#include <linux/swap.h>
#include <linux/proc_fs.h>
#include <linux/pfn.h>
+ #include <linux/hardirq.h>
#include <asm/asm-offsets.h>
#include <asm/bootinfo.h>
inc_preempt_count();
idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
#ifdef CONFIG_MIPS_MT_SMTC
- idx += FIX_N_COLOURS * smp_processor_id();
+ idx += FIX_N_COLOURS * smp_processor_id() +
+ (in_interrupt() ? (FIX_N_COLOURS * NR_CPUS) : 0);
+ #else
+ idx += in_interrupt() ? FIX_N_COLOURS : 0;
#endif
vaddr = __fix_to_virt(FIX_CMAP_END - idx);
pte = mk_pte(page, PAGE_KERNEL);
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
-static int __init page_is_ram(unsigned long pagenr)
+int page_is_ram(unsigned long pagenr)
{
int i;
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10,
- (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)));
+ totalhigh_pages << (PAGE_SHIFT-10));
}
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
__pa_symbol(&__init_end));
}
+ #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
unsigned long pgd_current[NR_CPUS];
+ #endif
/*
* On 64-bit we've got three-level pagetables with a slightly
* different layout ...
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
-static int __init page_is_ram(unsigned long pagenr)
+int page_is_ram(unsigned long pagenr)
{
if (pagenr >= min_low_pfn && pagenr < max_low_pfn)
return 1;
unsigned long codesize, reservedpages, datasize, initsize;
unsigned long tmp, ram = 0;
- max_mapnr = max_low_pfn;
high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
totalram_pages += free_all_bootmem();
totalram_pages -= setup_zero_page(); /* Setup zeroed pages. */
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
- kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
- kclist_add(&kcore_vmalloc, (void *) VMALLOC_START,
- VMALLOC_END - VMALLOC_START);
-
printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
"%ldk reserved, %ldk data, %ldk init, %ldk highmem)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
ram << (PAGE_SHIFT-10), codesize >> 10,
reservedpages << (PAGE_SHIFT-10), datasize >> 10,
initsize >> 10,
- (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)));
+ totalhigh_pages << (PAGE_SHIFT-10));
}
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
int checktype)
{
int i;
+ u64 end;
u64 real_removed_size = 0;
if (size > (ULLONG_MAX - start))
size = ULLONG_MAX - start;
+ end = start + size;
+ printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
+ (unsigned long long) start,
+ (unsigned long long) end);
+ e820_print_type(old_type);
+ printk(KERN_CONT "\n");
+
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
u64 final_start, final_end;
/*
* Early reserved memory areas.
*/
- #define MAX_EARLY_RES 20
+ #define MAX_EARLY_RES 32
struct early_res {
u64 start, end;
char overlap_ok;
};
static struct early_res early_res[MAX_EARLY_RES] __initdata = {
- { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */
+ { 0, PAGE_SIZE, "BIOS data page", 1 }, /* BIOS data page */
+ #if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
+ /*
+ * But first pinch a few for the stack/trampoline stuff
+ * FIXME: Don't need the extra page at 4K, but need to fix
+ * trampoline before removing it. (see the GDT stuff)
+ */
+ { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
+ #endif
+
{}
};
#include <asm/mtrr.h>
#include <asm/apic.h>
+ #include <asm/trampoline.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#ifdef CONFIG_X86_64
#include <asm/numa_64.h>
#endif
+ #include <asm/mce.h>
/*
* end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
* from boot_params into a safe place.
*
*/
- static inline void copy_edd(void)
+ static inline void __init copy_edd(void)
{
memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer,
sizeof(edd.mbr_signature));
edd.edd_info_nr = boot_params.eddbuf_entries;
}
#else
- static inline void copy_edd(void)
+ static inline void __init copy_edd(void)
{
}
#endif
},
},
{
+ .callback = dmi_low_memory_corruption,
+ .ident = "Phoenix/MSC BIOS",
+ .matches = {
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
+ },
+ },
/*
- * AMI BIOS with low memory corruption was found on Intel DG45ID board.
- * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
+ * AMI BIOS with low memory corruption was found on Intel DG45ID and
+ * DG45FC boards.
+ * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
* match only DMI_BOARD_NAME and see if there is more bad products
* with this vendor.
*/
+ {
.callback = dmi_low_memory_corruption,
.ident = "AMI BIOS",
.matches = {
DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
},
},
+ {
+ .callback = dmi_low_memory_corruption,
+ .ident = "AMI BIOS",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
+ },
+ },
#endif
{}
};
+static void __init trim_bios_range(void)
+{
+ /*
+ * A special case is the first 4Kb of memory;
+ * This is a BIOS owned area, not kernel ram, but generally
+ * not listed as such in the E820 table.
+ */
+ e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+ /*
+ * special case: Some BIOSen report the PC BIOS
+ * area (640->1Mb) as ram even though it is not.
+ * 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);
+}
+
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
-
+ trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
reserve_brk();
+ /*
+ * Find and reserve possible boot-time SMP configuration:
+ */
+ find_smp_config();
+
+ reserve_trampoline_memory();
+
#ifdef CONFIG_ACPI_SLEEP
/*
* Reserve low memory region for sleep support.
early_acpi_boot_init();
- /*
- * Find and reserve possible boot-time SMP configuration:
- */
- find_smp_config();
-
#ifdef CONFIG_ACPI_NUMA
/*
* Parse SRAT to discover nodes.
#endif
#endif
x86_init.oem.banner();
+
+ mcheck_init();
}
#ifdef CONFIG_X86_32
#include "physaddr.h"
-int page_is_ram(unsigned long pagenr)
-{
- resource_size_t addr, end;
- int i;
-
- /*
- * A special case is the first 4Kb of memory;
- * This is a BIOS owned area, not kernel ram, but generally
- * not listed as such in the E820 table.
- */
- if (pagenr == 0)
- return 0;
-
- /*
- * Second special case: Some BIOSen report the PC BIOS
- * area (640->1Mb) as ram even though it is not.
- */
- if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
- pagenr < (BIOS_END >> PAGE_SHIFT))
- return 0;
-
- for (i = 0; i < e820.nr_map; i++) {
- /*
- * Not usable memory:
- */
- if (e820.map[i].type != E820_RAM)
- continue;
- addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT;
- end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT;
-
-
- if ((pagenr >= addr) && (pagenr < end))
- return 1;
- }
- return 0;
-}
-
/*
* Fix up the linear direct mapping of the kernel to avoid cache attribute
* conflicts.
(unsigned long long)phys_addr,
(unsigned long long)(phys_addr + size),
prot_val, new_prot_val);
- free_memtype(phys_addr, phys_addr + size);
- return NULL;
+ goto err_free_memtype;
}
prot_val = new_prot_val;
}
*/
area = get_vm_area_caller(size, VM_IOREMAP, caller);
if (!area)
- return NULL;
+ goto err_free_memtype;
area->phys_addr = phys_addr;
vaddr = (unsigned long) area->addr;
- if (kernel_map_sync_memtype(phys_addr, size, prot_val)) {
- free_memtype(phys_addr, phys_addr + size);
- free_vm_area(area);
- return NULL;
- }
+ if (kernel_map_sync_memtype(phys_addr, size, prot_val))
+ goto err_free_area;
- if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
- free_memtype(phys_addr, phys_addr + size);
- free_vm_area(area);
- return NULL;
- }
+ if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
+ goto err_free_area;
ret_addr = (void __iomem *) (vaddr + offset);
mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
return ret_addr;
+ err_free_area:
+ free_vm_area(area);
+ err_free_memtype:
+ free_memtype(phys_addr, phys_addr + size);
+ return NULL;
}
/**
}
EXPORT_SYMBOL(ioremap_cache);
- static void __iomem *ioremap_default(resource_size_t phys_addr,
- unsigned long size)
- {
- unsigned long flags;
- void __iomem *ret;
- int err;
-
- /*
- * - WB for WB-able memory and no other conflicting mappings
- * - UC_MINUS for non-WB-able memory with no other conflicting mappings
- * - Inherit from confliting mappings otherwise
- */
- err = reserve_memtype(phys_addr, phys_addr + size,
- _PAGE_CACHE_WB, &flags);
- if (err < 0)
- return NULL;
-
- ret = __ioremap_caller(phys_addr, size, flags,
- __builtin_return_address(0));
-
- free_memtype(phys_addr, phys_addr + size);
- return ret;
- }
-
void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
unsigned long prot_val)
{
if (page_is_ram(start >> PAGE_SHIFT))
return __va(phys);
- addr = (void __force *)ioremap_default(start, PAGE_SIZE);
+ addr = (void __force *)ioremap_cache(start, PAGE_SIZE);
if (addr)
addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));
return atomic_inc_not_zero(&page->_count);
}
+extern int page_is_ram(unsigned long pfn);
+
/* Support for virtually mapped pages */
struct page *vmalloc_to_page(const void *addr);
unsigned long vmalloc_to_pfn(const void *addr);
/*
* On an anonymous page mapped into a user virtual memory area,
* page->mapping points to its anon_vma, not to a struct address_space;
- * with the PAGE_MAPPING_ANON bit set to distinguish it.
+ * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h.
+ *
+ * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
+ * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
+ * and then page->mapping points, not to an anon_vma, but to a private
+ * structure which KSM associates with that merged page. See ksm.h.
+ *
+ * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
*
* Please note that, confusingly, "page_mapping" refers to the inode
* address_space which maps the page from disk; whereas "page_mapped"
* refers to user virtual address space into which the page is mapped.
*/
#define PAGE_MAPPING_ANON 1
+ #define PAGE_MAPPING_KSM 2
+ #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
extern struct address_space swapper_space;
static inline struct address_space *page_mapping(struct page *page)
struct address_space *mapping = page->mapping;
VM_BUG_ON(PageSlab(page));
- #ifdef CONFIG_SWAP
if (unlikely(PageSwapCache(page)))
mapping = &swapper_space;
- else
- #endif
- if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+ else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
mapping = NULL;
return mapping;
}
+ /* Neutral page->mapping pointer to address_space or anon_vma or other */
+ static inline void *page_rmapping(struct page *page)
+ {
+ return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
+ }
+
static inline int PageAnon(struct page *page)
{
return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
* @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
* @pte_entry: if set, called for each non-empty PTE (4th-level) entry
* @pte_hole: if set, called for each hole at all levels
+ * @hugetlb_entry: if set, called for each hugetlb entry
*
* (see walk_page_range for more details)
*/
int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
+ int (*hugetlb_entry)(pte_t *, unsigned long, unsigned long,
+ struct mm_walk *);
struct mm_struct *mm;
void *private;
};
extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
extern void remove_all_active_ranges(void);
+ void sort_node_map(void);
+ unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
+ unsigned long end_pfn);
extern unsigned long absent_pages_in_range(unsigned long start_pfn,
unsigned long end_pfn);
extern void get_pfn_range_for_nid(unsigned int nid,
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
+ extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
/* prio_tree.c */
void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
size_t size);
extern void refund_locked_memory(struct mm_struct *mm, size_t size);
+ enum mf_flags {
+ MF_COUNT_INCREASED = 1 << 0,
+ };
extern void memory_failure(unsigned long pfn, int trapno);
- extern int __memory_failure(unsigned long pfn, int trapno, int ref);
+ extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+ extern int unpoison_memory(unsigned long pfn);
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
+ extern void shake_page(struct page *p, int access);
extern atomic_long_t mce_bad_pages;
+ extern int soft_offline_page(struct page *page, int flags);
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
#endif
+static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
+{
+ return 1;
+}
+/*
+ * This generic page_is_ram() returns true if specified address is
+ * registered as "System RAM" in iomem_resource list.
+ */
+int __weak page_is_ram(unsigned long pfn)
+{
+ return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
+}
+
/*
* Find empty slot in the resource tree given range and alignment.
*/
void *alignf_data)
{
struct resource *this = root->child;
+ struct resource tmp = *new;
- new->start = root->start;
+ tmp.start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
- * of this->start - 1 to new->end below would cause an underflow.
+ * of this->start - 1 to tmp->end below would cause an underflow.
*/
if (this && this->start == 0) {
- new->start = this->end + 1;
+ tmp.start = this->end + 1;
this = this->sibling;
}
for(;;) {
if (this)
- new->end = this->start - 1;
+ tmp.end = this->start - 1;
else
- new->end = root->end;
- if (new->start < min)
- new->start = min;
- if (new->end > max)
- new->end = max;
- new->start = ALIGN(new->start, align);
+ tmp.end = root->end;
+ if (tmp.start < min)
+ tmp.start = min;
+ if (tmp.end > max)
+ tmp.end = max;
+ tmp.start = ALIGN(tmp.start, align);
if (alignf)
- alignf(alignf_data, new, size, align);
- if (new->start < new->end && new->end - new->start >= size - 1) {
- new->end = new->start + size - 1;
+ alignf(alignf_data, &tmp, size, align);
+ if (tmp.start < tmp.end && tmp.end - tmp.start >= size - 1) {
+ new->start = tmp.start;
+ new->end = tmp.start + size - 1;
return 0;
}
if (!this)
break;
- new->start = this->end + 1;
+ tmp.start = this->end + 1;
this = this->sibling;
}
return -EBUSY;