The patch titled
Subject: mm/thp: narrow lru locking
has been added to the -mm tree. Its filename is
mm-thp-narrow-lru-locking.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-narrow-lru-locking.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-narrow-lru-locking.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Subject: mm/thp: narrow lru locking
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().
Link: http://lkml.kernel.org/r/1597144232-11370-6-git-send-email-alex.shi@xxxxxxxxxxxxxxxxx
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Signed-off-by: Wei Yang <richard.weiyang@xxxxxxxxx>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 25 +++++++++++++------------
1 file changed, 13 insertions(+), 12 deletions(-)
--- a/mm/huge_memory.c~mm-thp-narrow-lru-locking
+++ a/mm/huge_memory.c
@@ -2397,7 +2397,7 @@ static void __split_huge_page_tail(struc
}
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);
@@ -2406,8 +2406,6 @@ static void __split_huge_page(struct pag
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);
@@ -2419,6 +2417,11 @@ static void __split_huge_page(struct pag
xa_lock(&swap_cache->i_pages);
}
+ /* prevent PageLRU to go away from under us, and freeze lru stats */
+ 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 */
@@ -2438,6 +2441,8 @@ static void __split_huge_page(struct pag
}
ClearPageCompound(head);
+ spin_unlock(&pgdat->lru_lock);
+ /* Caller disabled irqs, so they are still disabled here */
split_page_owner(head, HPAGE_PMD_ORDER);
@@ -2455,8 +2460,7 @@ static void __split_huge_page(struct pag
page_ref_add(head, 2);
xa_unlock(&head->mapping->i_pages);
}
-
- spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+ local_irq_enable();
remap_page(head);
@@ -2595,12 +2599,10 @@ bool can_split_huge_page(struct page *pa
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);
@@ -2661,9 +2663,8 @@ int split_huge_page_to_list(struct page
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);
-
+ /* block interrupt reentry in xa_lock and spinlock */
+ local_irq_disable();
if (mapping) {
XA_STATE(xas, &mapping->i_pages, page_index(head));
@@ -2693,7 +2694,7 @@ int split_huge_page_to_list(struct page
__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) };
@@ -2712,7 +2713,7 @@ int split_huge_page_to_list(struct page
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;
}
_
Patches currently in -mm which might be from alex.shi@xxxxxxxxxxxxxxxxx are
mm-memcg-warning-on-memcg-after-readahead-page-charged.patch
mm-memcg-remove-useless-check-on-page-mem_cgroup.patch
mm-thp-move-lru_add_page_tail-func-to-huge_memoryc.patch
mm-thp-clean-up-lru_add_page_tail.patch
mm-thp-remove-code-path-which-never-got-into.patch
mm-thp-narrow-lru-locking.patch
