aboutsummaryrefslogtreecommitdiff
path: root/arch/ia64/mm/init.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/ia64/mm/init.c')
-rw-r--r--arch/ia64/mm/init.c411
1 files changed, 236 insertions, 175 deletions
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index b38b6d213c1..25c350264a4 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -4,13 +4,13 @@
* 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/bootmem.h>
#include <linux/efi.h>
#include <linux/elf.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/module.h>
@@ -20,10 +20,9 @@
#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/machvec.h>
#include <asm/numa.h>
@@ -31,24 +30,19 @@
#include <asm/pgalloc.h>
#include <asm/sal.h>
#include <asm/sections.h>
-#include <asm/system.h>
#include <asm/tlb.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/mca.h>
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-DEFINE_PER_CPU(unsigned long *, __pgtable_quicklist);
-DEFINE_PER_CPU(long, __pgtable_quicklist_size);
+#include <asm/paravirt.h>
extern void ia64_tlb_init (void);
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
@@ -56,81 +50,49 @@ EXPORT_SYMBOL(vmem_map);
struct page *zero_page_memmap_ptr; /* map entry for zero page */
EXPORT_SYMBOL(zero_page_memmap_ptr);
-#define MIN_PGT_PAGES 25UL
-#define MAX_PGT_FREES_PER_PASS 16L
-#define PGT_FRACTION_OF_NODE_MEM 16
-
-static inline long
-max_pgt_pages(void)
-{
- u64 node_free_pages, max_pgt_pages;
-
-#ifndef CONFIG_NUMA
- node_free_pages = nr_free_pages();
-#else
- node_free_pages = nr_free_pages_pgdat(NODE_DATA(numa_node_id()));
-#endif
- max_pgt_pages = node_free_pages / PGT_FRACTION_OF_NODE_MEM;
- max_pgt_pages = max(max_pgt_pages, MIN_PGT_PAGES);
- return max_pgt_pages;
-}
-
-static inline long
-min_pages_to_free(void)
-{
- long pages_to_free;
-
- pages_to_free = pgtable_quicklist_size - max_pgt_pages();
- pages_to_free = min(pages_to_free, MAX_PGT_FREES_PER_PASS);
- return pages_to_free;
-}
-
void
-check_pgt_cache(void)
-{
- long pages_to_free;
-
- if (unlikely(pgtable_quicklist_size <= MIN_PGT_PAGES))
- return;
-
- preempt_disable();
- while (unlikely((pages_to_free = min_pages_to_free()) > 0)) {
- while (pages_to_free--) {
- free_page((unsigned long)pgtable_quicklist_alloc());
- }
- preempt_enable();
- preempt_disable();
- }
- 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);
}
/*
@@ -151,14 +113,14 @@ ia64_init_addr_space (void)
* 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));
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
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|VM_ACCOUNT;
+ vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
down_write(&current->mm->mmap_sem);
if (insert_vm_struct(current->mm, vma)) {
up_write(&current->mm->mmap_sem);
@@ -170,13 +132,14 @@ ia64_init_addr_space (void)
/* 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));
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
vma->vm_mm = current->mm;
vma->vm_end = PAGE_SIZE;
vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
- vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | VM_RESERVED;
+ vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
+ VM_DONTEXPAND | VM_DONTDUMP;
down_write(&current->mm->mmap_sem);
if (insert_vm_struct(current->mm, vma)) {
up_write(&current->mm->mmap_sem);
@@ -191,25 +154,13 @@ ia64_init_addr_space (void)
void
free_initmem (void)
{
- unsigned long addr, eaddr;
-
- addr = (unsigned long) ia64_imva(__init_begin);
- eaddr = (unsigned long) ia64_imva(__init_end);
- while (addr < eaddr) {
- ClearPageReserved(virt_to_page(addr));
- set_page_count(virt_to_page(addr), 1);
- free_page(addr);
- ++totalram_pages;
- addr += PAGE_SIZE;
- }
- printk(KERN_INFO "Freeing unused kernel memory: %ldkB freed\n",
- (__init_end - __init_begin) >> 10);
+ free_reserved_area(ia64_imva(__init_begin), ia64_imva(__init_end),
+ -1, "unused kernel");
}
-void
+void __init
free_initrd_mem (unsigned long start, unsigned long end)
{
- struct page *page;
/*
* EFI uses 4KB pages while the kernel can use 4KB or bigger.
* Thus EFI and the kernel may have different page sizes. It is
@@ -250,18 +201,14 @@ free_initrd_mem (unsigned long start, unsigned long end)
for (; start < end; start += PAGE_SIZE) {
if (!virt_addr_valid(start))
continue;
- page = virt_to_page(start);
- ClearPageReserved(page);
- set_page_count(page, 1);
- free_page(start);
- ++totalram_pages;
+ free_reserved_page(virt_to_page(start));
}
}
/*
* 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;
@@ -294,9 +241,10 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
return page;
}
-static void
+static void __init
setup_gate (void)
{
+ void *gate_section;
struct page *page;
/*
@@ -304,10 +252,11 @@ setup_gate (void)
* 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);
@@ -329,11 +278,10 @@ setup_gate (void)
ia64_patch_gate();
}
-void __devinit
-ia64_mmu_init (void *my_cpu_data)
+void ia64_mmu_init(void *my_cpu_data)
{
- unsigned long psr, pta, impl_va_bits;
- extern void __devinit tlb_init (void);
+ unsigned long pta, impl_va_bits;
+ extern void tlb_init(void);
#ifdef CONFIG_DISABLE_VHPT
# define VHPT_ENABLE_BIT 0
@@ -341,15 +289,6 @@ ia64_mmu_init (void *my_cpu_data)
# 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
@@ -410,9 +349,61 @@ ia64_mmu_init (void *my_cpu_data)
}
#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);
+
+ end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
+ end_address = PAGE_ALIGN(end_address);
+ stop_address = (unsigned long) &vmem_map[pgdat_end_pfn(pgdat)];
+
+ 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;
+ }
-int
-create_mem_map_page_table (u64 start, u64 end, void *arg)
+ 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;
@@ -457,8 +448,8 @@ struct memmap_init_callback_data {
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;
@@ -483,16 +474,17 @@ virtual_memmap_init (u64 start, u64 end, void *arg)
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;
@@ -519,8 +511,7 @@ ia64_pfn_valid (unsigned long pfn)
}
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;
@@ -533,18 +524,38 @@ find_largest_hole (u64 start, u64 end, void *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)
{
- unsigned long num_reserved = 0;
- unsigned long *count = arg;
+ u64 end = start + len;
- for (; start < end; start += PAGE_SIZE)
- if (PageReserved(virt_to_page(start)))
- ++num_reserved;
- *count += num_reserved;
+#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)
+ memblock_add_node(__pa(start), end - start, nid);
+ 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;
}
@@ -556,7 +567,7 @@ count_reserved_pages (u64 start, u64 end, void *arg)
* purposes.
*/
-static int nolwsys;
+static int nolwsys __initdata;
static int __init
nolwsys_setup (char *s)
@@ -567,13 +578,10 @@ nolwsys_setup (char *s)
__setup("nolwsys", nolwsys_setup);
-void
+void __init
mem_init (void)
{
- long reserved_pages, codesize, datasize, initsize;
- 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);
@@ -589,33 +597,13 @@ mem_init (void)
#endif
#ifdef CONFIG_FLATMEM
- if (!mem_map)
- BUG();
- max_mapnr = max_low_pfn;
+ BUG_ON(!mem_map);
#endif
+ set_max_mapnr(max_low_pfn);
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)
- if (pgdat->bdata->node_bootmem_map)
- totalram_pages += free_all_bootmem_node(pgdat);
-
- reserved_pages = 0;
- efi_memmap_walk(count_reserved_pages, &reserved_pages);
-
- codesize = (unsigned long) _etext - (unsigned long) _stext;
- datasize = (unsigned long) _edata - (unsigned long) _etext;
- 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),
- num_physpages << (PAGE_SHIFT - 10), codesize >> 10,
- reserved_pages << (PAGE_SHIFT - 10), datasize >> 10, initsize >> 10);
-
+ free_all_bootmem();
+ mem_init_print_info(NULL);
/*
* For fsyscall entrpoints with no light-weight handler, use the ordinary
@@ -623,30 +611,17 @@ mem_init (void)
* 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;
}
setup_gate();
-
-#ifdef CONFIG_IA32_SUPPORT
- ia32_mem_init();
-#endif
}
#ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
- ClearPageReserved(page);
- set_page_count(page, 1);
- __free_page(page);
- totalram_pages++;
- num_physpages++;
-}
-
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat;
struct zone *zone;
@@ -654,20 +629,106 @@ int add_memory(u64 start, u64 size)
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
- pgdat = NODE_DATA(0);
+ pgdat = NODE_DATA(nid);
zone = pgdat->node_zones + ZONE_NORMAL;
- ret = __add_pages(zone, start_pfn, nr_pages);
+ ret = __add_pages(nid, zone, start_pfn, nr_pages);
if (ret)
printk("%s: Problem encountered in __add_pages() as ret=%d\n",
- __FUNCTION__, ret);
+ __func__, ret);
return ret;
}
-int remove_memory(u64 start, u64 size)
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
{
- return -EINVAL;
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+ struct zone *zone;
+ int ret;
+
+ zone = page_zone(pfn_to_page(start_pfn));
+ ret = __remove_pages(zone, start_pfn, nr_pages);
+ if (ret)
+ pr_warn("%s: Problem encountered in __remove_pages() as"
+ " ret=%d\n", __func__, ret);
+
+ return ret;
}
#endif
+#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);
+
+/**
+ * show_mem - give short summary of memory stats
+ *
+ * Shows a simple page count of reserved and used pages in the system.
+ * For discontig machines, it does this on a per-pgdat basis.
+ */
+void show_mem(unsigned int filter)
+{
+ int total_reserved = 0;
+ unsigned long total_present = 0;
+ pg_data_t *pgdat;
+
+ printk(KERN_INFO "Mem-info:\n");
+ show_free_areas(filter);
+ printk(KERN_INFO "Node memory in pages:\n");
+ for_each_online_pgdat(pgdat) {
+ unsigned long present;
+ unsigned long flags;
+ int reserved = 0;
+ int nid = pgdat->node_id;
+ int zoneid;
+
+ if (skip_free_areas_node(filter, nid))
+ continue;
+ pgdat_resize_lock(pgdat, &flags);
+
+ for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+ struct zone *zone = &pgdat->node_zones[zoneid];
+ if (!populated_zone(zone))
+ continue;
+
+ reserved += zone->present_pages - zone->managed_pages;
+ }
+ present = pgdat->node_present_pages;
+
+ pgdat_resize_unlock(pgdat, &flags);
+ total_present += present;
+ total_reserved += reserved;
+ printk(KERN_INFO "Node %4d: RAM: %11ld, rsvd: %8d, ",
+ nid, present, reserved);
+ }
+ printk(KERN_INFO "%ld pages of RAM\n", total_present);
+ printk(KERN_INFO "%d reserved pages\n", total_reserved);
+ printk(KERN_INFO "Total of %ld pages in page table cache\n",
+ quicklist_total_size());
+ printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
+}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-05 20:31:34 +0000