#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
-#include <linux/mutex.h>
#include <linux/debug_locks.h>
-#include <linux/backing-dev.h>
#include <linux/mm_types.h>
struct mempolicy;
#define sysctl_legacy_va_layout 0
#endif
+extern unsigned long mmap_min_addr;
+
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+
/*
* Linux kernel virtual memory manager primitives.
* The idea being to have a "virtual" mm in the same way
#endif
/*
- * vm_flags..
+ * vm_flags in vm_area_struct, see mm_types.h.
*/
#define VM_READ 0x00000001 /* currently active flags */
#define VM_WRITE 0x00000002
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
#define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
+#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */
#define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */
#define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */
#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */
+#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
+#define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
void (*open)(struct vm_area_struct * area);
void (*close)(struct vm_area_struct * area);
int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
- struct page *(*nopage)(struct vm_area_struct *area,
- unsigned long address, int *type);
- unsigned long (*nopfn)(struct vm_area_struct *area,
- unsigned long address);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page);
+
+ /* called by access_process_vm when get_user_pages() fails, typically
+ * for use by special VMAs that can switch between memory and hardware
+ */
+ int (*access)(struct vm_area_struct *vma, unsigned long addr,
+ void *buf, int len, int write);
#ifdef CONFIG_NUMA
+ /*
+ * set_policy() op must add a reference to any non-NULL @new mempolicy
+ * to hold the policy upon return. Caller should pass NULL @new to
+ * remove a policy and fall back to surrounding context--i.e. do not
+ * install a MPOL_DEFAULT policy, nor the task or system default
+ * mempolicy.
+ */
int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
+
+ /*
+ * get_policy() op must add reference [mpol_get()] to any policy at
+ * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure
+ * in mm/mempolicy.c will do this automatically.
+ * get_policy() must NOT add a ref if the policy at (vma,addr) is not
+ * marked as MPOL_SHARED. vma policies are protected by the mmap_sem.
+ * If no [shared/vma] mempolicy exists at the addr, get_policy() op
+ * must return NULL--i.e., do not "fallback" to task or system default
+ * policy.
+ */
struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
unsigned long addr);
int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
*/
static inline int get_page_unless_zero(struct page *page)
{
- VM_BUG_ON(PageCompound(page));
+ VM_BUG_ON(PageTail(page));
return atomic_inc_not_zero(&page->_count);
}
+/* Support for virtually mapped pages */
+struct page *vmalloc_to_page(const void *addr);
+unsigned long vmalloc_to_pfn(const void *addr);
+
+/*
+ * Determine if an address is within the vmalloc range
+ *
+ * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
+ * is no special casing required.
+ */
+static inline int is_vmalloc_addr(const void *x)
+{
+#ifdef CONFIG_MMU
+ unsigned long addr = (unsigned long)x;
+
+ return addr >= VMALLOC_START && addr < VMALLOC_END;
+#else
+ return 0;
+#endif
+}
+
static inline struct page *compound_head(struct page *page)
{
if (unlikely(PageTail(page)))
* we have run out of space and have to fall back to an
* alternate (slower) way of determining the node.
*
- * No sparsemem: | NODE | ZONE | ... | FLAGS |
- * with space for node: | SECTION | NODE | ZONE | ... | FLAGS |
- * no space for node: | SECTION | ZONE | ... | FLAGS |
+ * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS |
+ * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
+ * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS |
*/
-#ifdef CONFIG_SPARSEMEM
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTIONS_WIDTH SECTIONS_SHIFT
#else
#define SECTIONS_WIDTH 0
#define ZONES_WIDTH ZONES_SHIFT
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= FLAGS_RESERVED
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
#define NODES_WIDTH NODES_SHIFT
#else
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#error "Vmemmap: No space for nodes field in page flags"
+#endif
#define NODES_WIDTH 0
#endif
#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0))
-#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
-#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
+#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
+#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
#endif
#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
static inline unsigned long page_to_section(struct page *page)
{
return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
+#endif
static inline void set_page_zone(struct page *page, enum zone_type zone)
{
}
/*
+ * If a hint addr is less than mmap_min_addr change hint to be as
+ * low as possible but still greater than mmap_min_addr
+ */
+static inline unsigned long round_hint_to_min(unsigned long hint)
+{
+#ifdef CONFIG_SECURITY
+ hint &= PAGE_MASK;
+ if (((void *)hint != NULL) &&
+ (hint < mmap_min_addr))
+ return PAGE_ALIGN(mmap_min_addr);
+#endif
+ return hint;
+}
+
+/*
* Some inline functions in vmstat.h depend on page_zone()
*/
#include <linux/vmstat.h>
struct address_space *mapping = page->mapping;
VM_BUG_ON(PageSlab(page));
+#ifdef CONFIG_SWAP
if (unlikely(PageSwapCache(page)))
mapping = &swapper_space;
- else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+ else
+#endif
+ if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
mapping = NULL;
return mapping;
}
}
/*
- * Error return values for the *_nopage functions
- */
-#define NOPAGE_SIGBUS (NULL)
-#define NOPAGE_OOM ((struct page *) (-1))
-
-/*
- * Error return values for the *_nopfn functions
- */
-#define NOPFN_SIGBUS ((unsigned long) -1)
-#define NOPFN_OOM ((unsigned long) -2)
-#define NOPFN_REFAULT ((unsigned long) -3)
-
-/*
* Different kinds of faults, as returned by handle_mm_fault().
* Used to decide whether a process gets delivered SIGBUS or
* just gets major/minor fault counters bumped up.
extern void show_free_areas(void);
#ifdef CONFIG_SHMEM
-int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new);
-struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
- unsigned long addr);
int shmem_lock(struct file *file, int lock, struct user_struct *user);
#else
static inline int shmem_lock(struct file *file, int lock,
{
return 0;
}
-
-static inline int shmem_set_policy(struct vm_area_struct *vma,
- struct mempolicy *new)
-{
- return 0;
-}
-
-static inline struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
- unsigned long addr)
-{
- return NULL;
-}
#endif
struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags);
unsigned long truncate_count; /* Compare vm_truncate_count */
};
-struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t);
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ pte_t pte);
+
+int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
+ unsigned long size);
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *);
unsigned long unmap_vmas(struct mmu_gather **tlb,
struct vm_area_struct *start_vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *);
-void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
+
+/**
+ * mm_walk - callbacks for walk_page_range
+ * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
+ * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
+ * @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
+ *
+ * (see walk_page_range for more details)
+ */
+struct mm_walk {
+ int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *);
+ int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *);
+ 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 *);
+ struct mm_struct *mm;
+ void *private;
+};
+
+int walk_page_range(unsigned long addr, unsigned long end,
+ struct mm_walk *walk);
+void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
unsigned long end, unsigned long floor, unsigned long ceiling);
-void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,
- unsigned long floor, unsigned long ceiling);
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma);
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows);
+int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
+ void *buf, int len, int write);
static inline void unmap_shared_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen)
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
-void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned long offset);
int __set_page_dirty_no_writeback(struct page *page);
int redirty_page_for_writepage(struct writeback_control *wbc,
struct page *page);
-int FASTCALL(set_page_dirty(struct page *page));
+int set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);
unsigned long end, unsigned long newflags);
/*
+ * get_user_pages_fast provides equivalent functionality to get_user_pages,
+ * operating on current and current->mm (force=0 and doesn't return any vmas).
+ *
+ * get_user_pages_fast may take mmap_sem and page tables, so no assumptions
+ * can be made about locking. get_user_pages_fast is to be implemented in a
+ * way that is advantageous (vs get_user_pages()) when the user memory area is
+ * already faulted in and present in ptes. However if the pages have to be
+ * faulted in, it may turn out to be slightly slower).
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+ struct page **pages);
+
+/*
* A callback you can register to apply pressure to ageable caches.
*
* 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should
int vma_wants_writenotify(struct vm_area_struct *vma);
-extern pte_t *FASTCALL(get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl));
+extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl);
#ifdef __PAGETABLE_PUD_FOLDED
static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
#define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;})
#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+static inline void pgtable_page_ctor(struct page *page)
+{
+ pte_lock_init(page);
+ inc_zone_page_state(page, NR_PAGETABLE);
+}
+
+static inline void pgtable_page_dtor(struct page *page)
+{
+ pte_lock_deinit(page);
+ dec_zone_page_state(page, NR_PAGETABLE);
+}
+
#define pte_offset_map_lock(mm, pmd, address, ptlp) \
({ \
spinlock_t *__ptl = pte_lockptr(mm, pmd); \
NULL: pte_offset_kernel(pmd, address))
extern void free_area_init(unsigned long * zones_size);
-extern void free_area_init_node(int nid, pg_data_t *pgdat,
- unsigned long * zones_size, unsigned long zone_start_pfn,
- unsigned long *zholes_size);
+extern void free_area_init_node(int nid, unsigned long * zones_size,
+ unsigned long zone_start_pfn, unsigned long *zholes_size);
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
* With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
extern void free_area_init_nodes(unsigned long *max_zone_pfn);
extern void add_active_range(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
-extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
- unsigned long new_end_pfn);
+extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
+ unsigned long end_pfn);
extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
extern void remove_all_active_ranges(void);
extern void get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn);
extern unsigned long find_min_pfn_with_active_regions(void);
-extern unsigned long find_max_pfn_with_active_regions(void);
extern void free_bootmem_with_active_regions(int nid,
unsigned long max_low_pfn);
+typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
+extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
extern void sparse_memory_present_with_active_regions(int nid);
#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
extern int early_pfn_to_nid(unsigned long pfn);
extern void show_mem(void);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);
+extern int after_bootmem;
#ifdef CONFIG_NUMA
extern void setup_per_cpu_pageset(void);
extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
unsigned long addr, unsigned long len, pgoff_t pgoff);
extern void exit_mmap(struct mm_struct *);
+
+extern int mm_take_all_locks(struct mm_struct *mm);
+extern void mm_drop_all_locks(struct mm_struct *mm);
+
+#ifdef CONFIG_PROC_FS
+/* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */
+extern void added_exe_file_vma(struct mm_struct *mm);
+extern void removed_exe_file_vma(struct mm_struct *mm);
+#else
+static inline void added_exe_file_vma(struct mm_struct *mm)
+{}
+
+static inline void removed_exe_file_vma(struct mm_struct *mm)
+{}
+#endif /* CONFIG_PROC_FS */
+
extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
extern int install_special_mapping(struct mm_struct *mm,
unsigned long addr, unsigned long len,
pgprot_t vm_get_page_prot(unsigned long vm_flags);
struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
-struct page *vmalloc_to_page(void *addr);
-unsigned long vmalloc_to_pfn(void *addr);
int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t);
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
+int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn);
struct page *follow_page(struct vm_area_struct *, unsigned long address,
unsigned int foll_flags);
#define FOLL_GET 0x04 /* do get_page on page */
#define FOLL_ANON 0x08 /* give ZERO_PAGE if no pgtable */
-typedef int (*pte_fn_t)(pte_t *pte, struct page *pmd_page, unsigned long addr,
+typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
unsigned long size, pte_fn_t fn, void *data);
}
#endif /* CONFIG_PROC_FS */
-#ifndef CONFIG_DEBUG_PAGEALLOC
+#ifdef CONFIG_DEBUG_PAGEALLOC
+extern int debug_pagealloc_enabled;
+
+extern void kernel_map_pages(struct page *page, int numpages, int enable);
+
+static inline void enable_debug_pagealloc(void)
+{
+ debug_pagealloc_enabled = 1;
+}
+#ifdef CONFIG_HIBERNATION
+extern bool kernel_page_present(struct page *page);
+#endif /* CONFIG_HIBERNATION */
+#else
static inline void
kernel_map_pages(struct page *page, int numpages, int enable) {}
+static inline void enable_debug_pagealloc(void)
+{
+}
+#ifdef CONFIG_HIBERNATION
+static inline bool kernel_page_present(struct page *page) { return true; }
+#endif /* CONFIG_HIBERNATION */
#endif
extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
void __user *, size_t *, loff_t *);
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
unsigned long lru_pages);
-void drop_pagecache(void);
-void drop_slab(void);
#ifndef CONFIG_MMU
#define randomize_va_space 0
#endif
const char * arch_vma_name(struct vm_area_struct *vma);
+void print_vma_addr(char *prefix, unsigned long rip);
struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
int vmemmap_populate_basepages(struct page *start_page,
unsigned long pages, int node);
int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
+void vmemmap_populate_print_last(void);
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */