mm: memory-failure: update ttu flag inside unmap_poisoned_folio

Patch series "mm: memory_failure: unmap poisoned folio during migrate
properly", v3.

Fix two bugs during folio migration if the folio is poisoned.


This patch (of 3):

Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON in
order to stop send SIGBUS signal when accessing an error page after a
memory error on a clean folio.  However during page migration, anon folio
must be set with TTU_HWPOISON during unmap_*().  For pagecache we need
some policy just like the one in hwpoison_user_mappings to set this flag. 
So move this policy from hwpoison_user_mappings to unmap_poisoned_folio to
handle this warning properly.

Warning will be produced during unamp poison folio with the following log:

  ------------[ cut here ]------------
  WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c
  Modules linked in:
  CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G        W          6.13.0-rc1-00018-gacdb4bbda7ab #42
  Tainted: [W]=WARN
  Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
  pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : try_to_unmap_one+0x8fc/0xd3c
  lr : try_to_unmap_one+0x3dc/0xd3c
  Call trace:
   try_to_unmap_one+0x8fc/0xd3c (P)
   try_to_unmap_one+0x3dc/0xd3c (L)
   rmap_walk_anon+0xdc/0x1f8
   rmap_walk+0x3c/0x58
   try_to_unmap+0x88/0x90
   unmap_poisoned_folio+0x30/0xa8
   do_migrate_range+0x4a0/0x568
   offline_pages+0x5a4/0x670
   memory_block_action+0x17c/0x374
   memory_subsys_offline+0x3c/0x78
   device_offline+0xa4/0xd0
   state_store+0x8c/0xf0
   dev_attr_store+0x18/0x2c
   sysfs_kf_write+0x44/0x54
   kernfs_fop_write_iter+0x118/0x1a8
   vfs_write+0x3a8/0x4bc
   ksys_write+0x6c/0xf8
   __arm64_sys_write+0x1c/0x28
   invoke_syscall+0x44/0x100
   el0_svc_common.constprop.0+0x40/0xe0
   do_el0_svc+0x1c/0x28
   el0_svc+0x30/0xd0
   el0t_64_sync_handler+0xc8/0xcc
   el0t_64_sync+0x198/0x19c
  ---[ end trace 0000000000000000 ]---

[mawupeng1@huawei.com: unmap_poisoned_folio(): remove shadowed local `mapping', per Miaohe]
  Link: https://lkml.kernel.org/r/20250219060653.3849083-1-mawupeng1@huawei.com
Link: https://lkml.kernel.org/r/20250217014329.3610326-1-mawupeng1@huawei.com
Link: https://lkml.kernel.org/r/20250217014329.3610326-2-mawupeng1@huawei.com
Fixes: 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Ma Wupeng <mawupeng1@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 31 insertions, 32 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 995a15eb67e2..327e02fdc029 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1556,11 +1556,35 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
 	return ret;
 }
 
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
-	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
-		struct address_space *mapping;
+	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
+	struct address_space *mapping;
+
+	if (folio_test_swapcache(folio)) {
+		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
+		ttu &= ~TTU_HWPOISON;
+	}
 
+	/*
+	 * Propagate the dirty bit from PTEs to struct page first, because we
+	 * need this to decide if we should kill or just drop the page.
+	 * XXX: the dirty test could be racy: set_page_dirty() may not always
+	 * be called inside page lock (it's recommended but not enforced).
+	 */
+	mapping = folio_mapping(folio);
+	if (!must_kill && !folio_test_dirty(folio) && mapping &&
+	    mapping_can_writeback(mapping)) {
+		if (folio_mkclean(folio)) {
+			folio_set_dirty(folio);
+		} else {
+			ttu &= ~TTU_HWPOISON;
+			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
+				pfn);
+		}
+	}
+
+	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
 		/*
 		 * For hugetlb folios in shared mappings, try_to_unmap
 		 * could potentially call huge_pmd_unshare.  Because of
@@ -1572,7 +1596,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 		if (!mapping) {
 			pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
 				folio_pfn(folio));
-			return;
+			return -EBUSY;
 		}
 
 		try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
@@ -1580,6 +1604,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 	} else {
 		try_to_unmap(folio, ttu);
 	}
+
+	return folio_mapped(folio) ? -EBUSY : 0;
 }
 
 /*
@@ -1589,8 +1615,6 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 		unsigned long pfn, int flags)
 {
-	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
-	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	bool unmap_success;
 	int forcekill;
@@ -1613,29 +1637,6 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 	if (!folio_mapped(folio))
 		return true;
 
-	if (folio_test_swapcache(folio)) {
-		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
-		ttu &= ~TTU_HWPOISON;
-	}
-
-	/*
-	 * Propagate the dirty bit from PTEs to struct page first, because we
-	 * need this to decide if we should kill or just drop the page.
-	 * XXX: the dirty test could be racy: set_page_dirty() may not always
-	 * be called inside page lock (it's recommended but not enforced).
-	 */
-	mapping = folio_mapping(folio);
-	if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping &&
-	    mapping_can_writeback(mapping)) {
-		if (folio_mkclean(folio)) {
-			folio_set_dirty(folio);
-		} else {
-			ttu &= ~TTU_HWPOISON;
-			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
-				pfn);
-		}
-	}
-
 	/*
 	 * First collect all the processes that have the page
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
@@ -1643,9 +1644,7 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 	 */
 	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
 
-	unmap_poisoned_folio(folio, ttu);
-
-	unmap_success = !folio_mapped(folio);
+	unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL);
 	if (!unmap_success)
 		pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n",
 		       pfn, folio_mapcount(folio));