vma_map_pages currently calls vm_insert_page on each individual page in the mapping, which creates significant overhead because we are repeatedly spinlocking. Instead, we should batch insert pages using vm_insert_pages, which amortizes the cost of the spinlock. Tested through watching hardware accelerated video on a MTK ChromeOS device. This particular path maps both a V4L2 buffer and a GEM allocated buffer into userspace and converts the contents from one pixel format to another. Both vb2_mmap() and mtk_gem_object_mmap() exercise this pathway. Signed-off-by: Justin Green --- mm/memory.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index da360a6eb8a4..7ae6ac42e7d8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2499,7 +2499,6 @@ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; - int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) @@ -2509,14 +2508,7 @@ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, if (count > num - offset) return -ENXIO; - for (i = 0; i < count; i++) { - ret = vm_insert_page(vma, uaddr, pages[offset + i]); - if (ret < 0) - return ret; - uaddr += PAGE_SIZE; - } - - return 0; + return vm_insert_pages(vma, uaddr, pages + offset, &count); } /** -- 2.53.0.rc1.217.geba53bf80e-goog