powerpc: Merge arch/ppc64/mm to arch/powerpc/mm

This moves the remaining files in arch/ppc64/mm to arch/powerpc/mm,
and arranges that we use them when compiling with ARCH=ppc64.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

arch/powerpc/mm/Makefile

@@ -5,8 +5,14 @@
 obj-y				:= fault.o mem.o lmb.o
 obj-$(CONFIG_PPC32)		+= init_32.o pgtable_32.o mmu_context_32.o \
 				   tlb_32.o
-obj-$(CONFIG_PPC64)		+= init_64.o pgtable_64.o mmu_context_64.o
+hash-$(CONFIG_PPC_MULTIPLATFORM) := hash_native_64.o
+obj-$(CONFIG_PPC64)		+= init_64.o pgtable_64.o mmu_context_64.o \
+				   hash_utils_64.o hash_low_64.o tlb_64.o \
+				   slb_low.o slb.o stab.o mmap.o imalloc.o \
+				   $(hash-y)
 obj-$(CONFIG_PPC_STD_MMU_32)	+= ppc_mmu_32.o hash_low_32.o
 obj-$(CONFIG_40x)		+= 4xx_mmu.o
 obj-$(CONFIG_44x)		+= 44x_mmu.o
 obj-$(CONFIG_FSL_BOOKE)		+= fsl_booke_mmu.o
+obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o

arch/ppc64/mm/hash_low.S → arch/powerpc/mm/hash_low_64.S

@@ -10,7 +10,7 @@
  * described in the kernel's COPYING file.
  */
 
-#include <asm/processor.h>
+#include <asm/reg.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/page.h>

arch/ppc64/mm/hash_utils.c → arch/powerpc/mm/hash_utils_64.c

@@ -78,7 +78,7 @@ extern unsigned long dart_tablebase;
 hpte_t *htab_address;
 unsigned long htab_hash_mask;
 
-extern unsigned long _SDR1;
+unsigned long _SDR1;
 
 #define KB (1024)
 #define MB (1024*KB)

arch/powerpc/mm/init_64.c

@@ -73,18 +73,8 @@
 #warning TASK_SIZE is smaller than it needs to be.
 #endif
 
-int mem_init_done;
-unsigned long ioremap_bot = IMALLOC_BASE;
-static unsigned long phbs_io_bot = PHBS_IO_BASE;
-
-extern pgd_t swapper_pg_dir[];
-extern struct task_struct *current_set[NR_CPUS];
-
 unsigned long klimit = (unsigned long)_end;
 
-unsigned long _SDR1=0;
-unsigned long _ASR=0;
-
 /* max amount of RAM to use */
 unsigned long __max_memory;
 
@@ -193,19 +183,6 @@ static int __init setup_kcore(void)
 }
 module_init(setup_kcore);
 
-void __iomem * reserve_phb_iospace(unsigned long size)
-{
-	void __iomem *virt_addr;
-		
-	if (phbs_io_bot >= IMALLOC_BASE) 
-		panic("reserve_phb_iospace(): phb io space overflow\n");
-			
-	virt_addr = (void __iomem *) phbs_io_bot;
-	phbs_io_bot += size;
-
-	return virt_addr;
-}
-
 static void zero_ctor(void *addr, kmem_cache_t *cache, unsigned long flags)
 {
 	memset(addr, 0, kmem_cache_size(cache));
@@ -244,16 +221,3 @@ void pgtable_cache_init(void)
 			      name);
 	}
 }
-
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long addr,
-			      unsigned long size, pgprot_t vma_prot)
-{
-	if (ppc_md.phys_mem_access_prot)
-		return ppc_md.phys_mem_access_prot(file, addr, size, vma_prot);
-
-	if (!page_is_ram(addr >> PAGE_SHIFT))
-		vma_prot = __pgprot(pgprot_val(vma_prot)
-				    | _PAGE_GUARDED | _PAGE_NO_CACHE);
-	return vma_prot;
-}
-EXPORT_SYMBOL(phys_mem_access_prot);

arch/powerpc/mm/mem.c

@@ -47,6 +47,9 @@
 #include <asm/prom.h>
 #include <asm/lmb.h>
 #include <asm/sections.h>
+#ifdef CONFIG_PPC64
+#include <asm/vdso.h>
+#endif
 
 #include "mmu_decl.h"
 
@@ -334,7 +337,7 @@ void flush_dcache_icache_page(struct page *page)
 	void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE);
 	__flush_dcache_icache(start);
 	kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
-#elif defined(CONFIG_8xx)
+#elif defined(CONFIG_8xx) || defined(CONFIG_PPC64)
 	/* On 8xx there is no need to kmap since highmem is not supported */
 	__flush_dcache_icache(page_address(page)); 
 #else
@@ -463,18 +466,18 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 	if (pgdir == NULL)
 		return;
 
-	ptep = find_linux_pte(pgdir, ea);
+	ptep = find_linux_pte(pgdir, address);
 	if (!ptep)
 		return;
 
-	vsid = get_vsid(vma->vm_mm->context.id, ea);
+	vsid = get_vsid(vma->vm_mm->context.id, address);
 
 	local_irq_save(flags);
 	tmp = cpumask_of_cpu(smp_processor_id());
 	if (cpus_equal(vma->vm_mm->cpu_vm_mask, tmp))
 		local = 1;
 
-	__hash_page(ea, pte_val(pte) & (_PAGE_USER|_PAGE_RW), vsid, ptep,
+	__hash_page(address, pte_val(pte) & (_PAGE_USER|_PAGE_RW), vsid, ptep,
 		    0x300, local);
 	local_irq_restore(flags);
 #endif

arch/powerpc/mm/mmu_decl.h

@@ -22,11 +22,11 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu.h>
 
+#ifdef CONFIG_PPC32
 extern void mapin_ram(void);
 extern int map_page(unsigned long va, phys_addr_t pa, int flags);
 extern void setbat(int index, unsigned long virt, unsigned long phys,
 		   unsigned int size, int flags);
-extern void reserve_phys_mem(unsigned long start, unsigned long size);
 extern void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 		      unsigned int size, int flags, unsigned int pid);
 extern void invalidate_tlbcam_entry(int index);
@@ -36,16 +36,16 @@ extern unsigned long ioremap_base;
 extern unsigned long ioremap_bot;
 extern unsigned int rtas_data, rtas_size;
 
-extern unsigned long __max_low_memory;
-extern unsigned long __initial_memory_limit;
-extern unsigned long total_memory;
-extern unsigned long total_lowmem;
-extern int mem_init_done;
-
 extern PTE *Hash, *Hash_end;
 extern unsigned long Hash_size, Hash_mask;
 
 extern unsigned int num_tlbcam_entries;
+#endif
+
+extern unsigned long __max_low_memory;
+extern unsigned long __initial_memory_limit;
+extern unsigned long total_memory;
+extern unsigned long total_lowmem;
 
 /* ...and now those things that may be slightly different between processor
  * architectures.  -- Dan
@@ -66,8 +66,8 @@ extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(void);
 extern void adjust_total_lowmem(void);
 
-#else
-/* anything except 4xx or 8xx */
+#elif defined(CONFIG_PPC32)
+/* anything 32-bit except 4xx or 8xx */
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(void);
 

arch/powerpc/mm/pgtable_64.c

@@ -67,30 +67,9 @@
 #include <asm/vdso.h>
 #include <asm/imalloc.h>
 
-#if PGTABLE_RANGE > USER_VSID_RANGE
-#warning Limited user VSID range means pagetable space is wasted
-#endif
-
-#if (TASK_SIZE_USER64 < PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
-#warning TASK_SIZE is smaller than it needs to be.
-#endif
-
-int mem_init_done;
 unsigned long ioremap_bot = IMALLOC_BASE;
 static unsigned long phbs_io_bot = PHBS_IO_BASE;
 
-extern pgd_t swapper_pg_dir[];
-extern struct task_struct *current_set[NR_CPUS];
-
-unsigned long klimit = (unsigned long)_end;
-
-/* max amount of RAM to use */
-unsigned long __max_memory;
-
-/* info on what we think the IO hole is */
-unsigned long 	io_hole_start;
-unsigned long	io_hole_size;
-
 #ifdef CONFIG_PPC_ISERIES
 
 void __iomem *ioremap(unsigned long addr, unsigned long size)
@@ -355,3 +334,16 @@ int iounmap_explicit(volatile void __iomem *start, unsigned long size)
 EXPORT_SYMBOL(ioremap);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(iounmap);
+
+void __iomem * reserve_phb_iospace(unsigned long size)
+{
+	void __iomem *virt_addr;
+		
+	if (phbs_io_bot >= IMALLOC_BASE) 
+		panic("reserve_phb_iospace(): phb io space overflow\n");
+			
+	virt_addr = (void __iomem *) phbs_io_bot;
+	phbs_io_bot += size;
+
+	return virt_addr;
+}

arch/ppc64/Makefile

@@ -83,7 +83,7 @@ head-y := arch/ppc64/kernel/head.o
 
 libs-y				+= arch/ppc64/lib/
 core-y				+= arch/ppc64/kernel/ arch/powerpc/kernel/
-core-y				+= arch/ppc64/mm/
+core-y				+= arch/powerpc/mm/
 core-y				+= arch/powerpc/platforms/
 core-$(CONFIG_XMON)		+= arch/ppc64/xmon/
 drivers-$(CONFIG_OPROFILE)	+= arch/powerpc/oprofile/

