diff options
| author | Jens Axboe <axboe@fb.com> | 2014-11-25 01:02:42 +0300 |
|---|---|---|
| committer | Jens Axboe <axboe@fb.com> | 2014-11-25 01:02:42 +0300 |
| commit | a33c1ba2913802b6fb23e974bb2f6a4e73c8b7ce (patch) | |
| tree | f1dbb27e9804ed4f8368e4eb0169b7325ec0792f /block | |
| parent | 394ffa503bc40e32d7f54a9b817264e81ce131b4 (diff) | |
| download | linux-a33c1ba2913802b6fb23e974bb2f6a4e73c8b7ce.tar.xz | |
blk-mq: use 'nr_cpu_ids' as highest CPU ID count for hwq <-> cpu map
We currently use num_possible_cpus(), but that breaks on sparc64 where
the CPU ID space is discontig. Use nr_cpu_ids as the highest CPU ID
instead, so we don't end up reading from invalid memory.
Cc: stable@kernel.org # 3.13+
Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'block')
| -rw-r--r-- | block/blk-mq-cpumap.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 1065d7c65fa1..72e5ed691e37 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -90,7 +90,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set) unsigned int *map; /* If cpus are offline, map them to first hctx */ - map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL, + map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL, set->numa_node); if (!map) return NULL; |