Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block-related fixes from Jens Axboe:

 - Improvements to the buffered and direct write IO plugging from
   Fengguang.

 - Abstract out the mapping of a bio in a request, and use that to
   provide a blk_bio_map_sg() helper.  Useful for mapping just a bio
   instead of a full request.

 - Regression fix from Hugh, fixing up a patch that went into the
   previous release cycle (and marked stable, too) attempting to prevent
   a loop in __getblk_slow().

 - Updates to discard requests, fixing up the sizing and how we align
   them.  Also a change to disallow merging of discard requests, since
   that doesn't really work properly yet.

 - A few drbd fixes.

 - Documentation updates.

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: replace __getblk_slow misfix by grow_dev_page fix
  drbd: Write all pages of the bitmap after an online resize
  drbd: Finish requests that completed while IO was frozen
  drbd: fix drbd wire compatibility for empty flushes
  Documentation: update tunable options in block/cfq-iosched.txt
  Documentation: update tunable options in block/cfq-iosched.txt
  Documentation: update missing index files in block/00-INDEX
  block: move down direct IO plugging
  block: remove plugging at buffered write time
  block: disable discard request merge temporarily
  bio: Fix potential memory leak in bio_find_or_create_slab()
  block: Don't use static to define "void *p" in show_partition_start()
  block: Add blk_bio_map_sg() helper
  block: Introduce __blk_segment_map_sg() helper
  fs/block-dev.c:fix performance regression in O_DIRECT writes to md block devices
  block: split discard into aligned requests
  block: reorganize rounding of max_discard_sectors

4 files changed, 44 insertions, 41 deletions

diff --git a/fs/bio.c b/fs/bio.c
index 5eaa70c9d96..71072ab9912 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -73,7 +73,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
 {
         unsigned int sz = sizeof(struct bio) + extra_size;
         struct kmem_cache *slab = NULL;
-        struct bio_slab *bslab;
+        struct bio_slab *bslab, *new_bio_slabs;
         unsigned int i, entry = -1;
 
         mutex_lock(&bio_slab_lock);
@@ -97,11 +97,12 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
 
         if (bio_slab_nr == bio_slab_max && entry == -1) {
                 bio_slab_max <<= 1;
-                bio_slabs = krealloc(bio_slabs,
-                                     bio_slab_max * sizeof(struct bio_slab),
-                                     GFP_KERNEL);
-                if (!bio_slabs)
+                new_bio_slabs = krealloc(bio_slabs,
+                                         bio_slab_max * sizeof(struct bio_slab),
+                                         GFP_KERNEL);
+                if (!new_bio_slabs)
                         goto out_unlock;
+                bio_slabs = new_bio_slabs;
         }
         if (entry == -1)
                 entry = bio_slab_nr++;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e519195d45..38e721b35d4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1578,10 +1578,12 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
                          unsigned long nr_segs, loff_t pos)
 {
         struct file *file = iocb->ki_filp;
+        struct blk_plug plug;
         ssize_t ret;
 
         BUG_ON(iocb->ki_pos != pos);
 
+        blk_start_plug(&plug);
         ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
         if (ret > 0 || ret == -EIOCBQUEUED) {
                 ssize_t err;
@@ -1590,6 +1592,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
                 if (err < 0 && ret > 0)
                         ret = err;
         }
+        blk_finish_plug(&plug);
         return ret;
 }
 EXPORT_SYMBOL_GPL(blkdev_aio_write);
diff --git a/fs/buffer.c b/fs/buffer.c
index 9f6d2e41281..58e2e7b7737 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -914,7 +914,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
 /*
  * Initialise the state of a blockdev page's buffers.
  */ 
-static void
+static sector_t
 init_page_buffers(struct page *page, struct block_device *bdev,
                         sector_t block, int size)
 {
@@ -936,33 +936,41 @@ init_page_buffers(struct page *page, struct block_device *bdev,
                 block++;
                 bh = bh->b_this_page;
         } while (bh != head);
+
+        /*
+         * Caller needs to validate requested block against end of device.
+         */
+        return end_block;
 }
 
 /*
  * Create the page-cache page that contains the requested block.
  *
- * This is user purely for blockdev mappings.
+ * This is used purely for blockdev mappings.
  */
-static struct page *
+static int
 grow_dev_page(struct block_device *bdev, sector_t block,
-                pgoff_t index, int size)
+                pgoff_t index, int size, int sizebits)
 {
         struct inode *inode = bdev->bd_inode;
         struct page *page;
         struct buffer_head *bh;
+        sector_t end_block;
+        int ret = 0;            /* Will call free_more_memory() */
 
         page = find_or_create_page(inode->i_mapping, index,
                 (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
         if (!page)
-                return NULL;
+                return ret;
 
         BUG_ON(!PageLocked(page));
 
         if (page_has_buffers(page)) {
                 bh = page_buffers(page);
                 if (bh->b_size == size) {
-                        init_page_buffers(page, bdev, block, size);
-                        return page;
+                        end_block = init_page_buffers(page, bdev,
+                                                index << sizebits, size);
+                        goto done;
                 }
                 if (!try_to_free_buffers(page))
                         goto failed;
@@ -982,14 +990,14 @@ grow_dev_page(struct block_device *bdev, sector_t block,
          */
         spin_lock(&inode->i_mapping->private_lock);
         link_dev_buffers(page, bh);
-        init_page_buffers(page, bdev, block, size);
+        end_block = init_page_buffers(page, bdev, index << sizebits, size);
         spin_unlock(&inode->i_mapping->private_lock);
-        return page;
-
+done:
+        ret = (block < end_block) ? 1 : -ENXIO;
 failed:
         unlock_page(page);
         page_cache_release(page);
-        return NULL;
+        return ret;
 }
 
 /*
@@ -999,7 +1007,6 @@ failed:
 static int
 grow_buffers(struct block_device *bdev, sector_t block, int size)
 {
-        struct page *page;
         pgoff_t index;
         int sizebits;
 
@@ -1023,22 +1030,14 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
                         bdevname(bdev, b));
                 return -EIO;
         }
-        block = index << sizebits;
+
         /* Create a page with the proper size buffers.. */
-        page = grow_dev_page(bdev, block, index, size);
-        if (!page)
-                return 0;
-        unlock_page(page);
-        page_cache_release(page);
-        return 1;
+        return grow_dev_page(bdev, block, index, size, sizebits);
 }
 
 static struct buffer_head *
 __getblk_slow(struct block_device *bdev, sector_t block, int size)
 {
-        int ret;
-        struct buffer_head *bh;
-
         /* Size must be multiple of hard sectorsize */
         if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
                         (size < 512 || size > PAGE_SIZE))) {
@@ -1051,21 +1050,20 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
                 return NULL;
         }
 
-retry:
-        bh = __find_get_block(bdev, block, size);
-        if (bh)
-                return bh;
+        for (;;) {
+                struct buffer_head *bh;
+                int ret;
 
-        ret = grow_buffers(bdev, block, size);
-        if (ret == 0) {
-                free_more_memory();
-                goto retry;
-        } else if (ret > 0) {
                 bh = __find_get_block(bdev, block, size);
                 if (bh)
                         return bh;
+
+                ret = grow_buffers(bdev, block, size);
+                if (ret < 0)
+                        return NULL;
+                if (ret == 0)
+                        free_more_memory();
         }
-        return NULL;
 }
 
 /*
@@ -1321,10 +1319,6 @@ EXPORT_SYMBOL(__find_get_block);
  * which corresponds to the passed block_device, block and size. The
  * returned buffer has its reference count incremented.
  *
- * __getblk() cannot fail - it just keeps trying.  If you pass it an
- * illegal block number, __getblk() will happily return a buffer_head
- * which represents the non-existent block.  Very weird.
- *
  * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
  * attempt is failing.  FIXME, perhaps?
  */
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 1faf4cb56f3..f86c720dba0 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1062,6 +1062,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         unsigned long user_addr;
         size_t bytes;
         struct buffer_head map_bh = { 0, };
+        struct blk_plug plug;
 
         if (rw & WRITE)
                 rw = WRITE_ODIRECT;
@@ -1177,6 +1178,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
                                 PAGE_SIZE - user_addr / PAGE_SIZE);
         }
 
+        blk_start_plug(&plug);
+
         for (seg = 0; seg < nr_segs; seg++) {
                 user_addr = (unsigned long)iov[seg].iov_base;
                 sdio.size += bytes = iov[seg].iov_len;
@@ -1235,6 +1238,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         if (sdio.bio)
                 dio_bio_submit(dio, &sdio);
 
+        blk_finish_plug(&plug);
+
         /*
          * It is possible that, we return short IO due to end of file.
          * In that case, we need to release all the pages we got hold on.