Messages in this thread | | | Date | Wed, 10 Nov 1999 17:08:37 +0100 (CET) | From | Andrea Arcangeli <> | Subject | Re: question: spinlocks and userspace. |
| |
On Wed, 10 Nov 1999, Ingo Molnar wrote:
>[..] This technique can be used for event-driven state >machines, but cannot be used if the IRQ _must_ get access to that data
You have two different option to access data with this technique:
o queue a tq_immediate task, mark_bh, and try (down_trylock()) again later ASAP o queue a tq_scheduler task, mark_bh and call a blocking down() and continue from kernel context (not from irq/bh context)
All depends on the latency you have to achieve.
Andrea
- 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/
| |