5 files changed, 226 insertions, 184 deletions

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index e9b1d7585b43..3bfb5c8ac3c7 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -71,7 +71,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct * vma;
 	vm_fault_t fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
 
 	pr_debug("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
 		regs->sr, regs->pc, address, error_code, mm ? mm->pgd : NULL);
@@ -125,7 +125,7 @@ good_area:
 		case 1:		/* read, present */
 			goto acc_err;
 		case 0:		/* read, not present */
-			if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+			if (unlikely(!vma_is_accessible(vma)))
 				goto acc_err;
 	}
 
@@ -138,7 +138,7 @@ good_area:
 	fault = handle_mm_fault(vma, address, flags);
 	pr_debug("handle_mm_fault returns %x\n", fault);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if (fault_signal_pending(fault, regs))
 		return 0;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
@@ -162,9 +162,6 @@ good_area:
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/*
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 27c453f4fffe..b88d510d4fe3 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -40,11 +40,6 @@
 void *empty_zero_page;
 EXPORT_SYMBOL(empty_zero_page);
 
-#if !defined(CONFIG_SUN3) && !defined(CONFIG_COLDFIRE)
-extern void init_pointer_table(unsigned long ptable);
-extern pmd_t *zero_pgtable;
-#endif
-
 #ifdef CONFIG_MMU
 
 pg_data_t pg_data_map[MAX_NUMNODES];
@@ -125,20 +120,31 @@ void free_initmem(void)
 static inline void init_pointer_tables(void)
 {
 #if defined(CONFIG_MMU) && !defined(CONFIG_SUN3) && !defined(CONFIG_COLDFIRE)
-	int i;
+	int i, j;
 
 	/* insert pointer tables allocated so far into the tablelist */
-	init_pointer_table((unsigned long)kernel_pg_dir);
+	init_pointer_table(kernel_pg_dir, TABLE_PGD);
 	for (i = 0; i < PTRS_PER_PGD; i++) {
-		pud_t *pud = (pud_t *)(&kernel_pg_dir[i]);
+		pud_t *pud = (pud_t *)&kernel_pg_dir[i];
+		pmd_t *pmd_dir;
 
-		if (pud_present(*pud))
-			init_pointer_table(pgd_page_vaddr(kernel_pg_dir[i]));
-	}
+		if (!pud_present(*pud))
+			continue;
+
+		pmd_dir = (pmd_t *)pgd_page_vaddr(kernel_pg_dir[i]);
+		init_pointer_table(pmd_dir, TABLE_PMD);
 
-	/* insert also pointer table that we used to unmap the zero page */
-	if (zero_pgtable)
-		init_pointer_table((unsigned long)zero_pgtable);
+		for (j = 0; j < PTRS_PER_PMD; j++) {
+			pmd_t *pmd = &pmd_dir[j];
+			pte_t *pte_dir;
+
+			if (!pmd_present(*pmd))
+				continue;
+
+			pte_dir = (pte_t *)__pmd_page(*pmd);
+			init_pointer_table(pte_dir, TABLE_PTE);
+		}
+	}
 #endif
 }
 
diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index 120030ad8dc4..14d31d216cef 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -24,8 +24,6 @@
 
 #undef DEBUG
 
-#define PTRTREESIZE	(256*1024)
-
 /*
  * For 040/060 we can use the virtual memory area like other architectures,
  * but for 020/030 we want to use early termination page descriptors and we
@@ -50,7 +48,7 @@ static inline void free_io_area(void *addr)
 
 #else
 
-#define IO_SIZE		(256*1024)
+#define IO_SIZE		PMD_SIZE
 
 static struct vm_struct *iolist;
 
@@ -81,14 +79,13 @@ static void __free_io_area(void *addr, unsigned long size)
 
 #if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
-			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
-			int pmd_type = pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK;
+			int pmd_type = pmd_val(*pmd_dir) & _DESCTYPE_MASK;
 
 			if (pmd_type == _PAGE_PRESENT) {
-				pmd_dir->pmd[pmd_off] = 0;
-				virtaddr += PTRTREESIZE;
-				size -= PTRTREESIZE;
-				continue;
+				pmd_clear(pmd_dir);
+				virtaddr += PMD_SIZE;
+				size -= PMD_SIZE;
+
 			} else if (pmd_type == 0)
 				continue;
 		}
@@ -249,7 +246,7 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
 
 	while ((long)size > 0) {
 #ifdef DEBUG
-		if (!(virtaddr & (PTRTREESIZE-1)))
+		if (!(virtaddr & (PMD_SIZE-1)))
 			printk ("\npa=%#lx va=%#lx ", physaddr, virtaddr);
 #endif
 		pgd_dir = pgd_offset_k(virtaddr);
@@ -263,10 +260,10 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
 
 #if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
-			pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr;
-			physaddr += PTRTREESIZE;
-			virtaddr += PTRTREESIZE;
-			size -= PTRTREESIZE;
+			pmd_val(*pmd_dir) = physaddr;
+			physaddr += PMD_SIZE;
+			virtaddr += PMD_SIZE;
+			size -= PMD_SIZE;
 		} else
 #endif
 		{
@@ -367,13 +364,12 @@ void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
 
 #if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
-			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
+			unsigned long pmd = pmd_val(*pmd_dir);
 
-			if ((pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK) == _PAGE_PRESENT) {
-				pmd_dir->pmd[pmd_off] = (pmd_dir->pmd[pmd_off] &
-							 _CACHEMASK040) | cmode;
-				virtaddr += PTRTREESIZE;
-				size -= PTRTREESIZE;
+			if ((pmd & _DESCTYPE_MASK) == _PAGE_PRESENT) {
+				*pmd_dir = __pmd((pmd & _CACHEMASK040) | cmode);
+				virtaddr += PMD_SIZE;
+				size -= PMD_SIZE;
 				continue;
 			}
 		}
diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c
index 227c04fe60d2..65e0c4071912 100644
--- a/arch/m68k/mm/memory.c
+++ b/arch/m68k/mm/memory.c
@@ -22,109 +22,6 @@
 #include <asm/machdep.h>
 
 
-/* ++andreas: {get,free}_pointer_table rewritten to use unused fields from
-   struct page instead of separately kmalloced struct.  Stolen from
-   arch/sparc/mm/srmmu.c ... */
-
-typedef struct list_head ptable_desc;
-static LIST_HEAD(ptable_list);
-
-#define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page(page)->lru))
-#define PD_PAGE(ptable) (list_entry(ptable, struct page, lru))
-#define PD_MARKBITS(dp) (*(unsigned char *)&PD_PAGE(dp)->index)
-
-#define PTABLE_SIZE (PTRS_PER_PMD * sizeof(pmd_t))
-
-void __init init_pointer_table(unsigned long ptable)
-{
-	ptable_desc *dp;
-	unsigned long page = ptable & PAGE_MASK;
-	unsigned char mask = 1 << ((ptable - page)/PTABLE_SIZE);
-
-	dp = PD_PTABLE(page);
-	if (!(PD_MARKBITS(dp) & mask)) {
-		PD_MARKBITS(dp) = 0xff;
-		list_add(dp, &ptable_list);
-	}
-
-	PD_MARKBITS(dp) &= ~mask;
-	pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
-
-	/* unreserve the page so it's possible to free that page */
-	__ClearPageReserved(PD_PAGE(dp));
-	init_page_count(PD_PAGE(dp));
-
-	return;
-}
-
-pmd_t *get_pointer_table (void)
-{
-	ptable_desc *dp = ptable_list.next;
-	unsigned char mask = PD_MARKBITS (dp);
-	unsigned char tmp;
-	unsigned int off;
-
-	/*
-	 * For a pointer table for a user process address space, a
-	 * table is taken from a page allocated for the purpose.  Each
-	 * page can hold 8 pointer tables.  The page is remapped in
-	 * virtual address space to be noncacheable.
-	 */
-	if (mask == 0) {
-		void *page;
-		ptable_desc *new;
-
-		if (!(page = (void *)get_zeroed_page(GFP_KERNEL)))
-			return NULL;
-
-		flush_tlb_kernel_page(page);
-		nocache_page(page);
-
-		new = PD_PTABLE(page);
-		PD_MARKBITS(new) = 0xfe;
-		list_add_tail(new, dp);
-
-		return (pmd_t *)page;
-	}
-
-	for (tmp = 1, off = 0; (mask & tmp) == 0; tmp <<= 1, off += PTABLE_SIZE)
-		;
-	PD_MARKBITS(dp) = mask & ~tmp;
-	if (!PD_MARKBITS(dp)) {
-		/* move to end of list */
-		list_move_tail(dp, &ptable_list);
-	}
-	return (pmd_t *) (page_address(PD_PAGE(dp)) + off);
-}
-
-int free_pointer_table (pmd_t *ptable)
-{
-	ptable_desc *dp;
-	unsigned long page = (unsigned long)ptable & PAGE_MASK;
-	unsigned char mask = 1 << (((unsigned long)ptable - page)/PTABLE_SIZE);
-
-	dp = PD_PTABLE(page);
-	if (PD_MARKBITS (dp) & mask)
-		panic ("table already free!");
-
-	PD_MARKBITS (dp) |= mask;
-
-	if (PD_MARKBITS(dp) == 0xff) {
-		/* all tables in page are free, free page */
-		list_del(dp);
-		cache_page((void *)page);
-		free_page (page);
-		return 1;
-	} else if (ptable_list.next != dp) {
-		/*
-		 * move this descriptor to the front of the list, since
-		 * it has one or more free tables.
-		 */
-		list_move(dp, &ptable_list);
-	}
-	return 0;
-}
-
 /* invalidate page in both caches */
 static inline void clear040(unsigned long paddr)
 {
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 4857985b8080..fc16190ec2d6 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -45,34 +45,185 @@ unsigned long mm_cachebits;
 EXPORT_SYMBOL(mm_cachebits);
 #endif
 
+
+/*
+ * Motorola 680x0 user's manual recommends using uncached memory for address
+ * translation tables.
+ *
+ * Seeing how the MMU can be external on (some of) these chips, that seems like
+ * a very important recommendation to follow. Provide some helpers to combat
+ * 'variation' amongst the users of this.
+ */
+
+void mmu_page_ctor(void *page)
+{
+	__flush_page_to_ram(page);
+	flush_tlb_kernel_page(page);
+	nocache_page(page);
+}
+
+void mmu_page_dtor(void *page)
+{
+	cache_page(page);
+}
+
+/* ++andreas: {get,free}_pointer_table rewritten to use unused fields from
+   struct page instead of separately kmalloced struct.  Stolen from
+   arch/sparc/mm/srmmu.c ... */
+
+typedef struct list_head ptable_desc;
+
+static struct list_head ptable_list[2] = {
+	LIST_HEAD_INIT(ptable_list[0]),
+	LIST_HEAD_INIT(ptable_list[1]),
+};
+
+#define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page(page)->lru))
+#define PD_PAGE(ptable) (list_entry(ptable, struct page, lru))
+#define PD_MARKBITS(dp) (*(unsigned int *)&PD_PAGE(dp)->index)
+
+static const int ptable_shift[2] = {
+	7+2, /* PGD, PMD */
+	6+2, /* PTE */
+};
+
+#define ptable_size(type) (1U << ptable_shift[type])
+#define ptable_mask(type) ((1U << (PAGE_SIZE / ptable_size(type))) - 1)
+
+void __init init_pointer_table(void *table, int type)
+{
+	ptable_desc *dp;
+	unsigned long ptable = (unsigned long)table;
+	unsigned long page = ptable & PAGE_MASK;
+	unsigned int mask = 1U << ((ptable - page)/ptable_size(type));
+
+	dp = PD_PTABLE(page);
+	if (!(PD_MARKBITS(dp) & mask)) {
+		PD_MARKBITS(dp) = ptable_mask(type);
+		list_add(dp, &ptable_list[type]);
+	}
+
+	PD_MARKBITS(dp) &= ~mask;
+	pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
+
+	/* unreserve the page so it's possible to free that page */
+	__ClearPageReserved(PD_PAGE(dp));
+	init_page_count(PD_PAGE(dp));
+
+	return;
+}
+
+void *get_pointer_table(int type)
+{
+	ptable_desc *dp = ptable_list[type].next;
+	unsigned int mask = list_empty(&ptable_list[type]) ? 0 : PD_MARKBITS(dp);
+	unsigned int tmp, off;
+
+	/*
+	 * For a pointer table for a user process address space, a
+	 * table is taken from a page allocated for the purpose.  Each
+	 * page can hold 8 pointer tables.  The page is remapped in
+	 * virtual address space to be noncacheable.
+	 */
+	if (mask == 0) {
+		void *page;
+		ptable_desc *new;
+
+		if (!(page = (void *)get_zeroed_page(GFP_KERNEL)))
+			return NULL;
+
+		if (type == TABLE_PTE) {
+			/*
+			 * m68k doesn't have SPLIT_PTE_PTLOCKS for not having
+			 * SMP.
+			 */
+			pgtable_pte_page_ctor(virt_to_page(page));
+		}
+
+		mmu_page_ctor(page);
+
+		new = PD_PTABLE(page);
+		PD_MARKBITS(new) = ptable_mask(type) - 1;
+		list_add_tail(new, dp);
+
+		return (pmd_t *)page;
+	}
+
+	for (tmp = 1, off = 0; (mask & tmp) == 0; tmp <<= 1, off += ptable_size(type))
+		;
+	PD_MARKBITS(dp) = mask & ~tmp;
+	if (!PD_MARKBITS(dp)) {
+		/* move to end of list */
+		list_move_tail(dp, &ptable_list[type]);
+	}
+	return page_address(PD_PAGE(dp)) + off;
+}
+
+int free_pointer_table(void *table, int type)
+{
+	ptable_desc *dp;
+	unsigned long ptable = (unsigned long)table;
+	unsigned long page = ptable & PAGE_MASK;
+	unsigned int mask = 1U << ((ptable - page)/ptable_size(type));
+
+	dp = PD_PTABLE(page);
+	if (PD_MARKBITS (dp) & mask)
+		panic ("table already free!");
+
+	PD_MARKBITS (dp) |= mask;
+
+	if (PD_MARKBITS(dp) == ptable_mask(type)) {
+		/* all tables in page are free, free page */
+		list_del(dp);
+		mmu_page_dtor((void *)page);
+		if (type == TABLE_PTE)
+			pgtable_pte_page_dtor(virt_to_page(page));
+		free_page (page);
+		return 1;
+	} else if (ptable_list[type].next != dp) {
+		/*
+		 * move this descriptor to the front of the list, since
+		 * it has one or more free tables.
+		 */
+		list_move(dp, &ptable_list[type]);
+	}
+	return 0;
+}
+
 /* size of memory already mapped in head.S */
 extern __initdata unsigned long m68k_init_mapped_size;
 
 extern unsigned long availmem;
 
+static pte_t *last_pte_table __initdata = NULL;
+
 static pte_t * __init kernel_page_table(void)
 {
-	pte_t *ptablep;
+	pte_t *pte_table = last_pte_table;
 
-	ptablep = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
-	if (!ptablep)
-		panic("%s: Failed to allocate %lu bytes align=%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	if (((unsigned long)last_pte_table & ~PAGE_MASK) == 0) {
+		pte_table = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+		if (!pte_table) {
+			panic("%s: Failed to allocate %lu bytes align=%lx\n",
+					__func__, PAGE_SIZE, PAGE_SIZE);
+		}
 
-	clear_page(ptablep);
-	__flush_page_to_ram(ptablep);
-	flush_tlb_kernel_page(ptablep);
-	nocache_page(ptablep);
+		clear_page(pte_table);
+		mmu_page_ctor(pte_table);
 
-	return ptablep;
+		last_pte_table = pte_table;
+	}
+
+	last_pte_table += PTRS_PER_PTE;
+
+	return pte_table;
 }
 
-static pmd_t *last_pgtable __initdata = NULL;
-pmd_t *zero_pgtable __initdata = NULL;
+static pmd_t *last_pmd_table __initdata = NULL;
 
 static pmd_t * __init kernel_ptr_table(void)
 {
-	if (!last_pgtable) {
+	if (!last_pmd_table) {
 		unsigned long pmd, last;
 		int i;
 
@@ -91,33 +242,29 @@ static pmd_t * __init kernel_ptr_table(void)
 				last = pmd;
 		}
 
-		last_pgtable = (pmd_t *)last;
+		last_pmd_table = (pmd_t *)last;
 #ifdef DEBUG
-		printk("kernel_ptr_init: %p\n", last_pgtable);
+		printk("kernel_ptr_init: %p\n", last_pmd_table);
 #endif
 	}
 
-	last_pgtable += PTRS_PER_PMD;
-	if (((unsigned long)last_pgtable & ~PAGE_MASK) == 0) {
-		last_pgtable = (pmd_t *)memblock_alloc_low(PAGE_SIZE,
+	last_pmd_table += PTRS_PER_PMD;
+	if (((unsigned long)last_pmd_table & ~PAGE_MASK) == 0) {
+		last_pmd_table = (pmd_t *)memblock_alloc_low(PAGE_SIZE,
 							   PAGE_SIZE);
-		if (!last_pgtable)
+		if (!last_pmd_table)
 			panic("%s: Failed to allocate %lu bytes align=%lx\n",
 			      __func__, PAGE_SIZE, PAGE_SIZE);
 
-		clear_page(last_pgtable);
-		__flush_page_to_ram(last_pgtable);
-		flush_tlb_kernel_page(last_pgtable);
-		nocache_page(last_pgtable);
+		clear_page(last_pmd_table);
+		mmu_page_ctor(last_pmd_table);
 	}
 
-	return last_pgtable;
+	return last_pmd_table;
 }
 
 static void __init map_node(int node)
 {
-#define PTRTREESIZE (256*1024)
-#define ROOTTREESIZE (32*1024*1024)
 	unsigned long physaddr, virtaddr, size;
 	pgd_t *pgd_dir;
 	p4d_t *p4d_dir;
@@ -135,21 +282,21 @@ static void __init map_node(int node)
 
 	while (size > 0) {
 #ifdef DEBUG
-		if (!(virtaddr & (PTRTREESIZE-1)))
+		if (!(virtaddr & (PMD_SIZE-1)))
 			printk ("\npa=%#lx va=%#lx ", physaddr & PAGE_MASK,
 				virtaddr);
 #endif
 		pgd_dir = pgd_offset_k(virtaddr);
 		if (virtaddr && CPU_IS_020_OR_030) {
-			if (!(virtaddr & (ROOTTREESIZE-1)) &&
-			    size >= ROOTTREESIZE) {
+			if (!(virtaddr & (PGDIR_SIZE-1)) &&
+			    size >= PGDIR_SIZE) {
 #ifdef DEBUG
 				printk ("[very early term]");
 #endif
 				pgd_val(*pgd_dir) = physaddr;
-				size -= ROOTTREESIZE;
-				virtaddr += ROOTTREESIZE;
-				physaddr += ROOTTREESIZE;
+				size -= PGDIR_SIZE;
+				virtaddr += PGDIR_SIZE;
+				physaddr += PGDIR_SIZE;
 				continue;
 			}
 		}
@@ -169,24 +316,23 @@ static void __init map_node(int node)
 #ifdef DEBUG
 				printk ("[early term]");
 #endif
-				pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr;
-				physaddr += PTRTREESIZE;
+				pmd_val(*pmd_dir) = physaddr;
+				physaddr += PMD_SIZE;
 			} else {
 				int i;
 #ifdef DEBUG
 				printk ("[zero map]");
 #endif
-				zero_pgtable = kernel_ptr_table();
-				pte_dir = (pte_t *)zero_pgtable;
-				pmd_dir->pmd[0] = virt_to_phys(pte_dir) |
-					_PAGE_TABLE | _PAGE_ACCESSED;
+				pte_dir = kernel_page_table();
+				pmd_set(pmd_dir, pte_dir);
+
 				pte_val(*pte_dir++) = 0;
 				physaddr += PAGE_SIZE;
-				for (i = 1; i < 64; physaddr += PAGE_SIZE, i++)
+				for (i = 1; i < PTRS_PER_PTE; physaddr += PAGE_SIZE, i++)
 					pte_val(*pte_dir++) = physaddr;
 			}
-			size -= PTRTREESIZE;
-			virtaddr += PTRTREESIZE;
+			size -= PMD_SIZE;
+			virtaddr += PMD_SIZE;
 		} else {
 			if (!pmd_present(*pmd_dir)) {
 #ifdef DEBUG