X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=fs%2Fblock_dev.c;h=0c59b703e9d56f8b104f4ad556e235db904573ac;hb=f50b6f8691cae2e0064c499dd3ef3f31142987f0;hp=f3c3a44dd8b6cd5dc723e5683081d3eb34690656;hpb=c48f70c3d046f021b1c22438604ef2a583380eca;p=powerpc.git

diff --git a/fs/block_dev.c b/fs/block_dev.c
index f3c3a44dd8..0c59b703e9 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -168,6 +168,203 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 				iov, offset, nr_segs, blkdev_get_blocks, NULL);
 }
 
+#if 0
+static int blk_end_aio(struct bio *bio, unsigned int bytes_done, int error)
+{
+	struct kiocb *iocb = bio->bi_private;
+	atomic_t *bio_count = &iocb->ki_bio_count;
+
+	if (bio_data_dir(bio) == READ)
+		bio_check_pages_dirty(bio);
+	else {
+		bio_release_pages(bio);
+		bio_put(bio);
+	}
+
+	/* iocb->ki_nbytes stores error code from LLDD */
+	if (error)
+		iocb->ki_nbytes = -EIO;
+
+	if (atomic_dec_and_test(bio_count)) {
+		if ((long)iocb->ki_nbytes < 0)
+			aio_complete(iocb, iocb->ki_nbytes, 0);
+		else
+			aio_complete(iocb, iocb->ki_left, 0);
+	}
+
+	return 0;
+}
+
+#define VEC_SIZE	16
+struct pvec {
+	unsigned short nr;
+	unsigned short idx;
+	struct page *page[VEC_SIZE];
+};
+
+#define PAGES_SPANNED(addr, len)	\
+	(DIV_ROUND_UP((addr) + (len), PAGE_SIZE) - (addr) / PAGE_SIZE);
+
+/*
+ * get page pointer for user addr, we internally cache struct page array for
+ * (addr, count) range in pvec to avoid frequent call to get_user_pages.  If
+ * internal page list is exhausted, a batch count of up to VEC_SIZE is used
+ * to get next set of page struct.
+ */
+static struct page *blk_get_page(unsigned long addr, size_t count, int rw,
+				 struct pvec *pvec)
+{
+	int ret, nr_pages;
+	if (pvec->idx == pvec->nr) {
+		nr_pages = PAGES_SPANNED(addr, count);
+		nr_pages = min(nr_pages, VEC_SIZE);
+		down_read(&current->mm->mmap_sem);
+		ret = get_user_pages(current, current->mm, addr, nr_pages,
+				     rw == READ, 0, pvec->page, NULL);
+		up_read(&current->mm->mmap_sem);
+		if (ret < 0)
+			return ERR_PTR(ret);
+		pvec->nr = ret;
+		pvec->idx = 0;
+	}
+	return pvec->page[pvec->idx++];
+}
+
+/* return a page back to pvec array */
+static void blk_unget_page(struct page *page, struct pvec *pvec)
+{
+	pvec->page[--pvec->idx] = page;
+}
+
+static ssize_t
+blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
+		 loff_t pos, unsigned long nr_segs)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	unsigned blkbits = blksize_bits(bdev_hardsect_size(I_BDEV(inode)));
+	unsigned blocksize_mask = (1 << blkbits) - 1;
+	unsigned long seg = 0;	/* iov segment iterator */
+	unsigned long nvec;	/* number of bio vec needed */
+	unsigned long cur_off;	/* offset into current page */
+	unsigned long cur_len;	/* I/O len of current page, up to PAGE_SIZE */
+
+	unsigned long addr;	/* user iovec address */
+	size_t count;		/* user iovec len */
+	size_t nbytes = iocb->ki_nbytes = iocb->ki_left; /* total xfer size */
+	loff_t size;		/* size of block device */
+	struct bio *bio;
+	atomic_t *bio_count = &iocb->ki_bio_count;
+	struct page *page;
+	struct pvec pvec;
+
+	pvec.nr = 0;
+	pvec.idx = 0;
+
+	if (pos & blocksize_mask)
+		return -EINVAL;
+
+	size = i_size_read(inode);
+	if (pos + nbytes > size) {
+		nbytes = size - pos;
+		iocb->ki_left = nbytes;
+	}
+
+	/*
+	 * check first non-zero iov alignment, the remaining
+	 * iov alignment is checked inside bio loop below.
+	 */
+	do {
+		addr = (unsigned long) iov[seg].iov_base;
+		count = min(iov[seg].iov_len, nbytes);
+		if (addr & blocksize_mask || count & blocksize_mask)
+			return -EINVAL;
+	} while (!count && ++seg < nr_segs);
+	atomic_set(bio_count, 1);
+
+	while (nbytes) {
+		/* roughly estimate number of bio vec needed */
+		nvec = (nbytes + PAGE_SIZE - 1) / PAGE_SIZE;
+		nvec = max(nvec, nr_segs - seg);
+		nvec = min(nvec, (unsigned long) BIO_MAX_PAGES);
+
+		/* bio_alloc should not fail with GFP_KERNEL flag */
+		bio = bio_alloc(GFP_KERNEL, nvec);
+		bio->bi_bdev = I_BDEV(inode);
+		bio->bi_end_io = blk_end_aio;
+		bio->bi_private = iocb;
+		bio->bi_sector = pos >> blkbits;
+same_bio:
+		cur_off = addr & ~PAGE_MASK;
+		cur_len = PAGE_SIZE - cur_off;
+		if (count < cur_len)
+			cur_len = count;
+
+		page = blk_get_page(addr, count, rw, &pvec);
+		if (unlikely(IS_ERR(page)))
+			goto backout;
+
+		if (bio_add_page(bio, page, cur_len, cur_off)) {
+			pos += cur_len;
+			addr += cur_len;
+			count -= cur_len;
+			nbytes -= cur_len;
+
+			if (count)
+				goto same_bio;
+			while (++seg < nr_segs) {
+				addr = (unsigned long) iov[seg].iov_base;
+				count = iov[seg].iov_len;
+				if (!count)
+					continue;
+				if (unlikely(addr & blocksize_mask ||
+					     count & blocksize_mask)) {
+					page = ERR_PTR(-EINVAL);
+					goto backout;
+				}
+				count = min(count, nbytes);
+				goto same_bio;
+			}
+		} else {
+			blk_unget_page(page, &pvec);
+		}
+
+		/* bio is ready, submit it */
+		if (rw == READ)
+			bio_set_pages_dirty(bio);
+		atomic_inc(bio_count);
+		submit_bio(rw, bio);
+	}
+
+completion:
+	iocb->ki_left -= nbytes;
+	nbytes = iocb->ki_left;
+	iocb->ki_pos += nbytes;
+
+	blk_run_address_space(inode->i_mapping);
+	if (atomic_dec_and_test(bio_count))
+		aio_complete(iocb, nbytes, 0);
+
+	return -EIOCBQUEUED;
+
+backout:
+	/*
+	 * back out nbytes count constructed so far for this bio,
+	 * we will throw away current bio.
+	 */
+	nbytes += bio->bi_size;
+	bio_release_pages(bio);
+	bio_put(bio);
+
+	/*
+	 * if no bio was submmitted, return the error code.
+	 * otherwise, proceed with pending I/O completion.
+	 */
+	if (atomic_read(bio_count) == 1)
+		return PTR_ERR(page);
+	goto completion;
+}
+#endif
+
 static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, blkdev_get_block, wbc);
@@ -190,7 +387,7 @@ static int blkdev_commit_write(struct file *file, struct page *page, unsigned fr
 
 /*
  * private llseek:
- * for a block special file file->f_dentry->d_inode->i_size is zero
+ * for a block special file file->f_path.dentry->d_inode->i_size is zero
  * so we compute the size by hand (just as in block_read/write above)
  */
 static loff_t block_llseek(struct file *file, loff_t offset, int origin)
@@ -263,7 +460,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
 	{
 		memset(bdev, 0, sizeof(*bdev));
 		mutex_init(&bdev->bd_mutex);
-		mutex_init(&bdev->bd_mount_mutex);
+		sema_init(&bdev->bd_mount_sem, 1);
 		INIT_LIST_HEAD(&bdev->bd_inodes);
 		INIT_LIST_HEAD(&bdev->bd_list);
 #ifdef CONFIG_SYSFS
@@ -292,7 +489,7 @@ static void bdev_clear_inode(struct inode *inode)
 	spin_unlock(&bdev_lock);
 }
 
-static struct super_operations bdev_sops = {
+static const struct super_operations bdev_sops = {
 	.statfs = simple_statfs,
 	.alloc_inode = bdev_alloc_inode,
 	.destroy_inode = bdev_destroy_inode,
@@ -1013,7 +1210,7 @@ static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
 	struct dentry fake_dentry = {};
 	fake_file.f_mode = mode;
 	fake_file.f_flags = flags;
-	fake_file.f_dentry = &fake_dentry;
+	fake_file.f_path.dentry = &fake_dentry;
 	fake_dentry.d_inode = bdev->bd_inode;
 
 	return do_open(bdev, &fake_file, for_part);