Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

10 files changed, 57 insertions, 78 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 33bd2de3bc1e..9c79e7603459 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -16,6 +16,7 @@
 #define __ASM_GENERIC_ATOMIC_H
 
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #ifdef CONFIG_SMP
 /* Force people to define core atomics */
@@ -182,11 +183,5 @@ static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 }
 #endif
 
-/* Assume that atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* __KERNEL__ */
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 6f692f8ac664..1402fa855388 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -62,6 +62,14 @@
 #define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
 #endif
 
+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic()	smp_mb()
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic()	smp_mb()
+#endif
+
 #define smp_store_release(p, v)						\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h
index 280ca7a96f75..dcdcacf2fd2b 100644
--- a/include/asm-generic/bitops.h
+++ b/include/asm-generic/bitops.h
@@ -11,14 +11,7 @@
 
 #include <linux/irqflags.h>
 #include <linux/compiler.h>
-
-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-#endif
+#include <asm/barrier.h>
 
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/ffz.h>
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 9ae6c34dc191..49673510b484 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -80,7 +80,7 @@ static inline void set_bit(int nr, volatile unsigned long *addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static inline void clear_bit(int nr, volatile unsigned long *addr)
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 308a9e22c802..c30266e94806 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -20,7 +20,7 @@
  */
 #define clear_bit_unlock(nr, addr)	\
 do {					\
-	smp_mb__before_clear_bit();	\
+	smp_mb__before_atomic();	\
 	clear_bit(nr, addr);		\
 } while (0)
 
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
index 2be8a2dbc868..0297e5875798 100644
--- a/include/asm-generic/dma-coherent.h
+++ b/include/asm-generic/dma-coherent.h
@@ -16,16 +16,13 @@ int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
  * Standard interface
  */
 #define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
-extern int
-dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-			    dma_addr_t device_addr, size_t size, int flags);
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+				dma_addr_t device_addr, size_t size, int flags);
 
-extern void
-dma_release_declared_memory(struct device *dev);
+void dma_release_declared_memory(struct device *dev);
 
-extern void *
-dma_mark_declared_memory_occupied(struct device *dev,
-				  dma_addr_t device_addr, size_t size);
+void *dma_mark_declared_memory_occupied(struct device *dev,
+					dma_addr_t device_addr, size_t size);
 #else
 #define dma_alloc_from_coherent(dev, size, handle, ret) (0)
 #define dma_release_from_coherent(dev, order, vaddr) (0)
diff --git a/include/asm-generic/ioctl.h b/include/asm-generic/ioctl.h
index d17295b290fa..297fb0d7cd6c 100644
--- a/include/asm-generic/ioctl.h
+++ b/include/asm-generic/ioctl.h
@@ -3,10 +3,15 @@
 
 #include <uapi/asm-generic/ioctl.h>
 
+#ifdef __CHECKER__
+#define _IOC_TYPECHECK(t) (sizeof(t))
+#else
 /* provoke compile error for invalid uses of size argument */
 extern unsigned int __invalid_size_argument_for_IOC;
 #define _IOC_TYPECHECK(t) \
 	((sizeof(t) == sizeof(t[1]) && \
 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
 	  sizeof(t) : __invalid_size_argument_for_IOC)
+#endif
+
 #endif /* _ASM_GENERIC_IOCTL_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a8015a7a55bb..53b2acc38213 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -233,6 +233,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 # define pte_accessible(mm, pte)	((void)(pte), 1)
 #endif
 
+#ifndef pte_present_nonuma
+#define pte_present_nonuma(pte) pte_present(pte)
+#endif
+
 #ifndef flush_tlb_fix_spurious_fault
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
@@ -670,7 +674,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 static inline int pte_numa(pte_t pte)
 {
 	return (pte_flags(pte) &
-		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+		(_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
 }
 #endif
 
@@ -678,7 +682,7 @@ static inline int pte_numa(pte_t pte)
 static inline int pmd_numa(pmd_t pmd)
 {
 	return (pmd_flags(pmd) &
-		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+		(_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
 }
 #endif
 
diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h
index 03cf5936bad6..1ac097279db1 100644
--- a/include/asm-generic/unaligned.h
+++ b/include/asm-generic/unaligned.h
@@ -4,22 +4,27 @@
 /*
  * This is the most generic implementation of unaligned accesses
  * and should work almost anywhere.
- *
- * If an architecture can handle unaligned accesses in hardware,
- * it may want to use the linux/unaligned/access_ok.h implementation
- * instead.
  */
 #include <asm/byteorder.h>
 
