Revision 3ad33b2436b545cbe8b28e53f3710432cad457ab authored by Lee Schermerhorn on 15 November 2007, 00:59:10 UTC, committed by Linus Torvalds on 15 November 2007, 02:45:38 UTC
We hit the BUG_ON() in mm/rmap.c:vma_address() when trying to migrate via mbind(MPOL_MF_MOVE) a non-anon region that spans multiple vmas. For anon-regions, we just fail to migrate any pages beyond the 1st vma in the range. This occurs because do_mbind() collects a list of pages to migrate by calling check_range(). check_range() walks the task's mm, spanning vmas as necessary, to collect the migratable pages into a list. Then, do_mbind() calls migrate_pages() passing the list of pages, a function to allocate new pages based on vma policy [new_vma_page()], and a pointer to the first vma of the range. For each page in the list, new_vma_page() calls page_address_in_vma() passing the page and the vma [first in range] to obtain the address to get for alloc_page_vma(). The page address is needed to get interleaving policy correct. If the pages in the list come from multiple vmas, eventually, new_page_address() will pass that page to page_address_in_vma() with the incorrect vma. For !PageAnon pages, this will result in a bug check in rmap.c:vma_address(). For anon pages, vma_address() will just return EFAULT and fail the migration. This patch modifies new_vma_page() to check the return value from page_address_in_vma(). If the return value is EFAULT, new_vma_page() searchs forward via vm_next for the vma that maps the page--i.e., that does not return EFAULT. This assumes that the pages in the list handed to migrate_pages() is in address order. This is currently case. The patch documents this assumption in a new comment block for new_vma_page(). If new_vma_page() cannot locate the vma mapping the page in a forward search in the mm, it will pass a NULL vma to alloc_page_vma(). This will result in the allocation using the task policy, if any, else system default policy. This situation is unlikely, but the patch documents this behavior with a comment. Note, this patch results in restarting from the first vma in a multi-vma range each time new_vma_page() is called. If this is not acceptable, we can make the vma argument a pointer, both in new_vma_page() and it's caller unmap_and_move() so that the value held by the loop in migrate_pages() always passes down the last vma in which a page was found. This will require changes to all new_page_t functions passed to migrate_pages(). Is this necessary? For this patch to work, we can't bug check in vma_address() for pages outside the argument vma. This patch removes the BUG_ON(). All other callers [besides new_vma_page()] already check the return status. Tested on x86_64, 4 node NUMA platform. Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent e1a1c99
bootmem.c
/*
* linux/mm/bootmem.c
*
* Copyright (C) 1999 Ingo Molnar
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
*
* simple boot-time physical memory area allocator and
* free memory collector. It's used to deal with reserved
* system memory and memory holes as well.
*/
#include <linux/init.h>
#include <linux/pfn.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <asm/bug.h>
#include <asm/io.h>
#include <asm/processor.h>
#include "internal.h"
/*
* Access to this subsystem has to be serialized externally. (this is
* true for the boot process anyway)
*/
unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;
static LIST_HEAD(bdata_list);
#ifdef CONFIG_CRASH_DUMP
/*
* If we have booted due to a crash, max_pfn will be a very low value. We need
* to know the amount of memory that the previous kernel used.
*/
unsigned long saved_max_pfn;
#endif
/* return the number of _pages_ that will be allocated for the boot bitmap */
unsigned long __init bootmem_bootmap_pages(unsigned long pages)
{
unsigned long mapsize;
mapsize = (pages+7)/8;
mapsize = (mapsize + ~PAGE_MASK) & PAGE_MASK;
mapsize >>= PAGE_SHIFT;
return mapsize;
}
/*
* link bdata in order
*/
static void __init link_bootmem(bootmem_data_t *bdata)
{
bootmem_data_t *ent;
if (list_empty(&bdata_list)) {
list_add(&bdata->list, &bdata_list);
return;
}
/* insert in order */
list_for_each_entry(ent, &bdata_list, list) {
if (bdata->node_boot_start < ent->node_boot_start) {
list_add_tail(&bdata->list, &ent->list);
return;
}
}
list_add_tail(&bdata->list, &bdata_list);
}
/*
* Given an initialised bdata, it returns the size of the boot bitmap
*/
static unsigned long __init get_mapsize(bootmem_data_t *bdata)
{
unsigned long mapsize;
unsigned long start = PFN_DOWN(bdata->node_boot_start);
unsigned long end = bdata->node_low_pfn;
mapsize = ((end - start) + 7) / 8;
return ALIGN(mapsize, sizeof(long));
}
/*
* Called once to set up the allocator itself.
*/
static unsigned long __init init_bootmem_core(pg_data_t *pgdat,
unsigned long mapstart, unsigned long start, unsigned long end)
{
bootmem_data_t *bdata = pgdat->bdata;
unsigned long mapsize;
bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
bdata->node_boot_start = PFN_PHYS(start);
bdata->node_low_pfn = end;
link_bootmem(bdata);
/*
* Initially all pages are reserved - setup_arch() has to
* register free RAM areas explicitly.
*/
mapsize = get_mapsize(bdata);
memset(bdata->node_bootmem_map, 0xff, mapsize);
return mapsize;
}
/*
* Marks a particular physical memory range as unallocatable. Usable RAM
* might be used for boot-time allocations - or it might get added
* to the free page pool later on.
*/
static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
unsigned long size)
{
unsigned long sidx, eidx;
unsigned long i;
/*
* round up, partially reserved pages are considered
* fully reserved.
*/
BUG_ON(!size);
BUG_ON(PFN_DOWN(addr) >= bdata->node_low_pfn);
BUG_ON(PFN_UP(addr + size) > bdata->node_low_pfn);
sidx = PFN_DOWN(addr - bdata->node_boot_start);
eidx = PFN_UP(addr + size - bdata->node_boot_start);
for (i = sidx; i < eidx; i++)
if (test_and_set_bit(i, bdata->node_bootmem_map)) {
#ifdef CONFIG_DEBUG_BOOTMEM
printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE);
#endif
}
}
static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
unsigned long size)
{
unsigned long sidx, eidx;
unsigned long i;
/*
* round down end of usable mem, partially free pages are
* considered reserved.
*/
BUG_ON(!size);
BUG_ON(PFN_DOWN(addr + size) > bdata->node_low_pfn);
if (addr < bdata->last_success)
bdata->last_success = addr;
/*
* Round up the beginning of the address.
*/
sidx = PFN_UP(addr) - PFN_DOWN(bdata->node_boot_start);
eidx = PFN_DOWN(addr + size - bdata->node_boot_start);
for (i = sidx; i < eidx; i++) {
if (unlikely(!test_and_clear_bit(i, bdata->node_bootmem_map)))
BUG();
}
}
/*
* We 'merge' subsequent allocations to save space. We might 'lose'
* some fraction of a page if allocations cannot be satisfied due to
* size constraints on boxes where there is physical RAM space
* fragmentation - in these cases (mostly large memory boxes) this
* is not a problem.
*
* On low memory boxes we get it right in 100% of the cases.
*
* alignment has to be a power of 2 value.
*
* NOTE: This function is _not_ reentrant.
*/
void * __init
__alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
unsigned long align, unsigned long goal, unsigned long limit)
{
unsigned long offset, remaining_size, areasize, preferred;
unsigned long i, start = 0, incr, eidx, end_pfn;
void *ret;
if (!size) {
printk("__alloc_bootmem_core(): zero-sized request\n");
BUG();
}
BUG_ON(align & (align-1));
if (limit && bdata->node_boot_start >= limit)
return NULL;
/* on nodes without memory - bootmem_map is NULL */
if (!bdata->node_bootmem_map)
return NULL;
end_pfn = bdata->node_low_pfn;
limit = PFN_DOWN(limit);
if (limit && end_pfn > limit)
end_pfn = limit;
eidx = end_pfn - PFN_DOWN(bdata->node_boot_start);
offset = 0;
if (align && (bdata->node_boot_start & (align - 1UL)) != 0)
offset = align - (bdata->node_boot_start & (align - 1UL));
offset = PFN_DOWN(offset);
/*
* We try to allocate bootmem pages above 'goal'
* first, then we try to allocate lower pages.
*/
if (goal && goal >= bdata->node_boot_start && PFN_DOWN(goal) < end_pfn) {
preferred = goal - bdata->node_boot_start;
if (bdata->last_success >= preferred)
if (!limit || (limit && limit > bdata->last_success))
preferred = bdata->last_success;
} else
preferred = 0;
preferred = PFN_DOWN(ALIGN(preferred, align)) + offset;
areasize = (size + PAGE_SIZE-1) / PAGE_SIZE;
incr = align >> PAGE_SHIFT ? : 1;
restart_scan:
for (i = preferred; i < eidx; i += incr) {
unsigned long j;
i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
i = ALIGN(i, incr);
if (i >= eidx)
break;
if (test_bit(i, bdata->node_bootmem_map))
continue;
for (j = i + 1; j < i + areasize; ++j) {
if (j >= eidx)
goto fail_block;
if (test_bit(j, bdata->node_bootmem_map))
goto fail_block;
}
start = i;
goto found;
fail_block:
i = ALIGN(j, incr);
}
if (preferred > offset) {
preferred = offset;
goto restart_scan;
}
return NULL;
found:
bdata->last_success = PFN_PHYS(start);
BUG_ON(start >= eidx);
/*
* Is the next page of the previous allocation-end the start
* of this allocation's buffer? If yes then we can 'merge'
* the previous partial page with this allocation.
*/
if (align < PAGE_SIZE &&
bdata->last_offset && bdata->last_pos+1 == start) {
offset = ALIGN(bdata->last_offset, align);
BUG_ON(offset > PAGE_SIZE);
remaining_size = PAGE_SIZE - offset;
if (size < remaining_size) {
areasize = 0;
/* last_pos unchanged */
bdata->last_offset = offset + size;
ret = phys_to_virt(bdata->last_pos * PAGE_SIZE +
offset +
bdata->node_boot_start);
} else {
remaining_size = size - remaining_size;
areasize = (remaining_size + PAGE_SIZE-1) / PAGE_SIZE;
ret = phys_to_virt(bdata->last_pos * PAGE_SIZE +
offset +
bdata->node_boot_start);
bdata->last_pos = start + areasize - 1;
bdata->last_offset = remaining_size;
}
bdata->last_offset &= ~PAGE_MASK;
} else {
bdata->last_pos = start + areasize - 1;
bdata->last_offset = size & ~PAGE_MASK;
ret = phys_to_virt(start * PAGE_SIZE + bdata->node_boot_start);
}
/*
* Reserve the area now:
*/
for (i = start; i < start + areasize; i++)
if (unlikely(test_and_set_bit(i, bdata->node_bootmem_map)))
BUG();
memset(ret, 0, size);
return ret;
}
static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
{
struct page *page;
unsigned long pfn;
bootmem_data_t *bdata = pgdat->bdata;
unsigned long i, count, total = 0;
unsigned long idx;
unsigned long *map;
int gofast = 0;
BUG_ON(!bdata->node_bootmem_map);
count = 0;
/* first extant page of the node */
pfn = PFN_DOWN(bdata->node_boot_start);
idx = bdata->node_low_pfn - pfn;
map = bdata->node_bootmem_map;
/* Check physaddr is O(LOG2(BITS_PER_LONG)) page aligned */
if (bdata->node_boot_start == 0 ||
ffs(bdata->node_boot_start) - PAGE_SHIFT > ffs(BITS_PER_LONG))
gofast = 1;
for (i = 0; i < idx; ) {
unsigned long v = ~map[i / BITS_PER_LONG];
if (gofast && v == ~0UL) {
int order;
page = pfn_to_page(pfn);
count += BITS_PER_LONG;
order = ffs(BITS_PER_LONG) - 1;
__free_pages_bootmem(page, order);
i += BITS_PER_LONG;
page += BITS_PER_LONG;
} else if (v) {
unsigned long m;
page = pfn_to_page(pfn);
for (m = 1; m && i < idx; m<<=1, page++, i++) {
if (v & m) {
count++;
__free_pages_bootmem(page, 0);
}
}
} else {
i += BITS_PER_LONG;
}
pfn += BITS_PER_LONG;
}
total += count;
/*
* Now free the allocator bitmap itself, it's not
* needed anymore:
*/
page = virt_to_page(bdata->node_bootmem_map);
count = 0;
idx = (get_mapsize(bdata) + PAGE_SIZE-1) >> PAGE_SHIFT;
for (i = 0; i < idx; i++, page++) {
__free_pages_bootmem(page, 0);
count++;
}
total += count;
bdata->node_bootmem_map = NULL;
return total;
}
unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
unsigned long startpfn, unsigned long endpfn)
{
return init_bootmem_core(pgdat, freepfn, startpfn, endpfn);
}
void __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
unsigned long size)
{
reserve_bootmem_core(pgdat->bdata, physaddr, size);
}
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
unsigned long size)
{
free_bootmem_core(pgdat->bdata, physaddr, size);
}
unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
{
return free_all_bootmem_core(pgdat);
}
unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
{
max_low_pfn = pages;
min_low_pfn = start;
return init_bootmem_core(NODE_DATA(0), start, 0, pages);
}
#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
void __init reserve_bootmem(unsigned long addr, unsigned long size)
{
reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size);
}
#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
void __init free_bootmem(unsigned long addr, unsigned long size)
{
free_bootmem_core(NODE_DATA(0)->bdata, addr, size);
}
unsigned long __init free_all_bootmem(void)
{
return free_all_bootmem_core(NODE_DATA(0));
}
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
unsigned long goal)
{
bootmem_data_t *bdata;
void *ptr;
list_for_each_entry(bdata, &bdata_list, list) {
ptr = __alloc_bootmem_core(bdata, size, align, goal, 0);
if (ptr)
return ptr;
}
return NULL;
}
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal)
{
void *mem = __alloc_bootmem_nopanic(size,align,goal);
if (mem)
return mem;
/*
* Whoops, we cannot satisfy the allocation request.
*/
printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
panic("Out of memory");
return NULL;
}
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
void *ptr;
ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
if (ptr)
return ptr;
return __alloc_bootmem(size, align, goal);
}
#ifndef ARCH_LOW_ADDRESS_LIMIT
#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL
#endif
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
unsigned long goal)
{
bootmem_data_t *bdata;
void *ptr;
list_for_each_entry(bdata, &bdata_list, list) {
ptr = __alloc_bootmem_core(bdata, size, align, goal,
ARCH_LOW_ADDRESS_LIMIT);
if (ptr)
return ptr;
}
/*
* Whoops, we cannot satisfy the allocation request.
*/
printk(KERN_ALERT "low bootmem alloc of %lu bytes failed!\n", size);
panic("Out of low memory");
return NULL;
}
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
return __alloc_bootmem_core(pgdat->bdata, size, align, goal,
ARCH_LOW_ADDRESS_LIMIT);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...