a26474e864
During 32/64 NUMA init unification, commit 797390d855 ("x86-32,
NUMA: use sparse_memory_present_with_active_regions()") made
32bit mm init call memory_present() automatically from
active_regions instead of leaving it to each NUMA init path.
This commit description is inaccurate - memory_present() calls
aren't the same for flat and numaq. After the commit,
memory_present() is only called for the intersection of e820 and
NUMA layout. Before, on flatmem, memory_present() would be
called from 0 to max_pfn. After, it would be called only on the
areas that e820 indicates to be populated.
This is how x86_64 works and should be okay as memmap is allowed
to contain holes; however, x86_32 DISCONTIGMEM is missing
early_pfn_valid(), which makes memmap_init_zone() assume that
memmap doesn't contain any hole. This leads to the following
oops if e820 map contains holes as it often does on machine with
near or more 4GiB of memory by calling pfn_to_page() on a pfn
which isn't mapped to a NUMA node, a reported by Conny Seidel:
BUG: unable to handle kernel paging request at 000012b0
IP: [<c1aa13ce>] memmap_init_zone+0x6c/0xf2
*pdpt =3D 0000000000000000 *pde =3D f000eef3f000ee00
Oops: 0000 [#1] SMP
last sysfs file:
Modules linked in:
Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00164-g797390d #1 To Be Filled By O.E.M. To Be Filled By O.E.M./E350M1
EIP: 0060:[<c1aa13ce>] EFLAGS: 00010012 CPU: 0
EIP is at memmap_init_zone+0x6c/0xf2
EAX: 00000000 EBX: 000a8000 ECX: 000a7fff EDX: f2c00b80
ESI: 000a8000 EDI: f2c00800 EBP: c19ffe54 ESP: c19ffe34
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Process swapper (pid: 0, ti=3Dc19fe000 task=3Dc1a07f60 task.ti=3Dc19fe000)
Stack:
00000002 00000000 0023f000 00000000 10000000 00000a00 f2c00000 f2c00b58
c19ffeb0 c1a80f24 000375fe 00000000 f2c00800 00000800 00000100 00000030
c1abb768 0000003c 00000000 00000000 00000004 00207a02 f2c00800 000375fe
Call Trace:
[<c1a80f24>] free_area_init_node+0x358/0x385
[<c1a81384>] free_area_init_nodes+0x420/0x487
[<c1a79326>] paging_init+0x114/0x11b
[<c1a6cb13>] setup_arch+0xb37/0xc0a
[<c1a69554>] start_kernel+0x76/0x316
[<c1a690a8>] i386_start_kernel+0xa8/0xb0
This patch fixes the bug by defining early_pfn_valid() to be the
same as pfn_valid() when DISCONTIGMEM.
Reported-bisected-and-tested-by: Conny Seidel <conny.seidel@amd.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: hans.rosenfeld@amd.com
Cc: Christoph Lameter <cl@linux.com>
Cc: Conny Seidel <conny.seidel@amd.com>
Link: http://lkml.kernel.org/r/20110628094107.GB3386@htj.dyndns.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
71 lines
1.5 KiB
C
71 lines
1.5 KiB
C
/*
|
|
* Written by Pat Gaughen (gone@us.ibm.com) Mar 2002
|
|
*
|
|
*/
|
|
|
|
#ifndef _ASM_X86_MMZONE_32_H
|
|
#define _ASM_X86_MMZONE_32_H
|
|
|
|
#include <asm/smp.h>
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern struct pglist_data *node_data[];
|
|
#define NODE_DATA(nid) (node_data[nid])
|
|
|
|
#include <asm/numaq.h>
|
|
|
|
extern void resume_map_numa_kva(pgd_t *pgd);
|
|
|
|
#else /* !CONFIG_NUMA */
|
|
|
|
static inline void resume_map_numa_kva(pgd_t *pgd) {}
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
#ifdef CONFIG_DISCONTIGMEM
|
|
|
|
/*
|
|
* generic node memory support, the following assumptions apply:
|
|
*
|
|
* 1) memory comes in 64Mb contiguous chunks which are either present or not
|
|
* 2) we will not have more than 64Gb in total
|
|
*
|
|
* for now assume that 64Gb is max amount of RAM for whole system
|
|
* 64Gb / 4096bytes/page = 16777216 pages
|
|
*/
|
|
#define MAX_NR_PAGES 16777216
|
|
#define MAX_ELEMENTS 1024
|
|
#define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
|
|
|
|
extern s8 physnode_map[];
|
|
|
|
static inline int pfn_to_nid(unsigned long pfn)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
return((int) physnode_map[(pfn) / PAGES_PER_ELEMENT]);
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
static inline int pfn_valid(int pfn)
|
|
{
|
|
int nid = pfn_to_nid(pfn);
|
|
|
|
if (nid >= 0)
|
|
return (pfn < node_end_pfn(nid));
|
|
return 0;
|
|
}
|
|
|
|
#define early_pfn_valid(pfn) pfn_valid((pfn))
|
|
|
|
#endif /* CONFIG_DISCONTIGMEM */
|
|
|
|
#ifdef CONFIG_NEED_MULTIPLE_NODES
|
|
/* always use node 0 for bootmem on this numa platform */
|
|
#define bootmem_arch_preferred_node(__bdata, size, align, goal, limit) \
|
|
(NODE_DATA(0)->bdata)
|
|
#endif /* CONFIG_NEED_MULTIPLE_NODES */
|
|
|
|
#endif /* _ASM_X86_MMZONE_32_H */
|