linux-kernel - [PATCH v3 6/7] blkcg: account requests instead of bios for request based request

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20171115172241.GX983427@devbig577.frc2.facebook.com>
Date:   Wed, 15 Nov 2017 09:22:41 -0800
From:   Tejun Heo <tj@...nel.org>
To:     Jens Axboe <axboe@...nel.dk>
Cc:     Shaohua Li <shli@...nel.org>, linux-kernel@...r.kernel.org,
        kernel-team@...com, lizefan@...wei.com, hannes@...xchg.org,
        cgroups@...r.kernel.org, guro@...com
Subject: [PATCH v3 6/7] blkcg: account requests instead of bios for request
 based request_queues

blkcg accounting is currently bio based, which is silly for request
based request_queues.  This is silly as the number of bios doesn't
have much to do with the actual number of IOs issued to the underlying
device (can be significantly higher or lower) and may change depending
on the implementation details on how the bios are issued (e.g. from
the recent split-bios-while-issuing change).

Do cgroup accounting for request based request_queues together with
gendisk accounting on request completion.

This makes cgroup accounting consistent with gendisk accounting and
what's happening on the system.

v3: Use q->request_fn test doesn't work on blk-mq.  Use
    queue_is_rq_based() instead as suggested by Jens.

v2: Use q->request_fn to skip bio based accounting instead of
    QUEUE_FLAG_IOSTAT as suggested by Shaohua.

Signed-off-by: Tejun Heo <tj@...nel.org>
Reviewed-by: Shaohua Li <shli@...nel.org>
---
 block/blk-core.c           |    3 +++
 include/linux/blk-cgroup.h |   18 +++++++++++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2429,6 +2429,7 @@ void blk_account_io_completion(struct re
 		cpu = part_stat_lock();
 		part = req->part;
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		blkcg_account_io_completion(req, bytes);
 		part_stat_unlock();
 	}
 }
@@ -2454,6 +2455,8 @@ void blk_account_io_done(struct request
 		part_round_stats(req->q, cpu, part);
 		part_dec_in_flight(req->q, part, rw);
 
+		blkcg_account_io_done(req);
+
 		hd_struct_put(part);
 		part_stat_unlock();
 	}
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -715,7 +715,8 @@ static inline bool blkcg_bio_issue_check
 
 	throtl = blk_throtl_bio(q, blkg, bio);
 
-	if (!throtl) {
+	/* if @q does io stat, blkcg stats are updated together with them */
+	if (!queue_is_rq_based(q) && !throtl) {
 		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
 				bio->bi_iter.bi_size);
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
@@ -764,6 +765,17 @@ static inline void blk_rq_disassociate_b
 	rq->blkg = NULL;
 }
 
+static inline void blkcg_account_io_completion(struct request *rq,
+					       unsigned int bytes)
+{
+	blkg_rwstat_add(&rq->blkg->stat_bytes, rq_data_dir(rq), bytes);
+}
+
+static inline void blkcg_account_io_done(struct request *rq)
+{
+	blkg_rwstat_add(&rq->blkg->stat_ios, rq_data_dir(rq), 1);
+}
+
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
@@ -823,6 +835,10 @@ static inline bool blkcg_bio_issue_check
 static inline void blk_rq_associate_blkg(struct request *rq, struct blkcg *blkcg) { }
 static inline void blk_rq_disassociate_blkg(struct request *rq) { }
 
+static inline void blkcg_account_io_completion(struct request *rq,
+					       unsigned int bytes) { }
+static inline void blkcg_account_io_done(struct request *rq) { }
+
 #define blk_queue_for_each_rl(rl, q)	\
 	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)