| 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
| ||
|
Message-Id: <1393942390-21293-1-git-send-email-r.peniaev@gmail.com>
Date: Tue, 4 Mar 2014 23:13:10 +0900
From: Roman Pen <r.peniaev@...il.com>
To: unlisted-recipients:; (no To-header on input)
Cc: Roman Pen <r.peniaev@...il.com>, Jens Axboe <axboe@...nel.dk>,
Steven Rostedt <rostedt@...dmis.org>,
Frederic Weisbecker <fweisbec@...il.com>,
Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org
Subject: [PATCH 1/1] blktrace: fix accounting of partially completed requests
trace_block_rq_complete does not take into account that request can
be partially completed, so we can get the following incorrect output
of blkparser:
C R 232 + 240 [0]
C R 240 + 232 [0]
C R 248 + 224 [0]
C R 256 + 216 [0]
but should be:
C R 232 + 8 [0]
C R 240 + 8 [0]
C R 248 + 8 [0]
C R 256 + 8 [0]
Also, the whole output summary statistics of completed requests and
final throughput will be incorrect.
This patch takes into account real completion size of the request and
fixes wrong completion accounting.
Signed-off-by: Roman Pen <r.peniaev@...il.com>
CC: Jens Axboe <axboe@...nel.dk>
CC: Steven Rostedt <rostedt@...dmis.org>
CC: Frederic Weisbecker <fweisbec@...il.com>
CC: Ingo Molnar <mingo@...hat.com>
CC: linux-kernel@...r.kernel.org
---
block/blk-core.c | 2 +-
block/blk-mq.c | 2 +-
include/trace/events/block.h | 33 ++++++++++++++++++++++++++++++---
kernel/trace/blktrace.c | 20 +++++++++++---------
4 files changed, 43 insertions(+), 14 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 853f927..99e20cc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2354,7 +2354,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
if (!req->bio)
return false;
- trace_block_rq_complete(req->q, req);
+ trace_block_rq_complete(req->q, req, nr_bytes);
/*
* For fs requests, rq is just carrier of independent bio's
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1fa9dd1..1037e84 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -309,7 +309,7 @@ void blk_mq_end_io(struct request *rq, int error)
struct bio *bio = rq->bio;
unsigned int bytes = 0;
- trace_block_rq_complete(rq->q, rq);
+ trace_block_rq_complete(rq->q, rq, blk_rq_bytes(rq));
while (bio) {
struct bio *next = bio->bi_next;
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index e76ae19..e8a5eca 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -132,6 +132,7 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
* block_rq_complete - block IO operation completed by device driver
* @q: queue containing the block operation request
* @rq: block operations request
+ * @nr_bytes: number of completed bytes
*
* The block_rq_complete tracepoint event indicates that some portion
* of operation request has been completed by the device driver. If
@@ -139,11 +140,37 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
* do for the request. If @rq->bio is non-NULL then there is
* additional work required to complete the request.
*/
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
- TP_PROTO(struct request_queue *q, struct request *rq),
+ TP_PROTO(struct request_queue *q, struct request *rq,
+ unsigned int nr_bytes),
- TP_ARGS(q, rq)
+ TP_ARGS(q, rq, nr_bytes),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( int, errors )
+ __array( char, rwbs, RWBS_LEN )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_rq_pos(rq);
+ __entry->nr_sector = nr_bytes >> 9;
+ __entry->errors = rq->errors;
+
+ blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+ blk_dump_cmd(__get_str(cmd), rq);
+ ),
+
+ TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->errors)
);
DECLARE_EVENT_CLASS(block_rq,
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b418cb0..4f3a3c03 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q)
* blk_add_trace_rq - Add a trace for a request oriented action
* @q: queue the io is for
* @rq: the source request
+ * @nr_bytes: number of completed bytes
* @what: the action
*
* Description:
@@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q)
*
**/
static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
- u32 what)
+ unsigned int nr_bytes, u32 what)
{
struct blk_trace *bt = q->blk_trace;
@@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
what |= BLK_TC_ACT(BLK_TC_PC);
- __blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+ __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
what, rq->errors, rq->cmd_len, rq->cmd);
} else {
what |= BLK_TC_ACT(BLK_TC_FS);
- __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+ __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
rq->cmd_flags, what, rq->errors, 0, NULL);
}
}
@@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
static void blk_add_trace_rq_abort(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
}
static void blk_add_trace_rq_insert(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
}
static void blk_add_trace_rq_issue(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
}
static void blk_add_trace_rq_requeue(void *ignore,
struct request_queue *q,
struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
}
static void blk_add_trace_rq_complete(void *ignore,
struct request_queue *q,
- struct request *rq)
+ struct request *rq,
+ unsigned int nr_bytes)
{
- blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+ blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
}
/**
--
1.8.5.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists