* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
-#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/errno.h>
-#include <linux/ptrace.h>
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
+#include <linux/highmem.h>
#include <asm/mach-types.h>
-#include <asm/hardware.h>
+#include <asm/sections.h>
#include <asm/setup.h>
+#include <asm/sizes.h>
#include <asm/tlb.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
-#define TABLE_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
+#include "mm.h"
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+static unsigned long phys_initrd_start __initdata = 0;
+static unsigned long phys_initrd_size __initdata = 0;
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern void _stext, _text, _etext, __data_start, _end, __init_begin, __init_end;
-extern unsigned long phys_initrd_start;
-extern unsigned long phys_initrd_size;
+static void __init early_initrd(char **p)
+{
+ unsigned long start, size;
-/*
- * The sole use of this is to pass memory configuration
- * data from paging_init to mem_init.
- */
-static struct meminfo meminfo __initdata = { 0, };
+ start = memparse(*p, p);
+ if (**p == ',') {
+ size = memparse((*p) + 1, p);
+
+ phys_initrd_start = start;
+ phys_initrd_size = size;
+ }
+}
+__early_param("initrd=", early_initrd);
+
+static int __init parse_tag_initrd(const struct tag *tag)
+{
+ printk(KERN_WARNING "ATAG_INITRD is deprecated; "
+ "please update your bootloader.\n");
+ phys_initrd_start = __virt_to_phys(tag->u.initrd.start);
+ phys_initrd_size = tag->u.initrd.size;
+ return 0;
+}
+
+__tagtable(ATAG_INITRD, parse_tag_initrd);
+
+static int __init parse_tag_initrd2(const struct tag *tag)
+{
+ phys_initrd_start = tag->u.initrd.start;
+ phys_initrd_size = tag->u.initrd.size;
+ return 0;
+}
+
+__tagtable(ATAG_INITRD2, parse_tag_initrd2);
/*
- * empty_zero_page is a special page that is used for
- * zero-initialized data and COW.
+ * This keeps memory configuration data used by a couple memory
+ * initialization functions, as well as show_mem() for the skipping
+ * of holes in the memory map. It is populated by arm_add_memory().
*/
-struct page *empty_zero_page;
+struct meminfo meminfo;
void show_mem(void)
{
int free = 0, total = 0, reserved = 0;
- int shared = 0, cached = 0, slab = 0, node;
+ int shared = 0, cached = 0, slab = 0, node, i;
+ struct meminfo * mi = &meminfo;
printk("Mem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
-
for_each_online_node(node) {
- struct page *page, *end;
-
- page = NODE_MEM_MAP(node);
- end = page + NODE_DATA(node)->node_spanned_pages;
-
- do {
- total++;
- if (PageReserved(page))
- reserved++;
- else if (PageSwapCache(page))
- cached++;
- else if (PageSlab(page))
- slab++;
- else if (!page_count(page))
- free++;
- else
- shared += page_count(page) - 1;
- page++;
- } while (page < end);
+ pg_data_t *n = NODE_DATA(node);
+ struct page *map = pgdat_page_nr(n, 0) - n->node_start_pfn;
+
+ for_each_nodebank (i,mi,node) {
+ struct membank *bank = &mi->bank[i];
+ unsigned int pfn1, pfn2;
+ struct page *page, *end;
+
+ pfn1 = bank_pfn_start(bank);
+ pfn2 = bank_pfn_end(bank);
+
+ page = map + pfn1;
+ end = map + pfn2;
+
+ do {
+ total++;
+ if (PageReserved(page))
+ reserved++;
+ else if (PageSwapCache(page))
+ cached++;
+ else if (PageSlab(page))
+ slab++;
+ else if (!page_count(page))
+ free++;
+ else
+ shared += page_count(page) - 1;
+ page++;
+ } while (page < end);
+ }
}
printk("%d pages of RAM\n", total);
printk("%d pages swap cached\n", cached);
}
-static inline pmd_t *pmd_off(pgd_t *pgd, unsigned long virt)
-{
- return pmd_offset(pgd, virt);
-}
-
-static inline pmd_t *pmd_off_k(unsigned long virt)
-{
- return pmd_off(pgd_offset_k(virt), virt);
-}
-
-#define for_each_nodebank(iter,mi,no) \
- for (iter = 0; iter < mi->nr_banks; iter++) \
- if (mi->bank[iter].node == no)
-
/*
* FIXME: We really want to avoid allocating the bootmap bitmap
* over the top of the initrd. Hopefully, this is located towards
static unsigned int __init
find_bootmap_pfn(int node, struct meminfo *mi, unsigned int bootmap_pages)
{
- unsigned int start_pfn, bank, bootmap_pfn;
+ unsigned int start_pfn, i, bootmap_pfn;
- start_pfn = PAGE_ALIGN(__pa(&_end)) >> PAGE_SHIFT;
+ start_pfn = PAGE_ALIGN(__pa(_end)) >> PAGE_SHIFT;
bootmap_pfn = 0;
- for_each_nodebank(bank, mi, node) {
+ for_each_nodebank(i, mi, node) {
+ struct membank *bank = &mi->bank[i];
unsigned int start, end;
- start = mi->bank[bank].start >> PAGE_SHIFT;
- end = (mi->bank[bank].size +
- mi->bank[bank].start) >> PAGE_SHIFT;
+ start = bank_pfn_start(bank);
+ end = bank_pfn_end(bank);
if (end < start_pfn)
continue;
initrd_node = -1;
for (i = 0; i < mi->nr_banks; i++) {
- unsigned long bank_end;
-
- bank_end = mi->bank[i].start + mi->bank[i].size;
-
- if (mi->bank[i].start <= phys_initrd_start &&
- end <= bank_end)
- initrd_node = mi->bank[i].node;
+ struct membank *bank = &mi->bank[i];
+ if (bank_phys_start(bank) <= phys_initrd_start &&
+ end <= bank_phys_end(bank))
+ initrd_node = bank->node;
}
}
if (initrd_node == -1) {
- printk(KERN_ERR "initrd (0x%08lx - 0x%08lx) extends beyond "
+ printk(KERN_ERR "INITRD: 0x%08lx+0x%08lx extends beyond "
"physical memory - disabling initrd\n",
- phys_initrd_start, end);
+ phys_initrd_start, phys_initrd_size);
phys_initrd_start = phys_initrd_size = 0;
}
#endif
return initrd_node;
}
-/*
- * Reserve the various regions of node 0
- */
-static __init void reserve_node_zero(pg_data_t *pgdat)
+static inline void map_memory_bank(struct membank *bank)
{
- unsigned long res_size = 0;
-
- /*
- * Register the kernel text and data with bootmem.
- * Note that this can only be in node 0.
- */
-#ifdef CONFIG_XIP_KERNEL
- reserve_bootmem_node(pgdat, __pa(&__data_start), &_end - &__data_start);
-#else
- reserve_bootmem_node(pgdat, __pa(&_stext), &_end - &_stext);
-#endif
-
- /*
- * Reserve the page tables. These are already in use,
- * and can only be in node 0.
- */
- reserve_bootmem_node(pgdat, __pa(swapper_pg_dir),
- PTRS_PER_PGD * sizeof(pgd_t));
-
- /*
- * Hmm... This should go elsewhere, but we really really need to
- * stop things allocating the low memory; ideally we need a better
- * implementation of GFP_DMA which does not assume that DMA-able
- * memory starts at zero.
- */
- if (machine_is_integrator() || machine_is_cintegrator())
- res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;
+#ifdef CONFIG_MMU
+ struct map_desc map;
- /*
- * These should likewise go elsewhere. They pre-reserve the
- * screen memory region at the start of main system memory.
- */
- if (machine_is_edb7211())
- res_size = 0x00020000;
- if (machine_is_p720t())
- res_size = 0x00014000;
+ map.pfn = bank_pfn_start(bank);
+ map.virtual = __phys_to_virt(bank_phys_start(bank));
+ map.length = bank_phys_size(bank);
+ map.type = MT_MEMORY;
-#ifdef CONFIG_SA1111
- /*
- * Because of the SA1111 DMA bug, we want to preserve our
- * precious DMA-able memory...
- */
- res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;
+ create_mapping(&map);
#endif
- if (res_size)
- reserve_bootmem_node(pgdat, PHYS_OFFSET, res_size);
}
-void __init build_mem_type_table(void);
-void __init create_mapping(struct map_desc *md);
-
-static unsigned long __init
-bootmem_init_node(int node, int initrd_node, struct meminfo *mi)
+static unsigned long __init bootmem_init_node(int node, struct meminfo *mi)
{
- unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
unsigned long start_pfn, end_pfn, boot_pfn;
unsigned int boot_pages;
pg_data_t *pgdat;
* Calculate the pfn range, and map the memory banks for this node.
