* Copyright (C) 1998-2003 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
*/
-#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/swap.h>
#include <linux/proc_fs.h>
#include <linux/bitops.h>
+#include <linux/kexec.h>
-#include <asm/a.out.h>
#include <asm/dma.h>
#include <asm/ia32.h>
#include <asm/io.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/mca.h>
+#include <asm/paravirt.h>
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;
#ifdef CONFIG_VIRTUAL_MEM_MAP
-unsigned long vmalloc_end = VMALLOC_END_INIT;
-EXPORT_SYMBOL(vmalloc_end);
+unsigned long VMALLOC_END = VMALLOC_END_INIT;
+EXPORT_SYMBOL(VMALLOC_END);
struct page *vmem_map;
EXPORT_SYMBOL(vmem_map);
#endif
-static int pgt_cache_water[2] = { 25, 50 };
-
-struct page *zero_page_memmap_ptr; /* map entry for zero page */
+struct page *zero_page_memmap_ptr; /* map entry for zero page */
EXPORT_SYMBOL(zero_page_memmap_ptr);
void
-check_pgt_cache (void)
-{
- int low, high;
-
- low = pgt_cache_water[0];
- high = pgt_cache_water[1];
-
- preempt_disable();
- if (pgtable_cache_size > (u64) high) {
- do {
- if (pgd_quicklist)
- free_page((unsigned long)pgd_alloc_one_fast(NULL));
- if (pmd_quicklist)
- free_page((unsigned long)pmd_alloc_one_fast(NULL, 0));
- } while (pgtable_cache_size > (u64) low);
- }
- preempt_enable();
-}
-
-void
-lazy_mmu_prot_update (pte_t pte)
+__ia64_sync_icache_dcache (pte_t pte)
{
unsigned long addr;
struct page *page;
- if (!pte_exec(pte))
- return; /* not an executable page... */
-
page = pte_page(pte);
addr = (unsigned long) page_address(page);
if (test_bit(PG_arch_1, &page->flags))
return; /* i-cache is already coherent with d-cache */
- flush_icache_range(addr, addr + PAGE_SIZE);
+ flush_icache_range(addr, addr + (PAGE_SIZE << compound_order(page)));
set_bit(PG_arch_1, &page->flags); /* mark page as clean */
}
+/*
+ * Since DMA is i-cache coherent, any (complete) pages that were written via
+ * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
+ * flush them when they get mapped into an executable vm-area.
+ */
+void
+dma_mark_clean(void *addr, size_t size)
+{
+ unsigned long pg_addr, end;
+
+ pg_addr = PAGE_ALIGN((unsigned long) addr);
+ end = (unsigned long) addr + size;
+ while (pg_addr + PAGE_SIZE <= end) {
+ struct page *page = virt_to_page(pg_addr);
+ set_bit(PG_arch_1, &page->flags);
+ pg_addr += PAGE_SIZE;
+ }
+}
+
inline void
ia64_set_rbs_bot (void)
{
- unsigned long stack_size = current->signal->rlim[RLIMIT_STACK].rlim_max & -16;
+ unsigned long stack_size = rlimit_max(RLIMIT_STACK) & -16;
if (stack_size > MAX_USER_STACK_SIZE)
stack_size = MAX_USER_STACK_SIZE;
- current->thread.rbs_bot = STACK_TOP - stack_size;
+ current->thread.rbs_bot = PAGE_ALIGN(current->mm->start_stack - stack_size);
}
/*
* the problem. When the process attempts to write to the register backing store
* for the first time, it will get a SEGFAULT in this case.
*/
- vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (vma) {
- memset(vma, 0, sizeof(*vma));
vma->vm_mm = current->mm;
vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
vma->vm_end = vma->vm_start + PAGE_SIZE;
- vma->vm_page_prot = protection_map[VM_DATA_DEFAULT_FLAGS & 0x7];
- vma->vm_flags = VM_DATA_DEFAULT_FLAGS | VM_GROWSUP;
+ vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
+ vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
down_write(¤t->mm->mmap_sem);
if (insert_vm_struct(current->mm, vma)) {
up_write(¤t->mm->mmap_sem);
/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
if (!(current->personality & MMAP_PAGE_ZERO)) {
- vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (vma) {
- memset(vma, 0, sizeof(*vma));
vma->vm_mm = current->mm;
vma->vm_end = PAGE_SIZE;
vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
eaddr = (unsigned long) ia64_imva(__init_end);
while (addr < eaddr) {
ClearPageReserved(virt_to_page(addr));
- set_page_count(virt_to_page(addr), 1);
+ init_page_count(virt_to_page(addr));
free_page(addr);
++totalram_pages;
addr += PAGE_SIZE;
(__init_end - __init_begin) >> 10);
}
-void
+void __init
free_initrd_mem (unsigned long start, unsigned long end)
{
struct page *page;
continue;
page = virt_to_page(start);
ClearPageReserved(page);
- set_page_count(page, 1);
+ init_page_count(page);
free_page(start);
++totalram_pages;
}
/*
* This installs a clean page in the kernel's page table.
*/
-struct page *
+static struct page * __init
put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
{
pgd_t *pgd;
pgd = pgd_offset_k(address); /* note: this is NOT pgd_offset()! */
- spin_lock(&init_mm.page_table_lock);
{
pud = pud_alloc(&init_mm, pgd, address);
if (!pud)
goto out;
-
pmd = pmd_alloc(&init_mm, pud, address);
if (!pmd)
goto out;
- pte = pte_alloc_map(&init_mm, pmd, address);
+ pte = pte_alloc_kernel(pmd, address);
if (!pte)
goto out;
- if (!pte_none(*pte)) {
- pte_unmap(pte);
+ if (!pte_none(*pte))
goto out;
- }
set_pte(pte, mk_pte(page, pgprot));
- pte_unmap(pte);
}
- out: spin_unlock(&init_mm.page_table_lock);
+ out:
/* no need for flush_tlb */
return page;
}
-static void
+static void __init
setup_gate (void)
{
+ void *gate_section;
struct page *page;
/*
- * Map the gate page twice: once read-only to export the ELF headers etc. and once
- * execute-only page to enable privilege-promotion via "epc":
+ * Map the gate page twice: once read-only to export the ELF
+ * headers etc. and once execute-only page to enable
+ * privilege-promotion via "epc":
*/
- page = virt_to_page(ia64_imva(__start_gate_section));
+ gate_section = paravirt_get_gate_section();
+ page = virt_to_page(ia64_imva(gate_section));
put_kernel_page(page, GATE_ADDR, PAGE_READONLY);
#ifdef HAVE_BUGGY_SEGREL
- page = virt_to_page(ia64_imva(__start_gate_section + PAGE_SIZE));
+ page = virt_to_page(ia64_imva(gate_section + PAGE_SIZE));
put_kernel_page(page, GATE_ADDR + PAGE_SIZE, PAGE_GATE);
#else
put_kernel_page(page, GATE_ADDR + PERCPU_PAGE_SIZE, PAGE_GATE);
+ /* Fill in the holes (if any) with read-only zero pages: */
+ {
+ unsigned long addr;
+
+ for (addr = GATE_ADDR + PAGE_SIZE;
+ addr < GATE_ADDR + PERCPU_PAGE_SIZE;
+ addr += PAGE_SIZE)
+ {
+ put_kernel_page(ZERO_PAGE(0), addr,
+ PAGE_READONLY);
+ put_kernel_page(ZERO_PAGE(0), addr + PERCPU_PAGE_SIZE,
+ PAGE_READONLY);
+ }
+ }
#endif
ia64_patch_gate();
}
void __devinit
ia64_mmu_init (void *my_cpu_data)
{
- unsigned long psr, pta, impl_va_bits;
+ unsigned long pta, impl_va_bits;
extern void __devinit tlb_init (void);
#ifdef CONFIG_DISABLE_VHPT
# define VHPT_ENABLE_BIT 1
#endif
- /* Pin mapping for percpu area into TLB */
- psr = ia64_clear_ic();
- ia64_itr(0x2, IA64_TR_PERCPU_DATA, PERCPU_ADDR,
- pte_val(pfn_pte(__pa(my_cpu_data) >> PAGE_SHIFT, PAGE_KERNEL)),
- PERCPU_PAGE_SHIFT);
-
- ia64_set_psr(psr);
- ia64_srlz_i();
-
/*
* Check if the virtually mapped linear page table (VMLPT) overlaps with a mapped
* address space. The IA-64 architecture guarantees that at least 50 bits of
if (impl_va_bits < 51 || impl_va_bits > 61)
panic("CPU has bogus IMPL_VA_MSB value of %lu!\n", impl_va_bits - 1);
+ /*
+ * mapped_space_bits - PAGE_SHIFT is the total number of ptes we need,
+ * which must fit into "vmlpt_bits - pte_bits" slots. Second half of
+ * the test makes sure that our mapped space doesn't overlap the
+ * unimplemented hole in the middle of the region.
+ */
+ if ((mapped_space_bits - PAGE_SHIFT > vmlpt_bits - pte_bits) ||
+ (mapped_space_bits > impl_va_bits - 1))
+ panic("Cannot build a big enough virtual-linear page table"
+ " to cover mapped address space.\n"
+ " Try using a smaller page size.\n");
+
/* place the VMLPT at the end of each page-table mapped region: */
pta = POW2(61) - POW2(vmlpt_bits);
- if (POW2(mapped_space_bits) >= pta)
- panic("mm/init: overlap between virtually mapped linear page table and "
- "mapped kernel space!");
/*
* Set the (virtually mapped linear) page table address. Bit
* 8 selects between the short and long format, bits 2-7 the
}
#ifdef CONFIG_VIRTUAL_MEM_MAP
+int vmemmap_find_next_valid_pfn(int node, int i)
+{
+ unsigned long end_address, hole_next_pfn;
+ unsigned long stop_address;
+ pg_data_t *pgdat = NODE_DATA(node);
-int
-create_mem_map_page_table (u64 start, u64 end, void *arg)
+ end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
+ end_address = PAGE_ALIGN(end_address);
+
+ stop_address = (unsigned long) &vmem_map[
+ pgdat->node_start_pfn + pgdat->node_spanned_pages];
+
+ do {
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_offset_k(end_address);
+ if (pgd_none(*pgd)) {
+ end_address += PGDIR_SIZE;
+ continue;
+ }
+
+ pud = pud_offset(pgd, end_address);
+ if (pud_none(*pud)) {
+ end_address += PUD_SIZE;
+ continue;
+ }
+
+ pmd = pmd_offset(pud, end_address);
+ if (pmd_none(*pmd)) {
+ end_address += PMD_SIZE;
+ continue;
+ }
+
+ pte = pte_offset_kernel(pmd, end_address);
+retry_pte:
+ if (pte_none(*pte)) {
+ end_address += PAGE_SIZE;
+ pte++;
+ if ((end_address < stop_address) &&
+ (end_address != ALIGN(end_address, 1UL << PMD_SHIFT)))
+ goto retry_pte;
+ continue;
+ }
+ /* Found next valid vmem_map page */
+ break;
+ } while (end_address < stop_address);
+
+ end_address = min(end_address, stop_address);
+ end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1;
+ hole_next_pfn = end_address / sizeof(struct page);
+ return hole_next_pfn - pgdat->node_start_pfn;
+}
+
+int __init create_mem_map_page_table(u64 start, u64 end, void *arg)
{
unsigned long address, start_page, end_page;
struct page *map_start, *map_end;
unsigned long zone;
};
-static int
-virtual_memmap_init (u64 start, u64 end, void *arg)
+static int __meminit
+virtual_memmap_init(u64 start, u64 end, void *arg)
{
struct memmap_init_callback_data *args;
struct page *map_start, *map_end;
if (map_start < map_end)
memmap_init_zone((unsigned long)(map_end - map_start),
- args->nid, args->zone, page_to_pfn(map_start));
+ args->nid, args->zone, page_to_pfn(map_start),
+ MEMMAP_EARLY);
return 0;
}
-void
+void __meminit
memmap_init (unsigned long size, int nid, unsigned long zone,
unsigned long start_pfn)
{
if (!vmem_map)
- memmap_init_zone(size, nid, zone, start_pfn);
+ memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY);
else {
struct page *start;
struct memmap_init_callback_data args;
}
EXPORT_SYMBOL(ia64_pfn_valid);
-int
-find_largest_hole (u64 start, u64 end, void *arg)
+int __init find_largest_hole(u64 start, u64 end, void *arg)
{
u64 *max_gap = arg;
last_end = end;
return 0;
}
+
#endif /* CONFIG_VIRTUAL_MEM_MAP */
-static int
-count_reserved_pages (u64 start, u64 end, void *arg)
+int __init register_active_ranges(u64 start, u64 len, int nid)
+{
+ u64 end = start + len;
+
+#ifdef CONFIG_KEXEC
+ if (start > crashk_res.start && start < crashk_res.end)
+ start = crashk_res.end;
+ if (end > crashk_res.start && end < crashk_res.end)
+ end = crashk_res.start;
+#endif
+
+ if (start < end)
+ add_active_range(nid, __pa(start) >> PAGE_SHIFT,
+ __pa(end) >> PAGE_SHIFT);
+ return 0;
+}
+
+static int __init
+count_reserved_pages(u64 start, u64 end, void *arg)
{
unsigned long num_reserved = 0;
unsigned long *count = arg;
return 0;
}
+int
+find_max_min_low_pfn (u64 start, u64 end, void *arg)
+{
+ unsigned long pfn_start, pfn_end;
+#ifdef CONFIG_FLATMEM
+ pfn_start = (PAGE_ALIGN(__pa(start))) >> PAGE_SHIFT;
+ pfn_end = (PAGE_ALIGN(__pa(end - 1))) >> PAGE_SHIFT;
+#else
+ pfn_start = GRANULEROUNDDOWN(__pa(start)) >> PAGE_SHIFT;
+ pfn_end = GRANULEROUNDUP(__pa(end - 1)) >> PAGE_SHIFT;
+#endif
+ min_low_pfn = min(min_low_pfn, pfn_start);
+ max_low_pfn = max(max_low_pfn, pfn_end);
+ return 0;
+}
+
/*
* Boot command-line option "nolwsys" can be used to disable the use of any light-weight
* system call handler. When this option is in effect, all fsyscalls will end up bubbling
* purposes.
*/
-static int nolwsys;
+static int nolwsys __initdata;
static int __init
nolwsys_setup (char *s)
__setup("nolwsys", nolwsys_setup);
-void
+void __init
mem_init (void)
{
long reserved_pages, codesize, datasize, initsize;
- unsigned long num_pgt_pages;
pg_data_t *pgdat;
int i;
- static struct kcore_list kcore_mem, kcore_vmem, kcore_kernel;
+
+ BUG_ON(PTRS_PER_PGD * sizeof(pgd_t) != PAGE_SIZE);
+ BUG_ON(PTRS_PER_PMD * sizeof(pmd_t) != PAGE_SIZE);
+ BUG_ON(PTRS_PER_PTE * sizeof(pte_t) != PAGE_SIZE);
#ifdef CONFIG_PCI
/*
platform_dma_init();
#endif
-#ifndef CONFIG_DISCONTIGMEM
- if (!mem_map)
- BUG();
+#ifdef CONFIG_FLATMEM
+ BUG_ON(!mem_map);
max_mapnr = max_low_pfn;
#endif
high_memory = __va(max_low_pfn * PAGE_SIZE);
- kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE);
- kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START);
- kclist_add(&kcore_kernel, _stext, _end - _stext);
-
- for_each_pgdat(pgdat)
- totalram_pages += free_all_bootmem_node(pgdat);
+ for_each_online_pgdat(pgdat)
+ if (pgdat->bdata->node_bootmem_map)
+ totalram_pages += free_all_bootmem_node(pgdat);
reserved_pages = 0;
efi_memmap_walk(count_reserved_pages, &reserved_pages);
initsize = (unsigned long) __init_end - (unsigned long) __init_begin;
printk(KERN_INFO "Memory: %luk/%luk available (%luk code, %luk reserved, "
- "%luk data, %luk init)\n", (unsigned long) nr_free_pages() << (PAGE_SHIFT - 10),
+ "%luk data, %luk init)\n", nr_free_pages() << (PAGE_SHIFT - 10),
num_physpages << (PAGE_SHIFT - 10), codesize >> 10,
reserved_pages << (PAGE_SHIFT - 10), datasize >> 10, initsize >> 10);
- /*
- * Allow for enough (cached) page table pages so that we can map the entire memory
- * at least once. Each task also needs a couple of page tables pages, so add in a
- * fudge factor for that (don't use "threads-max" here; that would be wrong!).
- * Don't allow the cache to be more than 10% of total memory, though.
- */
-# define NUM_TASKS 500 /* typical number of tasks */
- num_pgt_pages = nr_free_pages() / PTRS_PER_PGD + NUM_TASKS;
- if (num_pgt_pages > nr_free_pages() / 10)
- num_pgt_pages = nr_free_pages() / 10;
- if (num_pgt_pages > (u64) pgt_cache_water[1])
- pgt_cache_water[1] = num_pgt_pages;
/*
* For fsyscall entrpoints with no light-weight handler, use the ordinary
* code can tell them apart.
*/
for (i = 0; i < NR_syscalls; ++i) {
- extern unsigned long fsyscall_table[NR_syscalls];
extern unsigned long sys_call_table[NR_syscalls];
+ unsigned long *fsyscall_table = paravirt_get_fsyscall_table();
if (!fsyscall_table[i] || nolwsys)
fsyscall_table[i] = sys_call_table[i] | 1;
ia32_mem_init();
#endif
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int arch_add_memory(int nid, u64 start, u64 size)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+ int ret;
+
+ pgdat = NODE_DATA(nid);
+
+ zone = pgdat->node_zones + ZONE_NORMAL;
+ ret = __add_pages(nid, zone, start_pfn, nr_pages);
+
+ if (ret)
+ printk("%s: Problem encountered in __add_pages() as ret=%d\n",
+ __func__, ret);
+
+ return ret;
+}
+#endif
+
+/*
+ * Even when CONFIG_IA32_SUPPORT is not enabled it is
+ * useful to have the Linux/x86 domain registered to
+ * avoid an attempted module load when emulators call
+ * personality(PER_LINUX32). This saves several milliseconds
+ * on each such call.
+ */
+static struct exec_domain ia32_exec_domain;
+
+static int __init
+per_linux32_init(void)
+{
+ ia32_exec_domain.name = "Linux/x86";
+ ia32_exec_domain.handler = NULL;
+ ia32_exec_domain.pers_low = PER_LINUX32;
+ ia32_exec_domain.pers_high = PER_LINUX32;
+ ia32_exec_domain.signal_map = default_exec_domain.signal_map;
+ ia32_exec_domain.signal_invmap = default_exec_domain.signal_invmap;
+ register_exec_domain(&ia32_exec_domain);
+
+ return 0;
+}
+
+__initcall(per_linux32_init);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff