f2dbcfa738
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>
93 lines
2.5 KiB
C
93 lines
2.5 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* This file contains NUMA specific variables and functions which can
|
|
* be split away from DISCONTIGMEM and are used on NUMA machines with
|
|
* contiguous memory.
|
|
*
|
|
* 2002/08/07 Erich Focht <efocht@ess.nec.de>
|
|
*/
|
|
|
|
#include <linux/cpu.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/node.h>
|
|
#include <linux/init.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/module.h>
|
|
#include <asm/mmzone.h>
|
|
#include <asm/numa.h>
|
|
|
|
|
|
/*
|
|
* The following structures are usually initialized by ACPI or
|
|
* similar mechanisms and describe the NUMA characteristics of the machine.
|
|
*/
|
|
int num_node_memblks;
|
|
struct node_memblk_s node_memblk[NR_NODE_MEMBLKS];
|
|
struct node_cpuid_s node_cpuid[NR_CPUS] =
|
|
{ [0 ... NR_CPUS-1] = { .phys_id = 0, .nid = NUMA_NO_NODE } };
|
|
|
|
/*
|
|
* This is a matrix with "distances" between nodes, they should be
|
|
* proportional to the memory access latency ratios.
|
|
*/
|
|
u8 numa_slit[MAX_NUMNODES * MAX_NUMNODES];
|
|
|
|
/* Identify which cnode a physical address resides on */
|
|
int
|
|
paddr_to_nid(unsigned long paddr)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < num_node_memblks; i++)
|
|
if (paddr >= node_memblk[i].start_paddr &&
|
|
paddr < node_memblk[i].start_paddr + node_memblk[i].size)
|
|
break;
|
|
|
|
return (i < num_node_memblks) ? node_memblk[i].nid : (num_node_memblks ? -1 : 0);
|
|
}
|
|
|
|
#if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
|
|
/*
|
|
* Because of holes evaluate on section limits.
|
|
* If the section of memory exists, then return the node where the section
|
|
* resides. Otherwise return node 0 as the default. This is used by
|
|
* SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
|
|
* the section resides.
|
|
*/
|
|
int __meminit __early_pfn_to_nid(unsigned long pfn)
|
|
{
|
|
int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
|
|
|
|
for (i = 0; i < num_node_memblks; i++) {
|
|
ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
|
|
esec = (node_memblk[i].start_paddr + node_memblk[i].size +
|
|
((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
|
|
if (section >= ssec && section < esec)
|
|
return node_memblk[i].nid;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
/*
|
|
* SRAT information is stored in node_memblk[], then we can use SRAT
|
|
* information at memory-hot-add if necessary.
|
|
*/
|
|
|
|
int memory_add_physaddr_to_nid(u64 addr)
|
|
{
|
|
int nid = paddr_to_nid(addr);
|
|
if (nid < 0)
|
|
return 0;
|
|
return nid;
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
|
|
#endif
|
|
#endif
|