Please don't take this as a review. I only glanced over it while waiting for coffee to brew. How does this align with sn2's tlb shootdown mechanism? It seems similar in intent. On Mon, Sep 03, 2007 at 01:06:20AM -0700, Natalie Protasevich wrote: > global cache purge in their chipset implementation. (For such cases, Intel provided a SAL > table entry to specify if ptc.g is allowed and how many). This seems odd. You never use that sal call to initialized noptcg. Is that an oversight? > + /* > + * Wait for other CPUs to finish purging entries. > + */ > + while (atomic_read(&ia64_global_tlb_flush_cpu_count)) { > + /* Nothing */ I think you want a cpu_relax() for hyper-threaded cpus can make progress. > - /* HW requires global serialization of ptc.ga. */ > + /* > + * HW requires global serialization of ptc.ga, and same does > + * IPI based implementation of global TLB purge How about: * HW requires global serialization of ptc operations */ - To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
![]() |