btrfs: send: get send buffer pages for protocol v2

For encoded writes in send v2, we will get the encoded data with
btrfs_encoded_read_regular_fill_pages(), which expects a list of raw
pages. To avoid extra buffers and copies, we should read directly into
the send buffer. Therefore, we need the raw pages for the send buffer.

We currently allocate the send buffer with kvmalloc(), which may return
a kmalloc'd buffer or a vmalloc'd buffer. For vmalloc, we can get the
pages with vmalloc_to_page(). For kmalloc, we could use virt_to_page().
However, the buffer size we use (144K) is not a power of two, which in
theory is not guaranteed to return a page-aligned buffer, and in
practice would waste a lot of memory due to rounding up to the next
power of two. 144K is large enough that it usually gets allocated with
vmalloc(), anyways. So, for send v2, replace kvmalloc() with vmalloc()
and save the pages in an array.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 25 insertions, 4 deletions

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 02df94815ae9..57052fe4033c 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -87,6 +87,7 @@ struct send_ctx {
 	 * command (since protocol v2, data must be the last attribute).
 	 */
 	bool put_data;
+	struct page **send_buf_pages;
 	u64 flags;	/* 'flags' member of btrfs_ioctl_send_args is u64 */
 	/* Protocol version compatibility requested */
 	u32 proto;
@@ -7575,12 +7576,31 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
-	if (sctx->proto >= 2)
+	if (sctx->proto >= 2) {
+		u32 send_buf_num_pages;
+
 		sctx->send_max_size = ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED, PAGE_SIZE);
-	else
+		sctx->send_buf = vmalloc(sctx->send_max_size);
+		if (!sctx->send_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		send_buf_num_pages = sctx->send_max_size >> PAGE_SHIFT;
+		sctx->send_buf_pages = kcalloc(send_buf_num_pages,
+					       sizeof(*sctx->send_buf_pages),
+					       GFP_KERNEL);
+		if (!sctx->send_buf_pages) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		for (i = 0; i < send_buf_num_pages; i++) {
+			sctx->send_buf_pages[i] =
+				vmalloc_to_page(sctx->send_buf + (i << PAGE_SHIFT));
+		}
+	} else {
 		sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
-
-	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
+		sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
+	}
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -7773,6 +7793,7 @@ out:
 			fput(sctx->send_filp);
 
 		kvfree(sctx->clone_roots);
+		kfree(sctx->send_buf_pages);
 		kvfree(sctx->send_buf);
 
 		name_cache_free(sctx);