Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Anthony Yznaga <anthony.yznaga@oracle.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: willy@infradead.org, corbet@lwn.net, tglx@linutronix.de,
	mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
	dave.hansen@linux.intel.com, luto@kernel.org,
	peterz@infradead.org, rppt@linux.ibm.com,
	akpm@linux-foundation.org, hughd@google.com,
	ebiederm@xmission.com, masahiroy@kernel.org, ardb@kernel.org,
	ndesaulniers@google.com, dima@golovin.in,
	daniel.kiper@oracle.com, nivedita@alum.mit.edu,
	rafael.j.wysocki@intel.com, dan.j.williams@intel.com,
	zhenzhong.duan@oracle.com, jroedel@suse.de, bhe@redhat.com,
	guro@fb.com, Thomas.Lendacky@amd.com,
	andriy.shevchenko@linux.intel.com, keescook@chromium.org,
	hannes@cmpxchg.org, minchan@kernel.org, mhocko@kernel.org,
	ying.huang@intel.com, yang.shi@linux.alibaba.com,
	gustavo@embeddedor.com, ziqian.lzq@antfin.com,
	vdavydov.dev@gmail.com, jason.zeng@intel.com,
	kevin.tian@intel.com, zhiyuan.lv@intel.com, lei.l.li@intel.com,
	paul.c.lai@intel.com, ashok.raj@intel.com,
	linux-fsdevel@vger.kernel.org, linux-doc@vger.kernel.org,
	kexec@lists.infradead.org
Subject: [RFC 38/43] mm: implement splicing a list of pages to the LRU
Date: Wed,  6 May 2020 17:42:04 -0700	[thread overview]
Message-ID: <1588812129-8596-39-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

Considerable contention on the LRU lock happens when multiple threads
are used to insert pages into a shmem file in parallel. To alleviate this
provide a way for pages to be added to the same LRU to be staged so that
they can be added by splicing lists and updating stats once with the lock
held. For now only unevictable pages are supported.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 include/linux/swap.h |  11 ++++++
 mm/swap.c            | 101 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 112 insertions(+)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index e1bbf7a16b27..462045f536a8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -346,6 +346,17 @@ extern void swap_setup(void);
 
 extern void lru_cache_add_active_or_unevictable(struct page *page,
 						struct vm_area_struct *vma);
+struct lru_splice {
+	struct list_head	splice;
+	struct list_head	*lru_head;
+	struct pglist_data	*pgdat;
+	struct lruvec		*lruvec;
+	enum lru_list		lru;
+	unsigned long		nr_pages[MAX_NR_ZONES];
+	unsigned long		pgculled;
+};
+extern void lru_splice_add_anon(struct page *page, struct lru_splice *splice);
+extern void add_splice_to_lru_list(struct lru_splice *splice);
 
 /* linux/mm/vmscan.c */
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
diff --git a/mm/swap.c b/mm/swap.c
index bf9a79fed62d..848f8b516471 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -187,6 +187,107 @@ int get_kernel_page(unsigned long start, int write, struct page **pages)
 }
 EXPORT_SYMBOL_GPL(get_kernel_page);
 
