linux-fsdevel.vger.kernel.org archive mirror
 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 36/43] PKRAM: add support for loading pages in bulk
Date: Wed,  6 May 2020 17:42:02 -0700	[thread overview]
Message-ID: <1588812129-8596-37-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

This patch adds three functions:

pkram_prepare_load_pages()
  Called after calling pkram_prepare_load_obj()

pkram_load_pages()
  Loads some number of pages that are contiguous by their original
  file index values.  The index of the first page, an array of the
  page pointers, and the number of pages in the array are provided
  to the caller.

pkram_finish_load_pages()
  Called when no more pages will be loaded from the pkram_obj.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 include/linux/pkram.h |   6 +++
 mm/pkram.c            | 106 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 112 insertions(+)

diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index bf2e138b044e..3f059791f88c 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -18,6 +18,9 @@ struct pkram_stream {
 	struct pkram_link *link;		/* current link */
 	unsigned int entry_idx;		/* next entry in link */
 
+	struct page **pages;
+	unsigned int nr_pages;
+
 	unsigned long next_index;
 	struct address_space *mapping;
 	struct mm_struct *mm;
@@ -60,14 +63,17 @@ void pkram_discard_save(struct pkram_stream *ps);
 
 int pkram_prepare_load(struct pkram_stream *ps, const char *name);
 int pkram_prepare_load_obj(struct pkram_stream *ps);
+int pkram_prepare_load_pages(struct pkram_stream *ps);
 void pkram_finish_load(struct pkram_stream *ps);
 void pkram_finish_load_obj(struct pkram_stream *ps);
+void pkram_finish_load_pages(struct pkram_stream *ps);
 
 #define PKRAM_PAGE_TRANS_HUGE	0x1	/* page is a transparent hugepage */
 
 int pkram_save_page(struct pkram_stream *ps, struct page *page, short flags);
 struct page *pkram_load_page(struct pkram_stream *ps, unsigned long *index,
 			     short *flags);
+int pkram_load_pages(struct pkram_stream *ps, unsigned long *index);
 
 ssize_t pkram_write(struct pkram_stream *ps, const void *buf, size_t count);
 size_t pkram_read(struct pkram_stream *ps, void *buf, size_t count);
diff --git a/mm/pkram.c b/mm/pkram.c
index 042c14dedc25..ef092aa5ce7a 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -820,6 +820,37 @@ int pkram_prepare_load_obj(struct pkram_stream *ps)
 }
 
 /**
+ * Initialize stream @ps for loading preserved pages from it.
+ *
+ * Returns 0 on success, -errno on failure.
+ *
+ * Error values:
+ *	%ENOMEM: insufficient memory available
+ *
+ * After the load has finished, pkram_finish_load_pages() is to be called.
+ */
+int pkram_prepare_load_pages(struct pkram_stream *ps)
+{
+	BUG_ON((ps->node->flags & PKRAM_ACCMODE_MASK) != PKRAM_LOAD);
+
+	ps->pages = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!ps->pages)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * Finish the load of preserved pages started with pkram_prepare_load_pages()
+ */
+void pkram_finish_load_pages(struct pkram_stream *ps)
+{
+	BUG_ON((ps->node->flags & PKRAM_ACCMODE_MASK) != PKRAM_LOAD);
+
+	kfree(ps->pages);
+}
+
+/**
  * Finish the load of a preserved memory object started with
  * pkram_prepare_load_obj() freeing the object and any data that has not
  * been loaded from it.
@@ -1066,6 +1097,81 @@ struct page *pkram_load_page(struct pkram_stream *ps, unsigned long *index, shor
 }
 
 /**
+ * Load pages from the preserved memory object associated with stream
+ * @ps. The stream must have been initialized with pkram_prepare_load(),
+ * pkram_prepare_load_obj(), and pkram_prepare_load_pages().
+ * The page entries of a single pkram_link are processed, and the stream
+ * 'pages' buffer is populated with the page pointers.
+ *
+ * Returns 0 if one or more pages are loaded or -ENODATA if there are no
+ * pages to load.
+ *
+ * The pages loaded have an incremented refcount either because the page
+ * was initialized with a refcount of 1 at boot or because the page was
+ * subsequently preserved which increased the refcount.
+ */
+int pkram_load_pages(struct pkram_stream *ps, unsigned long *index)
+{
+	struct pkram_link *link = ps->link;
+	int nr_entries = 0;
+	int i;
+
+	if (!link) {
+		link = pkram_remove_link(ps->obj);
+		if (!link)
+			return -ENODATA;
+	}
+
+	*index = link->index;
+
+	for (i = 0; i < PKRAM_LINK_ENTRIES_MAX; i++) {
+		unsigned long p = link->entry[i];
+		struct page *page;
+		short flags;
+
+		if (!p)
+			break;
+
+		flags = (p >> PKRAM_ENTRY_FLAGS_SHIFT) & PKRAM_ENTRY_FLAGS_MASK;
+		nr_entries++;
+
+		page = pfn_to_page(PHYS_PFN(p));
+		ps->pages[i] = page;
+
+		if (flags & PKRAM_PAGE_TRANS_HUGE) {
+			int order = p & PKRAM_ENTRY_ORDER_MASK;
+			int nr_pages = 1 << order;
+			int j;
+
+			for (j = 0; j < nr_pages; j++) {
+				struct page *p = page + j;
+
+				ClearPageReserved(p);
+			}
+
+			prep_compound_page(page, order);
+			prep_transhuge_page(page);
+		} else {
+			ClearPageReserved(page);
+		}
+
+		pkram_remove_identity_map(page);
+	}
+
+	ps->nr_pages = nr_entries;
+
+	/* Advance to next pkram_link page and free this one */
+	if (link->link_pfn)
+		ps->link = pfn_to_kaddr(link->link_pfn);
+	else
+		ps->link = NULL;
+
+	pkram_free_page(link);
+
+	return 0;
+}
+
+/**
  * Copy @count bytes from @buf to the preserved memory node and object
  * associated with stream @ps. The stream must have been initialized with
  * pkram_prepare_save() and pkram_prepare_save_obj().
-- 
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 ` [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 ` Anthony Yznaga [this message]
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=1588812129-8596-37-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 \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).