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: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 35497de..612bc4e 100644
--- a/arch/powerpc/mm/Makefile
+++ b/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
diff --git a/arch/ppc64/mm/hash_low.S b/arch/powerpc/mm/hash_low_64.S
similarity index 98%
rename from arch/ppc64/mm/hash_low.S
rename to arch/powerpc/mm/hash_low_64.S
index ee5a5d3..d6ed910 100644
--- a/arch/ppc64/mm/hash_low.S
+++ b/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>
diff --git a/arch/ppc64/mm/hash_native.c b/arch/powerpc/mm/hash_native_64.c
similarity index 100%
rename from arch/ppc64/mm/hash_native.c
rename to arch/powerpc/mm/hash_native_64.c
diff --git a/arch/ppc64/mm/hash_utils.c b/arch/powerpc/mm/hash_utils_64.c
similarity index 98%
rename from arch/ppc64/mm/hash_utils.c
rename to arch/powerpc/mm/hash_utils_64.c
index 8350743..35dd93e 100644
--- a/arch/ppc64/mm/hash_utils.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -78,7 +78,7 @@
hpte_t *htab_address;
unsigned long htab_hash_mask;
-extern unsigned long _SDR1;
+unsigned long _SDR1;
#define KB (1024)
#define MB (1024*KB)
diff --git a/arch/ppc64/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
similarity index 100%
rename from arch/ppc64/mm/hugetlbpage.c
rename to arch/powerpc/mm/hugetlbpage.c
diff --git a/arch/ppc64/mm/imalloc.c b/arch/powerpc/mm/imalloc.c
similarity index 100%
rename from arch/ppc64/mm/imalloc.c
rename to arch/powerpc/mm/imalloc.c
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index c0ce6a7..b0fc822 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/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 @@
}
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 @@
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);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 0650de7..55b5860 100644
--- a/arch/powerpc/mm/mem.c
+++ b/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 *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 @@
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
diff --git a/arch/ppc64/mm/mmap.c b/arch/powerpc/mm/mmap.c
similarity index 100%
rename from arch/ppc64/mm/mmap.c
rename to arch/powerpc/mm/mmap.c
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 06fe8af..a4d7a32 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/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_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 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);
diff --git a/arch/ppc64/mm/numa.c b/arch/powerpc/mm/numa.c
similarity index 100%
rename from arch/ppc64/mm/numa.c
rename to arch/powerpc/mm/numa.c
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 724f97e..484d24f 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/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 @@
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;
+}
diff --git a/arch/ppc64/mm/slb.c b/arch/powerpc/mm/slb.c
similarity index 100%
rename from arch/ppc64/mm/slb.c
rename to arch/powerpc/mm/slb.c
diff --git a/arch/ppc64/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
similarity index 100%
rename from arch/ppc64/mm/slb_low.S
rename to arch/powerpc/mm/slb_low.S
diff --git a/arch/ppc64/mm/stab.c b/arch/powerpc/mm/stab.c
similarity index 100%
rename from arch/ppc64/mm/stab.c
rename to arch/powerpc/mm/stab.c
diff --git a/arch/ppc64/mm/tlb.c b/arch/powerpc/mm/tlb_64.c
similarity index 100%
rename from arch/ppc64/mm/tlb.c
rename to arch/powerpc/mm/tlb_64.c
diff --git a/arch/ppc64/Makefile b/arch/ppc64/Makefile
index fa88920..4a9928e 100644
--- a/arch/ppc64/Makefile
+++ b/arch/ppc64/Makefile
@@ -83,7 +83,7 @@
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-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/
diff --git a/arch/ppc64/mm/Makefile b/arch/ppc64/mm/Makefile
deleted file mode 100644
index 3695d00..0000000
--- a/arch/ppc64/mm/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-#
-# Makefile for the linux ppc-specific parts of the memory manager.
