+ mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages.patch added to -mm tree

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The patch titled
     Subject: mm: use common iterator for deferred_init_pages and deferred_free_pages
has been added to the -mm tree.  Its filename is
     mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Alexander Duyck <alexander.h.duyck@xxxxxxxxxxxxxxx>
Subject: mm: use common iterator for deferred_init_pages and deferred_free_pages

This patch creates a common iterator to be used by both
deferred_init_pages and deferred_free_pages.  By doing this we can cut
down a bit on code overhead as they will likely both be inlined into the
same function anyway.

This new approach allows deferred_init_pages to make use of
__init_pageblock.  By doing this we can cut down on the code size by
sharing code between both the hotplug and deferred memory init code paths.

An additional benefit to this approach is that we improve in cache
locality of the memory init as we can focus on the memory areas related to
identifying if a given PFN is valid and keep that warm in the cache until
we transition to a region of a different type.  So we will stream through
a chunk of valid blocks before we turn to initializing page structs.

On my x86_64 test system with 384GB of memory per node I saw a reduction
in initialization time from 1.38s to 1.06s as a result of this patch.

Link: http://lkml.kernel.org/r/154145280115.30046.13334106887516645119.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Alexander Duyck <alexander.h.duyck@xxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Khalid Aziz <khalid.aziz@xxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Laurent Dufour <ldufour@xxxxxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Pavel Tatashin <pavel.tatashin@xxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

 mm/page_alloc.c |  131 ++++++++++++++++++++++------------------------
 1 file changed, 64 insertions(+), 67 deletions(-)

--- a/mm/page_alloc.c~mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages
+++ a/mm/page_alloc.c
@@ -1488,31 +1488,6 @@ void clear_zone_contiguous(struct zone *
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void __init deferred_free_range(unsigned long pfn,
-				       unsigned long nr_pages)
-{
-	struct page *page;
-	unsigned long i;
-
-	if (!nr_pages)
-		return;
-
-	page = pfn_to_page(pfn);
-
-	/* Free a large naturally-aligned chunk if possible */
-	if (nr_pages == pageblock_nr_pages &&
-	    (pfn & (pageblock_nr_pages - 1)) == 0) {
-		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_boot_core(page, pageblock_order);
-		return;
-	}
-
-	for (i = 0; i < nr_pages; i++, page++, pfn++) {
-		if ((pfn & (pageblock_nr_pages - 1)) == 0)
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_boot_core(page, 0);
-	}
-}
 
 /* Completion tracking for deferred_init_memmap() threads */
 static atomic_t pgdat_init_n_undone __initdata;
@@ -1525,48 +1500,77 @@ static inline void __init pgdat_init_rep
 }
 
 /*
- * Returns true if page needs to be initialized or freed to buddy allocator.
+ * Returns count if page range needs to be initialized or freed
  *
- * First we check if pfn is valid on architectures where it is possible to have
- * holes within pageblock_nr_pages. On systems where it is not possible, this
- * function is optimized out.
+ * First, we check if a current large page is valid by only checking the
+ * validity of the head pfn.
  *
- * Then, we check if a current large page is valid by only checking the validity
- * of the head pfn.
+ * Then we check if the contiguous pfns are valid on architectures where it
+ * is possible to have holes within pageblock_nr_pages. On systems where it
+ * is not possible, this function is optimized out.
  */
-static inline bool __init deferred_pfn_valid(unsigned long pfn)
+static unsigned long __next_pfn_valid_range(unsigned long *i,
+					    unsigned long end_pfn)
 {
-	if (!pfn_valid_within(pfn))
-		return false;
-	if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
-		return false;
-	return true;
+	unsigned long pfn = *i;
+	unsigned long count;
+
+	while (pfn < end_pfn) {
+		unsigned long t = ALIGN(pfn + 1, pageblock_nr_pages);
+		unsigned long pageblock_pfn = min(t, end_pfn);
+
+#ifndef CONFIG_HOLES_IN_ZONE
+		count = pageblock_pfn - pfn;
+		pfn = pageblock_pfn;
+		if (!pfn_valid(pfn))
+			continue;
+#else
+		for (count = 0; pfn < pageblock_pfn; pfn++) {
+			if (pfn_valid_within(pfn)) {
+				count++;
+				continue;
+			}
+
+			if (count)
+				break;
+		}
+
+		if (!count)
+			continue;
+#endif
+		*i = pfn;
+		return count;
+	}
+
+	return 0;
 }
 
+#define for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) \
+	for (i = (start_pfn),						     \
+	     count = __next_pfn_valid_range(&i, (end_pfn));		     \
+	     count && ({ pfn = i - count; 1; });			     \
+	     count = __next_pfn_valid_range(&i, (end_pfn)))
 /*
  * Free pages to buddy allocator. Try to free aligned pages in
  * pageblock_nr_pages sizes.
  */
-static void __init deferred_free_pages(unsigned long pfn,
+static void __init deferred_free_pages(unsigned long start_pfn,
 				       unsigned long end_pfn)
 {
-	unsigned long nr_pgmask = pageblock_nr_pages - 1;
-	unsigned long nr_free = 0;
+	unsigned long i, pfn, count;
+
+	for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) {
+		struct page *page = pfn_to_page(pfn);
 
-	for (; pfn < end_pfn; pfn++) {
-		if (!deferred_pfn_valid(pfn)) {
-			deferred_free_range(pfn - nr_free, nr_free);
-			nr_free = 0;
-		} else if (!(pfn & nr_pgmask)) {
-			deferred_free_range(pfn - nr_free, nr_free);
-			nr_free = 1;
-			touch_nmi_watchdog();
+		if (count == pageblock_nr_pages) {
+			__free_pages_boot_core(page, pageblock_order);
 		} else {
-			nr_free++;
+			while (count--)
+				__free_pages_boot_core(page++, 0);
 		}
+
+		touch_nmi_watchdog();
 	}
-	/* Free the last block of pages to allocator */
-	deferred_free_range(pfn - nr_free, nr_free);
 }
 
 /*
@@ -1575,29 +1579,22 @@ static void __init deferred_free_pages(u
  * Return number of pages initialized.
  */
 static unsigned long  __init deferred_init_pages(struct zone *zone,
-						 unsigned long pfn,
+						 unsigned long start_pfn,
 						 unsigned long end_pfn)
 {
-	unsigned long nr_pgmask = pageblock_nr_pages - 1;
+	unsigned long i, pfn, count;
 	int nid = zone_to_nid(zone);
 	unsigned long nr_pages = 0;
 	int zid = zone_idx(zone);
-	struct page *page = NULL;
 
-	for (; pfn < end_pfn; pfn++) {
-		if (!deferred_pfn_valid(pfn)) {
-			page = NULL;
-			continue;
-		} else if (!page || !(pfn & nr_pgmask)) {
-			page = pfn_to_page(pfn);
-			touch_nmi_watchdog();
-		} else {
-			page++;
-		}
-		__init_single_page(page, pfn, zid, nid);
-		nr_pages++;
+	for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) {
+		nr_pages += count;
+		__init_pageblock(pfn, count, zid, nid, NULL, false);
+
+		touch_nmi_watchdog();
 	}
-	return (nr_pages);
+
+	return nr_pages;
 }
 
 /*
_

Patches currently in -mm which might be from alexander.h.duyck@xxxxxxxxxxxxxxx are

mm-use-mm_zero_struct_page-from-sparc-on-all-64b-architectures.patch
mm-drop-meminit_pfn_in_nid-as-it-is-redundant.patch
mm-implement-new-zone-specific-memblock-iterator.patch
mm-initialize-max_order_nr_pages-at-a-time-instead-of-doing-larger-sections.patch
mm-move-hot-plug-specific-memory-init-into-separate-functions-and-optimize.patch
mm-add-reserved-flag-setting-to-set_page_links.patch
mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages.patch




[Index of Archives]     [Kernel Archive]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]

  Powered by Linux