Merge branch 'core/urgent' into sched/core

Merge in asm goto fix, to be able to apply the asm/rmwcc.h fix.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index a37a50f..db50b62 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -296,10 +296,15 @@
 # Convert bzImage to zImage
 bzImage: zImage
 
-zImage Image xipImage bootpImage uImage: vmlinux
+BOOT_TARGETS	= zImage Image xipImage bootpImage uImage
+INSTALL_TARGETS	= zinstall uinstall install
+
+PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
+
+$(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-zinstall uinstall install: vmlinux
+$(INSTALL_TARGETS):
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
 %.dtb: | scripts
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 84aa2ca..ec2f806 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -95,24 +95,24 @@
 	@test "$(INITRD)" != "" || \
 	(echo You must specify INITRD; exit -1)
 
-install: $(obj)/Image
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+install:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
-zinstall: $(obj)/zImage
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+zinstall:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
-uinstall: $(obj)/uImage
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+uinstall:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/uImage System.map "$(INSTALL_PATH)"
 
 zi:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
 i:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
 subdir-	    := bootp compressed dts
diff --git a/arch/arm/boot/install.sh b/arch/arm/boot/install.sh
index 06ea7d4..2a45092 100644
--- a/arch/arm/boot/install.sh
+++ b/arch/arm/boot/install.sh
@@ -20,6 +20,20 @@
 #   $4 - default install path (blank if root directory)
 #
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
 if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c..863c892 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 JUMP_LABEL_NOP "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77e..e194f95 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\tnop\n\t"
+	asm_volatile_goto("1:\tnop\n\t"
 		"nop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c4..f016bb6 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 57d286a..c7cb8c2 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -495,14 +495,15 @@
 void do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct thread_info *curtp, *irqtp;
+	struct thread_info *curtp, *irqtp, *sirqtp;
 
 	/* Switch to the irq stack to handle this */
 	curtp = current_thread_info();
 	irqtp = hardirq_ctx[raw_smp_processor_id()];
+	sirqtp = softirq_ctx[raw_smp_processor_id()];
 
 	/* Already there ? */
-	if (unlikely(curtp == irqtp)) {
+	if (unlikely(curtp == irqtp || curtp == sirqtp)) {
 		__do_irq(regs);
 		set_irq_regs(old_regs);
 		return;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 294b7af..c71103b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1066,7 +1066,7 @@
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
 	ld	r7, HSTATE_DSCR(r13)
-	std	r8, VCPU_DSCR(r7)
+	std	r8, VCPU_DSCR(r9)
 	mtspr	SPRN_DSCR, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 1c6a9d72..c65593a 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -332,6 +332,13 @@
 	unsigned long hva;
 	int pfnmap = 0;
 	int tsize = BOOK3E_PAGESZ_4K;
+	int ret = 0;
+	unsigned long mmu_seq;
+	struct kvm *kvm = vcpu_e500->vcpu.kvm;
+
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
 
 	/*
 	 * Translate guest physical to true physical, acquiring
@@ -449,6 +456,12 @@
 		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
 	}
 
+	spin_lock(&kvm->mmu_lock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -457,10 +470,13 @@
 	/* Clear i-cache for new pages */
 	kvmppc_mmu_flush_icache(pfn);
 
+out:
+	spin_unlock(&kvm->mmu_lock);
+
 	/* Drop refcount on page, so that mmu notifiers can clear it */
 	kvm_release_pfn_clean(pfn);
 
-	return 0;
+	return ret;
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190..346b1c8 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("0:	brcl 0,0\n"
+	asm_volatile_goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
 		ASM_ALIGN "\n"
 		ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index c84f33d..7dd2172 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -40,28 +40,26 @@
 }
 
 /*
- * Copy up to one page to vmalloc or real memory
+ * Copy real to virtual or real memory
  */
-static ssize_t copy_page_real(void *buf, void *src, size_t csize)
+static int copy_from_realmem(void *dest, void *src, size_t count)
 {
-	size_t size;
+	unsigned long size;
+	int rc;
 
-	if (is_vmalloc_addr(buf)) {
-		BUG_ON(csize >= PAGE_SIZE);
-		/* If buf is not page aligned, copy first part */
-		size = min(roundup(__pa(buf), PAGE_SIZE) - __pa(buf), csize);
-		if (size) {
-			if (memcpy_real(load_real_addr(buf), src, size))
-				return -EFAULT;
-			buf += size;
-			src += size;
-		}
-		/* Copy second part */
-		size = csize - size;
-		return (size) ? memcpy_real(load_real_addr(buf), src, size) : 0;
-	} else {
-		return memcpy_real(buf, src, csize);
-	}
+	if (!count)
+		return 0;
+	if (!is_vmalloc_or_module_addr(dest))
+		return memcpy_real(dest, src, count);
+	do {
+		size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
+		if (memcpy_real(load_real_addr(dest), src, size))
+			return -EFAULT;
+		count -= size;
+		dest += size;
+		src += size;
+	} while (count);
+	return 0;
 }
 
 /*
@@ -114,7 +112,7 @@
 		rc = copy_to_user_real((void __force __user *) buf,
 				       (void *) src, csize);
 	else
-		rc = copy_page_real(buf, (void *) src, csize);
+		rc = copy_from_realmem(buf, (void *) src, csize);
 	return (rc == 0) ? rc : csize;
 }
 
@@ -210,7 +208,7 @@
 	if (OLDMEM_BASE) {
 		if ((unsigned long) src < OLDMEM_SIZE) {
 			copied = min(count, OLDMEM_SIZE - (unsigned long) src);
-			rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
+			rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
 			if (rc)
 				return rc;
 		}
@@ -223,7 +221,7 @@
 				return rc;
 		}
 	}
-	return memcpy_real(dest + copied, src + copied, count - copied);
+	return copy_from_realmem(dest + copied, src + copied, count - copied);
 }
 
 /*
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index cc30d1f..0dc2b6d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -266,6 +266,7 @@
 	tm	__TI_flags+3(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lm	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	l	%r10,__TI_sysc_table(%r12)	# 31 bit system call table
 	xr	%r8,%r8			# svc 0 returns -ENOSYS
 	clc	__PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
 	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 2b2188b..e5b43c9 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -297,6 +297,7 @@
 	tm	__TI_flags+7(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	lghi	%r8,0			# svc 0 returns -ENOSYS
 	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 0ce9fb2..d86e64e 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -67,6 +67,11 @@
 	case 0xac:	/* stnsm */
 	case 0xad:	/* stosm */
 		return -EINVAL;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x00: /* exrl   */
+			return -EINVAL;
+		}
 	}
 	switch (insn[0]) {
 	case 0x0101:	/* pr	 */
@@ -180,7 +185,6 @@
 		break;
 	case 0xc6:
 		switch (insn[0] & 0x0f) {
-		case 0x00: /* exrl   */
 		case 0x02: /* pfdrl  */
 		case 0x04: /* cghrl  */
 		case 0x05: /* chrl   */
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16..ec2e2e2 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-		asm goto("1:\n\t"
+		asm_volatile_goto("1:\n\t"
 			 "nop\n\t"
 			 "nop\n\t"
 			 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index d385eaa..7097984 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -166,7 +166,7 @@
  *
  * Atomically sets @v to @i and returns old @v
  */
-static inline u64 atomic64_xchg(atomic64_t *v, u64 n)
+static inline long long atomic64_xchg(atomic64_t *v, long long n)
 {
 	return xchg64(&v->counter, n);
 }
@@ -180,7 +180,8 @@
  * Atomically checks if @v holds @o and replaces it with @n if so.
  * Returns the old value at @v.
  */
-static inline u64 atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n)
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long o,
+					long long n)
 {
 	return cmpxchg64(&v->counter, o, n);
 }
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index 0d0395b..1ad4a1f 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -80,7 +80,7 @@
 /* A 64bit atomic type */
 
 typedef struct {
-	u64 __aligned(8) counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val) { (val) }
@@ -91,14 +91,14 @@
  *
  * Atomically reads the value of @v.
  */
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
 	/*
 	 * Requires an atomic op to read both 32-bit parts consistently.
 	 * Casting away const is safe since the atomic support routines
 	 * do not write to memory if the value has not been modified.
 	 */
-	return _atomic64_xchg_add((u64 *)&v->counter, 0);
+	return _atomic64_xchg_add((long long *)&v->counter, 0);
 }
 
 /**
@@ -108,7 +108,7 @@
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
 {
 	_atomic64_xchg_add(&v->counter, i);
 }
@@ -120,7 +120,7 @@
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
 	smp_mb();  /* barrier for proper semantics */
 	return _atomic64_xchg_add(&v->counter, i) + i;
@@ -135,7 +135,8 @@
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns non-zero if @v was not @u, and zero otherwise.
  */
-static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline long long atomic64_add_unless(atomic64_t *v, long long a,
+					long long u)
 {
 	smp_mb();  /* barrier for proper semantics */
 	return _atomic64_xchg_add_unless(&v->counter, a, u) != u;
@@ -151,7 +152,7 @@
  * atomic64_set() can't be just a raw store, since it would be lost if it
  * fell between the load and store of one of the other atomic ops.
  */
-static inline void atomic64_set(atomic64_t *v, u64 n)
+static inline void atomic64_set(atomic64_t *v, long long n)
 {
 	_atomic64_xchg(&v->counter, n);
 }
@@ -236,11 +237,13 @@
 extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
-extern u64 __atomic64_cmpxchg(volatile u64 *p, int *lock, u64 o, u64 n);
-extern u64 __atomic64_xchg(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add_unless(volatile u64 *p,
-				      int *lock, u64 o, u64 n);
+extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
+					long long o, long long n);
+extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
+					long long n);
+extern long long __atomic64_xchg_add_unless(volatile long long *p,
+					int *lock, long long o, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h
index 4001d5e..0ccda3c 100644
--- a/arch/tile/include/asm/cmpxchg.h
+++ b/arch/tile/include/asm/cmpxchg.h
@@ -35,10 +35,10 @@
 int _atomic_xchg_add(int *v, int i);
 int _atomic_xchg_add_unless(int *v, int a, int u);
 int _atomic_cmpxchg(int *ptr, int o, int n);
-u64 _atomic64_xchg(u64 *v, u64 n);
-u64 _atomic64_xchg_add(u64 *v, u64 i);
-u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u);
-u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
+long long _atomic64_xchg(long long *v, long long n);
+long long _atomic64_xchg_add(long long *v, long long i);
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u);
+long long _atomic64_cmpxchg(long long *v, long long o, long long n);
 
 #define xchg(ptr, n)							\
 	({								\
@@ -53,7 +53,8 @@
 		if (sizeof(*(ptr)) != 4)				\
 			__cmpxchg_called_with_bad_pointer();		\
 		smp_mb();						\
-		(typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o, (int)n); \
+		(typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o,	\
+						(int)n);		\
 	})
 
 #define xchg64(ptr, n)							\
@@ -61,7 +62,8 @@
 		if (sizeof(*(ptr)) != 8)				\
 			__xchg_called_with_bad_pointer();		\
 		smp_mb();						\
-		(typeof(*(ptr)))_atomic64_xchg((u64 *)(ptr), (u64)(n));	\
+		(typeof(*(ptr)))_atomic64_xchg((long long *)(ptr),	\
+						(long long)(n));	\
 	})
 
 #define cmpxchg64(ptr, o, n)						\
@@ -69,7 +71,8 @@
 		if (sizeof(*(ptr)) != 8)				\
 			__cmpxchg_called_with_bad_pointer();		\
 		smp_mb();						\
-		(typeof(*(ptr)))_atomic64_cmpxchg((u64 *)ptr, (u64)o, (u64)n); \
+		(typeof(*(ptr)))_atomic64_cmpxchg((long long *)ptr,	\
+					(long long)o, (long long)n);	\
 	})
 
 #else
@@ -81,10 +84,11 @@
 		switch (sizeof(*(ptr))) {				\
 		case 4:							\
 			__x = (typeof(__x))(unsigned long)		\
-				__insn_exch4((ptr), (u32)(unsigned long)(n)); \
+				__insn_exch4((ptr),			\
+					(u32)(unsigned long)(n));	\
 			break;						\
 		case 8:							\
-			__x = (typeof(__x))			\
+			__x = (typeof(__x))				\
 				__insn_exch((ptr), (unsigned long)(n));	\
 			break;						\
 		default:						\
@@ -103,10 +107,12 @@
 		switch (sizeof(*(ptr))) {				\
 		case 4:							\
 			__x = (typeof(__x))(unsigned long)		\
-				__insn_cmpexch4((ptr), (u32)(unsigned long)(n)); \
+				__insn_cmpexch4((ptr),			\
+					(u32)(unsigned long)(n));	\
 			break;						\
 		case 8:							\
-			__x = (typeof(__x))__insn_cmpexch((ptr), (u64)(n)); \
+			__x = (typeof(__x))__insn_cmpexch((ptr),	\
+						(long long)(n));	\
 			break;						\
 		default:						\
 			__cmpxchg_called_with_bad_pointer();		\
diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h
index 63294f5..4f7ae39 100644
--- a/arch/tile/include/asm/percpu.h
+++ b/arch/tile/include/asm/percpu.h
@@ -15,9 +15,37 @@
 #ifndef _ASM_TILE_PERCPU_H
 #define _ASM_TILE_PERCPU_H
 
-register unsigned long __my_cpu_offset __asm__("tp");
-#define __my_cpu_offset __my_cpu_offset
-#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp))
+register unsigned long my_cpu_offset_reg asm("tp");
+
+#ifdef CONFIG_PREEMPT
+/*
+ * For full preemption, we can't just use the register variable
+ * directly, since we need barrier() to hazard against it, causing the
+ * compiler to reload anything computed from a previous "tp" value.
+ * But we also don't want to use volatile asm, since we'd like the
+ * compiler to be able to cache the value across multiple percpu reads.
+ * So we use a fake stack read as a hazard against barrier().
+ * The 'U' constraint is like 'm' but disallows postincrement.
+ */
+static inline unsigned long __my_cpu_offset(void)
+{
+	unsigned long tp;
+	register unsigned long *sp asm("sp");
+	asm("move %0, tp" : "=r" (tp) : "U" (*sp));
+	return tp;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+/*
+ * We don't need to hazard against barrier() since "tp" doesn't ever
+ * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
+ * changes at function call points, at which we are already re-reading
+ * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
+ */
+#define __my_cpu_offset my_cpu_offset_reg
+#endif
+
+#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index df27a1f..531f4c3 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -66,7 +66,7 @@
 		0,
 		"udn",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_UDN].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_UDN].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_UDN].lock),
 		NULL
 	},
 #ifndef __tilepro__
@@ -77,7 +77,7 @@
 		1,  /* disabled pending hypervisor support */
 		"idn",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_IDN].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IDN].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IDN].lock),
 		NULL
 	},
 	{  /* access to user-space IPI */
@@ -87,7 +87,7 @@
 		0,
 		"ipi",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_IPI].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IPI].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IPI].lock),
 		NULL
 	},
 #endif
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index 088d5c1..2cbe6d5 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -815,6 +815,9 @@
 	}
 	bzt     r28, 1f
 	bnz     r29, 1f
+	/* Disable interrupts explicitly for preemption. */
+	IRQ_DISABLE(r20,r21)
+	TRACE_IRQS_OFF
 	jal     preempt_schedule_irq
 	FEEDBACK_REENTER(interrupt_return)
 1:
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index ec755d3..b8fc497 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -841,6 +841,9 @@
 	}
 	beqzt   r28, 1f
 	bnez    r29, 1f
+	/* Disable interrupts explicitly for preemption. */
+	IRQ_DISABLE(r20,r21)
+	TRACE_IRQS_OFF
 	jal     preempt_schedule_irq
 	FEEDBACK_REENTER(interrupt_return)
 1:
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 362284a..c93977a 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -23,6 +23,7 @@
 #include <linux/mmzone.h>
 #include <linux/dcache.h>
 #include <linux/fs.h>
+#include <linux/string.h>
 #include <asm/backtrace.h>
 #include <asm/page.h>
 #include <asm/ucontext.h>
@@ -332,21 +333,18 @@
 	}
 
 	if (vma->vm_file) {
-		char *s;
 		p = d_path(&vma->vm_file->f_path, buf, bufsize);
 		if (IS_ERR(p))
 			p = "?";
-		s = strrchr(p, '/');
-		if (s)
-			p = s+1;
+		name = kbasename(p);
 	} else {
-		p = "anon";
+		name = "anon";
 	}
 
 	/* Generate a string description of the vma info. */
-	namelen = strlen(p);
+	namelen = strlen(name);
 	remaining = (bufsize - 1) - namelen;
-	memmove(buf, p, namelen);
+	memmove(buf, name, namelen);
 	snprintf(buf + namelen, remaining, "[%lx+%lx] ",
 		 vma->vm_start, vma->vm_end - vma->vm_start);
 }
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index 759efa3..c89b211 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -107,19 +107,19 @@
 EXPORT_SYMBOL(_atomic_xor);
 
 
-u64 _atomic64_xchg(u64 *v, u64 n)
+long long _atomic64_xchg(long long *v, long long n)
 {
 	return __atomic64_xchg(v, __atomic_setup(v), n);
 }
 EXPORT_SYMBOL(_atomic64_xchg);
 
-u64 _atomic64_xchg_add(u64 *v, u64 i)
+long long _atomic64_xchg_add(long long *v, long long i)
 {
 	return __atomic64_xchg_add(v, __atomic_setup(v), i);
 }
 EXPORT_SYMBOL(_atomic64_xchg_add);
 
-u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u)
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u)
 {
 	/*
 	 * Note: argument order is switched here since it is easier
@@ -130,7 +130,7 @@
 }
 EXPORT_SYMBOL(_atomic64_xchg_add_unless);
 
-u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n)
+long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 {
 	return __atomic64_cmpxchg(v, __atomic_setup(v), o, n);
 }
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d3f5c63..89270b43 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -374,7 +374,7 @@
 		 * Catch too early usage of this before alternatives
 		 * have run.
 		 */
-		asm goto("1: jmp %l[t_warn]\n"
+		asm_volatile_goto("1: jmp %l[t_warn]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -388,7 +388,7 @@
 
 #endif
 
-		asm goto("1: jmp %l[t_no]\n"
+		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -453,7 +453,7 @@
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-		asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 64507f3..6a2cefb 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:"
+	asm_volatile_goto("1:"
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index e7e6751..07537a4 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -20,7 +20,7 @@
 static inline void __mutex_fastpath_lock(atomic_t *v,
 					 void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   decl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
 			  "   jns %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
@@ -75,7 +75,7 @@
 static inline void __mutex_fastpath_unlock(atomic_t *v,
 					   void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   incl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
 			  "   jg %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 897783b..9d84491 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1888,10 +1888,7 @@
 	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+	if (!sched_clock_stable)
 		return;
 
 	userpg->cap_user_time = 1;
@@ -1899,10 +1896,8 @@
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
-	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = this_cpu_read(cyc2ns_offset);
-	}
+	userpg->cap_user_time_zero = 1;
+	userpg->time_zero = this_cpu_read(cyc2ns_offset);
 }
 
 /*
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3b8e745..2b2fce1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3255,25 +3255,29 @@
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (!test_bit(VCPU_EXREG_PDPTR,
 		      (unsigned long *)&vcpu->arch.regs_dirty))
 		return;
 
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
-		vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
-		vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
-		vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
 	}
 }
 
 static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-		vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-		vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-		vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
 	__set_bit(VCPU_EXREG_PDPTR,
@@ -7777,10 +7781,6 @@
 		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
 		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
 		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_avail);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_dirty);
 	}
 
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 7737b5b..7a744d3 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -640,7 +640,7 @@
  */
 void add_device_randomness(const void *buf, unsigned int size)
 {
-	unsigned long time = get_cycles() ^ jiffies;
+	unsigned long time = random_get_entropy() ^ jiffies;
 
 	mix_pool_bytes(&input_pool, buf, size, NULL);
 	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
@@ -677,7 +677,7 @@
 		goto out;
 
 	sample.jiffies = jiffies;
-	sample.cycles = get_cycles();
+	sample.cycles = random_get_entropy();
 	sample.num = num;
 	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
 
