Merge remote-tracking branch 'remotes/fslc/4.9-2.3.x-imx' into toradex_4.9-2.3.x-imx-nextColibri-iMX7_LXDE-Image_2.8b6.184-20190401Colibri-iMX6_LXDE-Image_2.8b6.184-20190401Colibri-iMX6ULL_LXDE-Image_2.8b6.184-20190401Apalis-iMX6_LXDE-Image_2.8b6.184-20190401

153 files changed, 1212 insertions, 564 deletions

diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h
index 06377400dc09..469642801a68 100644
--- a/arch/alpha/include/asm/irq.h
+++ b/arch/alpha/include/asm/irq.h
@@ -55,15 +55,15 @@
 
 #elif defined(CONFIG_ALPHA_DP264) || \
       defined(CONFIG_ALPHA_LYNX)  || \
-      defined(CONFIG_ALPHA_SHARK) || \
-      defined(CONFIG_ALPHA_EIGER)
+      defined(CONFIG_ALPHA_SHARK)
 # define NR_IRQS	64
 
 #elif defined(CONFIG_ALPHA_TITAN)
 #define NR_IRQS		80
 
 #elif defined(CONFIG_ALPHA_RAWHIDE) || \
-	defined(CONFIG_ALPHA_TAKARA)
+      defined(CONFIG_ALPHA_TAKARA) || \
+      defined(CONFIG_ALPHA_EIGER)
 # define NR_IRQS	128
 
 #elif defined(CONFIG_ALPHA_WILDFIRE)
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 83e9eee57a55..f70663127aad 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -77,7 +77,7 @@ __load_new_mm_context(struct mm_struct *next_mm)
 /* Macro for exception fixup code to access integer registers.  */
 #define dpf_reg(r)							\
 	(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 :	\
-				 (r) <= 18 ? (r)+8 : (r)-10])
+				 (r) <= 18 ? (r)+10 : (r)-10])
 
 asmlinkage void
 do_page_fault(unsigned long address, unsigned long mmcsr,
diff --git a/arch/arc/configs/zebu_hs_defconfig b/arch/arc/configs/zebu_hs_defconfig
index 9f6166be7145..3346829b02bb 100644
--- a/arch/arc/configs/zebu_hs_defconfig
+++ b/arch/arc/configs/zebu_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/arc/configs/zebu_hs_smp_defconfig b/arch/arc/configs/zebu_hs_smp_defconfig
index 44e9693f4257..4471f9c37d7e 100644
--- a/arch/arc/configs/zebu_hs_smp_defconfig
+++ b/arch/arc/configs/zebu_hs_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 8da87feec59a..99e6d8948f4a 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -340,7 +340,7 @@ static inline __attribute__ ((const)) int __fls(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long word)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long word)
 {
 	if (!word)
 		return word;
@@ -400,9 +400,9 @@ static inline __attribute__ ((const)) int ffs(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 {
-	int n;
+	unsigned long n;
 
 	asm volatile(
 	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 4fd6272e6c01..c5816a224571 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -49,6 +49,17 @@
 
 #define ARCH_DMA_MINALIGN      L1_CACHE_BYTES
 
+/*
+ * Make sure slab-allocated buffers are 64-bit aligned when atomic64_t uses
+ * ARCv2 64-bit atomics (LLOCKD/SCONDD). This guarantess runtime 64-bit
+ * alignment for any atomic64_t embedded in buffer.
+ * Default ARCH_SLAB_MINALIGN is __alignof__(long long) which has a relaxed
+ * value of 4 (and not 8) in ARC ABI.
+ */
+#if defined(CONFIG_ARC_HAS_LL64) && defined(CONFIG_ARC_HAS_LLSC)
+#define ARCH_SLAB_MINALIGN	8
+#endif
+
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index c22b181e8206..2f39d9b3886e 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/page.h>
+#include <asm/unaligned.h>
 
 #ifdef CONFIG_ISA_ARCV2
 #include <asm/barrier.h>
@@ -94,6 +95,42 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 	return w;
 }
 
+/*
+ * {read,write}s{b,w,l}() repeatedly access the same IO address in
+ * native endianness in 8-, 16-, 32-bit chunks {into,from} memory,
+ * @count times
+ */
+#define __raw_readsx(t,f) \
+static inline void __raw_reads##f(const volatile void __iomem *addr,	\
+				  void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			*buf++ = x;					\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			put_unaligned(x, buf++);			\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_readsb __raw_readsb
+__raw_readsx(8, b)
+#define __raw_readsw __raw_readsw
+__raw_readsx(16, w)
+#define __raw_readsl __raw_readsl
+__raw_readsx(32, l)
+
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
 {
@@ -126,6 +163,35 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
+#define __raw_writesx(t,f)						\
+static inline void __raw_writes##f(volatile void __iomem *addr, 	\
+				   const void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	const u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			__raw_write##f(*buf++, addr);			\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			__raw_write##f(get_unaligned(buf++), addr);	\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_writesb __raw_writesb
+__raw_writesx(8, b)
+#define __raw_writesw __raw_writesw
+__raw_writesx(16, w)
+#define __raw_writesl __raw_writesl
+__raw_writesx(32, l)
+
 /*
  * MMIO can also get buffered/optimized in micro-arch, so barriers needed
  * Based on ARM model for the typical use case
@@ -141,10 +207,16 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 #define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
 #define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
 #define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+#define readsb(p,d,l)		({ __raw_readsb(p,d,l); __iormb(); })
+#define readsw(p,d,l)		({ __raw_readsw(p,d,l); __iormb(); })
+#define readsl(p,d,l)		({ __raw_readsl(p,d,l); __iormb(); })
 
 #define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
 #define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+#define writesb(p,d,l)		({ __iowmb(); __raw_writesb(p,d,l); })
+#define writesw(p,d,l)		({ __iowmb(); __raw_writesw(p,d,l); })
+#define writesl(p,d,l)		({ __iowmb(); __raw_writesl(p,d,l); })
 
 /*
  * Relaxed API for drivers which can handle barrier ordering themselves
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 9185541035cc..6958545390f0 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -103,7 +103,8 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
+	/* All jump instructions that are taken */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 0684fd2f42e8..f82393f89215 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -209,7 +209,7 @@ __arc_copy_from_user(void *to, const void __user *from, unsigned long n)
 		*/
 		  "=&r" (tmp), "+r" (to), "+r" (from)
 		:
-		: "lp_count", "lp_start", "lp_end", "memory");
+		: "lp_count", "memory");
 
 		return n;
 	}
@@ -438,7 +438,7 @@ __arc_copy_to_user(void __user *to, const void *from, unsigned long n)
 		 */
 		  "=&r" (tmp), "+r" (to), "+r" (from)
 		:
-		: "lp_count", "lp_start", "lp_end", "memory");
+		: "lp_count", "memory");
 
 		return n;
 	}
@@ -658,7 +658,7 @@ static inline unsigned long __arc_clear_user(void __user *to, unsigned long n)
 	"	.previous			\n"
 	: "+r"(d_char), "+r"(res)
 	: "i"(0)
-	: "lp_count", "lp_start", "lp_end", "memory");
+	: "lp_count", "memory");
 
 	return res;
 }
@@ -691,7 +691,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 	"	.previous			\n"
 	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
 	: "g"(-EFAULT), "r"(count)
-	: "lp_count", "lp_start", "lp_end", "memory");
+	: "lp_count", "memory");
 
 	return res;
 }
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 8b90d25a15cc..1f945d0f40da 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -17,6 +17,7 @@
 #include <asm/entry.h>
 #include <asm/arcregs.h>
 #include <asm/cache.h>
+#include <asm/irqflags.h>
 
 .macro CPU_EARLY_SETUP
 
@@ -47,6 +48,15 @@
 	sr	r5, [ARC_REG_DC_CTRL]
 
 1:
+
+#ifdef CONFIG_ISA_ARCV2
+	; Unaligned access is disabled at reset, so re-enable early as
+	; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access
+	; by default
+	lr	r5, [status32]
+	bset	r5, r5, STATUS_AD_BIT
+	kflag	r5
+#endif
 .endm
 
 	.section .init.text, "ax",@progbits
@@ -93,9 +103,9 @@ ENTRY(stext)
 #ifdef CONFIG_ARC_UBOOT_SUPPORT
 	; Uboot - kernel ABI
 	;    r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2
-	;    r1 = magic number (board identity, unused as of now
+	;    r1 = magic number (always zero as of now)
 	;    r2 = pointer to uboot provided cmdline or external DTB in mem
-	; These are handled later in setup_arch()
+	; These are handled later in handle_uboot_args()
 	st	r0, [@uboot_tag]
 	st	r2, [@uboot_arg]
 #endif
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 0385df77a697..9119bea503a7 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -381,43 +381,80 @@ void setup_processor(void)
 	arc_chk_core_config();
 }
 
-static inline int is_kernel(unsigned long addr)
+static inline bool uboot_arg_invalid(unsigned long addr)
 {
-	if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end)
-		return 1;
-	return 0;
+	/*
+	 * Check that it is a untranslated address (although MMU is not enabled
+	 * yet, it being a high address ensures this is not by fluke)
+	 */
+	if (addr < PAGE_OFFSET)
+		return true;
+
+	/* Check that address doesn't clobber resident kernel image */
+	return addr >= (unsigned long)_stext && addr <= (unsigned long)_end;
 }
 
-void __init setup_arch(char **cmdline_p)
+#define IGNORE_ARGS		"Ignore U-boot args: "
+
+/* uboot_tag values for U-boot - kernel ABI revision 0; see head.S */
+#define UBOOT_TAG_NONE		0
+#define UBOOT_TAG_CMDLINE	1
+#define UBOOT_TAG_DTB		2
+
+void __init handle_uboot_args(void)
 {
+	bool use_embedded_dtb = true;
+	bool append_cmdline = false;
+
 #ifdef CONFIG_ARC_UBOOT_SUPPORT
-	/* make sure that uboot passed pointer to cmdline/dtb is valid */
-	if (uboot_tag && is_kernel((unsigned long)uboot_arg))
-		panic("Invalid uboot arg\n");
+	/* check that we know this tag */
+	if (uboot_tag != UBOOT_TAG_NONE &&
+	    uboot_tag != UBOOT_TAG_CMDLINE &&
+	    uboot_tag != UBOOT_TAG_DTB) {
+		pr_warn(IGNORE_ARGS "invalid uboot tag: '%08x'\n", uboot_tag);
+		goto ignore_uboot_args;
+	}
+
+	if (uboot_tag != UBOOT_TAG_NONE &&
+            uboot_arg_invalid((unsigned long)uboot_arg)) {
+		pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg);
+		goto ignore_uboot_args;
+	}
+
+	/* see if U-boot passed an external Device Tree blob */
+	if (uboot_tag == UBOOT_TAG_DTB) {
+		machine_desc = setup_machine_fdt((void *)uboot_arg);
 
-	/* See if u-boot passed an external Device Tree blob */
-	machine_desc = setup_machine_fdt(uboot_arg);	/* uboot_tag == 2 */
-	if (!machine_desc)
+		/* external Device Tree blob is invalid - use embedded one */
+		use_embedded_dtb = !machine_desc;
+	}
+
+	if (uboot_tag == UBOOT_TAG_CMDLINE)
+		append_cmdline = true;
+
+ignore_uboot_args:
 #endif
-	{
-		/* No, so try the embedded one */
+
+	if (use_embedded_dtb) {
 		machine_desc = setup_machine_fdt(__dtb_start);
 		if (!machine_desc)
 			panic("Embedded DT invalid\n");
+	}
 
-		/*
-		 * If we are here, it is established that @uboot_arg didn't
-		 * point to DT blob. Instead if u-boot says it is cmdline,
-		 * append to embedded DT cmdline.
-		 * setup_machine_fdt() would have populated @boot_command_line
-		 */
-		if (uboot_tag == 1) {
-			/* Ensure a whitespace between the 2 cmdlines */
-			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
-			strlcat(boot_command_line, uboot_arg,
-				COMMAND_LINE_SIZE);
-		}
+	/*
+	 * NOTE: @boot_command_line is populated by setup_machine_fdt() so this
+	 * append processing can only happen after.
+	 */
+	if (append_cmdline) {
+		/* Ensure a whitespace between the 2 cmdlines */
+		strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
+		strlcat(boot_command_line, uboot_arg, COMMAND_LINE_SIZE);
 	}
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	handle_uboot_args();
 
 	/* Save unparsed command line copy for /proc/cmdline */
 	*cmdline_p = boot_command_line;
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index d61044dd8b58..ea14b0bf3116 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -25,15 +25,11 @@
 #endif
 
 #ifdef CONFIG_ARC_HAS_LL64
-# define PREFETCH_READ(RX)	prefetch    [RX, 56]
-# define PREFETCH_WRITE(RX)	prefetchw   [RX, 64]
 # define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
 # define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
 # define ZOLSHFT		5
 # define ZOLAND			0x1F
 #else
-# define PREFETCH_READ(RX)	prefetch    [RX, 28]
-# define PREFETCH_WRITE(RX)	prefetchw   [RX, 32]
 # define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
 # define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
 # define ZOLSHFT		4
@@ -41,8 +37,6 @@
 #endif
 
 ENTRY_CFI(memcpy)
-	prefetch [r1]		; Prefetch the read location
-	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
 ;;; if size is zero
 	jz.d	[blink]
@@ -72,8 +66,6 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy32_64bytes
 	;; LOOP START
 	LOADX (r6, r1)
-	PREFETCH_READ (r1)
-	PREFETCH_WRITE (r3)
 	LOADX (r8, r1)
 	LOADX (r10, r1)
 	LOADX (r4, r1)
@@ -117,9 +109,7 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy8bytes_1
 	;; LOOP START
 	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 24)
 	or	r7, r7, r5
@@ -162,9 +152,7 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy8bytes_2
 	;; LOOP START
 	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 16)
 	or	r7, r7, r5
@@ -204,9 +192,7 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy8bytes_3
 	;; LOOP START
 	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 8)
 	or	r7, r7, r5
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 62ad4bcb841a..f230bb7092fd 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -7,11 +7,39 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/cache.h>
 
-#undef PREALLOC_NOT_AVAIL
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR	reg, off
+	prealloc	[\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR	reg, off
+	prefetchw	[\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR
+.endm
+
+.macro PREFETCHW_INSTR
+.endm
+
+#endif
 
 ENTRY_CFI(memset)
-	prefetchw [r0]		; Prefetch the write location
+	PREFETCHW_INSTR	r0, 0	; Prefetch the first write location
 	mov.f	0, r2
 ;;; if size is zero
 	jz.d	[blink]
@@ -48,11 +76,8 @@ ENTRY_CFI(memset)
 
 	lpnz	@.Lset64bytes
 	;; LOOP START
-#ifdef PREALLOC_NOT_AVAIL
-	prefetchw [r3, 64]	;Prefetch the next write location
-#else
-	prealloc  [r3, 64]
-#endif
+	PREALLOC_INSTR	r3, 64	; alloc next line w/o fetching
+
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -85,7 +110,6 @@ ENTRY_CFI(memset)
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
-	prefetchw   [r3, 32]	;Prefetch the next write location
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 52af0ba2a41e..92eca4f39c1e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1467,6 +1467,7 @@ config NR_CPUS
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
 	depends on SMP
+	select GENERIC_IRQ_MIGRATION
 	help
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 78492a0bbbab..3c58ec707ea9 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -156,7 +156,7 @@
 
 	sound {
 		compatible = "simple-audio-card";
-		simple-audio-card,name = "DA850/OMAP-L138 EVM";
+		simple-audio-card,name = "DA850-OMAPL138 EVM";
 		simple-audio-card,widgets =
 			"Line", "Line In",
 			"Line", "Line Out";
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index 7b8ab21fed6c..920e64cdb673 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -26,7 +26,7 @@
 
 	sound {
 		compatible = "simple-audio-card";
-		simple-audio-card,name = "DA850/OMAP-L138 LCDK";
+		simple-audio-card,name = "DA850-OMAPL138 LCDK";
 		simple-audio-card,widgets =
 			"Line", "Line In",
 			"Line", "Line Out";
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 2a531beef4c7..51dbd8cb91cb 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -170,6 +170,9 @@
 			interrupt-controller;
 			#interrupt-cells = <3>;
 			interrupt-parent = <&gic>;
+			clock-names = "clkout8";
+			clocks = <&cmu CLK_FIN_PLL>;
+			#clock-cells = <1>;
 		};
 
 		mipi_phy: video-phy {
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index 5282d69e55bd..2d83cbf672b2 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -70,7 +70,7 @@
 	};
 
 	emmc_pwrseq: pwrseq {
-		pinctrl-0 = <&sd1_cd>;
+		pinctrl-0 = <&emmc_rstn>;
 		pinctrl-names = "default";
 		compatible = "mmc-pwrseq-emmc";
 		reset-gpios = <&gpk1 2 GPIO_ACTIVE_LOW>;
@@ -161,12 +161,6 @@
 	cpu0-supply = <&buck2_reg>;
 };
 
-/* RSTN signal for eMMC */
-&sd1_cd {
-	samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
-	samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
-};
-
 &pinctrl_1 {
 	gpio_power_key: power_key {
 		samsung,pins = "gpx1-3";
@@ -184,6 +178,11 @@
 		samsung,pins = "gpx3-7";
 		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
 	};
+
+	emmc_rstn: emmc-rstn {
+		samsung,pins = "gpk1-2";
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
 };
 
 &ehci {
diff --git a/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
new file mode 100644
index 000000000000..c8771c660550
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
@@ -0,0 +1,25 @@
+/*
+ * Device tree sources for Exynos5420 TMU sensor configuration
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ * Copyright (c) 2017 Krzysztof Kozlowski <krzk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <dt-bindings/thermal/thermal_exynos.h>
+
+#thermal-sensor-cells = <0>;
+samsung,tmu_gain = <8>;
+samsung,tmu_reference_voltage = <16>;
+samsung,tmu_noise_cancel_mode = <4>;
+samsung,tmu_efuse_value = <55>;
+samsung,tmu_min_efuse_value = <0>;
+samsung,tmu_max_efuse_value = <100>;
+samsung,tmu_first_point_trim = <25>;
+samsung,tmu_second_point_trim = <85>;
+samsung,tmu_default_temp_offset = <50>;
+samsung,tmu_cal_type = <TYPE_ONE_POINT_TRIMMING>;
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 00c4cfa54839..52f3d911f67f 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -694,7 +694,7 @@
 			interrupts = <0 65 0>;
 			clocks = <&clock CLK_TMU>;
 			clock-names = "tmu_apbif";
-			#include "exynos4412-tmu-sensor-conf.dtsi"
+			#include "exynos5420-tmu-sensor-conf.dtsi"
 		};
 
 		tmu_cpu1: tmu@10064000 {
@@ -703,7 +703,7 @@
 			interrupts = <0 183 0>;
 			clocks = <&clock CLK_TMU>;
 			clock-names = "tmu_apbif";
-			#include "exynos4412-tmu-sensor-conf.dtsi"
+			#include "exynos5420-tmu-sensor-conf.dtsi"
 		};
 
 		tmu_cpu2: tmu@10068000 {
@@ -712,7 +712,7 @@
 			interrupts = <0 184 0>;
 			clocks = <&clock CLK_TMU>, <&clock CLK_TMU>;
 			clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-			#include "exynos4412-tmu-sensor-conf.dtsi"
+			#include "exynos5420-tmu-sensor-conf.dtsi"
 		};
 
 		tmu_cpu3: tmu@1006c000 {
@@ -721,7 +721,7 @@
 			interrupts = <0 185 0>;
 			clocks = <&clock CLK_TMU>, <&clock CLK_TMU_GPU>;
 			clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-			#include "exynos4412-tmu-sensor-conf.dtsi"
+			#include "exynos5420-tmu-sensor-conf.dtsi"
 		};
 
 		tmu_gpu: tmu@100a0000 {
@@ -730,7 +730,7 @@
 			interrupts = <0 215 0>;
 			clocks = <&clock CLK_TMU_GPU>, <&clock CLK_TMU>;
 			clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-			#include "exynos4412-tmu-sensor-conf.dtsi"
+			#include "exynos5420-tmu-sensor-conf.dtsi"
 		};
 
 		sysmmu_g2dr: sysmmu@0x10A60000 {
diff --git a/arch/arm/boot/dts/imx7d-nitrogen7.dts b/arch/arm/boot/dts/imx7d-nitrogen7.dts
index 61b6c85eff69..f3efd247f682 100644
--- a/arch/arm/boot/dts/imx7d-nitrogen7.dts
+++ b/arch/arm/boot/dts/imx7d-nitrogen7.dts
@@ -117,13 +117,17 @@
 		compatible = "regulator-fixed";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
-		clocks = <&clks IMX7D_CLKO2_ROOT_DIV>;
-		clock-names = "slow";
 		regulator-name = "reg_wlan";
 		startup-delay-us = <70000>;
 		gpio = <&gpio4 21 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 	};
+
+	usdhc2_pwrseq: usdhc2_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&clks IMX7D_CLKO2_ROOT_DIV>;
+		clock-names = "ext_clock";
+	};
 };
 
 &adc1 {
@@ -430,6 +434,7 @@
 	bus-width = <4>;
 	non-removable;
 	vmmc-supply = <&reg_wlan>;
+	mmc-pwrseq = <&usdhc2_pwrseq>;
 	cap-power-off-card;
 	keep-power-in-suspend;
 	status = "okay";
diff --git a/arch/arm/boot/dts/kirkwood-dnskw.dtsi b/arch/arm/boot/dts/kirkwood-dnskw.dtsi
index d8fca9db46d0..dddbc0d03da5 100644
--- a/arch/arm/boot/dts/kirkwood-dnskw.dtsi
+++ b/arch/arm/boot/dts/kirkwood-dnskw.dtsi
@@ -35,8 +35,8 @@
 		compatible = "gpio-fan";
 		pinctrl-0 = <&pmx_fan_high_speed &pmx_fan_low_speed>;
 		pinctrl-names = "default";
-		gpios = <&gpio1 14 GPIO_ACTIVE_LOW
-			 &gpio1 13 GPIO_ACTIVE_LOW>;
+		gpios = <&gpio1 14 GPIO_ACTIVE_HIGH
+			 &gpio1 13 GPIO_ACTIVE_HIGH>;
 		gpio-fan,speed-map = <0    0
 				      3000 1
 				      6000 2>;
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index e262fa9ef334..876ed5f2922c 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -122,7 +122,7 @@
 };
 
 &mmc3 {
-	interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>;
+	interrupts-extended = <&intc 94 &omap3_pmx_core 0x136>;
 	pinctrl-0 = <&mmc3_pins &wl127x_gpio>;
 	pinctrl-names = "default";
 	vmmc-supply = <&wl12xx_vmmc>;
diff --git a/arch/arm/boot/dts/mmp2.dtsi b/arch/arm/boot/dts/mmp2.dtsi
index 766bbb8495b6..47e5b63339d1 100644
--- a/arch/arm/boot/dts/mmp2.dtsi
+++ b/arch/arm/boot/dts/mmp2.dtsi
@@ -220,12 +220,15 @@
 				status = "disabled";
 			};
 
-			twsi2: i2c@d4025000 {
+			twsi2: i2c@d4031000 {
 				compatible = "mrvl,mmp-twsi";
-				reg = <0xd4025000 0x1000>;
-				interrupts = <58>;
+				reg = <0xd4031000 0x1000>;
+				interrupt-parent = <&intcmux17>;
+				interrupts = <0>;
 				clocks = <&soc_clocks MMP2_CLK_TWSI1>;
 				resets = <&soc_clocks MMP2_CLK_TWSI1>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index d728ec963111..891ba75fd459 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -33,6 +33,7 @@
 		gpio = <&gpio2 16 GPIO_ACTIVE_HIGH>;  /* gpio line 48 */
 		enable-active-high;
 		regulator-boot-on;
+		startup-delay-us = <25000>;
 	};
 
 	vbat: fixedregulator-vbat {
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index e616f61f859d..7d727506096f 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -465,6 +465,17 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
+#ifdef CONFIG_CPU_SPECTRE
+	sub	\tmp, \limit, #1
+	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
+	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
+	subhss	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
+	csdb
+#endif
+	.endm
+
 	.macro	uaccess_disable, tmp, isb=1
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	/*
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index c55db1e22f0c..b9356dbfded0 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -106,6 +106,7 @@
 #define ARM_CPU_PART_SCORPION		0x510002d0
 
 extern unsigned int processor_id;
+struct proc_info_list *lookup_processor(u32 midr);
 
 #ifdef CONFIG_CPU_CP15
 #define read_cpuid(reg)							\
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index e53638c8ed8a..61e1d089ce1a 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -24,7 +24,6 @@
 #ifndef __ASSEMBLY__
 struct irqaction;
 struct pt_regs;
-extern void migrate_irqs(void);
 
 extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index f379f5f849a9..1bfcc3bcfc6d 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -23,7 +23,7 @@ struct mm_struct;
 /*
  * Don't change this structure - ASM code relies on it.
  */
-extern struct processor {
+struct processor {
 	/* MISC
 	 * get data abort address/flags
 	 */
@@ -79,9 +79,13 @@ extern struct processor {
 	unsigned int suspend_size;
 	void (*do_suspend)(void *);
 	void (*do_resume)(void *);
-} processor;
+};
 
 #ifndef MULTI_CPU
+static inline void init_proc_vtable(const struct processor *p)
+{
+}
+
 extern void cpu_proc_init(void);
 extern void cpu_proc_fin(void);
 extern int cpu_do_idle(void);
@@ -98,17 +102,50 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(void *);
 extern void cpu_do_resume(void *);
 #else
-#define cpu_proc_init			processor._proc_init
-#define cpu_proc_fin			processor._proc_fin
-#define cpu_reset			processor.reset
-#define cpu_do_idle			processor._do_idle
-#define cpu_dcache_clean_area		processor.dcache_clean_area
-#define cpu_set_pte_ext			processor.set_pte_ext
-#define cpu_do_switch_mm		processor.switch_mm
 
-/* These three are private to arch/arm/kernel/suspend.c */
-#define cpu_do_suspend			processor.do_suspend
-#define cpu_do_resume			processor.do_resume
+extern struct processor processor;
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+#include <linux/smp.h>
+/*
+ * This can't be a per-cpu variable because we need to access it before
+ * per-cpu has been initialised.  We have a couple of functions that are
+ * called in a pre-emptible context, and so can't use smp_processor_id()
+ * there, hence PROC_TABLE().  We insist in init_proc_vtable() that the
+ * function pointers for these are identical across all CPUs.
+ */
+extern struct processor *cpu_vtable[];
+#define PROC_VTABLE(f)			cpu_vtable[smp_processor_id()]->f
+#define PROC_TABLE(f)			cpu_vtable[0]->f
+static inline void init_proc_vtable(const struct processor *p)
+{
+	unsigned int cpu = smp_processor_id();
+	*cpu_vtable[cpu] = *p;
+	WARN_ON_ONCE(cpu_vtable[cpu]->dcache_clean_area !=
+		     cpu_vtable[0]->dcache_clean_area);
+	WARN_ON_ONCE(cpu_vtable[cpu]->set_pte_ext !=
+		     cpu_vtable[0]->set_pte_ext);
+}
+#else
+#define PROC_VTABLE(f)			processor.f
+#define PROC_TABLE(f)			processor.f
+static inline void init_proc_vtable(const struct processor *p)
+{
+	processor = *p;
+}
+#endif
+
+#define cpu_proc_init			PROC_VTABLE(_proc_init)
+#define cpu_check_bugs			PROC_VTABLE(check_bugs)
+#define cpu_proc_fin			PROC_VTABLE(_proc_fin)
+#define cpu_reset			PROC_VTABLE(reset)
+#define cpu_do_idle			PROC_VTABLE(_do_idle)
+#define cpu_dcache_clean_area		PROC_TABLE(dcache_clean_area)
+#define cpu_set_pte_ext			PROC_TABLE(set_pte_ext)
+#define cpu_do_switch_mm		PROC_VTABLE(switch_mm)
+
+/* These two are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend			PROC_VTABLE(do_suspend)
+#define cpu_do_resume			PROC_VTABLE(do_resume)
 #endif
 
 extern void cpu_resume(void);
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 57d2ad9c75ca..df8420672c7e 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -124,8 +124,8 @@ extern void vfp_flush_hwstate(struct thread_info *);
 struct user_vfp;
 struct user_vfp_exc;
 
-extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
-					   struct user_vfp_exc __user *);
+extern int vfp_preserve_user_clear_hwstate(struct user_vfp *,
+					   struct user_vfp_exc *);
 extern int vfp_restore_user_hwstate(struct user_vfp *,
 				    struct user_vfp_exc *);
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7b17460127fd..0f6c6b873bc5 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -99,6 +99,14 @@ extern int __put_user_bad(void);
 static inline void set_fs(mm_segment_t fs)
 {
 	current_thread_info()->addr_limit = fs;
+
+	/*
+	 * Prevent a mispredicted conditional call to set_fs from forwarding
+	 * the wrong address limit to access_ok under speculation.
+	 */
+	dsb(nsh);
+	isb();
+
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
 }
 
@@ -122,6 +130,32 @@ static inline void set_fs(mm_segment_t fs)
 	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
 /*
+ * Sanitise a uaccess pointer such that it becomes NULL if addr+size
+ * is above the current addr_limit.
+ */
+#define uaccess_mask_range_ptr(ptr, size)			\
+	((__typeof__(ptr))__uaccess_mask_range_ptr(ptr, size))
+static inline void __user *__uaccess_mask_range_ptr(const void __user *ptr,
+						    size_t size)
+{
+	void __user *safe_ptr = (void __user *)ptr;
+	unsigned long tmp;
+
+	asm volatile(
+	"	sub	%1, %3, #1\n"
+	"	subs	%1, %1, %0\n"
+	"	addhs	%1, %1, #1\n"
+	"	subhss	%1, %1, %2\n"
+	"	movlo	%0, #0\n"
+	: "+r" (safe_ptr), "=&r" (tmp)
+	: "r" (size), "r" (current_thread_info()->addr_limit)
+	: "cc");
+
+	csdb();
+	return safe_ptr;
+}
+
+/*
  * Single-value transfer routines.  They automatically use the right
  * size if we just have the right pointer type.  Note that the functions
  * which read from user space (*get_*) need to take care not to leak
@@ -392,6 +426,14 @@ do {									\
 	__pu_err;							\
 })
 
+#ifdef CONFIG_CPU_SPECTRE
+/*
+ * When mitigating Spectre variant 1.1, all accessors need to include
+ * verification of the address space.
+ */
+#define __put_user(x, ptr) put_user(x, ptr)
+
+#else
 #define __put_user(x, ptr)						\
 ({									\
 	long __pu_err = 0;						\
@@ -399,12 +441,6 @@ do {									\
 	__pu_err;							\
 })
 
-#define __put_user_error(x, ptr, err)					\
-({									\
-	__put_user_switch((x), (ptr), (err), __put_user_nocheck);	\
-	(void) 0;							\
-})
-
 #define __put_user_nocheck(x, __pu_ptr, __err, __size)			\
 	do {								\
 		unsigned long __pu_addr = (unsigned long)__pu_ptr;	\
@@ -484,6 +520,7 @@ do {									\
 	: "r" (x), "i" (-EFAULT)				\
 	: "cc")
 
+#endif /* !CONFIG_CPU_SPECTRE */
 
 #ifdef CONFIG_MMU
 extern unsigned long __must_check
diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c
index 7be511310191..d41d3598e5e5 100644
--- a/arch/arm/kernel/bugs.c
+++ b/arch/arm/kernel/bugs.c
@@ -6,8 +6,8 @@
 void check_other_bugs(void)
 {
 #ifdef MULTI_CPU
-	if (processor.check_bugs)
-		processor.check_bugs();
+	if (cpu_check_bugs)
+		cpu_check_bugs();
 #endif
 }
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 56be67ecf0fa..d69adfb3d79e 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -32,6 +32,7 @@
  * features make this path too inefficient.
  */
 ret_fast_syscall:
+__ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
@@ -57,6 +58,7 @@ fast_work_pending:
  * r0 first to avoid needing to save registers around each C function call.
  */
 ret_fast_syscall:
+__ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
@@ -223,7 +225,7 @@ local_restart:
 	tst	r10, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
 	bne	__sys_trace
 
-	invoke_syscall tbl, scno, r10, ret_fast_syscall
+	invoke_syscall tbl, scno, r10, __ret_fast_syscall
 
 	add	r1, sp, #S_OFF
 2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 8733012d231f..7e662bdd5cb3 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -122,6 +122,9 @@ __mmap_switched_data:
 	.long	init_thread_union + THREAD_START_SP @ sp
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
+	__FINIT
+	.text
+
 /*
  * This provides a C-API version of __lookup_processor_type
  */
@@ -133,9 +136,6 @@ ENTRY(lookup_processor_type)
 	ldmfd	sp!, {r4 - r6, r9, pc}
 ENDPROC(lookup_processor_type)
 
-	__FINIT
-	.text
-
 /*
  * Read processor ID register (CP#15, CR0), and look up in the linker-built
  * supported processor list.  Note that we can't use the absolute addresses
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ece04a457486..5b07c7a31c31 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -31,7 +31,6 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
-#include <linux/ratelimit.h>
 #include <linux/errno.h>
 #include <linux/list.h>
 #include <linux/kallsyms.h>
@@ -119,64 +118,3 @@ int __init arch_probe_nr_irqs(void)
 	return nr_irqs;
 }
 #endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-static bool migrate_one_irq(struct irq_desc *desc)
-{
-	struct irq_data *d = irq_desc_get_irq_data(desc);
-	const struct cpumask *affinity = irq_data_get_affinity_mask(d);
-	struct irq_chip *c;
-	bool ret = false;
-
-	/*
-	 * If this is a per-CPU interrupt, or the affinity does not
-	 * include this CPU, then we have nothing to do.
-	 */
-	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
-		return false;
-
-	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
-		affinity = cpu_online_mask;
-		ret = true;
-	}
-
-	c = irq_data_get_irq_chip(d);
-	if (!c->irq_set_affinity)
-		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
-		cpumask_copy(irq_data_get_affinity_mask(d), affinity);
-
-	return ret;
-}
-
-/*
- * The current CPU has been marked offline.  Migrate IRQs off this CPU.
- * If the affinity settings do not allow other CPUs, force them onto any
- * available CPU.
- *
- * Note: we must iterate over all IRQs, whether they have an attached
- * action structure or not, as we need to get chained interrupts too.
- */
-void migrate_irqs(void)
-{
-	unsigned int i;
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	for_each_irq_desc(i, desc) {
-		bool affinity_broken;
-
-		raw_spin_lock(&desc->lock);
-		affinity_broken = migrate_one_irq(desc);
-		raw_spin_unlock(&desc->lock);
-
-		if (affinity_broken)
-			pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
-				i, smp_processor_id());
-	}
-
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index f4e54503afa9..4764742db7b0 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -115,6 +115,11 @@ EXPORT_SYMBOL(elf_hwcap2);
 
 #ifdef MULTI_CPU
 struct processor processor __ro_after_init;
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+struct processor *cpu_vtable[NR_CPUS] = {
+	[0] = &processor,
+};
+#endif
 #endif
 #ifdef MULTI_TLB
 struct cpu_tlb_fns cpu_tlb __ro_after_init;
@@ -667,28 +672,33 @@ static void __init smp_build_mpidr_hash(void)
 }
 #endif
 
-static void __init setup_processor(void)
+/*
+ * locate processor in the list of supported processor types.  The linker
+ * builds this table for us from the entries in arch/arm/mm/proc-*.S
+ */
+struct proc_info_list *lookup_processor(u32 midr)
 {
-	struct proc_info_list *list;
+	struct proc_info_list *list = lookup_processor_type(midr);
 
-	/*
-	 * locate processor in the list of supported processor
-	 * types.  The linker builds this table for us from the
-	 * entries in arch/arm/mm/proc-*.S
-	 */
-	list = lookup_processor_type(read_cpuid_id());
 	if (!list) {
-		pr_err("CPU configuration botched (ID %08x), unable to continue.\n",
-		       read_cpuid_id());
-		while (1);
+		pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n",
+		       smp_processor_id(), midr);
+		while (1)
+		/* can't use cpu_relax() here as it may require MMU setup */;
 	}
 
+	return list;
+}
+
+static void __init setup_processor(void)
+{
+	unsigned int midr = read_cpuid_id();
+	struct proc_info_list *list = lookup_processor(midr);
+
 	cpu_name = list->cpu_name;
 	__cpu_architecture = __get_cpu_architecture();
 
-#ifdef MULTI_CPU
-	processor = *list->proc;
-#endif
+	init_proc_vtable(list->proc);
 #ifdef MULTI_TLB
 	cpu_tlb = *list->tlb;
 #endif
@@ -700,7 +710,7 @@ static void __init setup_processor(void)
 #endif
 
 	pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-		cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
+		list->cpu_name, midr, midr & 15,
 		proc_arch[cpu_architecture()], get_cr());
 
 	snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 6bee5c9b1133..0a066f03b5ec 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -94,17 +94,18 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)
 
 static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 {
-	const unsigned long magic = VFP_MAGIC;
-	const unsigned long size = VFP_STORAGE_SIZE;
+	struct vfp_sigframe kframe;
 	int err = 0;
 
-	__put_user_error(magic, &frame->magic, err);
-	__put_user_error(size, &frame->size, err);
+	memset(&kframe, 0, sizeof(kframe));
+	kframe.magic = VFP_MAGIC;
+	kframe.size = VFP_STORAGE_SIZE;
 
+	err = vfp_preserve_user_clear_hwstate(&kframe.ufp, &kframe.ufp_exc);
 	if (err)
-		return -EFAULT;
+		return err;
 
-	return vfp_preserve_user_clear_hwstate(&frame->ufp, &frame->ufp_exc);
+	return __copy_to_user(frame, &kframe, sizeof(kframe));
 }
 
 static int restore_vfp_context(struct vfp_sigframe __user *auxp)
@@ -256,30 +257,35 @@ static int
 setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 {
 	struct aux_sigframe __user *aux;
+	struct sigcontext context;
 	int err = 0;
 
-	__put_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
-	__put_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err);
-	__put_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err);
-	__put_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err);
-	__put_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err);
-	__put_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err);
-	__put_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err);
-	__put_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err);
-	__put_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err);
-	__put_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err);
-	__put_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err);
-	__put_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err);
-	__put_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err);
-	__put_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err);
-	__put_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err);
-	__put_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__put_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err);
-
-	__put_user_error(current->thread.trap_no, &sf->uc.uc_mcontext.trap_no, err);
-	__put_user_error(current->thread.error_code, &sf->uc.uc_mcontext.error_code, err);
-	__put_user_error(current->thread.address, &sf->uc.uc_mcontext.fault_address, err);
-	__put_user_error(set->sig[0], &sf->uc.uc_mcontext.oldmask, err);
+	context = (struct sigcontext) {
+		.arm_r0        = regs->ARM_r0,
+		.arm_r1        = regs->ARM_r1,
+		.arm_r2        = regs->ARM_r2,
+		.arm_r3        = regs->ARM_r3,
+		.arm_r4        = regs->ARM_r4,
+		.arm_r5        = regs->ARM_r5,
+		.arm_r6        = regs->ARM_r6,
+		.arm_r7        = regs->ARM_r7,
+		.arm_r8        = regs->ARM_r8,
+		.arm_r9        = regs->ARM_r9,
+		.arm_r10       = regs->ARM_r10,
+		.arm_fp        = regs->ARM_fp,
+		.arm_ip        = regs->ARM_ip,
+		.arm_sp        = regs->ARM_sp,
+		.arm_lr        = regs->ARM_lr,
+		.arm_pc        = regs->ARM_pc,
+		.arm_cpsr      = regs->ARM_cpsr,
+
+		.trap_no       = current->thread.trap_no,
+		.error_code    = current->thread.error_code,
+		.fault_address = current->thread.address,
+		.oldmask       = set->sig[0],
+	};
+
+	err |= __copy_to_user(&sf->uc.uc_mcontext, &context, sizeof(context));
 
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
@@ -296,7 +302,7 @@ setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 	if (err == 0)
 		err |= preserve_vfp_context(&aux->vfp);
 #endif
-	__put_user_error(0, &aux->end_magic, err);
+	err |= __put_user(0, &aux->end_magic);
 
 	return err;
 }
@@ -428,7 +434,7 @@ setup_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 	/*
 	 * Set uc.uc_flags to a value which sc.trap_no would never have.
 	 */
-	__put_user_error(0x5ac3c35a, &frame->uc.uc_flags, err);
+	err = __put_user(0x5ac3c35a, &frame->uc.uc_flags);
 
 	err |= setup_sigframe(frame, regs, set);
 	if (err == 0)
@@ -448,8 +454,8 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 
 	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
 
-	__put_user_error(0, &frame->sig.uc.uc_flags, err);
-	__put_user_error(NULL, &frame->sig.uc.uc_link, err);
+	err |= __put_user(0, &frame->sig.uc.uc_flags);
+	err |= __put_user(NULL, &frame->sig.uc.uc_link);
 
 	err |= __save_altstack(&frame->sig.uc.uc_stack, regs->ARM_sp);
 	err |= setup_sigframe(&frame->sig, regs, set);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index d2ce37da87d8..bc83ec7ed53f 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -27,6 +27,7 @@
 #include <linux/completion.h>
 #include <linux/cpufreq.h>
 #include <linux/irq_work.h>
+#include <linux/slab.h>
 
 #include <linux/atomic.h>
 #include <asm/bugs.h>
@@ -40,6 +41,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/procinfo.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -100,6 +102,30 @@ static unsigned long get_arch_pgd(pgd_t *pgd)
 #endif
 }
 
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+static int secondary_biglittle_prepare(unsigned int cpu)
+{
+	if (!cpu_vtable[cpu])
+		cpu_vtable[cpu] = kzalloc(sizeof(*cpu_vtable[cpu]), GFP_KERNEL);
+
+	return cpu_vtable[cpu] ? 0 : -ENOMEM;
+}
+
+static void secondary_biglittle_init(void)
+{
+	init_proc_vtable(lookup_processor(read_cpuid_id())->proc);
+}
+#else
+static int secondary_biglittle_prepare(unsigned int cpu)
+{
+	return 0;
+}
+
+static void secondary_biglittle_init(void)
+{
+}
+#endif
+
 int __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@@ -107,6 +133,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	if (!smp_ops.smp_boot_secondary)
 		return -ENOSYS;
 
+	ret = secondary_biglittle_prepare(cpu);
+	if (ret)
+		return ret;
+
 	/*
 	 * We need to tell the secondary core where to find
 	 * its stack and the page tables.
@@ -223,7 +253,7 @@ int __cpu_disable(void)
 	/*
 	 * OK - migrate IRQs away from this CPU
 	 */
-	migrate_irqs();
+	irq_migrate_all_off_this_cpu();
 
 	/*
 	 * Flush user cache and TLB mappings, and then remove this CPU
@@ -358,6 +388,8 @@ asmlinkage void secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu;
 
+	secondary_biglittle_init();
+
 	/*
 	 * The identity mapping is uncached (strongly ordered), so
 	 * switch away from it before attempting any exclusive accesses.
@@ -690,6 +722,21 @@ void smp_send_stop(void)
 		pr_warn("SMP: failed to stop secondary CPUs\n");
 }
 
+/* In case panic() and panic() called at the same time on CPU1 and CPU2,
+ * and CPU 1 calls panic_smp_self_stop() before crash_smp_send_stop()
+ * CPU1 can't receive the ipi irqs from CPU2, CPU1 will be always online,
+ * kdump fails. So split out the panic_smp_self_stop() and add
+ * set_cpu_online(smp_processor_id(), false).
+ */
+void panic_smp_self_stop(void)
+{
+	pr_debug("CPU %u will stop doing anything useful since another CPU has paniced\n",
+	         smp_processor_id());
+	set_cpu_online(smp_processor_id(), false);
+	while (1)
+		cpu_relax();
+}
+
 /*
  * not supported here
  */
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 640748e27035..d844c5c9364b 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -276,6 +276,7 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
 				    int maxevents, int timeout)
 {
 	struct epoll_event *kbuf;
+	struct oabi_epoll_event e;
 	mm_segment_t fs;
 	long ret, err, i;
 
@@ -294,8 +295,11 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
 	set_fs(fs);
 	err = 0;
 	for (i = 0; i < ret; i++) {
-		__put_user_error(kbuf[i].events, &events->events, err);
-		__put_user_error(kbuf[i].data,   &events->data,   err);
+		e.events = kbuf[i].events;
+		e.data = kbuf[i].data;
+		err = __copy_to_user(events, &e, sizeof(e));
+		if (err)
+			break;
 		events++;
 	}
 	kfree(kbuf);
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index dac7ceb1a677..08443a15e6be 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -117,6 +117,12 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
 	}
 
+	/*
+	 * The MMIO instruction is emulated and should not be re-executed
+	 * in the guest.
+	 */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 0;
 }
 
@@ -144,11 +150,6 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 	vcpu->arch.mmio_decode.sign_extend = sign_extend;
 	vcpu->arch.mmio_decode.rt = rt;
 
-	/*
-	 * The MMIO instruction is emulated and should not be re-executed
-	 * in the guest.
-	 */
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 	return 0;
 }
 
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index a826df3d3814..6709a8d33963 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -93,11 +93,7 @@ ENTRY(arm_copy_from_user)
 #ifdef CONFIG_CPU_SPECTRE
 	get_thread_info r3
 	ldr	r3, [r3, #TI_ADDR_LIMIT]
-	adds	ip, r1, r2	@ ip=addr+size
-	sub	r3, r3, #1	@ addr_limit - 1
-	cmpcc	ip, r3		@ if (addr+size > addr_limit - 1)
-	movcs	r1, #0		@ addr = NULL
-	csdb
+	uaccess_mask_range_ptr r1, r2, r3, ip
 #endif
 
 #include "copy_template.S"
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index caf5019d8161..970abe521197 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -94,6 +94,11 @@
 
 ENTRY(__copy_to_user_std)
 WEAK(arm_copy_to_user)
+#ifdef CONFIG_CPU_SPECTRE
+	get_thread_info r3
+	ldr	r3, [r3, #TI_ADDR_LIMIT]
+	uaccess_mask_range_ptr r0, r2, r3, ip
+#endif
 
 #include "copy_template.S"
 
@@ -108,4 +113,3 @@ ENDPROC(__copy_to_user_std)
 	rsb	r0, r0, r2
 	copy_abort_end
 	.popsection
-
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 6bd1089b07e0..f598d792bace 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -152,7 +152,8 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 		n = __copy_to_user_std(to, from, n);
 		uaccess_restore(ua_flags);
 	} else {
-		n = __copy_to_user_memcpy(to, from, n);
+		n = __copy_to_user_memcpy(uaccess_mask_range_ptr(to, n),
+					  from, n);
 	}
 	return n;
 }
diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c
index 318394ed5c7a..5e11ad3164e0 100644
--- a/arch/arm/mach-cns3xxx/pcie.c
+++ b/arch/arm/mach-cns3xxx/pcie.c
@@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus,
 	} else /* remote PCI bus */
 		base = cnspci->cfg1_regs + ((busno & 0xf) << 20);
 
-	return base + (where & 0xffc) + (devfn << 12);
+	return base + where + (devfn << 12);
 }
 
 static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
diff --git a/arch/arm/mach-imx/cpuidle-imx6sx.c b/arch/arm/mach-imx/cpuidle-imx6sx.c
index b16bee20fa14..534e47ff037b 100644
--- a/arch/arm/mach-imx/cpuidle-imx6sx.c
+++ b/arch/arm/mach-imx/cpuidle-imx6sx.c
@@ -233,6 +233,15 @@ int __init imx6sx_cpuidle_init(void)
 #endif
 
 	imx6_set_int_mem_clk_lpm(true);
+	imx6_enable_rbc(false);
+	/*
+	 * set ARM power up/down timing to the fastest,
+	 * sw2iso and sw can be set to one 32K cycle = 31us
+	 * except for power up sw2iso which need to be
+	 * larger than LDO ramp up time.
+	 */
+	imx_gpc_set_arm_power_up_timing(0xf, 1);
+	imx_gpc_set_arm_power_down_timing(1, 1);
 
 	if (imx_get_soc_revision() >= IMX_CHIP_REVISION_1_2) {
 		/*
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index ed9a01484030..a52fe871adbc 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -394,7 +394,11 @@ static int __ref impd1_probe(struct lm_device *dev)
 					      sizeof(*lookup) + 3 * sizeof(struct gpiod_lookup),
 					      GFP_KERNEL);
 			chipname = devm_kstrdup(&dev->dev, devname, GFP_KERNEL);
-			mmciname = kasprintf(GFP_KERNEL, "lm%x:00700", dev->id);
+			mmciname = devm_kasprintf(&dev->dev, GFP_KERNEL,
+						  "lm%x:00700", dev->id);
+			if (!lookup || !chipname || !mmciname)
+				return -ENOMEM;
+
 			lookup->dev_id = mmciname;
 			/*
 			 * Offsets on GPIO block 1:
diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c
index c1cd80ecc219..a904244264ce 100644
--- a/arch/arm/mach-iop32x/n2100.c
+++ b/arch/arm/mach-iop32x/n2100.c
@@ -75,8 +75,7 @@ void __init n2100_map_io(void)
 /*
  * N2100 PCI.
  */
-static int __init
-n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq;
 
diff --git a/arch/arm/mach-mmp/cputype.h b/arch/arm/mach-mmp/cputype.h
index 8a3b56dfd35d..8f94addd9bce 100644
--- a/arch/arm/mach-mmp/cputype.h
+++ b/arch/arm/mach-mmp/cputype.h
@@ -43,10 +43,12 @@ static inline int cpu_is_pxa910(void)
 #define cpu_is_pxa910()	(0)
 #endif
 
-#ifdef CONFIG_CPU_MMP2
+#if defined(CONFIG_CPU_MMP2) || defined(CONFIG_MACH_MMP2_DT)
 static inline int cpu_is_mmp2(void)
 {
-	return (((read_cpuid_id() >> 8) & 0xff) == 0x58);
+	return (((read_cpuid_id() >> 8) & 0xff) == 0x58) &&
+		(((mmp_chip_id & 0xfff) == 0x410) ||
+		 ((mmp_chip_id & 0xfff) == 0x610));
 }
 #else
 #define cpu_is_mmp2()	(0)
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 6613a6ff5dbc..c4b634c54fbd 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -511,6 +511,9 @@ static void modem_pm(struct uart_port *port, unsigned int state, unsigned old)
 {
 	struct modem_private_data *priv = port->private_data;
 
+	if (!priv)
+		return;
+
 	if (IS_ERR(priv->regulator))
 		return;
 
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 70b3eaf085e4..5ca7e29ad851 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -115,6 +115,7 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
 	u32 enable_mask, enable_shift;
 	u32 pipd_mask, pipd_shift;
 	u32 reg;
+	int ret;
 
 	if (dsi_id == 0) {
 		enable_mask = OMAP4_DSI1_LANEENABLE_MASK;
@@ -130,7 +131,11 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
 		return -ENODEV;
 	}
 
-	regmap_read(omap4_dsi_mux_syscon, OMAP4_DSIPHY_SYSCON_OFFSET, &reg);
+	ret = regmap_read(omap4_dsi_mux_syscon,
+					  OMAP4_DSIPHY_SYSCON_OFFSET,
+					  &reg);
+	if (ret)
+		return ret;
 
 	reg &= ~enable_mask;
 	reg &= ~pipd_mask;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index b5c1714ebfdd..bfc74954540c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2551,7 +2551,7 @@ static int __init _init(struct omap_hwmod *oh, void *data)
  * a stub; implementing this properly requires iclk autoidle usecounting in
  * the clock code.   No return value.
  */
-static void __init _setup_iclk_autoidle(struct omap_hwmod *oh)
+static void _setup_iclk_autoidle(struct omap_hwmod *oh)
 {
 	struct omap_hwmod_ocp_if *os;
 	struct list_head *p;
@@ -2586,7 +2586,7 @@ static void __init _setup_iclk_autoidle(struct omap_hwmod *oh)
  * reset.  Returns 0 upon success or a negative error code upon
  * failure.
  */
-static int __init _setup_reset(struct omap_hwmod *oh)
+static int _setup_reset(struct omap_hwmod *oh)
 {
 	int r;
 
@@ -2647,7 +2647,7 @@ static int __init _setup_reset(struct omap_hwmod *oh)
  *
  * No return value.
  */
-static void __init _setup_postsetup(struct omap_hwmod *oh)
+static void _setup_postsetup(struct omap_hwmod *oh)
 {
 	u8 postsetup_state;
 
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 30768003f854..8c505284bc0c 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -344,7 +344,7 @@ static void omap44xx_prm_reconfigure_io_chain(void)
  * to occur, WAKEUPENABLE bits must be set in the pad mux registers, and
  * omap44xx_prm_reconfigure_io_chain() must be called.  No return value.
  */
-static void __init omap44xx_prm_enable_io_wakeup(void)
+static void omap44xx_prm_enable_io_wakeup(void)
 {
 	s32 inst = omap4_prmst_get_prm_dev_inst();
 
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 868448d2cd82..38ab30869821 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -547,7 +547,7 @@ static struct pxa3xx_u2d_platform_data cm_x300_u2d_platform_data = {
 	.exit		= cm_x300_u2d_exit,
 };
 
-static void cm_x300_init_u2d(void)
+static void __init cm_x300_init_u2d(void)
 {
 	pxa3xx_set_u2d_info(&cm_x300_u2d_platform_data);
 }
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index 051c554776a6..ebdef6661f5f 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -183,7 +183,7 @@ static struct pxafb_mach_info littleton_lcd_info = {
 	.lcd_conn		= LCD_COLOR_TFT_16BPP,
 };
 
-static void littleton_init_lcd(void)
+static void __init littleton_init_lcd(void)
 {
 	pxa_set_fb_info(NULL, &littleton_lcd_info);
 }
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 3b94ecfb9426..3fcd5854bf5b 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -557,7 +557,7 @@ static struct pxaohci_platform_data zeus_ohci_platform_data = {
 	.flags		= ENABLE_PORT_ALL | POWER_SENSE_LOW,
 };
 
-static void zeus_register_ohci(void)
+static void __init zeus_register_ohci(void)
 {
 	/* Port 2 is shared between host and client interface. */
 	UP2OCR = UP2OCR_HXOE | UP2OCR_HXS | UP2OCR_DMPDE | UP2OCR_DPPDE;
diff --git a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
index 262ab0744748..f4fdfca9439b 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
@@ -70,16 +70,16 @@ static int osiris_dvs_notify(struct notifier_block *nb,
 
 	switch (val) {
 	case CPUFREQ_PRECHANGE:
-		if (old_dvs & !new_dvs ||
-		    cur_dvs & !new_dvs) {
+		if ((old_dvs && !new_dvs) ||
+		    (cur_dvs && !new_dvs)) {
 			pr_debug("%s: exiting dvs\n", __func__);
 			cur_dvs = false;
 			gpio_set_value(OSIRIS_GPIO_DVS, 1);
 		}
 		break;
 	case CPUFREQ_POSTCHANGE:
-		if (!old_dvs & new_dvs ||
-		    !cur_dvs & new_dvs) {
+		if ((!old_dvs && new_dvs) ||
+		    (!cur_dvs && new_dvs)) {
 			pr_debug("entering dvs\n");
 			cur_dvs = true;
 			gpio_set_value(OSIRIS_GPIO_DVS, 0);
diff --git a/arch/arm/mach-tango/pm.c b/arch/arm/mach-tango/pm.c
index b05c6d6f99d0..08d813234b2d 100644
--- a/arch/arm/mach-tango/pm.c
+++ b/arch/arm/mach-tango/pm.c
@@ -2,6 +2,7 @@
 #include <linux/suspend.h>
 #include <asm/suspend.h>
 #include "smc.h"
+#include "pm.h"
 
 static int tango_pm_powerdown(unsigned long arg)
 {
@@ -23,10 +24,7 @@ static const struct platform_suspend_ops tango_pm_ops = {
 	.valid = suspend_valid_only_mem,
 };
 
-static int __init tango_pm_init(void)
+void __init tango_pm_init(void)
 {
 	suspend_set_ops(&tango_pm_ops);
-	return 0;
 }
-
-late_initcall(tango_pm_init);
diff --git a/arch/arm/mach-tango/pm.h b/arch/arm/mach-tango/pm.h
new file mode 100644
index 000000000000..35ea705a0ee2
--- /dev/null
+++ b/arch/arm/mach-tango/pm.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CONFIG_SUSPEND
+void __init tango_pm_init(void);
+#else
+#define tango_pm_init NULL
+#endif
diff --git a/arch/arm/mach-tango/setup.c b/arch/arm/mach-tango/setup.c
index f14b6c7d255b..2b48e1098ea3 100644
--- a/arch/arm/mach-tango/setup.c
+++ b/arch/arm/mach-tango/setup.c
@@ -1,6 +1,7 @@
 #include <asm/mach/arch.h>
 #include <asm/hardware/cache-l2x0.h>
 #include "smc.h"
+#include "pm.h"
 
 static void tango_l2c_write(unsigned long val, unsigned int reg)
 {
@@ -14,4 +15,5 @@ DT_MACHINE_START(TANGO_DT, "Sigma Tango DT")
 	.dt_compat	= tango_dt_compat,
 	.l2c_aux_mask	= ~0,
 	.l2c_write_sec	= tango_l2c_write,
+	.init_late	= tango_pm_init,
 MACHINE_END
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index d2dd211f66ee..8bc5b751ad06 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -362,14 +362,16 @@ v7_dma_inv_range:
 	ALT_UP(W(nop))
 #endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
+	addne	r0, r0, r2
 
 	tst	r1, r3
 	bic	r1, r1, r3
 	mcrne	p15, 0, r1, c7, c14, 1		@ clean & invalidate D / U line
-1:
-	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
-	add	r0, r0, r2
 	cmp	r0, r1
+1:
+	mcrlo	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
+	addlo	r0, r0, r2
+	cmplo	r0, r1
 	blo	1b
 	dsb	st
 	ret	lr
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index 816a7e44e6f1..d29927740a19 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -73,9 +73,11 @@
 /*
  * dcimvac: Invalidate data cache line by MVA to PoC
  */
-.macro dcimvac, rt, tmp
-	v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC
+.irp    c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+.macro dcimvac\c, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC, \c
 .endm
+.endr
 
 /*
  * dccmvau: Clean data cache line by MVA to PoU
@@ -369,14 +371,16 @@ v7m_dma_inv_range:
 	tst	r0, r3
 	bic	r0, r0, r3
 	dccimvacne r0, r3
+	addne	r0, r0, r2
 	subne	r3, r2, #1	@ restore r3, corrupted by v7m's dccimvac
 	tst	r1, r3
 	bic	r1, r1, r3
 	dccimvacne r1, r3
-1:
-	dcimvac r0, r3
-	add	r0, r0, r2
 	cmp	r0, r1
+1:
+	dcimvaclo r0, r3
+	addlo	r0, r0, r2
+	cmplo	r0, r1
 	blo	1b
 	dsb	st
 	ret	lr
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 7d9176c4a21d..f8bb65032b79 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -275,6 +275,13 @@
 	.endm
 
 .macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0, bugs=0
+/*
+ * If we are building for big.Little with branch predictor hardening,
+ * we need the processor function tables to remain available after boot.
+ */
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+	.section ".rodata"
+#endif
 	.type	\name\()_processor_functions, #object
 	.align 2
 ENTRY(\name\()_processor_functions)
@@ -310,6 +317,9 @@ ENTRY(\name\()_processor_functions)
 	.endif
 
 	.size	\name\()_processor_functions, . - \name\()_processor_functions
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+	.previous
+#endif
 .endm
 
 .macro define_cache_functions name:req
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index 5544b82a2e7a..9a07916af8dd 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -52,8 +52,6 @@ static void cpu_v7_spectre_init(void)
 	case ARM_CPU_PART_CORTEX_A17:
 	case ARM_CPU_PART_CORTEX_A73:
 	case ARM_CPU_PART_CORTEX_A75:
-		if (processor.switch_mm != cpu_v7_bpiall_switch_mm)
-			goto bl_error;
 		per_cpu(harden_branch_predictor_fn, cpu) =
 			harden_branch_predictor_bpiall;
 		spectre_v2_method = "BPIALL";
@@ -61,8 +59,6 @@ static void cpu_v7_spectre_init(void)
 
 	case ARM_CPU_PART_CORTEX_A15:
 	case ARM_CPU_PART_BRAHMA_B15:
-		if (processor.switch_mm != cpu_v7_iciallu_switch_mm)
-			goto bl_error;
 		per_cpu(harden_branch_predictor_fn, cpu) =
 			harden_branch_predictor_iciallu;
 		spectre_v2_method = "ICIALLU";
@@ -88,11 +84,9 @@ static void cpu_v7_spectre_init(void)
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
 				break;
-			if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu)
-				goto bl_error;
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_hvc_arch_workaround_1;
-			processor.switch_mm = cpu_v7_hvc_switch_mm;
+			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
 			spectre_v2_method = "hypervisor";
 			break;
 
@@ -101,11 +95,9 @@ static void cpu_v7_spectre_init(void)
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
 				break;
-			if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu)
-				goto bl_error;
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_smc_arch_workaround_1;
-			processor.switch_mm = cpu_v7_smc_switch_mm;
+			cpu_do_switch_mm = cpu_v7_smc_switch_mm;
 			spectre_v2_method = "firmware";
 			break;
 
@@ -119,11 +111,6 @@ static void cpu_v7_spectre_init(void)
 	if (spectre_v2_method)
 		pr_info("CPU%u: Spectre v2: using %s workaround\n",
 			smp_processor_id(), spectre_v2_method);
-	return;
-
-bl_error:
-	pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n",
-		cpu);
 }
 #else
 static void cpu_v7_spectre_init(void)
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ba13f793fbce..b92673efffff 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -237,8 +237,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
 	if (ssp == NULL)
 		return -ENODEV;
 
-	iounmap(ssp->mmio_base);
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	release_mem_region(res->start, resource_size(res));
 
@@ -248,7 +246,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
 	list_del(&ssp->node);
 	mutex_unlock(&ssp_lock);
 
-	kfree(ssp);
 	return 0;
 }
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 8e5e97989fda..00dd8cf36632 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -554,12 +554,11 @@ void vfp_flush_hwstate(struct thread_info *thread)
  * Save the current VFP state into the provided structures and prepare
  * for entry into a new function (signal handler).
  */
-int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
-				    struct user_vfp_exc __user *ufp_exc)
+int vfp_preserve_user_clear_hwstate(struct user_vfp *ufp,
+				    struct user_vfp_exc *ufp_exc)
 {
 	struct thread_info *thread = current_thread_info();
 	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
-	int err = 0;
 
 	/* Ensure that the saved hwstate is up-to-date. */
 	vfp_sync_hwstate(thread);
@@ -568,22 +567,19 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
 	 */
-	err |= __copy_to_user(&ufp->fpregs, &hwstate->fpregs,
-			      sizeof(hwstate->fpregs));
+	memcpy(&ufp->fpregs, &hwstate->fpregs, sizeof(hwstate->fpregs));
+
 	/*
 	 * Copy the status and control register.
 	 */
-	__put_user_error(hwstate->fpscr, &ufp->fpscr, err);
+	ufp->fpscr = hwstate->fpscr;
 
 	/*
 	 * Copy the exception registers.
 	 */
-	__put_user_error(hwstate->fpexc, &ufp_exc->fpexc, err);
-	__put_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
-	__put_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
-
-	if (err)
-		return -EFAULT;
+	ufp_exc->fpexc = hwstate->fpexc;
+	ufp_exc->fpinst = hwstate->fpinst;
+	ufp_exc->fpinst2 = hwstate->fpinst2;
 
 	/* Ensure that VFP is disabled. */
 	vfp_flush_hwstate(thread);
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 2c93de7fffe5..bdea2d6fde94 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -219,7 +219,7 @@
 		compatible = "simple-bus";
 
 		intc: interrupt-controller@9bc0000 {
-			compatible = "arm,gic-v3";
+			compatible = "qcom,msm8996-gic-v3", "arm,gic-v3";
 			#interrupt-cells = <3>;
 			interrupt-controller;
 			#redistributor-regions = <1>;
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 3363560c79b7..7bc459d9235c 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -74,12 +74,13 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w8
+8:	cbz	w8, 91f
+	mov	w7, w8
 	add	w8, w8, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
-	eor	v0.16b, v0.16b, v1.16b
+91:	eor	v0.16b, v0.16b, v1.16b
 	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index f8ae6d6e4767..85a15b38b6d8 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -80,18 +80,8 @@
 #include <linux/stringify.h>
 #include <asm/barrier.h>
 
-#define read_gicreg(r)							\
-	({								\
-		u64 reg;						\
-		asm volatile("mrs_s %0, " __stringify(r) : "=r" (reg));	\
-		reg;							\
-	})
-
-#define write_gicreg(v,r)						\
-	do {								\
-		u64 __val = (v);					\
-		asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\
-	} while (0)
+#define read_gicreg			read_sysreg_s
+#define write_gicreg			write_sysreg_s
 
 /*
  * Low-level accessors
@@ -102,13 +92,13 @@
 
 static inline void gic_write_eoir(u32 irq)
 {
-	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" ((u64)irq));
+	write_sysreg_s(irq, ICC_EOIR1_EL1);
 	isb();
 }
 
 static inline void gic_write_dir(u32 irq)
 {
-	asm volatile("msr_s " __stringify(ICC_DIR_EL1) ", %0" : : "r" ((u64)irq));
+	write_sysreg_s(irq, ICC_DIR_EL1);
 	isb();
 }
 
@@ -116,7 +106,7 @@ static inline u64 gic_read_iar_common(void)
 {
 	u64 irqstat;
 
-	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	irqstat = read_sysreg_s(ICC_IAR1_EL1);
 	dsb(sy);
 	return irqstat;
 }
@@ -134,10 +124,12 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
 
 	asm volatile(
 		"nop;nop;nop;nop\n\t"
-		"nop;nop;nop;nop\n\t"
-		"mrs_s %0, " __stringify(ICC_IAR1_EL1) "\n\t"
-		"nop;nop;nop;nop"
-		: "=r" (irqstat));
+		"nop;nop;nop;nop");
+
+	irqstat = read_sysreg_s(ICC_IAR1_EL1);
+
+	asm volatile(
+		"nop;nop;nop;nop");
 	mb();
 
 	return irqstat;
@@ -145,43 +137,40 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
 
 static inline void gic_write_pmr(u32 val)
 {
-	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" ((u64)val));
+	write_sysreg_s(val, ICC_PMR_EL1);
 }
 
 static inline void gic_write_ctlr(u32 val)
 {
-	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" ((u64)val));
+	write_sysreg_s(val, ICC_CTLR_EL1);
 	isb();
 }
 
 static inline void gic_write_grpen1(u32 val)
 {
-	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" ((u64)val));
+	write_sysreg_s(val, ICC_GRPEN1_EL1);
 	isb();
 }
 
 static inline void gic_write_sgi1r(u64 val)
 {
-	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+	write_sysreg_s(val, ICC_SGI1R_EL1);
 }
 
 static inline u32 gic_read_sre(void)
 {
-	u64 val;
-
-	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
-	return val;
+	return read_sysreg_s(ICC_SRE_EL1);
 }
 
 static inline void gic_write_sre(u32 val)
 {
-	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" ((u64)val));
+	write_sysreg_s(val, ICC_SRE_EL1);
 	isb();
 }
 
 static inline void gic_write_bpr1(u32 val)
 {
-	asm volatile("msr_s " __stringify(ICC_BPR1_EL1) ", %0" : : "r" (val));
+	write_sysreg_s(val, ICC_BPR1_EL1);
 }
 
 #define gic_read_typer(c)		readq_relaxed(c)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0dbc1c6ab7dc..a11c8c2915c9 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,8 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_API		(UL(1) << 41)
+#define HCR_APK		(UL(1) << 40)
 #define HCR_E2H		(UL(1) << 34)
 #define HCR_ID		(UL(1) << 33)
 #define HCR_CD		(UL(1) << 32)
@@ -82,6 +84,7 @@
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
@@ -99,7 +102,7 @@
 			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
 
 /* VTCR_EL2 Registers bits */
-#define VTCR_EL2_RES1		(1 << 31)
+#define VTCR_EL2_RES1		(1U << 31)
 #define VTCR_EL2_HD		(1 << 22)
 #define VTCR_EL2_HA		(1 << 21)
 #define VTCR_EL2_PS_MASK	TCR_EL2_PS_MASK
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index aef02d2af3b5..7a87d32e98f4 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -78,7 +78,6 @@
 	.macro mcount_get_lr reg
 	ldr	\reg, [x29]
 	ldr	\reg, [\reg, #8]
-	mcount_adjust_addr	\reg, \reg
 	.endm
 
 	.macro mcount_get_lr_addr reg
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index fa52817d84c5..db6ff1944c41 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -517,10 +517,9 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 #endif
 
 	/* Hyp configuration. */
-	mov	x0, #HCR_RW			// 64-bit EL1
+	mov_q	x0, HCR_HOST_NVHE_FLAGS
 	cbz	x2, set_hcr
-	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
-	orr	x0, x0, #HCR_E2H
+	mov_q	x0, HCR_HOST_VHE_FLAGS
 set_hcr:
 	msr	hcr_el2, x0
 	isb
@@ -535,8 +534,7 @@ set_hcr:
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
 	ubfx	x0, x0, #24, #4
-	cmp	x0, #1
-	b.ne	3f
+	cbz	x0, 3f
 
 	mrs_s	x0, ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f6e71c73cceb..76c9b51fa7f1 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -297,8 +297,10 @@ int swsusp_arch_suspend(void)
 		dcache_clean_range(__idmap_text_start, __idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
-		if (el2_reset_needed())
+		if (el2_reset_needed()) {
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+		}
 
 		/*
 		 * Tell the hibernation core that we've just restored
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index d3b5f75e652e..fcb486d09555 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -28,6 +28,8 @@
 #include <asm/virt.h>
 
 	.text
+	.pushsection	.hyp.text, "ax"
+
 	.align 11
 
 ENTRY(__hyp_stub_vectors)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index d7e90d97f5c4..c9ca903462a6 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
+#include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
@@ -43,7 +44,7 @@ static __init u64 get_kaslr_seed(void *fdt)
 	return ret;
 }
 
-static __init const u8 *get_cmdline(void *fdt)
+static __init const u8 *kaslr_get_cmdline(void *fdt)
 {
 	static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE;
 
@@ -87,6 +88,7 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,
@@ -109,7 +111,7 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 	 * Check if 'nokaslr' appears on the command line, and
 	 * return 0 if that is the case.
 	 */
-	cmdline = get_cmdline(fdt);
+	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
 	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
 		return 0;
@@ -178,5 +180,8 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+
 	return offset;
 }
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 199a23f058d5..0770d6d1c37f 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1114,6 +1114,7 @@ static struct platform_driver armv8_pmu_driver = {
 	.driver		= {
 		.name	= ARMV8_PMU_PDEV_NAME,
 		.of_match_table = armv8_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= armv8_pmu_device_probe,
 };
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 30bcae0aef2a..d2b1b624ddc3 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -546,13 +546,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr)
 	    addr < (unsigned long)__entry_text_end) ||
 	    (addr >= (unsigned long)__idmap_text_start &&
 	    addr < (unsigned long)__idmap_text_end) ||
+	    (addr >= (unsigned long)__hyp_text_start &&
+	    addr < (unsigned long)__hyp_text_end) ||
 	    !!search_exception_tables(addr))
 		return true;
 
 	if (!is_kernel_in_hyp_mode()) {
-		if ((addr >= (unsigned long)__hyp_text_start &&
-		    addr < (unsigned long)__hyp_text_end) ||
-		    (addr >= (unsigned long)__hyp_idmap_text_start &&
+		if ((addr >= (unsigned long)__hyp_idmap_text_start &&
 		    addr < (unsigned long)__hyp_idmap_text_end))
 			return true;
 	}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5963be2e05f0..28bef94cf792 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -266,10 +266,12 @@ void die(const char *str, struct pt_regs *regs, int err)
 {
 	struct thread_info *thread = current_thread_info();
 	int ret;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&die_lock, flags);
 
 	oops_enter();
 
-	raw_spin_lock_irq(&die_lock);
 	console_verbose();
 	bust_spinlocks(1);
 	ret = __die(str, err, thread, regs);
@@ -279,13 +281,15 @@ void die(const char *str, struct pt_regs *regs, int err)
 
 	bust_spinlocks(0);
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-	raw_spin_unlock_irq(&die_lock);
 	oops_exit();
 
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 	if (panic_on_oops)
 		panic("Fatal exception");
+
+	raw_spin_unlock_irqrestore(&die_lock, flags);
+
 	if (ret != NOTIFY_STOP)
 		do_exit(SIGSEGV);
 }
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 12f9d1ecdf4c..115b0955715f 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -112,7 +112,7 @@ static void __hyp_text __deactivate_traps_vhe(void)
 
 static void __hyp_text __deactivate_traps_nvhe(void)
 {
-	write_sysreg(HCR_RW, hcr_el2);
+	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index f0dd9fc84002..a229d28e14cc 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -58,7 +58,10 @@ cpuflags-$(CONFIG_M5206e)	:= $(call cc-option,-mcpu=5206e,-m5200)
 cpuflags-$(CONFIG_M5206)	:= $(call cc-option,-mcpu=5206,-m5200)
 
 KBUILD_AFLAGS += $(cpuflags-y)
-KBUILD_CFLAGS += $(cpuflags-y) -pipe
+KBUILD_CFLAGS += $(cpuflags-y)
+
+KBUILD_CFLAGS += -pipe -ffreestanding
+
 ifdef CONFIG_MMU
 # without -fno-strength-reduce the 53c7xx.c driver fails ;-(
 KBUILD_CFLAGS += -fno-strength-reduce -ffixed-a2
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 34fbbf8fdeaa..bb9940c6927e 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -791,6 +791,7 @@ config SIBYTE_SWARM
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select ZONE_DMA32 if 64BIT
+	select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
 
 config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
@@ -813,6 +814,7 @@ config SIBYTE_SENTOSA
 	select SYS_HAS_CPU_SB1
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
 
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
@@ -826,6 +828,7 @@ config SIBYTE_BIGSUR
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select ZONE_DMA32 if 64BIT
+	select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
 
 config SNI_RM
 	bool "SNI RM200/300/400"
@@ -3135,6 +3138,7 @@ config MIPS32_O32
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
 	depends on 64BIT
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select COMPAT
 	select MIPS32_COMPAT
 	select SYSVIPC_COMPAT if SYSVIPC
diff --git a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
index 37fe58c19a90..542c3ede9722 100644
--- a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
+++ b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
@@ -13,6 +13,7 @@
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "../../../../include/linux/sizes.h"
 
 int main(int argc, char *argv[])
 {
@@ -45,11 +46,11 @@ int main(int argc, char *argv[])
 	vmlinuz_load_addr = vmlinux_load_addr + vmlinux_size;
 
 	/*
-	 * Align with 16 bytes: "greater than that used for any standard data
-	 * types by a MIPS compiler." -- See MIPS Run Linux (Second Edition).
+	 * Align with 64KB: KEXEC needs load sections to be aligned to PAGE_SIZE,
+	 * which may be as large as 64KB depending on the kernel configuration.
 	 */
 
-	vmlinuz_load_addr += (16 - vmlinux_size % 16);
+	vmlinuz_load_addr += (SZ_64K - vmlinux_size % SZ_64K);
 
 	printf("0x%llx\n", vmlinuz_load_addr);
 
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c
index 396236a02b8c..59defc5e88aa 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c
@@ -290,7 +290,8 @@ static cvmx_helper_interface_mode_t __cvmx_get_mode_cn7xxx(int interface)
 	case 3:
 		return CVMX_HELPER_INTERFACE_MODE_LOOP;
 	case 4:
-		return CVMX_HELPER_INTERFACE_MODE_RGMII;
+		/* TODO: Implement support for AGL (RGMII). */
+		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
 	default:
 		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
 	}
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 134879c1310a..4ed369c0ec6a 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -74,6 +74,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_SERIAL_8250_PCI is not set
 CONFIG_SERIAL_8250_NR_UARTS=1
 CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AR933X=y
 CONFIG_SERIAL_AR933X_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index e77672539e8e..e4456e450f94 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -21,15 +21,15 @@
 #endif
 
 #ifdef CONFIG_CPU_MICROMIPS
-#define NOP_INSN "nop32"
+#define B_INSN "b32"
 #else
-#define NOP_INSN "nop"
+#define B_INSN "b"
 #endif
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" NOP_INSN "\n\t"
-		"nop\n\t"
+	asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
+		"2:\tnop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 514cbc0a6a67..ef6f00798011 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -193,6 +193,11 @@ static inline int pmd_bad(pmd_t pmd)
 
 static inline int pmd_present(pmd_t pmd)
 {
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
+	if (unlikely(pmd_val(pmd) & _PAGE_HUGE))
+		return pmd_val(pmd) & _PAGE_PRESENT;
+#endif
+
 	return pmd_val(pmd) != (unsigned long) invalid_pte_table;
 }
 
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index 711d9b8465b8..377d5179ea3b 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -361,8 +361,8 @@ enum mm_32a_minor_op {
 	mm_ext_op = 0x02c,
 	mm_pool32axf_op = 0x03c,
 	mm_srl32_op = 0x040,
+	mm_srlv32_op = 0x050,
 	mm_sra_op = 0x080,
-	mm_srlv32_op = 0x090,
 	mm_rotr_op = 0x0c0,
 	mm_lwxs_op = 0x118,
 	mm_addu32_op = 0x150,
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index db6f5afff4ff..ea897912bc71 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -71,14 +71,15 @@ static int __init vdma_init(void)
 						    get_order(VDMA_PGTBL_SIZE));
 	BUG_ON(!pgtbl);
 	dma_cache_wback_inv((unsigned long)pgtbl, VDMA_PGTBL_SIZE);
-	pgtbl = (VDMA_PGTBL_ENTRY *)KSEG1ADDR(pgtbl);
+	pgtbl = (VDMA_PGTBL_ENTRY *)CKSEG1ADDR((unsigned long)pgtbl);
 
 	/*
 	 * Clear the R4030 translation table
 	 */
 	vdma_pgtbl_init();
 
-	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE, CPHYSADDR(pgtbl));
+	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE,
+			  CPHYSADDR((unsigned long)pgtbl));
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_LIM, VDMA_PGTBL_SIZE);
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
 
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 2b0a371b42af..24444ed456c8 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -52,6 +52,7 @@ asmlinkage void spurious_interrupt(void)
 void __init init_IRQ(void)
 {
 	int i;
+	unsigned int order = get_order(IRQ_STACK_SIZE);
 
 	for (i = 0; i < NR_IRQS; i++)
 		irq_set_noprobe(i);
@@ -62,8 +63,7 @@ void __init init_IRQ(void)
 	arch_init_irq();
 
 	for_each_possible_cpu(i) {
-		int irq_pages = IRQ_STACK_SIZE / PAGE_SIZE;
-		void *s = (void *)__get_free_pages(GFP_KERNEL, irq_pages);
+		void *s = (void *)__get_free_pages(GFP_KERNEL, order);
 
 		irq_stack[i] = s;
 		pr_debug("CPU%d IRQ stack at 0x%p - 0x%p\n", i,
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 659e6d3ae335..60177a612cb1 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -424,5 +424,5 @@ void mips_cm_error_report(void)
 	}
 
 	/* reprime cause register */
-	write_gcr_error_cause(0);
+	write_gcr_error_cause(cm_error);
 }
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 1cc133e7026f..fffd031dc6b6 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -344,7 +344,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip)
 static int get_frame_info(struct mips_frame_info *info)
 {
 	bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
-	union mips_instruction insn, *ip, *ip_end;
+	union mips_instruction insn, *ip;
 	const unsigned int max_insns = 128;
 	unsigned int last_insn_size = 0;
 	unsigned int i;
@@ -356,10 +356,9 @@ static int get_frame_info(struct mips_frame_info *info)
 	if (!ip)
 		goto err;
 
-	ip_end = (void *)ip + info->func_size;
-
-	for (i = 0; i < max_insns && ip < ip_end; i++) {
+	for (i = 0; i < max_insns; i++) {
 		ip = (void *)ip + last_insn_size;
+
 		if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
 			insn.halfword[0] = 0;
 			insn.halfword[1] = ip->halfword[0];
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index e88344e3d508..c6297a03d945 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -111,8 +111,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 	/* Map delay slot emulation page */
 	base = mmap_region(NULL, STACK_TOP, PAGE_SIZE,
-			   VM_READ|VM_WRITE|VM_EXEC|
-			   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+			   VM_READ | VM_EXEC |
+			   VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
 			   0);
 	if (IS_ERR_VALUE(base)) {
 		ret = base;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index f0a0e6d62be3..2d965d91fee4 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -138,6 +138,13 @@ SECTIONS
 	PERCPU_SECTION(1 << CONFIG_MIPS_L1_CACHE_SHIFT)
 #endif
 
+#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+	.appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
+		*(.appended_dtb)
+		KEEP(*(.appended_dtb))
+	}
+#endif
+
 #ifdef CONFIG_RELOCATABLE
 	. = ALIGN(4);
 
@@ -162,11 +169,6 @@ SECTIONS
 	__appended_dtb = .;
 	/* leave space for appended DTB */
 	. += 0x100000;
-#elif defined(CONFIG_MIPS_ELF_APPENDED_DTB)
-	.appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
-		*(.appended_dtb)
-		KEEP(*(.appended_dtb))
-	}
 #endif
 	/*
 	 * Align to 64K in attempt to eliminate holes before the
diff --git a/arch/mips/loongson64/lemote-2f/irq.c b/arch/mips/loongson64/lemote-2f/irq.c
index cab5f43e0e29..d371f0294cbb 100644
--- a/arch/mips/loongson64/lemote-2f/irq.c
+++ b/arch/mips/loongson64/lemote-2f/irq.c
@@ -102,7 +102,7 @@ static struct irqaction ip6_irqaction = {
 static struct irqaction cascade_irqaction = {
 	.handler = no_action,
 	.name = "cascade",
-	.flags = IRQF_NO_THREAD,
+	.flags = IRQF_NO_THREAD | IRQF_NO_SUSPEND,
 };
 
 void __init mach_init_irq(void)
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 4a094f7acb3d..7b4329861056 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -211,8 +211,9 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir,
 {
 	int isa16 = get_isa16_mode(regs->cp0_epc);
 	mips_instruction break_math;
-	struct emuframe __user *fr;
-	int err, fr_idx;
+	unsigned long fr_uaddr;
+	struct emuframe fr;
+	int fr_idx, ret;
 
 	/* NOP is easy */
 	if (ir == 0)
@@ -247,27 +248,31 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir,
 		fr_idx = alloc_emuframe();
 	if (fr_idx == BD_EMUFRAME_NONE)
 		return SIGBUS;
-	fr = &dsemul_page()[fr_idx];
 
 	/* Retrieve the appropriately encoded break instruction */
 	break_math = BREAK_MATH(isa16);
 
 	/* Write the instructions to the frame */
 	if (isa16) {
-		err = __put_user(ir >> 16,
-				 (u16 __user *)(&fr->emul));
-		err |= __put_user(ir & 0xffff,
-				  (u16 __user *)((long)(&fr->emul) + 2));
-		err |= __put_user(break_math >> 16,
-				  (u16 __user *)(&fr->badinst));
-		err |= __put_user(break_math & 0xffff,
-				  (u16 __user *)((long)(&fr->badinst) + 2));
+		union mips_instruction _emul = {
+			.halfword = { ir >> 16, ir }
+		};
+		union mips_instruction _badinst = {
+			.halfword = { break_math >> 16, break_math }
+		};
+
+		fr.emul = _emul.word;
+		fr.badinst = _badinst.word;
 	} else {
-		err = __put_user(ir, &fr->emul);
-		err |= __put_user(break_math, &fr->badinst);
+		fr.emul = ir;
+		fr.badinst = break_math;
 	}
 
-	if (unlikely(err)) {
+	/* Write the frame to user memory */
+	fr_uaddr = (unsigned long)&dsemul_page()[fr_idx];
+	ret = access_process_vm(current, fr_uaddr, &fr, sizeof(fr),
+				FOLL_FORCE | FOLL_WRITE);
+	if (unlikely(ret != sizeof(fr))) {
 		MIPS_FPU_EMU_INC_STATS(errors);
 		free_emuframe(fr_idx, current->mm);
 		return SIGBUS;
@@ -279,10 +284,7 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir,
 	atomic_set(&current->thread.bd_emu_frame, fr_idx);
 
 	/* Change user register context to execute the frame */
-	regs->cp0_epc = (unsigned long)&fr->emul | isa16;
-
-	/* Ensure the icache observes our newly written frame */
-	flush_cache_sigtramp((unsigned long)&fr->emul);
+	regs->cp0_epc = fr_uaddr | isa16;
 
 	return 0;
 }
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 2a5bb849b10e..288b58b00dc8 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void)
 	int irq;
 	struct irq_chip *msi;
 
-	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+		return 0;
+	} else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
 		msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
 		msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
 		msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 308d051fc45c..7c512834a8f1 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -573,6 +573,11 @@ static int __init octeon_pci_setup(void)
 	if (octeon_has_feature(OCTEON_FEATURE_PCIE))
 		return 0;
 
+	if (!octeon_is_pci_host()) {
+		pr_notice("Not in host mode, PCI Controller not initialized\n");
+		return 0;
+	}
+
 	/* Point pcibios_map_irq() to the PCI version of it */
 	octeon_pcibios_map_irq = octeon_pci_pcibios_map_irq;
 
@@ -584,11 +589,6 @@ static int __init octeon_pci_setup(void)
 	else
 		octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG;
 
-	if (!octeon_is_pci_host()) {
-		pr_notice("Not in host mode, PCI Controller not initialized\n");
-		return 0;
-	}
-
 	/* PCI I/O and PCI MEM values */
 	set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
 	ioport_resource.start = 0;
diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig
index 813826a456ca..55a5fee781e8 100644
--- a/arch/mips/ralink/Kconfig
+++ b/arch/mips/ralink/Kconfig
@@ -38,6 +38,7 @@ choice
 
 	config SOC_MT7620
 		bool "MT7620/8"
+		select CPU_MIPSR2_IRQ_VI
 		select HW_HAS_PCI
 
 	config SOC_MT7621
diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile
index b3d6bf23a662..3ef3fb658136 100644
--- a/arch/mips/sibyte/common/Makefile
+++ b/arch/mips/sibyte/common/Makefile
@@ -1,4 +1,5 @@
 obj-y := cfe.o
+obj-$(CONFIG_SWIOTLB)			+= dma.o
 obj-$(CONFIG_SIBYTE_BUS_WATCHER)	+= bus_watcher.o
 obj-$(CONFIG_SIBYTE_CFE_CONSOLE)	+= cfe_console.o
 obj-$(CONFIG_SIBYTE_TBPROF)		+= sb_tbprof.o
diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c
new file mode 100644
index 000000000000..eb47a94f3583
--- /dev/null
+++ b/arch/mips/sibyte/common/dma.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *	DMA support for Broadcom SiByte platforms.
+ *
+ *	Copyright (c) 2018  Maciej W. Rozycki
+ */
+
+#include <linux/swiotlb.h>
+#include <asm/bootinfo.h>
+
+void __init plat_swiotlb_setup(void)
+{
+	swiotlb_init(1);
+}
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index c3dc12a8b7d9..0b845cc7fbdc 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -116,7 +116,7 @@ $(obj)/%-o32.o: $(src)/%.c FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := -mabi=32
+$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=32
 $(obj)/vdso-o32.lds: $(src)/vdso.lds.S FORCE
 	$(call if_changed_dep,cpp_lds_S)
 
@@ -156,7 +156,7 @@ $(obj)/%-n32.o: $(src)/%.c FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := -mabi=n32
+$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=n32
 $(obj)/vdso-n32.lds: $(src)/vdso.lds.S FORCE
 	$(call if_changed_dep,cpp_lds_S)
 
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index e02d7b4d2b69..0780c375fe2e 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -311,15 +311,29 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs)) {
+	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
+		int rc = tracehook_report_syscall_entry(regs);
+
 		/*
-		 * Tracing decided this syscall should not happen or the
-		 * debugger stored an invalid system call number. Skip
-		 * the system call and the system call restart handling.
+		 * As tracesys_next does not set %r28 to -ENOSYS
+		 * when %r20 is set to -1, initialize it here.
 		 */
-		regs->gr[20] = -1UL;
-		goto out;
+		regs->gr[28] = -ENOSYS;
+
+		if (rc) {
+			/*
+			 * A nonzero return code from
+			 * tracehook_report_syscall_entry() tells us
+			 * to prevent the syscall execution.  Skip
+			 * the syscall call and the syscall restart handling.
+			 *
+			 * Note that the tracer may also just change
+			 * regs->gr[20] to an invalid syscall number,
+			 * that is handled by tracesys_next.
+			 */
+			regs->gr[20] = -1UL;
+			return -1;
+		}
 	}
 
 	/* Do the secure computing check after ptrace. */
@@ -343,7 +357,6 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 			regs->gr[24] & 0xffffffff,
 			regs->gr[23] & 0xffffffff);
 
-out:
 	/*
 	 * Sign extend the syscall number to 64bit since it may have been
 	 * modified by a compat ptrace call
diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
index 5c2199857aa8..a3550e8f1a77 100644
--- a/arch/powerpc/boot/crt0.S
+++ b/arch/powerpc/boot/crt0.S
@@ -15,7 +15,7 @@
 RELA = 7
 RELACOUNT = 0x6ffffff9
 
-	.text
+	.data
 	/* A procedure descriptor used when booting this as a COFF file.
 	 * When making COFF, this comes first in the link and we're
 	 * linked at 0x500000.
@@ -23,6 +23,8 @@ RELACOUNT = 0x6ffffff9
 	.globl	_zimage_start_opd
 _zimage_start_opd:
 	.long	0x500000, 0, 0, 0
+	.text
+	b	_zimage_start
 
 #ifdef __powerpc64__
 .balign 8
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index 334459ad145b..90863245df53 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -508,7 +508,7 @@ static unsigned long epapr_hypercall(unsigned long *in,
 
 static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 	unsigned long r;
 
@@ -520,7 +520,7 @@ static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2)
 
 static inline long epapr_hypercall0(unsigned int nr)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	return epapr_hypercall(in, out, nr);
@@ -528,7 +528,7 @@ static inline long epapr_hypercall0(unsigned int nr)
 
 static inline long epapr_hypercall1(unsigned int nr, unsigned long p1)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
@@ -538,7 +538,7 @@ static inline long epapr_hypercall1(unsigned int nr, unsigned long p1)
 static inline long epapr_hypercall2(unsigned int nr, unsigned long p1,
 				    unsigned long p2)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
@@ -549,7 +549,7 @@ static inline long epapr_hypercall2(unsigned int nr, unsigned long p1,
 static inline long epapr_hypercall3(unsigned int nr, unsigned long p1,
 				    unsigned long p2, unsigned long p3)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
@@ -562,7 +562,7 @@ static inline long epapr_hypercall4(unsigned int nr, unsigned long p1,
 				    unsigned long p2, unsigned long p3,
 				    unsigned long p4)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index c266227fdd5b..31913b3ac7ab 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -59,7 +59,7 @@
 #endif
 
 #define access_ok(type, addr, size)		\
-	(__chk_user_ptr(addr),			\
+	(__chk_user_ptr(addr), (void)(type),		\
 	 __access_ok((__force unsigned long)(addr), (size), get_fs()))
 
 /*
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3841d749a430..370645687cc7 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -698,6 +698,9 @@ fast_exception_return:
 	mtcr	r10
 	lwz	r10,_LINK(r11)
 	mtlr	r10
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r11)
 	REST_GPR(10, r11)
 	mtspr	SPRN_SRR1,r9
 	mtspr	SPRN_SRR0,r12
@@ -932,6 +935,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	mtcrf	0xFF,r10
 	mtlr	r11
 
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r1)
 	/*
 	 * Once we put values in SRR0 and SRR1, we are in a state
 	 * where exceptions are not recoverable, since taking an
@@ -969,6 +975,9 @@ exc_exit_restart_end:
 	mtlr	r11
 	lwz	r10,_CCR(r1)
 	mtcrf	0xff,r10
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r1)
 	REST_2GPRS(9, r1)
 	.globl exc_exit_restart
 exc_exit_restart:
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index dab616a33b8d..f2197654be07 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -34,5 +34,10 @@ void arch_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct pci_controller *phb = pci_bus_to_host(dev->bus);
 
-	phb->controller_ops.teardown_msi_irqs(dev);
+	/*
+	 * We can be called even when arch_setup_msi_irqs() returns -ENOSYS,
+	 * so check the pointer again.
+	 */
+	if (phb->controller_ops.teardown_msi_irqs)
+		phb->controller_ops.teardown_msi_irqs(dev);
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1c141d50fbc6..609f0e87ced7 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -153,7 +153,7 @@ void __giveup_fpu(struct task_struct *tsk)
 
 	save_fpu(tsk);
 	msr = tsk->thread.regs->msr;
-	msr &= ~MSR_FP;
+	msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
 #ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr &= ~MSR_VSX;
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index adfa63e7df8c..4f2829634d79 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -547,6 +547,7 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset,
 		/*
 		 * Copy out only the low-order word of vrsave.
 		 */
+		int start, end;
 		union {
 			elf_vrreg_t reg;
 			u32 word;
@@ -555,8 +556,10 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset,
 
 		vrsave.word = target->thread.vrsave;
 
+		start = 33 * sizeof(vector128);
+		end = start + sizeof(vrsave);
 		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
-					  33 * sizeof(vector128), -1);
+					  start, end);
 	}
 
 	return ret;
@@ -594,6 +597,7 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset,
 		/*
 		 * We use only the first word of vrsave.
 		 */
+		int start, end;
 		union {
 			elf_vrreg_t reg;
 			u32 word;
@@ -602,8 +606,10 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset,
 
 		vrsave.word = target->thread.vrsave;
 
+		start = 33 * sizeof(vector128);
+		end = start + sizeof(vrsave);
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
-					 33 * sizeof(vector128), -1);
+					 start, end);
 		if (!ret)
 			target->thread.vrsave = vrsave.word;
 	}
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 27aa913ac91d..2bfa5a7bb672 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -866,7 +866,23 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	/* If TM bits are set to the reserved value, it's an invalid context */
 	if (MSR_TM_RESV(msr_hi))
 		return 1;
-	/* Pull in the MSR TM bits from the user context */
+
+	/*
+	 * Disabling preemption, since it is unsafe to be preempted
+	 * with MSR[TS] set without recheckpointing.
+	 */
+	preempt_disable();
+
+	/*
+	 * CAUTION:
+	 * After regs->MSR[TS] being updated, make sure that get_user(),
+	 * put_user() or similar functions are *not* called. These
+	 * functions can generate page faults which will cause the process
+	 * to be de-scheduled with MSR[TS] set but without calling
+	 * tm_recheckpoint(). This can cause a bug.
+	 *
+	 * Pull in the MSR TM bits from the user context
+	 */
 	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK);
 	/* Now, recheckpoint.  This loads up all of the checkpointed (older)
 	 * registers, including FP and V[S]Rs.  After recheckpointing, the
@@ -891,6 +907,8 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	}
 #endif
 
+	preempt_enable();
+
 	return 0;
 }
 #endif
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 04e92257fd69..d929afab7b24 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -452,20 +452,6 @@ static long restore_tm_sigcontexts(struct task_struct *tsk,
 	if (MSR_TM_RESV(msr))
 		return -EINVAL;
 
-	/* pull in MSR TS bits from user context */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
-
-	/*
-	 * Ensure that TM is enabled in regs->msr before we leave the signal
-	 * handler. It could be the case that (a) user disabled the TM bit
-	 * through the manipulation of the MSR bits in uc_mcontext or (b) the
-	 * TM bit was disabled because a sufficient number of context switches
-	 * happened whilst in the signal handler and load_tm overflowed,
-	 * disabling the TM bit. In either case we can end up with an illegal
-	 * TM state leading to a TM Bad Thing when we return to userspace.
-	 */
-	regs->msr |= MSR_TM;
-
 	/* pull in MSR LE from user context */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
@@ -557,6 +543,34 @@ static long restore_tm_sigcontexts(struct task_struct *tsk,
 	tm_enable();
 	/* Make sure the transaction is marked as failed */
 	tsk->thread.tm_texasr |= TEXASR_FS;
+
+	/*
+	 * Disabling preemption, since it is unsafe to be preempted
+	 * with MSR[TS] set without recheckpointing.
+	 */
+	preempt_disable();
+
+	/* pull in MSR TS bits from user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
+
+	/*
+	 * Ensure that TM is enabled in regs->msr before we leave the signal
+	 * handler. It could be the case that (a) user disabled the TM bit
+	 * through the manipulation of the MSR bits in uc_mcontext or (b) the
+	 * TM bit was disabled because a sufficient number of context switches
+	 * happened whilst in the signal handler and load_tm overflowed,
+	 * disabling the TM bit. In either case we can end up with an illegal
+	 * TM state leading to a TM Bad Thing when we return to userspace.
+	 *
+	 * CAUTION:
+	 * After regs->MSR[TS] being updated, make sure that get_user(),
+	 * put_user() or similar functions are *not* called. These
+	 * functions can generate page faults which will cause the process
+	 * to be de-scheduled with MSR[TS] set but without calling
+	 * tm_recheckpoint(). This can cause a bug.
+	 */
+	regs->msr |= MSR_TM;
+
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&tsk->thread, msr);
 
@@ -570,6 +584,8 @@ static long restore_tm_sigcontexts(struct task_struct *tsk,
 		regs->msr |= MSR_VEC;
 	}
 
+	preempt_enable();
+
 	return err;
 }
 #endif
diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S
index 3d1ecd211776..8137f77abad5 100644
--- a/arch/powerpc/platforms/83xx/suspend-asm.S
+++ b/arch/powerpc/platforms/83xx/suspend-asm.S
@@ -26,13 +26,13 @@
 #define SS_MSR		0x74
 #define SS_SDR1		0x78
 #define SS_LR		0x7c
-#define SS_SPRG		0x80 /* 4 SPRGs */
-#define SS_DBAT		0x90 /* 8 DBATs */
-#define SS_IBAT		0xd0 /* 8 IBATs */
-#define SS_TB		0x110
-#define SS_CR		0x118
-#define SS_GPREG	0x11c /* r12-r31 */
-#define STATE_SAVE_SIZE 0x16c
+#define SS_SPRG		0x80 /* 8 SPRGs */
+#define SS_DBAT		0xa0 /* 8 DBATs */
+#define SS_IBAT		0xe0 /* 8 IBATs */
+#define SS_TB		0x120
+#define SS_CR		0x128
+#define SS_GPREG	0x12c /* r12-r31 */
+#define STATE_SAVE_SIZE 0x17c
 
 	.section .data
 	.align	5
@@ -103,6 +103,16 @@ _GLOBAL(mpc83xx_enter_deep_sleep)
 	stw	r7, SS_SPRG+12(r3)
 	stw	r8, SS_SDR1(r3)
 
+	mfspr	r4, SPRN_SPRG4
+	mfspr	r5, SPRN_SPRG5
+	mfspr	r6, SPRN_SPRG6
+	mfspr	r7, SPRN_SPRG7
+
+	stw	r4, SS_SPRG+16(r3)
+	stw	r5, SS_SPRG+20(r3)
+	stw	r6, SS_SPRG+24(r3)
+	stw	r7, SS_SPRG+28(r3)
+
 	mfspr	r4, SPRN_DBAT0U
 	mfspr	r5, SPRN_DBAT0L
 	mfspr	r6, SPRN_DBAT1U
@@ -493,6 +503,16 @@ mpc83xx_deep_resume:
 	mtspr	SPRN_IBAT7U, r6
 	mtspr	SPRN_IBAT7L, r7
 
+	lwz	r4, SS_SPRG+16(r3)
+	lwz	r5, SS_SPRG+20(r3)
+	lwz	r6, SS_SPRG+24(r3)
+	lwz	r7, SS_SPRG+28(r3)
+
+	mtspr	SPRN_SPRG4, r4
+	mtspr	SPRN_SPRG5, r5
+	mtspr	SPRN_SPRG6, r6
+	mtspr	SPRN_SPRG7, r7
+
 	lwz	r4, SS_SPRG+0(r3)
 	lwz	r5, SS_SPRG+4(r3)
 	lwz	r6, SS_SPRG+8(r3)
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 3fd683e40bc9..2914529c0695 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -104,6 +104,10 @@ unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
 	/* MEM2 64MB@0x10000000 */
 	delta = wii_hole_start + wii_hole_size;
 	size = top - delta;
+
+	if (__map_without_bats)
+		return delta;
+
 	for (bl = 128<<10; bl < max_size; bl <<= 1) {
 		if (bl * 2 > size)
 			break;
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index 39d6ff9e5630..d10bad14097b 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -98,7 +98,7 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
 }
 
 static struct bin_attribute opal_msglog_attr = {
-	.attr = {.name = "msglog", .mode = 0444},
+	.attr = {.name = "msglog", .mode = 0400},
 	.read = opal_msglog_read
 };
 
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 72ae2cdbcd6a..999b04819d69 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -288,6 +288,8 @@ int dlpar_detach_node(struct device_node *dn)
 	if (rc)
 		return rc;
 
+	of_node_put(dn);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 760545519a0b..687e8b8bf5c6 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -73,6 +73,9 @@ static int xmon_gate;
 #define xmon_owner 0
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_PPC_PSERIES
+static int set_indicator_token = RTAS_UNKNOWN_SERVICE;
+#endif
 static unsigned long in_xmon __read_mostly = 0;
 
 static unsigned long adrs;
@@ -340,7 +343,6 @@ static inline void disable_surveillance(void)
 #ifdef CONFIG_PPC_PSERIES
 	/* Since this can't be a module, args should end up below 4GB. */
 	static struct rtas_args args;
-	int token;
 
 	/*
 	 * At this point we have got all the cpus we can into
@@ -349,11 +351,11 @@ static inline void disable_surveillance(void)
 	 * If we did try to take rtas.lock there would be a
 	 * real possibility of deadlock.
 	 */
-	token = rtas_token("set-indicator");
-	if (token == RTAS_UNKNOWN_SERVICE)
+	if (set_indicator_token == RTAS_UNKNOWN_SERVICE)
 		return;
 
-	rtas_call_unlocked(&args, token, 3, 1, NULL, SURVEILLANCE_TOKEN, 0, 0);
+	rtas_call_unlocked(&args, set_indicator_token, 3, 1, NULL,
+			   SURVEILLANCE_TOKEN, 0, 0);
 
 #endif /* CONFIG_PPC_PSERIES */
 }
@@ -3227,6 +3229,14 @@ static void xmon_init(int enable)
 		__debugger_iabr_match = xmon_iabr_match;
 		__debugger_break_match = xmon_break_match;
 		__debugger_fault_handler = xmon_fault_handler;
+
+#ifdef CONFIG_PPC_PSERIES
+		/*
+		 * Get the token here to avoid trying to get a lock
+		 * during the crash, causing a deadlock.
+		 */
+		set_indicator_token = rtas_token("set-indicator");
+#endif
 	} else {
 		__debugger = NULL;
 		__debugger_ipi = NULL;
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 0c7a7d5d95f1..a651c2bc94ef 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -224,10 +224,10 @@ static noinline __init void detect_machine_type(void)
 	if (stsi(vmms, 3, 2, 2) || !vmms->count)
 		return;
 
-	/* Running under KVM? If not we assume z/VM */
+	/* Detect known hypervisors */
 	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
-	else
+	else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
 }
 
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 037c2a253ae4..1238e7ef1170 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -344,6 +344,8 @@ static int __hw_perf_event_init(struct perf_event *event)
 		break;
 
 	case PERF_TYPE_HARDWARE:
+		if (is_sampling_event(event))	/* No sampling support */
+			return -ENOENT;
 		ev = attr->config;
 		/* Count user space (problem-state) only */
 		if (!attr->exclude_user && attr->exclude_kernel) {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index feb9d97a9d14..a559908d180e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -863,6 +863,8 @@ void __init setup_arch(char **cmdline_p)
 		pr_info("Linux is running under KVM in 64-bit mode\n");
 	else if (MACHINE_IS_LPAR)
 		pr_info("Linux is running natively in 64-bit mode\n");
+	else
+		pr_info("Linux is running as a guest in 64-bit mode\n");
 
 	/* Have one command line that is parsed and saved in /proc/cmdline */
 	/* boot_command_line has been already set up in early.c */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 0a31110f41f6..d52a94e9f57f 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -357,9 +357,13 @@ void smp_call_online_cpu(void (*func)(void *), void *data)
  */
 void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
+	struct lowcore *lc = pcpu_devices->lowcore;
+
+	if (pcpu_devices[0].address == stap())
+		lc = &S390_lowcore;
+
 	pcpu_delegate(&pcpu_devices[0], func, data,
-		      pcpu_devices->lowcore->panic_stack -
-		      PANIC_FRAME_OFFSET + PAGE_SIZE);
+		      lc->panic_stack - PANIC_FRAME_OFFSET + PAGE_SIZE);
 }
 
 int smp_find_processor_id(u16 address)
@@ -1139,7 +1143,11 @@ static ssize_t __ref rescan_store(struct device *dev,
 {
 	int rc;
 
+	rc = lock_device_hotplug_sysfs();
+	if (rc)
+		return rc;
 	rc = smp_rescan_cpus();
+	unlock_device_hotplug();
 	return rc ? rc : count;
 }
 static DEVICE_ATTR(rescan, 0200, NULL, rescan_store);
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index 7485398d0737..9c04562310b3 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -197,12 +197,17 @@ static inline pte_t pte_mkold(pte_t pte)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 { 
-	pte_clear_bits(pte, _PAGE_RW);
+	if (likely(pte_get_bits(pte, _PAGE_RW)))
+		pte_clear_bits(pte, _PAGE_RW);
+	else
+		return pte;
 	return(pte_mknewprot(pte)); 
 }
 
 static inline pte_t pte_mkread(pte_t pte)
 { 
+	if (unlikely(pte_get_bits(pte, _PAGE_USER)))
+		return pte;
 	pte_set_bits(pte, _PAGE_USER);
 	return(pte_mknewprot(pte)); 
 }
@@ -221,6 +226,8 @@ static inline pte_t pte_mkyoung(pte_t pte)
 
 static inline pte_t pte_mkwrite(pte_t pte)	
 {
+	if (unlikely(pte_get_bits(pte,  _PAGE_RW)))
+		return pte;
 	pte_set_bits(pte, _PAGE_RW);
 	return(pte_mknewprot(pte)); 
 }
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index cda8e14bd72a..89b163351e64 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -34,6 +34,7 @@ KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += -mno-mmx -mno-sse
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index f910d1d449f0..0a5fedf43bdc 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -77,6 +77,7 @@ static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index cadf99923600..1e9f610d36a4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1942,7 +1942,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
  */
 static void free_fake_cpuc(struct cpu_hw_events *cpuc)
 {
-	kfree(cpuc->shared_regs);
+	intel_cpuc_finish(cpuc);
 	kfree(cpuc);
 }
 
@@ -1954,14 +1954,11 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
 	cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL);
 	if (!cpuc)
 		return ERR_PTR(-ENOMEM);
-
-	/* only needed, if we have extra_regs */
-	if (x86_pmu.extra_regs) {
-		cpuc->shared_regs = allocate_shared_regs(cpu);
-		if (!cpuc->shared_regs)
-			goto error;
-	}
 	cpuc->is_fake = 1;
+
+	if (intel_cpuc_prepare(cpuc, cpu))
+		goto error;
+
 	return cpuc;
 error:
 	free_fake_cpuc(cpuc);
@@ -2196,6 +2193,19 @@ void perf_check_microcode(void)
 }
 EXPORT_SYMBOL_GPL(perf_check_microcode);
 
+static int x86_pmu_check_period(struct perf_event *event, u64 value)
+{
+	if (x86_pmu.check_period && x86_pmu.check_period(event, value))
+		return -EINVAL;
+
+	if (value && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, value) > value)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2220,6 +2230,7 @@ static struct pmu pmu = {
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
+	.check_period		= x86_pmu_check_period,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 4f8560774082..098ab775135f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2493,6 +2493,35 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
 }
 
 static struct event_constraint *
+dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx)
+{
+	WARN_ON_ONCE(!cpuc->constraint_list);
+
+	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
+		struct event_constraint *cx;
+
+		/*
+		 * grab pre-allocated constraint entry
+		 */
+		cx = &cpuc->constraint_list[idx];
+
+		/*
+		 * initialize dynamic constraint
+		 * with static constraint
+		 */
+		*cx = *c;
+
+		/*
+		 * mark constraint as dynamic
+		 */
+		cx->flags |= PERF_X86_EVENT_DYNAMIC;
+		c = cx;
+	}
+
+	return c;
+}
+
+static struct event_constraint *
 intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 			   int idx, struct event_constraint *c)
 {
@@ -2522,27 +2551,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * only needed when constraint has not yet
 	 * been cloned (marked dynamic)
 	 */
-	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-		struct event_constraint *cx;
-
-		/*
-		 * grab pre-allocated constraint entry
-		 */
-		cx = &cpuc->constraint_list[idx];
-
-		/*
-		 * initialize dynamic constraint
-		 * with static constraint
-		 */
-		*cx = *c;
-
-		/*
-		 * mark constraint as dynamic, so we
-		 * can free it later on
-		 */
-		cx->flags |= PERF_X86_EVENT_DYNAMIC;
-		c = cx;
-	}
+	c = dyn_constraint(cpuc, c, idx);
 
 	/*
 	 * From here on, the constraint is dynamic.
@@ -3093,7 +3102,7 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-struct intel_shared_regs *allocate_shared_regs(int cpu)
+static struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
 	int i;
@@ -3125,10 +3134,9 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 	return c;
 }
 
-static int intel_pmu_cpu_prepare(int cpu)
-{
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
+int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
+{
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
@@ -3138,7 +3146,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
-		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
+		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
 		if (!cpuc->constraint_list)
 			goto err_shared_regs;
 
@@ -3163,6 +3171,11 @@ err:
 	return -ENOMEM;
 }
 
+static int intel_pmu_cpu_prepare(int cpu)
+{
+	return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu);
+}
+
 static void intel_pmu_cpu_starting(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
@@ -3218,9 +3231,8 @@ static void intel_pmu_cpu_starting(int cpu)
 	}
 }
 
-static void free_excl_cntrs(int cpu)
+static void free_excl_cntrs(struct cpu_hw_events *cpuc)
 {
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	struct intel_excl_cntrs *c;
 
 	c = cpuc->excl_cntrs;
@@ -3235,7 +3247,11 @@ static void free_excl_cntrs(int cpu)
 
 static void intel_pmu_cpu_dying(int cpu)
 {
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	fini_debug_store_on_cpu(cpu);
+}
+
+void intel_cpuc_finish(struct cpu_hw_events *cpuc)
+{
 	struct intel_shared_regs *pc;
 
 	pc = cpuc->shared_regs;
@@ -3245,9 +3261,12 @@ static void intel_pmu_cpu_dying(int cpu)
 		cpuc->shared_regs = NULL;
 	}
 
-	free_excl_cntrs(cpu);
+	free_excl_cntrs(cpuc);
+}
 
-	fini_debug_store_on_cpu(cpu);
+static void intel_pmu_cpu_dead(int cpu)
+{
+	intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu));
 }
 
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3259,6 +3278,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 		intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3324,6 +3348,9 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __initconst const struct x86_pmu intel_pmu = {
@@ -3359,8 +3386,12 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -4117,7 +4148,7 @@ static __init int fixup_ht_bug(void)
 	get_online_cpus();
 
 	for_each_online_cpu(c) {
-		free_excl_cntrs(c);
+		free_excl_cntrs(&per_cpu(cpu_hw_events, c));
 	}
 
 	put_online_cpus();
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 8c2a9fa0caf3..686dd4339370 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1221,6 +1221,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
 	.id_table	= snbep_uncore_pci_ids,
 };
 
+#define NODE_ID_MASK	0x7
+
 /*
  * build pci bus to socket mapping
  */
@@ -1242,7 +1244,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 		err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
 		if (err)
 			break;
-		nodeid = config;
+		nodeid = config & NODE_ID_MASK;
 		/* get the Node ID mapping */
 		err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
 		if (err)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7ace39c51ff7..c42c9d50c8ee 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -626,6 +626,11 @@ struct x86_pmu {
 	 * Intel host/guest support (KVM)
 	 */
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period) (struct perf_event *event, u64 period);
 };
 
 struct x86_perf_task_context {
@@ -833,7 +838,7 @@ static inline int amd_pmu_init(void)
 
 #ifdef CONFIG_CPU_SUP_INTEL
 
-static inline bool intel_pmu_has_bts(struct perf_event *event)
+static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
@@ -844,7 +849,14 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return hw_event == bts_event && hwc->sample_period == 1;
+	return hw_event == bts_event && period == 1;
+}
+
+static inline bool intel_pmu_has_bts(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
@@ -853,7 +865,8 @@ struct event_constraint *
 x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event);
 
-struct intel_shared_regs *allocate_shared_regs(int cpu);
+extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu);
+extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);
 
 int intel_pmu_init(void);
 
@@ -983,9 +996,13 @@ static inline int intel_pmu_init(void)
 	return 0;
 }
 
-static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
+static inline int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
+{
+	return 0;
+}
+
+static inline void intel_cpuc_finish(struct cpu_hw_events *cpuc)
 {
-	return NULL;
 }
 
 static inline int is_ht_workaround_enabled(void)
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index cb26f18d43af..555c002167ad 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -50,7 +50,7 @@ static unsigned long get_dr(int n)
 /*
  * fill in the user structure for a core dump..
  */
-static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
+static void fill_dump(struct pt_regs *regs, struct user32 *dump)
 {
 	u32 fs, gs;
 	memset(dump, 0, sizeof(*dump));
@@ -156,10 +156,12 @@ static int aout_core_dump(struct coredump_params *cprm)
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 	has_dumped = 1;
+
+	fill_dump(cprm->regs, &dump);
+
 	strncpy(dump.u_comm, current->comm, sizeof(current->comm));
 	dump.u_ar0 = offsetof(struct user32, regs);
 	dump.signal = cprm->siginfo->si_signo;
-	dump_thread32(cprm->regs, &dump);
 
 	/*
 	 * If the size of the dump file exceeds the rlimit, then see
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c56c24347f15..98444b77fbe3 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -314,6 +314,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 499d6ed0e376..21d6fa27b4a9 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -97,6 +97,9 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 #define user_insn(insn, output, input...)				\
 ({									\
 	int err;							\
+									\
+	might_fault();							\
+									\
 	asm volatile(ASM_STAC "\n"					\
 		     "1:" #insn "\n\t"					\
 		     "2: " ASM_CLAC "\n"				\
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 22a0ccb17ad0..9a8167b175d5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1324,7 +1324,7 @@ asmlinkage void kvm_spurious_fault(void);
 	"cmpb $0, kvm_rebooting \n\t"	      \
 	"jne 668b \n\t"      		      \
 	__ASM_SIZE(push) " $666b \n\t"	      \
-	"call kvm_spurious_fault \n\t"	      \
+	"jmp kvm_spurious_fault \n\t"	      \
 	".popsection \n\t" \
 	_ASM_EXTABLE(666b, 667b)
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index bbbb9b14ade1..9963e21ac443 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -575,6 +575,12 @@
 
 #define MSR_IA32_TSC_DEADLINE		0x000006E0
 
+
+#define MSR_TSX_FORCE_ABORT		0x0000010F
+
+#define MSR_TFA_RTM_FORCE_ABORT_BIT	0
+#define MSR_TFA_RTM_FORCE_ABORT		BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT)
+
 /* P4/Xeon+ specific */
 #define MSR_IA32_MCG_EAX		0x00000180
 #define MSR_IA32_MCG_EBX		0x00000181
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 9215e0527647..390fdd39e0e2 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -6,7 +6,11 @@
 #endif
 
 #ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
 #define KASAN_STACK_ORDER 1
+#endif
 #else
 #define KASAN_STACK_ORDER 0
 #endif
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index eaba08076030..9e78e963afb8 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -4,6 +4,29 @@
 #include <asm/cpufeature.h>
 #include <asm-generic/qspinlock_types.h>
 #include <asm/paravirt.h>
+#include <asm/rmwcc.h>
+
+#define _Q_PENDING_LOOPS	(1 << 9)
+
+#define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire
+
+static __always_inline bool __queued_RMW_btsl(struct qspinlock *lock)
+{
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter,
+			 "I", _Q_PENDING_OFFSET, "%0", c);
+}
+
+static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
+{
+	u32 val = 0;
+
+	if (__queued_RMW_btsl(lock))
+		val |= _Q_PENDING_VAL;
+
+	val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK;
+
+	return val;
+}
 
 #define	queued_spin_unlock queued_spin_unlock
 /**
@@ -14,7 +37,7 @@
  */
 static inline void native_queued_spin_unlock(struct qspinlock *lock)
 {
-	smp_store_release((u8 *)lock, 0);
+	smp_store_release(&lock->locked, 0);
 }
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 9d55f9b6e167..fc75415ae971 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -21,8 +21,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
  *
  * void __pv_queued_spin_unlock(struct qspinlock *lock)
  * {
- *	struct __qspinlock *l = (void *)lock;
- *	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ *	u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
  *
  *	if (likely(lockval == _Q_LOCKED_VAL))
  *		return;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a8d85a687cf4..2177c7551ff7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -292,8 +292,7 @@ do {									\
 		__put_user_asm(x, ptr, retval, "l", "k", "ir", errret);	\
 		break;							\
 	case 8:								\
-		__put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval,	\
-				   errret);				\
+		__put_user_asm_u64(x, ptr, retval, errret);		\
 		break;							\
 	default:							\
 		__put_user_bad();					\
@@ -427,8 +426,10 @@ do {									\
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
 	int __pu_err;						\
+	__typeof__(*(ptr)) __pu_val;				\
+	__pu_val = x;						\
 	__uaccess_begin();					\
-	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
+	__put_user_size(__pu_val, (ptr), (size), __pu_err, -EFAULT);\
 	__uaccess_end();					\
 	__builtin_expect(__pu_err, 0);				\
 })
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index e652a7cc6186..3f697a9e3f59 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -48,7 +48,8 @@ enum {
 	BIOS_STATUS_SUCCESS		=  0,
 	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
 	BIOS_STATUS_EINVAL		= -EINVAL,
-	BIOS_STATUS_UNAVAIL		= -EBUSY
+	BIOS_STATUS_UNAVAIL		= -EBUSY,
+	BIOS_STATUS_ABORT		= -EINTR,
 };
 
 /* Address map parameters */
@@ -167,4 +168,9 @@ extern long system_serial_number;
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 
+/*
+ * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details
+ */
+extern struct semaphore __efi_uv_runtime_lock;
+
 #endif /* _ASM_X86_UV_BIOS_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4c2648b96c9a..be6d0543e626 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -765,11 +765,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
-	/*
-	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
-	 * all up to and including B1.
-	 */
-	if (c->x86_model <= 1 && c->x86_stepping <= 1)
+
+	/* Fix erratum 1076: CPB feature bit not being set in CPUID. */
+	if (!cpu_has(c, X86_FEATURE_CPB))
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7e6163c9d434..25310d2b8609 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -751,6 +751,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			quirk_no_way_out(i, m, regs);
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			m->bank = i;
 			mce_read_aux(m, i);
 			*msg = tmp;
 			return 1;
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 6d9b45549109..d5b2a08e2b66 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -172,6 +172,8 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 	struct mtrr_gentry gentry;
 	void __user *arg = (void __user *) __arg;
 
+	memset(&gentry, 0, sizeof(gentry));
+
 	switch (cmd) {
 	case MTRRIOC_ADD_ENTRY:
 	case MTRRIOC_SET_ENTRY:
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index ae52ef05d098..769831d9fd11 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -342,10 +342,10 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
 		}
 
+		local_bh_disable();
 		fpu->fpstate_active = 1;
-		preempt_disable();
 		fpu__restore(fpu);
-		preempt_enable();
+		local_bh_enable();
 
 		return err;
 	} else {
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 490f9be3fda2..167ecc270ca5 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 	struct efi_info *current_ei = &boot_params.efi_info;
 	struct efi_info *ei = &params->efi_info;
 
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return 0;
+
 	if (!current_ei->efi_memmap_size)
 		return 0;
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 69a81a7daa24..c8630569e392 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -57,7 +57,7 @@
 #define APIC_BUS_CYCLE_NS 1
 
 /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
-#define apic_debug(fmt, arg...)
+#define apic_debug(fmt, arg...) do {} while (0)
 
 /* 14 is the version for Xeon and Pentium 8.4.8*/
 #define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fa1b0e3c8a06..01eb0451b96d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2862,6 +2862,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
 
+	/*
+	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
+	 * doesn't end up in L1.
+	 */
+	svm->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
+
 	return 0;
 }
 
@@ -3932,25 +3940,14 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
-		int i;
-		struct kvm_vcpu *vcpu;
-		struct kvm *kvm = svm->vcpu.kvm;
 		struct kvm_lapic *apic = svm->vcpu.arch.apic;
 
 		/*
-		 * At this point, we expect that the AVIC HW has already
-		 * set the appropriate IRR bits on the valid target
-		 * vcpus. So, we just need to kick the appropriate vcpu.
+		 * Update ICR high and low, then emulate sending IPI,
+		 * which is handled when writing APIC_ICR.
 		 */
-		kvm_for_each_vcpu(i, vcpu, kvm) {
-			bool m = kvm_apic_match_dest(vcpu, apic,
-						     icrl & KVM_APIC_SHORT_MASK,
-						     GET_APIC_DEST_FIELD(icrh),
-						     icrl & KVM_APIC_DEST_MASK);
-
-			if (m && !avic_vcpu_is_running(vcpu))
-				kvm_vcpu_wake_up(vcpu);
-		}
+		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	}
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -5223,6 +5220,13 @@ static bool svm_cpu_has_accelerated_tpr(void)
 
 static bool svm_has_emulated_msr(int index)
 {
+	switch (index) {
+	case MSR_IA32_MCG_EXT_CTL:
+		return false;
+	default:
+		break;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8888d894bf39..a34fb7284024 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1077,7 +1077,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
 static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
-static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 							  u32 msr, int type);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
@@ -2178,7 +2178,8 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	if (!entry_only)
 		j = find_msr(&m->host, msr);
 
-	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
+	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -4872,7 +4873,7 @@ static void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 							  u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
@@ -4907,7 +4908,7 @@ static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bit
 	}
 }
 
-static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
 							 u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
@@ -4942,7 +4943,7 @@ static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitm
 	}
 }
 
-static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
 			     			      u32 msr, int type, bool value)
 {
 	if (value)
@@ -5964,6 +5965,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 static int handle_triple_fault(struct kvm_vcpu *vcpu)
 {
 	vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+	vcpu->mmio_needed = 0;
 	return 0;
 }
 
@@ -6548,9 +6550,24 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
-		skip_emulated_instruction(vcpu);
 		trace_kvm_fast_mmio(gpa);
-		return 1;
+		/*
+		* Doing kvm_skip_emulated_instruction() depends on undefined
+		* behavior: Intel's manual doesn't mandate
+		* VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
+		* occurs and while on real hardware it was observed to be set,
+		* other hypervisors (namely Hyper-V) don't set it, we end up
+		* advancing IP with some random value. Disable fast mmio when
+		* running nested and keep it for real hardware in hope that
+		* VM_EXIT_INSTRUCTION_LEN will always be set correctly.
+		*/
+		if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) {
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		else
+			return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
+						       NULL, 0) == EMULATE_DONE;
 	}
 
 	ret = handle_mmio_page_fault(vcpu, gpa, true);
@@ -7030,6 +7047,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	/* Addr = segment_base + offset */
 	/* offset = base + [index * scale] + displacement */
 	off = exit_qualification; /* holds the displacement */
+	if (addr_size == 1)
+		off = (gva_t)sign_extend64(off, 31);
+	else if (addr_size == 0)
+		off = (gva_t)sign_extend64(off, 15);
 	if (base_is_valid)
 		off += kvm_register_read(vcpu, base_reg);
 	if (index_is_valid)
@@ -7072,10 +7093,16 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
-		/* Protected mode: #GP(0)/#SS(0) if the memory
-		 * operand is outside the segment limit.
+
+		/*
+		 * Protected mode: #GP(0)/#SS(0) if the memory operand is
+		 * outside the segment limit.  All CPUs that support VMX ignore
+		 * limit checks for flat segments, i.e. segments with base==0,
+		 * limit==0xffffffff and of type expand-up data or code.
 		 */
-		exn = exn || (off + sizeof(u64) > s.limit);
+		if (!(s.base == 0 && s.limit == 0xffffffff &&
+		     ((s.type & 8) || !(s.type & 4))))
+			exn = exn || (off + sizeof(u64) > s.limit);
 	}
 	if (exn) {
 		kvm_queue_exception_e(vcpu,
@@ -7353,6 +7380,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 	if (!vmx->nested.vmxon)
 		return;
 
+	hrtimer_cancel(&vmx->nested.preemption_timer);
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	nested_release_vmcs12(vmx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 27d13b870e07..a29df9ccbfde 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4513,6 +4513,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
 					  exception);
 }
@@ -5707,7 +5714,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		 * handle watchpoints yet, those would be handled in
 		 * the emulate_ops.
 		 */
-		if (kvm_vcpu_check_breakpoint(vcpu, &r))
+		if (!(emulation_type & EMULTYPE_SKIP) &&
+		    kvm_vcpu_check_breakpoint(vcpu, &r))
 			return r;
 
 		ctxt->interruptibility = 0;
@@ -5794,8 +5802,7 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE &&
-		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		if (r == EMULATE_DONE && ctxt->tf)
 			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
@@ -6762,6 +6769,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+			vcpu->mmio_needed = 0;
 			r = 0;
 			goto out;
 		}
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 0c7fe444dcdd..d8d868070e24 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -35,8 +35,8 @@ static inline u16 i8254(void)
 	u16 status, timer;
 
 	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+		     I8254_PORT_CONTROL);
 		status = inb(I8254_PORT_COUNTER0);
 		timer  = inb(I8254_PORT_COUNTER0);
 		timer |= inb(I8254_PORT_COUNTER0) << 8;
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index 526536c81ddc..ca1e8e6dccc8 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -50,8 +50,8 @@ static void __init cnb20le_res(u8 bus, u8 slot, u8 func)
 	word1 = read_pci_config_16(bus, slot, func, 0xc0);
 	word2 = read_pci_config_16(bus, slot, func, 0xc2);
 	if (word1 != word2) {
-		res.start = (word1 << 16) | 0x0000;
-		res.end   = (word2 << 16) | 0xffff;
+		res.start = ((resource_size_t) word1 << 16) | 0x0000;
+		res.end   = ((resource_size_t) word2 << 16) | 0xffff;
 		res.flags = IORESOURCE_MEM;
 		update_res(info, res.start, res.end, res.flags, 0);
 	}
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 5fdacb322ceb..c3e6be110b7d 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -179,7 +179,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
 			num--;
 		}
 
-		if (efi_x >= si->lfb_width) {
+		if (efi_x + font->width > si->lfb_width) {
 			efi_x = 0;
 			efi_y += font->height;
 		}
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index 4a6a5a26c582..eb33432f2f24 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -29,7 +29,8 @@
 
 struct uv_systab *uv_systab;
 
-s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
+static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
+			u64 a4, u64 a5)
 {
 	struct uv_systab *tab = uv_systab;
 	s64 ret;
@@ -51,6 +52,19 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 
 	return ret;
 }
+
+s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
+{
+	s64 ret;
+
+	if (down_interruptible(&__efi_uv_runtime_lock))
+		return BIOS_STATUS_ABORT;
+
+	ret = __uv_bios_call(which, a1, a2, a3, a4, a5);
+	up(&__efi_uv_runtime_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(uv_bios_call);
 
 s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
@@ -59,10 +73,15 @@ s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 	unsigned long bios_flags;
 	s64 ret;
 
+	if (down_interruptible(&__efi_uv_runtime_lock))
+		return BIOS_STATUS_ABORT;
+
 	local_irq_save(bios_flags);
-	ret = uv_bios_call(which, a1, a2, a3, a4, a5);
+	ret = __uv_bios_call(which, a1, a2, a3, a4, a5);
 	local_irq_restore(bios_flags);
 
+	up(&__efi_uv_runtime_lock);
+
 	return ret;
 }
 
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 14e3ca353ac8..5035b86a2e49 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -34,6 +34,7 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set
 # CONFIG_PCI is not set
+CONFIG_VECTORS_OFFSET=0x00002000
 CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0"
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 27c8e07ace43..29f445b410b3 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -281,12 +281,13 @@ should_never_return:
 
 	movi	a2, cpu_start_ccount
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	movi	a3, 0
 	s32i	a3, a2, 0
-	memw
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	wsr	a3, ccount
@@ -323,11 +324,13 @@ ENTRY(cpu_restart)
 	rsr	a0, prid
 	neg	a2, a0
 	movi	a3, cpu_start_id
+	memw
 	s32i	a2, a3, 0
 #if XCHAL_DCACHE_IS_WRITEBACK
 	dhwbi	a3, 0
 #endif
 1:
+	memw
 	l32i	a2, a3, 0
 	dhi	a3, 0
 	bne	a2, a0, 1b
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index fc4ad21a5ed4..44805673a250 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -80,7 +80,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned i;
 
-	for (i = 0; i < max_cpus; ++i)
+	for_each_possible_cpu(i)
 		set_cpu_present(i, true);
 }
 
@@ -93,6 +93,11 @@ void __init smp_init_cpus(void)
 	pr_info("%s: Core Count = %d\n", __func__, ncpus);
 	pr_info("%s: Core Id = %d\n", __func__, core_id);
 
+	if (ncpus > NR_CPUS) {
+		ncpus = NR_CPUS;
+		pr_info("%s: limiting core count by %d\n", __func__, ncpus);
+	}
+
 	for (i = 0; i < ncpus; ++i)
 		set_cpu_possible(i, true);
 }
@@ -192,9 +197,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 	int i;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpu_start_id = cpu;
-	system_flush_invalidate_dcache_range(
-			(unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+	WRITE_ONCE(cpu_start_id, cpu);
+	/* Pairs with the third memw in the cpu_restart */
+	mb();
+	system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id,
+					     sizeof(cpu_start_id));
 #endif
 	smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
 
@@ -203,18 +210,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 			ccount = get_ccount();
 		while (!ccount);
 
-		cpu_start_ccount = ccount;
+		WRITE_ONCE(cpu_start_ccount, ccount);
 
-		while (time_before(jiffies, timeout)) {
+		do {
+			/*
+			 * Pairs with the first two memws in the
+			 * .Lboot_secondary.
+			 */
 			mb();
-			if (!cpu_start_ccount)
-				break;
-		}
+			ccount = READ_ONCE(cpu_start_ccount);
+		} while (ccount && time_before(jiffies, timeout));
 
-		if (cpu_start_ccount) {
+		if (ccount) {
 			smp_call_function_single(0, mx_cpu_stop,
-					(void *)cpu, 1);
-			cpu_start_ccount = 0;
+						 (void *)cpu, 1);
+			WRITE_ONCE(cpu_start_ccount, 0);
 			return -EIO;
 		}
 	}
@@ -234,6 +244,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
 			__func__, cpu, idle, start_info.stack);
 
+	init_completion(&cpu_running);
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
 		wait_for_completion_timeout(&cpu_running,
@@ -295,8 +306,10 @@ void __cpu_die(unsigned int cpu)
 	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
 	while (time_before(jiffies, timeout)) {
 		system_invalidate_dcache_range((unsigned long)&cpu_start_id,
-				sizeof(cpu_start_id));
-		if (cpu_start_id == -cpu) {
+					       sizeof(cpu_start_id));
+		/* Pairs with the second memw in the cpu_restart */
+		mb();
+		if (READ_ONCE(cpu_start_id) == -cpu) {
 			platform_cpu_kill(cpu);
 			return;
 		}
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index be81e69b25bc..2251a6e0973a 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -89,7 +89,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt)
 		container_of(evt, struct ccount_timer, evt);
 
 	if (timer->irq_enabled) {
-		disable_irq(evt->irq);
+		disable_irq_nosync(evt->irq);
 		timer->irq_enabled = 0;
 	}
 	return 0;