Merge remote-tracking branch 'lts/linux-4.4.y' into linux-linaro-lsk-v4.4

Conflicts:
	set ARM64_WORKAROUND_CAVIUM_27456 to 12 in
	arch/arm64/include/asm/cpufeature.h
	and add asm/memory.h in arch/arm64/kernel/entry.S

51 files changed, 620 insertions, 342 deletions

diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 209d8451e23d..c05ea2b54276 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -18,6 +18,20 @@ cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
+is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0)
+
+ifdef CONFIG_ISA_ARCOMPACT
+ifeq ($(is_700), 0)
+    $(error Toolchain not configured for ARCompact builds)
+endif
+endif
+
+ifdef CONFIG_ISA_ARCV2
+ifeq ($(is_700), 1)
+    $(error Toolchain not configured for ARCv2 builds)
+endif
+endif
+
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
 # We had a customer reported bug where some code built in kernel was NOT using
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fac7d85ed6a..2c30a016cf15 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -374,12 +374,6 @@ static inline int is_isa_arcompact(void)
 	return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
 }
 
-#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7)
-#error "Toolchain not configured for ARCompact builds"
-#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS)
-#error "Toolchain not configured for ARCv2 builds"
-#endif
-
 #endif /* __ASEMBLY__ */
 
 #endif /* _ASM_ARC_ARCREGS_H */
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index ad7860c5ce15..51597f344a62 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -142,7 +142,7 @@
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 	; Retrieve orig r25 and save it with rest of callee_regs
-	ld.as   r12, [r12, PT_user_r25]
+	ld	r12, [r12, PT_user_r25]
 	PUSH	r12
 #else
 	PUSH	r25
@@ -198,7 +198,7 @@
 
 	; SP is back to start of pt_regs
 #ifdef CONFIG_ARC_CURR_IN_REG
-	st.as   r12, [sp, PT_user_r25]
+	st	r12, [sp, PT_user_r25]
 #endif
 .endm
 
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index c1d36458bfb7..4c6eed80cd8b 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void)
 .endm
 
 .macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
 	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
 .endm
 
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 57af2f05ae84..3cab04255ae0 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -110,7 +110,7 @@
 #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL)
 
 /* More Abbrevaited helpers */
 #define PAGE_U_NONE     __pgprot(___DEF)
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index ff7ff6cbb811..aaf1e2d1d900 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -914,6 +914,15 @@ void arc_cache_init(void)
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
+	/*
+	 * Only master CPU needs to execute rest of function:
+	 *  - Assume SMP so all cores will have same cache config so
+	 *    any geomtry checks will be same for all
+	 *  - IOC setup / dma callbacks only need to be setup once
+	 */
+	if (cpu)
+		return;
+
 	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
 		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 
diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts
index 97570cb7f2fc..1d23527d4ecf 100644
--- a/arch/arm/boot/dts/sun4i-a10-a1000.dts
+++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts
@@ -84,6 +84,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 15 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
index 2b17c5199151..6de83a6187d0 100644
--- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts
+++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
@@ -66,6 +66,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
index 7afc7a64eef1..e28f080b1fd5 100644
--- a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
+++ b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
@@ -80,6 +80,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;   /* PH19 */
 	};
diff --git a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
index 9fea918f949e..39731a78f087 100644
--- a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
@@ -79,6 +79,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 0 2 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8dbe3cba855c..0ddd4d9cc84c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -396,6 +396,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
@@ -406,6 +415,17 @@ config CAVIUM_ERRATUM_23154
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_27456
+	bool "Cavium erratum 27456: Broadcast TLBI instructions may cause icache corruption"
+	default y
+	help
+	  On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI
+	  instructions may cause the icache to become corrupted if it
+	  contains data for a non-current ASID.  The fix is to
+	  invalidate the icache when changing the mm context.
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index cc093a482aa4..e0ee2b00d573 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -262,6 +262,8 @@
 		#io-channel-cells = <1>;
 		clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
 		clock-names = "saradc", "apb_pclk";
+		resets = <&cru SRST_SARADC>;
+		reset-names = "saradc-apb";
 		status = "disabled";
 	};
 
@@ -517,7 +519,7 @@
 		#address-cells = <0>;
 
 		reg = <0x0 0xffb71000 0x0 0x1000>,
-		      <0x0 0xffb72000 0x0 0x1000>,
+		      <0x0 0xffb72000 0x0 0x2000>,
 		      <0x0 0xffb74000 0x0 0x2000>,
 		      <0x0 0xffb76000 0x0 0x2000>;
 		interrupts = <GIC_PPI 9
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25ed2..8ec88e5b290f 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 37a53fc6b384..876fe0622204 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -35,6 +35,8 @@
 #define ARM64_ALT_PAN_NOT_UAO			10
 
 #define ARM64_NCAPS				11
+#define ARM64_WORKAROUND_CAVIUM_27456		12	
+
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 83d48a599f69..7875c886ad24 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -140,6 +140,7 @@ typedef struct user_fpsimd_state elf_fpregset_t;
 
 #define SET_PERSONALITY(ex)		clear_thread_flag(TIF_32BIT);
 
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							\
 do {									\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5e6857b6bdc4..2d960f8588b0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -107,8 +107,6 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index a307eb6e7fa8..7f94755089e2 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -117,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)
diff --git a/arch/arm64/include/uapi/asm/auxvec.h b/arch/arm64/include/uapi/asm/auxvec.h
index 22d6d8885854..4cf0c17787a8 100644
--- a/arch/arm64/include/uapi/asm/auxvec.h
+++ b/arch/arm64/include/uapi/asm/auxvec.h
@@ -19,4 +19,6 @@
 /* vDSO location */
 #define AT_SYSINFO_EHDR	33
 
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
 #endif
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 25de8b244961..087cf9a65359 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -58,6 +58,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index e6bc988e8dbf..06afd04e02c0 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -88,6 +88,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01),
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+	{
+	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 1),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index c1492ba1f6d1..e51f27ac13fd 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -152,7 +152,6 @@ static int debug_monitors_init(void)
 	/* Clear the OS lock. */
 	on_each_cpu(clear_os_lock, NULL, 1);
 	isb();
-	local_dbg_enable();
 
 	/* Register hotplug handler. */
 	__register_cpu_notifier(&os_lock_nb);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 1f7f5a2b61bf..588c8e1778d4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,6 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -97,7 +98,13 @@
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -128,6 +135,12 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 24cb4f800033..a84623d91410 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -187,7 +187,6 @@ asmlinkage void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	local_dbg_enable();
 	local_irq_enable();
 	local_async_enable();
 
@@ -333,8 +332,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
-	cpuinfo_store_boot_cpu();
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	cpuinfo_store_boot_cpu();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 178ba2248a98..84c338f017b2 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
 	and	x4, x4, x5
-	ldr	x5, =TCR_EL2_FLAGS
+	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,15 +85,18 @@ __do_hyp_init:
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 #endif
-	msr	tcr_el2, x4
-
-	ldr	x4, =VTCR_EL2_FLAGS
 	/*
 	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * VTCR_EL2.
+	 * TCR_EL2 and VTCR_EL2.
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
+
+	msr	tcr_el2, x4
+
+	ldr	x4, =VTCR_EL2_FLAGS
+	bfi	x4, x5, #16, #3
+
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index cd4177a1781d..8fc302d84e1f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -748,9 +748,9 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
 	/*
 	 * Check whether the physical FDT address is set and meets the minimum
 	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
-	 * at least 8 bytes so that we can always access the size field of the
-	 * FDT header after mapping the first chunk, double check here if that
-	 * is indeed the case.
+	 * at least 8 bytes so that we can always access the magic and size
+	 * fields of the FDT header after mapping the first chunk, double check
+	 * here if that is indeed the case.
 	 */
 	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
 	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
@@ -778,7 +778,7 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
 	create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE),
 			dt_virt_base, SWAPPER_BLOCK_SIZE, prot);
 
-	if (fdt_check_header(dt_virt) != 0)
+	if (fdt_magic(dt_virt) != FDT_MAGIC)
 		return NULL;
 
 	*size = fdt_totalsize(dt_virt);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 0c19534a901e..a92738e8b1eb 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,6 +25,8 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
 
 #include "proc-macros.S"
 
@@ -137,7 +139,17 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
+alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
 	ret
+	nop
+	nop
+	nop
+alternative_else
+	ic	iallu
+	dsb	nsh
+	isb
+	ret
+alternative_endif
 ENDPROC(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "ax"
@@ -182,6 +194,8 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	isb					// Unmask debug exceptions now,
+	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index a62581815624..88fa25fae8bd 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -61,7 +61,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 		"	CMPT	%0, #HI(0x02000000)\n"			\
 		"	BNZ 1b\n"					\
 		: "=&d" (temp), "=&da" (result)				\
-		: "da" (&v->counter), "bd" (i)				\
+		: "da" (&v->counter), "br" (i)				\
 		: "cc");						\
 									\
 	smp_mb();							\
diff --git a/arch/metag/include/asm/cmpxchg_lnkget.h b/arch/metag/include/asm/cmpxchg_lnkget.h
index 0154e2807ebb..2369ad394876 100644
--- a/arch/metag/include/asm/cmpxchg_lnkget.h
+++ b/arch/metag/include/asm/cmpxchg_lnkget.h
@@ -73,7 +73,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
 		      "	DCACHE	[%2], %0\n"
 #endif
 		      "2:\n"
-		      : "=&d" (temp), "=&da" (retval)
+		      : "=&d" (temp), "=&d" (retval)
 		      : "da" (m), "bd" (old), "da" (new)
 		      : "cc"
 		      );
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index 1f910563fdf6..d76275da54cb 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
 {
 	return read_c0_count();
 }
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
 
 	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
+#ifndef CONFIG_CPU_FREQ
 	sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
 
 	return 0;
 }
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index dc10c77b7500..d6476d11212e 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1629,8 +1629,14 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 
 	preempt_disable();
 	if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
-		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
-			kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
+		    kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+			kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+				__func__, va, vcpu, read_c0_entryhi());
+			er = EMULATE_FAIL;
+			preempt_enable();
+			goto done;
+		}
 	} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
 		   KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
 		int index;
@@ -1665,14 +1671,19 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 								run, vcpu);
 				preempt_enable();
 				goto dont_update_pc;
-			} else {
-				/*
-				 * We fault an entry from the guest tlb to the
-				 * shadow host TLB
-				 */
-				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
-								     NULL,
-								     NULL);
+			}
+			/*
+			 * We fault an entry from the guest tlb to the
+			 * shadow host TLB
+			 */
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+								 NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+				preempt_enable();
+				goto done;
 			}
 		}
 	} else {
@@ -2633,8 +2644,13 @@ enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
 			 * OK we have a Guest TLB entry, now inject it into the
 			 * shadow host TLB
 			 */
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
-							     NULL);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+								 NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+			}
 		}
 	}
 
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index aed0ac2a4972..7a7ed9ca01bb 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -276,7 +276,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
 	}
 
 	gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
-	if (gfn >= kvm->arch.guest_pmap_npages) {
+	if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
 		kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
 			gfn, badvaddr);
 		kvm_mips_dump_host_tlbs();
@@ -361,25 +361,39 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
 	struct kvm *kvm = vcpu->kvm;
 	pfn_t pfn0, pfn1;
-
-	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
-		pfn0 = 0;
-		pfn1 = 0;
-	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					    >> PAGE_SHIFT];
-		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					    >> PAGE_SHIFT];
+	gfn_t gfn0, gfn1;
+	long tlb_lo[2];
+
+	tlb_lo[0] = tlb->tlb_lo0;
+	tlb_lo[1] = tlb->tlb_lo1;
+
+	/*
+	 * The commpage address must not be mapped to anything else if the guest
+	 * TLB contains entries nearby, or commpage accesses will break.
+	 */
+	if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+			VPN2_MASK & (PAGE_MASK << 1)))
+		tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
+
+	gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
+	gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
+	if (gfn0 >= kvm->arch.guest_pmap_npages ||
+	    gfn1 >= kvm->arch.guest_pmap_npages) {
+		kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+			__func__, gfn0, gfn1, tlb->tlb_hi);
+		kvm_mips_dump_guest_tlbs(vcpu);
+		return -1;
 	}
 
+	if (kvm_mips_map_page(kvm, gfn0) < 0)
+		return -1;
+
+	if (kvm_mips_map_page(kvm, gfn1) < 0)
+		return -1;
+
+	pfn0 = kvm->arch.guest_pmap[gfn0];
+	pfn1 = kvm->arch.guest_pmap[gfn1];
+
 	if (hpa0)
 		*hpa0 = pfn0 << PAGE_SHIFT;
 
@@ -391,9 +405,9 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 					       kvm_mips_get_kernel_asid(vcpu) :
 					       kvm_mips_get_user_asid(vcpu));
 	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
+		   (tlb_lo[0] & MIPS3_PG_D) | (tlb_lo[0] & MIPS3_PG_V);
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
+		   (tlb_lo[1] & MIPS3_PG_D) | (tlb_lo[1] & MIPS3_PG_V);
 
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo0, tlb->tlb_lo1);
@@ -794,10 +808,16 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 				local_irq_restore(flags);
 				return KVM_INVALID_INST;
 			}
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
-							     &vcpu->arch.
-							     guest_tlb[index],
-							     NULL, NULL);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+						&vcpu->arch.guest_tlb[index],
+						NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, opc, index, vcpu,
+					read_c0_entryhi());
+				kvm_mips_dump_guest_tlbs(vcpu);
+				local_irq_restore(flags);
+				return KVM_INVALID_INST;
+			}
 			inst = *(opc);
 		}
 		local_irq_restore(flags);
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index a2631a52ca99..444802e78554 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -13,8 +13,8 @@
 #define SMBUS_PCI_REG64		0x64
 #define SMBUS_PCI_REGB4		0xb4
 
-#define HPET_MIN_CYCLES		64
-#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+#define HPET_MIN_CYCLES		16
+#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES * 12)
 
 static DEFINE_SPINLOCK(hpet_lock);
 DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
@@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt)
 static int hpet_next_event(unsigned long delta,
 		struct clock_event_device *evt)
 {
-	unsigned int cnt;
-	int res;
+	u32 cnt;
+	s32 res;
 
 	cnt = hpet_read(HPET_COUNTER);
-	cnt += delta;
+	cnt += (u32) delta;
 	hpet_write(HPET_T0_CMP, cnt);
 
-	res = (int)(cnt - hpet_read(HPET_COUNTER));
+	res = (s32)(cnt - hpet_read(HPET_COUNTER));
 
