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 31/43] memblock, mm: defer initialization of preserved pages
Date: Wed,  6 May 2020 17:41:57 -0700	[thread overview]
Message-ID: <1588812129-8596-32-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

Preserved pages are represented in the memblock reserved list, but page
structs for pages in the reserved list are initialized early while boot
is single threaded which means that a large number of preserved pages
can impact boot time. To mitigate, defer initialization of preserved
pages by skipping them when other reserved pages are initialized and
initializing them later with a separate kernel thread.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 arch/x86/mm/init_64.c |  1 -
 include/linux/mm.h    |  2 +-
 mm/memblock.c         | 10 ++++++++--
 mm/page_alloc.c       | 52 +++++++++++++++++++++++++++++++++++++++++++--------
 4 files changed, 53 insertions(+), 12 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 72662615977b..ae569ef6bd7d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1245,7 +1245,6 @@ void __init mem_init(void)
 	after_bootmem = 1;
 	x86_init.hyper.init_after_bootmem();
 
-	pkram_free_pgt();
 	totalram_pages_add(pkram_reserved_pages);
 	/*
 	 * Must be done after boot memory is put on freelist, because here we
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5a323422d783..69b9cd08c721 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2297,7 +2297,7 @@ extern void free_highmem_page(struct page *page);
 extern void adjust_managed_page_count(struct page *page, long count);
 extern void mem_init_print_info(const char *str);
 
-extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
+extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
 static inline void __free_reserved_page(struct page *page)
diff --git a/mm/memblock.c b/mm/memblock.c
index 33597f352dc0..5524edbaf691 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -2042,11 +2042,17 @@ static unsigned long __init free_low_memory_core_early(void)
 	unsigned long count = 0;
 	phys_addr_t start, end;
 	u64 i;
+	enum memblock_flags exclude;
 
 	memblock_clear_hotplug(0, -1);
 
-	for_each_reserved_mem_region(i, &start, &end)
-		reserve_bootmem_region(start, end);
+	if (IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT))
+		exclude = MEMBLOCK_PRESERVED;
+	else
+		exclude = MEMBLOCK_NONE;
+
+	for_each_reserved_mem_range(i, 0, exclude, &start, &end, NULL)
+		reserve_bootmem_region(start, end, -1);
 
 	/*
 	 * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 69827d4fa052..afd97b31725e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -68,6 +68,7 @@
 #include <linux/lockdep.h>
 #include <linux/nmi.h>
 #include <linux/psi.h>
+#include <linux/pkram.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -1408,15 +1409,18 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn,
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void __meminit init_reserved_page(unsigned long pfn)
+static void __meminit init_reserved_page(unsigned long pfn, int nid)
 {
 	pg_data_t *pgdat;
-	int nid, zid;
+	int zid;
 
-	if (!early_page_uninitialised(pfn))
-		return;
+	if (nid == -1) {
+		if (!early_page_uninitialised(pfn))
+			return;
+
+		nid = early_pfn_to_nid(pfn);
+	}
 
-	nid = early_pfn_to_nid(pfn);
 	pgdat = NODE_DATA(nid);
 
 	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
@@ -1428,7 +1432,7 @@ static void __meminit init_reserved_page(unsigned long pfn)
 	__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
 }
 #else
-static inline void init_reserved_page(unsigned long pfn)
+static inline void init_reserved_page(unsigned long pfn, int nid)
 {
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
@@ -1439,7 +1443,7 @@ static inline void init_reserved_page(unsigned long pfn)
  * marks the pages PageReserved. The remaining valid pages are later
  * sent to the buddy page allocator.
  */
-void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
+void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long end_pfn = PFN_UP(end);
@@ -1448,7 +1452,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 		if (pfn_valid(start_pfn)) {
 			struct page *page = pfn_to_page(start_pfn);
 
-			init_reserved_page(start_pfn);
+			init_reserved_page(start_pfn, nid);
 
 			/* Avoid false-positive PageTail() */
 			INIT_LIST_HEAD(&page->lru);
@@ -1876,6 +1880,34 @@ static int __init deferred_init_memmap(void *data)
 	return 0;
 }
 
+#ifdef CONFIG_PKRAM
+static int __init deferred_init_preserved(void *dummy)
+{
+	unsigned long start = jiffies;
+	unsigned long nr_pages = 0;
+	phys_addr_t spa, epa;
+	int nid;
+	u64 i;
+
+	for_each_reserved_mem_range(i, MEMBLOCK_PRESERVED, 0, &spa, &epa, &nid) {
+		reserve_bootmem_region(spa, epa, nid);
+		nr_pages += ((epa - spa) >> PAGE_SHIFT);
+	}
+
+	pr_info("initialised %lu preserved pages in %ums\n", nr_pages,
+					jiffies_to_msecs(jiffies - start));
+
+	/*
+	 * Free the preserved pages pagetable now that page structs are
+	 * initialized.
+	 */
+	pkram_free_pgt();
+
+	pgdat_init_report_one_done();
+	return 0;
+}
+#endif /* CONFIG_PKRAM */
+
 /*
  * If this zone has deferred pages, try to grow it by initializing enough
  * deferred pages to satisfy the allocation specified by order, rounded up to
@@ -1985,6 +2017,10 @@ void __init page_alloc_init_late(void)
 
 	/* There will be num_node_state(N_MEMORY) threads */
 	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
+#ifdef CONFIG_PKRAM
+	atomic_inc(&pgdat_init_n_undone);
+	kthread_run(deferred_init_preserved, NULL, "pgdatainit_preserved");
+#endif
 	for_each_node_state(nid, N_MEMORY) {
 		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
 	}
-- 
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 ` Anthony Yznaga [this message]
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 ` [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=1588812129-8596-32-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 31/43] memblock, mm: defer initialization of preserved 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).