mm: introduce mf_dax_kill_procs() for fsdax case

This new function is a variant of mf_generic_kill_procs that accepts a
file, offset pair instead of a struct to support multiple files sharing a
DAX mapping.  It is intended to be called by the file systems as part of
the memory_failure handler after the file system performed a reverse
mapping from the storage address to the file and file offset.

Link: https://lkml.kernel.org/r/20220603053738.1218681-6-ruansy.fnst@fujitsu.com
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Williams <dan.j.wiliams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 88 insertions, 10 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 64393ed3330a..d4ebfc206e2b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3178,6 +3178,8 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
 };
+int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
+		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 46c77151f726..c9931c676335 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -297,10 +297,9 @@ void shake_page(struct page *p)
 }
 EXPORT_SYMBOL_GPL(shake_page);
 
-static unsigned long dev_pagemap_mapping_shift(struct page *page,
-		struct vm_area_struct *vma)
+static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
+		unsigned long address)
 {
-	unsigned long address = vma_address(page, vma);
 	unsigned long ret = 0;
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -340,10 +339,14 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 /*
  * 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.
  */
 static void add_to_kill(struct task_struct *tsk, struct page *p,
-		       struct vm_area_struct *vma,
-		       struct list_head *to_kill)
+			pgoff_t fsdax_pgoff, struct vm_area_struct *vma,
+			struct list_head *to_kill)
 {
 	struct to_kill *tk;
 
@@ -354,9 +357,15 @@ 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))
-		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
-	else
+	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)
+			tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma);
+		tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr);
+	} else
 		tk->size_shift = page_shift(compound_head(p));
 
 	/*
@@ -505,7 +514,7 @@ 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, vma, to_kill);
+				add_to_kill(t, page, 0, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -541,13 +550,41 @@ 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, vma, to_kill);
+				add_to_kill(t, page, 0, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
 	i_mmap_unlock_read(mapping);
 }
 
+#ifdef CONFIG_FS_DAX
+/*
+ * Collect processes when the error hit a fsdax page.
+ */
+static void collect_procs_fsdax(struct page *page,
+		struct address_space *mapping, pgoff_t pgoff,
+		struct list_head *to_kill)
+{
+	struct vm_area_struct *vma;
+	struct task_struct *tsk;
+
+	i_mmap_lock_read(mapping);
+	read_lock(&tasklist_lock);
+	for_each_process(tsk) {
+		struct task_struct *t = task_early_kill(tsk, true);
+
+		if (!t)
+			continue;
+		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, pgoff, vma, to_kill);
+		}
+	}
+	read_unlock(&tasklist_lock);
+	i_mmap_unlock_read(mapping);
+}
+#endif /* CONFIG_FS_DAX */
+
 /*
  * Collect the processes who have the corrupted page mapped to kill.
  */
@@ -1588,6 +1625,45 @@ unlock:
 	return rc;
 }
 
+#ifdef CONFIG_FS_DAX
+/**
+ * mf_dax_kill_procs - Collect and kill processes who are using this file range
+ * @mapping:	address_space of the file in use
+ * @index:	start pgoff of the range within the file
+ * @count:	length of the range, in unit of PAGE_SIZE
+ * @mf_flags:	memory failure flags
+ */
+int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
+		unsigned long count, int mf_flags)
+{
+	LIST_HEAD(to_kill);
+	dax_entry_t cookie;
+	struct page *page;
+	size_t end = index + count;
+
+	mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
+
+	for (; index < end; index++) {
+		page = NULL;
+		cookie = dax_lock_mapping_entry(mapping, index, &page);
+		if (!cookie)
+			return -EBUSY;
+		if (!page)
+			goto unlock;
+
+		SetPageHWPoison(page);
+
+		collect_procs_fsdax(page, mapping, index, &to_kill);
+		unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
+				index, mf_flags);
+unlock:
+		dax_unlock_mapping_entry(mapping, index, cookie);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mf_dax_kill_procs);
+#endif /* CONFIG_FS_DAX */
+
 /*
  * Called from hugetlb code with hugetlb_lock held.
  *