splice: use get_user_pages_fast

Use get_user_pages_fast in splice.  This reverts some mmap_sem batching
there, however the biggest problem with mmap_sem tends to be hold times
blocking out other threads rather than cacheline bouncing.  Further: on
architectures that implement get_user_pages_fast without locks, mmap_sem
can be avoided completely anyway.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Dave Kleikamp <shaggy@austin.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Dave Kleikamp <shaggy@austin.ibm.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Cc: Zach Brown <zach.brown@oracle.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/splice.c b/fs/splice.c
index 3994421..47dc1a4 100644 (file)
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1161,36 +1161,6 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 }
 
 /*
- * Do a copy-from-user while holding the mmap_semaphore for reading, in a
- * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
- * for writing) and page faulting on the user memory pointed to by src.
- * This assumes that we will very rarely hit the partial != 0 path, or this
- * will not be a win.
- */
-static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
-{
-       int partial;
-
-       if (!access_ok(VERIFY_READ, src, n))
-               return -EFAULT;
-
-       pagefault_disable();
-       partial = __copy_from_user_inatomic(dst, src, n);
-       pagefault_enable();
-
-       /*
-        * Didn't copy everything, drop the mmap_sem and do a faulting copy
-        */
-       if (unlikely(partial)) {
-               up_read(&current->mm->mmap_sem);
-               partial = copy_from_user(dst, src, n);
-               down_read(&current->mm->mmap_sem);
-       }
-
-       return partial;
-}
-
-/*
  * Map an iov into an array of pages and offset/length tupples. With the
  * partial_page structure, we can map several non-contiguous ranges into
  * our ones pages[] map instead of splitting that operation into pieces.
@@ -1203,8 +1173,6 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 {
        int buffers = 0, error = 0;
 
-       down_read(&current->mm->mmap_sem);
-
        while (nr_vecs) {
                unsigned long off, npages;
                struct iovec entry;
@@ -1213,7 +1181,7 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                int i;
 
                error = -EFAULT;
-               if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
+               if (copy_from_user(&entry, iov, sizeof(entry)))
                        break;
 
                base = entry.iov_base;
@@ -1247,9 +1215,8 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                if (npages > PIPE_BUFFERS - buffers)
                        npages = PIPE_BUFFERS - buffers;
 
-               error = get_user_pages(current, current->mm,
-                                      (unsigned long) base, npages, 0, 0,
-                                      &pages[buffers], NULL);
+               error = get_user_pages_fast((unsigned long)base, npages,
+                                       0, &pages[buffers]);
 
                if (unlikely(error <= 0))
                        break;
@@ -1288,8 +1255,6 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                iov++;
        }
 
-       up_read(&current->mm->mmap_sem);
-
        if (buffers)
                return buffers;