arch/ppc64/mm/Makefile

-#
-# Makefile for the linux ppc-specific parts of the memory manager.
-#
-
-EXTRA_CFLAGS += -mno-minimal-toc
-
-obj-y := fault.o init.o imalloc.o hash_utils.o hash_low.o tlb.o \
-	slb_low.o slb.o stab.o mmap.o
-obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-obj-$(CONFIG_PPC_MULTIPLATFORM) += hash_native.o

arch/ppc64/mm/fault.c

-/*
- *  arch/ppc/mm/fault.c
- *
- *  PowerPC version 
- *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- *  Derived from "arch/i386/mm/fault.c"
- *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  Modified by Cort Dougan and Paul Mackerras.
- *
- *  Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <linux/config.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/smp_lock.h>
-#include <linux/module.h>
-#include <linux/kprobes.h>
-
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/mmu_context.h>
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/kdebug.h>
-#include <asm/siginfo.h>
-
-/*
- * Check whether the instruction at regs->nip is a store using
- * an update addressing form which will update r1.
- */
-static int store_updates_sp(struct pt_regs *regs)
-{
-	unsigned int inst;
-
-	if (get_user(inst, (unsigned int __user *)regs->nip))
-		return 0;
-	/* check for 1 in the rA field */
-	if (((inst >> 16) & 0x1f) != 1)
-		return 0;
-	/* check major opcode */
-	switch (inst >> 26) {
-	case 37:	/* stwu */
-	case 39:	/* stbu */
-	case 45:	/* sthu */
-	case 53:	/* stfsu */
-	case 55:	/* stfdu */
-		return 1;
-	case 62:	/* std or stdu */
-		return (inst & 3) == 1;
-	case 31:
-		/* check minor opcode */
-		switch ((inst >> 1) & 0x3ff) {
-		case 181:	/* stdux */
-		case 183:	/* stwux */
-		case 247:	/* stbux */
-		case 439:	/* sthux */
-		case 695:	/* stfsux */
-		case 759:	/* stfdux */
-			return 1;
-		}
-	}
-	return 0;
-}
-
-static void do_dabr(struct pt_regs *regs, unsigned long error_code)
-{
-	siginfo_t info;
-
-	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
-			11, SIGSEGV) == NOTIFY_STOP)
-		return;
-
-	if (debugger_dabr_match(regs))
-		return;
-
-	/* Clear the DABR */
-	set_dabr(0);
-
-	/* Deliver the signal to userspace */
-	info.si_signo = SIGTRAP;
-	info.si_errno = 0;
-	info.si_code = TRAP_HWBKPT;
-	info.si_addr = (void __user *)regs->nip;
-	force_sig_info(SIGTRAP, &info, current);
-}
-
-/*
- * The error_code parameter is
- *  - DSISR for a non-SLB data access fault,
- *  - SRR1 & 0x08000000 for a non-SLB instruction access fault
- *  - 0 any SLB fault.
- * The return value is 0 if the fault was handled, or the signal
- * number if this is a kernel fault that can't be handled here.
- */
-int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
-			    unsigned long error_code)
-{
-	struct vm_area_struct * vma;
-	struct mm_struct *mm = current->mm;
-	siginfo_t info;
-	unsigned long code = SEGV_MAPERR;
-	unsigned long is_write = error_code & DSISR_ISSTORE;
-	unsigned long trap = TRAP(regs);
- 	unsigned long is_exec = trap == 0x400;
-
-	BUG_ON((trap == 0x380) || (trap == 0x480));
-
-	if (notify_die(DIE_PAGE_FAULT, "page_fault", regs, error_code,
-				11, SIGSEGV) == NOTIFY_STOP)
-		return 0;
-
-	if (trap == 0x300) {
-		if (debugger_fault_handler(regs))
-			return 0;
-	}
-
-	/* On a kernel SLB miss we can only check for a valid exception entry */
-	if (!user_mode(regs) && (address >= TASK_SIZE))
-		return SIGSEGV;
-
-  	if (error_code & DSISR_DABRMATCH) {
-		do_dabr(regs, error_code);
-		return 0;
-	}
-
-	if (in_atomic() || mm == NULL) {
-		if (!user_mode(regs))
-			return SIGSEGV;
-		/* in_atomic() in user mode is really bad,
-		   as is current->mm == NULL. */
-		printk(KERN_EMERG "Page fault in user mode with"
-		       "in_atomic() = %d mm = %p\n", in_atomic(), mm);
-		printk(KERN_EMERG "NIP = %lx  MSR = %lx\n",
-		       regs->nip, regs->msr);
-		die("Weird page fault", regs, SIGSEGV);
-	}
-
-	/* When running in the kernel we expect faults to occur only to
-	 * addresses in user space.  All other faults represent errors in the
-	 * kernel and should generate an OOPS.  Unfortunatly, in the case of an
-	 * erroneous fault occuring in a code path which already holds mmap_sem
-	 * we will deadlock attempting to validate the fault against the
