summaryrefslogtreecommitdiff
path: root/include/linux/mm.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/mm.h')
-rw-r--r--include/linux/mm.h164
1 files changed, 106 insertions, 58 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3ef2050ba..3ce30ef53 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -22,6 +22,7 @@
#include <linux/resource.h>
#include <linux/page_ext.h>
#include <linux/err.h>
+#include <linux/page_ref.h>
struct mempolicy;
struct anon_vma;
@@ -82,6 +83,27 @@ extern int mmap_rnd_compat_bits __read_mostly;
#define mm_forbids_zeropage(X) (0)
#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
+ * problem.
+ *
+ * When a program's coredump is generated as ELF format, a section is created
+ * per a vma. In ELF, the number of sections is represented in unsigned short.
+ * This means the number of sections should be smaller than 65535 at coredump.
+ * Because the kernel adds some informative sections to a image of program at
+ * generating coredump, we need some margin. The number of extra sections is
+ * 1-3 now and depends on arch. We use "5" as safe margin, here.
+ *
+ * ELF extended numbering allows more than 65535 sections, so 16-bit bound is
+ * not a hard limit any more. Although some userspace tools can be surprised by
+ * that.
+ */
+#define MAPCOUNT_ELF_CORE_MARGIN (5)
+#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
+
+extern int sysctl_max_map_count;
+
extern unsigned long sysctl_user_reserve_kbytes;
extern unsigned long sysctl_admin_reserve_kbytes;
@@ -122,6 +144,7 @@ extern unsigned int kobjsize(const void *objp);
/*
* vm_flags in vm_area_struct, see mm_types.h.
+ * When changing, update also include/trace/events/mmflags.h
*/
#define VM_NONE 0x00000000
@@ -170,8 +193,26 @@ extern unsigned int kobjsize(const void *objp);
#define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */
#define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */
+#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
+#define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0)
+#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1)
+#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2)
+#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3)
+#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
+
#if defined(CONFIG_X86)
# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */
+#if defined (CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)
+# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0
+# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */
+# define VM_PKEY_BIT1 VM_HIGH_ARCH_1
+# define VM_PKEY_BIT2 VM_HIGH_ARCH_2
+# define VM_PKEY_BIT3 VM_HIGH_ARCH_3
+#endif
#elif defined(CONFIG_PPC)
# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */
#elif defined(CONFIG_PARISC)
@@ -233,6 +274,8 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */
#define FAULT_FLAG_TRIED 0x20 /* Second try */
#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
+#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
+#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -364,8 +407,8 @@ static inline int pmd_devmap(pmd_t pmd)
*/
static inline int put_page_testzero(struct page *page)
{
- VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0, page);
- return atomic_dec_and_test(&page->_count);
+ VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+ return page_ref_dec_and_test(page);
}
/*
@@ -376,7 +419,7 @@ static inline int put_page_testzero(struct page *page)
*/
static inline int get_page_unless_zero(struct page *page)
{
- return atomic_inc_not_zero(&page->_count);
+ return page_ref_add_unless(page, 1, 0);
}
extern int page_is_ram(unsigned long pfn);
@@ -387,7 +430,8 @@ enum {
REGION_MIXED,
};
-int region_intersects(resource_size_t offset, size_t size, const char *type);
+int region_intersects(resource_size_t offset, size_t size, unsigned long flags,
+ unsigned long desc);
/* Support for virtually mapped pages */
struct page *vmalloc_to_page(const void *addr);
@@ -456,17 +500,21 @@ static inline int page_mapcount(struct page *page)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
int total_mapcount(struct page *page);
+int page_trans_huge_mapcount(struct page *page, int *total_mapcount);
#else
static inline int total_mapcount(struct page *page)
{
return page_mapcount(page);
}
-#endif
-
-static inline int page_count(struct page *page)
+static inline int page_trans_huge_mapcount(struct page *page,
+ int *total_mapcount)
{
- return atomic_read(&compound_head(page)->_count);
+ int mapcount = page_mapcount(page);
+ if (total_mapcount)
+ *total_mapcount = mapcount;
+ return mapcount;
}
+#endif
static inline struct page *virt_to_head_page(const void *x)
{
@@ -475,15 +523,6 @@ static inline struct page *virt_to_head_page(const void *x)
return compound_head(page);
}
-/*
- * Setup the page count before being freed into the page allocator for
- * the first time (boot or memory hotplug)
- */
-static inline void init_page_count(struct page *page)
-{
- atomic_set(&page->_count, 1);
-}
-
void __put_page(struct page *page);
void put_pages_list(struct list_head *pages);
@@ -593,7 +632,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
*
* A page may belong to an inode's memory mapping. In this case, page->mapping
* is the pointer to the inode, and page->index is the file offset of the page,
- * in units of PAGE_CACHE_SIZE.
+ * in units of PAGE_SIZE.
*
* If pagecache pages are not associated with an inode, they are said to be
* anonymous pages. These may become associated with the swapcache, and in that
@@ -693,8 +732,8 @@ static inline void get_page(struct page *page)
* Getting a normal page or the head of a compound page
* requires to already have an elevated page->_count.
*/
- VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
- atomic_inc(&page->_count);
+ VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+ page_ref_inc(page);
if (unlikely(is_zone_device_page(page)))
get_zone_device_page(page);
@@ -904,20 +943,11 @@ static inline struct mem_cgroup *page_memcg(struct page *page)
{
return page->mem_cgroup;
}
-
-static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
-{
- page->mem_cgroup = memcg;
-}
#else
static inline struct mem_cgroup *page_memcg(struct page *page)
{
return NULL;
}
-
-static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
-{
-}
#endif
/*
@@ -1053,8 +1083,6 @@ static inline void clear_page_pfmemalloc(struct page *page)
* just gets major/minor fault counters bumped up.
*/
-#define VM_FAULT_MINOR 0 /* For backwards compat. Remove me quickly. */
-
#define VM_FAULT_OOM 0x0001
#define VM_FAULT_SIGBUS 0x0002
#define VM_FAULT_MAJOR 0x0004
@@ -1115,6 +1143,8 @@ struct zap_details {
struct address_space *check_mapping; /* Check page->mapping if set */
pgoff_t first_index; /* Lowest page->index to unmap */
pgoff_t last_index; /* Highest page->index to unmap */
+ bool ignore_dirty; /* Ignore dirty pages */
+ bool check_swap_entries; /* Check also swap entries */
};
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1251,20 +1281,20 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int foll_flags, struct page **pages,
struct vm_area_struct **vmas, int *nonblocking);
-long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
- struct vm_area_struct **vmas);
-long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
- int *locked);
+long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ struct vm_area_struct **vmas);
+long get_user_pages(unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ struct vm_area_struct **vmas);
+long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages, int *locked);
long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
int write, int force, struct page **pages,
unsigned int gup_flags);
-long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, unsigned long nr_pages,
+long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
int write, int force, struct page **pages);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
@@ -1325,10 +1355,9 @@ int __set_page_dirty_nobuffers(struct page *page);
int __set_page_dirty_no_writeback(struct page *page);
int redirty_page_for_writepage(struct writeback_control *wbc,
struct page *page);
-void account_page_dirtied(struct page *page, struct address_space *mapping,
- struct mem_cgroup *memcg);
+void account_page_dirtied(struct page *page, struct address_space *mapping);
void account_page_cleaned(struct page *page, struct address_space *mapping,
- struct mem_cgroup *memcg, struct bdi_writeback *wb);
+ 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);
@@ -1558,8 +1587,7 @@ static inline void mm_dec_nr_pmds(struct mm_struct *mm)
}
#endif
-int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
- pmd_t *pmd, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
/*
@@ -1685,15 +1713,15 @@ static inline void pgtable_page_dtor(struct page *page)
pte_unmap(pte); \
} while (0)
-#define pte_alloc_map(mm, vma, pmd, address) \
- ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma, \
- pmd, address))? \
- NULL: pte_offset_map(pmd, address))
+#define pte_alloc(mm, pmd, address) \
+ (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd, address))
+
+#define pte_alloc_map(mm, pmd, address) \
+ (pte_alloc(mm, pmd, address) ? NULL : pte_offset_map(pmd, address))
#define pte_alloc_map_lock(mm, pmd, address, ptlp) \
- ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL, \
- pmd, address))? \
- NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
+ (pte_alloc(mm, pmd, address) ? \
+ NULL : pte_offset_map_lock(mm, pmd, address, ptlp))
#define pte_alloc_kernel(pmd, address) \
((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
@@ -1776,7 +1804,7 @@ extern void free_highmem_page(struct page *page);
extern void adjust_managed_page_count(struct page *page, long count);
extern void mem_init_print_info(const char *str);
-extern void reserve_bootmem_region(unsigned long start, unsigned long end);
+extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
/* Free the reserved page into the buddy system, so it gets managed. */
static inline void __free_reserved_page(struct page *page)
@@ -1888,6 +1916,7 @@ extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
extern void __init mmap_init(void);
extern void show_mem(unsigned int flags);
+extern long si_mem_available(void);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);
@@ -1902,6 +1931,7 @@ extern void zone_pcp_reset(struct zone *zone);
/* page_alloc.c */
extern int min_free_kbytes;
+extern int watermark_scale_factor;
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
@@ -2164,6 +2194,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
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_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, pgprot_t pgprot);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn);
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
@@ -2194,6 +2226,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */
#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */
#define FOLL_MLOCK 0x1000 /* lock present pages */
+#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
@@ -2201,6 +2234,17 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
unsigned long size, pte_fn_t fn, void *data);
+#ifdef CONFIG_PAGE_POISONING
+extern bool page_poisoning_enabled(void);
+extern void kernel_poison_pages(struct page *page, int numpages, int enable);
+extern bool page_is_poisoned(struct page *page);
+#else
+static inline bool page_poisoning_enabled(void) { return false; }
+static inline void kernel_poison_pages(struct page *page, int numpages,
+ int enable) { }
+static inline bool page_is_poisoned(struct page *page) { return false; }
+#endif
+
#ifdef CONFIG_DEBUG_PAGEALLOC
extern bool _debug_pagealloc_enabled;
extern void __kernel_map_pages(struct page *page, int numpages, int enable);
@@ -2220,14 +2264,18 @@ kernel_map_pages(struct page *page, int numpages, int enable)
}
#ifdef CONFIG_HIBERNATION
extern bool kernel_page_present(struct page *page);
-#endif /* CONFIG_HIBERNATION */
-#else
+#endif /* CONFIG_HIBERNATION */
+#else /* CONFIG_DEBUG_PAGEALLOC */
static inline void
kernel_map_pages(struct page *page, int numpages, int enable) {}
#ifdef CONFIG_HIBERNATION
static inline bool kernel_page_present(struct page *page) { return true; }
-#endif /* CONFIG_HIBERNATION */
-#endif
+#endif /* CONFIG_HIBERNATION */
+static inline bool debug_pagealloc_enabled(void)
+{
+ return false;
+}
+#endif /* CONFIG_DEBUG_PAGEALLOC */
#ifdef __HAVE_ARCH_GATE_AREA
extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);