summaryrefslogtreecommitdiff
path: root/mm/bootmem.c
diff options
context:
space:
mode:
authorMax Filippov <jcmvbkbc@gmail.com>2013-01-11 14:31:52 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-01-11 14:54:55 -0800
commit10d73e655cef6e86ea8589dca3df4e495e4900b0 (patch)
treea6bb3c7f80ec2a4b7eb65e714d6fe4426be26fcc /mm/bootmem.c
parentc060f943d0929f3e429c5d9522290584f6281d6e (diff)
downloadlwn-10d73e655cef6e86ea8589dca3df4e495e4900b0.tar.gz
lwn-10d73e655cef6e86ea8589dca3df4e495e4900b0.zip
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment
Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/bootmem.c')
-rw-r--r--mm/bootmem.c24
1 files changed, 18 insertions, 6 deletions
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 1324cd74faec..b93376c39b61 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -185,10 +185,23 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
while (start < end) {
unsigned long *map, idx, vec;
+ unsigned shift;
map = bdata->node_bootmem_map;
idx = start - bdata->node_min_pfn;
+ shift = idx & (BITS_PER_LONG - 1);
+ /*
+ * vec holds at most BITS_PER_LONG map bits,
+ * bit 0 corresponds to start.
+ */
vec = ~map[idx / BITS_PER_LONG];
+
+ if (shift) {
+ vec >>= shift;
+ if (end - start >= BITS_PER_LONG)
+ vec |= ~map[idx / BITS_PER_LONG + 1] <<
+ (BITS_PER_LONG - shift);
+ }
/*
* If we have a properly aligned and fully unreserved
* BITS_PER_LONG block of pages in front of us, free
@@ -201,19 +214,18 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
count += BITS_PER_LONG;
start += BITS_PER_LONG;
} else {
- unsigned long off = 0;
+ unsigned long cur = start;
- vec >>= start & (BITS_PER_LONG - 1);
- while (vec) {
+ start = ALIGN(start + 1, BITS_PER_LONG);
+ while (vec && cur != start) {
if (vec & 1) {
- page = pfn_to_page(start + off);
+ page = pfn_to_page(cur);
__free_pages_bootmem(page, 0);
count++;
}
vec >>= 1;
- off++;
+ ++cur;
}
- start = ALIGN(start + 1, BITS_PER_LONG);
}
}