* 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).
* PPC44x/36-bit changes by Matt Porter (mporter@mvista.com)
*
* Derived from "arch/i386/mm/init.c"
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
+#include <linux/gfp.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/highmem.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
+#include <linux/suspend.h>
+#include <linux/lmb.h>
+#include <linux/hugetlb.h>
#include <asm/pgalloc.h>
#include <asm/prom.h>
#include <asm/machdep.h>
#include <asm/btext.h>
#include <asm/tlb.h>
-#include <asm/prom.h>
-#include <asm/lmb.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"
int init_bootmem_done;
int mem_init_done;
-unsigned long memory_limit;
+phys_addr_t memory_limit;
-extern void hash_preload(struct mm_struct *mm, unsigned long ea,
- unsigned long access, unsigned long trap);
+#ifdef CONFIG_HIGHMEM
+pte_t *kmap_pte;
+pgprot_t kmap_prot;
-/*
- * 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)
+EXPORT_SYMBOL(kmap_prot);
+EXPORT_SYMBOL(kmap_pte);
+
+static inline pte_t *virt_to_kpte(unsigned long vaddr)
{
- unsigned long paddr = (pfn << PAGE_SHIFT);
+ 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 paddr < __pa(high_memory);
+ return pfn < max_pfn;
#else
+ unsigned long paddr = (pfn << PAGE_SHIFT);
int i;
for (i=0; i < lmb.memory.cnt; i++) {
unsigned long base;
return 0;
#endif
}
-EXPORT_SYMBOL(page_is_ram);
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);
if (!page_is_ram(pfn))
- vma_prot = __pgprot(pgprot_val(vma_prot)
- | _PAGE_GUARDED | _PAGE_NO_CACHE);
+ vma_prot = pgprot_noncached(vma_prot);
+
return vma_prot;
}
EXPORT_SYMBOL(phys_mem_access_prot);
#ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
- ClearPageReserved(page);
- init_page_count(page);
- __free_page(page);
- totalram_pages++;
- num_physpages++;
-}
-
#ifdef CONFIG_NUMA
int memory_add_physaddr_to_nid(u64 start)
{
}
#endif
-int __devinit arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdata;
struct zone *zone;
/* this should work for most non-highmem platforms */
zone = pgdata->node_zones;
- return __add_pages(zone, start_pfn, nr_pages);
-
- return 0;
+ return __add_pages(nid, zone, start_pfn, nr_pages);
}
+#endif /* CONFIG_MEMORY_HOTPLUG */
/*
- * First pass at this code will check to determine if the remove
- * request is within the RMO. Do not allow removal within the RMO.
+ * 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 lmb.memory structures. Walk through the
+ * memory regions, find holes and callback for contiguous regions.
*/
-int __devinit remove_memory(u64 start, u64 size)
-{
- struct zone *zone;
- unsigned long start_pfn, end_pfn, nr_pages;
-
- start_pfn = start >> PAGE_SHIFT;
- nr_pages = size >> PAGE_SHIFT;
- end_pfn = start_pfn + nr_pages;
-
- printk("%s(): Attempting to remove memoy in range "
- "%lx to %lx\n", __func__, start, start+size);
- /*
- * check for range within RMO
- */
- zone = page_zone(pfn_to_page(start_pfn));
-
- printk("%s(): memory will be removed from "
- "the %s zone\n", __func__, zone->name);
-
- /*
- * not handling removing memory ranges that
- * overlap multiple zones yet
- */
- if (end_pfn > (zone->zone_start_pfn + zone->spanned_pages))
- goto overlap;
-
- /* make sure it is NOT in RMO */
- if ((start < lmb.rmo_size) || ((start+size) < lmb.rmo_size)) {
- printk("%s(): range to be removed must NOT be in RMO!\n",
- __func__);
- goto in_rmo;
- }
-
- return __remove_pages(zone, start_pfn, nr_pages);
-
-overlap:
- printk("%s(): memory range to be removed overlaps "
- "multiple zones!!!\n", __func__);
-in_rmo:
- return -1;
-}
-#endif /* CONFIG_MEMORY_HOTPLUG */
-
-void show_mem(void)
+int
+walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
+ void *arg, int (*func)(unsigned long, unsigned long, void *))
{
- unsigned long total = 0, reserved = 0;
- unsigned long shared = 0, cached = 0;
- unsigned long highmem = 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_online_pgdat(pgdat) {
- unsigned long flags;
- pgdat_resize_lock(pgdat, &flags);
- for (i = 0; i < pgdat->node_spanned_pages; i++) {
- if (!pfn_valid(pgdat->node_start_pfn + i))
- continue;
- page = pgdat_page_nr(pgdat, i);
- total++;
- if (PageHighMem(page))
- highmem++;
- if (PageReserved(page))
- reserved++;
- else if (PageSwapCache(page))
- cached++;
- else if (page_count(page))
- shared += page_count(page) - 1;
- }
- pgdat_resize_unlock(pgdat, &flags);
+ struct lmb_property res;
+ unsigned long pfn, len;
+ u64 end;
+ int ret = -1;
+
+ res.base = (u64) start_pfn << PAGE_SHIFT;
+ res.size = (u64) nr_pages << PAGE_SHIFT;
+
+ end = res.base + res.size - 1;
+ while ((res.base < end) && (lmb_find(&res) >= 0)) {
+ pfn = (unsigned long)(res.base >> PAGE_SHIFT);
+ len = (unsigned long)(res.size >> PAGE_SHIFT);
+ ret = (*func)(pfn, len, arg);
+ if (ret)
+ break;
+ res.base += (res.size + 1);
+ res.size = (end - res.base + 1);
}
- printk("%ld pages of RAM\n", total);
-#ifdef CONFIG_HIGHMEM
- printk("%ld pages of HIGHMEM\n", highmem);
-#endif
- printk("%ld reserved pages\n", reserved);
- printk("%ld pages shared\n", shared);
- printk("%ld pages swap cached\n", cached);
+ return ret;
}
+EXPORT_SYMBOL_GPL(walk_system_ram_range);
/*
* Initialize the bootmem system and give it all the memory we
unsigned long total_pages;
int boot_mapsize;
- max_pfn = total_pages = lmb_end_of_DRAM() >> PAGE_SHIFT;
+ max_low_pfn = max_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
+ total_pages = (lmb_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
/*
start = lmb_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);
- boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages);
+ 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 (i = 0; i < lmb.memory.cnt; i++) {
* present.
*/
#ifdef CONFIG_HIGHMEM
- free_bootmem_with_active_regions(0, total_lowmem >> PAGE_SHIFT);
+ free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
+
+ /* reserve the sections we're already using */
+ for (i = 0; i < lmb.reserved.cnt; i++) {
+ unsigned long addr = lmb.reserved.region[i].base +
+ lmb_size_bytes(&lmb.reserved, i) - 1;
+ if (addr < lowmem_end_addr)
+ reserve_bootmem(lmb.reserved.region[i].base,
+ lmb_size_bytes(&lmb.reserved, i),
+ BOOTMEM_DEFAULT);
+ else if (lmb.reserved.region[i].base < lowmem_end_addr) {
+ unsigned long adjusted_size = lowmem_end_addr -
+ lmb.reserved.region[i].base;
+ reserve_bootmem(lmb.reserved.region[i].base,
+ adjusted_size, BOOTMEM_DEFAULT);
+ }
+ }
#else
free_bootmem_with_active_regions(0, max_pfn);
-#endif
/* 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));
+ lmb_size_bytes(&lmb.reserved, i),
+ 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)
+{
+ unsigned long lmb_next_region_start_pfn,
+ lmb_region_max_pfn;
+ int i;
+
+ for (i = 0; i < lmb.memory.cnt - 1; i++) {
+ lmb_region_max_pfn =
+ (lmb.memory.region[i].base >> PAGE_SHIFT) +
+ (lmb.memory.region[i].size >> PAGE_SHIFT);
+ lmb_next_region_start_pfn =
+ lmb.memory.region[i+1].base >> PAGE_SHIFT;
+
+ if (lmb_region_max_pfn < lmb_next_region_start_pfn)
+ register_nosave_region(lmb_region_max_pfn,
+ lmb_next_region_start_pfn);
+ }
+
+ 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 = lmb_phys_mem_size();
- unsigned long top_of_ram = lmb_end_of_DRAM();
+ phys_addr_t top_of_ram = lmb_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 = pte_offset_kernel(pmd_offset(pgd_offset_k
- (PKMAP_BASE), PKMAP_BASE), PKMAP_BASE);
- map_page(KMAP_FIX_BEGIN, 0, 0); /* XXX gross */
- kmap_pte = pte_offset_kernel(pmd_offset(pgd_offset_k
- (KMAP_FIX_BEGIN), KMAP_FIX_BEGIN), KMAP_FIX_BEGIN);
+ 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%lx, Total RAM: 0x%lx\n",
- top_of_ram, total_ram);
+ 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",
- (top_of_ram - total_ram) >> 20);
+ (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] = total_lowmem >> PAGE_SHIFT;
+ 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 */
struct page *page;
unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize;
+#ifdef CONFIG_SWIOTLB
+ if (ppc_swiotlb_enable)
+ swiotlb_init(1);
+#endif
+
num_physpages = lmb.memory.size >> PAGE_SHIFT;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
{
unsigned long pfn, highmem_mapnr;
- highmem_mapnr = total_lowmem >> PAGE_SHIFT;
+ highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT;
for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
struct page *page = pfn_to_page(pfn);
-
+ if (lmb_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",
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),
+ nr_free_pages() << (PAGE_SHIFT-10),
num_physpages << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
bsssize >> 10,
initsize >> 10);
- mem_init_done = 1;
+#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 */
- /* Initialize the vDSO */
- vdso_init();
+ mem_init_done = 1;
}
/*
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);
+ {
+ 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);
* This must always be called with the pte lock held.
*/
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
- pte_t pte)
+ pte_t *ptep)
{
#ifdef CONFIG_PPC_STD_MMU
unsigned long access = 0, trap;
-#endif
- unsigned long pfn = pte_pfn(pte);
-
- /* handle i-cache coherency */
- if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE) &&
- !cpu_has_feature(CPU_FTR_NOEXECUTE) &&
- pfn_valid(pfn)) {
- struct page *page = pfn_to_page(pfn);
- if (!PageReserved(page)
- && !test_bit(PG_arch_1, &page->flags)) {
- if (vma->vm_mm == current->active_mm) {
-#ifdef CONFIG_8xx
- /* On 8xx, cache control instructions (particularly
- * "dcbst" from flush_dcache_icache) fault as write
- * operation if there is an unpopulated TLB entry
- * for the address in question. To workaround that,
- * we invalidate the TLB here, thus avoiding dcbst
- * misbehaviour.
- */
- _tlbie(address);
-#endif
- __flush_dcache_icache((void *) address);
- } else
- flush_dcache_icache_page(page);
- set_bit(PG_arch_1, &page->flags);
- }
- }
-#ifdef CONFIG_PPC_STD_MMU
/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
- if (!pte_young(pte) || address >= TASK_SIZE)
+ if (!pte_young(*ptep) || address >= TASK_SIZE)
return;
/* We try to figure out if we are coming from an instruction