14 files changed, 420 insertions, 232 deletions

diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index b7babf020..a94cbebbc 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -23,236 +23,159 @@
 typedef atomic64_t atomic_long_t;
 
 #define ATOMIC_LONG_INIT(i)	ATOMIC64_INIT(i)
+#define ATOMIC_LONG_PFX(x)	atomic64 ## x
 
-static inline long atomic_long_read(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return (long)atomic64_read(v);
-}
-
-static inline void atomic_long_set(atomic_long_t *l, long i)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	atomic64_set(v, i);
-}
-
-static inline void atomic_long_inc(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	atomic64_inc(v);
-}
-
-static inline void atomic_long_dec(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	atomic64_dec(v);
-}
-
-static inline void atomic_long_add(long i, atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	atomic64_add(i, v);
-}
-
-static inline void atomic_long_sub(long i, atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	atomic64_sub(i, v);
-}
-
-static inline int atomic_long_sub_and_test(long i, atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return atomic64_sub_and_test(i, v);
-}
-
-static inline int atomic_long_dec_and_test(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return atomic64_dec_and_test(v);
-}
-
-static inline int atomic_long_inc_and_test(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return atomic64_inc_and_test(v);
-}
-
-static inline int atomic_long_add_negative(long i, atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return atomic64_add_negative(i, v);
-}
-
-static inline long atomic_long_add_return(long i, atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return (long)atomic64_add_return(i, v);
-}
-
-static inline long atomic_long_sub_return(long i, atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return (long)atomic64_sub_return(i, v);
-}
-
-static inline long atomic_long_inc_return(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return (long)atomic64_inc_return(v);
-}
-
-static inline long atomic_long_dec_return(atomic_long_t *l)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return (long)atomic64_dec_return(v);
-}
-
-static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
-{
-	atomic64_t *v = (atomic64_t *)l;
-
-	return (long)atomic64_add_unless(v, a, u);
-}
-
-#define atomic_long_inc_not_zero(l) atomic64_inc_not_zero((atomic64_t *)(l))
-
-#define atomic_long_cmpxchg(l, old, new) \
-	(atomic64_cmpxchg((atomic64_t *)(l), (old), (new)))
-#define atomic_long_xchg(v, new) \
-	(atomic64_xchg((atomic64_t *)(v), (new)))
-
-#else  /*  BITS_PER_LONG == 64  */
+#else
 
 typedef atomic_t atomic_long_t;
 
 #define ATOMIC_LONG_INIT(i)	ATOMIC_INIT(i)
-static inline long atomic_long_read(atomic_long_t *l)
-{
-	atomic_t *v = (atomic_t *)l;
-
-	return (long)atomic_read(v);
-}
-
-static inline void atomic_long_set(atomic_long_t *l, long i)
-{
-	atomic_t *v = (atomic_t *)l;
-
-	atomic_set(v, i);
-}
+#define ATOMIC_LONG_PFX(x)	atomic ## x
+
+#endif
+
+#define ATOMIC_LONG_READ_OP(mo)						\
+static inline long atomic_long_read##mo(atomic_long_t *l)		\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_read##mo)(v);			\
+}
+ATOMIC_LONG_READ_OP()
+ATOMIC_LONG_READ_OP(_acquire)
+
+#undef ATOMIC_LONG_READ_OP
+
+#define ATOMIC_LONG_SET_OP(mo)						\
+static inline void atomic_long_set##mo(atomic_long_t *l, long i)	\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	ATOMIC_LONG_PFX(_set##mo)(v, i);				\
+}
+ATOMIC_LONG_SET_OP()
+ATOMIC_LONG_SET_OP(_release)
+
+#undef ATOMIC_LONG_SET_OP
+
+#define ATOMIC_LONG_ADD_SUB_OP(op, mo)					\
+static inline long							\
+atomic_long_##op##_return##mo(long i, atomic_long_t *l)			\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_##op##_return##mo)(i, v);		\
+}
+ATOMIC_LONG_ADD_SUB_OP(add,)
+ATOMIC_LONG_ADD_SUB_OP(add, _relaxed)
+ATOMIC_LONG_ADD_SUB_OP(add, _acquire)
+ATOMIC_LONG_ADD_SUB_OP(add, _release)
+ATOMIC_LONG_ADD_SUB_OP(sub,)
+ATOMIC_LONG_ADD_SUB_OP(sub, _relaxed)
+ATOMIC_LONG_ADD_SUB_OP(sub, _acquire)
+ATOMIC_LONG_ADD_SUB_OP(sub, _release)
+
+#undef ATOMIC_LONG_ADD_SUB_OP
+
+#define atomic_long_cmpxchg_relaxed(l, old, new) \
+	(ATOMIC_LONG_PFX(_cmpxchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(l), \
+					   (old), (new)))
+#define atomic_long_cmpxchg_acquire(l, old, new) \
+	(ATOMIC_LONG_PFX(_cmpxchg_acquire)((ATOMIC_LONG_PFX(_t) *)(l), \
+					   (old), (new)))
+#define atomic_long_cmpxchg_release(l, old, new) \
+	(ATOMIC_LONG_PFX(_cmpxchg_release)((ATOMIC_LONG_PFX(_t) *)(l), \
+					   (old), (new)))
+#define atomic_long_cmpxchg(l, old, new) \
+	(ATOMIC_LONG_PFX(_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), (old), (new)))
+
+#define atomic_long_xchg_relaxed(v, new) \
+	(ATOMIC_LONG_PFX(_xchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
+#define atomic_long_xchg_acquire(v, new) \
+	(ATOMIC_LONG_PFX(_xchg_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
+#define atomic_long_xchg_release(v, new) \
+	(ATOMIC_LONG_PFX(_xchg_release)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
+#define atomic_long_xchg(v, new) \
+	(ATOMIC_LONG_PFX(_xchg)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
 
 static inline void atomic_long_inc(atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	atomic_inc(v);
+	ATOMIC_LONG_PFX(_inc)(v);
 }
 
 static inline void atomic_long_dec(atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	atomic_dec(v);
+	ATOMIC_LONG_PFX(_dec)(v);
 }
 
 static inline void atomic_long_add(long i, atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	atomic_add(i, v);
+	ATOMIC_LONG_PFX(_add)(i, v);
 }
 
 static inline void atomic_long_sub(long i, atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	atomic_sub(i, v);
+	ATOMIC_LONG_PFX(_sub)(i, v);
 }
 
 static inline int atomic_long_sub_and_test(long i, atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return atomic_sub_and_test(i, v);
+	return ATOMIC_LONG_PFX(_sub_and_test)(i, v);
 }
 
 static inline int atomic_long_dec_and_test(atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return atomic_dec_and_test(v);
+	return ATOMIC_LONG_PFX(_dec_and_test)(v);
 }
 
 static inline int atomic_long_inc_and_test(atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return atomic_inc_and_test(v);
+	return ATOMIC_LONG_PFX(_inc_and_test)(v);
 }
 
 static inline int atomic_long_add_negative(long i, atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return atomic_add_negative(i, v);
-}
-
-static inline long atomic_long_add_return(long i, atomic_long_t *l)
-{
-	atomic_t *v = (atomic_t *)l;
-
-	return (long)atomic_add_return(i, v);
-}
-
-static inline long atomic_long_sub_return(long i, atomic_long_t *l)
-{
-	atomic_t *v = (atomic_t *)l;
-
-	return (long)atomic_sub_return(i, v);
+	return ATOMIC_LONG_PFX(_add_negative)(i, v);
 }
 
 static inline long atomic_long_inc_return(atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return (long)atomic_inc_return(v);
+	return (long)ATOMIC_LONG_PFX(_inc_return)(v);
 }
 
 static inline long atomic_long_dec_return(atomic_long_t *l)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return (long)atomic_dec_return(v);
+	return (long)ATOMIC_LONG_PFX(_dec_return)(v);
 }
 
 static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 {
-	atomic_t *v = (atomic_t *)l;
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;
 
-	return (long)atomic_add_unless(v, a, u);
+	return (long)ATOMIC_LONG_PFX(_add_unless)(v, a, u);
 }
 
-#define atomic_long_inc_not_zero(l) atomic_inc_not_zero((atomic_t *)(l))
-
-#define atomic_long_cmpxchg(l, old, new) \
-	(atomic_cmpxchg((atomic_t *)(l), (old), (new)))
-#define atomic_long_xchg(v, new) \
-	(atomic_xchg((atomic_t *)(v), (new)))
-
-#endif  /*  BITS_PER_LONG == 64  */
+#define atomic_long_inc_not_zero(l) \
+	ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l))
 
 #endif  /*  _ASM_GENERIC_ATOMIC_LONG_H  */
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 1973ad2b1..d4d7e337f 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -98,15 +98,16 @@ ATOMIC_OP_RETURN(add, +)
 ATOMIC_OP_RETURN(sub, -)
 #endif
 
-#ifndef atomic_clear_mask
+#ifndef atomic_and
 ATOMIC_OP(and, &)
-#define atomic_clear_mask(i, v) atomic_and(~(i), (v))
 #endif
 
-#ifndef atomic_set_mask
-#define CONFIG_ARCH_HAS_ATOMIC_OR
+#ifndef atomic_or
 ATOMIC_OP(or, |)
-#define atomic_set_mask(i, v)	atomic_or((i), (v))
+#endif
+
+#ifndef atomic_xor
+ATOMIC_OP(xor, ^)
 #endif
 
 #undef ATOMIC_OP_RETURN
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 30ad9c86c..d48e78cca 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -32,6 +32,10 @@ extern long long atomic64_##op##_return(long long a, atomic64_t *v);
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
 
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
+
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 55e3abc2d..b42afada1 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -108,12 +108,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 940d5ec12..b1bc954ec 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -6,6 +6,7 @@
 #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,
@@ -237,4 +238,121 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
 
 #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/early_ioremap.h b/include/asm-generic/early_ioremap.h
index a5de55c04..734ad4db3 100644
--- a/include/asm-generic/early_ioremap.h
+++ b/include/asm-generic/early_ioremap.h
@@ -11,6 +11,8 @@ extern void __iomem *early_ioremap(resource_size_t phys_addr,
 				   unsigned long size);
 extern void *early_memremap(resource_size_t phys_addr,
 			    unsigned long size);
+extern void *early_memremap_ro(resource_size_t phys_addr,
+			       unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void early_memunmap(void *addr, unsigned long size);
 
@@ -33,6 +35,12 @@ extern void early_ioremap_setup(void);
  */
 extern void early_ioremap_reset(void);
 
+/*
+ * Early copy from unmapped memory to kernel mapped memory.
+ */
+extern void copy_from_early_mem(void *dest, phys_addr_t src,
+				unsigned long size);
+
 #else
 static inline void early_ioremap_init(void) { }
 static inline void early_ioremap_setup(void) { }
diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h
index f23174fb9..1cbb8338e 100644
--- a/include/asm-generic/fixmap.h
+++ b/include/asm-generic/fixmap.h
@@ -46,6 +46,9 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
 #ifndef FIXMAP_PAGE_NORMAL
 #define FIXMAP_PAGE_NORMAL PAGE_KERNEL
 #endif
+#if !defined(FIXMAP_PAGE_RO) && defined(PAGE_KERNEL_RO)
+#define FIXMAP_PAGE_RO PAGE_KERNEL_RO
+#endif
 #ifndef FIXMAP_PAGE_NOCACHE
 #define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NOCACHE
 #endif
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index f56094cfd..eed3bbe88 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -736,6 +736,35 @@ static inline void *phys_to_virt(unsigned long address)
 }
 #endif
 
+/**
+ * DOC: ioremap() and ioremap_*() variants
+ *
+ * If you have an IOMMU your architecture is expected to have both ioremap()
+ * and iounmap() implemented otherwise the asm-generic helpers will provide a
+ * direct mapping.
+ *
+ * There are ioremap_*() call variants, if you have no IOMMU we naturally will
+ * default to direct mapping for all of them, you can override these defaults.
+ * If you have an IOMMU you are highly encouraged to provide your own
+ * ioremap variant implementation as there currently is no safe architecture
+ * agnostic default. To avoid possible improper behaviour default asm-generic
+ * ioremap_*() variants all return NULL when an IOMMU is available. If you've
+ * defined your own ioremap_*() variant you must then declare your own
+ * ioremap_*() variant as defined to itself to avoid the default NULL return.
+ */
+
+#ifdef CONFIG_MMU
+
+#ifndef ioremap_uc
+#define ioremap_uc ioremap_uc
+static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
+{
+	return NULL;
+}
+#endif
+
+#else /* !CONFIG_MMU */
+
 /*
  * Change "struct page" to physical address.
  *
@@ -743,7 +772,6 @@ static inline void *phys_to_virt(unsigned long address)
  * you'll need to provide your own definitions.
  */
 
