powerpc/spufs: fix missed stop-and-signal event
authorLuke Browning <lukebrowning@us.ibm.com>
Mon, 16 Jun 2008 00:42:38 +0000 (10:42 +1000)
committerJeremy Kerr <jk@ozlabs.org>
Mon, 16 Jun 2008 04:35:01 +0000 (14:35 +1000)
There is a delay in the transition to the stopped state for class 2
interrupts. In some cases, the controlling thread detects the state of
the spu as running, and goes back to sleep resulting in a hung
application as the event is missed.

This change detects the stop condition and re-generates the wakeup event
after a context save.

Signed-off-by: Luke Browning <lukebrowning@us.ibm.com>
Signed-off-by: Jeremy Kerr <jk@ozlabs.org>

No differences found