On Wed, 20 May 2020 14:39:13 +0800 maobibo <maob...@loongson.cn> wrote:
> > I'm still worried about the impact on other architectures. The > > additional update_mmu_cache() calls won't occur only when multiple > > threads are racing against the same page, I think? For example, > > insert_pfn() will do this when making a read-only page a writable one. > How about defining ptep_set_access_flags function like this on mips system? > which is the same on riscv platform. > > static inline int ptep_set_access_flags(struct vm_area_struct *vma, > unsigned long address, pte_t *ptep, > pte_t entry, int dirty) > { > if (!pte_same(*ptep, entry)) > set_pte_at(vma->vm_mm, address, ptep, entry); > /* > * update_mmu_cache will unconditionally execute, handling both > * the case that the PTE changed and the spurious fault case. > */ > return true; > } > hm, it seems a bit abusive - ptep_set_access_flags() is supposed to return true if the pte changed, and that isn't the case here. I suppose we could run update_mmu_cache() directly from ptep_set_access_flags() if we're about to return false, but that doesn't seem a lot nicer? > > Would you have time to add some instrumentation into update_mmu_cache() > > (maybe a tracepoint) and see what effect this change has upon the > > frequency at which update_mmu_cache() is called for a selection of > > workloads? And add this info to the changelog to set minds at ease? > > OK, I will add some instrumentation data in the changelog. Well, if this testing shows no effect as you expect, perhaps we can leave the code as-is.