nvdimm.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
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>
Subject: [PATCH v7 3/8] mm: factor helpers for memory_failure_dev_pagemap
Date: Fri, 24 Sep 2021 21:09:54 +0800	[thread overview]
Message-ID: <20210924130959.2695749-4-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210924130959.2695749-1-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>
---
 mm/memory-failure.c | 140 ++++++++++++++++++++++++--------------------
 1 file changed, 76 insertions(+), 64 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 54879c339024..8ff9b52823c0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1430,6 +1430,79 @@ 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;
+
+	/*
+	 * 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))
+		return 0;
+
+	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);
+	dax_unlock_page(page, cookie);
+	return 0;
+}
+
 static int memory_failure_hugetlb(unsigned long pfn, int flags)
 {
 	struct page *p = pfn_to_page(pfn);
@@ -1519,12 +1592,8 @@ 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)
 		/*
@@ -1533,67 +1602,10 @@ 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;
-	}
-
-	/*
-	 * 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 = 0;
-		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, flags & MF_ACTION_REQUIRED);
-
-	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, flags & MF_MUST_KILL, 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);
-- 
2.33.0




  parent reply	other threads:[~2021-09-24 13:11 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-24 13:09 [PATCH v7 0/8] [PATCH v7 0/8] fsdax: introduce fs query to support reflink Shiyang Ruan
2021-09-24 13:09 ` [PATCH v7 1/8] dax: Use rwsem for dax_{read,write}_lock() Shiyang Ruan
2021-10-14 17:48   ` Darrick J. Wong
2021-10-20  5:19     ` Shiyang Ruan
2021-10-15  6:30   ` Christoph Hellwig
2021-09-24 13:09 ` [PATCH v7 2/8] dax: Introduce holder for dax_device Shiyang Ruan
2021-10-14 18:00   ` Darrick J. Wong
2021-10-20  6:58     ` Shiyang Ruan
2021-09-24 13:09 ` Shiyang Ruan [this message]
2021-10-14 18:02   ` [PATCH v7 3/8] mm: factor helpers for memory_failure_dev_pagemap Darrick J. Wong
2021-10-15  6:33   ` Christoph Hellwig
2021-09-24 13:09 ` [PATCH v7 4/8] pagemap,pmem: Introduce ->memory_failure() Shiyang Ruan
2021-10-14 18:05   ` Darrick J. Wong
2021-10-20  5:25     ` Shiyang Ruan
2021-10-15  6:36   ` Christoph Hellwig
2021-09-24 13:09 ` [PATCH v7 5/8] fsdax: Introduce dax_lock_mapping_entry() Shiyang Ruan
2021-10-14 18:17   ` Darrick J. Wong
2021-09-24 13:09 ` [PATCH v7 6/8] mm: Introduce mf_dax_kill_procs() for fsdax case Shiyang Ruan
2021-10-14 19:32   ` Darrick J. Wong
2021-10-20  5:47     ` Shiyang Ruan
2021-09-24 13:09 ` [PATCH v7 7/8] xfs: Implement ->notify_failure() for XFS Shiyang Ruan
2021-10-14 19:21   ` Darrick J. Wong
2021-10-15  6:41   ` Christoph Hellwig
2021-09-24 13:09 ` [PATCH v7 8/8] fsdax: add exception for reflinked files Shiyang Ruan
2021-10-14 19:24   ` Darrick J. Wong
2021-10-15  6:38     ` Christoph Hellwig

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=20210924130959.2695749-4-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=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;
as well as URLs for NNTP newsgroup(s).