X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=block%2Fbio.c;h=9c64edac75d5055896516efc9dc28c43d41f673d;hb=9fa72f250436aadfae7019afb10b8b2596fd73b3;hp=9ef6cf3addb38cae822d0e5c5ef18ba9e98cd2d7;hpb=c0208a33cbc428f66b446f5dd16c91fb76aaab88;p=mirror_ubuntu-bionic-kernel.git

diff --git a/block/bio.c b/block/bio.c
index 9ef6cf3addb3..9c64edac75d5 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -43,9 +43,9 @@
  * break badly! cannot be bigger than what you can fit into an
  * unsigned short
  */
-#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
+#define BV(x, n) { .nr_vecs = x, .name = "biovec-"#n }
 static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = {
-	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
+	BV(1, 1), BV(4, 4), BV(16, 16), BV(64, 64), BV(128, 128), BV(BIO_MAX_PAGES, max),
 };
 #undef BV
 
@@ -156,7 +156,7 @@ out:
 
 unsigned int bvec_nr_vecs(unsigned short idx)
 {
-	return bvec_slabs[idx].nr_vecs;
+	return bvec_slabs[--idx].nr_vecs;
 }
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
@@ -773,7 +773,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 			return 0;
 	}
 
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
+	if (bio_full(bio))
 		return 0;
 
 	/*
@@ -821,76 +821,108 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 EXPORT_SYMBOL(bio_add_pc_page);
 
 /**
- *	bio_add_page	-	attempt to add page to bio
- *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
+ * __bio_try_merge_page - try appending data to an existing bvec.
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
  *
- *	Attempt to add a page to the bio_vec maplist. This will only fail
- *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
+ * Try to add the data at @page + @off to the last bvec of @bio.  This is a
+ * a useful optimisation for file systems with a block size smaller than the
+ * page size.
+ *
+ * Return %true on success or %false on failure.
  */
-int bio_add_page(struct bio *bio, struct page *page,
-		 unsigned int len, unsigned int offset)
+bool __bio_try_merge_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off)
 {
-	struct bio_vec *bv;
-
-	/*
-	 * cloned bio must not modify vec list
-	 */
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
-		return 0;
+		return false;
 
-	/*
-	 * For filesystems with a blocksize smaller than the pagesize
-	 * we will often be called with the same page as last time and
-	 * a consecutive offset.  Optimize this special case.
-	 */
 	if (bio->bi_vcnt > 0) {
-		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
-		if (page == bv->bv_page &&
-		    offset == bv->bv_offset + bv->bv_len) {
+		if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) {
 			bv->bv_len += len;
-			goto done;
+			bio->bi_iter.bi_size += len;
+			return true;
 		}
 	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(__bio_try_merge_page);
 
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
-		return 0;
+/**
+ * __bio_add_page - add page to a bio in a new segment
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
+ *
+ * Add the data at @page + @off to @bio as a new bvec.  The caller must ensure
+ * that @bio has space for another bvec.
+ */
+void __bio_add_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off)
+{
+	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt];
 
-	bv		= &bio->bi_io_vec[bio->bi_vcnt];
-	bv->bv_page	= page;
-	bv->bv_len	= len;
-	bv->bv_offset	= offset;
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	WARN_ON_ONCE(bio_full(bio));
+
+	bv->bv_page = page;
+	bv->bv_offset = off;
+	bv->bv_len = len;
 
-	bio->bi_vcnt++;
-done:
 	bio->bi_iter.bi_size += len;
+	bio->bi_vcnt++;
+}
+EXPORT_SYMBOL_GPL(__bio_add_page);
+
+/**
+ *	bio_add_page	-	attempt to add page to bio
+ *	@bio: destination bio
+ *	@page: page to add
+ *	@len: vec entry length
+ *	@offset: vec entry offset
+ *
+ *	Attempt to add a page to the bio_vec maplist. This will only fail
+ *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
+ */
+int bio_add_page(struct bio *bio, struct page *page,
+		 unsigned int len, unsigned int offset)
+{
+	if (!__bio_try_merge_page(bio, page, len, offset)) {
+		if (bio_full(bio))
+			return 0;
+		__bio_add_page(bio, page, len, offset);
+	}
 	return len;
 }
 EXPORT_SYMBOL(bio_add_page);
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
  * pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
  */
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+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;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	size_t offset, diff;
+	size_t offset;
 	ssize_t size;
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	/*
 	 * Deep magic below:  We need to walk the pinned pages backwards
@@ -903,21 +935,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size += size;
 	bio->bi_vcnt += nr_pages;
 
-	diff = (nr_pages * PAGE_SIZE - offset) - size;
-	while (nr_pages--) {
-		bv[nr_pages].bv_page = pages[nr_pages];
-		bv[nr_pages].bv_len = PAGE_SIZE;
-		bv[nr_pages].bv_offset = 0;
+	while (idx--) {
+		bv[idx].bv_page = pages[idx];
+		bv[idx].bv_len = PAGE_SIZE;
+		bv[idx].bv_offset = 0;
 	}
 
 	bv[0].bv_offset += offset;
 	bv[0].bv_len -= offset;
-	if (diff)
-		bv[bio->bi_vcnt - 1].bv_len -= diff;
+	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
 
 	iov_iter_advance(iter, size);
 	return 0;
 }
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short orig_vcnt = bio->bi_vcnt;
+
+	do {
+		int ret = __bio_iov_iter_get_pages(bio, iter);
+
+		if (unlikely(ret))
+			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+	} while (iov_iter_count(iter) && !bio_full(bio));
+
+	return 0;
+}
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1259,8 +1316,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 			}
 		}
 
-		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+			if (!map_data)
+				__free_page(page);
 			break;
+		}
 
 		len -= bytes;
 		offset = 0;
@@ -1281,6 +1341,8 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 		if (ret)
 			goto cleanup;
 	} else {
+		if (bmd->is_our_pages)
+			zero_fill_bio(bio);
 		iov_iter_advance(iter, bio->bi_iter.bi_size);
 	}
 
@@ -1836,9 +1898,10 @@ struct bio *bio_split(struct bio *bio, int sectors,
 		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(bio, BIO_TRACE_COMPLETION);
+		bio_set_flag(split, BIO_TRACE_COMPLETION);
 
 	return split;
 }