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 32/43] shmem: PKRAM: preserve shmem files a chunk at a time
Date: Wed,  6 May 2020 17:41:58 -0700	[thread overview]
Message-ID: <1588812129-8596-33-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

To prepare for multithreading the work done to a preserve a file,
divide the work into subranges of the total index range of the file.
The chunk size is a rather arbitrary 256k indices.

A new API call, pkram_prepare_save_chunk(), is added.  It is called
after calling pkram_prepare_save_obj(), and it initializes pkram_stream
with the index range of the next available range of pages to save.
find_get_pages_range() can then be used to get the pages in the range.
When no more index ranges are available, pkram_prepare_save_chunk()
returns -ENODATA.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 include/linux/pkram.h |  6 +++++
 mm/pkram.c            | 26 +++++++++++++++++++++
 mm/shmem_pkram.c      | 63 +++++++++++++++++++++++++++++++++++----------------
 3 files changed, 75 insertions(+), 20 deletions(-)

diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index cbb79d2803c0..e71ccb91d6a6 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -20,6 +20,11 @@ struct pkram_stream {
 	struct address_space *mapping;
 	struct mm_struct *mm;
 
+	unsigned long start_idx;	/* first index in range to save */
+	unsigned long end_idx;		/* last index in range to save */
+	unsigned long max_idx;		/* maximum index to save */
+	atomic64_t *next_idx;		/* first index of next range to save */
+
 	/* byte data */
 	struct page *data_page;
 	unsigned int data_offset;
@@ -46,6 +51,7 @@ void pkram_free_pgt_walk_pgd(pgd_t *pgd);
 int pkram_prepare_save(struct pkram_stream *ps, const char *name,
 		       gfp_t gfp_mask);
 int pkram_prepare_save_obj(struct pkram_stream *ps);
+int pkram_prepare_save_chunk(struct pkram_stream *ps);
 void pkram_finish_save(struct pkram_stream *ps);
 void pkram_finish_save_obj(struct pkram_stream *ps);
 void pkram_discard_save(struct pkram_stream *ps);
diff --git a/mm/pkram.c b/mm/pkram.c
index b83d31740619..5f4e4d12865f 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -638,6 +638,25 @@ int pkram_prepare_save(struct pkram_stream *ps, const char *name, gfp_t gfp_mask
 	return 0;
 }
 
+unsigned long max_pages_per_chunk = 512 * 512;
+
+/*
+ * Initialize the stream @ps for the next index range to save.
+ *
+ * Returns 0 on success, -ENODATA if no index range is available
+ *
+ */
+int pkram_prepare_save_chunk(struct pkram_stream *ps)
+{
+	ps->start_idx = atomic64_fetch_add(max_pages_per_chunk, ps->next_idx);
+	if (ps->start_idx >= ps->max_idx)
+		return -ENODATA;
+
+	ps->end_idx = ps->start_idx + max_pages_per_chunk - 1;
+
+	return 0;
+}
+
 /**
  * Create a preserved memory object and initialize stream @ps for saving data
  * to it.
@@ -667,6 +686,11 @@ int pkram_prepare_save_obj(struct pkram_stream *ps)
 		obj->obj_pfn = node->obj_pfn;
 	node->obj_pfn = page_to_pfn(page);
 
+	ps->next_idx = kmalloc(sizeof(atomic64_t), GFP_KERNEL);
+	if (!ps->next_idx)
+		return -ENOMEM;
+	atomic64_set(ps->next_idx, 0);
+
 	pkram_stream_init_obj(ps, obj);
 	return 0;
 }
@@ -679,6 +703,8 @@ void pkram_finish_save_obj(struct pkram_stream *ps)
 	struct pkram_node *node = ps->node;
 
 	BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_SAVE);
+
+	kfree(ps->next_idx);
 }
 
 /**
diff --git a/mm/shmem_pkram.c b/mm/shmem_pkram.c
index c97d64393822..2f4d0bdf3e05 100644
--- a/mm/shmem_pkram.c
+++ b/mm/shmem_pkram.c
@@ -74,58 +74,81 @@ static int save_page(struct page *page, struct pkram_stream *ps)
 	return err;
 }
 
-static int save_file_content(struct pkram_stream *ps)
+static int save_file_content_range(struct address_space *mapping,
+				   struct pkram_stream *ps)
 {
+	unsigned long index, end;
 	struct pagevec pvec;
-	pgoff_t indices[PAGEVEC_SIZE];
-	pgoff_t index = 0;
 	struct page *page;
-	int i, err = 0;
+	int err = 0;
+	int i;
+
+	index = ps->start_idx;
+	end = ps->end_idx;
 
 	pagevec_init(&pvec);
 	for ( ; ; ) {
-		pvec.nr = find_get_entries(ps->mapping, index, PAGEVEC_SIZE,
-				pvec.pages, indices);
+		pvec.nr = find_get_pages_range(mapping, &index, end,
+				PAGEVEC_SIZE, pvec.pages);
 		if (!pvec.nr)
 			break;
-		for (i = 0; i < pagevec_count(&pvec); i++) {
+		for (i = 0; i < pagevec_count(&pvec); ) {
 			page = pvec.pages[i];
-			index = indices[i];
-
-			if (WARN_ON_ONCE(xa_is_value(page))) {
-				err = -EINVAL;
-				break;
-			}
-
 			lock_page(page);
 
 			if (PageTransTail(page)) {
 				WARN_ONCE(1, "PageTransTail returned true\n");
 				unlock_page(page);
+				i++;
 				continue;
 			}
 
-			BUG_ON(page->mapping != ps->mapping);
+			BUG_ON(page->mapping != mapping);
 			err = save_page(page, ps);
 
-			i += compound_nr(page) - 1;
-			index += compound_nr(page) - 1;
+			if (PageCompound(page)) {
+				index = page->index + compound_nr(page);
+				i += compound_nr(page);
+			} else {
+				i++;
+			}
 
 			unlock_page(page);
 			if (err)
 				break;
 		}
-		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		if (err)
+		if (err || (index > end))
 			break;
 		cond_resched();
-		index++;
 	}
 
 	return err;
 }
 
+static int do_save_file_content(struct pkram_stream *ps)
+{
+	int ret;
+
+	do {
+		ret = pkram_prepare_save_chunk(ps);
+		if (!ret)
+			ret = save_file_content_range(ps->mapping, ps);
+	} while (!ret);
+
+	if (ret == -ENODATA)
+		ret = 0;
+
+	return ret;
+}
+
+static int save_file_content(struct pkram_stream *ps)
+{
+	ps->max_idx = DIV_ROUND_UP(i_size_read(ps->mapping->host), PAGE_SIZE);
+
+	return do_save_file_content(ps);
+}
+
 static int save_file(struct dentry *dentry, struct pkram_stream *ps)
 {
 	struct inode *inode = dentry->d_inode;
-- 
2.13.3


  parent reply	other threads:[~2020-05-07  0:45 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 ` Anthony Yznaga [this message]
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 ` [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=1588812129-8596-33-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 32/43] shmem: PKRAM: preserve shmem files a chunk at a time' \
    /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).