[tip:numa/core] sched, numa, mm: Introduce last_nid in the pageframe

From: tip-bot for Peter Zijlstra
Date: Sun Oct 28 2012 - 13:08:55 EST

Next message: tip-bot for Peter Zijlstra: "[tip:numa/core] sched, numa, mm/mpol: Add_MPOL_F_HOME"
Previous message: tip-bot for Peter Zijlstra: "[tip:numa/core] sched, numa, mm: Implement home-node awareness"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Commit-ID: ebec8f0885cf99ac9fa1db0a91cc3b1898de79e0
Gitweb: http://git.kernel.org/tip/ebec8f0885cf99ac9fa1db0a91cc3b1898de79e0
Author: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
AuthorDate: Mon, 13 Aug 2012 15:22:20 +0200
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Sun, 28 Oct 2012 17:31:13 +0100

sched, numa, mm: Introduce last_nid in the pageframe

Introduce a per-page last_nid field, fold this into the struct
page::flags field whenever possible.

The unlikely/rare 32bit NUMA configs will likely grow the page-frame.

Completely dropping 32bit support for CONFIG_SCHED_NUMA would simplify
things, but it would also remove the warning if we grow enough 64bit
only page-flags to push the last-nid out.

Suggested-by: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Link: http://lkml.kernel.org/n/tip-0uois4f9skfw9mwyk1yoy0jq@xxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
include/linux/mm.h | 90 ++++++++++++++++++++-----------------
include/linux/mm_types.h | 5 ++
include/linux/mmzone.h | 14 +-----
include/linux/page-flags-layout.h | 83 ++++++++++++++++++++++++++++++++++
mm/huge_memory.c | 1 +
mm/memory.c | 4 ++
6 files changed, 143 insertions(+), 54 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1821629..54b3094 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -594,50 +594,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
* sets it, so none of the operations on it need to be atomic.
*/

-
-/*
- * page->flags layout:
- *
- * There are three possibilities for how page->flags get
- * laid out. The first is for the normal case, without
- * sparsemem. The second is for sparsemem when there is
- * plenty of space for node and section. The last is when
- * we have run out of space and have to fall back to an
- * alternate (slower) way of determining the node.
- *
- * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS |
- * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
- * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS |
- */
-#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
-#define SECTIONS_WIDTH SECTIONS_SHIFT
-#else
-#define SECTIONS_WIDTH 0
-#endif
-
-#define ZONES_WIDTH ZONES_SHIFT
-
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
-#define NODES_WIDTH NODES_SHIFT
-#else
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#error "Vmemmap: No space for nodes field in page flags"
-#endif
-#define NODES_WIDTH 0
-#endif
-
-/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
+/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */
#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
-
-/*
- * We are going to use the flags for the page to node mapping if its in
- * there. This includes the case where there is no node, so it is implicit.
- */
-#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
-#define NODE_NOT_IN_PAGE_FLAGS
-#endif
+#define LAST_NID_PGOFF (ZONES_PGOFF - LAST_NID_WIDTH)

/*
* Define the bit shifts to access each section. For non-existent
@@ -647,6 +608,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0))
+#define LAST_NID_PGSHIFT (LAST_NID_PGOFF * (LAST_NID_WIDTH != 0))

/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
#ifdef NODE_NOT_IN_PAGE_FLAGS
@@ -668,6 +630,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
+#define LAST_NID_MASK ((1UL << LAST_NID_WIDTH) - 1)
#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1)

static inline enum zone_type page_zonenum(const struct page *page)
@@ -706,6 +669,51 @@ static inline int page_to_nid(const struct page *page)
}
#endif

+#ifdef CONFIG_SCHED_NUMA
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+ return xchg(&page->_last_nid, nid);
+}
+
+static inline int page_last_nid(struct page *page)
+{
+ return page->_last_nid;
+}
+#else
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+ unsigned long old_flags, flags;
+ int last_nid;
+
+ do {
+ old_flags = flags = page->flags;
+ last_nid = (flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK;
+
+ flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
+ flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+ } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
+
+ return last_nid;
+}
+
+static inline int page_last_nid(struct page *page)
+{
+ return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK;
+}
+#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */
+#else /* CONFIG_SCHED_NUMA */
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+ return page_to_nid(page);
+}
+
+static inline int page_last_nid(struct page *page)
+{
+ return page_to_nid(page);
+}
+#endif /* CONFIG_SCHED_NUMA */
+
static inline struct zone *page_zone(const struct page *page)
{
return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 31f8a3a..5f0af06 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -12,6 +12,7 @@
#include <linux/cpumask.h>
#include <linux/page-debug-flags.h>
#include <linux/uprobes.h>
+#include <linux/page-flags-layout.h>
#include <asm/page.h>
#include <asm/mmu.h>

@@ -175,6 +176,10 @@ struct page {
*/
void *shadow;
#endif
+
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+ int _last_nid;
+#endif
}
/*
* The struct page can be forced to be double word aligned so that atomic ops
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 50aaca8..7e116ed 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -15,7 +15,7 @@
#include <linux/seqlock.h>
#include <linux/nodemask.h>
#include <linux/pageblock-flags.h>
-#include <generated/bounds.h>
+#include <linux/page-flags-layout.h>
#include <linux/atomic.h>
#include <asm/page.h>

@@ -318,16 +318,6 @@ enum zone_type {
* match the requested limits. See gfp_zone() in include/linux/gfp.h
*/

-#if MAX_NR_ZONES < 2
-#define ZONES_SHIFT 0
-#elif MAX_NR_ZONES <= 2
-#define ZONES_SHIFT 1
-#elif MAX_NR_ZONES <= 4
-#define ZONES_SHIFT 2
-#else
-#error ZONES_SHIFT -- too many zones configured adjust calculation
-#endif
-
struct zone {
/* Fields commonly accessed by the page allocator */

@@ -1030,8 +1020,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
* PA_SECTION_SHIFT physical address to/from section number
* PFN_SECTION_SHIFT pfn to/from section number
*/
-#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)
-
#define PA_SECTION_SHIFT (SECTION_SIZE_BITS)
#define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT)

diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
new file mode 100644
index 0000000..586ddb6
--- /dev/null
+++ b/include/linux/page-flags-layout.h
@@ -0,0 +1,83 @@
+#ifndef _LINUX_PAGE_FLAGS_LAYOUT
+#define _LINUX_PAGE_FLAGS_LAYOUT
+
+#include <linux/numa.h>
+#include <generated/bounds.h>
+
+#if MAX_NR_ZONES < 2
+#define ZONES_SHIFT 0
+#elif MAX_NR_ZONES <= 2
+#define ZONES_SHIFT 1
+#elif MAX_NR_ZONES <= 4
+#define ZONES_SHIFT 2
+#else
+#error ZONES_SHIFT -- too many zones configured adjust calculation
+#endif
+
+#ifdef CONFIG_SPARSEMEM
+#include <asm/sparsemem.h>
+
+/*
+ * SECTION_SHIFT #bits space required to store a section #
+ */
+#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)
+#endif
+
+/*
+ * page->flags layout:
+ *
+ * There are five possibilities for how page->flags get laid out. The first
+ * (and second) is for the normal case, without sparsemem. The third is for
+ * sparsemem when there is plenty of space for node and section. The last is
+ * when we have run out of space and have to fall back to an alternate (slower)
+ * way of determining the node.
+ *
+ * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS |
+ * " plus space for last_nid:| NODE | ZONE | LAST_NID | ... | FLAGS |
+ * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
+ * " plus space for last_nid:| SECTION | NODE | ZONE | LAST_NID | ... | FLAGS |
+ * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS |
+ */
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+
+#define SECTIONS_WIDTH SECTIONS_SHIFT
+#else
+#define SECTIONS_WIDTH 0
+#endif
+
+#define ZONES_WIDTH ZONES_SHIFT
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define NODES_WIDTH NODES_SHIFT
+#else
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#error "Vmemmap: No space for nodes field in page flags"
+#endif
+#define NODES_WIDTH 0
+#endif
+
+#ifdef CONFIG_SCHED_NUMA
+#define LAST_NID_SHIFT NODES_SHIFT
+#else
+#define LAST_NID_SHIFT 0
+#endif
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define LAST_NID_WIDTH LAST_NID_SHIFT
+#else
+#define LAST_NID_WIDTH 0
+#endif
+
+/*
+ * We are going to use the flags for the page to node mapping if its in
+ * there. This includes the case where there is no node, so it is implicit.
+ */
+#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
+#define NODE_NOT_IN_PAGE_FLAGS
+#endif
+
+#if defined(CONFIG_SCHED_NUMA) && LAST_NID_WIDTH == 0
+#define LAST_NID_NOT_IN_PAGE_FLAGS
+#endif
+
+#endif /* _LINUX_PAGE_FLAGS_LAYOUT */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 931caf4..3ff121d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1440,6 +1440,7 @@ static void __split_huge_page_refcount(struct page *page)
page_tail->mapping = page->mapping;

page_tail->index = page->index + i;
+ page_xchg_last_nid(page, page_last_nid(page_tail));

BUG_ON(!PageAnon(page_tail));
BUG_ON(!PageUptodate(page_tail));
diff --git a/mm/memory.c b/mm/memory.c
index 0d26a28..b2e3b79 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -68,6 +68,10 @@

#include "internal.h"

+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA config, growing page-frame for last_nid.
+#endif
+
#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: tip-bot for Peter Zijlstra: "[tip:numa/core] sched, numa, mm/mpol: Add_MPOL_F_HOME"
Previous message: tip-bot for Peter Zijlstra: "[tip:numa/core] sched, numa, mm: Implement home-node awareness"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]