Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

8 files changed, 3612 insertions, 0 deletions

diff --git a/arch/sparc64/mm/Makefile b/arch/sparc64/mm/Makefile
new file mode 100644
index 00000000000..cda87333a77
--- /dev/null
+++ b/arch/sparc64/mm/Makefile
@@ -0,0 +1,10 @@
+# $Id: Makefile,v 1.8 2000/12/14 22:57:25 davem Exp $
+# Makefile for the linux Sparc64-specific parts of the memory manager.
+#
+
+EXTRA_AFLAGS := -ansi
+EXTRA_CFLAGS := -Werror
+
+obj-y    := ultra.o tlb.o fault.o init.o generic.o extable.o
+
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/sparc64/mm/extable.c b/arch/sparc64/mm/extable.c
new file mode 100644
index 00000000000..ec334297ff4
--- /dev/null
+++ b/arch/sparc64/mm/extable.c
@@ -0,0 +1,80 @@
+/*
+ * linux/arch/sparc64/mm/extable.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <asm/uaccess.h>
+
+extern const struct exception_table_entry __start___ex_table[];
+extern const struct exception_table_entry __stop___ex_table[];
+
+void sort_extable(struct exception_table_entry *start,
+		  struct exception_table_entry *finish)
+{
+}
+
+/* Caller knows they are in a range if ret->fixup == 0 */
+const struct exception_table_entry *
+search_extable(const struct exception_table_entry *start,
+	       const struct exception_table_entry *last,
+	       unsigned long value)
+{
+	const struct exception_table_entry *walk;
+
+	/* Single insn entries are encoded as:
+	 *	word 1:	insn address
+	 *	word 2:	fixup code address
+	 *
+	 * Range entries are encoded as:
+	 *	word 1: first insn address
+	 *	word 2: 0
+	 *	word 3: last insn address + 4 bytes
+	 *	word 4: fixup code address
+	 *
+	 * See asm/uaccess.h for more details.
+	 */
+
+	/* 1. Try to find an exact match. */
+	for (walk = start; walk <= last; walk++) {
+		if (walk->fixup == 0) {
+			/* A range entry, skip both parts. */
+			walk++;
+			continue;
+		}
+
+		if (walk->insn == value)
+			return walk;
+	}
+
+	/* 2. Try to find a range match. */
+	for (walk = start; walk <= (last - 1); walk++) {
+		if (walk->fixup)
+			continue;
+
+		if (walk[0].insn <= value && walk[1].insn > value)
+			return walk;
+
+		walk++;
+	}
+
+        return NULL;
+}
+
+/* Special extable search, which handles ranges.  Returns fixup */
+unsigned long search_extables_range(unsigned long addr, unsigned long *g2)
+{
+	const struct exception_table_entry *entry;
+
+	entry = search_exception_tables(addr);
+	if (!entry)
+		return 0;
+
+	/* Inside range?  Fix g2 and return correct fixup */
+	if (!entry->fixup) {
+		*g2 = (addr - entry->insn) / 4;
+		return (entry + 1)->fixup;
+	}
+
+	return entry->fixup;
+}
diff --git a/arch/sparc64/mm/fault.c b/arch/sparc64/mm/fault.c
new file mode 100644
index 00000000000..3ffee7b51ae
--- /dev/null
+++ b/arch/sparc64/mm/fault.c
@@ -0,0 +1,527 @@
+/* $Id: fault.c,v 1.59 2002/02/09 19:49:31 davem Exp $
+ * arch/sparc64/mm/fault.c: Page fault handlers for the 64-bit Sparc.
+ *
+ * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1997, 1999 Jakub Jelinek (jj@ultra.linux.cz)
+ */
+
+#include <asm/head.h>
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/signal.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/openprom.h>
+#include <asm/oplib.h>
+#include <asm/uaccess.h>
+#include <asm/asi.h>
+#include <asm/lsu.h>
+#include <asm/sections.h>
+#include <asm/kdebug.h>
+
+#define ELEMENTS(arr) (sizeof (arr)/sizeof (arr[0]))
+
+extern struct sparc_phys_banks sp_banks[SPARC_PHYS_BANKS];
+
+/*
+ * To debug kernel during syscall entry.