-#ifndef CONFIG_MMU
 #ifndef ioremap
 #define ioremap ioremap
 static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 14909b0b9..4b4b056a6 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -69,6 +69,12 @@
 })
 #endif /* CONFIG_FLATMEM/DISCONTIGMEM/SPARSEMEM */
 
+/*
+ * Convert a physical address to a Page Frame Number and back
+ */
+#define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
+#define	__pfn_to_phys(pfn)	PFN_PHYS(pfn)
+
 #define page_to_pfn __page_to_pfn
 #define pfn_to_page __pfn_to_page
 
diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
index 7389c8711..b1e17fcee 100644
--- a/include/asm-generic/pci_iomap.h
+++ b/include/asm-generic/pci_iomap.h
@@ -15,9 +15,13 @@ struct pci_dev;
 #ifdef CONFIG_PCI
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+extern void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max);
 extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
 				     unsigned long offset,
 				     unsigned long maxlen);
+extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+					unsigned long offset,
+					unsigned long maxlen);
 /* Create a virtual mapping cookie for a port on a given PCI device.
  * Do not call this directly, it exists to make it easier for architectures
  * to override */
@@ -34,12 +38,22 @@ static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned lon
 	return NULL;
 }
 
+static inline void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max)
+{
+	return NULL;
+}
 static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
 					    unsigned long offset,
 					    unsigned long maxlen)
 {
 	return NULL;
 }
+static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+					       unsigned long offset,
+					       unsigned long maxlen)
+{
+	return NULL;
+}
 #endif
 
 #endif /* __ASM_GENERIC_IO_H */
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 6383d54bf..54a8e65e1 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -36,39 +36,39 @@
 /*
  * External function declarations
  */
-extern void queue_read_lock_slowpath(struct qrwlock *lock);
-extern void queue_write_lock_slowpath(struct qrwlock *lock);
+extern void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts);
+extern void queued_write_lock_slowpath(struct qrwlock *lock);
 
 /**
- * queue_read_can_lock- would read_trylock() succeed?
+ * queued_read_can_lock- would read_trylock() succeed?
  * @lock: Pointer to queue rwlock structure
  */
-static inline int queue_read_can_lock(struct qrwlock *lock)
+static inline int queued_read_can_lock(struct qrwlock *lock)
 {
 	return !(atomic_read(&lock->cnts) & _QW_WMASK);
 }
 
 /**
- * queue_write_can_lock- would write_trylock() succeed?
+ * queued_write_can_lock- would write_trylock() succeed?
  * @lock: Pointer to queue rwlock structure
  */
-static inline int queue_write_can_lock(struct qrwlock *lock)
+static inline int queued_write_can_lock(struct qrwlock *lock)
 {
 	return !atomic_read(&lock->cnts);
 }
 
 /**
- * queue_read_trylock - try to acquire read lock of a queue rwlock
+ * queued_read_trylock - try to acquire read lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  * Return: 1 if lock acquired, 0 if failed
  */
-static inline int queue_read_trylock(struct qrwlock *lock)
+static inline int queued_read_trylock(struct qrwlock *lock)
 {
 	u32 cnts;
 
 	cnts = atomic_read(&lock->cnts);
 	if (likely(!(cnts & _QW_WMASK))) {
-		cnts = (u32)atomic_add_return(_QR_BIAS, &lock->cnts);
+		cnts = (u32)atomic_add_return_acquire(_QR_BIAS, &lock->cnts);
 		if (likely(!(cnts & _QW_WMASK)))
 			return 1;
 		atomic_sub(_QR_BIAS, &lock->cnts);
@@ -77,11 +77,11 @@ static inline int queue_read_trylock(struct qrwlock *lock)
 }
 
 /**
- * queue_write_trylock - try to acquire write lock of a queue rwlock
+ * queued_write_trylock - try to acquire write lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  * Return: 1 if lock acquired, 0 if failed
  */
-static inline int queue_write_trylock(struct qrwlock *lock)
+static inline int queued_write_trylock(struct qrwlock *lock)
 {
 	u32 cnts;
 
@@ -89,78 +89,70 @@ static inline int queue_write_trylock(struct qrwlock *lock)
 	if (unlikely(cnts))
 		return 0;
 
-	return likely(atomic_cmpxchg(&lock->cnts,
-				     cnts, cnts | _QW_LOCKED) == cnts);
+	return likely(atomic_cmpxchg_acquire(&lock->cnts,
+					     cnts, cnts | _QW_LOCKED) == cnts);
 }
 /**
- * queue_read_lock - acquire read lock of a queue rwlock
+ * queued_read_lock - acquire read lock of a queue rwlock
  * @lock: Pointer to queue rwlock structure
  */
-static inline void queue_read_lock(struct qrwlock *lock)
+static inline void queued_read_lock(struct qrwlock *lock)
 {
 	u32 cnts;
 
-	cnts = atomic_add_return(_QR_BIAS, &lock->cnts);
+	cnts = atomic_add_return_acquire(_QR_BIAS, &lock->cnts);
 	if (likely(!(cnts & _QW_WMASK)))
 		return;
 
 	/* The slowpath will decrement the reader count, if necessary. */
-	queue_read_lock_slowpath(lock);
+	queued_read_lock_slowpath(lock, cnts);
 }
 
 /**
- * queue_write_lock - acquire write lock of a queue rwlock
+ * queued_write_lock - acquire write lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  */
-static inline void queue_write_lock(struct qrwlock *lock)
+static inline void queued_write_lock(struct qrwlock *lock)
 {
 	/* Optimize for the unfair lock case where the fair flag is 0. */
-	if (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0)
+	if (atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0)
 		return;
 
-	queue_write_lock_slowpath(lock);
+	queued_write_lock_slowpath(lock);
 }
 
 /**
- * queue_read_unlock - release read lock of a queue rwlock
+ * queued_read_unlock - release read lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  */
-static inline void queue_read_unlock(struct qrwlock *lock)
+static inline void queued_read_unlock(struct qrwlock *lock)
 {
 	/*
 	 * Atomically decrement the reader count
 	 */
-	smp_mb__before_atomic();
-	atomic_sub(_QR_BIAS, &lock->cnts);
+	(void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
 }
 
-#ifndef queue_write_unlock
 /**
- * queue_write_unlock - release write lock of a queue rwlock
+ * queued_write_unlock - release write lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  */
-static inline void queue_write_unlock(struct qrwlock *lock)
+static inline void queued_write_unlock(struct qrwlock *lock)
 {
-	/*
-	 * If the writer field is atomic, it can be cleared directly.
-	 * Otherwise, an atomic subtraction will be used to clear it.
-	 */
-	smp_mb__before_atomic();
-	atomic_sub(_QW_LOCKED, &lock->cnts);
+	smp_store_release((u8 *)&lock->cnts, 0);
 }
-#endif
 
 /*
  * Remapping rwlock architecture specific functions to the corresponding
  * queue rwlock functions.
  */
-#define arch_read_can_lock(l)	queue_read_can_lock(l)
-#define arch_write_can_lock(l)	queue_write_can_lock(l)
-#define arch_read_lock(l)	queue_read_lock(l)
-#define arch_write_lock(l)	queue_write_lock(l)
-#define arch_read_trylock(l)	queue_read_trylock(l)
-#define arch_write_trylock(l)	queue_write_trylock(l)
-#define arch_read_unlock(l)	queue_read_unlock(l)
-#define arch_write_unlock(l)	queue_write_unlock(l)
+#define arch_read_can_lock(l)	queued_read_can_lock(l)
+#define arch_write_can_lock(l)	queued_write_can_lock(l)
+#define arch_read_lock(l)	queued_read_lock(l)
+#define arch_write_lock(l)	queued_write_lock(l)
+#define arch_read_trylock(l)	queued_read_trylock(l)
+#define arch_write_trylock(l)	queued_write_trylock(l)
+#define arch_read_unlock(l)	queued_read_unlock(l)
+#define arch_write_unlock(l)	queued_write_unlock(l)
 
 #endif /* __ASM_GENERIC_QRWLOCK_H */
diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h
index fa86f240c..4e3b65583 100644
--- a/include/asm-generic/rtc.h
+++ b/include/asm-generic/rtc.h
@@ -16,6 +16,9 @@
 #include <linux/rtc.h>
 #include <linux/bcd.h>
 #include <linux/delay.h>
+#ifdef CONFIG_ACPI
+#include <linux/acpi.h>
+#endif
 
 #define RTC_PIE 0x40		/* periodic interrupt enable */
 #define RTC_AIE 0x20		/* alarm interrupt enable */
@@ -46,6 +49,7 @@ static inline unsigned int __get_rtc_time(struct rtc_time *time)
 {
 	unsigned char ctrl;
 	unsigned long flags;
+	unsigned char century = 0;
 
 #ifdef CONFIG_MACH_DECSTATION
 	unsigned int real_year;
@@ -79,6 +83,11 @@ static inline unsigned int __get_rtc_time(struct rtc_time *time)
 #ifdef CONFIG_MACH_DECSTATION
 	real_year = CMOS_READ(RTC_DEC_YEAR);
 #endif
+#ifdef CONFIG_ACPI
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
+	    acpi_gbl_FADT.century)
+		century = CMOS_READ(acpi_gbl_FADT.century);
+#endif
 	ctrl = CMOS_READ(RTC_CONTROL);
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
@@ -90,12 +99,16 @@ static inline unsigned int __get_rtc_time(struct rtc_time *time)
 		time->tm_mday = bcd2bin(time->tm_mday);
 		time->tm_mon = bcd2bin(time->tm_mon);
 		time->tm_year = bcd2bin(time->tm_year);
+		century = bcd2bin(century);
 	}
 
 #ifdef CONFIG_MACH_DECSTATION
 	time->tm_year += real_year - 72;
 #endif
 
+	if (century)
+		time->tm_year += (century - 19) * 100;
+
 	/*
 	 * Account for differences between how the RTC uses the values
 	 * and how they are defined in a struct rtc_time;
@@ -122,6 +135,7 @@ static inline int __set_rtc_time(struct rtc_time *time)
 #ifdef CONFIG_MACH_DECSTATION
 	unsigned int real_yrs, leap_yr;
 #endif
+	unsigned char century = 0;
 
 	yrs = time->tm_year;
 	mon = time->tm_mon + 1;   /* tm_mon starts at zero */
@@ -150,6 +164,15 @@ static inline int __set_rtc_time(struct rtc_time *time)
 		yrs = 73;
 	}
 #endif
+
+#ifdef CONFIG_ACPI
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
+	    acpi_gbl_FADT.century) {
+		century = (yrs + 1900) / 100;
+		yrs %= 100;
+	}
+#endif
+
 	/* These limits and adjustments are independent of
 	 * whether the chip is in binary mode or not.
 	 */
@@ -169,6 +192,7 @@ static inline int __set_rtc_time(struct rtc_time *time)
 		day = bin2bcd(day);
 		mon = bin2bcd(mon);
 		yrs = bin2bcd(yrs);
+		century = bin2bcd(century);
 	}
 
 	save_control = CMOS_READ(RTC_CONTROL);
@@ -185,6 +209,11 @@ static inline int __set_rtc_time(struct rtc_time *time)
 	CMOS_WRITE(hrs, RTC_HOURS);
 	CMOS_WRITE(min, RTC_MINUTES);
 	CMOS_WRITE(sec, RTC_SECONDS);
+#ifdef CONFIG_ACPI
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
+	    acpi_gbl_FADT.century)
+		CMOS_WRITE(century, acpi_gbl_FADT.century);
+#endif
 
 	CMOS_WRITE(save_control, RTC_CONTROL);
 	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8bd374d3c..1781e54ea 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -412,12 +412,10 @@
  * during second ld run in second ld pass when generating System.map */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot)						\
-		*(.text .text.fixup)					\
+		*(.text.hot .text .text.fixup .text.unlikely)		\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
 	MEM_KEEP(exit.text)						\
-		*(.text.unlikely)
 
 
 /* sched.text is aling to function alignment to secure we have same
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 94f9ea8ab..011dde083 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -1,15 +1,10 @@
 #ifndef _ASM_WORD_AT_A_TIME_H
 #define _ASM_WORD_AT_A_TIME_H
 
-/*
- * This says "generic", but it's actually big-endian only.
- * Little-endian can use more efficient versions of these
- * interfaces, see for example
- *	 arch/x86/include/asm/word-at-a-time.h
- * for those.
- */
-
 #include <linux/kernel.h>
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN
 
 struct word_at_a_time {
 	const unsigned long high_bits, low_bits;
@@ -53,4 +48,73 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 #define zero_bytemask(mask) (~1ul << __fls(mask))
 #endif
 
+#else
+
+/*
+ * The optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+	return mask*0x0001020304050608ul >> 56;
+}
+
+#else	/* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+#endif
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return count_masked_bytes(mask);
+}
+
+#endif /* __BIG_ENDIAN */
+
 #endif /* _ASM_WORD_AT_A_TIME_H */