Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries
are deleted from the llist.
llist_del_all are lock free with itself. folio_clear_hugetlb_hwpoison()s
from __update_and_free_hugetlb_folio and memory_failure won't need
explicit locking when freeing the raw_hwp_list.
Signed-off-by: Jiaqi Yan <[email protected]>
---
mm/memory-failure.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 004a02f44271..c415c3c462a3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1825,12 +1825,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
{
- struct llist_head *head;
- struct llist_node *t, *tnode;
+ struct llist_node *t, *tnode, *head;
unsigned long count = 0;
- head = raw_hwp_list_head(folio);
- llist_for_each_safe(tnode, t, head->first) {
+ head = llist_del_all(raw_hwp_list_head(folio));
+ llist_for_each_safe(tnode, t, head) {
struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
if (move_flag)
@@ -1840,7 +1839,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
kfree(p);
count++;
}
- llist_del_all(head);
return count;
}
--
2.41.0.162.gfafddb0af9-goog
On Fri, Jun 23, 2023 at 04:40:12PM +0000, Jiaqi Yan wrote:
> Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries
> are deleted from the llist.
>
> llist_del_all are lock free with itself. folio_clear_hugetlb_hwpoison()s
> from __update_and_free_hugetlb_folio and memory_failure won't need
> explicit locking when freeing the raw_hwp_list.
>
> Signed-off-by: Jiaqi Yan <[email protected]>
(Sorry if stupid question...) folio_set_hugetlb_hwpoison() also calls
llist_for_each_safe() but it still traverses the list without calling
llist_del_all(). This convention applies only when removing item(s)?
Thanks,
Naoya Horiguchi
> ---
> mm/memory-failure.c | 8 +++-----
> 1 file changed, 3 insertions(+), 5 deletions(-)
>
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 004a02f44271..c415c3c462a3 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1825,12 +1825,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
>
> static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> {
> - struct llist_head *head;
> - struct llist_node *t, *tnode;
> + struct llist_node *t, *tnode, *head;
> unsigned long count = 0;
>
> - head = raw_hwp_list_head(folio);
> - llist_for_each_safe(tnode, t, head->first) {
> + head = llist_del_all(raw_hwp_list_head(folio));
> + llist_for_each_safe(tnode, t, head) {
> struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
>
> if (move_flag)
> @@ -1840,7 +1839,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> kfree(p);
> count++;
> }
> - llist_del_all(head);
> return count;
> }
>
> --
> 2.41.0.162.gfafddb0af9-goog
>
>
>
On Fri, Jun 30, 2023 at 7:52 AM Naoya Horiguchi
<[email protected]> wrote:
>
> On Fri, Jun 23, 2023 at 04:40:12PM +0000, Jiaqi Yan wrote:
> > Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries
> > are deleted from the llist.
> >
> > llist_del_all are lock free with itself. folio_clear_hugetlb_hwpoison()s
> > from __update_and_free_hugetlb_folio and memory_failure won't need
> > explicit locking when freeing the raw_hwp_list.
> >
> > Signed-off-by: Jiaqi Yan <[email protected]>
>
> (Sorry if stupid question...) folio_set_hugetlb_hwpoison() also calls
> llist_for_each_safe() but it still traverses the list without calling
> llist_del_all(). This convention applies only when removing item(s)?
I think in our previous discussion, Mike and I agree as of today's
code in hugetlb.c and memory-failure.c, concurrent adding, deleting,
traversing are fine with each other and with themselves [1], but new
code need to be careful wrt ops on raw_hwp_list.
This patch is a low-hanging fruit to ensure any caller of
__folio_free_raw_hwp won't introduce any problem by correcting one
thing in __folio_free_raw_hwp: since it wants to delete raw_hwp_page
entries in the list, it should do it by first llist_del_all, and then
kfree with a llist_for_each_safe.
As for folio_set_hugetlb_hwpoison, I am not very comfortable fixing
it. I imagine a way to fix it is llist_del_all() =>
llist_for_each_safe{...} => llist_add_batch(), or llist_add() within
llist_for_each_safe{...}. I haven't really thought through if this is
a correct fix.
[1] https://lore.kernel.org/lkml/CACw3F51o1ZFSYZa+XLnk4Wwjy2w_q=Kn+aOQs0=qpfG-ZYDFKg@mail.gmail.com/#t
>
> Thanks,
> Naoya Horiguchi
>
> > ---
> > mm/memory-failure.c | 8 +++-----
> > 1 file changed, 3 insertions(+), 5 deletions(-)
> >
> > diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> > index 004a02f44271..c415c3c462a3 100644
> > --- a/mm/memory-failure.c
> > +++ b/mm/memory-failure.c
> > @@ -1825,12 +1825,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
> >
> > static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> > {
> > - struct llist_head *head;
> > - struct llist_node *t, *tnode;
> > + struct llist_node *t, *tnode, *head;
> > unsigned long count = 0;
> >
> > - head = raw_hwp_list_head(folio);
> > - llist_for_each_safe(tnode, t, head->first) {
> > + head = llist_del_all(raw_hwp_list_head(folio));
> > + llist_for_each_safe(tnode, t, head) {
> > struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
> >
> > if (move_flag)
> > @@ -1840,7 +1839,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> > kfree(p);
> > count++;
> > }
> > - llist_del_all(head);
> > return count;
> > }
> >
> > --
> > 2.41.0.162.gfafddb0af9-goog
> >
> >
> >
On Fri, Jun 30, 2023 at 01:59:23PM -0700, Jiaqi Yan wrote:
> On Fri, Jun 30, 2023 at 7:52 AM Naoya Horiguchi
> <[email protected]> wrote:
> >
> > On Fri, Jun 23, 2023 at 04:40:12PM +0000, Jiaqi Yan wrote:
> > > Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries
> > > are deleted from the llist.
> > >
> > > llist_del_all are lock free with itself. folio_clear_hugetlb_hwpoison()s
> > > from __update_and_free_hugetlb_folio and memory_failure won't need
> > > explicit locking when freeing the raw_hwp_list.
> > >
> > > Signed-off-by: Jiaqi Yan <[email protected]>
> >
> > (Sorry if stupid question...) folio_set_hugetlb_hwpoison() also calls
> > llist_for_each_safe() but it still traverses the list without calling
> > llist_del_all(). This convention applies only when removing item(s)?
>
> I think in our previous discussion, Mike and I agree as of today's
> code in hugetlb.c and memory-failure.c, concurrent adding, deleting,
> traversing are fine with each other and with themselves [1], but new
> code need to be careful wrt ops on raw_hwp_list.
>
> This patch is a low-hanging fruit to ensure any caller of
> __folio_free_raw_hwp won't introduce any problem by correcting one
> thing in __folio_free_raw_hwp: since it wants to delete raw_hwp_page
> entries in the list, it should do it by first llist_del_all, and then
> kfree with a llist_for_each_safe.
Thanks for the explanation, this is worth adding to the patch description
for future developers to understand the background.
>
> As for folio_set_hugetlb_hwpoison, I am not very comfortable fixing
> it. I imagine a way to fix it is llist_del_all() =>
> llist_for_each_safe{...} => llist_add_batch(), or llist_add() within
> llist_for_each_safe{...}. I haven't really thought through if this is
> a correct fix.
I see. Changing folio_set_hugetlb_hwpoison() like this is a little too complex
considering that this fix is for precaution.
So no change on this for now is fine to me.
Anyway this patch looks fine to me.
