Re: [PATCH] 2.1.88 Hanging Processes (Uninterruptible Sleep)

MOLNAR Ingo (mingo@chiara.csoma.elte.hu)
Tue, 3 Mar 1998 23:43:22 +0100 (CET)

> but if the "if (empty)" is indeed re-ordered before the
> "tsk->state = TASK_UNINTERRUPTIBLE", it looks like even on UP, we
> can take an interrupt just at the point in which the above example
> took an interrupt and set "tsk->state = TASK_RUNNING" on CPU #1.

an interrupt entry is always a 'synchronization point' on Intel. But it's
a nice place for screwup indeed, i think there was a (K6?) errata in this
area, IRQ handlers didnt see a consistent CPU state. But the CPU is
supposed to handle this issue transparently.

-- mingo

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu