linux/arch/powerpc/mm/mem.c

504 lines
14 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
* PPC44x/36-bit changes by Matt Porter (mporter@mvista.com)
*
* Derived from "arch/i386/mm/init.c"
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* 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/module.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.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/gfp.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
#include <linux/suspend.h>
#include <linux/memblock.h>
#include <linux/hugetlb.h>
#include <asm/pgalloc.h>
#include <asm/prom.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/smp.h>
#include <asm/machdep.h>
#include <asm/btext.h>
#include <asm/tlb.h>
#include <asm/sections.h>
#include <asm/sparsemem.h>
#include <asm/vdso.h>
#include <asm/fixmap.h>
#include <asm/swiotlb.h>
#include "mmu_decl.h"
#ifndef CPU_FTR_COHERENT_ICACHE
#define CPU_FTR_COHERENT_ICACHE 0 /* XXX for now */
#define CPU_FTR_NOEXECUTE 0
#endif
int init_bootmem_done;
int mem_init_done;
phys_addr_t memory_limit;
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
EXPORT_SYMBOL(kmap_prot);
EXPORT_SYMBOL(kmap_pte);
static inline pte_t *virt_to_kpte(unsigned long vaddr)
{
return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
vaddr), vaddr), vaddr);
}
#endif
int page_is_ram(unsigned long pfn)
{
#ifndef CONFIG_PPC64 /* XXX for now */
return pfn < max_pfn;
#else
unsigned long paddr = (pfn << PAGE_SHIFT);
struct memblock_region *reg;
for_each_memblock(memory, reg)
if (paddr >= reg->base && paddr < (reg->base + reg->size))
return 1;
return 0;
#endif
}
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
if (ppc_md.phys_mem_access_prot)
return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);
if (!page_is_ram(pfn))
vma_prot = pgprot_noncached(vma_prot);
return vma_prot;
}
EXPORT_SYMBOL(phys_mem_access_prot);
2005-10-31 02:37:12 +00:00
#ifdef CONFIG_MEMORY_HOTPLUG
#ifdef CONFIG_NUMA
int memory_add_physaddr_to_nid(u64 start)
{
return hot_add_scn_to_nid(start);
}
#endif
int arch_add_memory(int nid, u64 start, u64 size)
2005-10-31 02:37:12 +00:00
{
struct pglist_data *pgdata;
2005-10-31 02:37:12 +00:00
struct zone *zone;
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
pgdata = NODE_DATA(nid);
start = (unsigned long)__va(start);
create_section_mapping(start, start + size);
2005-10-31 02:37:12 +00:00
/* this should work for most non-highmem platforms */
zone = pgdata->node_zones;
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:14 +00:00
return __add_pages(nid, zone, start_pfn, nr_pages);
2005-10-31 02:37:12 +00:00
}
#endif /* CONFIG_MEMORY_HOTPLUG */
/*
* walk_memory_resource() needs to make sure there is no holes in a given
* memory range. PPC64 does not maintain the memory layout in /proc/iomem.
* Instead it maintains it in memblock.memory structures. Walk through the
* memory regions, find holes and callback for contiguous regions.
*/
int
walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg, int (*func)(unsigned long, unsigned long, void *))
{
struct memblock_region *reg;
unsigned long end_pfn = start_pfn + nr_pages;
unsigned long tstart, tend;
int ret = -1;
for_each_memblock(memory, reg) {
tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
if (tstart >= tend)
continue;
ret = (*func)(tstart, tend - tstart, arg);
if (ret)
break;
}
return ret;
}
EXPORT_SYMBOL_GPL(walk_system_ram_range);
/*
* Initialize the bootmem system and give it all the memory we
* have available. If we are using highmem, we only put the
* lowmem into the bootmem system.
*/
#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init do_init_bootmem(void)
{
unsigned long start, bootmap_pages;
unsigned long total_pages;
struct memblock_region *reg;
int boot_mapsize;
max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
total_pages = (memblock_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT;
#ifdef CONFIG_HIGHMEM
total_pages = total_lowmem >> PAGE_SHIFT;
max_low_pfn = lowmem_end_addr >> PAGE_SHIFT;
#endif
/*
* 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 = memblock_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);
[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
min_low_pfn = MEMORY_START >> PAGE_SHIFT;
boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
/* Add active regions with valid PFNs */
for_each_memblock(memory, reg) {
unsigned long start_pfn, end_pfn;
start_pfn = memblock_region_memory_base_pfn(reg);
end_pfn = memblock_region_memory_end_pfn(reg);
add_active_range(0, start_pfn, end_pfn);
}
/* Add all physical memory to the bootmem map, mark each area
* present.
*/
#ifdef CONFIG_HIGHMEM
free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
/* reserve the sections we're already using */
for_each_memblock(reserved, reg) {
unsigned long top = reg->base + reg->size - 1;
if (top < lowmem_end_addr)
reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
else if (reg->base < lowmem_end_addr) {
unsigned long trunc_size = lowmem_end_addr - reg->base;
reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
}
}
#else
free_bootmem_with_active_regions(0, max_pfn);
/* reserve the sections we're already using */
for_each_memblock(reserved, reg)
reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
#endif
/* XXX need to clip this if using highmem? */
sparse_memory_present_with_active_regions(0);
init_bootmem_done = 1;
}
/* mark pages that don't exist as nosave */
static int __init mark_nonram_nosave(void)
{
struct memblock_region *reg, *prev = NULL;
for_each_memblock(memory, reg) {
if (prev &&
memblock_region_memory_end_pfn(prev) < memblock_region_memory_base_pfn(reg))
register_nosave_region(memblock_region_memory_end_pfn(prev),
memblock_region_memory_base_pfn(reg));
prev = reg;
}
return 0;
}
/*
* paging_init() sets up the page tables - in fact we've already done this.
*/
void __init paging_init(void)
{
unsigned long total_ram = memblock_phys_mem_size();
phys_addr_t top_of_ram = memblock_end_of_DRAM();
unsigned long max_zone_pfns[MAX_NR_ZONES];
#ifdef CONFIG_PPC32
unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1);
unsigned long end = __fix_to_virt(FIX_HOLE);
for (; v < end; v += PAGE_SIZE)
map_page(v, 0, 0); /* XXX gross */
#endif
#ifdef CONFIG_HIGHMEM
map_page(PKMAP_BASE, 0, 0); /* XXX gross */
pkmap_page_table = virt_to_kpte(PKMAP_BASE);
kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
kmap_prot = PAGE_KERNEL;
#endif /* CONFIG_HIGHMEM */
printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%lx\n",
(unsigned long long)top_of_ram, total_ram);
printk(KERN_DEBUG "Memory hole size: %ldMB\n",
(long int)((top_of_ram - total_ram) >> 20));
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
#ifdef CONFIG_HIGHMEM
max_zone_pfns[ZONE_DMA] = lowmem_end_addr >> PAGE_SHIFT;
max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT;
#else
max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
#endif
free_area_init_nodes(max_zone_pfns);
mark_nonram_nosave();
}
#endif /* ! CONFIG_NEED_MULTIPLE_NODES */
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;
#ifdef CONFIG_SWIOTLB
if (ppc_swiotlb_enable)
swiotlb_init(1);
#endif
num_physpages = memblock_phys_mem_size() >> PAGE_SHIFT;
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 %d\n", nid);
totalram_pages +=
free_all_bootmem_node(NODE_DATA(nid));
}
}
#else
max_mapnr = max_pfn;
totalram_pages += free_all_bootmem();
#endif
for_each_online_pgdat(pgdat) {
for (i = 0; i < pgdat->node_spanned_pages; i++) {
if (!pfn_valid(pgdat->node_start_pfn + i))
continue;
page = pgdat_page_nr(pgdat, i);
if (PageReserved(page))
reservedpages++;
}
}
codesize = (unsigned long)&_sdata - (unsigned long)&_stext;
datasize = (unsigned long)&_edata - (unsigned long)&_sdata;
initsize = (unsigned long)&__init_end - (unsigned long)&__init_begin;
bsssize = (unsigned long)&__bss_stop - (unsigned long)&__bss_start;
#ifdef CONFIG_HIGHMEM
{
unsigned long pfn, highmem_mapnr;
highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT;
for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
struct page *page = pfn_to_page(pfn);
if (memblock_is_reserved(pfn << PAGE_SHIFT))
continue;
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
totalhigh_pages++;
reservedpages--;
}
totalram_pages += totalhigh_pages;
printk(KERN_DEBUG "High memory: %luk\n",
totalhigh_pages << (PAGE_SHIFT-10));
}
#endif /* CONFIG_HIGHMEM */
printk(KERN_INFO "Memory: %luk/%luk available (%luk kernel code, "
"%luk reserved, %luk data, %luk bss, %luk init)\n",
nr_free_pages() << (PAGE_SHIFT-10),
num_physpages << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
bsssize >> 10,
initsize >> 10);
#ifdef CONFIG_PPC32
pr_info("Kernel virtual memory layout:\n");
pr_info(" * 0x%08lx..0x%08lx : fixmap\n", FIXADDR_START, FIXADDR_TOP);
#ifdef CONFIG_HIGHMEM
pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n",
PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
#endif /* CONFIG_HIGHMEM */
#ifdef CONFIG_NOT_COHERENT_CACHE
pr_info(" * 0x%08lx..0x%08lx : consistent mem\n",
IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
#endif /* CONFIG_NOT_COHERENT_CACHE */
pr_info(" * 0x%08lx..0x%08lx : early ioremap\n",
ioremap_bot, IOREMAP_TOP);
pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n",
VMALLOC_START, VMALLOC_END);
#endif /* CONFIG_PPC32 */
mem_init_done = 1;
}
/*
* 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 flush_dcache_icache_page(struct page *page)
{
#ifdef CONFIG_HUGETLB_PAGE
if (PageCompound(page)) {
flush_dcache_icache_hugepage(page);
return;
}
#endif
#ifdef CONFIG_BOOKE
{
void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE);
__flush_dcache_icache(start);
kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
}
#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
__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
#endif
}
void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
{
clear_page(page);
/*
* We shouldnt have to do this, but some versions of glibc
* require it (ld.so assumes zero filled pages are icache clean)
* - Anton
*/
flush_dcache_page(pg);
}
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
flush_dcache_page(pg);
}
void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
unsigned long addr, int len)
{
unsigned long maddr;
maddr = (unsigned long) kmap(page) + (addr & ~PAGE_MASK);
flush_icache_range(maddr, maddr + len);
kunmap(page);
}
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 pte lock held.
*/
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
#ifdef CONFIG_PPC_STD_MMU
unsigned long access = 0, trap;
/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
if (!pte_young(*ptep) || address >= TASK_SIZE)
return;
/* We try to figure out if we are coming from an instruction
* access fault and pass that down to __hash_page so we avoid
* double-faulting on execution of fresh text. We have to test
* for regs NULL since init will get here first thing at boot
*
* We also avoid filling the hash if not coming from a fault
*/
if (current->thread.regs == NULL)
return;
trap = TRAP(current->thread.regs);
if (trap == 0x400)
access |= _PAGE_EXEC;
else if (trap != 0x300)
return;
hash_preload(vma->vm_mm, address, access, trap);
#endif /* CONFIG_PPC_STD_MMU */
}