mm: hwposion: support recovery from ksm_might_need_to_copy()
Commit Message
When the kernel copy a page from ksm_might_need_to_copy(), but runs
into an uncorrectable error, it will crash since poisoned page is
consumed by kernel, this is similar to Copy-on-write poison recovery,
When an error is detected during the page copy, return VM_FAULT_HWPOISON,
which help us to avoid system crash. Note, memory failure on a KSM
page will be skipped, but still call memory_failure_queue() to be
consistent with general memory failure process.
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
---
mm/ksm.c | 8 ++++++--
mm/memory.c | 3 +++
mm/swapfile.c | 2 +-
3 files changed, 10 insertions(+), 3 deletions(-)
Comments
sorry, please ignore it, will resend.
On 2022/12/9 10:10, Kefeng Wang wrote:
> When the kernel copy a page from ksm_might_need_to_copy(), but runs
> into an uncorrectable error, it will crash since poisoned page is
> consumed by kernel, this is similar to Copy-on-write poison recovery,
> When an error is detected during the page copy, return VM_FAULT_HWPOISON,
> which help us to avoid system crash. Note, memory failure on a KSM
> page will be skipped, but still call memory_failure_queue() to be
> consistent with general memory failure process.
>
> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
> ---
> mm/ksm.c | 8 ++++++--
> mm/memory.c | 3 +++
> mm/swapfile.c | 2 +-
> 3 files changed, 10 insertions(+), 3 deletions(-)
>
> diff --git a/mm/ksm.c b/mm/ksm.c
> index f1e06b1d47f3..356e93b85287 100644
> --- a/mm/ksm.c
> +++ b/mm/ksm.c
> @@ -2629,8 +2629,12 @@ struct page *ksm_might_need_to_copy(struct page *page,
> new_page = NULL;
> }
> if (new_page) {
> - copy_user_highpage(new_page, page, address, vma);
> -
> + if (copy_mc_user_highpage(new_page, page, address, vma)) {
> + put_page(new_page);
> + new_page = ERR_PTR(-EHWPOISON);
> + memory_failure_queue(page_to_pfn(page), 0);
> + return new_page;
> + }
> SetPageDirty(new_page);
> __SetPageUptodate(new_page);
> __SetPageLocked(new_page);
> diff --git a/mm/memory.c b/mm/memory.c
> index 2615fa615be4..bb7b35e42297 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3840,6 +3840,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> if (unlikely(!page)) {
> ret = VM_FAULT_OOM;
> goto out_page;
> + } els if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
> + ret = VM_FAULT_HWPOISON;
> + goto out_page;
> }
> folio = page_folio(page);
>
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index f670ffb7df7e..763ff6a8a576 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -1767,7 +1767,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
>
> swapcache = page;
> page = ksm_might_need_to_copy(page, vma, addr);
> - if (unlikely(!page))
> + if (IS_ERR_OR_NULL(!page))
> return -ENOMEM;
>
> pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
@@ -2629,8 +2629,12 @@ struct page *ksm_might_need_to_copy(struct page *page,
new_page = NULL;
}
if (new_page) {
- copy_user_highpage(new_page, page, address, vma);
-
+ if (copy_mc_user_highpage(new_page, page, address, vma)) {
+ put_page(new_page);
+ new_page = ERR_PTR(-EHWPOISON);
+ memory_failure_queue(page_to_pfn(page), 0);
+ return new_page;
+ }
SetPageDirty(new_page);
__SetPageUptodate(new_page);
__SetPageLocked(new_page);
@@ -3840,6 +3840,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
if (unlikely(!page)) {
ret = VM_FAULT_OOM;
goto out_page;
+ } els if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+ ret = VM_FAULT_HWPOISON;
+ goto out_page;
}
folio = page_folio(page);
@@ -1767,7 +1767,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
swapcache = page;
page = ksm_might_need_to_copy(page, vma, addr);
- if (unlikely(!page))
+ if (IS_ERR_OR_NULL(!page))
return -ENOMEM;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);