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 35/43] shmem: introduce shmem_insert_pages()
Date: Wed,  6 May 2020 17:42:01 -0700	[thread overview]
Message-ID: <1588812129-8596-36-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

Calling shmem_insert_page() to insert one page at a time does
not scale well when multiple threads are inserting pages into
the same shmem segment.  This is primarily due to the locking needed
when adding to the pagecache and LRU but also due to contention
on the shmem_inode_info lock. To address the shmem_inode_info lock
and prepare for future optimizations, introduce shmem_insert_pages()
which allows a caller to pass an array of pages to be inserted into a
shmem segment.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 include/linux/shmem_fs.h |   3 +-
 mm/shmem.c               | 114 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 116 insertions(+), 1 deletion(-)

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index f2ce9937a8f2..d308a6a154b6 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -105,7 +105,8 @@ extern int shmem_getpage(struct inode *inode, pgoff_t index,
 
 extern int shmem_insert_page(struct mm_struct *mm, struct inode *inode,
 		pgoff_t index, struct page *page);
-
+extern int shmem_insert_pages(struct mm_struct *mm, struct inode *inode,
+			      pgoff_t index, struct page *pages[], int npages);
 #ifdef CONFIG_PKRAM
 extern int shmem_parse_pkram(const char *str, struct shmem_pkram_info **pkram);
 extern void shmem_show_pkram(struct seq_file *seq, struct shmem_pkram_info *pkram,
diff --git a/mm/shmem.c b/mm/shmem.c
index 1f3b43b8fa34..ca5edf580f24 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -781,6 +781,120 @@ int shmem_insert_page(struct mm_struct *mm, struct inode *inode, pgoff_t index,
 	return err;
 }
 
+int shmem_insert_pages(struct mm_struct *mm, struct inode *inode, pgoff_t index,
+		       struct page *pages[], int npages)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	gfp_t gfp = mapping_gfp_mask(mapping);
+	struct mem_cgroup *memcg;
+	int i, err;
+	int nr = 0;
+
+	for (i = 0; i < npages; i++)
+		nr += compound_nr(pages[i]);
+
+	if (index + nr - 1 > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
+		return -EFBIG;
+
+retry:
+	err = 0;
+	if (!shmem_inode_acct_block(inode, nr))
+		err = -ENOSPC;
+	if (err) {
+		int retry = 5;
+
+		/*
+		 * Try to reclaim some space by splitting a huge page
+		 * beyond i_size on the filesystem.
+		 */
+		while (retry--) {
+			int ret;
+
+			ret = shmem_unused_huge_shrink(sbinfo, NULL, 1);
+			if (ret == SHRINK_STOP)
+				break;
+			if (ret)
+				goto retry;
+		}
+		goto failed;
+	}
+
+	for (i = 0; i < npages; i++) {
+		if (!PageLRU(pages[i])) {
+			__SetPageLocked(pages[i]);
+			__SetPageSwapBacked(pages[i]);
+		} else {
+			lock_page(pages[i]);
+		}
+
+		__SetPageReferenced(pages[i]);
+
+		if (pages[i]->mem_cgroup)
+			continue;
+
+		err = mem_cgroup_try_charge_delay(pages[i], mm, gfp,
+					&memcg, PageTransHuge(pages[i]));
+		if (err)
+			goto out_unlock;
+
+	}
+
+	for (i = 0; i < npages; i++) {
+		err = shmem_add_to_page_cache(pages[i], mapping, index,
+					NULL, gfp & GFP_RECLAIM_MASK);
+		if (err)
+			goto out_truncate;
+
+		if (PageTransHuge(pages[i]))
+			index += HPAGE_PMD_NR;
+		else
+			index++;
+	}
+
+	spin_lock(&info->lock);
+	info->alloced += nr;
+	inode->i_blocks += BLOCKS_PER_PAGE * nr;
+	shmem_recalc_inode(inode);
+	spin_unlock(&info->lock);
+
+	for (i = 0; i < npages; i++) {
+		if (!pages[i]->mem_cgroup) {
+			mem_cgroup_commit_charge(pages[i], memcg,
+				PageLRU(pages[i]), PageTransHuge(pages[i]));
+		}
+
+		if (!PageLRU(pages[i]))
+			lru_cache_add_anon(pages[i]);
+
+		flush_dcache_page(pages[i]);
+		SetPageUptodate(pages[i]);
+		set_page_dirty(pages[i]);
+
+		unlock_page(pages[i]);
+	}
+
+	return 0;
+
+out_truncate:
+	while (--i >= 0)
+		truncate_inode_page(mapping, pages[i]);
+	i = npages;
+out_unlock:
+	while (--i >= 0) {
+		if (!pages[i]->mem_cgroup) {
+			mem_cgroup_cancel_charge(pages[i], memcg,
+				PageTransHuge(pages[i]));
+		}
+
+		unlock_page(pages[i]);
+	}
+	shmem_inode_unacct_blocks(inode, nr);
+failed:
+	return err;
+}
+
 /*
  * Remove swap entry from page cache, free the swap and its page cache.
  */
-- 
2.13.3


  parent reply	other threads:[~2020-05-07  0:46 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 ` Anthony Yznaga [this message]
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 ` [RFC 38/43] mm: implement splicing a list of pages to the LRU Anthony Yznaga
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=1588812129-8596-36-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 35/43] shmem: introduce shmem_insert_pages()' \
    /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).