Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/ieee802154/fakehard.c

A bug fix went into 'net' for ieee802154/fakehard.c, which is removed
in 'net-next'.

Add build fix into the merge from Stephen Rothwell in openvswitch, the
logging macros take a new initial 'log' argument, a new call was added
in 'net' so when we merge that in here we have to explicitly add the
new 'log' arg to it else the build fails.

Signed-off-by: David S. Miller <davem@davemloft.net>

62 files changed, 407 insertions, 159 deletions

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 413fd94b5301..68be9017593d 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -397,8 +397,7 @@ dtb_check_done:
 		add	sp, sp, r6
 #endif
 
-		tst	r4, #1
-		bleq	cache_clean_flush
+		bl	cache_clean_flush
 
 		adr	r0, BSYM(restart)
 		add	r0, r0, r6
@@ -1047,6 +1046,8 @@ cache_clean_flush:
 		b	call_cache_fn
 
 __armv4_mpu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r2, #1
 		mov	r3, #0
 		mcr	p15, 0, ip, c7, c6, 0	@ invalidate D cache
@@ -1064,6 +1065,8 @@ __armv4_mpu_cache_flush:
 		mov	pc, lr
 		
 __fa526_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r1, #0
 		mcr	p15, 0, r1, c7, c14, 0	@ clean and invalidate D cache
 		mcr	p15, 0, r1, c7, c5, 0	@ flush I cache
@@ -1072,13 +1075,16 @@ __fa526_cache_flush:
 
 __armv6_mmu_cache_flush:
 		mov	r1, #0
-		mcr	p15, 0, r1, c7, c14, 0	@ clean+invalidate D
+		tst	r4, #1
+		mcreq	p15, 0, r1, c7, c14, 0	@ clean+invalidate D
 		mcr	p15, 0, r1, c7, c5, 0	@ invalidate I+BTB
-		mcr	p15, 0, r1, c7, c15, 0	@ clean+invalidate unified
+		mcreq	p15, 0, r1, c7, c15, 0	@ clean+invalidate unified
 		mcr	p15, 0, r1, c7, c10, 4	@ drain WB
 		mov	pc, lr
 
 __armv7_mmu_cache_flush:
+		tst	r4, #1
+		bne	iflush
 		mrc	p15, 0, r10, c0, c1, 5	@ read ID_MMFR1
 		tst	r10, #0xf << 16		@ hierarchical cache (ARMv7)
 		mov	r10, #0
@@ -1139,6 +1145,8 @@ iflush:
 		mov	pc, lr
 
 __armv5tej_mmu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 1:		mrc	p15, 0, r15, c7, c14, 3	@ test,clean,invalidate D cache
 		bne	1b
 		mcr	p15, 0, r0, c7, c5, 0	@ flush I cache
@@ -1146,6 +1154,8 @@ __armv5tej_mmu_cache_flush:
 		mov	pc, lr
 
 __armv4_mmu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r2, #64*1024		@ default: 32K dcache size (*2)
 		mov	r11, #32		@ default: 32 byte line size
 		mrc	p15, 0, r3, c0, c0, 1	@ read cache type
@@ -1179,6 +1189,8 @@ no_cache_id:
 
 __armv3_mmu_cache_flush:
 __armv3_mpu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r1, #0
 		mcr	p15, 0, r1, c7, c0, 0	@ invalidate whole cache v3
 		mov	pc, lr
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index e2156a583de7..c4b968f0feb5 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -489,7 +489,7 @@
 			reg = <0x00060000 0x00020000>;
 		};
 		partition@4 {
-			label = "NAND.u-boot-spl";
+			label = "NAND.u-boot-spl-os";
 			reg = <0x00080000 0x00040000>;
 		};
 		partition@5 {
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index e7ac47fa6615..a521ac0a7d5a 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -291,8 +291,8 @@
 		dcdc3: regulator-dcdc3 {
 			compatible = "ti,tps65218-dcdc3";
 			regulator-name = "vdcdc3";
-			regulator-min-microvolt = <1350000>;
-			regulator-max-microvolt = <1350000>;
+			regulator-min-microvolt = <1500000>;
+			regulator-max-microvolt = <1500000>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 859ff3d620ee..87aa4f3b8b3d 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -363,8 +363,8 @@
 		dcdc3: regulator-dcdc3 {
 			compatible = "ti,tps65218-dcdc3";
 			regulator-name = "vdds_ddr";
-			regulator-min-microvolt = <1350000>;
-			regulator-max-microvolt = <1350000>;
+			regulator-min-microvolt = <1500000>;
+			regulator-max-microvolt = <1500000>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index ac3e4859935f..f7e9bba10bd6 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -358,8 +358,8 @@
 		dcdc3: regulator-dcdc3 {
 			compatible = "ti,tps65218-dcdc3";
 			regulator-name = "vdcdc3";
-			regulator-min-microvolt = <1350000>;
-			regulator-max-microvolt = <1350000>;
+			regulator-min-microvolt = <1500000>;
+			regulator-max-microvolt = <1500000>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/sama5d31.dtsi b/arch/arm/boot/dts/sama5d31.dtsi
index 7997dc9863ed..883878b32971 100644
--- a/arch/arm/boot/dts/sama5d31.dtsi
+++ b/arch/arm/boot/dts/sama5d31.dtsi
@@ -12,5 +12,5 @@
 #include "sama5d3_uart.dtsi"
 
 / {
-	compatible = "atmel,samad31", "atmel,sama5d3", "atmel,sama5";
+	compatible = "atmel,sama5d31", "atmel,sama5d3", "atmel,sama5";
 };
diff --git a/arch/arm/boot/dts/sama5d33.dtsi b/arch/arm/boot/dts/sama5d33.dtsi
index 39f832253caf..4b4434aca351 100644
--- a/arch/arm/boot/dts/sama5d33.dtsi
+++ b/arch/arm/boot/dts/sama5d33.dtsi
@@ -10,5 +10,5 @@
 #include "sama5d3_gmac.dtsi"
 
 / {
-	compatible = "atmel,samad33", "atmel,sama5d3", "atmel,sama5";
+	compatible = "atmel,sama5d33", "atmel,sama5d3", "atmel,sama5";
 };
diff --git a/arch/arm/boot/dts/sama5d34.dtsi b/arch/arm/boot/dts/sama5d34.dtsi
index 89cda2c0da39..aa01573fdee9 100644
--- a/arch/arm/boot/dts/sama5d34.dtsi
+++ b/arch/arm/boot/dts/sama5d34.dtsi
@@ -12,5 +12,5 @@
 #include "sama5d3_mci2.dtsi"
 
 / {
-	compatible = "atmel,samad34", "atmel,sama5d3", "atmel,sama5";
+	compatible = "atmel,sama5d34", "atmel,sama5d3", "atmel,sama5";
 };
diff --git a/arch/arm/boot/dts/sama5d35.dtsi b/arch/arm/boot/dts/sama5d35.dtsi
index d20cd71b5f0e..16c39f4c96a4 100644
--- a/arch/arm/boot/dts/sama5d35.dtsi
+++ b/arch/arm/boot/dts/sama5d35.dtsi
@@ -14,5 +14,5 @@
 #include "sama5d3_tcb1.dtsi"
 
 / {
-	compatible = "atmel,samad35", "atmel,sama5d3", "atmel,sama5";
+	compatible = "atmel,sama5d35", "atmel,sama5d3", "atmel,sama5";
 };
diff --git a/arch/arm/boot/dts/sama5d36.dtsi b/arch/arm/boot/dts/sama5d36.dtsi
index db58cad6acd3..e85139ef40af 100644
--- a/arch/arm/boot/dts/sama5d36.dtsi
+++ b/arch/arm/boot/dts/sama5d36.dtsi
@@ -16,5 +16,5 @@
 #include "sama5d3_uart.dtsi"
 
 / {
-	compatible = "atmel,samad36", "atmel,sama5d3", "atmel,sama5";
+	compatible = "atmel,sama5d36", "atmel,sama5d3", "atmel,sama5";
 };
diff --git a/arch/arm/boot/dts/sama5d3xcm.dtsi b/arch/arm/boot/dts/sama5d3xcm.dtsi
index 962dc28dc37b..cfcd200b0c17 100644
--- a/arch/arm/boot/dts/sama5d3xcm.dtsi
+++ b/arch/arm/boot/dts/sama5d3xcm.dtsi
@@ -8,7 +8,7 @@
  */
 
 / {
-	compatible = "atmel,samad3xcm", "atmel,sama5d3", "atmel,sama5";
+	compatible = "atmel,sama5d3xcm", "atmel,sama5d3", "atmel,sama5";
 
 	chosen {
 		bootargs = "console=ttyS0,115200 rootfstype=ubifs ubi.mtd=5 root=ubi0:rootfs";
diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c
index 6478626e3ff6..d0d39f150fab 100644
--- a/arch/arm/mach-mvebu/board-v7.c
+++ b/arch/arm/mach-mvebu/board-v7.c
@@ -188,7 +188,7 @@ static void __init thermal_quirk(void)
 
 static void __init mvebu_dt_init(void)
 {
-	if (of_machine_is_compatible("plathome,openblocks-ax3-4"))
+	if (of_machine_is_compatible("marvell,armadaxp"))
 		i2c_quirk();
 	if (of_machine_is_compatible("marvell,a375-db")) {
 		external_abort_quirk();
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index ae69809a9e47..7eb94e6fc376 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -798,6 +798,7 @@ config NEED_KUSER_HELPERS
 
 config KUSER_HELPERS
 	bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
+	depends on MMU
 	default y
 	help
 	  Warning: disabling this option may break user programs.
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index b61a3bcc2fa8..e048f6198d68 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -497,6 +497,34 @@ static void orion_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 #define orion_gpio_dbg_show NULL
 #endif
 
+static void orion_gpio_unmask_irq(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+	u32 reg_val;
+	u32 mask = d->mask;
+
+	irq_gc_lock(gc);
+	reg_val = irq_reg_readl(gc->reg_base + ct->regs.mask);
+	reg_val |= mask;
+	irq_reg_writel(reg_val, gc->reg_base + ct->regs.mask);
+	irq_gc_unlock(gc);
+}
+
+static void orion_gpio_mask_irq(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+	u32 mask = d->mask;
+	u32 reg_val;
+
+	irq_gc_lock(gc);
+	reg_val = irq_reg_readl(gc->reg_base + ct->regs.mask);
+	reg_val &= ~mask;
+	irq_reg_writel(reg_val, gc->reg_base + ct->regs.mask);
+	irq_gc_unlock(gc);
+}
+
 void __init orion_gpio_init(struct device_node *np,
 			    int gpio_base, int ngpio,
 			    void __iomem *base, int mask_offset,
@@ -565,8 +593,8 @@ void __init orion_gpio_init(struct device_node *np,
 	ct = gc->chip_types;
 	ct->regs.mask = ochip->mask_offset + GPIO_LEVEL_MASK_OFF;
 	ct->type = IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW;
-	ct->chip.irq_mask = irq_gc_mask_clr_bit;
-	ct->chip.irq_unmask = irq_gc_mask_set_bit;
+	ct->chip.irq_mask = orion_gpio_mask_irq;
+	ct->chip.irq_unmask = orion_gpio_unmask_irq;
 	ct->chip.irq_set_type = gpio_irq_set_type;
 	ct->chip.name = ochip->chip.label;
 
@@ -575,8 +603,8 @@ void __init orion_gpio_init(struct device_node *np,
 	ct->regs.ack = GPIO_EDGE_CAUSE_OFF;
 	ct->type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
 	ct->chip.irq_ack = irq_gc_ack_clr_bit;
-	ct->chip.irq_mask = irq_gc_mask_clr_bit;
-	ct->chip.irq_unmask = irq_gc_mask_set_bit;
+	ct->chip.irq_mask = orion_gpio_mask_irq;
+	ct->chip.irq_unmask = orion_gpio_unmask_irq;
 	ct->chip.irq_set_type = gpio_irq_set_type;
 	ct->handler = handle_edge_irq;
 	ct->chip.name = ochip->chip.label;
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ccc7087d3c4e..a62cd077457b 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -142,7 +142,7 @@ static inline void *phys_to_virt(phys_addr_t x)
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
  *  virt_addr_valid(k)	indicates whether a virtual address is valid
  */
-#define ARCH_PFN_OFFSET		PHYS_PFN_OFFSET
+#define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define	virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 619b1dd7bcde..d18a44940968 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -54,18 +54,17 @@ ENTRY(efi_stub_entry)
 	b.eq	efi_load_fail
 
 	/*
-	 * efi_entry() will have relocated the kernel image if necessary
-	 * and we return here with device tree address in x0 and the kernel
-	 * entry point stored at *image_addr. Save those values in registers
-	 * which are callee preserved.
+	 * efi_entry() will have copied the kernel image if necessary and we
+	 * return here with device tree address in x0 and the kernel entry
+	 * point stored at *image_addr. Save those values in registers which
+	 * are callee preserved.
 	 */
 	mov	x20, x0		// DTB address
 	ldr	x0, [sp, #16]	// relocated _text address
 	mov	x21, x0
 
 	/*
-	 * Flush dcache covering current runtime addresses
-	 * of kernel text/data. Then flush all of icache.
+	 * Calculate size of the kernel Image (same for original and copy).
 	 */
 	adrp	x1, _text
 	add	x1, x1, #:lo12:_text
@@ -73,9 +72,24 @@ ENTRY(efi_stub_entry)
 	add	x2, x2, #:lo12:_edata
 	sub	x1, x2, x1
 
+	/*
+	 * Flush the copied Image to the PoC, and ensure it is not shadowed by
+	 * stale icache entries from before relocation.
+	 */
 	bl	__flush_dcache_area
 	ic	ialluis
 
