From: Benjamin Coddington <ben.coddington@hammerspace.com>
To: Trond Myklebust <trondmy@kernel.org>, Anna Schumaker <anna@kernel.org>
Cc: linux-nfs@vger.kernel.org,
Jonathan Curley <jcurley@purestorage.com>,
Mike Snitzer <snitzer@kernel.org>,
Jeff Layton <jlayton@kernel.org>
Subject: [PATCH v2 09/23] NFSv4/flexfiles: Hold a device node reference for layoutstats encoding
Date: Fri, 21 Aug 2026 12:29:13 -0400 [thread overview]
Message-ID: <ff832a1b5cd1412c2be32f02b86cb60108ffc8cb.1787327939.git.bcodding@hammerspace.com> (raw)
In-Reply-To: <cover.1787327939.git.bcodding@hammerspace.com>
ff_layout_mirror_prepare_stats() records a stripe's device under i_lock,
but the layoutstats/layoutreturn XDR encode runs later and dereferences
the mirror's pinned device node (for the DS netaddr) with no reference
of its own. Once a CHANGE notification can re-point the pinned node,
that read becomes use-after-free.
Take a node reference at prepare time and carry it with the stripe in a
per-devinfo nfs4_ff_layoutstat_priv, released in
ff_layout_free_layoutstats(). The priv entries live alongside the
devinfo array: co-allocated for LAYOUTSTATS, an additional member of
nfs4_flexfile_layoutreturn_args for LAYOUTRETURN.
Assisted-by: Claude:claude-fable-5
Signed-off-by: Benjamin Coddington <bcodding@hammerspace.com>
---
fs/nfs/flexfilelayout/flexfilelayout.c | 53 +++++++++++++++++---------
fs/nfs/flexfilelayout/flexfilelayout.h | 11 ++++++
2 files changed, 47 insertions(+), 17 deletions(-)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 4a9a36af4223..947bb277c4ef 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -44,10 +44,11 @@ static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
static int
ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
struct nfs42_layoutstat_devinfo *devinfo,
+ struct nfs4_ff_layoutstat_priv *priv,
int dev_limit, enum nfs4_ff_op_type type);
static void ff_layout_encode_ff_layoutupdate(struct xdr_stream *xdr,
const struct nfs42_layoutstat_devinfo *devinfo,
- struct nfs4_ff_layout_ds_stripe *dss_info);
+ struct nfs4_ff_layoutstat_priv *priv);
static struct pnfs_layout_hdr *
ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
@@ -2706,7 +2707,7 @@ ff_layout_prepare_layoutreturn(struct nfs4_layoutreturn_args *args)
spin_lock(&args->inode->i_lock);
ff_args->num_dev = ff_layout_mirror_prepare_stats(
- &ff_layout->generic_hdr, &ff_args->devinfo[0],
+ &ff_layout->generic_hdr, &ff_args->devinfo[0], &ff_args->priv[0],
ARRAY_SIZE(ff_args->devinfo), NFS4_FF_OP_LAYOUTRETURN);
spin_unlock(&args->inode->i_lock);
@@ -2881,10 +2882,11 @@ ff_layout_encode_io_latency(struct xdr_stream *xdr,
static void
ff_layout_encode_ff_layoutupdate(struct xdr_stream *xdr,
const struct nfs42_layoutstat_devinfo *devinfo,
- struct nfs4_ff_layout_ds_stripe *dss_info)
+ struct nfs4_ff_layoutstat_priv *priv)
{
+ struct nfs4_ff_layout_ds_stripe *dss_info = priv->dss_info;
struct nfs4_pnfs_ds_addr *da;
- struct nfs4_pnfs_ds *ds = dss_info->mirror_ds->ds;
+ struct nfs4_pnfs_ds *ds = priv->mirror_ds->ds;
struct nfs_fh *fh = &dss_info->fh_versions[0];
__be32 *p;
@@ -2931,10 +2933,10 @@ ff_layout_encode_layoutstats(struct xdr_stream *xdr, const void *args,
static void
ff_layout_free_layoutstats(struct nfs4_xdr_opaque_data *opaque)
{
- struct nfs4_ff_layout_ds_stripe *dss_info = opaque->data;
- struct nfs4_ff_layout_mirror *mirror = dss_info->mirror;
+ struct nfs4_ff_layoutstat_priv *priv = opaque->data;
- ff_layout_put_mirror(mirror);
+ nfs4_ff_layout_put_deviceid(priv->mirror_ds);
+ ff_layout_put_mirror(priv->dss_info->mirror);
}
static const struct nfs4_xdr_opaque_ops layoutstat_ops = {
@@ -2945,12 +2947,13 @@ static const struct nfs4_xdr_opaque_ops layoutstat_ops = {
static int
ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
struct nfs42_layoutstat_devinfo *devinfo,
+ struct nfs4_ff_layoutstat_priv *priv,
int dev_limit, enum nfs4_ff_op_type type)
{
struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(lo);
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_ff_layout_ds_stripe *dss_info;
- struct nfs4_deviceid_node *dev;
+ struct nfs4_ff_layout_ds *mirror_ds;
int i = 0, dss_id;
list_for_each_entry(mirror, &ff_layout->mirrors, mirrors) {
@@ -2958,7 +2961,8 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
dss_info = &mirror->dss[dss_id];
if (i >= dev_limit)
break;
- if (IS_ERR_OR_NULL(dss_info->mirror_ds))
+ mirror_ds = dss_info->mirror_ds;
+ if (IS_ERR_OR_NULL(mirror_ds))
continue;
if (!test_and_clear_bit(NFS4_FF_MIRROR_STAT_AVAIL,
&mirror->flags) &&
@@ -2967,9 +2971,14 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
/* mirror refcount put in cleanup_layoutstats */
if (!refcount_inc_not_zero(&mirror->ref))
continue;
- dev = &dss_info->mirror_ds->id_node;
+ /*
+ * The mirror's pin holds the node while we're under
+ * i_lock; take a reference for the encode, put in
+ * ff_layout_free_layoutstats().
+ */
+ atomic_inc(&mirror_ds->id_node.ref);
memcpy(&devinfo->dev_id,
- &dev->deviceid,
+ &mirror_ds->id_node.deviceid,
NFS4_DEVICEID4_SIZE);
devinfo->offset = 0;
devinfo->length = NFS4_MAX_UINT64;
@@ -2985,9 +2994,12 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
spin_unlock(&mirror->lock);
devinfo->layout_type = LAYOUT_FLEX_FILES;
devinfo->ld_private.ops = &layoutstat_ops;
- devinfo->ld_private.data = &mirror->dss[dss_id];
+ priv->dss_info = dss_info;
+ priv->mirror_ds = mirror_ds;
+ devinfo->ld_private.data = priv;
devinfo++;
+ priv++;
i++;
}
}
@@ -2998,21 +3010,28 @@ static int ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
{
struct pnfs_layout_hdr *lo;
struct nfs4_flexfile_layout *ff_layout;
+ struct nfs4_ff_layoutstat_priv *priv;
const int dev_count = PNFS_LAYOUTSTATS_MAXDEV;
- /* For now, send at most PNFS_LAYOUTSTATS_MAXDEV statistics */
- args->devinfo = kmalloc_objs(*args->devinfo, dev_count,
- nfs_io_gfp_mask());
+ /*
+ * For now, send at most PNFS_LAYOUTSTATS_MAXDEV statistics.
+ * The per-devinfo private entries are co-allocated after the
+ * devinfo array and freed along with it.
+ */
+ args->devinfo = kmalloc(dev_count * (sizeof(*args->devinfo) +
+ sizeof(*priv)),
+ nfs_io_gfp_mask());
if (!args->devinfo)
return -ENOMEM;
+ priv = (struct nfs4_ff_layoutstat_priv *)&args->devinfo[dev_count];
spin_lock(&args->inode->i_lock);
lo = NFS_I(args->inode)->layout;
if (lo && pnfs_layout_is_valid(lo)) {
ff_layout = FF_LAYOUT_FROM_HDR(lo);
args->num_dev = ff_layout_mirror_prepare_stats(
- &ff_layout->generic_hdr, &args->devinfo[0], dev_count,
- NFS4_FF_OP_LAYOUTSTATS);
+ &ff_layout->generic_hdr, &args->devinfo[0], priv,
+ dev_count, NFS4_FF_OP_LAYOUTSTATS);
} else
args->num_dev = 0;
spin_unlock(&args->inode->i_lock);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index ceed1a9dd697..d6ec80cf8a6e 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -124,9 +124,20 @@ struct nfs4_flexfile_layout {
unsigned long flags;
};
+/*
+ * Per-devinfo private data for a layoutstats/layoutreturn encode: the
+ * stripe the stats describe plus a reference on its device node so the
+ * node (and its DS addresses) stay valid until the XDR encode runs.
+ */
+struct nfs4_ff_layoutstat_priv {
+ struct nfs4_ff_layout_ds_stripe *dss_info;
+ struct nfs4_ff_layout_ds *mirror_ds;
+};
+
struct nfs4_flexfile_layoutreturn_args {
struct list_head errors;
struct nfs42_layoutstat_devinfo devinfo[FF_LAYOUTSTATS_MAXDEV];
+ struct nfs4_ff_layoutstat_priv priv[FF_LAYOUTSTATS_MAXDEV];
unsigned int num_errors;
unsigned int num_dev;
struct page *pages[1];
--
2.53.0
next prev parent reply other threads:[~2026-08-21 16:29 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-21 16:29 [PATCH v2 00/23] NFS: flexfiles device notifications and caching for wide striped layouts Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 01/23] NFSv4/flexfiles: reject a stripe_unit that does not fit 32 bits Benjamin Coddington
2026-08-27 19:25 ` Anna Schumaker
2026-08-28 11:24 ` Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 02/23] NFSv4/pnfs: bound the CB_NOTIFY_DEVICEID array count before allocating Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 03/23] pNFS: Fix CB_NOTIFY_DEVICEID CHANGE to consume ndc_immediate Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 04/23] NFSv4/flexfiles: Use the full 64-bit offset for read DS selection Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 05/23] NFSv4/flexfiles: Bound page coalescing on the absolute stripe offset Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 06/23] NFSv4/filelayout: Anchor page coalescing on pattern_offset Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 07/23] NFSv4/flexfiles: Reference the device node across DS setup Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 08/23] NFSv4/flexfiles: Carry the device node reference across each I/O Benjamin Coddington
2026-08-21 16:29 ` Benjamin Coddington [this message]
2026-08-21 16:29 ` [PATCH v2 10/23] NFSv4/flexfiles: Make the pinned device node pointer RCU-managed Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 11/23] pNFS: Add a reresolve_deviceid layout driver hook Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 12/23] NFSv4/flexfiles: Implement in-place device re-resolve on CHANGE Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 13/23] NFSv4: Dispatch CB_NOTIFY_DEVICEID CHANGE to an in-place refresh Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 14/23] NFSv4/flexfiles: Honor ndc_immediate on CB_NOTIFY_DEVICEID CHANGE Benjamin Coddington
2026-08-28 17:41 ` Anna Schumaker
2026-08-28 20:50 ` Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 15/23] pNFS: Discard a GETDEVICEINFO reply that raced a CHANGE notification Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 16/23] pNFS: Add deviceid reference query and collection walkers Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 17/23] NFSv4/pnfs: Recover revoked layouts on a deleted deviceID Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 18/23] NFSv4/pnfs: Confirm a deviceID delete via GETDEVICEINFO Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 19/23] NFSv4/pnfs: Dispatch CB_NOTIFY_DEVICEID DELETE to race recovery Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 20/23] NFSv4/pnfs: Grow the deviceid cache hash table Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 21/23] NFSv4/pnfs: Re-home the data-server cache onto hash buckets Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 22/23] NFSv4/pnfs: Key the data-server cache by its address set Benjamin Coddington
2026-08-21 16:29 ` [PATCH v2 23/23] NFSv4/flexfiles: Add a dataserver_nconnect cap Benjamin Coddington
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=ff832a1b5cd1412c2be32f02b86cb60108ffc8cb.1787327939.git.bcodding@hammerspace.com \
--to=ben.coddington@hammerspace.com \
--cc=anna@kernel.org \
--cc=jcurley@purestorage.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=snitzer@kernel.org \
--cc=trondmy@kernel.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