forked from Minki/linux
9d8cebd4bc
Strangely, current mbind() doesn't merge vma with neighbor vma although it's possible.
Unfortunately, many vma can reduce performance...
This patch fixes it.
reproduced program
----------------------------------------------------------------
#include <numaif.h>
#include <numa.h>
#include <sys/mman.h>
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
static unsigned long pagesize;
int main(int argc, char** argv)
{
void* addr;
int ch;
int node;
struct bitmask *nmask = numa_allocate_nodemask();
int err;
int node_set = 0;
char buf[128];
while ((ch = getopt(argc, argv, "n:")) != -1){
switch (ch){
case 'n':
node = strtol(optarg, NULL, 0);
numa_bitmask_setbit(nmask, node);
node_set = 1;
break;
default:
;
}
}
argc -= optind;
argv += optind;
if (!node_set)
numa_bitmask_setbit(nmask, 0);
pagesize = getpagesize();
addr = mmap(NULL, pagesize*3, PROT_READ|PROT_WRITE,
MAP_ANON|MAP_PRIVATE, 0, 0);
if (addr == MAP_FAILED)
perror("mmap "), exit(1);
fprintf(stderr, "pid = %d \n" "addr = %p\n", getpid(), addr);
/* make page populate */
memset(addr, 0, pagesize*3);
/* first mbind */
err = mbind(addr+pagesize, pagesize, MPOL_BIND, nmask->maskp,
nmask->size, MPOL_MF_MOVE_ALL);
if (err)
error("mbind1 ");
/* second mbind */
err = mbind(addr, pagesize*3, MPOL_DEFAULT, NULL, 0, 0);
if (err)
error("mbind2 ");
sprintf(buf, "cat /proc/%d/maps", getpid());
system(buf);
return 0;
}
----------------------------------------------------------------
result without this patch
addr = 0x7fe26ef09000
[snip]
7fe26ef09000-7fe26ef0a000 rw-p 00000000 00:00 0
7fe26ef0a000-7fe26ef0b000 rw-p 00000000 00:00 0
7fe26ef0b000-7fe26ef0c000 rw-p 00000000 00:00 0
7fe26ef0c000-7fe26ef0d000 rw-p 00000000 00:00 0
=> 0x7fe26ef09000-0x7fe26ef0c000 have three vmas.
result with this patch
addr = 0x7fc9ebc76000
[snip]
7fc9ebc76000-7fc9ebc7a000 rw-p 00000000 00:00 0
7fffbe690000-7fffbe6a5000 rw-p 00000000 00:00 0 [stack]
=> 0x7fc9ebc76000-0x7fc9ebc7a000 have only one vma.
[minchan.kim@gmail.com: fix file offset passed to vma_merge()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
||
|---|---|---|
| .. | ||
| backing-dev.c | ||
| bootmem.c | ||
| bounce.c | ||
| debug-pagealloc.c | ||
| dmapool.c | ||
| fadvise.c | ||
| failslab.c | ||
| filemap_xip.c | ||
| filemap.c | ||
| fremap.c | ||
| highmem.c | ||
| hugetlb.c | ||
| hwpoison-inject.c | ||
| init-mm.c | ||
| internal.h | ||
| Kconfig | ||
| Kconfig.debug | ||
| kmemcheck.c | ||
| kmemleak-test.c | ||
| kmemleak.c | ||
| ksm.c | ||
| maccess.c | ||
| madvise.c | ||
| Makefile | ||
| memcontrol.c | ||
| memory_hotplug.c | ||
| memory-failure.c | ||
| memory.c | ||
| mempolicy.c | ||
| mempool.c | ||
| migrate.c | ||
| mincore.c | ||
| mlock.c | ||
| mm_init.c | ||
| mmap.c | ||
| mmu_context.c | ||
| mmu_notifier.c | ||
| mmzone.c | ||
| mprotect.c | ||
| mremap.c | ||
| msync.c | ||
| nommu.c | ||
| oom_kill.c | ||
| page_alloc.c | ||
| page_cgroup.c | ||
| page_io.c | ||
| page_isolation.c | ||
| page-writeback.c | ||
| pagewalk.c | ||
| percpu.c | ||
| prio_tree.c | ||
| quicklist.c | ||
| readahead.c | ||
| rmap.c | ||
| shmem.c | ||
| slab.c | ||
| slob.c | ||
| slub.c | ||
| sparse-vmemmap.c | ||
| sparse.c | ||
| swap_state.c | ||
| swap.c | ||
| swapfile.c | ||
| thrash.c | ||
| truncate.c | ||
| util.c | ||
| vmalloc.c | ||
| vmscan.c | ||
| vmstat.c | ||