From f23eb2b2b28547fc70df82dd5049eb39bec5ba12 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 22 Mar 2011 16:17:32 -0700 Subject: tty: stop using "delayed_work" in the tty layer Using delayed-work for tty flip buffers ends up causing us to wait for the next tick to complete some actions. That's usually not all that noticeable, but for certain latency-critical workloads it ends up being totally unacceptable. As an extreme case of this, passing a token back-and-forth over a pty will take two ticks per iteration, so even just a thousand iterations will take 8 seconds assuming a common 250Hz configuration. Avoiding the whole delayed work issue brings that ping-pong test-case down to 0.009s on my machine. In more practical terms, this latency has been a performance problem for things like dive computer simulators (simulating the serial interface using the ptys) and for other environments (Alan mentions a CP/M emulator). Reported-by: Jef Driesen Acked-by: Greg KH Acked-by: Alan Cox Signed-off-by: Linus Torvalds --- drivers/tty/tty_buffer.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'drivers/tty/tty_buffer.c') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index d8210ca00720..b9451219528b 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -322,7 +322,7 @@ void tty_schedule_flip(struct tty_struct *tty) if (tty->buf.tail != NULL) tty->buf.tail->commit = tty->buf.tail->used; spin_unlock_irqrestore(&tty->buf.lock, flags); - schedule_delayed_work(&tty->buf.work, 1); + schedule_work(&tty->buf.work); } EXPORT_SYMBOL(tty_schedule_flip); @@ -402,7 +402,7 @@ EXPORT_SYMBOL_GPL(tty_prepare_flip_string_flags); static void flush_to_ldisc(struct work_struct *work) { struct tty_struct *tty = - container_of(work, struct tty_struct, buf.work.work); + container_of(work, struct tty_struct, buf.work); unsigned long flags; struct tty_ldisc *disc; @@ -443,7 +443,7 @@ static void flush_to_ldisc(struct work_struct *work) if (test_bit(TTY_FLUSHPENDING, &tty->flags)) break; if (!tty->receive_room || seen_tail) { - schedule_delayed_work(&tty->buf.work, 1); + schedule_work(&tty->buf.work); break; } if (count > tty->receive_room) @@ -481,7 +481,7 @@ static void flush_to_ldisc(struct work_struct *work) */ void tty_flush_to_ldisc(struct tty_struct *tty) { - flush_delayed_work(&tty->buf.work); + flush_work(&tty->buf.work); } /** @@ -506,9 +506,9 @@ void tty_flip_buffer_push(struct tty_struct *tty) spin_unlock_irqrestore(&tty->buf.lock, flags); if (tty->low_latency) - flush_to_ldisc(&tty->buf.work.work); + flush_to_ldisc(&tty->buf.work); else - schedule_delayed_work(&tty->buf.work, 1); + schedule_work(&tty->buf.work); } EXPORT_SYMBOL(tty_flip_buffer_push); @@ -529,6 +529,6 @@ void tty_buffer_init(struct tty_struct *tty) tty->buf.tail = NULL; tty->buf.free = NULL; tty->buf.memory_used = 0; - INIT_DELAYED_WORK(&tty->buf.work, flush_to_ldisc); + INIT_WORK(&tty->buf.work, flush_to_ldisc); } -- cgit v1.2.3 From a5660b41af6a28f8004e70eb261e1202ad55c5e3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 4 Apr 2011 14:26:54 -0700 Subject: tty: fix endless work loop when the buffer fills up Commit f23eb2b2b285 ('tty: stop using "delayed_work" in the tty layer') ended up causing hung machines on UP with no preemption, because the work routine to flip the buffer data to the ldisc would endlessly re-arm itself if the destination buffer had filled up. With the delayed work, that only caused a timer-driving polling of the tty state every timer tick, but without the delay we just ended up with basically a busy loop instead. Stop the insane polling, and instead make the code that opens up the receive room re-schedule the buffer flip work. That's what we should have been doing anyway. This same "poll for tty room" issue is almost certainly also the cause of excessive kworker activity when idle reported by Dave Jones, who also reported "flush_to_ldisc executing 2500 times a second" back in Nov 2010: http://lkml.org/lkml/2010/11/30/592 which is that silly flushing done every timer tick. Wasting both power and CPU for no good reason. Reported-and-tested-by: Alexander Beregalov Reported-and-tested-by: Sitsofe Wheeler Cc: Greg KH Cc: Alan Cox Cc: Dave Jones Signed-off-by: Linus Torvalds --- drivers/tty/tty_buffer.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/tty/tty_buffer.c') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index b9451219528b..f1a7918d71aa 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -442,10 +442,8 @@ static void flush_to_ldisc(struct work_struct *work) line discipline as we want to empty the queue */ if (test_bit(TTY_FLUSHPENDING, &tty->flags)) break; - if (!tty->receive_room || seen_tail) { - schedule_work(&tty->buf.work); + if (!tty->receive_room || seen_tail) break; - } if (count > tty->receive_room) count = tty->receive_room; char_buf = head->char_buf_ptr + head->read; -- cgit v1.2.3