+/*
+ * Update stats and move accumulated pages from an lru_splice to the lru.
+ */
+void add_splice_to_lru_list(struct lru_splice *splice)
+{
+	struct pglist_data *pgdat = splice->pgdat;
+	struct lruvec *lruvec = splice->lruvec;
+	enum lru_list lru = splice->lru;
+	unsigned long flags = 0;
+	int zid;
+
+	spin_lock_irqsave(&pgdat->lru_lock, flags);
+	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+		if (splice->nr_pages[zid])
+			update_lru_size(lruvec, lru, zid, splice->nr_pages[zid]);
+	}
+	count_vm_events(UNEVICTABLE_PGCULLED, splice->pgculled);
+	list_splice(&splice->splice, splice->lru_head);
+	spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+
+	splice->lru_head = NULL;
+	splice->pgculled = 0;
+}
+
+static void add_page_to_lru_splice(struct page *page,
+				   struct lru_splice *splice,
+				   struct lruvec *lruvec, enum lru_list lru)
+{
+	int zid;
+
+	if (splice->lru_head == &lruvec->lists[lru]) {
+		list_add(&page->lru, &splice->splice);
+		splice->nr_pages[page_zonenum(page)] += hpage_nr_pages(page);
+		return;
+	}
+
+	INIT_LIST_HEAD(&splice->splice);
+	splice->lruvec = lruvec;
+	splice->lru_head = &lruvec->lists[lru];
+	splice->lru = lru;
+	list_add(&page->lru, &splice->splice);
+	for (zid = 0; zid < MAX_NR_ZONES; zid++)
+		splice->nr_pages[zid] = 0;
+	splice->nr_pages[page_zonenum(page)] = hpage_nr_pages(page);
+
+}
+
+/*
+ * Similar in functionality to __pagevec_lru_add_fn() but here the page is
+ * being added to an lru_splice and the LRU lock is not held.
+ */
+static void page_lru_splice_add(struct page *page, struct lruvec *lruvec, struct lru_splice *splice)
+{
+	enum lru_list lru;
+	int was_unevictable = TestClearPageUnevictable(page);
+
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	/* XXX only supports unevictable pages at the moment */
+	VM_BUG_ON_PAGE(was_unevictable, page);
+
+	SetPageLRU(page);
+	smp_mb();
+
+	lru = LRU_UNEVICTABLE;
+	ClearPageActive(page);
+	SetPageUnevictable(page);
+	if (!was_unevictable)
+		splice->pgculled++;
+
+	add_page_to_lru_splice(page, splice, lruvec, lru);
+	trace_mm_lru_insertion(page, lru);
+}
+
+static void lru_splice_add(struct page *page, struct lru_splice *splice)
+{
+	struct pglist_data *pagepgdat, *pgdat = splice->pgdat;
+	struct lruvec *lruvec;
+
+	pagepgdat = page_pgdat(page);
+
+	if (pagepgdat != pgdat) {
+		if (pgdat)
+			add_splice_to_lru_list(splice);
+		splice->pgdat = pagepgdat;
+	}
+
+	lruvec = mem_cgroup_page_lruvec(page, pagepgdat);
+	page_lru_splice_add(page, lruvec, splice);
+}
+
+void lru_splice_add_anon(struct page *page, struct lru_splice *splice)
+{
+	if (PageActive(page))
+		ClearPageActive(page);
+	get_page(page);
+
+	lru_splice_add(page, splice);
+
+	put_page(page);
+}
+
 static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
 	void *arg)
-- 
2.13.3


  parent reply	other threads:[~2020-05-07  0:47 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-07  0:41 [RFC 00/43] PKRAM: Preserved-over-Kexec RAM Anthony Yznaga
2020-05-07  0:41 ` [RFC 01/43] mm: add PKRAM API stubs and Kconfig Anthony Yznaga
2020-05-07  0:41 ` [RFC 02/43] mm: PKRAM: implement node load and save functions Anthony Yznaga
2020-05-07  0:41 ` [RFC 03/43] mm: PKRAM: implement object " Anthony Yznaga
2020-05-07  0:41 ` [RFC 04/43] mm: PKRAM: implement page stream operations Anthony Yznaga
2020-05-07  0:41 ` [RFC 05/43] mm: PKRAM: support preserving transparent hugepages Anthony Yznaga
2020-05-07  0:41 ` [RFC 06/43] mm: PKRAM: implement byte stream operations Anthony Yznaga
2020-05-07  0:41 ` [RFC 07/43] mm: PKRAM: link nodes by pfn before reboot Anthony Yznaga
2020-05-07  0:41 ` [RFC 08/43] mm: PKRAM: introduce super block Anthony Yznaga
2020-05-07  0:41 ` [RFC 09/43] PKRAM: build a physical mapping pagetable of pages to be preserved Anthony Yznaga
2020-05-07  0:41 ` [RFC 10/43] PKRAM: add code for walking the preserved pages pagetable Anthony Yznaga
2020-05-07  0:41 ` [RFC 11/43] PKRAM: pass the preserved pages pagetable to the next kernel Anthony Yznaga
2020-05-07  0:41 ` [RFC 12/43] mm: PKRAM: reserve preserved memory at boot Anthony Yznaga
2020-05-07  0:41 ` [RFC 13/43] mm: PKRAM: free preserved pages pagetable Anthony Yznaga
2020-05-07  0:41 ` [RFC 14/43] mm: memblock: PKRAM: prevent memblock resize from clobbering preserved pages Anthony Yznaga
2020-05-11 13:57   ` Mike Rapoport
2020-05-11 23:29     ` Anthony Yznaga
2020-05-07  0:41 ` [RFC 15/43] PKRAM: provide a way to ban pages from use by PKRAM Anthony Yznaga
2020-05-07  0:41 ` [RFC 16/43] kexec: PKRAM: prevent kexec clobbering preserved pages in some cases Anthony Yznaga
2020-05-07  0:41 ` [RFC 17/43] PKRAM: provide a way to check if a memory range has preserved pages Anthony Yznaga
2020-05-07  0:41 ` [RFC 18/43] kexec: PKRAM: avoid clobbering already " Anthony Yznaga
2020-05-07  0:41 ` [RFC 19/43] mm: PKRAM: allow preserved memory to be freed from userspace Anthony Yznaga
2020-05-07  0:41 ` [RFC 20/43] PKRAM: disable feature when running the kdump kernel Anthony Yznaga
2020-05-07  0:41 ` [RFC 21/43] x86/KASLR: PKRAM: support physical kaslr Anthony Yznaga
2020-05-07 17:51   ` Kees Cook
2020-05-07 18:41     ` Anthony Yznaga
2020-05-07  0:41 ` [RFC 22/43] mm: shmem: introduce shmem_insert_page Anthony Yznaga
2020-05-07  0:41 ` [RFC 23/43] mm: shmem: enable saving to PKRAM Anthony Yznaga
2020-05-07  0:41 ` [RFC 24/43] mm: shmem: prevent swapping of PKRAM-enabled tmpfs pages Anthony Yznaga
2020-05-07  0:41 ` [RFC 25/43] mm: shmem: specify the mm to use when inserting pages Anthony Yznaga
2020-05-07  0:41 ` [RFC 26/43] mm: shmem: when inserting, handle pages already charged to a memcg Anthony Yznaga
2020-05-07  0:41 ` [RFC 27/43] x86/mm/numa: add numa_isolate_memblocks() Anthony Yznaga
2020-05-07  0:41 ` [RFC 28/43] PKRAM: ensure memblocks with preserved pages init'd for numa Anthony Yznaga
2020-05-07  0:41 ` [RFC 29/43] memblock: PKRAM: mark memblocks that contain preserved pages Anthony Yznaga
2020-05-07  0:41 ` [RFC 30/43] memblock: add for_each_reserved_mem_range() Anthony Yznaga
2020-05-07  0:41 ` [RFC 31/43] memblock, mm: defer initialization of preserved pages Anthony Yznaga
2020-05-07  0:41 ` [RFC 32/43] shmem: PKRAM: preserve shmem files a chunk at a time Anthony Yznaga
2020-05-07  0:41 ` [RFC 33/43] PKRAM: atomically add and remove link pages Anthony Yznaga
2020-05-07  0:42 ` [RFC 34/43] shmem: PKRAM: multithread preserving and restoring shmem pages Anthony Yznaga
2020-05-07 16:30   ` Randy Dunlap
2020-05-07 17:59     ` Anthony Yznaga
2020-05-07  0:42 ` [RFC 35/43] shmem: introduce shmem_insert_pages() Anthony Yznaga
2020-05-07  0:42 ` [RFC 36/43] PKRAM: add support for loading pages in bulk Anthony Yznaga
2020-05-07  0:42 ` [RFC 37/43] shmem: PKRAM: enable bulk loading of preserved pages into shmem Anthony Yznaga
2020-05-07  0:42 ` Anthony Yznaga [this message]
2020-05-07  0:42 ` [RFC 39/43] shmem: optimize adding pages to the LRU in shmem_insert_pages() Anthony Yznaga
2020-05-07  0:42 ` [RFC 40/43] shmem: initial support for adding multiple pages to pagecache Anthony Yznaga
2020-05-07  0:42 ` [RFC 41/43] XArray: add xas_export_node() and xas_import_node() Anthony Yznaga
2020-05-07  0:42 ` [RFC 42/43] shmem: reduce time holding xa_lock when inserting pages Anthony Yznaga
2020-05-07  0:42 ` [RFC 43/43] PKRAM: improve index alignment of pkram_link entries Anthony Yznaga

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=1588812129-8596-39-git-send-email-anthony.yznaga@oracle.com \
    --to=anthony.yznaga@oracle.com \
    --cc=Thomas.Lendacky@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=ardb@kernel.org \
    --cc=ashok.raj@intel.com \
    --cc=bhe@redhat.com \
    --cc=bp@alien8.de \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=daniel.kiper@oracle.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dima@golovin.in \
    --cc=ebiederm@xmission.com \
    --cc=guro@fb.com \
    --cc=gustavo@embeddedor.com \
    --cc=hannes@cmpxchg.org \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jason.zeng@intel.com \
    --cc=jroedel@suse.de \
    --cc=keescook@chromium.org \
    --cc=kevin.tian@intel.com \
    --cc=kexec@lists.infradead.org \
    --cc=lei.l.li@intel.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=masahiroy@kernel.org \
    --cc=mhocko@kernel.org \
    --cc=minchan@kernel.org \
    --cc=mingo@redhat.com \
    --cc=ndesaulniers@google.com \
    --cc=nivedita@alum.mit.edu \
    --cc=paul.c.lai@intel.com \
    --cc=peterz@infradead.org \
    --cc=rafael.j.wysocki@intel.com \
    --cc=rppt@linux.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=vdavydov.dev@gmail.com \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ying.huang@intel.com \
    --cc=zhenzhong.duan@oracle.com \
    --cc=zhiyuan.lv@intel.com \
    --cc=ziqian.lzq@antfin.com \
    --subject='Re: [RFC 38/43] mm: implement splicing a list of pages to the LRU' \
    /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: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).