mm: export __get_user_pages

In most cases, get_user_pages and get_user_pages_fast should be used
to pin user pages in memory.  But sometimes, some special flags except
FOLL_GET, FOLL_WRITE and FOLL_FORCE are needed, for example in
following patch, KVM needs FOLL_HWPOISON.  To support these users,
__get_user_pages is exported directly.

There are some symbol name conflicts in infiniband driver, fixed them too.

Signed-off-by: Huang Ying <ying.huang@intel.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Michel Lespinasse <walken@google.com>
CC: Roland Dreier <roland@kernel.org>
CC: Ralph Campbell <infinipath@qlogic.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

5 files changed, 60 insertions, 11 deletions

diff --git a/drivers/infiniband/hw/ipath/ipath_user_pages.c b/drivers/infiniband/hw/ipath/ipath_user_pages.c
index bab9f74c0665..cfed5399f074 100644
--- a/drivers/infiniband/hw/ipath/ipath_user_pages.c
+++ b/drivers/infiniband/hw/ipath/ipath_user_pages.c
@@ -53,8 +53,8 @@ static void __ipath_release_user_pages(struct page **p, size_t num_pages,
 }
 
 /* call with current->mm->mmap_sem held */
-static int __get_user_pages(unsigned long start_page, size_t num_pages,
-                        struct page **p, struct vm_area_struct **vma)
+static int __ipath_get_user_pages(unsigned long start_page, size_t num_pages,
+                                  struct page **p, struct vm_area_struct **vma)
 {
         unsigned long lock_limit;
         size_t got;
@@ -165,7 +165,7 @@ int ipath_get_user_pages(unsigned long start_page, size_t num_pages,
 
         down_write(&current->mm->mmap_sem);
 
-        ret = __get_user_pages(start_page, num_pages, p, NULL);
+        ret = __ipath_get_user_pages(start_page, num_pages, p, NULL);
 
         up_write(&current->mm->mmap_sem);
 
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index d7a26c1d4f37..7689e49c13c9 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -51,8 +51,8 @@ static void __qib_release_user_pages(struct page **p, size_t num_pages,
 /*
  * Call with current->mm->mmap_sem held.
  */
-static int __get_user_pages(unsigned long start_page, size_t num_pages,
-                            struct page **p, struct vm_area_struct **vma)
+static int __qib_get_user_pages(unsigned long start_page, size_t num_pages,
+                                struct page **p, struct vm_area_struct **vma)
 {
         unsigned long lock_limit;
         size_t got;
@@ -136,7 +136,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 
         down_write(&current->mm->mmap_sem);
 
-        ret = __get_user_pages(start_page, num_pages, p, NULL);
+        ret = __qib_get_user_pages(start_page, num_pages, p, NULL);
 
         up_write(&current->mm->mmap_sem);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 679300c050f5..46150c66318e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -965,6 +965,10 @@ 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, unsigned int foll_flags,
+                     struct page **pages, struct vm_area_struct **vmas,
+                     int *nonblocking);
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         unsigned long start, int nr_pages, int write, int force,
                         struct page **pages, struct vm_area_struct **vmas);
diff --git a/mm/internal.h b/mm/internal.h
index 69488205723d..3438dd43a062 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -245,11 +245,6 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 }
 #endif /* CONFIG_SPARSEMEM */
 
-int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-                     unsigned long start, int len, unsigned int foll_flags,
-                     struct page **pages, struct vm_area_struct **vmas,
-                     int *nonblocking);
-
 #define ZONE_RECLAIM_NOSCAN     -2
 #define ZONE_RECLAIM_FULL       -1
 #define ZONE_RECLAIM_SOME       0
diff --git a/mm/memory.c b/mm/memory.c
index 5823698c2b71..806a37ec71bd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1410,6 +1410,55 @@ no_page_table:
         return page;
 }
 
+/**
+ * __get_user_pages() - pin user pages in memory
+ * @tsk:        task_struct of target task
+ * @mm:         mm_struct of target mm
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @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.
+ * @nonblocking: whether waiting for disk IO or mmap_sem contention
+ *
+ * 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. 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 @gup_flags & FOLL_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.
+ *
+ * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
+ * or mmap_sem contention, and if waiting is needed to pin all pages,
+ * *@nonblocking will be set to 0.
+ *
+ * In most cases, get_user_pages or get_user_pages_fast should be used
+ * instead of __get_user_pages. __get_user_pages should be used only if
+ * you need some special @gup_flags.
+ */
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                      unsigned long start, int nr_pages, unsigned int gup_flags,
                      struct page **pages, struct vm_area_struct **vmas,
@@ -1578,6 +1627,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
         } while (nr_pages);
         return i;
 }
+EXPORT_SYMBOL(__get_user_pages);
 
 /**
  * get_user_pages() - pin user pages in memory