From: "Matthew Wilcox (Oracle)" <[email protected]>
Instead of having a 'done' variable that controls the nested loops,
have a writeback_finish() that can be returned directly. This involves
keeping more things in writeback_control, but it's just moving stuff
allocated on the stack to being allocated slightly earlier on the stack.
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
[hch: reorder and comment struct writeback_control]
Signed-off-by: Christoph Hellwig <[email protected]>
---
include/linux/writeback.h | 8 +++++
mm/page-writeback.c | 72 +++++++++++++++++++++------------------
2 files changed, 46 insertions(+), 34 deletions(-)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 083387c00f0c8b..05e8add4b5ae3c 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -11,6 +11,7 @@
#include <linux/flex_proportions.h>
#include <linux/backing-dev-defs.h>
#include <linux/blk_types.h>
+#include <linux/pagevec.h>
struct bio;
@@ -40,6 +41,7 @@ enum writeback_sync_modes {
* in a manner such that unspecified fields are set to zero.
*/
struct writeback_control {
+ /* public fields that can be set and/or consumed by the caller: */
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
long pages_skipped; /* Pages which were not written */
@@ -77,6 +79,12 @@ struct writeback_control {
*/
struct swap_iocb **swap_plug;
+ /* internal fields used by the ->writepages implementation: */
+ struct folio_batch fbatch;
+ pgoff_t done_index;
+ int err;
+ unsigned range_whole:1; /* entire file */
+
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *wb; /* wb this writeback is issued under */
struct inode *inode; /* inode being written out */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ee2fd6a6af4072..45309f3b8193f8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2360,6 +2360,24 @@ void tag_pages_for_writeback(struct address_space *mapping,
}
EXPORT_SYMBOL(tag_pages_for_writeback);
+static int writeback_finish(struct address_space *mapping,
+ struct writeback_control *wbc, bool done)
+{
+ folio_batch_release(&wbc->fbatch);
+
+ /*
+ * If we hit the last page and there is more work to be done:
+ * wrap the index back to the start of the file for the next
+ * time we are called.
+ */
+ if (wbc->range_cyclic && !done)
+ wbc->done_index = 0;
+ if (wbc->range_cyclic || (wbc->range_whole && wbc->nr_to_write > 0))
+ mapping->writeback_index = wbc->done_index;
+
+ return wbc->err;
+}
+
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
@@ -2395,18 +2413,12 @@ int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
- 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;
@@ -2414,7 +2426,7 @@ int write_cache_pages(struct address_space *mapping,
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;
+ wbc->range_whole = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) {
tag_pages_for_writeback(mapping, index, end);
@@ -2422,21 +2434,25 @@ int write_cache_pages(struct address_space *mapping,
} else {
tag = PAGECACHE_TAG_DIRTY;
}
- done_index = index;
- while (!done && (index <= end)) {
+
+ wbc->done_index = index;
+ folio_batch_init(&wbc->fbatch);
+ wbc->err = 0;
+
+ while (index <= end) {
int i;
nr_folios = filemap_get_folios_tag(mapping, &index, end,
- tag, &fbatch);
+ tag, &wbc->fbatch);
if (nr_folios == 0)
break;
for (i = 0; i < nr_folios; i++) {
- struct folio *folio = fbatch.folios[i];
+ struct folio *folio = wbc->fbatch.folios[i];
unsigned long nr;
- done_index = folio->index;
+ wbc->done_index = folio->index;
folio_lock(folio);
@@ -2490,13 +2506,13 @@ int write_cache_pages(struct address_space *mapping,
folio_unlock(folio);
error = 0;
} else if (wbc->sync_mode != WB_SYNC_ALL) {
- ret = error;
- done_index = folio->index + nr;
- done = 1;
- break;
+ wbc->err = error;
+ wbc->done_index = folio->index + nr;
+ return writeback_finish(mapping,
+ wbc, true);
}
- if (!ret)
- ret = error;
+ if (!wbc->err)
+ wbc->err = error;
}
/*
@@ -2507,26 +2523,14 @@ int write_cache_pages(struct address_space *mapping,
*/
wbc->nr_to_write -= nr;
if (wbc->nr_to_write <= 0 &&
- wbc->sync_mode == WB_SYNC_NONE) {
- done = 1;
- break;
- }
+ wbc->sync_mode == WB_SYNC_NONE)
+ return writeback_finish(mapping, wbc, true);
}
- folio_batch_release(&fbatch);
+ folio_batch_release(&wbc->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;
+ return writeback_finish(mapping, wbc, false);
}
EXPORT_SYMBOL(write_cache_pages);
--
2.39.2
On Thu 14-12-23 14:25:34, Christoph Hellwig wrote:
> From: "Matthew Wilcox (Oracle)" <[email protected]>
>
> Instead of having a 'done' variable that controls the nested loops,
> have a writeback_finish() that can be returned directly. This involves
> keeping more things in writeback_control, but it's just moving stuff
> allocated on the stack to being allocated slightly earlier on the stack.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> [hch: reorder and comment struct writeback_control]
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> include/linux/writeback.h | 8 +++++
> mm/page-writeback.c | 72 +++++++++++++++++++++------------------
> 2 files changed, 46 insertions(+), 34 deletions(-)
>
> diff --git a/include/linux/writeback.h b/include/linux/writeback.h
> index 083387c00f0c8b..05e8add4b5ae3c 100644
> --- a/include/linux/writeback.h
> +++ b/include/linux/writeback.h
> @@ -11,6 +11,7 @@
> #include <linux/flex_proportions.h>
> #include <linux/backing-dev-defs.h>
> #include <linux/blk_types.h>
> +#include <linux/pagevec.h>
>
> struct bio;
>
> @@ -40,6 +41,7 @@ enum writeback_sync_modes {
> * in a manner such that unspecified fields are set to zero.
> */
> struct writeback_control {
> + /* public fields that can be set and/or consumed by the caller: */
> long nr_to_write; /* Write this many pages, and decrement
> this for each page written */
> long pages_skipped; /* Pages which were not written */
> @@ -77,6 +79,12 @@ struct writeback_control {
> */
> struct swap_iocb **swap_plug;
>
> + /* internal fields used by the ->writepages implementation: */
> + struct folio_batch fbatch;
> + pgoff_t done_index;
> + int err;
> + unsigned range_whole:1; /* entire file */
Do we really need the range_whole member here? It is trivially derived from
range_start && range_end and used only in one place in writeback_finish().
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index ee2fd6a6af4072..45309f3b8193f8 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -2360,6 +2360,24 @@ void tag_pages_for_writeback(struct address_space *mapping,
> }
> EXPORT_SYMBOL(tag_pages_for_writeback);
>
> +static int writeback_finish(struct address_space *mapping,
> + struct writeback_control *wbc, bool done)
> +{
> + folio_batch_release(&wbc->fbatch);
> +
> + /*
> + * If we hit the last page and there is more work to be done:
> + * wrap the index back to the start of the file for the next
> + * time we are called.
> + */
> + if (wbc->range_cyclic && !done)
> + wbc->done_index = 0;
> + if (wbc->range_cyclic || (wbc->range_whole && wbc->nr_to_write > 0))
> + mapping->writeback_index = wbc->done_index;
> +
> + return wbc->err;
> +}
Also I suspect we can get rid of the 'done' argument here. After all it
just controls whether we cycle back to index 0 which we could just
determine as:
if (wbc->range_cyclic && !wbc->err && wbc->nr_to_write > 0) {
WARN_ON_ONCE(wbc->sync_mode != WB_SYNC_NONE);
wbc->done_index = 0;
}
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Fri, Dec 15, 2023 at 02:26:39PM +0100, Jan Kara wrote:
> > + /* internal fields used by the ->writepages implementation: */
> > + struct folio_batch fbatch;
> > + pgoff_t done_index;
> > + int err;
> > + unsigned range_whole:1; /* entire file */
>
> Do we really need the range_whole member here? It is trivially derived from
> range_start && range_end and used only in one place in writeback_finish().
Yes, as nothing modified range_start and range_end this should be
easily doable.