LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
To: akpm@linux-foundation.org, linux-mm@kvack.org
Cc: sparclinux@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org, davem@davemloft.net,
	pavel.tatashin@microsoft.com, mhocko@suse.com, mingo@kernel.org,
	kirill.shutemov@linux.intel.com, dan.j.williams@intel.com,
	dave.jiang@intel.com, alexander.h.duyck@linux.intel.com,
	rppt@linux.vnet.ibm.com, willy@infradead.org, vbabka@suse.cz,
	khalid.aziz@oracle.com, ldufour@linux.vnet.ibm.com,
	mgorman@techsingularity.net, yi.z.zhang@linux.intel.com,
	alexander.h.duyck@linux.intel.com
Subject: [mm PATCH v5 5/7] mm: Move hot-plug specific memory init into separate functions and optimize
Date: Mon, 05 Nov 2018 13:19:50 -0800
Message-ID: <154145279094.30046.504725873397414096.stgit@ahduyck-desk1.jf.intel.com> (raw)
In-Reply-To: <154145268025.30046.11742652345962594283.stgit@ahduyck-desk1.jf.intel.com>

This patch is going through and combining the bits in memmap_init_zone and
memmap_init_zone_device that are related to hotplug into a single function
called __memmap_init_hotplug.

I also took the opportunity to integrate __init_single_page's functionality
into this function. In doing so I can get rid of some of the redundancy
such as the LRU pointers versus the pgmap.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 mm/page_alloc.c |  214 +++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 144 insertions(+), 70 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3466a01ed90a..dbe00c1a0e23 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1192,6 +1192,92 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn,
 #endif
 }
 
+static void __meminit __init_pageblock(unsigned long start_pfn,
+				       unsigned long nr_pages,
+				       unsigned long zone, int nid,
+				       struct dev_pagemap *pgmap)
+{
+	unsigned long nr_pgmask = pageblock_nr_pages - 1;
+	struct page *start_page = pfn_to_page(start_pfn);
+	unsigned long pfn = start_pfn + nr_pages - 1;
+#ifdef WANT_PAGE_VIRTUAL
+	bool is_highmem = is_highmem_idx(zone);
+#endif
+	struct page *page;
+
+	/*
+	 * Enforce the following requirements:
+	 * size > 0
+	 * size < pageblock_nr_pages
+	 * start_pfn -> pfn does not cross pageblock_nr_pages boundary
+	 */
+	VM_BUG_ON(((start_pfn ^ pfn) | (nr_pages - 1)) > nr_pgmask);
+
+	/*
+	 * Work from highest page to lowest, this way we will still be
+	 * warm in the cache when we call set_pageblock_migratetype
+	 * below.
+	 *
+	 * The loop is based around the page pointer as the main index
+	 * instead of the pfn because pfn is not used inside the loop if
+	 * the section number is not in page flags and WANT_PAGE_VIRTUAL
+	 * is not defined.
+	 */
+	for (page = start_page + nr_pages; page-- != start_page; pfn--) {
+		mm_zero_struct_page(page);
+
+		/*
+		 * We use the start_pfn instead of pfn in the set_page_links
+		 * call because of the fact that the pfn number is used to
+		 * get the section_nr and this function should not be
+		 * spanning more than a single section.
+		 */
+		set_page_links(page, zone, nid, start_pfn);
+		init_page_count(page);
+		page_mapcount_reset(page);
+		page_cpupid_reset_last(page);
+
+		/*
+		 * We can use the non-atomic __set_bit operation for setting
+		 * the flag as we are still initializing the pages.
+		 */
+		__SetPageReserved(page);
+
+		/*
+		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
+		 * pointer and hmm_data.  It is a bug if a ZONE_DEVICE
+		 * page is ever freed or placed on a driver-private list.
+		 */
+		page->pgmap = pgmap;
+		if (!pgmap)
+			INIT_LIST_HEAD(&page->lru);
+
+#ifdef WANT_PAGE_VIRTUAL
+		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
+		if (!is_highmem)
+			set_page_address(page, __va(pfn << PAGE_SHIFT));
+#endif
+	}
+
+	/*
+	 * Mark the block movable so that blocks are reserved for
+	 * movable at startup. This will force kernel allocations
+	 * to reserve their blocks rather than leaking throughout
+	 * the address space during boot when many long-lived
+	 * kernel allocations are made.
+	 *
+	 * bitmap is created for zone's valid pfn range. but memmap
+	 * can be created for invalid pages (for alignment)
+	 * check here not to call set_pageblock_migratetype() against
+	 * pfn out of zone.
+	 *
+	 * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+	 * because this is done early in sparse_add_one_section
+	 */
+	if (!(start_pfn & nr_pgmask))
+		set_pageblock_migratetype(start_page, MIGRATE_MOVABLE);
+}
+
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static void __meminit init_reserved_page(unsigned long pfn)
 {
@@ -5513,6 +5599,25 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
 	return false;
 }
 
