Merge branches 'misc' and 'sa1111-base' into for-linus

author: Russell King <rmk+kernel@armlinux.org.uk> 2016-10-06 08:56:43 +0100
committer: Russell King <rmk+kernel@armlinux.org.uk> 2016-10-06 08:56:43 +0100
commit: 301a36fa700f9add6e14f5a95c7573e01578343a (patch)
tree: 6ff94ff3b08b838353b9127eb5f8055b3de6b25f /arch
parent: b828f960215f02e5d2c88bbd27565c694254a15a (diff)
parent: b60752f2b20c167859943e001727f0d4da419b23 (diff)
311 files changed, 2355 insertions, 1540 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index bd8056b5b246..fd6e9712af81 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -336,17 +336,6 @@ config HAVE_ARCH_SECCOMP_FILTER
 	    results in the system call being skipped immediately.
 	  - seccomp syscall wired up
 
-	  For best performance, an arch should use seccomp_phase1 and
-	  seccomp_phase2 directly.  It should call seccomp_phase1 for all
-	  syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not
-	  need to be called from a ptrace-safe context.  It must then
-	  call seccomp_phase2 if seccomp_phase1 returns anything other
-	  than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP.
-
-	  As an additional optimization, an arch may provide seccomp_data
-	  directly to seccomp_phase1; this avoids multiple calls
-	  to the syscall_xyz helpers for every syscall.
-
 config SECCOMP_FILTER
 	def_bool y
 	depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
@@ -461,6 +450,15 @@ config CC_STACKPROTECTOR_STRONG
 
 endchoice
 
+config HAVE_ARCH_WITHIN_STACK_FRAMES
+	bool
+	help
+	  An architecture should select this if it can walk the kernel stack
+	  frames to determine if an object is part of either the arguments
+	  or local variables (i.e. that it excludes saved return addresses,
+	  and similar) by implementing an inline arch_within_stack_frames(),
+	  which is used by CONFIG_HARDENED_USERCOPY.
+
 config HAVE_CONTEXT_TRACKING
 	bool
 	help
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index c419b43c461d..466e42e96bfa 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -371,14 +371,6 @@ __copy_tofrom_user_nocheck(void *to, const void *from, long len)
 	return __cu_len;
 }
 
-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
-	if (__access_ok((unsigned long)validate, len, get_fs()))
-		len = __copy_tofrom_user_nocheck(to, from, len);
-	return len;
-}
-
 #define __copy_to_user(to, from, n)					\
 ({									\
 	__chk_user_ptr(to);						\
@@ -393,17 +385,22 @@ __copy_tofrom_user(void *to, const void *from, long len, const void __user *vali
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
-
 extern inline long
 copy_to_user(void __user *to, const void *from, long n)
 {
-	return __copy_tofrom_user((__force void *)to, from, n, to);
+	if (likely(__access_ok((unsigned long)to, n, get_fs())))
+		n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+	return n;
 }
 
 extern inline long
 copy_from_user(void *to, const void __user *from, long n)
 {
-	return __copy_tofrom_user(to, (__force void *)from, n, from);
+	if (likely(__access_ok((unsigned long)from, n, get_fs())))
+		n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+	else
+		memset(to, 0, n);
+	return n;
 }
 
 extern void __do_clear_user(void);
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 0f92d97432a2..89eeb3720051 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
-#define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index a78d5670884f..41faf17cd28d 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -83,7 +83,10 @@
 	"2:	;nop\n"				\
 	"	.section .fixup, \"ax\"\n"	\
 	"	.align 4\n"			\
-	"3:	mov %0, %3\n"			\
+	"3:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
 	"	j   2b\n"			\
 	"	.previous\n"			\
 	"	.section __ex_table, \"a\"\n"	\
@@ -101,7 +104,11 @@
 	"2:	;nop\n"				\
 	"	.section .fixup, \"ax\"\n"	\
 	"	.align 4\n"			\
-	"3:	mov %0, %3\n"			\
+	"3:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
+	"	mov %R1, 0\n"			\
 	"	j   2b\n"			\
 	"	.previous\n"			\
 	"	.section __ex_table, \"a\"\n"	\
diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h
index 0f99ac8fcbb2..0037a587320d 100644
--- a/arch/arc/include/uapi/asm/elf.h
+++ b/arch/arc/include/uapi/asm/elf.h
@@ -13,8 +13,15 @@
 
 /* Machine specific ELF Hdr flags */
 #define EF_ARC_OSABI_MSK	0x00000f00
-#define EF_ARC_OSABI_ORIG	0x00000000   /* MUST be zero for back-compat */
-#define EF_ARC_OSABI_CURRENT	0x00000300   /* v3 (no legacy syscalls) */
+
+#define EF_ARC_OSABI_V3		0x00000300   /* v3 (no legacy syscalls) */
+#define EF_ARC_OSABI_V4		0x00000400   /* v4 (64bit data any reg align) */
+
+#if __GNUC__ < 6
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V3
+#else
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V4
+#endif
 
 typedef unsigned long elf_greg_t;
 typedef unsigned long elf_fpregset_t;
diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c
index 4d9e77724bed..000dd041ab42 100644
--- a/arch/arc/kernel/arcksyms.c
+++ b/arch/arc/kernel/arcksyms.c
@@ -28,6 +28,7 @@ extern void __muldf3(void);
 extern void __divdf3(void);
 extern void __floatunsidf(void);
 extern void __floatunsisf(void);
+extern void __udivdi3(void);
 
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
@@ -45,6 +46,7 @@ EXPORT_SYMBOL(__muldf3);
 EXPORT_SYMBOL(__divdf3);
 EXPORT_SYMBOL(__floatunsidf);
 EXPORT_SYMBOL(__floatunsisf);
+EXPORT_SYMBOL(__udivdi3);
 
 /* ARC optimised assembler routines */
 EXPORT_SYMBOL(memset);
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index b5db9e7fd649..be1972bd2729 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -199,7 +199,7 @@ int elf_check_arch(const struct elf32_hdr *x)
 	}
 
 	eflags = x->e_flags;
-	if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
+	if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) {
 		pr_err("ABI mismatch - you need newer toolchain\n");
 		force_sigsegv(SIGSEGV, current);
 		return 0;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index a946400a86d0..f52a0d0dc462 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -291,8 +291,10 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 			       cpu->dccm.base_addr, TO_KB(cpu->dccm.sz),
 			       cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
 
-	n += scnprintf(buf + n, len - n,
-		       "OS ABI [v3]\t: no-legacy-syscalls\n");
+	n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
+			EF_ARC_OSABI_CURRENT >> 8,
+			EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
+			"no-legacy-syscalls" : "64-bit data any register aligned");
 
 	return buf;
 }
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 5a294b2c3cb3..0b10efe3a6a7 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -921,6 +921,15 @@ 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/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 04f83322c9fd..77ff64a874a1 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -61,6 +61,7 @@ void *kmap(struct page *page)
 
 	return kmap_high(page);
 }
+EXPORT_SYMBOL(kmap);
 
 void *kmap_atomic(struct page *page)
 {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2d601d769a1c..a9c4e48bb7ec 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -35,6 +35,7 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
+	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 6e30b8bc21b9..6be9ee148b78 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -259,12 +259,14 @@ machdirs := $(patsubst %,arch/arm/mach-%/,$(machine-y))
 platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y)))
 
 ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y)
+ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y)
 ifeq ($(KBUILD_SRC),)
 KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs))
 else
 KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs))
 endif
 endif
+endif
 
 export	TEXT_OFFSET GZFLAGS MMUEXT
 
diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi
index c8609d8d2c55..b689172632ef 100644
--- a/arch/arm/boot/dts/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/am335x-baltos.dtsi
@@ -226,7 +226,7 @@
 
 		#address-cells = <1>;
 		#size-cells = <1>;
-		elm_id = <&elm>;
+		ti,elm-id = <&elm>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/am335x-igep0033.dtsi b/arch/arm/boot/dts/am335x-igep0033.dtsi
index df63484ef9b3..e7d9ca1305fa 100644
--- a/arch/arm/boot/dts/am335x-igep0033.dtsi
+++ b/arch/arm/boot/dts/am335x-igep0033.dtsi
@@ -161,7 +161,7 @@
 
 		#address-cells = <1>;
 		#size-cells = <1>;
-		elm_id = <&elm>;
+		ti,elm-id = <&elm>;
 
 		/* MTD partition table */
 		partition@0 {
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
index 86f773165d5c..1263c9d4cba3 100644
--- a/arch/arm/boot/dts/am335x-phycore-som.dtsi
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -197,7 +197,7 @@
 		gpmc,wr-access-ns = <30>;
 		gpmc,wr-data-mux-bus-ns = <0>;
 
-		elm_id = <&elm>;
+		ti,elm-id = <&elm>;
 
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm/boot/dts/arm-realview-pbx-a9.dts b/arch/arm/boot/dts/arm-realview-pbx-a9.dts
index db808f92dd79..90d00b407f85 100644
--- a/arch/arm/boot/dts/arm-realview-pbx-a9.dts
+++ b/arch/arm/boot/dts/arm-realview-pbx-a9.dts
@@ -70,13 +70,12 @@
 		 * associativity as these may be erroneously set
 		 * up by boot loader(s).
 		 */
-		cache-size = <1048576>; // 1MB
-		cache-sets = <4096>;
+		cache-size = <131072>; // 128KB
+		cache-sets = <512>;
 		cache-line-size = <32>;
 		arm,parity-disable;
-		arm,tag-latency = <1>;
-		arm,data-latency = <1 1>;
-		arm,dirty-latency = <1>;
+		arm,tag-latency = <1 1 1>;
+		arm,data-latency = <1 1 1>;
 	};
 
 	scu: scu@1f000000 {
diff --git a/arch/arm/boot/dts/armada-388-clearfog.dts b/arch/arm/boot/dts/armada-388-clearfog.dts
index 2e0556af6e5e..d3e6bd805006 100644
--- a/arch/arm/boot/dts/armada-388-clearfog.dts
+++ b/arch/arm/boot/dts/armada-388-clearfog.dts
@@ -390,12 +390,12 @@
 
 			port@0 {
 				reg = <0>;
-				label = "lan1";
+				label = "lan5";
 			};
 
 			port@1 {
 				reg = <1>;
-				label = "lan2";
+				label = "lan4";
 			};
 
 			port@2 {
@@ -405,12 +405,12 @@
 
 			port@3 {
 				reg = <3>;
-				label = "lan4";
+				label = "lan2";
 			};
 
 			port@4 {
 				reg = <4>;
-				label = "lan5";
+				label = "lan1";
 			};
 
 			port@5 {
diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index caf2707680c1..e9b47b2bbc33 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -2,6 +2,7 @@
 
 / {
 	memory {
+		device_type = "memory";
 		reg = <0 0x10000000>;
 	};
 
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index b98252232d20..445624a1a1de 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -2,7 +2,6 @@
 #include <dt-bindings/clock/bcm2835.h>
 #include <dt-bindings/clock/bcm2835-aux.h>
 #include <dt-bindings/gpio/gpio.h>
-#include "skeleton.dtsi"
 
 /* This include file covers the common peripherals and configuration between
  * bcm2835 and bcm2836 implementations, leaving the CPU configuration to
@@ -13,6 +12,8 @@
 	compatible = "brcm,bcm2835";
 	model = "BCM2835";
 	interrupt-parent = <&intc>;
+	#address-cells = <1>;
+	#size-cells = <1>;
 
 	chosen {
 		bootargs = "earlyprintk console=ttyAMA0";
diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts
index d9499310a301..f6d135245a4b 100644
--- a/arch/arm/boot/dts/exynos5410-odroidxu.dts
+++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts
@@ -447,14 +447,11 @@
 	samsung,dw-mshc-ciu-div = <3>;
 	samsung,dw-mshc-sdr-timing = <0 4>;
 	samsung,dw-mshc-ddr-timing = <0 2>;
-	samsung,dw-mshc-hs400-timing = <0 2>;
-	samsung,read-strobe-delay = <90>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus1 &sd0_bus4 &sd0_bus8 &sd0_cd>;
 	bus-width = <8>;
 	cap-mmc-highspeed;
 	mmc-hs200-1_8v;
-	mmc-hs400-1_8v;
 	vmmc-supply = <&ldo20_reg>;
 	vqmmc-supply = <&ldo11_reg>;
 };
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index b620ac884cfd..b13b0b2db881 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -243,7 +243,7 @@
 					clocks = <&clks IMX6QDL_CLK_SPDIF_GCLK>, <&clks IMX6QDL_CLK_OSC>,
 						 <&clks IMX6QDL_CLK_SPDIF>, <&clks IMX6QDL_CLK_ASRC>,
 						 <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_ESAI_EXTAL>,
-						 <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_MLB>,
+						 <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_DUMMY>,
 						 <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_SPBA>;
 					clock-names = "core",  "rxtx0",
 						      "rxtx1", "rxtx2",
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 96ea936eeeb0..240a2864d044 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -64,7 +64,7 @@
 	cd-gpios = <&gpio7 11 GPIO_ACTIVE_LOW>;
 	no-1-8-v;
 	keep-power-in-suspend;
-	enable-sdio-wakup;
+	wakeup-source;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index 95ee268ed510..2f33c463cbce 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -131,7 +131,7 @@
 		ti,y-min = /bits/ 16 <0>;
 		ti,y-max = /bits/ 16 <0>;
 		ti,pressure-max = /bits/ 16 <0>;
-		ti,x-plat-ohms = /bits/ 16 <400>;
+		ti,x-plate-ohms = /bits/ 16 <400>;
 		wakeup-source;
 	};
 };
diff --git a/arch/arm/boot/dts/integratorap.dts b/arch/arm/boot/dts/integratorap.dts
index cf06e32ee108..4b34b54e09a1 100644
--- a/arch/arm/boot/dts/integratorap.dts
+++ b/arch/arm/boot/dts/integratorap.dts
@@ -42,7 +42,7 @@
 	};
 
 	syscon {
-		compatible = "arm,integrator-ap-syscon";
+		compatible = "arm,integrator-ap-syscon", "syscon";
 		reg = <0x11000000 0x100>;
 		interrupt-parent = <&pic>;
 		/* These are the logical module IRQs */
diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts
index d43f15b4f79a..79430fbfec3b 100644
--- a/arch/arm/boot/dts/integratorcp.dts
+++ b/arch/arm/boot/dts/integratorcp.dts
@@ -94,7 +94,7 @@
 	};
 
 	syscon {
-		compatible = "arm,integrator-cp-syscon";
+		compatible = "arm,integrator-cp-syscon", "syscon";
 		reg = <0xcb000000 0x100>;
 	};
 
diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi
index 00cb314d5e4d..e23f46d15c80 100644
--- a/arch/arm/boot/dts/keystone.dtsi
+++ b/arch/arm/boot/dts/keystone.dtsi
@@ -70,14 +70,6 @@
 		cpu_on		= <0x84000003>;
 	};
 
-	psci {
-		compatible	= "arm,psci";
-		method		= "smc";
-		cpu_suspend	= <0x84000001>;
-		cpu_off		= <0x84000002>;
-		cpu_on		= <0x84000003>;
-	};
-
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts
index ef84d8699a76..5bf62897014c 100644
--- a/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts
@@ -113,7 +113,7 @@
 
 	partition@e0000 {
 		label = "u-boot environment";
-		reg = <0xe0000 0x100000>;
+		reg = <0xe0000 0x20000>;
 	};
 
 	partition@100000 {
diff --git a/arch/arm/boot/dts/kirkwood-openrd.dtsi b/arch/arm/boot/dts/kirkwood-openrd.dtsi
index e4ecab112601..7175511a92da 100644
--- a/arch/arm/boot/dts/kirkwood-openrd.dtsi
+++ b/arch/arm/boot/dts/kirkwood-openrd.dtsi
@@ -116,6 +116,10 @@
 	};
 };
 
+&pciec {
+	status = "okay";
+};
+
 &pcie0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 365f39ff58bb..0ff1c2de95bf 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -35,10 +35,15 @@
 	ranges = <0 0 0x00000000 0x1000000>;	/* CS0: 16MB for NAND */
 
 	nand@0,0 {
-		linux,mtd-name = "micron,mt29f4g16abbda3w";
+		compatible = "ti,omap2-nand";
 		reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
+		interrupt-parent = <&gpmc>;
+		interrupts = <0 IRQ_TYPE_NONE>, /* fifoevent */
+			     <1 IRQ_TYPE_NONE>;	/* termcount */
+		linux,mtd-name = "micron,mt29f4g16abbda3w";
 		nand-bus-width = <16>;
 		ti,nand-ecc-opt = "bch8";
+		rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
 		gpmc,sync-clk-ps = <0>;
 		gpmc,cs-on-ns = <0>;
 		gpmc,cs-rd-off-ns = <44>;
@@ -54,10 +59,6 @@
 		gpmc,wr-access-ns = <40>;
 		gpmc,wr-data-mux-bus-ns = <0>;
 		gpmc,device-width = <2>;
-
-		gpmc,page-burst-access-ns = <5>;
-		gpmc,cycle2cycle-delay-ns = <50>;
-
 		#address-cells = <1>;
 		#size-cells = <1>;
 
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 5e9a13c0eaf7..1c2c74655416 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -46,6 +46,7 @@
 		linux,mtd-name = "micron,mt29f4g16abbda3w";
 		nand-bus-width = <16>;
 		ti,nand-ecc-opt = "bch8";
+		rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
 		gpmc,sync-clk-ps = <0>;
 		gpmc,cs-on-ns = <0>;
 		gpmc,cs-rd-off-ns = <44>;
diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi
index de256fa8da48..3e946cac55f3 100644
--- a/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-base.dtsi
@@ -223,7 +223,9 @@
 };
 
 &gpmc {
-	ranges = <0 0 0x00000000 0x20000000>;
+	ranges = <0 0 0x30000000 0x1000000>,	/* CS0 */
+		 <4 0 0x2b000000 0x1000000>,	/* CS4 */
+		 <5 0 0x2c000000 0x1000000>;	/* CS5 */
 
 	nand@0,0 {
 		compatible = "ti,omap2-nand";
diff --git a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
index 7df27926ead2..4f4c6efbd518 100644
--- a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
@@ -55,8 +55,6 @@
 #include "omap-gpmc-smsc9221.dtsi"
 
 &gpmc {
-	ranges = <5 0 0x2c000000 0x1000000>;	/* CS5 */
-
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 9e24b6a1d07b..1b304e2f1bd2 100644
--- a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
@@ -27,8 +27,6 @@
 #include "omap-gpmc-smsc9221.dtsi"
 
 &gpmc {
-	ranges = <5 0 0x2c000000 0x1000000>;	/* CS5 */
-
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
index 334109e14613..82e98ee3023a 100644
--- a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
@@ -15,9 +15,6 @@
 #include "omap-gpmc-smsc9221.dtsi"
 
 &gpmc {
-	ranges = <4 0 0x2b000000 0x1000000>,	/* CS4 */
-		 <5 0 0x2c000000 0x1000000>;	/* CS5 */
-
 	smsc1: ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/rk3066a.dtsi b/arch/arm/boot/dts/rk3066a.dtsi
index c0ba86c3a2ab..0d0dae3a1694 100644
--- a/arch/arm/boot/dts/rk3066a.dtsi
+++ b/arch/arm/boot/dts/rk3066a.dtsi
@@ -197,6 +197,8 @@
 		clock-names = "saradc", "apb_pclk";
 		interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
 		#io-channel-cells = <1>;
+		resets = <&cru SRST_SARADC>;
+		reset-names = "saradc-apb";
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index cd33f0170890..91c4b3c7a8d5 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -279,6 +279,8 @@
 		#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";
 	};
 
diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi
index 99bbcc2c9b89..e2cd683b4e4b 100644
--- a/arch/arm/boot/dts/rk3xxx.dtsi
+++ b/arch/arm/boot/dts/rk3xxx.dtsi
@@ -399,6 +399,8 @@
 		#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";
 	};
 
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index d294e82447a2..8b063ab10c19 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -550,8 +550,9 @@
 			interrupt-names = "mmcirq";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_mmc0>;
-			clock-names = "mmc";
-			clocks = <&clk_s_c0_flexgen CLK_MMC_0>;
+			clock-names = "mmc", "icn";
+			clocks = <&clk_s_c0_flexgen CLK_MMC_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
 			bus-width = <8>;
 			non-removable;
 		};
@@ -565,8 +566,9 @@
 			interrupt-names = "mmcirq";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_sd1>;
-			clock-names = "mmc";
-			clocks = <&clk_s_c0_flexgen CLK_MMC_1>;
+			clock-names = "mmc", "icn";
+			clocks = <&clk_s_c0_flexgen CLK_MMC_1>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
 			resets = <&softreset STIH407_MMC1_SOFTRESET>;
 			bus-width = <4>;
 		};
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index 18ed1ad10d32..40318869c733 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -41,7 +41,8 @@
 			compatible = "st,st-ohci-300x";
 			reg = <0x9a03c00 0x100>;
 			interrupts = <GIC_SPI 180 IRQ_TYPE_NONE>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT0_SOFTRESET>;
 			reset-names = "power", "softreset";
@@ -57,7 +58,8 @@
 			interrupts = <GIC_SPI 151 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb0>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT0_SOFTRESET>;
 			reset-names = "power", "softreset";
@@ -71,7 +73,8 @@
 			compatible = "st,st-ohci-300x";
 			reg = <0x9a83c00 0x100>;
 			interrupts = <GIC_SPI 181 IRQ_TYPE_NONE>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT1_SOFTRESET>;
 			reset-names = "power", "softreset";
@@ -87,7 +90,8 @@
 			interrupts = <GIC_SPI 153 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb1>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT1_SOFTRESET>;
 			reset-names = "power", "softreset";
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index e012890e0cf2..a17ba0243db3 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -84,7 +84,7 @@
 			trips {
 				cpu_alert0: cpu_alert0 {
 					/* milliCelsius */
-					temperature = <850000>;
+					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
diff --git a/arch/arm/boot/dts/tegra114-dalmore.dts b/arch/arm/boot/dts/tegra114-dalmore.dts
index 1dfc492cc004..1444fbd543e7 100644
--- a/arch/arm/boot/dts/tegra114-dalmore.dts
+++ b/arch/arm/boot/dts/tegra114-dalmore.dts
@@ -897,7 +897,7 @@
 		palmas: tps65913@58 {
 			compatible = "ti,palmas";
 			reg = <0x58>;
-			interrupts = <0 86 IRQ_TYPE_LEVEL_LOW>;
+			interrupts = <0 86 IRQ_TYPE_LEVEL_HIGH>;
 
 			#interrupt-cells = <2>;
 			interrupt-controller;
diff --git a/arch/arm/boot/dts/tegra114-roth.dts b/arch/arm/boot/dts/tegra114-roth.dts
index 70cf40996c3f..966a7fc044af 100644
--- a/arch/arm/boot/dts/tegra114-roth.dts
+++ b/arch/arm/boot/dts/tegra114-roth.dts
@@ -802,7 +802,7 @@
 		palmas: pmic@58 {
 			compatible = "ti,palmas";
 			reg = <0x58>;
-			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 
 			#interrupt-cells = <2>;
 			interrupt-controller;
diff --git a/arch/arm/boot/dts/tegra114-tn7.dts b/arch/arm/boot/dts/tegra114-tn7.dts
index 17dd14545862..a161fa1dfb61 100644
--- a/arch/arm/boot/dts/tegra114-tn7.dts
+++ b/arch/arm/boot/dts/tegra114-tn7.dts
@@ -63,7 +63,7 @@
 		palmas: pmic@58 {
 			compatible = "ti,palmas";
 			reg = <0x58>;
-			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 
 			#interrupt-cells = <2>;
 			interrupt-controller;
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 0e97b4b871f9..6c7b06854fce 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -140,7 +140,7 @@ static struct locomo_dev_info locomo_devices[] = {
 
 static void locomo_handler(struct irq_desc *desc)
 {
-	struct locomo *lchip = irq_desc_get_chip_data(desc);
+	struct locomo *lchip = irq_desc_get_handler_data(desc);
 	int req, i;
 
 	/* Acknowledge the parent IRQ */
@@ -200,8 +200,7 @@ static void locomo_setup_irq(struct locomo *lchip)
 	 * Install handler for IRQ_LOCOMO_HW.
 	 */
 	irq_set_irq_type(lchip->irq, IRQ_TYPE_EDGE_FALLING);
-	irq_set_chip_data(lchip->irq, lchip);
-	irq_set_chained_handler(lchip->irq, locomo_handler);
+	irq_set_chained_handler_and_data(lchip->irq, locomo_handler, lchip);
 
 	/* Install handlers for IRQ_LOCOMO_* */
 	for ( ; irq <= lchip->irq_base + 3; irq++) {
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index fb0a0a4dfea4..4ecd5120fce7 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -15,6 +15,7 @@
  * from machine specific code with proper arguments when required.
  */
 #include <linux/module.h>
+#include <linux/gpio/driver.h>
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
@@ -107,6 +108,7 @@ struct sa1111 {
 	spinlock_t	lock;
 	void __iomem	*base;
 	struct sa1111_platform_data *pdata;
+	struct gpio_chip gc;
 #ifdef CONFIG_PM
 	void		*saved_state;
 #endif
@@ -231,132 +233,44 @@ static void sa1111_irq_handler(struct irq_desc *desc)
 #define SA1111_IRQMASK_LO(x)	(1 << (x - sachip->irq_base))
 #define SA1111_IRQMASK_HI(x)	(1 << (x - sachip->irq_base - 32))
 
-static void sa1111_ack_irq(struct irq_data *d)
-{
-}
-
-static void sa1111_mask_lowirq(struct irq_data *d)
+static u32 sa1111_irqmask(struct irq_data *d)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned long ie0;
 
-	ie0 = sa1111_readl(mapbase + SA1111_INTEN0);
-	ie0 &= ~SA1111_IRQMASK_LO(d->irq);
-	writel(ie0, mapbase + SA1111_INTEN0);
+	return BIT((d->irq - sachip->irq_base) & 31);
 }
 
-static void sa1111_unmask_lowirq(struct irq_data *d)
+static int sa1111_irqbank(struct irq_data *d)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned long ie0;
 
-	ie0 = sa1111_readl(mapbase + SA1111_INTEN0);
-	ie0 |= SA1111_IRQMASK_LO(d->irq);
-	sa1111_writel(ie0, mapbase + SA1111_INTEN0);
+	return ((d->irq - sachip->irq_base) / 32) * 4;
 }
 
-/*
- * Attempt to re-trigger the interrupt.  The SA1111 contains a register
- * (INTSET) which claims to do this.  However, in practice no amount of
- * manipulation of INTEN and INTSET guarantees that the interrupt will
- * be triggered.  In fact, its very difficult, if not impossible to get
- * INTSET to re-trigger the interrupt.
- */
-static int sa1111_retrigger_lowirq(struct irq_data *d)
-{
-	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned int mask = SA1111_IRQMASK_LO(d->irq);
-	unsigned long ip0;
-	int i;
-
-	ip0 = sa1111_readl(mapbase + SA1111_INTPOL0);
-	for (i = 0; i < 8; i++) {
-		sa1111_writel(ip0 ^ mask, mapbase + SA1111_INTPOL0);
-		sa1111_writel(ip0, mapbase + SA1111_INTPOL0);
-		if (sa1111_readl(mapbase + SA1111_INTSTATCLR0) & mask)
-			break;
-	}
-
-	if (i == 8)
-		pr_err("Danger Will Robinson: failed to re-trigger IRQ%d\n",
-		       d->irq);
-	return i == 8 ? -1 : 0;
-}
-
-static int sa1111_type_lowirq(struct irq_data *d, unsigned int flags)
-{
-	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned int mask = SA1111_IRQMASK_LO(d->irq);
-	unsigned long ip0;
-
-	if (flags == IRQ_TYPE_PROBE)
-		return 0;
-
-	if ((!(flags & IRQ_TYPE_EDGE_RISING) ^ !(flags & IRQ_TYPE_EDGE_FALLING)) == 0)
-		return -EINVAL;
-
-	ip0 = sa1111_readl(mapbase + SA1111_INTPOL0);
-	if (flags & IRQ_TYPE_EDGE_RISING)
-		ip0 &= ~mask;
-	else
-		ip0 |= mask;
-	sa1111_writel(ip0, mapbase + SA1111_INTPOL0);
-	sa1111_writel(ip0, mapbase + SA1111_WAKEPOL0);
-
-	return 0;
-}
-
-static int sa1111_wake_lowirq(struct irq_data *d, unsigned int on)
+static void sa1111_ack_irq(struct irq_data *d)
 {
-	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned int mask = SA1111_IRQMASK_LO(d->irq);
-	unsigned long we0;
-
-	we0 = sa1111_readl(mapbase + SA1111_WAKEEN0);
-	if (on)
-		we0 |= mask;
-	else
-		we0 &= ~mask;
-	sa1111_writel(we0, mapbase + SA1111_WAKEEN0);
-
-	return 0;
 }
 
-static struct irq_chip sa1111_low_chip = {
-	.name		= "SA1111-l",
-	.irq_ack	= sa1111_ack_irq,
-	.irq_mask	= sa1111_mask_lowirq,
-	.irq_unmask	= sa1111_unmask_lowirq,
-	.irq_retrigger	= sa1111_retrigger_lowirq,
-	.irq_set_type	= sa1111_type_lowirq,
-	.irq_set_wake	= sa1111_wake_lowirq,
-};
-
-static void sa1111_mask_highirq(struct irq_data *d)
+static void sa1111_mask_irq(struct irq_data *d)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned long ie1;
+	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
+	u32 ie;
 
-	ie1 = sa1111_readl(mapbase + SA1111_INTEN1);
-	ie1 &= ~SA1111_IRQMASK_HI(d->irq);
-	sa1111_writel(ie1, mapbase + SA1111_INTEN1);
+	ie = sa1111_readl(mapbase + SA1111_INTEN0);
+	ie &= ~sa1111_irqmask(d);
+	sa1111_writel(ie, mapbase + SA1111_INTEN0);
 }
 
-static void sa1111_unmask_highirq(struct irq_data *d)
+static void sa1111_unmask_irq(struct irq_data *d)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned long ie1;
+	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
+	u32 ie;
 
-	ie1 = sa1111_readl(mapbase + SA1111_INTEN1);
-	ie1 |= SA1111_IRQMASK_HI(d->irq);
-	sa1111_writel(ie1, mapbase + SA1111_INTEN1);
+	ie = sa1111_readl(mapbase + SA1111_INTEN0);
+	ie |= sa1111_irqmask(d);
+	sa1111_writel(ie, mapbase + SA1111_INTEN0);
 }
 
 /*
@@ -366,19 +280,18 @@ static void sa1111_unmask_highirq(struct irq_data *d)
  * be triggered.  In fact, its very difficult, if not impossible to get
  * INTSET to re-trigger the interrupt.
  */
-static int sa1111_retrigger_highirq(struct irq_data *d)
+static int sa1111_retrigger_irq(struct irq_data *d)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned int mask = SA1111_IRQMASK_HI(d->irq);
-	unsigned long ip1;
+	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
+	u32 ip, mask = sa1111_irqmask(d);
 	int i;
 
-	ip1 = sa1111_readl(mapbase + SA1111_INTPOL1);
+	ip = sa1111_readl(mapbase + SA1111_INTPOL0);
 	for (i = 0; i < 8; i++) {
-		sa1111_writel(ip1 ^ mask, mapbase + SA1111_INTPOL1);
-		sa1111_writel(ip1, mapbase + SA1111_INTPOL1);
-		if (sa1111_readl(mapbase + SA1111_INTSTATCLR1) & mask)
+		sa1111_writel(ip ^ mask, mapbase + SA1111_INTPOL0);
+		sa1111_writel(ip, mapbase + SA1111_INTPOL0);
+		if (sa1111_readl(mapbase + SA1111_INTSTATCLR0) & mask)
 			break;
 	}
 
@@ -388,12 +301,11 @@ static int sa1111_retrigger_highirq(struct irq_data *d)
 	return i == 8 ? -1 : 0;
 }
 
-static int sa1111_type_highirq(struct irq_data *d, unsigned int flags)
+static int sa1111_type_irq(struct irq_data *d, unsigned int flags)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned int mask = SA1111_IRQMASK_HI(d->irq);
-	unsigned long ip1;
+	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
+	u32 ip, mask = sa1111_irqmask(d);
 
 	if (flags == IRQ_TYPE_PROBE)
 		return 0;
@@ -401,42 +313,41 @@ static int sa1111_type_highirq(struct irq_data *d, unsigned int flags)
 	if ((!(flags & IRQ_TYPE_EDGE_RISING) ^ !(flags & IRQ_TYPE_EDGE_FALLING)) == 0)
 		return -EINVAL;
 
-	ip1 = sa1111_readl(mapbase + SA1111_INTPOL1);
+	ip = sa1111_readl(mapbase + SA1111_INTPOL0);
 	if (flags & IRQ_TYPE_EDGE_RISING)
-		ip1 &= ~mask;
+		ip &= ~mask;
 	else
-		ip1 |= mask;
-	sa1111_writel(ip1, mapbase + SA1111_INTPOL1);
-	sa1111_writel(ip1, mapbase + SA1111_WAKEPOL1);
+		ip |= mask;
+	sa1111_writel(ip, mapbase + SA1111_INTPOL0);
+	sa1111_writel(ip, mapbase + SA1111_WAKEPOL0);
 
 	return 0;
 }
 
-static int sa1111_wake_highirq(struct irq_data *d, unsigned int on)
+static int sa1111_wake_irq(struct irq_data *d, unsigned int on)
 {
 	struct sa1111 *sachip = irq_data_get_irq_chip_data(d);
-	void __iomem *mapbase = sachip->base + SA1111_INTC;
-	unsigned int mask = SA1111_IRQMASK_HI(d->irq);
-	unsigned long we1;
+	void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d);
+	u32 we, mask = sa1111_irqmask(d);
 
