Messages in this thread | | | From | Paul Mackerras <> | Date | Wed, 22 May 2002 09:05:40 +1000 (EST) | Subject | Re: Make 2.5.17 TLB even more friendlier |
| |
Linus Torvalds writes:
> Sp why don't you just make "tlb_remove_pte_entry()" look at your bit, and > then if that bit is set you try to remove the entry from the hash chains > at that point?
Simply the desire to batch up the hash table searches for efficiency, particularly on SMP where we have to take a spinlock before touching the MMU hash table. This will be an even bigger win on ppc64 on partitioned machines where we have to call the hypervisor to make changes to the MMU hash table.
I'm thinking now that I would be better off doing the batching by storing a list of virtual addresses needing flushing in the mmu_gather_t, instead of relying on getting at the special bits in the PTEs at some time after the tlb_remove_tlb_entry call.
Regards, Paul. - 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/
| |