#ifndef _LINUX_MM_H
#define _LINUX_MM_H
-#include <linux/sched.h>
#include <linux/errno.h>
-#include <linux/capability.h>
#ifdef __KERNEL__
struct mempolicy;
struct anon_vma;
+struct user_struct;
#ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
extern unsigned long num_physpages;
extern void * high_memory;
-extern unsigned long vmalloc_earlyreserve;
extern int page_cluster;
#ifdef CONFIG_SYSCTL
#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */
#define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */
+#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */
+
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif
*/
extern pgprot_t protection_map[16];
+#define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */
+#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */
+
+
+#define FAULT_RET_NOPAGE 0x0100 /* ->fault did not return a page. This
+ * can be used if the handler installs
+ * their own pte.
+ */
+#define FAULT_RET_LOCKED 0x0200 /* ->fault locked the page, caller must
+ * unlock after installing the mapping.
+ * This is used by pagecache in
+ * particular, where the page lock is
+ * used to synchronise against truncate
+ * and invalidate. Mutually exclusive
+ * with FAULT_RET_NOPAGE.
+ */
+
+/*
+ * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * ->fault function. The vma's ->fault is responsible for returning the
+ * VM_FAULT_xxx type which occupies the lowest byte of the return code, ORed
+ * with FAULT_RET_ flags that occupy the next byte and give details about
+ * how the fault was handled.
+ *
+ * pgoff should be used in favour of virtual_address, if possible. If pgoff
+ * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear
+ * mapping support.
+ */
+struct vm_fault {
+ unsigned int flags; /* FAULT_FLAG_xxx flags */
+ pgoff_t pgoff; /* Logical page offset based on vma */
+ void __user *virtual_address; /* Faulting virtual address */
+
+ struct page *page; /* ->fault handlers should return a
+ * page here, unless FAULT_RET_NOPAGE
+ * is set (which is also implied by
+ * VM_FAULT_OOM or SIGBUS).
+ */
+};
/*
* These are the virtual MM functions - opening of an area, closing and
struct vm_operations_struct {
void (*open)(struct vm_area_struct * area);
void (*close)(struct vm_area_struct * area);
- struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
- unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address);
- int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
+ 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 */
return atomic_inc_not_zero(&page->_count);
}
+static inline struct page *compound_head(struct page *page)
+{
+ if (unlikely(PageTail(page)))
+ return page->first_page;
+ return page;
+}
+
static inline int page_count(struct page *page)
{
- if (unlikely(PageCompound(page)))
- page = (struct page *)page_private(page);
- return atomic_read(&page->_count);
+ return atomic_read(&compound_head(page)->_count);
}
static inline void get_page(struct page *page)
{
- if (unlikely(PageCompound(page)))
- page = (struct page *)page_private(page);
+ page = compound_head(page);
VM_BUG_ON(atomic_read(&page->_count) == 0);
atomic_inc(&page->_count);
}
+static inline struct page *virt_to_head_page(const void *x)
+{
+ struct page *page = virt_to_page(x);
+ return compound_head(page);
+}
+
/*
* Setup the page count before being freed into the page allocator for
* the first time (boot or memory hotplug)
return (compound_page_dtor *)page[1].lru.next;
}
+static inline int compound_order(struct page *page)
+{
+ if (!PageHead(page))
+ return 0;
+ return (unsigned long)page[1].lru.prev;
+}
+
+static inline void set_compound_order(struct page *page, unsigned long order)
+{
+ page[1].lru.prev = (void *)order;
+}
+
/*
* Multiple processes may "see" the same page. E.g. for untouched
* mappings of /dev/null, all processes see the same page full of
{
struct address_space *mapping = page->mapping;
+ VM_BUG_ON(PageSlab(page));
if (unlikely(PageSwapCache(page)))
mapping = &swapper_space;
+#ifdef CONFIG_SLUB
+ else if (unlikely(PageSlab(page)))
+ mapping = NULL;
+#endif
else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
mapping = NULL;
return mapping;
*/
#define NOPAGE_SIGBUS (NULL)
#define NOPAGE_OOM ((struct page *) (-1))
-#define NOPAGE_REFAULT ((struct page *) (-2)) /* Return to userspace, rerun */
/*
* Error return values for the *_nopfn functions
* Used to decide whether a process gets delivered SIGBUS or
* just gets major/minor fault counters bumped up.
*/
-#define VM_FAULT_OOM 0x00
-#define VM_FAULT_SIGBUS 0x01
+
+/*
+ * VM_FAULT_ERROR is set for the error cases, to make some tests simpler.
+ */
+#define VM_FAULT_ERROR 0x20
+
+#define VM_FAULT_OOM (0x00 | VM_FAULT_ERROR)
+#define VM_FAULT_SIGBUS (0x01 | VM_FAULT_ERROR)
#define VM_FAULT_MINOR 0x02
#define VM_FAULT_MAJOR 0x03
*/
#define VM_FAULT_WRITE 0x10
+/*
+ * Mask of VM_FAULT_ flags
+ */
+#define VM_FAULT_MASK 0xff
+
#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
extern void show_free_areas(void);
unsigned long flags);
#endif
-static inline int can_do_mlock(void)
-{
- if (capable(CAP_IPC_LOCK))
- return 1;
- if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
- return 1;
- return 0;
-}
+extern int can_do_mlock(void);
extern int user_shm_lock(size_t, struct user_struct *);
extern void user_shm_unlock(size_t, struct user_struct *);
extern int vmtruncate(struct inode * inode, loff_t offset);
extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
-extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
-extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
#ifdef CONFIG_MMU
extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,
unsigned long flags, unsigned long new_addr);
/*
- * Prototype to add a shrinker callback for ageable caches.
- *
- * These functions are passed a count `nr_to_scan' and a gfpmask. They should
- * scan `nr_to_scan' objects, attempting to free them.
+ * A callback you can register to apply pressure to ageable caches.
*
- * The callback must return the number of objects which remain in the cache.
+ * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should
+ * look through the least-recently-used 'nr_to_scan' entries and
+ * attempt to free them up. It should return the number of objects
+ * which remain in the cache. If it returns -1, it means it cannot do
+ * any scanning at this time (eg. there is a risk of deadlock).
*
- * The callback will be passed nr_to_scan == 0 when the VM is querying the
- * cache size, so a fastpath for that case is appropriate.
- */
-typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask);
-
-/*
- * Add an aging callback. The int is the number of 'seeks' it takes
- * to recreate one of the objects that these functions age.
+ * The 'gfpmask' refers to the allocation we are currently trying to
+ * fulfil.
+ *
+ * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
+ * querying the cache size, so a fastpath for that case is appropriate.
*/
+struct shrinker {
+ int (*shrink)(int nr_to_scan, gfp_t gfp_mask);
+ int seeks; /* seeks to recreate an obj */
-#define DEFAULT_SEEKS 2
-struct shrinker;
-extern struct shrinker *set_shrinker(int, shrinker_t);
-extern void remove_shrinker(struct shrinker *shrinker);
+ /* These are for internal use */
+ struct list_head list;
+ long nr; /* objs pending delete */
+};
+#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
+extern void register_shrinker(struct shrinker *);
+extern void unregister_shrinker(struct shrinker *);
/*
* Some shared mappigns will want the pages marked read-only
extern pte_t *FASTCALL(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,
+ unsigned long address)
+{
+ return 0;
+}
+#else
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+#endif
+
+#ifdef __PAGETABLE_PMD_FOLDED
+static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
+ unsigned long address)
+{
+ return 0;
+}
+#else
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+#endif
+
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff);
+extern unsigned long mmap_region(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long flags,
+ unsigned int vm_flags, unsigned long pgoff,
+ int accountable);
static inline unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
loff_t lstart, loff_t lend);
/* generic vm_area_ops exported for stackable file systems */
-extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
-extern int filemap_populate(struct vm_area_struct *, unsigned long,
- unsigned long, pgprot_t, unsigned long, int);
+extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
/* mm/page-writeback.c */
int write_one_page(struct page *page, int wait);
#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,
+ void *data);
+extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
+ unsigned long size, pte_fn_t fn, void *data);
+
#ifdef CONFIG_PROC_FS
void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
#else
projects / deliverable / linux.git / blobdiff