Acked-by: Naoya Horiguchi <[email protected]>
>
> [1] https://lore.kernel.org/lkml/CACw3F51o1ZFSYZa+XLnk4Wwjy2w_q=Kn+aOQs0=qpfG-ZYDFKg@mail.gmail.com/#t
>
>
> >
> > Thanks,
> > Naoya Horiguchi
> >
> > > ---
> > > mm/memory-failure.c | 8 +++-----
> > > 1 file changed, 3 insertions(+), 5 deletions(-)
> > >
> > > diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> > > index 004a02f44271..c415c3c462a3 100644
> > > --- a/mm/memory-failure.c
> > > +++ b/mm/memory-failure.c
> > > @@ -1825,12 +1825,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
> > >
> > > static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> > > {
> > > - struct llist_head *head;
> > > - struct llist_node *t, *tnode;
> > > + struct llist_node *t, *tnode, *head;
> > > unsigned long count = 0;
> > >
> > > - head = raw_hwp_list_head(folio);
> > > - llist_for_each_safe(tnode, t, head->first) {
> > > + head = llist_del_all(raw_hwp_list_head(folio));
> > > + llist_for_each_safe(tnode, t, head) {
> > > struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
> > >
> > > if (move_flag)
> > > @@ -1840,7 +1839,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> > > kfree(p);
> > > count++;
> > > }
> > > - llist_del_all(head);
> > > return count;
> > > }
> > >
> > > --
> > > 2.41.0.162.gfafddb0af9-goog
> > >
> > >
> > >
On 06/23/23 16:40, Jiaqi Yan wrote:
> Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries
> are deleted from the llist.
>
> llist_del_all are lock free with itself. folio_clear_hugetlb_hwpoison()s
> from __update_and_free_hugetlb_folio and memory_failure won't need
> explicit locking when freeing the raw_hwp_list.
>
> Signed-off-by: Jiaqi Yan <[email protected]>
> ---
> mm/memory-failure.c | 8 +++-----
> 1 file changed, 3 insertions(+), 5 deletions(-)
After updating the reason for patch in commit message as suggested by Naoya,
Acked-by: Mike Kravetz <[email protected]>
--
Mike Kravetz
>
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 004a02f44271..c415c3c462a3 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1825,12 +1825,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
>
> static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> {
> - struct llist_head *head;
> - struct llist_node *t, *tnode;
> + struct llist_node *t, *tnode, *head;
> unsigned long count = 0;
>
> - head = raw_hwp_list_head(folio);
> - llist_for_each_safe(tnode, t, head->first) {
> + head = llist_del_all(raw_hwp_list_head(folio));
> + llist_for_each_safe(tnode, t, head) {
> struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
>
> if (move_flag)
> @@ -1840,7 +1839,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> kfree(p);
> count++;
> }
> - llist_del_all(head);
> return count;
> }
>
> --
> 2.41.0.162.gfafddb0af9-goog
>
On Wed, Jul 5, 2023 at 4:36 PM Mike Kravetz <[email protected]> wrote:
>
> On 06/23/23 16:40, Jiaqi Yan wrote:
> > Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries
> > are deleted from the llist.
> >
> > llist_del_all are lock free with itself. folio_clear_hugetlb_hwpoison()s
> > from __update_and_free_hugetlb_folio and memory_failure won't need
> > explicit locking when freeing the raw_hwp_list.
> >
> > Signed-off-by: Jiaqi Yan <[email protected]>
> > ---
> > mm/memory-failure.c | 8 +++-----
> > 1 file changed, 3 insertions(+), 5 deletions(-)
>
> After updating the reason for patch in commit message as suggested by Naoya,
Thank you both Mike and Naoya! I will add the explanation in the next version.
>
> Acked-by: Mike Kravetz <[email protected]>
>
> --
> Mike Kravetz
>
> >
> > diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> > index 004a02f44271..c415c3c462a3 100644
> > --- a/mm/memory-failure.c
> > +++ b/mm/memory-failure.c
> > @@ -1825,12 +1825,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
> >
> > static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> > {
> > - struct llist_head *head;
> > - struct llist_node *t, *tnode;
> > + struct llist_node *t, *tnode, *head;
> > unsigned long count = 0;
> >
> > - head = raw_hwp_list_head(folio);
> > - llist_for_each_safe(tnode, t, head->first) {
> > + head = llist_del_all(raw_hwp_list_head(folio));
> > + llist_for_each_safe(tnode, t, head) {
> > struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
> >
> > if (move_flag)
> > @@ -1840,7 +1839,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
> > kfree(p);
> > count++;
> > }
> > - llist_del_all(head);
> > return count;
> > }
> >
> > --
> > 2.41.0.162.gfafddb0af9-goog
> >