Merge bk://kernel.bkbits.net/davem/sparc-2.6

into ppc970.osdl.org:/home/torvalds/v2.6/linux

arch/sparc64/kernel/process.c

@@ -434,14 +434,13 @@ void flush_thread(void)
 		if (test_thread_flag(TIF_32BIT)) {
 			struct mm_struct *mm = t->task->mm;
 			pgd_t *pgd0 = &mm->pgd[0];
+			pud_t *pud0 = pud_offset(pgd0, 0);
 
-			if (pgd_none(*pgd0)) {
-				pmd_t *page = pmd_alloc_one_fast(NULL, 0);
-				if (!page)
-					page = pmd_alloc_one(NULL, 0);
-				pgd_set(pgd0, page);
+			if (pud_none(*pud0)) {
+				pmd_t *page = pmd_alloc_one(mm, 0);
+				pud_set(pud0, page);
 			}
-			pgd_cache = ((unsigned long) pgd_val(*pgd0)) << 11UL;
+			pgd_cache = ((unsigned long) pud_val(*pud0)) << 11UL;
 		}
 		__asm__ __volatile__("stxa %0, [%1] %2\n\t"
 				     "membar #Sync"

arch/sparc64/kernel/setup.c

@@ -151,6 +151,7 @@ int prom_callback(long *args)
 			struct task_struct *p;
 			struct mm_struct *mm = NULL;
 			pgd_t *pgdp;
+			pud_t *pudp;
 			pmd_t *pmdp;
 			pte_t *ptep;
 
@@ -166,7 +167,10 @@ int prom_callback(long *args)
 			pgdp = pgd_offset(mm, va);
 			if (pgd_none(*pgdp))
 				goto done;
-			pmdp = pmd_offset(pgdp, va);
+			pudp = pud_offset(pgdp, va);
+			if (pud_none(*pudp))
+				goto done;
+			pmdp = pmd_offset(pudp, va);
 			if (pmd_none(*pmdp))
 				goto done;
 
@@ -208,6 +212,7 @@ int prom_callback(long *args)
 			 * vmalloc or prom_inherited mapping.
 			 */
 			pgd_t *pgdp;
+			pud_t *pudp;
 			pmd_t *pmdp;
 			pte_t *ptep;
 			int error;
@@ -221,7 +226,10 @@ int prom_callback(long *args)
 			pgdp = pgd_offset_k(va);
 			if (pgd_none(*pgdp))
 				goto done;
-			pmdp = pmd_offset(pgdp, va);
+			pudp = pud_offset(pgdp, va);
+			if (pud_none(*pudp))
+				goto done;
+			pmdp = pmd_offset(pudp, va);
 			if (pmd_none(*pmdp))
 				goto done;
 

arch/sparc64/kernel/signal32.c

@@ -857,7 +857,8 @@ static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 		/* Flush instruction space. */
 		unsigned long address = ((unsigned long)&(sf->insns[0]));
 		pgd_t *pgdp = pgd_offset(current->mm, address);
-		pmd_t *pmdp = pmd_offset(pgdp, address);
+		pud_t *pudp = pud_offset(pgdp, address);
+		pmd_t *pmdp = pmd_offset(pudp, address);
 		pte_t *ptep;
 
 		regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2);
@@ -1268,7 +1269,8 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 		/* Flush instruction space. */
 		unsigned long address = ((unsigned long)&(sf->insns[0]));
 		pgd_t *pgdp = pgd_offset(current->mm, address);
-		pmd_t *pmdp = pmd_offset(pgdp, address);
+		pud_t *pudp = pud_offset(pgdp, address);
+		pmd_t *pmdp = pmd_offset(pudp, address);
 		pte_t *ptep;
 
 		regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2);

arch/sparc64/lib/atomic.S

@@ -7,8 +7,22 @@
 #include <asm/asi.h>
 
 	.text
-	.align	64
 
+	/* We use these stubs for the uncommon case
+	 * of contention on the atomic value.  This is
+	 * so that we can keep the main fast path 8
+	 * instructions long and thus fit into a single
+	 * L2 cache line.
+	 */
+__atomic_add_membar:
+	ba,pt	%xcc, __atomic_add
+	 membar	#StoreLoad | #StoreStore
+
+__atomic_sub_membar:
+	ba,pt	%xcc, __atomic_sub
+	 membar	#StoreLoad | #StoreStore
+
+	.align	64
 	.globl	__atomic_add
 	.type	__atomic_add,#function
 __atomic_add: /* %o0 = increment, %o1 = atomic_ptr */
@@ -16,10 +30,10 @@ __atomic_add: /* %o0 = increment, %o1 = atomic_ptr */
 	add	%g5, %o0, %g7
 	cas	[%o1], %g5, %g7
 	cmp	%g5, %g7
-	bne,pn	%icc, __atomic_add
-	 membar	#StoreLoad | #StoreStore
+	bne,pn	%icc, __atomic_add_membar
+	 add	%g7, %o0, %g7
 	retl
-	 add	%g7, %o0, %o0
+	 sra	%g7, 0, %o0
 	.size	__atomic_add, .-__atomic_add
 
 	.globl	__atomic_sub
@@ -29,10 +43,10 @@ __atomic_sub: /* %o0 = increment, %o1 = atomic_ptr */
 	sub	%g5, %o0, %g7
 	cas	[%o1], %g5, %g7
 	cmp	%g5, %g7
-	bne,pn	%icc, __atomic_sub
-	 membar	#StoreLoad | #StoreStore
+	bne,pn	%icc, __atomic_sub_membar
+	 sub	%g7, %o0, %g7
 	retl
-	 sub	%g7, %o0, %o0
+	 sra	%g7, 0, %o0
 	.size	__atomic_sub, .-__atomic_sub
 
 	.globl	__atomic64_add

arch/sparc64/mm/fault.c

@@ -175,6 +175,7 @@ static void bad_kernel_pc(struct pt_regs *regs)
 static unsigned int get_user_insn(unsigned long tpc)
 {
 	pgd_t *pgdp = pgd_offset(current->mm, tpc);
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep, pte;
 	unsigned long pa;
@@ -183,7 +184,10 @@ static unsigned int get_user_insn(unsigned long tpc)
 
 	if (pgd_none(*pgdp))
 		goto outret;
-	pmdp = pmd_offset(pgdp, tpc);
+	pudp = pud_offset(pgdp, tpc);
+	if (pud_none(*pudp))
+		goto outret;
+	pmdp = pmd_offset(pudp, tpc);
 	if (pmd_none(*pmdp))
 		goto outret;
 

arch/sparc64/mm/generic.c

@@ -96,6 +96,27 @@ static inline int io_remap_pmd_range(pmd_t * pmd, unsigned long address, unsigne
 	return 0;
 }
 
+static inline int io_remap_pud_range(pud_t * pud, unsigned long address, unsigned long size,
+	unsigned long offset, pgprot_t prot, int space)
+{
+	unsigned long end;
+
+	address &= ~PUD_MASK;
+	end = address + size;
+	if (end > PUD_SIZE)
+		end = PUD_SIZE;
+	offset -= address;
+	do {
+		pmd_t *pmd = pmd_alloc(current->mm, pud, address);
+		if (!pud)
+			return -ENOMEM;
+		io_remap_pmd_range(pmd, address, end - address, address + offset, prot, space);
+		address = (address + PUD_SIZE) & PUD_MASK;
+		pud++;
+	} while (address < end);
+	return 0;
+}
+
 int io_remap_page_range(struct vm_area_struct *vma, unsigned long from, unsigned long offset, unsigned long size, pgprot_t prot, int space)
 {
 	int error = 0;
@@ -111,11 +132,11 @@ int io_remap_page_range(struct vm_area_struct *vma, unsigned long from, unsigned
 
 	spin_lock(&mm->page_table_lock);
 	while (from < end) {
-		pmd_t *pmd = pmd_alloc(current->mm, dir, from);
+		pud_t *pud = pud_alloc(current->mm, dir, from);
 		error = -ENOMEM;
-		if (!pmd)
+		if (!pud)
 			break;
-		error = io_remap_pmd_range(pmd, from, end - from, offset + from, prot, space);
+		error = io_remap_pud_range(pud, from, end - from, offset + from, prot, space);
 		if (error)
 			break;
 		from = (from + PGDIR_SIZE) & PGDIR_MASK;

arch/sparc64/mm/hugetlbpage.c

@@ -24,14 +24,18 @@
 static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd) {
-		pmd = pmd_alloc(mm, pgd, addr);
-		if (pmd)
-			pte = pte_alloc_map(mm, pmd, addr);
+		pud = pud_offset(pgd, addr);
+		if (pud) {
+			pmd = pmd_alloc(mm, pud, addr);
+			if (pmd)
+				pte = pte_alloc_map(mm, pmd, addr);
+		}
 	}
 	return pte;
 }
@@ -39,14 +43,18 @@ static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd) {
-		pmd = pmd_offset(pgd, addr);
-		if (pmd)
-			pte = pte_offset_map(pmd, addr);
+		pud = pud_offset(pgd, addr);
+		if (pud) {
+			pmd = pmd_offset(pud, addr);
+			if (pmd)
+				pte = pte_offset_map(pmd, addr);
+		}
 	}
 	return pte;
 }

arch/sparc64/mm/init.c

@@ -1462,7 +1462,8 @@ void __init paging_init(void)
 	memset(swapper_pmd_dir, 0, sizeof(swapper_pmd_dir));
 
 	/* Now can init the kernel/bad page tables. */
-	pgd_set(&swapper_pg_dir[0], swapper_pmd_dir + (shift / sizeof(pgd_t)));
+	pud_set(pud_offset(&swapper_pg_dir[0], 0),
+		swapper_pmd_dir + (shift / sizeof(pgd_t)));
 	
 	sparc64_vpte_patchme1[0] |=
 		(((unsigned long)pgd_val(init_mm.pgd[0])) >> 10);

include/asm-sparc64/page.h

@@ -21,11 +21,14 @@ extern void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
 #define copy_page(X,Y)	memcpy((void *)(X), (void *)(Y), PAGE_SIZE)
 extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
 
-/* GROSS, defining this makes gcc pass these types as aggregates,
- * and thus on the stack, turn this crap off... -DaveM
+/* Unlike sparc32, sparc64's parameter passing API is more
+ * sane in that structures which as small enough are passed
+ * in registers instead of on the stack.  Thus, setting
+ * STRICT_MM_TYPECHECKS does not generate worse code so
+ * let's enable it to get the type checking.
  */
 
-/* #define STRICT_MM_TYPECHECKS */
+#define STRICT_MM_TYPECHECKS
 
 #ifdef STRICT_MM_TYPECHECKS
 /* These are used to make use of C type-checking.. */
@@ -33,25 +36,19 @@ typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long iopte; } iopte_t;
 typedef struct { unsigned int pmd; } pmd_t;
 typedef struct { unsigned int pgd; } pgd_t;
-typedef struct { unsigned long ctxd; } ctxd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
-typedef struct { unsigned long iopgprot; } iopgprot_t;
 
 #define pte_val(x)	((x).pte)
 #define iopte_val(x)	((x).iopte)
 #define pmd_val(x)      ((x).pmd)
 #define pgd_val(x)	((x).pgd)
-#define ctxd_val(x)	((x).ctxd)
 #define pgprot_val(x)	((x).pgprot)
-#define iopgprot_val(x)	((x).iopgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
 #define __iopte(x)	((iopte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
 #define __pgd(x)	((pgd_t) { (x) } )
-#define __ctxd(x)	((ctxd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
-#define __iopgprot(x)	((iopgprot_t) { (x) } )
 
 #else
 /* .. while these make it easier on the compiler */
@@ -59,25 +56,19 @@ typedef unsigned long pte_t;
 typedef unsigned long iopte_t;
 typedef unsigned int pmd_t;
 typedef unsigned int pgd_t;
-typedef unsigned long ctxd_t;
 typedef unsigned long pgprot_t;
-typedef unsigned long iopgprot_t;
 
 #define pte_val(x)	(x)
 #define iopte_val(x)	(x)
 #define pmd_val(x)      (x)
 #define pgd_val(x)	(x)
-#define ctxd_val(x)	(x)
 #define pgprot_val(x)	(x)
-#define iopgprot_val(x)	(x)
 
 #define __pte(x)	(x)
 #define __iopte(x)	(x)
 #define __pmd(x)        (x)
 #define __pgd(x)	(x)
-#define __ctxd(x)	(x)
 #define __pgprot(x)	(x)
-#define __iopgprot(x)	(x)
 
 #endif /* (STRICT_MM_TYPECHECKS) */
 

include/asm-sparc64/pgalloc.h

@@ -133,7 +133,7 @@ static __inline__ void free_pgd_slow(pgd_t *pgd)
 #define DCACHE_COLOR(address)		0
 #endif
 
-#define pgd_populate(MM, PGD, PMD)	pgd_set(PGD, PMD)
+#define pud_populate(MM, PUD, PMD)	pud_set(PUD, PMD)
 
 static __inline__ pmd_t *pmd_alloc_one_fast(struct mm_struct *mm, unsigned long address)
 {

include/asm-sparc64/pgtable.h

@@ -12,7 +12,7 @@
  * the SpitFire page tables.
  */
 
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopud.h>
 
 #include <linux/config.h>
 #include <asm/spitfire.h>
@@ -263,23 +263,23 @@ static inline pte_t pte_modify(pte_t orig_pte, pgprot_t new_prot)
 }
 #define pmd_set(pmdp, ptep)	\
 	(pmd_val(*(pmdp)) = (__pa((unsigned long) (ptep)) >> 11UL))
-#define pgd_set(pgdp, pmdp)	\
-	(pgd_val(*(pgdp)) = (__pa((unsigned long) (pmdp)) >> 11UL))
+#define pud_set(pudp, pmdp)	\
+	(pud_val(*(pudp)) = (__pa((unsigned long) (pmdp)) >> 11UL))
 #define __pmd_page(pmd)		\
 	((unsigned long) __va((((unsigned long)pmd_val(pmd))<<11UL)))
 #define pmd_page(pmd) 			virt_to_page((void *)__pmd_page(pmd))
-#define pgd_page(pgd)		\
-	((unsigned long) __va((((unsigned long)pgd_val(pgd))<<11UL)))
+#define pud_page(pud)		\
+	((unsigned long) __va((((unsigned long)pud_val(pud))<<11UL)))
 #define pte_none(pte) 			(!pte_val(pte))
 #define pte_present(pte)		(pte_val(pte) & _PAGE_PRESENT)
 #define pmd_none(pmd)			(!pmd_val(pmd))
 #define pmd_bad(pmd)			(0)
 #define pmd_present(pmd)		(pmd_val(pmd) != 0U)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0U)
-#define pgd_none(pgd)			(!pgd_val(pgd))
-#define pgd_bad(pgd)			(0)
-#define pgd_present(pgd)		(pgd_val(pgd) != 0U)
-#define pgd_clear(pgdp)			(pgd_val(*(pgdp)) = 0U)
+#define pud_none(pud)			(!pud_val(pud))
+#define pud_bad(pud)			(0)
+#define pud_present(pud)		(pud_val(pud) != 0U)
+#define pud_clear(pudp)			(pud_val(*(pudp)) = 0U)
 
 /* The following only work if pte_present() is true.
  * Undefined behaviour if not..
@@ -313,8 +313,8 @@ static inline pte_t pte_modify(pte_t orig_pte, pgprot_t new_prot)
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
 /* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, address)	\
-	((pmd_t *) pgd_page(*(dir)) + \
+#define pmd_offset(pudp, address)	\
+	((pmd_t *) pud_page(*(pudp)) + \
 	 (((address) >> PMD_SHIFT) & (REAL_PTRS_PER_PMD-1)))
 
 /* Find an entry in the third-level page table.. */
@@ -384,6 +384,7 @@ static __inline__ unsigned long
 sun4u_get_pte (unsigned long addr)
 {
 	pgd_t *pgdp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 
@@ -392,7 +393,8 @@ sun4u_get_pte (unsigned long addr)
 	if ((addr >= LOW_OBP_ADDRESS) && (addr < HI_OBP_ADDRESS))
 		return prom_virt_to_phys(addr, NULL);
 	pgdp = pgd_offset_k(addr);
-	pmdp = pmd_offset(pgdp, addr);
+	pudp = pud_offset(pgdp, addr);
+	pmdp = pmd_offset(pudp, addr);
 	ptep = pte_offset_kernel(pmdp, addr);
 	return pte_val(*ptep) & _PAGE_PADDR;
 }

include/asm-sparc64/tlb.h

@@ -121,6 +121,7 @@ static inline void tlb_remove_page(struct mmu_gather *mp, struct page *page)
 #define tlb_remove_tlb_entry(mp,ptep,addr) do { } while (0)
 #define pte_free_tlb(mp,ptepage) pte_free(ptepage)
 #define pmd_free_tlb(mp,pmdp) pmd_free(pmdp)
+#define pud_free_tlb(tlb,pudp) __pud_free_tlb(tlb,pudp)
 
 #define tlb_migrate_finish(mm)	do { } while (0)
 #define tlb_start_vma(tlb, vma) do { } while (0)

mm/memory.c

@@ -2096,7 +2096,6 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
 }
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
-#if (PTRS_PER_PUD > 1)
 /*
  * Allocate page upper directory.
  *
@@ -2125,12 +2124,10 @@ pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long addr
 		goto out;
 	}
 	pgd_populate(mm, pgd, new);
-out:
+ out:
 	return pud_offset(pgd, address);
 }
-#endif
 
-#if (PTRS_PER_PMD > 1)
 /*
  * Allocate page middle directory.
  *
@@ -2159,10 +2156,9 @@ pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr
 		goto out;
 	}
 	pud_populate(mm, pud, new);
-out:
+ out:
 	return pmd_offset(pud, address);
 }
-#endif
 #else
 pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 {