On 12/14/23 7:06 PM, Matthew Wilcox wrote: > On Thu, Dec 14, 2023 at 03:59:00PM -0800, Jianfeng Wang wrote: >> On 12/14/23 3:00 PM, Matthew Wilcox wrote: >>> On Thu, Dec 14, 2023 at 02:27:17PM -0800, Jianfeng Wang wrote: >>>> When unmapping VMA pages, pages will be gathered in batch and released by >>>> tlb_finish_mmu() if CONFIG_MMU_GATHER_NO_GATHER is not set. The function >>>> tlb_finish_mmu() is responsible for calling free_pages_and_swap_cache(), >>>> which calls lru_add_drain() to drain cached pages in folio_batch before >>>> releasing gathered pages. Thus, it is redundant to call lru_add_drain() >>>> before gathering pages, if CONFIG_MMU_GATHER_NO_GATHER is not set. >>>> >>>> Remove lru_add_drain() prior to gathering and unmapping pages in >>>> exit_mmap() and unmap_region() if CONFIG_MMU_GATHER_NO_GATHER is not set. >>>> >>>> Note that the page unmapping process in oom_killer (e.g., in >>>> __oom_reap_task_mm()) also uses tlb_finish_mmu() and does not have >>>> redundant lru_add_drain(). So, this commit makes the code more consistent. >>> >>> Shouldn't we put this in __tlb_gather_mmu() which already has the >>> CONFIG_MMU_GATHER_NO_GATHER ifdefs? That would presuambly help with, eg >>> zap_page_range_single() too. >>> >> >> Thanks. It makes sense to me. >> This commit is motivated by a workload that use mmap/unmap heavily. >> While the mmu_gather feature is also used by hugetlb, madvise, mprotect, >> etc., thus I prefer to have another standalone commit (following this one) >> that moves lru_add_drain() to __tlb_gather_mmu() to unify these cases for >> not making redundant lru_add_drain() calls when using mmu_gather. > > That's not normally the approach we take. Okay, understood. Thanks for pointing it out. Let me send a new patch that aligns with your suggestion.
