19 files changed, 99 insertions, 178 deletions

diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index e928618838bc..6024c26c0585 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += preempt.h
+generic-y += rwsem.h
 generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += types.h
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7dcbebbcaec6..ee3f11c43cda 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,9 +20,10 @@
 #define ATOMIC_INIT(i)  { (i) }
 
 int atomic_add_return(int, atomic_t *);
-void atomic_and(int, atomic_t *);
-void atomic_or(int, atomic_t *);
-void atomic_xor(int, atomic_t *);
+int atomic_fetch_add(int, atomic_t *);
+int atomic_fetch_and(int, atomic_t *);
+int atomic_fetch_or(int, atomic_t *);
+int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
@@ -35,7 +36,13 @@ void atomic_set(atomic_t *, int);
 #define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
 #define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
+#define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
+#define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
+#define atomic_xor(i, v)	((void)atomic_fetch_xor((i), (v)))
+
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
+#define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
+
 #define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
 #define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f2fbf9e16faf..24827a3f733a 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -28,16 +28,24 @@ void atomic64_##op(long, atomic64_t *);
 int atomic_##op##_return(int, atomic_t *);				\
 long atomic64_##op##_return(long, atomic64_t *);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+int atomic_fetch_##op(int, atomic_t *);					\
+long atomic64_fetch_##op(long, atomic64_t *);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sparc/include/asm/head_32.h b/arch/sparc/include/asm/head_32.h
index 5f1dbe315bc8..6fc60fd182c4 100644
--- a/arch/sparc/include/asm/head_32.h
+++ b/arch/sparc/include/asm/head_32.h
@@ -43,10 +43,10 @@
 	nop;
 
 #ifdef CONFIG_KGDB
-#define KGDB_TRAP(num) \
-	b kgdb_trap_low; \
-	rd %psr,%l0; \
-	nop; \
+#define KGDB_TRAP(num)                  \
+	mov num, %l7;                   \
+	b kgdb_trap_low;                \
+	rd %psr,%l0;                    \
 	nop;
 #else
 #define KGDB_TRAP(num) \
diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h
index 10e9dabc4c41..f0700cfeedd7 100644
--- a/arch/sparc/include/asm/head_64.h
+++ b/arch/sparc/include/asm/head_64.h
@@ -15,6 +15,10 @@
 
 #define	PTREGS_OFF	(STACK_BIAS + STACKFRAME_SZ)
 
+#define	RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define	RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
 #define __CHEETAH_ID	0x003e0014
 #define __JALAPENO_ID	0x003e0016
 #define __SERRANO_ID	0x003e0022
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 139e711ff80c..dcbf985ab243 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -31,14 +31,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
@@ -82,4 +74,8 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
+			    unsigned long end, unsigned long floor,
+			    unsigned long ceiling);
+
 #endif /* _ASM_SPARC64_HUGETLB_H */
diff --git a/arch/sparc/include/asm/kgdb.h b/arch/sparc/include/asm/kgdb.h
index 47366af7a589..a6ad7bf84bac 100644
--- a/arch/sparc/include/asm/kgdb.h
+++ b/arch/sparc/include/asm/kgdb.h
@@ -28,10 +28,10 @@ enum regnames {
 #define NUMREGBYTES		((GDB_CSR + 1) * 4)
 #else
 #define NUMREGBYTES		((GDB_Y + 1) * 8)
+#endif
 
 struct pt_regs;
 asmlinkage void kgdb_trap(unsigned long trap_level, struct pt_regs *regs);
-#endif
 
 void arch_kgdb_breakpoint(void);
 