-#
-
-EXTRA_CFLAGS += -mno-minimal-toc
-
-obj-y := fault.o init.o imalloc.o hash_utils.o hash_low.o tlb.o \
- slb_low.o slb.o stab.o mmap.o
-obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-obj-$(CONFIG_PPC_MULTIPLATFORM) += hash_native.o
diff --git a/arch/ppc64/mm/fault.c b/arch/ppc64/mm/fault.c
deleted file mode 100644
index be3f25c..0000000
--- a/arch/ppc64/mm/fault.c
+++ /dev/null
@@ -1,333 +0,0 @@
-/*
- * 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);
-}
diff --git a/arch/ppc64/mm/init.c b/arch/ppc64/mm/init.c
deleted file mode 100644
index c2157c9..0000000
--- a/arch/ppc64/mm/init.c
+++ /dev/null
@@ -1,870 +0,0 @@
-/*
- * PowerPC version
- * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
- * and Cort Dougan (PReP) (cort@cs.nmt.edu)
- * Copyright (C) 1996 Paul Mackerras
- * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
- *
- * Derived from "arch/i386/mm/init.c"
- * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
- *
- * Dave Engebretsen <engebret@us.ibm.com>
- * Rework for PPC64 port.
- *
- * 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/swap.h>
-#include <linux/stddef.h>
-#include <linux/vmalloc.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/bootmem.h>
-#include <linux/highmem.h>
-#include <linux/idr.h>
-#include <linux/nodemask.h>
-#include <linux/module.h>
-
-#include <asm/pgalloc.h>
-#include <asm/page.h>
-#include <asm/prom.h>
-#include <asm/lmb.h>
-#include <asm/rtas.h>
-#include <asm/io.h>
-#include <asm/mmu_context.h>
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/uaccess.h>
-#include <asm/smp.h>
-#include <asm/machdep.h>
-#include <asm/tlb.h>
-#include <asm/eeh.h>
-#include <asm/processor.h>
-#include <asm/mmzone.h>
-#include <asm/cputable.h>
-#include <asm/ppcdebug.h>
-#include <asm/sections.h>
-#include <asm/system.h>
-#include <asm/iommu.h>
-#include <asm/abs_addr.h>
-#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;
-
-unsigned long _SDR1=0;
-unsigned long _ASR=0;
-
-/* 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;
-
-void show_mem(void)
-{
- unsigned long total = 0, reserved = 0;
- unsigned long shared = 0, cached = 0;
- struct page *page;
- pg_data_t *pgdat;
- unsigned long i;
-
- printk("Mem-info:\n");
- show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
- for_each_pgdat(pgdat) {
- for (i = 0; i < pgdat->node_spanned_pages; i++) {
- page = pgdat_page_nr(pgdat, i);
- total++;
- if (PageReserved(page))
- reserved++;
- else if (PageSwapCache(page))
- cached++;
- else if (page_count(page))
- shared += page_count(page) - 1;
- }
- }
- printk("%ld pages of RAM\n", total);
- printk("%ld reserved pages\n", reserved);
- printk("%ld pages shared\n", shared);
- printk("%ld pages swap cached\n", cached);
-}
-
-#ifdef CONFIG_PPC_ISERIES
-
-void __iomem *ioremap(unsigned long addr, unsigned long size)
-{
- return (void __iomem *)addr;
-}
-
-extern void __iomem *__ioremap(unsigned long addr, unsigned long size,
- unsigned long flags)
-{
- return (void __iomem *)addr;
-}
-
-void iounmap(volatile void __iomem *addr)
-{
- return;
-}
-
-#else
-
-/*
- * map_io_page currently only called by __ioremap
- * map_io_page adds an entry to the ioremap page table
- * and adds an entry to the HPT, possibly bolting it
- */
-static int map_io_page(unsigned long ea, unsigned long pa, int flags)
-{
- pgd_t *pgdp;
- pud_t *pudp;
- pmd_t *pmdp;
- pte_t *ptep;
- unsigned long vsid;
-
- if (mem_init_done) {
- spin_lock(&init_mm.page_table_lock);
- pgdp = pgd_offset_k(ea);
- pudp = pud_alloc(&init_mm, pgdp, ea);
- if (!pudp)
- return -ENOMEM;
- pmdp = pmd_alloc(&init_mm, pudp, ea);
- if (!pmdp)
- return -ENOMEM;
- ptep = pte_alloc_kernel(&init_mm, pmdp, ea);
- if (!ptep)
- return -ENOMEM;
- set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
- __pgprot(flags)));
- spin_unlock(&init_mm.page_table_lock);
- } else {
- unsigned long va, vpn, hash, hpteg;
-
- /*
- * If the mm subsystem is not fully up, we cannot create a
- * linux page table entry for this mapping. Simply bolt an
- * entry in the hardware page table.
- */
- vsid = get_kernel_vsid(ea);
- va = (vsid << 28) | (ea & 0xFFFFFFF);
- vpn = va >> PAGE_SHIFT;
-
- hash = hpt_hash(vpn, 0);
-
- hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
-
- /* Panic if a pte grpup is full */
- if (ppc_md.hpte_insert(hpteg, va, pa >> PAGE_SHIFT,
- HPTE_V_BOLTED,
- _PAGE_NO_CACHE|_PAGE_GUARDED|PP_RWXX)
- == -1) {
- panic("map_io_page: could not insert mapping");
- }
- }
- return 0;
-}
-
-
-static void __iomem * __ioremap_com(unsigned long addr, unsigned long pa,
- unsigned long ea, unsigned long size,
- unsigned long flags)
-{
- unsigned long i;
-
- if ((flags & _PAGE_PRESENT) == 0)
- flags |= pgprot_val(PAGE_KERNEL);
-
- for (i = 0; i < size; i += PAGE_SIZE)
- if (map_io_page(ea+i, pa+i, flags))
- return NULL;
-
- return (void __iomem *) (ea + (addr & ~PAGE_MASK));
-}
-
-
-void __iomem *
-ioremap(unsigned long addr, unsigned long size)
-{
- return __ioremap(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED);
-}
-
-void __iomem * __ioremap(unsigned long addr, unsigned long size,
- unsigned long flags)
-{
- unsigned long pa, ea;
- void __iomem *ret;
-
- /*
- * Choose an address to map it to.
- * Once the imalloc system is running, we use it.
- * Before that, we map using addresses going
- * up from ioremap_bot. imalloc will use
- * the addresses from ioremap_bot through
- * IMALLOC_END
- *
- */
- pa = addr & PAGE_MASK;
- size = PAGE_ALIGN(addr + size) - pa;
-
- if (size == 0)
- return NULL;
-
- if (mem_init_done) {
- struct vm_struct *area;
- area = im_get_free_area(size);
- if (area == NULL)
- return NULL;
- ea = (unsigned long)(area->addr);
- ret = __ioremap_com(addr, pa, ea, size, flags);
- if (!ret)
- im_free(area->addr);
- } else {
- ea = ioremap_bot;
- ret = __ioremap_com(addr, pa, ea, size, flags);
- if (ret)
- ioremap_bot += size;
- }
- return ret;
-}
-
-#define IS_PAGE_ALIGNED(_val) ((_val) == ((_val) & PAGE_MASK))
-
-int __ioremap_explicit(unsigned long pa, unsigned long ea,
- unsigned long size, unsigned long flags)
-{
- struct vm_struct *area;
- void __iomem *ret;
-
- /* For now, require page-aligned values for pa, ea, and size */
- if (!IS_PAGE_ALIGNED(pa) || !IS_PAGE_ALIGNED(ea) ||
- !IS_PAGE_ALIGNED(size)) {
- printk(KERN_ERR "unaligned value in %s\n", __FUNCTION__);
- return 1;
- }
-
- if (!mem_init_done) {
- /* Two things to consider in this case:
- * 1) No records will be kept (imalloc, etc) that the region
- * has been remapped
- * 2) It won't be easy to iounmap() the region later (because
- * of 1)
- */
- ;
- } else {
- area = im_get_area(ea, size,
- IM_REGION_UNUSED|IM_REGION_SUBSET|IM_REGION_EXISTS);
- if (area == NULL) {
- /* Expected when PHB-dlpar is in play */
- return 1;
- }
- if (ea != (unsigned long) area->addr) {
- printk(KERN_ERR "unexpected addr return from "
- "im_get_area\n");
- return 1;
- }
- }
-
- ret = __ioremap_com(pa, pa, ea, size, flags);
- if (ret == NULL) {
- printk(KERN_ERR "ioremap_explicit() allocation failure !\n");
- return 1;
- }
- if (ret != (void *) ea) {
- printk(KERN_ERR "__ioremap_com() returned unexpected addr\n");
- return 1;
- }
-
- return 0;
-}
-
-/*
- * Unmap an IO region and remove it from imalloc'd list.