-	we1 = sa1111_readl(mapbase + SA1111_WAKEEN1);
+	we = sa1111_readl(mapbase + SA1111_WAKEEN0);
 	if (on)
-		we1 |= mask;
+		we |= mask;
 	else
-		we1 &= ~mask;
-	sa1111_writel(we1, mapbase + SA1111_WAKEEN1);
+		we &= ~mask;
+	sa1111_writel(we, mapbase + SA1111_WAKEEN0);
 
 	return 0;
 }
 
-static struct irq_chip sa1111_high_chip = {
-	.name		= "SA1111-h",
+static struct irq_chip sa1111_irq_chip = {
+	.name		= "SA1111",
 	.irq_ack	= sa1111_ack_irq,
-	.irq_mask	= sa1111_mask_highirq,
-	.irq_unmask	= sa1111_unmask_highirq,
-	.irq_retrigger	= sa1111_retrigger_highirq,
-	.irq_set_type	= sa1111_type_highirq,
-	.irq_set_wake	= sa1111_wake_highirq,
+	.irq_mask	= sa1111_mask_irq,
+	.irq_unmask	= sa1111_unmask_irq,
+	.irq_retrigger	= sa1111_retrigger_irq,
+	.irq_set_type	= sa1111_type_irq,
+	.irq_set_wake	= sa1111_wake_irq,
 };
 
 static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
@@ -472,8 +383,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 	 * specifies that S0ReadyInt and S1ReadyInt should be '1'.
 	 */
 	sa1111_writel(0, irqbase + SA1111_INTPOL0);
-	sa1111_writel(SA1111_IRQMASK_HI(IRQ_S0_READY_NINT) |
-		      SA1111_IRQMASK_HI(IRQ_S1_READY_NINT),
+	sa1111_writel(BIT(IRQ_S0_READY_NINT & 31) |
+		      BIT(IRQ_S1_READY_NINT & 31),
 		      irqbase + SA1111_INTPOL1);
 
 	/* clear all IRQs */
@@ -482,16 +393,14 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 
 	for (i = IRQ_GPAIN0; i <= SSPROR; i++) {
 		irq = sachip->irq_base + i;
-		irq_set_chip_and_handler(irq, &sa1111_low_chip,
-					 handle_edge_irq);
+		irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq);
 		irq_set_chip_data(irq, sachip);
 		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
 
 	for (i = AUDXMTDMADONEA; i <= IRQ_S1_BVD1_STSCHG; i++) {
 		irq = sachip->irq_base + i;
-		irq_set_chip_and_handler(irq, &sa1111_high_chip,
-					 handle_edge_irq);
+		irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq);
 		irq_set_chip_data(irq, sachip);
 		irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
@@ -509,6 +418,181 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 	return 0;
 }
 
+static void sa1111_remove_irq(struct sa1111 *sachip)
+{
+	void __iomem *irqbase = sachip->base + SA1111_INTC;
+
+	/* disable all IRQs */
+	sa1111_writel(0, irqbase + SA1111_INTEN0);
+	sa1111_writel(0, irqbase + SA1111_INTEN1);
+	sa1111_writel(0, irqbase + SA1111_WAKEEN0);
+	sa1111_writel(0, irqbase + SA1111_WAKEEN1);
+
+	if (sachip->irq != NO_IRQ) {
+		irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
+		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
+
+		release_mem_region(sachip->phys + SA1111_INTC, 512);
+	}
+}
+
+enum {
+	SA1111_GPIO_PXDDR = (SA1111_GPIO_PADDR - SA1111_GPIO_PADDR),
+	SA1111_GPIO_PXDRR = (SA1111_GPIO_PADRR - SA1111_GPIO_PADDR),
+	SA1111_GPIO_PXDWR = (SA1111_GPIO_PADWR - SA1111_GPIO_PADDR),
+	SA1111_GPIO_PXSDR = (SA1111_GPIO_PASDR - SA1111_GPIO_PADDR),
+	SA1111_GPIO_PXSSR = (SA1111_GPIO_PASSR - SA1111_GPIO_PADDR),
+};
+
+static struct sa1111 *gc_to_sa1111(struct gpio_chip *gc)
+{
+	return container_of(gc, struct sa1111, gc);
+}
+
+static void __iomem *sa1111_gpio_map_reg(struct sa1111 *sachip, unsigned offset)
+{
+	void __iomem *reg = sachip->base + SA1111_GPIO;
+
+	if (offset < 4)
+		return reg + SA1111_GPIO_PADDR;
+	if (offset < 10)
+		return reg + SA1111_GPIO_PBDDR;
+	if (offset < 18)
+		return reg + SA1111_GPIO_PCDDR;
+	return NULL;
+}
+
+static u32 sa1111_gpio_map_bit(unsigned offset)
+{
+	if (offset < 4)
+		return BIT(offset);
+	if (offset < 10)
+		return BIT(offset - 4);
+	if (offset < 18)
+		return BIT(offset - 10);
+	return 0;
+}
+
+static void sa1111_gpio_modify(void __iomem *reg, u32 mask, u32 set)
+{
+	u32 val;
+
+	val = readl_relaxed(reg);
+	val &= ~mask;
+	val |= mask & set;
+	writel_relaxed(val, reg);
+}
+
+static int sa1111_gpio_get_direction(struct gpio_chip *gc, unsigned offset)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+	void __iomem *reg = sa1111_gpio_map_reg(sachip, offset);
+	u32 mask = sa1111_gpio_map_bit(offset);
+
+	return !!(readl_relaxed(reg + SA1111_GPIO_PXDDR) & mask);
+}
+
+static int sa1111_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+	unsigned long flags;
+	void __iomem *reg = sa1111_gpio_map_reg(sachip, offset);
+	u32 mask = sa1111_gpio_map_bit(offset);
+
+	spin_lock_irqsave(&sachip->lock, flags);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXDDR, mask, mask);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXSDR, mask, mask);
+	spin_unlock_irqrestore(&sachip->lock, flags);
+
+	return 0;
+}
+
+static int sa1111_gpio_direction_output(struct gpio_chip *gc, unsigned offset,
+	int value)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+	unsigned long flags;
+	void __iomem *reg = sa1111_gpio_map_reg(sachip, offset);
+	u32 mask = sa1111_gpio_map_bit(offset);
+
+	spin_lock_irqsave(&sachip->lock, flags);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXDWR, mask, value ? mask : 0);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXSSR, mask, value ? mask : 0);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXDDR, mask, 0);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXSDR, mask, 0);
+	spin_unlock_irqrestore(&sachip->lock, flags);
+
+	return 0;
+}
+
+static int sa1111_gpio_get(struct gpio_chip *gc, unsigned offset)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+	void __iomem *reg = sa1111_gpio_map_reg(sachip, offset);
+	u32 mask = sa1111_gpio_map_bit(offset);
+
+	return !!(readl_relaxed(reg + SA1111_GPIO_PXDRR) & mask);
+}
+
+static void sa1111_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+	unsigned long flags;
+	void __iomem *reg = sa1111_gpio_map_reg(sachip, offset);
+	u32 mask = sa1111_gpio_map_bit(offset);
+
+	spin_lock_irqsave(&sachip->lock, flags);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXDWR, mask, value ? mask : 0);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PXSSR, mask, value ? mask : 0);
+	spin_unlock_irqrestore(&sachip->lock, flags);
+}
+
+static void sa1111_gpio_set_multiple(struct gpio_chip *gc, unsigned long *mask,
+	unsigned long *bits)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+	unsigned long flags;
+	void __iomem *reg = sachip->base + SA1111_GPIO;
+	u32 msk, val;
+
+	msk = *mask;
+	val = *bits;
+
+	spin_lock_irqsave(&sachip->lock, flags);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PADWR, msk & 15, val);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PASSR, msk & 15, val);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PBDWR, (msk >> 4) & 255, val >> 4);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PBSSR, (msk >> 4) & 255, val >> 4);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PCDWR, (msk >> 12) & 255, val >> 12);
+	sa1111_gpio_modify(reg + SA1111_GPIO_PCSSR, (msk >> 12) & 255, val >> 12);
+	spin_unlock_irqrestore(&sachip->lock, flags);
+}
+
+static int sa1111_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
+{
+	struct sa1111 *sachip = gc_to_sa1111(gc);
+
+	return sachip->irq_base + offset;
+}
+
+static int sa1111_setup_gpios(struct sa1111 *sachip)
+{
+	sachip->gc.label = "sa1111";
+	sachip->gc.parent = sachip->dev;
+	sachip->gc.owner = THIS_MODULE;
+	sachip->gc.get_direction = sa1111_gpio_get_direction;
+	sachip->gc.direction_input = sa1111_gpio_direction_input;
+	sachip->gc.direction_output = sa1111_gpio_direction_output;
+	sachip->gc.get = sa1111_gpio_get;
+	sachip->gc.set = sa1111_gpio_set;
+	sachip->gc.set_multiple = sa1111_gpio_set_multiple;
+	sachip->gc.to_irq = sa1111_gpio_to_irq;
+	sachip->gc.base = -1;
+	sachip->gc.ngpio = 18;
+
+	return devm_gpiochip_add_data(sachip->dev, &sachip->gc, sachip);
+}
+
 /*
  * Bring the SA1111 out of reset.  This requires a set procedure:
  *  1. nRESET asserted (by hardware)
@@ -607,7 +691,7 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 
 static void sa1111_dev_release(struct device *_dev)
 {
-	struct sa1111_dev *dev = SA1111_DEV(_dev);
+	struct sa1111_dev *dev = to_sa1111_device(_dev);
 
 	kfree(dev);
 }
@@ -696,19 +780,17 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	if (!pd)
 		return -EINVAL;
 
-	sachip = kzalloc(sizeof(struct sa1111), GFP_KERNEL);
+	sachip = devm_kzalloc(me, sizeof(struct sa1111), GFP_KERNEL);
 	if (!sachip)
 		return -ENOMEM;
 
-	sachip->clk = clk_get(me, "SA1111_CLK");
-	if (IS_ERR(sachip->clk)) {
-		ret = PTR_ERR(sachip->clk);
-		goto err_free;
-	}
+	sachip->clk = devm_clk_get(me, "SA1111_CLK");
+	if (IS_ERR(sachip->clk))
+		return PTR_ERR(sachip->clk);
 
 	ret = clk_prepare(sachip->clk);
 	if (ret)
-		goto err_clkput;
+		return ret;
 
 	spin_lock_init(&sachip->lock);
 
@@ -754,9 +836,14 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	if (sachip->irq != NO_IRQ) {
 		ret = sa1111_setup_irq(sachip, pd->irq_base);
 		if (ret)
-			goto err_unmap;
+			goto err_clk;
 	}
 
+	/* Setup the GPIOs - should really be done after the IRQ setup */
+	ret = sa1111_setup_gpios(sachip);
+	if (ret)
+		goto err_irq;
+
 #ifdef CONFIG_ARCH_SA1100
 	{
 	unsigned int val;
@@ -799,20 +886,22 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
 
 	return 0;
 
+ err_irq:
+	sa1111_remove_irq(sachip);
+ err_clk:
+	clk_disable(sachip->clk);
  err_unmap:
 	iounmap(sachip->base);
  err_clk_unprep:
 	clk_unprepare(sachip->clk);
- err_clkput:
-	clk_put(sachip->clk);
- err_free:
-	kfree(sachip);
 	return ret;
 }
 
 static int sa1111_remove_one(struct device *dev, void *data)
 {
-	struct sa1111_dev *sadev = SA1111_DEV(dev);
+	struct sa1111_dev *sadev = to_sa1111_device(dev);
+	if (dev->bus != &sa1111_bus_type)
+		return 0;
 	device_del(&sadev->dev);
 	release_resource(&sadev->res);
 	put_device(&sadev->dev);
@@ -821,29 +910,14 @@ static int sa1111_remove_one(struct device *dev, void *data)
 
 static void __sa1111_remove(struct sa1111 *sachip)
 {
-	void __iomem *irqbase = sachip->base + SA1111_INTC;
-
 	device_for_each_child(sachip->dev, NULL, sa1111_remove_one);
 
-	/* disable all IRQs */
-	sa1111_writel(0, irqbase + SA1111_INTEN0);
-	sa1111_writel(0, irqbase + SA1111_INTEN1);
-	sa1111_writel(0, irqbase + SA1111_WAKEEN0);
-	sa1111_writel(0, irqbase + SA1111_WAKEEN1);
+	sa1111_remove_irq(sachip);
 
 	clk_disable(sachip->clk);
 	clk_unprepare(sachip->clk);
 
-	if (sachip->irq != NO_IRQ) {
-		irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
-		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
-
-		release_mem_region(sachip->phys + SA1111_INTC, 512);
-	}
-
 	iounmap(sachip->base);
-	clk_put(sachip->clk);
-	kfree(sachip);
 }
 
 struct sa1111_save_data {
@@ -869,9 +943,9 @@ struct sa1111_save_data {
 
 #ifdef CONFIG_PM
 
-static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
+static int sa1111_suspend_noirq(struct device *dev)
 {
-	struct sa1111 *sachip = platform_get_drvdata(dev);
+	struct sa1111 *sachip = dev_get_drvdata(dev);
 	struct sa1111_save_data *save;
 	unsigned long flags;
 	unsigned int val;
@@ -934,9 +1008,9 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
  *	restored by their respective drivers, and must be called
  *	via LDM after this function.
  */
-static int sa1111_resume(struct platform_device *dev)
+static int sa1111_resume_noirq(struct device *dev)
 {
-	struct sa1111 *sachip = platform_get_drvdata(dev);
+	struct sa1111 *sachip = dev_get_drvdata(dev);
 	struct sa1111_save_data *save;
 	unsigned long flags, id;
 	void __iomem *base;
@@ -952,7 +1026,7 @@ static int sa1111_resume(struct platform_device *dev)
 	id = sa1111_readl(sachip->base + SA1111_SKID);
 	if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
 		__sa1111_remove(sachip);
-		platform_set_drvdata(dev, NULL);
+		dev_set_drvdata(dev, NULL);
 		kfree(save);
 		return 0;
 	}
@@ -1003,8 +1077,8 @@ static int sa1111_resume(struct platform_device *dev)
 }
 
 #else
-#define sa1111_suspend NULL
-#define sa1111_resume  NULL
+#define sa1111_suspend_noirq NULL
+#define sa1111_resume_noirq  NULL
 #endif
 
 static int sa1111_probe(struct platform_device *pdev)
@@ -1017,7 +1091,7 @@ static int sa1111_probe(struct platform_device *pdev)
 		return -EINVAL;
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
-		return -ENXIO;
+		return irq;
 
 	return __sa1111_probe(&pdev->dev, mem, irq);
 }
@@ -1038,6 +1112,11 @@ static int sa1111_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static struct dev_pm_ops sa1111_pm_ops = {
+	.suspend_noirq = sa1111_suspend_noirq,
+	.resume_noirq = sa1111_resume_noirq,
+};
+
 /*
  *	Not sure if this should be on the system bus or not yet.
  *	We really want some way to register a system device at
@@ -1050,10 +1129,9 @@ static int sa1111_remove(struct platform_device *pdev)
 static struct platform_driver sa1111_device_driver = {
 	.probe		= sa1111_probe,
 	.remove		= sa1111_remove,
-	.suspend	= sa1111_suspend,
-	.resume		= sa1111_resume,
 	.driver		= {
 		.name	= "sa1111",
+		.pm	= &sa1111_pm_ops,
 	},
 };
 
@@ -1279,6 +1357,14 @@ void sa1111_disable_device(struct sa1111_dev *sadev)
 }
 EXPORT_SYMBOL(sa1111_disable_device);
 
+int sa1111_get_irq(struct sa1111_dev *sadev, unsigned num)
+{
+	if (num >= ARRAY_SIZE(sadev->irq))
+		return -EINVAL;
+	return sadev->irq[num];
+}
+EXPORT_SYMBOL_GPL(sa1111_get_irq);
+
 /*
  *	SA1111 "Register Access Bus."
  *
@@ -1287,7 +1373,7 @@ EXPORT_SYMBOL(sa1111_disable_device);
  */
 static int sa1111_match(struct device *_dev, struct device_driver *_drv)
 {
-	struct sa1111_dev *dev = SA1111_DEV(_dev);
+	struct sa1111_dev *dev = to_sa1111_device(_dev);
 	struct sa1111_driver *drv = SA1111_DRV(_drv);
 
 	return !!(dev->devid & drv->devid);
@@ -1295,7 +1381,7 @@ static int sa1111_match(struct device *_dev, struct device_driver *_drv)
 
 static int sa1111_bus_suspend(struct device *dev, pm_message_t state)
 {
-	struct sa1111_dev *sadev = SA1111_DEV(dev);
+	struct sa1111_dev *sadev = to_sa1111_device(dev);
 	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
 	int ret = 0;
 
@@ -1306,7 +1392,7 @@ static int sa1111_bus_suspend(struct device *dev, pm_message_t state)
 
 static int sa1111_bus_resume(struct device *dev)
 {
-	struct sa1111_dev *sadev = SA1111_DEV(dev);
+	struct sa1111_dev *sadev = to_sa1111_device(dev);
 	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
 	int ret = 0;
 
@@ -1320,12 +1406,12 @@ static void sa1111_bus_shutdown(struct device *dev)
 	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
 
 	if (drv && drv->shutdown)
-		drv->shutdown(SA1111_DEV(dev));
+		drv->shutdown(to_sa1111_device(dev));
 }
 
 static int sa1111_bus_probe(struct device *dev)
 {
-	struct sa1111_dev *sadev = SA1111_DEV(dev);
+	struct sa1111_dev *sadev = to_sa1111_device(dev);
 	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
 	int ret = -ENODEV;
 
@@ -1336,7 +1422,7 @@ static int sa1111_bus_probe(struct device *dev)
 
 static int sa1111_bus_remove(struct device *dev)
 {
-	struct sa1111_dev *sadev = SA1111_DEV(dev);
+	struct sa1111_dev *sadev = to_sa1111_device(dev);
 	struct sa1111_driver *drv = SA1111_DRV(dev->driver);
 	int ret = 0;
 
@@ -1401,7 +1487,7 @@ static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
 static int sa1111_notifier_call(struct notifier_block *n, unsigned long action,
 	void *data)
 {
-	struct sa1111_dev *dev = SA1111_DEV(data);
+	struct sa1111_dev *dev = to_sa1111_device(data);
 
 	switch (action) {
 	case BUS_NOTIFY_ADD_DEVICE:
diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig
index b6e54ee9bdbd..ca39c04fec6b 100644
--- a/arch/arm/configs/aspeed_g4_defconfig
+++ b/arch/arm/configs/aspeed_g4_defconfig
@@ -58,7 +58,7 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_FIRMWARE_MEMMAP=y
 CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_PAGE_POISONING=y
diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig
index 892605167357..4f366b0370e9 100644
--- a/arch/arm/configs/aspeed_g5_defconfig
+++ b/arch/arm/configs/aspeed_g5_defconfig
@@ -59,7 +59,7 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_FIRMWARE_MEMMAP=y
 CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_PAGE_POISONING=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index 71b42e66488a..78cd2f197e01 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -161,6 +161,7 @@ CONFIG_USB_MON=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_DWC3=y
+CONFIG_NOP_USB_XCEIV=y
 CONFIG_KEYSTONE_USB_PHY=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 2c8665cd9dc5..ea3566fb92e2 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -781,7 +781,7 @@ CONFIG_MXS_DMA=y
 CONFIG_DMA_BCM2835=y
 CONFIG_DMA_OMAP=y
 CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_VDMA=y
+CONFIG_XILINX_DMA=y
 CONFIG_DMA_SUN6I=y
 CONFIG_STAGING=y
 CONFIG_SENSORS_ISL29018=y
diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h
index 7c2bbc7f0be1..8979fa3bbf2d 100644
--- a/arch/arm/include/asm/hardware/sa1111.h
+++ b/arch/arm/include/asm/hardware/sa1111.h
@@ -420,7 +420,7 @@ struct sa1111_dev {
 	u64		dma_mask;
 };
 
-#define SA1111_DEV(_d)	container_of((_d), struct sa1111_dev, dev)
+#define to_sa1111_device(x)	container_of(x, struct sa1111_dev, dev)
 
 #define sa1111_get_drvdata(d)	dev_get_drvdata(&(d)->dev)
 #define sa1111_set_drvdata(d,p)	dev_set_drvdata(&(d)->dev, p)
@@ -446,6 +446,8 @@ struct sa1111_driver {
 int sa1111_enable_device(struct sa1111_dev *);
 void sa1111_disable_device(struct sa1111_dev *);
 
+int sa1111_get_irq(struct sa1111_dev *, unsigned num);
+
 unsigned int sa1111_pll_clock(struct sa1111_dev *);
 
 #define SA1111_AUDIO_ACLINK	0
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index d0131ee6f6af..3f82e9da7cec 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -47,6 +47,7 @@
 #define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
 #define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
 #define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_CACHE_MASK	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
 #define PMD_SECT_NONSHARED_DEV	(PMD_SECT_TEX(2))
 
 /*
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
index f8f1cff62065..4cd664abfcd3 100644
--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -62,6 +62,7 @@
 #define PMD_SECT_WT		(_AT(pmdval_t, 2) << 2)	/* normal inner write-through */
 #define PMD_SECT_WB		(_AT(pmdval_t, 3) << 2)	/* normal inner write-back */
 #define PMD_SECT_WBWA		(_AT(pmdval_t, 7) << 2)	/* normal inner write-alloc */
+#define PMD_SECT_CACHE_MASK	(_AT(pmdval_t, 7) << 2)
 
 /*
  * + Level 3 descriptor (PTE)
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 62a6f65029e6..a93c0f99acf7 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -480,7 +480,10 @@ arm_copy_from_user(void *to, const void __user *from, unsigned long n);
 static inline unsigned long __must_check
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	unsigned int __ua_flags = uaccess_save_and_enable();
+	unsigned int __ua_flags;
+
+	check_object_size(to, n, false);
+	__ua_flags = uaccess_save_and_enable();
 	n = arm_copy_from_user(to, from, n);
 	uaccess_restore(__ua_flags);
 	return n;
@@ -495,11 +498,15 @@ static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 #ifndef CONFIG_UACCESS_WITH_MEMCPY
-	unsigned int __ua_flags = uaccess_save_and_enable();
+	unsigned int __ua_flags;
+
+	check_object_size(from, n, true);
+	__ua_flags = uaccess_save_and_enable();
 	n = arm_copy_to_user(to, from, n);
 	uaccess_restore(__ua_flags);
 	return n;
 #else
+	check_object_size(from, n, true);
 	return arm_copy_to_user(to, from, n);
 #endif
 }
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index bc5f50799d75..9f157e7c51e7 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -295,6 +295,7 @@ __und_svc_fault:
 	bl	__und_fault
 
 __und_svc_finish:
+	get_thread_info tsk
 	ldr	r5, [sp, #S_PSR]		@ Get SVC cpsr
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 0b1e4a93d67e..15d073ae5da2 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -142,6 +142,19 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 	and	r7, #0x1f		@ Preserve HPMN
 	mcr	p15, 4, r7, c1, c1, 1	@ HDCR
 
+	@ Make sure NS-SVC is initialised appropriately
+	mrc	p15, 0, r7, c1, c0, 0	@ SCTLR
+	orr	r7, #(1 << 5)		@ CP15 barriers enabled
+	bic	r7, #(3 << 7)		@ Clear SED/ITD for v8 (RES0 for v7)
+	bic	r7, #(3 << 19)		@ WXN and UWXN disabled
+	mcr	p15, 0, r7, c1, c0, 0	@ SCTLR
+
+	mrc	p15, 0, r7, c0, c0, 0	@ MIDR
+	mcr	p15, 4, r7, c0, c0, 0	@ VPIDR
+
+	mrc	p15, 0, r7, c0, c0, 5	@ MPIDR
+	mcr	p15, 4, r7, c0, c0, 5	@ VMPIDR
+
 #if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER)
 	@ make CNTP_* and CNTPCT accessible from PL1
 	mrc	p15, 0, r7, c0, c1, 1	@ ID_PFR1
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 087acb569b63..5f221acd21ae 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
 	mm_segment_t fs;
 	long ret, err, i;
 
-	if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event)))
+	if (maxevents <= 0 ||
+			maxevents > (INT_MAX/sizeof(*kbuf)) ||
+			maxevents > (INT_MAX/sizeof(*events)))
 		return -EINVAL;
+	if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents))
+		return -EFAULT;
 	kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL);
 	if (!kbuf)
 		return -ENOMEM;
@@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid,
 
 	if (nsops < 1 || nsops > SEMOPM)
 		return -EINVAL;
+	if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops))
+		return -EFAULT;
 	sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
 	if (!sops)
 		return -ENOMEM;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d94bb9093ead..c94b90d43772 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -158,8 +158,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	int i;
 
-	kvm_free_stage2_pgd(kvm);
-
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_arch_vcpu_free(kvm->vcpus[i]);
@@ -1009,9 +1007,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
+		int ret;
 		if (!vgic_present)
 			return -ENXIO;
-		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_lock(&kvm->lock);
+		ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_unlock(&kvm->lock);
+		return ret;
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
 		struct kvm_arm_device_addr dev_addr;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index bda27b6b1aa2..e9a5c0e0c115 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1309,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	smp_rmb();
 
 	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return -EFAULT;
 
 	if (kvm_is_device_pfn(pfn)) {
@@ -1714,7 +1714,8 @@ int kvm_mmu_init(void)
 		 kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
 
 	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
-	    hyp_idmap_start <  kern_hyp_va(~0UL)) {
+	    hyp_idmap_start <  kern_hyp_va(~0UL) &&
+	    hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
 		/*
 		 * The idmap page is intersecting with the VA space,
 		 * it is not safe to continue further.
@@ -1893,6 +1894,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
+	kvm_free_stage2_pgd(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/arm/mach-clps711x/Kconfig b/arch/arm/mach-clps711x/Kconfig
index dc7c6edeab39..61284b9389cf 100644
--- a/arch/arm/mach-clps711x/Kconfig
+++ b/arch/arm/mach-clps711x/Kconfig
@@ -1,13 +1,13 @@
 menuconfig ARCH_CLPS711X
 	bool "Cirrus Logic EP721x/EP731x-based"
 	depends on ARCH_MULTI_V4T
-	select ARCH_REQUIRE_GPIOLIB
 	select AUTO_ZRELADDR
 	select CLKSRC_OF
 	select CLPS711X_TIMER
 	select COMMON_CLK
 	select CPU_ARM720T
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select MFD_SYSCON
 	select OF_IRQ
 	select USE_OF
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 3750575c73c5..06332f626565 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -255,6 +255,12 @@ static int __init exynos_pmu_irq_init(struct device_node *node,
 		return -ENOMEM;
 	}
 
+	/*
+	 * Clear the OF_POPULATED flag set in of_irq_init so that
+	 * later the Exynos PMU platform device won't be skipped.
+	 */
+	of_node_clear_flag(node, OF_POPULATED);
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index fd8720532471..0df062d8b2c9 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -271,6 +271,12 @@ static int __init imx_gpc_init(struct device_node *node,
 	for (i = 0; i < IMR_NUM; i++)
 		writel_relaxed(~0, gpc_base + GPC_IMR1 + i * 4);
 
+	/*
+	 * Clear the OF_POPULATED flag set in of_irq_init so that
+	 * later the GPC power domain driver will not be skipped.
+	 */
+	of_node_clear_flag(node, OF_POPULATED);
+
 	return 0;
 }
 IRQCHIP_DECLARE(imx_gpc, "fsl,imx6q-gpc", imx_gpc_init);
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index 5d9bfab279dd..6bb7d9cf1e38 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -64,6 +64,7 @@ static void __init imx6ul_init_machine(void)
 	if (parent == NULL)
 		pr_warn("failed to initialize soc device\n");
 
+	of_platform_default_populate(NULL, NULL, parent);
 	imx6ul_enet_init();
 	imx_anatop_init();
 	imx6ul_pm_init();
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 58924b3844df..fe708e26d021 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -295,7 +295,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode)
 		val &= ~BM_CLPCR_SBYOS;
 		if (cpu_is_imx6sl())
 			val |= BM_CLPCR_BYPASS_PMIC_READY;
-		if (cpu_is_imx6sl() || cpu_is_imx6sx())
+		if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
 			val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
 		else
 			val |= BM_CLPCR_BYP_MMDC_CH1_LPM_HS;
@@ -310,7 +310,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode)
 		val |= 0x3 << BP_CLPCR_STBY_COUNT;
 		val |= BM_CLPCR_VSTBY;
 		val |= BM_CLPCR_SBYOS;
-		if (cpu_is_imx6sl())
+		if (cpu_is_imx6sl() || cpu_is_imx6sx())
 			val |= BM_CLPCR_BYPASS_PMIC_READY;
 		if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
 			val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index e53c6cfcab51..6c6497e80a7b 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -1,5 +1,4 @@
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
-	-I$(srctree)/arch/arm/plat-orion/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include
 
 AFLAGS_coherency_ll.o		:= -Wa,-march=armv7-a
 CFLAGS_pmsu.o			:= -march=armv7-a
diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c
index c073fb57dd13..6f2d0aec0513 100644
--- a/arch/arm/mach-omap2/cm33xx.c
+++ b/arch/arm/mach-omap2/cm33xx.c
@@ -220,9 +220,6 @@ static int am33xx_cm_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs,
 {
 	int i = 0;
 
-	if (!clkctrl_offs)
-		return 0;
-
 	omap_test_timeout(_is_module_ready(inst, clkctrl_offs),
 			  MAX_MODULE_READY_TIME, i);
 
@@ -246,9 +243,6 @@ static int am33xx_cm_wait_module_idle(u8 part, s16 inst, u16 clkctrl_offs,
 {
 	int i = 0;
 
-	if (!clkctrl_offs)
-		return 0;
-
 	omap_test_timeout((_clkctrl_idlest(inst, clkctrl_offs) ==
 				CLKCTRL_IDLEST_DISABLED),
 				MAX_MODULE_READY_TIME, i);
diff --git a/arch/arm/mach-omap2/cminst44xx.c b/arch/arm/mach-omap2/cminst44xx.c
index 2c0e07ed6b99..2ab27ade136a 100644
--- a/arch/arm/mach-omap2/cminst44xx.c
+++ b/arch/arm/mach-omap2/cminst44xx.c
@@ -278,9 +278,6 @@ static int omap4_cminst_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs,
 {
 	int i = 0;
 
-	if (!clkctrl_offs)
-		return 0;
-
 	omap_test_timeout(_is_module_ready(part, inst, clkctrl_offs),
 			  MAX_MODULE_READY_TIME, i);
 
@@ -304,9 +301,6 @@ static int omap4_cminst_wait_module_idle(u8 part, s16 inst, u16 clkctrl_offs,
 {
 	int i = 0;
 
-	if (!clkctrl_offs)
-		return 0;
-
 	omap_test_timeout((_clkctrl_idlest(part, inst, clkctrl_offs) ==
 			   CLKCTRL_IDLEST_DISABLED),
 			  MAX_MODULE_DISABLE_TIME, i);
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 5b709383381c..1052b29697b8 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1053,6 +1053,10 @@ static int _omap4_wait_target_disable(struct omap_hwmod *oh)
 	if (oh->flags & HWMOD_NO_IDLEST)
 		return 0;
 
+	if (!oh->prcm.omap4.clkctrl_offs &&
+	    !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET))
+		return 0;
+
 	return omap_cm_wait_module_idle(oh->clkdm->prcm_partition,
 					oh->clkdm->cm_inst,
 					oh->prcm.omap4.clkctrl_offs, 0);
@@ -2971,6 +2975,10 @@ static int _omap4_wait_target_ready(struct omap_hwmod *oh)
 	if (!_find_mpu_rt_port(oh))
 		return 0;
 
+	if (!oh->prcm.omap4.clkctrl_offs &&
+	    !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET))
+		return 0;
+
 	/* XXX check module SIDLEMODE, hardreset status */
 
 	return omap_cm_wait_module_ready(oh->clkdm->prcm_partition,
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 4041bad79a9a..78904017f18c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -443,8 +443,12 @@ struct omap_hwmod_omap2_prcm {
  * HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT: Some IP blocks don't have a PRCM
  *     module-level context loss register associated with them; this
  *     flag bit should be set in those cases
+ * HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET: Some IP blocks have a valid CLKCTRL
+ *	offset of zero; this flag bit should be set in those cases to
+ *	distinguish from hwmods that have no clkctrl offset.
  */
 #define HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT		(1 << 0)
+#define HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET		(1 << 1)
 
 /**
  * struct omap_hwmod_omap4_prcm - OMAP4-specific PRCM data
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index 55c5878577f4..e2d84aa7f595 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -29,6 +29,7 @@
 #define CLKCTRL(oh, clkctrl) ((oh).prcm.omap4.clkctrl_offs = (clkctrl))
 #define RSTCTRL(oh, rstctrl) ((oh).prcm.omap4.rstctrl_offs = (rstctrl))
 #define RSTST(oh, rstst) ((oh).prcm.omap4.rstst_offs = (rstst))
+#define PRCM_FLAGS(oh, flag) ((oh).prcm.omap4.flags = (flag))
 
 /*
  * 'l3' class
@@ -1296,6 +1297,7 @@ static void omap_hwmod_am33xx_clkctrl(void)
 	CLKCTRL(am33xx_i2c1_hwmod, AM33XX_CM_WKUP_I2C0_CLKCTRL_OFFSET);
 	CLKCTRL(am33xx_wd_timer1_hwmod, AM33XX_CM_WKUP_WDT1_CLKCTRL_OFFSET);
 	CLKCTRL(am33xx_rtc_hwmod, AM33XX_CM_RTC_RTC_CLKCTRL_OFFSET);
+	PRCM_FLAGS(am33xx_rtc_hwmod, HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET);
 	CLKCTRL(am33xx_mmc2_hwmod, AM33XX_CM_PER_MMC2_CLKCTRL_OFFSET);
 	CLKCTRL(am33xx_gpmc_hwmod, AM33XX_CM_PER_GPMC_CLKCTRL_OFFSET);
 	CLKCTRL(am33xx_l4_ls_hwmod, AM33XX_CM_PER_L4LS_CLKCTRL_OFFSET);
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d72ee6185d5e..1cc4a6f3954e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -722,8 +722,20 @@ static struct omap_hwmod omap3xxx_dss_dispc_hwmod = {
  * display serial interface controller
  */
 
+static struct omap_hwmod_class_sysconfig omap3xxx_dsi_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
 static struct omap_hwmod_class omap3xxx_dsi_hwmod_class = {
 	.name = "dsi",
+	.sysc	= &omap3xxx_dsi_sysc,
 };
 
 static struct omap_hwmod_irq_info omap3xxx_dsi1_irqs[] = {
diff --git a/arch/arm/mach-oxnas/Kconfig b/arch/arm/mach-oxnas/Kconfig
index 567496bd250a..29100beb2e7f 100644
--- a/arch/arm/mach-oxnas/Kconfig
+++ b/arch/arm/mach-oxnas/Kconfig
@@ -11,11 +11,13 @@ if ARCH_OXNAS
 
 config MACH_OX810SE
 	bool "Support OX810SE Based Products"
+	select ARCH_HAS_RESET_CONTROLLER
 	select COMMON_CLK_OXNAS
 	select CPU_ARM926T
 	select MFD_SYSCON
 	select OXNAS_RPS_TIMER
 	select PINCTRL_OXNAS
+	select RESET_CONTROLLER
 	select RESET_OXNAS
 	select VERSATILE_FPGA_IRQ
 	help
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index dc109dc3a622..10bfdb169366 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/module.h>	/* symbol_get ; symbol_put */
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/major.h>
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index c410d84b243d..66070acaa888 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_USE_DMA | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 7245f3359564..d6159f8ef0c2 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -137,6 +137,18 @@ static struct pxa2xx_udc_mach_info udc_info __initdata = {
 	// no D+ pullup; lubbock can't connect/disconnect in software
 };
 
+static void lubbock_init_pcmcia(void)
+{
+	struct clk *clk;
+
+	/* Add an alias for the SA1111 PCMCIA clock */
+	clk = clk_get_sys("pxa2xx-pcmcia", NULL);
+	if (!IS_ERR(clk)) {
+		clkdev_create(clk, NULL, "1800");
+		clk_put(clk);
+	}
+}
+
 static struct resource sa1111_resources[] = {
 	[0] = {
 		.start	= 0x10000000,
@@ -467,6 +479,8 @@ static void __init lubbock_init(void)
 	pxa_set_btuart_info(NULL);
 	pxa_set_stuart_info(NULL);
 
+	lubbock_init_pcmcia();
+
 	clk_add_alias("SA1111_CLK", NULL, "GPIO11_CLK", NULL);
 	pxa_set_udc_info(&udc_info);
 	pxa_set_fb_info(NULL, &sharp_lm8v31);
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 1080580b1343..2c150bfc0cd5 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/module.h>	/* symbol_get ; symbol_put */
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/gpio_keys.h>
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 3f06cd90567a..056369ef250e 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata xcep_smc91x_info = {
-	.flags	= SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+	.flags	= SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		  SMC91X_NOWAIT | SMC91X_USE_DMA,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile
index dae8d86ef4cc..404882130956 100644
--- a/arch/arm/mach-realview/Makefile
+++ b/arch/arm/mach-realview/Makefile
@@ -1,8 +1,7 @@
 #
 # Makefile for the linux kernel.
 #
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
-	-I$(srctree)/arch/arm/plat-versatile/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include
 
 obj-y					:= core.o
 obj-$(CONFIG_REALVIEW_DT)		+= realview-dt.o
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index baf174542e36..a0ead0ae23d6 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -93,7 +93,8 @@ static struct smsc911x_platform_config smsc911x_config = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 };
 
 static struct platform_device realview_eth_device = {
diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile
index 72b9e9671507..fa7fb716e388 100644
--- a/arch/arm/mach-s5pv210/Makefile
+++ b/arch/arm/mach-s5pv210/Makefile
@@ -5,7 +5,7 @@
 #
 # Licensed under GPLv2
 
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include
 
 # Core
 
diff --git a/arch/arm/mach-sa1100/clock.c b/arch/arm/mach-sa1100/clock.c
index cbf53bb9c814..0db46895c82a 100644
--- a/arch/arm/mach-sa1100/clock.c
+++ b/arch/arm/mach-sa1100/clock.c
@@ -125,6 +125,8 @@ static unsigned long clk_36864_get_rate(struct clk *clk)
 }
 
 static struct clkops clk_36864_ops = {
+	.enable		= clk_cpu_enable,
+	.disable	= clk_cpu_disable,
 	.get_rate	= clk_36864_get_rate,
 };
 
@@ -140,9 +142,8 @@ static struct clk_lookup sa11xx_clkregs[] = {
 	CLKDEV_INIT(NULL, "OSTIMER0", &clk_36864),
 };
 
-static int __init sa11xx_clk_init(void)
+int __init sa11xx_clk_init(void)
 {
 	clkdev_add_table(sa11xx_clkregs, ARRAY_SIZE(sa11xx_clkregs));
 	return 0;
 }
-core_initcall(sa11xx_clk_init);
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 345e63f4eb71..3e09beddb6e8 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -34,6 +34,7 @@
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
+#include <mach/reset.h>
 
 #include "generic.h"
 #include <clocksource/pxa.h>
@@ -95,6 +96,8 @@ static void sa1100_power_off(void)
 
 void sa11x0_restart(enum reboot_mode mode, const char *cmd)
 {
+	clear_reset_status(RESET_STATUS_ALL);
+
 	if (mode == REBOOT_SOFT) {
 		/* Jump into ROM at address 0 */
 		soft_restart(0);
@@ -388,6 +391,7 @@ void __init sa1100_init_irq(void)
 	sa11x0_init_irq_nodt(IRQ_GPIO0_SC, irq_resource.start);
 
 	sa1100_init_gpio();
+	sa11xx_clk_init();
 }
 
 /*
diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h
index 0d92e119b36b..68199b603ff7 100644
--- a/arch/arm/mach-sa1100/generic.h
+++ b/arch/arm/mach-sa1100/generic.h
@@ -44,3 +44,5 @@ int sa11x0_pm_init(void);
 #else
 static inline int sa11x0_pm_init(void) { return 0; }
 #endif
+
+int sa11xx_clk_init(void);
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 1525d7b5f1b7..88149f85bc49 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index f3dba6f356e2..02e21bceb085 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -40,5 +40,8 @@ bool shmobile_smp_cpu_can_disable(unsigned int cpu)
 bool __init shmobile_smp_init_fallback_ops(void)
 {
 	/* fallback on PSCI/smp_ops if no other DT based method is detected */
+	if (!IS_ENABLED(CONFIG_SMP))
+		return false;
+
 	return platform_can_secondary_boot() ? true : false;
 }
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 62437b57813e..73e3adbc1330 100644
--- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -41,39 +41,26 @@
 
 #define REGULATOR_IRQ_MASK	BIT(2)	/* IRQ2, active low */
 
-static void __iomem *irqc;
-
-static const u8 da9063_mask_regs[] = {
-	DA9063_REG_IRQ_MASK_A,
-	DA9063_REG_IRQ_MASK_B,
-	DA9063_REG_IRQ_MASK_C,
-	DA9063_REG_IRQ_MASK_D,
-};
-
-/* DA9210 System Control and Event Registers */
+/* start of DA9210 System Control and Event Registers */
 #define DA9210_REG_MASK_A		0x54
-#define DA9210_REG_MASK_B		0x55
-
-static const u8 da9210_mask_regs[] = {
-	DA9210_REG_MASK_A,
-	DA9210_REG_MASK_B,
-};
-
-static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[],
-			     unsigned int nregs)
-{
-	unsigned int i;
 
-	dev_info(&client->dev, "Masking %s interrupt sources\n", client->name);
+static void __iomem *irqc;
 
-	for (i = 0; i < nregs; i++) {
-		int error = i2c_smbus_write_byte_data(client, regs[i], ~0);
-		if (error) {
-			dev_err(&client->dev, "i2c error %d\n", error);
-			return;
-		}
-	}
-}
+/* first byte sets the memory pointer, following are consecutive reg values */
+static u8 da9063_irq_clr[] = { DA9063_REG_IRQ_MASK_A, 0xff, 0xff, 0xff, 0xff };
+static u8 da9210_irq_clr[] = { DA9210_REG_MASK_A, 0xff, 0xff };
+
+static struct i2c_msg da9xxx_msgs[2] = {
+	{
+		.addr = 0x58,
+		.len = ARRAY_SIZE(da9063_irq_clr),
+		.buf = da9063_irq_clr,
+	}, {
+		.addr = 0x68,
+		.len = ARRAY_SIZE(da9210_irq_clr),
+		.buf = da9210_irq_clr,
+	},
+};
 
 static int regulator_quirk_notify(struct notifier_block *nb,
 				  unsigned long action, void *data)
@@ -93,12 +80,15 @@ static int regulator_quirk_notify(struct notifier_block *nb,
 	client = to_i2c_client(dev);
 	dev_dbg(dev, "Detected %s\n", client->name);
 
-	if ((client->addr == 0x58 && !strcmp(client->name, "da9063")))
-		da9xxx_mask_irqs(client, da9063_mask_regs,
-				 ARRAY_SIZE(da9063_mask_regs));
-	else if (client->addr == 0x68 && !strcmp(client->name, "da9210"))
-		da9xxx_mask_irqs(client, da9210_mask_regs,
-				 ARRAY_SIZE(da9210_mask_regs));
+	if ((client->addr == 0x58 && !strcmp(client->name, "da9063")) ||
+	    (client->addr == 0x68 && !strcmp(client->name, "da9210"))) {
+		int ret;
+
+		dev_info(&client->dev, "clearing da9063/da9210 interrupts\n");
+		ret = i2c_transfer(client->adapter, da9xxx_msgs, ARRAY_SIZE(da9xxx_msgs));
+		if (ret != ARRAY_SIZE(da9xxx_msgs))
+			dev_err(&client->dev, "i2c error %d\n", ret);
+	}
 
 	mon = ioread32(irqc + IRQC_MONITOR);
 	if (mon & REGULATOR_IRQ_MASK)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 2396935e715c..4001dd15818d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -137,7 +137,7 @@ void __init init_default_cache_policy(unsigned long pmd)
 
 	initial_pmd_value = pmd;
 
-	pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE;
+	pmd &= PMD_SECT_CACHE_MASK;
 
 	for (i = 0; i < ARRAY_SIZE(cache_policies); i++)
 		if (cache_policies[i].pmd == pmd) {
@@ -728,7 +728,8 @@ static void *__init late_alloc(unsigned long sz)
 {
 	void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
 
-	BUG_ON(!ptr);
+	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+		BUG();
 	return ptr;
 }
 
@@ -1155,10 +1156,19 @@ void __init sanity_check_meminfo(void)
 {
 	phys_addr_t memblock_limit = 0;
 	int highmem = 0;
-	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
+	u64 vmalloc_limit;
 	struct memblock_region *reg;
 	bool should_use_highmem = false;
 
+	/*
+	 * Let's use our own (unoptimized) equivalent of __pa() that is
+	 * not affected by wrap-arounds when sizeof(phys_addr_t) == 4.
+	 * The result is used as the upper bound on physical memory address
+	 * and may itself be outside the valid range for which phys_addr_t
+	 * and therefore __pa() is defined.
+	 */
+	vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
+
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
@@ -1183,10 +1193,11 @@ void __init sanity_check_meminfo(void)
 			if (reg->size > size_limit) {
 				phys_addr_t overlap_size = reg->size - size_limit;
 
-				pr_notice("Truncating RAM at %pa-%pa to -%pa",
-					  &block_start, &block_end, &vmalloc_limit);
-				memblock_remove(vmalloc_limit, overlap_size);
+				pr_notice("Truncating RAM at %pa-%pa",
+					  &block_start, &block_end);
 				block_end = vmalloc_limit;
+				pr_cont(" to -%pa", &block_end);
+				memblock_remove(vmalloc_limit, overlap_size);
 				should_use_highmem = true;
 			}
 		}
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index a7123b4e129d..d00d52c9de3e 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -16,6 +16,7 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/memory.h>
 
 #include "proc-macros.S"
 
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index b0b82f5ea338..f193414d0f6f 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 static struct vcpu_info __percpu *xen_vcpu_info;
 
 /* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
 /* These are unused until we support booting "pre-ballooned" */
@@ -170,9 +170,6 @@ static int xen_starting_cpu(unsigned int cpu)
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
 
-	/* Direct vCPU id mapping for ARM guests. */
-	per_cpu(xen_vcpu_id, cpu) = cpu;
-
 	info.mfn = virt_to_gfn(vcpup);
 	info.offset = xen_offset_in_page(vcpup);
 
@@ -330,6 +327,7 @@ static int __init xen_guest_init(void)
 {
 	struct xen_add_to_physmap xatp;
 	struct shared_info *shared_info_page = NULL;
+	int cpu;
 
 	if (!xen_domain())
 		return 0;
@@ -380,7 +378,8 @@ static int __init xen_guest_init(void)
 		return -ENOMEM;
 
 	/* Direct vCPU id mapping for ARM guests. */
-	per_cpu(xen_vcpu_id, 0) = 0;
+	for_each_possible_cpu(cpu)
+		per_cpu(xen_vcpu_id, cpu) = cpu;
 
 	xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
 	if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 69c8787bec7d..bc3f00f586f1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -54,6 +54,7 @@ config ARM64
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
+	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index bb2616b16157..be5d824ebdba 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -8,7 +8,7 @@ config ARCH_SUNXI
 
 config ARCH_ALPINE
 	bool "Annapurna Labs Alpine platform"
-	select ALPINE_MSI
+	select ALPINE_MSI if PCI
 	help
 	  This enables support for the Annapurna Labs Alpine
 	  Soc family.
@@ -66,7 +66,7 @@ config ARCH_LG1K
 config ARCH_HISI
 	bool "Hisilicon SoC Family"
 	select ARM_TIMER_SP804
-	select HISILICON_IRQ_MBIGEN
+	select HISILICON_IRQ_MBIGEN if PCI
 	help
 	  This enables support for Hisilicon ARMv8 SoC family
 
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 445aa678f914..c2b9bcb0ef61 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -255,10 +255,10 @@
 		/* Local timer */
 		timer {
 			compatible = "arm,armv8-timer";
-			interrupts = <1 13 0xf01>,
-				     <1 14 0xf01>,
-				     <1 11 0xf01>,
-				     <1 10 0xf01>;
+			interrupts = <1 13 0xf08>,
+				     <1 14 0xf08>,
+				     <1 11 0xf08>,
+				     <1 10 0xf08>;
 		};
 
 		timer0: timer0@ffc03000 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index e502c24b0ac7..bf6c8d051002 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -102,13 +102,13 @@
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 13
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 14
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 11
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 10
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>;
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
 	xtal: xtal-clk {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index f1c2c713f9b0..c29dab9d1834 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -110,10 +110,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <1 0 0xff01>,	/* Secure Phys IRQ */
-			     <1 13 0xff01>,	/* Non-secure Phys IRQ */
-			     <1 14 0xff01>,	/* Virt IRQ */
-			     <1 15 0xff01>;	/* Hyp IRQ */
+		interrupts = <1 0 0xff08>,	/* Secure Phys IRQ */
+			     <1 13 0xff08>,	/* Non-secure Phys IRQ */
+			     <1 14 0xff08>,	/* Virt IRQ */
+			     <1 15 0xff08>;	/* Hyp IRQ */
 		clock-frequency = <50000000>;
 	};
 
diff --git a/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi b/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi
new file mode 120000
index 000000000000..3937b77cb310
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi
@@ -0,0 +1 @@
+../../../../arm/boot/dts/bcm2835-rpi.dtsi
+\ No newline at end of file
diff --git a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
index 6f47dd2bb1db..7841b724e340 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
+++ b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 #include "bcm2837.dtsi"
-#include "../../../../arm/boot/dts/bcm2835-rpi.dtsi"
-#include "../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi"
+#include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9514.dtsi"
 
 / {
 	compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
diff --git a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
index f2a31d06845d..8216bbb29fe0 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
@@ -1,4 +1,4 @@
-#include "../../../../arm/boot/dts/bcm283x.dtsi"
+#include "bcm283x.dtsi"
 
 / {
 	compatible = "brcm,bcm2836";
diff --git a/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi b/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi
new file mode 120000
index 000000000000..dca7c057d5a5
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi
@@ -0,0 +1 @@
+../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi
+\ No newline at end of file
diff --git a/arch/arm64/boot/dts/broadcom/bcm283x.dtsi b/arch/arm64/boot/dts/broadcom/bcm283x.dtsi
new file mode 120000
index 000000000000..5f54e4cab99b
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm283x.dtsi
@@ -0,0 +1 @@
+../../../../arm/boot/dts/bcm283x.dtsi
+\ No newline at end of file
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index f53b0955bfd3..d4a12fad8afd 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -88,13 +88,13 @@
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0xff) |
-			      IRQ_TYPE_EDGE_RISING)>,
+			      IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 14 (GIC_CPU_MASK_RAW(0xff) |
-			      IRQ_TYPE_EDGE_RISING)>,
+			      IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 11 (GIC_CPU_MASK_RAW(0xff) |
-			      IRQ_TYPE_EDGE_RISING)>,
+			      IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 10 (GIC_CPU_MASK_RAW(0xff) |
-			      IRQ_TYPE_EDGE_RISING)>;
+			      IRQ_TYPE_LEVEL_LOW)>;
 	};
 
 	pmu {
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index 2eb9b225f0bc..04dc8a8d1539 100644
--- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
@@ -354,10 +354,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <1 13 0xff01>,
-		             <1 14 0xff01>,
-		             <1 11 0xff01>,
-		             <1 10 0xff01>;
+		interrupts = <1 13 4>,
+		             <1 14 4>,
+		             <1 11 4>,
+		             <1 10 4>;
 	};
 
 	pmu {
diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index 299f3ce969ab..c528dd52ba2d 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -12,6 +12,7 @@
 /dts-v1/;
 #include "exynos7.dtsi"
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/samsung,s2mps11.h>
 
 / {
 	model = "Samsung Exynos7 Espresso board based on EXYNOS7";
@@ -43,6 +44,8 @@
 
 &rtc {
 	status = "okay";
+	clocks = <&clock_ccore PCLK_RTC>, <&s2mps15_osc S2MPS11_CLK_AP>;
+	clock-names = "rtc", "rtc_src";
 };
 
 &watchdog {
diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi
index ca663dfe5189..162831546e18 100644
--- a/arch/arm64/boot/dts/exynos/exynos7.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi
@@ -473,10 +473,10 @@
 
 		timer {
 			compatible = "arm,armv8-timer";
-			interrupts = <1 13 0xff01>,
-				     <1 14 0xff01>,
-				     <1 11 0xff01>,
-				     <1 10 0xff01>;
+			interrupts = <1 13 0xff08>,
+				     <1 14 0xff08>,
+				     <1 11 0xff08>,
+				     <1 10 0xff08>;
 		};
 
 		pmu_system_controller: system-controller@105c0000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index e669fbd7f9c3..a67e210e2019 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -119,10 +119,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <1 13 0x1>, /* Physical Secure PPI */
-			     <1 14 0x1>, /* Physical Non-Secure PPI */
-			     <1 11 0x1>, /* Virtual PPI */
-			     <1 10 0x1>; /* Hypervisor PPI */
+		interrupts = <1 13 0xf08>, /* Physical Secure PPI */
+			     <1 14 0xf08>, /* Physical Non-Secure PPI */
+			     <1 11 0xf08>, /* Virtual PPI */
+			     <1 10 0xf08>; /* Hypervisor PPI */
 	};
 
 	pmu {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index 21023a388c29..e3b6034ea5d9 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -191,10 +191,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */
-			     <1 14 0x8>, /* Physical Non-Secure PPI, active-low */
-			     <1 11 0x8>, /* Virtual PPI, active-low */
-			     <1 10 0x8>; /* Hypervisor PPI, active-low */
+		interrupts = <1 13 4>, /* Physical Secure PPI, active-low */
+			     <1 14 4>, /* Physical Non-Secure PPI, active-low */
+			     <1 11 4>, /* Virtual PPI, active-low */
+			     <1 10 4>; /* Hypervisor PPI, active-low */
 	};
 
 	pmu {
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index eab1a42fb934..c2a6745f168c 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -122,10 +122,10 @@
 
 			timer {
 				compatible = "arm,armv8-timer";
-				interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
-					     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
-					     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
-					     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>;
+				interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+					     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+					     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+					     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
 			};
 
 			odmi: odmi@300000 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index d02a900378e1..4f44d1191bfd 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -270,6 +270,8 @@
 		#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";
 	};
 
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
index c223915f0907..d73bdc8c9115 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
@@ -129,10 +129,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <1 13 0xf01>,
-			     <1 14 0xf01>,
-			     <1 11 0xf01>,
-			     <1 10 0xf01>;
+		interrupts = <1 13 4>,
+			     <1 14 4>,
+			     <1 11 4>,
+			     <1 10 4>;
 	};
 
 	soc {
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index e595f22e7e4b..3e2e51fbd2bc 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -65,10 +65,10 @@
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupt-parent = <&gic>;
-		interrupts = <1 13 0xf01>,
-			     <1 14 0xf01>,
-			     <1 11 0xf01>,
-			     <1 10 0xf01>;
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
 	};
 
 	amba_apu {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 0555b7caaf2c..eadf4855ad2d 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1,4 +1,3 @@
-# CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
@@ -15,10 +14,14 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_HUGETLB=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_NET_NS is not set
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
@@ -71,6 +74,7 @@ CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_SECCOMP=y
 CONFIG_XEN=y
 CONFIG_KEXEC=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
@@ -84,10 +88,37 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
+CONFIG_IPV6=m
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_TARGET_MASQUERADE=m
+CONFIG_BRIDGE=m
+CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
+CONFIG_VLAN_8021Q_MVRP=y
 CONFIG_BPF_JIT=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
@@ -103,6 +134,7 @@ CONFIG_MTD=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=m
 CONFIG_VIRTIO_BLK=y
 CONFIG_SRAM=y
 # CONFIG_SCSI_PROC_FS is not set
@@ -120,7 +152,10 @@ CONFIG_SATA_SIL24=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
+CONFIG_MACVLAN=m
+CONFIG_MACVTAP=m
 CONFIG_TUN=y
+CONFIG_VETH=m
 CONFIG_VIRTIO_NET=y
 CONFIG_AMD_XGBE=y
 CONFIG_NET_XGENE=y
@@ -350,12 +385,16 @@ CONFIG_EXYNOS_ADC=y
 CONFIG_PWM_SAMSUNG=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
 CONFIG_AUTOFS4_FS=y
-CONFIG_FUSE_FS=y
-CONFIG_CUSE=y
+CONFIG_FUSE_FS=m
+CONFIG_CUSE=m
+CONFIG_OVERLAY_FS=m
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 61b49150dfa3..1737aecfcc5e 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -22,7 +22,6 @@
 
 #define __ARCH_WANT_KPROBES_INSN_SLOT
 #define MAX_INSN_SIZE			1
-#define MAX_STACK_SIZE			128
 
 #define flush_insn_slot(p)		do { } while (0)
 #define kretprobe_blacklist_size	0
@@ -47,7 +46,6 @@ struct kprobe_ctlblk {
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
 	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 0a456bef8c79..2fee2f59288c 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -199,19 +199,19 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 #define _percpu_read(pcp)						\
 ({									\
 	typeof(pcp) __retval;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), 	\
 					      sizeof(pcp));		\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	__retval;							\
 })
 
 #define _percpu_write(pcp, val)						\
 do {									\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), 	\
 				sizeof(pcp));				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 } while(0)								\
 
 #define _pcp_protect(operation, pcp, val)			\
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index e875a5a551d7..89206b568cd4 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -363,4 +363,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock()	smp_mb()
+
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 5e834d10b291..c47257c91b77 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -265,22 +265,25 @@ extern unsigned long __must_check __clear_user(void __user *addr, unsigned long
 static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	kasan_check_write(to, n);
-	return  __arch_copy_from_user(to, from, n);
+	check_object_size(to, n, false);
+	return __arch_copy_from_user(to, from, n);
 }
 
 static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	kasan_check_read(from, n);
-	return  __arch_copy_to_user(to, from, n);
+	check_object_size(from, n, true);
+	return __arch_copy_to_user(to, from, n);
 }
 
 static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	kasan_check_write(to, n);
 
-	if (access_ok(VERIFY_READ, from, n))
+	if (access_ok(VERIFY_READ, from, n)) {
+		check_object_size(to, n, false);
 		n = __arch_copy_from_user(to, from, n);
-	else /* security hole - plug it */
+	} else /* security hole - plug it */
 		memset(to, 0, n);
 	return n;
 }
@@ -289,8 +292,10 @@ static inline unsigned long __must_check copy_to_user(void __user *to, const voi
 {
 	kasan_check_read(from, n);
 
-	if (access_ok(VERIFY_WRITE, to, n))
+	if (access_ok(VERIFY_WRITE, to, n)) {
+		check_object_size(from, n, true);
 		n = __arch_copy_to_user(to, from, n);
+	}
 	return n;
 }
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 96e4a2b64cc1..441420ca7d08 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -353,6 +353,8 @@ el1_sync:
 	lsr	x24, x1, #ESR_ELx_EC_SHIFT	// exception class
 	cmp	x24, #ESR_ELx_EC_DABT_CUR	// data abort in EL1
 	b.eq	el1_da
+	cmp	x24, #ESR_ELx_EC_IABT_CUR	// instruction abort in EL1
+	b.eq	el1_ia
 	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
 	b.eq	el1_undef
 	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
@@ -364,6 +366,11 @@ el1_sync:
 	cmp	x24, #ESR_ELx_EC_BREAKPT_CUR	// debug exception in EL1
 	b.ge	el1_dbg
 	b	el1_inv
+
+el1_ia:
+	/*
+	 * Fall through to the Data abort case
+	 */
 el1_da:
 	/*
 	 * Data abort handling
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b77f58355da1..3e7b050e99dc 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -757,6 +757,9 @@ ENTRY(__enable_mmu)
 	isb
 	bl	__create_page_tables		// recreate kernel mapping
 
+	tlbi	vmalle1				// Remove any stale TLB entries
+	dsb	nsh
+
 	msr	sctlr_el1, x19			// re-enable the MMU
 	isb
 	ic	iallu				// flush instructions fetched
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 21ab5df9fa76..65d81f965e74 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -35,6 +35,7 @@
 #include <asm/sections.h>
 #include <asm/smp.h>
 #include <asm/suspend.h>
+#include <asm/sysreg.h>
 #include <asm/virt.h>
 
 /*
@@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	set_pte(pte, __pte(virt_to_phys((void *)dst) |
 			 pgprot_val(PAGE_KERNEL_EXEC)));
 
-	/* Load our new page tables */
-	asm volatile("msr	ttbr0_el1, %0;"
-		     "isb;"
-		     "tlbi	vmalle1is;"
-		     "dsb	ish;"
-		     "isb" : : "r"(virt_to_phys(pgd)));
+	/*
+	 * Load our new page tables. A strict BBM approach requires that we
+	 * ensure that TLBs are free of any entries that may overlap with the
+	 * global mappings we are about to install.
+	 *
+	 * For a real hibernate/resume cycle TTBR0 currently points to a zero
+	 * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
+	 * runtime services), while for a userspace-driven test_resume cycle it
+	 * points to userspace page tables (and we must point it at a zero page
+	 * ourselves). Elsewhere we only (un)install the idmap with preemption
+	 * disabled, so T0SZ should be as required regardless.
+	 */
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
 
@@ -394,6 +405,38 @@ int swsusp_arch_resume(void)
 					  void *, phys_addr_t, phys_addr_t);
 
 	/*
+	 * Restoring the memory image will overwrite the ttbr1 page tables.
+	 * Create a second copy of just the linear map, and use this when
+	 * restoring.
+	 */
+	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!tmp_pg_dir) {
+		pr_err("Failed to allocate memory for temporary page tables.");
+		rc = -ENOMEM;
+		goto out;
+	}
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	if (rc)
+		goto out;
+
+	/*
+	 * Since we only copied the linear map, we need to find restore_pblist's
+	 * linear map address.
+	 */
+	lm_restore_pblist = LMADDR(restore_pblist);
+
+	/*
+	 * We need a zero page that is zero before & after resume in order to
+	 * to break before make on the ttbr1 page tables.
+	 */
+	zero_page = (void *)get_safe_page(GFP_ATOMIC);
+	if (!zero_page) {
+		pr_err("Failed to allocate zero page.");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/*
 	 * Locate the exit code in the bottom-but-one page, so that *NULL
 	 * still has disastrous affects.
 	 */
@@ -419,27 +462,6 @@ int swsusp_arch_resume(void)
 	__flush_dcache_area(hibernate_exit, exit_size);
 
 	/*
-	 * Restoring the memory image will overwrite the ttbr1 page tables.
-	 * Create a second copy of just the linear map, and use this when
-	 * restoring.
-	 */
-	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!tmp_pg_dir) {
-		pr_err("Failed to allocate memory for temporary page tables.");
-		rc = -ENOMEM;
-		goto out;
-	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
-	if (rc)
-		goto out;
-
-	/*
-	 * Since we only copied the linear map, we need to find restore_pblist's
-	 * linear map address.
-	 */
-	lm_restore_pblist = LMADDR(restore_pblist);
-
-	/*
 	 * KASLR will cause the el2 vectors to be in a different location in
 	 * the resumed kernel. Load hibernate's temporary copy into el2.
 	 *
@@ -453,12 +475,6 @@ int swsusp_arch_resume(void)
 		__hyp_set_vectors(el2_vectors);
 	}
 
-	/*
-	 * We need a zero page that is zero before & after resume in order to
-	 * to break before make on the ttbr1 page tables.
-	 */
-	zero_page = (void *)get_safe_page(GFP_ATOMIC);
-
 	hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
 		       resume_hdr.reenter_kernel, lm_restore_pblist,
 		       resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index bf9768588288..c6b0f40620d8 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -41,18 +41,6 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 static void __kprobes
 post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
 
-static inline unsigned long min_stack_size(unsigned long addr)
-{
-	unsigned long size;
-
-	if (on_irq_stack(addr, raw_smp_processor_id()))
-		size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr;
-	else
-		size = (unsigned long)current_thread_info() + THREAD_START_SP - addr;
-
-	return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack));
-}
-
 static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
 {
 	/* prepare insn slot */
@@ -489,20 +477,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_ptr = kernel_stack_pointer(regs);
 
 	kcb->jprobe_saved_regs = *regs;
 	/*
-	 * As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
+	 * Since we can't be sure where in the stack frame "stacked"
+	 * pass-by-value arguments are stored we just don't try to
+	 * duplicate any of the stack. Do not use jprobes on functions that
+	 * use more than 64 bytes (after padding each to an 8 byte boundary)
+	 * of arguments, or pass individual arguments larger than 16 bytes.
 	 */
-	kasan_disable_current();
-	memcpy(kcb->jprobes_stack, (void *)stack_ptr,
-	       min_stack_size(stack_ptr));
-	kasan_enable_current();
 
 	instruction_pointer_set(regs, (unsigned long) jp->entry);
 	preempt_disable();
@@ -554,10 +537,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	unpause_graph_tracing();
 	*regs = kcb->jprobe_saved_regs;
-	kasan_disable_current();
-	memcpy((void *)stack_addr, kcb->jprobes_stack,
-	       min_stack_size(stack_addr));
-	kasan_enable_current();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 9a3aec97ac09..ccf79d849e0a 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -101,12 +101,20 @@ ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 	/* enable the MMU early - so we can access sleep_save_stash by va */
 	adr_l	lr, __enable_mmu	/* __cpu_setup will return here */
-	ldr	x27, =_cpu_resume	/* __enable_mmu will branch here */
+	adr_l	x27, _resume_switched	/* __enable_mmu will branch here */
 	adrp	x25, idmap_pg_dir
 	adrp	x26, swapper_pg_dir
 	b	__cpu_setup
 ENDPROC(cpu_resume)
 
+	.pushsection	".idmap.text", "ax"
+_resume_switched:
+	ldr	x8, =_cpu_resume
+	br	x8
+ENDPROC(_resume_switched)
+	.ltorg
+	.popsection
+
 ENTRY(_cpu_resume)
 	mrs	x1, mpidr_el1
 	adrp	x8, mpidr_hash
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 76a6d9263908..d93d43352504 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -661,9 +661,9 @@ void __init smp_init_cpus(void)
 		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
 				      acpi_parse_gic_cpu_interface, 0);
 
-	if (cpu_count > NR_CPUS)
-		pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
-			cpu_count, NR_CPUS);
+	if (cpu_count > nr_cpu_ids)
+		pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n",
+			cpu_count, nr_cpu_ids);
 
 	if (!bootcpu_valid) {
 		pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
@@ -677,7 +677,7 @@ void __init smp_init_cpus(void)
 	 * with entries in cpu_logical_map while initializing the cpus.
 	 * If the cpu set-up fails, invalidate the cpu_logical_map entry.
 	 */
-	for (i = 1; i < NR_CPUS; i++) {
+	for (i = 1; i < nr_cpu_ids; i++) {
 		if (cpu_logical_map(i) != INVALID_HWID) {
 			if (smp_cpu_setup(i))
 				cpu_logical_map(i) = INVALID_HWID;
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index ae7855f16ec2..5a84b4562603 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -256,7 +256,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to Cortex-A57 erratum #852523.
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_guest_state(guest_ctxt);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index b0b225ceca18..e51367d159d0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -823,14 +823,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
  *
- * We could trap ID_DFR0 and tell the guest we don't support performance
- * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
- * NAKed, so it will read the PMCR anyway.
- *
- * Therefore we tell the guest we have 0 counters.  Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
- *
  * Debug handling: We do trap most, if not all debug related system
  * registers. The implementation is good enough to ensure that a guest
  * can use these with minimal performance degradation. The drawback is
@@ -1360,7 +1352,7 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
 
 	/* ICC_SRE */
-	{ Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
+	{ Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre },
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
 
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index f94b80eb295d..9c3e75df2180 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -242,7 +242,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 
 static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
 {
-	pte_t *pte = pte_offset_kernel(pmd, 0);
+	pte_t *pte = pte_offset_kernel(pmd, 0UL);
 	unsigned long addr;
 	unsigned i;
 
@@ -254,7 +254,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
 
 static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 {
-	pmd_t *pmd = pmd_offset(pud, 0);
+	pmd_t *pmd = pmd_offset(pud, 0UL);
 	unsigned long addr;
 	unsigned i;
 
@@ -271,7 +271,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 
 static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 {
-	pud_t *pud = pud_offset(pgd, 0);
+	pud_t *pud = pud_offset(pgd, 0UL);
 	unsigned long addr;
 	unsigned i;
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c8beaa0da7df..05d2bd776c69 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -153,6 +153,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 }
 #endif
 
+static bool is_el1_instruction_abort(unsigned int esr)
+{
+	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
+}
+
 /*
  * The kernel tried to access some page that wasn't present.
  */
@@ -161,8 +166,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
 {
 	/*
 	 * Are we prepared to handle this kernel fault?
+	 * We are almost certainly not prepared to handle instruction faults.
 	 */
-	if (fixup_exception(regs))
+	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
 		return;
 
 	/*
@@ -267,7 +273,8 @@ static inline bool is_permission_fault(unsigned int esr)
 	unsigned int ec       = ESR_ELx_EC(esr);
 	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
 
-	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
+	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
+	       (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -312,6 +319,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
+		if (is_el1_instruction_abort(esr))
+			die("Attempting to execute userspace memory", regs, esr);
+
 		if (!search_exception_tables(regs->pc))
 			die("Accessing user space memory outside uaccess.h routines", regs, esr);
 	}
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index c7fe3ec70774..5bb15eab6f00 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -23,6 +23,8 @@
 #include <linux/module.h>
 #include <linux/of.h>
 
+#include <asm/acpi.h>
+
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 nodemask_t numa_nodes_parsed __initdata;
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 5bb61de23201..9d37e967fa19 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -100,7 +100,16 @@ ENTRY(cpu_do_resume)
 
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
+
+	/*
+	 * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking
+	 * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug
+	 * exception. Mask them until local_dbg_restore() in cpu_suspend()
+	 * resets them.
+	 */
+	disable_dbg
 	msr	mdscr_el1, x10
+
 	msr	sctlr_el1, x12
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index 68cf638faf48..b1ec1fa06463 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -74,7 +74,7 @@ extern __kernel_size_t __copy_user(void *to, const void *from,
 
 extern __kernel_size_t copy_to_user(void __user *to, const void *from,
 				    __kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
 				      __kernel_size_t n);
 
 static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
@@ -88,6 +88,15 @@ static inline __kernel_size_t __copy_from_user(void *to,
 {
 	return __copy_user(to, (const void __force *)from, n);
 }
+static inline __kernel_size_t copy_from_user(void *to,
+					       const void __user *from,
+					       __kernel_size_t n)
+{
+	size_t res = ___copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
+}
 
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c
index d93ead02daed..7c6cf14f0985 100644
--- a/arch/avr32/kernel/avr32_ksyms.c
+++ b/arch/avr32/kernel/avr32_ksyms.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL(copy_page);
 /*
  * Userspace access stuff.
  */
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
 EXPORT_SYMBOL(copy_to_user);
 EXPORT_SYMBOL(__copy_user);
 EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/avr32/lib/copy_user.S b/arch/avr32/lib/copy_user.S
index ea59c04b07de..075373471da1 100644
--- a/arch/avr32/lib/copy_user.S
+++ b/arch/avr32/lib/copy_user.S
@@ -23,13 +23,13 @@
 	 */
 	.text
 	.align	1
-	.global	copy_from_user
-	.type	copy_from_user, @function
-copy_from_user:
+	.global	___copy_from_user
+	.type	___copy_from_user, @function
+___copy_from_user:
 	branch_if_kernel r8, __copy_user
 	ret_if_privileged r8, r11, r10, r10
 	rjmp	__copy_user
-	.size	copy_from_user, . - copy_from_user
+	.size	___copy_from_user, . - ___copy_from_user
 
 	.global	copy_to_user
 	.type	copy_to_user, @function
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 12f5d6851bbc..0a2a70096d8b 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -171,11 +171,12 @@ static inline int bad_user_access_length(void)
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n))) {
 		memcpy(to, (const void __force *)from, n);
-	else
-		return n;
-	return 0;
+		return 0;
+	}
+	memset(to, 0, n);
+	return n;
 }
 
 static inline unsigned long __must_check
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index c6db52ba3a06..10c57771822d 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index f35525b55819..57d1c43726d9 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };
diff --git a/arch/cris/include/asm/uaccess.h b/arch/cris/include/asm/uaccess.h
index e3530d0f13ee..56c7d5750abd 100644
--- a/arch/cris/include/asm/uaccess.h
+++ b/arch/cris/include/asm/uaccess.h
@@ -194,30 +194,6 @@ extern unsigned long __copy_user(void __user *to, const void *from, unsigned lon
 extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
 extern unsigned long __do_clear_user(void __user *to, unsigned long n);
 
-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_user(to, from, n);
-	return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_user_zeroing(to, from, n);
-	return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __do_clear_user(to, n);
-	return n;
-}
-
 static inline long
 __strncpy_from_user(char *dst, const char __user *src, long count)
 {
@@ -282,7 +258,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_from_user_24(to, from, ret);
 	else
-		ret = __generic_copy_from_user(to, from, n);
+		ret = __copy_user_zeroing(to, from, n);
 
 	return ret;
 }
@@ -333,7 +309,7 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_to_user_24(to, from, ret);
 	else
-		ret = __generic_copy_to_user(to, from, n);
+		ret = __copy_user(to, from, n);
 
 	return ret;
 }
@@ -366,26 +342,43 @@ __constant_clear_user(void __user *to, unsigned long n)
 	else if (n == 24)
 		__asm_clear_24(to, ret);
 	else
-		ret = __generic_clear_user(to, n);
+		ret = __do_clear_user(to, n);
 
 	return ret;
 }
 
 
-#define clear_user(to, n)				\
-	(__builtin_constant_p(n) ?			\
-	 __constant_clear_user(to, n) :			\
-	 __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+	if (__builtin_constant_p(n))
+		return __constant_clear_user(to, n);
+	else
+		return __do_clear_user(to, n);
+}
 
-#define copy_from_user(to, from, n)			\
-	(__builtin_constant_p(n) ?			\
-	 __constant_copy_from_user(to, from, n) :	\
-	 __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+		memset(to, 0, n);
+		return n;
+	}
+	if (__builtin_constant_p(n))
+		return __constant_copy_from_user(to, from, n);
+	else
+		return __copy_user_zeroing(to, from, n);
+}
 
-#define copy_to_user(to, from, n)			\
-	(__builtin_constant_p(n) ?			\
-	 __constant_copy_to_user(to, from, n) :		\
-	 __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+	if (__builtin_constant_p(n))
+		return __constant_copy_to_user(to, from, n);
+	else
+		return __copy_user(to, from, n);
+}
 
 /* We let the __ versions of copy_from/to_user inline, because they're often
  * used in fast paths and have only a small space overhead.
diff --git a/arch/frv/include/asm/uaccess.h b/arch/frv/include/asm/uaccess.h
index 3ac9a59d65d4..87d9e34c5df8 100644
--- a/arch/frv/include/asm/uaccess.h
+++ b/arch/frv/include/asm/uaccess.h
@@ -263,19 +263,25 @@ do {							\
 extern long __memset_user(void *dst, unsigned long count);
 extern long __memcpy_user(void *dst, const void *src, unsigned long count);
 
-#define clear_user(dst,count)			__memset_user(____force(dst), (count))
+#define __clear_user(dst,count)			__memset_user(____force(dst), (count))
 #define __copy_from_user_inatomic(to, from, n)	__memcpy_user((to), ____force(from), (n))
 #define __copy_to_user_inatomic(to, from, n)	__memcpy_user(____force(to), (from), (n))
 
 #else
 
-#define clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
 #define __copy_from_user_inatomic(to, from, n)	(memcpy((to), ____force(from), (n)), 0)
 #define __copy_to_user_inatomic(to, from, n)	(memcpy(____force(to), (from), (n)), 0)
 
 #endif
 
-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+	if (likely(__access_ok(to, n)))
+		n = __clear_user(to, n);
+	return n;
+}
 
 static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h
index 2e221c5f0203..f86918aed9e1 100644
--- a/arch/h8300/include/asm/io.h
+++ b/arch/h8300/include/asm/io.h
@@ -3,6 +3,8 @@
 
 #ifdef __KERNEL__
 
+#include <linux/types.h>
+
 /* H8/300 internal I/O functions */
 
 #define __raw_readb __raw_readb
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index f000a382bc7f..f61cfb28e9f2 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -103,7 +103,8 @@ static inline long hexagon_strncpy_from_user(char *dst, const char __user *src,
 {
 	long res = __strnlen_user(src, n);
 
-	/* return from strnlen can't be zero -- that would be rubbish. */
+	if (unlikely(!res))
+		return -EFAULT;
 
 	if (res > n) {
 		copy_from_user(dst, src, n);
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 6a15083cc366..18ca6a9ce566 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -52,6 +52,7 @@ config IA64
 	select MODULES_USE_ELF_RELA
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HARDENED_USERCOPY
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 2189d5ddc1ee..bfe13196f770 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -241,12 +241,16 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use
 static inline unsigned long
 __copy_to_user (void __user *to, const void *from, unsigned long count)
 {
+	check_object_size(from, count, true);
+
 	return __copy_user(to, (__force void __user *) from, count);
 }
 
 static inline unsigned long
 __copy_from_user (void *to, const void __user *from, unsigned long count)
 {
+	check_object_size(to, count, false);
+
 	return __copy_user((__force void __user *) to, from, count);
 }
 
@@ -258,22 +262,23 @@ __copy_from_user (void *to, const void __user *from, unsigned long count)
 	const void *__cu_from = (from);							\
 	long __cu_len = (n);								\
 											\
-	if (__access_ok(__cu_to, __cu_len, get_fs()))					\
-		__cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len);	\
+	if (__access_ok(__cu_to, __cu_len, get_fs())) {					\
+		check_object_size(__cu_from, __cu_len, true);			\
+		__cu_len = __copy_user(__cu_to, (__force void __user *)  __cu_from, __cu_len);	\
+	}										\
 	__cu_len;									\
 })
 
-#define copy_from_user(to, from, n)							\
-({											\
-	void *__cu_to = (to);								\
-	const void __user *__cu_from = (from);						\
-	long __cu_len = (n);								\
-											\
-	__chk_user_ptr(__cu_from);							\
-	if (__access_ok(__cu_from, __cu_len, get_fs()))					\
-		__cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len);	\
-	__cu_len;									\
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	check_object_size(to, n, false);
+	if (likely(__access_ok(from, n, get_fs())))
+		n = __copy_user((__force void __user *) to, from, n);
+	else
+		memset(to, 0, n);
+	return n;
+}
 
 #define __copy_in_user(to, from, size)	__copy_user((to), (from), (size))
 
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index cac7014daef3..6f8982157a75 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -219,7 +219,7 @@ extern int fixup_exception(struct pt_regs *regs);
 #define __get_user_nocheck(x, ptr, size)				\
 ({									\
 	long __gu_err = 0;						\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	might_fault();							\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err);		\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 2dcee3a88867..9202f82dfce6 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -213,7 +213,6 @@ static inline int frame_extra_sizes(int f)
 
 static inline void adjustformat(struct pt_regs *regs)
 {
-	((struct switch_stack *)regs - 1)->a5 = current->mm->start_data;
 	/*
 	 * set format byte to make stack appear modulo 4, which it will
 	 * be when doing the rte
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 8282cbce7e39..273e61225c27 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -204,8 +204,9 @@ extern unsigned long __must_check __copy_user_zeroing(void *to,
 static inline unsigned long
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n)))
 		return __copy_user_zeroing(to, from, n);
+	memset(to, 0, n);
 	return n;
 }
 
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index 11fa51c89617..c0ec116b3993 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -390,7 +390,6 @@ void __init mem_init(void)
 
 	free_all_bootmem();
 	mem_init_print_info(NULL);
-	show_mem(0);
 }
 
 void free_initmem(void)
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 331b0d35f89c..826676778094 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -227,7 +227,7 @@ extern long __user_bad(void);
 
 #define __get_user(x, ptr)						\
 ({									\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	/*unsigned long __gu_ptr = (unsigned long)(ptr);*/		\
 	long __gu_err;							\
 	switch (sizeof(*(ptr))) {					\
@@ -373,10 +373,13 @@ extern long __user_bad(void);
 static inline long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long res = n;
 	might_fault();
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_from_user(to, from, n);
-	return n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 #define __copy_to_user(to, from, n)	\
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ea0cd9773914..5f987598054f 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -164,7 +164,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
  */
 static inline unsigned long ___pa(unsigned long x)
 {
-	if (config_enabled(CONFIG_64BIT)) {
+	if (IS_ENABLED(CONFIG_64BIT)) {
 		/*
 		 * For MIPS64 the virtual address may either be in one of
 		 * the compatibility segements ckseg0 or ckseg1, or it may
@@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x)
 		return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x);
 	}
 
-	if (!config_enabled(CONFIG_EVA)) {
+	if (!IS_ENABLED(CONFIG_EVA)) {
 		/*
 		 * We're using the standard MIPS32 legacy memory map, ie.
 		 * the address x is going to be in kseg0 or kseg1. We can
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 11b965f98d95..21a2aaba20d5 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/thread_info.h>
+#include <linux/string.h>
 #include <asm/asm-eva.h>
 
 /*
@@ -1170,6 +1171,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
 			__cu_len = __invoke_copy_from_user(__cu_to,	\
 							   __cu_from,	\
 							   __cu_len);   \
+		} else {						\
+			memset(__cu_to, 0, __cu_len);			\
 		}							\
 	}								\
 	__cu_len;							\
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 6eb52b9c9818..e788515f766b 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1642,8 +1642,14 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
 
 	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;
@@ -1680,12 +1686,18 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
 								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);
+			}
+			/*
+			 * We fault an entry from the guest tlb to the
+			 * shadow host TLB
+			 */
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+				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 {
@@ -2659,7 +2671,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 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);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+				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/mmu.c b/arch/mips/kvm/mmu.c
index 57319ee57c4f..121008c0fcc9 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -40,7 +40,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	pfn = gfn_to_pfn(kvm, gfn);
 
-	if (is_error_pfn(pfn)) {
+	if (is_error_noslot_pfn(pfn)) {
 		kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn);
 		err = -EFAULT;
 		goto out;
@@ -99,7 +99,7 @@ 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();
@@ -138,35 +138,49 @@ 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;
 	kvm_pfn_t pfn0, pfn1;
+	gfn_t gfn0, gfn1;
+	long tlb_lo[2];
 	int ret;
 
-	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
-		pfn0 = 0;
-		pfn1 = 0;
-	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0])
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1])
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		pfn0 = kvm->arch.guest_pmap[
-			mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT];
-		pfn1 = kvm->arch.guest_pmap[
-			mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT];
+	tlb_lo[0] = tlb->tlb_lo[0];
+	tlb_lo[1] = tlb->tlb_lo[1];
+
+	/*
+	 * 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];
+
 	/* Get attributes from the Guest TLB */
 	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) |
 		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
-		(tlb->tlb_lo[0] & ENTRYLO_D) |
-		(tlb->tlb_lo[0] & ENTRYLO_V);
+		(tlb_lo[0] & ENTRYLO_D) |
+		(tlb_lo[0] & ENTRYLO_V);
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) |
 		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
-		(tlb->tlb_lo[1] & ENTRYLO_D) |
-		(tlb->tlb_lo[1] & ENTRYLO_V);
+		(tlb_lo[1] & ENTRYLO_D) |
+		(tlb_lo[1] & ENTRYLO_V);
 
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo[0], tlb->tlb_lo[1]);
@@ -354,9 +368,15 @@ u32 kvm_get_inst(u32 *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]);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+						&vcpu->arch.guest_tlb[index])) {
+				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/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 20f7bf6de384..d012e877a95a 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -166,6 +166,7 @@ struct __large_struct { unsigned long buf[100]; };
 		"2:\n"						\
 		"	.section	.fixup,\"ax\"\n"	\
 		"3:\n\t"					\
+		"	mov		0,%1\n"			\
 		"	mov		%3,%0\n"		\
 		"	jmp		2b\n"			\
 		"	.previous\n"				\
diff --git a/arch/mn10300/lib/usercopy.c b/arch/mn10300/lib/usercopy.c
index 7826e6c364e7..ce8899e5e171 100644
--- a/arch/mn10300/lib/usercopy.c
+++ b/arch/mn10300/lib/usercopy.c
@@ -9,7 +9,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the Licence, or (at your option) any later version.
  */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long
 __generic_copy_to_user(void *to, const void *from, unsigned long n)
@@ -24,6 +24,8 @@ __generic_copy_from_user(void *to, const void *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n))
 		__copy_user_zeroing(to, from, n);
+	else
+		memset(to, 0, n);
 	return n;
 }
 
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index caa51ff85a3c..0ab82324c817 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -102,9 +102,12 @@ extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
 static inline long copy_from_user(void *to, const void __user *from,
 				unsigned long n)
 {
-	if (!access_ok(VERIFY_READ, from, n))
-		return n;
-	return __copy_from_user(to, from, n);
+	unsigned long res = n;
+	if (access_ok(VERIFY_READ, from, n))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline long copy_to_user(void __user *to, const void *from,
@@ -139,7 +142,7 @@ extern long strnlen_user(const char __user *s, long n);
 
 #define __get_user_unknown(val, size, ptr, err) do {			\
 	err = 0;							\
-	if (copy_from_user(&(val), ptr, size)) {			\
+	if (__copy_from_user(&(val), ptr, size)) {			\
 		err = -EFAULT;						\
 	}								\
 	} while (0)
@@ -166,7 +169,7 @@ do {									\
 	({								\
 	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
 	(x) = (__force __typeof__(x))__gu_val;				\
 	__gu_err;							\
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index a6bd07ca3d6c..5cc6b4f1b795 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -273,28 +273,20 @@ __copy_tofrom_user(void *to, const void *from, unsigned long size);
 static inline unsigned long
 copy_from_user(void *to, const void *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_tofrom_user(to, from, n);
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + n - TASK_SIZE;
-		return __copy_tofrom_user(to, from, n - over) + over;
-	}
-	return n;
+	unsigned long res = n;
+
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_tofrom_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline unsigned long
 copy_to_user(void *to, const void *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_tofrom_user(to, from, n);
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + n - TASK_SIZE;
-		return __copy_tofrom_user(to, from, n - over) + over;
-	}
+	if (likely(access_ok(VERIFY_WRITE, to, n)))
+		n = __copy_tofrom_user(to, from, n);
 	return n;
 }
 
@@ -303,13 +295,8 @@ extern unsigned long __clear_user(void *addr, unsigned long size);
 static inline __must_check unsigned long
 clear_user(void *addr, unsigned long size)
 {
-
-	if (access_ok(VERIFY_WRITE, addr, size))
-		return __clear_user(addr, size);
-	if ((unsigned long)addr < TASK_SIZE) {
-		unsigned long over = (unsigned long)addr + size - TASK_SIZE;
-		return __clear_user(addr, size - over) + over;
-	}
+	if (likely(access_ok(VERIFY_WRITE, addr, size)))
+		size = __clear_user(addr, size);
 	return size;
 }
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index cd8778103165..af12c2db9bb8 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -1,6 +1,5 @@
 config PARISC
 	def_bool y
-	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select HAVE_IDE
 	select HAVE_OPROFILE
diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig
index 1a8f6f95689e..f6a4c016304b 100644
--- a/arch/parisc/configs/c8000_defconfig
+++ b/arch/parisc/configs/c8000_defconfig
@@ -245,7 +245,6 @@ CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_PROVE_RCU_DELAY=y
 CONFIG_DEBUG_BLOCK_EXT_DEVT=y
 CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_KEYS=y
 # CONFIG_CRYPTO_HW is not set
 CONFIG_FONTS=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index 7e0792658952..c564e6e1fa23 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -291,7 +291,6 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 0f59fd9ca205..482847865dac 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -10,6 +10,7 @@
 #include <asm-generic/uaccess-unaligned.h>
 
 #include <linux/bug.h>
+#include <linux/string.h>
 
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
@@ -208,26 +209,30 @@ unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned lo
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
-extern void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-        __compiletime_error("copy_from_user() buffer size is not provably correct")
-#else
-        __compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
 
 static inline unsigned long __must_check copy_from_user(void *to,
                                           const void __user *from,
                                           unsigned long n)
 {
         int sz = __compiletime_object_size(to);
-        int ret = -EFAULT;
+        unsigned long ret = n;
 
-        if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n))
+        if (likely(sz == -1 || sz >= n))
                 ret = __copy_from_user(to, from, n);
-        else
-                copy_from_user_overflow();
+        else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
+	else
+                __bad_copy_user();
 
+	if (unlikely(ret))
+		memset(to + (n - ret), 0, ret);
         return ret;
 }
 
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/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index 5adc339eb7c8..0c2a94a0f751 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -51,8 +51,6 @@ EXPORT_SYMBOL(_parisc_requires_coherency);
 
 DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data);
 
-extern int update_cr16_clocksource(void);	/* from time.c */
-
 /*
 **  	PARISC CPU driver - claim "device" and initialize CPU data structures.
 **
@@ -228,12 +226,6 @@ static int processor_probe(struct parisc_device *dev)
 	}
 #endif
 
-	/* If we've registered more than one cpu,
-	 * we'll use the jiffies clocksource since cr16
-	 * is not synchronized between CPUs.
-	 */
-	update_cr16_clocksource();
-
 	return 0;
 }
 
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 505cf1ac5af2..4b0b963d52a7 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -221,18 +221,6 @@ static struct clocksource clocksource_cr16 = {
 	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-int update_cr16_clocksource(void)
-{
-	/* since the cr16 cycle counters are not synchronized across CPUs,
-	   we'll check if we should switch to a safe clocksource: */
-	if (clocksource_cr16.rating != 0 && num_online_cpus() > 1) {
-		clocksource_change_rating(&clocksource_cr16, 0);
-		return 1;
-	}
-
-	return 0;
-}
-
 void __init start_cpu_itimer(void)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ec4047e170a0..927d2ab2ce08 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -166,6 +166,7 @@ config PPC
 	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select GENERIC_CPU_AUTOPROBE
 	select HAVE_VIRT_CPU_ACCOUNTING
+	select HAVE_ARCH_HARDENED_USERCOPY
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index ca254546cd05..1934707bf321 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -66,29 +66,28 @@ endif
 UTS_MACHINE := $(OLDARCH)
 
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-override CC	+= -mlittle-endian
-ifneq ($(cc-name),clang)
-override CC	+= -mno-strict-align
-endif
-override AS	+= -mlittle-endian
 override LD	+= -EL
-override CROSS32CC += -mlittle-endian
 override CROSS32AS += -mlittle-endian
 LDEMULATION	:= lppc
 GNUTARGET	:= powerpcle
 MULTIPLEWORD	:= -mno-multiple
 KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect)
 else
-ifeq ($(call cc-option-yn,-mbig-endian),y)
-override CC	+= -mbig-endian
-override AS	+= -mbig-endian
-endif
 override LD	+= -EB
 LDEMULATION	:= ppc
 GNUTARGET	:= powerpc
 MULTIPLEWORD	:= -mmultiple
 endif
 
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
+ifneq ($(cc-name),clang)
+  cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
+endif
+
+aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
+
 ifeq ($(HAS_BIARCH),y)
 override AS	+= -a$(CONFIG_WORD_SIZE)
 override LD	+= -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION)
@@ -232,6 +231,9 @@ cpu-as-$(CONFIG_E200)		+= -Wa,-me200
 KBUILD_AFLAGS += $(cpu-as-y)
 KBUILD_CFLAGS += $(cpu-as-y)
 
+KBUILD_AFLAGS += $(aflags-y)
+KBUILD_CFLAGS += $(cflags-y)
+
 head-y				:= arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o
 head-$(CONFIG_8xx)		:= arch/powerpc/kernel/head_8xx.o
 head-$(CONFIG_40x)		:= arch/powerpc/kernel/head_40x.o
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index bfe3d37a24ef..9fa046d56eba 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -4,6 +4,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/cpufeature.h>
 #include <asm/switch_to.h>
 
 #define CHKSUM_BLOCK_SIZE	1
@@ -157,7 +158,7 @@ static void __exit crc32c_vpmsum_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(crc32c_vpmsum_mod_init);
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init);
 module_exit(crc32c_vpmsum_mod_fini);
 
 MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 2ef55f8968a2..b312b152461b 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -15,7 +15,7 @@ static inline bool early_cpu_has_feature(unsigned long feature)
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
 #include <linux/jump_label.h>
 
-#define NUM_CPU_FTR_KEYS	64
+#define NUM_CPU_FTR_KEYS	BITS_PER_LONG
 
 extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS];
 
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 3d7fc06532a1..01b8a13f0224 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -19,4 +19,17 @@ extern u64 pnv_first_deep_stop_state;
 
 #endif
 
+/* Idle state entry routines */
+#ifdef	CONFIG_PPC_P7_NAP
+#define	IDLE_STATE_ENTER_SEQ(IDLE_INST)				\
+	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
+	std	r0,0(r1);					\
+	ptesync;						\
+	ld	r0,0(r1);					\
+1:	cmp	cr0,r0,r0;					\
+	bne	1b;						\
+	IDLE_INST;						\
+	b	.
+#endif /* CONFIG_PPC_P7_NAP */
+
 #endif
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 666bef4ebfae..9377bdf42eb8 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -3,6 +3,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
+#include <asm/cpu_has_feature.h>
 
 /*
  * Mapping of threads to cores
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 57fec8ac7b92..ddf54f5bbdd1 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -186,6 +186,7 @@ label##3:					       	\
 
 #ifndef __ASSEMBLY__
 void apply_feature_fixups(void);
+void setup_feature_keys(void);
 #endif
 
 #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */
diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h
index 88b4901ac4ee..85b7a1a21e22 100644
--- a/arch/powerpc/include/asm/hmi.h
+++ b/arch/powerpc/include/asm/hmi.h
@@ -21,7 +21,7 @@
 #ifndef __ASM_PPC64_HMI_H__
 #define __ASM_PPC64_HMI_H__
 
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 
 #define	CORE_TB_RESYNC_REQ_BIT		63
 #define MAX_SUBCORE_PER_CORE		4
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 148303e7771f..6a6792bb39fb 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -183,11 +183,6 @@ struct paca_struct {
 	 */
 	u16 in_mce;
 	u8 hmi_event_available;		 /* HMI event is available */
-	/*
-	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
-	 * more details
-	 */
-	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 
 	/* Stuff for accurate time accounting */
@@ -202,6 +197,13 @@ struct paca_struct {
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 #endif
 	struct kvmppc_host_state kvm_hstate;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/*
+	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+	 * more details
+	 */
+	struct sibling_subcore_state *sibling_subcore_state;
+#endif
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index b5e88e4a171a..c0309c59bed8 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -301,6 +301,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 /* Allocate & free a PCI host bridge structure */
 extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
 extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge);
 
 #ifdef CONFIG_PCI
 extern int pcibios_vaddr_is_ioport(void __iomem *address);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 0a74ebe934e1..17c8380673a6 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -75,14 +75,6 @@ static inline void disable_kernel_spe(void)
 static inline void __giveup_spe(struct task_struct *t) { }
 #endif
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-extern void flush_tmregs_to_thread(struct task_struct *);
-#else
-static inline void flush_tmregs_to_thread(struct task_struct *t)
-{
-}
-#endif
-
 static inline void clear_task_ebb(struct task_struct *t)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index b7c20f0b8fbe..c266227fdd5b 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -308,29 +308,20 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 static inline unsigned long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n))) {
+		check_object_size(to, n, false);
 		return __copy_tofrom_user((__force void __user *)to, from, n);
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + n - TASK_SIZE;
-		return __copy_tofrom_user((__force void __user *)to, from,
-				n - over) + over;
 	}
+	memset(to, 0, n);
 	return n;
 }
 
 static inline unsigned long copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_WRITE, to, n))
+	if (access_ok(VERIFY_WRITE, to, n)) {
+		check_object_size(from, n, true);
 		return __copy_tofrom_user(to, (__force void __user *)from, n);
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + n - TASK_SIZE;
-		return __copy_tofrom_user(to, (__force void __user *)from,
-				n - over) + over;
 	}
 	return n;
 }
@@ -372,6 +363,9 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
 		if (ret == 0)
 			return 0;
 	}
+
+	check_object_size(to, n, false);
+
 	return __copy_tofrom_user((__force void __user *)to, from, n);
 }
 
@@ -398,6 +392,9 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to,
 		if (ret == 0)
 			return 0;
 	}
+
+	check_object_size(from, n, true);
+
 	return __copy_tofrom_user(to, (__force const void __user *)from, n);
 }
 
@@ -422,10 +419,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 	might_fault();
 	if (likely(access_ok(VERIFY_WRITE, addr, size)))
 		return __clear_user(addr, size);
-	if ((unsigned long)addr < TASK_SIZE) {
-		unsigned long over = (unsigned long)addr + size - TASK_SIZE;
-		return __clear_user(addr, size - over) + over;
-	}
 	return size;
 }
 
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index f5f729c11578..f0b238516e9b 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -159,6 +159,8 @@ extern void xics_teardown_cpu(void);
 extern void xics_kexec_teardown_cpu(int secondary);
 extern void xics_migrate_irqs_away(void);
 extern void icp_native_eoi(struct irq_data *d);
+extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type);
+extern int xics_retrigger(struct irq_data *data);
 #ifdef CONFIG_SMP
 extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
 			       unsigned int strict_check);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b2027a5cf508..fe4c075bcf50 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -41,7 +41,7 @@ obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index c9bc78e9c610..7429556eb8df 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 	int n = 0, l = 0;
 	char buffer[128];
 
-	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
 		       edev->phb->global_number, pdn->busno,
 		       PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
-	pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+	pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n",
 		edev->phb->global_number, pdn->busno,
 		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6b8bc0dd09d4..5afd03e5e8b8 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -368,13 +368,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 tabort_syscall:
 	/* Firstly we need to enable TM in the kernel */
 	mfmsr	r10
-	li	r13, 1
-	rldimi	r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+	li	r9, 1
+	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
 	mtmsrd	r10, 0
 
 	/* tabort, this dooms the transaction, nothing else */
-	li	r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R13)
+	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R9)
 
 	/*
 	 * Return directly to userspace. We have corrupted user register state,
@@ -382,8 +382,8 @@ tabort_syscall:
 	 * resume after the tbegin of the aborted transaction with the
 	 * checkpointed register state.
 	 */
-	li	r13, MSR_RI
-	andc	r10, r10, r13
+	li	r9, MSR_RI
+	andc	r10, r10, r9
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 41091fdf9bd8..bffec73dbffc 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -144,29 +144,14 @@ machine_check_pSeries_1:
 	 * vector
 	 */
 	SET_SCRATCH0(r13)		/* save r13 */
-#ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
-	/* Running native on arch 2.06 or later, check if we are
-	 * waking up from nap. We only handle no state loss and
-	 * supervisor state loss. We do -not- handle hypervisor
-	 * state loss at this time.
+	/*
+	 * Running native on arch 2.06 or later, we may wakeup from winkle
+	 * inside machine check. If yes, then last bit of HSPGR0 would be set
+	 * to 1. Hence clear it unconditionally.
 	 */
-	mfspr	r13,SPRN_SRR1
-	rlwinm.	r13,r13,47-31,30,31
-	OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-	beq	9f
-
-	mfspr	r13,SPRN_SRR1
-	rlwinm.	r13,r13,47-31,30,31
-	/* waking up from powersave (nap) state */
-	cmpwi	cr1,r13,2
-	/* Total loss of HV state is fatal. let's just stay stuck here */
-	OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-	bgt	cr1,.
-9:
-	OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
+	GET_PACA(r13)
+	clrrdi	r13,r13,1
+	SET_PACA(r13)
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 BEGIN_FTR_SECTION
 	b	machine_check_powernv_early
@@ -500,7 +485,23 @@ machine_check_fwnmi:
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 machine_check_pSeries_0:
 	EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200)
-	EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD)
+	/*
+	 * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
+	 * difference that MSR_RI is not enabled, because PACA_EXMC is being
+	 * used, so nested machine check corrupts it. machine_check_common
+	 * enables MSR_RI.
+	 */
+	ld	r12,PACAKBASE(r13)
+	ld	r10,PACAKMSR(r13)
+	xori	r10,r10,MSR_RI
+	mfspr	r11,SPRN_SRR0
+	LOAD_HANDLER(r12, machine_check_common)
+	mtspr	SPRN_SRR0,r12
+	mfspr	r12,SPRN_SRR1
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.	/* prevent speculative execution */
+
 	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
@@ -984,14 +985,17 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 machine_check_common:
 
 	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
+	std	r10,PACA_EXMC+EX_DAR(r13)
 	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	stw	r10,PACA_EXMC+EX_DSISR(r13)
 	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
 	FINISH_NAP
 	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	ld	r3,PACA_EXMC+EX_DAR(r13)
+	lwz	r4,PACA_EXMC+EX_DSISR(r13)
+	/* Enable MSR_RI when finished with PACA_EXMC */
+	li	r10,MSR_RI
+	mtmsrd 	r10,1
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 	bl	save_nvgprs
@@ -1273,25 +1277,51 @@ machine_check_handle_early:
 	 * Check if thread was in power saving mode. We come here when any
 	 * of the following is true:
 	 * a. thread wasn't in power saving mode
-	 * b. thread was in power saving mode with no state loss or
-	 *    supervisor state loss
+	 * b. thread was in power saving mode with no state loss,
+	 *    supervisor state loss or hypervisor state loss.
 	 *
-	 * Go back to nap again if (b) is true.
+	 * Go back to nap/sleep/winkle mode again if (b) is true.
 	 */
 	rlwinm.	r11,r12,47-31,30,31	/* Was it in power saving mode? */
 	beq	4f			/* No, it wasn;t */
 	/* Thread was in power saving mode. Go back to nap again. */
 	cmpwi	r11,2
-	bne	3f
-	/* Supervisor state loss */
+	blt	3f
+	/* Supervisor/Hypervisor state loss */
 	li	r0,1
 	stb	r0,PACA_NAPSTATELOST(r13)
 3:	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
 	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
-	li	r3,PNV_THREAD_NAP
-	b	pnv_enter_arch207_idle_mode
+	/*
+	 * Check what idle state this CPU was in and go back to same mode
+	 * again.
+	 */
+	lbz	r3,PACA_THREAD_IDLE_STATE(r13)
+	cmpwi	r3,PNV_THREAD_NAP
+	bgt	10f
+	IDLE_STATE_ENTER_SEQ(PPC_NAP)
+	/* No return */
+10:
+	cmpwi	r3,PNV_THREAD_SLEEP
+	bgt	2f
+	IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+	/* No return */
+
+2:
+	/*
+	 * Go back to winkle. Please note that this thread was woken up in
+	 * machine check from winkle and have not restored the per-subcore
+	 * state. Hence before going back to winkle, set last bit of HSPGR0
+	 * to 1. This will make sure that if this thread gets woken up
+	 * again at reset vector 0x100 then it will get chance to restore
+	 * the subcore state.
+	 */
+	ori	r13,r13,1
+	SET_PACA(r13)
+	IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
+	/* No return */
 4:
 #endif
 	/*
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index ba79d15f4ddd..bd739fed26e3 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -44,18 +44,6 @@
 				PSSCR_PSLL_MASK | PSSCR_TR_MASK | \
 				PSSCR_MTL_MASK
 
-/* Idle state entry routines */
-
-#define	IDLE_STATE_ENTER_SEQ(IDLE_INST)				\
-	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
-	std	r0,0(r1);					\
-	ptesync;						\
-	ld	r0,0(r1);					\
-1:	cmp	cr0,r0,r0;					\
-	bne	1b;						\
-	IDLE_INST;						\
-	b	.
-
 	.text
 
 /*
@@ -363,8 +351,8 @@ _GLOBAL(power9_idle_stop)
  * cr3 - set to gt if waking up with partial/complete hypervisor state loss
  */
 _GLOBAL(pnv_restore_hyp_resource)
-	ld	r2,PACATOC(r13);
 BEGIN_FTR_SECTION
+	ld	r2,PACATOC(r13);
 	/*
 	 * POWER ISA 3. Use PSSCR to determine if we
 	 * are waking up from deep idle state
@@ -395,6 +383,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	 */
 	clrldi	r5,r13,63
 	clrrdi	r13,r13,1
+
+	/* Now that we are sure r13 is corrected, load TOC */
+	ld	r2,PACATOC(r13);
 	cmpwi	cr4,r5,1
 	mtspr	SPRN_HSPRG0,r13
 
@@ -420,7 +411,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
  *
  * r13 - PACA
  * cr3 - gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
  */
 _GLOBAL(pnv_wakeup_tb_loss)
 	ld	r1,PACAR1(r13)
@@ -462,7 +453,7 @@ lwarx_loop2:
 	 * At this stage
 	 * cr2 - eq if first thread to wakeup in core
 	 * cr3-  gt if waking up with partial/complete hypervisor state loss
-	 * cr4 - eq if waking up from complete hypervisor state loss.
+	 * cr4 - gt or eq if waking up from complete hypervisor state loss.
 	 */
 
 	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
@@ -490,7 +481,7 @@ first_thread_in_subcore:
 	 * If waking up from sleep, subcore state is not lost. Hence
 	 * skip subcore state restore
 	 */
-	bne	cr4,subcore_state_restored
+	blt	cr4,subcore_state_restored
 
 	/* Restore per-subcore state */
 	ld      r4,_SDR1(r1)
@@ -535,7 +526,7 @@ timebase_resync:
 	 * If waking up from sleep, per core state is not lost, skip to
 	 * clear_lock.
 	 */
-	bne	cr4,clear_lock
+	blt	cr4,clear_lock
 
 	/*
 	 * First thread in the core to wake up and its waking up with
@@ -566,7 +557,7 @@ common_exit:
 	 * If waking up from sleep, hypervisor state is not lost. Hence
 	 * skip hypervisor state restore.
 	 */
-	bne	cr4,hypervisor_state_restored
+	blt	cr4,hypervisor_state_restored
 
 	/* Waking up from winkle */
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 3ed8ec09b5c9..e785cc9e1ecd 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -29,7 +29,7 @@
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
 #include <asm/code-patching.h>
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index ef267fd9dd22..5e7ece0fda9f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
 	mce->in_use = 1;
 
 	mce->initiator = MCE_INITIATOR_CPU;
-	if (handled)
+	/* Mark it recovered if we have handled it and MSR(RI=1). */
+	if (handled && (regs->msr & MSR_RI))
 		mce->disposition = MCE_DISPOSITION_RECOVERED;
 	else
 		mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index a5c0153ede37..e58908066b0e 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -78,6 +78,7 @@ EXPORT_SYMBOL(get_pci_dma_ops);
 static int get_phb_number(struct device_node *dn)
 {
 	int ret, phb_id = -1;
+	u32 prop_32;
 	u64 prop;
 
 	/*
@@ -86,8 +87,10 @@ static int get_phb_number(struct device_node *dn)
 	 * reading "ibm,opal-phbid", only present in OPAL environment.
 	 */
 	ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
-	if (ret)
-		ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop);
+	if (ret) {
+		ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
+		prop = prop_32;
+	}
 
 	if (!ret)
 		phb_id = (int)(prop & (MAX_PHBS - 1));
@@ -151,6 +154,42 @@ void pcibios_free_controller(struct pci_controller *phb)
 EXPORT_SYMBOL_GPL(pcibios_free_controller);
 
 /*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ *                             pcibios_free_controller_deferred
+ *                             (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *phb = (struct pci_controller *)
+					 bridge->release_data;
+
+	pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+	pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
+/*
  * The function is used to return the minimal alignment
  * for memory or I/O windows of the associated P2P bridge.
  * By default, 4KiB alignment for I/O windows and 1MiB for
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 58ccf86415b4..9ee2623e0f67 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1074,26 +1074,6 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 #endif
 }
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void flush_tmregs_to_thread(struct task_struct *tsk)
-{
-	/*
-	 * Process self tracing is not yet supported through
-	 * ptrace interface. Ptrace generic code should have
-	 * prevented this from happening in the first place.
-	 * Warn once here with the message, if some how it
-	 * is attempted.
-	 */
-	WARN_ONCE(tsk == current,
-		"Not expecting ptrace on self: TM regs may be incorrect\n");
-
-	/*
-	 * If task is not current, it should have been flushed
-	 * already to it's thread_struct during __switch_to().
-	 */
-}
-#endif
-
 struct task_struct *__switch_to(struct task_struct *prev,
 	struct task_struct *new)
 {
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 6ee4b72cda42..d3eff99e938c 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -695,7 +695,7 @@ unsigned char ibm_architecture_vec[] = {
 	OV4_MIN_ENT_CAP,		/* minimum VP entitled capacity */
 
 	/* option vector 5: PAPR/OF options */
-	VECTOR_LENGTH(18),		/* length */
+	VECTOR_LENGTH(21),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
 	OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -726,8 +726,11 @@ unsigned char ibm_architecture_vec[] = {
 	0,
 	0,
 	OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
-	OV5_FEAT(OV5_PFO_HW_842),
-	OV5_FEAT(OV5_SUB_PROCESSORS),
+	OV5_FEAT(OV5_PFO_HW_842),				/* Byte 17 */
+	0,							/* Byte 18 */
+	0,							/* Byte 19 */
+	0,							/* Byte 20 */
+	OV5_FEAT(OV5_SUB_PROCESSORS),				/* Byte 21 */
 
 	/* option vector 6: IBM PAPR hints */
 	VECTOR_LENGTH(3),		/* length */
@@ -2940,7 +2943,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 
 	/* Don't print anything after quiesce under OPAL, it crashes OFW */
 	if (of_platform != PLATFORM_OPAL) {
-		prom_printf("Booting Linux via __start() ...\n");
+		prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
 		prom_debug("->dt_header_start=0x%x\n", hdr);
 	}
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 4f3c5756cc09..bf91658a8a40 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -38,6 +38,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/switch_to.h>
+#include <asm/tm.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -118,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+	/*
+	 * If task is not current, it will have been flushed already to
+	 * it's thread_struct during __switch_to().
+	 *
+	 * A reclaim flushes ALL the state.
+	 */
+
+	if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(TM_CAUSE_SIGNAL);
+
+}
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
 /**
  * regs_query_register_offset() - query register offset from its name
  * @name:	the name of a register
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index c3e861df4b20..24ec3ea4b3a2 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -93,15 +93,16 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  * and we are running with enough of the MMU enabled to have our
  * proper kernel virtual addresses
  *
- * Find out what kind of machine we're on and save any data we need
- * from the early boot process (devtree is copied on pmac by prom_init()).
- * This is called very early on the boot process, after a minimal
- * MMU environment has been set up but before MMU_init is called.
+ * We do the initial parsing of the flat device-tree and prepares
+ * for the MMU to be fully initialized.
  */
 extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
 
 notrace void __init machine_init(u64 dt_ptr)
 {
+	/* Configure static keys first, now that we're relocated. */
+	setup_feature_keys();
+
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index eafb9a79e011..7ac8e6eaab5b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -300,6 +300,7 @@ void __init early_setup(unsigned long dt_ptr)
 
 	/* Apply all the dynamic patching */
 	apply_feature_fixups();
+	setup_feature_keys();
 
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b6aa378aff63..a7daf749b97f 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1226,7 +1226,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
 	if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf)))
 		goto bad;
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * If there is a transactional state then throw it away.
+	 * The purpose of a sigreturn is to destroy all traces of the
+	 * signal frame, this includes any transactional state created
+	 * within in. We only check for suspended as we can never be
+	 * active in the kernel, we are active, there is nothing better to
+	 * do than go ahead and Bad Thing later.
+	 * The cause is not important as there will never be a
+	 * recheckpoint so it's not user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+
 	if (__get_user(tmp, &rt_sf->uc.uc_link))
 		goto bad;
 	uc_transact = (struct ucontext __user *)(uintptr_t)tmp;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 7e49984d4331..70409bb90a95 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -676,7 +676,21 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 	if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * If there is a transactional state then throw it away.
+	 * The purpose of a sigreturn is to destroy all traces of the
+	 * signal frame, this includes any transactional state created
+	 * within in. We only check for suspended as we can never be
+	 * active in the kernel, we are active, there is nothing better to
+	 * do than go ahead and Bad Thing later.
+	 * The cause is not important as there will never be a
+	 * recheckpoint so it's not user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+
 	if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
 		goto badframe;
 	if (MSR_TM_ACTIVE(msr)) {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 25a39052bf6b..9c6f3fd58059 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -830,7 +830,7 @@ int __cpu_disable(void)
 
 	/* Update sibling maps */
 	base = cpu_first_thread_sibling(cpu);
-	for (i = 0; i < threads_per_core; i++) {
+	for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) {
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
 		cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
 		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 2cb589264cb7..62859ebe0062 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -25,7 +25,8 @@
 #include <linux/user.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
+#include <linux/module.h>	/* print_modules */
 #include <linux/prctl.h>
 #include <linux/delay.h>
 #include <linux/kprobes.h>
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 6767605ea8da..4111d30badfa 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -22,6 +22,7 @@
 #include <linux/security.h>
 #include <linux/memblock.h>
 
+#include <asm/cpu_has_feature.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index cbabd143acae..78a7449bf489 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc
 $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
 	$(call if_changed,vdso32ld)
 
 # strip rule for the .so file
@@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso32): %.o: %.S
+$(obj-vdso32): %.o: %.S FORCE
 	$(call if_changed_dep,vdso32as)
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index c710802b8fb6..366ae09b14c1 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
 	$(call if_changed,vdso64ld)
 
 # strip rule for the .so file
@@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso64): %.o: %.S
+$(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 1f9e5529e692..855d4b95d752 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -78,6 +78,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 
 ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+	book3s_hv_hmi.o \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \
diff --git a/arch/powerpc/kernel/hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c
index e3f738eb1cac..e3f738eb1cac 100644
--- a/arch/powerpc/kernel/hmi.c
+++ b/arch/powerpc/kvm/book3s_hv_hmi.c
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index a75ba38a2d81..05aa11399a78 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1329,20 +1329,16 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 	xics->kvm = kvm;
 
 	/* Already there ? */
-	mutex_lock(&kvm->lock);
 	if (kvm->arch.xics)
 		ret = -EEXIST;
 	else
 		kvm->arch.xics = xics;
-	mutex_unlock(&kvm->lock);
 
 	if (ret) {
 		kfree(xics);
 		return ret;
 	}
 
-	xics_debugfs_init(xics);
-
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
 		/* Enable real mode support */
@@ -1354,9 +1350,17 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 	return 0;
 }
 
+static void kvmppc_xics_init(struct kvm_device *dev)
+{
+	struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private;
+
+	xics_debugfs_init(xics);
+}
+
 struct kvm_device_ops kvm_xics_ops = {
 	.name = "kvm-xics",
 	.create = kvmppc_xics_create,
+	.init = kvmppc_xics_init,
 	.destroy = kvmppc_xics_free,
 	.set_attr = xics_set_attr,
 	.get_attr = xics_get_attr,
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index d90870a66b60..aa8214f30c92 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -127,17 +127,19 @@ _GLOBAL(csum_partial_copy_generic)
 	stw	r7,12(r1)
 	stw	r8,8(r1)
 
-	andi.	r0,r4,1			/* is destination address even ? */
-	cmplwi	cr7,r0,0
 	addic	r12,r6,0
 	addi	r6,r4,-4
 	neg	r0,r4
 	addi	r4,r3,-4
 	andi.	r0,r0,CACHELINE_MASK	/* # bytes to start of cache line */
+	crset	4*cr7+eq
 	beq	58f
 
 	cmplw	0,r5,r0			/* is this more than total to do? */
 	blt	63f			/* if not much to do */
+	rlwinm	r7,r6,3,0x8
+	rlwnm	r12,r12,r7,0,31	/* odd destination address: rotate one byte */
+	cmplwi	cr7,r7,0	/* is destination address even ? */
 	andi.	r8,r0,3			/* get it word-aligned first */
 	mtctr	r8
 	beq+	61f
@@ -237,7 +239,7 @@ _GLOBAL(csum_partial_copy_generic)
 66:	addze	r3,r12
 	addi	r1,r1,16
 	beqlr+	cr7
-	rlwinm	r3,r3,8,0,31	/* swap bytes for odd destination */
+	rlwinm	r3,r3,8,0,31	/* odd destination address: rotate one byte */
 	blr
 
 /* read fault */
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 74145f02ad41..043415f0bdb1 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -188,7 +188,10 @@ void __init apply_feature_fixups(void)
 			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
 #endif
 	do_final_fixups();
+}
 
+void __init setup_feature_keys(void)
+{
 	/*
 	 * Initialise jump label. This causes all the cpu/mmu_has_feature()
 	 * checks to take on their correct polarity based on the current set of
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a4db22f65021..bb1ffc559f38 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -26,7 +26,7 @@
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index dfdb90cb4403..9f1983404e1a 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -113,7 +113,12 @@ BEGIN_FTR_SECTION
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
-0:
+0:	/*
+	 * For userspace addresses, make sure this is region 0.
+	 */
+	cmpdi	r9, 0
+	bne	8f
+
 	/* when using slices, we extract the psize off the slice bitmaps
 	 * and then we need to get the sllp encoding off the mmu_psize_defs
 	 * array.
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 8eb82b043dd8..d93dd4acf40b 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -528,7 +528,6 @@ static struct platform_driver mpc512x_lpbfifo_driver = {
 	.remove = mpc512x_lpbfifo_remove,
 	.driver = {
 		.name = DRV_NAME,
-		.owner = THIS_MODULE,
 		.of_match_table = mpc512x_lpbfifo_match,
 	},
 };
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index dbcd0303afed..63c5ab6489c9 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -222,7 +222,6 @@ static const struct of_device_id mcu_of_match_table[] = {
 static struct i2c_driver mcu_driver = {
 	.driver = {
 		.name = "mcu-mpc8349emitx",
-		.owner = THIS_MODULE,
 		.of_match_table = mcu_of_match_table,
 	},
 	.probe = mcu_probe,
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 5be15cff758d..2975754c65ea 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -496,8 +496,10 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode)
 	gang = alloc_spu_gang();
 	SPUFS_I(inode)->i_ctx = NULL;
 	SPUFS_I(inode)->i_gang = gang;
-	if (!gang)
+	if (!gang) {
+		ret = -ENOMEM;
 		goto out_iput;
+	}
 
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index dafba1057a47..dfd310031549 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -26,7 +26,7 @@
 #include <linux/tty.h>
 #include <linux/serial_core.h>
 #include <linux/of_platform.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 80804f9916ee..f97bab8e37a2 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -23,7 +23,7 @@
 #include <linux/pci.h>
 #include <linux/kdev_t.h>
 #include <linux/console.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index 309d9ccccd50..c61667e8bb06 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -187,6 +187,11 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev)
 	if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
 	    !firmware_has_feature(FW_FEATURE_LPAR)) {
 		dev->dev.archdata.dma_ops = &dma_direct_ops;
+		/*
+		 * Set the coherent DMA mask to prevent the iommu
+		 * being used unnecessarily
+		 */
+		dev->dev.coherent_dma_mask = DMA_BIT_MASK(44);
 		return;
 	}
 #endif
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 2ee96431f736..4c827826c05e 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data)
 	uint32_t dump_id, dump_size, dump_type;
 	struct dump_obj *dump;
 	char name[22];
+	struct kobject *kobj;
 
 	rc = dump_read_info(&dump_id, &dump_size, &dump_type);
 	if (rc != OPAL_SUCCESS)
@@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(dump_kset, name))
+	kobj = kset_find_obj(dump_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return 0;
+	}
 
 	dump = create_dump_obj(dump_id, dump_size, dump_type);
 	if (!dump)
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 37f959bf392e..f2344cbd2f46 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data)
 	uint64_t elog_type;
 	int rc;
 	char name[2+16+1];
+	struct kobject *kobj;
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
@@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(elog_kset, name))
+	kobj = kset_find_obj(elog_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return IRQ_HANDLED;
+	}
 
 	create_elog_obj(log_id, elog_size, elog_type);
 
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index e505223b4ec5..ed8bba68a162 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -228,7 +228,8 @@ int __init opal_event_init(void)
 		}
 
 		/* Install interrupt handler */
-		rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
+		rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW,
+				 "opal", NULL);
 		if (rc) {
 			irq_dispose_mapping(virq);
 			pr_warn("Error %d requesting irq %d (0x%x)\n",
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 8b4fc68cebcb..6c9a65b52e63 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -399,6 +399,7 @@ static int opal_recover_mce(struct pt_regs *regs,
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
+		pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
 		recovered = 0;
 	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 6b9528307f62..bc0c91e84ca0 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -111,10 +111,17 @@ static int __init iommu_setup(char *str)
 }
 early_param("iommu", iommu_setup);
 
-static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
+static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
 {
-	return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) ==
-		(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
+	/*
+	 * WARNING: We cannot rely on the resource flags. The Linux PCI
+	 * allocation code sometimes decides to put a 64-bit prefetchable
+	 * BAR in the 32-bit window, so we have to compare the addresses.
+	 *
+	 * For simplicity we only test resource start.
+	 */
+	return (r->start >= phb->ioda.m64_base &&
+		r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
 }
 
 static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
@@ -142,7 +149,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 
 static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
-	unsigned long pe = phb->ioda.total_pe_num - 1;
+	long pe;
 
 	for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
 		if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
@@ -155,11 +162,12 @@ static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
 static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 {
 	struct pnv_phb *phb = pe->phb;
+	unsigned int pe_num = pe->pe_number;
 
 	WARN_ON(pe->pdev);
 
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
-	clear_bit(pe->pe_number, phb->ioda.pe_alloc);
+	clear_bit(pe_num, phb->ioda.pe_alloc);
 }
 
 /* The default M64 BAR is shared by all PEs */
@@ -229,7 +237,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
 	sgsz = phb->ioda.m64_segsize;
 	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
 		r = &pdev->resource[i];
-		if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags))
+		if (!r->parent || !pnv_pci_is_m64(phb, r))
 			continue;
 
 		start = _ALIGN_DOWN(r->start - base, sgsz);
@@ -1877,7 +1885,7 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm,
 					unsigned shift, unsigned long index,
 					unsigned long npages)
 {
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
 	unsigned long start, end, inc;
 
 	/* We'll invalidate DMA address in PE scope */
@@ -2209,7 +2217,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
 
 	pnv_pci_link_table_and_group(phb->hose->node, num,
 			tbl, &pe->table_group);
-	pnv_pci_phb3_tce_invalidate_pe(pe);
+	pnv_pci_ioda2_tce_invalidate_pe(pe);
 
 	return 0;
 }
@@ -2347,7 +2355,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
 	if (ret)
 		pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
 	else
-		pnv_pci_phb3_tce_invalidate_pe(pe);
+		pnv_pci_ioda2_tce_invalidate_pe(pe);
 
 	pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
 
@@ -2863,7 +2871,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 		res = &pdev->resource[i + PCI_IOV_RESOURCES];
 		if (!res->flags || res->parent)
 			continue;
-		if (!pnv_pci_is_mem_pref_64(res->flags)) {
+		if (!pnv_pci_is_m64(phb, res)) {
 			dev_warn(&pdev->dev, "Don't support SR-IOV with"
 					" non M64 VF BAR%d: %pR. \n",
 				 i, res);
@@ -2958,7 +2966,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
 			index++;
 		}
 	} else if ((res->flags & IORESOURCE_MEM) &&
-		   !pnv_pci_is_mem_pref_64(res->flags)) {
+		   !pnv_pci_is_m64(phb, res)) {
 		region.start = res->start -
 			       phb->hose->mem_offset[0] -
 			       phb->ioda.m32_pci_base;
@@ -3083,9 +3091,12 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 		bridge = bridge->bus->self;
 	}
 
-	/* We fail back to M32 if M64 isn't supported */
-	if (phb->ioda.m64_segsize &&
-	    pnv_pci_is_mem_pref_64(type))
+	/*
+	 * We fall back to M32 if M64 isn't supported. We enforce the M64
+	 * alignment for any 64-bit resource, PCIe doesn't care and
+	 * bridges only do 64-bit prefetchable anyway.
+	 */
+	if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64))
 		return phb->ioda.m64_segsize;
 	if (type & IORESOURCE_MEM)
 		return phb->ioda.m32_segsize;
@@ -3125,7 +3136,7 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus,
 		w = NULL;
 		if (r->flags & type & IORESOURCE_IO)
 			w = &hose->io_resource;
-		else if (pnv_pci_is_mem_pref_64(r->flags) &&
+		else if (pnv_pci_is_m64(phb, r) &&
 			 (type & IORESOURCE_PREFETCH) &&
 			 phb->ioda.m64_segsize)
 			w = &hose->mem_resources[1];
@@ -3392,12 +3403,6 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 	struct pnv_phb *phb = pe->phb;
 	struct pnv_ioda_pe *slave, *tmp;
 
-	/* Release slave PEs in compound PE */
-	if (pe->flags & PNV_IODA_PE_MASTER) {
-		list_for_each_entry_safe(slave, tmp, &pe->slaves, list)
-			pnv_ioda_release_pe(slave);
-	}
-
 	list_del(&pe->list);
 	switch (phb->type) {
 	case PNV_PHB_IODA1:
@@ -3412,7 +3417,26 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 
 	pnv_ioda_release_pe_seg(pe);
 	pnv_ioda_deconfigure_pe(pe->phb, pe);
-	pnv_ioda_free_pe(pe);
+
+	/* Release slave PEs in the compound PE */
+	if (pe->flags & PNV_IODA_PE_MASTER) {
+		list_for_each_entry_safe(slave, tmp, &pe->slaves, list) {
+			list_del(&slave->list);
+			pnv_ioda_free_pe(slave);
+		}
+	}
+
+	/*
+	 * The PE for root bus can be removed because of hotplug in EEH
+	 * recovery for fenced PHB error. We need to mark the PE dead so
+	 * that it can be populated again in PCI hot add path. The PE
+	 * shouldn't be destroyed as it's the global reserved resource.
+	 */
+	if (phb->ioda.root_pe_populated &&
+	    phb->ioda.root_pe_idx == pe->pe_number)
+		phb->ioda.root_pe_populated = false;
+	else
+		pnv_ioda_free_pe(pe);
 }
 
 static void pnv_pci_release_device(struct pci_dev *pdev)
@@ -3428,7 +3452,17 @@ static void pnv_pci_release_device(struct pci_dev *pdev)
 	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
 		return;
 
+	/*
+	 * PCI hotplug can happen as part of EEH error recovery. The @pdn
+	 * isn't removed and added afterwards in this scenario. We should
+	 * set the PE number in @pdn to an invalid one. Otherwise, the PE's
+	 * device count is decreased on removing devices while failing to
+	 * be increased on adding devices. It leads to unbalanced PE's device
+	 * count and eventually make normal PCI hotplug path broken.
+	 */
 	pe = &phb->ioda.pe_array[pdn->pe_number];
+	pdn->pe_number = IODA_INVALID_PE;
+
 	WARN_ON(--pe->device_count < 0);
 	if (pe->device_count == 0)
 		pnv_ioda_release_pe(pe);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 43f7beb2902d..76ec104e88be 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -320,19 +320,6 @@ static int dlpar_remove_device_tree_lmb(struct of_drconf_cell *lmb)
 	return dlpar_update_device_tree_lmb(lmb);
 }
 
-static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
-{
-	unsigned long section_nr;
-	struct mem_section *mem_sect;
-	struct memory_block *mem_block;
-
-	section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
-	mem_sect = __nr_to_section(section_nr);
-
-	mem_block = find_memory_block(mem_sect);
-	return mem_block;
-}
-
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
@@ -420,6 +407,19 @@ static bool lmb_is_removable(struct of_drconf_cell *lmb)
 
 static int dlpar_add_lmb(struct of_drconf_cell *);
 
+static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
+{
+	unsigned long section_nr;
+	struct mem_section *mem_sect;
+	struct memory_block *mem_block;
+
+	section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
+	mem_sect = __nr_to_section(section_nr);
+
+	mem_block = find_memory_block(mem_sect);
+	return mem_block;
+}
+
 static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
 {
 	struct memory_block *mem_block;
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index fe16a50700de..09eba5a9929a 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -119,6 +119,10 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 
 	bus = bridge->bus;
 
+	/* Rely on the pcibios_free_controller_deferred() callback. */
+	pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred,
+					(void *) pci_bus_to_host(bus));
+
 	dn = pcibios_get_phb_of_node(bus);
 	if (!dn)
 		return 0;
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 906dbaa97fe2..547fd13e4f8e 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -106,8 +106,11 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		release_resource(res);
 	}
 
-	/* Free pci_controller data structure */
-	pcibios_free_controller(phb);
+	/*
+	 * The pci_controller data structure is freed by
+	 * the pcibios_free_controller_deferred() callback;
+	 * see pseries_root_bridge_prepare().
+	 */
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 4ffcaa6f8670..a39d20e8623d 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -41,7 +41,6 @@
 #include <linux/root_dev.h>
 #include <linux/of.h>
 #include <linux/of_pci.h>
-#include <linux/kexec.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -66,6 +65,7 @@
 #include <asm/eeh.h>
 #include <asm/reg.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/kexec.h>
 
 #include "pseries.h"
 
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 6c110994d902..81d49476c47e 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -534,7 +534,8 @@ struct cpm1_gpio16_chip {
 
 static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio16_chip *cpm1_gc =
+		container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
 	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
 
 	cpm1_gc->cpdata = in_be16(&iop->dat);
@@ -649,7 +650,8 @@ struct cpm1_gpio32_chip {
 
 static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio32_chip *cpm1_gc =
+		container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
 	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
 
 	cpm1_gc->cpdata = in_be32(&iop->dat);
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 911456d17713..947f42007734 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -94,7 +94,8 @@ struct cpm2_gpio32_chip {
 
 static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm2_gpio32_chip *cpm2_gc =
+		container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc);
 	struct cpm2_ioports __iomem *iop = mm_gc->regs;
 
 	cpm2_gc->cpdata = in_be32(&iop->dat);
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 68e7c0dd2e45..3cc7cace194a 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -23,7 +23,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig
index 0031eda320c3..385e7aa9e273 100644
--- a/arch/powerpc/sysdev/xics/Kconfig
+++ b/arch/powerpc/sysdev/xics/Kconfig
@@ -1,6 +1,7 @@
 config PPC_XICS
        def_bool n
        select PPC_SMP_MUXED_IPI
+       select HARDIRQS_SW_RESEND
 
 config PPC_ICP_NATIVE
        def_bool n
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index 57d72f10a97f..9114243fa1b5 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -23,10 +23,10 @@
 
 static void icp_opal_teardown_cpu(void)
 {
-	int cpu = smp_processor_id();
+	int hw_cpu = hard_smp_processor_id();
 
 	/* Clear any pending IPI */
-	opal_int_set_mfrr(cpu, 0xff);
+	opal_int_set_mfrr(hw_cpu, 0xff);
 }
 
 static void icp_opal_flush_ipi(void)
@@ -101,14 +101,16 @@ static void icp_opal_eoi(struct irq_data *d)
 
 static void icp_opal_cause_ipi(int cpu, unsigned long data)
 {
-	opal_int_set_mfrr(cpu, IPI_PRIORITY);
+	int hw_cpu = get_hard_smp_processor_id(cpu);
+
+	opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
 }
 
 static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
 {
-	int cpu = smp_processor_id();
+	int hw_cpu = hard_smp_processor_id();
 
-	opal_int_set_mfrr(cpu, 0xff);
+	opal_int_set_mfrr(hw_cpu, 0xff);
 
 	return smp_ipi_demux();
 }
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index 27c936c080a6..1c6bf4b66f56 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -156,7 +156,9 @@ static struct irq_chip ics_opal_irq_chip = {
 	.irq_mask = ics_opal_mask_irq,
 	.irq_unmask = ics_opal_unmask_irq,
 	.irq_eoi = NULL, /* Patched at init time */
-	.irq_set_affinity = ics_opal_set_affinity
+	.irq_set_affinity = ics_opal_set_affinity,
+	.irq_set_type = xics_set_irq_type,
+	.irq_retrigger = xics_retrigger,
 };
 
 static int ics_opal_map(struct ics *ics, unsigned int virq);
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index 3854dd41558d..78ee5c778ef8 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -163,7 +163,9 @@ static struct irq_chip ics_rtas_irq_chip = {
 	.irq_mask = ics_rtas_mask_irq,
 	.irq_unmask = ics_rtas_unmask_irq,
 	.irq_eoi = NULL, /* Patched at init time */
-	.irq_set_affinity = ics_rtas_set_affinity
+	.irq_set_affinity = ics_rtas_set_affinity,
+	.irq_set_type = xics_set_irq_type,
+	.irq_retrigger = xics_retrigger,
 };
 
 static int ics_rtas_map(struct ics *ics, unsigned int virq)
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index a795a5f0301c..9d530f479588 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -328,8 +328,12 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq,
 
 	pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
 
-	/* They aren't all level sensitive but we just don't really know */
-	irq_set_status_flags(virq, IRQ_LEVEL);
+	/*
+	 * Mark interrupts as edge sensitive by default so that resend
+	 * actually works. The device-tree parsing will turn the LSIs
+	 * back to level.
+	 */
+	irq_clear_status_flags(virq, IRQ_LEVEL);
 
 	/* Don't call into ICS for IPIs */
 	if (hw == XICS_IPI) {
@@ -351,13 +355,54 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
-	/* Current xics implementation translates everything
-	 * to level. It is not technically right for MSIs but this
-	 * is irrelevant at this point. We might get smarter in the future
-	 */
 	*out_hwirq = intspec[0];
-	*out_flags = IRQ_TYPE_LEVEL_LOW;
 
+	/*
+	 * If intsize is at least 2, we look for the type in the second cell,
+	 * we assume the LSB indicates a level interrupt.
+	 */
+	if (intsize > 1) {
+		if (intspec[1] & 1)
+			*out_flags = IRQ_TYPE_LEVEL_LOW;
+		else
+			*out_flags = IRQ_TYPE_EDGE_RISING;
+	} else
+		*out_flags = IRQ_TYPE_LEVEL_LOW;
+
+	return 0;
+}
+
+int xics_set_irq_type(struct irq_data *d, unsigned int flow_type)
+{
+	/*
+	 * We only support these. This has really no effect other than setting
+	 * the corresponding descriptor bits mind you but those will in turn
+	 * affect the resend function when re-enabling an edge interrupt.
+	 *
+	 * Set set the default to edge as explained in map().
+	 */
+	if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE)
+		flow_type = IRQ_TYPE_EDGE_RISING;
+
+	if (flow_type != IRQ_TYPE_EDGE_RISING &&
+	    flow_type != IRQ_TYPE_LEVEL_LOW)
+		return -EINVAL;
+
+	irqd_set_trigger_type(d, flow_type);
+
+	return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+int xics_retrigger(struct irq_data *data)
+{
+	/*
+	 * We need to push a dummy CPPR when retriggering, since the subsequent
+	 * EOI will try to pop it. Passing 0 works, as the function hard codes
+	 * the priority value anyway.
+	 */
+	xics_push_cppr(0);
+
+	/* Tell the core to do a soft retrigger */
 	return 0;
 }
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9e607bf2d640..c109f073d454 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -68,7 +68,6 @@ config DEBUG_RODATA
 config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -123,6 +122,7 @@ config S390
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_EARLY_PFN_TO_NID
+	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_JUMP_LABEL
 	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER
@@ -871,4 +871,17 @@ config S390_GUEST
 	  Select this option if you want to run the kernel as a guest under
 	  the KVM hypervisor.
 
+config S390_GUEST_OLD_TRANSPORT
+	def_bool y
+	prompt "Guest support for old s390 virtio transport (DEPRECATED)"
+	depends on S390_GUEST
+	help
+	  Enable this option to add support for the old s390-virtio
+	  transport (i.e. virtio devices NOT based on virtio-ccw). This
+	  type of virtio devices is only available on the experimental
+	  kuli userspace or with old (< 2.6) qemu. If you are running
+	  with a modern version of qemu (which supports virtio-ccw since
+	  1.4 and uses it by default since version 2.4), you probably won't
+	  need this.
+
 endmenu
diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
index f86a4eef28a9..28c4f96a2d9c 100644
--- a/arch/s390/boot/compressed/head.S
+++ b/arch/s390/boot/compressed/head.S
@@ -21,16 +21,21 @@ ENTRY(startup_continue)
 	lg	%r15,.Lstack-.LPG1(%r13)
 	aghi	%r15,-160
 	brasl	%r14,decompress_kernel
-	# setup registers for memory mover & branch to target
+	# Set up registers for memory mover. We move the decompressed image to
+	# 0x11000, starting at offset 0x11000 in the decompressed image so
+	# that code living at 0x11000 in the image will end up at 0x11000 in
+	# memory.
 	lgr	%r4,%r2
 	lg	%r2,.Loffset-.LPG1(%r13)
 	la	%r4,0(%r2,%r4)
 	lg	%r3,.Lmvsize-.LPG1(%r13)
 	lgr	%r5,%r3
-	# move the memory mover someplace safe
+	# Move the memory mover someplace safe so it doesn't overwrite itself.
 	la	%r1,0x200
 	mvc	0(mover_end-mover,%r1),mover-.LPG1(%r13)
-	# decompress image is started at 0x11000
+	# When the memory mover is done we pass control to
+	# arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in
+	# the decompressed image.
 	lgr	%r6,%r2
 	br	%r1
 mover:
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 889ea3450210..412b1bd21029 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -602,7 +602,6 @@ CONFIG_FAIL_FUTEX=y
 CONFIG_FAULT_INJECTION_DEBUG_FS=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_IRQSOFF_TRACER=y
 CONFIG_PREEMPT_TRACER=y
 CONFIG_SCHED_TRACER=y
@@ -678,7 +677,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_ASYMMETRIC_KEY_TYPE=y
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
 CONFIG_X509_CERTIFICATE_PARSER=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 1bcfd764910a..bec279eb4b93 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -552,7 +552,6 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
 CONFIG_PM_NOTIFIER_ERROR_INJECT=m
 CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_KPROBE_EVENT is not set
 CONFIG_TRACE_ENUM_MAP_FILE=y
@@ -616,7 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_ASYMMETRIC_KEY_TYPE=y
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
 CONFIG_X509_CERTIFICATE_PARSER=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 13ff090139c8..1751446a5bbb 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -549,7 +549,6 @@ CONFIG_TIMER_STATS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
@@ -615,7 +614,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_ASYMMETRIC_KEY_TYPE=y
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
 CONFIG_X509_CERTIFICATE_PARSER=m
diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c
index 577ae1d4ae89..2bad9d837029 100644
--- a/arch/s390/crypto/crc32-vx.c
+++ b/arch/s390/crypto/crc32-vx.c
@@ -51,6 +51,9 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
 		struct kernel_fpu vxstate;				    \
 		unsigned long prealign, aligned, remaining;		    \
 									    \
+		if (datalen < VX_MIN_LEN + VX_ALIGN_MASK)		    \
+			return ___crc32_sw(crc, data, datalen);		    \
+									    \
 		if ((unsigned long)data & VX_ALIGN_MASK) {		    \
 			prealign = VX_ALIGNMENT -			    \
 				  ((unsigned long)data & VX_ALIGN_MASK);    \
@@ -59,9 +62,6 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
 			data = (void *)((unsigned long)data + prealign);    \
 		}							    \
 									    \
-		if (datalen < VX_MIN_LEN)				    \
-			return ___crc32_sw(crc, data, datalen);		    \
-									    \
 		aligned = datalen & ~VX_ALIGN_MASK;			    \
 		remaining = datalen & VX_ALIGN_MASK;			    \
 									    \
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index ccccebeeaaf6..2d40ef0a6295 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -172,7 +172,6 @@ CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_RCU_TRACE=y
 CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
@@ -234,7 +233,7 @@ CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRC7=m
 # CONFIG_XZ_DEC_X86 is not set
 # CONFIG_XZ_DEC_POWERPC is not set
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 9b49cf1daa8f..52d7c8709279 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -266,28 +266,28 @@ int __put_user_bad(void) __attribute__((noreturn));
 	__chk_user_ptr(ptr);					\
 	switch (sizeof(*(ptr))) {				\
 	case 1: {						\
-		unsigned char __x;				\
+		unsigned char __x = 0;				\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 2: {						\
-		unsigned short __x;				\
+		unsigned short __x = 0;				\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 4: {						\
-		unsigned int __x;				\
+		unsigned int __x = 0;				\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 8: {						\
-		unsigned long long __x;				\
+		unsigned long long __x = 0;			\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
@@ -311,6 +311,14 @@ int __get_user_bad(void) __attribute__((noreturn));
 #define __put_user_unaligned __put_user
 #define __get_user_unaligned __get_user
 
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
 /**
  * copy_to_user: - Copy a block of data into user space.
  * @to:   Destination address, in user space.
@@ -332,12 +340,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
 	return __copy_to_user(to, from, n);
 }
 
-void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-__compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
-
 /**
  * copy_from_user: - Copy a block of data from user space.
  * @to:   Destination address, in kernel space.
@@ -362,7 +364,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 
 	might_fault();
 	if (unlikely(sz != -1 && sz < n)) {
-		copy_from_user_overflow();
+		if (!__builtin_constant_p(n))
+			copy_user_overflow(sz, n);
+		else
+			__bad_copy_user();
 		return n;
 	}
 	return __copy_from_user(to, from, n);
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 56e4d8234ef2..4431905f8cfa 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -309,7 +309,9 @@ ENTRY(startup_kdump)
 	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-STACK_FRAME_OVERHEAD
 	brasl	%r14,verify_facilities
-	/* Continue with startup code in head64.S */
+# For uncompressed images, continue in
+# arch/s390/kernel/head64.S. For compressed images, continue in
+# arch/s390/boot/compressed/head.S.
 	jg	startup_continue
 
 .Lstack:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ba5f456edaa9..7f7ba5f23f13 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -204,11 +204,9 @@ static void __init conmode_default(void)
 #endif
 		}
 	} else if (MACHINE_IS_KVM) {
-		if (sclp.has_vt220 &&
-		    config_enabled(CONFIG_SCLP_VT220_CONSOLE))
+		if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE))
 			SET_CONSOLE_VT220;
-		else if (sclp.has_linemode &&
-			 config_enabled(CONFIG_SCLP_CONSOLE))
+		else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE))
 			SET_CONSOLE_SCLP;
 		else
 			SET_CONSOLE_HVC;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 3f3ae4865d57..607ec91966c7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1672,6 +1672,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2230,9 +2231,10 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 		return -EINVAL;
 	current->thread.fpu.fpc = fpu->fpc;
 	if (MACHINE_HAS_VX)
-		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+		convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
+				 (freg_t *) fpu->fprs);
 	else
-		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
+		memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	return 0;
 }
 
@@ -2241,9 +2243,10 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	/* make sure we have the latest values */
 	save_fpu_regs();
 	if (MACHINE_HAS_VX)
-		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+		convert_vx_to_fp((freg_t *) fpu->fprs,
+				 (__vector128 *) vcpu->run->s.regs.vrs);
 	else
-		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+		memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
 	fpu->fpc = current->thread.fpu.fpc;
 	return 0;
 }
@@ -2361,8 +2364,10 @@ retry:
 		rc = gmap_mprotect_notify(vcpu->arch.gmap,
 					  kvm_s390_get_prefix(vcpu),
 					  PAGE_SIZE * 2, PROT_WRITE);
-		if (rc)
+		if (rc) {
+			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 			return rc;
+		}
 		goto retry;
 	}
 
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index c106488b4137..d8673e243f13 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -584,7 +584,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		/* Validity 0x0044 will be checked by SIE */
 		if (rc)
 			goto unpin;
-		scb_s->gvrd = hpa;
+		scb_s->riccbd = hpa;
 	}
 	return 0;
 unpin:
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index e390bbb16443..48352bffbc92 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -237,11 +237,10 @@ char * strrchr(const char * s, int c)
 EXPORT_SYMBOL(strrchr);
 
 static inline int clcle(const char *s1, unsigned long l1,
-			const char *s2, unsigned long l2,
-			int *diff)
+			const char *s2, unsigned long l2)
 {
 	register unsigned long r2 asm("2") = (unsigned long) s1;
-	register unsigned long r3 asm("3") = (unsigned long) l2;
+	register unsigned long r3 asm("3") = (unsigned long) l1;
 	register unsigned long r4 asm("4") = (unsigned long) s2;
 	register unsigned long r5 asm("5") = (unsigned long) l2;
 	int cc;
@@ -252,7 +251,6 @@ static inline int clcle(const char *s1, unsigned long l1,
 		      "   srl   %0,28"
 		      : "=&d" (cc), "+a" (r2), "+a" (r3),
 			"+a" (r4), "+a" (r5) : : "cc");
-	*diff = *(char *)r2 - *(char *)r4;
 	return cc;
 }
 
@@ -270,9 +268,9 @@ char * strstr(const char * s1,const char * s2)
 		return (char *) s1;
 	l1 = __strend(s1) - s1;
 	while (l1-- >= l2) {
-		int cc, dummy;
+		int cc;
 
-		cc = clcle(s1, l1, s2, l2, &dummy);
+		cc = clcle(s1, l2, s2, l2);
 		if (!cc)
 			return (char *) s1;
 		s1++;
@@ -313,11 +311,11 @@ EXPORT_SYMBOL(memchr);
  */
 int memcmp(const void *cs, const void *ct, size_t n)
 {
-	int ret, diff;
+	int ret;
 
-	ret = clcle(cs, n, ct, n, &diff);
+	ret = clcle(cs, n, ct, n);
 	if (ret)
-		ret = diff;
+		ret = ret == 1 ? -1 : 1;
 	return ret;
 }
 EXPORT_SYMBOL(memcmp);
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index d96596128e9f..f481fcde067b 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -104,6 +104,7 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
 
 unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
+	check_object_size(to, n, false);
 	if (static_branch_likely(&have_mvcos))
 		return copy_from_user_mvcos(to, from, n);
 	return copy_from_user_mvcp(to, from, n);
@@ -177,6 +178,7 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x,
 
 unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+	check_object_size(from, n, true);
 	if (static_branch_likely(&have_mvcos))
 		return copy_to_user_mvcos(to, from, n);
 	return copy_to_user_mvcs(to, from, n);
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 7104ffb5a67f..af7cf28cf97e 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -252,6 +252,8 @@ static int change_page_attr(unsigned long addr, unsigned long end,
 	int rc = -EINVAL;
 	pgd_t *pgdp;
 
+	if (addr == end)
+		return 0;
 	if (end >= MODULES_END)
 		return -EINVAL;
 	mutex_lock(&cpa_mutex);
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index 20a3591225cc..01aec8ccde83 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -163,7 +163,7 @@ do {									\
 		__get_user_asm(val, "lw", ptr);				\
 		 break;							\
 	case 8: 							\
-		if ((copy_from_user((void *)&val, ptr, 8)) == 0)	\
+		if (__copy_from_user((void *)&val, ptr, 8) == 0)	\
 			__gu_err = 0;					\
 		else							\
 			__gu_err = -EFAULT;				\
@@ -188,6 +188,8 @@ do {									\
 									\
 	if (likely(access_ok(VERIFY_READ, __gu_ptr, size)))		\
 		__get_user_common((x), size, __gu_ptr);			\
+	else								\
+		(x) = 0;						\
 									\
 	__gu_err;							\
 })
@@ -201,6 +203,7 @@ do {									\
 		"2:\n"							\
 		".section .fixup,\"ax\"\n"				\
 		"3:li	%0, %4\n"					\
+		"li	%1, 0\n"					\
 		"j	2b\n"						\
 		".previous\n"						\
 		".section __ex_table,\"a\"\n"				\
@@ -298,35 +301,34 @@ extern int __copy_tofrom_user(void *to, const void *from, unsigned long len);
 static inline unsigned long
 copy_from_user(void *to, const void *from, unsigned long len)
 {
-	unsigned long over;
+	unsigned long res = len;
 
-	if (access_ok(VERIFY_READ, from, len))
-		return __copy_tofrom_user(to, from, len);
+	if (likely(access_ok(VERIFY_READ, from, len)))
+		res = __copy_tofrom_user(to, from, len);
 
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + len - TASK_SIZE;
-		return __copy_tofrom_user(to, from, len - over) + over;
-	}
-	return len;
+	if (unlikely(res))
+		memset(to + (len - res), 0, res);
+
+	return res;
 }
 
 static inline unsigned long
 copy_to_user(void *to, const void *from, unsigned long len)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_WRITE, to, len))
-		return __copy_tofrom_user(to, from, len);
+	if (likely(access_ok(VERIFY_WRITE, to, len)))
+		len = __copy_tofrom_user(to, from, len);
 
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + len - TASK_SIZE;
-		return __copy_tofrom_user(to, from, len - over) + over;
-	}
 	return len;
 }
 
-#define __copy_from_user(to, from, len)	\
-		__copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+	unsigned long left = __copy_tofrom_user(to, from, len);
+	if (unlikely(left))
+		memset(to + (len - left), 0, left);
+	return left;
+}
 
 #define __copy_to_user(to, from, len)		\
 		__copy_tofrom_user((to), (from), (len))
@@ -340,17 +342,17 @@ __copy_to_user_inatomic(void *to, const void *from, unsigned long len)
 static inline unsigned long
 __copy_from_user_inatomic(void *to, const void *from, unsigned long len)
 {
-	return __copy_from_user(to, from, len);
+	return __copy_tofrom_user(to, from, len);
 }
 
-#define __copy_in_user(to, from, len)	__copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len)	__copy_tofrom_user(to, from, len)
 
 static inline unsigned long
 copy_in_user(void *to, const void *from, unsigned long len)
 {
 	if (access_ok(VERIFY_READ, from, len) &&
 		      access_ok(VERFITY_WRITE, to, len))
-		return copy_from_user(to, from, len);
+		return __copy_tofrom_user(to, from, len);
 }
 
 /*
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index a49635c51266..92ade79ac427 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -151,7 +151,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 	__kernel_size_t __copy_size = (__kernel_size_t) n;
 
 	if (__copy_size && __access_ok(__copy_from, __copy_size))
-		return __copy_user(to, from, __copy_size);
+		__copy_size = __copy_user(to, from, __copy_size);
+
+	if (unlikely(__copy_size))
+		memset(to + (n - __copy_size), 0, __copy_size);
 
 	return __copy_size;
 }
diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h
index c01376c76b86..ca5073dd4596 100644
--- a/arch/sh/include/asm/uaccess_64.h
+++ b/arch/sh/include/asm/uaccess_64.h
@@ -24,6 +24,7 @@
 #define __get_user_size(x,ptr,size,retval)			\
 do {								\
 	retval = 0;						\
+	x = 0;							\
 	switch (size) {						\
 	case 1:							\
 		retval = __get_user_asm_b((void *)&x,		\
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 546293d9e6c5..59b09600dd32 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,6 +43,7 @@ config SPARC
 	select OLD_SIGSUSPEND
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
+	select HAVE_ARCH_HARDENED_USERCOPY
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 57aca2792d29..ea55f86d7ccd 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -248,23 +248,28 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon
 
 static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (n && __access_ok((unsigned long) to, n))
+	if (n && __access_ok((unsigned long) to, n)) {
+		check_object_size(from, n, true);
 		return __copy_user(to, (__force void __user *) from, n);
-	else
+	} else
 		return n;
 }
 
 static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+	check_object_size(from, n, true);
 	return __copy_user(to, (__force void __user *) from, n);
 }
 
 static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (n && __access_ok((unsigned long) from, n))
+	if (n && __access_ok((unsigned long) from, n)) {
+		check_object_size(to, n, false);
 		return __copy_user((__force void __user *) to, from, n);
-	else
+	} else {
+		memset(to, 0, n);
 		return n;
+	}
 }
 
 static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index e9a51d64974d..37a315d0ddd4 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -210,8 +210,11 @@ unsigned long copy_from_user_fixup(void *to, const void __user *from,
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long size)
 {
-	unsigned long ret = ___copy_from_user(to, from, size);
+	unsigned long ret;
 
+	check_object_size(to, size, false);
+
+	ret = ___copy_from_user(to, from, size);
 	if (unlikely(ret))
 		ret = copy_from_user_fixup(to, from, size);
 
@@ -227,8 +230,11 @@ unsigned long copy_to_user_fixup(void __user *to, const void *from,
 static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long size)
 {
-	unsigned long ret = ___copy_to_user(to, from, size);
+	unsigned long ret;
+
+	check_object_size(from, size, true);
 
+	ret = ___copy_to_user(to, from, size);
 	if (unlikely(ret))
 		ret = copy_to_user_fixup(to, from, size);
 	return ret;
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 4820a02838ac..78da75b670bc 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -4,7 +4,6 @@
 config TILE
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index 0a9c4265763b..a77369e91e54 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -416,14 +416,13 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
 	return n;
 }
 
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-/*
- * There are still unprovable places in the generic code as of 2.6.34, so this
- * option is not really compatible with -Werror, which is more useful in
- * general.
- */
-extern void copy_from_user_overflow(void)
-	__compiletime_warning("copy_from_user() size is not provably correct");
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
 
 static inline unsigned long __must_check copy_from_user(void *to,
 					  const void __user *from,
@@ -433,14 +432,13 @@ static inline unsigned long __must_check copy_from_user(void *to,
 
 	if (likely(sz == -1 || sz >= n))
 		n = _copy_from_user(to, from, n);
+	else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
 	else
-		copy_from_user_overflow();
+		__bad_copy_user();
 
 	return n;
 }
-#else
-#define copy_from_user _copy_from_user
-#endif
 
 #ifdef __tilegx__
 /**
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/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c
index ef4b8f949b51..b783ac87d98a 100644
--- a/arch/um/kernel/skas/syscall.c
+++ b/arch/um/kernel/skas/syscall.c
@@ -21,21 +21,17 @@ void handle_syscall(struct uml_pt_regs *r)
 	PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
 
 	if (syscall_trace_enter(regs))
-		return;
+		goto out;
 
 	/* Do the seccomp check after ptrace; failures should be fast. */
 	if (secure_computing(NULL) == -1)
-		return;
+		goto out;
 
-	/* Update the syscall number after orig_ax has potentially been updated
-	 * with ptrace.
-	 */
-	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
 	syscall = UPT_SYSCALL_NR(r);
-
 	if (syscall >= 0 && syscall <= __NR_syscall_max)
 		PT_REGS_SET_SYSCALL_RETURN(regs,
 				EXECUTE_SYSCALL(syscall, regs));
 
+out:
 	syscall_trace_leave(regs);
 }
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index e35632ef23c7..62dfc644c908 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -98,7 +98,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 }
 
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
-		bool write, bool foreign)
+		bool write, bool execute, bool foreign)
 {
 	/* by default, allow everything */
 	return true;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5c6e7471b732..2a1f0ce7c59a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,7 +24,6 @@ config X86
 	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
@@ -80,6 +79,7 @@ config X86
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
 	select HAVE_AOUT			if X86_32
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if X86_64 && SPARSEMEM_VMEMMAP
@@ -91,6 +91,7 @@ config X86
 	select HAVE_ARCH_SOFT_DIRTY		if X86_64
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_EBPF_JIT			if X86_64
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff574dad95cc..94dd4a31f5b3 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1004,79 +1004,87 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 	return status;
 }
 
-static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle, bool is64)
-{
-	struct efi_info *efi = &boot_params->efi_info;
-	unsigned long map_sz, key, desc_size;
-	efi_memory_desc_t *mem_map;
+struct exit_boot_struct {
+	struct boot_params *boot_params;
+	struct efi_info *efi;
 	struct setup_data *e820ext;
-	const char *signature;
 	__u32 e820ext_size;
-	__u32 nr_desc, prev_nr_desc;
-	efi_status_t status;
-	__u32 desc_version;
-	bool called_exit = false;
-	u8 nr_entries;
-	int i;
-
-	nr_desc = 0;
-	e820ext = NULL;
-	e820ext_size = 0;
-
-get_map:
-	status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
-				    &desc_version, &key);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	prev_nr_desc = nr_desc;
-	nr_desc = map_sz / desc_size;
-	if (nr_desc > prev_nr_desc &&
-	    nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
-		u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
-		status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
-		if (status != EFI_SUCCESS)
-			goto free_mem_map;
+	bool is64;
+};
 
-		efi_call_early(free_pool, mem_map);
-		goto get_map; /* Allocated memory, get map again */
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+				   struct efi_boot_memmap *map,
+				   void *priv)
+{
+	static bool first = true;
+	const char *signature;
+	__u32 nr_desc;
+	efi_status_t status;
+	struct exit_boot_struct *p = priv;
+
+	if (first) {
+		nr_desc = *map->buff_size / *map->desc_size;
+		if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+			u32 nr_e820ext = nr_desc -
+					ARRAY_SIZE(p->boot_params->e820_map);
+
+			status = alloc_e820ext(nr_e820ext, &p->e820ext,
+					       &p->e820ext_size);
+			if (status != EFI_SUCCESS)
+				return status;
+		}
+		first = false;
 	}
 
-	signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
-	memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	efi->efi_systab = (unsigned long)sys_table;
-	efi->efi_memdesc_size = desc_size;
-	efi->efi_memdesc_version = desc_version;
-	efi->efi_memmap = (unsigned long)mem_map;
-	efi->efi_memmap_size = map_sz;
+	p->efi->efi_systab = (unsigned long)sys_table_arg;
+	p->efi->efi_memdesc_size = *map->desc_size;
+	p->efi->efi_memdesc_version = *map->desc_ver;
+	p->efi->efi_memmap = (unsigned long)*map->map;
+	p->efi->efi_memmap_size = *map->map_size;
 
 #ifdef CONFIG_X86_64
-	efi->efi_systab_hi = (unsigned long)sys_table >> 32;
-	efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+	p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+	p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
 #endif
 
+	return EFI_SUCCESS;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+			      void *handle, bool is64)
+{
+	unsigned long map_sz, key, desc_size, buff_size;
+	efi_memory_desc_t *mem_map;
+	struct setup_data *e820ext;
+	__u32 e820ext_size;
+	efi_status_t status;
+	__u32 desc_version;
+	struct efi_boot_memmap map;
+	struct exit_boot_struct priv;
+
+	map.map =		&mem_map;
+	map.map_size =		&map_sz;
+	map.desc_size =		&desc_size;
+	map.desc_ver =		&desc_version;
+	map.key_ptr =		&key;
+	map.buff_size =		&buff_size;
+	priv.boot_params =	boot_params;
+	priv.efi =		&boot_params->efi_info;
+	priv.e820ext =		NULL;
+	priv.e820ext_size =	0;
+	priv.is64 =		is64;
+
 	/* Might as well exit boot services now */
-	status = efi_call_early(exit_boot_services, handle, key);
-	if (status != EFI_SUCCESS) {
-		/*
-		 * ExitBootServices() will fail if any of the event
-		 * handlers change the memory map. In which case, we
-		 * must be prepared to retry, but only once so that
-		 * we're guaranteed to exit on repeated failures instead
-		 * of spinning forever.
-		 */
-		if (called_exit)
-			goto free_mem_map;
-
-		called_exit = true;
-		efi_call_early(free_pool, mem_map);
-		goto get_map;
-	}
+	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+					exit_boot_func);
+	if (status != EFI_SUCCESS)
+		return status;
 
+	e820ext = priv.e820ext;
+	e820ext_size = priv.e820ext_size;
 	/* Historic? */
 	boot_params->alt_mem_k = 32 * 1024;
 
@@ -1085,10 +1093,6 @@ get_map:
 		return status;
 
 	return EFI_SUCCESS;
-
-free_mem_map:
-	efi_call_early(free_pool, mem_map);
-	return status;
 }
 
 /*
diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config
index 4e2ecfa23c15..4b429df40d7a 100644
--- a/arch/x86/configs/tiny.config
+++ b/arch/x86/configs/tiny.config
@@ -1 +1,3 @@
 CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 89fa85e8b10c..6f97fb33ae21 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -485,10 +485,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index b691da981cd9..a78a0694ddef 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -265,13 +265,14 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2)
 	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
-	movl	_args_digest+4*32(state, idx, 4), tmp2_w
+	vmovd   _args_digest(state , idx, 4) , %xmm0
 	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
 
-	vmovdqu	%xmm0, _result_digest(job_rax)
-	movl	tmp2_w, _result_digest+1*16(job_rax)
+        vmovdqu %xmm0, _result_digest(job_rax)
+        offset =  (_result_digest + 1*16)
+        vmovdqu %xmm1, offset(job_rax)
 
 	pop	%rbx
 
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index f4cf5b78fd36..d210174a52b0 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -497,10 +497,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index fe91c25092da..77f28ce9c646 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -5,6 +5,8 @@
 OBJECT_FILES_NON_STANDARD_entry_$(BITS).o   := y
 OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
 
+CFLAGS_syscall_64.o		+= -Wno-override-init
+CFLAGS_syscall_32.o		+= -Wno-override-init
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index b846875aeea6..d172c619c449 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -288,11 +288,15 @@ return_from_SYSCALL_64:
 	jne	opportunistic_sysret_failed
 
 	/*
-	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
-	 * restoring TF results in a trap from userspace immediately after
-	 * SYSRET.  This would cause an infinite loop whenever #DB happens
-	 * with register state that satisfies the opportunistic SYSRET
-	 * conditions.  For example, single-stepping this user code:
+	 * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
+	 * restore RF properly. If the slowpath sets it for whatever reason, we
+	 * need to restore it correctly.
+	 *
+	 * SYSRET can restore TF, but unlike IRET, restoring TF results in a
+	 * trap from userspace immediately after SYSRET.  This would cause an
+	 * infinite loop whenever #DB happens with register state that satisfies
+	 * the opportunistic SYSRET conditions.  For example, single-stepping
+	 * this user code:
 	 *
 	 *           movq	$stuck_here, %rcx
 	 *           pushfq
@@ -601,9 +605,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym)
 .endm
 #endif
 
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+# define PUSH_SECTION_IRQENTRY	.pushsection .irqentry.text, "ax"
+# define POP_SECTION_IRQENTRY	.popsection
+#else
+# define PUSH_SECTION_IRQENTRY
+# define POP_SECTION_IRQENTRY
+#endif
+
 .macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
 apicinterrupt3 \num \sym \do_sym
 trace_apicinterrupt \num \sym
+POP_SECTION_IRQENTRY
 .endm
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e07a22bb9308..f5f4b3fbbbc2 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -119,8 +119,8 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
   [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
   [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x0080,
-  [PERF_COUNT_HW_CACHE_MISSES]			= 0x0081,
+  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x077d,
+  [PERF_COUNT_HW_CACHE_MISSES]			= 0x077e,
   [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
   [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
   [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index e6131d4454e6..65577f081d07 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -29,6 +29,8 @@
 
 #define COUNTER_SHIFT		16
 
+static HLIST_HEAD(uncore_unused_list);
+
 struct amd_uncore {
 	int id;
 	int refcnt;
@@ -39,7 +41,7 @@ struct amd_uncore {
 	cpumask_t *active_mask;
 	struct pmu *pmu;
 	struct perf_event *events[MAX_COUNTERS];
-	struct amd_uncore *free_when_cpu_online;
+	struct hlist_node node;
 };
 
 static struct amd_uncore * __percpu *amd_uncore_nb;
@@ -306,6 +308,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
 		uncore_nb->active_mask = &amd_nb_active_mask;
 		uncore_nb->pmu = &amd_nb_pmu;
+		uncore_nb->id = -1;
 		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
@@ -319,6 +322,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
 		uncore_l2->active_mask = &amd_l2_active_mask;
 		uncore_l2->pmu = &amd_l2_pmu;
+		uncore_l2->id = -1;
 		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
 	}
 
@@ -348,7 +352,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
 			continue;
 
 		if (this->id == that->id) {
-			that->free_when_cpu_online = this;
+			hlist_add_head(&this->node, &uncore_unused_list);
 			this = that;
 			break;
 		}
@@ -388,13 +392,23 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
 	return 0;
 }
 
+static void uncore_clean_online(void)
+{
+	struct amd_uncore *uncore;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+		hlist_del(&uncore->node);
+		kfree(uncore);
+	}
+}
+
 static void uncore_online(unsigned int cpu,
 			  struct amd_uncore * __percpu *uncores)
 {
 	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
 
-	kfree(uncore->free_when_cpu_online);
-	uncore->free_when_cpu_online = NULL;
+	uncore_clean_online();
 
 	if (cpu == uncore->cpu)
 		cpumask_set_cpu(cpu, uncore->active_mask);
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 0a6e393a2e62..bdcd6510992c 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -31,7 +31,17 @@
 struct bts_ctx {
 	struct perf_output_handle	handle;
 	struct debug_store		ds_back;
-	int				started;
+	int				state;
+};
+
+/* BTS context states: */
+enum {
+	/* no ongoing AUX transactions */
+	BTS_STATE_STOPPED = 0,
+	/* AUX transaction is on, BTS tracing is disabled */
+	BTS_STATE_INACTIVE,
+	/* AUX transaction is on, BTS tracing is running */
+	BTS_STATE_ACTIVE,
 };
 
 static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
@@ -204,6 +214,15 @@ static void bts_update(struct bts_ctx *bts)
 static int
 bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ *  - is set when bts::handle::event is valid, that is, between
+ *    perf_aux_output_begin() and perf_aux_output_end();
+ *  - is zero otherwise;
+ *  - is ordered against bts::handle::event with a compiler barrier.
+ */
+
 static void __bts_event_start(struct perf_event *event)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
@@ -221,10 +240,13 @@ static void __bts_event_start(struct perf_event *event)
 
 	/*
 	 * local barrier to make sure that ds configuration made it
-	 * before we enable BTS
+	 * before we enable BTS and bts::state goes ACTIVE
 	 */
 	wmb();
 
+	/* INACTIVE/STOPPED -> ACTIVE */
+	WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
 	intel_pmu_enable_bts(config);
 
 }
@@ -251,9 +273,6 @@ static void bts_event_start(struct perf_event *event, int flags)
 
 	__bts_event_start(event);
 
-	/* PMI handler: this counter is running and likely generating PMIs */
-	ACCESS_ONCE(bts->started) = 1;
-
 	return;
 
 fail_end_stop:
@@ -263,30 +282,34 @@ fail_stop:
 	event->hw.state = PERF_HES_STOPPED;
 }
 
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
 {
+	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+	/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+	WRITE_ONCE(bts->state, state);
+
 	/*
 	 * No extra synchronization is mandated by the documentation to have
 	 * BTS data stores globally visible.
 	 */
 	intel_pmu_disable_bts();
-
-	if (event->hw.state & PERF_HES_STOPPED)
-		return;
-
-	ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
 }
 
 static void bts_event_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_buffer *buf = NULL;
+	int state = READ_ONCE(bts->state);
 
-	/* PMI handler: don't restart this counter */
-	ACCESS_ONCE(bts->started) = 0;
+	if (state == BTS_STATE_ACTIVE)
+		__bts_event_stop(event, BTS_STATE_STOPPED);
 
-	__bts_event_stop(event);
+	if (state != BTS_STATE_STOPPED)
+		buf = perf_get_aux(&bts->handle);
+
+	event->hw.state |= PERF_HES_STOPPED;
 
 	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
@@ -296,6 +319,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
 				bts->handle.head =
 					local_xchg(&buf->data_size,
 						   buf->nr_pages << PAGE_SHIFT);
+
 			perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
 					    !!local_xchg(&buf->lost, 0));
 		}
@@ -310,8 +334,20 @@ static void bts_event_stop(struct perf_event *event, int flags)
 void intel_bts_enable_local(void)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	int state = READ_ONCE(bts->state);
+
+	/*
+	 * Here we transition from INACTIVE to ACTIVE;
+	 * if we instead are STOPPED from the interrupt handler,
+	 * stay that way. Can't be ACTIVE here though.
+	 */
+	if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+		return;
+
+	if (state == BTS_STATE_STOPPED)
+		return;
 
-	if (bts->handle.event && bts->started)
+	if (bts->handle.event)
 		__bts_event_start(bts->handle.event);
 }
 
@@ -319,8 +355,15 @@ void intel_bts_disable_local(void)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 
+	/*
+	 * Here we transition from ACTIVE to INACTIVE;
+	 * do nothing for STOPPED or INACTIVE.
+	 */
+	if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+		return;
+
 	if (bts->handle.event)
-		__bts_event_stop(bts->handle.event);
+		__bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
 }
 
 static int
@@ -335,8 +378,6 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 		return 0;
 
 	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
-	if (WARN_ON_ONCE(head != local_read(&buf->head)))
-		return -EINVAL;
 
 	phys = &buf->buf[buf->cur_buf];
 	space = phys->offset + phys->displacement + phys->size - head;
@@ -403,22 +444,37 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 
 int intel_bts_interrupt(void)
 {
+	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct perf_event *event = bts->handle.event;
 	struct bts_buffer *buf;
 	s64 old_head;
-	int err;
+	int err = -ENOSPC, handled = 0;
 
-	if (!event || !bts->started)
-		return 0;
+	/*
+	 * The only surefire way of knowing if this NMI is ours is by checking
+	 * the write ptr against the PMI threshold.
+	 */
+	if (ds->bts_index >= ds->bts_interrupt_threshold)
+		handled = 1;
+
+	/*
+	 * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+	 * so we can only be INACTIVE or STOPPED
+	 */
+	if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+		return handled;
 
 	buf = perf_get_aux(&bts->handle);
+	if (!buf)
+		return handled;
+
 	/*
 	 * Skip snapshot counters: they don't use the interrupt, but
 	 * there's no other way of telling, because the pointer will
 	 * keep moving
 	 */
-	if (!buf || buf->snapshot)
+	if (buf->snapshot)
 		return 0;
 
 	old_head = local_read(&buf->head);
@@ -426,18 +482,27 @@ int intel_bts_interrupt(void)
 
 	/* no new data */
 	if (old_head == local_read(&buf->head))
-		return 0;
+		return handled;
 
 	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
 			    !!local_xchg(&buf->lost, 0));
 
 	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
-		return 1;
+	if (buf)
+		err = bts_buffer_reset(buf, &bts->handle);
+
+	if (err) {
+		WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
 
-	err = bts_buffer_reset(buf, &bts->handle);
-	if (err)
-		perf_aux_output_end(&bts->handle, 0, false);
+		if (buf) {
+			/*
+			 * BTS_STATE_STOPPED should be visible before
+			 * cleared handle::event
+			 */
+			barrier();
+			perf_aux_output_end(&bts->handle, 0, false);
+		}
+	}
 
 	return 1;
 }
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2cbde2f449aa..4c9a79b9cd69 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1730,9 +1730,11 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * disabled state if called consecutively.
  *
  * During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
  */
 static void __intel_pmu_disable_all(void)
 {
@@ -1742,8 +1744,6 @@ static void __intel_pmu_disable_all(void)
 
 	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
-	else
-		intel_bts_disable_local();
 
 	intel_pmu_pebs_disable_all();
 }
@@ -1771,8 +1771,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 			return;
 
 		intel_pmu_enable_bts(event->hw.config);
-	} else
-		intel_bts_enable_local();
+	}
 }
 
 static void intel_pmu_enable_all(int added)
@@ -2073,6 +2072,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	 */
 	if (!x86_pmu.late_ack)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
+	intel_bts_disable_local();
 	__intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
@@ -2172,6 +2172,7 @@ done:
 	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
 	if (cpuc->enabled)
 		__intel_pmu_enable_all(0, true);
+	intel_bts_enable_local();
 
 	/*
 	 * Only unmask the NMI after the overflow counters
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 783c49ddef29..8f82b02934fa 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -458,6 +458,11 @@ static void __intel_cqm_event_count(void *info);
 static void init_mbm_sample(u32 rmid, u32 evt_type);
 static void __intel_mbm_event_count(void *info);
 
+static bool is_cqm_event(int e)
+{
+	return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
 static bool is_mbm_event(int e)
 {
 	return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
@@ -1366,6 +1371,10 @@ static int intel_cqm_event_init(struct perf_event *event)
 	     (event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
 		return -EINVAL;
 
+	if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+	    (is_mbm_event(event->attr.config) && !mbm_enabled))
+		return -EINVAL;
+
 	/* unsupported modes and filters */
 	if (event->attr.exclude_user   ||
 	    event->attr.exclude_kernel ||
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f669e6..9b983a474253 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1274,18 +1274,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		struct pebs_record_nhm *p = at;
 		u64 pebs_status;
 
-		/* PEBS v3 has accurate status bits */
+		pebs_status = p->status & cpuc->pebs_enabled;
+		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
-			for_each_set_bit(bit, (unsigned long *)&p->status,
-					 MAX_PEBS_EVENTS)
+			for_each_set_bit(bit, (unsigned long *)&pebs_status,
+					 x86_pmu.max_pebs_events)
 				counts[bit]++;
 
 			continue;
 		}
 
-		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
 		/*
 		 * On some CPUs the PEBS status can be zero when PEBS is
 		 * racing with clearing of GLOBAL_STATUS.
@@ -1333,8 +1333,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		event = cpuc->events[bit];
-		WARN_ON_ONCE(!event);
-		WARN_ON_ONCE(!event->attr.precise_ip);
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		if (WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
 
 		/* log dropped samples number */
 		if (error[bit])
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 04bb5fb5a8d7..861a7d9cb60f 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1074,6 +1074,11 @@ static void pt_addr_filters_fini(struct perf_event *event)
 	event->hw.addr_filters = NULL;
 }
 
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+	return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
 static int pt_event_addr_filters_validate(struct list_head *filters)
 {
 	struct perf_addr_filter *filter;
@@ -1081,11 +1086,16 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 
 	list_for_each_entry(filter, filters, entry) {
 		/* PT doesn't support single address triggers */
-		if (!filter->range)
+		if (!filter->range || !filter->size)
 			return -EOPNOTSUPP;
 
-		if (!filter->inode && !kernel_ip(filter->offset))
-			return -EINVAL;
+		if (!filter->inode) {
+			if (!valid_kernel_ip(filter->offset))
+				return -EINVAL;
+
+			if (!valid_kernel_ip(filter->offset + filter->size))
+				return -EINVAL;
+		}
 
 		if (++range > pt_cap_get(PT_CAP_num_address_ranges))
 			return -EOPNOTSUPP;
@@ -1111,7 +1121,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		} else {
 			/* apply the offset */
 			msr_a = filter->offset + offs[range];
-			msr_b = filter->size + msr_a;
+			msr_b = filter->size + msr_a - 1;
 		}
 
 		filters->filter[range].msr_a  = msr_a;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 97a69dbba649..9d35ec0cb8fc 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+		SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
 static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
@@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = {
 
 static struct intel_uncore_ops snb_uncore_msr_ops = {
 	.init_box	= snb_uncore_msr_init_box,
+	.enable_box	= snb_uncore_msr_enable_box,
 	.exit_box	= snb_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
@@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+		SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
 static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
@@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 
 static struct intel_uncore_ops skl_uncore_msr_ops = {
 	.init_box	= skl_uncore_msr_init_box,
+	.enable_box	= skl_uncore_msr_enable_box,
 	.exit_box	= skl_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 824e54086e07..8aee83bcf71f 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2626,7 +2626,7 @@ void hswep_uncore_cpu_init(void)
 
 static struct intel_uncore_type hswep_uncore_ha = {
 	.name		= "ha",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 2,
 	.perf_ctr_bits	= 48,
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
@@ -2645,7 +2645,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = {
 
 static struct intel_uncore_type hswep_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
@@ -2691,7 +2691,7 @@ static struct intel_uncore_type hswep_uncore_irp = {
 
 static struct intel_uncore_type hswep_uncore_qpi = {
 	.name			= "qpi",
-	.num_counters		= 5,
+	.num_counters		= 4,
 	.num_boxes		= 3,
 	.perf_ctr_bits		= 48,
 	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
@@ -2773,7 +2773,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = {
 
 static struct intel_uncore_type hswep_uncore_r3qpi = {
 	.name		= "r3qpi",
-	.num_counters   = 4,
+	.num_counters   = 3,
 	.num_boxes	= 3,
 	.perf_ctr_bits	= 44,
 	.constraints	= hswep_uncore_r3qpi_constraints,
@@ -2972,7 +2972,7 @@ static struct intel_uncore_type bdx_uncore_ha = {
 
 static struct intel_uncore_type bdx_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f5befd4945f2..124357773ffa 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -135,6 +135,7 @@ extern void init_apic_mappings(void);
 void register_lapic_address(unsigned long address);
 extern void setup_boot_APIC_clock(void);
 extern void setup_secondary_APIC_clock(void);
+extern void lapic_update_tsc_freq(void);
 extern int APIC_init_uniprocessor(void);
 
 #ifdef CONFIG_X86_64
@@ -170,6 +171,7 @@ static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
 # define setup_boot_APIC_clock x86_init_noop
 # define setup_secondary_APIC_clock x86_init_noop
+static inline void lapic_update_tsc_freq(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 7178043b0e1d..59405a248fc2 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -22,10 +22,6 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	/*
-	 * irq_tlb_count is double-counted in irq_call_count, so it must be
-	 * subtracted from irq_call_count when displaying irq_call_count
-	 */
 	unsigned int irq_tlb_count;
 #endif
 #ifdef CONFIG_X86_THERMAL_VECTOR
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 223042086f4e..737da62bfeb0 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -5,10 +5,10 @@ struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
 	void *context;			 /* context for alloc_pgt_page */
 	unsigned long pmd_flag;		 /* page flag for PMD entry */
-	bool kernel_mapping;		 /* kernel mapping or ident mapping */
+	unsigned long offset;		 /* ident mapping offset */
 };
 
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
-				unsigned long addr, unsigned long end);
+				unsigned long pstart, unsigned long pend);
 
 #endif /* _ASM_X86_INIT_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 7e8ec7ae10fa..1cc82ece9ac1 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2|1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
- * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
+ * | OFFSET (14->63) | TYPE (9-13)  |0|X|X|X| X| X|X|X|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
 #define SWP_TYPE_BITS 5
 /* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
+#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 9c6b890d5e7a..b2988c0ed829 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -58,7 +58,15 @@ extern unsigned char boot_gdt[];
 extern unsigned char secondary_startup_64[];
 #endif
 
+static inline size_t real_mode_size_needed(void)
+{
+	if (real_mode_header)
+		return 0;	/* already allocated. */
+
+	return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
+}
+
+void set_real_mode_mem(phys_addr_t mem, size_t size);
 void reserve_real_mode(void);
-void setup_real_mode(void);
 
 #endif /* _ARCH_X86_REALMODE_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 84b59846154a..8b7c8d8e0852 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -176,6 +176,50 @@ static inline unsigned long current_stack_pointer(void)
 	return sp;
 }
 
+/*
+ * Walks up the stack frames to make sure that the specified object is
+ * entirely contained by a single stack frame.
+ *
+ * Returns:
+ *		 1 if within a frame
+ *		-1 if placed across a frame boundary (or outside stack)
+ *		 0 unable to determine (no frame pointers, etc)
+ */
+static inline int arch_within_stack_frames(const void * const stack,
+					   const void * const stackend,
+					   const void *obj, unsigned long len)
+{
+#if defined(CONFIG_FRAME_POINTER)
+	const void *frame = NULL;
+	const void *oldframe;
+
+	oldframe = __builtin_frame_address(1);
+	if (oldframe)
+		frame = __builtin_frame_address(2);
+	/*
+	 * low ----------------------------------------------> high
+	 * [saved bp][saved ip][args][local vars][saved bp][saved ip]
+	 *                     ^----------------^
+	 *               allow copies only within here
+	 */
+	while (stack <= frame && frame < stackend) {
+		/*
+		 * If obj + len extends past the last frame, this
+		 * check won't pass and the next frame will be 0,
+		 * causing us to bail out and correctly report
+		 * the copy as invalid.
+		 */
+		if (obj + len <= frame)
+			return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1;
+		oldframe = frame;
+		frame = *(const void * const *)frame;
+	}
+	return -1;
+#else
+	return 0;
+#endif
+}
+
 #else /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 4e5be94e079a..6fa85944af83 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -135,7 +135,14 @@ 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/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index c03bfb68c503..2131c4ce7d8a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -433,7 +433,11 @@ do {									\
 #define __get_user_asm_ex(x, addr, itype, rtype, ltype)			\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
-		     _ASM_EXTABLE_EX(1b, 2b)				\
+		     ".section .fixup,\"ax\"\n"				\
+                     "3:xor"itype" %"rtype"0,%"rtype"0\n"		\
+		     "  jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE_EX(1b, 3b)				\
 		     : ltype(x) : "m" (__m(addr)))
 
 #define __put_user_nocheck(x, ptr, size)			\
@@ -697,44 +701,15 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from,
 unsigned long __must_check _copy_to_user(void __user *to, const void *from,
 					 unsigned n);
 
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-# define copy_user_diag __compiletime_error
-#else
-# define copy_user_diag __compiletime_warning
-#endif
-
-extern void copy_user_diag("copy_from_user() buffer size is too small")
-copy_from_user_overflow(void);
-extern void copy_user_diag("copy_to_user() buffer size is too small")
-copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
-
-#undef copy_user_diag
-
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-
-extern void
-__compiletime_warning("copy_from_user() buffer size is not provably correct")
-__copy_from_user_overflow(void) __asm__("copy_from_user_overflow");
-#define __copy_from_user_overflow(size, count) __copy_from_user_overflow()
-
-extern void
-__compiletime_warning("copy_to_user() buffer size is not provably correct")
-__copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
-#define __copy_to_user_overflow(size, count) __copy_to_user_overflow()
-
-#else
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
 
-static inline void
-__copy_from_user_overflow(int size, unsigned long count)
+static inline void copy_user_overflow(int size, unsigned long count)
 {
 	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
 }
 
-#define __copy_to_user_overflow __copy_from_user_overflow
-
-#endif
-
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
@@ -743,35 +718,18 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 
 	kasan_check_write(to, n);
 
-	/*
-	 * While we would like to have the compiler do the checking for us
-	 * even in the non-constant size case, any false positives there are
-	 * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even
-	 * without - the [hopefully] dangerous looking nature of the warning
-	 * would make people go look at the respecitive call sites over and
-	 * over again just to find that there's no problem).
-	 *
-	 * And there are cases where it's just not realistic for the compiler
-	 * to prove the count to be in range. For example when multiple call
-	 * sites of a helper function - perhaps in different source files -
-	 * all doing proper range checking, yet the helper function not doing
-	 * so again.
-	 *
-	 * Therefore limit the compile time checking to the constant size
-	 * case, and do only runtime checking for non-constant sizes.
-	 */
-
-	if (likely(sz < 0 || sz >= n))
+	if (likely(sz < 0 || sz >= n)) {
+		check_object_size(to, n, false);
 		n = _copy_from_user(to, from, n);
-	else if(__builtin_constant_p(n))
-		copy_from_user_overflow();
+	} else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
 	else
-		__copy_from_user_overflow(sz, n);
+		__bad_copy_user();
 
 	return n;
 }
 
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	int sz = __compiletime_object_size(from);
@@ -780,20 +738,17 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
 
 	might_fault();
 
-	/* See the comment in copy_from_user() above. */
-	if (likely(sz < 0 || sz >= n))
+	if (likely(sz < 0 || sz >= n)) {
+		check_object_size(from, n, true);
 		n = _copy_to_user(to, from, n);
-	else if(__builtin_constant_p(n))
-		copy_to_user_overflow();
+	} else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
 	else
-		__copy_to_user_overflow(sz, n);
+		__bad_copy_user();
 
 	return n;
 }
 
-#undef __copy_from_user_overflow
-#undef __copy_to_user_overflow
-
 /*
  * We rely on the nested NMI work to allow atomic faults from the NMI path; the
  * nested NMI paths are careful to preserve CR2.
@@ -812,21 +767,21 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
 #define user_access_begin()	__uaccess_begin()
 #define user_access_end()	__uaccess_end()
 
-#define unsafe_put_user(x, ptr)						\
-({										\
+#define unsafe_put_user(x, ptr, err_label)					\
+do {										\
 	int __pu_err;								\
 	__put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT);		\
-	__builtin_expect(__pu_err, 0);						\
-})
+	if (unlikely(__pu_err)) goto err_label;					\
+} while (0)
 
-#define unsafe_get_user(x, ptr)						\
-({										\
+#define unsafe_get_user(x, ptr, err_label)					\
+do {										\
 	int __gu_err;								\
 	unsigned long __gu_val;							\
 	__get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
-	__builtin_expect(__gu_err, 0);						\
-})
+	if (unlikely(__gu_err)) goto err_label;					\
+} while (0)
 
 #endif /* _ASM_X86_UACCESS_H */
 
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 4b32da24faaf..7d3bdd1ed697 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -37,6 +37,7 @@ unsigned long __must_check __copy_from_user_ll_nocache_nozero
 static __always_inline unsigned long __must_check
 __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 {
+	check_object_size(from, n, true);
 	return __copy_to_user_ll(to, from, n);
 }
 
@@ -95,6 +96,7 @@ static __always_inline unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	might_fault();
+	check_object_size(to, n, false);
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 2eac2aa3e37f..673059a109fe 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -54,6 +54,7 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
 
+	check_object_size(dst, size, false);
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
@@ -119,6 +120,7 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
 {
 	int ret = 0;
 
+	check_object_size(src, size, true);
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index c852590254d5..e652a7cc6186 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -79,7 +79,7 @@ struct uv_gam_range_entry {
 	u16	nasid;		/* HNasid */
 	u16	sockid;		/* Socket ID, high bits of APIC ID */
 	u16	pnode;		/* Index to MMR and GRU spaces */
-	u32	pxm;		/* ACPI proximity domain number */
+	u32	unused2;
 	u32	limit;		/* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
 };
 
@@ -88,7 +88,8 @@ struct uv_gam_range_entry {
 #define	UV_SYSTAB_VERSION_UV4		0x400	/* UV4 BIOS base version */
 #define	UV_SYSTAB_VERSION_UV4_1		0x401	/* + gpa_shift */
 #define	UV_SYSTAB_VERSION_UV4_2		0x402	/* + TYPE_NVRAM/WINDOW/MBOX */
-#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_2
+#define	UV_SYSTAB_VERSION_UV4_3		0x403	/* - GAM Range PXM Value */
+#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_3
 
 #define	UV_SYSTAB_TYPE_UNUSED		0	/* End of table (offset == 0) */
 #define	UV_SYSTAB_TYPE_GAM_PARAMS	1	/* GAM PARAM conversions */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 20abd912f0e4..f3e9b2df4b16 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -313,7 +313,7 @@ int lapic_get_maxlvt(void)
 
 /* Clock divisor */
 #define APIC_DIVISOR 16
-#define TSC_DIVISOR  32
+#define TSC_DIVISOR  8
 
 /*
  * This function sets up the local APIC timer, with a timeout of
@@ -565,13 +565,37 @@ static void setup_APIC_timer(void)
 				    CLOCK_EVT_FEAT_DUMMY);
 		levt->set_next_event = lapic_next_deadline;
 		clockevents_config_and_register(levt,
-						(tsc_khz / TSC_DIVISOR) * 1000,
+						tsc_khz * (1000 / TSC_DIVISOR),
 						0xF, ~0UL);
 	} else
 		clockevents_register_device(levt);
 }
 
 /*
+ * Install the updated TSC frequency from recalibration at the TSC
+ * deadline clockevent devices.
+ */
+static void __lapic_update_tsc_freq(void *info)
+{
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
+
+	if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return;
+
+	clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR));
+}
+
+void lapic_update_tsc_freq(void)
+{
+	/*
+	 * The clockevent device's ->mult and ->shift can both be
+	 * changed. In order to avoid races, schedule the frequency
+	 * update code on each CPU.
+	 */
+	on_each_cpu(__lapic_update_tsc_freq, NULL, 0);
+}
+
+/*
  * In this functions we calibrate APIC bus clocks to the external timer.
  *
  * We want to do the calibration only once since we want to have local timer
@@ -1599,6 +1623,9 @@ 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;
@@ -2066,7 +2093,6 @@ int generic_processor_info(int apicid, int version)
 		return -EINVAL;
 	}
 
-	num_processors++;
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
 		 * x86_bios_cpu_apicid is required to have processors listed
@@ -2089,10 +2115,13 @@ int generic_processor_info(int apicid, int version)
 
 		pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
 			   thiscpu, apicid);
+
 		disabled_cpus++;
 		return -ENOSPC;
 	}
 
+	num_processors++;
+
 	/*
 	 * Validate version
 	 */
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 6368fa69d2af..54f35d988025 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -155,7 +155,7 @@ static void init_x2apic_ldr(void)
 /*
  * At CPU state changes, update the x2apic cluster sibling info.
  */
-int x2apic_prepare_cpu(unsigned int cpu)
+static int x2apic_prepare_cpu(unsigned int cpu)
 {
 	if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
 		return -ENOMEM;
@@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu)
 	return 0;
 }
 
-int x2apic_dead_cpu(unsigned int this_cpu)
+static int x2apic_dead_cpu(unsigned int this_cpu)
 {
 	int cpu;
 
@@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu)
 static int x2apic_cluster_probe(void)
 {
 	int cpu = smp_processor_id();
+	int ret;
 
 	if (!x2apic_mode)
 		return 0;
 
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+				x2apic_prepare_cpu, x2apic_dead_cpu);
+	if (ret < 0) {
+		pr_err("Failed to register X2APIC_PREPARE\n");
+		return 0;
+	}
 	cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
-	cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
-			  x2apic_prepare_cpu, x2apic_dead_cpu);
 	return 1;
 }
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 09b59adaea3f..cb0673c1e940 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -223,6 +223,11 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	if (strncmp(oem_id, "SGI", 3) != 0)
 		return 0;
 
+	if (numa_off) {
+		pr_err("UV: NUMA is off, disabling UV support\n");
+		return 0;
+	}
+
 	/* Setup early hub type field in uv_hub_info for Node 0 */
 	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
 
@@ -325,7 +330,7 @@ static __init void build_uv_gr_table(void)
 	struct uv_gam_range_entry *gre = uv_gre_table;
 	struct uv_gam_range_s *grt;
 	unsigned long last_limit = 0, ram_limit = 0;
-	int bytes, i, sid, lsid = -1;
+	int bytes, i, sid, lsid = -1, indx = 0, lindx = -1;
 
 	if (!gre)
 		return;
@@ -356,11 +361,12 @@ static __init void build_uv_gr_table(void)
 		}
 		sid = gre->sockid - _min_socket;
 		if (lsid < sid) {		/* new range */
-			grt = &_gr_table[sid];
-			grt->base = lsid;
+			grt = &_gr_table[indx];
+			grt->base = lindx;
 			grt->nasid = gre->nasid;
 			grt->limit = last_limit = gre->limit;
 			lsid = sid;
+			lindx = indx++;
 			continue;
 		}
 		if (lsid == sid && !ram_limit) {	/* update range */
@@ -371,7 +377,7 @@ static __init void build_uv_gr_table(void)
 		}
 		if (!ram_limit) {		/* non-contiguous ram range */
 			grt++;
-			grt->base = sid - 1;
+			grt->base = lindx;
 			grt->nasid = gre->nasid;
 			grt->limit = last_limit = gre->limit;
 			continue;
@@ -1155,19 +1161,18 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (!index) {
 			pr_info("UV: GAM Range Table...\n");
-			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s %3s\n",
+			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n",
 				"Range", "", "Size", "Type", "NASID",
-				"SID", "PN", "PXM");
+				"SID", "PN");
 		}
 		pr_info(
-		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x %3d\n",
+		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x\n",
 			index++,
 			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
 			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
 			((unsigned long)(gre->limit - lgre)) >>
 				(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
-			gre->type, gre->nasid, gre->sockid,
-			gre->pnode, gre->pxm);
+			gre->type, gre->nasid, gre->sockid, gre->pnode);
 
 		lgre = gre->limit;
 		if (sock_min > gre->sockid)
@@ -1286,7 +1291,7 @@ static void __init build_socket_tables(void)
 		_pnode_to_socket[i] = SOCK_EMPTY;
 
 	/* fill in pnode/node/addr conversion list values */
-	pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n");
+	pr_info("UV: GAM Building socket/pnode conversion tables\n");
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
 			continue;
@@ -1294,20 +1299,18 @@ static void __init build_socket_tables(void)
 		if (_socket_to_pnode[i] != SOCK_EMPTY)
 			continue;	/* duplicate */
 		_socket_to_pnode[i] = gre->pnode;
-		_socket_to_node[i] = gre->pxm;
 
 		i = gre->pnode - minpnode;
 		_pnode_to_socket[i] = gre->sockid;
 
 		pr_info(
-		"UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n",
+		"UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
 			gre->sockid, gre->type, gre->nasid,
 			_socket_to_pnode[gre->sockid - minsock],
-			_socket_to_node[gre->sockid - minsock],
 			_pnode_to_socket[gre->pnode - minpnode]);
 	}
 
-	/* check socket -> node values */
+	/* Set socket -> node values */
 	lnid = -1;
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
@@ -1318,14 +1321,9 @@ static void __init build_socket_tables(void)
 		lnid = nid;
 		apicid = per_cpu(x86_cpu_to_apicid, cpu);
 		sockid = apicid >> uv_cpuid.socketid_shift;
-		i = sockid - minsock;
-
-		if (nid != _socket_to_node[i]) {
-			pr_warn(
-			"UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n",
-				i, sockid, gre->type, _socket_to_node[i], nid);
-			_socket_to_node[i] = nid;
-		}
+		_socket_to_node[sockid - minsock] = nid;
+		pr_info("UV: sid:%02x: apicid:%04x node:%2d\n",
+			sockid, apicid, nid);
 	}
 
 	/* Setup physical blade to pnode translation from GAM Range Table */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f5c69d8974e1..b81fe2d63e15 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -669,6 +669,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
 }
 
+#define MSR_AMD64_DE_CFG	0xC0011029
+
+static void init_amd_ln(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Apply erratum 665 fix unconditionally so machines without a BIOS
+	 * fix work.
+	 */
+	msr_set_bit(MSR_AMD64_DE_CFG, 31);
+}
+
 static void init_amd_bd(struct cpuinfo_x86 *c)
 {
 	u64 value;
@@ -726,6 +737,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 6:	   init_amd_k7(c); break;
 	case 0xf:  init_amd_k8(c); break;
 	case 0x10: init_amd_gh(c); break;
+	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	}
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 27a0228c9cae..620ab06bcf45 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -54,6 +54,7 @@ static LIST_HEAD(pcache);
  */
 static u8 *container;
 static size_t container_size;
+static bool ucode_builtin;
 
 static u32 ucode_new_rev;
 static u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -281,18 +282,22 @@ static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
 void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct cpio_data cp;
+	bool *builtin;
 	void **data;
 	size_t *size;
 
 #ifdef CONFIG_X86_32
 	data =  (void **)__pa_nodebug(&ucode_cpio.data);
 	size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+	builtin = (bool *)__pa_nodebug(&ucode_builtin);
 #else
 	data = &ucode_cpio.data;
 	size = &ucode_cpio.size;
+	builtin = &ucode_builtin;
 #endif
 
-	if (!load_builtin_amd_microcode(&cp, family))
+	*builtin = load_builtin_amd_microcode(&cp, family);
+	if (!*builtin)
 		cp = find_ucode_in_initrd();
 
 	if (!(cp.data && cp.size))
@@ -355,6 +360,7 @@ void load_ucode_amd_ap(void)
 	unsigned int cpu = smp_processor_id();
 	struct equiv_cpu_entry *eq;
 	struct microcode_amd *mc;
+	u8 *cont = container;
 	u32 rev, eax;
 	u16 eq_id;
 
@@ -371,8 +377,12 @@ void load_ucode_amd_ap(void)
 	if (check_current_patch_level(&rev, false))
 		return;
 
+	/* Add CONFIG_RANDOMIZE_MEMORY offset. */
+	if (!ucode_builtin)
+		cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+
 	eax = cpuid_eax(0x00000001);
-	eq  = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ);
+	eq  = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
 
 	eq_id = find_equiv_id(eq, eax);
 	if (!eq_id)
@@ -434,6 +444,10 @@ int __init save_microcode_in_initrd_amd(void)
 	else
 		container = cont_va;
 
+	/* Add CONFIG_RANDOMIZE_MEMORY offset. */
+	if (!ucode_builtin)
+		container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 680049aa4593..01567aa87503 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -866,105 +866,17 @@ const void *get_xsave_field_ptr(int xsave_state)
 	return get_xsave_addr(&fpu->state.xsave, xsave_state);
 }
 
-
-/*
- * Set xfeatures (aka XSTATE_BV) bit for a feature that we want
- * to take out of its "init state".  This will ensure that an
- * XRSTOR actually restores the state.
- */
-static void fpu__xfeature_set_non_init(struct xregs_state *xsave,
-		int xstate_feature_mask)
-{
-	xsave->header.xfeatures |= xstate_feature_mask;
-}
-
-/*
- * This function is safe to call whether the FPU is in use or not.
- *
- * Note that this only works on the current task.
- *
- * Inputs:
- *	@xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
- *	XFEATURE_MASK_SSE, etc...)
- *	@xsave_state_ptr: a pointer to a copy of the state that you would
- *	like written in to the current task's FPU xsave state.  This pointer
- *	must not be located in the current tasks's xsave area.
- * Output:
- *	address of the state in the xsave area or NULL if the state
- *	is not present or is in its 'init state'.
- */
-static void fpu__xfeature_set_state(int xstate_feature_mask,
-		void *xstate_feature_src, size_t len)
-{
-	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
-	struct fpu *fpu = &current->thread.fpu;
-	void *dst;
-
-	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
-		WARN_ONCE(1, "%s() attempted with no xsave support", __func__);
-		return;
-	}
-
-	/*
-	 * Tell the FPU code that we need the FPU state to be in
-	 * 'fpu' (not in the registers), and that we need it to
-	 * be stable while we write to it.
-	 */
-	fpu__current_fpstate_write_begin();
-
-	/*
-	 * This method *WILL* *NOT* work for compact-format
-	 * buffers.  If the 'xstate_feature_mask' is unset in
-	 * xcomp_bv then we may need to move other feature state
-	 * "up" in the buffer.
-	 */
-	if (xsave->header.xcomp_bv & xstate_feature_mask) {
-		WARN_ON_ONCE(1);
-		goto out;
-	}
-
-	/* find the location in the xsave buffer of the desired state */
-	dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask);
-
-	/*
-	 * Make sure that the pointer being passed in did not
-	 * come from the xsave buffer itself.
-	 */
-	WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself");
-
-	/* put the caller-provided data in the location */
-	memcpy(dst, xstate_feature_src, len);
-
-	/*
-	 * Mark the xfeature so that the CPU knows there is state
-	 * in the buffer now.
-	 */
-	fpu__xfeature_set_non_init(xsave, xstate_feature_mask);
-out:
-	/*
-	 * We are done writing to the 'fpu'.  Reenable preeption
-	 * and (possibly) move the fpstate back in to the fpregs.
-	 */
-	fpu__current_fpstate_write_end();
-}
-
 #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
 #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
 
 /*
- * This will go out and modify the XSAVE buffer so that PKRU is
- * set to a particular state for access to 'pkey'.
- *
- * PKRU state does affect kernel access to user memory.  We do
- * not modfiy PKRU *itself* here, only the XSAVE state that will
- * be restored in to PKRU when we return back to userspace.
+ * This will go out and modify PKRU register to set the access
+ * rights for @pkey to @init_val.
  */
 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 		unsigned long init_val)
 {
-	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
-	struct pkru_state *old_pkru_state;
-	struct pkru_state new_pkru_state;
+	u32 old_pkru;
 	int pkey_shift = (pkey * PKRU_BITS_PER_PKEY);
 	u32 new_pkru_bits = 0;
 
@@ -974,6 +886,15 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 	 */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return -EINVAL;
+	/*
+	 * For most XSAVE components, this would be an arduous task:
+	 * brining fpstate up to date with fpregs, updating fpstate,
+	 * then re-populating fpregs.  But, for components that are
+	 * never lazily managed, we can just access the fpregs
+	 * directly.  PKRU is never managed lazily, so we can just
+	 * manipulate it directly.  Make sure it stays that way.
+	 */
+	WARN_ON_ONCE(!use_eager_fpu());
 
 	/* Set the bits we need in PKRU:  */
 	if (init_val & PKEY_DISABLE_ACCESS)
@@ -984,37 +905,12 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 	/* Shift the bits in to the correct place in PKRU for pkey: */
 	new_pkru_bits <<= pkey_shift;
 
-	/* Locate old copy of the state in the xsave buffer: */
-	old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU);
-
-	/*
-	 * When state is not in the buffer, it is in the init
-	 * state, set it manually.  Otherwise, copy out the old
-	 * state.
-	 */
-	if (!old_pkru_state)
-		new_pkru_state.pkru = 0;
-	else
-		new_pkru_state.pkru = old_pkru_state->pkru;
-
-	/* Mask off any old bits in place: */
-	new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
-
-	/* Set the newly-requested bits: */
-	new_pkru_state.pkru |= new_pkru_bits;
-
-	/*
-	 * We could theoretically live without zeroing pkru.pad.
-	 * The current XSAVE feature state definition says that
-	 * only bytes 0->3 are used.  But we do not want to
-	 * chance leaking kernel stack out to userspace in case a
-	 * memcpy() of the whole xsave buffer was done.
-	 *
-	 * They're in the same cacheline anyway.
-	 */
-	new_pkru_state.pad = 0;
+	/* Get old PKRU and mask off any old bits in place: */
+	old_pkru = read_pkru();
+	old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
 
-	fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state));
+	/* Write old part along with new part: */
+	write_pkru(old_pkru | new_pkru_bits);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 2dda0bc4576e..f16c55bfc090 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -25,8 +25,6 @@ static void __init i386_default_early_setup(void)
 	/* Initialize 32bit specific setup functions */
 	x86_init.resources.reserve_resources = i386_reserve_resources;
 	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
-
-	reserve_bios_regions();
 }
 
 asmlinkage __visible void __init i386_start_kernel(void)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 99d48e7d2974..54a2372f5dbb 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -183,7 +183,6 @@ void __init x86_64_start_reservations(char *real_mode_data)
 		copy_bootdata(__va(real_mode_data));
 
 	x86_early_init_platform_quirks();
-	reserve_bios_regions();
 
 	switch (boot_params.hdr.hardware_subarch) {
 	case X86_SUBARCH_INTEL_MID:
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ed16e58658a4..c6dfd801df97 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1242,7 +1242,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
 	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
-		mc146818_set_time(&curr_time);
+		mc146818_get_time(&curr_time);
 
 	if (hpet_rtc_flags & RTC_UIE &&
 	    curr_time.tm_sec != hpet_prev_update_sec) {
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 61521dc19c10..9f669fdd2010 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_puts(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
-					irq_stats(j)->irq_tlb_count);
+		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
 	seq_puts(p, "  Function call interrupts\n");
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1d39bfbd26bb..3692249a70f1 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -289,6 +289,7 @@ void __init kvmclock_init(void)
 	put_cpu();
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index ad5bc9578a73..1acfd76e3e26 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -56,12 +56,12 @@ asm (".pushsection .entry.text, \"ax\"\n"
      ".popsection");
 
 /* identity function, which can be inlined */
-u32 _paravirt_ident_32(u32 x)
+u32 notrace _paravirt_ident_32(u32 x)
 {
 	return x;
 }
 
-u64 _paravirt_ident_64(u64 x)
+u64 notrace _paravirt_ident_64(u64 x)
 {
 	return x;
 }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 991b77986d57..0fa60f5f5a16 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -936,8 +936,6 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
-	kernel_randomize_memory();
-
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();
@@ -1055,6 +1053,12 @@ void __init setup_arch(char **cmdline_p)
 
 	max_possible_pfn = max_pfn;
 
+	/*
+	 * Define random base addresses for memory sections after max_pfn is
+	 * defined and before each memory section base is used.
+	 */
+	kernel_randomize_memory();
+
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();
@@ -1097,6 +1101,8 @@ void __init setup_arch(char **cmdline_p)
 		efi_find_mirror();
 	}
 
+	reserve_bios_regions();
+
 	/*
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
@@ -1125,7 +1131,15 @@ void __init setup_arch(char **cmdline_p)
 
 	early_trap_pf_init();
 
-	setup_real_mode();
+	/*
+	 * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
+	 * with the current CR4 value.  This may not be necessary, but
+	 * auditing all the early-boot CR4 manipulation would be needed to
+	 * rule it out.
+	 */
+	if (boot_cpu_data.cpuid_level >= 0)
+		/* A CPU has %cr4 if and only if it has CPUID. */
+		mmu_cr4_features = __read_cr4();
 
 	memblock_set_current_limit(get_max_mapped());
 
@@ -1174,13 +1188,6 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-	if (boot_cpu_data.cpuid_level >= 0) {
-		/* A CPU has %cr4 if and only if it has CPUID */
-		mmu_cr4_features = __read_cr4();
-		if (trampoline_cr4_features)
-			*trampoline_cr4_features = mmu_cr4_features;
-	}
-
 #ifdef CONFIG_X86_32
 	/* sync back kernel address range */
 	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2a6e84a30a54..4296beb8fdd3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -100,10 +100,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 /* Logical package management. We might want to allocate that dynamically */
 static int *physical_to_logical_pkg __read_mostly;
 static unsigned long *physical_package_map __read_mostly;;
-static unsigned long *logical_package_map  __read_mostly;
 static unsigned int max_physical_pkg_id __read_mostly;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
+static unsigned int logical_packages __read_mostly;
+static bool logical_packages_frozen __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
 int __max_smt_threads __read_mostly;
@@ -277,14 +278,14 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu)
 	if (test_and_set_bit(pkg, physical_package_map))
 		goto found;
 
-	new = find_first_zero_bit(logical_package_map, __max_logical_packages);
-	if (new >= __max_logical_packages) {
+	if (logical_packages_frozen) {
 		physical_to_logical_pkg[pkg] = -1;
-		pr_warn("APIC(%x) Package %u exceeds logical package map\n",
+		pr_warn("APIC(%x) Package %u exceeds logical package max\n",
 			apicid, pkg);
 		return -ENOSPC;
 	}
-	set_bit(new, logical_package_map);
+
+	new = logical_packages++;
 	pr_info("APIC(%x) Converting physical %u to logical package %u\n",
 		apicid, pkg, new);
 	physical_to_logical_pkg[pkg] = new;
@@ -341,6 +342,7 @@ static void __init smp_init_package_map(void)
 	}
 
 	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
+	logical_packages = 0;
 
 	/*
 	 * Possibly larger than what we need as the number of apic ids per
@@ -352,10 +354,6 @@ static void __init smp_init_package_map(void)
 	memset(physical_to_logical_pkg, 0xff, size);
 	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
 	physical_package_map = kzalloc(size, GFP_KERNEL);
-	size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long);
-	logical_package_map = kzalloc(size, GFP_KERNEL);
-
-	pr_info("Max logical packages: %u\n", __max_logical_packages);
 
 	for_each_present_cpu(cpu) {
 		unsigned int apicid = apic->cpu_present_to_apicid(cpu);
@@ -369,6 +367,15 @@ static void __init smp_init_package_map(void)
 		set_cpu_possible(cpu, false);
 		set_cpu_present(cpu, false);
 	}
+
+	if (logical_packages > __max_logical_packages) {
+		pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n",
+			logical_packages, __max_logical_packages);
+		logical_packages_frozen = true;
+		__max_logical_packages  = logical_packages;
+	}
+
+	pr_info("Max logical packages: %u\n", __max_logical_packages);
 }
 
 void __init smp_store_boot_cpu_info(void)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 1ef87e887051..78b9cb5a26af 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -22,6 +22,7 @@
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
 #include <asm/geode.h>
+#include <asm/apic.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -1249,6 +1250,9 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 		(unsigned long)tsc_khz / 1000,
 		(unsigned long)tsc_khz % 1000);
 
+	/* Inform the TSC deadline clockevent devices about the recalibration */
+	lapic_update_tsc_freq();
+
 out:
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c1ff31d99ff..495c776de4b4 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/ioapic.c b/arch/x86/kvm/ioapic.c
index 5f42d038fcb4..c7220ba94aa7 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -109,6 +109,7 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 {
 	bool new_val, old_val;
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
 	union kvm_ioapic_redirect_entry *e;
 
 	e = &ioapic->redirtbl[RTC_GSI];
@@ -117,16 +118,17 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 		return;
 
 	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
-	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+	old_val = test_bit(vcpu->vcpu_id, dest_map->map);
 
 	if (new_val == old_val)
 		return;
 
 	if (new_val) {
-		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+		__set_bit(vcpu->vcpu_id, dest_map->map);
+		dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
 		ioapic->rtc_status.pending_eoi++;
 	} else {
-		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+		__clear_bit(vcpu->vcpu_id, dest_map->map);
 		ioapic->rtc_status.pending_eoi--;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 39b91127ef07..cd944435dfbd 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -23,8 +23,8 @@
 static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
 	[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
 	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
-	[2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
-	[3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+	[2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+	[3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
 	[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
 	[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a45d8580f91e..5cede40e2552 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -422,6 +422,7 @@ struct nested_vmx {
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
+	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 	/*
@@ -435,6 +436,8 @@ struct nested_vmx {
 	bool pi_pending;
 	u16 posted_intr_nv;
 
+	unsigned long *msr_bitmap;
+
 	struct hrtimer preemption_timer;
 	bool preemption_timer_expired;
 
@@ -924,7 +927,6 @@ static unsigned long *vmx_msr_bitmap_legacy;
 static unsigned long *vmx_msr_bitmap_longmode;
 static unsigned long *vmx_msr_bitmap_legacy_x2apic;
 static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_nested;
 static unsigned long *vmx_vmread_bitmap;
 static unsigned long *vmx_vmwrite_bitmap;
 
@@ -2198,6 +2200,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 			new.control) != old.control);
 }
 
+static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
+{
+	vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
+	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
@@ -2256,10 +2264,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Setup TSC multiplier */
 	if (kvm_has_tsc_control &&
-	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
-		vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
-		vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
-	}
+	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
+		decache_tsc_multiplier(vmx);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 	vmx->host_pkru = read_pkru();
@@ -2508,7 +2514,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 	unsigned long *msr_bitmap;
 
 	if (is_guest_mode(vcpu))
-		msr_bitmap = vmx_msr_bitmap_nested;
+		msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
 	else if (cpu_has_secondary_exec_ctrls() &&
 		 (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
 		  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
@@ -6363,13 +6369,6 @@ static __init int hardware_setup(void)
 	if (!vmx_msr_bitmap_longmode_x2apic)
 		goto out4;
 
-	if (nested) {
-		vmx_msr_bitmap_nested =
-			(unsigned long *)__get_free_page(GFP_KERNEL);
-		if (!vmx_msr_bitmap_nested)
-			goto out5;
-	}
-
 	vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_vmread_bitmap)
 		goto out6;
@@ -6392,8 +6391,6 @@ static __init int hardware_setup(void)
 
 	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
 	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-	if (nested)
-		memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
 
 	if (setup_vmcs_config(&vmcs_config) < 0) {
 		r = -EIO;
@@ -6529,9 +6526,6 @@ out8:
 out7:
 	free_page((unsigned long)vmx_vmread_bitmap);
 out6:
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
-out5:
 	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
 out4:
 	free_page((unsigned long)vmx_msr_bitmap_longmode);
@@ -6557,8 +6551,6 @@ static __exit void hardware_unsetup(void)
 	free_page((unsigned long)vmx_io_bitmap_a);
 	free_page((unsigned long)vmx_vmwrite_bitmap);
 	free_page((unsigned long)vmx_vmread_bitmap);
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
 
 	free_kvm_area();
 }
@@ -6995,16 +6987,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	if (cpu_has_vmx_msr_bitmap()) {
+		vmx->nested.msr_bitmap =
+				(unsigned long *)__get_free_page(GFP_KERNEL);
+		if (!vmx->nested.msr_bitmap)
+			goto out_msr_bitmap;
+	}
+
 	vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
 	if (!vmx->nested.cached_vmcs12)
-		return -ENOMEM;
+		goto out_cached_vmcs12;
 
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
-		if (!shadow_vmcs) {
-			kfree(vmx->nested.cached_vmcs12);
-			return -ENOMEM;
-		}
+		if (!shadow_vmcs)
+			goto out_shadow_vmcs;
 		/* mark vmcs as shadow */
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
@@ -7024,6 +7021,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
 	return 1;
+
+out_shadow_vmcs:
+	kfree(vmx->nested.cached_vmcs12);
+
+out_cached_vmcs12:
+	free_page((unsigned long)vmx->nested.msr_bitmap);
+
+out_msr_bitmap:
+	return -ENOMEM;
 }
 
 /*
@@ -7098,6 +7104,10 @@ static void free_nested(struct vcpu_vmx *vmx)
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	nested_release_vmcs12(vmx);
+	if (vmx->nested.msr_bitmap) {
+		free_page((unsigned long)vmx->nested.msr_bitmap);
+		vmx->nested.msr_bitmap = NULL;
+	}
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
 	kfree(vmx->nested.cached_vmcs12);
@@ -8419,6 +8429,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 {
 	u32 sec_exec_control;
 
+	/* Postpone execution until vmcs01 is the current VMCS. */
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+		return;
+	}
+
 	/*
 	 * There is not point to enable virtualize x2apic without enable
 	 * apicv
@@ -9472,8 +9488,10 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 {
 	int msr;
 	struct page *page;
-	unsigned long *msr_bitmap;
+	unsigned long *msr_bitmap_l1;
+	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
 
+	/* This shortcut is ok because we support only x2APIC MSRs so far. */
 	if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
 		return false;
 
@@ -9482,63 +9500,37 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 		return false;
 	}
-	msr_bitmap = (unsigned long *)kmap(page);
-	if (!msr_bitmap) {
+	msr_bitmap_l1 = (unsigned long *)kmap(page);
+	if (!msr_bitmap_l1) {
 		nested_release_page_clean(page);
 		WARN_ON(1);
 		return false;
 	}
 
+	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+
 	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
 		if (nested_cpu_has_apic_reg_virt(vmcs12))
 			for (msr = 0x800; msr <= 0x8ff; msr++)
 				nested_vmx_disable_intercept_for_msr(
-					msr_bitmap,
-					vmx_msr_bitmap_nested,
+					msr_bitmap_l1, msr_bitmap_l0,
 					msr, MSR_TYPE_R);
-		/* TPR is allowed */
-		nested_vmx_disable_intercept_for_msr(msr_bitmap,
-				vmx_msr_bitmap_nested,
+
+		nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
 				MSR_TYPE_R | MSR_TYPE_W);
+
 		if (nested_cpu_has_vid(vmcs12)) {
-			/* EOI and self-IPI are allowed */
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_EOI >> 4),
 				MSR_TYPE_W);
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
 				MSR_TYPE_W);
 		}
-	} else {
-		/*
-		 * Enable reading intercept of all the x2apic
-		 * MSRs. We should not rely on vmcs12 to do any
-		 * optimizations here, it may have been modified
-		 * by L1.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				msr,
-				MSR_TYPE_R);
-
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_EOI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
-				MSR_TYPE_W);
 	}
 	kunmap(page);
 	nested_release_page_clean(page);
@@ -9957,10 +9949,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
-		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
-		/* MSR_BITMAP will be set by following vmx_set_efer. */
-	} else
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+		; /* MSR_BITMAP will be set by following vmx_set_efer. */
+	else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
 	/*
@@ -10011,6 +10003,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 			vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
 	else
 		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+	if (kvm_has_tsc_control)
+		decache_tsc_multiplier(vmx);
 
 	if (enable_vpid) {
 		/*
@@ -10767,6 +10761,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	else
 		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
 			      PIN_BASED_VMX_PREEMPTION_TIMER);
+	if (kvm_has_tsc_control)
+		decache_tsc_multiplier(vmx);
+
+	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+		vmx_set_virtual_x2apic_mode(vcpu,
+				vcpu->arch.apic_base & X2APIC_ENABLE);
+	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
 	vmx->host_rsp = 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 19f9f9e05c2a..699f8726539a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2743,16 +2743,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 
-		if (kvm_lapic_hv_timer_in_use(vcpu) &&
-				kvm_x86_ops->set_hv_timer(vcpu,
-					kvm_get_lapic_tscdeadline_msr(vcpu)))
-			kvm_lapic_switch_to_sw_timer(vcpu);
 		if (check_tsc_unstable()) {
 			u64 offset = kvm_compute_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
 			kvm_x86_ops->write_tsc_offset(vcpu, offset);
 			vcpu->arch.tsc_catchup = 1;
 		}
+		if (kvm_lapic_hv_timer_in_use(vcpu) &&
+				kvm_x86_ops->set_hv_timer(vcpu,
+					kvm_get_lapic_tscdeadline_msr(vcpu)))
+			kvm_lapic_switch_to_sw_timer(vcpu);
 		/*
 		 * On a host with synchronized TSC, there is no need to update
 		 * kvmclock on vcpu->cpu migration
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 02de3d74d2c5..8a602a1e404a 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -35,6 +35,7 @@ ENDPROC(__sw_hweight32)
 
 ENTRY(__sw_hweight64)
 #ifdef CONFIG_X86_64
+	pushq   %rdi
 	pushq   %rdx
 
 	movq    %rdi, %rdx                      # w -> t
@@ -60,6 +61,7 @@ ENTRY(__sw_hweight64)
 	shrq    $56, %rax                       # w = w_tmp >> 56
 
 	popq    %rdx
+	popq    %rdi
 	ret
 #else /* CONFIG_X86_32 */
 	/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index f7dfeda83e5c..121f59c6ee54 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -19,7 +19,7 @@
 #include <asm/cpufeature.h>
 #include <asm/setup.h>
 
-#define debug_putstr(v) early_printk(v)
+#define debug_putstr(v) early_printk("%s", v)
 #define has_cpuflag(f) boot_cpu_has(f)
 #define get_boot_seed() kaslr_offset()
 #endif
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index ec21796ac5fd..4473cb4f8b90 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -3,15 +3,17 @@
  * included by both the compressed kernel and the regular kernel.
  */
 
-static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
 			   unsigned long addr, unsigned long end)
 {
 	addr &= PMD_MASK;
 	for (; addr < end; addr += PMD_SIZE) {
 		pmd_t *pmd = pmd_page + pmd_index(addr);
 
-		if (!pmd_present(*pmd))
-			set_pmd(pmd, __pmd(addr | pmd_flag));
+		if (pmd_present(*pmd))
+			continue;
+
+		set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag));
 	}
 }
 
@@ -30,13 +32,13 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 
 		if (pud_present(*pud)) {
 			pmd = pmd_offset(pud, 0);
-			ident_pmd_init(info->pmd_flag, pmd, addr, next);
+			ident_pmd_init(info, pmd, addr, next);
 			continue;
 		}
 		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
 		if (!pmd)
 			return -ENOMEM;
-		ident_pmd_init(info->pmd_flag, pmd, addr, next);
+		ident_pmd_init(info, pmd, addr, next);
 		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
 	}
 
@@ -44,14 +46,15 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 }
 
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
-			      unsigned long addr, unsigned long end)
+			      unsigned long pstart, unsigned long pend)
 {
+	unsigned long addr = pstart + info->offset;
+	unsigned long end = pend + info->offset;
 	unsigned long next;
 	int result;
-	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
 
 	for (; addr < end; addr = next) {
-		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+		pgd_t *pgd = pgd_page + pgd_index(addr);
 		pud_t *pud;
 
 		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 620928903be3..d28a2d741f9e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -122,8 +122,18 @@ __ref void *alloc_low_pages(unsigned int num)
 	return __va(pfn << PAGE_SHIFT);
 }
 
-/* need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE	(6 * PAGE_SIZE)
+/*
+ * By default need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS.
+ * With KASLR memory randomization, depending on the machine e820 memory
+ * and the PUD alignment. We may need twice more pages when KASLR memory
+ * randomization is enabled.
+ */
+#ifndef CONFIG_RANDOMIZE_MEMORY
+#define INIT_PGD_PAGE_COUNT      6
+#else
+#define INIT_PGD_PAGE_COUNT      12
+#endif
+#define INIT_PGT_BUF_SIZE	(INIT_PGD_PAGE_COUNT * PAGE_SIZE)
 RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
 void  __init early_alloc_pgt_buf(void)
 {
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 26dccd6c0df1..bda8d5eef04d 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -77,7 +77,7 @@ static inline unsigned long get_padding(struct kaslr_memory_region *region)
  */
 static inline bool kaslr_memory_enabled(void)
 {
-	return kaslr_enabled() && !config_enabled(CONFIG_KASAN);
+	return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
 }
 
 /* Initialize base and padding for each memory region randomized with KASLR */
@@ -97,7 +97,7 @@ void __init kernel_randomize_memory(void)
 	 * add padding if needed (especially for memory hotplug support).
 	 */
 	BUG_ON(kaslr_regions[0].base != &page_offset_base);
-	memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) +
+	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
 		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
 
 	/* Adapt phyiscal memory region size based on available memory */
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ecb1b69c1651..170cc4ff057b 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -927,9 +927,10 @@ int track_pfn_copy(struct vm_area_struct *vma)
 }
 
 /*
- * prot is passed in as a parameter for the new mapping. If the vma has a
- * linear pfn mapping for the entire range reserve the entire vma range with
- * single reserve_pfn_range call.
+ * prot is passed in as a parameter for the new mapping. If the vma has
+ * a linear pfn mapping for the entire range, or no vma is provided,
+ * reserve the entire pfn + size range with single reserve_pfn_range
+ * call.
  */
 int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 		    unsigned long pfn, unsigned long addr, unsigned long size)
@@ -938,11 +939,12 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 	enum page_cache_mode pcm;
 
 	/* reserve the whole chunk starting from paddr */
-	if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
+	if (!vma || (addr == vma->vm_start
+				&& size == (vma->vm_end - vma->vm_start))) {
 		int ret;
 
 		ret = reserve_pfn_range(paddr, size, prot, 0);
-		if (!ret)
+		if (ret == 0 && vma)
 			vma->vm_flags |= VM_PAT;
 		return ret;
 	}
@@ -997,7 +999,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	resource_size_t paddr;
 	unsigned long prot;
 
-	if (!(vma->vm_flags & VM_PAT))
+	if (vma && !(vma->vm_flags & VM_PAT))
 		return;
 
 	/* free the chunk starting from pfn or the whole chunk */
@@ -1011,7 +1013,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
-	vma->vm_flags &= ~VM_PAT;
+	if (vma)
+		vma->vm_flags &= ~VM_PAT;
 }
 
 /*
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 837ea36a837d..6d52b94f4bb9 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -553,15 +553,21 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
 
 /*
- * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
  *
- * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
- * entry BDF2.
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
  */
-static void pci_bdwep_bar(struct pci_dev *dev)
+static void pci_invalid_bar(struct pci_dev *dev)
 {
 	dev->non_compliant_bars = 1;
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c
index b814ca675131..7948be342ee9 100644
--- a/arch/x86/pci/vmd.c
+++ b/arch/x86/pci/vmd.c
@@ -41,6 +41,7 @@ static DEFINE_RAW_SPINLOCK(list_lock);
  * @node:	list item for parent traversal.
  * @rcu:	RCU callback item for freeing.
  * @irq:	back pointer to parent.
+ * @enabled:	true if driver enabled IRQ
  * @virq:	the virtual IRQ value provided to the requesting driver.
  *
  * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
@@ -50,6 +51,7 @@ struct vmd_irq {
 	struct list_head	node;
 	struct rcu_head		rcu;
 	struct vmd_irq_list	*irq;
+	bool			enabled;
 	unsigned int		virq;
 };
 
@@ -122,7 +124,9 @@ static void vmd_irq_enable(struct irq_data *data)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&list_lock, flags);
+	WARN_ON(vmdirq->enabled);
 	list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
+	vmdirq->enabled = true;
 	raw_spin_unlock_irqrestore(&list_lock, flags);
 
 	data->chip->irq_unmask(data);
@@ -136,8 +140,10 @@ static void vmd_irq_disable(struct irq_data *data)
 	data->chip->irq_mask(data);
 
 	raw_spin_lock_irqsave(&list_lock, flags);
-	list_del_rcu(&vmdirq->node);
-	INIT_LIST_HEAD_RCU(&vmdirq->node);
+	if (vmdirq->enabled) {
+		list_del_rcu(&vmdirq->node);
+		vmdirq->enabled = false;
+	}
 	raw_spin_unlock_irqrestore(&list_lock, flags);
 }
 
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 4480c06cade7..89d1146f5a6f 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -254,6 +254,7 @@ void __init efi_free_boot_services(void)
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		size_t rm_size;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)
@@ -263,6 +264,26 @@ void __init efi_free_boot_services(void)
 		if (md->attribute & EFI_MEMORY_RUNTIME)
 			continue;
 
+		/*
+		 * Nasty quirk: if all sub-1MB memory is used for boot
+		 * services, we can get here without having allocated the
+		 * real mode trampoline.  It's too late to hand boot services
+		 * memory back to the memblock allocator, so instead
+		 * try to manually allocate the trampoline if needed.
+		 *
+		 * I've seen this on a Dell XPS 13 9350 with firmware
+		 * 1.4.4 with SGX enabled booting Linux via Fedora 24's
+		 * grub2-efi on a hard disk.  (And no, I don't know why
+		 * this happened, but Linux should still try to boot rather
+		 * panicing early.)
+		 */
+		rm_size = real_mode_size_needed();
+		if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
+			set_real_mode_mem(start, rm_size);
+			start += rm_size;
+			size -= rm_size;
+		}
+
 		free_bootmem_late(start, size);
 	}
 
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index 66b2166ea4a1..23f2f3e41c7f 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -187,7 +187,8 @@ EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
 void uv_bios_init(void)
 {
 	uv_systab = NULL;
-	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) {
+	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
+	    !efi.uv_systab || efi_runtime_disabled()) {
 		pr_crit("UV: UVsystab: missing\n");
 		return;
 	}
@@ -199,12 +200,14 @@ void uv_bios_init(void)
 		return;
 	}
 
+	/* Starting with UV4 the UV systab size is variable */
 	if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) {
+		int size = uv_systab->size;
+
 		iounmap(uv_systab);
-		uv_systab = ioremap(efi.uv_systab, uv_systab->size);
+		uv_systab = ioremap(efi.uv_systab, size);
 		if (!uv_systab) {
-			pr_err("UV: UVsystab: ioremap(%d) failed!\n",
-				uv_systab->size);
+			pr_err("UV: UVsystab: ioremap(%d) failed!\n", size);
 			return;
 		}
 	}
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index f0b5f2d402af..9634557a5444 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -87,7 +87,7 @@ static int set_up_temporary_mappings(void)
 	struct x86_mapping_info info = {
 		.alloc_pgt_page	= alloc_pgt_page,
 		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
-		.kernel_mapping = true,
+		.offset		= __PAGE_OFFSET,
 	};
 	unsigned long mstart, mend;
 	pgd_t *pgd;
@@ -113,7 +113,7 @@ static int set_up_temporary_mappings(void)
 			return result;
 	}
 
-	temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET;
+	temp_level4_pgt = __pa(pgd);
 	return 0;
 }
 
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 705e3fffb4a1..5db706f14111 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -1,9 +1,11 @@
 #include <linux/io.h>
+#include <linux/slab.h>
 #include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/realmode.h>
+#include <asm/tlbflush.h>
 
 struct real_mode_header *real_mode_header;
 u32 *trampoline_cr4_features;
@@ -11,25 +13,37 @@ u32 *trampoline_cr4_features;
 /* Hold the pgd entry used on booting additional CPUs */
 pgd_t trampoline_pgd_entry;
 
+void __init set_real_mode_mem(phys_addr_t mem, size_t size)
+{
+	void *base = __va(mem);
+
+	real_mode_header = (struct real_mode_header *) base;
+	printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
+	       base, (unsigned long long)mem, size);
+}
+
 void __init reserve_real_mode(void)
 {
 	phys_addr_t mem;
-	unsigned char *base;
-	size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
+	size_t size = real_mode_size_needed();
+
+	if (!size)
+		return;
+
+	WARN_ON(slab_is_available());
 
 	/* Has to be under 1M so we can execute real-mode AP code. */
 	mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
-	if (!mem)
-		panic("Cannot allocate trampoline\n");
+	if (!mem) {
+		pr_info("No sub-1M memory is available for the trampoline\n");
+		return;
+	}
 
-	base = __va(mem);
 	memblock_reserve(mem, size);
-	real_mode_header = (struct real_mode_header *) base;
-	printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
-	       base, (unsigned long long)mem, size);
+	set_real_mode_mem(mem, size);
 }
 
-void __init setup_real_mode(void)
+static void __init setup_real_mode(void)
 {
 	u16 real_mode_seg;
 	const u32 *rel;
@@ -84,7 +98,7 @@ void __init setup_real_mode(void)
 
 	trampoline_header->start = (u64) secondary_startup_64;
 	trampoline_cr4_features = &trampoline_header->cr4;
-	*trampoline_cr4_features = __read_cr4();
+	*trampoline_cr4_features = mmu_cr4_features;
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
 	trampoline_pgd[0] = trampoline_pgd_entry.pgd;
@@ -100,7 +114,7 @@ void __init setup_real_mode(void)
  * need to mark it executable at do_pre_smp_initcalls() at least,
  * thus run it as a early_initcall().
  */
-static int __init set_real_mode_permissions(void)
+static void __init set_real_mode_permissions(void)
 {
 	unsigned char *base = (unsigned char *) real_mode_header;
 	size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
@@ -119,7 +133,16 @@ static int __init set_real_mode_permissions(void)
 	set_memory_nx((unsigned long) base, size >> PAGE_SHIFT);
 	set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT);
 	set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT);
+}
+
+static int __init init_real_mode(void)
+{
+	if (!real_mode_header)
+		panic("Real mode trampoline was not allocated");
+
+	setup_real_mode();
+	set_real_mode_permissions();
 
 	return 0;
 }
-early_initcall(set_real_mode_permissions);
+early_initcall(init_real_mode);
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index ebd4dd6ef73b..a7ef7b131e25 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -84,7 +84,10 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
 	case EAX:
 	case EIP:
 	case UESP:
+		break;
 	case ORIG_EAX:
+		/* Update the syscall number. */
+		UPT_SYSCALL_NR(&child->thread.regs.regs) = value;
 		break;
 	case FS:
 		if (value && (value & 3) != 3)
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index faab418876ce..0b5c184dd5b3 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -78,7 +78,11 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
 	case RSI:
 	case RDI:
 	case RBP:
+		break;
+
 	case ORIG_RAX:
+		/* Update the syscall number. */
+		UPT_SYSCALL_NR(&child->thread.regs.regs) = value;
 		break;
 
 	case FS:
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 8ffb089b19a5..b86ebb1a9a7f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -118,7 +118,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
author	Russell King <rmk+kernel@armlinux.org.uk>	2016-10-06 08:56:43 +0100
committer	Russell King <rmk+kernel@armlinux.org.uk>	2016-10-06 08:56:43 +0100
commit	301a36fa700f9add6e14f5a95c7573e01578343a (patch)
tree	6ff94ff3b08b838353b9127eb5f8055b3de6b25f /arch
parent	b828f960215f02e5d2c88bbd27565c694254a15a (diff)
parent	b60752f2b20c167859943e001727f0d4da419b23 (diff)