From 23e7b5c2e2715947cf1ff57124dd3e96caf48521 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:50:06 -0700 Subject: [PATCH] mm, madvise_inject_error: Let memory_failure() optionally take a page reference The madvise_inject_error() routine uses get_user_pages() to lookup the pfn and other information for injected error, but it does not release that pin. The assumption is that failed pages should be taken out of circulation. However, for dax mappings it is not possible to take pages out of circulation since they are 1:1 physically mapped as filesystem blocks, or device-dax capacity. They also typically represent persistent memory which has an error clearing capability. In preparation for adding a special handler for dax mappings, shift the responsibility of taking the page reference to memory_failure(). I.e. drop the page reference and do not specify MF_COUNT_INCREASED to memory_failure(). Cc: Michal Hocko Cc: Naoya Horiguchi Signed-off-by: Dan Williams Acked-by: Naoya Horiguchi Signed-off-by: Dave Jiang --- mm/madvise.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/mm/madvise.c b/mm/madvise.c index 4d3c922..972a9ea 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -631,11 +631,13 @@ static int madvise_inject_error(int behavior, for (; start < end; start += PAGE_SIZE << order) { + unsigned long pfn; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; + pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page @@ -651,17 +653,25 @@ static int madvise_inject_error(int behavior, if (behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", - page_to_pfn(page), start); + pfn, start); ret = soft_offline_page(page, MF_COUNT_INCREASED); if (ret) return ret; continue; } + pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", - page_to_pfn(page), start); + pfn, start); - ret = memory_failure(page_to_pfn(page), MF_COUNT_INCREASED); + /* + * Drop the page reference taken by get_user_pages_fast(). In + * the absence of MF_COUNT_INCREASED the memory_failure() + * routine is responsible for pinning the page to prevent it + * from being released back to the page allocator. + */ + put_page(page); + ret = memory_failure(pfn, 0); if (ret) return ret; } -- 2.7.4