A-Team_Digital_Solutions/android_kernel_motorola_sm6375
Watch
2
0
Fork
You've already forked android_kernel_motorola_sm6375
 0
mirror of https://github.com/BobTheBlinker/android_kernel_motorola_sm6375.git synced 2026-10-29 03:01:39 -04:00
Code Issues Projects Releases Packages Wiki Activity

blk-mq: fix iteration of busy bitmap

Browse source 
Commit 889fa31f00 was a bit too eager in reducing the loop count,
so we ended up missing queues in some configurations. Ensure that
our division rounds up, so that's not the case.

Reported-by: Guenter Roeck <[email protected]>
Fixes: 889fa31f00 ("blk-mq: reduce unnecessary software queue looping")
Signed-off-by: Jens Axboe <[email protected]>
This commit is contained in:
Jens Axboe 2015-04-17 08:28:50 -06:00
commit 569fd0ce96
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
block/blk-mq.c
View file

@ -41,7 +41,7 @@ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
unsigned int i;
for (i = 0; i < hctx->ctx_map.map_size; i++)
for (i = 0; i < hctx->ctx_map.size; i++)
if (hctx->ctx_map.map[i].word)
return true;
@ -730,7 +730,7 @@ static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
struct blk_mq_ctx *ctx;
int i;
for (i = 0; i < hctx->ctx_map.map_size; i++) {
for (i = 0; i < hctx->ctx_map.size; i++) {
struct blk_align_bitmap *bm = &hctx->ctx_map.map[i];
unsigned int off, bit;
@ -1818,7 +1818,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
* This is more accurate and more efficient than looping
* over all possibly mapped software queues.
*/
map->map_size = hctx->nr_ctx / map->bits_per_word;
map->size = DIV_ROUND_UP(hctx->nr_ctx, map->bits_per_word);
/*
* Initialize batch roundrobin counts