+	/*
+	 * Ensure that the rest of this function (in the original Image) is
+	 * visible when the caches are disabled. The I-cache can't have stale
+	 * entries for the VA range of the current image, so no maintenance is
+	 * necessary.
+	 */
+	adr	x0, efi_stub_entry
+	adr	x1, efi_stub_entry_end
+	sub	x1, x1, x0
+	bl	__flush_dcache_area
+
 	/* Turn off Dcache and MMU */
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
@@ -105,4 +119,5 @@ efi_load_fail:
 	ldp	x29, x30, [sp], #32
 	ret
 
+efi_stub_entry_end:
 ENDPROC(efi_stub_entry)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index e007714ded04..8cd27fedc8b6 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -163,9 +163,10 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 		 * which ends with "dsb; isb" pair guaranteeing global
 		 * visibility.
 		 */
-		atomic_set(&pp->cpu_count, -1);
+		/* Notify other processors with an additional increment. */
+		atomic_inc(&pp->cpu_count);
 	} else {
-		while (atomic_read(&pp->cpu_count) != -1)
+		while (atomic_read(&pp->cpu_count) <= num_online_cpus())
 			cpu_relax();
 		isb();
 	}
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 6e0ed93d51fe..c17967fdf5f6 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -46,7 +46,7 @@ USER(9f, strh	wzr, [x0], #2	)
 	sub	x1, x1, #2
 4:	adds	x1, x1, #1
 	b.mi	5f
-	strb	wzr, [x0]
+USER(9f, strb	wzr, [x0]	)
 5:	mov	x0, #0
 	ret
 ENDPROC(__clear_user)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 0bf90d26e745..f4f8b500f74c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -202,7 +202,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
-				  unsigned long end, unsigned long phys,
+				  unsigned long end, phys_addr_t phys,
 				  int map_io)
 {
 	pud_t *pud;
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index e194f957ca8c..fdbff44e5482 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -20,9 +20,15 @@
 #define WORD_INSN ".word"
 #endif
 
+#ifdef CONFIG_CPU_MICROMIPS
+#define NOP_INSN "nop32"
+#else
+#define NOP_INSN "nop"
+#endif
+
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm_volatile_goto("1:\tnop\n\t"
+	asm_volatile_goto("1:\t" NOP_INSN "\n\t"
 		"nop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
index 7d28f95b0512..6d69332f21ec 100644
--- a/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
@@ -41,10 +41,8 @@
 #define cpu_has_mcheck		0
 #define cpu_has_mdmx		0
 #define cpu_has_mips16		0
-#define cpu_has_mips32r1	0
 #define cpu_has_mips32r2	0
 #define cpu_has_mips3d		0
-#define cpu_has_mips64r1	0
 #define cpu_has_mips64r2	0
 #define cpu_has_mipsmt		0
 #define cpu_has_prefetch	0
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index a10951090234..133678ab4eb8 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -301,7 +301,8 @@ do {									\
 			__get_kernel_common((x), size, __gu_ptr);	\
 		else							\
 			__get_user_common((x), size, __gu_ptr);		\
-	}								\
+	} else								\
+		(x) = 0;						\
 									\
 	__gu_err;							\
 })
@@ -316,6 +317,7 @@ do {									\
 	"	.insn						\n"	\
 	"	.section .fixup,\"ax\"				\n"	\
 	"3:	li	%0, %4					\n"	\
+	"	move	%1, $0					\n"	\
 	"	j	2b					\n"	\
 	"	.previous					\n"	\
 	"	.section __ex_table,\"a\"			\n"	\
@@ -630,6 +632,7 @@ do {									\
 	"	.insn						\n"	\
 	"	.section .fixup,\"ax\"				\n"	\
 	"3:	li	%0, %4					\n"	\
+	"	move	%1, $0					\n"	\
 	"	j	2b					\n"	\
 	"	.previous					\n"	\
 	"	.section __ex_table,\"a\"			\n"	\
@@ -773,10 +776,11 @@ extern void __put_user_unaligned_unknown(void);
 	"jal\t" #destination "\n\t"
 #endif
 
-#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
-#define DADDI_SCRATCH "$0"
-#else
+#if defined(CONFIG_CPU_DADDI_WORKAROUNDS) || (defined(CONFIG_EVA) &&	\
+					      defined(CONFIG_CPU_HAS_PREFETCH))
 #define DADDI_SCRATCH "$3"
+#else
+#define DADDI_SCRATCH "$0"
 #endif
 
 extern size_t __copy_user(void *__to, const void *__from, size_t __n);
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 94c4a0c0a577..d5a4f380b019 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -757,31 +757,34 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			c->cputype = CPU_LOONGSON2;
 			__cpu_name[cpu] = "ICT Loongson-2";
 			set_elf_platform(cpu, "loongson2e");
+			set_isa(c, MIPS_CPU_ISA_III);
 			break;
 		case PRID_REV_LOONGSON2F:
 			c->cputype = CPU_LOONGSON2;
 			__cpu_name[cpu] = "ICT Loongson-2";
 			set_elf_platform(cpu, "loongson2f");
+			set_isa(c, MIPS_CPU_ISA_III);
 			break;
 		case PRID_REV_LOONGSON3A:
 			c->cputype = CPU_LOONGSON3;
-			c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
+			set_isa(c, MIPS_CPU_ISA_M64R1);
 			break;
 		case PRID_REV_LOONGSON3B_R1:
 		case PRID_REV_LOONGSON3B_R2:
 			c->cputype = CPU_LOONGSON3;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3b");
+			set_isa(c, MIPS_CPU_ISA_M64R1);
 			break;
 		}
 
-		set_isa(c, MIPS_CPU_ISA_III);
 		c->options = R4K_OPTS |
 			     MIPS_CPU_FPU | MIPS_CPU_LLSC |
 			     MIPS_CPU_32FPR;
 		c->tlbsize = 64;
+		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		break;
 	case PRID_IMP_LOONGSON_32:  /* Loongson-1 */
 		decode_configs(c);
diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c
index 6001610cfe55..dda800e9e731 100644
--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@@ -18,31 +18,53 @@
 
 #ifdef HAVE_JUMP_LABEL
 
-#define J_RANGE_MASK ((1ul << 28) - 1)
+/*
+ * Define parameters for the standard MIPS and the microMIPS jump
+ * instruction encoding respectively:
+ *
+ * - the ISA bit of the target, either 0 or 1 respectively,
+ *
+ * - the amount the jump target address is shifted right to fit in the
+ *   immediate field of the machine instruction, either 2 or 1,
+ *
+ * - the mask determining the size of the jump region relative to the
+ *   delay-slot instruction, either 256MB or 128MB,
+ *
+ * - the jump target alignment, either 4 or 2 bytes.
+ */
+#define J_ISA_BIT	IS_ENABLED(CONFIG_CPU_MICROMIPS)
+#define J_RANGE_SHIFT	(2 - J_ISA_BIT)
+#define J_RANGE_MASK	((1ul << (26 + J_RANGE_SHIFT)) - 1)
+#define J_ALIGN_MASK	((1ul << J_RANGE_SHIFT) - 1)
 
 void arch_jump_label_transform(struct jump_entry *e,
 			       enum jump_label_type type)
 {
+	union mips_instruction *insn_p;
 	union mips_instruction insn;
-	union mips_instruction *insn_p =
-		(union mips_instruction *)(unsigned long)e->code;
 
