From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
<nvdimm@lists.linux.dev>, <linux-mm@kvack.org>,
<linux-fsdevel@vger.kernel.org>
Cc: <djwong@kernel.org>, <dan.j.williams@intel.com>,
<david@fromorbit.com>, <hch@infradead.org>, <jane.chu@oracle.com>,
Christoph Hellwig <hch@lst.de>
Subject: [PATCH v13 2/7] mm: factor helpers for memory_failure_dev_pagemap
Date: Tue, 19 Apr 2022 12:50:40 +0800 [thread overview]
Message-ID: <20220419045045.1664996-3-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20220419045045.1664996-1-ruansy.fnst@fujitsu.com>
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.
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
mm/memory-failure.c | 157 ++++++++++++++++++++++++--------------------
1 file changed, 87 insertions(+), 70 deletions(-)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e3fbff5bd467..7c8c047bfdc8 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1498,6 +1498,90 @@ static int try_to_split_thp_page(struct page *page, const char *msg)
return 0;
}
+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;
+ }
+
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ /*
+ * TODO: Handle HMM pages which may need coordination
+ * with device-side memory.
+ */
+ return -EBUSY;
+ }
+
+ /*
+ * 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;
+}
+
/*
* Called from hugetlb code with hugetlb_lock held.
*
@@ -1644,12 +1728,8 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
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)
/*
@@ -1658,73 +1738,10 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
put_page(page);
/* device metadata space is not recoverable */
- if (!pgmap_pfn_valid(pgmap, pfn)) {
- rc = -ENXIO;
- 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)
+ if (!pgmap_pfn_valid(pgmap, pfn))
goto out;
- if (hwpoison_filter(page)) {
- rc = -EOPNOTSUPP;
- goto unlock;
- }
-
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- /*
- * TODO: Handle HMM pages which may need coordination
- * with device-side memory.
- */
- goto unlock;
- }
-
- /*
- * 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);
--
2.35.1
next prev parent reply other threads:[~2022-04-19 4:51 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-19 4:50 [PATCH v13 0/7] fsdax: introduce fs query to support reflink Shiyang Ruan
2022-04-19 4:50 ` [PATCH v13 1/7] dax: Introduce holder for dax_device Shiyang Ruan
2022-04-20 17:42 ` Darrick J. Wong
2022-04-19 4:50 ` Shiyang Ruan [this message]
2022-04-21 6:13 ` [PATCH v13 2/7] mm: factor helpers for memory_failure_dev_pagemap HORIGUCHI NAOYA(堀口 直也)
2022-04-21 8:10 ` Shiyang Ruan
2022-04-21 8:12 ` Miaohe Lin
2022-04-19 4:50 ` [PATCH v13 3/7] pagemap,pmem: Introduce ->memory_failure() Shiyang Ruan
2022-04-20 17:45 ` Darrick J. Wong
2022-04-21 6:54 ` HORIGUCHI NAOYA(堀口 直也)
2022-04-21 8:24 ` Miaohe Lin
2022-04-22 7:06 ` Shiyang Ruan
2022-04-24 2:00 ` Miaohe Lin
2022-04-19 4:50 ` [PATCH v13 4/7] fsdax: Introduce dax_lock_mapping_entry() Shiyang Ruan
2022-04-20 17:53 ` Darrick J. Wong
2022-04-19 4:50 ` [PATCH v13 5/7] mm: Introduce mf_dax_kill_procs() for fsdax case Shiyang Ruan
2022-04-20 17:58 ` Darrick J. Wong
2022-04-21 8:47 ` Miaohe Lin
2022-04-21 12:50 ` HORIGUCHI NAOYA(堀口 直也)
2022-04-19 4:50 ` [PATCH v13 6/7] xfs: Implement ->notify_failure() for XFS Shiyang Ruan
2022-04-19 15:38 ` Darrick J. Wong
2022-04-20 7:33 ` [PATCH v13.1 " Shiyang Ruan
2022-04-20 17:30 ` Darrick J. Wong
2022-04-19 4:50 ` [PATCH v13 7/7] fsdax: set a CoW flag when associate reflink mappings Shiyang Ruan
2022-04-19 7:27 ` Christoph Hellwig
2022-04-20 17:35 ` Darrick J. Wong
2022-04-21 1:20 ` [PATCH v13 0/7] fsdax: introduce fs query to support reflink Dave Chinner
2022-04-21 1:48 ` Shiyang Ruan
2022-04-21 2:20 ` Dan Williams
2022-04-21 4:35 ` Dave Chinner
2022-04-21 5:47 ` HORIGUCHI NAOYA(堀口 直也)
2022-04-21 5:54 ` Christoph Hellwig
2022-04-21 7:46 ` Dave Chinner
2022-04-22 21:27 ` Dan Williams
2022-04-23 0:01 ` Dave Chinner
2022-04-23 17:32 ` Dan Williams
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220419045045.1664996-3-ruansy.fnst@fujitsu.com \
--to=ruansy.fnst@fujitsu.com \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=hch@infradead.org \
--cc=hch@lst.de \
--cc=jane.chu@oracle.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=nvdimm@lists.linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox