[PATCH 25/26] block: Add bio_get_user_pages()

[Kent Overstreet]

This replaces some of the code that was in __bio_map_user_iov(), and
soon we're going to use this helper in the dio code.

Note that this relies on the recent change to make
generic_make_request() take arbitrary sized bios - we're not using
bio_add_page() here.

Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
---
 fs/bio.c            | 123 +++++++++++++++++++++++++++-------------------------
 include/linux/bio.h |   2 +
 2 files changed, 66 insertions(+), 59 deletions(-)

diff --git a/fs/bio.c b/fs/bio.c
index 10d71cf..fe88f6e 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1212,17 +1212,69 @@ struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
 }
 EXPORT_SYMBOL(bio_copy_user);
 
+/**
+ * bio_get_user_pages - pin user pages and add them to a biovec
+ * @bio: bio to add pages to
+ * @uaddr: start of user address
+ * @len: length in bytes
+ * @write_to_vm: bool indicating writing to pages or not
+ *
+ * Pins pages for up to @len bytes and appends them to @bio's bvec array. May
+ * pin only part of the requested pages - @bio need not have room for all the
+ * pages and can already have had pages added to it.
+ *
+ * Returns the number of bytes from @len added to @bio.
+ */
+ssize_t bio_get_user_pages(struct bio *bio, unsigned long uaddr,
+			   unsigned long len, int write_to_vm)
+{
+	int ret;
+	unsigned nr_pages, bytes;
+	unsigned offset = offset_in_page(uaddr);
+	struct bio_vec *bv;
+	struct page **pages;
+
+	nr_pages = min_t(size_t,
+			 DIV_ROUND_UP(len + offset, PAGE_SIZE),
+			 bio->bi_max_vecs - bio->bi_vcnt);
+
+	bv = &bio->bi_io_vec[bio->bi_vcnt];
+	pages = (void *) bv;
+
+	ret = get_user_pages_fast(uaddr, nr_pages, write_to_vm, pages);
+	if (ret < 0)
+		return ret;
+
+	bio->bi_vcnt += ret;
+	bytes = ret * PAGE_SIZE - offset;
+
+	while (ret--) {
+		bv[ret].bv_page = pages[ret];
+		bv[ret].bv_len = PAGE_SIZE;
+		bv[ret].bv_offset = 0;
+	}
+
+	bv[0].bv_offset += offset;
+	bv[0].bv_len -= offset;
+
+	if (bytes > len) {
+		bio->bi_io_vec[bio->bi_vcnt - 1].bv_len -= bytes - len;
+		bytes = len;
+	}
+
+	bio->bi_iter.bi_size += bytes;
+
+	return bytes;
+}
+
 static struct bio *__bio_map_user_iov(struct request_queue *q,
 				      struct block_device *bdev,
 				      struct sg_iovec *iov, int iov_count,
 				      int write_to_vm, gfp_t gfp_mask)
 {
-	int i, j;
-	int nr_pages = 0;
-	struct page **pages;
+	ssize_t ret;
+	int i, nr_pages = 0;
 	struct bio *bio;
-	int cur_page = 0;
-	int ret, offset;
 
 	for (i = 0; i < iov_count; i++) {
 		unsigned long uaddr = (unsigned long)iov[i].iov_base;
@@ -1251,57 +1303,17 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
 
-	ret = -ENOMEM;
-	pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
-	if (!pages)
-		goto out;
-
 	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
-		unsigned long len = iov[i].iov_len;
-		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		unsigned long start = uaddr >> PAGE_SHIFT;
-		const int local_nr_pages = end - start;
-		const int page_limit = cur_page + local_nr_pages;
-
-		ret = get_user_pages_fast(uaddr, local_nr_pages,
-				write_to_vm, &pages[cur_page]);
-		if (ret < local_nr_pages) {
-			ret = -EFAULT;
-			goto out_unmap;
-		}
-
-		offset = uaddr & ~PAGE_MASK;
-		for (j = cur_page; j < page_limit; j++) {
-			unsigned int bytes = PAGE_SIZE - offset;
+		ret = bio_get_user_pages(bio, (size_t) iov[i].iov_base,
+					 iov[i].iov_len,
+					 write_to_vm);
+		if (ret < 0)
+			goto out;
 
-			if (len <= 0)
-				break;
-			
-			if (bytes > len)
-				bytes = len;
-
-			/*
-			 * sorry...
-			 */
-			if (bio_add_pc_page(q, bio, pages[j], bytes, offset) <
-					    bytes)
-				break;
-
-			len -= bytes;
-			offset = 0;
-		}
-
-		cur_page = j;
-		/*
-		 * release the pages we didn't map into the bio, if any
-		 */
-		while (j < page_limit)
-			page_cache_release(pages[j++]);
+		if (ret != iov[i].iov_len)
+			break;
 	}
 
-	kfree(pages);
-
 	/*
 	 * set data direction, and check if mapped pages need bouncing
 	 */
@@ -1312,14 +1324,7 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
 	bio->bi_flags |= (1 << BIO_USER_MAPPED);
 	return bio;
 
- out_unmap:
-	for (i = 0; i < nr_pages; i++) {
-		if(!pages[i])
-			break;
-		page_cache_release(pages[i]);
-	}
  out:
-	kfree(pages);
 	bio_put(bio);
 	return ERR_PTR(ret);
 }
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 444cc91..340d859 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -333,6 +333,8 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 extern int bio_get_nr_vecs(struct block_device *);
+extern ssize_t bio_get_user_pages(struct bio *, unsigned long,
+				  unsigned long, int);
 extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
 				unsigned long, unsigned int, int, gfp_t);
 struct sg_iovec;
-- 
1.8.3.rc1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/