtc_set_mmss(unsigned long nowtime)
 
 	vrtc_cmos_write(real_sec, RTC_SECONDS);
 	vrtc_cmos_write(real_min, RTC_MINUTES);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return 0;
 }