linux/arch/powerpc/mm/init_64.c

333 lines
9.3 KiB
C
Raw Normal View History

/*
* 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
*
* 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.
*
*/
#undef DEBUG
#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 <linux/poison.h>
#include <linux/memblock.h>
powerpc/mm: Allow more flexible layouts for hugepage pagetables Currently each available hugepage size uses a slightly different pagetable layout: that is, the bottem level table of pointers to hugepages is a different size, and may branch off from the normal page tables at a different level. Every hugepage aware path that needs to walk the pagetables must therefore look up the hugepage size from the slice info first, and work out the correct way to walk the pagetables accordingly. Future hardware is likely to add more possible hugepage sizes, more layout options and more mess. This patch, therefore reworks the handling of hugepage pagetables to reduce this complexity. In the new scheme, instead of having to consult the slice mask, pagetable walking code can check a flag in the PGD/PUD/PMD entries to see where to branch off to hugepage pagetables, and the entry also contains the information (eseentially hugepage shift) necessary to then interpret that table without recourse to the slice mask. This scheme can be extended neatly to handle multiple levels of self-describing "special" hugepage pagetables, although for now we assume only one level exists. This approach means that only the pagetable allocation path needs to know how the pagetables should be set out. All other (hugepage) pagetable walking paths can just interpret the structure as they go. There already was a flag bit in PGD/PUD/PMD entries for hugepage directory pointers, but it was only used for debug. We alter that flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable pointer (normally it would be 1 since the pointer lies in the linear mapping). This means that asm pagetable walking can test for (and punt on) hugepage pointers with the same test that checks for unpopulated page directory entries (beq becomes bge), since hugepage pointers will always be positive, and normal pointers always negative. While we're at it, we get rid of the confusing (and grep defeating) #defining of hugepte_shift to be the same thing as mmu_huge_psizes. Signed-off-by: David Gibson <dwg@au1.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-10-26 19:24:31 +00:00
#include <linux/hugetlb.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/prom.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/sections.h>
#include <asm/system.h>
#include <asm/iommu.h>
#include <asm/abs_addr.h>
#include <asm/vdso.h>
#include "mmu_decl.h"
#ifdef CONFIG_PPC_STD_MMU_64
#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
#endif /* CONFIG_PPC_STD_MMU_64 */
[POWERPC] 85xx: Add support for relocatable kernel (and booting at non-zero) Added support to allow an 85xx kernel to be run from a non-zero physical address (useful for cooperative asymmetric multiprocessing situations and kdump). The support can be configured at compile time by setting CONFIG_PAGE_OFFSET, CONFIG_KERNEL_START, and CONFIG_PHYSICAL_START as desired. Alternatively, the kernel build can set CONFIG_RELOCATABLE. Setting this config option causes the kernel to determine at runtime the physical addresses of CONFIG_PAGE_OFFSET and CONFIG_KERNEL_START. If CONFIG_RELOCATABLE is set, then CONFIG_PHYSICAL_START has no meaning. However, CONFIG_PHYSICAL_START will always be used to set the LOAD program header physical address field in the resulting ELF image. Currently we are limited to running at a physical address that is a multiple of 256M. This is due to how we map TLBs to cover lowmem. This should be fixed to allow 64M or maybe even 16M alignment in the future. It is considered an error to try and run a kernel at a non-aligned physical address. All the magic for this support is accomplished by proper initialization of the kernel memory subsystem and use of ARCH_PFN_OFFSET. The use of ARCH_PFN_OFFSET only affects normal memory and not IO mappings. ioremap uses map_page and isn't affected by ARCH_PFN_OFFSET. /dev/mem continues to allow access to any physical address in the system regardless of how CONFIG_PHYSICAL_START is set. Signed-off-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-04-21 18:22:34 +00:00
phys_addr_t memstart_addr = ~0;
EXPORT_SYMBOL_GPL(memstart_addr);
[POWERPC] 85xx: Add support for relocatable kernel (and booting at non-zero) Added support to allow an 85xx kernel to be run from a non-zero physical address (useful for cooperative asymmetric multiprocessing situations and kdump). The support can be configured at compile time by setting CONFIG_PAGE_OFFSET, CONFIG_KERNEL_START, and CONFIG_PHYSICAL_START as desired. Alternatively, the kernel build can set CONFIG_RELOCATABLE. Setting this config option causes the kernel to determine at runtime the physical addresses of CONFIG_PAGE_OFFSET and CONFIG_KERNEL_START. If CONFIG_RELOCATABLE is set, then CONFIG_PHYSICAL_START has no meaning. However, CONFIG_PHYSICAL_START will always be used to set the LOAD program header physical address field in the resulting ELF image. Currently we are limited to running at a physical address that is a multiple of 256M. This is due to how we map TLBs to cover lowmem. This should be fixed to allow 64M or maybe even 16M alignment in the future. It is considered an error to try and run a kernel at a non-aligned physical address. All the magic for this support is accomplished by proper initialization of the kernel memory subsystem and use of ARCH_PFN_OFFSET. The use of ARCH_PFN_OFFSET only affects normal memory and not IO mappings. ioremap uses map_page and isn't affected by ARCH_PFN_OFFSET. /dev/mem continues to allow access to any physical address in the system regardless of how CONFIG_PHYSICAL_START is set. Signed-off-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-04-21 18:22:34 +00:00
phys_addr_t kernstart_addr;
EXPORT_SYMBOL_GPL(kernstart_addr);
void free_initmem(void)
{
unsigned long addr;
addr = (unsigned long)__init_begin;
for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
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));
init_page_count(virt_to_page(start));
free_page(start);
totalram_pages++;
}
}
#endif
static void pgd_ctor(void *addr)
{
memset(addr, 0, PGD_TABLE_SIZE);
}
static void pmd_ctor(void *addr)
{
memset(addr, 0, PMD_TABLE_SIZE);
}
struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
/*
* Create a kmem_cache() for pagetables. This is not used for PTE
* pages - they're linked to struct page, come from the normal free
* pages pool and have a different entry size (see real_pte_t) to
* everything else. Caches created by this function are used for all
* the higher level pagetables, and for hugepage pagetables.
*/
void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
{
char *name;
unsigned long table_size = sizeof(void *) << shift;
unsigned long align = table_size;
/* When batching pgtable pointers for RCU freeing, we store
* the index size in the low bits. Table alignment must be
powerpc/mm: Allow more flexible layouts for hugepage pagetables Currently each available hugepage size uses a slightly different pagetable layout: that is, the bottem level table of pointers to hugepages is a different size, and may branch off from the normal page tables at a different level. Every hugepage aware path that needs to walk the pagetables must therefore look up the hugepage size from the slice info first, and work out the correct way to walk the pagetables accordingly. Future hardware is likely to add more possible hugepage sizes, more layout options and more mess. This patch, therefore reworks the handling of hugepage pagetables to reduce this complexity. In the new scheme, instead of having to consult the slice mask, pagetable walking code can check a flag in the PGD/PUD/PMD entries to see where to branch off to hugepage pagetables, and the entry also contains the information (eseentially hugepage shift) necessary to then interpret that table without recourse to the slice mask. This scheme can be extended neatly to handle multiple levels of self-describing "special" hugepage pagetables, although for now we assume only one level exists. This approach means that only the pagetable allocation path needs to know how the pagetables should be set out. All other (hugepage) pagetable walking paths can just interpret the structure as they go. There already was a flag bit in PGD/PUD/PMD entries for hugepage directory pointers, but it was only used for debug. We alter that flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable pointer (normally it would be 1 since the pointer lies in the linear mapping). This means that asm pagetable walking can test for (and punt on) hugepage pointers with the same test that checks for unpopulated page directory entries (beq becomes bge), since hugepage pointers will always be positive, and normal pointers always negative. While we're at it, we get rid of the confusing (and grep defeating) #defining of hugepte_shift to be the same thing as mmu_huge_psizes. Signed-off-by: David Gibson <dwg@au1.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-10-26 19:24:31 +00:00
* big enough to fit it.
*
* Likewise, hugeapge pagetable pointers contain a (different)
* shift value in the low bits. All tables must be aligned so
* as to leave enough 0 bits in the address to contain it. */
unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
HUGEPD_SHIFT_MASK + 1);
struct kmem_cache *new;
/* It would be nice if this was a BUILD_BUG_ON(), but at the
* moment, gcc doesn't seem to recognize is_power_of_2 as a
* constant expression, so so much for that. */
BUG_ON(!is_power_of_2(minalign));
BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
if (PGT_CACHE(shift))
return; /* Already have a cache of this size */
align = max_t(unsigned long, align, minalign);
name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
new = kmem_cache_create(name, table_size, align, 0, ctor);
PGT_CACHE(shift) = new;
pr_debug("Allocated pgtable cache for order %d\n", shift);
}
void pgtable_cache_init(void)
{
pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
panic("Couldn't allocate pgtable caches");
/* In all current configs, when the PUD index exists it's the
* same size as either the pgd or pmd index. Verify that the
* initialization above has also created a PUD cache. This
* will need re-examiniation if we add new possibilities for
* the pagetable layout. */
BUG_ON(PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE));
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Given an address within the vmemmap, determine the pfn of the page that
* represents the start of the section it is within. Note that we have to
* do this by hand as the proffered address may not be correctly aligned.
* Subtraction of non-aligned pointers produces undefined results.
*/
static unsigned long __meminit vmemmap_section_start(unsigned long page)
{
unsigned long offset = page - ((unsigned long)(vmemmap));
/* Return the pfn of the start of the section. */
return (offset / sizeof(struct page)) & PAGE_SECTION_MASK;
}
/*
* Check if this vmemmap page is already initialised. If any section
* which overlaps this vmemmap page is initialised then this page is
* initialised already.
*/
static int __meminit vmemmap_populated(unsigned long start, int page_size)
{
unsigned long end = start + page_size;
for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page)))
if (pfn_valid(vmemmap_section_start(start)))
return 1;
return 0;
}
/* On hash-based CPUs, the vmemmap is bolted in the hash table.
*
* On Book3E CPUs, the vmemmap is currently mapped in the top half of
* the vmalloc space using normal page tables, though the size of
* pages encoded in the PTEs can be different
*/
#ifdef CONFIG_PPC_BOOK3E
static void __meminit vmemmap_create_mapping(unsigned long start,
unsigned long page_size,
unsigned long phys)
{
/* Create a PTE encoding without page size */
unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED |
_PAGE_KERNEL_RW;
/* PTEs only contain page size encodings up to 32M */
BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf);
/* Encode the size in the PTE */
flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8;
/* For each PTE for that area, map things. Note that we don't
* increment phys because all PTEs are of the large size and
* thus must have the low bits clear
*/
for (i = 0; i < page_size; i += PAGE_SIZE)
BUG_ON(map_kernel_page(start + i, phys, flags));
}
#else /* CONFIG_PPC_BOOK3E */
static void __meminit vmemmap_create_mapping(unsigned long start,
unsigned long page_size,
unsigned long phys)
{
int mapped = htab_bolt_mapping(start, start + page_size, phys,
PAGE_KERNEL, mmu_vmemmap_psize,
mmu_kernel_ssize);
BUG_ON(mapped < 0);
}
#endif /* CONFIG_PPC_BOOK3E */
struct vmemmap_backing *vmemmap_list;
static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node)
{
static struct vmemmap_backing *next;
static int num_left;
/* allocate a page when required and hand out chunks */
if (!next || !num_left) {
next = vmemmap_alloc_block(PAGE_SIZE, node);
if (unlikely(!next)) {
WARN_ON(1);
return NULL;
}
num_left = PAGE_SIZE / sizeof(struct vmemmap_backing);
}
num_left--;
return next++;
}
static __meminit void vmemmap_list_populate(unsigned long phys,
unsigned long start,
int node)
{
struct vmemmap_backing *vmem_back;
vmem_back = vmemmap_list_alloc(node);
if (unlikely(!vmem_back)) {
WARN_ON(1);
return;
}
vmem_back->phys = phys;
vmem_back->virt_addr = start;
vmem_back->list = vmemmap_list;
vmemmap_list = vmem_back;
}
int __meminit vmemmap_populate(struct page *start_page,
unsigned long nr_pages, int node)
{
unsigned long start = (unsigned long)start_page;
unsigned long end = (unsigned long)(start_page + nr_pages);
unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
/* Align to the page size of the linear mapping. */
start = _ALIGN_DOWN(start, page_size);
pr_debug("vmemmap_populate page %p, %ld pages, node %d\n",
start_page, nr_pages, node);
pr_debug(" -> map %lx..%lx\n", start, end);
for (; start < end; start += page_size) {
void *p;
if (vmemmap_populated(start, page_size))
continue;
p = vmemmap_alloc_block(page_size, node);
if (!p)
return -ENOMEM;
vmemmap_list_populate(__pa(p), start, node);
pr_debug(" * %016lx..%016lx allocated at %p\n",
start, start + page_size, p);
vmemmap_create_mapping(start, page_size, __pa(p));
}
return 0;
}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */