[v11,6/8] mm: Introduce mf_dax_kill_procs() for fsdax case

Commit Message

Shiyang Ruan Feb. 27, 2022, 12:07 p.m. UTC

This function is called at the end of RMAP routine, i.e. filesystem
recovery function, to collect and kill processes using a shared page of
DAX file.  The difference with mf_generic_kill_procs() is, it accepts
file's (mapping,offset) instead of struct page because different files'
mappings and offsets may share the same page in fsdax mode.
It will be called when filesystem's RMAP results are found.

Signed-off-by: Shiyang Ruan <[e-mail]>
Reviewed-by: Dan Williams <[e-mail]>
---
 include/linux/mm.h  |  4 ++
 mm/memory-failure.c | 96 ++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 90 insertions(+), 10 deletions(-)

Comments

Christoph Hellwig March 30, 2022, 5:51 a.m. UTC | #1

On Sun, Feb 27, 2022 at 08:07:45PM +0800, Shiyang Ruan wrote:
> This function is called at the end of RMAP routine, i.e. filesystem
> recovery function, to collect and kill processes using a shared page of
> DAX file.

I think just throwing RMAP inhere is rather confusing.

> The difference with mf_generic_kill_procs() is, it accepts
> file's (mapping,offset) instead of struct page because different files'
> mappings and offsets may share the same page in fsdax mode.
> It will be called when filesystem's RMAP results are found.

So maybe I'd word the whole log as something like:

This new function is a variant of mf_generic_kill_procs that accepts
a file, offset pair instead o 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.

Otherwise looks good:

Reviewed-by: Christoph Hellwig <[e-mail]>

> index 9b1d56c5c224..0420189e4788 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3195,6 +3195,10 @@ enum mf_flags {
>  	MF_SOFT_OFFLINE = 1 << 3,
>  	MF_UNPOISON = 1 << 4,
>  };
> +#if IS_ENABLED(CONFIG_FS_DAX)
> +int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
> +		      unsigned long count, int mf_flags);
> +#endif /* CONFIG_FS_DAX */

No need for the ifdef here, having the stable declaration around is
just fine.

> +#if IS_ENABLED(CONFIG_FS_DAX)

No need for the IS_ENABLED as CONFIG_FS_DAX can't be modular.
A good old #ifdef will do it.

Otherwise looks good:

Reviewed-by: Christoph Hellwig <[e-mail]>

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9b1d56c5c224..0420189e4788 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3195,6 +3195,10 @@  enum mf_flags {
 	MF_SOFT_OFFLINE = 1 << 3,
 	MF_UNPOISON = 1 << 4,
 };
+#if IS_ENABLED(CONFIG_FS_DAX)
+int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
+		      unsigned long count, int mf_flags);
+#endif /* CONFIG_FS_DAX */
 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 8dd2f58c1aa8..2ba79c3869ed 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -304,10 +304,9 @@  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;
@@ -346,10 +345,14 @@  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;
 
@@ -360,9 +363,15 @@  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(vma, fsdax_pgoff);
+		tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr);
+	} else
 		tk->size_shift = page_shift(compound_head(p));
 
 	/*
@@ -510,7 +519,7 @@  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);
@@ -546,12 +555,40 @@  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);
+}
+
+#if IS_ENABLED(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.
@@ -1574,6 +1611,45 @@  static int mf_generic_kill_procs(unsigned long long pfn, int flags,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_FS_DAX)
+/**
+ * mf_dax_kill_procs - Collect and kill processes who are using this file range
+ * @mapping:	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 */
+
 static int memory_failure_hugetlb(unsigned long pfn, int flags)
 {
 	struct page *p = pfn_to_page(pfn);