[RFC PATCH 10/17] block: refactor bio_get_user_pages() from __bio_map_user_iov()

From: Dongsu Park
Date: Mon Dec 22 2014 - 06:50:36 EST


From: Kent Overstreet <kmo@xxxxxxxxxxxxx>

Split up a part of the code that was in __bio_map_user_iov() into
a new function bio_get_user_pages(). This helper is going to be used
by future block layer rewriting, especially from direct-IO part.

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

Signed-off-by: Kent Overstreet <kmo@xxxxxxxxxxxxx>
[dpark: add more description in commit message]
Signed-off-by: Dongsu Park <dongsu.park@xxxxxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
---
block/bio.c | 130 +++++++++++++++++++++++++++-------------------------
include/linux/bio.h | 2 +
2 files changed, 70 insertions(+), 62 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 2adb68b..470e330 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1228,19 +1228,79 @@ 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, struct iov_iter *i, int write_to_vm)
+{
+ while (bio->bi_vcnt < bio->bi_max_vecs && iov_iter_count(i)) {
+ struct iovec iov = iov_iter_iovec(i);
+ int ret;
+ unsigned nr_pages, bytes;
+ unsigned offset = offset_in_page(iov.iov_base);
+ struct bio_vec *bv;
+ struct page **pages;
+
+ nr_pages = min_t(size_t,
+ DIV_ROUND_UP(iov.iov_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((unsigned long) iov.iov_base,
+ nr_pages, write_to_vm, pages);
+ if (ret < 0) {
+ if (bio->bi_vcnt)
+ return 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 > iov.iov_len) {
+ bio->bi_io_vec[bio->bi_vcnt - 1].bv_len -=
+ bytes - iov.iov_len;
+ bytes = iov.iov_len;
+ }
+
+ bio->bi_iter.bi_size += bytes;
+ iov_iter_advance(i, bytes);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(bio_get_user_pages);
+
static struct bio *__bio_map_user_iov(struct request_queue *q,
struct block_device *bdev,
const struct iov_iter *iter,
int write_to_vm, gfp_t gfp_mask)
{
- int j;
+ ssize_t ret;
int nr_pages = 0;
- struct page **pages;
struct bio *bio;
- int cur_page = 0;
- int ret, offset;
- struct iov_iter i;
- struct iovec iov;

nr_pages = iov_count_pages(iter, queue_dma_alignment(q));
if (nr_pages < 0)
@@ -1253,57 +1313,10 @@ 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)
+ ret = bio_get_user_pages(bio, (struct iov_iter *)iter, write_to_vm);
+ if (ret < 0)
goto out;

- iov_for_each(iov, i, *iter) {
- unsigned long uaddr = (unsigned long) iov.iov_base;
- unsigned long len = iov.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;
-
- 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++]);
- }
-
- kfree(pages);
-
/*
* set data direction, and check if mapped pages need bouncing
*/
@@ -1314,14 +1327,7 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
bio->bi_flags |= (1 << BIO_USER_MAPPED);
return bio;

- out_unmap:
- for (j = 0; j < nr_pages; j++) {
- if (!pages[j])
- break;
- page_cache_release(pages[j]);
- }
out:
- kfree(pages);
bio_put(bio);
return ERR_PTR(ret);
}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a69f7b1..c80131a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -428,6 +428,8 @@ 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 *);
+struct iov_iter;
+extern ssize_t bio_get_user_pages(struct bio *, struct iov_iter *, int);
extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
unsigned long, unsigned int, int, gfp_t);
struct iov_iter;
--
2.1.0

--
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/