From: Alex Shi <alex.shi@linux.alibaba.com> To: akpm@linux-foundation.org, mgorman@techsingularity.net, tj@kernel.org, hughd@google.com, khlebnikov@yandex-team.ru, daniel.m.jordan@oracle.com, yang.shi@linux.alibaba.com, willy@infradead.org, hannes@cmpxchg.org, lkp@intel.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, shakeelb@google.com, iamjoonsoo.kim@lge.com, richard.weiyang@gmail.com Cc: Alex Shi <alex.shi@linux.alibaba.com>, "Kirill A. Shutemov" <kirill@shutemov.name>, Andrea Arcangeli <aarcange@redhat.com> Subject: [PATCH v11 07/16] mm/thp: narrow lru locking Date: Thu, 28 May 2020 19:00:49 +0800 [thread overview] Message-ID: <1590663658-184131-8-git-send-email-alex.shi@linux.alibaba.com> (raw) In-Reply-To: <1590663658-184131-1-git-send-email-alex.shi@linux.alibaba.com> 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/preempt_disable to block interrupt re-entry and statistic update. Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com> Signed-off-by: Wei Yang <richard.weiyang@gmail.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org --- mm/huge_memory.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a4ba75e143b3..44d4b45281a3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2418,8 +2418,6 @@ 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); @@ -2431,6 +2429,11 @@ static void __split_huge_page(struct page *page, struct list_head *list, xa_lock(&swap_cache->i_pages); } + /* lock lru list/PageCompound, isolate 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 */ @@ -2448,8 +2451,8 @@ static void __split_huge_page(struct page *page, struct list_head *list, head + i, 0); } } - ClearPageCompound(head); + spin_unlock(&pgdat->lru_lock); split_page_owner(head, HPAGE_PMD_ORDER); @@ -2467,8 +2470,8 @@ 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); + preempt_enable(); + local_irq_restore(flags); remap_page(head); @@ -2607,7 +2610,6 @@ 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; @@ -2673,9 +2675,8 @@ 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_save(flags); + preempt_disable(); if (mapping) { XA_STATE(xas, &mapping->i_pages, page_index(head)); @@ -2724,7 +2725,8 @@ 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); + preempt_enable(); + local_irq_restore(flags); remap_page(head); ret = -EBUSY; } -- 1.8.3.1
WARNING: multiple messages have this Message-ID (diff)
From: Alex Shi <alex.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org> To: akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org, mgorman-3eNAlZScCAx27rWaFMvyedHuzzzSOjJt@public.gmane.org, tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org, hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org, khlebnikov-XoJtRXgx1JseBXzfvpsJ4g@public.gmane.org, daniel.m.jordan-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org, yang.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org, willy-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org, hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org, lkp-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, shakeelb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org, iamjoonsoo.kim-Hm3cg6mZ9cc@public.gmane.org, richard.weiyang-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org Cc: Alex Shi <alex.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org>, "Kirill A. Shutemov" <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>, Andrea Arcangeli <aarcange-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> Subject: [PATCH v11 07/16] mm/thp: narrow lru locking Date: Thu, 28 May 2020 19:00:49 +0800 [thread overview] Message-ID: <1590663658-184131-8-git-send-email-alex.shi@linux.alibaba.com> (raw) In-Reply-To: <1590663658-184131-1-git-send-email-alex.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org> 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/preempt_disable to block interrupt re-entry and statistic update. Signed-off-by: Alex Shi <alex.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org> Signed-off-by: Wei Yang <richard.weiyang-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> Cc: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org> Cc: Andrea Arcangeli <aarcange-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> Cc: Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org> Cc: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org> Cc: linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org --- mm/huge_memory.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a4ba75e143b3..44d4b45281a3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2418,8 +2418,6 @@ 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); @@ -2431,6 +2429,11 @@ static void __split_huge_page(struct page *page, struct list_head *list, xa_lock(&swap_cache->i_pages); } + /* lock lru list/PageCompound, isolate 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 */ @@ -2448,8 +2451,8 @@ static void __split_huge_page(struct page *page, struct list_head *list, head + i, 0); } } - ClearPageCompound(head); + spin_unlock(&pgdat->lru_lock); split_page_owner(head, HPAGE_PMD_ORDER); @@ -2467,8 +2470,8 @@ 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); + preempt_enable(); + local_irq_restore(flags); remap_page(head); @@ -2607,7 +2610,6 @@ 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; @@ -2673,9 +2675,8 @@ 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_save(flags); + preempt_disable(); if (mapping) { XA_STATE(xas, &mapping->i_pages, page_index(head)); @@ -2724,7 +2725,8 @@ 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); + preempt_enable(); + local_irq_restore(flags); remap_page(head); ret = -EBUSY; } -- 1.8.3.1
next prev parent reply other threads:[~2020-05-28 11:03 UTC|newest] Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-05-28 11:00 [PATCH v11 00/16] per memcg lru lock Alex Shi 2020-05-28 11:00 ` [PATCH v11 01/16] mm/vmscan: remove unnecessary lruvec adding Alex Shi 2020-05-28 11:00 ` [PATCH v11 02/16] mm/page_idle: no unlikely double check for idle page counting Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 03/16] mm/compaction: correct the comments of compact_defer_shift Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 04/16] mm/compaction: rename compact_deferred as compact_should_defer Alex Shi 2020-05-28 11:00 ` [PATCH v11 05/16] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 06/16] mm/thp: clean up lru_add_page_tail Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` Alex Shi [this message] 2020-05-28 11:00 ` [PATCH v11 07/16] mm/thp: narrow lru locking Alex Shi 2020-05-28 11:00 ` [PATCH v11 08/16] mm/memcg: add debug checking in lock_page_memcg Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 09/16] mm/lru: introduce TestClearPageLRU Alex Shi 2020-05-28 11:00 ` [PATCH v11 10/16] mm/compaction: do page isolation first in compaction Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 11/16] mm/mlock: reorder isolation sequence during munlock Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 12/16] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 13/16] mm/lru: introduce the relock_page_lruvec function Alex Shi 2020-05-28 11:00 ` [PATCH v11 14/16] mm/vmscan: use relock for move_pages_to_lru Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 15/16] mm/pgdat: remove pgdat lru_lock Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-05-28 11:00 ` [PATCH v11 16/16] mm/lru: revise the comments of lru_lock Alex Shi 2020-05-28 11:00 ` Alex Shi 2020-06-08 4:15 ` [PATCH v11 00/16] per memcg lru lock Hugh Dickins 2020-06-08 4:15 ` Hugh Dickins 2020-06-08 4:15 ` Hugh Dickins 2020-06-08 6:13 ` Alex Shi 2020-06-08 6:13 ` Alex Shi 2020-06-10 3:22 ` Hugh Dickins 2020-06-10 3:22 ` Hugh Dickins 2020-06-10 3:22 ` Hugh Dickins 2020-06-11 6:06 ` Alex Shi 2020-06-11 6:06 ` Alex Shi 2020-06-11 22:09 ` Hugh Dickins 2020-06-11 22:09 ` Hugh Dickins 2020-06-11 22:09 ` Hugh Dickins 2020-06-12 10:43 ` Alex Shi 2020-06-12 10:43 ` Alex Shi 2020-06-16 6:14 ` Alex Shi 2020-06-16 6:14 ` Alex Shi
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1590663658-184131-8-git-send-email-alex.shi@linux.alibaba.com \ --to=alex.shi@linux.alibaba.com \ --cc=aarcange@redhat.com \ --cc=akpm@linux-foundation.org \ --cc=cgroups@vger.kernel.org \ --cc=daniel.m.jordan@oracle.com \ --cc=hannes@cmpxchg.org \ --cc=hughd@google.com \ --cc=iamjoonsoo.kim@lge.com \ --cc=khlebnikov@yandex-team.ru \ --cc=kirill@shutemov.name \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=lkp@intel.com \ --cc=mgorman@techsingularity.net \ --cc=richard.weiyang@gmail.com \ --cc=shakeelb@google.com \ --cc=tj@kernel.org \ --cc=willy@infradead.org \ --cc=yang.shi@linux.alibaba.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.