- * Access to IO memory should be serialized by driver.
- * This code is modeled after vmalloc code - unmap_vm_area()
- *
- * XXX what about calls before mem_init_done (ie python_countermeasures())
- */
-void iounmap(volatile void __iomem *token)
-{
- void *addr;
-
- if (!mem_init_done)
- return;
-
- addr = (void *) ((unsigned long __force) token & PAGE_MASK);
-
- im_free(addr);
-}
-
-static int iounmap_subset_regions(unsigned long addr, unsigned long size)
-{
- struct vm_struct *area;
-
- /* Check whether subsets of this region exist */
- area = im_get_area(addr, size, IM_REGION_SUPERSET);
- if (area == NULL)
- return 1;
-
- while (area) {
- iounmap((void __iomem *) area->addr);
- area = im_get_area(addr, size,
- IM_REGION_SUPERSET);
- }
-
- return 0;
-}
-
-int iounmap_explicit(volatile void __iomem *start, unsigned long size)
-{
- struct vm_struct *area;
- unsigned long addr;
- int rc;
-
- addr = (unsigned long __force) start & PAGE_MASK;
-
- /* Verify that the region either exists or is a subset of an existing
- * region. In the latter case, split the parent region to create
- * the exact region
- */
- area = im_get_area(addr, size,
- IM_REGION_EXISTS | IM_REGION_SUBSET);
- if (area == NULL) {
- /* Determine whether subset regions exist. If so, unmap */
- rc = iounmap_subset_regions(addr, size);
- if (rc) {
- printk(KERN_ERR
- "%s() cannot unmap nonexistent range 0x%lx\n",
- __FUNCTION__, addr);
- return 1;
- }
- } else {
- iounmap((void __iomem *) area->addr);
- }
- /*
- * FIXME! This can't be right:
- iounmap(area->addr);
- * Maybe it should be "iounmap(area);"
- */
- return 0;
-}
-
-#endif
-
-EXPORT_SYMBOL(ioremap);
-EXPORT_SYMBOL(__ioremap);
-EXPORT_SYMBOL(iounmap);
-
-void free_initmem(void)
-{
- unsigned long addr;
-
- addr = (unsigned long)__init_begin;
- for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
- memset((void *)addr, 0xcc, PAGE_SIZE);
- ClearPageReserved(virt_to_page(addr));
- set_page_count(virt_to_page(addr), 1);
- free_page(addr);
- totalram_pages++;
- }
- printk ("Freeing unused kernel memory: %luk freed\n",
- ((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
- if (start < end)
- printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
- for (; start < end; start += PAGE_SIZE) {
- ClearPageReserved(virt_to_page(start));
- set_page_count(virt_to_page(start), 1);
- free_page(start);
- totalram_pages++;
- }
-}
-#endif
-
-static DEFINE_SPINLOCK(mmu_context_lock);
-static DEFINE_IDR(mmu_context_idr);
-
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
- int index;
- int err;
-
-again:
- if (!idr_pre_get(&mmu_context_idr, GFP_KERNEL))
- return -ENOMEM;
-
- spin_lock(&mmu_context_lock);
- err = idr_get_new_above(&mmu_context_idr, NULL, 1, &index);
- spin_unlock(&mmu_context_lock);
-
- if (err == -EAGAIN)
- goto again;
- else if (err)
- return err;
-
- if (index > MAX_CONTEXT) {
- idr_remove(&mmu_context_idr, index);
- return -ENOMEM;
- }
-
- mm->context.id = index;
-
- return 0;
-}
-
-void destroy_context(struct mm_struct *mm)
-{
- spin_lock(&mmu_context_lock);
- idr_remove(&mmu_context_idr, mm->context.id);
- spin_unlock(&mmu_context_lock);
-
- mm->context.id = NO_CONTEXT;
-}
-
-/*
- * Do very early mm setup.
- */
-void __init mm_init_ppc64(void)
-{
-#ifndef CONFIG_PPC_ISERIES
- unsigned long i;
-#endif
-
- ppc64_boot_msg(0x100, "MM Init");
-
- /* This is the story of the IO hole... please, keep seated,
- * unfortunately, we are out of oxygen masks at the moment.
- * So we need some rough way to tell where your big IO hole
- * is. On pmac, it's between 2G and 4G, on POWER3, it's around
- * that area as well, on POWER4 we don't have one, etc...
- * We need that as a "hint" when sizing the TCE table on POWER3
- * So far, the simplest way that seem work well enough for us it
- * to just assume that the first discontinuity in our physical
- * RAM layout is the IO hole. That may not be correct in the future
- * (and isn't on iSeries but then we don't care ;)
- */
-
-#ifndef CONFIG_PPC_ISERIES
- for (i = 1; i < lmb.memory.cnt; i++) {
- unsigned long base, prevbase, prevsize;
-
- prevbase = lmb.memory.region[i-1].base;
- prevsize = lmb.memory.region[i-1].size;
- base = lmb.memory.region[i].base;
- if (base > (prevbase + prevsize)) {
- io_hole_start = prevbase + prevsize;
- io_hole_size = base - (prevbase + prevsize);
- break;
- }
- }
-#endif /* CONFIG_PPC_ISERIES */
- if (io_hole_start)
- printk("IO Hole assumed to be %lx -> %lx\n",
- io_hole_start, io_hole_start + io_hole_size - 1);
-
- ppc64_boot_msg(0x100, "MM Init Done");
-}
-
-/*
- * This is called by /dev/mem to know if a given address has to
- * be mapped non-cacheable or not
- */
-int page_is_ram(unsigned long pfn)
-{
- int i;
- unsigned long paddr = (pfn << PAGE_SHIFT);
-
- for (i=0; i < lmb.memory.cnt; i++) {
- unsigned long base;
-
- base = lmb.memory.region[i].base;
-
- if ((paddr >= base) &&
- (paddr < (base + lmb.memory.region[i].size))) {
- return 1;
- }
- }
-
- return 0;
-}
-EXPORT_SYMBOL(page_is_ram);
-
-/*
- * Initialize the bootmem system and give it all the memory we
- * have available.
- */
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init do_init_bootmem(void)
-{
- unsigned long i;
- unsigned long start, bootmap_pages;
- unsigned long total_pages = lmb_end_of_DRAM() >> PAGE_SHIFT;
- int boot_mapsize;
-
- /*
- * Find an area to use for the bootmem bitmap. Calculate the size of
- * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE.
- * Add 1 additional page in case the address isn't page-aligned.
- */
- bootmap_pages = bootmem_bootmap_pages(total_pages);
-
- start = lmb_alloc(bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
- BUG_ON(!start);
-
- boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages);
-
- max_pfn = max_low_pfn;
-
- /* Add all physical memory to the bootmem map, mark each area
- * present.
- */
- for (i=0; i < lmb.memory.cnt; i++)
- free_bootmem(lmb.memory.region[i].base,
- lmb_size_bytes(&lmb.memory, i));
-
- /* reserve the sections we're already using */
- for (i=0; i < lmb.reserved.cnt; i++)
- reserve_bootmem(lmb.reserved.region[i].base,
- lmb_size_bytes(&lmb.reserved, i));
-
- for (i=0; i < lmb.memory.cnt; i++)
- memory_present(0, lmb_start_pfn(&lmb.memory, i),
- lmb_end_pfn(&lmb.memory, i));
-}
-
-/*
- * paging_init() sets up the page tables - in fact we've already done this.
- */
-void __init paging_init(void)
-{
- unsigned long zones_size[MAX_NR_ZONES];
- unsigned long zholes_size[MAX_NR_ZONES];
- unsigned long total_ram = lmb_phys_mem_size();
- unsigned long top_of_ram = lmb_end_of_DRAM();
-
- printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
- top_of_ram, total_ram);
- printk(KERN_INFO "Memory hole size: %ldMB\n",
- (top_of_ram - total_ram) >> 20);
- /*
- * All pages are DMA-able so we put them all in the DMA zone.
- */
- memset(zones_size, 0, sizeof(zones_size));
- memset(zholes_size, 0, sizeof(zholes_size));
-
- zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
- zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT;
-
- free_area_init_node(0, NODE_DATA(0), zones_size,
- __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size);
-}
-#endif /* ! CONFIG_NEED_MULTIPLE_NODES */
-
-static struct kcore_list kcore_vmem;
-
-static int __init setup_kcore(void)
-{
- int i;
-
- for (i=0; i < lmb.memory.cnt; i++) {
- unsigned long base, size;
- struct kcore_list *kcore_mem;
-
- base = lmb.memory.region[i].base;
- size = lmb.memory.region[i].size;
-
- /* GFP_ATOMIC to avoid might_sleep warnings during boot */
- kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC);
- if (!kcore_mem)
- panic("mem_init: kmalloc failed\n");
-
- kclist_add(kcore_mem, __va(base), size);
- }
-
- kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START);
-
- return 0;
-}
-module_init(setup_kcore);
-
-void __init mem_init(void)
-{
-#ifdef CONFIG_NEED_MULTIPLE_NODES
- int nid;
-#endif
- pg_data_t *pgdat;
- unsigned long i;
- struct page *page;
- unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize;
-
- num_physpages = max_low_pfn; /* RAM is assumed contiguous */
- high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-
-#ifdef CONFIG_NEED_MULTIPLE_NODES
- for_each_online_node(nid) {
- if (NODE_DATA(nid)->node_spanned_pages != 0) {
- printk("freeing bootmem node %x\n", nid);
- totalram_pages +=
- free_all_bootmem_node(NODE_DATA(nid));
- }
- }
-#else
- max_mapnr = num_physpages;
- totalram_pages += free_all_bootmem();
-#endif
-
- for_each_pgdat(pgdat) {
- for (i = 0; i < pgdat->node_spanned_pages; i++) {
- page = pgdat_page_nr(pgdat, i);
- if (PageReserved(page))
- reservedpages++;
- }
- }
-
- codesize = (unsigned long)&_etext - (unsigned long)&_stext;
- initsize = (unsigned long)&__init_end - (unsigned long)&__init_begin;
- datasize = (unsigned long)&_edata - (unsigned long)&__init_end;
- bsssize = (unsigned long)&__bss_stop - (unsigned long)&__bss_start;
-
- printk(KERN_INFO "Memory: %luk/%luk available (%luk kernel code, "
- "%luk reserved, %luk data, %luk bss, %luk init)\n",
- (unsigned long)nr_free_pages() << (PAGE_SHIFT-10),
- num_physpages << (PAGE_SHIFT-10),
- codesize >> 10,
- reservedpages << (PAGE_SHIFT-10),
- datasize >> 10,
- bsssize >> 10,
- initsize >> 10);
-
- mem_init_done = 1;
-
- /* Initialize the vDSO */
- vdso_init();
-}
-
-/*
- * This is called when a page has been modified by the kernel.
- * It just marks the page as not i-cache clean. We do the i-cache
- * flush later when the page is given to a user process, if necessary.
- */
-void flush_dcache_page(struct page *page)
-{
- if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
- return;
- /* avoid an atomic op if possible */
- if (test_bit(PG_arch_1, &page->flags))
- clear_bit(PG_arch_1, &page->flags);
-}
-EXPORT_SYMBOL(flush_dcache_page);
-
-void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
-{
- clear_page(page);
-
- if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
- return;
- /*
- * We shouldnt have to do this, but some versions of glibc
- * require it (ld.so assumes zero filled pages are icache clean)
- * - Anton
- */
-
- /* avoid an atomic op if possible */
- if (test_bit(PG_arch_1, &pg->flags))
- clear_bit(PG_arch_1, &pg->flags);
-}
-EXPORT_SYMBOL(clear_user_page);
-
-void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
- struct page *pg)
-{
- copy_page(vto, vfrom);
-
- /*
- * We should be able to use the following optimisation, however
- * there are two problems.