-	 * address space.  Luckily the kernel only validly references user
-	 * space from well defined areas of code, which are listed in the
-	 * exceptions table.
-	 *
-	 * As the vast majority of faults will be valid we will only perform
-	 * the source reference check when there is a possibilty of a deadlock.
-	 * Attempt to lock the address space, if we cannot we then validate the
-	 * source.  If this is invalid we can skip the address space check,
-	 * thus avoiding the deadlock.
-	 */
-	if (!down_read_trylock(&mm->mmap_sem)) {
-		if (!user_mode(regs) && !search_exception_tables(regs->nip))
-			goto bad_area_nosemaphore;
-
-		down_read(&mm->mmap_sem);
-	}
-
-	vma = find_vma(mm, address);
-	if (!vma)
-		goto bad_area;
-
-	if (vma->vm_start <= address) {
-		goto good_area;
-	}
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
-
-	/*
-	 * N.B. The POWER/Open ABI allows programs to access up to
-	 * 288 bytes below the stack pointer.
-	 * The kernel signal delivery code writes up to about 1.5kB
-	 * below the stack pointer (r1) before decrementing it.
-	 * The exec code can write slightly over 640kB to the stack
-	 * before setting the user r1.  Thus we allow the stack to
-	 * expand to 1MB without further checks.
-	 */
-	if (address + 0x100000 < vma->vm_end) {
-		/* get user regs even if this fault is in kernel mode */
-		struct pt_regs *uregs = current->thread.regs;
-		if (uregs == NULL)
-			goto bad_area;
-
-		/*
-		 * A user-mode access to an address a long way below
-		 * the stack pointer is only valid if the instruction
-		 * is one which would update the stack pointer to the
-		 * address accessed if the instruction completed,
-		 * i.e. either stwu rs,n(r1) or stwux rs,r1,rb
-		 * (or the byte, halfword, float or double forms).
-		 *
-		 * If we don't check this then any write to the area
-		 * between the last mapped region and the stack will
-		 * expand the stack rather than segfaulting.
-		 */
-		if (address + 2048 < uregs->gpr[1]
-		    && (!user_mode(regs) || !store_updates_sp(regs)))
-			goto bad_area;
-	}
-
-	if (expand_stack(vma, address))
-		goto bad_area;
-
-good_area:
-	code = SEGV_ACCERR;
-
-	if (is_exec) {
-		/* protection fault */
-		if (error_code & DSISR_PROTFAULT)
-			goto bad_area;
-		if (!(vma->vm_flags & VM_EXEC))
-			goto bad_area;
-	/* a write */
-	} else if (is_write) {
-		if (!(vma->vm_flags & VM_WRITE))
-			goto bad_area;
-	/* a read */
-	} else {
-		if (!(vma->vm_flags & VM_READ))
-			goto bad_area;
-	}
-
- survive:
-	/*
-	 * If for any reason at all we couldn't handle the fault,
-	 * make sure we exit gracefully rather than endlessly redo
-	 * the fault.
-	 */
-	switch (handle_mm_fault(mm, vma, address, is_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);
-	return 0;
-
-bad_area:
-	up_read(&mm->mmap_sem);
-
-bad_area_nosemaphore:
-	/* User mode accesses cause a SIGSEGV */
-	if (user_mode(regs)) {
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		info.si_code = code;
-		info.si_addr = (void __user *) address;
-		force_sig_info(SIGSEGV, &info, current);
-		return 0;
-	}
-
-	if (trap == 0x400 && (error_code & DSISR_PROTFAULT)
-	    && printk_ratelimit())
-		printk(KERN_CRIT "kernel tried to execute NX-protected"
-		       " page (%lx) - exploit attempt? (uid: %d)\n",
-		       address, current->uid);
-
-	return SIGSEGV;
-
-/*
- * 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:
-	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
-	printk("VM: killing process %s\n", current->comm);
-	if (user_mode(regs))
-		do_exit(SIGKILL);
-	return SIGKILL;
-
-do_sigbus:
-	up_read(&mm->mmap_sem);
-	if (user_mode(regs)) {
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
-		return 0;
-	}
-	return SIGBUS;
-}
-
-/*
- * bad_page_fault is called when we have a bad access from the kernel.
- * It is called from do_page_fault above and from some of the procedures
- * in traps.c.
- */
-void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
-{
-	const struct exception_table_entry *entry;
-
-	/* Are we prepared to handle this fault?  */
-	if ((entry = search_exception_tables(regs->nip)) != NULL) {
-		regs->nip = entry->fixup;
-		return;
-	}
-
-	/* kernel has accessed a bad area */
-	die("Kernel access of bad area", regs, sig);
-}