-	/* Jump only works within a 256MB aligned region. */
-	BUG_ON((e->target & ~J_RANGE_MASK) != (e->code & ~J_RANGE_MASK));
+	insn_p = (union mips_instruction *)msk_isa16_mode(e->code);
+
+	/* Jump only works within an aligned region its delay slot is in. */
+	BUG_ON((e->target & ~J_RANGE_MASK) != ((e->code + 4) & ~J_RANGE_MASK));
 
-	/* Target must have 4 byte alignment. */
-	BUG_ON((e->target & 3) != 0);
+	/* Target must have the right alignment and ISA must be preserved. */
+	BUG_ON((e->target & J_ALIGN_MASK) != J_ISA_BIT);
 
 	if (type == JUMP_LABEL_ENABLE) {
-		insn.j_format.opcode = j_op;
-		insn.j_format.target = (e->target & J_RANGE_MASK) >> 2;
+		insn.j_format.opcode = J_ISA_BIT ? mm_j32_op : j_op;
+		insn.j_format.target = e->target >> J_RANGE_SHIFT;
 	} else {
 		insn.word = 0; /* nop */
 	}
 
 	get_online_cpus();
 	mutex_lock(&text_mutex);
-	*insn_p = insn;
+	if (IS_ENABLED(CONFIG_CPU_MICROMIPS)) {
+		insn_p->halfword[0] = insn.word >> 16;
+		insn_p->halfword[1] = insn.word;
+	} else
+		*insn_p = insn;
 
 	flush_icache_range((unsigned long)insn_p,
 			   (unsigned long)insn_p + sizeof(*insn_p));
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index c17ef80cf65a..5d3238af9b5c 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -503,6 +503,7 @@
 	STOREB(t0, NBYTES-2(dst), .Ls_exc_p1\@)
 .Ldone\@:
 	jr	ra
+	 nop
 	.if __memcpy == 1
 	END(memcpy)
 	.set __memcpy, 0
diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c
index 37ed184398c6..42323bcc5d28 100644
--- a/arch/mips/loongson/loongson-3/numa.c
+++ b/arch/mips/loongson/loongson-3/numa.c
@@ -33,6 +33,7 @@
 
 static struct node_data prealloc__node_data[MAX_NUMNODES];
 unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
+EXPORT_SYMBOL(__node_distances);
 struct node_data *__node_data[MAX_NUMNODES];
 EXPORT_SYMBOL(__node_data);
 
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index fa6ebd4bc9e9..c3917e251f59 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -299,6 +299,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 
 	local_irq_save(flags);
 
+	htw_stop();
 	pid = read_c0_entryhi() & ASID_MASK;
 	address &= (PAGE_MASK << 1);
 	write_c0_entryhi(address | pid);
@@ -346,6 +347,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 			tlb_write_indexed();
 	}
 	tlbw_use_hazard();
+	htw_start();
 	flush_itlb_vm(vma);
 	local_irq_restore(flags);
 }
@@ -422,6 +424,7 @@ __init int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1,
 
 	local_irq_save(flags);
 	/* Save old context and create impossible VPN2 value */
+	htw_stop();
 	old_ctx = read_c0_entryhi();
 	old_pagemask = read_c0_pagemask();
 	wired = read_c0_wired();
@@ -443,6 +446,7 @@ __init int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1,
 
 	write_c0_entryhi(old_ctx);
 	write_c0_pagemask(old_pagemask);
+	htw_start();
 out:
 	local_irq_restore(flags);
 	return ret;
diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c
index 6854ed5097d2..83a1dfd8f0e3 100644
--- a/arch/mips/oprofile/backtrace.c
+++ b/arch/mips/oprofile/backtrace.c
@@ -92,7 +92,7 @@ static inline int unwind_user_frame(struct stackframe *old_frame,
 				/* This marks the end of the previous function,
 				   which means we overran. */
 				break;
-			stack_size = (unsigned) stack_adjustment;
+			stack_size = (unsigned long) stack_adjustment;
 		} else if (is_ra_save_ins(&ip)) {
 			int ra_slot = ip.i_format.simmediate;
 			if (ra_slot < 0)
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index a95c00f5fb96..a304bcc37e4f 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -107,6 +107,7 @@ static void router_recurse(klrou_t *router_a, klrou_t *router_b, int depth)
 }
 
 unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
+EXPORT_SYMBOL(__node_distances);
 
 static int __init compute_node_distance(nasid_t nasid_a, nasid_t nasid_b)
 {
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 4006964d8e12..a5cb070b54bf 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -9,6 +9,8 @@
 #include <asm/errno.h>
 #include <asm-generic/uaccess-unaligned.h>
 
+#include <linux/bug.h>
+
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
 
@@ -28,11 +30,6 @@
  * that put_user is the same as __put_user, etc.
  */
 
-extern int __get_kernel_bad(void);
-extern int __get_user_bad(void);
-extern int __put_kernel_bad(void);
-extern int __put_user_bad(void);
-
 static inline long access_ok(int type, const void __user * addr,
 		unsigned long size)
 {
@@ -43,8 +40,8 @@ static inline long access_ok(int type, const void __user * addr,
 #define get_user __get_user
 
 #if !defined(CONFIG_64BIT)
-#define LDD_KERNEL(ptr)		__get_kernel_bad();
-#define LDD_USER(ptr)		__get_user_bad();
+#define LDD_KERNEL(ptr)		BUILD_BUG()
+#define LDD_USER(ptr)		BUILD_BUG()
 #define STD_KERNEL(x, ptr)	__put_kernel_asm64(x,ptr)
 #define STD_USER(x, ptr)	__put_user_asm64(x,ptr)
 #define ASM_WORD_INSN		".word\t"
@@ -94,7 +91,7 @@ struct exception_data {
 	    case 2: __get_kernel_asm("ldh",ptr); break; \
 	    case 4: __get_kernel_asm("ldw",ptr); break; \
 	    case 8: LDD_KERNEL(ptr); break;		\
-	    default: __get_kernel_bad(); break;         \
+	    default: BUILD_BUG(); break;		\
 	    }                                           \
 	}                                               \
 	else {                                          \
@@ -103,7 +100,7 @@ struct exception_data {
 	    case 2: __get_user_asm("ldh",ptr); break;   \
 	    case 4: __get_user_asm("ldw",ptr); break;   \
 	    case 8: LDD_USER(ptr);  break;		\
-	    default: __get_user_bad(); break;           \
+	    default: BUILD_BUG(); break;		\
 	    }                                           \
 	}                                               \
 							\
@@ -136,7 +133,7 @@ struct exception_data {
 	    case 2: __put_kernel_asm("sth",__x,ptr); break;     \
 	    case 4: __put_kernel_asm("stw",__x,ptr); break;     \
 	    case 8: STD_KERNEL(__x,ptr); break;			\
-	    default: __put_kernel_bad(); break;			\
+	    default: BUILD_BUG(); break;			\
 	    }                                                   \
 	}                                                       \
 	else {                                                  \
@@ -145,7 +142,7 @@ struct exception_data {
 	    case 2: __put_user_asm("sth",__x,ptr); break;       \
 	    case 4: __put_user_asm("stw",__x,ptr); break;       \
 	    case 8: STD_USER(__x,ptr); break;			\
-	    default: __put_user_bad(); break;			\
+	    default: BUILD_BUG(); break;			\
 	    }                                                   \
 	}                                                       \
 								\
diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h
index 75196b415d3f..e0a23c7bdd43 100644
--- a/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -1,13 +1,7 @@
 #ifndef __ASM_PARISC_BITSPERLONG_H
 #define __ASM_PARISC_BITSPERLONG_H
 
