Now this is news. I wasn't aware there was a separate Read-For-Ownership
mode or signal. Of course, any P6 write that misses the cache causes a
cache line fill, but I wasn't aware that this was different from a normal
read. That would logically set "Invalid" on the other CPU.
This chitchat is nice, but a Linus says: "Show me the code" . And I've
been trying to break WB spinlocks by modifying Ingo's test code. No such
luck. I can have as many threads as I like pounding away on spinlocks
for 15-minutes to an hour without breakage. Yet slip a tight coupled
spin_unlock()/spin_lock() pair in, and it breaks immediately as it's
supposed to. So I have to admit WT spinlocks are safe, or I am stupid.
Or both :)
-- Robert
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/