@@ -744,7 +744,7 @@
 	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
 	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
-	__u32			input[4], cycles = get_cycles();
+	__u32			input[4], cycles = random_get_entropy();
 
 	input[0] = cycles ^ jiffies;
 	input[1] = irq;
@@ -1459,12 +1459,11 @@
 
 static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
 
-static int __init random_int_secret_init(void)
+int random_int_secret_init(void)
 {
 	get_random_bytes(random_int_secret, sizeof(random_int_secret));
 	return 0;
 }
-late_initcall(random_int_secret_init);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
@@ -1483,7 +1482,7 @@
 
 	hash = get_cpu_var(get_random_int_hash);
 
-	hash[0] += current->pid + jiffies + get_cycles();
+	hash[0] += current->pid + jiffies + random_get_entropy();
 	md5_transform(hash, random_int_secret);
 	ret = hash[0];
 	put_cpu_var(get_random_int_hash);
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 71b70e3..c91d547 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -241,6 +241,7 @@
 	  - Sharkoon Drakonia / Perixx MX-2000 gaming mice
 	  - Tracer Sniper TRM-503 / NOVA Gaming Slider X200 /
 	    Zalman ZM-GM1
+	  - SHARKOON DarkGlider Gaming mouse
 
 config HOLTEK_FF
 	bool "Holtek On Line Grip force feedback support"
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index b8470b1..5a8c011 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1715,6 +1715,7 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_580) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_JESS2, USB_DEVICE_ID_JESS2_COLOR_RUMBLE_PAD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ION, USB_DEVICE_ID_ICADE) },
diff --git a/drivers/hid/hid-holtek-mouse.c b/drivers/hid/hid-holtek-mouse.c
index 7e6db3c..e696566 100644
--- a/drivers/hid/hid-holtek-mouse.c
+++ b/drivers/hid/hid-holtek-mouse.c
@@ -27,6 +27,7 @@
  * - USB ID 04d9:a067, sold as Sharkoon Drakonia and Perixx MX-2000
  * - USB ID 04d9:a04a, sold as Tracer Sniper TRM-503, NOVA Gaming Slider X200
  *   and Zalman ZM-GM1
+ * - USB ID 04d9:a081, sold as SHARKOON DarkGlider Gaming mouse
  */
 
 static __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
@@ -46,6 +47,7 @@
 			}
 			break;
 		case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A:
+		case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081:
 			if (*rsize >= 113 && rdesc[106] == 0xff && rdesc[107] == 0x7f
 					&& rdesc[111] == 0xff && rdesc[112] == 0x7f) {
 				hid_info(hdev, "Fixing up report descriptor\n");
@@ -63,6 +65,8 @@
 			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT,
 			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT,
+			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, holtek_mouse_devices);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index e60e8d5..9cbc7ab 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -450,6 +450,7 @@
 #define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD	0xa055
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067	0xa067
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A	0xa04a
+#define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081	0xa081
 
 #define USB_VENDOR_ID_IMATION		0x0718
 #define USB_DEVICE_ID_DISC_STAKKA	0xd000
diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c
index 602c188..6101816 100644
--- a/drivers/hid/hid-roccat-kone.c
+++ b/drivers/hid/hid-roccat-kone.c
@@ -382,7 +382,7 @@
 }
 #define PROFILE_ATTR(number)					\
 static struct bin_attribute bin_attr_profile##number = {	\
-	.attr = { .name = "profile##number", .mode = 0660 },	\
+	.attr = { .name = "profile" #number, .mode = 0660 },	\
 	.size = sizeof(struct kone_profile),			\
 	.read = kone_sysfs_read_profilex,			\
 	.write = kone_sysfs_write_profilex,			\
diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c
index 5ddf605..5e99fcd 100644
--- a/drivers/hid/hid-roccat-koneplus.c
+++ b/drivers/hid/hid-roccat-koneplus.c
@@ -229,13 +229,13 @@
 
 #define PROFILE_ATTR(number)						\
 static struct bin_attribute bin_attr_profile##number##_settings = {	\
-	.attr = { .name = "profile##number##_settings", .mode = 0440 },	\
+	.attr = { .name = "profile" #number "_settings", .mode = 0440 },	\
 	.size = KONEPLUS_SIZE_PROFILE_SETTINGS,				\
 	.read = koneplus_sysfs_read_profilex_settings,			\
 	.private = &profile_numbers[number-1],				\
 };									\
 static struct bin_attribute bin_attr_profile##number##_buttons = {	\
-	.attr = { .name = "profile##number##_buttons", .mode = 0440 },	\
+	.attr = { .name = "profile" #number "_buttons", .mode = 0440 },	\
 	.size = KONEPLUS_SIZE_PROFILE_BUTTONS,				\
 	.read = koneplus_sysfs_read_profilex_buttons,			\
 	.private = &profile_numbers[number-1],				\
diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c
index 515bc03..0c8e1ef 100644
--- a/drivers/hid/hid-roccat-kovaplus.c
+++ b/drivers/hid/hid-roccat-kovaplus.c
@@ -257,13 +257,13 @@
 
 #define PROFILE_ATTR(number)						\
 static struct bin_attribute bin_attr_profile##number##_settings = {	\
-	.attr = { .name = "profile##number##_settings", .mode = 0440 },	\
+	.attr = { .name = "profile" #number "_settings", .mode = 0440 },	\
 	.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,				\
 	.read = kovaplus_sysfs_read_profilex_settings,			\
 	.private = &profile_numbers[number-1],				\
 };									\
 static struct bin_attribute bin_attr_profile##number##_buttons = {	\
-	.attr = { .name = "profile##number##_buttons", .mode = 0440 },	\
+	.attr = { .name = "profile" #number "_buttons", .mode = 0440 },	\
 	.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,				\
 	.read = kovaplus_sysfs_read_profilex_buttons,			\
 	.private = &profile_numbers[number-1],				\
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index 5a6dbbe..1a07e07 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -225,13 +225,13 @@
 
 #define PROFILE_ATTR(number)						\
 static struct bin_attribute bin_attr_profile##number##_settings = {	\
-	.attr = { .name = "profile##number##_settings", .mode = 0440 },	\
+	.attr = { .name = "profile" #number "_settings", .mode = 0440 },	\
 	.size = PYRA_SIZE_PROFILE_SETTINGS,				\
 	.read = pyra_sysfs_read_profilex_settings,			\
 	.private = &profile_numbers[number-1],				\
 };									\
 static struct bin_attribute bin_attr_profile##number##_buttons = {	\
-	.attr = { .name = "profile##number##_buttons", .mode = 0440 },	\
+	.attr = { .name = "profile" #number "_buttons", .mode = 0440 },	\
 	.size = PYRA_SIZE_PROFILE_BUTTONS,				\
 	.read = pyra_sysfs_read_profilex_buttons,			\
 	.private = &profile_numbers[number-1],				\
diff --git a/drivers/hid/hid-wiimote-modules.c b/drivers/hid/hid-wiimote-modules.c
index 2e7d644..71adf9e 100644
--- a/drivers/hid/hid-wiimote-modules.c
+++ b/drivers/hid/hid-wiimote-modules.c
@@ -119,12 +119,22 @@
  * the rumble motor, this flag shouldn't be set.
  */
 
+/* used by wiimod_rumble and wiipro_rumble */
+static void wiimod_rumble_worker(struct work_struct *work)
+{
+	struct wiimote_data *wdata = container_of(work, struct wiimote_data,
+						  rumble_worker);
+
+	spin_lock_irq(&wdata->state.lock);
+	wiiproto_req_rumble(wdata, wdata->state.cache_rumble);
+	spin_unlock_irq(&wdata->state.lock);
+}
+
 static int wiimod_rumble_play(struct input_dev *dev, void *data,
 			      struct ff_effect *eff)
 {
 	struct wiimote_data *wdata = input_get_drvdata(dev);
 	__u8 value;
-	unsigned long flags;
 
 	/*
 	 * The wiimote supports only a single rumble motor so if any magnitude
@@ -137,9 +147,10 @@
 	else
 		value = 0;
 
-	spin_lock_irqsave(&wdata->state.lock, flags);
-	wiiproto_req_rumble(wdata, value);
-	spin_unlock_irqrestore(&wdata->state.lock, flags);
+	/* Locking state.lock here might deadlock with input_event() calls.
+	 * schedule_work acts as barrier. Merging multiple changes is fine. */
+	wdata->state.cache_rumble = value;
+	schedule_work(&wdata->rumble_worker);
 
 	return 0;
 }
@@ -147,6 +158,8 @@
 static int wiimod_rumble_probe(const struct wiimod_ops *ops,
 			       struct wiimote_data *wdata)
 {
+	INIT_WORK(&wdata->rumble_worker, wiimod_rumble_worker);
+
 	set_bit(FF_RUMBLE, wdata->input->ffbit);
 	if (input_ff_create_memless(wdata->input, NULL, wiimod_rumble_play))
 		return -ENOMEM;
@@ -159,6 +172,8 @@
 {
 	unsigned long flags;
 
+	cancel_work_sync(&wdata->rumble_worker);
+
 	spin_lock_irqsave(&wdata->state.lock, flags);
 	wiiproto_req_rumble(wdata, 0);
 	spin_unlock_irqrestore(&wdata->state.lock, flags);
@@ -1731,7 +1746,6 @@
 {
 	struct wiimote_data *wdata = input_get_drvdata(dev);
 	__u8 value;
-	unsigned long flags;
 
 	/*
 	 * The wiimote supports only a single rumble motor so if any magnitude
@@ -1744,9 +1758,10 @@
 	else
 		value = 0;
 
-	spin_lock_irqsave(&wdata->state.lock, flags);
-	wiiproto_req_rumble(wdata, value);
-	spin_unlock_irqrestore(&wdata->state.lock, flags);
+	/* Locking state.lock here might deadlock with input_event() calls.
+	 * schedule_work acts as barrier. Merging multiple changes is fine. */
+	wdata->state.cache_rumble = value;
+	schedule_work(&wdata->rumble_worker);
 
 	return 0;
 }
@@ -1756,6 +1771,8 @@
 {
 	int ret, i;
 
+	INIT_WORK(&wdata->rumble_worker, wiimod_rumble_worker);
+
 	wdata->extension.input = input_allocate_device();
 	if (!wdata->extension.input)
 		return -ENOMEM;
@@ -1817,12 +1834,13 @@
 	if (!wdata->extension.input)
 		return;
 
+	input_unregister_device(wdata->extension.input);
+	wdata->extension.input = NULL;
+	cancel_work_sync(&wdata->rumble_worker);
+
 	spin_lock_irqsave(&wdata->state.lock, flags);
 	wiiproto_req_rumble(wdata, 0);
 	spin_unlock_irqrestore(&wdata->state.lock, flags);
-
-	input_unregister_device(wdata->extension.input);
-	wdata->extension.input = NULL;
 }
 
 static const struct wiimod_ops wiimod_pro = {
diff --git a/drivers/hid/hid-wiimote.h b/drivers/hid/hid-wiimote.h
index f1474f3..75db0c4 100644
--- a/drivers/hid/hid-wiimote.h
+++ b/drivers/hid/hid-wiimote.h
@@ -133,13 +133,15 @@
 	__u8 *cmd_read_buf;
 	__u8 cmd_read_size;
 
-	/* calibration data */
+	/* calibration/cache data */
 	__u16 calib_bboard[4][3];
+	__u8 cache_rumble;
 };
 
 struct wiimote_data {
 	struct hid_device *hdev;
 	struct input_dev *input;
+	struct work_struct rumble_worker;
 	struct led_classdev *leds[4];
 	struct input_dev *accel;
 	struct input_dev *ir;
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 8918dd1..6a6dd5c 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -308,18 +308,25 @@
 static void drop_ref(struct hidraw *hidraw, int exists_bit)
 {
 	if (exists_bit) {
-		hid_hw_close(hidraw->hid);
 		hidraw->exist = 0;
-		if (hidraw->open)
+		if (hidraw->open) {
+			hid_hw_close(hidraw->hid);
 			wake_up_interruptible(&hidraw->wait);
+		}
 	} else {
 		--hidraw->open;
 	}
-
-	if (!hidraw->open && !hidraw->exist) {
-		device_destroy(hidraw_class, MKDEV(hidraw_major, hidraw->minor));
-		hidraw_table[hidraw->minor] = NULL;
-		kfree(hidraw);
+	if (!hidraw->open) {
+		if (!hidraw->exist) {
+			device_destroy(hidraw_class,
+					MKDEV(hidraw_major, hidraw->minor));
+			hidraw_table[hidraw->minor] = NULL;
+			kfree(hidraw);
+		} else {
+			/* close device for last reader */
+			hid_hw_power(hidraw->hid, PM_HINT_NORMAL);
+			hid_hw_close(hidraw->hid);
+		}
 	}
 }
 
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 5bf2fb7..93b00d7 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -615,7 +615,7 @@
 
 static struct miscdevice uhid_misc = {
 	.fops		= &uhid_fops,
-	.minor		= MISC_DYNAMIC_MINOR,
+	.minor		= UHID_MINOR,
 	.name		= UHID_NAME,
 };
 
@@ -634,4 +634,5 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("David Herrmann <dh.herrmann@gmail.com>");
 MODULE_DESCRIPTION("User-space I/O driver support for HID subsystem");
+MODULE_ALIAS_MISCDEV(UHID_MINOR);
 MODULE_ALIAS("devname:" UHID_NAME);
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 98814d1..3288f13 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -230,6 +230,7 @@
 
 static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 {
+	u8 status, data = 0;
 	int i;
 
 	if (send_command(cmd) || send_argument(key)) {
@@ -237,6 +238,7 @@
 		return -EIO;
 	}
 
+	/* This has no effect on newer (2012) SMCs */
 	if (send_byte(len, APPLESMC_DATA_PORT)) {
 		pr_warn("%.4s: read len fail\n", key);
 		return -EIO;
@@ -250,6 +252,17 @@
 		buffer[i] = inb(APPLESMC_DATA_PORT);
 	}
 
+	/* Read the data port until bit0 is cleared */
+	for (i = 0; i < 16; i++) {
+		udelay(APPLESMC_MIN_WAIT);
+		status = inb(APPLESMC_CMD_PORT);
+		if (!(status & 0x01))
+			break;
+		data = inb(APPLESMC_DATA_PORT);
+	}
+	if (i)
+		pr_warn("flushed %d bytes, last value is: %d\n", i, data);
+
 	return 0;
 }
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 71eb233..b6a74bc 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -996,6 +996,7 @@
 		closure_bio_submit(bio, cl, s->d);
 	} else {
 		bch_writeback_add(dc);
+		s->op.cache_bio = bio;
 
 		if (bio->bi_rw & REQ_FLUSH) {
 			/* Also need to send a flush to the backing device */
@@ -1008,8 +1009,6 @@
 			flush->bi_private = cl;
 
 			closure_bio_submit(flush, cl, s->d);
-		} else {
-			s->op.cache_bio = bio;
 		}
 	}
 out:
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 26b14f9..6bc9618 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -168,12 +168,25 @@
  */
 static inline int set_4byte(struct m25p *flash, u32 jedec_id, int enable)
 {
+	int status;
+	bool need_wren = false;
+
 	switch (JEDEC_MFR(jedec_id)) {
-	case CFI_MFR_MACRONIX:
 	case CFI_MFR_ST: /* Micron, actually */
+		/* Some Micron need WREN command; all will accept it */
+		need_wren = true;
+	case CFI_MFR_MACRONIX:
 	case 0xEF /* winbond */:
+		if (need_wren)
+			write_enable(flash);
+
 		flash->command[0] = enable ? OPCODE_EN4B : OPCODE_EX4B;
-		return spi_write(flash->spi, flash->command, 1);
+		status = spi_write(flash->spi, flash->command, 1);
+
+		if (need_wren)
+			write_disable(flash);
+
+		return status;
 	default:
 		/* Spansion style */
 		flash->command[0] = OPCODE_BRWR;
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 7ed4841..d340b2f 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2869,10 +2869,8 @@
 
 	len = le16_to_cpu(p->ext_param_page_length) * 16;
 	ep = kmalloc(len, GFP_KERNEL);
-	if (!ep) {
-		ret = -ENOMEM;
-		goto ext_out;
-	}
+	if (!ep)
+		return -ENOMEM;
 
 	/* Send our own NAND_CMD_PARAM. */
 	chip->cmdfunc(mtd, NAND_CMD_PARAM, 0, -1);
@@ -2920,7 +2918,7 @@
 	}
 
 	pr_info("ONFI extended param page detected.\n");
-	return 0;
+	ret = 0;
 
 ext_out:
 	kfree(ep);
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 8cd34bf..77df9cb 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -145,9 +145,11 @@
 
 	if (sccb->header.response_code != 0x20)
 		return 0;
-	if (sccb->sclp_send_mask & (EVTYP_MSG_MASK | EVTYP_PMSGCMD_MASK))
-		return 1;
-	return 0;
+	if (!(sccb->sclp_send_mask & (EVTYP_OPCMD_MASK | EVTYP_PMSGCMD_MASK)))
+		return 0;
+	if (!(sccb->sclp_receive_mask & (EVTYP_MSG_MASK | EVTYP_PMSGCMD_MASK)))
+		return 0;
+	return 1;
 }
 
 bool __init sclp_has_vt220(void)
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index a0f47c8..3f4ca4e 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -810,7 +810,7 @@
 	struct winsize ws;
 
 	screen = tty3270_alloc_screen(tp->n_rows, tp->n_cols);
-	if (!screen)
+	if (IS_ERR(screen))
 		return;
 	/* Switch to new output size */
 	spin_lock_bh(&tp->view.lock);
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index fd7cc56..d4ac60b 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1583,7 +1583,7 @@
 	/* Initialize the hardware */
 	ret = clk_prepare_enable(clk);
 	if (ret)
-		goto out_unmap_regs;
+		goto out_free_irq;
 	spi_writel(as, CR, SPI_BIT(SWRST));
 	spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */
 	if (as->caps.has_wdrbt) {
@@ -1614,6 +1614,7 @@
 	spi_writel(as, CR, SPI_BIT(SWRST));
 	spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */
 	clk_disable_unprepare(clk);
+out_free_irq:
 	free_irq(irq, master);
 out_unmap_regs:
 	iounmap(as->regs);
diff --git a/drivers/spi/spi-clps711x.c b/drivers/spi/spi-clps711x.c
index 5655acf..6416798 100644
--- a/drivers/spi/spi-clps711x.c
+++ b/drivers/spi/spi-clps711x.c
@@ -226,7 +226,6 @@
 			       dev_name(&pdev->dev), hw);
 	if (ret) {
 		dev_err(&pdev->dev, "Can't request IRQ\n");
-		clk_put(hw->spi_clk);
 		goto clk_out;
 	}
 
@@ -247,7 +246,6 @@
 			gpio_free(hw->chipselect[i]);
 
 	spi_master_put(master);
-	kfree(master);
 
 	return ret;
 }
@@ -263,7 +261,6 @@
 			gpio_free(hw->chipselect[i]);
 
 	spi_unregister_master(master);
-	kfree(master);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 6cd07d1..4e44575 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -476,15 +476,9 @@
 	master->bus_num = bus_num;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "can't get platform resource\n");
-		ret = -EINVAL;
-		goto out_master_put;
-	}
-
 	dspi->base = devm_ioremap_resource(&pdev->dev, res);
-	if (!dspi->base) {
-		ret = -EINVAL;
+	if (IS_ERR(dspi->base)) {
+		ret = PTR_ERR(dspi->base);
 		goto out_master_put;
 	}
 
diff --git a/drivers/spi/spi-mpc512x-psc.c b/drivers/spi/spi-mpc512x-psc.c
index dbc5e99..6adf4e3 100644
--- a/drivers/spi/spi-mpc512x-psc.c
+++ b/drivers/spi/spi-mpc512x-psc.c
@@ -522,8 +522,10 @@
 	psc_num = master->bus_num;
 	snprintf(clk_name, sizeof(clk_name), "psc%d_mclk", psc_num);
 	clk = devm_clk_get(dev, clk_name);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
 		goto free_irq;
+	}
 	ret = clk_prepare_enable(clk);
 	if (ret)
 		goto free_irq;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 2eb06ee..c1a5067 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -546,8 +546,17 @@
 	if (pm_runtime_suspended(&drv_data->pdev->dev))
 		return IRQ_NONE;
 
-	sccr1_reg = read_SSCR1(reg);
+	/*
+	 * If the device is not yet in RPM suspended state and we get an
+	 * interrupt that is meant for another device, check if status bits
+	 * are all set to one. That means that the device is already
+	 * powered off.
+	 */
 	status = read_SSSR(reg);
+	if (status == ~0)
+		return IRQ_NONE;
+
+	sccr1_reg = read_SSCR1(reg);
 
 	/* Ignore possible writes if we don't need to write */
 	if (!(sccr1_reg & SSCR1_TIE))
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 512b8893..a80376d 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -1428,6 +1428,8 @@
 	       S3C64XX_SPI_INT_TX_OVERRUN_EN | S3C64XX_SPI_INT_TX_UNDERRUN_EN,
 	       sdd->regs + S3C64XX_SPI_INT_EN);
 
+	pm_runtime_enable(&pdev->dev);
+
 	if (spi_register_master(master)) {
 		dev_err(&pdev->dev, "cannot register SPI master\n");
 		ret = -EBUSY;
@@ -1440,8 +1442,6 @@
 					mem_res,
 					sdd->rx_dma.dmach, sdd->tx_dma.dmach);
 
-	pm_runtime_enable(&pdev->dev);
-
 	return 0;
 
 err3:
diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c
index 0b68cb5..e488a90 100644
--- a/drivers/spi/spi-sh-hspi.c
+++ b/drivers/spi/spi-sh-hspi.c
@@ -296,6 +296,8 @@
 		goto error1;
 	}
 
+	pm_runtime_enable(&pdev->dev);
+
 	master->num_chipselect	= 1;
 	master->bus_num		= pdev->id;
 	master->setup		= hspi_setup;
@@ -309,8 +311,6 @@
 		goto error1;
 	}
 
-	pm_runtime_enable(&pdev->dev);
-
 	return 0;
 
  error1:
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 5be5e3d..19f3c3f 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -802,6 +802,12 @@
 		return -ENODEV;
 	}
 
+	/*
+	 * Ignore all auxilary iLO devices with the following PCI ID
+	 */
+	if (dev->subsystem_device == 0x1979)
+		return -ENODEV;
+
 	if (pci_enable_device(dev)) {
 		dev_warn(&dev->dev,
 			"Not possible to enable PCI Device: 0x%x:0x%x.\n",
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 842de22..ded4299 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -65,6 +65,21 @@
 #define __visible __attribute__((externally_visible))
 #endif
 
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#if GCC_VERSION <= 40801
+# define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
+#else
+# define asm_volatile_goto(x...)	do { asm goto(x); } while (0)
+#endif
 
 #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
 #if GCC_VERSION >= 40400
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 09c2300..cb35835 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -45,6 +45,7 @@
 #define MAPPER_CTRL_MINOR	236
 #define LOOP_CTRL_MINOR		237
 #define VHOST_NET_MINOR		238
+#define UHID_MINOR		239
 #define MISC_DYNAMIC_MINOR	255
 
 struct device;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 866e85c..c8ba627 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -294,9 +294,31 @@
  */
 struct perf_event {
 #ifdef CONFIG_PERF_EVENTS
-	struct list_head		group_entry;
+	/*
+	 * entry onto perf_event_context::event_list;
+	 *   modifications require ctx->lock
+	 *   RCU safe iterations.
+	 */
 	struct list_head		event_entry;
+
+	/*
+	 * XXX: group_entry and sibling_list should be mutually exclusive;
+	 * either you're a sibling on a group, or you're the group leader.
+	 * Rework the code to always use the same list element.
+	 *
+	 * Locked for modification by both ctx->mutex and ctx->lock; holding
+	 * either sufficies for read.
+	 */
+	struct list_head		group_entry;
 	struct list_head		sibling_list;
+
+	/*
+	 * We need storage to track the entries in perf_pmu_migrate_context; we
+	 * cannot use the event_entry because of RCU and we want to keep the
+	 * group in tact which avoids us using the other two entries.
+	 */
+	struct list_head		migrate_entry;
+
 	struct hlist_node		hlist_entry;
 	int				nr_siblings;
 	int				group_flags;
diff --git a/include/linux/random.h b/include/linux/random.h
index 3b9377d..6312dd9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -17,6 +17,7 @@
 extern void get_random_bytes(void *buf, int nbytes);
 extern void get_random_bytes_arch(void *buf, int nbytes);
 void generate_random_uuid(unsigned char uuid_out[16]);
+extern int random_int_secret_init(void);
 
 #ifndef MODULE
 extern const struct file_operations random_fops, urandom_fops;
diff --git a/include/linux/timex.h b/include/linux/timex.h
index dd3edd7..9d3f1a5 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -64,6 +64,20 @@
 
 #include <asm/timex.h>
 
+#ifndef random_get_entropy
+/*
+ * The random_get_entropy() function is used by the /dev/random driver
+ * in order to extract entropy via the relative unpredictability of
+ * when an interrupt takes places versus a high speed, fine-grained
+ * timing source or cycle counter.  Since it will be occurred on every
+ * single interrupt, it must have a very low cost/overhead.
+ *
+ * By default we use get_cycles() for this purpose, but individual
+ * architectures may override this in their asm/timex.h header file.
+ */
+#define random_get_entropy()	get_cycles()
+#endif
+
 /*
  * SHIFT_PLL is used as a dampening factor to define how much we
  * adjust the frequency correction for a given offset in PLL mode.
diff --git a/init/main.c b/init/main.c
index 7cc4b78..379090f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -76,6 +76,7 @@
 #include <linux/elevator.h>
 #include <linux/sched_clock.h>
 #include <linux/context_tracking.h>
+#include <linux/random.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -780,6 +781,7 @@
 	do_ctors();
 	usermodehelper_enable();
 	do_initcalls();
+	random_int_secret_init();
 }
 
 static void __init do_pre_smp_initcalls(void)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cb4238e..d49a9d2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7234,15 +7234,15 @@
 		perf_remove_from_context(event);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
-		list_add(&event->event_entry, &events);
+		list_add(&event->migrate_entry, &events);
 	}
 	mutex_unlock(&src_ctx->mutex);
 
 	synchronize_rcu();
 
 	mutex_lock(&dst_ctx->mutex);
-	list_for_each_entry_safe(event, tmp, &events, event_entry) {
-		list_del(&event->event_entry);
+	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+		list_del(&event->migrate_entry);
 		if (event->state >= PERF_EVENT_STATE_OFF)
 			event->state = PERF_EVENT_STATE_INACTIVE;
 		account_event_cpu(event, dst_cpu);
diff --git a/lib/kobject.c b/lib/kobject.c
index 669bf19..084f7b1 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -592,7 +592,7 @@
 {
 	struct kobject *kobj = container_of(kref, struct kobject, kref);
 #ifdef CONFIG_DEBUG_KOBJECT_RELEASE
-	pr_debug("kobject: '%s' (%p): %s, parent %p (delayed)\n",
+	pr_info("kobject: '%s' (%p): %s, parent %p (delayed)\n",
 		 kobject_name(kobj), kobj, __func__, kobj->parent);
 	INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup);
 	schedule_delayed_work(&kobj->release, HZ);
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3a0ff7f..64c043b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -770,6 +770,7 @@
 install-bin: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
+	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f686d5f..5098f14 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -457,6 +457,7 @@
 			perror("failed to prepare workload");
 			return -1;
 		}
+		child_pid = evsel_list->workload.pid;
 	}
 
 	if (group)
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index d5a8dd4..f793057 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -219,7 +219,7 @@
 
 int main(void)
 {
-	printf(\"error message: %s\n\", audit_errno_to_name(0));
+	printf(\"error message: %s\", audit_errno_to_name(0));
 	return audit_open();
 }
 endef
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index e23bde1..7defd77 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -426,7 +426,7 @@
  * @die_mem: a buffer for result DIE
  *
  * Search a non-inlined function DIE which includes @addr. Stores the
- * DIE to @die_mem and returns it if found. Returns NULl if failed.
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
  */
 Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem)
@@ -454,15 +454,32 @@
 }
 
 /**
- * die_find_inlinefunc - Search an inlined function at given address
- * @cu_die: a CU DIE which including @addr
+ * die_find_top_inlinefunc - Search the top inlined function at given address
+ * @sp_die: a subprogram DIE which including @addr
  * @addr: target address
  * @die_mem: a buffer for result DIE
  *
  * Search an inlined function DIE which includes @addr. Stores the
- * DIE to @die_mem and returns it if found. Returns NULl if failed.
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ * Even if several inlined functions are expanded recursively, this
+ * doesn't trace it down, and returns the topmost one.
+ */
+Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				   Dwarf_Die *die_mem)
+{
+	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+}
+
+/**
+ * die_find_inlinefunc - Search an inlined function at given address
+ * @sp_die: a subprogram DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search an inlined function DIE which includes @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
  * If several inlined functions are expanded recursively, this trace
- * it and returns deepest one.
+ * it down and returns deepest one.
  */
 Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 			       Dwarf_Die *die_mem)
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 8658d41..b4fe90c 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -79,7 +79,11 @@
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
-/* Search an inlined function including given address */
+/* Search the top inlined function including given address */
+extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+					  Dwarf_Die *die_mem);
+
+/* Search the deepest inlined function including given address */
 extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 				      Dwarf_Die *die_mem);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ce69901..c3e5a3b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2768,6 +2768,18 @@
 	if (perf_file_header__read(&f_header, header, fd) < 0)
 		return -EINVAL;
 
+	/*
+	 * Sanity check that perf.data was written cleanly; data size is
+	 * initialized to 0 and updated only if the on_exit function is run.
+	 * If data size is still 0 then the file contains only partial
+	 * information.  Just warn user and process it as much as it can.
+	 */
+	if (f_header.data.size == 0) {
+		pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
+			   "Was the 'perf record' command properly terminated?\n",
+			   session->filename);
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 371476c..c09e0a9 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1327,8 +1327,8 @@
 				struct perf_probe_point *ppt)
 {
 	Dwarf_Die cudie, spdie, indie;
-	Dwarf_Addr _addr, baseaddr;
-	const char *fname = NULL, *func = NULL, *tmp;
+	Dwarf_Addr _addr = 0, baseaddr = 0;
+	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
 
 	/* Adjust address with bias */
@@ -1349,27 +1349,36 @@
 	/* Find a corresponding function (name, baseline and baseaddr) */
 	if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
 		/* Get function entry information */
-		tmp = dwarf_diename(&spdie);
-		if (!tmp ||
+		func = basefunc = dwarf_diename(&spdie);
+		if (!func ||
 		    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
-		    dwarf_decl_line(&spdie, &baseline) != 0)
+		    dwarf_decl_line(&spdie, &baseline) != 0) {
+			lineno = 0;
 			goto post;
-		func = tmp;
+		}
 
-		if (addr == (unsigned long)baseaddr)
+		if (addr == (unsigned long)baseaddr) {
 			/* Function entry - Relative line number is 0 */
 			lineno = baseline;
-		else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-					     &indie)) {
+			fname = dwarf_decl_file(&spdie);
+			goto post;
+		}
+
+		/* Track down the inline functions step by step */
+		while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr,
+						&indie)) {
+			/* There is an inline function */
 			if (dwarf_entrypc(&indie, &_addr) == 0 &&
-			    _addr == addr)
+			    _addr == addr) {
 				/*
 				 * addr is at an inline function entry.
 				 * In this case, lineno should be the call-site
-				 * line number.
+				 * line number. (overwrite lineinfo)
 				 */
 				lineno = die_get_call_lineno(&indie);
-			else {
+				fname = die_get_call_file(&indie);
+				break;
+			} else {
 				/*
 				 * addr is in an inline function body.
 				 * Since lineno points one of the lines
@@ -1377,19 +1386,27 @@
 				 * be the entry line of the inline function.
 				 */
 				tmp = dwarf_diename(&indie);
-				if (tmp &&
-				    dwarf_decl_line(&spdie, &baseline) == 0)
-					func = tmp;
+				if (!tmp ||
+				    dwarf_decl_line(&indie, &baseline) != 0)
+					break;
+				func = tmp;
+				spdie = indie;
 			}
 		}
+		/* Verify the lineno and baseline are in a same file */
+		tmp = dwarf_decl_file(&spdie);
+		if (!tmp || strcmp(tmp, fname) != 0)
+			lineno = 0;
 	}
 
 post:
 	/* Make a relative line number or an offset */
 	if (lineno)
 		ppt->line = lineno - baseline;
-	else if (func)
+	else if (basefunc) {
 		ppt->offset = addr - (unsigned long)baseaddr;
+		func = basefunc;
+	}
 
 	/* Duplicate strings */
 	if (func) {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 70ffa41..568b750 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -256,6 +256,8 @@
 		tool->sample = process_event_sample_stub;
 	if (tool->mmap == NULL)
 		tool->mmap = process_event_stub;
+	if (tool->mmap2 == NULL)
+		tool->mmap2 = process_event_stub;
 	if (tool->comm == NULL)
 		tool->comm = process_event_stub;
 	if (tool->fork == NULL)
@@ -1310,7 +1312,7 @@
 	file_offset = page_offset;
 	head = data_offset - page_offset;
 
-	if (data_offset + data_size < file_size)
+	if (data_size && (data_offset + data_size < file_size))
 		file_size = data_offset + data_size;
 
 	progress_next = file_size / 16;