+static void __meminit __memmap_init_hotplug(unsigned long size, int nid,
+					    unsigned long zone,
+					    unsigned long start_pfn,
+					    struct dev_pagemap *pgmap)
+{
+	unsigned long pfn = start_pfn + size;
+
+	while (pfn != start_pfn) {
+		unsigned long stride = pfn;
+
+		pfn = max(ALIGN_DOWN(pfn - 1, pageblock_nr_pages), start_pfn);
+		stride -= pfn;
+
+		__init_pageblock(pfn, stride, zone, nid, pgmap);
+
+		cond_resched();
+	}
+}
+
 /*
  * Initially all pages are reserved - free ones are freed
  * up by memblock_free_all() once the early boot process is
@@ -5523,49 +5628,59 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		struct vmem_altmap *altmap)
 {
 	unsigned long pfn, end_pfn = start_pfn + size;
-	struct page *page;
 
 	if (highest_memmap_pfn < end_pfn - 1)
 		highest_memmap_pfn = end_pfn - 1;
 
+	if (context == MEMMAP_HOTPLUG) {
 #ifdef CONFIG_ZONE_DEVICE
-	/*
-	 * Honor reservation requested by the driver for this ZONE_DEVICE
-	 * memory. We limit the total number of pages to initialize to just
-	 * those that might contain the memory mapping. We will defer the
-	 * ZONE_DEVICE page initialization until after we have released
-	 * the hotplug lock.
-	 */
-	if (zone == ZONE_DEVICE) {
-		if (!altmap)
-			return;
+		/*
+		 * Honor reservation requested by the driver for this
+		 * ZONE_DEVICE memory. We limit the total number of pages to
+		 * initialize to just those that might contain the memory
+		 * mapping. We will defer the ZONE_DEVICE page initialization
+		 * until after we have released the hotplug lock.
+		 */
+		if (zone == ZONE_DEVICE) {
+			if (!altmap)
+				return;
+
+			if (start_pfn == altmap->base_pfn)
+				start_pfn += altmap->reserve;
+			end_pfn = altmap->base_pfn +
+				  vmem_altmap_offset(altmap);
+		}
+#endif
+		/*
+		 * For these ZONE_DEVICE pages we don't need to record the
+		 * pgmap as they should represent only those pages used to
+		 * store the memory map. The actual ZONE_DEVICE pages will
+		 * be initialized later.
+		 */
+		__memmap_init_hotplug(end_pfn - start_pfn, nid, zone,
+				      start_pfn, NULL);
 
-		if (start_pfn == altmap->base_pfn)
-			start_pfn += altmap->reserve;
-		end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
+		return;
 	}
-#endif
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		struct page *page;
+
 		/*
 		 * There can be holes in boot-time mem_map[]s handed to this
 		 * function.  They do not exist on hotplugged memory.
 		 */
-		if (context == MEMMAP_EARLY) {
-			if (!early_pfn_valid(pfn))
-				continue;
-			if (!early_pfn_in_nid(pfn, nid))
-				continue;
-			if (overlap_memmap_init(zone, &pfn))
-				continue;
-			if (defer_init(nid, pfn, end_pfn))
-				break;
-		}
+		if (!early_pfn_valid(pfn))
+			continue;
+		if (!early_pfn_in_nid(pfn, nid))
+			continue;
+		if (overlap_memmap_init(zone, &pfn))
+			continue;
+		if (defer_init(nid, pfn, end_pfn))
+			break;
 
 		page = pfn_to_page(pfn);
 		__init_single_page(page, pfn, zone, nid);
-		if (context == MEMMAP_HOTPLUG)
-			__SetPageReserved(page);
 
