linux/arch/sh/mm/init.c

562 lines
13 KiB
C
Raw Normal View History

/*
* linux/arch/sh/mm/init.c
*
* Copyright (C) 1999 Niibe Yutaka
* Copyright (C) 2002 - 2011 Paul Mundt
*
* Based on linux/arch/i386/mm/init.c:
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/init.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/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pagemap.h>
#include <linux/percpu.h>
#include <linux/io.h>
#include <linux/memblock.h>
#include <linux/dma-mapping.h>
#include <linux/export.h>
#include <asm/mmu_context.h>
#include <asm/mmzone.h>
#include <asm/kexec.h>
#include <asm/tlb.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/cache.h>
#include <asm/sizes.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD];
void __init generic_mem_init(void)
{
memblock_add(__MEMORY_START, __MEMORY_SIZE);
}
void __init __weak plat_mem_setup(void)
{
/* Nothing to see here, move along. */
}
#ifdef CONFIG_MMU
static pte_t *__get_pte_phys(unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset_k(addr);
if (pgd_none(*pgd)) {
pgd_ERROR(*pgd);
return NULL;
}
pud = pud_alloc(NULL, pgd, addr);
if (unlikely(!pud)) {
pud_ERROR(*pud);
return NULL;
}
pmd = pmd_alloc(NULL, pud, addr);
if (unlikely(!pmd)) {
pmd_ERROR(*pmd);
return NULL;
}
return pte_offset_kernel(pmd, addr);
}
static void set_pte_phys(unsigned long addr, unsigned long phys, pgprot_t prot)
{
pte_t *pte;
pte = __get_pte_phys(addr);
if (!pte_none(*pte)) {
pte_ERROR(*pte);
return;
}
set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, prot));
local_flush_tlb_one(get_asid(), addr);
if (pgprot_val(prot) & _PAGE_WIRED)
tlb_wire_entry(NULL, addr, *pte);
}
static void clear_pte_phys(unsigned long addr, pgprot_t prot)
{
pte_t *pte;
pte = __get_pte_phys(addr);
if (pgprot_val(prot) & _PAGE_WIRED)
tlb_unwire_entry();
set_pte(pte, pfn_pte(0, __pgprot(0)));
local_flush_tlb_one(get_asid(), addr);
}
void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
{
unsigned long address = __fix_to_virt(idx);
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
}
set_pte_phys(address, phys, prot);
}
void __clear_fixmap(enum fixed_addresses idx, pgprot_t prot)
{
unsigned long address = __fix_to_virt(idx);
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
}
clear_pte_phys(address, prot);
}
static pmd_t * __init one_md_table_init(pud_t *pud)
{
if (pud_none(*pud)) {
pmd_t *pmd;
pmd = alloc_bootmem_pages(PAGE_SIZE);
pud_populate(&init_mm, pud, pmd);
BUG_ON(pmd != pmd_offset(pud, 0));
}
return pmd_offset(pud, 0);
}
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
if (pmd_none(*pmd)) {
pte_t *pte;
pte = alloc_bootmem_pages(PAGE_SIZE);
pmd_populate_kernel(&init_mm, pmd, pte);
BUG_ON(pte != pte_offset_kernel(pmd, 0));
}
return pte_offset_kernel(pmd, 0);
}
static pte_t * __init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
unsigned long vaddr, pte_t *lastpte)
{
return pte;
}
void __init page_table_range_init(unsigned long start, unsigned long end,
pgd_t *pgd_base)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte = NULL;
int i, j, k;
unsigned long vaddr;
vaddr = start;
i = __pgd_offset(vaddr);
j = __pud_offset(vaddr);
k = __pmd_offset(vaddr);
pgd = pgd_base + i;
for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
pud = (pud_t *)pgd;
for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) {
pmd = one_md_table_init(pud);
#ifndef __PAGETABLE_PMD_FOLDED
pmd += k;
#endif
for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) {
pte = page_table_kmap_check(one_page_table_init(pmd),
pmd, vaddr, pte);
vaddr += PMD_SIZE;
}
k = 0;
}
j = 0;
}
}
#endif /* CONFIG_MMU */
void __init allocate_pgdat(unsigned int nid)
{
unsigned long start_pfn, end_pfn;
#ifdef CONFIG_NEED_MULTIPLE_NODES
unsigned long phys;
#endif
get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
#ifdef CONFIG_NEED_MULTIPLE_NODES
phys = __memblock_alloc_base(sizeof(struct pglist_data),
SMP_CACHE_BYTES, end_pfn << PAGE_SHIFT);
/* Retry with all of system memory */
if (!phys)
phys = __memblock_alloc_base(sizeof(struct pglist_data),
SMP_CACHE_BYTES, memblock_end_of_DRAM());
if (!phys)
panic("Can't allocate pgdat for node %d\n", nid);
NODE_DATA(nid) = __va(phys);
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
#endif
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
}
static void __init bootmem_init_one_node(unsigned int nid)
{
unsigned long total_pages, paddr;
unsigned long end_pfn;
struct pglist_data *p;
p = NODE_DATA(nid);
/* Nothing to do.. */
if (!p->node_spanned_pages)
return;
end_pfn = p->node_start_pfn + p->node_spanned_pages;
total_pages = bootmem_bootmap_pages(p->node_spanned_pages);
paddr = memblock_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE);
if (!paddr)
panic("Can't allocate bootmap for nid[%d]\n", nid);
init_bootmem_node(p, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn);
free_bootmem_with_active_regions(nid, end_pfn);
/*
* XXX Handle initial reservations for the system memory node
* only for the moment, we'll refactor this later for handling
* reservations in other nodes.
*/
if (nid == 0) {
struct memblock_region *reg;
/* Reserve the sections we're already using. */
for_each_memblock(reserved, reg) {
reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
}
}
sparse_memory_present_with_active_regions(nid);
}
static void __init do_init_bootmem(void)
{
struct memblock_region *reg;
int i;
/* 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);
}
/* All of system RAM sits in node 0 for the non-NUMA case */
allocate_pgdat(0);
node_set_online(0);
plat_mem_setup();
for_each_online_node(i)
bootmem_init_one_node(i);
sparse_init();
}
static void __init early_reserve_mem(void)
{
unsigned long start_pfn;
u32 zero_base = (u32)__MEMORY_START + (u32)PHYSICAL_OFFSET;
u32 start = zero_base + (u32)CONFIG_ZERO_PAGE_OFFSET;
/*
* Partially used pages are not usable - thus
* we are rounding upwards:
*/
start_pfn = PFN_UP(__pa(_end));
/*
* Reserve the kernel text and Reserve the bootmem bitmap. We do
* this in two steps (first step was init_bootmem()), because
* this catches the (definitely buggy) case of us accidentally
* initializing the bootmem allocator with an invalid RAM area.
*/
memblock_reserve(start, (PFN_PHYS(start_pfn) + PAGE_SIZE - 1) - start);
/*
* Reserve physical pages below CONFIG_ZERO_PAGE_OFFSET.
*/
if (CONFIG_ZERO_PAGE_OFFSET != 0)
memblock_reserve(zero_base, CONFIG_ZERO_PAGE_OFFSET);
/*
* Handle additional early reservations
*/
check_for_initrd();
reserve_crashkernel();
}
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
unsigned long vaddr, end;
int nid;
sh_mv.mv_mem_init();
early_reserve_mem();
/*
* Once the early reservations are out of the way, give the
* platforms a chance to kick out some memory.
*/
if (sh_mv.mv_mem_reserve)
sh_mv.mv_mem_reserve();
memblock_enforce_memory_limit(memory_limit);
memblock: s/memblock_analyze()/memblock_allow_resize()/ and update users The only function of memblock_analyze() is now allowing resize of memblock region arrays. Rename it to memblock_allow_resize() and update its users. * The following users remain the same other than renaming. arm/mm/init.c::arm_memblock_init() microblaze/kernel/prom.c::early_init_devtree() powerpc/kernel/prom.c::early_init_devtree() openrisc/kernel/prom.c::early_init_devtree() sh/mm/init.c::paging_init() sparc/mm/init_64.c::paging_init() unicore32/mm/init.c::uc32_memblock_init() * In the following users, analyze was used to update total size which is no longer necessary. powerpc/kernel/machine_kexec.c::reserve_crashkernel() powerpc/kernel/prom.c::early_init_devtree() powerpc/mm/init_32.c::MMU_init() powerpc/mm/tlb_nohash.c::__early_init_mmu() powerpc/platforms/ps3/mm.c::ps3_mm_add_memory() powerpc/platforms/embedded6xx/wii.c::wii_memory_fixups() sh/kernel/machine_kexec.c::reserve_crashkernel() * x86/kernel/e820.c::memblock_x86_fill() was directly setting memblock_can_resize before populating memblock and calling analyze afterwards. Call memblock_allow_resize() before start populating. memblock_can_resize is now static inside memblock.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: "H. Peter Anvin" <hpa@zytor.com>
2011-12-08 18:22:08 +00:00
memblock_allow_resize();
memblock_dump_all();
/*
* Determine low and high memory ranges:
*/
max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
min_low_pfn = __MEMORY_START >> PAGE_SHIFT;
nodes_clear(node_online_map);
memory_start = (unsigned long)__va(__MEMORY_START);
memory_end = memory_start + (memory_limit ?: memblock_phys_mem_size());
uncached_init();
pmb_init();
do_init_bootmem();
ioremap_fixed_init();
/* We don't need to map the kernel through the TLB, as
* it is permanatly mapped using P1. So clear the
* entire pgd. */
memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir));
/* Set an initial value for the MMU.TTB so we don't have to
* check for a null value. */
set_TTB(swapper_pg_dir);
/*
* Populate the relevant portions of swapper_pg_dir so that
* we can use the fixmap entries without calling kmalloc.
* pte's will be filled in by __set_fixmap().
*/
vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
page_table_range_init(vaddr, end, swapper_pg_dir);
kmap_coherent_init();
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long low, start_pfn;
start_pfn = pgdat->bdata->node_min_pfn;
low = pgdat->bdata->node_low_pfn;
if (max_zone_pfns[ZONE_NORMAL] < low)
max_zone_pfns[ZONE_NORMAL] = low;
printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n",
nid, start_pfn, low);
}
free_area_init_nodes(max_zone_pfns);
}
/*
* Early initialization for any I/O MMUs we might have.
*/
static void __init iommu_init(void)
{
no_iommu_init();
}
unsigned int mem_init_done = 0;
void __init mem_init(void)
{
int codesize, datasize, initsize;
int nid;
iommu_init();
num_physpages = 0;
high_memory = NULL;
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long node_pages = 0;
void *node_high_memory;
num_physpages += pgdat->node_present_pages;
if (pgdat->node_spanned_pages)
node_pages = free_all_bootmem_node(pgdat);
totalram_pages += node_pages;
node_high_memory = (void *)__va((pgdat->node_start_pfn +
pgdat->node_spanned_pages) <<
PAGE_SHIFT);
if (node_high_memory > high_memory)
high_memory = node_high_memory;
}
/* Set this up early, so we can take care of the zero page */
cpu_cache_init();
/* clear the zero-page */
memset(empty_zero_page, 0, PAGE_SIZE);
__flush_wback_region(empty_zero_page, PAGE_SIZE);
vsyscall_init();
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, "
"%dk data, %dk init)\n",
nr_free_pages() << (PAGE_SHIFT-10),
num_physpages << (PAGE_SHIFT-10),
codesize >> 10,
datasize >> 10,
initsize >> 10);
printk(KERN_INFO "virtual kernel memory layout:\n"
" fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
" pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#endif
" vmalloc : 0x%08lx - 0x%08lx (%4ld MB)\n"
" lowmem : 0x%08lx - 0x%08lx (%4ld MB) (cached)\n"
#ifdef CONFIG_UNCACHED_MAPPING
" : 0x%08lx - 0x%08lx (%4ld MB) (uncached)\n"
#endif
" .init : 0x%08lx - 0x%08lx (%4ld kB)\n"
" .data : 0x%08lx - 0x%08lx (%4ld kB)\n"
" .text : 0x%08lx - 0x%08lx (%4ld kB)\n",
FIXADDR_START, FIXADDR_TOP,
(FIXADDR_TOP - FIXADDR_START) >> 10,
#ifdef CONFIG_HIGHMEM
PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
(LAST_PKMAP*PAGE_SIZE) >> 10,
#endif
(unsigned long)VMALLOC_START, VMALLOC_END,
(VMALLOC_END - VMALLOC_START) >> 20,
(unsigned long)memory_start, (unsigned long)high_memory,
((unsigned long)high_memory - (unsigned long)memory_start) >> 20,
#ifdef CONFIG_UNCACHED_MAPPING
uncached_start, uncached_end, uncached_size >> 20,
#endif
(unsigned long)&__init_begin, (unsigned long)&__init_end,
((unsigned long)&__init_end -
(unsigned long)&__init_begin) >> 10,
(unsigned long)&_etext, (unsigned long)&_edata,
((unsigned long)&_edata - (unsigned long)&_etext) >> 10,
(unsigned long)&_text, (unsigned long)&_etext,
((unsigned long)&_etext - (unsigned long)&_text) >> 10);
mem_init_done = 1;
}
void free_initmem(void)
{
unsigned long addr;
addr = (unsigned long)(&__init_begin);
for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
free_page(addr);
totalram_pages++;
}
printk("Freeing unused kernel memory: %ldk 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)
{
unsigned long p;
for (p = start; p < end; p += PAGE_SIZE) {
ClearPageReserved(virt_to_page(p));
init_page_count(virt_to_page(p));
free_page(p);
totalram_pages++;
}
printk("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
}
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
int arch_add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat;
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
pgdat = NODE_DATA(nid);
/* We only have ZONE_NORMAL, so this is easy.. */
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
ret = __add_pages(nid, pgdat->node_zones + ZONE_NORMAL,
start_pfn, nr_pages);
if (unlikely(ret))
printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);
#ifdef CONFIG_NUMA
int memory_add_physaddr_to_nid(u64 addr)
{
/* Node 0 for now.. */
return 0;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif
#endif /* CONFIG_MEMORY_HOTPLUG */