+ */
+void syscall_trace_entry(struct pt_regs *regs)
+{
+	printk("scall entry: %s[%d]/cpu%d: %d\n", current->comm, current->pid, smp_processor_id(), (int) regs->u_regs[UREG_G1]);
+}
+
+/*
+ * To debug kernel during syscall exit.
+ */
+void syscall_trace_exit(struct pt_regs *regs)
+{
+	printk("scall exit: %s[%d]/cpu%d: %d\n", current->comm, current->pid, smp_processor_id(), (int) regs->u_regs[UREG_G1]);
+}
+
+/*
+ * To debug kernel to catch accesses to certain virtual/physical addresses.
+ * Mode = 0 selects physical watchpoints, mode = 1 selects virtual watchpoints.
+ * flags = VM_READ watches memread accesses, flags = VM_WRITE watches memwrite accesses.
+ * Caller passes in a 64bit aligned addr, with mask set to the bytes that need to be
+ * watched. This is only useful on a single cpu machine for now. After the watchpoint
+ * is detected, the process causing it will be killed, thus preventing an infinite loop.
+ */
+void set_brkpt(unsigned long addr, unsigned char mask, int flags, int mode)
+{
+	unsigned long lsubits;
+
+	__asm__ __volatile__("ldxa [%%g0] %1, %0"
+			     : "=r" (lsubits)
+			     : "i" (ASI_LSU_CONTROL));
+	lsubits &= ~(LSU_CONTROL_PM | LSU_CONTROL_VM |
+		     LSU_CONTROL_PR | LSU_CONTROL_VR |
+		     LSU_CONTROL_PW | LSU_CONTROL_VW);
+
+	__asm__ __volatile__("stxa	%0, [%1] %2\n\t"
+			     "membar	#Sync"
+			     : /* no outputs */
+			     : "r" (addr), "r" (mode ? VIRT_WATCHPOINT : PHYS_WATCHPOINT),
+			       "i" (ASI_DMMU));
+
+	lsubits |= ((unsigned long)mask << (mode ? 25 : 33));
+	if (flags & VM_READ)
+		lsubits |= (mode ? LSU_CONTROL_VR : LSU_CONTROL_PR);
+	if (flags & VM_WRITE)
+		lsubits |= (mode ? LSU_CONTROL_VW : LSU_CONTROL_PW);
+	__asm__ __volatile__("stxa %0, [%%g0] %1\n\t"
+			     "membar #Sync"
+			     : /* no outputs */
+			     : "r" (lsubits), "i" (ASI_LSU_CONTROL)
+			     : "memory");
+}
+
+/* Nice, simple, prom library does all the sweating for us. ;) */
+unsigned long __init prom_probe_memory (void)
+{
+	register struct linux_mlist_p1275 *mlist;
+	register unsigned long bytes, base_paddr, tally;
+	register int i;
+
+	i = 0;
+	mlist = *prom_meminfo()->p1275_available;
+	bytes = tally = mlist->num_bytes;
+	base_paddr = mlist->start_adr;
+  
+	sp_banks[0].base_addr = base_paddr;
+	sp_banks[0].num_bytes = bytes;
+
+	while (mlist->theres_more != (void *) 0) {
+		i++;
+		mlist = mlist->theres_more;
+		bytes = mlist->num_bytes;
+		tally += bytes;
+		if (i >= SPARC_PHYS_BANKS-1) {
+			printk ("The machine has more banks than "
+				"this kernel can support\n"
+				"Increase the SPARC_PHYS_BANKS "
+				"setting (currently %d)\n",
+				SPARC_PHYS_BANKS);
+			i = SPARC_PHYS_BANKS-1;
+			break;
+		}
+    
+		sp_banks[i].base_addr = mlist->start_adr;
+		sp_banks[i].num_bytes = mlist->num_bytes;
+	}
+
+	i++;
+	sp_banks[i].base_addr = 0xdeadbeefbeefdeadUL;
+	sp_banks[i].num_bytes = 0;
+
+	/* Now mask all bank sizes on a page boundary, it is all we can
+	 * use anyways.
