mlock: do not hold mmap_sem for extended periods of time

__get_user_pages gets a new 'nonblocking' parameter to signal that the
caller is prepared to re-acquire mmap_sem and retry the operation if
needed.  This is used to split off long operations if they are going to
block on a disk transfer, or when we detect contention on the mmap_sem.

[akpm@linux-foundation.org: remove ref to rwsem_is_contended()]
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 18 insertions, 5 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 15e1f19a3b10..1bbe9a22429c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1363,7 +1363,8 @@ no_page_table:
 
 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)
+                     struct page **pages, struct vm_area_struct **vmas,
+                     int *nonblocking)
 {
         int i;
         unsigned long vm_flags;
@@ -1463,10 +1464,15 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         cond_resched();
                         while (!(page = follow_page(vma, start, foll_flags))) {
                                 int ret;
+                                unsigned int fault_flags = 0;
+
+                                if (foll_flags & FOLL_WRITE)
+                                        fault_flags |= FAULT_FLAG_WRITE;
+                                if (nonblocking)
+                                        fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 
                                 ret = handle_mm_fault(mm, vma, start,
-                                        (foll_flags & FOLL_WRITE) ?
-                                        FAULT_FLAG_WRITE : 0);
+                                                        fault_flags);
 
                                 if (ret & VM_FAULT_ERROR) {
                                         if (ret & VM_FAULT_OOM)
@@ -1482,6 +1488,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                 else
                                         tsk->min_flt++;
 
+                                if (ret & VM_FAULT_RETRY) {
+                                        *nonblocking = 0;
+                                        return i;
+                                }
+
                                 /*
                                  * The VM_FAULT_WRITE bit tells us that
                                  * do_wp_page has broken COW when necessary,
@@ -1581,7 +1592,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
         if (force)
                 flags |= FOLL_FORCE;
 
-        return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
+        return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
+                                NULL);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -1606,7 +1618,8 @@ struct page *get_dump_page(unsigned long addr)
         struct page *page;
 
         if (__get_user_pages(current, current->mm, addr, 1,
-                        FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
+                             FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
+                             NULL) < 1)
                 return NULL;
         flush_cache_page(vma, addr, page_to_pfn(page));
         return page;