- * Firstly a bug in some versions of binutils meant PLT sections
- * were not marked executable.
- * Secondly the first word in the GOT section is blrl, used
- * to establish the GOT address. Until recently the GOT was
- * not marked executable.
- * - Anton
- */
-#if 0
- if (!vma->vm_file && ((vma->vm_flags & VM_EXEC) == 0))
- return;
-#endif
-
- if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
- return;
-
- /* avoid an atomic op if possible */
- if (test_bit(PG_arch_1, &pg->flags))
- clear_bit(PG_arch_1, &pg->flags);
-}
-
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
- unsigned long addr, int len)
-{
- unsigned long maddr;
-
- maddr = (unsigned long)page_address(page) + (addr & ~PAGE_MASK);
- flush_icache_range(maddr, maddr + len);
-}
-EXPORT_SYMBOL(flush_icache_user_range);
-
-/*
- * This is called at the end of handling a user page fault, when the
- * fault has been handled by updating a PTE in the linux page tables.
- * We use it to preload an HPTE into the hash table corresponding to
- * the updated linux PTE.
- *
- * This must always be called with the mm->page_table_lock held
- */
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long ea,
- pte_t pte)
-{
- unsigned long vsid;
- void *pgdir;
- pte_t *ptep;
- int local = 0;
- cpumask_t tmp;
- unsigned long flags;
-
- /* handle i-cache coherency */
- if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE) &&
- !cpu_has_feature(CPU_FTR_NOEXECUTE)) {
- unsigned long pfn = pte_pfn(pte);
- if (pfn_valid(pfn)) {
- struct page *page = pfn_to_page(pfn);
- if (!PageReserved(page)
- && !test_bit(PG_arch_1, &page->flags)) {
- __flush_dcache_icache(page_address(page));
- set_bit(PG_arch_1, &page->flags);
- }
- }
- }
-
- /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
- if (!pte_young(pte))
- return;
-
- pgdir = vma->vm_mm->pgd;
- if (pgdir == NULL)
- return;
-
- ptep = find_linux_pte(pgdir, ea);
- if (!ptep)
- return;
-
- vsid = get_vsid(vma->vm_mm->context.id, ea);
-
- 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,
- 0x300, local);
- local_irq_restore(flags);
-}
-
-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));
-}
-
-static const int pgtable_cache_size[2] = {
- PTE_TABLE_SIZE, PMD_TABLE_SIZE
-};
-static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
- "pgd_pte_cache", "pud_pmd_cache",
-};
-
-kmem_cache_t *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];
-
-void pgtable_cache_init(void)
-{
- int i;
-
- BUILD_BUG_ON(PTE_TABLE_SIZE != pgtable_cache_size[PTE_CACHE_NUM]);
- BUILD_BUG_ON(PMD_TABLE_SIZE != pgtable_cache_size[PMD_CACHE_NUM]);
- BUILD_BUG_ON(PUD_TABLE_SIZE != pgtable_cache_size[PUD_CACHE_NUM]);
- BUILD_BUG_ON(PGD_TABLE_SIZE != pgtable_cache_size[PGD_CACHE_NUM]);
-
- for (i = 0; i < ARRAY_SIZE(pgtable_cache_size); i++) {
- int size = pgtable_cache_size[i];
- const char *name = pgtable_cache_name[i];
-
- pgtable_cache[i] = kmem_cache_create(name,
- size, size,
- SLAB_HWCACHE_ALIGN
- | SLAB_MUST_HWCACHE_ALIGN,
- zero_ctor,
- NULL);
- if (! pgtable_cache[i])
- panic("pgtable_cache_init(): could not create %s!\n",
- 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);