Linux-libre 4.5-gnu

9 files changed, 368 insertions, 512 deletions

diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index b42afada1..1cceca146 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -54,22 +54,38 @@
 #define read_barrier_depends()		do { } while (0)
 #endif
 
+#ifndef __smp_mb
+#define __smp_mb()	mb()
+#endif
+
+#ifndef __smp_rmb
+#define __smp_rmb()	rmb()
+#endif
+
+#ifndef __smp_wmb
+#define __smp_wmb()	wmb()
+#endif
+
+#ifndef __smp_read_barrier_depends
+#define __smp_read_barrier_depends()	read_barrier_depends()
+#endif
+
 #ifdef CONFIG_SMP
 
 #ifndef smp_mb
-#define smp_mb()	mb()
+#define smp_mb()	__smp_mb()
 #endif
 
 #ifndef smp_rmb
-#define smp_rmb()	rmb()
+#define smp_rmb()	__smp_rmb()
 #endif
 
 #ifndef smp_wmb
-#define smp_wmb()	wmb()
+#define smp_wmb()	__smp_wmb()
 #endif
 
 #ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	read_barrier_depends()
+#define smp_read_barrier_depends()	__smp_read_barrier_depends()
 #endif
 
 #else	/* !CONFIG_SMP */
@@ -92,32 +108,104 @@
 
 #endif	/* CONFIG_SMP */
 
+#ifndef __smp_store_mb
+#define __smp_store_mb(var, value)  do { WRITE_ONCE(var, value); __smp_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
+
+#ifndef __smp_store_release
+#define __smp_store_release(p, v)					\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__smp_mb();							\
+	WRITE_ONCE(*p, v);						\
+} while (0)
+#endif
+
+#ifndef __smp_load_acquire
+#define __smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__smp_mb();							\
+	___p1;								\
+})
+#endif
+
+#ifdef CONFIG_SMP
+
+#ifndef smp_store_mb
+#define smp_store_mb(var, value)  __smp_store_mb(var, value)
+#endif
+
+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic()	__smp_mb__before_atomic()
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic()	__smp_mb__after_atomic()
+#endif
+
+#ifndef smp_store_release
+#define smp_store_release(p, v) __smp_store_release(p, v)
+#endif
+
+#ifndef smp_load_acquire
+#define smp_load_acquire(p) __smp_load_acquire(p)
+#endif
+
+#else	/* !CONFIG_SMP */
+
 #ifndef smp_store_mb
-#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); barrier(); } while (0)
 #endif
 
 #ifndef smp_mb__before_atomic
-#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__before_atomic()	barrier()
 #endif
 
 #ifndef smp_mb__after_atomic
-#define smp_mb__after_atomic()	smp_mb()
+#define smp_mb__after_atomic()	barrier()
 #endif
 
+#ifndef smp_store_release
 #define smp_store_release(p, v)						\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
-	smp_mb();							\
+	barrier();							\
 	WRITE_ONCE(*p, v);						\
 } while (0)
+#endif
 
+#ifndef smp_load_acquire
 #define smp_load_acquire(p)						\
 ({									\
 	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
-	smp_mb();							\
+	barrier();							\
 	___p1;								\
 })
+#endif
+
+#endif
+
+/* Barriers for virtual machine guests when talking to an SMP host */
+#define virt_mb() __smp_mb()
+#define virt_rmb() __smp_rmb()
+#define virt_wmb() __smp_wmb()
+#define virt_read_barrier_depends() __smp_read_barrier_depends()
+#define virt_store_mb(var, value) __smp_store_mb(var, value)
+#define virt_mb__before_atomic() __smp_mb__before_atomic()
+#define virt_mb__after_atomic()	__smp_mb__after_atomic()
+#define virt_store_release(p, v) __smp_store_release(p, v)
+#define virt_load_acquire(p) __smp_load_acquire(p)
 
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/div64.h b/include/asm-generic/div64.h
index 8f4e31933..163f77999 100644
--- a/include/asm-generic/div64.h
+++ b/include/asm-generic/div64.h
@@ -4,6 +4,9 @@
  * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
  * Based on former asm-ppc/div64.h and asm-m68knommu/div64.h
  *
+ * Optimization for constant divisors on 32-bit machines:
+ * Copyright (C) 2006-2015 Nicolas Pitre
+ *
  * The semantics of do_div() are:
  *
  * uint32_t do_div(uint64_t *n, uint32_t base)
@@ -32,7 +35,168 @@
 
 #elif BITS_PER_LONG == 32
 
+#include <linux/log2.h>
+
+/*
+ * If the divisor happens to be constant, we determine the appropriate
+ * inverse at compile time to turn the division into a few inline
+ * multiplications which ought to be much faster. And yet only if compiling
+ * with a sufficiently recent gcc version to perform proper 64-bit constant
+ * propagation.
+ *
+ * (It is unfortunate that gcc doesn't perform all this internally.)
+ */
+
+#ifndef __div64_const32_is_OK
+#define __div64_const32_is_OK (__GNUC__ >= 4)
+#endif
+
+#define __div64_const32(n, ___b)					\
+({									\
+	/*								\
+	 * Multiplication by reciprocal of b: n / b = n * (p / b) / p	\
+	 *								\
+	 * We rely on the fact that most of this code gets optimized	\
+	 * away at compile time due to constant propagation and only	\
+	 * a few multiplication instructions should remain.		\
+	 * Hence this monstrous macro (static inline doesn't always	\
+	 * do the trick here).						\
+	 */								\
+	uint64_t ___res, ___x, ___t, ___m, ___n = (n);			\
+	uint32_t ___p, ___bias;						\
+									\
+	/* determine MSB of b */					\
+	___p = 1 << ilog2(___b);					\
+									\
+	/* compute m = ((p << 64) + b - 1) / b */			\
+	___m = (~0ULL / ___b) * ___p;					\
+	___m += (((~0ULL % ___b + 1) * ___p) + ___b - 1) / ___b;	\
+									\
+	/* one less than the dividend with highest result */		\
+	___x = ~0ULL / ___b * ___b - 1;					\
+									\
+	/* test our ___m with res = m * x / (p << 64) */		\
+	___res = ((___m & 0xffffffff) * (___x & 0xffffffff)) >> 32;	\
+	___t = ___res += (___m & 0xffffffff) * (___x >> 32);		\
+	___res += (___x & 0xffffffff) * (___m >> 32);			\
+	___t = (___res < ___t) ? (1ULL << 32) : 0;			\
+	___res = (___res >> 32) + ___t;					\
+	___res += (___m >> 32) * (___x >> 32);				\
+	___res /= ___p;							\
+									\
+	/* Now sanitize and optimize what we've got. */			\
+	if (~0ULL % (___b / (___b & -___b)) == 0) {			\
+		/* special case, can be simplified to ... */		\
+		___n /= (___b & -___b);					\
+		___m = ~0ULL / (___b / (___b & -___b));			\
+		___p = 1;						\
+		___bias = 1;						\
+	} else if (___res != ___x / ___b) {				\
+		/*							\
+		 * We can't get away without a bias to compensate	\
+		 * for bit truncation errors.  To avoid it we'd need an	\
+		 * additional bit to represent m which would overflow	\
+		 * a 64-bit variable.					\
+		 *							\
+		 * Instead we do m = p / b and n / b = (n * m + m) / p.	\
+		 */							\
+		___bias = 1;						\
+		/* Compute m = (p << 64) / b */				\
+		___m = (~0ULL / ___b) * ___p;				\
+		___m += ((~0ULL % ___b + 1) * ___p) / ___b;		\
+	} else {							\
+		/*							\
+		 * Reduce m / p, and try to clear bit 31 of m when	\
+		 * possible, otherwise that'll need extra overflow	\
+		 * handling later.					\
+		 */							\
+		uint32_t ___bits = -(___m & -___m);			\
+		___bits |= ___m >> 32;					\
+		___bits = (~___bits) << 1;				\
+		/*							\
+		 * If ___bits == 0 then setting bit 31 is  unavoidable.	\
+		 * Simply apply the maximum possible reduction in that	\
+		 * case. Otherwise the MSB of ___bits indicates the	\
+		 * best reduction we should apply.			\
+		 */							\
+		if (!___bits) {						\
+			___p /= (___m & -___m);				\
+			___m /= (___m & -___m);				\
+		} else {						\
+			___p >>= ilog2(___bits);			\
+			___m >>= ilog2(___bits);			\
+		}							\
+		/* No bias needed. */					\
+		___bias = 0;						\
+	}								\
+									\
+	/*								\
+	 * Now we have a combination of 2 conditions:			\
+	 *								\
+	 * 1) whether or not we need to apply a bias, and		\
+	 *								\
+	 * 2) whether or not there might be an overflow in the cross	\
+	 *    product determined by (___m & ((1 << 63) | (1 << 31))).	\
+	 *								\
+	 * Select the best way to do (m_bias + m * n) / (1 << 64).	\
+	 * From now on there will be actual runtime code generated.	\
+	 */								\
+	___res = __arch_xprod_64(___m, ___n, ___bias);			\
+									\
+	___res /= ___p;							\
+})
+
+#ifndef __arch_xprod_64
+/*
+ * Default C implementation for __arch_xprod_64()
+ *
+ * Prototype: uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+ * Semantic:  retval = ((bias ? m : 0) + m * n) >> 64
+ *
+ * The product is a 128-bit value, scaled down to 64 bits.
+ * Assuming constant propagation to optimize away unused conditional code.
+ * Architectures may provide their own optimized assembly implementation.
+ */
+static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+{
+	uint32_t m_lo = m;
+	uint32_t m_hi = m >> 32;
+	uint32_t n_lo = n;
+	uint32_t n_hi = n >> 32;
+	uint64_t res, tmp;
+
+	if (!bias) {
+		res = ((uint64_t)m_lo * n_lo) >> 32;
+	} else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+		/* there can't be any overflow here */
+		res = (m + (uint64_t)m_lo * n_lo) >> 32;
+	} else {
+		res = m + (uint64_t)m_lo * n_lo;
+		tmp = (res < m) ? (1ULL << 32) : 0;
+		res = (res >> 32) + tmp;
+	}
+
+	if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+		/* there can't be any overflow here */
+		res += (uint64_t)m_lo * n_hi;
+		res += (uint64_t)m_hi * n_lo;
+		res >>= 32;
+	} else {
+		tmp = res += (uint64_t)m_lo * n_hi;
+		res += (uint64_t)m_hi * n_lo;
+		tmp = (res < tmp) ? (1ULL << 32) : 0;
+		res = (res >> 32) + tmp;
+	}
+
+	res += (uint64_t)m_hi * n_hi;
+
+	return res;
+}
+#endif
+
+#ifndef __div64_32
 extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
+#endif
 
 /* The unnecessary pointer compare is there
  * to check for type safety (n must be 64bit)
@@ -41,7 +205,19 @@ extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
 	uint32_t __base = (base);			\
 	uint32_t __rem;					\
 	(void)(((typeof((n)) *)0) == ((uint64_t *)0));	\
-	if (likely(((n) >> 32) == 0)) {			\
+	if (__builtin_constant_p(__base) &&		\
+	    is_power_of_2(__base)) {			\
+		__rem = (n) & (__base - 1);		\
+		(n) >>= ilog2(__base);			\
+	} else if (__div64_const32_is_OK &&		\
+		   __builtin_constant_p(__base) &&	\
+		   __base != 0) {			\
+		uint32_t __res_lo, __n_lo = (n);	\
+		(n) = __div64_const32(n, __base);	\
+		/* the remainder can be computed with 32-bit regs */ \
+		__res_lo = (n);				\
+		__rem = __n_lo - __res_lo * __base;	\
+	} else if (likely(((n) >> 32) == 0)) {		\
 		__rem = (uint32_t)(n) % __base;		\
 		(n) = (uint32_t)(n) / __base;		\
 	} else 						\
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
deleted file mode 100644
index 0297e5875..000000000
--- a/include/asm-generic/dma-coherent.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef DMA_COHERENT_H
-#define DMA_COHERENT_H
-
-#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
-/*
- * These three functions are only for dma allocator.
- * Don't use them in device drivers.
- */
-int dma_alloc_from_coherent(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret);
-int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
-
-int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
-			    void *cpu_addr, size_t size, int *ret);
-/*
- * Standard interface
- */
-#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				dma_addr_t device_addr, size_t size, int flags);
-
-void dma_release_declared_memory(struct device *dev);
-
-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)
-#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
-#endif
-
-#endif
diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h
deleted file mode 100644
index 6c32af918..000000000
--- a/include/asm-generic/dma-mapping-broken.h
+++ /dev/null
@@ -1,95 +0,0 @@
-#ifndef _ASM_GENERIC_DMA_MAPPING_H
-#define _ASM_GENERIC_DMA_MAPPING_H
-
-/* define the dma api to allow compilation but not linking of
- * dma dependent code.  Code that depends on the dma-mapping
- * API needs to set 'depends on HAS_DMA' in its Kconfig
- */
-
-struct scatterlist;
-
-extern void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		   gfp_t flag);
-
-extern void
-dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-		    dma_addr_t dma_handle);
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flag,
-				    struct dma_attrs *attrs)
-{
-	/* attrs is not supported and ignored */
-	return dma_alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *cpu_addr, dma_addr_t dma_handle,
-				  struct dma_attrs *attrs)
-{
-	/* attrs is not supported and ignored */
-	dma_free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-extern dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction);
-
-extern void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction);
-
-extern int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction direction);
-
-extern void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction);
-
-extern dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction);
-
-extern void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction);
-
-extern void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-			enum dma_data_direction direction);
-
-extern void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction direction);
-
-extern void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-		    enum dma_data_direction direction);
-
-#define dma_sync_single_for_device dma_sync_single_for_cpu
-#define dma_sync_single_range_for_device dma_sync_single_range_for_cpu
-#define dma_sync_sg_for_device dma_sync_sg_for_cpu
-
-extern int
-dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
-extern int
-dma_supported(struct device *dev, u64 mask);
-
-extern int
-dma_set_mask(struct device *dev, u64 mask);
-
-extern int
-dma_get_cache_alignment(void);
-
-extern void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction);
-
-#endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
deleted file mode 100644
index b1bc954ec..000000000
--- a/include/asm-generic/dma-mapping-common.h
+++ /dev/null
@@ -1,358 +0,0 @@
-#ifndef _ASM_GENERIC_DMA_MAPPING_H
-#define _ASM_GENERIC_DMA_MAPPING_H
-
-#include <linux/kmemcheck.h>
-#include <linux/bug.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <linux/dma-attrs.h>
-#include <asm-generic/dma-coherent.h>
-
-static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
-					      size_t size,
-					      enum dma_data_direction dir,
-					      struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	kmemcheck_mark_initialized(ptr, size);
-	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, virt_to_page(ptr),
-			     (unsigned long)ptr & ~PAGE_MASK, size,
-			     dir, attrs);
-	debug_dma_map_page(dev, virt_to_page(ptr),
-			   (unsigned long)ptr & ~PAGE_MASK, size,
-			   dir, addr, true);
-	return addr;
-}
-
-static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
-					  size_t size,
-					  enum dma_data_direction dir,
-					  struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir, true);
-}
-
-/*
- * dma_maps_sg_attrs returns 0 on error and > 0 on success.
- * It should never return a value < 0.
- */
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir,
-				   struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	int i, ents;
-	struct scatterlist *s;
-
-	for_each_sg(sg, s, nents, i)
-		kmemcheck_mark_initialized(sg_virt(s), s->length);
-	BUG_ON(!valid_dma_direction(dir));
-	ents = ops->map_sg(dev, sg, nents, dir, attrs);
-	BUG_ON(ents < 0);
-	debug_dma_map_sg(dev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-				      int nents, enum dma_data_direction dir,
-				      struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (ops->unmap_sg)
-		ops->unmap_sg(dev, sg, nents, dir, attrs);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	kmemcheck_mark_initialized(page_address(page) + offset, size);
-	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, page, offset, size, dir, NULL);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
-
-	return addr;
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-				  size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, NULL);
-	debug_dma_unmap_page(dev, addr, size, dir, false);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-					   size_t size,
-					   enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr, size, dir);
-	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t addr, size_t size,
-					      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr, size, dir);
-	debug_dma_sync_single_for_device(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-						 dma_addr_t addr,
-						 unsigned long offset,
-						 size_t size,
-						 enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr + offset, size, dir);
-	debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t addr,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr + offset, size, dir);
-	debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
-
-}
-
-#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
-#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL)
-#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL)
-#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL)
-
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-
-void *dma_common_contiguous_remap(struct page *page, size_t size,
-			unsigned long vm_flags,
-			pgprot_t prot, const void *caller);
-
-void *dma_common_pages_remap(struct page **pages, size_t size,
-			unsigned long vm_flags, pgprot_t prot,
-			const void *caller);
-void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
-
-/**
- * dma_mmap_attrs - map a coherent DMA allocation into user space
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @vma: vm_area_struct describing requested user mapping
- * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
- * @handle: device-view address returned from dma_alloc_attrs
- * @size: size of memory originally requested in dma_alloc_attrs
- * @attrs: attributes of mapping properties requested in dma_alloc_attrs
- *
- * Map a coherent DMA buffer previously allocated by dma_alloc_attrs
- * into user space.  The coherent DMA buffer must not be freed by the
- * driver until the user space mapping has been released.
- */
-static inline int
-dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
-	       dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	if (ops->mmap)
-		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
-
-int
-dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
-
-static inline int
-dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
-		      dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	if (ops->get_sgtable)
-		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
-					attrs);
-	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size);
-}
-
-#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL)
-
-#ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev, flag)	(true)
-#endif
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *cpu_addr;
-
-	BUG_ON(!ops);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr))
-		return cpu_addr;
-
-	if (!arch_dma_alloc_attrs(&dev, &flag))
-		return NULL;
-	if (!ops->alloc)
-		return NULL;
-
-	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
-	return cpu_addr;
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle,
-				     struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!ops);
-	WARN_ON(irqs_disabled());
-
-	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
-		return;
-
-	if (!ops->free)
-		return;
-
-	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free(dev, size, cpu_addr, dma_handle, attrs);
-}
-
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag)
-{
-	return dma_alloc_attrs(dev, size, dma_handle, flag, NULL);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle)
-{
-	return dma_free_attrs(dev, size, cpu_addr, dma_handle, NULL);
-}
-
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp)
-{
-	DEFINE_DMA_ATTRS(attrs);
-
-	dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs);
-	return dma_alloc_attrs(dev, size, dma_handle, gfp, &attrs);
-}
-
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle)
-{
-	DEFINE_DMA_ATTRS(attrs);
-
-	dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs);
-	dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	debug_dma_mapping_error(dev, dma_addr);
-
-	if (get_dma_ops(dev)->mapping_error)
-		return get_dma_ops(dev)->mapping_error(dev, dma_addr);
-
-#ifdef DMA_ERROR_CODE
-	return dma_addr == DMA_ERROR_CODE;
-#else
-	return 0;
-#endif
-}
-
-#ifndef HAVE_ARCH_DMA_SUPPORTED
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (!ops)
-		return 0;
-	if (!ops->dma_supported)
-		return 1;
-	return ops->dma_supported(dev, mask);
-}
-#endif
-
-#ifndef HAVE_ARCH_DMA_SET_MASK
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (ops->set_dma_mask)
-		return ops->set_dma_mask(dev, mask);
-
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-	*dev->dma_mask = mask;
-	return 0;
-}
-#endif
-
-#endif
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 4b4b056a6..5148150cc 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_MEMORY_MODEL_H
 #define __ASM_MEMORY_MODEL_H
 
+#include <linux/pfn.h>
+
 #ifndef __ASSEMBLY__
 
 #if defined(CONFIG_FLATMEM)
@@ -72,7 +74,7 @@
 /*
  * Convert a physical address to a Page Frame Number and back
  */
-#define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
+#define	__phys_to_pfn(paddr)	PHYS_PFN(paddr)
 #define	__pfn_to_phys(pfn)	PFN_PHYS(pfn)
 
 #define page_to_pfn __page_to_pfn
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 776b5a043..f387ed12c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_GENERIC_PGTABLE_H
 #define _ASM_GENERIC_PGTABLE_H
 
+#include <linux/pfn.h>
+
 #ifndef __ASSEMBLY__
 #ifdef CONFIG_MMU
 
@@ -207,11 +209,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-extern void pmdp_splitting_flush(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp);
-#endif
-
 #ifndef pmdp_collapse_flush
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
@@ -242,6 +239,14 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+					   unsigned long address, pmd_t *pmdp)
+{
+
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
@@ -554,7 +559,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
  * by vm_insert_pfn().
  */
 static inline int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-				   unsigned long pfn)
+				   pfn_t pfn)
 {
 	return 0;
 }
@@ -569,7 +574,7 @@ static inline int track_pfn_copy(struct vm_area_struct *vma)
 }
 
 /*
- * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack_pfn is called while unmapping a pfnmap for a region.
  * untrack can be called for a specific region indicated by pfn and size or
  * can be for the entire vma (in which case pfn, size are zero).
  */
@@ -577,15 +582,23 @@ static inline void untrack_pfn(struct vm_area_struct *vma,
 			       unsigned long pfn, unsigned long size)
 {
 }
+
+/*
+ * untrack_pfn_moved is called while mremapping a pfnmap for a new region.
+ */
+static inline void untrack_pfn_moved(struct vm_area_struct *vma)
+{
+}
 #else
 extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			   unsigned long pfn, unsigned long addr,
 			   unsigned long size);
 extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-			    unsigned long pfn);
+			    pfn_t pfn);
 extern int track_pfn_copy(struct vm_area_struct *vma);
 extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
+extern void untrack_pfn_moved(struct vm_area_struct *vma);
 #endif
 
 #ifdef CONFIG_UKSM
@@ -632,10 +645,6 @@ static inline int pmd_trans_huge(pmd_t pmd)
 {
 	return 0;
 }
-static inline int pmd_trans_splitting(pmd_t pmd)
-{
-	return 0;
-}
 #ifndef __HAVE_ARCH_PMD_WRITE
 static inline int pmd_write(pmd_t pmd)
 {
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index e2aadbc71..39e1cb201 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -12,8 +12,9 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <waiman.long@hp.com>
+ * Authors: Waiman Long <waiman.long@hpe.com>
  */
 #ifndef __ASM_GENERIC_QSPINLOCK_H
 #define __ASM_GENERIC_QSPINLOCK_H
@@ -62,7 +63,7 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
 	if (!atomic_read(&lock->val) &&
-	   (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+	   (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
 		return 1;
 	return 0;
 }
@@ -77,7 +78,7 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
 {
 	u32 val;
 
-	val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+	val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
 	if (likely(val == 0))
 		return;
 	queued_spin_lock_slowpath(lock, val);
@@ -93,7 +94,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 	/*
 	 * smp_mb__before_atomic() in order to guarantee release semantics
 	 */
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_sub(_Q_LOCKED_VAL, &lock->val);
 }
 #endif
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index b58fd667f..af0254c09 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -4,6 +4,7 @@
 /* References to section boundaries */
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 
 /*
  * Usage guidelines:
@@ -63,4 +64,68 @@ static inline int arch_is_kernel_data(unsigned long addr)
 }
 #endif
 
+/**
+ * memory_contains - checks if an object is contained within a memory region
+ * @begin: virtual address of the beginning of the memory region
+ * @end: virtual address of the end of the memory region
+ * @virt: virtual address of the memory object
+ * @size: size of the memory object
+ *
+ * Returns: true if the object specified by @virt and @size is entirely
+ * contained within the memory region defined by @begin and @end, false
+ * otherwise.
+ */
+static inline bool memory_contains(void *begin, void *end, void *virt,
+				   size_t size)
+{
+	return virt >= begin && virt + size <= end;
+}
+
+/**
+ * memory_intersects - checks if the region occupied by an object intersects
+ *                     with another memory region
+ * @begin: virtual address of the beginning of the memory regien
+ * @end: virtual address of the end of the memory region
+ * @virt: virtual address of the memory object
+ * @size: size of the memory object
+ *
+ * Returns: true if an object's memory region, specified by @virt and @size,
+ * intersects with the region specified by @begin and @end, false otherwise.
+ */
+static inline bool memory_intersects(void *begin, void *end, void *virt,
+				     size_t size)
+{
+	void *vend = virt + size;
+
+	return (virt >= begin && virt < end) || (vend >= begin && vend < end);
+}
+
+/**
+ * init_section_contains - checks if an object is contained within the init
+ *                         section
+ * @virt: virtual address of the memory object
+ * @size: size of the memory object
+ *
+ * Returns: true if the object specified by @virt and @size is entirely
+ * contained within the init section, false otherwise.
+ */
+static inline bool init_section_contains(void *virt, size_t size)
+{
+	return memory_contains(__init_begin, __init_end, virt, size);
+}
+
+/**
+ * init_section_intersects - checks if the region occupied by an object
+ *                           intersects with the init section
+ * @virt: virtual address of the memory object
+ * @size: size of the memory object
+ *
+ * Returns: true if an object's memory region, specified by @virt and @size,
+ * intersects with the init section, false otherwise.
+ */
+static inline bool init_section_intersects(void *virt, size_t size)
+{
+	return memory_intersects(__init_begin, __init_end, virt, size);
+}
+
 #endif /* _ASM_GENERIC_SECTIONS_H_ */