+	 */
+	for (i = 0; sp_banks[i].num_bytes != 0; i++)
+		sp_banks[i].num_bytes &= PAGE_MASK;
+
+	return tally;
+}
+
+static void unhandled_fault(unsigned long address, struct task_struct *tsk,
+			    struct pt_regs *regs)
+{
+	if ((unsigned long) address < PAGE_SIZE) {
+		printk(KERN_ALERT "Unable to handle kernel NULL "
+		       "pointer dereference\n");
+	} else {
+		printk(KERN_ALERT "Unable to handle kernel paging request "
+		       "at virtual address %016lx\n", (unsigned long)address);
+	}
+	printk(KERN_ALERT "tsk->{mm,active_mm}->context = %016lx\n",
+	       (tsk->mm ?
+		CTX_HWBITS(tsk->mm->context) :
+		CTX_HWBITS(tsk->active_mm->context)));
+	printk(KERN_ALERT "tsk->{mm,active_mm}->pgd = %016lx\n",
+	       (tsk->mm ? (unsigned long) tsk->mm->pgd :
+		          (unsigned long) tsk->active_mm->pgd));
+	if (notify_die(DIE_GPF, "general protection fault", regs,
+		       0, 0, SIGSEGV) == NOTIFY_STOP)
+		return;
+	die_if_kernel("Oops", regs);
+}
+
+static void bad_kernel_pc(struct pt_regs *regs)
+{
+	unsigned long *ksp;
+
+	printk(KERN_CRIT "OOPS: Bogus kernel PC [%016lx] in fault handler\n",
+	       regs->tpc);
+	__asm__("mov %%sp, %0" : "=r" (ksp));
+	show_stack(current, ksp);
+	unhandled_fault(regs->tpc, current, regs);
+}
+
+/*
+ * We now make sure that mmap_sem is held in all paths that call 
+ * this. Additionally, to prevent kswapd from ripping ptes from
+ * under us, raise interrupts around the time that we look at the
+ * pte, kswapd will have to wait to get his smp ipi response from
+ * us. This saves us having to get page_table_lock.
+ */
+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;
+	u32 insn = 0;
+	unsigned long pstate;
+
+	if (pgd_none(*pgdp))
+		goto outret;
+	pudp = pud_offset(pgdp, tpc);
+	if (pud_none(*pudp))
+		goto outret;
+	pmdp = pmd_offset(pudp, tpc);
+	if (pmd_none(*pmdp))
+		goto outret;
+
+	/* This disables preemption for us as well. */
+	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
+	__asm__ __volatile__("wrpr %0, %1, %%pstate"
+				: : "r" (pstate), "i" (PSTATE_IE));
+	ptep = pte_offset_map(pmdp, tpc);
+	pte = *ptep;
+	if (!pte_present(pte))
+		goto out;
+
+	pa  = (pte_val(pte) & _PAGE_PADDR);
+	pa += (tpc & ~PAGE_MASK);
+
+	/* Use phys bypass so we don't pollute dtlb/dcache. */
+	__asm__ __volatile__("lduwa [%1] %2, %0"
+			     : "=r" (insn)
+			     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+
+out:
+	pte_unmap(ptep);
+	__asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
+outret:
+	return insn;
+}
+
+extern unsigned long compute_effective_address(struct pt_regs *, unsigned int, unsigned int);
+
+static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
+			     unsigned int insn, int fault_code)
+{
+	siginfo_t info;
+
+	info.si_code = code;
+	info.si_signo = sig;
+	info.si_errno = 0;
+	if (fault_code & FAULT_CODE_ITLB)
+		info.si_addr = (void __user *) regs->tpc;
+	else
+		info.si_addr = (void __user *)
+			compute_effective_address(regs, insn, 0);
+	info.si_trapno = 0;
+	force_sig_info(sig, &info, current);
+}
+
+extern int handle_ldf_stq(u32, struct pt_regs *);
+extern int handle_ld_nf(u32, struct pt_regs *);
+
+static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
+{
+	if (!insn) {
+		if (!regs->tpc || (regs->tpc & 0x3))
+			return 0;
+		if (regs->tstate & TSTATE_PRIV) {
+			insn = *(unsigned int *) regs->tpc;
+		} else {
+			insn = get_user_insn(regs->tpc);
+		}
+	}
+	return insn;
+}
+
+static void do_kernel_fault(struct pt_regs *regs, int si_code, int fault_code,
+			    unsigned int insn, unsigned long address)
+{
+	unsigned long g2;
+	unsigned char asi = ASI_P;
+ 
+	if ((!insn) && (regs->tstate & TSTATE_PRIV))
+		goto cannot_handle;
+
+	/* If user insn could be read (thus insn is zero), that
+	 * is fine.  We will just gun down the process with a signal
+	 * in that case.
+	 */
+
+	if (!(fault_code & (FAULT_CODE_WRITE|FAULT_CODE_ITLB)) &&
+	    (insn & 0xc0800000) == 0xc0800000) {
+		if (insn & 0x2000)
+			asi = (regs->tstate >> 24);
+		else
+			asi = (insn >> 5);
+		if ((asi & 0xf2) == 0x82) {
+			if (insn & 0x1000000) {
+				handle_ldf_stq(insn, regs);
+			} else {
+				/* This was a non-faulting load. Just clear the
+				 * destination register(s) and continue with the next
+				 * instruction. -jj
+				 */
+				handle_ld_nf(insn, regs);
+			}
+			return;
+		}
+	}
+		
+	g2 = regs->u_regs[UREG_G2];
+
+	/* Is this in ex_table? */
+	if (regs->tstate & TSTATE_PRIV) {
+		unsigned long fixup;
+
+		if (asi == ASI_P && (insn & 0xc0800000) == 0xc0800000) {
+			if (insn & 0x2000)
+				asi = (regs->tstate >> 24);
+			else
+				asi = (insn >> 5);
+		}
+	
+		/* Look in asi.h: All _S asis have LS bit set */
+		if ((asi & 0x1) &&
+		    (fixup = search_extables_range(regs->tpc, &g2))) {
+			regs->tpc = fixup;
+			regs->tnpc = regs->tpc + 4;
+			regs->u_regs[UREG_G2] = g2;
+			return;
+		}
+	} else {
+		/* The si_code was set to make clear whether
+		 * this was a SEGV_MAPERR or SEGV_ACCERR fault.
+		 */
+		do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
+		return;
+	}
+
+cannot_handle:
+	unhandled_fault (address, current, regs);
+}
+
+asmlinkage void do_sparc64_fault(struct pt_regs *regs)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned int insn = 0;
+	int si_code, fault_code;
+	unsigned long address;
+
+	fault_code = get_thread_fault_code();
+
+	if (notify_die(DIE_PAGE_FAULT, "page_fault", regs,
+		       fault_code, 0, SIGSEGV) == NOTIFY_STOP)
+		return;
+
+	si_code = SEGV_MAPERR;
+	address = current_thread_info()->fault_address;
+
+	if ((fault_code & FAULT_CODE_ITLB) &&
+	    (fault_code & FAULT_CODE_DTLB))
+		BUG();
+
+	if (regs->tstate & TSTATE_PRIV) {
+		unsigned long tpc = regs->tpc;
+
+		/* Sanity check the PC. */
+		if ((tpc >= KERNBASE && tpc < (unsigned long) _etext) ||
+		    (tpc >= MODULES_VADDR && tpc < MODULES_END)) {
+			/* Valid, no problems... */
+		} else {
+			bad_kernel_pc(regs);
+			return;
+		}
+	}
+
+	/*
+	 * If we're in an interrupt or have no user
+	 * context, we must not take the fault..
+	 */
+	if (in_atomic() || !mm)
+		goto intr_or_no_mm;
+
+	if (test_thread_flag(TIF_32BIT)) {
+		if (!(regs->tstate & TSTATE_PRIV))
+			regs->tpc &= 0xffffffff;
+		address &= 0xffffffff;
+	}
+
+	if (!down_read_trylock(&mm->mmap_sem)) {
+		if ((regs->tstate & TSTATE_PRIV) &&
+		    !search_exception_tables(regs->tpc)) {
+			insn = get_fault_insn(regs, insn);
+			goto handle_kernel_fault;
+		}
+		down_read(&mm->mmap_sem);
+	}
+
+	vma = find_vma(mm, address);
+	if (!vma)
+		goto bad_area;
+
+	/* Pure DTLB misses do not tell us whether the fault causing
+	 * load/store/atomic was a write or not, it only says that there
+	 * was no match.  So in such a case we (carefully) read the
+	 * instruction to try and figure this out.  It's an optimization
+	 * so it's ok if we can't do this.
+	 *
+	 * Special hack, window spill/fill knows the exact fault type.
+	 */
+	if (((fault_code &
+	      (FAULT_CODE_DTLB | FAULT_CODE_WRITE | FAULT_CODE_WINFIXUP)) == FAULT_CODE_DTLB) &&
+	    (vma->vm_flags & VM_WRITE) != 0) {
+		insn = get_fault_insn(regs, 0);
+		if (!insn)
+			goto continue_fault;
+		if ((insn & 0xc0200000) == 0xc0200000 &&
+		    (insn & 0x1780000) != 0x1680000) {
+			/* Don't bother updating thread struct value,
+			 * because update_mmu_cache only cares which tlb
+			 * the access came from.
+			 */
+			fault_code |= FAULT_CODE_WRITE;
+		}
+	}
+continue_fault:
+
+	if (vma->vm_start <= address)
+		goto good_area;
+	if (!(vma->vm_flags & VM_GROWSDOWN))
+		goto bad_area;
+	if (!(fault_code & FAULT_CODE_WRITE)) {
+		/* Non-faulting loads shouldn't expand stack. */
+		insn = get_fault_insn(regs, insn);
+		if ((insn & 0xc0800000) == 0xc0800000) {
+			unsigned char asi;
+
+			if (insn & 0x2000)
+				asi = (regs->tstate >> 24);
+			else
+				asi = (insn >> 5);
+			if ((asi & 0xf2) == 0x82)
+				goto bad_area;
+		}
+	}
+	if (expand_stack(vma, address))
+		goto bad_area;
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it..
+	 */
+good_area:
+	si_code = SEGV_ACCERR;
+
+	/* If we took a ITLB miss on a non-executable page, catch
+	 * that here.
+	 */
+	if ((fault_code & FAULT_CODE_ITLB) && !(vma->vm_flags & VM_EXEC)) {
+		BUG_ON(address != regs->tpc);
+		BUG_ON(regs->tstate & TSTATE_PRIV);
+		goto bad_area;
+	}
+
+	if (fault_code & FAULT_CODE_WRITE) {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto bad_area;
+
+		/* Spitfire has an icache which does not snoop
+		 * processor stores.  Later processors do...
+		 */
+		if (tlb_type == spitfire &&
+		    (vma->vm_flags & VM_EXEC) != 0 &&
+		    vma->vm_file != NULL)
+			set_thread_fault_code(fault_code |
+					      FAULT_CODE_BLKCOMMIT);
+	} else {
+		/* Allow reads even for write-only mappings */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			goto bad_area;
+	}
+
+	switch (handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE))) {
+	case VM_FAULT_MINOR:
+		current->min_flt++;
+		break;
+	case VM_FAULT_MAJOR:
+		current->maj_flt++;
+		break;
+	case VM_FAULT_SIGBUS:
+		goto do_sigbus;
+	case VM_FAULT_OOM:
+		goto out_of_memory;
+	default:
+		BUG();
+	}
+
+	up_read(&mm->mmap_sem);
+	goto fault_done;
+
+	/*
+	 * Something tried to access memory that isn't in our memory map..
+	 * Fix it, but check if it's kernel or user first..
+	 */
+bad_area:
+	insn = get_fault_insn(regs, insn);
+	up_read(&mm->mmap_sem);
+
+handle_kernel_fault:
+	do_kernel_fault(regs, si_code, fault_code, insn, address);
+
+	goto fault_done;
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+	insn = get_fault_insn(regs, insn);
+	up_read(&mm->mmap_sem);
+	printk("VM: killing process %s\n", current->comm);
+	if (!(regs->tstate & TSTATE_PRIV))
+		do_exit(SIGKILL);
+	goto handle_kernel_fault;
+
+intr_or_no_mm:
+	insn = get_fault_insn(regs, 0);
+	goto handle_kernel_fault;
+
+do_sigbus:
+	insn = get_fault_insn(regs, insn);
+	up_read(&mm->mmap_sem);
+
+	/*
+	 * Send a sigbus, regardless of whether we were in kernel
+	 * or user mode.
+	 */
+	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);
+
+	/* Kernel mode? Handle exceptions or die */
+	if (regs->tstate & TSTATE_PRIV)
+		goto handle_kernel_fault;
+
+fault_done:
+	/* These values are no longer needed, clear them. */
+	set_thread_fault_code(0);
+	current_thread_info()->fault_address = 0;
+}
diff --git a/arch/sparc64/mm/generic.c b/arch/sparc64/mm/generic.c
new file mode 100644
index 00000000000..6b31f6117a9
--- /dev/null
+++ b/arch/sparc64/mm/generic.c
@@ -0,0 +1,182 @@
+/* $Id: generic.c,v 1.18 2001/12/21 04:56:15 davem Exp $
+ * generic.c: Generic Sparc mm routines that are not dependent upon
+ *            MMU type but are Sparc specific.
+ *
+ * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+
+/* Remap IO memory, the same way as remap_pfn_range(), but use
+ * the obio memory space.
+ *
+ * They use a pgprot that sets PAGE_IO and does not check the
+ * mem_map table as this is independent of normal memory.
+ */
+static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
+				      unsigned long address,
+				      unsigned long size,
+				      unsigned long offset, pgprot_t prot,
+				      int space)
+{
+	unsigned long end;
+
+	/* clear hack bit that was used as a write_combine side-effect flag */
+	offset &= ~0x1UL;
+	address &= ~PMD_MASK;
+	end = address + size;
+	if (end > PMD_SIZE)
+		end = PMD_SIZE;
+	do {
+		pte_t entry;
+		unsigned long curend = address + PAGE_SIZE;
+		
+		entry = mk_pte_io(offset, prot, space);
+		if (!(address & 0xffff)) {
+			if (!(address & 0x3fffff) && !(offset & 0x3ffffe) && end >= address + 0x400000) {
+				entry = mk_pte_io(offset,
+						  __pgprot(pgprot_val (prot) | _PAGE_SZ4MB),
+						  space);
+				curend = address + 0x400000;
+				offset += 0x400000;
+			} else if (!(address & 0x7ffff) && !(offset & 0x7fffe) && end >= address + 0x80000) {
+				entry = mk_pte_io(offset,
+						  __pgprot(pgprot_val (prot) | _PAGE_SZ512K),
+						  space);
+				curend = address + 0x80000;
+				offset += 0x80000;
+			} else if (!(offset & 0xfffe) && end >= address + 0x10000) {
+				entry = mk_pte_io(offset,
+						  __pgprot(pgprot_val (prot) | _PAGE_SZ64K),
+						  space);
+				curend = address + 0x10000;
+				offset += 0x10000;
+			} else
+				offset += PAGE_SIZE;
+		} else
+			offset += PAGE_SIZE;
+
+		do {
+			BUG_ON(!pte_none(*pte));
+			set_pte_at(mm, address, pte, entry);
+			address += PAGE_SIZE;
+			pte++;
+		} while (address < curend);
+	} while (address < end);
+}
+
+static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
+	unsigned long offset, pgprot_t prot, int space)
+{
+	unsigned long end;
+
+	address &= ~PGDIR_MASK;
+	end = address + size;
+	if (end > PGDIR_SIZE)
+		end = PGDIR_SIZE;
+	offset -= address;
+	do {
+		pte_t * pte = pte_alloc_map(mm, pmd, address);
+		if (!pte)
+			return -ENOMEM;
+		io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
+		pte_unmap(pte);
+		address = (address + PMD_SIZE) & PMD_MASK;
+		pmd++;
+	} while (address < end);
+	return 0;
+}
+
+static inline int io_remap_pud_range(struct mm_struct *mm, 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(mm, pud, address);
+		if (!pud)
+			return -ENOMEM;
+		io_remap_pmd_range(mm, 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;
+	pgd_t * dir;
+	unsigned long beg = from;
+	unsigned long end = from + size;
+	struct mm_struct *mm = vma->vm_mm;
+
+	prot = __pgprot(pg_iobits);
+	offset -= from;
+	dir = pgd_offset(mm, from);
+	flush_cache_range(vma, beg, end);
+
+	spin_lock(&mm->page_table_lock);
+	while (from < end) {
+		pud_t *pud = pud_alloc(mm, dir, from);
+		error = -ENOMEM;
+		if (!pud)
+			break;
+		error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
+		if (error)
+			break;
+		from = (from + PGDIR_SIZE) & PGDIR_MASK;
+		dir++;
+	}
+	flush_tlb_range(vma, beg, end);
+	spin_unlock(&mm->page_table_lock);
+
+	return error;
+}
+
+int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	int error = 0;
+	pgd_t * dir;
+	unsigned long beg = from;
+	unsigned long end = from + size;
+	struct mm_struct *mm = vma->vm_mm;
+	int space = GET_IOSPACE(pfn);
+	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
+
+	prot = __pgprot(pg_iobits);
+	offset -= from;
+	dir = pgd_offset(mm, from);
+	flush_cache_range(vma, beg, end);
+
+	spin_lock(&mm->page_table_lock);
+	while (from < end) {
+		pud_t *pud = pud_alloc(current->mm, dir, from);
+		error = -ENOMEM;
+		if (!pud)
+			break;
+		error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
+		if (error)
+			break;
+		from = (from + PGDIR_SIZE) & PGDIR_MASK;
+		dir++;
+	}
+	flush_tlb_range(vma, beg, end);
+	spin_unlock(&mm->page_table_lock);
+
+	return error;
+}
diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc64/mm/hugetlbpage.c
new file mode 100644
index 00000000000..5a1f831b2de
--- /dev/null
+++ b/arch/sparc64/mm/hugetlbpage.c
@@ -0,0 +1,310 @@
+/*
+ * SPARC64 Huge TLB page support.
+ *
+ * Copyright (C) 2002, 2003 David S. Miller (davem@redhat.com)
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/smp_lock.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+
+#include <asm/mman.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+
+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) {
+		pud = pud_offset(pgd, addr);
+		if (pud) {
+			pmd = pmd_alloc(mm, pud, addr);
+			if (pmd)
+				pte = pte_alloc_map(mm, pmd, addr);
+		}
+	}
+	return pte;
+}
+
+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) {
+		pud = pud_offset(pgd, addr);
+		if (pud) {
+			pmd = pmd_offset(pud, addr);
+			if (pmd)
+				pte = pte_offset_map(pmd, addr);
+		}
+	}
+	return pte;
+}
+
+#define mk_pte_huge(entry) do { pte_val(entry) |= _PAGE_SZHUGE; } while (0)
+
+static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma,
+			 unsigned long addr,
+			 struct page *page, pte_t * page_table, int write_access)
+{
+	unsigned long i;
+	pte_t entry;
+
+	add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
+
+	if (write_access)
+		entry = pte_mkwrite(pte_mkdirty(mk_pte(page,
+						       vma->vm_page_prot)));
+	else
+		entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
+	entry = pte_mkyoung(entry);
+	mk_pte_huge(entry);
+
+	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+		set_pte_at(mm, addr, page_table, entry);
+		page_table++;
+		addr += PAGE_SIZE;
+
+		pte_val(entry) += PAGE_SIZE;
+	}
+}
+
+/*
+ * This function checks for proper alignment of input addr and len parameters.
+ */
+int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
+			    struct vm_area_struct *vma)
+{
+	pte_t *src_pte, *dst_pte, entry;
+	struct page *ptepage;
+	unsigned long addr = vma->vm_start;
+	unsigned long end = vma->vm_end;
+	int i;
+
+	while (addr < end) {
+		dst_pte = huge_pte_alloc(dst, addr);
+		if (!dst_pte)
+			goto nomem;
+		src_pte = huge_pte_offset(src, addr);
+		BUG_ON(!src_pte || pte_none(*src_pte));
+		entry = *src_pte;
+		ptepage = pte_page(entry);
+		get_page(ptepage);
+		for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+			set_pte_at(dst, addr, dst_pte, entry);
+			pte_val(entry) += PAGE_SIZE;
+			dst_pte++;
+			addr += PAGE_SIZE;
+		}
+		add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
+	}
+	return 0;
+
+nomem:
+	return -ENOMEM;
+}
+
+int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
+			struct page **pages, struct vm_area_struct **vmas,
+			unsigned long *position, int *length, int i)
+{
+	unsigned long vaddr = *position;
+	int remainder = *length;
+
+	WARN_ON(!is_vm_hugetlb_page(vma));
+
+	while (vaddr < vma->vm_end && remainder) {
+		if (pages) {
+			pte_t *pte;
+			struct page *page;
+
+			pte = huge_pte_offset(mm, vaddr);
+
+			/* hugetlb should be locked, and hence, prefaulted */
+			BUG_ON(!pte || pte_none(*pte));
+
+			page = pte_page(*pte);
+
+			WARN_ON(!PageCompound(page));
+
+			get_page(page);
+			pages[i] = page;
+		}
+
+		if (vmas)
+			vmas[i] = vma;
+
+		vaddr += PAGE_SIZE;
+		--remainder;
+		++i;
+	}
+
+	*length = remainder;
+	*position = vaddr;
+
+	return i;
+}
+
+struct page *follow_huge_addr(struct mm_struct *mm,
+			      unsigned long address, int write)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+			     pmd_t *pmd, int write)
+{
+	return NULL;
+}
+
+void unmap_hugepage_range(struct vm_area_struct *vma,
+			  unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long address;
+	pte_t *pte;
+	struct page *page;
+	int i;
+
+	BUG_ON(start & (HPAGE_SIZE - 1));
+	BUG_ON(end & (HPAGE_SIZE - 1));
+
+	for (address = start; address < end; address += HPAGE_SIZE) {
+		pte = huge_pte_offset(mm, address);
+		BUG_ON(!pte);
+		if (pte_none(*pte))
+			continue;
+		page = pte_page(*pte);
+		put_page(page);
+		for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+			pte_clear(mm, address+(i*PAGE_SIZE), pte);
+			pte++;
+		}
+	}
+	add_mm_counter(mm, rss, -((end - start) >> PAGE_SHIFT));
+	flush_tlb_range(vma, start, end);
+}
+
+static void context_reload(void *__data)
+{
+	struct mm_struct *mm = __data;
+
+	if (mm == current->mm)
+		load_secondary_context(mm);
+}
+
+int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr;
+	int ret = 0;
+
+	/* On UltraSPARC-III+ and later, configure the second half of
+	 * the Data-TLB for huge pages.
+	 */
+	if (tlb_type == cheetah_plus) {
+		unsigned long ctx;
+
+		spin_lock(&ctx_alloc_lock);
+		ctx = mm->context.sparc64_ctx_val;
+		ctx &= ~CTX_PGSZ_MASK;
+		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
+		ctx |= CTX_PGSZ_HUGE << CTX_PGSZ1_SHIFT;
+
+		if (ctx != mm->context.sparc64_ctx_val) {
+			/* When changing the page size fields, we
+			 * must perform a context flush so that no
+			 * stale entries match.  This flush must
+			 * occur with the original context register
+			 * settings.
+			 */
+			do_flush_tlb_mm(mm);
+
+			/* Reload the context register of all processors
+			 * also executing in this address space.
+			 */
+			mm->context.sparc64_ctx_val = ctx;
+			on_each_cpu(context_reload, mm, 0, 0);
+		}
+		spin_unlock(&ctx_alloc_lock);
+	}
+
+	BUG_ON(vma->vm_start & ~HPAGE_MASK);
+	BUG_ON(vma->vm_end & ~HPAGE_MASK);
+
+	spin_lock(&mm->page_table_lock);
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+		unsigned long idx;
+		pte_t *pte = huge_pte_alloc(mm, addr);
+		struct page *page;
+
+		if (!pte) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		if (!pte_none(*pte))
+			continue;
+
+		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+		page = find_get_page(mapping, idx);
+		if (!page) {
+			/* charge the fs quota first */
+			if (hugetlb_get_quota(mapping)) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			page = alloc_huge_page();
+			if (!page) {
+				hugetlb_put_quota(mapping);
+				ret = -ENOMEM;
+				goto out;
+			}
+			ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
+			if (! ret) {
+				unlock_page(page);
+			} else {
+				hugetlb_put_quota(mapping);
+				free_huge_page(page);
+				goto out;
+			}