On 2019-01-08 16:16, Davidlohr Bueso wrote:
On 2019-01-08 04:42, Roman Penyaev wrote:
What we can do:
a) disable irqs if we are not in interrupt.
b) revert the patch completely.
David, is it really crucial in terms of performance to avoid double
local_irq_save() on Xen on this
On 2019-01-08 04:42, Roman Penyaev wrote:
What we can do:
a) disable irqs if we are not in interrupt.
b) revert the patch completely.
David, is it really crucial in terms of performance to avoid double
local_irq_save() on Xen on this ep_poll_callback() hot path?
Note that such optimizations
On 2019-01-08 11:01, Roman Penyaev wrote:
That was wrong assumption that all drivers disable irqs before waking
up
a wait queue. Even assert line is removed the whole logic stays
correct:
epoll always locks rwlock with irqs disabled and by itself does not
call
from interrupts, thus it is up
That was wrong assumption that all drivers disable irqs before waking up
a wait queue. Even assert line is removed the whole logic stays correct:
epoll always locks rwlock with irqs disabled and by itself does not call
from interrupts, thus it is up to driver how to call wake_up_locked(),
because
4 matches
Mail list logo