On 6/8/26 10:40, Michael S. Tsirkin wrote: > When a balloon page marked PageZeroed is freed during migration, > use put_page_zeroed() to propagate the zeroed hint to the buddy > allocator. Previously the hint was silently lost via plain put_page(). > > No page has PageZeroed set yet; the next patch > (VIRTIO_BALLOON_F_DEVICE_INIT_ON_INFLATE) will set it on > pages the host has zeroed during inflate. > Note: during balloon migration, the migration core holds an > extra reference, so put_page_zeroed() will not be the final > put. The zeroed hint is lost in that case, which is > acceptable: it is a best-effort optimization. > > Signed-off-by: Michael S. Tsirkin <[email protected]> > Assisted-by: Claude:claude-opus-4-6 > --- > mm/balloon.c | 10 +++++++++- > 1 file changed, 9 insertions(+), 1 deletion(-) > > diff --git a/mm/balloon.c b/mm/balloon.c > index 96a8f1e20bc6..6c9dd8ab0c5d 100644 > --- a/mm/balloon.c > +++ b/mm/balloon.c > @@ -324,7 +324,15 @@ static int balloon_page_migrate(struct page *newpage, > struct page *page, > balloon_page_finalize(page); > spin_unlock_irqrestore(&balloon_pages_lock, flags); > > - put_page(page); > + if (PageZeroed(page)) { > + /* Atomic to serialize with memory_failure's > + * TestSetPageHWPoison; not under zone->lock here. > + */ > + ClearPageZeroed(page); > + put_page_zeroed(page); > + } else { > + put_page(page); > + } > > return 0; > }
I think I raised previously that this is best done later. This patch set is currently trying to do too many things, and is on the larger side. I think we should try to reduce it to the bare minimum and get some agreement between maintainers on the core design. -- Cheers, David