*/
for_each_nodebank(i, mi, node) {
+ struct membank *bank = &mi->bank[i];
unsigned long start, end;
- struct map_desc map;
- start = mi->bank[i].start >> PAGE_SHIFT;
- end = (mi->bank[i].start + mi->bank[i].size) >> PAGE_SHIFT;
+ start = bank_pfn_start(bank);
+ end = bank_pfn_end(bank);
if (start_pfn > start)
start_pfn = start;
if (end_pfn < end)
end_pfn = end;
- map.pfn = __phys_to_pfn(mi->bank[i].start);
- map.virtual = __phys_to_virt(mi->bank[i].start);
- map.length = mi->bank[i].size;
- map.type = MT_MEMORY;
-
- create_mapping(&map);
+ map_memory_bank(bank);
}
/*
pgdat = NODE_DATA(node);
init_bootmem_node(pgdat, boot_pfn, start_pfn, end_pfn);
- for_each_nodebank(i, mi, node)
- free_bootmem_node(pgdat, mi->bank[i].start, mi->bank[i].size);
+ for_each_nodebank(i, mi, node) {
+ struct membank *bank = &mi->bank[i];
+ free_bootmem_node(pgdat, bank_phys_start(bank), bank_phys_size(bank));
+ memory_present(node, bank_pfn_start(bank), bank_pfn_end(bank));
+ }
/*
* Reserve the bootmem bitmap for this node.
*/
reserve_bootmem_node(pgdat, boot_pfn << PAGE_SHIFT,
- boot_pages << PAGE_SHIFT);
+ boot_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
+
+ return end_pfn;
+}
+static void __init bootmem_reserve_initrd(int node)
+{
#ifdef CONFIG_BLK_DEV_INITRD
- /*
- * If the initrd is in this node, reserve its memory.
- */
- if (node == initrd_node) {
- reserve_bootmem_node(pgdat, phys_initrd_start,
- phys_initrd_size);
+ pg_data_t *pgdat = NODE_DATA(node);
+ int res;
+
+ res = reserve_bootmem_node(pgdat, phys_initrd_start,
+ phys_initrd_size, BOOTMEM_EXCLUSIVE);
+
+ if (res == 0) {
initrd_start = __phys_to_virt(phys_initrd_start);
initrd_end = initrd_start + phys_initrd_size;
+ } else {
+ printk(KERN_ERR
+ "INITRD: 0x%08lx+0x%08lx overlaps in-use "
+ "memory region - disabling initrd\n",
+ phys_initrd_start, phys_initrd_size);
}
#endif
+}
- /*
- * Finally, reserve any node zero regions.
- */
- if (node == 0)
- reserve_node_zero(pgdat);
+static void __init bootmem_free_node(int node, struct meminfo *mi)
+{
+ unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
+ unsigned long start_pfn, end_pfn;
+ pg_data_t *pgdat = NODE_DATA(node);
+ int i;
+
+ start_pfn = pgdat->bdata->node_min_pfn;
+ end_pfn = pgdat->bdata->node_low_pfn;
/*
* initialise the zones within this node.
*/
zhole_size[0] = zone_size[0];
for_each_nodebank(i, mi, node)
- zhole_size[0] -= mi->bank[i].size >> PAGE_SHIFT;
+ zhole_size[0] -= bank_pfn_size(&mi->bank[i]);
/*
* Adjust the sizes according to any special requirements for
*/
arch_adjust_zones(node, zone_size, zhole_size);
- free_area_init_node(node, pgdat, zone_size, start_pfn, zhole_size);
-
- return end_pfn;
+ free_area_init_node(node, zone_size, start_pfn, zhole_size);
}
-static void __init bootmem_init(struct meminfo *mi)
+void __init bootmem_init(void)
{
- unsigned long addr, memend_pfn = 0;
- int node, initrd_node, i;
-
- /*
- * Invalidate the node number for empty or invalid memory banks
- */
- for (i = 0; i < mi->nr_banks; i++)
- if (mi->bank[i].size == 0 || mi->bank[i].node >= MAX_NUMNODES)
- mi->bank[i].node = -1;
-
- memcpy(&meminfo, mi, sizeof(meminfo));
-
- /*
- * Clear out all the mappings below the kernel image.
- */
- for (addr = 0; addr < MODULE_START; addr += PGDIR_SIZE)
- pmd_clear(pmd_off_k(addr));
-#ifdef CONFIG_XIP_KERNEL
- /* The XIP kernel is mapped in the module area -- skip over it */
- addr = ((unsigned long)&_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
-#endif
- for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
- pmd_clear(pmd_off_k(addr));
-
- /*
- * Clear out all the kernel space mappings, except for the first
- * memory bank, up to the end of the vmalloc region.
- */
- for (addr = __phys_to_virt(mi->bank[0].start + mi->bank[0].size);
- addr < VMALLOC_END; addr += PGDIR_SIZE)
- pmd_clear(pmd_off_k(addr));
+ struct meminfo *mi = &meminfo;
+ unsigned long memend_pfn = 0;
+ int node, initrd_node;
/*
* Locate which node contains the ramdisk image, if any.
* Run through each node initialising the bootmem allocator.
*/
for_each_node(node) {
- unsigned long end_pfn;
+ unsigned long end_pfn = bootmem_init_node(node, mi);
+
+ /*
+ * Reserve any special node zero regions.
+ */
+ if (node == 0)
+ reserve_node_zero(NODE_DATA(node));
- end_pfn = bootmem_init_node(node, initrd_node, mi);
+ /*
+ * If the initrd is in this node, reserve its memory.
+ */
+ if (node == initrd_node)
+ bootmem_reserve_initrd(node);
/*
* Remember the highest memory PFN.
memend_pfn = end_pfn;
}
- high_memory = __va(memend_pfn << PAGE_SHIFT);
+ /*
+ * sparse_init() needs the bootmem allocator up and running.
+ */
+ sparse_init();
+
+ /*
+ * Now free memory in each node - free_area_init_node needs
+ * the sparse mem_map arrays initialized by sparse_init()
+ * for memmap_init_zone(), otherwise all PFNs are invalid.
+ */
+ for_each_node(node)
+ bootmem_free_node(node, mi);
+
+ high_memory = __va((memend_pfn << PAGE_SHIFT) - 1) + 1;
/*
* This doesn't seem to be used by the Linux memory manager any
max_pfn = max_low_pfn = memend_pfn - PHYS_PFN_OFFSET;
}
-/*
- * Set up device the mappings. Since we clear out the page tables for all
- * mappings above VMALLOC_END, we will remove any debug device mappings.
- * This means you have to be careful how you debug this function, or any
- * called function. (Do it by code inspection!)
- */
-static void __init devicemaps_init(struct machine_desc *mdesc)
+static inline int free_area(unsigned long pfn, unsigned long end, char *s)
{
- struct map_desc map;
- unsigned long addr;
- void *vectors;
-
- for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
- pmd_clear(pmd_off_k(addr));
-
- /*
- * Map the kernel if it is XIP.
- * It is always first in the modulearea.
- */
-#ifdef CONFIG_XIP_KERNEL
- map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & PGDIR_MASK);
- map.virtual = MODULE_START;
- map.length = ((unsigned long)&_etext - map.virtual + ~PGDIR_MASK) & PGDIR_MASK;
- map.type = MT_ROM;
- create_mapping(&map);
-#endif
-
- /*
- * Map the cache flushing regions.
- */
-#ifdef FLUSH_BASE
- map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS);
- map.virtual = FLUSH_BASE;
- map.length = PGDIR_SIZE;
- map.type = MT_CACHECLEAN;
- create_mapping(&map);
-#endif
-#ifdef FLUSH_BASE_MINICACHE
- map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS + PGDIR_SIZE);
- map.virtual = FLUSH_BASE_MINICACHE;
- map.length = PGDIR_SIZE;
- map.type = MT_MINICLEAN;
- create_mapping(&map);
-#endif
-
- flush_cache_all();
- local_flush_tlb_all();
-
- vectors = alloc_bootmem_low_pages(PAGE_SIZE);
- BUG_ON(!vectors);
+ unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);
- /*
- * Create a mapping for the machine vectors at the high-vectors
- * location (0xffff0000). If we aren't using high-vectors, also
- * create a mapping at the low-vectors virtual address.
- */
- map.pfn = __phys_to_pfn(virt_to_phys(vectors));
- map.virtual = 0xffff0000;
- map.length = PAGE_SIZE;
- map.type = MT_HIGH_VECTORS;
- create_mapping(&map);
-
- if (!vectors_high()) {
- map.virtual = 0;
- map.type = MT_LOW_VECTORS;
- create_mapping(&map);
- }
-
- /*
- * Ask the machine support to map in the statically mapped devices.
- * After this point, we can start to touch devices again.
- */
- if (mdesc->map_io)
- mdesc->map_io();
-}
-
-/*
- * paging_init() sets up the page tables, initialises the zone memory
- * maps, and sets up the zero page, bad page and bad page tables.
- */
-void __init paging_init(struct meminfo *mi, struct machine_desc *mdesc)
-{
- void *zero_page;
-
- build_mem_type_table();
- bootmem_init(mi);
- devicemaps_init(mdesc);
-
- top_pmd = pmd_off_k(0xffff0000);
-
- /*
- * allocate the zero page. Note that we count on this going ok.
- */
- zero_page = alloc_bootmem_low_pages(PAGE_SIZE);
- memzero(zero_page, PAGE_SIZE);
- empty_zero_page = virt_to_page(zero_page);
- flush_dcache_page(empty_zero_page);
-}
-
-static inline void free_area(unsigned long addr, unsigned long end, char *s)
-{
- unsigned int size = (end - addr) >> 10;
-
- for (; addr < end; addr += PAGE_SIZE) {
- struct page *page = virt_to_page(addr);
+ for (; pfn < end; pfn++) {
+ struct page *page = pfn_to_page(pfn);
ClearPageReserved(page);
- set_page_count(page, 1);
- free_page(addr);
- totalram_pages++;
+ init_page_count(page);
+ __free_page(page);
+ pages++;
}
if (size && s)
printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
+
+ return pages;
}
static inline void
* information on the command line.
*/
for_each_nodebank(i, mi, node) {
- bank_start = mi->bank[i].start >> PAGE_SHIFT;
+ struct membank *bank = &mi->bank[i];
+
+ bank_start = bank_pfn_start(bank);
if (bank_start < prev_bank_end) {
printk(KERN_ERR "MEM: unordered memory banks. "
"Not freeing memmap.\n");
if (prev_bank_end && prev_bank_end != bank_start)
free_memmap(node, prev_bank_end, bank_start);
- prev_bank_end = (mi->bank[i].start +
- mi->bank[i].size) >> PAGE_SHIFT;
+ prev_bank_end = bank_pfn_end(bank);
}
}
*/
void __init mem_init(void)
{
- unsigned int codepages, datapages, initpages;
+ unsigned int codesize, datasize, initsize;
int i, node;
- codepages = &_etext - &_text;
- datapages = &_end - &__data_start;
- initpages = &__init_end - &__init_begin;
-
#ifndef CONFIG_DISCONTIGMEM
- max_mapnr = virt_to_page(high_memory) - mem_map;
+ max_mapnr = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
#endif
/* this will put all unused low memory onto the freelists */
#ifdef CONFIG_SA1111
/* now that our DMA memory is actually so designated, we can free it */
- free_area(PAGE_OFFSET, (unsigned long)swapper_pg_dir, NULL);
+ totalram_pages += free_area(PHYS_PFN_OFFSET,
+ __phys_to_pfn(__pa(swapper_pg_dir)), NULL);
+#endif
+
+#ifdef CONFIG_HIGHMEM
+ /* set highmem page free */
+ for_each_online_node(node) {
+ for_each_nodebank (i, &meminfo, node) {
+ unsigned long start = bank_pfn_start(&meminfo.bank[i]);
+ unsigned long end = bank_pfn_end(&meminfo.bank[i]);
+ if (start >= max_low_pfn + PHYS_PFN_OFFSET)
+ totalhigh_pages += free_area(start, end, NULL);
+ }
+ }
+ totalram_pages += totalhigh_pages;
#endif
/*
* real number of pages we have in this system
*/
printk(KERN_INFO "Memory:");
-
num_physpages = 0;
for (i = 0; i < meminfo.nr_banks; i++) {
- num_physpages += meminfo.bank[i].size >> PAGE_SHIFT;
- printk(" %ldMB", meminfo.bank[i].size >> 20);
+ num_physpages += bank_pfn_size(&meminfo.bank[i]);
+ printk(" %ldMB", bank_phys_size(&meminfo.bank[i]) >> 20);
}
-
printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT));
+
+ codesize = _etext - _text;
+ datasize = _end - _data;
+ initsize = __init_end - __init_begin;
+
printk(KERN_NOTICE "Memory: %luKB available (%dK code, "
- "%dK data, %dK init)\n",
+ "%dK data, %dK init, %luK highmem)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
- codepages >> 10, datapages >> 10, initpages >> 10);
+ codesize >> 10, datasize >> 10, initsize >> 10,
+ (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)));
if (PAGE_SIZE >= 16384 && num_physpages <= 128) {
extern int sysctl_overcommit_memory;
void free_initmem(void)
{
- if (!machine_is_integrator() && !machine_is_cintegrator()) {
- free_area((unsigned long)(&__init_begin),
- (unsigned long)(&__init_end),
- "init");
- }
+ if (!machine_is_integrator() && !machine_is_cintegrator())
+ totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
+ __phys_to_pfn(__pa(__init_end)),
+ "init");
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
if (!keep_initrd)
- free_area(start, end, "initrd");
+ totalram_pages += free_area(__phys_to_pfn(__pa(start)),
+ __phys_to_pfn(__pa(end)),
+ "initrd");
}
static int __init keepinitrd_setup(char *__unused)