#define MAX_BANKS 32
- static struct linux_prom64_registers pavail[MAX_BANKS] __devinitdata;
- static int pavail_ents __devinitdata;
+ static struct linux_prom64_registers pavail[MAX_BANKS];
+ static int pavail_ents;
static int cmp_p64(const void *a, const void *b)
{
void prom_world(int enter)
{
if (!enter)
- set_fs((mm_segment_t) { get_thread_current_ds() });
+ set_fs(get_fs());
__asm__ __volatile__("flushw");
}
printk("Booting Linux...\n");
}
- int __devinit page_in_phys_avail(unsigned long paddr)
+ int page_in_phys_avail(unsigned long paddr)
{
int i;
flushi(&valid_addr_bitmap_insn[0]);
}
+static void __init register_page_bootmem_info(void)
+{
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ int i;
+
+ for_each_online_node(i)
+ if (NODE_DATA(i)->node_spanned_pages)
+ register_page_bootmem_info_node(NODE_DATA(i));
+#endif
+}
void __init mem_init(void)
{
unsigned long codepages, datapages, initpages;
high_memory = __va(last_valid_pfn << PAGE_SHIFT);
-#ifdef CONFIG_NEED_MULTIPLE_NODES
- {
- int i;
- for_each_online_node(i) {
- if (NODE_DATA(i)->node_spanned_pages != 0) {
- totalram_pages +=
- free_all_bootmem_node(NODE_DATA(i));
- }
- }
- totalram_pages += free_low_memory_core_early(MAX_NUMNODES);
- }
-#else
+ register_page_bootmem_info();
totalram_pages = free_all_bootmem();
-#endif
/* We subtract one to account for the mem_map_zero page
* allocated below.
static inline int pte_present(pte_t a)
{
- return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+ return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
+ _PAGE_NUMA);
+ }
+
+ #define pte_accessible pte_accessible
+ static inline int pte_accessible(pte_t a)
+ {
+ return pte_flags(a) & _PAGE_PRESENT;
}
static inline int pte_hidden(pte_t pte)
* the _PAGE_PSE flag will remain set at all times while the
* _PAGE_PRESENT bit is clear).
*/
- return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
+ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE |
+ _PAGE_NUMA);
}
static inline int pmd_none(pmd_t pmd)
static inline int pmd_bad(pmd_t pmd)
{
+ #ifdef CONFIG_NUMA_BALANCING
+ /* pmd_numa check */
+ if ((pmd_flags(pmd) & (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA)
+ return 0;
+ #endif
return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
}
#ifndef __ASSEMBLY__
extern int direct_gbpages;
+void init_mem_mapping(void);
+void early_alloc_pgt_buf(void);
/* local pte updates need not use xchg for locking */
static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
#define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
+ /*
+ * _PAGE_NUMA indicates that this page will trigger a numa hinting
+ * minor page fault to gather numa placement statistics (see
+ * pte_numa()). The bit picked (8) is within the range between
+ * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't
+ * require changes to the swp entry format because that bit is always
+ * zero when the pte is not present.
+ *
+ * The bit picked must be always zero when the pmd is present and not
+ * present, so that we don't lose information when we set it while
+ * atomically clearing the present bit.
+ *
+ * Because we shared the same bit (8) with _PAGE_PROTNONE this can be
+ * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE
+ * couldn't reach, like handle_mm_fault() (see access_error in
+ * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for
+ * handle_mm_fault() to be invoked).
+ */
+ #define _PAGE_NUMA _PAGE_PROTNONE
+
#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_DIRTY)
#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \
/* Install a pte for a particular vaddr in kernel space. */
void set_pte_vaddr(unsigned long vaddr, pte_t pte);
-extern void native_pagetable_reserve(u64 start, u64 end);
#ifdef CONFIG_X86_32
extern void native_pagetable_init(void);
#else
#ifdef CONFIG_X86_64
# include <asm/proto.h>
-# include <asm/numa_64.h>
#endif /* X86 */
#define BAD_MADT_ENTRY(entry, end) ( \
return irq;
}
+ EXPORT_SYMBOL_GPL(acpi_register_gsi);
+
+ void acpi_unregister_gsi(u32 gsi)
+ {
+ }
+ EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
void __init acpi_set_irq_model_pic(void)
{
} while (unlikely (val != old));
return old & 0x1;
}
+
+ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
+ {
+ e820_add_region(addr, size, E820_ACPI);
+ update_e820();
+ }
#include <asm/pci-direct.h>
#ifdef CONFIG_X86_64
-# include <asm/numa_64.h>
# include <asm/mmconfig.h>
# include <asm/cacheflush.h>
#endif
int cpu = smp_processor_id();
/* get information required for multi-node processors */
- if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+ if (cpu_has_topoext) {
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
}
}
+ /*
+ * The way access filter has a performance penalty on some workloads.
+ * Disable it on the affected CPUs.
+ */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+ u64 val;
+
+ if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+ val |= 0x1E;
+ wrmsrl_safe(0xc0011021, val);
+ }
+ }
+
cpu_detect_cache_sizes(c);
/* Multi core CPU? */
detect_ht(c);
#endif
- if (c->extended_cpuid_level >= 0x80000006) {
- if (cpuid_edx(0x80000006) & 0xf000)
- num_cache_leaves = 4;
- else
- num_cache_leaves = 3;
- }
+ init_amd_cacheinfo(c);
if (c->x86 >= 0xf)
set_cpu_cap(c, X86_FEATURE_K8);
* benefit in doing so.
*/
if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ unsigned long pfn = tseg >> PAGE_SHIFT;
+
printk(KERN_DEBUG "tseg: %010llx\n", tseg);
- if ((tseg>>PMD_SHIFT) <
- (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
- ((tseg>>PMD_SHIFT) <
- (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
- (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+ if (pfn_range_is_mapped(pfn, pfn + 1))
set_memory_4k((unsigned long)__va(tseg), 1);
}
}
static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
{
- if (!cpu_has_invlpg)
- return;
-
tlb_flushall_shift = 5;
if (c->x86 <= 0x11)
#ifdef CONFIG_X86_64
#include <linux/topology.h>
-#include <asm/numa_64.h>
#endif
#include "cpu.h"
static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
{
- if (!cpu_has_invlpg) {
- tlb_flushall_shift = -1;
- return;
- }
switch ((c->x86 << 8) + c->x86_model) {
case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
#include <asm/topology.h>
#include <asm/apicdef.h>
#include <asm/amd_nb.h>
-#ifdef CONFIG_X86_64
-#include <asm/numa_64.h>
-#endif
#include <asm/mce.h>
#include <asm/alternative.h>
#include <asm/prom.h>
/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
+ * max_low_pfn_mapped: highest direct mapped pfn under 4GB
+ * max_pfn_mapped: highest direct mapped pfn over 4GB
+ *
+ * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * represented by pfn_mapped
*/
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
}
#endif
- #ifndef CONFIG_DEBUG_BOOT_PARAMS
- struct boot_params __initdata boot_params;
- #else
struct boot_params boot_params;
- #endif
/*
* Machine setup..
return ret;
}
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
- if (direct_gbpages && cpu_has_gbpages)
- printk(KERN_INFO "Using GB pages for direct mapping\n");
- else
- direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
+#ifdef CONFIG_X86_32
static void __init cleanup_highmap(void)
{
}
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
u64 area_size = PAGE_ALIGN(ramdisk_size);
- u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
- /* We need to move the initrd down into lowmem */
- ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
- PAGE_SIZE);
+ /* We need to move the initrd down into directly mapped mem */
+ ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+ area_size, PAGE_SIZE);
if (!ramdisk_here)
panic("Cannot find place for new RAMDISK of size %lld\n",
ramdisk_size);
- /* Note: this includes all the lowmem currently occupied by
+ /* Note: this includes all the mem currently occupied by
the initrd, we rely on that fact to keep the data intact. */
memblock_reserve(ramdisk_here, area_size);
initrd_start = ramdisk_here + PAGE_OFFSET;
q = (char *)initrd_start;
- /* Copy any lowmem portion of the initrd */
- if (ramdisk_image < end_of_lowmem) {
- clen = end_of_lowmem - ramdisk_image;
- p = (char *)__va(ramdisk_image);
- memcpy(q, p, clen);
- q += clen;
- ramdisk_image += clen;
- ramdisk_size -= clen;
- }
-
- /* Copy the highmem portion of the initrd */
+ /* Copy the initrd */
while (ramdisk_size) {
slop = ramdisk_image & ~PAGE_MASK;
clen = ramdisk_size;
ramdisk_image += clen;
ramdisk_size -= clen;
}
- /* high pages is not converted by early_res_to_bootmem */
+
ramdisk_image = boot_params.hdr.ramdisk_image;
ramdisk_size = boot_params.hdr.ramdisk_size;
printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
+static u64 __init get_mem_size(unsigned long limit_pfn)
+{
+ int i;
+ u64 mapped_pages = 0;
+ unsigned long start_pfn, end_pfn;
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+ start_pfn = min_t(unsigned long, start_pfn, limit_pfn);
+ end_pfn = min_t(unsigned long, end_pfn, limit_pfn);
+ mapped_pages += end_pfn - start_pfn;
+ }
+
+ return mapped_pages << PAGE_SHIFT;
+}
static void __init reserve_initrd(void)
{
/* Assume only end is not page aligned */
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+ u64 mapped_size;
if (!boot_params.hdr.type_of_loader ||
!ramdisk_image || !ramdisk_size)
initrd_start = 0;
- if (ramdisk_size >= (end_of_lowmem>>1)) {
+ mapped_size = get_mem_size(max_pfn_mapped);
+ if (ramdisk_size >= (mapped_size>>1))
panic("initrd too large to handle, "
"disabling initrd (%lld needed, %lld available)\n",
- ramdisk_size, end_of_lowmem>>1);
- }
+ ramdisk_size, mapped_size>>1);
printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
ramdisk_end - 1);
-
- if (ramdisk_end <= end_of_lowmem) {
- /* All in lowmem, easy case */
+ if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image),
+ PFN_DOWN(ramdisk_end))) {
+ /* All are mapped, easy case */
/*
* don't need to reserve again, already reserved early
* in i386_start_kernel
static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
+ static bool __init snb_gfx_workaround_needed(void)
+ {
+ #ifdef CONFIG_PCI
+ int i;
+ u16 vendor, devid;
+ static const __initconst u16 snb_ids[] = {
+ 0x0102,
+ 0x0112,
+ 0x0122,
+ 0x0106,
+ 0x0116,
+ 0x0126,
+ 0x010a,
+ };
+
+ /* Assume no if something weird is going on with PCI */
+ if (!early_pci_allowed())
+ return false;
+
+ vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
+ if (vendor != 0x8086)
+ return false;
+
+ devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
+ for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
+ if (devid == snb_ids[i])
+ return true;
+ #endif
+
+ return false;
+ }
+
+ /*
+ * Sandy Bridge graphics has trouble with certain ranges, exclude
+ * them from allocation.
+ */
+ static void __init trim_snb_memory(void)
+ {
+ static const __initconst unsigned long bad_pages[] = {
+ 0x20050000,
+ 0x20110000,
+ 0x20130000,
+ 0x20138000,
+ 0x40004000,
+ };
+ int i;
+
+ if (!snb_gfx_workaround_needed())
+ return;
+
+ printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
+
+ /*
+ * Reserve all memory below the 1 MB mark that has not
+ * already been reserved.
+ */
+ memblock_reserve(0, 1<<20);
+
+ for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
+ if (memblock_reserve(bad_pages[i], PAGE_SIZE))
+ printk(KERN_WARNING "failed to reserve 0x%08lx\n",
+ bad_pages[i]);
+ }
+ }
+
+ /*
+ * Here we put platform-specific memory range workarounds, i.e.
+ * memory known to be corrupt or otherwise in need to be reserved on
+ * specific platforms.
+ *
+ * If this gets used more widely it could use a real dispatch mechanism.
+ */
+ static void __init trim_platform_memory_ranges(void)
+ {
+ trim_snb_memory();
+ }
+
static void __init trim_bios_range(void)
{
/*
* take them out.
*/
e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
}
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
+ /*
+ * Complain if .text .data and .bss are not marked as E820_RAM and
+ * attempt to fix it by adding the range. We may have a confused BIOS,
+ * or the user may have incorrectly supplied it via memmap=exactmap. If
+ * we really are running on top non-RAM, we will crash later anyways.
