do_mpage_readpage(): don't submit lots of small bios on boundary

[safe/jmp/linux-2.6] / fs / splice.c

diff --git a/fs/splice.c b/fs/splice.c
index aa5f6f6..1abab5c 100644 (file)
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -371,7 +371,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                         * for an in-flight io page
                         */
                        if (flags & SPLICE_F_NONBLOCK) {
-                               if (TestSetPageLocked(page)) {
+                               if (!trylock_page(page)) {
                                        error = -EAGAIN;
                                        break;
                                }
@@ -379,13 +379,22 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                                lock_page(page);
 
                        /*
-                        * page was truncated, stop here. if this isn't the
-                        * first page, we'll just complete what we already
-                        * added
+                        * Page was truncated, or invalidated by the
+                        * filesystem.  Redo the find/create, but this time the
+                        * page is kept locked, so there's no chance of another
+                        * race with truncate/invalidate.
                         */
                        if (!page->mapping) {
                                unlock_page(page);
-                               break;
+                               page = find_or_create_page(mapping, index,
+                                               mapping_gfp_mask(mapping));
+
+                               if (!page) {
+                                       error = -ENOMEM;
+                                       break;
+                               }
+                               page_cache_release(pages[page_nr]);
+                               pages[page_nr] = page;
                        }
                        /*
                         * page was already under io and is now done, great
@@ -722,8 +731,8 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
        };
 
        /*
-        * The actor worker might be calling ->prepare_write and
-        * ->commit_write. Most of the time, these expect i_mutex to
+        * The actor worker might be calling ->write_begin and
+        * ->write_end. Most of the time, these expect i_mutex to
         * be held. Since this may result in an ABBA deadlock with
         * pipe->inode, we have to order lock acquiry here.
         */
@@ -763,7 +772,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out,
        ssize_t ret;
        int err;
 
-       err = remove_suid(out->f_path.dentry);
+       err = file_remove_suid(out);
        if (unlikely(err))
                return err;
 
@@ -821,7 +830,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
        ssize_t ret;
 
        inode_double_lock(inode, pipe->inode);
-       ret = remove_suid(out->f_path.dentry);
+       ret = file_remove_suid(out);
        if (likely(!ret))
                ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
        inode_double_unlock(inode, pipe->inode);
@@ -889,6 +898,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
        if (unlikely(!(out->f_mode & FMODE_WRITE)))
                return -EBADF;
 
+       if (unlikely(out->f_flags & O_APPEND))
+               return -EINVAL;
+
        ret = rw_verify_area(WRITE, out, ppos, len);
        if (unlikely(ret < 0))
                return ret;
@@ -1152,36 +1164,6 @@ 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.
@@ -1194,8 +1176,6 @@ 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;
@@ -1204,7 +1184,7 @@ 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;
@@ -1238,9 +1218,8 @@ 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;
@@ -1279,8 +1258,6 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                iov++;
        }
 
-       up_read(&current->mm->mmap_sem);
-
        if (buffers)
                return buffers;