}
EXPORT_SYMBOL(bio_add_page);
+#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *))
+
/**
* __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
* @bio: bio to add pages to
*/
static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
- unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
+ unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+ unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
struct page **pages = (struct page **)bv;
+ ssize_t size, left;
+ unsigned len, i;
size_t offset;
- ssize_t size;
+
+ /*
+ * Move page array up in the allocated memory for the bio vecs as far as
+ * possible so that we can start filling biovecs from the beginning
+ * without overwriting the temporary page array.
+ */
+ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
+ pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
if (unlikely(size <= 0))
return size ? size : -EFAULT;
- idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
- /*
- * Deep magic below: We need to walk the pinned pages backwards
- * because we are abusing the space allocated for the bio_vecs
- * for the page array. Because the bio_vecs are larger than the
- * page pointers by definition this will always work. But it also
- * means we can't use bio_add_page, so any changes to it's semantics
- * need to be reflected here as well.
- */
- bio->bi_iter.bi_size += size;
- bio->bi_vcnt += nr_pages;
+ for (left = size, i = 0; left > 0; left -= len, i++) {
+ struct page *page = pages[i];
- while (idx--) {
- bv[idx].bv_page = pages[idx];
- bv[idx].bv_len = PAGE_SIZE;
- bv[idx].bv_offset = 0;
+ len = min_t(size_t, PAGE_SIZE - offset, left);
+ if (WARN_ON_ONCE(bio_add_page(bio, page, len, offset) != len))
+ return -EINVAL;
+ offset = 0;
}
- bv[0].bv_offset += offset;
- bv[0].bv_len -= offset;
- bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
-
iov_iter_advance(iter, size);
return 0;
}
bio_integrity_trim(split);
bio_advance(bio, split->bi_iter.bi_size);
- bio->bi_iter.bi_done = 0;
if (bio_flagged(bio, BIO_TRACE_COMPLETION))
bio_set_flag(split, BIO_TRACE_COMPLETION);
*
* This function takes an extra reference of @blkcg_css which will be put
* when @bio is released. The caller must own @bio and is responsible for
- * synchronizing calls to this function.
+ * synchronizing calls to this function. If @blkcg_css is NULL, a call to
+ * blkcg_get_css finds the current css from the kthread or task.
*/
int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
{
if (unlikely(bio->bi_css))
return -EBUSY;
- css_get(blkcg_css);
+
+ if (blkcg_css)
+ css_get(blkcg_css);
+ else
+ blkcg_css = blkcg_get_css();
+
bio->bi_css = blkcg_css;
return 0;
}
EXPORT_SYMBOL_GPL(bio_associate_blkcg);
/**
- * bio_associate_blkg - associate a bio with the specified blkg
+ * bio_associate_blkg - associate a bio with the a blkg
* @bio: target bio
* @blkg: the blkg to associate
*
- * Associate @bio with the blkg specified by @blkg. This is the queue specific
- * blkcg information associated with the @bio, a reference will be taken on the
- * @blkg and will be freed when the bio is freed.
+ * This tries to associate @bio with the specified blkg. Association failure
+ * is handled by walking up the blkg tree. Therefore, the blkg associated can
+ * be anything between @blkg and the root_blkg. This situation only happens
+ * when a cgroup is dying and then the remaining bios will spill to the closest
+ * alive blkg.
+ *
+ * A reference will be taken on the @blkg and will be released when @bio is
+ * freed.
*/
int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
{
if (unlikely(bio->bi_blkg))
return -EBUSY;
- blkg_get(blkg);
- bio->bi_blkg = blkg;
+ bio->bi_blkg = blkg_try_get_closest(blkg);
return 0;
}