cifs test patch to make cifs use its own version of write_cache_pages()

[David Howells <dhowells@redhat.com>]

David Howells <dhowells@redhat.com> wrote:

> And then CIFS. ...
> 
>   Base + Own write_cache_pages():
> 	WRITE: bw=451MiB/s (473MB/s), 113MiB/s-113MiB/s (118MB/s-118MB/s)
> 	WRITE: bw=455MiB/s (478MB/s), 114MiB/s-114MiB/s (119MB/s-120MB/s)
> 	WRITE: bw=453MiB/s (475MB/s), 113MiB/s-113MiB/s (119MB/s-119MB/s)
> 	WRITE: bw=459MiB/s (481MB/s), 115MiB/s-115MiB/s (120MB/s-120MB/s)

Here's my patch to give cifs its own copy of write_cache_pages() so that the
function pointer can be eliminated in case some sort of spectre thing is
causing a slowdown.

This goes on top of "cifs test patch to convert to using write_cache_pages()".

David
---
 fs/cifs/file.c |  137 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 136 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 04e2466609d9..c33c7db729c7 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2802,6 +2802,141 @@ static int cifs_writepages_add_folio(struct folio *folio,
 	return 0;
 }
 
+static int cifs_write_cache_pages(struct address_space *mapping,
+				  struct writeback_control *wbc,
+				  struct cifs_writepages_context *ctx)
+{
+	int ret = 0;
+	int done = 0;
+	int error;
+	struct folio_batch fbatch;
+	int nr_folios;
+	pgoff_t index;
+	pgoff_t end;		/* Inclusive */
+	pgoff_t done_index;
+	int range_whole = 0;
+	xa_mark_t tag;
+
+	folio_batch_init(&fbatch);
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index; /* prev offset */
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
+	}
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) {
+		tag_pages_for_writeback(mapping, index, end);
+		tag = PAGECACHE_TAG_TOWRITE;
+	} else {
+		tag = PAGECACHE_TAG_DIRTY;
+	}
+	done_index = index;
+	while (!done && (index <= end)) {
+		int i;
+
+		nr_folios = filemap_get_folios_tag(mapping, &index, end,
+				tag, &fbatch);
+
+		if (nr_folios == 0)
+			break;
+
+		for (i = 0; i < nr_folios; i++) {
+			struct folio *folio = fbatch.folios[i];
+
+			done_index = folio->index;
+
+			folio_lock(folio);
+
+			/*
+			 * Page truncated or invalidated. We can freely skip it
+			 * then, even for data integrity operations: the page
+			 * has disappeared concurrently, so there could be no
+			 * real expectation of this data integrity operation
+			 * even if there is now a new, dirty page at the same
+			 * pagecache address.
+			 */
+			if (unlikely(folio->mapping != mapping)) {
+continue_unlock:
+				folio_unlock(folio);
+				continue;
+			}
+
+			if (!folio_test_dirty(folio)) {
+				/* someone wrote it for us */
+				goto continue_unlock;
+			}
+
+			if (folio_test_writeback(folio)) {
+				if (wbc->sync_mode != WB_SYNC_NONE)
+					folio_wait_writeback(folio);
+				else
+					goto continue_unlock;
+			}
+
+			BUG_ON(folio_test_writeback(folio));
+			if (!folio_clear_dirty_for_io(folio))
+				goto continue_unlock;
+
+			error = cifs_writepages_add_folio(folio, wbc, ctx);
+			if (unlikely(error)) {
+				/*
+				 * Handle errors according to the type of
+				 * writeback. There's no need to continue for
+				 * background writeback. Just push done_index
+				 * past this page so media errors won't choke
+				 * writeout for the entire file. For integrity
+				 * writeback, we must process the entire dirty
+				 * set regardless of errors because the fs may
+				 * still have state to clear for each page. In
+				 * that case we continue processing and return
+				 * the first error.
+				 */
+				if (error == AOP_WRITEPAGE_ACTIVATE) {
+					folio_unlock(folio);
+					error = 0;
+				} else if (wbc->sync_mode != WB_SYNC_ALL) {
+					ret = error;
+					done_index = folio->index +
+						folio_nr_pages(folio);
+					done = 1;
+					break;
+				}
+				if (!ret)
+					ret = error;
+			}
+
+			/*
+			 * We stop writing back only if we are not doing
+			 * integrity sync. In case of integrity sync we have to
+			 * keep going until we have written all the pages
+			 * we tagged for writeback prior to entering this loop.
+			 */
+			if (--wbc->nr_to_write <= 0 &&
+			    wbc->sync_mode == WB_SYNC_NONE) {
+				done = 1;
+				break;
+			}
+		}
+		folio_batch_release(&fbatch);
+		cond_resched();
+	}
+
+	/*
+	 * If we hit the last page and there is more work to be done: wrap
+	 * back the index back to the start of the file for the next
+	 * time we are called.
+	 */
+	if (wbc->range_cyclic && !done)
+		done_index = 0;
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		mapping->writeback_index = done_index;
+
+	return ret;
+}
+
 /*
  * Write some of the pending data back to the server
  */
@@ -2816,7 +2951,7 @@ static int cifs_writepages(struct address_space *mapping,
 	 * to prevent it.
 	 */
 
-	ret = write_cache_pages(mapping, wbc, cifs_writepages_add_folio, &ctx);
+	ret = cifs_write_cache_pages(mapping, wbc, &ctx);
 	if (ret >= 0 && ctx.begun) {
 		ret = cifs_writepages_submit(mapping, wbc, &ctx);
 		if (ret < 0)