[PATCH 4/4] mm/memory-failure: Fall back to vma_address() when ->notify_failure() fails

[Dan Williams <dan.j.williams@xxxxxxxxx>]

In the case where a filesystem is polled to take over the memory failure
and receives -EOPNOTSUPP it indicates that page->index and page->mapping
are valid for reverse mapping the failure address. Introduce
FSDAX_INVALID_PGOFF to distinguish when add_to_kill() is being called
from mf_dax_kill_procs() by a filesytem vs the typical memory_failure()
path.

Otherwise, vma_pgoff_address() is called with an invalid fsdax_pgoff
which then trips this failing signature:

 kernel BUG at mm/memory-failure.c:319!
 invalid opcode: 0000 [#1] PREEMPT SMP PTI
 CPU: 13 PID: 1262 Comm: dax-pmd Tainted: G           OE    N 6.0.0-rc2+ #62
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
 RIP: 0010:add_to_kill.cold+0x19d/0x209
 [..]
 Call Trace:
  <TASK>
  collect_procs.part.0+0x2c4/0x460
  memory_failure+0x71b/0xba0
  ? _printk+0x58/0x73
  do_madvise.part.0.cold+0xaf/0xc5

Fixes: c36e20249571 ("mm: introduce mf_dax_kill_procs() for fsdax case")
Cc: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Darrick J. Wong <djwong@xxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Goldwyn Rodrigues <rgoldwyn@xxxxxxx>
Cc: Jane Chu <jane.chu@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Ritesh Harjani <riteshh@xxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
 mm/memory-failure.c |   22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8a4294afbfa0..e424a9dac749 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -345,13 +345,17 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
  * not much we can do.	We just print a message and ignore otherwise.
  */
 
+#define FSDAX_INVALID_PGOFF ULONG_MAX
+
 /*
  * Schedule a process for later kill.
  * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
  *
- * Notice: @fsdax_pgoff is used only when @p is a fsdax page.
- *   In other cases, such as anonymous and file-backend page, the address to be
- *   killed can be caculated by @p itself.
+ * Note: @fsdax_pgoff is used only when @p is a fsdax page and a
+ * filesystem with a memory failure handler has claimed the
+ * memory_failure event. In all other cases, page->index and
+ * page->mapping are sufficient for mapping the page back to its
+ * corresponding user virtual address.
  */
 static void add_to_kill(struct task_struct *tsk, struct page *p,
 			pgoff_t fsdax_pgoff, struct vm_area_struct *vma,
@@ -367,11 +371,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 
 	tk->addr = page_address_in_vma(p, vma);
 	if (is_zone_device_page(p)) {
-		/*
-		 * Since page->mapping is not used for fsdax, we need
-		 * calculate the address based on the vma.
-		 */
-		if (p->pgmap->type == MEMORY_DEVICE_FS_DAX)
+		if (fsdax_pgoff != FSDAX_INVALID_PGOFF)
 			tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma);
 		tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr);
 	} else
@@ -523,7 +523,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			if (!page_mapped_in_vma(page, vma))
 				continue;
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, 0, vma, to_kill);
+				add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma,
+					    to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -559,7 +560,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * to be informed of all such data corruptions.
 			 */
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, 0, vma, to_kill);
+				add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma,
+					    to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);