Messages in this thread | | | Date | Tue, 21 Nov 2006 15:54:43 -0500 (EST) | From | Alan Stern <> | Subject | Re: [patch] cpufreq: mark cpufreq_tsc() as core_initcall_sync |
| |
On Tue, 21 Nov 2006, Oleg Nesterov wrote:
> On 11/20, Alan Stern wrote: > > > > Both CPUs execute their "mb" instructions. The mb forces each > > cache to wait until it receives an Acknowdgement for the > > Invalidate it sent. > > > > Both caches send an Acknowledgement message to the other. The > > mb instructions complete. > > > > "b = B" and "a = A" execute. The caches return A==0 and B==0 > > because they haven't yet invalidated their cache lines. > > > > The reason the code failed is because the mb instructions didn't force > > the caches to wait until the Invalidate messages in their queues had been > > fully carried out (i.e., the lines had actually been invalidated). > > However, from > http://marc.theaimsgroup.com/?l=linux-kernel&m=113435711112941 > > Paul E. McKenney wrote: > > > > 2. rmb() guarantees that any changes seen by the interconnect > > preceding the rmb() will be seen by any reads following the > > rmb(). > > > > 3. mb() combines the guarantees made by rmb() and wmb(). > > Confused :(
I'm not certain the odd behavior can occur on systems that use an interconnect like Paul described. In the context I was describing, rmb() guarantees only that any changes seen _and acknowledged_ by the cache preceding the rmb() will be seen by any reads following the rmb(). It's a weaker guarantee, but it still suffices to show that
A = 1 b = B wmb rmb B = 2 a = A
will work as expected.
Alan
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |