Merge tag 'v5.9-rc2' into drm-misc-fixes

Backmerge requested by Tomi for a fix to omap inconsistent
locking state issue, and because we need at least v5.9-rc2 now.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

17 files changed, 92 insertions, 127 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 2144530d1428..e41c113c6688 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -16,15 +16,14 @@
 
 /*
  * To ensure dependency ordering is preserved for the _relaxed and
- * _release atomics, an smp_read_barrier_depends() is unconditionally
- * inserted into the _relaxed variants, which are used to build the
- * barriered versions. Avoid redundant back-to-back fences in the
- * _acquire and _fence versions.
+ * _release atomics, an smp_mb() is unconditionally inserted into the
+ * _relaxed variants, which are used to build the barriered versions.
+ * Avoid redundant back-to-back fences in the _acquire and _fence
+ * versions.
  */
 #define __atomic_acquire_fence()
 #define __atomic_post_full_fence()
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
@@ -70,7 +69,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -88,7 +87,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -123,7 +122,7 @@ static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -141,7 +140,7 @@ static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 92ec486a4f9e..c56bfffc9918 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -2,64 +2,15 @@
 #ifndef __BARRIER_H
 #define __BARRIER_H
 
-#include <asm/compiler.h>
-
 #define mb()	__asm__ __volatile__("mb": : :"memory")
 #define rmb()	__asm__ __volatile__("mb": : :"memory")
 #define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
+#define __smp_load_acquire(p)						\
+({									\
+	compiletime_assert_atomic_type(*p);				\
+	__READ_ONCE(*p);						\
+})
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
diff --git a/arch/alpha/include/asm/core_apecs.h b/arch/alpha/include/asm/core_apecs.h
index 0a07055bc0fe..2d9726fc02ef 100644
--- a/arch/alpha/include/asm/core_apecs.h
+++ b/arch/alpha/include/asm/core_apecs.h
@@ -384,7 +384,7 @@ struct el_apecs_procdata
 		}						\
 	} while (0)
 
-__EXTERN_INLINE unsigned int apecs_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -420,7 +420,7 @@ __EXTERN_INLINE void apecs_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int apecs_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -456,7 +456,7 @@ __EXTERN_INLINE void apecs_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int apecs_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < APECS_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_cia.h b/arch/alpha/include/asm/core_cia.h
index c706a7f2b061..cb22991f6761 100644
--- a/arch/alpha/include/asm/core_cia.h
+++ b/arch/alpha/include/asm/core_cia.h
@@ -342,7 +342,7 @@ struct el_CIA_sysdata_mcheck {
 #define vuip	volatile unsigned int __force *
 #define vulp	volatile unsigned long __force *
 
-__EXTERN_INLINE unsigned int cia_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -374,7 +374,7 @@ __EXTERN_INLINE void cia_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int cia_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -404,7 +404,7 @@ __EXTERN_INLINE void cia_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int cia_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < CIA_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_lca.h b/arch/alpha/include/asm/core_lca.h
index 84d5e5b84f4f..ec86314418cb 100644
--- a/arch/alpha/include/asm/core_lca.h
+++ b/arch/alpha/include/asm/core_lca.h
@@ -230,7 +230,7 @@ union el_lca {
 	} while (0)
 
 
-__EXTERN_INLINE unsigned int lca_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -266,7 +266,7 @@ __EXTERN_INLINE void lca_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int lca_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -302,7 +302,7 @@ __EXTERN_INLINE void lca_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int lca_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < LCA_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_marvel.h b/arch/alpha/include/asm/core_marvel.h
index cc6fd92d5fa9..b266e02e284b 100644
--- a/arch/alpha/include/asm/core_marvel.h
+++ b/arch/alpha/include/asm/core_marvel.h
@@ -332,10 +332,10 @@ struct io7 {
 #define vucp	volatile unsigned char __force *
 #define vusp	volatile unsigned short __force *
 
-extern unsigned int marvel_ioread8(void __iomem *);
+extern unsigned int marvel_ioread8(const void __iomem *);
 extern void marvel_iowrite8(u8 b, void __iomem *);
 
-__EXTERN_INLINE unsigned int marvel_ioread16(void __iomem *addr)
+__EXTERN_INLINE unsigned int marvel_ioread16(const void __iomem *addr)
 {
 	return __kernel_ldwu(*(vusp)addr);
 }
diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h
index b30dc128210d..cb24d1bd6141 100644
--- a/arch/alpha/include/asm/core_mcpcia.h
+++ b/arch/alpha/include/asm/core_mcpcia.h
@@ -267,7 +267,7 @@ extern inline int __mcpcia_is_mmio(unsigned long addr)
 	return (addr & 0x80000000UL) == 0;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK;
 	unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK;
@@ -291,7 +291,7 @@ __EXTERN_INLINE void mcpcia_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + hose + 0x00) = w;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK;
 	unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK;
@@ -315,7 +315,7 @@ __EXTERN_INLINE void mcpcia_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + hose + 0x08) = w;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr;
 
diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h
index e0b33d09e93a..12bb7addc789 100644
--- a/arch/alpha/include/asm/core_t2.h
+++ b/arch/alpha/include/asm/core_t2.h
@@ -572,7 +572,7 @@ __EXTERN_INLINE int t2_is_mmio(const volatile void __iomem *addr)
    it doesn't make sense to merge the pio and mmio routines.  */
 
 #define IOPORT(OS, NS)							\
-__EXTERN_INLINE unsigned int t2_ioread##NS(void __iomem *xaddr)		\
+__EXTERN_INLINE unsigned int t2_ioread##NS(const void __iomem *xaddr)		\
 {									\
 	if (t2_is_mmio(xaddr))						\
 		return t2_read##OS(xaddr);				\
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index a4d0c19f1e79..1f6a909d1fa5 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -150,9 +150,9 @@ static inline void generic_##NAME(TYPE b, QUAL void __iomem *addr)	\
 	alpha_mv.mv_##NAME(b, addr);					\
 }
 
-REMAP1(unsigned int, ioread8, /**/)
-REMAP1(unsigned int, ioread16, /**/)
-REMAP1(unsigned int, ioread32, /**/)
+REMAP1(unsigned int, ioread8, const)
+REMAP1(unsigned int, ioread16, const)
+REMAP1(unsigned int, ioread32, const)
 REMAP1(u8, readb, const volatile)
 REMAP1(u16, readw, const volatile)
 REMAP1(u32, readl, const volatile)
@@ -307,7 +307,7 @@ static inline int __is_mmio(const volatile void __iomem *addr)
  */
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
-extern inline unsigned int ioread8(void __iomem *addr)
+extern inline unsigned int ioread8(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -316,7 +316,7 @@ extern inline unsigned int ioread8(void __iomem *addr)
 	return ret;
 }
 
-extern inline unsigned int ioread16(void __iomem *addr)
+extern inline unsigned int ioread16(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -359,7 +359,7 @@ extern inline void outw(u16 b, unsigned long port)
 #endif
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
-extern inline unsigned int ioread32(void __iomem *addr)
+extern inline unsigned int ioread32(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -489,10 +489,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 }
 #endif
 
-#define ioread16be(p) be16_to_cpu(ioread16(p))
-#define ioread32be(p) be32_to_cpu(ioread32(p))
-#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p))
-#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p))
+#define ioread16be(p) swab16(ioread16(p))
+#define ioread32be(p) swab32(ioread32(p))
+#define iowrite16be(v,p) iowrite16(swab16(v), (p))
+#define iowrite32be(v,p) iowrite32(swab32(v), (p))
 
 #define inb_p		inb
 #define inw_p		inw
diff --git a/arch/alpha/include/asm/io_trivial.h b/arch/alpha/include/asm/io_trivial.h
index ba3d8f0cfe0c..a1a29cbe02fa 100644
--- a/arch/alpha/include/asm/io_trivial.h
+++ b/arch/alpha/include/asm/io_trivial.h
@@ -7,15 +7,15 @@
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread8)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread8)(const void __iomem *a)
 {
-	return __kernel_ldbu(*(volatile u8 __force *)a);
+	return __kernel_ldbu(*(const volatile u8 __force *)a);
 }
 
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread16)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread16)(const void __iomem *a)
 {
-	return __kernel_ldwu(*(volatile u16 __force *)a);
+	return __kernel_ldwu(*(const volatile u16 __force *)a);
 }
 
 __EXTERN_INLINE void
@@ -33,9 +33,9 @@ IO_CONCAT(__IO_PREFIX,iowrite16)(u16 b, void __iomem *a)
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread32)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread32)(const void __iomem *a)
 {
-	return *(volatile u32 __force *)a;
+	return *(const volatile u32 __force *)a;
 }
 
 __EXTERN_INLINE void
@@ -73,14 +73,14 @@ IO_CONCAT(__IO_PREFIX,writew)(u16 b, volatile void __iomem *a)
 __EXTERN_INLINE u8
 IO_CONCAT(__IO_PREFIX,readb)(const volatile void __iomem *a)
 {
-	void __iomem *addr = (void __iomem *)a;
+	const void __iomem *addr = (const void __iomem *)a;
 	return IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 }
 
 __EXTERN_INLINE u16
 IO_CONCAT(__IO_PREFIX,readw)(const volatile void __iomem *a)
 {
-	void __iomem *addr = (void __iomem *)a;
+	const void __iomem *addr = (const void __iomem *)a;
 	return IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 }
 
diff --git a/arch/alpha/include/asm/jensen.h b/arch/alpha/include/asm/jensen.h
index 436dc905b6ad..916895155a88 100644
--- a/arch/alpha/include/asm/jensen.h
+++ b/arch/alpha/include/asm/jensen.h
@@ -305,7 +305,7 @@ __EXTERN_INLINE int jensen_is_mmio(const volatile void __iomem *addr)
    that it doesn't make sense to merge them.  */
 
 #define IOPORT(OS, NS)							\
-__EXTERN_INLINE unsigned int jensen_ioread##NS(void __iomem *xaddr)	\
+__EXTERN_INLINE unsigned int jensen_ioread##NS(const void __iomem *xaddr)	\
 {									\
 	if (jensen_is_mmio(xaddr))					\
 		return jensen_read##OS(xaddr - 0x100000000ul);		\
diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h
index a6b73c6d10ee..a4e96e2bec74 100644
--- a/arch/alpha/include/asm/machvec.h
+++ b/arch/alpha/include/asm/machvec.h
@@ -46,9 +46,9 @@ struct alpha_machine_vector
 	void (*mv_pci_tbi)(struct pci_controller *hose,
 			   dma_addr_t start, dma_addr_t end);
 
-	unsigned int (*mv_ioread8)(void __iomem *);
-	unsigned int (*mv_ioread16)(void __iomem *);
-	unsigned int (*mv_ioread32)(void __iomem *);
+	unsigned int (*mv_ioread8)(const void __iomem *);
+	unsigned int (*mv_ioread16)(const void __iomem *);
+	unsigned int (*mv_ioread32)(const void __iomem *);
 
 	void (*mv_iowrite8)(u8, void __iomem *);
 	void (*mv_iowrite16)(u16, void __iomem *);
diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h
index a1a29f60934c..9c6a24fe493d 100644
--- a/arch/alpha/include/asm/pgalloc.h
+++ b/arch/alpha/include/asm/pgalloc.h
@@ -5,7 +5,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 
-#include <asm-generic/pgalloc.h>	/* for pte_{alloc,free}_one */
+#include <asm-generic/pgalloc.h>
 
 /*      
  * Allocate and free page tables. The xxx_kernel() versions are
@@ -34,23 +34,4 @@ pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
-static inline void
-pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	free_page((unsigned long)pgd);
-}
-
-static inline pmd_t *
-pmd_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-	pmd_t *ret = (pmd_t *)__get_free_page(GFP_PGTABLE_USER);
-	return ret;
-}
-
-static inline void
-pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-	free_page((unsigned long)pmd);
-}
-
 #endif /* _ALPHA_PGALLOC_H */
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 162c17b2631f..660b14ce1317 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -277,9 +277,9 @@ extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; retur
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
 
 /*
- * The smp_read_barrier_depends() in the following functions are required to
- * order the load of *dir (the pointer in the top level page table) with any
- * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir).
+ * The smp_rmb() in the following functions are required to order the load of
+ * *dir (the pointer in the top level page table) with any subsequent load of
+ * the returned pmd_t *ret (ret is data dependent on *dir).
  *
  * If this ordering is not enforced, the CPU might load an older value of
  * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
@@ -293,7 +293,7 @@ extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; retu
 extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
 {
 	pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pmd_offset pmd_offset
@@ -303,7 +303,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
 {
 	pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
 		+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pte_offset_kernel pte_offset_kernel
diff --git a/arch/alpha/include/asm/rwonce.h b/arch/alpha/include/asm/rwonce.h
new file mode 100644
index 000000000000..35542bcf92b3
--- /dev/null
+++ b/arch/alpha/include/asm/rwonce.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#ifdef CONFIG_SMP
+
+#include <asm/barrier.h>
+
+/*
+ * Alpha is apparently daft enough to reorder address-dependent loads
+ * on some CPU implementations. Knock some common sense into it with
+ * a memory barrier in READ_ONCE().
+ *
+ * For the curious, more information about this unusual reordering is
+ * available in chapter 15 of the "perfbook":
+ *
+ *  https://kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.html
+ *
+ */
+#define __READ_ONCE(x)							\
+({									\
+	__unqual_scalar_typeof(x) __x =					\
+		(*(volatile typeof(__x) *)(&(x)));			\
+	mb();								\
+	(typeof(x))__x;							\
+})
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/rwonce.h>
+
+#endif /* __ASM_RWONCE_H */
diff --git a/arch/alpha/include/asm/tlbflush.h b/arch/alpha/include/asm/tlbflush.h
index f8b492408f51..94dc37cf873a 100644
--- a/arch/alpha/include/asm/tlbflush.h
+++ b/arch/alpha/include/asm/tlbflush.h
@@ -5,7 +5,6 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <asm/compiler.h>
-#include <asm/pgalloc.h>
 
 #ifndef __EXTERN_INLINE
 #define __EXTERN_INLINE extern inline
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 1fe2b56cb861..1b6f25efa247 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -20,7 +20,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * Is a address valid? This does a straightforward calculation rather