Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Steven Rostedt
On Fri, 2007-06-22 at 22:45 +0900, Akinobu Mita wrote: > 2007/6/22, Steven Rostedt <[EMAIL PROTECTED]>: > > > +static inline void tasklet_unlock_wait(struct tasklet_struct *t) > > +{ > > + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } > > +} > > BTW, can we use

Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Akinobu Mita
2007/6/22, Steven Rostedt <[EMAIL PROTECTED]>: +static inline void tasklet_unlock_wait(struct tasklet_struct *t) +{ + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } +} BTW, can we use cpu_relax() instead of barrier() in this busy-wait loop? - To unsubscribe from this

Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Steven Rostedt
On Fri, 2007-06-22 at 08:11 +0100, Christoph Hellwig wrote: > On Fri, Jun 22, 2007 at 12:00:16AM -0400, Steven Rostedt wrote: > > Tasklets are really a separate entity from softirqs, so they > > deserve their own file. Also this allows us to easily replace > > tasklets for something else ;-) > >

Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Christoph Hellwig
On Fri, Jun 22, 2007 at 12:00:16AM -0400, Steven Rostedt wrote: > Tasklets are really a separate entity from softirqs, so they > deserve their own file. Also this allows us to easily replace > tasklets for something else ;-) It's a bit pointless when softirq.h still always includes it. A while

Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Steven Rostedt
On Fri, 2007-06-22 at 08:11 +0100, Christoph Hellwig wrote: On Fri, Jun 22, 2007 at 12:00:16AM -0400, Steven Rostedt wrote: Tasklets are really a separate entity from softirqs, so they deserve their own file. Also this allows us to easily replace tasklets for something else ;-) It's a

Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Akinobu Mita
2007/6/22, Steven Rostedt [EMAIL PROTECTED]: +static inline void tasklet_unlock_wait(struct tasklet_struct *t) +{ + while (test_bit(TASKLET_STATE_RUN, (t)-state)) { barrier(); } +} BTW, can we use cpu_relax() instead of barrier() in this busy-wait loop? - To unsubscribe from this list:

Re: [RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-22 Thread Steven Rostedt
On Fri, 2007-06-22 at 22:45 +0900, Akinobu Mita wrote: 2007/6/22, Steven Rostedt [EMAIL PROTECTED]: +static inline void tasklet_unlock_wait(struct tasklet_struct *t) +{ + while (test_bit(TASKLET_STATE_RUN, (t)-state)) { barrier(); } +} BTW, can we use cpu_relax() instead of

[RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-21 Thread Steven Rostedt
Tasklets are really a separate entity from softirqs, so they deserve their own file. Also this allows us to easily replace tasklets for something else ;-) Signed-off-by: Steven Rostedt <[EMAIL PROTECTED]> Index: linux-2.6-test/include/linux/interrupt.h

[RFC PATCH 2/6] Split out tasklets from softirq.c

2007-06-21 Thread Steven Rostedt
Tasklets are really a separate entity from softirqs, so they deserve their own file. Also this allows us to easily replace tasklets for something else ;-) Signed-off-by: Steven Rostedt [EMAIL PROTECTED] Index: linux-2.6-test/include/linux/interrupt.h