The patch titled
Subject: mm: factor helpers for memory_failure_dev_pagemap
has been added to the -mm mm-unstable branch. Its filename is
mm-factor-helpers-for-memory_failure_dev_pagemap.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-factor-helpers-for-memory_failure_dev_pagemap.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
Subject: mm: factor helpers for memory_failure_dev_pagemap
Date: Fri, 3 Jun 2022 13:37:26 +0800
memory_failure_dev_pagemap code is a bit complex before introduce RMAP
feature for fsdax. So it is needed to factor some helper functions to
simplify these code.
Link: https://lkml.kernel.org/r/20220603053738.1218681-3-ruansy.fnst@xxxxxxxxxxx
Signed-off-by: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.wiliams@xxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
Cc: Goldwyn Rodrigues <rgoldwyn@xxxxxxx>
Cc: Jane Chu <jane.chu@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: Ritesh Harjani <riteshh@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory-failure.c | 167 +++++++++++++++++++++++-------------------
1 file changed, 92 insertions(+), 75 deletions(-)
--- a/mm/memory-failure.c~mm-factor-helpers-for-memory_failure_dev_pagemap
+++ a/mm/memory-failure.c
@@ -1552,6 +1552,95 @@ out:
return ret;
}
+static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn,
+ struct address_space *mapping, pgoff_t index, int flags)
+{
+ struct to_kill *tk;
+ unsigned long size = 0;
+
+ list_for_each_entry(tk, to_kill, nd)
+ if (tk->size_shift)
+ size = max(size, 1UL << tk->size_shift);
+
+ if (size) {
+ /*
+ * Unmap the largest mapping to avoid breaking up device-dax
+ * mappings which are constant size. The actual size of the
+ * mapping being torn down is communicated in siginfo, see
+ * kill_proc()
+ */
+ loff_t start = (index << PAGE_SHIFT) & ~(size - 1);
+
+ unmap_mapping_range(mapping, start, size, 0);
+ }
+
+ kill_procs(to_kill, flags & MF_MUST_KILL, false, pfn, flags);
+}
+
+static int mf_generic_kill_procs(unsigned long long pfn, int flags,
+ struct dev_pagemap *pgmap)
+{
+ struct page *page = pfn_to_page(pfn);
+ LIST_HEAD(to_kill);
+ dax_entry_t cookie;
+ int rc = 0;
+
+ /*
+ * Pages instantiated by device-dax (not filesystem-dax)
+ * may be compound pages.
+ */
+ page = compound_head(page);
+
+ /*
+ * Prevent the inode from being freed while we are interrogating
+ * the address_space, typically this would be handled by
+ * lock_page(), but dax pages do not use the page lock. This
+ * also prevents changes to the mapping of this pfn until
+ * poison signaling is complete.
+ */
+ cookie = dax_lock_page(page);
+ if (!cookie)
+ return -EBUSY;
+
+ if (hwpoison_filter(page)) {
+ rc = -EOPNOTSUPP;
+ goto unlock;
+ }
+
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_COHERENT:
+ /*
+ * TODO: Handle device pages which may need coordination
+ * with device-side memory.
+ */
+ rc = -ENXIO;
+ goto unlock;
+ default:
+ break;
+ }
+
+ /*
+ * Use this flag as an indication that the dax page has been
+ * remapped UC to prevent speculative consumption of poison.
+ */
+ SetPageHWPoison(page);
+
+ /*
+ * Unlike System-RAM there is no possibility to swap in a
+ * different physical page at a given virtual address, so all
+ * userspace consumption of ZONE_DEVICE memory necessitates
+ * SIGBUS (i.e. MF_MUST_KILL)
+ */
+ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
+ collect_procs(page, &to_kill, true);
+
+ unmap_and_kill(&to_kill, pfn, page->mapping, page->index, flags);
+unlock:
+ dax_unlock_page(page, cookie);
+ return rc;
+}
+
/*
* Taking refcount of hugetlb pages needs extra care about race conditions
* with basic operations like hugepage allocation/free/demotion.
@@ -1636,12 +1725,7 @@ static int memory_failure_dev_pagemap(un
struct dev_pagemap *pgmap)
{
struct page *page = pfn_to_page(pfn);
- unsigned long size = 0;
- struct to_kill *tk;
- LIST_HEAD(tokill);
- int rc = -EBUSY;
- loff_t start;
- dax_entry_t cookie;
+ int rc = -ENXIO;
if (flags & MF_COUNT_INCREASED)
/*
@@ -1650,77 +1734,10 @@ static int memory_failure_dev_pagemap(un
put_page(page);
/* device metadata space is not recoverable */
- if (!pgmap_pfn_valid(pgmap, pfn)) {
- rc = -ENXIO;
+ if (!pgmap_pfn_valid(pgmap, pfn))
goto out;
- }
-
- /*
- * Pages instantiated by device-dax (not filesystem-dax)
- * may be compound pages.
- */
- page = compound_head(page);
-
- /*
- * Prevent the inode from being freed while we are interrogating
- * the address_space, typically this would be handled by
- * lock_page(), but dax pages do not use the page lock. This
- * also prevents changes to the mapping of this pfn until
- * poison signaling is complete.
- */
- cookie = dax_lock_page(page);
- if (!cookie)
- goto out;
-
- if (hwpoison_filter(page)) {
- rc = -EOPNOTSUPP;
- goto unlock;
- }
-
- switch (pgmap->type) {
- case MEMORY_DEVICE_PRIVATE:
- case MEMORY_DEVICE_COHERENT:
- /*
- * TODO: Handle device pages which may need coordination
- * with device-side memory.
- */
- goto unlock;
- default:
- break;
- }
-
- /*
- * Use this flag as an indication that the dax page has been
- * remapped UC to prevent speculative consumption of poison.
- */
- SetPageHWPoison(page);
- /*
- * Unlike System-RAM there is no possibility to swap in a
- * different physical page at a given virtual address, so all
- * userspace consumption of ZONE_DEVICE memory necessitates
- * SIGBUS (i.e. MF_MUST_KILL)
- */
- flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
- collect_procs(page, &tokill, true);
-
- list_for_each_entry(tk, &tokill, nd)
- if (tk->size_shift)
- size = max(size, 1UL << tk->size_shift);
- if (size) {
- /*
- * Unmap the largest mapping to avoid breaking up
- * device-dax mappings which are constant size. The
- * actual size of the mapping being torn down is
- * communicated in siginfo, see kill_proc()
- */
- start = (page->index << PAGE_SHIFT) & ~(size - 1);
- unmap_mapping_range(page->mapping, start, size, 0);
- }
- kill_procs(&tokill, true, false, pfn, flags);
- rc = 0;
-unlock:
- dax_unlock_page(page, cookie);
+ rc = mf_generic_kill_procs(pfn, flags, pgmap);
out:
/* drop pgmap ref acquired in caller */
put_dev_pagemap(pgmap);
_
Patches currently in -mm which might be from ruansy.fnst@xxxxxxxxxxx are
dax-introduce-holder-for-dax_device.patch
mm-factor-helpers-for-memory_failure_dev_pagemap.patch
pagemappmem-introduce-memory_failure.patch
fsdax-introduce-dax_lock_mapping_entry.patch
mm-introduce-mf_dax_kill_procs-for-fsdax-case.patch
xfs-implement-notify_failure-for-xfs.patch
fsdax-set-a-cow-flag-when-associate-reflink-mappings.patch
fsdax-output-address-in-dax_iomap_pfn-and-rename-it.patch
fsdax-introduce-dax_iomap_cow_copy.patch
fsdax-replace-mmap-entry-in-case-of-cow.patch
fsdax-add-dax_iomap_cow_copy-for-dax-zero.patch
fsdax-dedup-file-range-to-use-a-compare-function.patch
xfs-support-cow-in-fsdax-mode.patch
xfs-add-dax-dedupe-support.patch
