#define mm_forbids_zeropage(X) (0)
#endif
+/*
+ * On some architectures it is expensive to call memset() for small sizes.
+ * Those architectures should provide their own implementation of "struct page"
+ * zeroing by defining this macro in <asm/pgtable.h>.
+ */
+#ifndef mm_zero_struct_page
+#define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page)))
+#endif
+
/*
* Default maximum number of active map areas, this limits the number of vmas
* per mm struct. Users can overwrite this number by sysctl but there is a
* mmap() functions).
*/
-extern struct kmem_cache *vm_area_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *);
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
+void vm_area_free(struct vm_area_struct *);
#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
#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_SYNC 0x00800000 /* Synchronous page faults */
#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */
#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */
#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */
struct vm_operations_struct {
void (*open)(struct vm_area_struct * area);
void (*close)(struct vm_area_struct * area);
+ int (*split)(struct vm_area_struct * area, unsigned long addr);
int (*mremap)(struct vm_area_struct * area);
int (*fault)(struct vm_fault *vmf);
int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
+/* 127: arbitrary random number, small enough to assemble well */
+#define page_ref_zero_or_close_to_overflow(page) \
+ ((unsigned int) page_ref_count(page) + 127u <= 127u)
+
static inline void get_page(struct page *page)
{
page = compound_head(page);
* Getting a normal page or the head of a compound page
* requires to already have an elevated page->_refcount.
*/
- VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+ VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page);
page_ref_inc(page);
}
#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */
#define VM_FAULT_DONE_COW 0x1000 /* ->fault has fully handled COW */
-
-#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
+#define VM_FAULT_NEEDDSYNC 0x2000 /* ->fault did not modify page tables
+ * and needs fsync() to complete (for
+ * synchronous page faults in DAX) */
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
{ VM_FAULT_LOCKED, "LOCKED" }, \
{ VM_FAULT_RETRY, "RETRY" }, \
{ VM_FAULT_FALLBACK, "FALLBACK" }, \
- { VM_FAULT_DONE_COW, "DONE_COW" }
+ { VM_FAULT_DONE_COW, "DONE_COW" }, \
+ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }
/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
}
#endif
+extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
+extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
+ int);
+extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
+extern void vma_do_fput(struct vm_area_struct *, const char[], int);
+
+#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \
+ __LINE__)
+#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \
+ __LINE__)
+#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__)
+#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__)
+
+#ifndef CONFIG_MMU
+extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
+extern void vmr_do_fput(struct vm_region *, const char[], int);
+
+#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \
+ __LINE__)
+#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__)
+#endif /* !CONFIG_MMU */
+
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
unsigned int gup_flags);
extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
unsigned int gup_flags, struct page **pages, int *locked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
+#ifdef CONFIG_FS_DAX
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas);
+#else
+static inline long get_user_pages_longterm(unsigned long start,
+ unsigned long nr_pages, unsigned int gup_flags,
+ struct page **pages, struct vm_area_struct **vmas)
+{
+ return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+#endif /* CONFIG_FS_DAX */
+
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
struct bdi_writeback *wb);
int set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
-void cancel_dirty_page(struct page *page);
+void __cancel_dirty_page(struct page *page);
+static inline void cancel_dirty_page(struct page *page)
+{
+ /* Avoid atomic ops, locking, etc. when not actually needed. */
+ if (PageDirty(page))
+ __cancel_dirty_page(page);
+}
int clear_page_dirty_for_io(struct page *page);
int get_cmdline(struct task_struct *task, char *buffer, int buflen);
int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
#endif
-#ifdef __PAGETABLE_PUD_FOLDED
+#if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU)
static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
unsigned long address)
{
return 0;
}
+static inline void mm_inc_nr_puds(struct mm_struct *mm) {}
+static inline void mm_dec_nr_puds(struct mm_struct *mm) {}
+
#else
int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
-#endif
-#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
-static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
- unsigned long address)
+static inline void mm_inc_nr_puds(struct mm_struct *mm)
{
- return 0;
+ if (mm_pud_folded(mm))
+ return;
+ atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
}
-static inline void mm_nr_pmds_init(struct mm_struct *mm) {}
+static inline void mm_dec_nr_puds(struct mm_struct *mm)
+{
+ if (mm_pud_folded(mm))
+ return;
+ atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
+}
+#endif
-static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
+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);
-static inline void mm_nr_pmds_init(struct mm_struct *mm)
+static inline void mm_inc_nr_pmds(struct mm_struct *mm)
{
- atomic_long_set(&mm->nr_pmds, 0);
+ if (mm_pmd_folded(mm))
+ return;
+ atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
}
-static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+static inline void mm_dec_nr_pmds(struct mm_struct *mm)
{
- return atomic_long_read(&mm->nr_pmds);
+ if (mm_pmd_folded(mm))
+ return;
+ atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
}
+#endif
-static inline void mm_inc_nr_pmds(struct mm_struct *mm)
+#ifdef CONFIG_MMU
+static inline void mm_pgtables_bytes_init(struct mm_struct *mm)
{
- atomic_long_inc(&mm->nr_pmds);
+ atomic_long_set(&mm->pgtables_bytes, 0);
}
-static inline void mm_dec_nr_pmds(struct mm_struct *mm)
+static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
{
- atomic_long_dec(&mm->nr_pmds);
+ return atomic_long_read(&mm->pgtables_bytes);
}
+
+static inline void mm_inc_nr_ptes(struct mm_struct *mm)
+{
+ atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
+}
+
+static inline void mm_dec_nr_ptes(struct mm_struct *mm)
+{
+ atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
+}
+#else
+
+static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {}
+static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void mm_inc_nr_ptes(struct mm_struct *mm) {}
+static inline void mm_dec_nr_ptes(struct mm_struct *mm) {}
#endif
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
struct mminit_pfnnid_cache *state);
#endif
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
+void zero_resv_unavail(void);
+#else
+static inline void zero_resv_unavail(void) {}
+#endif
+
extern void set_dma_reserve(unsigned long new_dma_reserve);
extern void memmap_init_zone(unsigned long, int, unsigned long,
unsigned long, enum memmap_context);
return vma;
}
+static inline bool range_in_vma(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ return (vma && vma->vm_start <= start && end <= vma->vm_end);
+}
+
#ifdef CONFIG_MMU
pgprot_t vm_get_page_prot(unsigned long vm_flags);
void vma_set_page_prot(struct vm_area_struct *vma);
#define FOLL_MLOCK 0x1000 /* lock present pages */
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
#define FOLL_COW 0x4000 /* internal GUP flag */
+#define FOLL_ANON 0x8000 /* don't do file mappings */
static inline int vm_fault_to_errno(int vm_fault, int foll_flags)
{
void vmemmap_free(unsigned long start, unsigned long end);
#endif
void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
- unsigned long size);
+ unsigned long nr_pages);
enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
MF_MSG_POISONED_HUGE,
MF_MSG_HUGE,
MF_MSG_FREE_HUGE,
+ MF_MSG_NON_PMD_HUGE,
MF_MSG_UNMAP_FAILED,
MF_MSG_DIRTY_SWAPCACHE,
MF_MSG_CLEAN_SWAPCACHE,