-/*
- * using CONFIG_* outside of __KERNEL__ is wrong,
- * __LP64__ was also removed from headers, so what
- * is the right approach on parisc?
- *	-arnd
- */
-#if (defined(__KERNEL__) && defined(CONFIG_64BIT)) || defined (__LP64__)
+#if defined(__LP64__)
 #define __BITS_PER_LONG 64
 #define SHIFT_PER_LONG 6
 #else
diff --git a/arch/parisc/include/uapi/asm/msgbuf.h b/arch/parisc/include/uapi/asm/msgbuf.h
index fe88f2649418..342138983914 100644
--- a/arch/parisc/include/uapi/asm/msgbuf.h
+++ b/arch/parisc/include/uapi/asm/msgbuf.h
@@ -1,6 +1,8 @@
 #ifndef _PARISC_MSGBUF_H
 #define _PARISC_MSGBUF_H
 
+#include <asm/bitsperlong.h>
+
 /* 
  * The msqid64_ds structure for parisc architecture, copied from sparc.
  * Note extra padding because this structure is passed back and forth
@@ -13,15 +15,15 @@
 
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int   __pad1;
 #endif
 	__kernel_time_t msg_stime;	/* last msgsnd time */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int   __pad2;
 #endif
 	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int   __pad3;
 #endif
 	__kernel_time_t msg_ctime;	/* last change time */
diff --git a/arch/parisc/include/uapi/asm/sembuf.h b/arch/parisc/include/uapi/asm/sembuf.h
index 1e59ffd3bd1e..f01d89e30d73 100644
--- a/arch/parisc/include/uapi/asm/sembuf.h
+++ b/arch/parisc/include/uapi/asm/sembuf.h
@@ -1,6 +1,8 @@
 #ifndef _PARISC_SEMBUF_H
 #define _PARISC_SEMBUF_H
 
+#include <asm/bitsperlong.h>
+
 /* 
  * The semid64_ds structure for parisc architecture.
  * Note extra padding because this structure is passed back and forth
@@ -13,11 +15,11 @@
 
 struct semid64_ds {
 	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int	__pad1;
 #endif
 	__kernel_time_t	sem_otime;		/* last semop time */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int	__pad2;
 #endif
 	__kernel_time_t	sem_ctime;		/* last change time */
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index 0a3eada1863b..8496c38560c6 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -1,6 +1,8 @@
 #ifndef _PARISC_SHMBUF_H
 #define _PARISC_SHMBUF_H
 
+#include <asm/bitsperlong.h>
+
 /* 
  * The shmid64_ds structure for parisc architecture.
  * Note extra padding because this structure is passed back and forth
@@ -13,19 +15,19 @@
 
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int		__pad1;
 #endif
 	__kernel_time_t		shm_atime;	/* last attach time */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int		__pad2;
 #endif
 	__kernel_time_t		shm_dtime;	/* last detach time */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int		__pad3;
 #endif
 	__kernel_time_t		shm_ctime;	/* last change time */
-#ifndef CONFIG_64BIT
+#if __BITS_PER_LONG != 64
 	unsigned int		__pad4;
 #endif
 	size_t			shm_segsz;	/* size of segment (bytes) */
@@ -36,23 +38,16 @@ struct shmid64_ds {
 	unsigned int		__unused2;
 };
 
-#ifdef CONFIG_64BIT
-/* The 'unsigned int' (formerly 'unsigned long') data types below will
- * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
- * a wide kernel, but if some of these values are meant to contain pointers
- * they may need to be 'long long' instead. -PB XXX FIXME
- */
-#endif
 struct shminfo64 {
-	unsigned int	shmmax;
-	unsigned int	shmmin;
-	unsigned int	shmmni;
-	unsigned int	shmseg;
-	unsigned int	shmall;
-	unsigned int	__unused1;
-	unsigned int	__unused2;
-	unsigned int	__unused3;
-	unsigned int	__unused4;
+	unsigned long	shmmax;
+	unsigned long	shmmin;
+	unsigned long	shmmni;
+	unsigned long	shmseg;
+	unsigned long	shmall;
+	unsigned long	__unused1;
+	unsigned long	__unused2;
+	unsigned long	__unused3;
+	unsigned long	__unused4;
 };
 
 #endif /* _PARISC_SHMBUF_H */
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index 10df7079f4cd..e26043b73f5d 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -85,7 +85,7 @@
 struct siginfo;
 
 /* Type of a signal handler.  */
-#ifdef CONFIG_64BIT
+#if defined(__LP64__)
 /* function pointers on 64-bit parisc are pointers to little structs and the
  * compiler doesn't support code which changes or tests the address of
  * the function in the little struct.  This is really ugly -PB
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 8667f18be238..5f5c0373de63 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -833,8 +833,9 @@
 #define __NR_seccomp		(__NR_Linux + 338)
 #define __NR_getrandom		(__NR_Linux + 339)
 #define __NR_memfd_create	(__NR_Linux + 340)
+#define __NR_bpf		(__NR_Linux + 341)
 
-#define __NR_Linux_syscalls	(__NR_memfd_create + 1)
+#define __NR_Linux_syscalls	(__NR_bpf + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index b563d9c8268b..fe4f0b89bf8f 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -286,11 +286,11 @@
 	ENTRY_COMP(msgsnd)
 	ENTRY_COMP(msgrcv)
 	ENTRY_SAME(msgget)		/* 190 */
-	ENTRY_SAME(msgctl)
-	ENTRY_SAME(shmat)
+	ENTRY_COMP(msgctl)
+	ENTRY_COMP(shmat)
 	ENTRY_SAME(shmdt)
 	ENTRY_SAME(shmget)
-	ENTRY_SAME(shmctl)		/* 195 */
+	ENTRY_COMP(shmctl)		/* 195 */
 	ENTRY_SAME(ni_syscall)		/* streams1 */
 	ENTRY_SAME(ni_syscall)		/* streams2 */
 	ENTRY_SAME(lstat64)
@@ -323,7 +323,7 @@
 	ENTRY_SAME(epoll_ctl)		/* 225 */
 	ENTRY_SAME(epoll_wait)
  	ENTRY_SAME(remap_file_pages)
-	ENTRY_SAME(semtimedop)
+	ENTRY_COMP(semtimedop)
 	ENTRY_COMP(mq_open)
 	ENTRY_SAME(mq_unlink)		/* 230 */
 	ENTRY_COMP(mq_timedsend)
@@ -436,6 +436,7 @@
 	ENTRY_SAME(seccomp)
 	ENTRY_SAME(getrandom)
 	ENTRY_SAME(memfd_create)	/* 340 */
+	ENTRY_SAME(bpf)
 
 	/* Nothing yet */
 
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index de40b48b460e..da08ed088157 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -361,7 +361,7 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 	cascade_data->virq = virt_msir;
 	msi->cascade_array[irq_index] = cascade_data;
 
-	ret = request_irq(virt_msir, fsl_msi_cascade, 0,
+	ret = request_irq(virt_msir, fsl_msi_cascade, IRQF_NO_THREAD,
 			  "fsl-msi-cascade", cascade_data);
 	if (ret) {
 		dev_err(&dev->dev, "failed to request_irq(%d), ret = %d\n",
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 765c1776ec9f..0e69b7e7a439 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -22,7 +22,7 @@
 
 int atomic_add_return(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 32c29a133f9d..d38b52dca216 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -11,22 +11,14 @@
 #ifndef __ARCH_SPARC_CMPXCHG__
 #define __ARCH_SPARC_CMPXCHG__
 
-static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
-{
-	__asm__ __volatile__("swap [%2], %0"
-			     : "=&r" (val)
-			     : "0" (val), "r" (m)
-			     : "memory");
-	return val;
-}
-
+unsigned long __xchg_u32(volatile u32 *m, u32 new);
 void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
 	case 4:
-		return xchg_u32(ptr, x);
+		return __xchg_u32(ptr, x);
 	}
 	__xchg_called_with_bad_pointer();
 	return x;
diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h
index a34ad079487e..4c7c12d69bea 100644
--- a/arch/sparc/include/uapi/asm/swab.h
+++ b/arch/sparc/include/uapi/asm/swab.h
@@ -9,9 +9,9 @@ static inline __u16 __arch_swab16p(const __u16 *addr)
 {
 	__u16 ret;
 
-	__asm__ __volatile__ ("lduha [%1] %2, %0"
+	__asm__ __volatile__ ("lduha [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab16p __arch_swab16p
@@ -20,9 +20,9 @@ static inline __u32 __arch_swab32p(const __u32 *addr)
 {
 	__u32 ret;
 
-	__asm__ __volatile__ ("lduwa [%1] %2, %0"
+	__asm__ __volatile__ ("lduwa [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab32p __arch_swab32p
@@ -31,9 +31,9 @@ static inline __u64 __arch_swab64p(const __u64 *addr)
 {
 	__u64 ret;
 
-	__asm__ __volatile__ ("ldxa [%1] %2, %0"
+	__asm__ __volatile__ ("ldxa [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab64p __arch_swab64p
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 8f76f23dac38..f9c6813c132d 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 {
 	unsigned long csr_reg, csr, csr_error_bits;
 	irqreturn_t ret = IRQ_NONE;
-	u16 stat;
+	u32 stat;
 
 	csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL;
 	csr = upa_readq(csr_reg);
@@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 			       pbm->name);
 		ret = IRQ_HANDLED;
 	}
-	pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat);
+	pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat);
 	if (stat & (PCI_STATUS_PARITY |
 		    PCI_STATUS_SIG_TARGET_ABORT |
 		    PCI_STATUS_REC_TARGET_ABORT |
@@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 		    PCI_STATUS_SIG_SYSTEM_ERROR)) {
 		printk("%s: PCI bus error, PCI_STATUS[%04x]\n",
 		       pbm->name, stat);
-		pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff);
+		pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff);
 		ret = IRQ_HANDLED;
 	}
 	return ret;
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 302c476413d5..da6f1a7fc4db 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -816,13 +816,17 @@ void arch_send_call_function_single_ipi(int cpu)
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	irq_enter();
 	generic_smp_call_function_interrupt();
+	irq_exit();
 }
 
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	irq_enter();
 	generic_smp_call_function_single_interrupt();
+	irq_exit();
 }
 
 static void tsb_sync(void *info)
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index a7c418ac26af..71cd65ab200c 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -45,6 +45,19 @@ ATOMIC_OP(add, +=)
 
 #undef ATOMIC_OP
 
+int atomic_xchg(atomic_t *v, int new)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(ATOMIC_HASH(v), flags);
+	ret = v->counter;
+	v->counter = new;
+	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
+	return ret;
+}
+EXPORT_SYMBOL(atomic_xchg);
+
 int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -137,3 +150,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new)
 	return (unsigned long)prev;
 }
 EXPORT_SYMBOL(__cmpxchg_u32);
+
+unsigned long __xchg_u32(volatile u32 *ptr, u32 new)
+{
+	unsigned long flags;
+	u32 prev;
+
+	spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
+	prev = *ptr;
+	*ptr = new;
+	spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
+
+	return (unsigned long)prev;
+}
+EXPORT_SYMBOL(__xchg_u32);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ded8a6774ac9..41a503c15862 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -144,7 +144,7 @@ config INSTRUCTION_DECODER
 
 config PERF_EVENTS_INTEL_UNCORE
 	def_bool y
-	depends on PERF_EVENTS && SUP_SUP_INTEL && PCI
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
 
 config OUTPUT_FORMAT
 	string
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 704f58aa79cd..be1e07d4b596 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -76,8 +76,10 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
+RUN_SIZE = $(shell objdump -h vmlinux | \
+	     perl $(srctree)/arch/x86/tools/calc_run_size.pl)
 quiet_cmd_mkpiggy = MKPIGGY $@
-      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
+      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
 targets += piggy.S
 $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index cbed1407a5cd..1d7fbbcc196d 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -207,7 +207,8 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
 				/* push arguments for decompress_kernel: */
-	pushl	$z_output_len	/* decompressed length */
+	pushl	$z_run_size	/* size of kernel with .bss and .brk */
+	pushl	$z_output_len	/* decompressed length, end of relocs */
 	leal	z_extract_offset_negative(%ebx), %ebp
 	pushl	%ebp		/* output address */
 	pushl	$z_input_len	/* input_len */
@@ -217,7 +218,7 @@ relocated:
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
 	call	decompress_kernel /* returns kernel location in %eax */
-	addl	$24, %esp
+	addl	$28, %esp
 
 /*
  * Jump to the decompressed kernel.
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 2884e0c3e8a5..6b1766c6c082 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -402,13 +402,16 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
+	movq	$z_run_size, %r9	/* size of kernel with .bss and .brk */
+	pushq	%r9
 	movq	%rsi, %rdi		/* real mode address */
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
-	movq	$z_output_len, %r9	/* decompressed length */
+	movq	$z_output_len, %r9	/* decompressed length, end of relocs */
 	call	decompress_kernel	/* returns kernel location in %rax */
+	popq	%r9
 	popq	%rsi
 
 /*
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 57ab74df7eea..30dd59a9f0b4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -358,7 +358,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
-				  unsigned long output_len)
+				  unsigned long output_len,
+				  unsigned long run_size)
 {
 	real_mode = rmode;
 
@@ -381,8 +382,14 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
-	output = choose_kernel_location(input_data, input_len,
-					output, output_len);
+	/*
+	 * The memory hole needed for the kernel is the larger of either
+	 * the entire decompressed kernel plus relocation table, or the
+	 * entire decompressed kernel plus .bss and .brk sections.
+	 */
+	output = choose_kernel_location(input_data, input_len, output,
+					output_len > run_size ? output_len
+							      : run_size);
 
 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index b669ab65bf6c..d8222f213182 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -36,11 +36,13 @@ int main(int argc, char *argv[])
 	uint32_t olen;
 	long ilen;
 	unsigned long offs;
+	unsigned long run_size;
 	FILE *f = NULL;
 	int retval = 1;
 
-	if (argc < 2) {
-		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+	if (argc < 3) {
+		fprintf(stderr, "Usage: %s compressed_file run_size\n",
+				argv[0]);
 		goto bail;
 	}
 
@@ -74,6 +76,7 @@ int main(int argc, char *argv[])
 	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
 	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
 	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+	run_size = atoi(argv[2]);
 
 	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");
@@ -85,6 +88,8 @@ int main(int argc, char *argv[])
 	/* z_extract_offset_negative allows simplification of head_32.S */
 	printf(".globl z_extract_offset_negative\n");
 	printf("z_extract_offset_negative = -0x%lx\n", offs);
+	printf(".globl z_run_size\n");
+	printf("z_run_size = %lu\n", run_size);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 8cd27e08e23c..8cd1cc3bc835 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -150,6 +150,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 }
 
 void cpu_disable_common(void);
+void cpu_die_common(unsigned int cpu);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4b4f78c9ba19..cfa9b5b2c27a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -146,6 +146,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 static int __init x86_xsave_setup(char *s)
 {
+	if (strlen(s))
+		return 0;
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 7aa1acc79789..06674473b0e6 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size)
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
  */
-static void apply_ucode_in_initrd(void *ucode, size_t size)
+static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
 {
 	struct equiv_cpu_entry *eq;
 	size_t *cont_sz;
 	u32 *header;
 	u8  *data, **cont;
+	u8 (*patch)[PATCH_MAX_SIZE];
 	u16 eq_id = 0;
 	int offset, left;
 	u32 rev, eax, ebx, ecx, edx;
@@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
 	cont_sz = (size_t *)__pa_nodebug(&container_size);
 	cont	= (u8 **)__pa_nodebug(&container);
+	patch	= (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
 #else
 	new_rev = &ucode_new_rev;
 	cont_sz = &container_size;
 	cont	= &container;
+	patch	= &amd_ucode_patch;
 #endif
 
 	data   = ucode;
@@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 				rev = mc->hdr.patch_id;
 				*new_rev = rev;
 
-				/* save ucode patch */
-				memcpy(amd_ucode_patch, mc,
-				       min_t(u32, header[1], PATCH_MAX_SIZE));
+				if (save_patch)
+					memcpy(patch, mc,
+					       min_t(u32, header[1], PATCH_MAX_SIZE));
 			}
 		}
 
@@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void)
 	*data = cp.data;
 	*size = cp.size;
 
-	apply_ucode_in_initrd(cp.data, cp.size);
+	apply_ucode_in_initrd(cp.data, cp.size, true);
 }
 
 #ifdef CONFIG_X86_32
@@ -263,7 +266,7 @@ void load_ucode_amd_ap(void)
 	size_t *usize;
 	void **ucode;
 
-	mc = (struct microcode_amd *)__pa(amd_ucode_patch);
+	mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
 	if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
 		__apply_microcode_amd(mc);
 		return;
@@ -275,7 +278,7 @@ void load_ucode_amd_ap(void)
 	if (!*ucode || !*usize)
 		return;
 
-	apply_ucode_in_initrd(*ucode, *usize);
+	apply_ucode_in_initrd(*ucode, *usize, false);
 }
 
 static void __init collect_cpu_sig_on_bsp(void *arg)
@@ -339,7 +342,7 @@ void load_ucode_amd_ap(void)
 		 * AP has a different equivalence ID than BSP, looks like
 		 * mixed-steppings silicon so go through the ucode blob anew.
 		 */
-		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
+		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false);
 	}
 }
 #endif
@@ -347,7 +350,9 @@ void load_ucode_amd_ap(void)
 int __init save_microcode_in_initrd_amd(void)
 {
 	unsigned long cont;
+	int retval = 0;
 	enum ucode_state ret;
+	u8 *cont_va;
 	u32 eax;
 
 	if (!container)
@@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void)
 
 #ifdef CONFIG_X86_32
 	get_bsp_sig();
-	cont = (unsigned long)container;
+	cont	= (unsigned long)container;
+	cont_va = __va(container);
 #else
 	/*
 	 * We need the physical address of the container for both bitness since
 	 * boot_params.hdr.ramdisk_image is a physical address.
 	 */
-	cont = __pa(container);
+	cont    = __pa(container);
+	cont_va = container;
 #endif
 
 	/*
@@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void)
 	if (relocated_ramdisk)
 		container = (u8 *)(__va(relocated_ramdisk) +
 			     (cont - boot_params.hdr.ramdisk_image));
+	else
+		container = cont_va;
 
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
@@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void)
 
 	ret = load_microcode_amd(eax, container, container_size);
 	if (ret != UCODE_OK)
-		return -EINVAL;
+		retval = -EINVAL;
 
 	/*
 	 * This will be freed any msec now, stash patches for the current
@@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void)
 	container = NULL;
 	container_size = 0;
 
-	return 0;
+	return retval;
 }
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index dd9d6190b08d..2ce9051174e6 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -465,6 +465,14 @@ static void mc_bp_resume(void)
 
 	if (uci->valid && uci->mc)
 		microcode_ops->apply_microcode(cpu);
+	else if (!uci->mc)
+		/*
+		 * We might resume and not have applied late microcode but still
+		 * have a newer patch stashed from the early loader. We don't
+		 * have it in uci->mc so we have to load it the same way we're
+		 * applying patches early on the APs.
+		 */
+		load_ucode_ap();
 }
 
 static struct syscore_ops mc_syscore_ops = {
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index 5f28a64e71ea..2c017f242a78 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -124,7 +124,7 @@ void __init load_ucode_bsp(void)
 static bool check_loader_disabled_ap(void)
 {
 #ifdef CONFIG_X86_32
-	return __pa_nodebug(dis_ucode_ldr);
+	return *((bool *)__pa_nodebug(&dis_ucode_ldr));
 #else
 	return dis_ucode_ldr;
 #endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index adf138eac85c..f9ed429d6e4f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -486,14 +486,17 @@ static struct attribute_group snbep_uncore_qpi_format_group = {
 	.attrs = snbep_uncore_qpi_formats_attr,
 };
 
-#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
-	.init_box	= snbep_uncore_msr_init_box,		\
+#define __SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
 	.disable_box	= snbep_uncore_msr_disable_box,		\
 	.enable_box	= snbep_uncore_msr_enable_box,		\
 	.disable_event	= snbep_uncore_msr_disable_event,	\
 	.enable_event	= snbep_uncore_msr_enable_event,	\
 	.read_counter	= uncore_msr_read_counter
 
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	__SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),			\
+	.init_box	= snbep_uncore_msr_init_box		\
+
 static struct intel_uncore_ops snbep_uncore_msr_ops = {
 	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
@@ -1919,6 +1922,30 @@ static struct intel_uncore_type hswep_uncore_cbox = {
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
+/*
+ * Write SBOX Initialization register bit by bit to avoid spurious #GPs
+ */
+static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+
+	if (msr) {
+		u64 init = SNBEP_PMON_BOX_CTL_INT;
+		u64 flags = 0;
+		int i;
+
+		for_each_set_bit(i, (unsigned long *)&init, 64) {
+			flags |= (1ULL << i);
+			wrmsrl(msr, flags);
+		}
+	}
+}
+
+static struct intel_uncore_ops hswep_uncore_sbox_msr_ops = {
+	__SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.init_box		= hswep_uncore_sbox_msr_init_box
+};
+
 static struct attribute *hswep_uncore_sbox_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -1944,7 +1971,7 @@ static struct intel_uncore_type hswep_uncore_sbox = {
 	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
 	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
 	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
-	.ops			= &snbep_uncore_msr_ops,
+	.ops			= &hswep_uncore_sbox_msr_ops,
 	.format_group		= &hswep_uncore_sbox_format_group,
 };
 
@@ -2025,13 +2052,27 @@ static struct intel_uncore_type hswep_uncore_imc = {
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+static unsigned hswep_uncore_irp_ctrs[] = {0xa0, 0xa8, 0xb0, 0xb8};
+
+static u64 hswep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 count = 0;
+
+	pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+	pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+	return count;
+}
+
 static struct intel_uncore_ops hswep_uncore_irp_ops = {
 	.init_box	= snbep_uncore_pci_init_box,
 	.disable_box	= snbep_uncore_pci_disable_box,
 	.enable_box	= snbep_uncore_pci_enable_box,
 	.disable_event	= ivbep_uncore_irp_disable_event,
 	.enable_event	= ivbep_uncore_irp_enable_event,
-	.read_counter	= ivbep_uncore_irp_read_counter,
+	.read_counter	= hswep_uncore_irp_read_counter,
 };
 
 static struct intel_uncore_type hswep_uncore_irp = {
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 749b0e423419..e510618b2e91 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1484,7 +1484,7 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 	 */
 	if (work & _TIF_NOHZ) {
 		user_exit();
-		work &= ~TIF_NOHZ;
+		work &= ~_TIF_NOHZ;
 	}
 
 #ifdef CONFIG_SECCOMP
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4d2128ac70bd..668d8f2a8781 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1303,10 +1303,14 @@ static void __ref remove_cpu_from_maps(int cpu)
 	numa_remove_cpu(cpu);
 }
 
+static DEFINE_PER_CPU(struct completion, die_complete);
+
 void cpu_disable_common(void)
 {
 	int cpu = smp_processor_id();
 
+	init_completion(&per_cpu(die_complete, smp_processor_id()));
+
 	remove_siblinginfo(cpu);
 
 	/* It's now safe to remove this processor from the online map */
@@ -1316,8 +1320,6 @@ void cpu_disable_common(void)
 	fixup_irqs();
 }
 
-static DEFINE_PER_CPU(struct completion, die_complete);
-
 int native_cpu_disable(void)
 {
 	int ret;
@@ -1327,16 +1329,21 @@ int native_cpu_disable(void)
 		return ret;
 
 	clear_local_APIC();
-	init_completion(&per_cpu(die_complete, smp_processor_id()));
 	cpu_disable_common();
 
 	return 0;
 }
 
+void cpu_die_common(unsigned int cpu)
+{
+	wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+}
+
 void native_cpu_die(unsigned int cpu)
 {
 	/* We don't do anything here: idle task is faking death itself. */
-	wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+
+	cpu_die_common(cpu);
 
 	/* They ack this in play_dead() by setting CPU_DEAD */
 	if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 7609e0e421ec..1318f75d56e4 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -41,9 +41,8 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
 		while (((unsigned long)src & 6) && len >= 2) {
 			__u16 val16;
 
-			*errp = __get_user(val16, (const __u16 __user *)src);
-			if (*errp)
-				return isum;
+			if (__get_user(val16, (const __u16 __user *)src))
+				goto out_err;
 
 			*(__u16 *)dst = val16;
 			isum = (__force __wsum)add32_with_carry(
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 4cb8763868fc..4e5dfec750fc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1123,7 +1123,7 @@ void mark_rodata_ro(void)
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
 	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
 	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
-	unsigned long all_end = PFN_ALIGN(&_end);
+	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
@@ -1134,7 +1134,16 @@ void mark_rodata_ro(void)
 	/*
 	 * The rodata/data/bss/brk section (but not the kernel text!)
 	 * should also be not-executable.
+	 *
+	 * We align all_end to PMD_SIZE because the existing mapping
+	 * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+	 * split the PMD and the reminder between _brk_end and the end
+	 * of the PMD will remain mapped executable.
+	 *
+	 * Any PMD which was setup after the one which covers _brk_end
+	 * has been zapped already via cleanup_highmem().
 	 */
+	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
new file mode 100644
index 000000000000..23210baade2d
--- /dev/null
+++ b/arch/x86/tools/calc_run_size.pl
@@ -0,0 +1,39 @@
+#!/usr/bin/perl
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | perl calc_run_size.pl
+use strict;
+
+my $mem_size = 0;
+my $file_offset = 0;
+
+my $sections=" *[0-9]+ \.(?:bss|brk) +";
+while (<>) {
+	if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
+		my $size = hex($1);
+		my $offset = hex($2);
+		$mem_size += $size;
+		if ($file_offset == 0) {
+			$file_offset = $offset;
+		} elsif ($file_offset != $offset) {
+			# BFD linker shows the same file offset in ELF.
+			# Gold linker shows them as consecutive.
+			next if ($file_offset + $mem_size == $offset + $size);
+
+			printf STDERR "file_offset: 0x%lx\n", $file_offset;
+			printf STDERR "mem_size: 0x%lx\n", $mem_size;
+			printf STDERR "offset: 0x%lx\n", $offset;
+			printf STDERR "size: 0x%lx\n", $size;
+
+			die ".bss and .brk are non-contiguous\n";
+		}
+	}
+}
+
+if ($file_offset == 0) {
+	die "Never found .bss or .brk file offset\n";
+}
+printf("%d\n", $mem_size + $file_offset);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8650cdb53209..4c071aeb8417 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -510,6 +510,9 @@ static void xen_cpu_die(unsigned int cpu)
 		current->state = TASK_UNINTERRUPTIBLE;
 		schedule_timeout(HZ/10);
 	}
+
+	cpu_die_common(cpu);
+
 	xen_smp_intr_free(cpu);
 	xen_uninit_lock_cpu(cpu);
 	xen_teardown_timer(cpu);