Hi Rafael,
On Wed, Aug 08, 2012 at 07:53:19PM -0300, Rafael Aquini wrote:
> Memory fragmentation introduced by ballooning might reduce significantly
> the number of 2MB contiguous memory blocks that can be used within a guest,
> thus imposing performance penalties associated with the reduced number of
> transparent huge pages that could be used by the guest workload.
>
> This patch introduces the helper functions as well as the necessary changes
> to teach compaction and migration bits how to cope with pages which are
> part of a guest memory balloon, in order to make them movable by memory
> compaction procedures.
>
> Signed-off-by: Rafael Aquini <aqu...@redhat.com>
> ---
> include/linux/mm.h | 17 +++++++
> mm/compaction.c | 131
> +++++++++++++++++++++++++++++++++++++++++++++--------
> mm/migrate.c | 30 +++++++++++-
> 3 files changed, 158 insertions(+), 20 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 311be90..18f978b 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1662,5 +1662,22 @@ static inline unsigned int
> debug_guardpage_minorder(void) { return 0; }
> static inline bool page_is_guard(struct page *page) { return false; }
> #endif /* CONFIG_DEBUG_PAGEALLOC */
>
> +#if (defined(CONFIG_VIRTIO_BALLOON) || \
> + defined(CONFIG_VIRTIO_BALLOON_MODULE)) && defined(CONFIG_COMPACTION)
> +extern bool isolate_balloon_page(struct page *);
> +extern bool putback_balloon_page(struct page *);
> +extern struct address_space *balloon_mapping;
> +
> +static inline bool movable_balloon_page(struct page *page)
> +{
> + return (page->mapping && page->mapping == balloon_mapping);
> +}
> +
> +#else
> +static inline bool isolate_balloon_page(struct page *page) { return false; }
> +static inline bool putback_balloon_page(struct page *page) { return false; }
> +static inline bool movable_balloon_page(struct page *page) { return false; }
> +#endif /* (VIRTIO_BALLOON || VIRTIO_BALLOON_MODULE) && CONFIG_COMPACTION */
> +
> #endif /* __KERNEL__ */
> #endif /* _LINUX_MM_H */
> diff --git a/mm/compaction.c b/mm/compaction.c
> index e78cb96..7372592 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -14,6 +14,7 @@
> #include <linux/backing-dev.h>
> #include <linux/sysctl.h>
> #include <linux/sysfs.h>
> +#include <linux/export.h>
> #include "internal.h"
>
> #if defined CONFIG_COMPACTION || defined CONFIG_CMA
> @@ -21,6 +22,90 @@
> #define CREATE_TRACE_POINTS
> #include <trace/events/compaction.h>
>
> +#if defined(CONFIG_VIRTIO_BALLOON) || defined(CONFIG_VIRTIO_BALLOON_MODULE)
> +/*
> + * Balloon pages special page->mapping.
> + * Users must properly allocate and initialize an instance of
> balloon_mapping,
> + * and set it as the page->mapping for balloon enlisted page instances.
> + * There is no need on utilizing struct address_space locking schemes for
> + * balloon_mapping as, once it gets initialized at balloon driver, it will
> + * remain just like a static reference that helps us on identifying a guest
> + * ballooned page by its mapping, as well as it will keep the 'a_ops'
> callback
> + * pointers to the functions that will execute the balloon page mobility
> tasks.
> + *
> + * address_space_operations necessary methods for ballooned pages:
> + * .migratepage - used to perform balloon's page migration (as is)
> + * .invalidatepage - used to isolate a page from balloon's page list
> + * .freepage - used to reinsert an isolated page to balloon's page
> list
> + */
> +struct address_space *balloon_mapping;
> +EXPORT_SYMBOL_GPL(balloon_mapping);
> +
> +static inline void __isolate_balloon_page(struct page *page)
> +{
> + page->mapping->a_ops->invalidatepage(page, 0);
> +}
> +
> +static inline void __putback_balloon_page(struct page *page)
> +{
> + page->mapping->a_ops->freepage(page);
> +}
> +
> +/* __isolate_lru_page() counterpart for a ballooned page */
> +bool isolate_balloon_page(struct page *page)
> +{
> + if (WARN_ON(!movable_balloon_page(page)))
> + return false;
> +
> + if (likely(get_page_unless_zero(page))) {
> + /*
> + * As balloon pages are not isolated from LRU lists, concurrent
> + * compaction threads can race against page migration functions
> + * move_to_new_page() & __unmap_and_move().