+ */
+ if (!e820_all_mapped(code_resource.start, __pa(__brk_limit), E820_RAM)) {
+ pr_warn(".text .data .bss are not marked as E820_RAM!\n");
+
+ e820_add_region(code_resource.start,
+ __pa(__brk_limit) - code_resource.start + 1,
+ E820_RAM);
+ }
+
trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
reserve_ibft_region();
+ early_alloc_pgt_buf();
+
/*
* Need to conclude brk, before memblock_x86_fill()
* it could use memblock_find_in_range, could overlap with
cleanup_highmap();
- memblock.current_limit = get_max_mapped();
+ memblock.current_limit = ISA_END_ADDRESS;
memblock_x86_fill();
/*
setup_real_mode();
- init_gbpages();
+ trim_platform_memory_ranges();
+
+ init_mem_mapping();
- /* max_pfn_mapped is updated here */
- max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
- max_pfn_mapped = max_low_pfn_mapped;
-
-#ifdef CONFIG_X86_64
- if (max_pfn > max_low_pfn) {
- int i;
- unsigned long start, end;
- unsigned long start_pfn, end_pfn;
-
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
- NULL) {
-
- end = PFN_PHYS(end_pfn);
- if (end <= (1UL<<32))
- continue;
-
- start = PFN_PHYS(start_pfn);
- max_pfn_mapped = init_memory_mapping(
- max((1UL<<32), start), end);
- }
-
- /* can we preseve max_low_pfn ?*/
- max_low_pfn = max_pfn;
- }
-#endif
memblock.current_limit = get_max_mapped();
dma_contiguous_reserve(0);
reserve_initrd();
+ #if defined(CONFIG_ACPI) && defined(CONFIG_BLK_DEV_INITRD)
+ acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start);
+ #endif
+
reserve_crashkernel();
vsmp_init();
#include <asm/page_types.h>
#include <asm/init.h>
+#include "mm_internal.h"
+
unsigned long highstart_pfn, highend_pfn;
static noinline int do_test_wp_bit(void);
bool __read_mostly __vmalloc_start_set = false;
-static __init void *alloc_low_page(void)
-{
- unsigned long pfn = pgt_buf_end++;
- void *adr;
-
- if (pfn >= pgt_buf_top)
- panic("alloc_low_page: ran out of memory");
-
- adr = __va(pfn * PAGE_SIZE);
- clear_page(adr);
- return adr;
-}
-
/*
* Creates a middle page table and puts a pointer to it in the
* given global directory entry. This only returns the gd entry
#ifdef CONFIG_X86_PAE
if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
- if (after_bootmem)
- pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE);
- else
- pmd_table = (pmd_t *)alloc_low_page();
+ pmd_table = (pmd_t *)alloc_low_page();
paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
pud = pud_offset(pgd, 0);
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
- pte_t *page_table = NULL;
-
- if (after_bootmem) {
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
- page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
-#endif
- if (!page_table)
- page_table =
- (pte_t *)alloc_bootmem_pages(PAGE_SIZE);
- } else
- page_table = (pte_t *)alloc_low_page();
+ pte_t *page_table = (pte_t *)alloc_low_page();
paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
return one_page_table_init(pmd) + pte_idx;
}
+static unsigned long __init
+page_table_range_init_count(unsigned long start, unsigned long end)
+{
+ unsigned long count = 0;
+#ifdef CONFIG_HIGHMEM
+ int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+ int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+ int pgd_idx, pmd_idx;
+ unsigned long vaddr;
+
+ if (pmd_idx_kmap_begin == pmd_idx_kmap_end)
+ return 0;
+
+ vaddr = start;
+ pgd_idx = pgd_index(vaddr);
+
+ for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
+ for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
+ pmd_idx++) {
+ if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin &&
+ (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end)
+ count++;
+ vaddr += PMD_SIZE;
+ }
+ pmd_idx = 0;
+ }
+#endif
+ return count;
+}
+
static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
- unsigned long vaddr, pte_t *lastpte)
+ unsigned long vaddr, pte_t *lastpte,
+ void **adr)
{
#ifdef CONFIG_HIGHMEM
/*
if (pmd_idx_kmap_begin != pmd_idx_kmap_end
&& (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
- && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
- && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start
- || (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) {
+ && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) {
pte_t *newpte;
int i;
BUG_ON(after_bootmem);
- newpte = alloc_low_page();
+ newpte = *adr;
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(newpte + i, pte[i]);
+ *adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE);
paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte = NULL;
+ unsigned long count = page_table_range_init_count(start, end);
+ void *adr = NULL;
+
+ if (count)
+ adr = alloc_low_pages(count);
vaddr = start;
pgd_idx = pgd_index(vaddr);
for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
pmd++, pmd_idx++) {
pte = page_table_kmap_check(one_page_table_init(pmd),
- pmd, vaddr, pte);
+ pmd, vaddr, pte, &adr);
vaddr += PMD_SIZE;
}
__pgprot(PTE_IDENT_ATTR |
_PAGE_PSE);
+ pfn &= PMD_MASK >> PAGE_SHIFT;
addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
PAGE_OFFSET + PAGE_SIZE-1;
/*
* Remove any mappings which extend past the end of physical
- * memory from the boot time page table:
+ * memory from the boot time page table.
+ * In virtual address space, we should have at least two pages
+ * from VMALLOC_END to pkmap or fixmap according to VMALLOC_END
+ * definition. And max_low_pfn is set to VMALLOC_END physical
+ * address. If initial memory mapping is doing right job, we
+ * should have pte used near max_low_pfn or one pmd is not present.
*/
- for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
+ for (pfn = max_low_pfn; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
pgd = base + pgd_index(va);
if (!pgd_present(*pgd))
if (!pmd_present(*pmd))
break;
+ /* should not be large page here */
+ if (pmd_large(*pmd)) {
+ pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n",
+ pfn, pmd, __pa(pmd));
+ BUG_ON(1);
+ }
+
pte = pte_offset_kernel(pmd, va);
if (!pte_present(*pte))
break;
+ printk(KERN_DEBUG "clearing pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx pte: %p pte phys: %lx\n",
+ pfn, pmd, __pa(pmd), pte, __pa(pte));
pte_clear(NULL, va, pte);
}
paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
* artificially via the highmem=x boot parameter then create
* it:
*/
-void __init lowmem_pfn_init(void)
+static void __init lowmem_pfn_init(void)
{
/* max_low_pfn is 0, we already have early_res support */
max_low_pfn = max_pfn;
* We have more RAM than fits into lowmem - we try to put it into
* highmem, also taking the highmem=x boot parameter into account:
*/
-void __init highmem_pfn_init(void)
+static void __init highmem_pfn_init(void)
{
max_low_pfn = MAXMEM_PFN;
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
-
- after_bootmem = 1;
}
/*
if (!boot_cpu_data.wp_works_ok) {
printk(KERN_CONT "No.\n");
- #ifdef CONFIG_X86_WP_WORKS_OK
- panic(
- "This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
- #endif
+ panic("Linux doesn't support CPUs with broken WP.");
} else {
printk(KERN_CONT "Ok.\n");
}
if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
reservedpages++;
+ after_bootmem = 1;
+
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
#include <asm/uv/uv.h>
#include <asm/setup.h>
+#include "mm_internal.h"
+
static int __init parse_direct_gbpages_off(char *arg)
{
direct_gbpages = 0;
}
}
-static __ref void *alloc_low_page(unsigned long *phys)
-{
- unsigned long pfn = pgt_buf_end++;
- void *adr;
-
- if (after_bootmem) {
- adr = (void *)get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
- *phys = __pa(adr);
-
- return adr;
- }
-
- if (pfn >= pgt_buf_top)
- panic("alloc_low_page: ran out of memory");
-
- adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
- clear_page(adr);
- *phys = pfn * PAGE_SIZE;
- return adr;
-}
-
-static __ref void *map_low_page(void *virt)
-{
- void *adr;
- unsigned long phys, left;
-
- if (after_bootmem)
- return virt;
-
- phys = __pa(virt);
- left = phys & (PAGE_SIZE - 1);
- adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE);
- adr = (void *)(((unsigned long)adr) | left);
-
- return adr;
-}
-
-static __ref void unmap_low_page(void *adr)
-{
- if (after_bootmem)
- return;
-
- early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE);
-}
-
static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
pgprot_t prot)
{
- unsigned pages = 0;
+ unsigned long pages = 0, next;
unsigned long last_map_addr = end;
int i;
pte_t *pte = pte_page + pte_index(addr);
- for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {
-
+ for (i = pte_index(addr); i < PTRS_PER_PTE; i++, addr = next, pte++) {
+ next = (addr & PAGE_MASK) + PAGE_SIZE;
if (addr >= end) {
- if (!after_bootmem) {
- for(; i < PTRS_PER_PTE; i++, pte++)
- set_pte(pte, __pte(0));
- }
- break;
+ if (!after_bootmem &&
+ !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) &&
+ !e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN))
+ set_pte(pte, __pte(0));
+ continue;
}
/*
int i = pmd_index(address);
for (; i < PTRS_PER_PMD; i++, address = next) {
- unsigned long pte_phys;
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
pgprot_t new_prot = prot;
+ next = (address & PMD_MASK) + PMD_SIZE;
if (address >= end) {
- if (!after_bootmem) {
- for (; i < PTRS_PER_PMD; i++, pmd++)
- set_pmd(pmd, __pmd(0));
- }
- break;
+ if (!after_bootmem &&
+ !e820_any_mapped(address & PMD_MASK, next, E820_RAM) &&
+ !e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN))
+ set_pmd(pmd, __pmd(0));
+ continue;
}
- next = (address & PMD_MASK) + PMD_SIZE;
-
if (pmd_val(*pmd)) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
- pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd));
+ pte = (pte_t *)pmd_page_vaddr(*pmd);
last_map_addr = phys_pte_init(pte, address,
end, prot);
- unmap_low_page(pte);
spin_unlock(&init_mm.page_table_lock);
continue;
}
pages++;
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pmd,
- pfn_pte(address >> PAGE_SHIFT,
+ pfn_pte((address & PMD_MASK) >> PAGE_SHIFT,
__pgprot(pgprot_val(prot) | _PAGE_PSE)));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = next;
continue;
}
- pte = alloc_low_page(&pte_phys);
+ pte = alloc_low_page();
last_map_addr = phys_pte_init(pte, address, end, new_prot);
- unmap_low_page(pte);
spin_lock(&init_mm.page_table_lock);
- pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
+ pmd_populate_kernel(&init_mm, pmd, pte);
spin_unlock(&init_mm.page_table_lock);
}
update_page_count(PG_LEVEL_2M, pages);
int i = pud_index(addr);
for (; i < PTRS_PER_PUD; i++, addr = next) {
- unsigned long pmd_phys;
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
pgprot_t prot = PAGE_KERNEL;
- if (addr >= end)
- break;
-
next = (addr & PUD_MASK) + PUD_SIZE;
-
- if (!after_bootmem && !e820_any_mapped(addr, next, 0)) {
- set_pud(pud, __pud(0));
+ if (addr >= end) {
+ if (!after_bootmem &&
+ !e820_any_mapped(addr & PUD_MASK, next, E820_RAM) &&
+ !e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN))
+ set_pud(pud, __pud(0));
continue;
}
if (pud_val(*pud)) {
if (!pud_large(*pud)) {
- pmd = map_low_page(pmd_offset(pud, 0));
+ pmd = pmd_offset(pud, 0);
last_map_addr = phys_pmd_init(pmd, addr, end,
page_size_mask, prot);
- unmap_low_page(pmd);
__flush_tlb_all();
continue;
}
pages++;
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pud,
- pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+ pfn_pte((addr & PUD_MASK) >> PAGE_SHIFT,
+ PAGE_KERNEL_LARGE));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = next;
continue;
}
- pmd = alloc_low_page(&pmd_phys);
+ pmd = alloc_low_page();
last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
prot);
- unmap_low_page(pmd);
spin_lock(&init_mm.page_table_lock);
- pud_populate(&init_mm, pud, __va(pmd_phys));
+ pud_populate(&init_mm, pud, pmd);
spin_unlock(&init_mm.page_table_lock);
}
__flush_tlb_all();
for (; start < end; start = next) {
pgd_t *pgd = pgd_offset_k(start);
- unsigned long pud_phys;
pud_t *pud;
next = (start + PGDIR_SIZE) & PGDIR_MASK;
next = end;
if (pgd_val(*pgd)) {
- pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd));
+ pud = (pud_t *)pgd_page_vaddr(*pgd);
last_map_addr = phys_pud_init(pud, __pa(start),
__pa(end), page_size_mask);
- unmap_low_page(pud);
continue;
}
- pud = alloc_low_page(&pud_phys);
+ pud = alloc_low_page();
last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
page_size_mask);
- unmap_low_page(pud);
spin_lock(&init_mm.page_table_lock);
- pgd_populate(&init_mm, pgd, __va(pud_phys));
+ pgd_populate(&init_mm, pgd, pud);
spin_unlock(&init_mm.page_table_lock);
pgd_changed = true;
}
* numa support is not compiled in, and later node_set_state
* will not set it back.
*/
- node_clear_state(0, N_NORMAL_MEMORY);
+ node_clear_state(0, N_MEMORY);
+ if (N_MEMORY != N_NORMAL_MEMORY)
+ node_clear_state(0, N_NORMAL_MEMORY);
zone_sizes_init();
}
{
struct pglist_data *pgdat = NODE_DATA(nid);
struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
- unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT;
+ unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
- last_mapped_pfn = init_memory_mapping(start, start + size);
- if (last_mapped_pfn > max_pfn_mapped)
- max_pfn_mapped = last_mapped_pfn;
+ init_memory_mapping(start, start + size);
ret = __add_pages(nid, zone, start_pfn, nr_pages);
WARN_ON_ONCE(ret);
static struct kcore_list kcore_vsyscall;
+static void __init register_page_bootmem_info(void)
+{
+#ifdef CONFIG_NUMA
+ int i;
+
+ for_each_online_node(i)
+ register_page_bootmem_info_node(NODE_DATA(i));
+#endif
+}
+
void __init mem_init(void)
{
long codesize, reservedpages, datasize, initsize;
reservedpages = 0;
/* this will put all low memory onto the freelists */
-#ifdef CONFIG_NUMA
- totalram_pages = numa_free_all_bootmem();
-#else
+ register_page_bootmem_info();
totalram_pages = free_all_bootmem();
-#endif
absent_pages = absent_pages_in_range(0, max_pfn);
reservedpages = max_pfn - totalram_pages - absent_pages;
static void xen_post_allocator_init(void);
-static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
-{
- /* reserve the range used */
- native_pagetable_reserve(start, end);
-
- /* set as RW the rest */
- printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
- PFN_PHYS(pgt_buf_top));
- while (end < PFN_PHYS(pgt_buf_top)) {
- make_lowmem_page_readwrite(__va(end));
- end += PAGE_SIZE;
- }
-}
-
#ifdef CONFIG_X86_64
static void __init xen_cleanhighmap(unsigned long vaddr,
unsigned long vaddr_end)
#else /* CONFIG_X86_64 */
static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
{
- unsigned long pfn = pte_pfn(pte);
-
- /*
- * If the new pfn is within the range of the newly allocated
- * kernel pagetable, and it isn't being mapped into an
- * early_ioremap fixmap slot as a freshly allocated page, make sure
- * it is RO.
- */
- if (((!is_early_ioremap_ptep(ptep) &&
- pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
- (is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
- pte = pte_wrprotect(pte);
-
return pte;
}
#endif /* CONFIG_X86_64 */
void __init xen_init_mmu_ops(void)
{
- x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
x86_init.paging.pagetable_init = xen_pagetable_init;
pv_mmu_ops = xen_mmu_ops;
int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
unsigned long addr,
- unsigned long mfn, int nr,
- pgprot_t prot, unsigned domid)
+ xen_pfn_t mfn, int nr,
+ pgprot_t prot, unsigned domid,
+ struct page **pages)
+
{
struct remap_data rmd;
struct mmu_update mmu_update[REMAP_BATCH_SIZE];
return err;
}
EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
+
+ /* Returns: 0 success */
+ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+ int numpgs, struct page **pages)
+ {
+ if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
+ return 0;
+
+ return -EINVAL;
+ }
+ EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
void split_page(struct page *page, unsigned int order);
int split_free_page(struct page *page);
- int capture_free_page(struct page *page, int alloc_order, int migratetype);
/*
* Compound pages have a destructor function. Provide a
}
#endif
+ #ifdef CONFIG_NUMA_BALANCING
+ static inline int page_xchg_last_nid(struct page *page, int nid)
+ {
+ return xchg(&page->_last_nid, nid);
+ }
+
+ static inline int page_last_nid(struct page *page)
+ {
+ return page->_last_nid;
+ }
+ static inline void reset_page_last_nid(struct page *page)
+ {
+ page->_last_nid = -1;
+ }
+ #else
+ static inline int page_xchg_last_nid(struct page *page, int nid)
+ {
+ return page_to_nid(page);
+ }
+
+ static inline int page_last_nid(struct page *page)
+ {
+ return page_to_nid(page);
+ }
+
+ static inline void reset_page_last_nid(struct page *page)
+ {
+ }
+ #endif
+
static inline struct zone *page_zone(const struct page *page)
{
return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
extern void truncate_setsize(struct inode *inode, loff_t newsize);
- extern int vmtruncate(struct inode *inode, loff_t offset);
void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
int truncate_inode_page(struct address_space *mapping, struct page *page);
int generic_error_remove_page(struct address_space *mapping, struct page *page);
extern unsigned long do_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr);
+ extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, pgprot_t newprot,
+ int dirty_accountable, int prot_numa);
extern int mprotect_fixup(struct vm_area_struct *vma,
struct vm_area_struct **pprev, unsigned long start,
unsigned long end, unsigned long newflags);
extern void show_mem(unsigned int flags);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);
-extern int after_bootmem;
extern __printf(3, 4)
void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
unsigned long, unsigned long,
unsigned long, unsigned long);
+ struct vm_unmapped_area_info {
+ #define VM_UNMAPPED_AREA_TOPDOWN 1
+ unsigned long flags;
+ unsigned long length;
+ unsigned long low_limit;
+ unsigned long high_limit;
+ unsigned long align_mask;
+ unsigned long align_offset;
+ };
+
+ extern unsigned long unmapped_area(struct vm_unmapped_area_info *info);
+ extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info);
+
+ /*
+ * Search for an unmapped address range.
+ *
+ * We are looking for a range that:
+ * - does not intersect with any VMA;
+ * - is contained within the [low_limit, high_limit) interval;
+ * - is at least the desired size.
+ * - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
+ */
+ static inline unsigned long
+ vm_unmapped_area(struct vm_unmapped_area_info *info)
+ {
+ if (!(info->flags & VM_UNMAPPED_AREA_TOPDOWN))
+ return unmapped_area(info);
+ else
+ return unmapped_area_topdown(info);
+ }
+
/* truncate.c */
extern void truncate_inode_pages(struct address_space *, loff_t);
extern void truncate_inode_pages_range(struct address_space *,
}
#endif
+ #ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+ unsigned long change_prot_numa(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
+ #endif
+
struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t);
#define FOLL_MLOCK 0x40 /* mark page as mlocked */
#define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */
#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */
+ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
return count;
}
-/**
- * free_all_bootmem_node - release a node's free pages to the buddy allocator
- * @pgdat: node to be released
- *
- * Returns the number of pages actually released.
- */
-unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
-{
- register_page_bootmem_info_node(pgdat);
- reset_node_lowmem_managed_pages(pgdat);
-
- /* free_low_memory_core_early(MAX_NUMNODES) will be called later */
- return 0;
-}
-
+ static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+ {
+ struct zone *z;
+
+ /*
+ * In free_area_init_core(), highmem zone's managed_pages is set to
+ * present_pages, and bootmem allocator doesn't allocate from highmem
+ * zones. So there's no need to recalculate managed_pages because all
+ * highmem pages will be managed by the buddy system. Here highmem
+ * zone also includes highmem movable zone.
+ */
+ for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+ if (!is_highmem(z))
+ z->managed_pages = 0;
+ }
+
/**
* free_all_bootmem - release free pages to the buddy allocator
*
*/
unsigned long __init free_all_bootmem(void)
{
+ struct pglist_data *pgdat;
+
+ for_each_online_pgdat(pgdat)
+ reset_node_lowmem_managed_pages(pgdat);
+
/*
* We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
* because in some case like Node0 doesn't have RAM installed