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
@@ -230,7 +230,7 @@ void __init setup_hpet_timer(void)
 
 	cd = &per_cpu(hpet_clockevent_device, cpu);
 	cd->name = "hpet";
-	cd->rating = 320;
+	cd->rating = 100;
 	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	cd->set_state_shutdown = hpet_set_state_shutdown;
 	cd->set_state_periodic = hpet_set_state_periodic;
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index b4a837893562..5abe51cad899 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -65,7 +65,7 @@ static struct insn insn_table[] = {
 #ifndef CONFIG_CPU_MIPSR6
 	{ insn_cache,  M(cache_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 #else
-	{ insn_cache,  M6(cache_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
+	{ insn_cache,  M6(spec3_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
 #endif
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index c0ae62520d15..274d5bc6ecce 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -97,10 +97,10 @@
 #define	ENOTCONN	235	/* Transport endpoint is not connected */
 #define	ESHUTDOWN	236	/* Cannot send after transport endpoint shutdown */
 #define	ETOOMANYREFS	237	/* Too many references: cannot splice */
-#define EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
-#define EREMOTERELEASE	240	/* Remote peer released connection */
+#define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
+#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 9f8402b35115..27e588f6c72e 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -164,6 +164,7 @@ struct coprocessor_request_block {
 #define ICSWX_INITIATED		(0x8)
 #define ICSWX_BUSY		(0x4)
 #define ICSWX_REJECTED		(0x2)
+#define ICSWX_XERS0		(0x1)	/* undefined or set from XERSO. */
 
 static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
 {
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index b34e8a54f7db..98949b0df00a 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -677,7 +677,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 	/* Check if the request is finished successfully */
 	if (active_flag) {
 		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if (rc <= 0)
+		if (rc < 0)
 			return rc;
 
 		if (rc & active_flag)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index bf8f34a58670..b7019b559ddb 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
 	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
-	/* We need to setup MSR for VSX register save instructions.  Here we
-	 * also clear the MSR RI since when we do the treclaim, we won't have a
-	 * valid kernel pointer for a while.  We clear RI here as it avoids
-	 * adding another mtmsr closer to the treclaim.  This makes the region
-	 * maked as non-recoverable wider than it needs to be but it saves on
-	 * inserting another mtmsrd later.
-	 */
+	/* We need to setup MSR for VSX register save instructions. */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
-	li	r16, MSR_RI
+	li	r16, 0
 	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
 1:	tdeqi   r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* The moment we treclaim, ALL of our GPRs will switch
+	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	li	r4, 0
+	mtmsrd	r4, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 *
+	 * The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
 	 */
@@ -197,6 +201,11 @@ dont_backup_fp:
 
 	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
+
+	/* Reset MSR RI so we can take SLB faults again */
+	li	r11, MSR_RI
+	mtmsrd	r11, 1
+
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -397,11 +406,6 @@ restore_gprs:
 	ld	r5, THREAD_TM_DSCR(r3)
 	ld	r6, THREAD_TM_PPR(r3)
 
-	/* Clear the MSR RI since we are about to change R1.  EE is already off
-	 */
-	li	r4, 0
-	mtmsrd	r4, 1
-
 	REST_GPR(0, r7)				/* GPR0 */
 	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
 	ld	r6, _CCR(r7)
 	mtcr    r6
 
-	REST_GPR(1, r7)				/* GPR1 */
-	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
-	ld	r7, GPR7(r7)
+
+	/*
+	 * Store r1 and r5 on the stack so that we can access them
+	 * after we clear MSR RI.
+	 */
+
+	REST_GPR(5, r7)
+	std	r5, -8(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -16(r1)
+
+	REST_GPR(7, r7)
+
+	/* Clear MSR RI since we are about to change r1. EE is already off */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 */
+
+	ld	r5, -8(r1)
+	ld	r1, -16(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 463af88c95a2..974f73df00bb 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -655,112 +655,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	skip_tm
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-
-	/* Turn on TM/FP/VSX/VMX so we can restore them. */
-	mfmsr	r5
-	li	r6, MSR_TM >> 32
-	sldi	r6, r6, 32
-	or	r5, r5, r6
-	ori	r5, r5, MSR_FP
-	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
-	mtmsrd	r5
-
-	/*
-	 * The user may change these outside of a transaction, so they must
-	 * always be context switched.
-	 */
-	ld	r5, VCPU_TFHAR(r4)
-	ld	r6, VCPU_TFIAR(r4)
-	ld	r7, VCPU_TEXASR(r4)
-	mtspr	SPRN_TFHAR, r5
-	mtspr	SPRN_TFIAR, r6
-	mtspr	SPRN_TEXASR, r7
-
-	ld	r5, VCPU_MSR(r4)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	skip_tm	/* TM not active in guest */
-
-	/* Make sure the failure summary is set, otherwise we'll program check
-	 * when we trechkpt.  It's possible that this might have been not set
-	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
-	 * host.
-	 */
-	oris	r7, r7, (TEXASR_FS)@h
-	mtspr	SPRN_TEXASR, r7
-
-	/*
-	 * We need to load up the checkpointed state for the guest.
-	 * We need to do this early as it will blow away any GPRs, VSRs and
-	 * some SPRs.
-	 */
-
-	mr	r31, r4
-	addi	r3, r31, VCPU_FPRS_TM
-	bl	load_fp_state
-	addi	r3, r31, VCPU_VRS_TM
-	bl	load_vr_state
-	mr	r4, r31
-	lwz	r7, VCPU_VRSAVE_TM(r4)
-	mtspr	SPRN_VRSAVE, r7
-
-	ld	r5, VCPU_LR_TM(r4)
-	lwz	r6, VCPU_CR_TM(r4)
-	ld	r7, VCPU_CTR_TM(r4)
-	ld	r8, VCPU_AMR_TM(r4)
-	ld	r9, VCPU_TAR_TM(r4)
-	mtlr	r5
-	mtcr	r6
-	mtctr	r7
-	mtspr	SPRN_AMR, r8
-	mtspr	SPRN_TAR, r9
-
-	/*
-	 * Load up PPR and DSCR values but don't put them in the actual SPRs
-	 * till the last moment to avoid running with userspace PPR and DSCR for
-	 * too long.
-	 */
-	ld	r29, VCPU_DSCR_TM(r4)
-	ld	r30, VCPU_PPR_TM(r4)
-
-	std	r2, PACATMSCRATCH(r13) /* Save TOC */
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* Load GPRs r0-r28 */
-	reg = 0
-	.rept	29
-	ld	reg, VCPU_GPRS_TM(reg)(r31)
-	reg = reg + 1
-	.endr
-
-	mtspr	SPRN_DSCR, r29
-	mtspr	SPRN_PPR, r30
-
-	/* Load final GPRs */
-	ld	29, VCPU_GPRS_TM(29)(r31)
-	ld	30, VCPU_GPRS_TM(30)(r31)
-	ld	31, VCPU_GPRS_TM(31)(r31)
-
-	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
-	TRECHKPT
-
-	/* Now let's get back the state we need. */
-	HMT_MEDIUM
-	GET_PACA(r13)
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATMSCRATCH(r13)
-
-	/* Set the MSR RI since we have our registers back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-skip_tm:
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Load guest PMU registers */
@@ -841,12 +737,6 @@ BEGIN_FTR_SECTION
 	/* Skip next section on POWER7 */
 	b	8f
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
 	/* Load up POWER8-specific registers */
 	ld	r5, VCPU_IAMR(r4)
 	lwz	r6, VCPU_PSPB(r4)
@@ -1436,106 +1326,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	2f
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-	/* Turn on TM. */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
-	ld	r5, VCPU_MSR(r9)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	1f	/* TM not active in guest. */
-
-	li	r3, TM_CAUSE_KVM_RESCHED
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* All GPRs are volatile at this point. */
-	TRECLAIM(R3)
-
-	/* Temporarily store r13 and r9 so we have some regs to play with */
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	std	r9, PACATMSCRATCH(r13)
-	ld	r9, HSTATE_KVM_VCPU(r13)
-
-	/* Get a few more GPRs free. */
-	std	r29, VCPU_GPRS_TM(29)(r9)
-	std	r30, VCPU_GPRS_TM(30)(r9)
-	std	r31, VCPU_GPRS_TM(31)(r9)
-
-	/* Save away PPR and DSCR soon so don't run with user values. */
-	mfspr	r31, SPRN_PPR
-	HMT_MEDIUM
-	mfspr	r30, SPRN_DSCR
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-
-	/* Save all but r9, r13 & r29-r31 */
-	reg = 0
-	.rept	29
-	.if (reg != 9) && (reg != 13)
-	std	reg, VCPU_GPRS_TM(reg)(r9)
-	.endif
-	reg = reg + 1
-	.endr
-	/* ... now save r13 */
-	GET_SCRATCH0(r4)
-	std	r4, VCPU_GPRS_TM(13)(r9)
-	/* ... and save r9 */
-	ld	r4, PACATMSCRATCH(r13)
-	std	r4, VCPU_GPRS_TM(9)(r9)
-
-	/* Reload stack pointer and TOC. */
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
-
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	/* Save away checkpinted SPRs. */
-	std	r31, VCPU_PPR_TM(r9)
-	std	r30, VCPU_DSCR_TM(r9)
-	mflr	r5
-	mfcr	r6
-	mfctr	r7
-	mfspr	r8, SPRN_AMR
-	mfspr	r10, SPRN_TAR
-	std	r5, VCPU_LR_TM(r9)
-	stw	r6, VCPU_CR_TM(r9)
-	std	r7, VCPU_CTR_TM(r9)
-	std	r8, VCPU_AMR_TM(r9)
-	std	r10, VCPU_TAR_TM(r9)
-
-	/* Restore r12 as trap number. */
-	lwz	r12, VCPU_TRAP(r9)
-
-	/* Save FP/VSX. */
-	addi	r3, r9, VCPU_FPRS_TM
-	bl	store_fp_state
-	addi	r3, r9, VCPU_VRS_TM
-	bl	store_vr_state
-	mfspr	r6, SPRN_VRSAVE
-	stw	r6, VCPU_VRSAVE_TM(r9)
-1:
-	/*
-	 * We need to save these SPRs after the treclaim so that the software
-	 * error code is recorded correctly in the TEXASR.  Also the user may
-	 * change these outside of a transaction, so they must always be
-	 * context switched.
-	 */
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-2:
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Increment yield count if they have a VPA */
@@ -2245,6 +2037,13 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	/* save FP state */
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/*
 	 * Set DEC to the smaller of DEC and HDEC, so that we wake
 	 * no later than the end of our timeslice (HDEC interrupts
@@ -2321,6 +2120,12 @@ kvm_end_cede:
 	bl	kvmhv_accumulate_time
 #endif
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
@@ -2629,6 +2434,239 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mr	r4,r31
 	blr
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Save transactional state and TM-related registers.
+ * Called with r9 pointing to the vcpu struct.
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 and r9 (vcpu pointer) before exit.
+ */
+kvmppc_save_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	std	r1, HSTATE_HOST_R1(r13)
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with r4 pointing to the vcpu struct.
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2, r4 from the PACA.
+ */
+kvmppc_restore_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM/FP/VSX/VMX so we can restore them. */
+	mfmsr	r5
+	li	r6, MSR_TM >> 32
+	sldi	r6, r6, 32
+	or	r5, r5, r6
+	ori	r5, r5, MSR_FP
+	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
+	mtmsrd	r5
+
+	/*
+	 * The user may change these outside of a transaction, so they must
+	 * always be context switched.
+	 */
+	ld	r5, VCPU_TFHAR(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+
+	ld	r5, VCPU_MSR(r4)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beqlr		/* TM not active in guest */
+	std	r1, HSTATE_HOST_R1(r13)
+
+	/* Make sure the failure summary is set, otherwise we'll program check
+	 * when we trechkpt.  It's possible that this might have been not set
+	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+	 * host.
+	 */
+	oris	r7, r7, (TEXASR_FS)@h
+	mtspr	SPRN_TEXASR, r7
+
+	/*
+	 * We need to load up the checkpointed state for the guest.
+	 * We need to do this early as it will blow away any GPRs, VSRs and
+	 * some SPRs.
+	 */
+
+	mr	r31, r4
+	addi	r3, r31, VCPU_FPRS_TM
+	bl	load_fp_state
+	addi	r3, r31, VCPU_VRS_TM
+	bl	load_vr_state
+	mr	r4, r31
+	lwz	r7, VCPU_VRSAVE_TM(r4)
+	mtspr	SPRN_VRSAVE, r7
+
+	ld	r5, VCPU_LR_TM(r4)
+	lwz	r6, VCPU_CR_TM(r4)
+	ld	r7, VCPU_CTR_TM(r4)
+	ld	r8, VCPU_AMR_TM(r4)
+	ld	r9, VCPU_TAR_TM(r4)
+	mtlr	r5
+	mtcr	r6
+	mtctr	r7
+	mtspr	SPRN_AMR, r8
+	mtspr	SPRN_TAR, r9
+
+	/*
+	 * Load up PPR and DSCR values but don't put them in the actual SPRs
+	 * till the last moment to avoid running with userspace PPR and DSCR for
+	 * too long.
+	 */
+	ld	r29, VCPU_DSCR_TM(r4)
+	ld	r30, VCPU_PPR_TM(r4)
+
+	std	r2, PACATMSCRATCH(r13) /* Save TOC */
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* Load GPRs r0-r28 */
+	reg = 0
+	.rept	29
+	ld	reg, VCPU_GPRS_TM(reg)(r31)
+	reg = reg + 1
+	.endr
+
+	mtspr	SPRN_DSCR, r29
+	mtspr	SPRN_PPR, r30
+
+	/* Load final GPRs */
+	ld	29, VCPU_GPRS_TM(29)(r31)
+	ld	30, VCPU_GPRS_TM(30)(r31)
+	ld	31, VCPU_GPRS_TM(31)(r31)
+
+	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
+	TRECHKPT
+
+	/* Now let's get back the state we need. */
+	HMT_MEDIUM
+	GET_PACA(r13)
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATMSCRATCH(r13)
+
+	/* Set the MSR RI since we have our registers back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+#endif
+
 /*
  * We come here if we get any exception or interrupt while we are
  * executing host real mode code while in guest MMU context.
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index b8045b97f4fb..d750cc0dfe30 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -669,11 +669,13 @@ static const struct file_operations prng_tdes_fops = {
 static struct miscdevice prng_sha512_dev = {
 	.name	= "prandom",
 	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0644,
 	.fops	= &prng_sha512_fops,
 };
 static struct miscdevice prng_tdes_dev = {
 	.name	= "prandom",
 	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0644,
 	.fops	= &prng_tdes_fops,
 };
 
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 1aac41e83ea1..92df3eb8d14e 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -23,6 +23,8 @@ enum zpci_ioat_dtype {
 #define ZPCI_IOTA_FS_2G			2
 #define ZPCI_KEY			(PAGE_DEFAULT_KEY << 5)
 
+#define ZPCI_TABLE_SIZE_RT	(1UL << 42)
+
 #define ZPCI_IOTA_STO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
 #define ZPCI_IOTA_RTTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
 #define ZPCI_IOTA_RSTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 19442395f413..f2f6720a3331 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -701,8 +701,7 @@ static int zpci_restore(struct device *dev)
 		goto out;
 
 	zpci_map_resources(pdev);
-	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
-			   zdev->start_dma + zdev->iommu_size - 1,
+	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 			   (u64) zdev->dma_table);
 
 out:
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d348f2c09a1e..3a40f718baef 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -458,7 +458,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_clean;
 	}
 
-	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	/*
+	 * Restrict the iommu bitmap size to the minimum of the following:
+	 * - main memory size
+	 * - 3-level pagetable address limit minus start_dma offset
+	 * - DMA address range allowed by the hardware (clp query pci fn)
+	 *
+	 * Also set zdev->end_dma to the actual end address of the usable
+	 * range, instead of the theoretical maximum as reported by hardware.
+	 */
+	zdev->iommu_size = min3((u64) high_memory,
+				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
+				zdev->end_dma - zdev->start_dma + 1);
+	zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
 	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
@@ -466,10 +478,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_reg;
 	}
 
-	rc = zpci_register_ioat(zdev,
-				0,
-				zdev->start_dma + PAGE_OFFSET,
-				zdev->start_dma + zdev->iommu_size - 1,
+	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
 		goto out_reg;
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index 1dd5bd8a8c59..133055311dce 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -81,7 +81,7 @@
   .altinstr_replacement : { *(.altinstr_replacement) }
   /* .exit.text is discard at runtime, not link time, to deal with references
      from .altinstructions and .eh_frame */
-  .exit.text : { *(.exit.text) }
+  .exit.text : { EXIT_TEXT }
   .exit.data : { *(.exit.data) }
 
   .preinit_array : {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6df2029405a3..3142218e546f 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -86,7 +86,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 static inline void __native_flush_tlb(void)
 {
+	/*
+	 * If current->mm == NULL then we borrow a mm which may change during a
+	 * task switch and therefore we must not be preempted while we write CR3
+	 * back:
+	 */
+	preempt_disable();
 	native_write_cr3(native_read_cr3());
+	preempt_enable();
 }
 
 static inline void __native_flush_tlb_global_irq_disabled(void)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2f69e3b184f6..a3e1f8497f8c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1587,6 +1587,9 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	int ret, ir_stat;
 
+	if (skip_ioapic_setup)
+		return;
+
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
 		return;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 20e242ea1bc4..cfc4a966e2b9 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static unsigned char hv_get_nmi_reason(void)
+{
+	return 0;
+}
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 	mark_tsc_unstable("running on Hyper-V");
+
+	/*
+	 * Generation 2 instances don't support reading the NMI status from
+	 * 0x61 port.
+	 */
+	if (efi_enabled(EFI_BOOT))
+		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index a316ca96f1b6..fc704ed587e8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -211,6 +211,20 @@ static void __put_rmid(u32 rmid)
 	list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
 }
 
+static void cqm_cleanup(void)
+{
+	int i;
+
+	if (!cqm_rmid_ptrs)
+		return;
+
+	for (i = 0; i < cqm_max_rmid; i++)
+		kfree(cqm_rmid_ptrs[i]);
+
+	kfree(cqm_rmid_ptrs);
+	cqm_rmid_ptrs = NULL;
+}
+
 static int intel_cqm_setup_rmid_cache(void)
 {
 	struct cqm_rmid_entry *entry;
@@ -218,7 +232,7 @@ static int intel_cqm_setup_rmid_cache(void)
 	int r = 0;
 
 	nr_rmids = cqm_max_rmid + 1;
-	cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+	cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) *
 				nr_rmids, GFP_KERNEL);
 	if (!cqm_rmid_ptrs)
 		return -ENOMEM;
@@ -249,11 +263,9 @@ static int intel_cqm_setup_rmid_cache(void)
 	mutex_unlock(&cache_mutex);
 
 	return 0;
-fail:
-	while (r--)
-		kfree(cqm_rmid_ptrs[r]);
 
-	kfree(cqm_rmid_ptrs);
+fail:
+	cqm_cleanup();
 	return -ENOMEM;
 }
 
@@ -281,9 +293,13 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 
 	/*
 	 * Events that target same task are placed into the same cache group.
+	 * Mark it as a multi event group, so that we update ->count
+	 * for every event rather than just the group leader later.
 	 */
-	if (a->hw.target == b->hw.target)
+	if (a->hw.target == b->hw.target) {
+		b->hw.is_group_event = true;
 		return true;
+	}
 
 	/*
 	 * Are we an inherited event?
@@ -849,6 +865,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 	bool conflict = false;
 	u32 rmid;
 
+	event->hw.is_group_event = false;
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
 
@@ -940,7 +957,9 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 		return __perf_event_count(event);
 
 	/*
-	 * Only the group leader gets to report values. This stops us
+	 * Only the group leader gets to report values except in case of
+	 * multiple events in the same group, we still need to read the
+	 * other events.This stops us
 	 * reporting duplicate values to userspace, and gives us a clear
 	 * rule for which task gets to report the values.
 	 *
@@ -948,7 +967,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 	 * specific packages - we forfeit that ability when we create
 	 * task events.
 	 */
-	if (!cqm_group_leader(event))
+	if (!cqm_group_leader(event) && !event->hw.is_group_event)
 		return 0;
 
 	/*
@@ -1315,7 +1334,7 @@ static const struct x86_cpu_id intel_cqm_match[] = {
 
 static int __init intel_cqm_init(void)
 {
-	char *str, scale[20];
+	char *str = NULL, scale[20];
 	int i, cpu, ret;
 
 	if (!x86_match_cpu(intel_cqm_match))
@@ -1375,16 +1394,25 @@ static int __init intel_cqm_init(void)
 		cqm_pick_event_reader(i);
 	}
 
-	__perf_cpu_notifier(intel_cqm_cpu_notifier);
-
 	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
-	if (ret)
+	if (ret) {
 		pr_err("Intel CQM perf registration failed: %d\n", ret);
-	else
-		pr_info("Intel CQM monitoring enabled\n");
+		goto out;
+	}
+
+	pr_info("Intel CQM monitoring enabled\n");
 
+	/*
+	 * Register the hot cpu notifier once we are sure cqm
+	 * is enabled to avoid notifier leak.
+	 */
+	__perf_cpu_notifier(intel_cqm_cpu_notifier);
 out:
 	cpu_notifier_register_done();
+	if (ret) {
+		kfree(str);
+		cqm_cleanup();
+	}
 
 	return ret;
 }
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index bf4db6eaec8f..c6aace2bbe08 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 		*cursor &= 0xfe;
 	}
 	/*
-	 * Similar treatment for VEX3 prefix.
-	 * TODO: add XOP/EVEX treatment when insn decoder supports them
+	 * Similar treatment for VEX3/EVEX prefix.
+	 * TODO: add XOP treatment when insn decoder supports them
 	 */
-	if (insn->vex_prefix.nbytes == 3) {
+	if (insn->vex_prefix.nbytes >= 3) {
 		/*
 		 * vex2:     c5    rvvvvLpp   (has no b bit)
 		 * vex3/xop: c4/8f rxbmmmmm wvvvvLpp
 		 * evex:     62    rxbR00mm wvvvv1pp zllBVaaa
-		 *   (evex will need setting of both b and x since
-		 *   in non-sib encoding evex.x is 4th bit of MODRM.rm)
-		 * Setting VEX3.b (setting because it has inverted meaning):
+		 * Setting VEX3.b (setting because it has inverted meaning).
+		 * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+		 * is the 4th bit of MODRM.rm, and needs the same treatment.
+		 * For VEX3-encoded insns, VEX3.x value has no effect in
+		 * non-SIB encoding, the change is superfluous but harmless.
 		 */
 		cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
-		*cursor |= 0x20;
+		*cursor |= 0x60;
 	}
 
 	/*
@@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 
 	reg = MODRM_REG(insn);	/* Fetch modrm.reg */
 	reg2 = 0xff;		/* Fetch vex.vvvv */
-	if (insn->vex_prefix.nbytes == 2)
-		reg2 = insn->vex_prefix.bytes[1];
-	else if (insn->vex_prefix.nbytes == 3)
+	if (insn->vex_prefix.nbytes)
 		reg2 = insn->vex_prefix.bytes[2];
 	/*
-	 * TODO: add XOP, EXEV vvvv reading.
+	 * TODO: add XOP vvvv reading.
 	 *
 	 * vex.vvvv field is in bits 6-3, bits are inverted.
 	 * But in 32-bit mode, high-order bit may be ignored.
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index c146f3c262c3..0149ac59c273 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -539,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
 
 	iter->fixed = false;
 	iter->start_max = iter->start;
+	iter->range = NULL;
 	iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
 
 	__mtrr_lookup_var_next(iter);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 41e7943004fe..4589b6feeb7b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8124,6 +8124,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8736,6 +8737,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8744,8 +8761,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 		vmx_destroy_pml_buffer(vmx);
 	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
-	vmx_load_vmcs01(vcpu);
-	free_nested(vmx);
+	vmx_free_vcpu_nested(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 8b93e634af84..ae97f24a4371 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -37,6 +37,7 @@
 
 /* Quirks for the listed devices */
 #define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
+#define PCI_DEVICE_ID_INTEL_MRFL_HSU	0x1191
 
 /* Fixed BAR fields */
 #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00	/* Fixed BAR (TBD) */
@@ -225,13 +226,20 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 		/* Special treatment for IRQ0 */
 		if (dev->irq == 0) {
 			/*
+			 * Skip HS UART common registers device since it has
+			 * IRQ0 assigned and not used by the kernel.
+			 */
+			if (dev->device == PCI_DEVICE_ID_INTEL_MRFL_HSU)
+				return -EBUSY;
+			/*
 			 * TNG has IRQ0 assigned to eMMC controller. But there
 			 * are also other devices with bogus PCI configuration
 			 * that have IRQ0 assigned. This check ensures that
-			 * eMMC gets it.
+			 * eMMC gets it. The rest of devices still could be
+			 * enabled without interrupt line being allocated.
 			 */
 			if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
-				return -EBUSY;
+				return 0;
 		}
 		break;
 	default: