linux-kernel.vger.kernel.org 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>,
	Christoph Hellwig <hch@lst.de>
Subject: [PATCH v10 2/9] mm: factor helpers for memory_failure_dev_pagemap
Date: Thu, 27 Jan 2022 20:40:51 +0800	[thread overview]
Message-ID: <20220127124058.1172422-3-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20220127124058.1172422-1-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>
---
 mm/memory-failure.c | 141 ++++++++++++++++++++++++--------------------
 1 file changed, 77 insertions(+), 64 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 14ae5c18e776..98b6144e4b9b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1500,6 +1500,80 @@ 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);
@@ -1576,12 +1650,8 @@ 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)
 		/*
@@ -1590,67 +1660,10 @@ 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);
-- 
2.34.1




  parent reply	other threads:[~2022-01-27 12:41 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-27 12:40 [PATCH v10 0/9] fsdax: introduce fs query to support reflink Shiyang Ruan
2022-01-27 12:40 ` [PATCH v10 1/9] dax: Introduce holder for dax_device Shiyang Ruan
2022-01-27 16:13   ` kernel test robot
2022-01-27 16:44   ` kernel test robot
2022-02-02 13:03   ` Christoph Hellwig
2022-02-13 12:58     ` [PATCH v10.1 " Shiyang Ruan
2022-02-15 22:06       ` Dan Williams
2022-01-27 12:40 ` Shiyang Ruan [this message]
2022-02-01 21:03   ` [PATCH v10 2/9] mm: factor helpers for memory_failure_dev_pagemap Matthew Wilcox
2022-02-15 22:11   ` Dan Williams
2022-01-27 12:40 ` [PATCH v10 3/9] pagemap,pmem: Introduce ->memory_failure() Shiyang Ruan
2022-02-15 22:38   ` Dan Williams
2022-01-27 12:40 ` [PATCH v10 4/9] fsdax: fix function description Shiyang Ruan
2022-02-02 13:04   ` Christoph Hellwig
2022-02-15 23:51     ` Dan Williams
2022-01-27 12:40 ` [PATCH v10 5/9] fsdax: Introduce dax_load_page() Shiyang Ruan
2022-02-16  1:34   ` Dan Williams
2022-02-16  3:02     ` Shiyang Ruan
2022-02-16  3:07       ` Dan Williams
2022-01-27 12:40 ` [PATCH v10 6/9] mm: move pgoff_address() to vma_pgoff_address() Shiyang Ruan
2022-02-16  1:37   ` Dan Williams
2022-01-27 12:40 ` [PATCH v10 7/9] mm: Introduce mf_dax_kill_procs() for fsdax case Shiyang Ruan
2022-02-16  1:47   ` Dan Williams
2022-02-16  1:49   ` Dan Williams
2022-01-27 12:40 ` [PATCH v10 8/9] xfs: Implement ->notify_failure() for XFS Shiyang Ruan
2022-01-27 17:56   ` kernel test robot
2022-01-27 19:39   ` kernel test robot
2022-02-01 20:41   ` Darrick J. Wong
2022-02-13 13:02     ` [PATCH v10.1 " Shiyang Ruan
2022-02-15  1:46       ` Darrick J. Wong
2022-02-15  9:42         ` Shiyang Ruan
2022-02-16  1:56   ` [PATCH v10 " Dan Williams
2022-01-27 12:40 ` [PATCH v10 9/9] fsdax: set a CoW flag when associate reflink mappings Shiyang Ruan
2022-02-16  2:09   ` Dan Williams
2022-02-16  2:55     ` Shiyang Ruan
2022-02-16  3:09       ` 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=20220127124058.1172422-3-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;
as well as URLs for NNTP newsgroup(s).