Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/m68k/mm/cache.c b/arch/m68k/mm/cache.c
index 079e648..b486c08 100644
--- a/arch/m68k/mm/cache.c
+++ b/arch/m68k/mm/cache.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
 #include <asm/traps.h>
 
 
@@ -73,7 +73,7 @@
 
 /* Push n pages at kernel virtual address and clear the icache */
 /* RZ: use cpush %bc instead of cpush %dc, cinv %ic */
-void flush_icache_range(unsigned long address, unsigned long endaddr)
+void flush_icache_user_range(unsigned long address, unsigned long endaddr)
 {
 	if (CPU_IS_COLDFIRE) {
 		unsigned long start, end;
@@ -104,9 +104,18 @@
 			      : "di" (FLUSH_I));
 	}
 }
+
+void flush_icache_range(unsigned long address, unsigned long endaddr)
+{
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	flush_icache_user_range(address, endaddr);
+	set_fs(old_fs);
+}
 EXPORT_SYMBOL(flush_icache_range);
 
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			     unsigned long addr, int len)
 {
 	if (CPU_IS_COLDFIRE) {
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index e9b1d75..ef46e77 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -12,10 +12,10 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/pgalloc.h>
 
 extern void die_if_kernel(char *, struct pt_regs *, long);
 
@@ -71,7 +71,7 @@
 	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);
@@ -85,8 +85,10 @@
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -116,7 +118,7 @@
 	pr_debug("do_page_fault: good_area\n");
 	switch (error_code & 3) {
 		default:	/* 3: write, present */
-			/* fall through */
+			fallthrough;
 		case 2:		/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto acc_err;
@@ -125,7 +127,7 @@
 		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;
 	}
 
@@ -135,10 +137,10 @@
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 	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)) {
@@ -151,24 +153,12 @@
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		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;
 
 			/*
-			 * No need to up_read(&mm->mmap_sem) as we would
+			 * No need to mmap_read_unlock(mm) as we would
 			 * have already released it in __lock_page_or_retry
 			 * in mm/filemap.c.
 			 */
@@ -177,7 +167,7 @@
 		}
 	}
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return 0;
 
 /*
@@ -185,7 +175,7 @@
  * us unable to handle the page fault gracefully.
  */
 out_of_memory:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();
@@ -214,6 +204,6 @@
 	current->thread.faddr = address;
 
 send_sig:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return send_fault_sig(regs);
 }
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 778cacb..5304085 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];
@@ -89,7 +84,7 @@
 	 * page_alloc get different views of the world.
 	 */
 	unsigned long end_mem = memory_end & PAGE_MASK;
-	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, };
 
 	high_memory = (void *) end_mem;
 
@@ -103,8 +98,8 @@
 	 */
 	set_fs (USER_DS);
 
-	zones_size[ZONE_DMA] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
-	free_area_init(zones_size);
+	max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT;
+	free_area_init(max_zone_pfn);
 }
 
 #endif /* CONFIG_MMU */
@@ -125,18 +120,31 @@
 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++) {
-		if (pgd_present(kernel_pg_dir[i]))
-			init_pointer_table(__pgd_page(kernel_pg_dir[i]));
-	}
+		pud_t *pud = (pud_t *)&kernel_pg_dir[i];
+		pmd_t *pmd_dir;
 
-	/* insert also pointer table that we used to unmap the zero page */
-	if (zero_pgtable)
-		init_pointer_table((unsigned long)zero_pgtable);
+		if (!pud_present(*pud))
+			continue;
+
+		pmd_dir = (pmd_t *)pgd_page_vaddr(kernel_pg_dir[i]);
+		init_pointer_table(pmd_dir, TABLE_PMD);
+
+		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_vaddr(*pmd);
+			init_pointer_table(pte_dir, TABLE_PTE);
+		}
+	}
 #endif
 }
 
diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index 40a3b32..1269d51 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -19,13 +19,11 @@
 #include <asm/setup.h>
 #include <asm/segment.h>
 #include <asm/page.h>
-#include <asm/pgalloc.h>
 #include <asm/io.h>
+#include <asm/tlbflush.h>
 
 #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
@@ -50,10 +48,64 @@
 
 #else
 
-#define IO_SIZE		(256*1024)
+#define IO_SIZE		PMD_SIZE
 
 static struct vm_struct *iolist;
 
+/*
+ * __free_io_area unmaps nearly everything, so be careful
+ * Currently it doesn't free pointer/page tables anymore but this
+ * wasn't used anyway and might be added later.
+ */
+static void __free_io_area(void *addr, unsigned long size)
+{
+	unsigned long virtaddr = (unsigned long)addr;
+	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
+	pmd_t *pmd_dir;
+	pte_t *pte_dir;
+
+	while ((long)size > 0) {
+		pgd_dir = pgd_offset_k(virtaddr);
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		if (pud_bad(*pud_dir)) {
+			printk("iounmap: bad pud(%08lx)\n", pud_val(*pud_dir));
+			pud_clear(pud_dir);
+			return;
+		}
+		pmd_dir = pmd_offset(pud_dir, virtaddr);
+
+#if CONFIG_PGTABLE_LEVELS == 3
+		if (CPU_IS_020_OR_030) {
+			int pmd_type = pmd_val(*pmd_dir) & _DESCTYPE_MASK;
+
+			if (pmd_type == _PAGE_PRESENT) {
+				pmd_clear(pmd_dir);
+				virtaddr += PMD_SIZE;
+				size -= PMD_SIZE;
+
+			} else if (pmd_type == 0)
+				continue;
+		}
+#endif
+
+		if (pmd_bad(*pmd_dir)) {
+			printk("iounmap: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
+			pmd_clear(pmd_dir);
+			return;
+		}
+		pte_dir = pte_offset_kernel(pmd_dir, virtaddr);
+
+		pte_val(*pte_dir) = 0;
+		virtaddr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+
+	flush_tlb_all();
+}
+
 static struct vm_struct *get_io_area(unsigned long size)
 {
 	unsigned long addr;
@@ -90,7 +142,7 @@
 		if (tmp->addr == addr) {
 			*p = tmp->next;
 			/* remove gap added in get_io_area() */
-			__iounmap(tmp->addr, tmp->size - IO_SIZE);
+			__free_io_area(tmp->addr, tmp->size - IO_SIZE);
 			kfree(tmp);
 			return;
 		}
@@ -110,6 +162,8 @@
 	unsigned long virtaddr, retaddr;
 	long offset;
 	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
@@ -192,22 +246,27 @@
 
 	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);
-		pmd_dir = pmd_alloc(&init_mm, pgd_dir, virtaddr);
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		pmd_dir = pmd_alloc(&init_mm, pud_dir, virtaddr);
 		if (!pmd_dir) {
 			printk("ioremap: no mem for pmd_dir\n");
 			return NULL;
 		}
 
+#if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
-			pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr;
-			physaddr += PTRTREESIZE;
-			virtaddr += PTRTREESIZE;
-			size -= PTRTREESIZE;
-		} else {
+			pmd_val(*pmd_dir) = physaddr;
+			physaddr += PMD_SIZE;
+			virtaddr += PMD_SIZE;
+			size -= PMD_SIZE;
+		} else
+#endif
+		{
 			pte_dir = pte_alloc_kernel(pmd_dir, virtaddr);
 			if (!pte_dir) {
 				printk("ioremap: no mem for pte_dir\n");
@@ -250,55 +309,6 @@
 EXPORT_SYMBOL(iounmap);
 
 /*
- * __iounmap unmaps nearly everything, so be careful
- * Currently it doesn't free pointer/page tables anymore but this
- * wasn't used anyway and might be added later.
- */
-void __iounmap(void *addr, unsigned long size)
-{
-	unsigned long virtaddr = (unsigned long)addr;
-	pgd_t *pgd_dir;
-	pmd_t *pmd_dir;
-	pte_t *pte_dir;
-
-	while ((long)size > 0) {
-		pgd_dir = pgd_offset_k(virtaddr);
-		if (pgd_bad(*pgd_dir)) {
-			printk("iounmap: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
-			pgd_clear(pgd_dir);
-			return;
-		}
-		pmd_dir = pmd_offset(pgd_dir, virtaddr);
-
-		if (CPU_IS_020_OR_030) {
-			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
-			int pmd_type = pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK;
-
-			if (pmd_type == _PAGE_PRESENT) {
-				pmd_dir->pmd[pmd_off] = 0;
-				virtaddr += PTRTREESIZE;
-				size -= PTRTREESIZE;
-				continue;
-			} else if (pmd_type == 0)
-				continue;
-		}
-
-		if (pmd_bad(*pmd_dir)) {
-			printk("iounmap: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
-			pmd_clear(pmd_dir);
-			return;
-		}
-		pte_dir = pte_offset_kernel(pmd_dir, virtaddr);
-
-		pte_val(*pte_dir) = 0;
-		virtaddr += PAGE_SIZE;
-		size -= PAGE_SIZE;
-	}
-
-	flush_tlb_all();
-}
-
-/*
  * Set new cache mode for some kernel address space.
  * The caller must push data for that range itself, if such data may already
  * be in the cache.
@@ -307,6 +317,8 @@
 {
 	unsigned long virtaddr = (unsigned long)addr;
 	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
@@ -341,24 +353,27 @@
 
 	while ((long)size > 0) {
 		pgd_dir = pgd_offset_k(virtaddr);
-		if (pgd_bad(*pgd_dir)) {
-			printk("iocachemode: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
-			pgd_clear(pgd_dir);
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		if (pud_bad(*pud_dir)) {
+			printk("iocachemode: bad pud(%08lx)\n", pud_val(*pud_dir));
+			pud_clear(pud_dir);
 			return;
 		}
-		pmd_dir = pmd_offset(pgd_dir, virtaddr);
+		pmd_dir = pmd_offset(pud_dir, virtaddr);
 
+#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;
 			}
 		}
+#endif
 
 		if (pmd_bad(*pmd_dir)) {
 			printk("iocachemode: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 70a5f55..eac9dde 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -17,10 +17,10 @@
 
 #include <asm/setup.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 #include <asm/mcf_pgalloc.h>
 #include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
 
 #define KMAPAREA(x)	((x >= VMALLOC_START) && (x < KMAP_END))
 
@@ -39,11 +39,10 @@
 	pte_t *pg_table;
 	unsigned long address, size;
 	unsigned long next_pgtable, bootmem_end;
-	unsigned long zones_size[MAX_NR_ZONES];
-	enum zone_type zone;
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
 	int i;
 
-	empty_zero_page = (void *) memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 	if (!empty_zero_page)
 		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
 		      __func__, PAGE_SIZE, PAGE_SIZE);
@@ -80,11 +79,8 @@
 	}
 
 	current->mm = NULL;
-
-	for (zone = 0; zone < MAX_NR_ZONES; zone++)
-		zones_size[zone] = 0x0;
-	zones_size[ZONE_DMA] = num_pages;
-	free_area_init(zones_size);
+	max_zone_pfn[ZONE_DMA] = PFN_DOWN(_ramend);
+	free_area_init(max_zone_pfn);
 }
 
 int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
@@ -92,6 +88,8 @@
 	unsigned long flags, mmuar, mmutr;
 	struct mm_struct *mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	int asid;
@@ -113,7 +111,19 @@
 		return -1;
 	}
 
-	pmd = pmd_offset(pgd, mmuar);
+	p4d = p4d_offset(pgd, mmuar);
+	if (p4d_none(*p4d)) {
+		local_irq_restore(flags);
+		return -1;
+	}
+
+	pud = pud_offset(p4d, mmuar);
+	if (pud_none(*pud)) {
+		local_irq_restore(flags);
+		return -1;
+	}
+
+	pmd = pmd_offset(pud, mmuar);
 	if (pmd_none(*pmd)) {
 		local_irq_restore(flags);
 		return -1;
@@ -204,11 +214,6 @@
 
 /*
  * Steal a context from a task that has one at the moment.
- * This is only used on 8xx and 4xx and we presently assume that
- * they don't do SMP.  If they do then thicfpgalloc.hs will have to check
- * whether the MM we steal is in use.
- * We also assume that this is only used on systems that don't
- * use an MMU hash table - this is true for 8xx and 4xx.
  * This isn't an LRU system, it just frees up each context in
  * turn (sort-of pseudo-random replacement :).  This would be the
  * place to implement an LRU scheme if anyone was motivated to do it.
diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c
index 227c04f..fe75aec 100644
--- a/arch/m68k/mm/memory.c
+++ b/arch/m68k/mm/memory.c
@@ -17,114 +17,10 @@
 #include <asm/setup.h>
 #include <asm/segment.h>
 #include <asm/page.h>
-#include <asm/pgalloc.h>
 #include <asm/traps.h>
 #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 356601b..3a653f0 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -45,34 +45,210 @@
 EXPORT_SYMBOL(mm_cachebits);
 #endif
 
+/* Prior to calling these routines, the page should have been flushed
+ * from both the cache and ATC, or the CPU might not notice that the
+ * cache setting for the page has been changed. -jskov
+ */
+static inline void nocache_page(void *vaddr)
+{
+	unsigned long addr = (unsigned long)vaddr;
+
+	if (CPU_IS_040_OR_060) {
+		pte_t *ptep = virt_to_kpte(addr);
+
+		*ptep = pte_mknocache(*ptep);
+	}
+}
+
+static inline void cache_page(void *vaddr)
+{
+	unsigned long addr = (unsigned long)vaddr;
+
+	if (CPU_IS_040_OR_060) {
+		pte_t *ptep = virt_to_kpte(addr);
+
+		*ptep = pte_mkcache(*ptep);
+	}
+}
+
+/*
+ * 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 (PAGE_ALIGNED(last_pte_table)) {
+		pte_table = 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;
 
@@ -82,42 +258,41 @@
 		 */
 		last = (unsigned long)kernel_pg_dir;
 		for (i = 0; i < PTRS_PER_PGD; i++) {
-			if (!pgd_present(kernel_pg_dir[i]))
+			pud_t *pud = (pud_t *)(&kernel_pg_dir[i]);
+
+			if (!pud_present(*pud))
 				continue;
-			pmd = __pgd_page(kernel_pg_dir[i]);
+			pmd = pgd_page_vaddr(kernel_pg_dir[i]);
 			if (pmd > last)
 				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,
-							   PAGE_SIZE);
-		if (!last_pgtable)
+	last_pmd_table += PTRS_PER_PMD;
+	if (PAGE_ALIGNED(last_pmd_table)) {
+		last_pmd_table = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+		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;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
@@ -131,56 +306,57 @@
 
 	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;
 			}
 		}
-		if (!pgd_present(*pgd_dir)) {
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		if (!pud_present(*pud_dir)) {
 			pmd_dir = kernel_ptr_table();
 #ifdef DEBUG
 			printk ("[new pointer %p]", pmd_dir);
 #endif
-			pgd_set(pgd_dir, pmd_dir);
+			pud_set(pud_dir, pmd_dir);
 		} else
-			pmd_dir = pmd_offset(pgd_dir, virtaddr);
+			pmd_dir = pmd_offset(pud_dir, virtaddr);
 
 		if (CPU_IS_020_OR_030) {
 			if (virtaddr) {
 #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
@@ -213,7 +389,7 @@
  */
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, };
 	unsigned long min_addr, max_addr;
 	unsigned long addr;
 	int i;
@@ -234,7 +410,7 @@
 
 	min_addr = m68k_memory[0].addr;
 	max_addr = min_addr + m68k_memory[0].size;
-	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0);
 	for (i = 1; i < m68k_num_memory;) {
 		if (m68k_memory[i].addr < min_addr) {
 			printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n",
@@ -245,7 +421,7 @@
 				(m68k_num_memory - i) * sizeof(struct m68k_mem_info));
 			continue;
 		}
-		memblock_add(m68k_memory[i].addr, m68k_memory[i].size);
+		memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i);
 		addr = m68k_memory[i].addr + m68k_memory[i].size;
 		if (addr > max_addr)
 			max_addr = addr;
@@ -296,12 +472,10 @@
 #ifdef DEBUG
 	printk ("before free_area_init\n");
 #endif
-	for (i = 0; i < m68k_num_memory; i++) {
-		zones_size[ZONE_DMA] = m68k_memory[i].size >> PAGE_SHIFT;
-		free_area_init_node(i, zones_size,
-				    m68k_memory[i].addr >> PAGE_SHIFT, NULL);
+	for (i = 0; i < m68k_num_memory; i++)
 		if (node_present_pages(i))
 			node_set_state(i, N_NORMAL_MEMORY);
-	}
-}
 
+	max_zone_pfn[ZONE_DMA] = memblock_end_of_DRAM();
+	free_area_init(max_zone_pfn);
+}
diff --git a/arch/m68k/mm/sun3kmap.c b/arch/m68k/mm/sun3kmap.c
index ae03555..4f2a7ef 100644
--- a/arch/m68k/mm/sun3kmap.c
+++ b/arch/m68k/mm/sun3kmap.c
@@ -15,7 +15,6 @@
 #include <linux/vmalloc.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/sun3mmu.h>
 
diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c
index eca1c46..dad4942 100644
--- a/arch/m68k/mm/sun3mmu.c
+++ b/arch/m68k/mm/sun3mmu.c
@@ -21,7 +21,6 @@
 #include <asm/setup.h>
 #include <linux/uaccess.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
 
@@ -42,7 +41,7 @@
 	unsigned long address;
 	unsigned long next_pgtable;
 	unsigned long bootmem_end;
-	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, };
 	unsigned long size;
 
 	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
@@ -89,14 +88,10 @@
 	current->mm = NULL;
 
 	/* memory sizing is a hack stolen from motorola.c..  hope it works for us */
-	zones_size[ZONE_DMA] = ((unsigned long)high_memory - PAGE_OFFSET) >> PAGE_SHIFT;
+	max_zone_pfn[ZONE_DMA] = ((unsigned long)high_memory) >> PAGE_SHIFT;
 
 	/* I really wish I knew why the following change made things better...  -- Sam */
-/*	free_area_init(zones_size); */
-	free_area_init_node(0, zones_size,
-			    (__pa(PAGE_OFFSET) >> PAGE_SHIFT) + 1, NULL);
+	free_area_init(max_zone_pfn);
 
 
 }
-
-