Instead of a convoluted chain just check for REQ_OP_READ directly,
and keep all the memory stall code together in a single unlikely
branch.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
block/blk-core.c | 30 ++++++++++++++----------------
1 file changed, 14 insertions(+), 16 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 68351ee94ad2e..81a291085c6ca 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1148,10 +1148,6 @@ EXPORT_SYMBOL_GPL(direct_make_request);
*/
blk_qc_t submit_bio(struct bio *bio)
{
- bool workingset_read = false;
- unsigned long pflags;
- blk_qc_t ret;
-
if (blkcg_punt_bio_submit(bio))
return BLK_QC_T_NONE;
@@ -1170,8 +1166,6 @@ blk_qc_t submit_bio(struct bio *bio)
if (op_is_write(bio_op(bio))) {
count_vm_events(PGPGOUT, count);
} else {
- if (bio_flagged(bio, BIO_WORKINGSET))
- workingset_read = true;
task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, count);
}
@@ -1187,20 +1181,24 @@ blk_qc_t submit_bio(struct bio *bio)
}
/*
- * If we're reading data that is part of the userspace
- * workingset, count submission time as memory stall. When the
- * device is congested, or the submitting cgroup IO-throttled,
- * submission can be a significant part of overall IO time.
+ * If we're reading data that is part of the userspace workingset, count
+ * submission time as memory stall. When the device is congested, or
+ * the submitting cgroup IO-throttled, submission can be a significant
+ * part of overall IO time.
*/
- if (workingset_read)
- psi_memstall_enter(&pflags);
-
- ret = generic_make_request(bio);
+ if (unlikely(bio_op(bio) == REQ_OP_READ &&
+ bio_flagged(bio, BIO_WORKINGSET))) {
+ unsigned long pflags;
+ blk_qc_t ret;
- if (workingset_read)
+ psi_memstall_enter(&pflags);
+ ret = generic_make_request(bio);
psi_memstall_leave(&pflags);
- return ret;
+ return ret;
+ }
+
+ return generic_make_request(bio);
}
EXPORT_SYMBOL(submit_bio);
--
2.26.2
