lkml.org 
[lkml]   [2020]   [Mar]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 5/9] completion: Use simple wait queues
Date
From: Thomas Gleixner <tglx@linutronix.de>

completion uses a wait_queue_head_t to enqueue waiters.

wait_queue_head_t contains a spinlock_t to protect the list of waiters
which excludes it from being used in truly atomic context on a PREEMPT_RT
enabled kernel.

The spinlock in the wait queue head cannot be replaced by a raw_spinlock
because:

- wait queues can have custom wakeup callbacks, which acquire other
spinlock_t locks and have potentially long execution times

- wake_up() walks an unbounded number of list entries during the wake up
and may wake an unbounded number of waiters.

For simplicity and performance reasons complete() should be usable on
PREEMPT_RT enabled kernels.

completions do not use custom wakeup callbacks and are usually single
waiter, except for a few corner cases.

Replace the wait queue in the completion with a simple wait queue (swait),
which uses a raw_spinlock_t for protecting the waiter list and therefore is
safe to use inside truly atomic regions on PREEMPT_RT.

complete_all() might cause unbound latencies with a large number of waiters
being woken at once, but most complete_all() usage sites are either in
testing or initialization code or have only a really small number of
concurrent waiters which for now does not cause a latency problem. Keep it
simple for now.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
arch/powerpc/platforms/ps3/device-init.c | 4 +--
.../wireless/intersil/orinoco/orinoco_usb.c | 4 +--
drivers/usb/gadget/function/f_fs.c | 2 +-
drivers/usb/gadget/legacy/inode.c | 4 +--
include/linux/completion.h | 8 ++---
kernel/sched/completion.c | 36 ++++++++++---------
6 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 2735ec90414dc..359231cea8cd7 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -738,8 +738,8 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
}
pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);

- res = wait_event_interruptible(dev->done.wait,
- dev->done.done || kthread_should_stop());
+ res = swait_event_interruptible_exclusive(dev->done.wait,
+ dev->done.done || kthread_should_stop());
if (kthread_should_stop())
res = -EINTR;
if (res) {
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index e753f43e0162f..7e53a0ba57762 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -693,8 +693,8 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
while (!ctx->done.done && msecs--)
udelay(1000);
} else {
- wait_event_interruptible(ctx->done.wait,
- ctx->done.done);
+ swait_event_interruptible_exclusive(ctx->done.wait,
+ ctx->done.done);
}
break;
default:
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 571917677d358..234177dd1ed57 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1703,7 +1703,7 @@ static void ffs_data_put(struct ffs_data *ffs)
pr_info("%s(): freeing\n", __func__);
ffs_data_clear(ffs);
BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
- waitqueue_active(&ffs->ep0req_completion.wait) ||
+ swait_active(&ffs->ep0req_completion.wait) ||
waitqueue_active(&ffs->wait));
destroy_workqueue(ffs->io_completion_wq);
kfree(ffs->dev_name);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index b47938dff1a22..e5141c1136e47 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -344,7 +344,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
spin_unlock_irq (&epdata->dev->lock);

if (likely (value == 0)) {
- value = wait_event_interruptible (done.wait, done.done);
+ value = swait_event_interruptible_exclusive(done.wait, done.done);
if (value != 0) {
spin_lock_irq (&epdata->dev->lock);
if (likely (epdata->ep != NULL)) {
@@ -353,7 +353,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
usb_ep_dequeue (epdata->ep, epdata->req);
spin_unlock_irq (&epdata->dev->lock);

- wait_event (done.wait, done.done);
+ swait_event_exclusive(done.wait, done.done);
if (epdata->status == -ECONNRESET)
epdata->status = -EINTR;
} else {
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 519e94915d185..bf8e77001f18f 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,7 +9,7 @@
* See kernel/sched/completion.c for details.
*/

-#include <linux/wait.h>
+#include <linux/swait.h>

/*
* struct completion - structure used to maintain state for a "completion"
@@ -25,7 +25,7 @@
*/
struct completion {
unsigned int done;
- wait_queue_head_t wait;
+ struct swait_queue_head wait;
};

#define init_completion_map(x, m) __init_completion(x)
@@ -34,7 +34,7 @@ static inline void complete_acquire(struct completion *x) {}
static inline void complete_release(struct completion *x) {}

#define COMPLETION_INITIALIZER(work) \
- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }

#define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
(*({ init_completion_map(&(work), &(map)); &(work); }))
@@ -85,7 +85,7 @@ static inline void complete_release(struct completion *x) {}
static inline void __init_completion(struct completion *x)
{
x->done = 0;
- init_waitqueue_head(&x->wait);
+ init_swait_queue_head(&x->wait);
}

/**
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a1ad5b7d5521b..f15e96164ff1e 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -29,12 +29,12 @@ void complete(struct completion *x)
{
unsigned long flags;

- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);

if (x->done != UINT_MAX)
x->done++;
- __wake_up_locked(&x->wait, TASK_NORMAL, 1);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ swake_up_locked(&x->wait);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);

@@ -58,10 +58,12 @@ void complete_all(struct completion *x)
{
unsigned long flags;

- spin_lock_irqsave(&x->wait.lock, flags);
+ WARN_ON(irqs_disabled());
+
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
x->done = UINT_MAX;
- __wake_up_locked(&x->wait, TASK_NORMAL, 0);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ swake_up_all_locked(&x->wait);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);

@@ -70,20 +72,20 @@ do_wait_for_common(struct completion *x,
long (*action)(long), long timeout, int state)
{
if (!x->done) {
- DECLARE_WAITQUEUE(wait, current);
+ DECLARE_SWAITQUEUE(wait);

- __add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
do {
if (signal_pending_state(state, current)) {
timeout = -ERESTARTSYS;
break;
}
+ __prepare_to_swait(&x->wait, &wait);
__set_current_state(state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
timeout = action(timeout);
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
} while (!x->done && timeout);
- __remove_wait_queue(&x->wait, &wait);
+ __finish_swait(&x->wait, &wait);
if (!x->done)
return timeout;
}
@@ -100,9 +102,9 @@ __wait_for_common(struct completion *x,

complete_acquire(x);

- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
timeout = do_wait_for_common(x, action, timeout, state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);

complete_release(x);

@@ -291,12 +293,12 @@ bool try_wait_for_completion(struct completion *x)
if (!READ_ONCE(x->done))
return false;

- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = false;
else if (x->done != UINT_MAX)
x->done--;
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);
@@ -322,8 +324,8 @@ bool completion_done(struct completion *x)
* otherwise we can end up freeing the completion before complete()
* is done referencing it.
*/
- spin_lock_irqsave(&x->wait.lock, flags);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return true;
}
EXPORT_SYMBOL(completion_done);
--
2.25.1
\
 
 \ /
  Last update: 2020-03-13 18:48    [W:0.233 / U:0.360 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site