sparc,sparc64: unify mm/

- move all sparc64/mm/ files to arch/sparc/mm/
- commonly named files are named _64.c
- add files to sparc/mm/Makefile preserving link order
- delete now unused sparc64/mm/Makefile
- sparc64 now finds mm/ in sparc

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 2360 insertions, 0 deletions

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
new file mode 100644
index 00000000000..6ea73da2931
--- /dev/null
+++ b/arch/sparc/mm/init_64.c
@@ -0,0 +1,2360 @@
+/*
+ *  arch/sparc64/mm/init.c
+ *
+ *  Copyright (C) 1996-1999 David S. Miller (davem@caip.rutgers.edu)
+ *  Copyright (C) 1997-1999 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ */
+ 
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/slab.h>
+#include <linux/initrd.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/poison.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/kprobes.h>
+#include <linux/cache.h>
+#include <linux/sort.h>
+#include <linux/percpu.h>
+#include <linux/lmb.h>
+#include <linux/mmzone.h>
+
+#include <asm/head.h>
+#include <asm/system.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/oplib.h>
+#include <asm/iommu.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/dma.h>
+#include <asm/starfire.h>
+#include <asm/tlb.h>
+#include <asm/spitfire.h>
+#include <asm/sections.h>
+#include <asm/tsb.h>
+#include <asm/hypervisor.h>
+#include <asm/prom.h>
+#include <asm/mdesc.h>
+#include <asm/cpudata.h>
+#include <asm/irq.h>
+
+#include "init_64.h"
+
+unsigned long kern_linear_pte_xor[2] __read_mostly;
+
+/* A bitmap, one bit for every 256MB of physical memory.  If the bit
+ * is clear, we should use a 4MB page (via kern_linear_pte_xor[0]) else
+ * if set we should use a 256MB page (via kern_linear_pte_xor[1]).
+ */
+unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
+
+#ifndef CONFIG_DEBUG_PAGEALLOC
+/* A special kernel TSB for 4MB and 256MB linear mappings.
+ * Space is allocated for this right after the trap table
+ * in arch/sparc64/kernel/head.S
+ */
+extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES];
+#endif
+
+#define MAX_BANKS	32
+
+static struct linux_prom64_registers pavail[MAX_BANKS] __initdata;
+static int pavail_ents __initdata;
+
+static int cmp_p64(const void *a, const void *b)
+{
+	const struct linux_prom64_registers *x = a, *y = b;
+
+	if (x->phys_addr > y->phys_addr)
+		return 1;
+	if (x->phys_addr < y->phys_addr)
+		return -1;
+	return 0;
+}
+
+static void __init read_obp_memory(const char *property,
+				   struct linux_prom64_registers *regs,
+				   int *num_ents)
+{
+	int node = prom_finddevice("/memory");
+	int prop_size = prom_getproplen(node, property);
+	int ents, ret, i;
+
+	ents = prop_size / sizeof(struct linux_prom64_registers);
+	if (ents > MAX_BANKS) {
+		prom_printf("The machine has more %s property entries than "
+			    "this kernel can support (%d).\n",
+			    property, MAX_BANKS);
+		prom_halt();
+	}
+
+	ret = prom_getproperty(node, property, (char *) regs, prop_size);
+	if (ret == -1) {
+		prom_printf("Couldn't get %s property from /memory.\n");
+		prom_halt();
+	}
+
+	/* Sanitize what we got from the firmware, by page aligning
+	 * everything.
+	 */
+	for (i = 0; i < ents; i++) {
+		unsigned long base, size;
+
+		base = regs[i].phys_addr;
+		size = regs[i].reg_size;
+
+		size &= PAGE_MASK;
+		if (base & ~PAGE_MASK) {
+			unsigned long new_base = PAGE_ALIGN(base);
+
+			size -= new_base - base;
+			if ((long) size < 0L)
+				size = 0UL;
+			base = new_base;
+		}
+		if (size == 0UL) {
+			/* If it is empty, simply get rid of it.
+			 * This simplifies the logic of the other
+			 * functions that process these arrays.
+			 */
+			memmove(&regs[i], &regs[i + 1],
+				(ents - i - 1) * sizeof(regs[0]));
+			i--;
+			ents--;
+			continue;
+		}
+		regs[i].phys_addr = base;
+		regs[i].reg_size = size;
+	}
+
+	*num_ents = ents;
+
+	sort(regs, ents, sizeof(struct linux_prom64_registers),
+	     cmp_p64, NULL);
+}
+
+unsigned long *sparc64_valid_addr_bitmap __read_mostly;
+
+/* Kernel physical address base and size in bytes.  */
+unsigned long kern_base __read_mostly;
+unsigned long kern_size __read_mostly;
+
+/* Initial ramdisk setup */
+extern unsigned long sparc_ramdisk_image64;
+extern unsigned int sparc_ramdisk_image;
+extern unsigned int sparc_ramdisk_size;
+
+struct page *mem_map_zero __read_mostly;
+EXPORT_SYMBOL(mem_map_zero);
+
+unsigned int sparc64_highest_unlocked_tlb_ent __read_mostly;
+
+unsigned long sparc64_kern_pri_context __read_mostly;
+unsigned long sparc64_kern_pri_nuc_bits __read_mostly;
+unsigned long sparc64_kern_sec_context __read_mostly;
+
+int num_kernel_image_mappings;
+
+#ifdef CONFIG_DEBUG_DCFLUSH
+atomic_t dcpage_flushes = ATOMIC_INIT(0);
+#ifdef CONFIG_SMP
+atomic_t dcpage_flushes_xcall = ATOMIC_INIT(0);
+#endif
+#endif
+
+inline void flush_dcache_page_impl(struct page *page)
+{
+	BUG_ON(tlb_type == hypervisor);
+#ifdef CONFIG_DEBUG_DCFLUSH
+	atomic_inc(&dcpage_flushes);
+#endif
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+	__flush_dcache_page(page_address(page),
+			    ((tlb_type == spitfire) &&
+			     page_mapping(page) != NULL));
+#else
+	if (page_mapping(page) != NULL &&
+	    tlb_type == spitfire)
+		__flush_icache_page(__pa(page_address(page)));
+#endif
+}
+
+#define PG_dcache_dirty		PG_arch_1
+#define PG_dcache_cpu_shift	32UL
+#define PG_dcache_cpu_mask	\
+	((1UL<<ilog2(roundup_pow_of_two(NR_CPUS)))-1UL)
+
+#define dcache_dirty_cpu(page) \
+	(((page)->flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask)
+
+static inline void set_dcache_dirty(struct page *page, int this_cpu)
+{
+	unsigned long mask = this_cpu;
+	unsigned long non_cpu_bits;
+
+	non_cpu_bits = ~(PG_dcache_cpu_mask << PG_dcache_cpu_shift);
+	mask = (mask << PG_dcache_cpu_shift) | (1UL << PG_dcache_dirty);
+
+	__asm__ __volatile__("1:\n\t"
+			     "ldx	[%2], %%g7\n\t"
+			     "and	%%g7, %1, %%g1\n\t"
+			     "or	%%g1, %0, %%g1\n\t"
+			     "casx	[%2], %%g7, %%g1\n\t"
+			     "cmp	%%g7, %%g1\n\t"
+			     "bne,pn	%%xcc, 1b\n\t"
+			     " nop"
+			     : /* no outputs */
+			     : "r" (mask), "r" (non_cpu_bits), "r" (&page->flags)
+			     : "g1", "g7");
+}
+
+static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu)
+{
+	unsigned long mask = (1UL << PG_dcache_dirty);
+
+	__asm__ __volatile__("! test_and_clear_dcache_dirty\n"
+			     "1:\n\t"
+			     "ldx	[%2], %%g7\n\t"
+			     "srlx	%%g7, %4, %%g1\n\t"
+			     "and	%%g1, %3, %%g1\n\t"
+			     "cmp	%%g1, %0\n\t"
+			     "bne,pn	%%icc, 2f\n\t"
+			     " andn	%%g7, %1, %%g1\n\t"
+			     "casx	[%2], %%g7, %%g1\n\t"
+			     "cmp	%%g7, %%g1\n\t"
+			     "bne,pn	%%xcc, 1b\n\t"
+			     " nop\n"
+			     "2:"
+			     : /* no outputs */
+			     : "r" (cpu), "r" (mask), "r" (&page->flags),
+			       "i" (PG_dcache_cpu_mask),
+			       "i" (PG_dcache_cpu_shift)
+			     : "g1", "g7");
+}
+
+static inline void tsb_insert(struct tsb *ent, unsigned long tag, unsigned long pte)
+{
+	unsigned long tsb_addr = (unsigned long) ent;
+
+	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+		tsb_addr = __pa(tsb_addr);
+
+	__tsb_insert(tsb_addr, tag, pte);
+}
+
+unsigned long _PAGE_ALL_SZ_BITS __read_mostly;
+unsigned long _PAGE_SZBITS __read_mostly;
+
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t pte)
+{
+	struct mm_struct *mm;
+	struct tsb *tsb;
+	unsigned long tag, flags;
+	unsigned long tsb_index, tsb_hash_shift;
+
+	if (tlb_type != hypervisor) {
+		unsigned long pfn = pte_pfn(pte);
+		unsigned long pg_flags;
+		struct page *page;
+
+		if (pfn_valid(pfn) &&
+		    (page = pfn_to_page(pfn), page_mapping(page)) &&
+		    ((pg_flags = page->flags) & (1UL << PG_dcache_dirty))) {
+			int cpu = ((pg_flags >> PG_dcache_cpu_shift) &
+				   PG_dcache_cpu_mask);
+			int this_cpu = get_cpu();
+
+			/* This is just to optimize away some function calls
+			 * in the SMP case.
+			 */
+			if (cpu == this_cpu)
+				flush_dcache_page_impl(page);
+			else
+				smp_flush_dcache_page_impl(page, cpu);
+
+			clear_dcache_dirty_cpu(page, cpu);
+
+			put_cpu();
+		}
+	}
+
+	mm = vma->vm_mm;
+
+	tsb_index = MM_TSB_BASE;
+	tsb_hash_shift = PAGE_SHIFT;
+
+	spin_lock_irqsave(&mm->context.lock, flags);
+
+#ifdef CONFIG_HUGETLB_PAGE
+	if (mm->context.tsb_block[MM_TSB_HUGE].tsb != NULL) {
+		if ((tlb_type == hypervisor &&
+		     (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
+		    (tlb_type != hypervisor &&
+		     (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U)) {
+			tsb_index = MM_TSB_HUGE;
+			tsb_hash_shift = HPAGE_SHIFT;
+		}
+	}
+#endif
+
+	tsb = mm->context.tsb_block[tsb_index].tsb;
+	tsb += ((address >> tsb_hash_shift) &
+		(mm->context.tsb_block[tsb_index].tsb_nentries - 1UL));
+	tag = (address >> 22UL);
+	tsb_insert(tsb, tag, pte_val(pte));
+
+	spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
+void flush_dcache_page(struct page *page)
+{
+	struct address_space *mapping;
+	int this_cpu;
+
+	if (tlb_type == hypervisor)
+		return;
+
+	/* Do not bother with the expensive D-cache flush if it
+	 * is merely the zero page.  The 'bigcore' testcase in GDB
+	 * causes this case to run millions of times.
+	 */
+	if (page == ZERO_PAGE(0))
+		return;
+
+	this_cpu = get_cpu();
+
+	mapping = page_mapping(page);
+	if (mapping && !mapping_mapped(mapping)) {
+		int dirty = test_bit(PG_dcache_dirty, &page->flags);
+		if (dirty) {
+			int dirty_cpu = dcache_dirty_cpu(page);
+
+			if (dirty_cpu == this_cpu)
+				goto out;
+			smp_flush_dcache_page_impl(page, dirty_cpu);
+		}
+		set_dcache_dirty(page, this_cpu);
+	} else {
+		/* We could delay the flush for the !page_mapping
+		 * case too.  But that case is for exec env/arg
+		 * pages and those are %99 certainly going to get
+		 * faulted into the tlb (and thus flushed) anyways.
+		 */
+		flush_dcache_page_impl(page);
+	}
+
+out:
+	put_cpu();
+}
+
+void __kprobes flush_icache_range(unsigned long start, unsigned long end)
+{
+	/* Cheetah and Hypervisor platform cpus have coherent I-cache. */
+	if (tlb_type == spitfire) {
+		unsigned long kaddr;
+
+		/* This code only runs on Spitfire cpus so this is
+		 * why we can assume _PAGE_PADDR_4U.
+		 */
+		for (kaddr = start; kaddr < end; kaddr += PAGE_SIZE) {
+			unsigned long paddr, mask = _PAGE_PADDR_4U;
+
+			if (kaddr >= PAGE_OFFSET)
+				paddr = kaddr & mask;
+			else {
+				pgd_t *pgdp = pgd_offset_k(kaddr);
+				pud_t *pudp = pud_offset(pgdp, kaddr);
+				pmd_t *pmdp = pmd_offset(pudp, kaddr);
+				pte_t *ptep = pte_offset_kernel(pmdp, kaddr);
+
+				paddr = pte_val(*ptep) & mask;
+			}
+			__flush_icache_page(paddr);
+		}
+	}
+}
+
+void mmu_info(struct seq_file *m)
+{
+	if (tlb_type == cheetah)
+		seq_printf(m, "MMU Type\t: Cheetah\n");
+	else if (tlb_type == cheetah_plus)
+		seq_printf(m, "MMU Type\t: Cheetah+\n");
+	else if (tlb_type == spitfire)
+		seq_printf(m, "MMU Type\t: Spitfire\n");
+	else if (tlb_type == hypervisor)
+		seq_printf(m, "MMU Type\t: Hypervisor (sun4v)\n");
+	else
+		seq_printf(m, "MMU Type\t: ???\n");
+
+#ifdef CONFIG_DEBUG_DCFLUSH
+	seq_printf(m, "DCPageFlushes\t: %d\n",
+		   atomic_read(&dcpage_flushes));
+#ifdef CONFIG_SMP
+	seq_printf(m, "DCPageFlushesXC\t: %d\n",
+		   atomic_read(&dcpage_flushes_xcall));
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_DEBUG_DCFLUSH */
+}
+
+struct linux_prom_translation prom_trans[512] __read_mostly;
+unsigned int prom_trans_ents __read_mostly;
+
+unsigned long kern_locked_tte_data;
+
+/* The obp translations are saved based on 8k pagesize, since obp can
+ * use a mixture of pagesizes. Misses to the LOW_OBP_ADDRESS ->
+ * HI_OBP_ADDRESS range are handled in ktlb.S.
+ */
+static inline int in_obp_range(unsigned long vaddr)
+{
+	return (vaddr >= LOW_OBP_ADDRESS &&
+		vaddr < HI_OBP_ADDRESS);
+}
+
+static int cmp_ptrans(const void *a, const void *b)
+{
+	const struct linux_prom_translation *x = a, *y = b;
+
+	if (x->virt > y->virt)
+		return 1;
+	if (x->virt < y->virt)
+		return -1;
+	return 0;
+}
+
+/* Read OBP translations property into 'prom_trans[]'.  */
+static void __init read_obp_translations(void)
+{
+	int n, node, ents, first, last, i;
+
+	node = prom_finddevice("/virtual-memory");
+	n = prom_getproplen(node, "translations");
+	if (unlikely(n == 0 || n == -1)) {
+		prom_printf("prom_mappings: Couldn't get size.\n");
+		prom_halt();
+	}
+	if (unlikely(n > sizeof(prom_trans))) {
+		prom_printf("prom_mappings: Size %Zd is too big.\n", n);
+		prom_halt();
+	}
+
+	if ((n = prom_getproperty(node, "translations",
+				  (char *)&prom_trans[0],
+				  sizeof(prom_trans))) == -1) {
+		prom_printf("prom_mappings: Couldn't get property.\n");
+		prom_halt();
+	}
+
+	n = n / sizeof(struct linux_prom_translation);
+
+	ents = n;
+
+	sort(prom_trans, ents, sizeof(struct linux_prom_translation),
+	     cmp_ptrans, NULL);
+
+	/* Now kick out all the non-OBP entries.  */
+	for (i = 0; i < ents; i++) {
+		if (in_obp_range(prom_trans[i].virt))
+			break;
+	}
+	first = i;
+	for (; i < ents; i++) {
+		if (!in_obp_range(prom_trans[i].virt))
+			break;
+	}
+	last = i;
+
+	for (i = 0; i < (last - first); i++) {
+		struct linux_prom_translation *src = &prom_trans[i + first];
+		struct linux_prom_translation *dest = &prom_trans[i];
+
+		*dest = *src;
+	}
+	for (; i < ents; i++) {
+		struct linux_prom_translation *dest = &prom_trans[i];
+		dest->virt = dest->size = dest->data = 0x0UL;
+	}
+
+	prom_trans_ents = last - first;
+
+	if (tlb_type == spitfire) {
+		/* Clear diag TTE bits. */
+		for (i = 0; i < prom_trans_ents; i++)
+			prom_trans[i].data &= ~0x0003fe0000000000UL;
+	}
+}
+
+static void __init hypervisor_tlb_lock(unsigned long vaddr,
+				       unsigned long pte,
+				       unsigned long mmu)
+{
+	unsigned long ret = sun4v_mmu_map_perm_addr(vaddr, 0, pte, mmu);
+
+	if (ret != 0) {
+		prom_printf("hypervisor_tlb_lock[%lx:%lx:%lx:%lx]: "
+			    "errors with %lx\n", vaddr, 0, pte, mmu, ret);
+		prom_halt();
+	}
+}
+
+static unsigned long kern_large_tte(unsigned long paddr);
+
+static void __init remap_kernel(void)
+{
+	unsigned long phys_page, tte_vaddr, tte_data;
+	int i, tlb_ent = sparc64_highest_locked_tlbent();
+
+	tte_vaddr = (unsigned long) KERNBASE;
+	phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	tte_data = kern_large_tte(phys_page);
+
+	kern_locked_tte_data = tte_data;
+
+	/* Now lock us into the TLBs via Hypervisor or OBP. */
+	if (tlb_type == hypervisor) {
+		for (i = 0; i < num_kernel_image_mappings; i++) {
+			hypervisor_tlb_lock(tte_vaddr, tte_data, HV_MMU_DMMU);
+			hypervisor_tlb_lock(tte_vaddr, tte_data, HV_MMU_IMMU);
+			tte_vaddr += 0x400000;
+			tte_data += 0x400000;
+		}
+	} else {
+		for (i = 0; i < num_kernel_image_mappings; i++) {
+			prom_dtlb_load(tlb_ent - i, tte_data, tte_vaddr);
+			prom_itlb_load(tlb_ent - i, tte_data, tte_vaddr);
+			tte_vaddr += 0x400000;
+			tte_data += 0x400000;
+		}
+		sparc64_highest_unlocked_tlb_ent = tlb_ent - i;
+	}
+	if (tlb_type == cheetah_plus) {
+		sparc64_kern_pri_context = (CTX_CHEETAH_PLUS_CTX0 |
+					    CTX_CHEETAH_PLUS_NUC);
+		sparc64_kern_pri_nuc_bits = CTX_CHEETAH_PLUS_NUC;
+		sparc64_kern_sec_context = CTX_CHEETAH_PLUS_CTX0;
+	}
+}
+
+
+static void __init inherit_prom_mappings(void)
+{
+	/* Now fixup OBP's idea about where we really are mapped. */
+	printk("Remapping the kernel... ");
+	remap_kernel();
+	printk("done.\n");
+}
+
+void prom_world(int enter)
+{
+	if (!enter)
+		set_fs((mm_segment_t) { get_thread_current_ds() });
+
+	__asm__ __volatile__("flushw");
+}
+
+void __flush_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long va;
+
+	if (tlb_type == spitfire) {
+		int n = 0;
+
+		for (va = start; va < end; va += 32) {
+			spitfire_put_dcache_tag(va & 0x3fe0, 0x0);
+			if (++n >= 512)
+				break;
+		}
+	} else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
+		start = __pa(start);
+		end = __pa(end);
+		for (va = start; va < end; va += 32)
+			__asm__ __volatile__("stxa %%g0, [%0] %1\n\t"
+					     "membar #Sync"
+					     : /* no outputs */
+					     : "r" (va),
+					       "i" (ASI_DCACHE_INVALIDATE));
+	}
+}
+
+/* get_new_mmu_context() uses "cache + 1".  */
+DEFINE_SPINLOCK(ctx_alloc_lock);
+unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+#define MAX_CTX_NR	(1UL << CTX_NR_BITS)
+#define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
+DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+
+/* Caller does TLB context flushing on local CPU if necessary.
+ * The caller also ensures that CTX_VALID(mm->context) is false.
+ *
+ * We must be careful about boundary cases so that we never
+ * let the user have CTX 0 (nucleus) or we ever use a CTX
+ * version of zero (and thus NO_CONTEXT would not be caught
+ * by version mis-match tests in mmu_context.h).
+ *
+ * Always invoked with interrupts disabled.
+ */
+void get_new_mmu_context(struct mm_struct *mm)
+{
+	unsigned long ctx, new_ctx;
+	unsigned long orig_pgsz_bits;
+	unsigned long flags;
+	int new_version;
+
+	spin_lock_irqsave(&ctx_alloc_lock, flags);
+	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
+	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
+	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
+	new_version = 0;
+	if (new_ctx >= (1 << CTX_NR_BITS)) {
+		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
+		if (new_ctx >= ctx) {
+			int i;
+			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
+				CTX_FIRST_VERSION;
+			if (new_ctx == 1)
+				new_ctx = CTX_FIRST_VERSION;
+
+			/* Don't call memset, for 16 entries that's just
+			 * plain silly...
+			 */
+			mmu_context_bmap[0] = 3;
+			mmu_context_bmap[1] = 0;
+			mmu_context_bmap[2] = 0;
+			mmu_context_bmap[3] = 0;
+			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
+				mmu_context_bmap[i + 0] = 0;
+				mmu_context_bmap[i + 1] = 0;
+				mmu_context_bmap[i + 2] = 0;
+				mmu_context_bmap[i + 3] = 0;
+			}
+			new_version = 1;
+			goto out;
+		}
+	}
+	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
+	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
+out:
+	tlb_context_cache = new_ctx;
+	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+	spin_unlock_irqrestore(&ctx_alloc_lock, flags);
+
+	if (unlikely(new_version))
+		smp_new_mmu_context_version();
+}
+
+static int numa_enabled = 1;
+static int numa_debug;
+
+static int __init early_numa(char *p)
+{
+	if (!p)
+		return 0;
+
+	if (strstr(p, "off"))
+		numa_enabled = 0;
+
+	if (strstr(p, "debug"))
+		numa_debug = 1;
+
+	return 0;
+}
+early_param("numa", early_numa);
+
+#define numadbg(f, a...) \
+do {	if (numa_debug) \
+		printk(KERN_INFO f, ## a); \
+} while (0)
+
+static void __init find_ramdisk(unsigned long phys_base)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (sparc_ramdisk_image || sparc_ramdisk_image64) {
+		unsigned long ramdisk_image;
+
+		/* Older versions of the bootloader only supported a
+		 * 32-bit physical address for the ramdisk image
+		 * location, stored at sparc_ramdisk_image.  Newer
+		 * SILO versions set sparc_ramdisk_image to zero and
+		 * provide a full 64-bit physical address at
+		 * sparc_ramdisk_image64.
+		 */
+		ramdisk_image = sparc_ramdisk_image;
+		if (!ramdisk_image)
+			ramdisk_image = sparc_ramdisk_image64;
+
+		/* Another bootloader quirk.  The bootloader normalizes
+		 * the physical address to KERNBASE, so we have to
+		 * factor that back out and add in the lowest valid
+		 * physical page address to get the true physical address.
+		 */
+		ramdisk_image -= KERNBASE;
+		ramdisk_image += phys_base;
+
+		numadbg("Found ramdisk at physical address 0x%lx, size %u\n",
+			ramdisk_image, sparc_ramdisk_size);
+
+		initrd_start = ramdisk_image;
+		initrd_end = ramdisk_image + sparc_ramdisk_size;
+
+		lmb_reserve(initrd_start, sparc_ramdisk_size);
+
+		initrd_start += PAGE_OFFSET;
+		initrd_end += PAGE_OFFSET;
+	}
+#endif
+}
+
+struct node_mem_mask {
+	unsigned long mask;
+	unsigned long val;
+	unsigned long bootmem_paddr;
+};
+static struct node_mem_mask node_masks[MAX_NUMNODES];
+static int num_node_masks;
+
+int numa_cpu_lookup_table[NR_CPUS];
+cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+
+struct mdesc_mblock {
+	u64	base;
+	u64	size;
+	u64	offset; /* RA-to-PA */
+};
+static struct mdesc_mblock *mblocks;
+static int num_mblocks;
+
+static unsigned long ra_to_pa(unsigned long addr)
+{
+	int i;
+
+	for (i = 0; i < num_mblocks; i++) {
+		struct mdesc_mblock *m = &mblocks[i];
+
+		if (addr >= m->base &&
+		    addr < (m->base + m->size)) {
+			addr += m->offset;
+			break;
+		}
+	}
+	return addr;
+}
+
+static int find_node(unsigned long addr)
+{
+	int i;
+
+	addr = ra_to_pa(addr);
+	for (i = 0; i < num_node_masks; i++) {
+		struct node_mem_mask *p = &node_masks[i];
+
+		if ((addr & p->mask) == p->val)
+			return i;
+	}
+	return -1;
+}
+
+static unsigned long nid_range(unsigned long start, unsigned long end,
+			       int *nid)
+{
+	*nid = find_node(start);
+	start += PAGE_SIZE;
+	while (start < end) {
+		int n = find_node(start);
+
+		if (n != *nid)
+			break;
+		start += PAGE_SIZE;
+	}
+
+	if (start > end)
+		start = end;
+
+	return start;
+}
+#else
+static unsigned long nid_range(unsigned long start, unsigned long end,
+			       int *nid)
+{
+	*nid = 0;
+	return end;
+}
+#endif
+
+/* This must be invoked after performing all of the necessary
+ * add_active_range() calls for 'nid'.  We need to be able to get
+ * correct data from get_pfn_range_for_nid().
+ */
+static void __init allocate_node_data(int nid)
+{
+	unsigned long paddr, num_pages, start_pfn, end_pfn;
+	struct pglist_data *p;
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	paddr = lmb_alloc_nid(sizeof(struct pglist_data),
+			      SMP_CACHE_BYTES, nid, nid_range);
+	if (!paddr) {
+		prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
+		prom_halt();
+	}
+	NODE_DATA(nid) = __va(paddr);
+	memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
+
+	NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+#endif
+
+	p = NODE_DATA(nid);
+
+	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+	p->node_start_pfn = start_pfn;
+	p->node_spanned_pages = end_pfn - start_pfn;
+
+	if (p->node_spanned_pages) {
+		num_pages = bootmem_bootmap_pages(p->node_spanned_pages);
+
+		paddr = lmb_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid,
+				      nid_range);
+		if (!paddr) {
+			prom_printf("Cannot allocate bootmap for nid[%d]\n",
+				  nid);
+			prom_halt();
+		}
+		node_masks[nid].bootmem_paddr = paddr;
+	}
+}
+
+static void init_node_masks_nonnuma(void)
+{
+	int i;
+
+	numadbg("Initializing tables for non-numa.\n");
+
+	node_masks[0].mask = node_masks[0].val = 0;
+	num_node_masks = 1;
+
+	for (i = 0; i < NR_CPUS; i++)
+		numa_cpu_lookup_table[i] = 0;
+
+	numa_cpumask_lookup_table[0] = CPU_MASK_ALL;
+}
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+struct pglist_data *node_data[MAX_NUMNODES];
+
+EXPORT_SYMBOL(numa_cpu_lookup_table);
+EXPORT_SYMBOL(numa_cpumask_lookup_table);
+EXPORT_SYMBOL(node_data);
+
+struct mdesc_mlgroup {
+	u64	node;
+	u64	latency;
+	u64	match;
+	u64	mask;
+};
+static struct mdesc_mlgroup *mlgroups;
+static int num_mlgroups;
+
+static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio,
+				   u32 cfg_handle)
+{
+	u64 arc;
+
+	mdesc_for_each_arc(arc, md, pio, MDESC_ARC_TYPE_FWD) {
+		u64 target = mdesc_arc_target(md, arc);
+		const u64 *val;
+
+		val = mdesc_get_property(md, target,
+					 "cfg-handle", NULL);
+		if (val && *val == cfg_handle)
+			return 0;
+	}
+	return -ENODEV;
+}
+
+static int scan_arcs_for_cfg_handle(struct mdesc_handle *md, u64 grp,
+				    u32 cfg_handle)
+{
+	u64 arc, candidate, best_latency = ~(u64)0;
+
+	candidate = MDESC_NODE_NULL;
+	mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_FWD) {
+		u64 target = mdesc_arc_target(md, arc);
+		const char *name = mdesc_node_name(md, target);
+		const u64 *val;
+
+		if (strcmp(name, "pio-latency-group"))
+			continue;
+
+		val = mdesc_get_property(md, target, "latency", NULL);
+		if (!val)
+			continue;
+
+		if (*val < best_latency) {
+			candidate = target;
+			best_latency = *val;
+		}
+	}
+
+	if (candidate == MDESC_NODE_NULL)
+		return -ENODEV;
+
+	return scan_pio_for_cfg_handle(md, candidate, cfg_handle);
+}
+
+int of_node_to_nid(struct device_node *dp)
+{
+	const struct linux_prom64_registers *regs;
+	struct mdesc_handle *md;
+	u32 cfg_handle;
+	int count, nid;
+	u64 grp;
+
+	/* This is the right thing to do on currently supported
+	 * SUN4U NUMA platforms as well, as the PCI controller does
+	 * not sit behind any particular memory controller.
+	 */
+	if (!mlgroups)
+		return -1;
+
+	regs = of_get_property(dp, "reg", NULL);
+	if (!regs)
+		return -1;
+
+	cfg_handle = (regs->phys_addr >> 32UL) & 0x0fffffff;
+
+	md = mdesc_grab();
+
+	count = 0;
+	nid = -1;
+	mdesc_for_each_node_by_name(md, grp, "group") {
+		if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) {
+			nid = count;
+			break;
+		}
+		count++;
+	}
+
+	mdesc_release(md);
+
+	return nid;
+}
+
+static void add_node_ranges(void)
+{
+	int i;
+
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		unsigned long size = lmb_size_bytes(&lmb.memory, i);
+		unsigned long start, end;
+
+		start = lmb.memory.region[i].base;
+		end = start + size;
+		while (start < end) {
+			unsigned long this_end;
+			int nid;
+
+			this_end = nid_range(start, end, &nid);
+
+			numadbg("Adding active range nid[%d] "
+				"start[%lx] end[%lx]\n",
+				nid, start, this_end);
+
+			add_active_range(nid,
+					 start >> PAGE_SHIFT,
+					 this_end >> PAGE_SHIFT);
+
+			start = this_end;
+		}
+	}
+}
+
+static int __init grab_mlgroups(struct mdesc_handle *md)
+{
+	unsigned long paddr;
+	int count = 0;
+	u64 node;
+
+	mdesc_for_each_node_by_name(md, node, "memory-latency-group")
+		count++;
+	if (!count)
+		return -ENOENT;
+
+	paddr = lmb_alloc(count * sizeof(struct mdesc_mlgroup),
+			  SMP_CACHE_BYTES);
+	if (!paddr)
+		return -ENOMEM;
+
+	mlgroups = __va(paddr);
+	num_mlgroups = count;
+
+	count = 0;
+	mdesc_for_each_node_by_name(md, node, "memory-latency-group") {
+		struct mdesc_mlgroup *m = &mlgroups[count++];
+		const u64 *val;
+
+		m->node = node;
+
+		val = mdesc_get_property(md, node, "latency", NULL);
+		m->latency = *val;
+		val = mdesc_get_property(md, node, "address-match", NULL);
+		m->match = *val;
+		val = mdesc_get_property(md, node, "address-mask", NULL);
+		m->mask = *val;
+
+		numadbg("MLGROUP[%d]: node[%lx] latency[%lx] "
+			"match[%lx] mask[%lx]\n",
+			count - 1, m->node, m->latency, m->match, m->mask);
+	}
+
+	return 0;
+}
+
+static int __init grab_mblocks(struct mdesc_handle *md)
+{
+	unsigned long paddr;
+	int count = 0;
+	u64 node;
+
+	mdesc_for_each_node_by_name(md, node, "mblock")
+		count++;
+	if (!count)
+		return -ENOENT;
+
+	paddr = lmb_alloc(count * sizeof(struct mdesc_mblock),
+			  SMP_CACHE_BYTES);
+	if (!paddr)
+		return -ENOMEM;
+
+	mblocks = __va(paddr);
+	num_mblocks = count;
+
+	count = 0;
+	mdesc_for_each_node_by_name(md, node, "mblock") {
+		struct mdesc_mblock *m = &mblocks[count++];
+		const u64 *val;
+
+		val = mdesc_get_property(md, node, "base", NULL);
+		m->base = *val;
+		val = mdesc_get_property(md, node, "size", NULL);
+		m->size = *val;
+		val = mdesc_get_property(md, node,
+					 "address-congruence-offset", NULL);
+		m->offset = *val;
+
+		numadbg("MBLOCK[%d]: base[%lx] size[%lx] offset[%lx]\n",
+			count - 1, m->base, m->size, m->offset);
+	}
+
+	return 0;
+}
+
+static void __init numa_parse_mdesc_group_cpus(struct mdesc_handle *md,
+					       u64 grp, cpumask_t *mask)
+{
+	u64 arc;
+
+	cpus_clear(*mask);
+
+	mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_BACK) {
+		u64 target = mdesc_arc_target(md, arc);
+		const char *name = mdesc_node_name(md, target);
+		const u64 *id;
+
+		if (strcmp(name, "cpu"))
+			continue;
+		id = mdesc_get_property(md, target, "id", NULL);
+		if (*id < NR_CPUS)
+			cpu_set(*id, *mask);
+	}
+}
+
+static struct mdesc_mlgroup * __init find_mlgroup(u64 node)
+{
+	int i;
+
+	for (i = 0; i < num_mlgroups; i++) {
+		struct mdesc_mlgroup *m = &mlgroups[i];
+		if (m->node == node)
+			return m;
+	}
+	return NULL;
+}
+
+static int __init numa_attach_mlgroup(struct mdesc_handle *md, u64 grp,
+				      int index)
+{
+	struct mdesc_mlgroup *candidate = NULL;
+	u64 arc, best_latency = ~(u64)0;
+	struct node_mem_mask *n;
+
+	mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_FWD) {
+		u64 target = mdesc_arc_target(md, arc);
+		struct mdesc_mlgroup *m = find_mlgroup(target);
+		if (!m)
+			continue;
+		if (m->latency < best_latency) {
+			candidate = m;
+			best_latency = m->latency;
+		}
+	}
+	if (!candidate)
+		return -ENOENT;
+
+	if (num_node_masks != index) {
+		printk(KERN_ERR "Inconsistent NUMA state, "
+		       "index[%d] != num_node_masks[%d]\n",
+		       index, num_node_masks);
+		return -EINVAL;
+	}
+
+	n = &node_masks[num_node_masks++];
+
+	n->mask = candidate->mask;
+	n->val = candidate->match;
+
+	numadbg("NUMA NODE[%d]: mask[%lx] val[%lx] (latency[%lx])\n",
+		index, n->mask, n->val, candidate->latency);
+
+	return 0;
+}
+
+static int __init numa_parse_mdesc_group(struct mdesc_handle *md, u64 grp,
+					 int index)
+{
+	cpumask_t mask;
+	int cpu;
+
+	numa_parse_mdesc_group_cpus(md, grp, &mask);
+
+	for_each_cpu_mask(cpu, mask)
+		numa_cpu_lookup_table[cpu] = index;
+	numa_cpumask_lookup_table[index] = mask;
+
+	if (numa_debug) {
+		printk(KERN_INFO "NUMA GROUP[%d]: cpus [ ", index);
+		for_each_cpu_mask(cpu, mask)
+			printk("%d ", cpu);
+		printk("]\n");
+	}
+
+	return numa_attach_mlgroup(md, grp, index);
+}
+
+static int __init numa_parse_mdesc(void)
+{
+	struct mdesc_handle *md = mdesc_grab();
+	int i, err, count;
+	u64 node;
+
+	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+	if (node == MDESC_NODE_NULL) {
+		mdesc_release(md);
+		return -ENOENT;
+	}
+
+	err = grab_mblocks(md);
+	if (err < 0)
+		goto out;
+
+	err = grab_mlgroups(md);
+	if (err < 0)
+		goto out;
+
+	count = 0;
+	mdesc_for_each_node_by_name(md, node, "group") {
+		err = numa_parse_mdesc_group(md, node, count);
+		if (err < 0)
+			break;
+		count++;
+	}
+
+	add_node_ranges();
+
+	for (i = 0; i < num_node_masks; i++) {
+		allocate_node_data(i);
+		node_set_online(i);
+	}
+
+	err = 0;
+out:
+	mdesc_release(md);
+	return err;
+}
+
+static int __init numa_parse_jbus(void)
+{
+	unsigned long cpu, index;
+
+	/* NUMA node id is encoded in bits 36 and higher, and there is
+	 * a 1-to-1 mapping from CPU ID to NUMA node ID.
+	 */
+	index = 0;
+	for_each_present_cpu(cpu) {
+		numa_cpu_lookup_table[cpu] = index;
+		numa_cpumask_lookup_table[index] = cpumask_of_cpu(cpu);
+		node_masks[index].mask = ~((1UL << 36UL) - 1UL);
+		node_masks[index].val = cpu << 36UL;
+
+		index++;
+	}
+	num_node_masks = index;
+