From: John Groves <John@Groves.net>
To: John Groves <John@Groves.net>, Miklos Szeredi <miklos@szeredi.hu>,
Dan Williams <dan.j.williams@intel.com>,
Bernd Schubert <bschubert@ddn.com>,
Alison Schofield <alison.schofield@intel.com>
Cc: John Groves <jgroves@micron.com>,
Jonathan Corbet <corbet@lwn.net>,
Vishal Verma <vishal.l.verma@intel.com>,
Dave Jiang <dave.jiang@intel.com>,
Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>,
Alexander Viro <viro@zeniv.linux.org.uk>,
David Hildenbrand <david@kernel.org>,
Christian Brauner <brauner@kernel.org>,
"Darrick J . Wong" <djwong@kernel.org>,
Randy Dunlap <rdunlap@infradead.org>,
Jeff Layton <jlayton@kernel.org>,
Amir Goldstein <amir73il@gmail.com>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Stefan Hajnoczi <shajnocz@redhat.com>,
Joanne Koong <joannelkoong@gmail.com>,
Josef Bacik <josef@toxicpanda.com>,
Bagas Sanjaya <bagasdotme@gmail.com>,
James Morse <james.morse@arm.com>, Fuad Tabba <tabba@google.com>,
Sean Christopherson <seanjc@google.com>,
Shivank Garg <shivankg@amd.com>,
Ackerley Tng <ackerleytng@google.com>,
Gregory Price <gourry@gourry.net>,
Aravind Ramesh <arramesh@micron.com>,
Ajay Joshi <ajayjoshi@micron.com>,
venkataravis@micron.com, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, nvdimm@lists.linux.dev,
linux-cxl@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH V4 16/19] famfs_fuse: Add holder_operations for dax notify_failure()
Date: Wed, 14 Jan 2026 15:32:03 -0600 [thread overview]
Message-ID: <20260114213209.29453-17-john@groves.net> (raw)
In-Reply-To: <20260114213209.29453-1-john@groves.net>
Memory errors are at least somewhat more likely on disaggregated memory
than on-board memory. This commit registers to be notified by fsdev_dax
in the event that a memory failure is detected.
When a file access resolves to a daxdev with memory errors, it will fail
with an appropriate error.
If a daxdev failed fs_dax_get(), we set dd->dax_err. If a daxdev called
our notify_failure(), set dd->error. When any of the above happens, set
(file)->error and stop allowing access.
In general, the recovery from memory errors is to unmount the file
system and re-initialize the memory, but there may be usable degraded
modes of operation - particularly in the future when famfs supports
file systems backed by more than one daxdev. In those cases,
accessing data that is on a working daxdev can still work.
For now, return errors for any file that has encountered a memory or dax
error.
Signed-off-by: John Groves <john@groves.net>
---
fs/fuse/famfs.c | 110 +++++++++++++++++++++++++++++++++++++++---
fs/fuse/famfs_kfmap.h | 3 +-
2 files changed, 105 insertions(+), 8 deletions(-)
diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
index 2de70aef1df8..ee3526175b6b 100644
--- a/fs/fuse/famfs.c
+++ b/fs/fuse/famfs.c
@@ -21,6 +21,26 @@
#include "famfs_kfmap.h"
#include "fuse_i.h"
+static void famfs_set_daxdev_err(
+ struct fuse_conn *fc, struct dax_device *dax_devp);
+
+static int
+famfs_dax_notify_failure(struct dax_device *dax_devp, u64 offset,
+ u64 len, int mf_flags)
+{
+ struct fuse_conn *fc = dax_holder(dax_devp);
+
+ famfs_set_daxdev_err(fc, dax_devp);
+
+ return 0;
+}
+
+static const struct dax_holder_operations famfs_fuse_dax_holder_ops = {
+ .notify_failure = famfs_dax_notify_failure,
+};
+
+/*****************************************************************************/
+
/*
* famfs_teardown()
*
@@ -47,9 +67,12 @@ famfs_teardown(struct fuse_conn *fc)
if (!dd->valid)
continue;
- /* Release reference from dax_dev_get() */
- if (dd->devp)
+ /* Only call fs_put_dax if fs_dax_get succeeded */
+ if (dd->devp) {
+ if (!dd->dax_err)
+ fs_put_dax(dd->devp, fc);
put_dax(dd->devp);
+ }
kfree(dd->name);
}
@@ -170,6 +193,17 @@ famfs_fuse_get_daxdev(struct fuse_mount *fm, const u64 index)
if (!daxdev->name)
return -ENOMEM;
+ rc = fs_dax_get(daxdev->devp, fc, &famfs_fuse_dax_holder_ops);
+ if (rc) {
+ /* If fs_dax_get() fails, we don't attempt recovery;
+ * We mark the daxdev valid with dax_err
+ */
+ daxdev->dax_err = 1;
+ pr_err("%s: fs_dax_get(%lld) failed\n",
+ __func__, (u64)daxdev->devno);
+ return -EBUSY;
+ }
+
wmb(); /* All other fields must be visible before valid */
daxdev->valid = 1;
}
@@ -245,6 +279,36 @@ famfs_update_daxdev_table(
return 0;
}
+static void
+famfs_set_daxdev_err(
+ struct fuse_conn *fc,
+ struct dax_device *dax_devp)
+{
+ int i;
+
+ /* Gotta search the list by dax_devp;
+ * read lock because we're not adding or removing daxdev entries
+ */
+ scoped_guard(rwsem_write, &fc->famfs_devlist_sem) {
+ for (i = 0; i < fc->dax_devlist->nslots; i++) {
+ if (fc->dax_devlist->devlist[i].valid) {
+ struct famfs_daxdev *dd;
+
+ dd = &fc->dax_devlist->devlist[i];
+ if (dd->devp != dax_devp)
+ continue;
+
+ dd->error = true;
+
+ pr_err("%s: memory error on daxdev %s (%d)\n",
+ __func__, dd->name, i);
+ return;
+ }
+ }
+ }
+ pr_err("%s: memory err on unrecognized daxdev\n", __func__);
+}
+
/***************************************************************************/
void __famfs_meta_free(void *famfs_meta)
@@ -583,6 +647,26 @@ famfs_file_init_dax(
static int famfs_file_bad(struct inode *inode);
+static int famfs_dax_err(struct famfs_daxdev *dd)
+{
+ if (!dd->valid) {
+ pr_err("%s: daxdev=%s invalid\n",
+ __func__, dd->name);
+ return -EIO;
+ }
+ if (dd->dax_err) {
+ pr_err("%s: daxdev=%s dax_err\n",
+ __func__, dd->name);
+ return -EIO;
+ }
+ if (dd->error) {
+ pr_err("%s: daxdev=%s memory error\n",
+ __func__, dd->name);
+ return -EHWPOISON;
+ }
+ return 0;
+}
+
static int
famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
loff_t file_offset, off_t len, unsigned int flags)
@@ -617,6 +701,7 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
/* Is the data is in this striped extent? */
if (local_offset < ext_size) {
+ struct famfs_daxdev *dd;
u64 chunk_num = local_offset / chunk_size;
u64 chunk_offset = local_offset % chunk_size;
u64 chunk_remainder = chunk_size - chunk_offset;
@@ -625,6 +710,7 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
u64 strip_offset = chunk_offset + (stripe_num * chunk_size);
u64 strip_dax_ofs = fei->ie_strips[strip_num].ext_offset;
u64 strip_devidx = fei->ie_strips[strip_num].dev_index;
+ int rc;
if (strip_devidx >= fc->dax_devlist->nslots) {
pr_err("%s: strip_devidx %llu >= nslots %d\n",
@@ -639,6 +725,15 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
goto err_out;
}
+ dd = &fc->dax_devlist->devlist[strip_devidx];
+
+ rc = famfs_dax_err(dd);
+ if (rc) {
+ /* Shut down access to this file */
+ meta->error = true;
+ return rc;
+ }
+
iomap->addr = strip_dax_ofs + strip_offset;
iomap->offset = file_offset;
iomap->length = min_t(loff_t, len, chunk_remainder);
@@ -736,6 +831,7 @@ famfs_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
if (local_offset < dax_ext_len) {
loff_t ext_len_remainder = dax_ext_len - local_offset;
struct famfs_daxdev *dd;
+ int rc;
if (daxdev_idx >= fc->dax_devlist->nslots) {
pr_err("%s: daxdev_idx %llu >= nslots %d\n",
@@ -746,11 +842,11 @@ famfs_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
dd = &fc->dax_devlist->devlist[daxdev_idx];
- if (!dd->valid || dd->error) {
- pr_err("%s: daxdev=%lld %s\n", __func__,
- daxdev_idx,
- dd->valid ? "error" : "invalid");
- goto err_out;
+ rc = famfs_dax_err(dd);
+ if (rc) {
+ /* Shut down access to this file */
+ meta->error = true;
+ return rc;
}
/*
diff --git a/fs/fuse/famfs_kfmap.h b/fs/fuse/famfs_kfmap.h
index eb9f70b5cb81..0fff841f5a9e 100644
--- a/fs/fuse/famfs_kfmap.h
+++ b/fs/fuse/famfs_kfmap.h
@@ -73,7 +73,8 @@ struct famfs_file_meta {
struct famfs_daxdev {
/* Include dev uuid? */
bool valid;
- bool error;
+ bool error; /* Dax has reported a memory error (probably poison) */
+ bool dax_err; /* fs_dax_get() failed */
dev_t devno;
struct dax_device *devp;
char *name;
--
2.52.0
next prev parent reply other threads:[~2026-01-14 21:41 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20260114153133.29420.compound@groves.net>
[not found] ` <20260114213209.29453-1-john@groves.net>
2026-01-14 21:31 ` [PATCH V4 01/19] dax: move dax_pgoff_to_phys from [drivers/dax/] device.c to bus.c John Groves
2026-01-14 21:31 ` [PATCH V4 02/19] dax: Factor out dax_folio_reset_order() helper John Groves
2026-01-14 21:31 ` [PATCH V4 03/19] dax: add fsdev.c driver for fs-dax on character dax John Groves
2026-01-14 21:31 ` [PATCH V4 04/19] dax: Save the kva from memremap John Groves
2026-01-14 21:31 ` [PATCH V4 05/19] dax: Add dax_operations for use by fs-dax on fsdev dax John Groves
2026-01-14 21:31 ` [PATCH V4 06/19] dax: Add dax_set_ops() for setting dax_operations at bind time John Groves
2026-01-14 21:31 ` [PATCH V4 07/19] dax: Add fs_dax_get() func to prepare dax for fs-dax usage John Groves
2026-01-14 21:31 ` [PATCH V4 08/19] dax: export dax_dev_get() John Groves
2026-01-14 21:31 ` [PATCH V4 09/19] famfs_fuse: magic.h: Add famfs magic numbers John Groves
2026-01-14 21:31 ` [PATCH V4 10/19] famfs_fuse: Update macro s/FUSE_IS_DAX/FUSE_IS_VIRTIO_DAX/ John Groves
2026-01-14 21:31 ` [PATCH V4 11/19] famfs_fuse: Basic fuse kernel ABI enablement for famfs John Groves
2026-01-14 21:31 ` [PATCH V4 12/19] famfs_fuse: Plumb the GET_FMAP message/response John Groves
2026-01-14 21:32 ` [PATCH V4 13/19] famfs_fuse: Create files with famfs fmaps John Groves
2026-01-14 21:32 ` [PATCH V4 15/19] famfs_fuse: Plumb dax iomap and fuse read/write/mmap John Groves
2026-01-14 21:32 ` John Groves [this message]
2026-01-14 21:32 ` [PATCH V4 17/19] famfs_fuse: Add DAX address_space_operations with noop_dirty_folio John Groves
2026-01-14 21:32 ` [PATCH V4 18/19] famfs_fuse: Add famfs fmap metadata documentation John Groves
2026-01-14 21:32 ` [PATCH V4 19/19] famfs_fuse: Add documentation John Groves
2026-01-14 21:43 ` [PATCH V4 0/3] John Groves
2026-01-14 21:43 ` [PATCH V4 1/3] fuse_kernel.h: bring up to baseline 6.19 John Groves
2026-01-14 21:43 ` [PATCH V4 2/3] fuse_kernel.h: add famfs DAX fmap protocol definitions John Groves
2026-01-14 21:43 ` [PATCH V4 3/3] fuse: add famfs DAX fmap support John Groves
2026-01-14 21:45 ` [PATCH V2 0/2] ndctl: Add daxctl support for the new "famfs" mode of devdax John Groves
2026-01-14 21:45 ` [PATCH V2 1/2] daxctl: Add support for famfs mode John Groves
2026-01-14 21:45 ` [PATCH V2 2/2] Add test/daxctl-famfs.sh to test famfs mode transitions: John Groves
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=20260114213209.29453-17-john@groves.net \
--to=john@groves.net \
--cc=Jonathan.Cameron@huawei.com \
--cc=ackerleytng@google.com \
--cc=ajayjoshi@micron.com \
--cc=alison.schofield@intel.com \
--cc=amir73il@gmail.com \
--cc=arramesh@micron.com \
--cc=bagasdotme@gmail.com \
--cc=brauner@kernel.org \
--cc=bschubert@ddn.com \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=david@kernel.org \
--cc=djwong@kernel.org \
--cc=gourry@gourry.net \
--cc=jack@suse.cz \
--cc=james.morse@arm.com \
--cc=jgroves@micron.com \
--cc=jlayton@kernel.org \
--cc=joannelkoong@gmail.com \
--cc=josef@toxicpanda.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=nvdimm@lists.linux.dev \
--cc=rdunlap@infradead.org \
--cc=seanjc@google.com \
--cc=shajnocz@redhat.com \
--cc=shivankg@amd.com \
--cc=tabba@google.com \
--cc=venkataravis@micron.com \
--cc=viro@zeniv.linux.org.uk \
--cc=vishal.l.verma@intel.com \
--cc=willy@infradead.org \
/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