From 26b5679e437ef4f83db66437981c7c0d569973b1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 11 Oct 2016 13:54:33 -0700 Subject: relay: Use irq_work instead of plain timer for deferred wakeup Relay avoids calling wake_up_interruptible() for doing the wakeup of readers/consumers, waiting for the generation of new data, from the context of a process which produced the data. This is apparently done to prevent the possibility of a deadlock in case Scheduler itself is is generating data for the relay, after acquiring rq->lock. The following patch used a timer (to be scheduled at next jiffy), for delegating the wakeup to another context. commit 7c9cb38302e78d24e37f7d8a2ea7eed4ae5f2fa7 Author: Tom Zanussi Date: Wed May 9 02:34:01 2007 -0700 relay: use plain timer instead of delayed work relay doesn't need to use schedule_delayed_work() for waking readers when a simple timer will do. Scheduling a plain timer, at next jiffies boundary, to do the wakeup causes a significant wakeup latency for the Userspace client, which makes relay less suitable for the high-frequency low-payload use cases where the data gets generated at a very high rate, like multiple sub buffers getting filled within a milli second. Moreover the timer is re-scheduled on every newly produced sub buffer so the timer keeps getting pushed out if sub buffers are filled in a very quick succession (less than a jiffy gap between filling of 2 sub buffers). As a result relay runs out of sub buffers to store the new data. By using irq_work it is ensured that wakeup of userspace client, blocked in the poll call, is done at earliest (through self IPI or next timer tick) enabling it to always consume the data in time. Also this makes relay consistent with printk & ring buffers (trace), as they too use irq_work for deferred wake up of readers. [arnd@arndb.de: select CONFIG_IRQ_WORK] Link: http://lkml.kernel.org/r/20160912154035.3222156-1-arnd@arndb.de [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1472906487-1559-1-git-send-email-akash.goel@intel.com Signed-off-by: Peter Zijlstra Signed-off-by: Akash Goel Cc: Tom Zanussi Cc: Chris Wilson Cc: Tvrtko Ursulin Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/relay.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'kernel/relay.c') diff --git a/kernel/relay.c b/kernel/relay.c index 9988f5cc2d46..da79a109dbeb 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -328,13 +328,15 @@ static struct rchan_callbacks default_channel_callbacks = { /** * wakeup_readers - wake up readers waiting on a channel - * @data: contains the channel buffer + * @work: contains the channel buffer * - * This is the timer function used to defer reader waking. + * This is the function used to defer reader waking */ -static void wakeup_readers(unsigned long data) +static void wakeup_readers(struct irq_work *work) { - struct rchan_buf *buf = (struct rchan_buf *)data; + struct rchan_buf *buf; + + buf = container_of(work, struct rchan_buf, wakeup_work); wake_up_interruptible(&buf->read_wait); } @@ -352,9 +354,10 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) if (init) { init_waitqueue_head(&buf->read_wait); kref_init(&buf->kref); - setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); - } else - del_timer_sync(&buf->timer); + init_irq_work(&buf->wakeup_work, wakeup_readers); + } else { + irq_work_sync(&buf->wakeup_work); + } buf->subbufs_produced = 0; buf->subbufs_consumed = 0; @@ -487,7 +490,7 @@ free_buf: static void relay_close_buf(struct rchan_buf *buf) { buf->finalized = 1; - del_timer_sync(&buf->timer); + irq_work_sync(&buf->wakeup_work); buf->chan->cb->remove_buf_file(buf->dentry); kref_put(&buf->kref, relay_remove_buf); } @@ -754,14 +757,15 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) buf->early_bytes += buf->chan->subbuf_size - buf->padding[old_subbuf]; smp_mb(); - if (waitqueue_active(&buf->read_wait)) + if (waitqueue_active(&buf->read_wait)) { /* * Calling wake_up_interruptible() from here * will deadlock if we happen to be logging * from the scheduler (trying to re-grab * rq->lock), so defer it. */ - mod_timer(&buf->timer, jiffies + 1); + irq_work_queue(&buf->wakeup_work); + } } old = buf->data; -- cgit v1.2.3-58-ga151