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index 70067ce184b1..f7de0dbc38af 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -92,7 +92,8 @@ struct tsb_config {
 typedef struct {
 	spinlock_t		lock;
 	unsigned long		sparc64_ctx_val;
-	unsigned long		huge_pte_count;
+	unsigned long		hugetlb_pte_count;
+	unsigned long		thp_pte_count;
 	struct tsb_config	tsb_block[MM_NUM_TSBS];
 	struct hv_tsb_descr	tsb_descr[MM_NUM_TSBS];
 } mm_context_t;
diff --git a/arch/sparc/include/asm/page_32.h b/arch/sparc/include/asm/page_32.h
index f82a1f36b655..0efd0583a8c9 100644
--- a/arch/sparc/include/asm/page_32.h
+++ b/arch/sparc/include/asm/page_32.h
@@ -69,7 +69,6 @@ typedef struct { unsigned long iopgprot; } iopgprot_t;
 
 #define __pte(x)	((pte_t) { (x) } )
 #define __iopte(x)	((iopte_t) { (x) } )
-/* #define __pmd(x)        ((pmd_t) { (x) } ) */ /* XXX procedure with loop */
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __ctxd(x)	((ctxd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
@@ -97,7 +96,6 @@ typedef unsigned long iopgprot_t;
 
 #define __pte(x)	(x)
 #define __iopte(x)	(x)
-/* #define __pmd(x)        (x) */ /* XXX later */
 #define __pgd(x)	(x)
 #define __ctxd(x)	(x)
 #define __pgprot(x)	(x)
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index a3890da94428..0346c7e62452 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -29,9 +29,9 @@ static inline void free_pgd_fast(pgd_t *pgd)
 
 static inline void pgd_set(pgd_t * pgdp, pmd_t * pmdp)
 {
-	unsigned long pa = __nocache_pa((unsigned long)pmdp);
+	unsigned long pa = __nocache_pa(pmdp);
 
-	set_pte((pte_t *)pgdp, (SRMMU_ET_PTD | (pa >> 4)));
+	set_pte((pte_t *)pgdp, __pte((SRMMU_ET_PTD | (pa >> 4))));
 }
 
 #define pgd_populate(MM, PGD, PMD)      pgd_set(PGD, PMD)
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5e3187185b4a..3529f1378cd8 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -41,8 +41,7 @@ static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache,
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -52,8 +51,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache,
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 91b963a887b7..ce6f56980aef 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -298,7 +298,7 @@ static inline pte_t mk_pte_io(unsigned long page, pgprot_t pgprot, int space)
 #define pgprot_noncached pgprot_noncached
 static inline pgprot_t pgprot_noncached(pgprot_t prot)
 {
-	prot &= ~__pgprot(SRMMU_CACHE);
+	pgprot_val(prot) &= ~pgprot_val(__pgprot(SRMMU_CACHE));
 	return prot;
 }
 
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index f089cfa249f3..1fb317fbc0b3 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -375,7 +375,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 #define pgprot_noncached pgprot_noncached
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline pte_t pte_mkhuge(pte_t pte)
+static inline unsigned long __pte_huge_mask(void)
 {
 	unsigned long mask;
 
@@ -390,8 +390,24 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	: "=r" (mask)
 	: "i" (_PAGE_SZHUGE_4U), "i" (_PAGE_SZHUGE_4V));
 
-	return __pte(pte_val(pte) | mask);
+	return mask;
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_PMD_HUGE | __pte_huge_mask());
+}
+
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return !!(pte_val(pte) & __pte_huge_mask());
 }
+
+static inline bool is_hugetlb_pmd(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & _PAGE_PMD_HUGE);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
@@ -403,6 +419,11 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 #endif
+#else
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return false;
+}
 #endif
 
 static inline pte_t pte_mkdirty(pte_t pte)
@@ -681,8 +702,6 @@ static inline unsigned long pmd_trans_huge(pmd_t pmd)
 	return pte_val(pte) & _PAGE_PMD_HUGE;
 }
 
-#define has_transparent_hugepage() 1
-
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
@@ -858,6 +877,19 @@ static inline unsigned long pud_pfn(pud_t pud)
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm);
 
+static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+				pte_t *ptep, pte_t orig, int fullmm)
+{
+	/* It is more efficient to let flush_tlb_kernel_range()
+	 * handle init_mm tlb flushes.
+	 *
+	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
+	 *             and SUN4V pte layout, so this inline test is fine.
+	 */
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
+		tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+}
+
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr,
@@ -874,15 +906,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pte_t orig = *ptep;
 
 	*ptep = pte;
-
-	/* It is more efficient to let flush_tlb_kernel_range()
-	 * handle init_mm tlb flushes.
-	 *
-	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
-	 *             and SUN4V pte layout, so this inline test is fine.
-	 */
-	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
-		tlb_batch_add(mm, addr, ptep, orig, fullmm);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
 #define set_pte_at(mm,addr,ptep,pte)	\
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
deleted file mode 100644
index 069bf4d663a1..000000000000
--- a/arch/sparc/include/asm/rwsem.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * rwsem.h: R/W semaphores implemented using CAS
- *
- * Written by David S. Miller (davem@redhat.com), 2001.
- * Derived from asm-i386/rwsem.h
- */
-#ifndef _SPARC64_RWSEM_H
-#define _SPARC64_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_ACTIVE_MASK		0xffffffffL
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic64_inc_return((atomic64_t *)(&sem->count)) <= 0L))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	while ((tmp = sem->count) >= 0L) {
-		if (tmp == cmpxchg(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
-{
-	long tmp;
-
-	tmp = atomic64_add_return(RWSEM_ACTIVE_WRITE_BIAS,
-				  (atomic64_t *)(&sem->count));
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		rwsem_down_write_failed(sem);
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	__down_write_nested(sem, 0);
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic64_dec_return((atomic64_t *)(&sem->count));
-	if (unlikely(tmp < -1L && (tmp & RWSEM_ACTIVE_MASK) == 0L))
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic64_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-					 (atomic64_t *)(&sem->count)) < 0L))
-		rwsem_wake(sem);
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	atomic64_add(delta, (atomic64_t *)(&sem->count));
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic64_add_return(-RWSEM_WAITING_BIAS, (atomic64_t *)(&sem->count));
-	if (tmp < 0L)
-		rwsem_downgrade_wake(sem);
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return atomic64_add_return(delta, (atomic64_t *)(&sem->count));
-}
-
-#endif /* __KERNEL__ */
-
-#endif /* _SPARC64_RWSEM_H */
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index bcc98fc35281..d9c5876c6121 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -9,12 +9,15 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/psr.h>
+#include <asm/barrier.h>
 #include <asm/processor.h> /* for cpu_relax */
 
 #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0)
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 968917694978..87990b7c6b0d 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -8,6 +8,9 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/processor.h>
+#include <asm/barrier.h>
+
 /* To get debugging spinlocks which detect and catch
  * deadlock situations, set CONFIG_DEBUG_SPINLOCK
  * and rebuild your kernel.
@@ -23,9 +26,10 @@
 
 #define arch_spin_is_locked(lp)	((lp)->lock != 0)
 
-#define arch_spin_unlock_wait(lp)	\
-	do {	rmb();			\
-	} while((lp)->lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index dea1cfa2122b..a8e192e90700 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -8,6 +8,7 @@
 #define TLB_BATCH_NR	192
 
 struct tlb_batch {
+	bool huge;
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
 	unsigned long active;
@@ -16,7 +17,7 @@ struct tlb_batch {
 
 void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);
 
 /* TLB flush operations. */
 
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index c6a155c3904e..32258e08da03 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -203,7 +203,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * We have to propagate the 4MB bit of the virtual address
 	 * because we are fabricating 8MB pages using 4MB hw pages.
 	 */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
 #define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
 	brz,pn		REG1, FAIL_LABEL;		\
 	 sethi		%uhi(_PAGE_PMD_HUGE), REG2;	\
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 71b5a67522ab..781b9f1dbdc2 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -589,8 +589,8 @@ user_rtt_fill_64bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop; nop;			\
 	nop; nop; nop; nop; nop;			\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
@@ -652,8 +652,8 @@ user_rtt_fill_32bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
 	nop; nop; nop;					\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;