 		/*
 		 * Mark the block movable so that blocks are reserved for
@@ -5592,7 +5707,6 @@ void __ref memmap_init_zone_device(struct zone *zone,
 				   unsigned long size,
 				   struct dev_pagemap *pgmap)
 {
-	unsigned long pfn, end_pfn = start_pfn + size;
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long zone_idx = zone_idx(zone);
 	unsigned long start = jiffies;
@@ -5608,53 +5722,13 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	 */
 	if (pgmap->altmap_valid) {
 		struct vmem_altmap *altmap = &pgmap->altmap;
+		unsigned long end_pfn = start_pfn + size;
 
 		start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
 		size = end_pfn - start_pfn;
 	}
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
-		struct page *page = pfn_to_page(pfn);
-
-		__init_single_page(page, pfn, zone_idx, nid);
-
-		/*
-		 * Mark page reserved as it will need to wait for onlining
-		 * phase for it to be fully associated with a zone.
-		 *
-		 * We can use the non-atomic __set_bit operation for setting
-		 * the flag as we are still initializing the pages.
-		 */
-		__SetPageReserved(page);
-
-		/*
-		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
-		 * pointer and hmm_data.  It is a bug if a ZONE_DEVICE
-		 * page is ever freed or placed on a driver-private list.
-		 */
-		page->pgmap = pgmap;
-		page->hmm_data = 0;
-
-		/*
-		 * Mark the block movable so that blocks are reserved for
-		 * movable at startup. This will force kernel allocations
-		 * to reserve their blocks rather than leaking throughout
-		 * the address space during boot when many long-lived
-		 * kernel allocations are made.
-		 *
-		 * bitmap is created for zone's valid pfn range. but memmap
-		 * can be created for invalid pages (for alignment)
-		 * check here not to call set_pageblock_migratetype() against
-		 * pfn out of zone.
-		 *
-		 * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
-		 * because this is done early in sparse_add_one_section
-		 */
-		if (!(pfn & (pageblock_nr_pages - 1))) {
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-			cond_resched();
-		}
-	}
+	__memmap_init_hotplug(size, nid, zone_idx, start_pfn, pgmap);
 
 	pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev),
 		size, jiffies_to_msecs(jiffies - start));


  parent reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-05 21:19 [mm PATCH v5 0/7] Deferred page init improvements Alexander Duyck
2018-11-05 21:19 ` [mm PATCH v5 1/7] mm: Use mm_zero_struct_page from SPARC on all 64b architectures Alexander Duyck
2018-11-05 21:19 ` [mm PATCH v5 2/7] mm: Drop meminit_pfn_in_nid as it is redundant Alexander Duyck
2018-11-05 21:19 ` [mm PATCH v5 3/7] mm: Implement new zone specific memblock iterator Alexander Duyck
2018-11-09 23:26   ` Pavel Tatashin
2018-11-09 23:58     ` Alexander Duyck
2018-11-10  0:11       ` Pavel Tatashin
2018-11-05 21:19 ` [mm PATCH v5 4/7] mm: Initialize MAX_ORDER_NR_PAGES at a time instead of doing larger sections Alexander Duyck
2018-11-10  1:02   ` Pavel Tatashin
2018-11-19 18:53     ` Alexander Duyck
2018-11-05 21:19 ` Alexander Duyck [this message]
2018-11-10  2:07   ` [mm PATCH v5 5/7] mm: Move hot-plug specific memory init into separate functions and optimize Pavel Tatashin
2018-11-05 21:19 ` [mm PATCH v5 6/7] mm: Add reserved flag setting to set_page_links Alexander Duyck
2018-11-10  2:11   ` Pavel Tatashin
2018-11-05 21:20 ` [mm PATCH v5 7/7] mm: Use common iterator for deferred_init_pages and deferred_free_pages Alexander Duyck
2018-11-10  4:13   ` Pavel Tatashin
2018-11-12 15:12     ` Alexander Duyck
2018-11-09 21:15 ` [mm PATCH v5 0/7] Deferred page init improvements Pavel Tatashin
2018-11-09 23:14   ` Alexander Duyck
2018-11-10  0:00     ` Pavel Tatashin
2018-11-10  0:46       ` Alexander Duyck
2018-11-10  1:16         ` Pavel Tatashin
2018-11-12 19:10           ` Alexander Duyck
2018-11-12 20:37             ` Pavel Tatashin
2018-11-12 16:25       ` Daniel Jordan
2018-11-14 15:07 ` Michal Hocko
2018-11-14 19:12   ` Pavel Tatashin
2018-11-14 21:35     ` Michal Hocko
2018-11-15  0:50   ` Alexander Duyck
2018-11-15  1:55     ` Mike Rapoport
2018-11-15 19:09       ` Mike Rapoport
2018-11-15  8:10     ` Michal Hocko
2018-11-15 16:02       ` Alexander Duyck
2018-11-15 16:40         ` Michal Hocko

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=154145279094.30046.504725873397414096.stgit@ahduyck-desk1.jf.intel.com \
    --to=alexander.h.duyck@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=davem@davemloft.net \
    --cc=khalid.aziz@oracle.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=ldufour@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=mingo@kernel.org \
    --cc=pavel.tatashin@microsoft.com \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=sparclinux@vger.kernel.org \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=yi.z.zhang@linux.intel.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git