Re: [PATCH v14 07/20] mm/thp: narrow lru locking

From: Alex Shi
Date: Mon Jul 06 2020 - 05:15:46 EST


Hi Kirill & Johannes & Matthew,

Would you like to give some comments or share your concern of this patchset,
specialy for THP part?

Many Thanks
Alex

在 2020/7/3 下午1:07, Alex Shi 写道:
> lru_lock and page cache xa_lock have no reason with current sequence,
> put them together isn't necessary. let's narrow the lru locking, but
> left the local_irq_disable to block interrupt re-entry and statistic update.
>
> Hugh Dickins point: split_huge_page_to_list() was already silly,to be
> using the _irqsave variant: it's just been taking sleeping locks, so
> would already be broken if entered with interrupts enabled.
> so we can save passing flags argument down to __split_huge_page().
>
> Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Wei Yang <richard.weiyang@xxxxxxxxx>
> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: linux-mm@xxxxxxxxx
> Cc: linux-kernel@xxxxxxxxxxxxxxx
> ---
> mm/huge_memory.c | 24 ++++++++++++------------
> 1 file changed, 12 insertions(+), 12 deletions(-)
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index b18f21da4dac..607869330329 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2433,7 +2433,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
> }
>
> static void __split_huge_page(struct page *page, struct list_head *list,
> - pgoff_t end, unsigned long flags)
> + pgoff_t end)
> {
> struct page *head = compound_head(page);
> pg_data_t *pgdat = page_pgdat(head);
> @@ -2442,8 +2442,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> unsigned long offset = 0;
> int i;
>
> - lruvec = mem_cgroup_page_lruvec(head, pgdat);
> -
> /* complete memcg works before add pages to LRU */
> mem_cgroup_split_huge_fixup(head);
>
> @@ -2455,6 +2453,11 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> xa_lock(&swap_cache->i_pages);
> }
>
> + /* lock lru list/PageCompound, ref freezed by page_ref_freeze */
> + spin_lock(&pgdat->lru_lock);
> +
> + lruvec = mem_cgroup_page_lruvec(head, pgdat);
> +
> for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
> __split_huge_page_tail(head, i, lruvec, list);
> /* Some pages can be beyond i_size: drop them from page cache */
> @@ -2474,6 +2477,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> }
>
> ClearPageCompound(head);
> + spin_unlock(&pgdat->lru_lock);
> + /* Caller disabled irqs, so they are still disabled here */
>
> split_page_owner(head, HPAGE_PMD_ORDER);
>
> @@ -2491,8 +2496,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> page_ref_add(head, 2);
> xa_unlock(&head->mapping->i_pages);
> }
> -
> - spin_unlock_irqrestore(&pgdat->lru_lock, flags);
> + local_irq_enable();
>
> remap_page(head);
>
> @@ -2631,12 +2635,10 @@ bool can_split_huge_page(struct page *page, int *pextra_pins)
> int split_huge_page_to_list(struct page *page, struct list_head *list)
> {
> struct page *head = compound_head(page);
> - struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
> struct deferred_split *ds_queue = get_deferred_split_queue(head);
> struct anon_vma *anon_vma = NULL;
> struct address_space *mapping = NULL;
> int count, mapcount, extra_pins, ret;
> - unsigned long flags;
> pgoff_t end;
>
> VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
> @@ -2697,9 +2699,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
> unmap_page(head);
> VM_BUG_ON_PAGE(compound_mapcount(head), head);
>
> - /* prevent PageLRU to go away from under us, and freeze lru stats */
> - spin_lock_irqsave(&pgdata->lru_lock, flags);
> -
> + local_irq_disable();
> if (mapping) {
> XA_STATE(xas, &mapping->i_pages, page_index(head));
>
> @@ -2729,7 +2729,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
> __dec_node_page_state(head, NR_FILE_THPS);
> }
>
> - __split_huge_page(page, list, end, flags);
> + __split_huge_page(page, list, end);
> if (PageSwapCache(head)) {
> swp_entry_t entry = { .val = page_private(head) };
>
> @@ -2748,7 +2748,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
> spin_unlock(&ds_queue->split_queue_lock);
> fail: if (mapping)
> xa_unlock(&mapping->i_pages);
> - spin_unlock_irqrestore(&pgdata->lru_lock, flags);
> + local_irq_enable();
> remap_page(head);
> ret = -EBUSY;
> }
>