aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/linux/mm.h20
-rw-r--r--mm/memory.c50
-rw-r--r--mm/util.c16
3 files changed, 67 insertions, 19 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 33da7f53884..a880161a385 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -824,8 +824,11 @@ static inline int handle_mm_fault(struct mm_struct *mm,
extern int make_pages_present(unsigned long addr, unsigned long end);
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
-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);
+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);
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+ struct page **pages);
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned long offset);
@@ -850,19 +853,6 @@ extern int mprotect_fixup(struct vm_area_struct *vma,
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
diff --git a/mm/memory.c b/mm/memory.c
index 4126dd16778..891bad0613f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1360,6 +1360,56 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
return i;
}
+/**
+ * get_user_pages() - pin user pages in memory
+ * @tsk: task_struct of target task
+ * @mm: mm_struct of target mm
+ * @start: starting user address
+ * @len: number of pages from start to pin
+ * @write: whether pages will be written to by the caller
+ * @force: whether to force write access even if user mapping is
+ * readonly. This will result in the page being COWed even
+ * in MAP_SHARED mappings. You do not want this.
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If len is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with. vmas will only
+ * remain valid while mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If write=0, the page must not be written to. If the page is written to,
+ * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
+ * after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ */
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)
diff --git a/mm/util.c b/mm/util.c
index abc65aa7cdf..d5d2213728c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -233,13 +233,21 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
* Returns number of pages pinned. This may be fewer than the number
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
+ *
+ * get_user_pages_fast provides equivalent functionality to get_user_pages,
+ * operating on current and current->mm, with force=0 and vma=NULL. However
+ * unlike get_user_pages, it must be called without mmap_sem held.
+ *
+ * get_user_pages_fast may take mmap_sem and page table locks, so no
+ * assumptions can be made about lack of 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 so
+ * callers need to carefully consider what to use. On many architectures,
+ * get_user_pages_fast simply falls back to get_user_pages.
*/
int __attribute__((weak)) get_user_pages_fast(unsigned long start,
int nr_pages, int write, struct page **pages)