vfs: make guard_bh_eod() more generic

This patchset implements readpages() operation for block device by using
mpage_readpages() which can create multipage BIOs instead of BIOs for each
page and reduce system CPU time consumption.

This patch (of 3):

guard_bh_eod() is used in submit_bh() to allow us to do IO even on the odd
last sectors of a device, even if the block size is some multiple of the
physical sector size.  This makes guard_bh_eod() more generic and renames
it guard_bio_eod() so that we can use it without struct buffer_head
argument.

The reason for this change is that using mpage_readpages() for block
device requires to add this guard check in mpage code.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/buffer.c b/fs/buffer.c
index 3588a80854b27acb18d185d437662d03668eddae..e442a26e80f7de12875781dbee49e19923272a2a 100644 (file)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2956,7 +2956,7 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
 
 /*
  * This allows us to do IO even on the odd last sectors
- * of a device, even if the bh block size is some multiple
+ * of a device, even if the block size is some multiple
  * of the physical sector size.
  *
  * We'll just truncate the bio to the size of the device,
@@ -2966,10 +2966,11 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
  * errors, this only handles the "we need to be able to
  * do IO at the final sector" case.
  */
-static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
+static void guard_bio_eod(int rw, struct bio *bio)
 {
        sector_t maxsector;
-       unsigned bytes;
+       struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
+       unsigned truncated_bytes;
 
        maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
        if (!maxsector)
@@ -2984,23 +2985,20 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
                return;
 
        maxsector -= bio->bi_iter.bi_sector;
-       bytes = bio->bi_iter.bi_size;
-       if (likely((bytes >> 9) <= maxsector))
+       if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
                return;
 
-       /* Uhhuh. We've got a bh that straddles the device size! */
-       bytes = maxsector << 9;
+       /* Uhhuh. We've got a bio that straddles the device size! */
+       truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
 
        /* Truncate the bio.. */
-       bio->bi_iter.bi_size = bytes;
-       bio->bi_io_vec[0].bv_len = bytes;
+       bio->bi_iter.bi_size -= truncated_bytes;
+       bvec->bv_len -= truncated_bytes;
 
        /* ..and clear the end of the buffer for reads */
        if ((rw & RW_MASK) == READ) {
-               void *kaddr = kmap_atomic(bh->b_page);
-               memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
-               kunmap_atomic(kaddr);
-               flush_dcache_page(bh->b_page);
+               zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+                               truncated_bytes);
        }
 }
 
@@ -3041,7 +3039,7 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
        bio->bi_flags |= bio_flags;
 
        /* Take care of bh's that straddle the end of the device */
-       guard_bh_eod(rw, bio, bh);
+       guard_bio_eod(rw, bio);
 
        if (buffer_meta(bh))
                rw |= REQ_META;