From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
<linux-nvdimm@lists.01.org>, <linux-mm@kvack.org>,
<linux-fsdevel@vger.kernel.org>, <dm-devel@redhat.com>
Cc: darrick.wong@oracle.com, david@fromorbit.com, hch@lst.de,
agk@redhat.com, snitzer@redhat.com, rgoldwyn@suse.de,
qi.fuli@fujitsu.com, y-goto@fujitsu.com
Subject: [PATCH v3 06/11] mm, pmem: Implement ->memory_failure() in pmem driver
Date: Mon, 8 Feb 2021 18:55:25 +0800 [thread overview]
Message-ID: <20210208105530.3072869-7-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20210208105530.3072869-1-ruansy.fnst@cn.fujitsu.com>
Call the ->memory_failure() which is implemented by pmem driver, in
order to finally notify filesystem to handle the corrupted data. The
handler which collects and kills processes are moved into
mf_dax_mapping_kill_procs(), which will be called by filesystem.
Keep the old handler in order to roll back if driver/device/filesystem
does not support ->memory_failure()/->corrupted_range().
Signed-off-by: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
---
drivers/nvdimm/pmem.c | 26 +++++++++++
mm/memory-failure.c | 102 +++++++++++++++++++++++++-----------------
2 files changed, 87 insertions(+), 41 deletions(-)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 875076b0ea6c..c77c80e3d155 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -363,9 +363,35 @@ static void pmem_release_disk(void *__pmem)
put_disk(pmem->disk);
}
+static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap,
+ unsigned long pfn, int flags)
+{
+ struct pmem_device *pdev;
+ struct gendisk *disk;
+ loff_t disk_offset;
+ int rc = 0;
+ unsigned long size = page_size(pfn_to_page(pfn));
+
+ pdev = container_of(pgmap, struct pmem_device, pgmap);
+ disk = pdev->disk;
+ if (!disk)
+ return -ENXIO;
+
+ disk_offset = PFN_PHYS(pfn) - pdev->phys_addr - pdev->data_offset;
+ if (disk->fops->corrupted_range) {
+ rc = disk->fops->corrupted_range(disk, NULL, disk_offset,
+ size, &flags);
+ if (rc == -ENODEV)
+ rc = -ENXIO;
+ } else
+ rc = -EOPNOTSUPP;
+ return rc;
+}
+
static const struct dev_pagemap_ops fsdax_pagemap_ops = {
.kill = pmem_pagemap_kill,
.cleanup = pmem_pagemap_cleanup,
+ .memory_failure = pmem_pagemap_memory_failure,
};
static int pmem_attach_disk(struct device *dev,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 158fe0c8e602..670e29cd263e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1219,6 +1219,54 @@ static int try_to_split_thp_page(struct page *page, const char *msg)
return 0;
}
+int mf_generic_kill_procs(unsigned long long pfn, int flags)
+{
+ struct page *page = pfn_to_page(pfn);
+ const bool unmap_success = true;
+ unsigned long size = 0;
+ struct to_kill *tk;
+ LIST_HEAD(to_kill);
+ loff_t start;
+ 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;
+ /*
+ * 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, flags & MF_ACTION_REQUIRED);
+
+ 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()
+ */
+ start = (page->index << PAGE_SHIFT) & ~(size - 1);
+ unmap_mapping_range(page->mapping, start, start + size, 0);
+ }
+ kill_procs(&to_kill, flags & MF_MUST_KILL, !unmap_success, pfn, flags);
+
+ dax_unlock_page(page, cookie);
+ return 0;
+}
+
int mf_dax_mapping_kill_procs(struct address_space *mapping, pgoff_t index, int flags)
{
const bool unmap_success = true;
@@ -1343,13 +1391,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
struct dev_pagemap *pgmap)
{
struct page *page = pfn_to_page(pfn);
- const bool unmap_success = true;
- unsigned long size = 0;
- struct to_kill *tk;
- LIST_HEAD(to_kill);
int rc = -EBUSY;
- loff_t start;
- dax_entry_t cookie;
if (flags & MF_COUNT_INCREASED)
/*
@@ -1357,20 +1399,9 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
*/
put_page(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 = 0;
- goto unlock;
+ goto out;
}
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
@@ -1378,7 +1409,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
* TODO: Handle HMM pages which may need coordination
* with device-side memory.
*/
- goto unlock;
+ goto out;
}
/*
@@ -1388,32 +1419,21 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
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)
+ * Call driver's implementation to handle the memory failure,
+ * otherwise roll back to generic handler.
*/
- flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
- collect_procs_file(page, page->mapping, page->index, &to_kill,
- flags & MF_ACTION_REQUIRED);
-
- list_for_each_entry(tk, &to_kill, nd)
- if (tk->size_shift)
- size = max(size, 1UL << tk->size_shift);
- if (size) {
+ if (pgmap->ops->memory_failure) {
+ rc = pgmap->ops->memory_failure(pgmap, pfn, flags);
/*
- * 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()
+ * Roll back to generic handler too if operation is not
+ * supported inside the driver/device/filesystem.
*/
- start = (page->index << PAGE_SHIFT) & ~(size - 1);
- unmap_mapping_range(page->mapping, start, start + size, 0);
+ if (rc != EOPNOTSUPP)
+ goto out;
}
- kill_procs(&to_kill, flags & MF_MUST_KILL, !unmap_success, pfn, flags);
- rc = 0;
-unlock:
- dax_unlock_page(page, cookie);
+
+ rc = mf_generic_kill_procs(pfn, flags);
+
out:
/* drop pgmap ref acquired in caller */
put_dev_pagemap(pgmap);
--
2.30.0
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org
next prev parent reply other threads:[~2021-02-08 10:55 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-08 10:55 [PATCH v3 00/11] fsdax: introduce fs query to support reflink Shiyang Ruan
2021-02-08 10:55 ` [PATCH v3 01/11] pagemap: Introduce ->memory_failure() Shiyang Ruan
2021-02-10 13:20 ` Christoph Hellwig
2021-03-06 20:36 ` Dan Williams
2021-03-08 3:38 ` ruansy.fnst
2021-03-08 5:23 ` Dan Williams
2021-03-08 11:34 ` ruansy.fnst
2021-03-08 18:01 ` Dan Williams
2021-03-12 10:18 ` ruansy.fnst
2021-03-19 2:17 ` ruansy.fnst
2021-03-24 2:19 ` Dan Williams
2021-03-24 7:47 ` Christoph Hellwig
2021-03-24 16:37 ` Dan Williams
2021-03-24 17:39 ` Christoph Hellwig
2021-03-24 18:00 ` Dan Williams
2021-02-08 10:55 ` [PATCH v3 02/11] blk: Introduce ->corrupted_range() for block device Shiyang Ruan
2021-02-10 13:21 ` Christoph Hellwig
2021-03-04 22:42 ` Darrick J. Wong
2021-03-05 6:10 ` Christoph Hellwig
2021-02-08 10:55 ` [PATCH v3 03/11] fs: Introduce ->corrupted_range() for superblock Shiyang Ruan
2021-02-08 10:55 ` [PATCH v3 04/11] block_dev: Introduce bd_corrupted_range() for block device Shiyang Ruan
2021-02-08 10:55 ` [PATCH v3 05/11] mm, fsdax: Refactor memory-failure handler for dax mapping Shiyang Ruan
2021-02-10 13:33 ` Christoph Hellwig
2021-02-17 2:56 ` Ruan Shiyang
2021-02-18 8:32 ` Christoph Hellwig
2021-02-18 8:59 ` Ruan Shiyang
2021-03-16 3:21 ` zhong jiang
2021-03-17 3:46 ` ruansy.fnst
2021-02-08 10:55 ` Shiyang Ruan [this message]
2021-02-10 13:41 ` [PATCH v3 06/11] mm, pmem: Implement ->memory_failure() in pmem driver Christoph Hellwig
2021-02-08 10:55 ` [PATCH v3 07/11] pmem: Implement ->corrupted_range() for " Shiyang Ruan
2021-02-08 10:55 ` [PATCH v3 08/11] dm: Introduce ->rmap() to find bdev offset Shiyang Ruan
2021-02-08 10:55 ` [PATCH v3 09/11] md: Implement ->corrupted_range() Shiyang Ruan
2021-02-08 10:55 ` [PATCH v3 10/11] xfs: Implement ->corrupted_range() for XFS Shiyang Ruan
2021-02-10 13:44 ` Christoph Hellwig
2021-02-08 10:55 ` [PATCH v3 11/11] fs/dax: Remove useless functions Shiyang Ruan
2021-02-10 13:09 ` 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=20210208105530.3072869-7-ruansy.fnst@cn.fujitsu.com \
--to=ruansy.fnst@cn.fujitsu.com \
--cc=agk@redhat.com \
--cc=darrick.wong@oracle.com \
--cc=david@fromorbit.com \
--cc=dm-devel@redhat.com \
--cc=hch@lst.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-xfs@vger.kernel.org \
--cc=qi.fuli@fujitsu.com \
--cc=rgoldwyn@suse.de \
--cc=snitzer@redhat.com \
--cc=y-goto@fujitsu.com \
/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).