block: invalidate cached plug timestamp after task switch

commit fad156c2af227f42ca796cbb20ddc354a6dd9932 upstream.

blk_time_get_ns() caches ktime_get_ns() in current->plug->cur_ktime
and marks the task with PF_BLOCK_TS. That cache is only valid while the
task keeps running; if the task is switched out, wall-clock time
advances and the cached value must not be reused when the task runs again.

The existing invalidation covers explicit plug flushes through
__blk_flush_plug(), and the schedule() / rtmutex paths through
sched_update_worker(). It does not cover in-kernel preemption paths such
as preempt_schedule(), preempt_schedule_notrace(), and
preempt_schedule_irq(), which enter __schedule(SM_PREEMPT) directly and
return without calling sched_update_worker().

As a result, a task preempted while holding a plug with PF_BLOCK_TS set
can reuse a stale plug->cur_ktime after it is scheduled back in. blk-iocost
then consumes that stale timestamp through ioc_now(), producing stale vnow
values for throttle decisions, and through ioc_rqos_done(), inflating
on-queue time and feeding false missed-QoS samples into vrate
adjustment.

Move the schedule-side invalidation to finish_task_switch(), which runs
for the scheduled-in task after every actual context switch regardless
of which schedule entry point was used. Keep __blk_flush_plug() as the
explicit flush/finish-plug invalidation path, and remove only the
PF_BLOCK_TS handling from sched_update_worker().

Fixes: 06b23f92af87 ("block: update cached timestamp post schedule/preemption")
Cc: stable@vger.kernel.org
Signed-off-by: Usama Arif <usama.arif@linux.dev>
Link: https://patch.msgid.link/20260616141604.328820-3-usama.arif@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 14 insertions, 14 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 890128cdea1c..dda80803740f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1214,16 +1214,12 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 		__blk_flush_plug(plug, async);
 }
 
-/*
- * tsk == current here
- */
-static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+static __always_inline void blk_plug_invalidate_ts(void)
 {
-	struct blk_plug *plug = tsk->plug;
-
-	if (plug)
-		plug->cur_ktime = 0;
-	current->flags &= ~PF_BLOCK_TS;
+	if (unlikely(current->flags & PF_BLOCK_TS)) {
+		current->plug->cur_ktime = 0;
+		current->flags &= ~PF_BLOCK_TS;
+	}
 }
 
 int blkdev_issue_flush(struct block_device *bdev);
@@ -1249,7 +1245,7 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
 }
 
-static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+static inline void blk_plug_invalidate_ts(void)
 {
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b8871449d3c6..3314ead93127 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5252,6 +5252,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 */
 	kmap_local_sched_in();
 
+	/*
+	 * Any cached block-layer timestamp (plug->cur_ktime) is stale now,
+	 * invalidate it.
+	 */
+	blk_plug_invalidate_ts();
+
 	fire_sched_in_preempt_notifiers(current);
 	/*
 	 * When switching through a kernel thread, the loop in
@@ -7251,12 +7257,10 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 static void sched_update_worker(struct task_struct *tsk)
 {
-	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
-		if (tsk->flags & PF_BLOCK_TS)
-			blk_plug_invalidate_ts(tsk);
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		if (tsk->flags & PF_WQ_WORKER)
 			wq_worker_running(tsk);
-		else if (tsk->flags & PF_IO_WORKER)
+		else
 			io_wq_worker_running(tsk);
 	}
 }