> + * In order to avoid having an already isolated balloon page
> + * being (wrongly) re-isolated while it is under migration,
> + * lets be sure we have the page lock before proceeding with
> + * the balloon page isolation steps.
> + */
> + if (likely(trylock_page(page))) {
> + /*
> + * A ballooned page, by default, has just one refcount.
> + * Prevent concurrent compaction threads from isolating
> + * an already isolated balloon page.
> + */
> + if (movable_balloon_page(page) &&
> + (page_count(page) == 2)) {
> + __isolate_balloon_page(page);
> + unlock_page(page);
> + return true;
> + }
> + unlock_page(page);
> + }
> + /* Drop refcount taken for this already isolated page */
> + put_page(page);
> + }
> + return false;
> +}
> +
> +/* putback_lru_page() counterpart for a ballooned page */
> +bool putback_balloon_page(struct page *page)
> +{
> + if (WARN_ON(!movable_balloon_page(page)))
> + return false;
> +
> + if (likely(trylock_page(page))) {
> + if (movable_balloon_page(page)) {
> + __putback_balloon_page(page);
> + put_page(page);
> + unlock_page(page);
> + return true;
> + }
> + unlock_page(page);
> + }
> + return false;
> +}
> +#endif /* CONFIG_VIRTIO_BALLOON || CONFIG_VIRTIO_BALLOON_MODULE */
> +
> static unsigned long release_freepages(struct list_head *freelist)
> {
> struct page *page, *next;
> @@ -312,32 +397,40 @@ isolate_migratepages_range(struct zone *zone, struct
> compact_control *cc,
> continue;
> }
>
> - if (!PageLRU(page))
> - continue;
> -
> /*
> - * PageLRU is set, and lru_lock excludes isolation,
> - * splitting and collapsing (collapsing has already
> - * happened if PageLRU is set).
> + * It is possible to migrate LRU pages and balloon pages.
> + * Skip any other type of page.
> */
> - if (PageTransHuge(page)) {
> - low_pfn += (1 << compound_order(page)) - 1;
> - continue;
> - }
> + if (PageLRU(page)) {
> + /*
> + * PageLRU is set, and lru_lock excludes isolation,
> + * splitting and collapsing (collapsing has already
> + * happened if PageLRU is set).
> + */
> + if (PageTransHuge(page)) {
> + low_pfn += (1 << compound_order(page)) - 1;
> + continue;
> + }
>
> - if (!cc->sync)
> - mode |= ISOLATE_ASYNC_MIGRATE;
> + if (!cc->sync)
> + mode |= ISOLATE_ASYNC_MIGRATE;
>
> - lruvec = mem_cgroup_page_lruvec(page, zone);
> + lruvec = mem_cgroup_page_lruvec(page, zone);
>
> - /* Try isolate the page */
> - if (__isolate_lru_page(page, mode) != 0)
> - continue;
> + /* Try isolate the page */
> + if (__isolate_lru_page(page, mode) != 0)
> + continue;
> +
> + VM_BUG_ON(PageTransCompound(page));
>
> - VM_BUG_ON(PageTransCompound(page));
> + /* Successfully isolated */
> + del_page_from_lru_list(page, lruvec, page_lru(page));
> + } else if (unlikely(movable_balloon_page(page))) {
> + if (!isolate_balloon_page(page))
> + continue;
> + } else
> + continue;
>
> - /* Successfully isolated */
> - del_page_from_lru_list(page, lruvec, page_lru(page));
> list_add(&page->lru, migratelist);
> cc->nr_migratepages++;
> nr_isolated++;
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 77ed2d7..871a304 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -79,7 +79,10 @@ void putback_lru_pages(struct list_head *l)
> list_del(&page->lru);
> dec_zone_page_state(page, NR_ISOLATED_ANON +
> page_is_file_cache(page));
> - putback_lru_page(page);
> + if (unlikely(movable_balloon_page(page)))
> + WARN_ON(!putback_balloon_page(page));
> + else
> + putback_lru_page(page);
> }
Don't hack putback_lru_pages. It's a function for handling LRU pages
and is used by several places.
Plz, don't add complexity to unrelavant parts.
You can define a new function putback_migratepages should be used as pair with
isolate_migratepages_range so that both functions are aware of balloon page.
IMHO, it's better abstraction rather than hook of generic function.
Otherwise, Looks good to me.
Thanks.
--
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
