| Message ID | 20250310172318.653630-7-sj@kernel.org (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE | expand |
On Mon, Mar 10, 2025 at 10:23:15AM -0700, SeongJae Park wrote: > Some of zap_page_range_single() callers such as [process_]madvise() with > MADV_DONEED[_LOCKED] cannot batch tlb flushes because > zap_page_range_single() does tlb flushing for each invocation. Split > out the body of zap_page_range_single() except mmu_gather object > initialization and gathered tlb entries flushing parts for such batched > tlb flushing usage. > > Signed-off-by: SeongJae Park <sj@kernel.org> > --- > mm/memory.c | 36 ++++++++++++++++++++++-------------- > 1 file changed, 22 insertions(+), 14 deletions(-) > > diff --git a/mm/memory.c b/mm/memory.c > index 78c7ee62795e..88c478e2ed1a 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -1995,38 +1995,46 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, > mmu_notifier_invalidate_range_end(&range); > } > > -/** > - * zap_page_range_single - remove user pages in a given range > - * @vma: vm_area_struct holding the applicable pages > - * @address: starting address of pages to zap > - * @size: number of bytes to zap > - * @details: details of shared cache invalidation > - * > - * The range must fit into one VMA. > - */ > -void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, > +static void unmap_vma_single(struct mmu_gather *tlb, > + struct vm_area_struct *vma, unsigned long address, > unsigned long size, struct zap_details *details) > { > const unsigned long end = address + size; > struct mmu_notifier_range range; > - struct mmu_gather tlb; > > mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, > address, end); > hugetlb_zap_begin(vma, &range.start, &range.end); > - tlb_gather_mmu(&tlb, vma->vm_mm); > update_hiwater_rss(vma->vm_mm); > mmu_notifier_invalidate_range_start(&range); > /* > * unmap 'address-end' not 'range.start-range.end' as range > * could have been expanded for hugetlb pmd sharing. > */ > - unmap_single_vma(&tlb, vma, address, end, details, false); > + unmap_single_vma(tlb, vma, address, end, details, false); > mmu_notifier_invalidate_range_end(&range); > - tlb_finish_mmu(&tlb); > hugetlb_zap_end(vma, details); Previously hugetlb_zap_end() would happen after tlb_finish_mmu(), now it happens before? This seems like a major problem with this change. If not you need to explain why not in the commit message. > } > > +/** > + * zap_page_range_single - remove user pages in a given range > + * @vma: vm_area_struct holding the applicable pages > + * @address: starting address of pages to zap > + * @size: number of bytes to zap > + * @details: details of shared cache invalidation > + * > + * The range must fit into one VMA. > + */ > +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, > + unsigned long size, struct zap_details *details) > +{ > + struct mmu_gather tlb; > + > + tlb_gather_mmu(&tlb, vma->vm_mm); > + unmap_vma_single(&tlb, vma, address, size, details); > + tlb_finish_mmu(&tlb); > +} > + > /** > * zap_vma_ptes - remove ptes mapping the vma > * @vma: vm_area_struct holding ptes to be zapped > -- > 2.39.5
diff --git a/mm/memory.c b/mm/memory.c index 78c7ee62795e..88c478e2ed1a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1995,38 +1995,46 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, mmu_notifier_invalidate_range_end(&range); } -/** - * zap_page_range_single - remove user pages in a given range - * @vma: vm_area_struct holding the applicable pages - * @address: starting address of pages to zap - * @size: number of bytes to zap - * @details: details of shared cache invalidation - * - * The range must fit into one VMA. - */ -void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, +static void unmap_vma_single(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { const unsigned long end = address + size; struct mmu_notifier_range range; - struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); hugetlb_zap_begin(vma, &range.start, &range.end); - tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); /* * unmap 'address-end' not 'range.start-range.end' as range * could have been expanded for hugetlb pmd sharing. */ - unmap_single_vma(&tlb, vma, address, end, details, false); + unmap_single_vma(tlb, vma, address, end, details, false); mmu_notifier_invalidate_range_end(&range); - tlb_finish_mmu(&tlb); hugetlb_zap_end(vma, details); } +/** + * zap_page_range_single - remove user pages in a given range + * @vma: vm_area_struct holding the applicable pages + * @address: starting address of pages to zap + * @size: number of bytes to zap + * @details: details of shared cache invalidation + * + * The range must fit into one VMA. + */ +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details) +{ + struct mmu_gather tlb; + + tlb_gather_mmu(&tlb, vma->vm_mm); + unmap_vma_single(&tlb, vma, address, size, details); + tlb_finish_mmu(&tlb); +} + /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped
Some of zap_page_range_single() callers such as [process_]madvise() with MADV_DONEED[_LOCKED] cannot batch tlb flushes because zap_page_range_single() does tlb flushing for each invocation. Split out the body of zap_page_range_single() except mmu_gather object initialization and gathered tlb entries flushing parts for such batched tlb flushing usage. Signed-off-by: SeongJae Park <sj@kernel.org> --- mm/memory.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-)