+/* Set by the arch if it can handle unaligned accesses in hardware. */
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+# include <linux/unaligned/access_ok.h>
+#endif
+
 #if defined(__LITTLE_ENDIAN)
-# include <linux/unaligned/le_struct.h>
-# include <linux/unaligned/be_byteshift.h>
+# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#  include <linux/unaligned/le_struct.h>
+#  include <linux/unaligned/be_byteshift.h>
+# endif
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_le
 # define put_unaligned	__put_unaligned_le
 #elif defined(__BIG_ENDIAN)
-# include <linux/unaligned/be_struct.h>
-# include <linux/unaligned/le_byteshift.h>
+# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#  include <linux/unaligned/be_struct.h>
+#  include <linux/unaligned/le_byteshift.h>
+# endif
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_be
 # define put_unaligned	__put_unaligned_be
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 146e4fffd710..d647637cd699 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -139,52 +139,23 @@
 #define TRACE_SYSCALLS()
 #endif
 
-#ifdef CONFIG_CLKSRC_OF
-#define CLKSRC_OF_TABLES() . = ALIGN(8);				\
-			   VMLINUX_SYMBOL(__clksrc_of_table) = .;	\
-			   *(__clksrc_of_table)				\
-			   *(__clksrc_of_table_end)
-#else
-#define CLKSRC_OF_TABLES()
-#endif
 
-#ifdef CONFIG_IRQCHIP
-#define IRQCHIP_OF_MATCH_TABLE()					\
+#define ___OF_TABLE(cfg, name)	_OF_TABLE_##cfg(name)
+#define __OF_TABLE(cfg, name)	___OF_TABLE(cfg, name)
+#define OF_TABLE(cfg, name)	__OF_TABLE(config_enabled(cfg), name)
+#define _OF_TABLE_0(name)
+#define _OF_TABLE_1(name)						\
 	. = ALIGN(8);							\
-	VMLINUX_SYMBOL(__irqchip_begin) = .;				\
-	*(__irqchip_of_table)		  				\
-	*(__irqchip_of_end)
-#else
-#define IRQCHIP_OF_MATCH_TABLE()
-#endif
-
-#ifdef CONFIG_COMMON_CLK
-#define CLK_OF_TABLES() . = ALIGN(8);				\
-			VMLINUX_SYMBOL(__clk_of_table) = .;	\
-			*(__clk_of_table)			\
-			*(__clk_of_table_end)
-#else
-#define CLK_OF_TABLES()
-#endif
-
-#ifdef CONFIG_OF_RESERVED_MEM
-#define RESERVEDMEM_OF_TABLES()				\
-	. = ALIGN(8);					\
-	VMLINUX_SYMBOL(__reservedmem_of_table) = .;	\
-	*(__reservedmem_of_table)			\
-	*(__reservedmem_of_table_end)
-#else
-#define RESERVEDMEM_OF_TABLES()
-#endif
+	VMLINUX_SYMBOL(__##name##_of_table) = .;			\
+	*(__##name##_of_table)						\
+	*(__##name##_of_table_end)
 
-#ifdef CONFIG_SMP
-#define CPU_METHOD_OF_TABLES() . = ALIGN(8);				    \
-			   VMLINUX_SYMBOL(__cpu_method_of_table_begin) = .; \
-			   *(__cpu_method_of_table)			    \
-			   VMLINUX_SYMBOL(__cpu_method_of_table_end) = .;
-#else
-#define CPU_METHOD_OF_TABLES()
-#endif
+#define CLKSRC_OF_TABLES()	OF_TABLE(CONFIG_CLKSRC_OF, clksrc)
+#define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip)
+#define CLK_OF_TABLES()		OF_TABLE(CONFIG_COMMON_CLK, clk)
+#define RESERVEDMEM_OF_TABLES()	OF_TABLE(CONFIG_OF_RESERVED_MEM, reservedmem)
+#define CPU_METHOD_OF_TABLES()	OF_TABLE(CONFIG_SMP, cpu_method)
+#define EARLYCON_OF_TABLES()	OF_TABLE(CONFIG_SERIAL_EARLYCON, earlycon)
 
 #define KERNEL_DTB()							\
 	STRUCT_ALIGN();							\
@@ -513,7 +484,8 @@
 	CLKSRC_OF_TABLES()						\
 	CPU_METHOD_OF_TABLES()						\
 	KERNEL_DTB()							\
-	IRQCHIP_OF_MATCH_TABLE()
+	IRQCHIP_OF_MATCH_TABLE()					\
+	EARLYCON_OF_TABLES()
 
 #define INIT_TEXT							\
 	*(.init.text)							\