mm: hwpoison: support recovery from ksm_might_need_to_copy()

When the kernel copies 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 the issue recently fixed by Copy-on-write
poison recovery.

When an error is detected during the page copy, return VM_FAULT_HWPOISON
in do_swap_page(), and install a hwpoison entry in unuse_pte() when
swapoff, 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, and we could support KSM
page recovery in the feature.

[wangkefeng.wang@huawei.com: enhance unuse_pte(), fix issue found by lkp]
  Link: https://lkml.kernel.org/r/20221213120523.141588-1-wangkefeng.wang@huawei.com
[wangkefeng.wang@huawei.com: update changelog, alter ksm_might_need_to_copy(), restore unlikely() in unuse_pte()]
  Link: https://lkml.kernel.org/r/20230201074433.96641-1-wangkefeng.wang@huawei.com
Link: https://lkml.kernel.org/r/20221209072801.193221-1-wangkefeng.wang@huawei.comSigned-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/ksm.c

@@ -2629,8 +2629,11 @@ 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);
+			memory_failure_queue(page_to_pfn(page), 0);
+			return ERR_PTR(-EHWPOISON);
+		}
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
 		__SetPageLocked(new_page);

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;
+		} else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+			ret = VM_FAULT_HWPOISON;
+			goto out_page;
 		}
 		folio = page_folio(page);
 

mm/swapfile.c

@@ -1764,12 +1764,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *swapcache;
 	spinlock_t *ptl;
 	pte_t *pte, new_pte;
+	bool hwposioned = false;
 	int ret = 1;
 
 	swapcache = page;
 	page = ksm_might_need_to_copy(page, vma, addr);
 	if (unlikely(!page))
 		return -ENOMEM;
+	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
+		hwposioned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
@@ -1777,15 +1780,19 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		goto out;
 	}
 
-	if (unlikely(!PageUptodate(page))) {
-		pte_t pteval;
+	if (unlikely(hwposioned || !PageUptodate(page))) {
+		swp_entry_t swp_entry;
 
 		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
-		pteval = swp_entry_to_pte(make_swapin_error_entry());
-		set_pte_at(vma->vm_mm, addr, pte, pteval);
-		swap_free(entry);
+		if (hwposioned) {
+			swp_entry = make_hwpoison_entry(swapcache);
+			page = swapcache;
+		} else {
+			swp_entry = make_swapin_error_entry();
+		}
+		new_pte = swp_entry_to_pte(swp_entry);
 		ret = 0;
-		goto out;
+		goto setpte;
 	}
 
 	/* See do_swap_page() */
@@ -1817,6 +1824,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		new_pte = pte_mksoft_dirty(new_pte);
 	if (pte_swp_uffd_wp(*pte))
 		new_pte = pte_mkuffd_wp(new_pte);
+setpte:
 	set_pte_at(vma->vm_mm, addr, pte, new_pte);
 	swap_free(entry);
 out: