![Dave Hansen](/assets/img/avatar_default.png)
This code was an optimization for 32-bit NUMA systems. It has probably been the cause of a number of subtle bugs over the years, although the conditions to excite them would have been hard to trigger. Essentially, we remap part of the kernel linear mapping area, and then sometimes part of that area gets freed back in to the bootmem allocator. If those pages get used by kernel data structures (say mem_map[] or a dentry), there's no big deal. But, if anyone ever tried to use the linear mapping for these pages _and_ cared about their physical address, bad things happen. For instance, say you passed __GFP_ZERO to the page allocator and then happened to get handed one of these pages, it zero the remapped page, but it would make a pte to the _old_ page. There are probably a hundred other ways that it could screw with things. We don't need to hang on to performance optimizations for these old boxes any more. All my 32-bit NUMA systems are long dead and buried, and I probably had access to more than most people. This code is causing real things to break today: https://lkml.org/lkml/2013/1/9/376 I looked in to actually fixing this, but it requires surgery to way too much brittle code, as well as stuff like per_cpu_ptr_to_phys(). [ hpa: Cc: this for -stable, since it is a memory corruption issue. However, an alternative is to simply mark NUMA as depends BROKEN rather than EXPERIMENTAL in the X86_32 subclause... ] Link: http://lkml.kernel.org/r/20130131005616.1C79F411@kernel.stglabs.ibm.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: <stable@vger.kernel.org>
105 lines
3.2 KiB
C
105 lines
3.2 KiB
C
/*
|
|
* Written by: Patricia Gaughen <gone@us.ibm.com>, IBM Corporation
|
|
* August 2002: added remote node KVA remap - Martin J. Bligh
|
|
*
|
|
* Copyright (C) 2002, IBM Corp.
|
|
*
|
|
* All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for more
|
|
* details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*/
|
|
|
|
#include <linux/bootmem.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/module.h>
|
|
|
|
#include "numa_internal.h"
|
|
|
|
#ifdef CONFIG_DISCONTIGMEM
|
|
/*
|
|
* 4) physnode_map - the mapping between a pfn and owning node
|
|
* physnode_map keeps track of the physical memory layout of a generic
|
|
* numa node on a 64Mb break (each element of the array will
|
|
* represent 64Mb of memory and will be marked by the node id. so,
|
|
* if the first gig is on node 0, and the second gig is on node 1
|
|
* physnode_map will contain:
|
|
*
|
|
* physnode_map[0-15] = 0;
|
|
* physnode_map[16-31] = 1;
|
|
* physnode_map[32- ] = -1;
|
|
*/
|
|
s8 physnode_map[MAX_SECTIONS] __read_mostly = { [0 ... (MAX_SECTIONS - 1)] = -1};
|
|
EXPORT_SYMBOL(physnode_map);
|
|
|
|
void memory_present(int nid, unsigned long start, unsigned long end)
|
|
{
|
|
unsigned long pfn;
|
|
|
|
printk(KERN_INFO "Node: %d, start_pfn: %lx, end_pfn: %lx\n",
|
|
nid, start, end);
|
|
printk(KERN_DEBUG " Setting physnode_map array to node %d for pfns:\n", nid);
|
|
printk(KERN_DEBUG " ");
|
|
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
|
|
physnode_map[pfn / PAGES_PER_SECTION] = nid;
|
|
printk(KERN_CONT "%lx ", pfn);
|
|
}
|
|
printk(KERN_CONT "\n");
|
|
}
|
|
|
|
unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
|
|
unsigned long end_pfn)
|
|
{
|
|
unsigned long nr_pages = end_pfn - start_pfn;
|
|
|
|
if (!nr_pages)
|
|
return 0;
|
|
|
|
return (nr_pages + 1) * sizeof(struct page);
|
|
}
|
|
#endif
|
|
|
|
extern unsigned long highend_pfn, highstart_pfn;
|
|
|
|
void __init initmem_init(void)
|
|
{
|
|
x86_numa_init();
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
highstart_pfn = highend_pfn = max_pfn;
|
|
if (max_pfn > max_low_pfn)
|
|
highstart_pfn = max_low_pfn;
|
|
printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
|
|
pages_to_mb(highend_pfn - highstart_pfn));
|
|
num_physpages = highend_pfn;
|
|
high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
|
|
#else
|
|
num_physpages = max_low_pfn;
|
|
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
|
|
#endif
|
|
printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
|
|
pages_to_mb(max_low_pfn));
|
|
printk(KERN_DEBUG "max_low_pfn = %lx, highstart_pfn = %lx\n",
|
|
max_low_pfn, highstart_pfn);
|
|
|
|
printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
|
|
(ulong) pfn_to_kaddr(max_low_pfn));
|
|
|
|
printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
|
|
(ulong) pfn_to_kaddr(highstart_pfn));
|
|
|
|
setup_bootmem_allocator();
|
|
}
|