During the era of memcg charge migration, the kernel has to be make sure
that the dirty stat updates do not race with the charge migration.
Otherwise it might update the dirty stats of the wrong memcg. Now with
the memcg charge migration deprecated, there is no more race for dirty
stat updates and the previous locking can be removed.
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
---
fs/buffer.c | 5 -----
mm/page-writeback.c | 16 +++-------------
2 files changed, 3 insertions(+), 18 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 1fc9a50def0b..88e765b0699f 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -736,15 +736,12 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
* Lock out page's memcg migration to keep PageDirty
* synchronized with per-memcg dirty page counters.
*/
- folio_memcg_lock(folio);
newly_dirty = !folio_test_set_dirty(folio);
spin_unlock(&mapping->i_private_lock);
if (newly_dirty)
__folio_mark_dirty(folio, mapping, 1);
- folio_memcg_unlock(folio);
-
if (newly_dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -1194,13 +1191,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
struct folio *folio = bh->b_folio;
struct address_space *mapping = NULL;
- folio_memcg_lock(folio);
if (!folio_test_set_dirty(folio)) {
mapping = folio->mapping;
if (mapping)
__folio_mark_dirty(folio, mapping, 0);
}
- folio_memcg_unlock(folio);
if (mapping)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 1d7179aba8e3..a76a73529fd9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2743,8 +2743,6 @@ EXPORT_SYMBOL(noop_dirty_folio);
/*
* Helper function for set_page_dirty family.
*
- * Caller must hold folio_memcg_lock().
- *
* NOTE: This relies on being atomic wrt interrupts.
*/
static void folio_account_dirtied(struct folio *folio,
@@ -2777,7 +2775,6 @@ static void folio_account_dirtied(struct folio *folio,
/*
* Helper function for deaccounting dirty page without writeback.
*
- * Caller must hold folio_memcg_lock().
*/
void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
{
@@ -2795,9 +2792,8 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
* If warn is true, then emit a warning if the folio is not uptodate and has
* not been truncated.
*
- * The caller must hold folio_memcg_lock(). It is the caller's
- * responsibility to prevent the folio from being truncated while
- * this function is in progress, although it may have been truncated
+ * It is the caller's responsibility to prevent the folio from being truncated
+ * while this function is in progress, although it may have been truncated
* before this function is called. Most callers have the folio locked.
* A few have the folio blocked from truncation through other means (e.g.
* zap_vma_pages() has it mapped and is holding the page table lock).
@@ -2841,14 +2837,10 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
*/
bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
{
- folio_memcg_lock(folio);
- if (folio_test_set_dirty(folio)) {
- folio_memcg_unlock(folio);
+ if (folio_test_set_dirty(folio))
return false;
- }
__folio_mark_dirty(folio, mapping, !folio_test_private(folio));
- folio_memcg_unlock(folio);
if (mapping->host) {
/* !PageAnon && !swapper_space */
@@ -2975,14 +2967,12 @@ void __folio_cancel_dirty(struct folio *folio)
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
- folio_memcg_lock(folio);
wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (folio_test_clear_dirty(folio))
folio_account_cleaned(folio, wb);
unlocked_inode_to_wb_end(inode, &cookie);
- folio_memcg_unlock(folio);
} else {
folio_clear_dirty(folio);
}
--
2.43.5On Thu, Oct 24, 2024 at 06:23:00PM -0700, Shakeel Butt wrote: > During the era of memcg charge migration, the kernel has to be make sure > that the dirty stat updates do not race with the charge migration. > Otherwise it might update the dirty stats of the wrong memcg. Now with > the memcg charge migration deprecated, there is no more race for dirty > stat updates and the previous locking can be removed. > > Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
On Thu, Oct 24, 2024 at 06:23:00PM -0700, Shakeel Butt wrote: > During the era of memcg charge migration, the kernel has to be make sure > that the dirty stat updates do not race with the charge migration. > Otherwise it might update the dirty stats of the wrong memcg. Now with > the memcg charge migration deprecated, there is no more race for dirty > stat updates and the previous locking can be removed. > > Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev> Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
On Thu 24-10-24 18:23:00, Shakeel Butt wrote:
> During the era of memcg charge migration, the kernel has to be make sure
> that the dirty stat updates do not race with the charge migration.
> Otherwise it might update the dirty stats of the wrong memcg. Now with
> the memcg charge migration deprecated, there is no more race for dirty
s@deprecated@gone@
> stat updates and the previous locking can be removed.
>
> Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
LGTM otherwise
Acked-by: Michal Hocko <mhocko@suse.com>
> ---
> fs/buffer.c | 5 -----
> mm/page-writeback.c | 16 +++-------------
> 2 files changed, 3 insertions(+), 18 deletions(-)
>
> diff --git a/fs/buffer.c b/fs/buffer.c
> index 1fc9a50def0b..88e765b0699f 100644
> --- a/fs/buffer.c
> +++ b/fs/buffer.c
> @@ -736,15 +736,12 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
> * Lock out page's memcg migration to keep PageDirty
> * synchronized with per-memcg dirty page counters.
> */
> - folio_memcg_lock(folio);
> newly_dirty = !folio_test_set_dirty(folio);
> spin_unlock(&mapping->i_private_lock);
>
> if (newly_dirty)
> __folio_mark_dirty(folio, mapping, 1);
>
> - folio_memcg_unlock(folio);
> -
> if (newly_dirty)
> __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
>
> @@ -1194,13 +1191,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
> struct folio *folio = bh->b_folio;
> struct address_space *mapping = NULL;
>
> - folio_memcg_lock(folio);
> if (!folio_test_set_dirty(folio)) {
> mapping = folio->mapping;
> if (mapping)
> __folio_mark_dirty(folio, mapping, 0);
> }
> - folio_memcg_unlock(folio);
> if (mapping)
> __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
> }
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 1d7179aba8e3..a76a73529fd9 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -2743,8 +2743,6 @@ EXPORT_SYMBOL(noop_dirty_folio);
> /*
> * Helper function for set_page_dirty family.
> *
> - * Caller must hold folio_memcg_lock().
> - *
> * NOTE: This relies on being atomic wrt interrupts.
> */
> static void folio_account_dirtied(struct folio *folio,
> @@ -2777,7 +2775,6 @@ static void folio_account_dirtied(struct folio *folio,
> /*
> * Helper function for deaccounting dirty page without writeback.
> *
> - * Caller must hold folio_memcg_lock().
> */
> void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
> {
> @@ -2795,9 +2792,8 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
> * If warn is true, then emit a warning if the folio is not uptodate and has
> * not been truncated.
> *
> - * The caller must hold folio_memcg_lock(). It is the caller's
> - * responsibility to prevent the folio from being truncated while
> - * this function is in progress, although it may have been truncated
> + * It is the caller's responsibility to prevent the folio from being truncated
> + * while this function is in progress, although it may have been truncated
> * before this function is called. Most callers have the folio locked.
> * A few have the folio blocked from truncation through other means (e.g.
> * zap_vma_pages() has it mapped and is holding the page table lock).
> @@ -2841,14 +2837,10 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
> */
> bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
> {
> - folio_memcg_lock(folio);
> - if (folio_test_set_dirty(folio)) {
> - folio_memcg_unlock(folio);
> + if (folio_test_set_dirty(folio))
> return false;
> - }
>
> __folio_mark_dirty(folio, mapping, !folio_test_private(folio));
> - folio_memcg_unlock(folio);
>
> if (mapping->host) {
> /* !PageAnon && !swapper_space */
> @@ -2975,14 +2967,12 @@ void __folio_cancel_dirty(struct folio *folio)
> struct bdi_writeback *wb;
> struct wb_lock_cookie cookie = {};
>
> - folio_memcg_lock(folio);
> wb = unlocked_inode_to_wb_begin(inode, &cookie);
>
> if (folio_test_clear_dirty(folio))
> folio_account_cleaned(folio, wb);
>
> unlocked_inode_to_wb_end(inode, &cookie);
> - folio_memcg_unlock(folio);
> } else {
> folio_clear_dirty(folio);
> }
> --
> 2.43.5
--
Michal Hocko
SUSE Labs
On Fri, Oct 25, 2024 at 08:56:14AM GMT, Michal Hocko wrote: > On Thu 24-10-24 18:23:00, Shakeel Butt wrote: > > During the era of memcg charge migration, the kernel has to be make sure > > that the dirty stat updates do not race with the charge migration. > > Otherwise it might update the dirty stats of the wrong memcg. Now with > > the memcg charge migration deprecated, there is no more race for dirty > > s@deprecated@gone@ > > > stat updates and the previous locking can be removed. > > > > Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev> > > LGTM otherwise > Acked-by: Michal Hocko <mhocko@suse.com> > Thanks Michal for the review. Andrew, please fixup the commit message as suggested by Michal when you pick this series.
© 2016 - 2024 Red Hat, Inc.