Revision 73223e4e2e3867ebf033a5a8eb2e5df0158ccc99 authored by zhong jiang on 18 August 2017, 22:16:24 UTC, committed by Linus Torvalds on 18 August 2017, 22:32:02 UTC
I hit a use after free issue when executing trinity and repoduced it with KASAN enabled. The related call trace is as follows. BUG: KASan: use after free in SyS_get_mempolicy+0x3c8/0x960 at addr ffff8801f582d766 Read of size 2 by task syz-executor1/798 INFO: Allocated in mpol_new.part.2+0x74/0x160 age=3 cpu=1 pid=799 __slab_alloc+0x768/0x970 kmem_cache_alloc+0x2e7/0x450 mpol_new.part.2+0x74/0x160 mpol_new+0x66/0x80 SyS_mbind+0x267/0x9f0 system_call_fastpath+0x16/0x1b INFO: Freed in __mpol_put+0x2b/0x40 age=4 cpu=1 pid=799 __slab_free+0x495/0x8e0 kmem_cache_free+0x2f3/0x4c0 __mpol_put+0x2b/0x40 SyS_mbind+0x383/0x9f0 system_call_fastpath+0x16/0x1b INFO: Slab 0xffffea0009cb8dc0 objects=23 used=8 fp=0xffff8801f582de40 flags=0x200000000004080 INFO: Object 0xffff8801f582d760 @offset=5984 fp=0xffff8801f582d600 Bytes b4 ffff8801f582d750: ae 01 ff ff 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ Object ffff8801f582d760: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff8801f582d770: 6b 6b 6b 6b 6b 6b 6b a5 kkkkkkk. Redzone ffff8801f582d778: bb bb bb bb bb bb bb bb ........ Padding ffff8801f582d8b8: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ Memory state around the buggy address: ffff8801f582d600: fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8801f582d680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff8801f582d700: fc fc fc fc fc fc fc fc fc fc fc fc fb fb fb fc !shared memory policy is not protected against parallel removal by other thread which is normally protected by the mmap_sem. do_get_mempolicy, however, drops the lock midway while we can still access it later. Early premature up_read is a historical artifact from times when put_user was called in this path see https://lwn.net/Articles/124754/ but that is gone since 8bccd85ffbaf ("[PATCH] Implement sys_* do_* layering in the memory policy layer."). but when we have the the current mempolicy ref count model. The issue was introduced accordingly. Fix the issue by removing the premature release. Link: http://lkml.kernel.org/r/1502950924-27521-1-git-send-email-zhongjiang@huawei.com Signed-off-by: zhong jiang <zhongjiang@huawei.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: <stable@vger.kernel.org> [2.6+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent da094e4
bounce.c
/* bounce buffer handling for block devices
*
* - Split from highmem.c
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
#include <linux/bootmem.h>
#include <linux/printk.h>
#include <asm/tlbflush.h>
#include <trace/events/block.h>
#include "blk.h"
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
static struct bio_set *bounce_bio_set, *bounce_bio_split;
static mempool_t *page_pool, *isa_page_pool;
#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL)
static __init int init_emergency_pool(void)
{
#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
if (max_pfn <= max_low_pfn)
return 0;
#endif
page_pool = mempool_create_page_pool(POOL_SIZE, 0);
BUG_ON(!page_pool);
pr_info("pool size: %d pages\n", POOL_SIZE);
bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
BUG_ON(!bounce_bio_set);
if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
BUG_ON(1);
bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
BUG_ON(!bounce_bio_split);
return 0;
}
__initcall(init_emergency_pool);
#endif
#ifdef CONFIG_HIGHMEM
/*
* highmem version, map in to vec
*/
static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
{
unsigned long flags;
unsigned char *vto;
local_irq_save(flags);
vto = kmap_atomic(to->bv_page);
memcpy(vto + to->bv_offset, vfrom, to->bv_len);
kunmap_atomic(vto);
local_irq_restore(flags);
}
#else /* CONFIG_HIGHMEM */
#define bounce_copy_vec(to, vfrom) \
memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
#endif /* CONFIG_HIGHMEM */
/*
* allocate pages in the DMA region for the ISA pool
*/
static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
{
return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
}
/*
* gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
* as the max address, so check if the pool has already been created.
*/
int init_emergency_isa_pool(void)
{
if (isa_page_pool)
return 0;
isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
mempool_free_pages, (void *) 0);
BUG_ON(!isa_page_pool);
pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE);
return 0;
}
/*
* Simple bounce buffer support for highmem pages. Depending on the
* queue gfp mask set, *to may or may not be a highmem page. kmap it
* always, it will do the Right Thing
*/
static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
{
unsigned char *vfrom;
struct bio_vec tovec, *fromvec = from->bi_io_vec;
struct bvec_iter iter;
bio_for_each_segment(tovec, to, iter) {
if (tovec.bv_page != fromvec->bv_page) {
/*
* fromvec->bv_offset and fromvec->bv_len might have
* been modified by the block layer, so use the original
* copy, bounce_copy_vec already uses tovec->bv_len
*/
vfrom = page_address(fromvec->bv_page) +
tovec.bv_offset;
bounce_copy_vec(&tovec, vfrom);
flush_dcache_page(tovec.bv_page);
}
fromvec++;
}
}
static void bounce_end_io(struct bio *bio, mempool_t *pool)
{
struct bio *bio_orig = bio->bi_private;
struct bio_vec *bvec, *org_vec;
int i;
int start = bio_orig->bi_iter.bi_idx;
/*
* free up bounce indirect pages used
*/
bio_for_each_segment_all(bvec, bio, i) {
org_vec = bio_orig->bi_io_vec + i + start;
if (bvec->bv_page == org_vec->bv_page)
continue;
dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
mempool_free(bvec->bv_page, pool);
}
bio_orig->bi_status = bio->bi_status;
bio_endio(bio_orig);
bio_put(bio);
}
static void bounce_end_io_write(struct bio *bio)
{
bounce_end_io(bio, page_pool);
}
static void bounce_end_io_write_isa(struct bio *bio)
{
bounce_end_io(bio, isa_page_pool);
}
static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
{
struct bio *bio_orig = bio->bi_private;
if (!bio->bi_status)
copy_to_high_bio_irq(bio_orig, bio);
bounce_end_io(bio, pool);
}
static void bounce_end_io_read(struct bio *bio)
{
__bounce_end_io_read(bio, page_pool);
}
static void bounce_end_io_read_isa(struct bio *bio)
{
__bounce_end_io_read(bio, isa_page_pool);
}
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
mempool_t *pool)
{
struct bio *bio;
int rw = bio_data_dir(*bio_orig);
struct bio_vec *to, from;
struct bvec_iter iter;
unsigned i = 0;
bool bounce = false;
int sectors = 0;
bio_for_each_segment(from, *bio_orig, iter) {
if (i++ < BIO_MAX_PAGES)
sectors += from.bv_len >> 9;
if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
bounce = true;
}
if (!bounce)
return;
if (sectors < bio_sectors(*bio_orig)) {
bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
bio_chain(bio, *bio_orig);
generic_make_request(*bio_orig);
*bio_orig = bio;
}
bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
if (page_to_pfn(page) <= q->limits.bounce_pfn)
continue;
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
inc_zone_page_state(to->bv_page, NR_BOUNCE);
if (rw == WRITE) {
char *vto, *vfrom;
flush_dcache_page(page);
vto = page_address(to->bv_page) + to->bv_offset;
vfrom = kmap_atomic(page) + to->bv_offset;
memcpy(vto, vfrom, to->bv_len);
kunmap_atomic(vfrom);
}
}
trace_block_bio_bounce(q, *bio_orig);
bio->bi_flags |= (1 << BIO_BOUNCED);
if (pool == page_pool) {
bio->bi_end_io = bounce_end_io_write;
if (rw == READ)
bio->bi_end_io = bounce_end_io_read;
} else {
bio->bi_end_io = bounce_end_io_write_isa;
if (rw == READ)
bio->bi_end_io = bounce_end_io_read_isa;
}
bio->bi_private = *bio_orig;
*bio_orig = bio;
}
void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
{
mempool_t *pool;
/*
* Data-less bio, nothing to bounce
*/
if (!bio_has_data(*bio_orig))
return;
/*
* for non-isa bounce case, just check if the bounce pfn is equal
* to or bigger than the highest pfn in the system -- in that case,
* don't waste time iterating over bio segments
*/
if (!(q->bounce_gfp & GFP_DMA)) {
if (q->limits.bounce_pfn >= blk_max_pfn)
return;
pool = page_pool;
} else {
BUG_ON(!isa_page_pool);
pool = isa_page_pool;
}
/*
* slow path
*/
__blk_queue_bounce(q, bio_orig, pool);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...