linux/arch/x86/include/asm/mmzone_64.h
KAMEZAWA Hiroyuki f2dbcfa738 mm: clean up for early_pfn_to_nid()
What's happening is that the assertion in mm/page_alloc.c:move_freepages()
is triggering:

	BUG_ON(page_zone(start_page) != page_zone(end_page));

Once I knew this is what was happening, I added some annotations:

	if (unlikely(page_zone(start_page) != page_zone(end_page))) {
		printk(KERN_ERR "move_freepages: Bogus zones: "
		       "start_page[%p] end_page[%p] zone[%p]\n",
		       start_page, end_page, zone);
		printk(KERN_ERR "move_freepages: "
		       "start_zone[%p] end_zone[%p]\n",
		       page_zone(start_page), page_zone(end_page));
		printk(KERN_ERR "move_freepages: "
		       "start_pfn[0x%lx] end_pfn[0x%lx]\n",
		       page_to_pfn(start_page), page_to_pfn(end_page));
		printk(KERN_ERR "move_freepages: "
		       "start_nid[%d] end_nid[%d]\n",
		       page_to_nid(start_page), page_to_nid(end_page));
 ...

And here's what I got:

	move_freepages: Bogus zones: start_page[2207d0000] end_page[2207dffc0] zone[fffff8103effcb00]
	move_freepages: start_zone[fffff8103effcb00] end_zone[fffff8003fffeb00]
	move_freepages: start_pfn[0x81f600] end_pfn[0x81f7ff]
	move_freepages: start_nid[1] end_nid[0]

My memory layout on this box is:

[    0.000000] Zone PFN ranges:
[    0.000000]   Normal   0x00000000 -> 0x0081ff5d
[    0.000000] Movable zone start PFN for each node
[    0.000000] early_node_map[8] active PFN ranges
[    0.000000]     0: 0x00000000 -> 0x00020000
[    0.000000]     1: 0x00800000 -> 0x0081f7ff
[    0.000000]     1: 0x0081f800 -> 0x0081fe50
[    0.000000]     1: 0x0081fed1 -> 0x0081fed8
[    0.000000]     1: 0x0081feda -> 0x0081fedb
[    0.000000]     1: 0x0081fedd -> 0x0081fee5
[    0.000000]     1: 0x0081fee7 -> 0x0081ff51
[    0.000000]     1: 0x0081ff59 -> 0x0081ff5d

So it's a block move in that 0x81f600-->0x81f7ff region which triggers
the problem.

This patch:

Declaration of early_pfn_to_nid() is scattered over per-arch include
files, and it seems it's complicated to know when the declaration is used.
 I think it makes fix-for-memmap-init not easy.

This patch moves all declaration to include/linux/mm.h

After this,
  if !CONFIG_NODES_POPULATES_NODE_MAP && !CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
     -> Use static definition in include/linux/mm.h
  else if !CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
     -> Use generic definition in mm/page_alloc.c
  else
     -> per-arch back end function will be called.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reported-by: David Miller <davem@davemlloft.net>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: <stable@kernel.org>		[2.6.25.x, 2.6.26.x, 2.6.27.x, 2.6.28.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-18 15:37:55 -08:00

49 lines
1.3 KiB
C

/* K8 NUMA support */
/* Copyright 2002,2003 by Andi Kleen, SuSE Labs */
/* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */
#ifndef _ASM_X86_MMZONE_64_H
#define _ASM_X86_MMZONE_64_H
#ifdef CONFIG_NUMA
#include <linux/mmdebug.h>
#include <asm/smp.h>
/* Simple perfect hash to map physical addresses to node numbers */
struct memnode {
int shift;
unsigned int mapsize;
s16 *map;
s16 embedded_map[64 - 8];
} ____cacheline_aligned; /* total size = 128 bytes */
extern struct memnode memnode;
#define memnode_shift memnode.shift
#define memnodemap memnode.map
#define memnodemapsize memnode.mapsize
extern struct pglist_data *node_data[];
static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
{
unsigned nid;
VIRTUAL_BUG_ON(!memnodemap);
nid = memnodemap[addr >> memnode_shift];
VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
return nid;
}
#define NODE_DATA(nid) (node_data[nid])
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \
NODE_DATA(nid)->node_spanned_pages)
#ifdef CONFIG_NUMA_EMU
#define FAKE_NODE_MIN_SIZE (64 * 1024 * 1024)
#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
#endif
#endif
#endif /* _ASM_X86_MMZONE_64_H */